Merge branch 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm

Pull ARM updates from Russell King:
 "These are late by a week; they should have been merged during the
  merge window, but unfortunately, the ARM kernel build/boot farms were
  indicating random failures, and it wasn't clear whether the cause was
  something in these changes or something during the merge window.

  This is a set of merge window fixes with some documentation additions"

* 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm:
  ARM: avoid unwanted GCC memset()/memcpy() optimisations for IO variants
  ARM: pgtable: document mapping types
  ARM: io: convert ioremap*() to functions
  ARM: io: fix ioremap_wt() implementation
  ARM: io: document ARM specific behaviour of ioremap*() implementations
  ARM: fix lockdep unannotated irqs-off warning
  ARM: 8397/1: fix vdsomunge not to depend on glibc specific error.h
  ARM: add helpful message when truncating physical memory
  ARM: add help text for HIGHPTE configuration entry
  ARM: fix DEBUG_SET_MODULE_RONX build dependencies
  ARM: 8396/1: use phys_addr_t in pfn_to_kaddr()
  ARM: 8394/1: update memblock limit after mapping lowmem
  ARM: 8393/1: smp: Fix suspicious RCU usage with ipi tracepoints
diff --git a/CREDITS b/CREDITS
index 4df764e..1d61664 100644
--- a/CREDITS
+++ b/CREDITS
@@ -2740,6 +2740,10 @@
 S: Valladolid 47009
 S: Spain
 
+N: Jens Osterkamp
+E: jens@de.ibm.com
+D: Maintainer of Spidernet network driver for Cell
+
 N: Gadi Oxman
 E: gadio@netvision.net.il
 D: Original author and maintainer of IDE/ATAPI floppy/tape drivers
diff --git a/Documentation/ABI/testing/sysfs-driver-toshiba_haps b/Documentation/ABI/testing/sysfs-driver-toshiba_haps
new file mode 100644
index 0000000..a662370
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-driver-toshiba_haps
@@ -0,0 +1,20 @@
+What:		/sys/devices/LNXSYSTM:00/LNXSYBUS:00/TOS620A:00/protection_level
+Date:		August 16, 2014
+KernelVersion:	3.17
+Contact:	Azael Avalos <coproscefalo@gmail.com>
+Description:	This file controls the built-in accelerometer protection level,
+		valid values are:
+			* 0 -> Disabled
+			* 1 -> Low
+			* 2 -> Medium
+			* 3 -> High
+		The default potection value is set to 2 (Medium).
+Users:		KToshiba
+
+What:		/sys/devices/LNXSYSTM:00/LNXSYBUS:00/TOS620A:00/reset_protection
+Date:		August 16, 2014
+KernelVersion:	3.17
+Contact:	Azael Avalos <coproscefalo@gmail.com>
+Description:	This file turns off the built-in accelerometer for a few
+		seconds and then restore normal operation. Accepting 1 as the
+		only parameter.
diff --git a/Documentation/clk.txt b/Documentation/clk.txt
index 0e4f90a..f463bdc 100644
--- a/Documentation/clk.txt
+++ b/Documentation/clk.txt
@@ -230,30 +230,7 @@
 
 See the basic clock types in drivers/clk/clk-*.c for examples.
 
-	Part 5 - static initialization of clock data
-
-For platforms with many clocks (often numbering into the hundreds) it
-may be desirable to statically initialize some clock data.  This
-presents a problem since the definition of struct clk should be hidden
-from everyone except for the clock core in drivers/clk/clk.c.
-
-To get around this problem struct clk's definition is exposed in
-include/linux/clk-private.h along with some macros for more easily
-initializing instances of the basic clock types.  These clocks must
-still be initialized with the common clock framework via a call to
-__clk_init.
-
-clk-private.h must NEVER be included by code which implements struct
-clk_ops callbacks, nor must it be included by any logic which pokes
-around inside of struct clk at run-time.  To do so is a layering
-violation.
-
-To better enforce this policy, always follow this simple rule: any
-statically initialized clock data MUST be defined in a separate file
-from the logic that implements its ops.  Basically separate the logic
-from the data and all is well.
-
-	Part 6 - Disabling clock gating of unused clocks
+	Part 5 - Disabling clock gating of unused clocks
 
 Sometimes during development it can be useful to be able to bypass the
 default disabling of unused clocks. For example, if drivers aren't enabling
@@ -264,7 +241,7 @@
 To bypass this disabling, include "clk_ignore_unused" in the bootargs to the
 kernel.
 
-	Part 7 - Locking
+	Part 6 - Locking
 
 The common clock framework uses two global locks, the prepare lock and the
 enable lock.
diff --git a/Documentation/devicetree/bindings/arc/archs-idu-intc.txt b/Documentation/devicetree/bindings/arc/archs-idu-intc.txt
new file mode 100644
index 0000000..0dcb7c7
--- /dev/null
+++ b/Documentation/devicetree/bindings/arc/archs-idu-intc.txt
@@ -0,0 +1,46 @@
+* ARC-HS Interrupt Distribution Unit
+
+  This optional 2nd level interrupt controller can be used in SMP configurations for
+  dynamic IRQ routing, load balancing of common/external IRQs towards core intc.
+
+Properties:
+
+- compatible: "snps,archs-idu-intc"
+- interrupt-controller: This is an interrupt controller.
+- interrupt-parent: <reference to parent core intc>
+- #interrupt-cells: Must be <2>.
+- interrupts: <...> specifies the upstream core irqs
+
+  First cell specifies the "common" IRQ from peripheral to IDU
+  Second cell specifies the irq distribution mode to cores
+     0=Round Robin; 1=cpu0, 2=cpu1, 4=cpu2, 8=cpu3
+
+  intc accessed via the special ARC AUX register interface, hence "reg" property
+  is not specified.
+
+Example:
+	core_intc: core-interrupt-controller {
+		compatible = "snps,archs-intc";
+		interrupt-controller;
+		#interrupt-cells = <1>;
+	};
+
+	idu_intc: idu-interrupt-controller {
+		compatible = "snps,archs-idu-intc";
+		interrupt-controller;
+		interrupt-parent = <&core_intc>;
+
+		/*
+		 * <hwirq  distribution>
+		 * distribution: 0=RR; 1=cpu0, 2=cpu1, 4=cpu2, 8=cpu3
+		 */
+		#interrupt-cells = <2>;
+
+		/* upstream core irqs: downstream these are "COMMON" irq 0,1..  */
+		interrupts = <24 25 26 27 28 29 30 31>;
+	};
+
+	some_device: serial@c0fc1000 {
+		interrupt-parent = <&idu_intc>;
+		interrupts = <0 0>;	/* upstream idu IRQ #24, Round Robin */
+	};
diff --git a/Documentation/devicetree/bindings/arc/archs-intc.txt b/Documentation/devicetree/bindings/arc/archs-intc.txt
new file mode 100644
index 0000000..69f326d
--- /dev/null
+++ b/Documentation/devicetree/bindings/arc/archs-intc.txt
@@ -0,0 +1,22 @@
+* ARC-HS incore Interrupt Controller (Provided by cores implementing ARCv2 ISA)
+
+Properties:
+
+- compatible: "snps,archs-intc"
+- interrupt-controller: This is an interrupt controller.
+- #interrupt-cells: Must be <1>.
+
+  Single Cell "interrupts" property of a device specifies the IRQ number
+  between 16 to 256
+
+  intc accessed via the special ARC AUX register interface, hence "reg" property
+  is not specified.
+
+Example:
+
+	intc: interrupt-controller {
+		compatible = "snps,archs-intc";
+		interrupt-controller;
+		#interrupt-cells = <1>;
+		interrupts = <16 17 18 19 20 21 22 23 24 25>;
+	};
diff --git a/Documentation/devicetree/bindings/arc/axs101.txt b/Documentation/devicetree/bindings/arc/axs101.txt
new file mode 100644
index 0000000..48290d5
--- /dev/null
+++ b/Documentation/devicetree/bindings/arc/axs101.txt
@@ -0,0 +1,7 @@
+Synopsys DesignWare ARC Software Development Platforms Device Tree Bindings
+---------------------------------------------------------------------------
+
+SDP Main Board with an AXC001 CPU Card hoisting ARC700 core in silicon
+
+Required root node properties:
+    - compatible = "snps,axs101", "snps,arc-sdp";
diff --git a/Documentation/devicetree/bindings/arc/axs103.txt b/Documentation/devicetree/bindings/arc/axs103.txt
new file mode 100644
index 0000000..6eea862
--- /dev/null
+++ b/Documentation/devicetree/bindings/arc/axs103.txt
@@ -0,0 +1,8 @@
+Synopsys DesignWare ARC Software Development Platforms Device Tree Bindings
+---------------------------------------------------------------------------
+
+SDP Main Board with an AXC003 FPGA Card which can contain various flavours of
+HS38x cores.
+
+Required root node properties:
+    - compatible = "snps,axs103", "snps,arc-sdp";
diff --git a/Documentation/devicetree/bindings/arm/mediatek/mediatek,apmixedsys.txt b/Documentation/devicetree/bindings/arm/mediatek/mediatek,apmixedsys.txt
new file mode 100644
index 0000000..936166f
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/mediatek/mediatek,apmixedsys.txt
@@ -0,0 +1,23 @@
+Mediatek apmixedsys controller
+==============================
+
+The Mediatek apmixedsys controller provides the PLLs to the system.
+
+Required Properties:
+
+- compatible: Should be:
+	- "mediatek,mt8135-apmixedsys"
+	- "mediatek,mt8173-apmixedsys"
+- #clock-cells: Must be 1
+
+The apmixedsys controller uses the common clk binding from
+Documentation/devicetree/bindings/clock/clock-bindings.txt
+The available clocks are defined in dt-bindings/clock/mt*-clk.h.
+
+Example:
+
+apmixedsys: clock-controller@10209000 {
+	compatible = "mediatek,mt8173-apmixedsys";
+	reg = <0 0x10209000 0 0x1000>;
+	#clock-cells = <1>;
+};
diff --git a/Documentation/devicetree/bindings/arm/mediatek/mediatek,infracfg.txt b/Documentation/devicetree/bindings/arm/mediatek/mediatek,infracfg.txt
new file mode 100644
index 0000000..f6cd3e4
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/mediatek/mediatek,infracfg.txt
@@ -0,0 +1,30 @@
+Mediatek infracfg controller
+============================
+
+The Mediatek infracfg controller provides various clocks and reset
+outputs to the system.
+
+Required Properties:
+
+- compatible: Should be:
+	- "mediatek,mt8135-infracfg", "syscon"
+	- "mediatek,mt8173-infracfg", "syscon"
+- #clock-cells: Must be 1
+- #reset-cells: Must be 1
+
+The infracfg controller uses the common clk binding from
+Documentation/devicetree/bindings/clock/clock-bindings.txt
+The available clocks are defined in dt-bindings/clock/mt*-clk.h.
+Also it uses the common reset controller binding from
+Documentation/devicetree/bindings/reset/reset.txt.
+The available reset outputs are defined in
+dt-bindings/reset-controller/mt*-resets.h
+
+Example:
+
+infracfg: power-controller@10001000 {
+	compatible = "mediatek,mt8173-infracfg", "syscon";
+	reg = <0 0x10001000 0 0x1000>;
+	#clock-cells = <1>;
+	#reset-cells = <1>;
+};
diff --git a/Documentation/devicetree/bindings/arm/mediatek/mediatek,pericfg.txt b/Documentation/devicetree/bindings/arm/mediatek/mediatek,pericfg.txt
new file mode 100644
index 0000000..f25b854
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/mediatek/mediatek,pericfg.txt
@@ -0,0 +1,30 @@
+Mediatek pericfg controller
+===========================
+
+The Mediatek pericfg controller provides various clocks and reset
+outputs to the system.
+
+Required Properties:
+
+- compatible: Should be:
+	- "mediatek,mt8135-pericfg", "syscon"
+	- "mediatek,mt8173-pericfg", "syscon"
+- #clock-cells: Must be 1
+- #reset-cells: Must be 1
+
+The pericfg controller uses the common clk binding from
+Documentation/devicetree/bindings/clock/clock-bindings.txt
+The available clocks are defined in dt-bindings/clock/mt*-clk.h.
+Also it uses the common reset controller binding from
+Documentation/devicetree/bindings/reset/reset.txt.
+The available reset outputs are defined in
+dt-bindings/reset-controller/mt*-resets.h
+
+Example:
+
+pericfg: power-controller@10003000 {
+	compatible = "mediatek,mt8173-pericfg", "syscon";
+	reg = <0 0x10003000 0 0x1000>;
+	#clock-cells = <1>;
+	#reset-cells = <1>;
+};
diff --git a/Documentation/devicetree/bindings/arm/mediatek/mediatek,topckgen.txt b/Documentation/devicetree/bindings/arm/mediatek/mediatek,topckgen.txt
new file mode 100644
index 0000000..f9e9179
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/mediatek/mediatek,topckgen.txt
@@ -0,0 +1,23 @@
+Mediatek topckgen controller
+============================
+
+The Mediatek topckgen controller provides various clocks to the system.
+
+Required Properties:
+
+- compatible: Should be:
+	- "mediatek,mt8135-topckgen"
+	- "mediatek,mt8173-topckgen"
+- #clock-cells: Must be 1
+
+The topckgen controller uses the common clk binding from
+Documentation/devicetree/bindings/clock/clock-bindings.txt
+The available clocks are defined in dt-bindings/clock/mt*-clk.h.
+
+Example:
+
+topckgen: power-controller@10000000 {
+	compatible = "mediatek,mt8173-topckgen";
+	reg = <0 0x10000000 0 0x1000>;
+	#clock-cells = <1>;
+};
diff --git a/Documentation/devicetree/bindings/clock/amlogic,meson8b-clkc.txt b/Documentation/devicetree/bindings/clock/amlogic,meson8b-clkc.txt
new file mode 100644
index 0000000..2b7b3fa
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/amlogic,meson8b-clkc.txt
@@ -0,0 +1,40 @@
+* Amlogic Meson8b Clock and Reset Unit
+
+The Amlogic Meson8b clock controller generates and supplies clock to various
+controllers within the SoC.
+
+Required Properties:
+
+- compatible: should be "amlogic,meson8b-clkc"
+- reg: it must be composed by two tuples:
+	0) physical base address of the xtal register and length of memory
+	   mapped region.
+	1) physical base address of the clock controller and length of memory
+	   mapped region.
+
+- #clock-cells: should be 1.
+
+Each clock is assigned an identifier and client nodes can use this identifier
+to specify the clock which they consume. All available clocks are defined as
+preprocessor macros in the dt-bindings/clock/meson8b-clkc.h header and can be
+used in device tree sources.
+
+Example: Clock controller node:
+
+	clkc: clock-controller@c1104000 {
+		#clock-cells = <1>;
+		compatible = "amlogic,meson8b-clkc";
+		reg = <0xc1108000 0x4>, <0xc1104000 0x460>;
+	};
+
+
+Example: UART controller node that consumes the clock generated by the clock
+  controller:
+
+	uart_AO: serial@c81004c0 {
+		compatible = "amlogic,meson-uart";
+		reg = <0xc81004c0 0x14>;
+		interrupts = <0 90 1>;
+		clocks = <&clkc CLKID_CLK81>;
+		status = "disabled";
+	};
diff --git a/Documentation/devicetree/bindings/clock/bcm-cygnus-clock.txt b/Documentation/devicetree/bindings/clock/bcm-cygnus-clock.txt
deleted file mode 100644
index 00d26ed..0000000
--- a/Documentation/devicetree/bindings/clock/bcm-cygnus-clock.txt
+++ /dev/null
@@ -1,34 +0,0 @@
-Broadcom Cygnus Clocks
-
-This binding uses the common clock binding:
-Documentation/devicetree/bindings/clock/clock-bindings.txt
-
-Currently various "fixed" clocks are declared for peripheral drivers that use
-the common clock framework to reference their core clocks. Proper support of
-these clocks will be added later
-
-Device tree example:
-
-	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		osc: oscillator {
-			compatible = "fixed-clock";
-			#clock-cells = <1>;
-			clock-frequency = <25000000>;
-		};
-
-		apb_clk: apb_clk {
-			compatible = "fixed-clock";
-			#clock-cells = <0>;
-			clock-frequency = <1000000000>;
-		};
-
-		periph_clk: periph_clk {
-			compatible = "fixed-clock";
-			#clock-cells = <0>;
-			clock-frequency = <500000000>;
-		};
-	};
diff --git a/Documentation/devicetree/bindings/clock/brcm,iproc-clocks.txt b/Documentation/devicetree/bindings/clock/brcm,iproc-clocks.txt
new file mode 100644
index 0000000..da8d9bb
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/brcm,iproc-clocks.txt
@@ -0,0 +1,132 @@
+Broadcom iProc Family Clocks
+
+This binding uses the common clock binding:
+    Documentation/devicetree/bindings/clock/clock-bindings.txt
+
+The iProc clock controller manages clocks that are common to the iProc family.
+An SoC from the iProc family may have several PPLs, e.g., ARMPLL, GENPLL,
+LCPLL0, MIPIPLL, and etc., all derived from an onboard crystal. Each PLL
+comprises of several leaf clocks
+
+Required properties for a PLL and its leaf clocks:
+
+- compatible:
+    Should have a value of the form "brcm,<soc>-<pll>". For example, GENPLL on
+Cygnus has a compatible string of "brcm,cygnus-genpll"
+
+- #clock-cells:
+    Have a value of <1> since there are more than 1 leaf clock of a given PLL
+
+- reg:
+    Define the base and range of the I/O address space that contain the iProc
+clock control registers required for the PLL
+
+- clocks:
+    The input parent clock phandle for the PLL. For most iProc PLLs, this is an
+onboard crystal with a fixed rate
+
+- clock-output-names:
+    An ordered list of strings defining the names of the clocks
+
+Example:
+
+	osc: oscillator {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <25000000>;
+	};
+
+	genpll: genpll {
+		#clock-cells = <1>;
+		compatible = "brcm,cygnus-genpll";
+		reg = <0x0301d000 0x2c>, <0x0301c020 0x4>;
+		clocks = <&osc>;
+		clock-output-names = "genpll", "axi21", "250mhz", "ihost_sys",
+				     "enet_sw", "audio_125", "can";
+	};
+
+Required properties for ASIU clocks:
+
+ASIU clocks are a special case. These clocks are derived directly from the
+reference clock of the onboard crystal
+
+- compatible:
+    Should have a value of the form "brcm,<soc>-asiu-clk". For example, ASIU
+clocks for Cygnus have a compatible string of "brcm,cygnus-asiu-clk"
+
+- #clock-cells:
+    Have a value of <1> since there are more than 1 ASIU clocks
+
+- reg:
+    Define the base and range of the I/O address space that contain the iProc
+clock control registers required for ASIU clocks
+
+- clocks:
+    The input parent clock phandle for the ASIU clock, i.e., the onboard
+crystal
+
+- clock-output-names:
+    An ordered list of strings defining the names of the ASIU clocks
+
+Example:
+
+	osc: oscillator {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <25000000>;
+	};
+
+	asiu_clks: asiu_clks {
+		#clock-cells = <1>;
+		compatible = "brcm,cygnus-asiu-clk";
+		reg = <0x0301d048 0xc>, <0x180aa024 0x4>;
+		clocks = <&osc>;
+		clock-output-names = "keypad", "adc/touch", "pwm";
+	};
+
+Cygnus
+------
+PLL and leaf clock compatible strings for Cygnus are:
+    "brcm,cygnus-armpll"
+    "brcm,cygnus-genpll"
+    "brcm,cygnus-lcpll0"
+    "brcm,cygnus-mipipll"
+    "brcm,cygnus-asiu-clk"
+
+The following table defines the set of PLL/clock index and ID for Cygnus.
+These clock IDs are defined in:
+    "include/dt-bindings/clock/bcm-cygnus.h"
+
+    Clock      Source (Parent)  Index   ID
+    ---        -----            -----   ---------
+    crystal    N/A              N/A     N/A
+
+    armpll     crystal          N/A     N/A
+
+    keypad     crystal (ASIU)   0       BCM_CYGNUS_ASIU_KEYPAD_CLK
+    adc/tsc    crystal (ASIU)   1       BCM_CYGNUS_ASIU_ADC_CLK
+    pwm        crystal (ASIU)   2       BCM_CYGNUS_ASIU_PWM_CLK
+
+    genpll     crystal          0       BCM_CYGNUS_GENPLL
+    axi21      genpll           1       BCM_CYGNUS_GENPLL_AXI21_CLK
+    250mhz     genpll           2       BCM_CYGNUS_GENPLL_250MHZ_CLK
+    ihost_sys  genpll           3       BCM_CYGNUS_GENPLL_IHOST_SYS_CLK
+    enet_sw    genpll           4       BCM_CYGNUS_GENPLL_ENET_SW_CLK
+    audio_125  genpll           5       BCM_CYGNUS_GENPLL_AUDIO_125_CLK
+    can        genpll           6       BCM_CYGNUS_GENPLL_CAN_CLK
+
+    lcpll0     crystal          0       BCM_CYGNUS_LCPLL0
+    pcie_phy   lcpll0           1       BCM_CYGNUS_LCPLL0_PCIE_PHY_REF_CLK
+    ddr_phy    lcpll0           2       BCM_CYGNUS_LCPLL0_DDR_PHY_CLK
+    sdio       lcpll0           3       BCM_CYGNUS_LCPLL0_SDIO_CLK
+    usb_phy    lcpll0           4       BCM_CYGNUS_LCPLL0_USB_PHY_REF_CLK
+    smart_card lcpll0           5       BCM_CYGNUS_LCPLL0_SMART_CARD_CLK
+    ch5_unused lcpll0           6       BCM_CYGNUS_LCPLL0_CH5_UNUSED
+
+    mipipll    crystal          0       BCM_CYGNUS_MIPIPLL
+    ch0_unused mipipll          1       BCM_CYGNUS_MIPIPLL_CH0_UNUSED
+    ch1_lcd    mipipll          2       BCM_CYGNUS_MIPIPLL_CH1_LCD
+    ch2_v3d    mipipll          3       BCM_CYGNUS_MIPIPLL_CH2_V3D
+    ch3_unused mipipll          4       BCM_CYGNUS_MIPIPLL_CH3_UNUSED
+    ch4_unused mipipll          5       BCM_CYGNUS_MIPIPLL_CH4_UNUSED
+    ch5_unused mipipll          6       BCM_CYGNUS_MIPIPLL_CH5_UNUSED
diff --git a/Documentation/devicetree/bindings/clock/clock-bindings.txt b/Documentation/devicetree/bindings/clock/clock-bindings.txt
index 06fc6d5..2ec489e 100644
--- a/Documentation/devicetree/bindings/clock/clock-bindings.txt
+++ b/Documentation/devicetree/bindings/clock/clock-bindings.txt
@@ -138,9 +138,10 @@
 and clock frequencies. Such a configuration can be specified in a device tree
 node through assigned-clocks, assigned-clock-parents and assigned-clock-rates
 properties. The assigned-clock-parents property should contain a list of parent
-clocks in form of phandle and clock specifier pairs, the assigned-clock-parents
-property the list of assigned clock frequency values - corresponding to clocks
-listed in the assigned-clocks property.
+clocks in the form of a phandle and clock specifier pair and the
+assigned-clock-rates property should contain a list of frequencies in Hz. Both
+these properties should correspond to the clocks listed in the assigned-clocks
+property.
 
 To skip setting parent or rate of a clock its corresponding entry should be
 set to 0, or can be omitted if it is not followed by any non-zero entry.
diff --git a/Documentation/devicetree/bindings/clock/csr,atlas7-car.txt b/Documentation/devicetree/bindings/clock/csr,atlas7-car.txt
new file mode 100644
index 0000000..54d6d13
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/csr,atlas7-car.txt
@@ -0,0 +1,55 @@
+* Clock and reset bindings for CSR atlas7
+
+Required properties:
+- compatible: Should be "sirf,atlas7-car"
+- reg: Address and length of the register set
+- #clock-cells: Should be <1>
+- #reset-cells: Should be <1>
+
+The clock consumer should specify the desired clock by having the clock
+ID in its "clocks" phandle cell.
+The ID list atlas7_clks defined in drivers/clk/sirf/clk-atlas7.c
+
+The reset consumer should specify the desired reset by having the reset
+ID in its "reset" phandle cell.
+The ID list atlas7_reset_unit defined in drivers/clk/sirf/clk-atlas7.c
+
+Examples: Clock and reset controller node:
+
+car: clock-controller@18620000 {
+	compatible = "sirf,atlas7-car";
+	reg = <0x18620000 0x1000>;
+	#clock-cells = <1>;
+	#reset-cells = <1>;
+};
+
+Examples: Consumers using clock or reset:
+
+timer@10dc0000 {
+	compatible = "sirf,macro-tick";
+	reg = <0x10dc0000 0x1000>;
+	clocks = <&car 54>;
+	interrupts = <0 0 0>,
+		   <0 1 0>,
+		   <0 2 0>,
+		   <0 49 0>,
+		   <0 50 0>,
+		   <0 51 0>;
+};
+
+uart1: uart@18020000 {
+	cell-index = <1>;
+	compatible = "sirf,macro-uart";
+	reg = <0x18020000 0x1000>;
+	clocks = <&clks 95>;
+	interrupts = <0 18 0>;
+	fifosize = <32>;
+};
+
+vpp@13110000 {
+	compatible = "sirf,prima2-vpp";
+	reg = <0x13110000 0x10000>;
+	interrupts = <0 31 0>;
+	clocks = <&car 85>;
+	resets = <&car 29>;
+};
diff --git a/Documentation/devicetree/bindings/clock/emev2-clock.txt b/Documentation/devicetree/bindings/clock/emev2-clock.txt
index 60bbb1a..268ca61 100644
--- a/Documentation/devicetree/bindings/clock/emev2-clock.txt
+++ b/Documentation/devicetree/bindings/clock/emev2-clock.txt
@@ -52,7 +52,7 @@
 
 Example of consumer:
 
-uart@e1020000 {
+serial@e1020000 {
 	compatible = "renesas,em-uart";
 	reg = <0xe1020000 0x38>;
 	interrupts = <0 8 0>;
diff --git a/Documentation/devicetree/bindings/clock/keystone-pll.txt b/Documentation/devicetree/bindings/clock/keystone-pll.txt
index 225990f..47570d2 100644
--- a/Documentation/devicetree/bindings/clock/keystone-pll.txt
+++ b/Documentation/devicetree/bindings/clock/keystone-pll.txt
@@ -15,8 +15,8 @@
 - compatible : shall be "ti,keystone,main-pll-clock" or "ti,keystone,pll-clock"
 - clocks : parent clock phandle
 - reg - pll control0 and pll multipler registers
-- reg-names : control and multiplier. The multiplier is applicable only for
-		main pll clock
+- reg-names : control, multiplier and post-divider. The multiplier and
+		post-divider registers are applicable only for main pll clock
 - fixed-postdiv : fixed post divider value. If absent, use clkod register bits
 		for postdiv
 
@@ -25,8 +25,8 @@
 		#clock-cells = <0>;
 		compatible = "ti,keystone,main-pll-clock";
 		clocks = <&refclksys>;
-		reg = <0x02620350 4>, <0x02310110 4>;
-		reg-names = "control", "multiplier";
+		reg = <0x02620350 4>, <0x02310110 4>, <0x02310108 4>;
+		reg-names = "control", "multiplier", "post-divider";
 		fixed-postdiv = <2>;
 	};
 
diff --git a/Documentation/devicetree/bindings/clock/lpc1850-ccu.txt b/Documentation/devicetree/bindings/clock/lpc1850-ccu.txt
new file mode 100644
index 0000000..fa97c12
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/lpc1850-ccu.txt
@@ -0,0 +1,77 @@
+* NXP LPC1850 Clock Control Unit (CCU)
+
+Each CGU base clock has several clock branches which can be turned on
+or off independently by the Clock Control Units CCU1 or CCU2. The
+branch clocks are distributed between CCU1 and CCU2.
+
+ - Above text taken from NXP LPC1850 User Manual.
+
+This binding uses the common clock binding:
+    Documentation/devicetree/bindings/clock/clock-bindings.txt
+
+Required properties:
+- compatible:
+	Should be "nxp,lpc1850-ccu"
+- reg:
+	Shall define the base and range of the address space
+	containing clock control registers
+- #clock-cells:
+	Shall have value <1>.  The permitted clock-specifier values
+	are the branch clock names defined in table below.
+- clocks:
+	Shall contain a list of phandles for the base clocks routed
+	from the CGU to the specific CCU. See mapping of base clocks
+	and CCU in table below.
+- clock-names:
+	Shall contain a list of names for the base clock routed
+	from the CGU to the specific CCU. Valid CCU clock names:
+	"base_usb0_clk",  "base_periph_clk", "base_usb1_clk",
+	"base_cpu_clk",   "base_spifi_clk",  "base_spi_clk",
+	"base_apb1_clk",  "base_apb3_clk",   "base_adchs_clk",
+	"base_sdio_clk",  "base_ssp0_clk",   "base_ssp1_clk",
+	"base_uart0_clk", "base_uart1_clk",  "base_uart2_clk",
+	"base_uart3_clk", "base_audio_clk"
+
+Which branch clocks that are available on the CCU depends on the
+specific LPC part. Check the user manual for your specific part.
+
+A list of CCU clocks can be found in dt-bindings/clock/lpc18xx-ccu.h.
+
+Example board file:
+
+soc {
+	ccu1: clock-controller@40051000 {
+		compatible = "nxp,lpc1850-ccu";
+		reg = <0x40051000 0x1000>;
+		#clock-cells = <1>;
+		clocks = <&cgu BASE_APB3_CLK>,   <&cgu BASE_APB1_CLK>,
+			 <&cgu BASE_SPIFI_CLK>,  <&cgu BASE_CPU_CLK>,
+			 <&cgu BASE_PERIPH_CLK>, <&cgu BASE_USB0_CLK>,
+			 <&cgu BASE_USB1_CLK>,   <&cgu BASE_SPI_CLK>;
+		clock-names = "base_apb3_clk",   "base_apb1_clk",
+			      "base_spifi_clk",  "base_cpu_clk",
+			      "base_periph_clk", "base_usb0_clk",
+			      "base_usb1_clk",   "base_spi_clk";
+	};
+
+	ccu2: clock-controller@40052000 {
+		compatible = "nxp,lpc1850-ccu";
+		reg = <0x40052000 0x1000>;
+		#clock-cells = <1>;
+		clocks = <&cgu BASE_AUDIO_CLK>, <&cgu BASE_UART3_CLK>,
+			 <&cgu BASE_UART2_CLK>, <&cgu BASE_UART1_CLK>,
+			 <&cgu BASE_UART0_CLK>, <&cgu BASE_SSP1_CLK>,
+			 <&cgu BASE_SSP0_CLK>,  <&cgu BASE_SDIO_CLK>;
+		clock-names = "base_audio_clk", "base_uart3_clk",
+			      "base_uart2_clk", "base_uart1_clk",
+			      "base_uart0_clk", "base_ssp1_clk",
+			      "base_ssp0_clk",  "base_sdio_clk";
+	};
+
+	/* A user of CCU brach clocks */
+	uart1: serial@40082000 {
+		...
+		clocks = <&ccu2 CLK_APB0_UART1>, <&ccu1 CLK_CPU_UART1>;
+		...
+	};
+};
diff --git a/Documentation/devicetree/bindings/clock/lpc1850-cgu.txt b/Documentation/devicetree/bindings/clock/lpc1850-cgu.txt
new file mode 100644
index 0000000..2cc32a9
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/lpc1850-cgu.txt
@@ -0,0 +1,131 @@
+* NXP LPC1850 Clock Generation Unit (CGU)
+
+The CGU generates multiple independent clocks for the core and the
+peripheral blocks of the LPC18xx. Each independent clock is called
+a base clock and itself is one of the inputs to the two Clock
+Control Units (CCUs) which control the branch clocks to the
+individual peripherals.
+
+The CGU selects the inputs to the clock generators from multiple
+clock sources, controls the clock generation, and routes the outputs
+of the clock generators through the clock source bus to the output
+stages. Each output stage provides an independent clock source and
+corresponds to one of the base clocks for the LPC18xx.
+
+ - Above text taken from NXP LPC1850 User Manual.
+
+
+This binding uses the common clock binding:
+    Documentation/devicetree/bindings/clock/clock-bindings.txt
+
+Required properties:
+- compatible:
+	Should be "nxp,lpc1850-cgu"
+- reg:
+	Shall define the base and range of the address space
+	containing clock control registers
+- #clock-cells:
+	Shall have value <1>.  The permitted clock-specifier values
+	are the base clock numbers defined below.
+- clocks:
+	Shall contain a list of phandles for the external input
+	sources to the CGU. The list shall be in the following
+	order: xtal, 32khz, enet_rx_clk, enet_tx_clk, gp_clkin.
+- clock-indices:
+	Shall be an ordered list of numbers defining the base clock
+	number provided by the CGU.
+- clock-output-names:
+	Shall be an ordered list of strings defining the names of
+	the clocks provided by the CGU.
+
+Which base clocks that are available on the CGU depends on the
+specific LPC part. Base clocks are numbered from 0 to 27.
+
+Number:		Name:			Description:
+ 0		BASE_SAFE_CLK		Base safe clock (always on) for WWDT
+ 1		BASE_USB0_CLK		Base clock for USB0
+ 2		BASE_PERIPH_CLK		Base clock for Cortex-M0SUB subsystem,
+					SPI, and SGPIO
+ 3		BASE_USB1_CLK		Base clock for USB1
+ 4		BASE_CPU_CLK		System base clock for ARM Cortex-M core
+					and APB peripheral blocks #0 and #2
+ 5		BASE_SPIFI_CLK		Base clock for SPIFI
+ 6		BASE_SPI_CLK		Base clock for SPI
+ 7		BASE_PHY_RX_CLK		Base clock for Ethernet PHY Receive clock
+ 8		BASE_PHY_TX_CLK		Base clock for Ethernet PHY Transmit clock
+ 9		BASE_APB1_CLK		Base clock for APB peripheral block # 1
+10		BASE_APB3_CLK		Base clock for APB peripheral block # 3
+11		BASE_LCD_CLK		Base clock for LCD
+12		BASE_ADCHS_CLK		Base clock for ADCHS
+13		BASE_SDIO_CLK		Base clock for SD/MMC
+14		BASE_SSP0_CLK		Base clock for SSP0
+15		BASE_SSP1_CLK		Base clock for SSP1
+16		BASE_UART0_CLK		Base clock for UART0
+17		BASE_UART1_CLK		Base clock for UART1
+18		BASE_UART2_CLK		Base clock for UART2
+19		BASE_UART3_CLK		Base clock for UART3
+20		BASE_OUT_CLK		Base clock for CLKOUT pin
+24-21		-			Reserved
+25		BASE_AUDIO_CLK		Base clock for audio system (I2S)
+26 		BASE_CGU_OUT0_CLK	Base clock for CGU_OUT0 clock output
+27 		BASE_CGU_OUT1_CLK	Base clock for CGU_OUT1 clock output
+
+BASE_PERIPH_CLK and BASE_SPI_CLK is only available on LPC43xx.
+BASE_ADCHS_CLK is only available on LPC4370.
+
+
+Example board file:
+
+/ {
+	clocks {
+		xtal: xtal {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <12000000>;
+		};
+
+		xtal32: xtal32 {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <32768>;
+		};
+
+		enet_rx_clk: enet_rx_clk {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <0>;
+			clock-output-names = "enet_rx_clk";
+		};
+
+		enet_tx_clk: enet_tx_clk {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <0>;
+			clock-output-names = "enet_tx_clk";
+		};
+
+		gp_clkin: gp_clkin {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <0>;
+			clock-output-names = "gp_clkin";
+		};
+	};
+
+	soc {
+		cgu: clock-controller@40050000 {
+			compatible = "nxp,lpc1850-cgu";
+			reg = <0x40050000 0x1000>;
+			#clock-cells = <1>;
+			clocks = <&xtal>, <&creg_clk 1>, <&enet_rx_clk>, <&enet_tx_clk>, <&gp_clkin>;
+		};
+
+		/* A CGU and CCU clock consumer */
+		lcdc: lcdc@40008000 {
+			...
+			clocks = <&cgu BASE_LCD_CLK>, <&ccu1 CLK_CPU_LCD>;
+			clock-names = "clcdclk", "apb_pclk";
+			...
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/clock/marvell,pxa1928.txt b/Documentation/devicetree/bindings/clock/marvell,pxa1928.txt
new file mode 100644
index 0000000..809c5a2
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/marvell,pxa1928.txt
@@ -0,0 +1,21 @@
+* Marvell PXA1928 Clock Controllers
+
+The PXA1928 clock subsystem generates and supplies clock to various
+controllers within the PXA1928 SoC. The PXA1928 contains 3 clock controller
+blocks called APMU, MPMU, and APBC roughly corresponding to internal buses.
+
+Required Properties:
+
+- compatible: should be one of the following.
+  - "marvell,pxa1928-apmu" - APMU controller compatible
+  - "marvell,pxa1928-mpmu" - MPMU controller compatible
+  - "marvell,pxa1928-apbc" - APBC controller compatible
+- reg: physical base address of the clock controller and length of memory mapped
+  region.
+- #clock-cells: should be 1.
+- #reset-cells: should be 1.
+
+Each clock is assigned an identifier and client nodes use the clock controller
+phandle and this identifier to specify the clock which they consume.
+
+All these identifiers can be found in <dt-bindings/clock/marvell,pxa1928.h>.
diff --git a/Documentation/devicetree/bindings/clock/mvebu-gated-clock.txt b/Documentation/devicetree/bindings/clock/mvebu-gated-clock.txt
index 31c7c0c..660e649 100644
--- a/Documentation/devicetree/bindings/clock/mvebu-gated-clock.txt
+++ b/Documentation/devicetree/bindings/clock/mvebu-gated-clock.txt
@@ -19,6 +19,7 @@
 9	pex1	PCIe Cntrl 1
 15	sata0	SATA Host 0
 17	sdio	SDHCI Host
+23	crypto	CESA (crypto engine)
 25	tdm	Time Division Mplx
 28	ddr	DDR Cntrl
 30	sata1	SATA Host 0
diff --git a/Documentation/devicetree/bindings/clock/nvidia,tegra124-car.txt b/Documentation/devicetree/bindings/clock/nvidia,tegra124-car.txt
index c6620bc..7f02fb4 100644
--- a/Documentation/devicetree/bindings/clock/nvidia,tegra124-car.txt
+++ b/Documentation/devicetree/bindings/clock/nvidia,tegra124-car.txt
@@ -20,15 +20,38 @@
 - #reset-cells : Should be 1.
   In clock consumers, this cell represents the bit number in the CAR's
   array of CLK_RST_CONTROLLER_RST_DEVICES_* registers.
+- nvidia,external-memory-controller : phandle of the EMC driver.
+
+The node should contain a "emc-timings" subnode for each supported RAM type (see
+field RAM_CODE in register PMC_STRAPPING_OPT_A).
+
+Required properties for "emc-timings" nodes :
+- nvidia,ram-code : Should contain the value of RAM_CODE this timing set
+  is used for.
+
+Each "emc-timings" node should contain a "timing" subnode for every supported
+EMC clock rate.
+
+Required properties for "timing" nodes :
+- clock-frequency : Should contain the memory clock rate to which this timing
+relates.
+- nvidia,parent-clock-frequency : Should contain the rate at which the current
+parent of the EMC clock should be running at this timing.
+- clocks : Must contain an entry for each entry in clock-names.
+  See ../clocks/clock-bindings.txt for details.
+- clock-names : Must include the following entries:
+  - emc-parent : the clock that should be the parent of the EMC clock at this
+timing.
 
 Example SoC include file:
 
 / {
-	tegra_car: clock {
+	tegra_car: clock@60006000 {
 		compatible = "nvidia,tegra124-car";
 		reg = <0x60006000 0x1000>;
 		#clock-cells = <1>;
 		#reset-cells = <1>;
+		nvidia,external-memory-controller = <&emc>;
 	};
 
 	usb@c5004000 {
@@ -62,4 +85,23 @@
 	&tegra_car {
 		clocks = <&clk_32k> <&osc>;
 	};
+
+	clock@60006000 {
+		emc-timings-3 {
+			nvidia,ram-code = <3>;
+
+			timing-12750000 {
+				clock-frequency = <12750000>;
+				nvidia,parent-clock-frequency = <408000000>;
+				clocks = <&tegra_car TEGRA124_CLK_PLL_P>;
+				clock-names = "emc-parent";
+			};
+			timing-20400000 {
+				clock-frequency = <20400000>;
+				nvidia,parent-clock-frequency = <408000000>;
+				clocks = <&tegra_car TEGRA124_CLK_PLL_P>;
+				clock-names = "emc-parent";
+			};
+		};
+	};
 };
diff --git a/Documentation/devicetree/bindings/clock/renesas,cpg-div6-clocks.txt b/Documentation/devicetree/bindings/clock/renesas,cpg-div6-clocks.txt
index 054f65f..5ddb684 100644
--- a/Documentation/devicetree/bindings/clock/renesas,cpg-div6-clocks.txt
+++ b/Documentation/devicetree/bindings/clock/renesas,cpg-div6-clocks.txt
@@ -10,9 +10,11 @@
     - "renesas,r8a73a4-div6-clock" for R8A73A4 (R-Mobile APE6) DIV6 clocks
     - "renesas,r8a7740-div6-clock" for R8A7740 (R-Mobile A1) DIV6 clocks
     - "renesas,r8a7790-div6-clock" for R8A7790 (R-Car H2) DIV6 clocks
-    - "renesas,r8a7791-div6-clock" for R8A7791 (R-Car M2) DIV6 clocks
+    - "renesas,r8a7791-div6-clock" for R8A7791 (R-Car M2-W) DIV6 clocks
+    - "renesas,r8a7793-div6-clock" for R8A7793 (R-Car M2-N) DIV6 clocks
+    - "renesas,r8a7794-div6-clock" for R8A7794 (R-Car E2) DIV6 clocks
     - "renesas,sh73a0-div6-clock" for SH73A0 (SH-Mobile AG5) DIV6 clocks
-    - "renesas,cpg-div6-clock" for generic DIV6 clocks
+    and "renesas,cpg-div6-clock" as a fallback.
   - reg: Base address and length of the memory resource used by the DIV6 clock
   - clocks: Reference to the parent clock(s); either one, four, or eight
     clocks must be specified.  For clocks with multiple parents, invalid
diff --git a/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt b/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt
index 0a80fa7..16ed181 100644
--- a/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt
+++ b/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt
@@ -13,12 +13,14 @@
     - "renesas,r7s72100-mstp-clocks" for R7S72100 (RZ) MSTP gate clocks
     - "renesas,r8a73a4-mstp-clocks" for R8A73A4 (R-Mobile APE6) MSTP gate clocks
     - "renesas,r8a7740-mstp-clocks" for R8A7740 (R-Mobile A1) MSTP gate clocks
+    - "renesas,r8a7778-mstp-clocks" for R8A7778 (R-Car M1) MSTP gate clocks
     - "renesas,r8a7779-mstp-clocks" for R8A7779 (R-Car H1) MSTP gate clocks
     - "renesas,r8a7790-mstp-clocks" for R8A7790 (R-Car H2) MSTP gate clocks
-    - "renesas,r8a7791-mstp-clocks" for R8A7791 (R-Car M2) MSTP gate clocks
+    - "renesas,r8a7791-mstp-clocks" for R8A7791 (R-Car M2-W) MSTP gate clocks
+    - "renesas,r8a7793-mstp-clocks" for R8A7793 (R-Car M2-N) MSTP gate clocks
     - "renesas,r8a7794-mstp-clocks" for R8A7794 (R-Car E2) MSTP gate clocks
     - "renesas,sh73a0-mstp-clocks" for SH73A0 (SH-MobileAG5) MSTP gate clocks
-    - "renesas,cpg-mstp-clock" for generic MSTP gate clocks
+    and "renesas,cpg-mstp-clocks" as a fallback.
   - reg: Base address and length of the I/O mapped registers used by the MSTP
     clocks. The first register is the clock control register and is mandatory.
     The second register is the clock status register and is optional when not
diff --git a/Documentation/devicetree/bindings/clock/renesas,rcar-gen2-cpg-clocks.txt b/Documentation/devicetree/bindings/clock/renesas,rcar-gen2-cpg-clocks.txt
index b02944f..56f111b 100644
--- a/Documentation/devicetree/bindings/clock/renesas,rcar-gen2-cpg-clocks.txt
+++ b/Documentation/devicetree/bindings/clock/renesas,rcar-gen2-cpg-clocks.txt
@@ -10,7 +10,7 @@
     - "renesas,r8a7791-cpg-clocks" for the r8a7791 CPG
     - "renesas,r8a7793-cpg-clocks" for the r8a7793 CPG
     - "renesas,r8a7794-cpg-clocks" for the r8a7794 CPG
-    - "renesas,rcar-gen2-cpg-clocks" for the generic R-Car Gen2 CPG
+    and "renesas,rcar-gen2-cpg-clocks" as a fallback.
 
   - reg: Base address and length of the memory resource used by the CPG
 
diff --git a/Documentation/devicetree/bindings/clock/renesas,rz-cpg-clocks.txt b/Documentation/devicetree/bindings/clock/renesas,rz-cpg-clocks.txt
index 98a2574..b0f7ddb 100644
--- a/Documentation/devicetree/bindings/clock/renesas,rz-cpg-clocks.txt
+++ b/Documentation/devicetree/bindings/clock/renesas,rz-cpg-clocks.txt
@@ -7,7 +7,7 @@
 
   - compatible: Must be one of
     - "renesas,r7s72100-cpg-clocks" for the r7s72100 CPG
-    - "renesas,rz-cpg-clocks" for the generic RZ CPG
+    and "renesas,rz-cpg-clocks" as a fallback.
   - reg: Base address and length of the memory resource used by the CPG
   - clocks: References to possible parent clocks. Order must match clock modes
     in the datasheet. For the r7s72100, this is extal, usb_x1.
diff --git a/Documentation/devicetree/bindings/clock/st,stm32-rcc.txt b/Documentation/devicetree/bindings/clock/st,stm32-rcc.txt
new file mode 100644
index 0000000..fee3205
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/st,stm32-rcc.txt
@@ -0,0 +1,65 @@
+STMicroelectronics STM32 Reset and Clock Controller
+===================================================
+
+The RCC IP is both a reset and a clock controller. This documentation only
+describes the clock part.
+
+Please also refer to clock-bindings.txt in this directory for common clock
+controller binding usage.
+
+Required properties:
+- compatible: Should be "st,stm32f42xx-rcc"
+- reg: should be register base and length as documented in the
+  datasheet
+- #clock-cells: 2, device nodes should specify the clock in their "clocks"
+  property, containing a phandle to the clock device node, an index selecting
+  between gated clocks and other clocks and an index specifying the clock to
+  use.
+
+Example:
+
+	rcc: rcc@40023800 {
+		#clock-cells = <2>
+		compatible = "st,stm32f42xx-rcc", "st,stm32-rcc";
+		reg = <0x40023800 0x400>;
+	};
+
+Specifying gated clocks
+=======================
+
+The primary index must be set to 0.
+
+The secondary index is the bit number within the RCC register bank, starting
+from the first RCC clock enable register (RCC_AHB1ENR, address offset 0x30).
+
+It is calculated as: index = register_offset / 4 * 32 + bit_offset.
+Where bit_offset is the bit offset within the register (LSB is 0, MSB is 31).
+
+Example:
+
+	/* Gated clock, AHB1 bit 0 (GPIOA) */
+	... {
+		clocks = <&rcc 0 0>
+	};
+
+	/* Gated clock, AHB2 bit 4 (CRYP) */
+	... {
+		clocks = <&rcc 0 36>
+	};
+
+Specifying other clocks
+=======================
+
+The primary index must be set to 1.
+
+The secondary index is bound with the following magic numbers:
+
+	0	SYSTICK
+	1	FCLK
+
+Example:
+
+	/* Misc clock, FCLK */
+	... {
+		clocks = <&rcc 1 1>
+	};
diff --git a/Documentation/devicetree/bindings/clock/sunxi.txt b/Documentation/devicetree/bindings/clock/sunxi.txt
index 4fa11af..8a47b77 100644
--- a/Documentation/devicetree/bindings/clock/sunxi.txt
+++ b/Documentation/devicetree/bindings/clock/sunxi.txt
@@ -67,6 +67,7 @@
 	"allwinner,sun4i-a10-usb-clk" - for usb gates + resets on A10 / A20
 	"allwinner,sun5i-a13-usb-clk" - for usb gates + resets on A13
 	"allwinner,sun6i-a31-usb-clk" - for usb gates + resets on A31
+	"allwinner,sun8i-a23-usb-clk" - for usb gates + resets on A23
 	"allwinner,sun9i-a80-usb-mod-clk" - for usb gates + resets on A80
 	"allwinner,sun9i-a80-usb-phy-clk" - for usb phy gates + resets on A80
 
diff --git a/Documentation/devicetree/bindings/clock/ti,cdce925.txt b/Documentation/devicetree/bindings/clock/ti,cdce925.txt
new file mode 100644
index 0000000..4c7669a
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/ti,cdce925.txt
@@ -0,0 +1,42 @@
+Binding for TO CDCE925 programmable I2C clock synthesizers.
+
+Reference
+This binding uses the common clock binding[1].
+
+[1] Documentation/devicetree/bindings/clock/clock-bindings.txt
+[2] http://www.ti.com/product/cdce925
+
+The driver provides clock sources for each output Y1 through Y5.
+
+Required properties:
+ - compatible: Shall be "ti,cdce925"
+ - reg: I2C device address.
+ - clocks: Points to a fixed parent clock that provides the input frequency.
+ - #clock-cells: From common clock bindings: Shall be 1.
+
+Optional properties:
+ - xtal-load-pf: Crystal load-capacitor value to fine-tune performance on a
+                 board, or to compensate for external influences.
+
+For both PLL1 and PLL2 an optional child node can be used to specify spread
+spectrum clocking parameters for a board.
+  - spread-spectrum: SSC mode as defined in the data sheet.
+  - spread-spectrum-center: Use "centered" mode instead of "max" mode. When
+    present, the clock runs at the requested frequency on average. Otherwise
+    the requested frequency is the maximum value of the SCC range.
+
+
+Example:
+
+	clockgen: cdce925pw@64 {
+		compatible = "cdce925";
+		reg = <0x64>;
+		clocks = <&xtal_27Mhz>;
+		#clock-cells = <1>;
+		xtal-load-pf = <5>;
+		/* PLL options to get SSC 1% centered */
+		PLL2 {
+			spread-spectrum = <4>;
+			spread-spectrum-center;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/hwlock/hwlock.txt b/Documentation/devicetree/bindings/hwlock/hwlock.txt
new file mode 100644
index 0000000..085d1f5
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwlock/hwlock.txt
@@ -0,0 +1,59 @@
+Generic hwlock bindings
+=======================
+
+Generic bindings that are common to all the hwlock platform specific driver
+implementations.
+
+Please also look through the individual platform specific hwlock binding
+documentations for identifying any additional properties specific to that
+platform.
+
+hwlock providers:
+=================
+
+Required properties:
+- #hwlock-cells:        Specifies the number of cells needed to represent a
+                        specific lock.
+
+hwlock users:
+=============
+
+Consumers that require specific hwlock(s) should specify them using the
+property "hwlocks", and an optional "hwlock-names" property.
+
+Required properties:
+- hwlocks:              List of phandle to a hwlock provider node and an
+                        associated hwlock args specifier as indicated by
+                        #hwlock-cells. The list can have just a single hwlock
+                        or multiple hwlocks, with each hwlock represented by
+                        a phandle and a corresponding args specifier.
+
+Optional properties:
+- hwlock-names:         List of hwlock name strings defined in the same order
+                        as the hwlocks, with one name per hwlock. Consumers can
+                        use the hwlock-names to match and get a specific hwlock.
+
+
+1. Example of a node using a single specific hwlock:
+
+The following example has a node requesting a hwlock in the bank defined by
+the node hwlock1. hwlock1 is a hwlock provider with an argument specifier
+of length 1.
+
+	node {
+		...
+		hwlocks = <&hwlock1 2>;
+		...
+	};
+
+2. Example of a node using multiple specific hwlocks:
+
+The following example has a node requesting two hwlocks, a hwlock within
+the hwlock device node 'hwlock1' with #hwlock-cells value of 1, and another
+hwlock within the hwlock device node 'hwlock2' with #hwlock-cells value of 2.
+
+	node {
+		...
+		hwlocks = <&hwlock1 2>, <&hwlock2 0 3>;
+		...
+	};
diff --git a/Documentation/devicetree/bindings/hwlock/omap-hwspinlock.txt b/Documentation/devicetree/bindings/hwlock/omap-hwspinlock.txt
new file mode 100644
index 0000000..2c9804f
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwlock/omap-hwspinlock.txt
@@ -0,0 +1,26 @@
+OMAP4+ HwSpinlock Driver
+========================
+
+Required properties:
+- compatible:		Should be "ti,omap4-hwspinlock" for
+			    OMAP44xx, OMAP54xx, AM33xx, AM43xx, DRA7xx SoCs
+- reg:			Contains the hwspinlock module register address space
+			(base address and length)
+- ti,hwmods:		Name of the hwmod associated with the hwspinlock device
+- #hwlock-cells:	Should be 1. The OMAP hwspinlock users will use a
+			0-indexed relative hwlock number as the argument
+			specifier value for requesting a specific hwspinlock
+			within a hwspinlock bank.
+
+Please look at the generic hwlock binding for usage information for consumers,
+"Documentation/devicetree/bindings/hwlock/hwlock.txt"
+
+Example:
+
+/* OMAP4 */
+hwspinlock: spinlock@4a0f6000 {
+	compatible = "ti,omap4-hwspinlock";
+	reg = <0x4a0f6000 0x1000>;
+	ti,hwmods = "spinlock";
+	#hwlock-cells = <1>;
+};
diff --git a/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.txt b/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.txt
new file mode 100644
index 0000000..4563f52
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.txt
@@ -0,0 +1,39 @@
+Qualcomm Hardware Mutex Block:
+
+The hardware block provides mutexes utilized between different processors on
+the SoC as part of the communication protocol used by these processors.
+
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: must be one of:
+		    "qcom,sfpb-mutex",
+		    "qcom,tcsr-mutex"
+
+- syscon:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: one cell containing:
+		    syscon phandle
+		    offset of the hwmutex block within the syscon
+		    stride of the hwmutex registers
+
+- #hwlock-cells:
+	Usage: required
+	Value type: <u32>
+	Definition: must be 1, the specified cell represent the lock id
+		    (hwlock standard property, see hwlock.txt)
+
+Example:
+
+	tcsr_mutex_block: syscon@fd484000 {
+		compatible = "syscon";
+		reg = <0xfd484000 0x2000>;
+	};
+
+	hwlock@fd484000 {
+		compatible = "qcom,tcsr-mutex";
+		syscon = <&tcsr_mutex_block 0 0x80>;
+
+		#hwlock-cells = <1>;
+	};
diff --git a/Documentation/devicetree/bindings/hwlock/sirf,hwspinlock.txt b/Documentation/devicetree/bindings/hwlock/sirf,hwspinlock.txt
new file mode 100644
index 0000000..9bb1240a6
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwlock/sirf,hwspinlock.txt
@@ -0,0 +1,28 @@
+SIRF Hardware spinlock device Binding
+-----------------------------------------------
+
+Required properties :
+- compatible : shall contain only one of the following:
+	"sirf,hwspinlock"
+
+- reg : the register address of hwspinlock
+
+- #hwlock-cells : hwlock users only use the hwlock id to represent a specific
+	hwlock, so the number of cells should be <1> here.
+
+Please look at the generic hwlock binding for usage information for consumers,
+"Documentation/devicetree/bindings/hwlock/hwlock.txt"
+
+Example of hwlock provider:
+	hwlock {
+		compatible = "sirf,hwspinlock";
+		reg = <0x13240000 0x00010000>;
+		#hwlock-cells = <1>;
+	};
+
+Example of hwlock users:
+	node {
+		...
+		hwlocks = <&hwlock 2>;
+		...
+	};
diff --git a/Documentation/devicetree/bindings/leds/leds-aat1290.txt b/Documentation/devicetree/bindings/leds/leds-aat1290.txt
new file mode 100644
index 0000000..c05ed91
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/leds-aat1290.txt
@@ -0,0 +1,73 @@
+* Skyworks Solutions, Inc. AAT1290 Current Regulator for Flash LEDs
+
+The device is controlled through two pins: FL_EN and EN_SET. The pins when,
+asserted high, enable flash strobe and movie mode (max 1/2 of flash current)
+respectively. In order to add a capability of selecting the strobe signal source
+(e.g. CPU or camera sensor) there is an additional switch required, independent
+of the flash chip. The switch is controlled with pin control.
+
+Required properties:
+
+- compatible : Must be "skyworks,aat1290".
+- flen-gpios : Must be device tree identifier of the flash device FL_EN pin.
+- enset-gpios : Must be device tree identifier of the flash device EN_SET pin.
+
+Optional properties:
+- pinctrl-names : Must contain entries: "default", "host", "isp". Entries
+		"default" and "host" must refer to the same pin configuration
+		node, which sets the host as a strobe signal provider. Entry
+		"isp" must refer to the pin configuration node, which sets the
+		ISP as a strobe signal provider.
+
+A discrete LED element connected to the device must be represented by a child
+node - see Documentation/devicetree/bindings/leds/common.txt.
+
+Required properties of the LED child node:
+- led-max-microamp : see Documentation/devicetree/bindings/leds/common.txt
+- flash-max-microamp : see Documentation/devicetree/bindings/leds/common.txt
+                       Maximum flash LED supply current can be calculated using
+                       following formula: I = 1A * 162kohm / Rset.
+- flash-timeout-us : see Documentation/devicetree/bindings/leds/common.txt
+                     Maximum flash timeout can be calculated using following
+                     formula: T = 8.82 * 10^9 * Ct.
+
+Optional properties of the LED child node:
+- label : see Documentation/devicetree/bindings/leds/common.txt
+
+Example (by Ct = 220nF, Rset = 160kohm and exynos4412-trats2 board with
+a switch that allows for routing strobe signal either from the host or from
+the camera sensor):
+
+#include "exynos4412.dtsi"
+
+aat1290 {
+	compatible = "skyworks,aat1290";
+	flen-gpios = <&gpj1 1 GPIO_ACTIVE_HIGH>;
+	enset-gpios = <&gpj1 2 GPIO_ACTIVE_HIGH>;
+
+	pinctrl-names = "default", "host", "isp";
+	pinctrl-0 = <&camera_flash_host>;
+	pinctrl-1 = <&camera_flash_host>;
+	pinctrl-2 = <&camera_flash_isp>;
+
+	camera_flash: flash-led {
+		label = "aat1290-flash";
+		led-max-microamp = <520833>;
+		flash-max-microamp = <1012500>;
+		flash-timeout-us = <1940000>;
+	};
+};
+
+&pinctrl_0 {
+	camera_flash_host: camera-flash-host {
+		samsung,pins = "gpj1-0";
+		samsung,pin-function = <1>;
+		samsung,pin-val = <0>;
+	};
+
+	camera_flash_isp: camera-flash-isp {
+		samsung,pins = "gpj1-0";
+		samsung,pin-function = <1>;
+		samsung,pin-val = <1>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/leds/leds-bcm6328.txt b/Documentation/devicetree/bindings/leds/leds-bcm6328.txt
new file mode 100644
index 0000000..f9e36ad
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/leds-bcm6328.txt
@@ -0,0 +1,309 @@
+LEDs connected to Broadcom BCM6328 controller
+
+This controller is present on BCM6318, BCM6328, BCM6362 and BCM63268.
+In these SoCs it's possible to control LEDs both as GPIOs or by hardware.
+However, on some devices there are Serial LEDs (LEDs connected to a 74x164
+controller), which can either be controlled by software (exporting the 74x164
+as spi-gpio. See Documentation/devicetree/bindings/gpio/gpio-74x164.txt), or
+by hardware using this driver.
+Some of these Serial LEDs are hardware controlled (e.g. ethernet LEDs) and
+exporting the 74x164 as spi-gpio prevents those LEDs to be hardware
+controlled, so the only chance to keep them working is by using this driver.
+
+BCM6328 LED controller has a HWDIS register, which controls whether a LED
+should be controlled by a hardware signal instead of the MODE register value,
+with 0 meaning hardware control enabled and 1 hardware control disabled. This
+is usually 1:1 for hardware to LED signals, but through the activity/link
+registers you have some limited control over rerouting the LEDs (as
+explained later in brcm,link-signal-sources). Even if a LED is hardware
+controlled you are still able to make it blink or light it up if it isn't,
+but you can't turn it off if the hardware decides to light it up. For this
+reason, hardware controlled LEDs aren't registered as LED class devices.
+
+Required properties:
+  - compatible : should be "brcm,bcm6328-leds".
+  - #address-cells : must be 1.
+  - #size-cells : must be 0.
+  - reg : BCM6328 LED controller address and size.
+
+Optional properties:
+  - brcm,serial-leds : Boolean, enables Serial LEDs.
+    Default : false
+
+Each LED is represented as a sub-node of the brcm,bcm6328-leds device.
+
+LED sub-node required properties:
+  - reg : LED pin number (only LEDs 0 to 23 are valid).
+
+LED sub-node optional properties:
+  a) Optional properties for sub-nodes related to software controlled LEDs:
+    - label : see Documentation/devicetree/bindings/leds/common.txt
+    - active-low : Boolean, makes LED active low.
+      Default : false
+    - default-state : see
+      Documentation/devicetree/bindings/leds/leds-gpio.txt
+    - linux,default-trigger : see
+      Documentation/devicetree/bindings/leds/common.txt
+
+  b) Optional properties for sub-nodes related to hardware controlled LEDs:
+    - brcm,hardware-controlled : Boolean, makes this LED hardware controlled.
+      Default : false
+    - brcm,link-signal-sources : An array of hardware link
+      signal sources. Up to four link hardware signals can get muxed into
+      these LEDs. Only valid for LEDs 0 to 7, where LED signals 0 to 3 may
+      be muxed to LEDs 0 to 3, and signals 4 to 7 may be muxed to LEDs
+      4 to 7. A signal can be muxed to more than one LED, and one LED can
+      have more than one source signal.
+    - brcm,activity-signal-sources : An array of hardware activity
+      signal sources. Up to four activity hardware signals can get muxed into
+      these LEDs. Only valid for LEDs 0 to 7, where LED signals 0 to 3 may
+      be muxed to LEDs 0 to 3, and signals 4 to 7 may be muxed to LEDs
+      4 to 7. A signal can be muxed to more than one LED, and one LED can
+      have more than one source signal.
+
+Examples:
+Scenario 1 : BCM6328 with 4 EPHY LEDs
+	leds0: led-controller@10000800 {
+		compatible = "brcm,bcm6328-leds";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0x10000800 0x24>;
+
+		alarm_red@2 {
+			reg = <2>;
+			active-low;
+			label = "red:alarm";
+		};
+		inet_green@3 {
+			reg = <3>;
+			active-low;
+			label = "green:inet";
+		};
+		power_green@4 {
+			reg = <4>;
+			active-low;
+			label = "green:power";
+			default-state = "on";
+		};
+		ephy0_spd@17 {
+			reg = <17>;
+			brcm,hardware-controlled;
+		};
+		ephy1_spd@18 {
+			reg = <18>;
+			brcm,hardware-controlled;
+		};
+		ephy2_spd@19 {
+			reg = <19>;
+			brcm,hardware-controlled;
+		};
+		ephy3_spd@20 {
+			reg = <20>;
+			brcm,hardware-controlled;
+		};
+	};
+
+Scenario 2 : BCM63268 with Serial/GPHY0 LEDs
+	leds0: led-controller@10001900 {
+		compatible = "brcm,bcm6328-leds";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0x10001900 0x24>;
+		brcm,serial-leds;
+
+		gphy0_spd0@0 {
+			reg = <0>;
+			brcm,hardware-controlled;
+			brcm,link-signal-sources = <0>;
+		};
+		gphy0_spd1@1 {
+			reg = <1>;
+			brcm,hardware-controlled;
+			brcm,link-signal-sources = <1>;
+		};
+		inet_red@2 {
+			reg = <2>;
+			active-low;
+			label = "red:inet";
+		};
+		dsl_green@3 {
+			reg = <3>;
+			active-low;
+			label = "green:dsl";
+		};
+		usb_green@4 {
+			reg = <4>;
+			active-low;
+			label = "green:usb";
+		};
+		wps_green@7 {
+			reg = <7>;
+			active-low;
+			label = "green:wps";
+		};
+		inet_green@8 {
+			reg = <8>;
+			active-low;
+			label = "green:inet";
+		};
+		ephy0_act@9 {
+			reg = <9>;
+			brcm,hardware-controlled;
+		};
+		ephy1_act@10 {
+			reg = <10>;
+			brcm,hardware-controlled;
+		};
+		ephy2_act@11 {
+			reg = <11>;
+			brcm,hardware-controlled;
+		};
+		gphy0_act@12 {
+			reg = <12>;
+			brcm,hardware-controlled;
+		};
+		ephy0_spd@13 {
+			reg = <13>;
+			brcm,hardware-controlled;
+		};
+		ephy1_spd@14 {
+			reg = <14>;
+			brcm,hardware-controlled;
+		};
+		ephy2_spd@15 {
+			reg = <15>;
+			brcm,hardware-controlled;
+		};
+		power_green@20 {
+			reg = <20>;
+			active-low;
+			label = "green:power";
+			default-state = "on";
+		};
+	};
+
+Scenario 3 : BCM6362 with 1 LED for each EPHY
+	leds0: led-controller@10001900 {
+		compatible = "brcm,bcm6328-leds";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0x10001900 0x24>;
+
+		usb@0 {
+			reg = <0>;
+			brcm,hardware-controlled;
+			brcm,link-signal-sources = <0>;
+			brcm,activity-signal-sources = <0>;
+			/* USB link/activity routed to USB LED */
+		};
+		inet@1 {
+			reg = <1>;
+			brcm,hardware-controlled;
+			brcm,activity-signal-sources = <1>;
+			/* INET activity routed to INET LED */
+		};
+		ephy0@4 {
+			reg = <4>;
+			brcm,hardware-controlled;
+			brcm,link-signal-sources = <4>;
+			/* EPHY0 link routed to EPHY0 LED */
+		};
+		ephy1@5 {
+			reg = <5>;
+			brcm,hardware-controlled;
+			brcm,link-signal-sources = <5>;
+			/* EPHY1 link routed to EPHY1 LED */
+		};
+		ephy2@6 {
+			reg = <6>;
+			brcm,hardware-controlled;
+			brcm,link-signal-sources = <6>;
+			/* EPHY2 link routed to EPHY2 LED */
+		};
+		ephy3@7 {
+			reg = <7>;
+			brcm,hardware-controlled;
+			brcm,link-signal-sources = <7>;
+			/* EPHY3 link routed to EPHY3 LED */
+		};
+		power_green@20 {
+			reg = <20>;
+			active-low;
+			label = "green:power";
+			default-state = "on";
+		};
+	};
+
+Scenario 4 : BCM6362 with 1 LED for all EPHYs
+	leds0: led-controller@10001900 {
+		compatible = "brcm,bcm6328-leds";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0x10001900 0x24>;
+
+		usb@0 {
+			reg = <0>;
+			brcm,hardware-controlled;
+			brcm,link-signal-sources = <0 1>;
+			brcm,activity-signal-sources = <0 1>;
+			/* USB/INET link/activity routed to USB LED */
+		};
+		ephy@4 {
+			reg = <4>;
+			brcm,hardware-controlled;
+			brcm,link-signal-sources = <4 5 6 7>;
+			/* EPHY0/1/2/3 link routed to EPHY0 LED */
+		};
+		power_green@20 {
+			reg = <20>;
+			active-low;
+			label = "green:power";
+			default-state = "on";
+		};
+	};
+
+Scenario 5 : BCM6362 with EPHY LEDs swapped
+	leds0: led-controller@10001900 {
+		compatible = "brcm,bcm6328-leds";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0x10001900 0x24>;
+
+		usb@0 {
+			reg = <0>;
+			brcm,hardware-controlled;
+			brcm,link-signal-sources = <0>;
+			brcm,activity-signal-sources = <0 1>;
+			/* USB link/act and INET act routed to USB LED */
+		};
+		ephy0@4 {
+			reg = <4>;
+			brcm,hardware-controlled;
+			brcm,link-signal-sources = <7>;
+			/* EPHY3 link routed to EPHY0 LED */
+		};
+		ephy1@5 {
+			reg = <5>;
+			brcm,hardware-controlled;
+			brcm,link-signal-sources = <6>;
+			/* EPHY2 link routed to EPHY1 LED */
+		};
+		ephy2@6 {
+			reg = <6>;
+			brcm,hardware-controlled;
+			brcm,link-signal-sources = <5>;
+			/* EPHY1 link routed to EPHY2 LED */
+		};
+		ephy3@7 {
+			reg = <7>;
+			brcm,hardware-controlled;
+			brcm,link-signal-sources = <4>;
+			/* EPHY0 link routed to EPHY3 LED */
+		};
+		power_green@20 {
+			reg = <20>;
+			active-low;
+			label = "green:power";
+			default-state = "on";
+		};
+	};
diff --git a/Documentation/devicetree/bindings/leds/leds-bcm6358.txt b/Documentation/devicetree/bindings/leds/leds-bcm6358.txt
new file mode 100644
index 0000000..b22a55b
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/leds-bcm6358.txt
@@ -0,0 +1,145 @@
+LEDs connected to Broadcom BCM6358 controller
+
+This controller is present on BCM6358 and BCM6368.
+In these SoCs there are Serial LEDs (LEDs connected to a 74x164 controller),
+which can either be controlled by software (exporting the 74x164 as spi-gpio.
+See Documentation/devicetree/bindings/gpio/gpio-74x164.txt), or
+by hardware using this driver.
+
+Required properties:
+  - compatible : should be "brcm,bcm6358-leds".
+  - #address-cells : must be 1.
+  - #size-cells : must be 0.
+  - reg : BCM6358 LED controller address and size.
+
+Optional properties:
+  - brcm,clk-div : SCK signal divider. Possible values are 1, 2, 4 and 8.
+    Default : 1
+  - brcm,clk-dat-low : Boolean, makes clock and data signals active low.
+    Default : false
+
+Each LED is represented as a sub-node of the brcm,bcm6358-leds device.
+
+LED sub-node required properties:
+  - reg : LED pin number (only LEDs 0 to 31 are valid).
+
+LED sub-node optional properties:
+  - label : see Documentation/devicetree/bindings/leds/common.txt
+  - active-low : Boolean, makes LED active low.
+    Default : false
+  - default-state : see
+    Documentation/devicetree/bindings/leds/leds-gpio.txt
+  - linux,default-trigger : see
+    Documentation/devicetree/bindings/leds/common.txt
+
+Examples:
+Scenario 1 : BCM6358
+	leds0: led-controller@fffe00d0 {
+		compatible = "brcm,bcm6358-leds";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0xfffe00d0 0x8>;
+
+		alarm_white {
+			reg = <0>;
+			active-low;
+			label = "white:alarm";
+		};
+		tv_white {
+			reg = <2>;
+			active-low;
+			label = "white:tv";
+		};
+		tel_white {
+			reg = <3>;
+			active-low;
+			label = "white:tel";
+		};
+		adsl_white {
+			reg = <4>;
+			active-low;
+			label = "white:adsl";
+		};
+	};
+
+Scenario 2 : BCM6368
+	leds0: led-controller@100000d0 {
+		compatible = "brcm,bcm6358-leds";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0x100000d0 0x8>;
+		brcm,pol-low;
+		brcm,clk-div = <4>;
+
+		power_red {
+			reg = <0>;
+			active-low;
+			label = "red:power";
+		};
+		power_green {
+			reg = <1>;
+			active-low;
+			label = "green:power";
+			default-state = "on";
+		};
+		power_blue {
+			reg = <2>;
+			label = "blue:power";
+		};
+		broadband_red {
+			reg = <3>;
+			active-low;
+			label = "red:broadband";
+		};
+		broadband_green {
+			reg = <4>;
+			label = "green:broadband";
+		};
+		broadband_blue {
+			reg = <5>;
+			active-low;
+			label = "blue:broadband";
+		};
+		wireless_red {
+			reg = <6>;
+			active-low;
+			label = "red:wireless";
+		};
+		wireless_green {
+			reg = <7>;
+			active-low;
+			label = "green:wireless";
+		};
+		wireless_blue {
+			reg = <8>;
+			label = "blue:wireless";
+		};
+		phone_red {
+			reg = <9>;
+			active-low;
+			label = "red:phone";
+		};
+		phone_green {
+			reg = <10>;
+			active-low;
+			label = "green:phone";
+		};
+		phone_blue {
+			reg = <11>;
+			label = "blue:phone";
+		};
+		upgrading_red {
+			reg = <12>;
+			active-low;
+			label = "red:upgrading";
+		};
+		upgrading_green {
+			reg = <13>;
+			active-low;
+			label = "green:upgrading";
+		};
+		upgrading_blue {
+			reg = <14>;
+			label = "blue:upgrading";
+		};
+	};
diff --git a/Documentation/devicetree/bindings/leds/leds-ktd2692.txt b/Documentation/devicetree/bindings/leds/leds-ktd2692.txt
new file mode 100644
index 0000000..8537374
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/leds-ktd2692.txt
@@ -0,0 +1,50 @@
+* Kinetic Technologies - KTD2692 Flash LED Driver
+
+KTD2692 is the ideal power solution for high-power flash LEDs.
+It uses ExpressWire single-wire programming for maximum flexibility.
+
+The ExpressWire interface through CTRL pin can control LED on/off and
+enable/disable the IC, Movie(max 1/3 of Flash current) / Flash mode current,
+Flash timeout, LVP(low voltage protection).
+
+Also, When the AUX pin is pulled high while CTRL pin is high,
+LED current will be ramped up to the flash-mode current level.
+
+Required properties:
+- compatible : Should be "kinetic,ktd2692".
+- ctrl-gpios : Specifier of the GPIO connected to CTRL pin.
+- aux-gpios : Specifier of the GPIO connected to AUX pin.
+
+Optional properties:
+- vin-supply : "vin" LED supply (2.7V to 5.5V).
+  See Documentation/devicetree/bindings/regulator/regulator.txt
+
+A discrete LED element connected to the device must be represented by a child
+node - See Documentation/devicetree/bindings/leds/common.txt
+
+Required properties for flash LED child nodes:
+  See Documentation/devicetree/bindings/leds/common.txt
+- led-max-microamp : Minimum Threshold for Timer protection
+  is defined internally (Maximum 300mA).
+- flash-max-microamp : Flash LED maximum current
+  Formula : I(mA) = 15000 / Rset.
+- flash-max-timeout-us : Flash LED maximum timeout.
+
+Optional properties for flash LED child nodes:
+- label : See Documentation/devicetree/bindings/leds/common.txt
+
+Example:
+
+ktd2692 {
+	compatible = "kinetic,ktd2692";
+	ctrl-gpios = <&gpc0 1 0>;
+	aux-gpios = <&gpc0 2 0>;
+	vin-supply = <&vbat>;
+
+	flash-led {
+		label = "ktd2692-flash";
+		led-max-microamp = <300000>;
+		flash-max-microamp = <1500000>;
+		flash-max-timeout-us = <1835000>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/leds/leds-tlc591xx.txt b/Documentation/devicetree/bindings/leds/leds-tlc591xx.txt
new file mode 100644
index 0000000..3bbbf70
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/leds-tlc591xx.txt
@@ -0,0 +1,40 @@
+LEDs connected to tlc59116 or tlc59108
+
+Required properties
+- compatible: should be "ti,tlc59116" or "ti,tlc59108"
+- #address-cells: must be 1
+- #size-cells: must be 0
+- reg: typically 0x68
+
+Each led is represented as a sub-node of the ti,tlc59116.
+See Documentation/devicetree/bindings/leds/common.txt
+
+LED sub-node properties:
+- reg: number of LED line, 0 to 15 or 0 to 7
+- label: (optional) name of LED
+- linux,default-trigger : (optional)
+
+Examples:
+
+tlc59116@68 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	compatible = "ti,tlc59116";
+	reg = <0x68>;
+
+	wan@0 {
+		label = "wrt1900ac:amber:wan";
+		reg = <0x0>;
+	};
+
+	2g@2 {
+		label = "wrt1900ac:white:2g";
+		reg = <0x2>;
+	};
+
+	alive@9 {
+		label = "wrt1900ac:green:alive";
+		reg = <0x9>;
+		linux,default_trigger = "heartbeat";
+	};
+};
diff --git a/Documentation/devicetree/bindings/mfd/tps6507x.txt b/Documentation/devicetree/bindings/mfd/tps6507x.txt
old mode 100755
new mode 100644
diff --git a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
index 750d577..f5a8ca2 100644
--- a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
+++ b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
@@ -1,7 +1,7 @@
 * Marvell Armada 370 / Armada XP Ethernet Controller (NETA)
 
 Required properties:
-- compatible: should be "marvell,armada-370-neta".
+- compatible: "marvell,armada-370-neta" or "marvell,armada-xp-neta".
 - reg: address and length of the register set for the device.
 - interrupts: interrupt for the device
 - phy: See ethernet.txt file in the same directory.
diff --git a/Documentation/devicetree/bindings/pinctrl/lantiq,falcon-pinumx.txt b/Documentation/devicetree/bindings/pinctrl/lantiq,pinctrl-falcon.txt
similarity index 100%
rename from Documentation/devicetree/bindings/pinctrl/lantiq,falcon-pinumx.txt
rename to Documentation/devicetree/bindings/pinctrl/lantiq,pinctrl-falcon.txt
diff --git a/Documentation/devicetree/bindings/pinctrl/lantiq,xway-pinumx.txt b/Documentation/devicetree/bindings/pinctrl/lantiq,pinctrl-xway.txt
similarity index 100%
rename from Documentation/devicetree/bindings/pinctrl/lantiq,xway-pinumx.txt
rename to Documentation/devicetree/bindings/pinctrl/lantiq,pinctrl-xway.txt
diff --git a/Documentation/devicetree/bindings/remoteproc/wkup_m3_rproc.txt b/Documentation/devicetree/bindings/remoteproc/wkup_m3_rproc.txt
new file mode 100644
index 0000000..3a70073
--- /dev/null
+++ b/Documentation/devicetree/bindings/remoteproc/wkup_m3_rproc.txt
@@ -0,0 +1,52 @@
+TI Wakeup M3 Remoteproc Driver
+==============================
+
+The TI AM33xx and AM43xx family of devices use a small Cortex M3 co-processor
+(commonly referred to as Wakeup M3 or CM3) to help with various low power tasks
+that cannot be controlled from the MPU. This CM3 processor requires a firmware
+binary to accomplish this. The wkup_m3 remoteproc driver handles the loading of
+the firmware and booting of the CM3.
+
+Wkup M3 Device Node:
+====================
+A wkup_m3 device node is used to represent the Wakeup M3 processor instance
+within the SoC. It is added as a child node of the parent interconnect bus
+(l4_wkup) through which it is accessible to the MPU.
+
+Required properties:
+--------------------
+- compatible:		Should be one of,
+				"ti,am3352-wkup-m3" for AM33xx SoCs
+				"ti,am4372-wkup-m3" for AM43xx SoCs
+- reg:			Should contain the address ranges for the two internal
+			memory regions, UMEM and DMEM. The parent node should
+			provide an appropriate ranges property for properly
+			translating these into bus addresses.
+- reg-names:		Contains the corresponding names for the two memory
+			regions. These should be named "umem" & "dmem".
+- ti,hwmods:		Name of the hwmod associated with the wkupm3 device.
+- ti,pm-firmware:	Name of firmware file to be used for loading and
+			booting the wkup_m3 remote processor.
+
+Example:
+--------
+/* AM33xx */
+ocp {
+	 l4_wkup: l4_wkup@44c00000 {
+		compatible = "am335-l4-wkup", "simple-bus";
+		ranges = <0 0x44c00000 0x400000>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		wkup_m3: wkup_m3@100000 {
+			compatible = "ti,am3352-wkup-m3";
+			reg = <0x100000 0x4000>,
+			      <0x180000 0x2000>;
+			reg-names = "umem", "dmem";
+			ti,hwmods = "wkup_m3";
+			ti,pm-firmware = "am335x-pm-firmware.elf";
+		};
+	};
+
+	...
+};
diff --git a/Documentation/devicetree/bindings/usb/atmel-usb.txt b/Documentation/devicetree/bindings/usb/atmel-usb.txt
index 1be8d7a..5883b73 100644
--- a/Documentation/devicetree/bindings/usb/atmel-usb.txt
+++ b/Documentation/devicetree/bindings/usb/atmel-usb.txt
@@ -79,9 +79,9 @@
 
 Required properties:
  - compatible: Should be one of the following
-	       "at91sam9rl-udc"
-	       "at91sam9g45-udc"
-	       "sama5d3-udc"
+	       "atmel,at91sam9rl-udc"
+	       "atmel,at91sam9g45-udc"
+	       "atmel,sama5d3-udc"
  - reg: Address and length of the register set for the device
  - interrupts: Should contain usba interrupt
  - clocks: Should reference the peripheral and host clocks
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 7b607761..d444757 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -114,6 +114,7 @@
 isil	Intersil
 karo	Ka-Ro electronics GmbH
 keymile	Keymile GmbH
+kinetic Kinetic Technologies
 lacie	LaCie
 lantiq	Lantiq Semiconductor
 lenovo	Lenovo Group Ltd.
@@ -226,4 +227,5 @@
 xlnx	Xilinx
 zyxel	ZyXEL Communications Corp.
 zarlink	Zarlink Semiconductor
+zii	Zodiac Inflight Innovations
 zte	ZTE Corp.
diff --git a/Documentation/devicetree/bindings/watchdog/digicolor-wdt.txt b/Documentation/devicetree/bindings/watchdog/digicolor-wdt.txt
new file mode 100644
index 0000000..a882967
--- /dev/null
+++ b/Documentation/devicetree/bindings/watchdog/digicolor-wdt.txt
@@ -0,0 +1,25 @@
+Conexant Digicolor SoCs Watchdog timer
+
+The watchdog functionality in Conexant Digicolor SoCs relies on the so called
+"Agent Communication" block. This block includes the eight programmable system
+timer counters. The first timer (called "Timer A") is the only one that can be
+used as watchdog.
+
+Required properties:
+
+- compatible : Should be "cnxt,cx92755-wdt"
+- reg : Specifies base physical address and size of the registers
+- clocks : phandle; specifies the clock that drives the timer
+
+Optional properties:
+
+- timeout-sec : Contains the watchdog timeout in seconds
+
+Example:
+
+	watchdog@f0000fc0 {
+		compatible = "cnxt,cx92755-wdt";
+		reg = <0xf0000fc0 0x8>;
+		clocks = <&main_clk>;
+		timeout-sec = <15>;
+	};
diff --git a/Documentation/devicetree/bindings/watchdog/omap-wdt.txt b/Documentation/devicetree/bindings/watchdog/omap-wdt.txt
index c227970..1fa20e4 100644
--- a/Documentation/devicetree/bindings/watchdog/omap-wdt.txt
+++ b/Documentation/devicetree/bindings/watchdog/omap-wdt.txt
@@ -1,10 +1,11 @@
 TI Watchdog Timer (WDT) Controller for OMAP
 
 Required properties:
-compatible:
-- "ti,omap3-wdt" for OMAP3
-- "ti,omap4-wdt" for OMAP4
-- ti,hwmods: Name of the hwmod associated to the WDT
+- compatible : "ti,omap3-wdt" for OMAP3 or "ti,omap4-wdt" for OMAP4
+- ti,hwmods : Name of the hwmod associated to the WDT
+
+Optional properties:
+- timeout-sec : default watchdog timeout in seconds
 
 Examples:
 
diff --git a/Documentation/filesystems/caching/backend-api.txt b/Documentation/filesystems/caching/backend-api.txt
index 277d1e8..c0bd567 100644
--- a/Documentation/filesystems/caching/backend-api.txt
+++ b/Documentation/filesystems/caching/backend-api.txt
@@ -676,6 +676,29 @@
      as possible.
 
 
+ (*) Indicate that a stale object was found and discarded:
+
+	void fscache_object_retrying_stale(struct fscache_object *object);
+
+     This is called to indicate that the lookup procedure found an object in
+     the cache that the netfs decided was stale.  The object has been
+     discarded from the cache and the lookup will be performed again.
+
+
+ (*) Indicate that the caching backend killed an object:
+
+	void fscache_object_mark_killed(struct fscache_object *object,
+					enum fscache_why_object_killed why);
+
+     This is called to indicate that the cache backend preemptively killed an
+     object.  The why parameter should be set to indicate the reason:
+
+	FSCACHE_OBJECT_IS_STALE - the object was stale and needs discarding.
+	FSCACHE_OBJECT_NO_SPACE - there was insufficient cache space
+	FSCACHE_OBJECT_WAS_RETIRED - the object was retired when relinquished.
+	FSCACHE_OBJECT_WAS_CULLED - the object was culled to make space.
+
+
  (*) Get and release references on a retrieval record:
 
 	void fscache_get_retrieval(struct fscache_retrieval *op);
diff --git a/Documentation/filesystems/caching/fscache.txt b/Documentation/filesystems/caching/fscache.txt
index 770267a..50f0a57 100644
--- a/Documentation/filesystems/caching/fscache.txt
+++ b/Documentation/filesystems/caching/fscache.txt
@@ -284,8 +284,9 @@
 		enq=N	Number of times async ops queued for processing
 		can=N	Number of async ops cancelled
 		rej=N	Number of async ops rejected due to object lookup/create failure
+		ini=N	Number of async ops initialised
 		dfr=N	Number of async ops queued for deferred release
-		rel=N	Number of async ops released
+		rel=N	Number of async ops released (should equal ini=N when idle)
 		gc=N	Number of deferred-release async ops garbage collected
 	CacheOp	alo=N	Number of in-progress alloc_object() cache ops
 		luo=N	Number of in-progress lookup_object() cache ops
@@ -303,6 +304,10 @@
 		wrp=N	Number of in-progress write_page() cache ops
 		ucp=N	Number of in-progress uncache_page() cache ops
 		dsp=N	Number of in-progress dissociate_pages() cache ops
+	CacheEv	nsp=N	Number of object lookups/creations rejected due to lack of space
+		stl=N	Number of stale objects deleted
+		rtr=N	Number of objects retired when relinquished
+		cul=N	Number of objects culled
 
 
  (*) /proc/fs/fscache/histogram
diff --git a/Documentation/filesystems/dax.txt b/Documentation/filesystems/dax.txt
index baf4111..7af2851 100644
--- a/Documentation/filesystems/dax.txt
+++ b/Documentation/filesystems/dax.txt
@@ -18,8 +18,10 @@
 -----
 
 If you have a block device which supports DAX, you can make a filesystem
-on it as usual.  When mounting it, use the -o dax option manually
-or add 'dax' to the options in /etc/fstab.
+on it as usual.  The DAX code currently only supports files with a block
+size equal to your kernel's PAGE_SIZE, so you may need to specify a block
+size when creating the filesystem.  When mounting it, use the "-o dax"
+option on the command line or add 'dax' to the options in /etc/fstab.
 
 
 Implementation Tips for Block Driver Writers
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index 68f1c91..f24d1b8 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -500,3 +500,7 @@
 	dentry,  it does not get nameidata at all and it gets called only when cookie
 	is non-NULL.  Note that link body isn't available anymore, so if you need it,
 	store it as cookie.
+--
+[mandatory]
+	__fd_install() & fd_install() can now sleep. Callers should not
+	hold a spinlock	or other resources that do not allow a schedule.
diff --git a/Documentation/hwmon/submitting-patches b/Documentation/hwmon/submitting-patches
index 3d1bac39..d201828 100644
--- a/Documentation/hwmon/submitting-patches
+++ b/Documentation/hwmon/submitting-patches
@@ -81,6 +81,13 @@
 
 * Provide a detect function if and only if a chip can be detected reliably.
 
+* Only the following I2C addresses shall be probed: 0x18-0x1f, 0x28-0x2f,
+  0x48-0x4f, 0x58, 0x5c, 0x73 and 0x77. Probing other addresses is strongly
+  discouraged as it is known to cause trouble with other (non-hwmon) I2C
+  chips. If your chip lives at an address which can't be probed then the
+  device will have to be instantiated explicitly (which is always better
+  anyway.)
+
 * Avoid writing to chip registers in the detect function. If you have to write,
   only do it after you have already gathered enough data to be certain that the
   detection is going to be successful.
diff --git a/Documentation/hwmon/w83792d b/Documentation/hwmon/w83792d
index 53f7b68..f2ffc40 100644
--- a/Documentation/hwmon/w83792d
+++ b/Documentation/hwmon/w83792d
@@ -8,6 +8,7 @@
     Datasheet: http://www.winbond.com.tw
 
 Author: Shane Huang (Winbond)
+Updated: Roger Lucas
 
 
 Module Parameters
@@ -38,9 +39,16 @@
 The driver implements three temperature sensors, seven fan rotation speed
 sensors, nine voltage sensors, and two automatic fan regulation
 strategies called: Smart Fan I (Thermal Cruise mode) and Smart Fan II.
-Automatic fan control mode is possible only for fan1-fan3. Fan4-fan7 can run
-synchronized with selected fan (fan1-fan3). This functionality and manual PWM
-control for fan4-fan7 is not yet implemented.
+
+The driver also implements up to seven fan control outputs: pwm1-7.  Pwm1-7
+can be configured to PWM output or Analogue DC output via their associated
+pwmX_mode. Outputs pwm4 through pwm7 may or may not be present depending on
+how the W83792AD/D was configured by the BIOS.
+
+Automatic fan control mode is possible only for fan1-fan3.
+
+For all pwmX outputs, a value of 0 means minimum fan speed and a value of
+255 means maximum fan speed.
 
 Temperatures are measured in degrees Celsius and measurement resolution is 1
 degC for temp1 and 0.5 degC for temp2 and temp3. An alarm is triggered when
@@ -157,14 +165,14 @@
 /sys files
 ----------
 
-pwm[1-3] - this file stores PWM duty cycle or DC value (fan speed) in range:
+pwm[1-7] - this file stores PWM duty cycle or DC value (fan speed) in range:
 	0 (stop) to 255 (full)
 pwm[1-3]_enable - this file controls mode of fan/temperature control:
             * 0 Disabled
             * 1 Manual mode
             * 2 Smart Fan II
             * 3 Thermal Cruise
-pwm[1-3]_mode - Select PWM of DC mode
+pwm[1-7]_mode - Select PWM or DC mode
             * 0 DC
             * 1 PWM
 thermal_cruise[1-3] - Selects the desired temperature for cruise (degC)
diff --git a/Documentation/hwspinlock.txt b/Documentation/hwspinlock.txt
index 62f7d4e..61c1ee9 100644
--- a/Documentation/hwspinlock.txt
+++ b/Documentation/hwspinlock.txt
@@ -48,6 +48,16 @@
      ids for predefined purposes.
      Should be called from a process context (might sleep).
 
+  int of_hwspin_lock_get_id(struct device_node *np, int index);
+   - retrieve the global lock id for an OF phandle-based specific lock.
+     This function provides a means for DT users of a hwspinlock module
+     to get the global lock id of a specific hwspinlock, so that it can
+     be requested using the normal hwspin_lock_request_specific() API.
+     The function returns a lock id number on success, -EPROBE_DEFER if
+     the hwspinlock device is not yet registered with the core, or other
+     error values.
+     Should be called from a process context (might sleep).
+
   int hwspin_lock_free(struct hwspinlock *hwlock);
    - free a previously-assigned hwspinlock; returns 0 on success, or an
      appropriate error code on failure (e.g. -EINVAL if the hwspinlock
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 51f4221..611c522 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -321,6 +321,7 @@
 0xDB	00-0F	drivers/char/mwave/mwavepub.h
 0xDD	00-3F	ZFCP device driver	see drivers/s390/scsi/
 					<mailto:aherrman@de.ibm.com>
+0xE5	00-3F	linux/fuse.h
 0xEC	00-01	drivers/platform/chrome/cros_ec_dev.h	ChromeOS EC driver
 0xF3	00-3F	drivers/usb/misc/sisusbvga/sisusb.h	sisfb (in development)
 					<mailto:thomas@winischhofer.net>
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index afe7e2b..1d6f045 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -293,6 +293,12 @@
 	acpi_os_name=	[HW,ACPI] Tell ACPI BIOS the name of the OS
 			Format: To spoof as Windows 98: ="Microsoft Windows"
 
+	acpi_rev_override [ACPI] Override the _REV object to return 5 (instead
+			of 2 which is mandated by ACPI 6) as the supported ACPI
+			specification revision (when using this switch, it may
+			be necessary to carry out a cold reboot _twice_ in a
+			row to make it take effect on the platform firmware).
+
 	acpi_osi=	[HW,ACPI] Modify list of supported OS interface strings
 			acpi_osi="string1"	# add string1
 			acpi_osi="!string2"	# remove string2
diff --git a/Documentation/leds/leds-class-flash.txt b/Documentation/leds/leds-class-flash.txt
index 19bb673..8da3c6f 100644
--- a/Documentation/leds/leds-class-flash.txt
+++ b/Documentation/leds/leds-class-flash.txt
@@ -20,3 +20,54 @@
 	- max_flash_timeout
 	- flash_strobe
 	- flash_fault
+
+
+V4L2 flash wrapper for flash LEDs
+=================================
+
+A LED subsystem driver can be controlled also from the level of VideoForLinux2
+subsystem. In order to enable this CONFIG_V4L2_FLASH_LED_CLASS symbol has to
+be defined in the kernel config.
+
+The driver must call the v4l2_flash_init function to get registered in the
+V4L2 subsystem. The function takes six arguments:
+- dev       : flash device, e.g. an I2C device
+- of_node   : of_node of the LED, may be NULL if the same as device's
+- fled_cdev : LED flash class device to wrap
+- iled_cdev : LED flash class device representing indicator LED associated with
+	      fled_cdev, may be NULL
+- ops : V4L2 specific ops
+	* external_strobe_set - defines the source of the flash LED strobe -
+		V4L2_CID_FLASH_STROBE control or external source, typically
+		a sensor, which makes it possible to synchronise the flash
+		strobe start with exposure start,
+	* intensity_to_led_brightness and led_brightness_to_intensity - perform
+		enum led_brightness <-> V4L2 intensity conversion in a device
+		specific manner - they can be used for devices with non-linear
+		LED current scale.
+- config : configuration for V4L2 Flash sub-device
+	* dev_name - the name of the media entity, unique in the system,
+	* flash_faults - bitmask of flash faults that the LED flash class
+		device can report; corresponding LED_FAULT* bit definitions are
+		available in <linux/led-class-flash.h>,
+	* torch_intensity - constraints for the LED in TORCH mode
+		in microamperes,
+	* indicator_intensity - constraints for the indicator LED
+		in microamperes,
+	* has_external_strobe - determines whether the flash strobe source
+		can be switched to external,
+
+On remove the v4l2_flash_release function has to be called, which takes one
+argument - struct v4l2_flash pointer returned previously by v4l2_flash_init.
+This function can be safely called with NULL or error pointer argument.
+
+Please refer to drivers/leds/leds-max77693.c for an exemplary usage of the
+v4l2 flash wrapper.
+
+Once the V4L2 sub-device is registered by the driver which created the Media
+controller device, the sub-device node acts just as a node of a native V4L2
+flash API device would. The calls are simply routed to the LED flash API.
+
+Opening the V4L2 flash sub-device makes the LED subsystem sysfs interface
+unavailable. The interface is re-enabled after the V4L2 flash sub-device
+is closed.
diff --git a/Documentation/leds/leds-lp5523.txt b/Documentation/leds/leds-lp5523.txt
index 5b3e91d4..0dbbd27 100644
--- a/Documentation/leds/leds-lp5523.txt
+++ b/Documentation/leds/leds-lp5523.txt
@@ -49,6 +49,36 @@
 2) Firmware interface - LP55xx common interface
   For the details, please refer to 'firmware' section in leds-lp55xx.txt
 
+LP5523 has three master faders. If a channel is mapped to one of
+the master faders, its output is dimmed based on the value of the master
+fader.
+
+For example,
+
+  echo "123000123" > master_fader_leds
+
+creates the following channel-fader mappings:
+
+  channel 0,6 to master_fader1
+  channel 1,7 to master_fader2
+  channel 2,8 to master_fader3
+
+Then, to have 25% of the original output on channel 0,6:
+
+  echo 64 > master_fader1
+
+To have 0% of the original output (i.e. no output) channel 1,7:
+
+  echo 0 > master_fader2
+
+To have 100% of the original output (i.e. no dimming) on channel 2,8:
+
+  echo 255 > master_fader3
+
+To clear all master fader controls:
+
+  echo "000000000" > master_fader_leds
+
 Selftest uses always the current from the platform data.
 
 Each channel contains led current settings.
diff --git a/Documentation/ntb.txt b/Documentation/ntb.txt
new file mode 100644
index 0000000..1d9bbab
--- /dev/null
+++ b/Documentation/ntb.txt
@@ -0,0 +1,127 @@
+# NTB Drivers
+
+NTB (Non-Transparent Bridge) is a type of PCI-Express bridge chip that connects
+the separate memory systems of two computers to the same PCI-Express fabric.
+Existing NTB hardware supports a common feature set, including scratchpad
+registers, doorbell registers, and memory translation windows.  Scratchpad
+registers are read-and-writable registers that are accessible from either side
+of the device, so that peers can exchange a small amount of information at a
+fixed address.  Doorbell registers provide a way for peers to send interrupt
+events.  Memory windows allow translated read and write access to the peer
+memory.
+
+## NTB Core Driver (ntb)
+
+The NTB core driver defines an api wrapping the common feature set, and allows
+clients interested in NTB features to discover NTB the devices supported by
+hardware drivers.  The term "client" is used here to mean an upper layer
+component making use of the NTB api.  The term "driver," or "hardware driver,"
+is used here to mean a driver for a specific vendor and model of NTB hardware.
+
+## NTB Client Drivers
+
+NTB client drivers should register with the NTB core driver.  After
+registering, the client probe and remove functions will be called appropriately
+as ntb hardware, or hardware drivers, are inserted and removed.  The
+registration uses the Linux Device framework, so it should feel familiar to
+anyone who has written a pci driver.
+
+### NTB Transport Client (ntb\_transport) and NTB Netdev (ntb\_netdev)
+
+The primary client for NTB is the Transport client, used in tandem with NTB
+Netdev.  These drivers function together to create a logical link to the peer,
+across the ntb, to exchange packets of network data.  The Transport client
+establishes a logical link to the peer, and creates queue pairs to exchange
+messages and data.  The NTB Netdev then creates an ethernet device using a
+Transport queue pair.  Network data is copied between socket buffers and the
+Transport queue pair buffer.  The Transport client may be used for other things
+besides Netdev, however no other applications have yet been written.
+
+### NTB Ping Pong Test Client (ntb\_pingpong)
+
+The Ping Pong test client serves as a demonstration to exercise the doorbell
+and scratchpad registers of NTB hardware, and as an example simple NTB client.
+Ping Pong enables the link when started, waits for the NTB link to come up, and
+then proceeds to read and write the doorbell scratchpad registers of the NTB.
+The peers interrupt each other using a bit mask of doorbell bits, which is
+shifted by one in each round, to test the behavior of multiple doorbell bits
+and interrupt vectors.  The Ping Pong driver also reads the first local
+scratchpad, and writes the value plus one to the first peer scratchpad, each
+round before writing the peer doorbell register.
+
+Module Parameters:
+
+* unsafe - Some hardware has known issues with scratchpad and doorbell
+	registers.  By default, Ping Pong will not attempt to exercise such
+	hardware.  You may override this behavior at your own risk by setting
+	unsafe=1.
+* delay\_ms - Specify the delay between receiving a doorbell
+	interrupt event and setting the peer doorbell register for the next
+	round.
+* init\_db - Specify the doorbell bits to start new series of rounds.  A new
+	series begins once all the doorbell bits have been shifted out of
+	range.
+* dyndbg - It is suggested to specify dyndbg=+p when loading this module, and
+	then to observe debugging output on the console.
+
+### NTB Tool Test Client (ntb\_tool)
+
+The Tool test client serves for debugging, primarily, ntb hardware and drivers.
+The Tool provides access through debugfs for reading, setting, and clearing the
+NTB doorbell, and reading and writing scratchpads.
+
+The Tool does not currently have any module parameters.
+
+Debugfs Files:
+
+* *debugfs*/ntb\_tool/*hw*/ - A directory in debugfs will be created for each
+	NTB device probed by the tool.  This directory is shortened to *hw*
+	below.
+* *hw*/db - This file is used to read, set, and clear the local doorbell.  Not
+	all operations may be supported by all hardware.  To read the doorbell,
+	read the file.  To set the doorbell, write `s` followed by the bits to
+	set (eg: `echo 's 0x0101' > db`).  To clear the doorbell, write `c`
+	followed by the bits to clear.
+* *hw*/mask - This file is used to read, set, and clear the local doorbell mask.
+	See *db* for details.
+* *hw*/peer\_db - This file is used to read, set, and clear the peer doorbell.
+	See *db* for details.
+* *hw*/peer\_mask - This file is used to read, set, and clear the peer doorbell
+	mask.  See *db* for details.
+* *hw*/spad - This file is used to read and write local scratchpads.  To read
+	the values of all scratchpads, read the file.  To write values, write a
+	series of pairs of scratchpad number and value
+	(eg: `echo '4 0x123 7 0xabc' > spad`
+	# to set scratchpads `4` and `7` to `0x123` and `0xabc`, respectively).
+* *hw*/peer\_spad - This file is used to read and write peer scratchpads.  See
+	*spad* for details.
+
+## NTB Hardware Drivers
+
+NTB hardware drivers should register devices with the NTB core driver.  After
+registering, clients probe and remove functions will be called.
+
+### NTB Intel Hardware Driver (ntb\_hw\_intel)
+
+The Intel hardware driver supports NTB on Xeon and Atom CPUs.
+
+Module Parameters:
+
+* b2b\_mw\_idx - If the peer ntb is to be accessed via a memory window, then use
+	this memory window to access the peer ntb.  A value of zero or positive
+	starts from the first mw idx, and a negative value starts from the last
+	mw idx.  Both sides MUST set the same value here!  The default value is
+	`-1`.
+* b2b\_mw\_share - If the peer ntb is to be accessed via a memory window, and if
+	the memory window is large enough, still allow the client to use the
+	second half of the memory window for address translation to the peer.
+* xeon\_b2b\_usd\_bar2\_addr64 - If using B2B topology on Xeon hardware, use
+	this 64 bit address on the bus between the NTB devices for the window
+	at BAR2, on the upstream side of the link.
+* xeon\_b2b\_usd\_bar4\_addr64 - See *xeon\_b2b\_bar2\_addr64*.
+* xeon\_b2b\_usd\_bar4\_addr32 - See *xeon\_b2b\_bar2\_addr64*.
+* xeon\_b2b\_usd\_bar5\_addr32 - See *xeon\_b2b\_bar2\_addr64*.
+* xeon\_b2b\_dsd\_bar2\_addr64 - See *xeon\_b2b\_bar2\_addr64*.
+* xeon\_b2b\_dsd\_bar4\_addr64 - See *xeon\_b2b\_bar2\_addr64*.
+* xeon\_b2b\_dsd\_bar4\_addr32 - See *xeon\_b2b\_bar2\_addr64*.
+* xeon\_b2b\_dsd\_bar5\_addr32 - See *xeon\_b2b\_bar2\_addr64*.
diff --git a/Documentation/remoteproc.txt b/Documentation/remoteproc.txt
index e6469fd..ef0219f 100644
--- a/Documentation/remoteproc.txt
+++ b/Documentation/remoteproc.txt
@@ -51,6 +51,12 @@
         rproc_shutdown() returns, and users can still use it with a subsequent
         rproc_boot(), if needed.
 
+  struct rproc *rproc_get_by_phandle(phandle phandle)
+    - Find an rproc handle using a device tree phandle. Returns the rproc
+      handle on success, and NULL on failure. This function increments
+      the remote processor's refcount, so always use rproc_put() to
+      decrement it back once rproc isn't needed anymore.
+
 3. Typical usage
 
 #include <linux/remoteproc.h>
diff --git a/Documentation/target/tcm_mod_builder.py b/Documentation/target/tcm_mod_builder.py
index 6085e1f..949de19 100755
--- a/Documentation/target/tcm_mod_builder.py
+++ b/Documentation/target/tcm_mod_builder.py
@@ -50,15 +50,6 @@
 	buf = "#define " + fabric_mod_name.upper() + "_VERSION	\"v0.1\"\n"
 	buf += "#define " + fabric_mod_name.upper() + "_NAMELEN	32\n"
 	buf += "\n"
-	buf += "struct " + fabric_mod_name + "_nacl {\n"
-	buf += "	/* Binary World Wide unique Port Name for FC Initiator Nport */\n"
-	buf += "	u64 nport_wwpn;\n"
-	buf += "	/* ASCII formatted WWPN for FC Initiator Nport */\n"
-	buf += "	char nport_name[" + fabric_mod_name.upper() + "_NAMELEN];\n"
-	buf += "	/* Returned by " + fabric_mod_name + "_make_nodeacl() */\n"
-	buf += "	struct se_node_acl se_node_acl;\n"
-	buf += "};\n"
-	buf += "\n"
 	buf += "struct " + fabric_mod_name + "_tpg {\n"
 	buf += "	/* FC lport target portal group tag for TCM */\n"
 	buf += "	u16 lport_tpgt;\n"
@@ -69,8 +60,6 @@
 	buf += "};\n"
 	buf += "\n"
 	buf += "struct " + fabric_mod_name + "_lport {\n"
-	buf += "	/* SCSI protocol the lport is providing */\n"
-	buf += "	u8 lport_proto_id;\n"
 	buf += "	/* Binary World Wide unique Port Name for FC Target Lport */\n"
 	buf += "	u64 lport_wwpn;\n"
 	buf += "	/* ASCII formatted WWPN for FC Target Lport */\n"
@@ -105,14 +94,6 @@
 	buf = "#define " + fabric_mod_name.upper() + "_VERSION  \"v0.1\"\n"
 	buf += "#define " + fabric_mod_name.upper() + "_NAMELEN 32\n"
 	buf += "\n"
-	buf += "struct " + fabric_mod_name + "_nacl {\n"
-	buf += "	/* Binary World Wide unique Port Name for SAS Initiator port */\n"
-	buf += "	u64 iport_wwpn;\n"
-	buf += "	/* ASCII formatted WWPN for Sas Initiator port */\n"
-	buf += "	char iport_name[" + fabric_mod_name.upper() + "_NAMELEN];\n"
-	buf += "	/* Returned by " + fabric_mod_name + "_make_nodeacl() */\n"
-	buf += "	struct se_node_acl se_node_acl;\n"
-	buf += "};\n\n"
 	buf += "struct " + fabric_mod_name + "_tpg {\n"
 	buf += "	/* SAS port target portal group tag for TCM */\n"
 	buf += "	u16 tport_tpgt;\n"
@@ -122,8 +103,6 @@
 	buf += "	struct se_portal_group se_tpg;\n"
 	buf += "};\n\n"
 	buf += "struct " + fabric_mod_name + "_tport {\n"
-	buf += "	/* SCSI protocol the tport is providing */\n"
-	buf += "	u8 tport_proto_id;\n"
 	buf += "	/* Binary World Wide unique Port Name for SAS Target port */\n"
 	buf += "	u64 tport_wwpn;\n"
 	buf += "	/* ASCII formatted WWPN for SAS Target port */\n"
@@ -158,12 +137,6 @@
 	buf = "#define " + fabric_mod_name.upper() + "_VERSION  \"v0.1\"\n"
 	buf += "#define " + fabric_mod_name.upper() + "_NAMELEN 32\n"
 	buf += "\n"
-	buf += "struct " + fabric_mod_name + "_nacl {\n"
-	buf += "	/* ASCII formatted InitiatorName */\n"
-	buf += "	char iport_name[" + fabric_mod_name.upper() + "_NAMELEN];\n"
-	buf += "	/* Returned by " + fabric_mod_name + "_make_nodeacl() */\n"
-	buf += "	struct se_node_acl se_node_acl;\n"
-	buf += "};\n\n"
 	buf += "struct " + fabric_mod_name + "_tpg {\n"
 	buf += "	/* iSCSI target portal group tag for TCM */\n"
 	buf += "	u16 tport_tpgt;\n"
@@ -173,8 +146,6 @@
 	buf += "	struct se_portal_group se_tpg;\n"
 	buf += "};\n\n"
 	buf += "struct " + fabric_mod_name + "_tport {\n"
-	buf += "	/* SCSI protocol the tport is providing */\n"
-	buf += "	u8 tport_proto_id;\n"
 	buf += "	/* ASCII formatted TargetName for IQN */\n"
 	buf += "	char tport_name[" + fabric_mod_name.upper() + "_NAMELEN];\n"
 	buf += "	/* Returned by " + fabric_mod_name + "_make_tport() */\n"
@@ -232,61 +203,12 @@
 	buf += "#include <target/target_core_base.h>\n"
 	buf += "#include <target/target_core_fabric.h>\n"
 	buf += "#include <target/target_core_fabric_configfs.h>\n"
-	buf += "#include <target/target_core_configfs.h>\n"
 	buf += "#include <target/configfs_macros.h>\n\n"
 	buf += "#include \"" + fabric_mod_name + "_base.h\"\n"
 	buf += "#include \"" + fabric_mod_name + "_fabric.h\"\n\n"
 
 	buf += "static const struct target_core_fabric_ops " + fabric_mod_name + "_ops;\n\n"
 
-	buf += "static struct se_node_acl *" + fabric_mod_name + "_make_nodeacl(\n"
-	buf += "	struct se_portal_group *se_tpg,\n"
-	buf += "	struct config_group *group,\n"
-	buf += "	const char *name)\n"
-	buf += "{\n"
-	buf += "	struct se_node_acl *se_nacl, *se_nacl_new;\n"
-	buf += "	struct " + fabric_mod_name + "_nacl *nacl;\n"
-
-	if proto_ident == "FC" or proto_ident == "SAS":
-		buf += "	u64 wwpn = 0;\n"
-
-	buf += "	u32 nexus_depth;\n\n"
-	buf += "	/* " + fabric_mod_name + "_parse_wwn(name, &wwpn, 1) < 0)\n"
-	buf += "		return ERR_PTR(-EINVAL); */\n"
-	buf += "	se_nacl_new = " + fabric_mod_name + "_alloc_fabric_acl(se_tpg);\n"
-	buf += "	if (!se_nacl_new)\n"
-	buf += "		return ERR_PTR(-ENOMEM);\n"
-	buf += "//#warning FIXME: Hardcoded nexus depth in " + fabric_mod_name + "_make_nodeacl()\n"
-	buf += "	nexus_depth = 1;\n"
-	buf += "	/*\n"
-	buf += "	 * se_nacl_new may be released by core_tpg_add_initiator_node_acl()\n"
-	buf += "	 * when converting a NodeACL from demo mode -> explict\n"
-	buf += "	 */\n"
-	buf += "	se_nacl = core_tpg_add_initiator_node_acl(se_tpg, se_nacl_new,\n"
-	buf += "				name, nexus_depth);\n"
-	buf += "	if (IS_ERR(se_nacl)) {\n"
-	buf += "		" + fabric_mod_name + "_release_fabric_acl(se_tpg, se_nacl_new);\n"
-	buf += "		return se_nacl;\n"
-	buf += "	}\n"
-	buf += "	/*\n"
-	buf += "	 * Locate our struct " + fabric_mod_name + "_nacl and set the FC Nport WWPN\n"
-	buf += "	 */\n"
-	buf += "	nacl = container_of(se_nacl, struct " + fabric_mod_name + "_nacl, se_node_acl);\n"
-
-	if proto_ident == "FC" or proto_ident == "SAS":
-		buf += "	nacl->" + fabric_mod_init_port + "_wwpn = wwpn;\n"
-
-	buf += "	/* " + fabric_mod_name + "_format_wwn(&nacl->" + fabric_mod_init_port + "_name[0], " + fabric_mod_name.upper() + "_NAMELEN, wwpn); */\n\n"
-	buf += "	return se_nacl;\n"
-	buf += "}\n\n"
-	buf += "static void " + fabric_mod_name + "_drop_nodeacl(struct se_node_acl *se_acl)\n"
-	buf += "{\n"
-	buf += "	struct " + fabric_mod_name + "_nacl *nacl = container_of(se_acl,\n"
-	buf += "				struct " + fabric_mod_name + "_nacl, se_node_acl);\n"
-	buf += "	core_tpg_del_initiator_node_acl(se_acl->se_tpg, se_acl, 1);\n"
-	buf += "	kfree(nacl);\n"
-	buf += "}\n\n"
-
 	buf += "static struct se_portal_group *" + fabric_mod_name + "_make_tpg(\n"
 	buf += "	struct se_wwn *wwn,\n"
 	buf += "	struct config_group *group,\n"
@@ -309,8 +231,7 @@
 	buf += "	tpg->" + fabric_mod_port + " = " + fabric_mod_port + ";\n"
 	buf += "	tpg->" + fabric_mod_port + "_tpgt = tpgt;\n\n"
 	buf += "	ret = core_tpg_register(&" + fabric_mod_name + "_ops, wwn,\n"
-	buf += "				&tpg->se_tpg, tpg,\n"
-	buf += "				TRANSPORT_TPG_TYPE_NORMAL);\n"
+	buf += "				&tpg->se_tpg, SCSI_PROTOCOL_SAS);\n"
 	buf += "	if (ret < 0) {\n"
 	buf += "		kfree(tpg);\n"
 	buf += "		return NULL;\n"
@@ -372,21 +293,13 @@
 	buf += "static const struct target_core_fabric_ops " + fabric_mod_name + "_ops = {\n"
 	buf += "	.module				= THIS_MODULE,\n"
 	buf += "	.name				= " + fabric_mod_name + ",\n"
-	buf += "	.get_fabric_proto_ident		= " + fabric_mod_name + "_get_fabric_proto_ident,\n"
 	buf += "	.get_fabric_name		= " + fabric_mod_name + "_get_fabric_name,\n"
-	buf += "	.get_fabric_proto_ident		= " + fabric_mod_name + "_get_fabric_proto_ident,\n"
 	buf += "	.tpg_get_wwn			= " + fabric_mod_name + "_get_fabric_wwn,\n"
 	buf += "	.tpg_get_tag			= " + fabric_mod_name + "_get_tag,\n"
-	buf += "	.tpg_get_default_depth		= " + fabric_mod_name + "_get_default_depth,\n"
-	buf += "	.tpg_get_pr_transport_id	= " + fabric_mod_name + "_get_pr_transport_id,\n"
-	buf += "	.tpg_get_pr_transport_id_len	= " + fabric_mod_name + "_get_pr_transport_id_len,\n"
-	buf += "	.tpg_parse_pr_out_transport_id	= " + fabric_mod_name + "_parse_pr_out_transport_id,\n"
 	buf += "	.tpg_check_demo_mode		= " + fabric_mod_name + "_check_false,\n"
 	buf += "	.tpg_check_demo_mode_cache	= " + fabric_mod_name + "_check_true,\n"
 	buf += "	.tpg_check_demo_mode_write_protect = " + fabric_mod_name + "_check_true,\n"
 	buf += "	.tpg_check_prod_mode_write_protect = " + fabric_mod_name + "_check_false,\n"
-	buf += "	.tpg_alloc_fabric_acl		= " + fabric_mod_name + "_alloc_fabric_acl,\n"
-	buf += "	.tpg_release_fabric_acl		= " + fabric_mod_name + "_release_fabric_acl,\n"
 	buf += "	.tpg_get_inst_index		= " + fabric_mod_name + "_tpg_get_inst_index,\n"
 	buf += "	.release_cmd			= " + fabric_mod_name + "_release_cmd,\n"
 	buf += "	.shutdown_session		= " + fabric_mod_name + "_shutdown_session,\n"
@@ -396,7 +309,6 @@
 	buf += "	.write_pending			= " + fabric_mod_name + "_write_pending,\n"
 	buf += "	.write_pending_status		= " + fabric_mod_name + "_write_pending_status,\n"
 	buf += "	.set_default_node_attributes	= " + fabric_mod_name + "_set_default_node_attrs,\n"
-	buf += "	.get_task_tag			= " + fabric_mod_name + "_get_task_tag,\n"
 	buf += "	.get_cmd_state			= " + fabric_mod_name + "_get_cmd_state,\n"
 	buf += "	.queue_data_in			= " + fabric_mod_name + "_queue_data_in,\n"
 	buf += "	.queue_status			= " + fabric_mod_name + "_queue_status,\n"
@@ -409,12 +321,6 @@
 	buf += "	.fabric_drop_wwn		= " + fabric_mod_name + "_drop_" + fabric_mod_port + ",\n"
 	buf += "	.fabric_make_tpg		= " + fabric_mod_name + "_make_tpg,\n"
 	buf += "	.fabric_drop_tpg		= " + fabric_mod_name + "_drop_tpg,\n"
-	buf += "	.fabric_post_link		= NULL,\n"
-	buf += "	.fabric_pre_unlink		= NULL,\n"
-	buf += "	.fabric_make_np			= NULL,\n"
-	buf += "	.fabric_drop_np			= NULL,\n"
-	buf += "	.fabric_make_nodeacl		= " + fabric_mod_name + "_make_nodeacl,\n"
-	buf += "	.fabric_drop_nodeacl		= " + fabric_mod_name + "_drop_nodeacl,\n"
 	buf += "\n"
 	buf += "	.tfc_wwn_attrs			= " + fabric_mod_name + "_wwn_attrs;\n"
 	buf += "};\n\n"
@@ -507,7 +413,6 @@
 	buf += "#include <scsi/scsi_proto.h>\n"
 	buf += "#include <target/target_core_base.h>\n"
 	buf += "#include <target/target_core_fabric.h>\n"
-	buf += "#include <target/target_core_configfs.h>\n\n"
 	buf += "#include \"" + fabric_mod_name + "_base.h\"\n"
 	buf += "#include \"" + fabric_mod_name + "_fabric.h\"\n\n"
 
@@ -539,35 +444,6 @@
 			bufi += "char *" + fabric_mod_name + "_get_fabric_name(void);\n"
 			continue
 
-		if re.search('get_fabric_proto_ident', fo):
-			buf += "u8 " + fabric_mod_name + "_get_fabric_proto_ident(struct se_portal_group *se_tpg)\n"
-			buf += "{\n"
-			buf += "	struct " + fabric_mod_name + "_tpg *tpg = container_of(se_tpg,\n"
-			buf += "				struct " + fabric_mod_name + "_tpg, se_tpg);\n"
-			buf += "	struct " + fabric_mod_name + "_" + fabric_mod_port + " *" + fabric_mod_port + " = tpg->" + fabric_mod_port + ";\n"
-			buf += "	u8 proto_id;\n\n"
-			buf += "	switch (" + fabric_mod_port + "->" + fabric_mod_port + "_proto_id) {\n"
-			if proto_ident == "FC":
-				buf += "	case SCSI_PROTOCOL_FCP:\n"
-				buf += "	default:\n"
-				buf += "		proto_id = fc_get_fabric_proto_ident(se_tpg);\n"
-				buf += "		break;\n"
-			elif proto_ident == "SAS":
-				buf += "	case SCSI_PROTOCOL_SAS:\n"
-				buf += "	default:\n"
-				buf += "		proto_id = sas_get_fabric_proto_ident(se_tpg);\n"
-				buf += "		break;\n"
-			elif proto_ident == "iSCSI":
-				buf += "	case SCSI_PROTOCOL_ISCSI:\n"
-				buf += "	default:\n"
-				buf += "		proto_id = iscsi_get_fabric_proto_ident(se_tpg);\n"
-				buf += "		break;\n"
-
-			buf += "	}\n\n"
-			buf += "	return proto_id;\n"
-			buf += "}\n\n"
-			bufi += "u8 " + fabric_mod_name + "_get_fabric_proto_ident(struct se_portal_group *);\n"
-
 		if re.search('get_wwn', fo):
 			buf += "char *" + fabric_mod_name + "_get_fabric_wwn(struct se_portal_group *se_tpg)\n"
 			buf += "{\n"
@@ -587,150 +463,6 @@
 			buf += "}\n\n"
 			bufi += "u16 " + fabric_mod_name + "_get_tag(struct se_portal_group *);\n"
 
-		if re.search('get_default_depth', fo):
-			buf += "u32 " + fabric_mod_name + "_get_default_depth(struct se_portal_group *se_tpg)\n"
-			buf += "{\n"
-			buf += "	return 1;\n"
-			buf += "}\n\n"
-			bufi += "u32 " + fabric_mod_name + "_get_default_depth(struct se_portal_group *);\n"
-
-		if re.search('get_pr_transport_id\)\(', fo):
-			buf += "u32 " + fabric_mod_name + "_get_pr_transport_id(\n"
-			buf += "	struct se_portal_group *se_tpg,\n"
-			buf += "	struct se_node_acl *se_nacl,\n"
-			buf += "	struct t10_pr_registration *pr_reg,\n"
-			buf += "	int *format_code,\n"
-			buf += "	unsigned char *buf)\n"
-			buf += "{\n"
-			buf += "	struct " + fabric_mod_name + "_tpg *tpg = container_of(se_tpg,\n"
-			buf += "				struct " + fabric_mod_name + "_tpg, se_tpg);\n"
-			buf += "	struct " + fabric_mod_name + "_" + fabric_mod_port + " *" + fabric_mod_port + " = tpg->" + fabric_mod_port + ";\n"
-			buf += "	int ret = 0;\n\n"
-			buf += "	switch (" + fabric_mod_port + "->" + fabric_mod_port + "_proto_id) {\n"
-			if proto_ident == "FC":
-				buf += "	case SCSI_PROTOCOL_FCP:\n"
-				buf += "	default:\n"
-				buf += "		ret = fc_get_pr_transport_id(se_tpg, se_nacl, pr_reg,\n"
-				buf += "					format_code, buf);\n"
-				buf += "		break;\n"
-			elif proto_ident == "SAS":
-				buf += "	case SCSI_PROTOCOL_SAS:\n"
-				buf += "	default:\n"
-				buf += "		ret = sas_get_pr_transport_id(se_tpg, se_nacl, pr_reg,\n"
-				buf += "					format_code, buf);\n"
-				buf += "		break;\n"
-			elif proto_ident == "iSCSI":
-				buf += "	case SCSI_PROTOCOL_ISCSI:\n"
-				buf += "	default:\n"
-				buf += "		ret = iscsi_get_pr_transport_id(se_tpg, se_nacl, pr_reg,\n"
-				buf += "					format_code, buf);\n"
-				buf += "		break;\n"
-
-			buf += "	}\n\n"
-			buf += "	return ret;\n"
-			buf += "}\n\n"
-			bufi += "u32 " + fabric_mod_name + "_get_pr_transport_id(struct se_portal_group *,\n"
-			bufi += "			struct se_node_acl *, struct t10_pr_registration *,\n"
-			bufi += "			int *, unsigned char *);\n"
-
-		if re.search('get_pr_transport_id_len\)\(', fo):
-			buf += "u32 " + fabric_mod_name + "_get_pr_transport_id_len(\n"
-			buf += "	struct se_portal_group *se_tpg,\n"
-			buf += "	struct se_node_acl *se_nacl,\n"
-			buf += "	struct t10_pr_registration *pr_reg,\n"
-			buf += "	int *format_code)\n"
-			buf += "{\n"
-			buf += "	struct " + fabric_mod_name + "_tpg *tpg = container_of(se_tpg,\n"
-			buf += "				struct " + fabric_mod_name + "_tpg, se_tpg);\n"
-			buf += "	struct " + fabric_mod_name + "_" + fabric_mod_port + " *" + fabric_mod_port + " = tpg->" + fabric_mod_port + ";\n"
-			buf += "	int ret = 0;\n\n"
-			buf += "	switch (" + fabric_mod_port + "->" + fabric_mod_port + "_proto_id) {\n"
-			if proto_ident == "FC":
-				buf += "	case SCSI_PROTOCOL_FCP:\n"
-				buf += "	default:\n"
-				buf += "		ret = fc_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,\n"
-				buf += "					format_code);\n"
-				buf += "		break;\n"
-			elif proto_ident == "SAS":
-				buf += "	case SCSI_PROTOCOL_SAS:\n"
-				buf += "	default:\n"
-				buf += "		ret = sas_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,\n"
-				buf += "					format_code);\n"
-				buf += "		break;\n"
-			elif proto_ident == "iSCSI":
-				buf += "	case SCSI_PROTOCOL_ISCSI:\n"
-				buf += "	default:\n"
-				buf += "		ret = iscsi_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,\n"
-				buf += "					format_code);\n"
-				buf += "		break;\n"
-
-
-			buf += "	}\n\n"
-			buf += "	return ret;\n"
-			buf += "}\n\n"
-			bufi += "u32 " + fabric_mod_name + "_get_pr_transport_id_len(struct se_portal_group *,\n"
-			bufi += "			struct se_node_acl *, struct t10_pr_registration *,\n"
-			bufi += "			int *);\n"
-
-		if re.search('parse_pr_out_transport_id\)\(', fo):
-			buf += "char *" + fabric_mod_name + "_parse_pr_out_transport_id(\n"
-			buf += "	struct se_portal_group *se_tpg,\n"
-			buf += "	const char *buf,\n"
-			buf += "	u32 *out_tid_len,\n"
-			buf += "	char **port_nexus_ptr)\n"
-			buf += "{\n"
-			buf += "	struct " + fabric_mod_name + "_tpg *tpg = container_of(se_tpg,\n"
-			buf += "				struct " + fabric_mod_name + "_tpg, se_tpg);\n"
-			buf += "	struct " + fabric_mod_name + "_" + fabric_mod_port + " *" + fabric_mod_port + " = tpg->" + fabric_mod_port + ";\n"
-			buf += "	char *tid = NULL;\n\n"
-			buf += "	switch (" + fabric_mod_port + "->" + fabric_mod_port + "_proto_id) {\n"
-			if proto_ident == "FC":
-				buf += "	case SCSI_PROTOCOL_FCP:\n"
-				buf += "	default:\n"
-				buf += "		tid = fc_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,\n"
-				buf += "					port_nexus_ptr);\n"
-			elif proto_ident == "SAS":
-				buf += "	case SCSI_PROTOCOL_SAS:\n"
-				buf += "	default:\n"
-				buf += "		tid = sas_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,\n"
-				buf += "					port_nexus_ptr);\n"
-			elif proto_ident == "iSCSI":
-				buf += "	case SCSI_PROTOCOL_ISCSI:\n"
-				buf += "	default:\n"
-				buf += "		tid = iscsi_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,\n"
-				buf += "					port_nexus_ptr);\n"
-
-			buf += "	}\n\n"
-			buf += "	return tid;\n"
-			buf += "}\n\n"
-			bufi += "char *" + fabric_mod_name + "_parse_pr_out_transport_id(struct se_portal_group *,\n"
-			bufi +=	"			const char *, u32 *, char **);\n"
-
-		if re.search('alloc_fabric_acl\)\(', fo):
-			buf += "struct se_node_acl *" + fabric_mod_name + "_alloc_fabric_acl(struct se_portal_group *se_tpg)\n"
-			buf += "{\n"
-			buf += "	struct " + fabric_mod_name + "_nacl *nacl;\n\n"
-			buf += "	nacl = kzalloc(sizeof(struct " + fabric_mod_name + "_nacl), GFP_KERNEL);\n"
-			buf += "	if (!nacl) {\n"
-			buf += "		printk(KERN_ERR \"Unable to allocate struct " + fabric_mod_name + "_nacl\\n\");\n"
-			buf += "		return NULL;\n"
-			buf += "	}\n\n"
-			buf += "	return &nacl->se_node_acl;\n"
-			buf += "}\n\n"
-			bufi += "struct se_node_acl *" + fabric_mod_name + "_alloc_fabric_acl(struct se_portal_group *);\n"
-
-		if re.search('release_fabric_acl\)\(', fo):
-			buf += "void " + fabric_mod_name + "_release_fabric_acl(\n"
-			buf += "	struct se_portal_group *se_tpg,\n"
-			buf += "	struct se_node_acl *se_nacl)\n"
-			buf += "{\n"
-			buf += "	struct " + fabric_mod_name + "_nacl *nacl = container_of(se_nacl,\n"
-			buf += "			struct " + fabric_mod_name + "_nacl, se_node_acl);\n"
-			buf += "	kfree(nacl);\n"
-			buf += "}\n\n"
-			bufi += "void " + fabric_mod_name + "_release_fabric_acl(struct se_portal_group *,\n"
-			bufi +=	"			struct se_node_acl *);\n"
-
 		if re.search('tpg_get_inst_index\)\(', fo):
 			buf += "u32 " + fabric_mod_name + "_tpg_get_inst_index(struct se_portal_group *se_tpg)\n"
 			buf += "{\n"
@@ -787,13 +519,6 @@
 			buf += "}\n\n"
 			bufi += "void " + fabric_mod_name + "_set_default_node_attrs(struct se_node_acl *);\n"
 
-		if re.search('get_task_tag\)\(', fo):
-			buf += "u32 " + fabric_mod_name + "_get_task_tag(struct se_cmd *se_cmd)\n"
-			buf += "{\n"
-			buf += "	return 0;\n"
-			buf += "}\n\n"
-			bufi += "u32 " + fabric_mod_name + "_get_task_tag(struct se_cmd *);\n"
-
 		if re.search('get_cmd_state\)\(', fo):
 			buf += "int " + fabric_mod_name + "_get_cmd_state(struct se_cmd *se_cmd)\n"
 			buf += "{\n"
diff --git a/Documentation/target/tcm_mod_builder.txt b/Documentation/target/tcm_mod_builder.txt
index 84533d8..ae22f70 100644
--- a/Documentation/target/tcm_mod_builder.txt
+++ b/Documentation/target/tcm_mod_builder.txt
@@ -13,8 +13,8 @@
 This script will create a new drivers/target/$TCM_NEW_MOD/, and will do the following
 
 	*) Generate new API callers for drivers/target/target_core_fabric_configs.c logic
-	   ->make_nodeacl(), ->drop_nodeacl(), ->make_tpg(), ->drop_tpg()
-	   ->make_wwn(), ->drop_wwn().  These are created into $TCM_NEW_MOD/$TCM_NEW_MOD_configfs.c
+	   ->make_tpg(), ->drop_tpg(), ->make_wwn(), ->drop_wwn().  These are created
+	   into $TCM_NEW_MOD/$TCM_NEW_MOD_configfs.c
 	*) Generate basic infrastructure for loading/unloading LKMs and TCM/ConfigFS fabric module
 	   using a skeleton struct target_core_fabric_ops API template.
 	*) Based on user defined T10 Proto_Ident for the new fabric module being built,
diff --git a/Documentation/target/tcmu-design.txt b/Documentation/target/tcmu-design.txt
index 263b907..bef81e4 100644
--- a/Documentation/target/tcmu-design.txt
+++ b/Documentation/target/tcmu-design.txt
@@ -152,7 +152,7 @@
 are accessible via tht req.iov[] array. iov_cnt contains the number of
 entries in iov[] needed to describe either the Data-In or Data-Out
 buffers. For bidirectional commands, iov_cnt specifies how many iovec
-entries cover the Data-Out area, and iov_bidi_count specifies how many
+entries cover the Data-Out area, and iov_bidi_cnt specifies how many
 iovec entries immediately after that in iov[] cover the Data-In
 area. Just like other fields, iov.iov_base is an offset from the start
 of the region.
diff --git a/Documentation/watchdog/watchdog-kernel-api.txt b/Documentation/watchdog/watchdog-kernel-api.txt
index a0438f3..d8b0d33 100644
--- a/Documentation/watchdog/watchdog-kernel-api.txt
+++ b/Documentation/watchdog/watchdog-kernel-api.txt
@@ -36,6 +36,10 @@
 device. The parameter of this routine is the pointer to the registered
 watchdog_device structure.
 
+The watchdog subsystem includes an registration deferral mechanism,
+which allows you to register an watchdog as early as you wish during
+the boot process.
+
 The watchdog device structure looks like this:
 
 struct watchdog_device {
@@ -52,6 +56,7 @@
 	void *driver_data;
 	struct mutex lock;
 	unsigned long status;
+	struct list_head deferred;
 };
 
 It contains following fields:
@@ -80,6 +85,8 @@
   information about the status of the device (Like: is the watchdog timer
   running/active, is the nowayout bit set, is the device opened via
   the /dev/watchdog interface or not, ...).
+* deferred: entry in wtd_deferred_reg_list which is used to
+  register early initialized watchdogs.
 
 The list of watchdog operations is defined as:
 
diff --git a/Documentation/watchdog/watchdog-parameters.txt b/Documentation/watchdog/watchdog-parameters.txt
index 692791c..9f9ec9f 100644
--- a/Documentation/watchdog/watchdog-parameters.txt
+++ b/Documentation/watchdog/watchdog-parameters.txt
@@ -208,6 +208,9 @@
 -------------------------------------------------
 omap_wdt:
 timer_margin: initial watchdog timeout (in seconds)
+early_enable: Watchdog is started on module insertion (default=0
+nowayout: Watchdog cannot be stopped once started
+	(default=kernel config parameter)
 -------------------------------------------------
 orion_wdt:
 heartbeat: Initial watchdog heartbeat in seconds
diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt
index 7c1f9fa..9da6f35 100644
--- a/Documentation/x86/boot.txt
+++ b/Documentation/x86/boot.txt
@@ -406,7 +406,7 @@
 	- If 0, the protected-mode code is loaded at 0x10000.
 	- If 1, the protected-mode code is loaded at 0x100000.
 
-  Bit 1 (kernel internal): ALSR_FLAG
+  Bit 1 (kernel internal): KASLR_FLAG
 	- Used internally by the compressed kernel to communicate
 	  KASLR status to kernel proper.
 	  If 1, KASLR enabled.
diff --git a/Documentation/x86/entry_64.txt b/Documentation/x86/entry_64.txt
index 33884d1..c1df8eb 100644
--- a/Documentation/x86/entry_64.txt
+++ b/Documentation/x86/entry_64.txt
@@ -1,14 +1,14 @@
 This file documents some of the kernel entries in
-arch/x86/kernel/entry_64.S.  A lot of this explanation is adapted from
+arch/x86/entry/entry_64.S.  A lot of this explanation is adapted from
 an email from Ingo Molnar:
 
 http://lkml.kernel.org/r/<20110529191055.GC9835%40elte.hu>
 
 The x86 architecture has quite a few different ways to jump into
 kernel code.  Most of these entry points are registered in
-arch/x86/kernel/traps.c and implemented in arch/x86/kernel/entry_64.S
-for 64-bit, arch/x86/kernel/entry_32.S for 32-bit and finally
-arch/x86/ia32/ia32entry.S which implements the 32-bit compatibility
+arch/x86/kernel/traps.c and implemented in arch/x86/entry/entry_64.S
+for 64-bit, arch/x86/entry/entry_32.S for 32-bit and finally
+arch/x86/entry/entry_64_compat.S which implements the 32-bit compatibility
 syscall entry points and thus provides for 32-bit processes the
 ability to execute syscalls when running on 64-bit kernels.
 
diff --git a/Kbuild b/Kbuild
index df99a5f..f55cefd 100644
--- a/Kbuild
+++ b/Kbuild
@@ -52,7 +52,6 @@
 
 timeconst-file := include/generated/timeconst.h
 
-#always  += $(timeconst-file)
 targets += $(timeconst-file)
 
 quiet_cmd_gentimeconst = GEN     $@
diff --git a/MAINTAINERS b/MAINTAINERS
index 0e6b091..8133cef 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2026,10 +2026,10 @@
 F:	drivers/net/hamradio/baycom*
 
 BCACHE (BLOCK LAYER CACHE)
-M:	Kent Overstreet <kmo@daterainc.com>
+M:	Kent Overstreet <kent.overstreet@gmail.com>
 L:	linux-bcache@vger.kernel.org
 W:	http://bcache.evilpiepirate.org
-S:	Maintained:
+S:	Maintained
 F:	drivers/md/bcache/
 
 BDISP ST MEDIA DRIVER
@@ -2280,7 +2280,7 @@
 F:	arch/mips/bmips/*
 F:	arch/mips/include/asm/mach-bmips/*
 F:	arch/mips/kernel/*bmips*
-F:	arch/mips/boot/dts/bcm*.dts*
+F:	arch/mips/boot/dts/brcm/bcm*.dts*
 F:	drivers/irqchip/irq-bcm7*
 F:	drivers/irqchip/irq-brcmstb*
 
@@ -2339,7 +2339,7 @@
 L:	bcm-kernel-feedback-list@broadcom.com
 S:	Supported
 F:	drivers/gpio/gpio-bcm-kona.c
-F:	Documentation/devicetree/bindings/gpio/gpio-bcm-kona.txt
+F:	Documentation/devicetree/bindings/gpio/brcm,kona-gpio.txt
 
 BROADCOM NVRAM DRIVER
 M:	Rafał Miłecki <zajec5@gmail.com>
@@ -2763,7 +2763,7 @@
 F:	drivers/media/platform/coda/
 
 COMMON CLK FRAMEWORK
-M:	Mike Turquette <mturquette@linaro.org>
+M:	Michael Turquette <mturquette@baylibre.com>
 M:	Stephen Boyd <sboyd@codeaurora.org>
 L:	linux-clk@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux.git
@@ -3216,6 +3216,11 @@
 S:	Maintained
 F:	drivers/platform/x86/dell-laptop.c
 
+DELL LAPTOP RBTN DRIVER
+M:	Pali Rohár <pali.rohar@gmail.com>
+S:	Maintained
+F:	drivers/platform/x86/dell-rbtn.*
+
 DELL LAPTOP FREEFALL DRIVER
 M:	Pali Rohár <pali.rohar@gmail.com>
 S:	Maintained
@@ -4425,9 +4430,11 @@
 M:	Miklos Szeredi <miklos@szeredi.hu>
 L:	fuse-devel@lists.sourceforge.net
 W:	http://fuse.sourceforge.net/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse.git
 S:	Maintained
 F:	fs/fuse/
 F:	include/uapi/linux/fuse.h
+F:	Documentation/filesystems/fuse.txt
 
 FUTURE DOMAIN TMC-16x0 SCSI DRIVER (16-bit)
 M:	Rik Faith <faith@cs.unc.edu>
@@ -5285,11 +5292,10 @@
 M:	Jie Yang <yang.jie@linux.intel.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 S:	Supported
-F:	sound/soc/intel/sst-haswell*
-F:	sound/soc/intel/sst-dsp*
-F:	sound/soc/intel/sst-firmware.c
-F:	sound/soc/intel/broadwell.c
-F:	sound/soc/intel/haswell.c
+F:	sound/soc/intel/common/sst-dsp*
+F:	sound/soc/intel/common/sst-firmware.c
+F:	sound/soc/intel/boards/broadwell.c
+F:	sound/soc/intel/haswell/
 
 INTEL C600 SERIES SAS CONTROLLER DRIVER
 M:	Intel SCU Linux support <intel-linux-scu@intel.com>
@@ -5464,6 +5470,13 @@
 F:	drivers/misc/mei/*
 F:	Documentation/misc-devices/mei/*
 
+INTEL PMC IPC DRIVER
+M:	Zha Qipeng<qipeng.zha@intel.com>
+L:	platform-driver-x86@vger.kernel.org
+S:	Maintained
+F:	drivers/platform/x86/intel_pmc_ipc.c
+F:	arch/x86/include/asm/intel_pmc_ipc.h
+
 IOC3 ETHERNET DRIVER
 M:	Ralf Baechle <ralf@linux-mips.org>
 L:	linux-mips@linux-mips.org
@@ -6787,9 +6800,8 @@
 F:	drivers/platform/x86/msi-laptop.c
 
 MSI WMI SUPPORT
-M:	Anisse Astier <anisse@astier.eu>
 L:	platform-driver-x86@vger.kernel.org
-S:	Supported
+S:	Orphan
 F:	drivers/platform/x86/msi-wmi.c
 
 MSI001 MEDIA DRIVER
@@ -7019,7 +7031,6 @@
 T:	git git://git.pengutronix.de/git/mpa/linux-nbd.git
 F:	Documentation/blockdev/nbd.txt
 F:	drivers/block/nbd.c
-F:	include/linux/nbd.h
 F:	include/uapi/linux/nbd.h
 
 NETWORK DROP MONITOR
@@ -7208,15 +7219,25 @@
 F:	drivers/power/isp1704_charger.c
 F:	drivers/power/rx51_battery.c
 
-NTB DRIVER
+NTB DRIVER CORE
 M:	Jon Mason <jdmason@kudzu.us>
 M:	Dave Jiang <dave.jiang@intel.com>
+M:	Allen Hubbe <Allen.Hubbe@emc.com>
 S:	Supported
 W:	https://github.com/jonmason/ntb/wiki
 T:	git git://github.com/jonmason/ntb.git
 F:	drivers/ntb/
 F:	drivers/net/ntb_netdev.c
 F:	include/linux/ntb.h
+F:	include/linux/ntb_transport.h
+
+NTB INTEL DRIVER
+M:	Jon Mason <jdmason@kudzu.us>
+M:	Dave Jiang <dave.jiang@intel.com>
+S:	Supported
+W:	https://github.com/jonmason/ntb/wiki
+T:	git git://github.com/jonmason/ntb.git
+F:	drivers/ntb/hw/intel/
 
 NTFS FILESYSTEM
 M:	Anton Altaparmakov <anton@tuxera.com>
@@ -7360,7 +7381,6 @@
 L:	linux-omap@vger.kernel.org
 S:	Maintained
 F:	drivers/hwspinlock/omap_hwspinlock.c
-F:	arch/arm/mach-omap2/hwspinlock.c
 
 OMAP MMC SUPPORT
 M:	Jarkko Lavinen <jarkko.lavinen@nokia.com>
@@ -7647,7 +7667,6 @@
 PARIDE DRIVERS FOR PARALLEL PORT IDE DEVICES
 M:	Tim Waugh <tim@cyberelk.net>
 L:	linux-parport@lists.infradead.org (subscribers-only)
-W:	http://www.torque.net/linux-pp.html
 S:	Maintained
 F:	Documentation/blockdev/paride.txt
 F:	drivers/block/paride/
@@ -9091,9 +9110,9 @@
 F:	drivers/net/ethernet/emulex/benet/
 
 EMULEX ONECONNECT ROCE DRIVER
-M:	Selvin Xavier <selvin.xavier@emulex.com>
-M:	Devesh Sharma <devesh.sharma@emulex.com>
-M:	Mitesh Ahuja <mitesh.ahuja@emulex.com>
+M:	Selvin Xavier <selvin.xavier@avagotech.com>
+M:	Devesh Sharma <devesh.sharma@avagotech.com>
+M:	Mitesh Ahuja <mitesh.ahuja@avagotech.com>
 L:	linux-rdma@vger.kernel.org
 W:	http://www.emulex.com
 S:	Supported
@@ -9593,7 +9612,6 @@
 
 SPIDERNET NETWORK DRIVER for CELL
 M:	Ishizaki Kou <kou.ishizaki@toshiba.co.jp>
-M:	Jens Osterkamp <jens@de.ibm.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	Documentation/networking/spider_net.txt
@@ -9832,6 +9850,13 @@
 F:	Documentation/devicetree/bindings/arc/
 F:	drivers/tty/serial/arc_uart.c
 
+SYNOPSYS ARC SDP platform support
+M:	Alexey Brodkin <abrodkin@synopsys.com>
+S:	Supported
+F:	arch/arc/plat-axs10x
+F:	arch/arc/boot/dts/ax*
+F:	Documentation/devicetree/bindings/arc/axs10*
+
 SYSTEM CONFIGURATION (SYSCON)
 M:	Lee Jones <lee.jones@linaro.org>
 M:	Arnd Bergmann <arnd@arndb.de>
@@ -11347,6 +11372,13 @@
 S:	Maintained
 F:	drivers/net/wireless/zd1211rw/
 
+ZPOOL COMPRESSED PAGE STORAGE API
+M:	Dan Streetman <ddstreet@ieee.org>
+L:	linux-mm@kvack.org
+S:	Maintained
+F:	mm/zpool.c
+F:	include/linux/zpool.h
+
 ZR36067 VIDEO FOR LINUX DRIVER
 L:	mjpeg-users@lists.sourceforge.net
 L:	linux-media@vger.kernel.org
diff --git a/Makefile b/Makefile
index 6c6f146..13270c0 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
-PATCHLEVEL = 1
+PATCHLEVEL = 2
 SUBLEVEL = 0
-EXTRAVERSION =
+EXTRAVERSION = -rc1
 NAME = Hurr durr I'ma sheep
 
 # *DOCUMENTATION*
@@ -335,15 +335,6 @@
 export KBUILD_MODULES KBUILD_BUILTIN
 export KBUILD_CHECKSRC KBUILD_SRC KBUILD_EXTMOD
 
-ifneq ($(CC),)
-ifeq ($(shell $(CC) -v 2>&1 | grep -c "clang version"), 1)
-COMPILER := clang
-else
-COMPILER := gcc
-endif
-export COMPILER
-endif
-
 # We need some generic definitions (do not try to remake the file).
 scripts/Kbuild.include: ;
 include scripts/Kbuild.include
@@ -670,6 +661,13 @@
 endif
 KBUILD_CFLAGS += $(stackp-flag)
 
+ifeq ($(shell $(CC) -v 2>&1 | grep -c "clang version"), 1)
+COMPILER := clang
+else
+COMPILER := gcc
+endif
+export COMPILER
+
 ifeq ($(COMPILER),clang)
 KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,)
 KBUILD_CPPFLAGS += $(call cc-option,-Wno-unknown-warning-option,)
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index df94ac1..e7cee0a 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -81,17 +81,37 @@
 
 menu "ARC Platform/SoC/Board"
 
-source "arch/arc/plat-arcfpga/Kconfig"
+source "arch/arc/plat-sim/Kconfig"
 source "arch/arc/plat-tb10x/Kconfig"
+source "arch/arc/plat-axs10x/Kconfig"
 #New platform adds here
 
 endmenu
 
+choice
+	prompt "ARC Instruction Set"
+	default ISA_ARCOMPACT
+
+config ISA_ARCOMPACT
+	bool "ARCompact ISA"
+	help
+	  The original ARC ISA of ARC600/700 cores
+
+config ISA_ARCV2
+	bool "ARC ISA v2"
+	help
+	  ISA for the Next Generation ARC-HS cores
+
+endchoice
+
 menu "ARC CPU Configuration"
 
 choice
 	prompt "ARC Core"
-	default ARC_CPU_770
+	default ARC_CPU_770 if ISA_ARCOMPACT
+	default ARC_CPU_HS if ISA_ARCV2
+
+if ISA_ARCOMPACT
 
 config ARC_CPU_750D
 	bool "ARC750D"
@@ -100,7 +120,7 @@
 
 config ARC_CPU_770
 	bool "ARC770"
-	select ARC_CPU_REL_4_10
+	select ARC_HAS_SWAPE
 	help
 	  Support for ARC770 core introduced with Rel 4.10 (Summer 2011)
 	  This core has a bunch of cool new features:
@@ -109,6 +129,27 @@
 	  -Caches: New Prog Model, Region Flush
 	  -Insns: endian swap, load-locked/store-conditional, time-stamp-ctr
 
+endif	#ISA_ARCOMPACT
+
+config ARC_CPU_HS
+	bool "ARC-HS"
+	depends on ISA_ARCV2
+	help
+	  Support for ARC HS38x Cores based on ARCv2 ISA
+	  The notable features are:
+	    - SMP configurations of upto 4 core with coherency
+	    - Optional L2 Cache and IO-Coherency
+	    - Revised Interrupt Architecture (multiple priorites, reg banks,
+	        auto stack switch, auto regfile save/restore)
+	    - MMUv4 (PIPT dcache, Huge Pages)
+	    - Instructions for
+		* 64bit load/store: LDD, STD
+		* Hardware assisted divide/remainder: DIV, REM
+		* Function prologue/epilogue: ENTER_S, LEAVE_S
+		* IRQ enable/disable: CLRI, SETI
+		* pop count: FFS, FLS
+		* SETcc, BMSKN, XBFU...
+
 endchoice
 
 config CPU_BIG_ENDIAN
@@ -117,17 +158,13 @@
 	help
 	  Build kernel for Big Endian Mode of ARC CPU
 
-# If a platform can't work with 0x8000_0000 based dma_addr_t
-config ARC_PLAT_NEEDS_CPU_TO_DMA
-	bool
-
 config SMP
-	bool "Symmetric Multi-Processing (Incomplete)"
+	bool "Symmetric Multi-Processing"
 	default n
+	select ARC_HAS_COH_CACHES if ISA_ARCV2
+	select ARC_MCIP if ISA_ARCV2
 	help
-	  This enables support for systems with more than one CPU. If you have
-	  a system with only one CPU, say N. If you have a system with more
-	  than one CPU, say Y.
+	  This enables support for systems with more than one CPU.
 
 if SMP
 
@@ -137,13 +174,20 @@
 config ARC_HAS_REENTRANT_IRQ_LV2
 	def_bool n
 
-endif
+config ARC_MCIP
+	bool "ARConnect Multicore IP (MCIP) Support "
+	depends on ISA_ARCV2
+	help
+	  This IP block enables SMP in ARC-HS38 cores.
+	  It provides for cross-core interrupts, multi-core debug
+	  hardware semaphores, shared memory,....
 
 config NR_CPUS
 	int "Maximum number of CPUs (2-4096)"
 	range 2 4096
-	depends on SMP
-	default "2"
+	default "4"
+
+endif	#SMP
 
 menuconfig ARC_CACHE
 	bool "Enable Cache Support"
@@ -185,7 +229,7 @@
 
 config ARC_CACHE_VIPT_ALIASING
 	bool "Support VIPT Aliasing D$"
-	depends on ARC_HAS_DCACHE
+	depends on ARC_HAS_DCACHE && ISA_ARCOMPACT
 	default n
 
 endif	#ARC_CACHE
@@ -226,9 +270,10 @@
 	  Multipler. Otherwise software multipy lib is used
 
 choice
-	prompt "ARC700 MMU Version"
+	prompt "MMU Version"
 	default ARC_MMU_V3 if ARC_CPU_770
 	default ARC_MMU_V2 if ARC_CPU_750D
+	default ARC_MMU_V4 if ARC_CPU_HS
 
 config ARC_MMU_V1
 	bool "MMU v1"
@@ -249,6 +294,10 @@
 	  Variable Page size (1k-16k), var JTLB size 128 x (2 or 4)
 	  Shared Address Spaces (SASID)
 
+config ARC_MMU_V4
+	bool "MMU v4"
+	depends on ISA_ARCV2
+
 endchoice
 
 
@@ -271,6 +320,8 @@
 
 endchoice
 
+if ISA_ARCOMPACT
+
 config ARC_COMPACT_IRQ_LEVELS
 	bool "ARCompact IRQ Priorities: High(2)/Low(1)"
 	default n
@@ -290,7 +341,7 @@
 config ARC_IRQ6_LV2
 	bool
 
-endif
+endif	#ARC_COMPACT_IRQ_LEVELS
 
 config ARC_FPU_SAVE_RESTORE
 	bool "Enable FPU state persistence across context switch"
@@ -303,32 +354,53 @@
 	  based on actual usage of FPU by a task. Thus our implemn does
 	  this for all tasks in system.
 
+endif	#ISA_ARCOMPACT
+
 config ARC_CANT_LLSC
 	def_bool n
 
-menuconfig ARC_CPU_REL_4_10
-	bool "Enable support for Rel 4.10 features"
-	default n
-	help
-	  -ARC770 (and dependent features) enabled
-	  -ARC750 also shares some of the new features with 770
-
 config ARC_HAS_LLSC
 	bool "Insn: LLOCK/SCOND (efficient atomic ops)"
 	default y
-	depends on ARC_CPU_770 && !ARC_CANT_LLSC
+	depends on !ARC_CPU_750D && !ARC_CANT_LLSC
 
 config ARC_HAS_SWAPE
 	bool "Insn: SWAPE (endian-swap)"
 	default y
-	depends on ARC_CPU_REL_4_10
 
-config ARC_HAS_RTSC
-	bool "Insn: RTSC (64-bit r/o cycle counter)"
+if ISA_ARCV2
+
+config ARC_HAS_LL64
+	bool "Insn: 64bit LDD/STD"
+	help
+	  Enable gcc to generate 64-bit load/store instructions
+	  ISA mandates even/odd registers to allow encoding of two
+	  dest operands with 2 possible source operands.
 	default y
-	depends on ARC_CPU_REL_4_10
+
+config ARC_HAS_RTC
+	bool "Local 64-bit r/o cycle counter"
+	default n
 	depends on !SMP
 
+config ARC_HAS_GRTC
+	bool "SMP synchronized 64-bit cycle counter"
+	default y
+	depends on SMP
+
+config ARC_NUMBER_OF_INTERRUPTS
+	int "Number of interrupts"
+	range 8 240
+	default 32
+	help
+	  This defines the number of interrupts on the ARCv2HS core.
+	  It affects the size of vector table.
+	  The initial 8 IRQs are fixed (Timer, ICI etc) and although configurable
+	  in hardware, it keep things simple for Linux to assume they are always
+	  present.
+
+endif	# ISA_ARCV2
+
 endmenu   # "ARC CPU Configuration"
 
 config LINUX_LINK_BASE
@@ -354,8 +426,10 @@
 
 config ARC_EMUL_UNALIGNED
 	bool "Emulate unaligned memory access (userspace only)"
+	default N
 	select SYSCTL_ARCH_UNALIGN_NO_WARN
 	select SYSCTL_ARCH_UNALIGN_ALLOW
+	depends on ISA_ARCOMPACT
 	help
 	  This enables misaligned 16 & 32 bit memory access from user space.
 	  Use ONLY-IF-ABS-NECESSARY as it will be very slow and also can hide
@@ -378,9 +452,10 @@
 	bool "ARC debugging"
 	default y
 
+if ARC_DBG
+
 config ARC_DW2_UNWIND
 	bool "Enable DWARF specific kernel stack unwind"
-	depends on ARC_DBG
 	default y
 	select KALLSYMS
 	help
@@ -394,18 +469,38 @@
 
 config ARC_DBG_TLB_PARANOIA
 	bool "Paranoia Checks in Low Level TLB Handlers"
-	depends on ARC_DBG
 	default n
 
 config ARC_DBG_TLB_MISS_COUNT
 	bool "Profile TLB Misses"
 	default n
 	select DEBUG_FS
-	depends on ARC_DBG
 	help
 	  Counts number of I and D TLB Misses and exports them via Debugfs
 	  The counters can be cleared via Debugfs as well
 
+if SMP
+
+config ARC_IPI_DBG
+	bool "Debug Inter Core interrupts"
+	default n
+
+endif
+
+endif
+
+config ARC_UBOOT_SUPPORT
+	bool "Support uboot arg Handling"
+	default n
+	help
+	  ARC Linux by default checks for uboot provided args as pointers to
+	  external cmdline or DTB. This however breaks in absence of uboot,
+	  when booting from Metaware debugger directly, as the registers are
+	  not zeroed out on reset by mdb and/or ARCv2 based cores. The bogus
+	  registers look like uboot args to kernel which then chokes.
+	  So only enable the uboot arg checking/processing if users are sure
+	  of uboot being in play.
+
 config ARC_BUILTIN_DTB_NAME
 	string "Built in DTB"
 	help
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index db72fec..6107062 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -9,12 +9,14 @@
 UTS_MACHINE := arc
 
 ifeq ($(CROSS_COMPILE),)
-CROSS_COMPILE := arc-linux-uclibc-
+CROSS_COMPILE := arc-linux-
 endif
 
 KBUILD_DEFCONFIG := nsim_700_defconfig
 
-cflags-y	+= -mA7 -fno-common -pipe -fno-builtin -D__linux__
+cflags-y	+= -fno-common -pipe -fno-builtin -D__linux__
+cflags-$(CONFIG_ISA_ARCOMPACT)	+= -mA7
+cflags-$(CONFIG_ISA_ARCV2)	+= -mcpu=archs
 
 ifdef CONFIG_ARC_CURR_IN_REG
 # For a global register defintion, make sure it gets passed to every file
@@ -33,7 +35,11 @@
 
 cflags-$(CONFIG_ARC_HAS_LLSC)		+= -mlock
 cflags-$(CONFIG_ARC_HAS_SWAPE)		+= -mswape
-cflags-$(CONFIG_ARC_HAS_RTSC)		+= -mrtsc
+
+ifndef CONFIG_ARC_HAS_LL64
+cflags-$(CONFIG_ISA_ARCV2)		+= -mno-ll64
+endif
+
 cflags-$(CONFIG_ARC_DW2_UNWIND)		+= -fasynchronous-unwind-tables
 
 # By default gcc 4.8 generates dwarf4 which kernel unwinder can't grok
@@ -81,8 +87,9 @@
 # w/o this dtb won't embed into kernel binary
 core-y		+= arch/arc/boot/dts/
 
-core-$(CONFIG_ARC_PLAT_FPGA_LEGACY)	+= arch/arc/plat-arcfpga/
-core-$(CONFIG_ARC_PLAT_TB10X)		+= arch/arc/plat-tb10x/
+core-$(CONFIG_ARC_PLAT_SIM)	+= arch/arc/plat-sim/
+core-$(CONFIG_ARC_PLAT_TB10X)	+= arch/arc/plat-tb10x/
+core-$(CONFIG_ARC_PLAT_AXS10X)	+= arch/arc/plat-axs10x/
 
 drivers-$(CONFIG_OPROFILE)	+= arch/arc/oprofile/
 
diff --git a/arch/arc/boot/dts/Makefile b/arch/arc/boot/dts/Makefile
index faf240e..b0e3f19 100644
--- a/arch/arc/boot/dts/Makefile
+++ b/arch/arc/boot/dts/Makefile
@@ -1,5 +1,5 @@
 # Built-in dtb
-builtindtb-y		:= angel4
+builtindtb-y		:= nsim_700
 
 ifneq ($(CONFIG_ARC_BUILTIN_DTB_NAME),"")
 	builtindtb-y	:= $(patsubst "%",%,$(CONFIG_ARC_BUILTIN_DTB_NAME))
diff --git a/arch/arc/boot/dts/axc001.dtsi b/arch/arc/boot/dts/axc001.dtsi
new file mode 100644
index 0000000..a5e2726
--- /dev/null
+++ b/arch/arc/boot/dts/axc001.dtsi
@@ -0,0 +1,100 @@
+/*
+ * Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Device tree for AXC001 770D/EM6/AS221 CPU card
+ * Note that this file only supports the 770D CPU
+ */
+
+/ {
+	compatible = "snps,arc";
+	clock-frequency = <750000000>;	/* 750 MHZ */
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	cpu_card {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		ranges = <0x00000000 0xf0000000 0x10000000>;
+
+		cpu_intc: arc700-intc@cpu {
+			compatible = "snps,arc700-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		/*
+		 * this GPIO block ORs all interrupts on CPU card (creg,..)
+		 * to uplink only 1 IRQ to ARC core intc
+		 */
+		dw-apb-gpio@0x2000 {
+			compatible = "snps,dw-apb-gpio";
+			reg = < 0x2000 0x80 >;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			ictl_intc: gpio-controller@0 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				snps,nr-gpios = <30>;
+				reg = <0>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				interrupt-parent = <&cpu_intc>;
+				interrupts = <15>;
+			};
+		};
+
+		debug_uart: dw-apb-uart@0x5000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x5000 0x100>;
+			clock-frequency = <33333000>;
+			interrupt-parent = <&ictl_intc>;
+			interrupts = <19 4>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+		arcpmu0: pmu {
+			compatible = "snps,arc700-pct";
+		};
+	};
+
+	/*
+	 * This INTC is actually connected to DW APB GPIO
+	 * which acts as a wire between MB INTC and CPU INTC.
+	 * GPIO INTC is configured in platform init code
+	 * and here we mimic direct connection from MB INTC to
+	 * CPU INTC, thus we set "interrupts = <7>" instead of
+	 * "interrupts = <12>"
+	 *
+	 * This intc actually resides on MB, but we move it here to
+	 * avoid duplicating the MB dtsi file given that IRQ from
+	 * this intc to cpu intc are different for axs101 and axs103
+	 */
+	mb_intc: dw-apb-ictl@0xe0012000 {
+		#interrupt-cells = <1>;
+		compatible = "snps,dw-apb-ictl";
+		reg = < 0xe0012000 0x200 >;
+		interrupt-controller;
+		interrupt-parent = <&cpu_intc>;
+		interrupts = < 7 >;
+	};
+
+	memory {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x00000000 0x80000000 0x40000000>;
+		device_type = "memory";
+		reg = <0x00000000 0x20000000>;	/* 512MiB */
+	};
+};
diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi
new file mode 100644
index 0000000..15c8d62
--- /dev/null
+++ b/arch/arc/boot/dts/axc003.dtsi
@@ -0,0 +1,102 @@
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Device tree for AXC003 CPU card: HS38x UP configuration
+ */
+
+/ {
+	compatible = "snps,arc";
+	clock-frequency = <75000000>;
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	cpu_card {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		ranges = <0x00000000 0xf0000000 0x10000000>;
+
+		cpu_intc: archs-intc@cpu {
+			compatible = "snps,archs-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		/*
+		 * this GPIO block ORs all interrupts on CPU card (creg,..)
+		 * to uplink only 1 IRQ to ARC core intc
+		 */
+		dw-apb-gpio@0x2000 {
+			compatible = "snps,dw-apb-gpio";
+			reg = < 0x2000 0x80 >;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			ictl_intc: gpio-controller@0 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				snps,nr-gpios = <30>;
+				reg = <0>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				interrupt-parent = <&cpu_intc>;
+				interrupts = <25>;
+			};
+		};
+
+		debug_uart: dw-apb-uart@0x5000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x5000 0x100>;
+			clock-frequency = <33333000>;
+			interrupt-parent = <&ictl_intc>;
+			interrupts = <2 4>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+		arcpct0: pct {
+			compatible = "snps,archs-pct";
+			#interrupt-cells = <1>;
+			interrupt-parent = <&cpu_intc>;
+			interrupts = <20>;
+		};
+	};
+
+	/*
+	 * This INTC is actually connected to DW APB GPIO
+	 * which acts as a wire between MB INTC and CPU INTC.
+	 * GPIO INTC is configured in platform init code
+	 * and here we mimic direct connection from MB INTC to
+	 * CPU INTC, thus we set "interrupts = <7>" instead of
+	 * "interrupts = <12>"
+	 *
+	 * This intc actually resides on MB, but we move it here to
+	 * avoid duplicating the MB dtsi file given that IRQ from
+	 * this intc to cpu intc are different for axs101 and axs103
+	 */
+	mb_intc: dw-apb-ictl@0xe0012000 {
+		#interrupt-cells = <1>;
+		compatible = "snps,dw-apb-ictl";
+		reg = < 0xe0012000 0x200 >;
+		interrupt-controller;
+		interrupt-parent = <&cpu_intc>;
+		interrupts = < 24 >;
+	};
+
+	memory {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x00000000 0x80000000 0x40000000>;
+		device_type = "memory";
+		reg = <0x00000000 0x20000000>;	/* 512MiB */
+	};
+};
diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi
new file mode 100644
index 0000000..199d428
--- /dev/null
+++ b/arch/arc/boot/dts/axc003_idu.dtsi
@@ -0,0 +1,126 @@
+/*
+ * Copyright (C) 2014, 2015 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Device tree for AXC003 CPU card: HS38x2 (Dual Core) with IDU intc
+ */
+
+/ {
+	compatible = "snps,arc";
+	clock-frequency = <75000000>;
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	cpu_card {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		ranges = <0x00000000 0xf0000000 0x10000000>;
+
+		cpu_intc: archs-intc@cpu {
+			compatible = "snps,archs-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		idu_intc: idu-interrupt-controller {
+			compatible = "snps,archs-idu-intc";
+			interrupt-controller;
+			interrupt-parent = <&cpu_intc>;
+
+			/*
+			 * <hwirq  distribution>
+			 * distribution: 0=RR; 1=cpu0, 2=cpu1, 4=cpu2, 8=cpu3
+			 */
+			#interrupt-cells = <2>;
+
+			/*
+			 * upstream irqs to core intc - downstream these are
+			 * "COMMON" irq 0,1..
+			 */
+			interrupts = <24 25>;
+		};
+
+		/*
+		 * this GPIO block ORs all interrupts on CPU card (creg,..)
+		 * to uplink only 1 IRQ to ARC core intc
+		 */
+		dw-apb-gpio@0x2000 {
+			compatible = "snps,dw-apb-gpio";
+			reg = < 0x2000 0x80 >;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			ictl_intc: gpio-controller@0 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				snps,nr-gpios = <30>;
+				reg = <0>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				interrupt-parent = <&idu_intc>;
+
+				/*
+				 * cmn irq 1 -> cpu irq 25
+				 * Distribute to cpu0 only
+				 */
+				interrupts = <1 1>;
+			};
+		};
+
+		debug_uart: dw-apb-uart@0x5000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x5000 0x100>;
+			clock-frequency = <33333000>;
+			interrupt-parent = <&ictl_intc>;
+			interrupts = <2 4>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+		arcpct0: pct {
+			compatible = "snps,archs-pct";
+			#interrupt-cells = <1>;
+			interrupt-parent = <&cpu_intc>;
+			interrupts = <20>;
+		};
+	};
+
+	/*
+	 * This INTC is actually connected to DW APB GPIO
+	 * which acts as a wire between MB INTC and CPU INTC.
+	 * GPIO INTC is configured in platform init code
+	 * and here we mimic direct connection from MB INTC to
+	 * CPU INTC, thus we set "interrupts = <0 1>" instead of
+	 * "interrupts = <12>"
+	 *
+	 * This intc actually resides on MB, but we move it here to
+	 * avoid duplicating the MB dtsi file given that IRQ from
+	 * this intc to cpu intc are different for axs101 and axs103
+	 */
+	mb_intc: dw-apb-ictl@0xe0012000 {
+		#interrupt-cells = <1>;
+		compatible = "snps,dw-apb-ictl";
+		reg = < 0xe0012000 0x200 >;
+		interrupt-controller;
+		interrupt-parent = <&idu_intc>;
+		interrupts = <0 1>;	/* cmn irq 0 -> cpu irq 24
+					   distribute to cpu0 only */
+	};
+
+	memory {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x00000000 0x80000000 0x40000000>;
+		device_type = "memory";
+		reg = <0x00000000 0x20000000>;	/* 512MiB */
+	};
+};
diff --git a/arch/arc/boot/dts/axs101.dts b/arch/arc/boot/dts/axs101.dts
new file mode 100644
index 0000000..3f9b058
--- /dev/null
+++ b/arch/arc/boot/dts/axs101.dts
@@ -0,0 +1,21 @@
+/*
+ * Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com)
+ *
+ * ARC AXS101 S/W development platform
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+/dts-v1/;
+
+/include/ "axc001.dtsi"
+/include/ "axs10x_mb.dtsi"
+
+/ {
+	compatible = "snps,axs101", "snps,arc-sdp";
+
+	chosen {
+		bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0";
+	};
+};
diff --git a/arch/arc/boot/dts/axs103.dts b/arch/arc/boot/dts/axs103.dts
new file mode 100644
index 0000000..e6d0e31
--- /dev/null
+++ b/arch/arc/boot/dts/axs103.dts
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Device Tree for AXS103 SDP with AXS10X Main Board and
+ * AXC003 FPGA Card (with UP bitfile)
+ */
+/dts-v1/;
+
+/include/ "axc003.dtsi"
+/include/ "axs10x_mb.dtsi"
+
+/ {
+	compatible = "snps,axs103", "snps,arc-sdp";
+
+	chosen {
+		bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=ttyS3,115200n8 debug print-fatal-signals=1";
+	};
+};
diff --git a/arch/arc/boot/dts/axs103_idu.dts b/arch/arc/boot/dts/axs103_idu.dts
new file mode 100644
index 0000000..f999fef
--- /dev/null
+++ b/arch/arc/boot/dts/axs103_idu.dts
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Device Tree for AXS103 SDP with AXS10X Main Board and
+ * AXC003 FPGA Card (with SMP bitfile)
+ */
+/dts-v1/;
+
+/include/ "axc003_idu.dtsi"
+/include/ "axs10x_mb.dtsi"
+
+/ {
+	compatible = "snps,axs103", "snps,arc-sdp";
+
+	chosen {
+		bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=ttyS3,115200n8 debug print-fatal-signals=1";
+	};
+};
diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi
new file mode 100644
index 0000000..f3db321
--- /dev/null
+++ b/arch/arc/boot/dts/axs10x_mb.dtsi
@@ -0,0 +1,224 @@
+/*
+ * Support for peripherals on the AXS10x mainboard
+ *
+ * Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/ {
+	axs10x_mb {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x00000000 0xe0000000 0x10000000>;
+		interrupt-parent = <&mb_intc>;
+
+		clocks {
+			i2cclk: i2cclk {
+				compatible = "fixed-clock";
+				clock-frequency = <50000000>;
+				#clock-cells = <0>;
+			};
+
+			apbclk: apbclk {
+				compatible = "fixed-clock";
+				clock-frequency = <50000000>;
+				#clock-cells = <0>;
+			};
+
+			mmcclk: mmcclk {
+				compatible = "fixed-clock";
+				clock-frequency = <50000000>;
+				#clock-cells = <0>;
+			};
+		};
+
+		ethernet@0x18000 {
+			#interrupt-cells = <1>;
+			compatible = "snps,dwmac";
+			reg = < 0x18000 0x2000 >;
+			interrupts = < 4 >;
+			interrupt-names = "macirq";
+			phy-mode = "rgmii";
+			snps,pbl = < 32 >;
+			clocks = <&apbclk>;
+			clock-names = "stmmaceth";
+		};
+
+		ehci@0x40000 {
+			compatible = "generic-ehci";
+			reg = < 0x40000 0x100 >;
+			interrupts = < 8 >;
+		};
+
+		ohci@0x60000 {
+			compatible = "generic-ohci";
+			reg = < 0x60000 0x100 >;
+			interrupts = < 8 >;
+		};
+
+		/*
+		 * According to DW Mobile Storage databook it is required
+		 * to use  "Hold Register" if card is enumerated in SDR12 or
+		 * SDR25 modes.
+		 *
+		 * Utilization of "Hold Register" is already implemented via
+		 * dw_mci_pltfm_prepare_command() which in its turn gets
+		 * used through dw_mci_drv_data->prepare_command call-back.
+		 * This call-back is used in Altera Socfpga platform and so
+		 * we may reuse it saying that we're compatible with their
+		 * "altr,socfpga-dw-mshc".
+		 *
+		 * Most probably "Hold Register" utilization is platform-
+		 * independent requirement which means that single unified
+		 * "snps,dw-mshc" should be enough for all users of DW MMC once
+		 * dw_mci_pltfm_prepare_command() is used in generic platform
+		 * code.
+		 */
+		mmc@0x15000 {
+			compatible = "altr,socfpga-dw-mshc";
+			reg = < 0x15000 0x400 >;
+			num-slots = < 1 >;
+			fifo-depth = < 16 >;
+			card-detect-delay = < 200 >;
+			clocks = <&apbclk>, <&mmcclk>;
+			clock-names = "biu", "ciu";
+			interrupts = < 7 >;
+			bus-width = < 4 >;
+		};
+
+		uart@0x20000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x20000 0x100>;
+			clock-frequency = <33333333>;
+			interrupts = <17>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+		uart@0x21000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x21000 0x100>;
+			clock-frequency = <33333333>;
+			interrupts = <18>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+		/* UART muxed with USB data port (ttyS3) */
+		uart@0x22000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x22000 0x100>;
+			clock-frequency = <33333333>;
+			interrupts = <19>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+		i2c@0x1d000 {
+			compatible = "snps,designware-i2c";
+			reg = <0x1d000 0x100>;
+			clock-frequency = <400000>;
+			clocks = <&i2cclk>;
+			interrupts = <14>;
+		};
+
+		i2c@0x1e000 {
+			compatible = "snps,designware-i2c";
+			reg = <0x1e000 0x100>;
+			clock-frequency = <400000>;
+			clocks = <&i2cclk>;
+			interrupts = <15>;
+		};
+
+		i2c@0x1f000 {
+			compatible = "snps,designware-i2c";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x1f000 0x100>;
+			clock-frequency = <400000>;
+			clocks = <&i2cclk>;
+			interrupts = <16>;
+
+			eeprom@0x54{
+				compatible = "24c01";
+				reg = <0x54>;
+				pagesize = <0x8>;
+			};
+
+			eeprom@0x57{
+				compatible = "24c04";
+				reg = <0x57>;
+				pagesize = <0x8>;
+			};
+		};
+
+		gpio0:gpio@13000 {
+			compatible = "snps,dw-apb-gpio";
+			reg = <0x13000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			gpio0_banka: gpio-controller@0 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				snps,nr-gpios = <32>;
+				reg = <0>;
+			};
+
+			gpio0_bankb: gpio-controller@1 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				snps,nr-gpios = <8>;
+				reg = <1>;
+			};
+
+			gpio0_bankc: gpio-controller@2 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				snps,nr-gpios = <8>;
+				reg = <2>;
+			};
+		};
+
+		gpio1:gpio@14000 {
+			compatible = "snps,dw-apb-gpio";
+			reg = <0x14000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			gpio1_banka: gpio-controller@0 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				snps,nr-gpios = <30>;
+				reg = <0>;
+			};
+
+			gpio1_bankb: gpio-controller@1 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				snps,nr-gpios = <10>;
+				reg = <1>;
+			};
+
+			gpio1_bankc: gpio-controller@2 {
+				compatible = "snps,dw-apb-gpio-port";
+				gpio-controller;
+				#gpio-cells = <2>;
+				snps,nr-gpios = <8>;
+				reg = <2>;
+			};
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/angel4.dts b/arch/arc/boot/dts/nsim_700.dts
similarity index 97%
rename from arch/arc/boot/dts/angel4.dts
rename to arch/arc/boot/dts/nsim_700.dts
index 3b076fb..105a001 100644
--- a/arch/arc/boot/dts/angel4.dts
+++ b/arch/arc/boot/dts/nsim_700.dts
@@ -10,7 +10,7 @@
 /include/ "skeleton.dtsi"
 
 / {
-	compatible = "snps,arc-angel4";
+	compatible = "snps,nsim";
 	clock-frequency = <80000000>;	/* 80 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
diff --git a/arch/arc/boot/dts/nsim_hs.dts b/arch/arc/boot/dts/nsim_hs.dts
new file mode 100644
index 0000000..911f069
--- /dev/null
+++ b/arch/arc/boot/dts/nsim_hs.dts
@@ -0,0 +1,53 @@
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+/dts-v1/;
+
+/include/ "skeleton.dtsi"
+
+/ {
+	compatible = "snps,nsim_hs";
+	interrupt-parent = <&core_intc>;
+
+	chosen {
+		bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8";
+	};
+
+	aliases {
+		serial0 = &arcuart0;
+	};
+
+	fpga {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		/* child and parent address space 1:1 mapped */
+		ranges;
+
+		core_intc: core-interrupt-controller {
+			compatible = "snps,archs-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		arcuart0: serial@c0fc1000 {
+			compatible = "snps,arc-uart";
+			reg = <0xc0fc1000 0x100>;
+			interrupts = <24>;
+			clock-frequency = <80000000>;
+			current-speed = <115200>;
+			status = "okay";
+		};
+
+		arcpct0: pct {
+			compatible = "snps,archs-pct";
+			#interrupt-cells = <1>;
+			interrupts = <20>;
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/nsim_hs_idu.dts b/arch/arc/boot/dts/nsim_hs_idu.dts
new file mode 100644
index 0000000..46ab319
--- /dev/null
+++ b/arch/arc/boot/dts/nsim_hs_idu.dts
@@ -0,0 +1,72 @@
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+/dts-v1/;
+
+/include/ "skeleton.dtsi"
+
+/ {
+	compatible = "snps,nsim_hs";
+	interrupt-parent = <&core_intc>;
+
+	chosen {
+		bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8";
+	};
+
+	aliases {
+		serial0 = &arcuart0;
+	};
+
+	fpga {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		/* child and parent address space 1:1 mapped */
+		ranges;
+
+		core_intc: core-interrupt-controller {
+			compatible = "snps,archs-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		idu_intc: idu-interrupt-controller {
+			compatible = "snps,archs-idu-intc";
+			interrupt-controller;
+			interrupt-parent = <&core_intc>;
+
+			/*
+			 * <hwirq  distribution>
+			 * distribution: 0=RR; 1=cpu0, 2=cpu1, 4=cpu2, 8=cpu3
+			 */
+			#interrupt-cells = <2>;
+
+			/*
+			 * upstream irqs to core intc - downstream these are
+			 * "COMMON" irq 0,1..
+			 */
+			interrupts = <24 25 26 27 28 29 30 31>;
+		};
+
+		arcuart0: serial@c0fc1000 {
+			compatible = "snps,arc-uart";
+			reg = <0xc0fc1000 0x100>;
+			interrupt-parent = <&idu_intc>;
+			interrupts = <0 0>;
+			clock-frequency = <80000000>;
+			current-speed = <115200>;
+			status = "okay";
+		};
+
+		arcpct0: pct {
+			compatible = "snps,archs-pct";
+			#interrupt-cells = <1>;
+			interrupts = <20>;
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/nsimosci_hs.dts b/arch/arc/boot/dts/nsimosci_hs.dts
new file mode 100644
index 0000000..d64a96f
--- /dev/null
+++ b/arch/arc/boot/dts/nsimosci_hs.dts
@@ -0,0 +1,80 @@
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+/dts-v1/;
+
+/include/ "skeleton.dtsi"
+
+/ {
+	compatible = "snps,nsimosci_hs";
+	clock-frequency = <20000000>;	/* 20 MHZ */
+	#address-cells = <1>;
+	#size-cells = <1>;
+	interrupt-parent = <&core_intc>;
+
+	chosen {
+		/* this is for console on PGU */
+		/* bootargs = "console=tty0 consoleblank=0"; */
+		/* this is for console on serial */
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug";
+	};
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	fpga {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		/* child and parent address space 1:1 mapped */
+		ranges;
+
+		core_intc: core-interrupt-controller {
+			compatible = "snps,archs-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		uart0: serial@f0000000 {
+			compatible = "ns8250";
+			reg = <0xf0000000 0x2000>;
+			interrupts = <24>;
+			clock-frequency = <3686400>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			no-loopback-test = <1>;
+		};
+
+		pgu0: pgu@f9000000 {
+			compatible = "snps,arcpgufb";
+			reg = <0xf9000000 0x400>;
+		};
+
+		ps2: ps2@f9001000 {
+			compatible = "snps,arc_ps2";
+			reg = <0xf9000400 0x14>;
+			interrupts = <27>;
+			interrupt-names = "arc_ps2_irq";
+		};
+
+		eth0: ethernet@f0003000 {
+			compatible = "snps,oscilan";
+			reg = <0xf0003000 0x44>;
+			interrupts = <25>, <26>;
+			interrupt-names = "rx", "tx";
+		};
+
+		arcpct0: pct {
+			compatible = "snps,archs-pct";
+			#interrupt-cells = <1>;
+			interrupts = <20>;
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/nsimosci_hs_idu.dts b/arch/arc/boot/dts/nsimosci_hs_idu.dts
new file mode 100644
index 0000000..f6bf0ca
--- /dev/null
+++ b/arch/arc/boot/dts/nsimosci_hs_idu.dts
@@ -0,0 +1,101 @@
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+/dts-v1/;
+
+/include/ "skeleton.dtsi"
+
+/ {
+	compatible = "snps,nsimosci_hs";
+	clock-frequency = <5000000>;	/* 5 MHZ */
+	#address-cells = <1>;
+	#size-cells = <1>;
+	interrupt-parent = <&core_intc>;
+
+	chosen {
+		/* this is for console on serial */
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblan=0 debug";
+	};
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	fpga {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		/* child and parent address space 1:1 mapped */
+		ranges;
+
+		core_intc: core-interrupt-controller {
+			compatible = "snps,archs-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+/*			interrupts = <16 17 18 19 20 21 22 23 24 25>; */
+		};
+
+		idu_intc: idu-interrupt-controller {
+			compatible = "snps,archs-idu-intc";
+			interrupt-controller;
+			interrupt-parent = <&core_intc>;
+
+			/*
+			 * <hwirq  distribution>
+			 * distribution: 0=RR; 1=cpu0, 2=cpu1, 4=cpu2, 8=cpu3
+			 */
+			#interrupt-cells = <2>;
+
+			/*
+			 * upstream irqs to core intc - downstream these are
+			 * "COMMON" irq 0,1..
+			 */
+			interrupts = <24 25 26 27 28 29 30 31>;
+		};
+
+		uart0: serial@f0000000 {
+			compatible = "ns8250";
+			reg = <0xf0000000 0x2000>;
+			interrupt-parent = <&idu_intc>;
+			interrupts = <0 0>; /* cmn irq 0 -> cpu irq 24
+						RR distribute to all cpus */
+			clock-frequency = <3686400>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			no-loopback-test = <1>;
+		};
+
+		pgu0: pgu@f9000000 {
+			compatible = "snps,arcpgufb";
+			reg = <0xf9000000 0x400>;
+		};
+
+		ps2: ps2@f9001000 {
+			compatible = "snps,arc_ps2";
+			reg = <0xf9000400 0x14>;
+			interrupts = <3 0>;
+			interrupt-parent = <&idu_intc>;
+			interrupt-names = "arc_ps2_irq";
+		};
+
+		eth0: ethernet@f0003000 {
+			compatible = "snps,oscilan";
+			reg = <0xf0003000 0x44>;
+			interrupt-parent = <&idu_intc>;
+			interrupts = <1 2>, <2 2>;
+			interrupt-names = "rx", "tx";
+		};
+
+		arcpct0: pct {
+			compatible = "snps,archs-pct";
+			#interrupt-cells = <1>;
+			interrupts = <20>;
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/vdk_axc003.dtsi b/arch/arc/boot/dts/vdk_axc003.dtsi
new file mode 100644
index 0000000..9393fd9
--- /dev/null
+++ b/arch/arc/boot/dts/vdk_axc003.dtsi
@@ -0,0 +1,61 @@
+/*
+ * Copyright (C) 2013, 2014 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Device tree for AXC003 CPU card: HS38x UP configuration (VDK version)
+ */
+
+/ {
+	compatible = "snps,arc";
+	clock-frequency = <50000000>;
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	cpu_card {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		ranges = <0x00000000 0xf0000000 0x10000000>;
+
+		cpu_intc: archs-intc@cpu {
+			compatible = "snps,archs-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		debug_uart: dw-apb-uart@0x5000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x5000 0x100>;
+			clock-frequency = <2403200>;
+			interrupt-parent = <&cpu_intc>;
+			interrupts = <19>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+	};
+
+	mb_intc: dw-apb-ictl@0xe0012000 {
+		#interrupt-cells = <1>;
+		compatible = "snps,dw-apb-ictl";
+		reg = < 0xe0012000 0x200 >;
+		interrupt-controller;
+		interrupt-parent = <&cpu_intc>;
+		interrupts = < 18 >;
+	};
+
+	memory {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x00000000 0x80000000 0x40000000>;
+		device_type = "memory";
+		reg = <0x00000000 0x20000000>;	/* 512MiB */
+	};
+};
diff --git a/arch/arc/boot/dts/vdk_axc003_idu.dtsi b/arch/arc/boot/dts/vdk_axc003_idu.dtsi
new file mode 100644
index 0000000..9bee8ed
--- /dev/null
+++ b/arch/arc/boot/dts/vdk_axc003_idu.dtsi
@@ -0,0 +1,76 @@
+/*
+ * Copyright (C) 2014, 2015 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Device tree for AXC003 CPU card:
+ * HS38x2 (Dual Core) with IDU intc (VDK version)
+ */
+
+/ {
+	compatible = "snps,arc";
+	clock-frequency = <50000000>;
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	cpu_card {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		ranges = <0x00000000 0xf0000000 0x10000000>;
+
+		cpu_intc: archs-intc@cpu {
+			compatible = "snps,archs-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		idu_intc: idu-interrupt-controller {
+			compatible = "snps,archs-idu-intc";
+			interrupt-controller;
+			interrupt-parent = <&cpu_intc>;
+
+			/*
+			 * <hwirq  distribution>
+			 * distribution: 0=RR; 1=cpu0, 2=cpu1, 4=cpu2, 8=cpu3
+			 */
+			#interrupt-cells = <2>;
+
+			interrupts = <24 25 26 27>;
+		};
+
+		debug_uart: dw-apb-uart@0x5000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x5000 0x100>;
+			clock-frequency = <2403200>;
+			interrupt-parent = <&idu_intc>;
+			interrupts = <2 0>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+	};
+
+	mb_intc: dw-apb-ictl@0xe0012000 {
+		#interrupt-cells = <1>;
+		compatible = "snps,dw-apb-ictl";
+		reg = < 0xe0012000 0x200 >;
+		interrupt-controller;
+		interrupt-parent = <&idu_intc>;
+		interrupts = < 0 0 >;
+	};
+
+	memory {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x00000000 0x80000000 0x40000000>;
+		device_type = "memory";
+		reg = <0x00000000 0x20000000>;	/* 512MiB */
+	};
+};
diff --git a/arch/arc/boot/dts/vdk_axs10x_mb.dtsi b/arch/arc/boot/dts/vdk_axs10x_mb.dtsi
new file mode 100644
index 0000000..45cd665
--- /dev/null
+++ b/arch/arc/boot/dts/vdk_axs10x_mb.dtsi
@@ -0,0 +1,93 @@
+/*
+ * Support for peripherals on the AXS10x mainboard (VDK version)
+ *
+ * Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/ {
+	axs10x_mb_vdk {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x00000000 0xe0000000 0x10000000>;
+		interrupt-parent = <&mb_intc>;
+
+		clocks {
+			apbclk: apbclk {
+				compatible = "fixed-clock";
+				clock-frequency = <50000000>;
+				#clock-cells = <0>;
+			};
+
+		};
+
+		ethernet@0x18000 {
+			#interrupt-cells = <1>;
+			compatible = "snps,dwmac";
+			reg = < 0x18000 0x2000 >;
+			interrupts = < 4 >;
+			interrupt-names = "macirq";
+			phy-mode = "rgmii";
+			snps,phy-addr = < 0 >;  // VDK model phy address is 0
+			snps,pbl = < 32 >;
+			clocks = <&apbclk>;
+			clock-names = "stmmaceth";
+		};
+
+		ehci@0x40000 {
+			compatible = "generic-ehci";
+			reg = < 0x40000 0x100 >;
+			interrupts = < 8 >;
+		};
+
+		uart@0x20000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x20000 0x100>;
+			clock-frequency = <2403200>;
+			interrupts = <17>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+		uart@0x21000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x21000 0x100>;
+			clock-frequency = <2403200>;
+			interrupts = <18>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+		uart@0x22000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x22000 0x100>;
+			clock-frequency = <2403200>;
+			interrupts = <19>;
+			baud = <115200>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+/* PGU output directly sent to virtual LCD screen; hdmi controller not modelled */
+		pgu@0x17000 {
+			compatible = "snps,arcpgufb";
+			reg = <0x17000 0x400>;
+			clock-frequency = <51000000>; /* PGU'clock is initated in init function */
+			/* interrupts = <5>;   PGU interrupts not used, this vector is used for ps2 below */
+		};
+
+/* VDK has additional ps2 keyboard/mouse interface integrated in LCD screen model */
+		ps2: ps2@e0017400 {
+			compatible = "snps,arc_ps2";
+			reg = <0x17400 0x14>;
+			interrupts = <5>;
+			interrupt-names = "arc_ps2_irq";
+		};
+	};
+};
diff --git a/arch/arc/boot/dts/vdk_hs38.dts b/arch/arc/boot/dts/vdk_hs38.dts
new file mode 100644
index 0000000..5d803dd
--- /dev/null
+++ b/arch/arc/boot/dts/vdk_hs38.dts
@@ -0,0 +1,21 @@
+/*
+ * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com)
+ *
+ * ARC HS38 Virtual Development Kit (VDK)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+/dts-v1/;
+
+/include/ "vdk_axc003.dtsi"
+/include/ "vdk_axs10x_mb.dtsi"
+
+/ {
+	compatible = "snps,axs103";
+
+	chosen {
+		bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0";
+	};
+};
diff --git a/arch/arc/boot/dts/vdk_hs38_smp.dts b/arch/arc/boot/dts/vdk_hs38_smp.dts
new file mode 100644
index 0000000..031a5bc
--- /dev/null
+++ b/arch/arc/boot/dts/vdk_hs38_smp.dts
@@ -0,0 +1,21 @@
+/*
+ * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com)
+ *
+ * ARC HS38 Virtual Development Kit, SMP version (VDK)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+/dts-v1/;
+
+/include/ "vdk_axc003_idu.dtsi"
+/include/ "vdk_axs10x_mb.dtsi"
+
+/ {
+	compatible = "snps,axs103";
+
+	chosen {
+		bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0";
+	};
+};
diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig
new file mode 100644
index 0000000..562dac6
--- /dev/null
+++ b/arch/arc/configs/axs101_defconfig
@@ -0,0 +1,111 @@
+CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_DEFAULT_HOSTNAME="ARCLinux"
+# CONFIG_SWAP is not set
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_NO_HZ_IDLE=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_NAMESPACES=y
+# CONFIG_UTS_NS is not set
+# CONFIG_PID_NS is not set
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE="../arc_initramfs/"
+CONFIG_EMBEDDED=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_SLUB_DEBUG is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_MODULES=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_ARC_PLAT_AXS10X=y
+CONFIG_AXS101=y
+CONFIG_ARC_CACHE_LINE_SHIFT=5
+CONFIG_ARC_BUILTIN_DTB_NAME="axs101"
+CONFIG_PREEMPT=y
+# CONFIG_COMPACTION is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_IPV6 is not set
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_NETDEVICES=y
+# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+CONFIG_STMMAC_ETH=y
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+CONFIG_NATIONAL_PHY=y
+# CONFIG_USB_NET_DRIVERS is not set
+CONFIG_INPUT_EVDEV=y
+CONFIG_MOUSE_PS2_TOUCHKIT=y
+CONFIG_MOUSE_SERIAL=y
+CONFIG_MOUSE_SYNAPTICS_USB=y
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
+CONFIG_I2C_DESIGNWARE_PLATFORM=y
+# CONFIG_HWMON is not set
+CONFIG_FB=y
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+# CONFIG_LOGO_LINUX_CLUT224 is not set
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PLATFORM=y
+CONFIG_USB_STORAGE=y
+CONFIG_MMC=y
+CONFIG_MMC_SDHCI=y
+CONFIG_MMC_SDHCI_PLTFM=y
+CONFIG_MMC_DW=y
+CONFIG_MMC_DW_IDMAC=y
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_NTFS_FS=y
+CONFIG_TMPFS=y
+CONFIG_JFFS2_FS=y
+CONFIG_NFS_FS=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_STRIP_ASM_SYMS=y
+CONFIG_LOCKUP_DETECTOR=y
+CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_DEBUG_PREEMPT is not set
+# CONFIG_FTRACE is not set
diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig
new file mode 100644
index 0000000..83a6d8d
--- /dev/null
+++ b/arch/arc/configs/axs103_defconfig
@@ -0,0 +1,117 @@
+CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_DEFAULT_HOSTNAME="ARCLinux"
+# CONFIG_SWAP is not set
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_NO_HZ_IDLE=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_NAMESPACES=y
+# CONFIG_UTS_NS is not set
+# CONFIG_PID_NS is not set
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
+CONFIG_EMBEDDED=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_SLUB_DEBUG is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_MODULES=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_ARC_PLAT_AXS10X=y
+CONFIG_AXS103=y
+CONFIG_ISA_ARCV2=y
+CONFIG_ARC_BUILTIN_DTB_NAME="axs103"
+CONFIG_PREEMPT=y
+# CONFIG_COMPACTION is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_IPV6 is not set
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_NAND=y
+CONFIG_MTD_NAND_AXS=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_NETDEVICES=y
+# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+CONFIG_STMMAC_ETH=y
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+CONFIG_NATIONAL_PHY=y
+# CONFIG_USB_NET_DRIVERS is not set
+CONFIG_INPUT_EVDEV=y
+CONFIG_MOUSE_PS2_TOUCHKIT=y
+CONFIG_MOUSE_SERIAL=y
+CONFIG_MOUSE_SYNAPTICS_USB=y
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
+CONFIG_I2C_DESIGNWARE_PLATFORM=y
+# CONFIG_HWMON is not set
+CONFIG_FB=y
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+# CONFIG_LOGO_LINUX_CLUT224 is not set
+CONFIG_USB=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PLATFORM=y
+CONFIG_USB_STORAGE=y
+CONFIG_MMC=y
+CONFIG_MMC_SDHCI=y
+CONFIG_MMC_SDHCI_PLTFM=y
+CONFIG_MMC_DW=y
+CONFIG_MMC_DW_IDMAC=y
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_NTFS_FS=y
+CONFIG_TMPFS=y
+CONFIG_JFFS2_FS=y
+CONFIG_NFS_FS=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_STRIP_ASM_SYMS=y
+CONFIG_LOCKUP_DETECTOR=y
+CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_DEBUG_PREEMPT is not set
+# CONFIG_FTRACE is not set
diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig
new file mode 100644
index 0000000..f1e1c84
--- /dev/null
+++ b/arch/arc/configs/axs103_smp_defconfig
@@ -0,0 +1,118 @@
+CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_DEFAULT_HOSTNAME="ARCLinux"
+# CONFIG_SWAP is not set
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_NO_HZ_IDLE=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_NAMESPACES=y
+# CONFIG_UTS_NS is not set
+# CONFIG_PID_NS is not set
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
+CONFIG_EMBEDDED=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_SLAB=y
+CONFIG_MODULES=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_ARC_PLAT_AXS10X=y
+CONFIG_AXS103=y
+CONFIG_ISA_ARCV2=y
+CONFIG_SMP=y
+CONFIG_ARC_BUILTIN_DTB_NAME="axs103_idu"
+CONFIG_PREEMPT=y
+# CONFIG_COMPACTION is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_IPV6 is not set
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_NAND=y
+CONFIG_MTD_NAND_AXS=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_NETDEVICES=y
+# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+CONFIG_STMMAC_ETH=y
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+CONFIG_NATIONAL_PHY=y
+# CONFIG_USB_NET_DRIVERS is not set
+CONFIG_INPUT_EVDEV=y
+CONFIG_MOUSE_PS2_TOUCHKIT=y
+CONFIG_MOUSE_SERIAL=y
+CONFIG_MOUSE_SYNAPTICS_USB=y
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
+CONFIG_I2C_DESIGNWARE_PLATFORM=y
+# CONFIG_HWMON is not set
+CONFIG_FB=y
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+# CONFIG_LOGO_LINUX_CLUT224 is not set
+CONFIG_USB=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PLATFORM=y
+CONFIG_USB_STORAGE=y
+CONFIG_MMC=y
+CONFIG_MMC_SDHCI=y
+CONFIG_MMC_SDHCI_PLTFM=y
+CONFIG_MMC_DW=y
+CONFIG_MMC_DW_IDMAC=y
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_NTFS_FS=y
+CONFIG_TMPFS=y
+CONFIG_JFFS2_FS=y
+CONFIG_NFS_FS=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_STRIP_ASM_SYMS=y
+CONFIG_LOCKUP_DETECTOR=y
+CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_DEBUG_PREEMPT is not set
+# CONFIG_FTRACE is not set
diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig
index ef4d3bc..138f9d8 100644
--- a/arch/arc/configs/nsim_700_defconfig
+++ b/arch/arc/configs/nsim_700_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
@@ -22,9 +22,8 @@
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
-CONFIG_ARC_PLAT_FPGA_LEGACY=y
-# CONFIG_ARC_HAS_RTSC is not set
-CONFIG_ARC_BUILTIN_DTB_NAME="angel4"
+CONFIG_ARC_PLAT_SIM=y
+CONFIG_ARC_BUILTIN_DTB_NAME="nsim_700"
 CONFIG_PREEMPT=y
 # CONFIG_COMPACTION is not set
 # CONFIG_CROSS_MEMORY_ATTACH is not set
diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig
new file mode 100644
index 0000000..f761a7c
--- /dev/null
+++ b/arch/arc/configs/nsim_hs_defconfig
@@ -0,0 +1,64 @@
+CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_DEFAULT_HOSTNAME="ARCLinux"
+# CONFIG_SWAP is not set
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_NAMESPACES=y
+# CONFIG_UTS_NS is not set
+# CONFIG_PID_NS is not set
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
+CONFIG_KALLSYMS_ALL=y
+CONFIG_EMBEDDED=y
+# CONFIG_SLUB_DEBUG is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_KPROBES=y
+CONFIG_MODULES=y
+# CONFIG_LBDAF is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_IOSCHED_CFQ is not set
+CONFIG_ARC_PLAT_SIM=y
+CONFIG_ISA_ARCV2=y
+CONFIG_ARC_BUILTIN_DTB_NAME="nsim_hs"
+CONFIG_PREEMPT=y
+# CONFIG_COMPACTION is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_UNIX_DIAG=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+# CONFIG_IPV6 is not set
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+# CONFIG_BLK_DEV is not set
+# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_SERIO is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_ARC=y
+CONFIG_SERIAL_ARC_CONSOLE=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+# CONFIG_VGA_CONSOLE is not set
+# CONFIG_HID is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT2_FS=y
+CONFIG_EXT2_FS_XATTR=y
+CONFIG_TMPFS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_NFS_FS=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+# CONFIG_DEBUG_PREEMPT is not set
+CONFIG_XZ_DEC=y
diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig
new file mode 100644
index 0000000..dc6f74f
--- /dev/null
+++ b/arch/arc/configs/nsim_hs_smp_defconfig
@@ -0,0 +1,63 @@
+CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_DEFAULT_HOSTNAME="ARCLinux"
+# CONFIG_SWAP is not set
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_NAMESPACES=y
+# CONFIG_UTS_NS is not set
+# CONFIG_PID_NS is not set
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
+CONFIG_KALLSYMS_ALL=y
+CONFIG_EMBEDDED=y
+# CONFIG_SLUB_DEBUG is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_KPROBES=y
+CONFIG_MODULES=y
+# CONFIG_LBDAF is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_IOSCHED_CFQ is not set
+CONFIG_ARC_PLAT_SIM=y
+CONFIG_ARC_BOARD_ML509=y
+CONFIG_ISA_ARCV2=y
+CONFIG_SMP=y
+CONFIG_ARC_BUILTIN_DTB_NAME="nsim_hs_idu"
+CONFIG_PREEMPT=y
+# CONFIG_COMPACTION is not set
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_UNIX_DIAG=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+# CONFIG_IPV6 is not set
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+# CONFIG_BLK_DEV is not set
+# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_SERIO is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_ARC=y
+CONFIG_SERIAL_ARC_CONSOLE=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+# CONFIG_VGA_CONSOLE is not set
+# CONFIG_HID is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT2_FS=y
+CONFIG_EXT2_FS_XATTR=y
+CONFIG_TMPFS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_NFS_FS=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_XZ_DEC=y
diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig
index d2ac4e5..31e1d95 100644
--- a/arch/arc/configs/nsimosci_defconfig
+++ b/arch/arc/configs/nsimosci_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
@@ -23,8 +23,7 @@
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
-CONFIG_ARC_PLAT_FPGA_LEGACY=y
-# CONFIG_ARC_HAS_RTSC is not set
+CONFIG_ARC_PLAT_SIM=y
 CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci"
 # CONFIG_COMPACTION is not set
 CONFIG_NET=y
diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig
new file mode 100644
index 0000000..3fef0a2
--- /dev/null
+++ b/arch/arc/configs/nsimosci_hs_defconfig
@@ -0,0 +1,73 @@
+CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_DEFAULT_HOSTNAME="ARCLinux"
+# CONFIG_SWAP is not set
+CONFIG_SYSVIPC=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_NAMESPACES=y
+# CONFIG_UTS_NS is not set
+# CONFIG_PID_NS is not set
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
+CONFIG_KALLSYMS_ALL=y
+CONFIG_EMBEDDED=y
+# CONFIG_SLUB_DEBUG is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_KPROBES=y
+CONFIG_MODULES=y
+# CONFIG_LBDAF is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_IOSCHED_CFQ is not set
+CONFIG_ARC_PLAT_SIM=y
+CONFIG_ISA_ARCV2=y
+CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci_hs"
+# CONFIG_COMPACTION is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_UNIX_DIAG=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+# CONFIG_IPV6 is not set
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+# CONFIG_BLK_DEV is not set
+CONFIG_NETDEVICES=y
+CONFIG_NET_OSCI_LAN=y
+CONFIG_INPUT_EVDEV=y
+# CONFIG_MOUSE_PS2_ALPS is not set
+# CONFIG_MOUSE_PS2_LOGIPS2PP is not set
+# CONFIG_MOUSE_PS2_SYNAPTICS is not set
+# CONFIG_MOUSE_PS2_TRACKPOINT is not set
+CONFIG_MOUSE_PS2_TOUCHKIT=y
+# CONFIG_SERIO_SERPORT is not set
+CONFIG_SERIO_ARC_PS2=y
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=1
+CONFIG_SERIAL_8250_RUNTIME_UARTS=1
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+CONFIG_FB=y
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_LOGO=y
+# CONFIG_HID is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT2_FS=y
+CONFIG_EXT2_FS_XATTR=y
+CONFIG_TMPFS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_NFS_FS=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig
new file mode 100644
index 0000000..5178483
--- /dev/null
+++ b/arch/arc/configs/nsimosci_hs_smp_defconfig
@@ -0,0 +1,93 @@
+CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_DEFAULT_HOSTNAME="ARCLinux"
+# CONFIG_SWAP is not set
+CONFIG_SYSVIPC=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+# CONFIG_UTS_NS is not set
+# CONFIG_PID_NS is not set
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
+# CONFIG_COMPAT_BRK is not set
+CONFIG_KPROBES=y
+CONFIG_MODULES=y
+# CONFIG_LBDAF is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_IOSCHED_CFQ is not set
+CONFIG_ARC_PLAT_SIM=y
+CONFIG_ARC_BOARD_ML509=y
+CONFIG_ISA_ARCV2=y
+CONFIG_SMP=y
+CONFIG_ARC_HAS_LL64=y
+# CONFIG_ARC_HAS_RTSC is not set
+CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci_hs_idu"
+CONFIG_PREEMPT=y
+# CONFIG_COMPACTION is not set
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_PACKET_DIAG=y
+CONFIG_UNIX=y
+CONFIG_UNIX_DIAG=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_LRO is not set
+# CONFIG_IPV6 is not set
+# CONFIG_WIRELESS is not set
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+# CONFIG_BLK_DEV is not set
+CONFIG_NETDEVICES=y
+# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+CONFIG_NET_OSCI_LAN=y
+# CONFIG_WLAN is not set
+CONFIG_INPUT_EVDEV=y
+CONFIG_MOUSE_PS2_TOUCHKIT=y
+# CONFIG_SERIO_SERPORT is not set
+CONFIG_SERIO_LIBPS2=y
+CONFIG_SERIO_ARC_PS2=y
+CONFIG_VT_HW_CONSOLE_BINDING=y
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=1
+CONFIG_SERIAL_8250_RUNTIME_UARTS=1
+CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+CONFIG_FB=y
+CONFIG_ARCPGU_RGB888=y
+CONFIG_ARCPGU_DISPTYPE=0
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_LOGO=y
+# CONFIG_HID is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT2_FS=y
+CONFIG_EXT2_FS_XATTR=y
+CONFIG_TMPFS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_NFS_FS=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_FTRACE=y
diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig
index 6be6492..3b4dc9c 100644
--- a/arch/arc/configs/tb10x_defconfig
+++ b/arch/arc/configs/tb10x_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="tb10x"
 CONFIG_SYSVIPC=y
@@ -26,7 +26,6 @@
 # CONFIG_BLOCK is not set
 CONFIG_ARC_PLAT_TB10X=y
 CONFIG_ARC_CACHE_LINE_SHIFT=5
-# CONFIG_ARC_HAS_RTSC is not set
 CONFIG_ARC_STACK_NONEXEC=y
 CONFIG_HZ=250
 CONFIG_ARC_BUILTIN_DTB_NAME="abilis_tb100_dvk"
diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig
new file mode 100644
index 0000000..ef35ef3
--- /dev/null
+++ b/arch/arc/configs/vdk_hs38_defconfig
@@ -0,0 +1,102 @@
+CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_DEFAULT_HOSTNAME="ARCLinux"
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_EMBEDDED=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_SLUB_DEBUG is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_ARC_PLAT_AXS10X=y
+CONFIG_AXS103=y
+CONFIG_ISA_ARCV2=y
+CONFIG_ARC_UBOOT_SUPPORT=y
+CONFIG_ARC_BUILTIN_DTB_NAME="vdk_hs38"
+CONFIG_PREEMPT=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+# CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_SLRAM=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_NETDEVICES=y
+# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+CONFIG_STMMAC_ETH=y
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+CONFIG_NATIONAL_PHY=y
+CONFIG_MOUSE_PS2_TOUCHKIT=y
+CONFIG_SERIO_ARC_PS2=y
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+CONFIG_FB=y
+CONFIG_ARCPGU_RGB888=y
+CONFIG_ARCPGU_DISPTYPE=0
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+# CONFIG_LOGO_LINUX_CLUT224 is not set
+CONFIG_USB=y
+CONFIG_USB_EHCI_HCD=y
+# CONFIG_USB_EHCI_TT_NEWSCHED is not set
+CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PLATFORM=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_SERIAL=y
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_NTFS_FS=y
+CONFIG_TMPFS=y
+CONFIG_JFFS2_FS=y
+CONFIG_NFS_FS=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_STRIP_ASM_SYMS=y
+CONFIG_DEBUG_SHIRQ=y
+CONFIG_LOCKUP_DETECTOR=y
+CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_DEBUG_PREEMPT is not set
+# CONFIG_FTRACE is not set
diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig
new file mode 100644
index 0000000..634509e
--- /dev/null
+++ b/arch/arc/configs/vdk_hs38_smp_defconfig
@@ -0,0 +1,104 @@
+CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_DEFAULT_HOSTNAME="ARCLinux"
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_EMBEDDED=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_SLUB_DEBUG is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_ARC_PLAT_AXS10X=y
+CONFIG_AXS103=y
+CONFIG_ISA_ARCV2=y
+CONFIG_SMP=y
+# CONFIG_ARC_HAS_GRTC is not set
+CONFIG_ARC_UBOOT_SUPPORT=y
+CONFIG_ARC_BUILTIN_DTB_NAME="vdk_hs38_smp"
+CONFIG_PREEMPT=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+# CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_SLRAM=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_NETDEVICES=y
+# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+CONFIG_STMMAC_ETH=y
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+CONFIG_NATIONAL_PHY=y
+CONFIG_MOUSE_PS2_TOUCHKIT=y
+CONFIG_SERIO_ARC_PS2=y
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+CONFIG_FB=y
+CONFIG_ARCPGU_RGB888=y
+CONFIG_ARCPGU_DISPTYPE=0
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+# CONFIG_LOGO_LINUX_CLUT224 is not set
+CONFIG_USB=y
+CONFIG_USB_EHCI_HCD=y
+# CONFIG_USB_EHCI_TT_NEWSCHED is not set
+CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PLATFORM=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_SERIAL=y
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_NTFS_FS=y
+CONFIG_TMPFS=y
+CONFIG_JFFS2_FS=y
+CONFIG_NFS_FS=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_STRIP_ASM_SYMS=y
+CONFIG_DEBUG_SHIRQ=y
+CONFIG_LOCKUP_DETECTOR=y
+CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_DEBUG_PREEMPT is not set
+# CONFIG_FTRACE is not set
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index 769b312..1a80cc9 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -1,5 +1,4 @@
 generic-y += auxvec.h
-generic-y += barrier.h
 generic-y += bitsperlong.h
 generic-y += bugs.h
 generic-y += clkdev.h
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index e2b1b12..070f588 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -16,6 +16,8 @@
 #define ARC_REG_PERIBASE_BCR	0x69
 #define ARC_REG_FP_BCR		0x6B	/* ARCompact: Single-Precision FPU */
 #define ARC_REG_DPFP_BCR	0x6C	/* ARCompact: Dbl Precision FPU */
+#define ARC_REG_FP_V2_BCR	0xc8	/* ARCv2 FPU */
+#define ARC_REG_SLC_BCR		0xce
 #define ARC_REG_DCCM_BCR	0x74	/* DCCM Present + SZ */
 #define ARC_REG_TIMERS_BCR	0x75
 #define ARC_REG_AP_BCR		0x76
@@ -31,6 +33,7 @@
 #define ARC_REG_BPU_BCR		0xc0
 #define ARC_REG_ISA_CFG_BCR	0xc1
 #define ARC_REG_RTT_BCR		0xF2
+#define ARC_REG_IRQ_BCR		0xF3
 #define ARC_REG_SMART_BCR	0xFF
 
 /* status32 Bits Positions */
@@ -51,6 +54,7 @@
  * [15: 8] = Exception Cause Code
  * [ 7: 0] = Exception Parameters (for certain types only)
  */
+#ifdef CONFIG_ISA_ARCOMPACT
 #define ECR_V_MEM_ERR			0x01
 #define ECR_V_INSN_ERR			0x02
 #define ECR_V_MACH_CHK			0x20
@@ -58,6 +62,15 @@
 #define ECR_V_DTLB_MISS			0x22
 #define ECR_V_PROTV			0x23
 #define ECR_V_TRAP			0x25
+#else
+#define ECR_V_MEM_ERR			0x01
+#define ECR_V_INSN_ERR			0x02
+#define ECR_V_MACH_CHK			0x03
+#define ECR_V_ITLB_MISS			0x04
+#define ECR_V_DTLB_MISS			0x05
+#define ECR_V_PROTV			0x06
+#define ECR_V_TRAP			0x09
+#endif
 
 /* DTLB Miss and Protection Violation Cause Codes */
 
@@ -76,9 +89,6 @@
 #define ECR_C_BIT_DTLB_LD_MISS		8
 #define ECR_C_BIT_DTLB_ST_MISS		9
 
-/* Dummy ECR values for Interrupts */
-#define event_IRQ1		0x0031abcd
-#define event_IRQ2		0x0032abcd
 
 /* Auxiliary registers */
 #define AUX_IDENTITY		4
@@ -204,9 +214,11 @@
 
 struct bcr_isa {
 #ifdef CONFIG_CPU_BIG_ENDIAN
-	unsigned int pad1:23, atomic1:1, ver:8;
+	unsigned int div_rem:4, pad2:4, ldd:1, unalign:1, atomic:1, be:1,
+		     pad1:11, atomic1:1, ver:8;
 #else
-	unsigned int ver:8, atomic1:1, pad1:23;
+	unsigned int ver:8, atomic1:1, pad1:11, be:1, atomic:1, unalign:1,
+		     ldd:1, pad2:4, div_rem:4;
 #endif
 };
 
@@ -269,11 +281,19 @@
 #endif
 };
 
+struct bcr_fp_arcv2 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad2:15, dp:1, pad1:7, sp:1, ver:8;
+#else
+	unsigned int ver:8, sp:1, pad1:7, dp:1, pad2:15;
+#endif
+};
+
 struct bcr_timer {
 #ifdef CONFIG_CPU_BIG_ENDIAN
-	unsigned int pad2:15, rtsc:1, pad1:6, t1:1, t0:1, ver:8;
+	unsigned int pad2:15, rtsc:1, pad1:5, rtc:1, t1:1, t0:1, ver:8;
 #else
-	unsigned int ver:8, t0:1, t1:1, pad1:6, rtsc:1, pad2:15;
+	unsigned int ver:8, t0:1, t1:1, rtc:1, pad1:5, rtsc:1, pad2:15;
 #endif
 };
 
@@ -285,6 +305,14 @@
 #endif
 };
 
+struct bcr_bpu_arcv2 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad:6, fbe:2, tqe:2, ts:4, ft:1, rse:2, pte:3, bce:3, ver:8;
+#else
+	unsigned int ver:8, bce:3, pte:3, rse:2, ft:1, ts:4, tqe:2, fbe:2, pad:6;
+#endif
+};
+
 struct bcr_generic {
 #ifdef CONFIG_CPU_BIG_ENDIAN
 	unsigned int pad:24, ver:8;
@@ -299,11 +327,12 @@
  */
 
 struct cpuinfo_arc_mmu {
-	unsigned int ver, pg_sz, sets, ways, u_dtlb, u_itlb, num_tlb;
+	unsigned int ver:4, pg_sz_k:8, s_pg_sz_m:8, u_dtlb:6, u_itlb:6;
+	unsigned int num_tlb:16, sets:12, ways:4;
 };
 
 struct cpuinfo_arc_cache {
-	unsigned int sz_k:8, line_len:8, assoc:4, ver:4, alias:1, vipt:1, pad:6;
+	unsigned int sz_k:14, line_len:8, assoc:4, ver:4, alias:1, vipt:1;
 };
 
 struct cpuinfo_arc_bpu {
@@ -315,14 +344,13 @@
 };
 
 struct cpuinfo_arc {
-	struct cpuinfo_arc_cache icache, dcache;
+	struct cpuinfo_arc_cache icache, dcache, slc;
 	struct cpuinfo_arc_mmu mmu;
 	struct cpuinfo_arc_bpu bpu;
 	struct bcr_identity core;
 	struct bcr_isa isa;
 	struct bcr_timer timers;
 	unsigned int vec_base;
-	unsigned int uncached_base;
 	struct cpuinfo_arc_ccm iccm, dccm;
 	struct {
 		unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, pad1:3,
@@ -336,6 +364,22 @@
 
 extern struct cpuinfo_arc cpuinfo_arc700[];
 
+static inline int is_isa_arcv2(void)
+{
+	return IS_ENABLED(CONFIG_ISA_ARCV2);
+}
+
+static inline int is_isa_arcompact(void)
+{
+	return IS_ENABLED(CONFIG_ISA_ARCOMPACT);
+}
+
+#if defined(CONFIG_ISA_ARCOMPACT) && !defined(_CPU_DEFAULT_A7)
+#error "Toolchain not configured for ARCompact builds"
+#elif defined(CONFIG_ISA_ARCV2) && !defined(_CPU_DEFAULT_HS)
+#error "Toolchain not configured for ARCv2 builds"
+#endif
+
 #endif /* __ASEMBLY__ */
 
 #endif /* _ASM_ARC_ARCREGS_H */
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 9917a45..03484cb 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -23,13 +23,21 @@
 
 #define atomic_set(v, i) (((v)->counter) = (i))
 
+#ifdef CONFIG_ISA_ARCV2
+#define PREFETCHW	"	prefetchw   [%1]	\n"
+#else
+#define PREFETCHW
+#endif
+
 #define ATOMIC_OP(op, c_op, asm_op)					\
 static inline void atomic_##op(int i, atomic_t *v)			\
 {									\
 	unsigned int temp;						\
 									\
 	__asm__ __volatile__(						\
-	"1:	llock   %0, [%1]	\n"				\
+	"1:				\n"				\
+	PREFETCHW							\
+	"	llock   %0, [%1]	\n"				\
 	"	" #asm_op " %0, %0, %2	\n"				\
 	"	scond   %0, [%1]	\n"				\
 	"	bnz     1b		\n"				\
@@ -43,8 +51,16 @@
 {									\
 	unsigned int temp;						\
 									\
+	/*								\
+	 * Explicit full memory barrier needed before/after as		\
+	 * LLOCK/SCOND thmeselves don't provide any such semantics	\
+	 */								\
+	smp_mb();							\
+									\
 	__asm__ __volatile__(						\
-	"1:	llock   %0, [%1]	\n"				\
+	"1:				\n"				\
+	PREFETCHW							\
+	"	llock   %0, [%1]	\n"				\
 	"	" #asm_op " %0, %0, %2	\n"				\
 	"	scond   %0, [%1]	\n"				\
 	"	bnz     1b		\n"				\
@@ -52,6 +68,8 @@
 	: "r"(&v->counter), "ir"(i)					\
 	: "cc");							\
 									\
+	smp_mb();							\
+									\
 	return temp;							\
 }
 
@@ -105,6 +123,9 @@
 	unsigned long flags;						\
 	unsigned long temp;						\
 									\
+	/*								\
+	 * spin lock/unlock provides the needed smp_mb() before/after	\
+	 */								\
 	atomic_ops_lock(flags);						\
 	temp = v->counter;						\
 	temp c_op i;							\
@@ -142,9 +163,19 @@
 #define __atomic_add_unless(v, a, u)					\
 ({									\
 	int c, old;							\
+									\
+	/*								\
+	 * Explicit full memory barrier needed before/after as		\
+	 * LLOCK/SCOND thmeselves don't provide any such semantics	\
+	 */								\
+	smp_mb();							\
+									\
 	c = atomic_read(v);						\
 	while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c)\
 		c = old;						\
+									\
+	smp_mb();							\
+									\
 	c;								\
 })
 
diff --git a/arch/arc/include/asm/barrier.h b/arch/arc/include/asm/barrier.h
new file mode 100644
index 0000000..a720998
--- /dev/null
+++ b/arch/arc/include/asm/barrier.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_BARRIER_H
+#define __ASM_BARRIER_H
+
+#ifdef CONFIG_ISA_ARCV2
+
+/*
+ * ARCv2 based HS38 cores are in-order issue, but still weakly ordered
+ * due to micro-arch buffering/queuing of load/store, cache hit vs. miss ...
+ *
+ * Explicit barrier provided by DMB instruction
+ *  - Operand supports fine grained load/store/load+store semantics
+ *  - Ensures that selected memory operation issued before it will complete
+ *    before any subsequent memory operation of same type
+ *  - DMB guarantees SMP as well as local barrier semantics
+ *    (asm-generic/barrier.h ensures sane smp_*mb if not defined here, i.e.
+ *    UP: barrier(), SMP: smp_*mb == *mb)
+ *  - DSYNC provides DMB+completion_of_cache_bpu_maintenance_ops hence not needed
+ *    in the general case. Plus it only provides full barrier.
+ */
+
+#define mb()	asm volatile("dmb 3\n" : : : "memory")
+#define rmb()	asm volatile("dmb 1\n" : : : "memory")
+#define wmb()	asm volatile("dmb 2\n" : : : "memory")
+
+#endif
+
+#ifdef CONFIG_ISA_ARCOMPACT
+
+/*
+ * ARCompact based cores (ARC700) only have SYNC instruction which is super
+ * heavy weight as it flushes the pipeline as well.
+ * There are no real SMP implementations of such cores.
+ */
+
+#define mb()	asm volatile("sync\n" : : : "memory")
+#endif
+
+#include <asm-generic/barrier.h>
+
+#endif
diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h
index 4051e95..99fe118 100644
--- a/arch/arc/include/asm/bitops.h
+++ b/arch/arc/include/asm/bitops.h
@@ -18,83 +18,50 @@
 #include <linux/types.h>
 #include <linux/compiler.h>
 #include <asm/barrier.h>
+#ifndef CONFIG_ARC_HAS_LLSC
+#include <asm/smp.h>
+#endif
 
-/*
- * Hardware assisted read-modify-write using ARC700 LLOCK/SCOND insns.
- * The Kconfig glue ensures that in SMP, this is only set if the container
- * SoC/platform has cross-core coherent LLOCK/SCOND
- */
 #if defined(CONFIG_ARC_HAS_LLSC)
 
-static inline void set_bit(unsigned long nr, volatile unsigned long *m)
-{
-	unsigned int temp;
+/*
+ * Hardware assisted Atomic-R-M-W
+ */
 
-	m += nr >> 5;
-
-	/*
-	 * ARC ISA micro-optimization:
-	 *
-	 * Instructions dealing with bitpos only consider lower 5 bits (0-31)
-	 * e.g (x << 33) is handled like (x << 1) by ASL instruction
-	 *  (mem pointer still needs adjustment to point to next word)
-	 *
-	 * Hence the masking to clamp @nr arg can be elided in general.
-	 *
-	 * However if @nr is a constant (above assumed it in a register),
-	 * and greater than 31, gcc can optimize away (x << 33) to 0,
-	 * as overflow, given the 32-bit ISA. Thus masking needs to be done
-	 * for constant @nr, but no code is generated due to const prop.
-	 */
-	if (__builtin_constant_p(nr))
-		nr &= 0x1f;
-
-	__asm__ __volatile__(
-	"1:	llock   %0, [%1]	\n"
-	"	bset    %0, %0, %2	\n"
-	"	scond   %0, [%1]	\n"
-	"	bnz     1b	\n"
-	: "=&r"(temp)
-	: "r"(m), "ir"(nr)
-	: "cc");
-}
-
-static inline void clear_bit(unsigned long nr, volatile unsigned long *m)
-{
-	unsigned int temp;
-
-	m += nr >> 5;
-
-	if (__builtin_constant_p(nr))
-		nr &= 0x1f;
-
-	__asm__ __volatile__(
-	"1:	llock   %0, [%1]	\n"
-	"	bclr    %0, %0, %2	\n"
-	"	scond   %0, [%1]	\n"
-	"	bnz     1b	\n"
-	: "=&r"(temp)
-	: "r"(m), "ir"(nr)
-	: "cc");
-}
-
-static inline void change_bit(unsigned long nr, volatile unsigned long *m)
-{
-	unsigned int temp;
-
-	m += nr >> 5;
-
-	if (__builtin_constant_p(nr))
-		nr &= 0x1f;
-
-	__asm__ __volatile__(
-	"1:	llock   %0, [%1]	\n"
-	"	bxor    %0, %0, %2	\n"
-	"	scond   %0, [%1]	\n"
-	"	bnz     1b		\n"
-	: "=&r"(temp)
-	: "r"(m), "ir"(nr)
-	: "cc");
+#define BIT_OP(op, c_op, asm_op)					\
+static inline void op##_bit(unsigned long nr, volatile unsigned long *m)\
+{									\
+	unsigned int temp;						\
+									\
+	m += nr >> 5;							\
+									\
+	/*								\
+	 * ARC ISA micro-optimization:					\
+	 *								\
+	 * Instructions dealing with bitpos only consider lower 5 bits	\
+	 * e.g (x << 33) is handled like (x << 1) by ASL instruction	\
+	 *  (mem pointer still needs adjustment to point to next word)	\
+	 *								\
+	 * Hence the masking to clamp @nr arg can be elided in general.	\
+	 *								\
+	 * However if @nr is a constant (above assumed in a register),	\
+	 * and greater than 31, gcc can optimize away (x << 33) to 0,	\
+	 * as overflow, given the 32-bit ISA. Thus masking needs to be	\
+	 * done for const @nr, but no code is generated due to gcc	\
+	 * const prop.							\
+	 */								\
+	if (__builtin_constant_p(nr))					\
+		nr &= 0x1f;						\
+									\
+	__asm__ __volatile__(						\
+	"1:	llock       %0, [%1]		\n"			\
+	"	" #asm_op " %0, %0, %2	\n"				\
+	"	scond       %0, [%1]		\n"			\
+	"	bnz         1b			\n"			\
+	: "=&r"(temp)	/* Early clobber, to prevent reg reuse */	\
+	: "r"(m),	/* Not "m": llock only supports reg direct addr mode */	\
+	  "ir"(nr)							\
+	: "cc");							\
 }
 
 /*
@@ -108,75 +75,38 @@
  * Since ARC lacks a equivalent h/w primitive, the bit is set unconditionally
  * and the old value of bit is returned
  */
-static inline int test_and_set_bit(unsigned long nr, volatile unsigned long *m)
-{
-	unsigned long old, temp;
-
-	m += nr >> 5;
-
-	if (__builtin_constant_p(nr))
-		nr &= 0x1f;
-
-	__asm__ __volatile__(
-	"1:	llock   %0, [%2]	\n"
-	"	bset    %1, %0, %3	\n"
-	"	scond   %1, [%2]	\n"
-	"	bnz     1b		\n"
-	: "=&r"(old), "=&r"(temp)
-	: "r"(m), "ir"(nr)
-	: "cc");
-
-	return (old & (1 << nr)) != 0;
-}
-
-static inline int
-test_and_clear_bit(unsigned long nr, volatile unsigned long *m)
-{
-	unsigned int old, temp;
-
-	m += nr >> 5;
-
-	if (__builtin_constant_p(nr))
-		nr &= 0x1f;
-
-	__asm__ __volatile__(
-	"1:	llock   %0, [%2]	\n"
-	"	bclr    %1, %0, %3	\n"
-	"	scond   %1, [%2]	\n"
-	"	bnz     1b		\n"
-	: "=&r"(old), "=&r"(temp)
-	: "r"(m), "ir"(nr)
-	: "cc");
-
-	return (old & (1 << nr)) != 0;
-}
-
-static inline int
-test_and_change_bit(unsigned long nr, volatile unsigned long *m)
-{
-	unsigned int old, temp;
-
-	m += nr >> 5;
-
-	if (__builtin_constant_p(nr))
-		nr &= 0x1f;
-
-	__asm__ __volatile__(
-	"1:	llock   %0, [%2]	\n"
-	"	bxor    %1, %0, %3	\n"
-	"	scond   %1, [%2]	\n"
-	"	bnz     1b		\n"
-	: "=&r"(old), "=&r"(temp)
-	: "r"(m), "ir"(nr)
-	: "cc");
-
-	return (old & (1 << nr)) != 0;
+#define TEST_N_BIT_OP(op, c_op, asm_op)					\
+static inline int test_and_##op##_bit(unsigned long nr, volatile unsigned long *m)\
+{									\
+	unsigned long old, temp;					\
+									\
+	m += nr >> 5;							\
+									\
+	if (__builtin_constant_p(nr))					\
+		nr &= 0x1f;						\
+									\
+	/*								\
+	 * Explicit full memory barrier needed before/after as		\
+	 * LLOCK/SCOND themselves don't provide any such smenatic	\
+	 */								\
+	smp_mb();							\
+									\
+	__asm__ __volatile__(						\
+	"1:	llock       %0, [%2]	\n"				\
+	"	" #asm_op " %1, %0, %3	\n"				\
+	"	scond       %1, [%2]	\n"				\
+	"	bnz         1b		\n"				\
+	: "=&r"(old), "=&r"(temp)					\
+	: "r"(m), "ir"(nr)						\
+	: "cc");							\
+									\
+	smp_mb();							\
+									\
+	return (old & (1 << nr)) != 0;					\
 }
 
 #else	/* !CONFIG_ARC_HAS_LLSC */
 
-#include <asm/smp.h>
-
 /*
  * Non hardware assisted Atomic-R-M-W
  * Locking would change to irq-disabling only (UP) and spinlocks (SMP)
@@ -193,108 +123,43 @@
  *             at compile time)
  */
 
-static inline void set_bit(unsigned long nr, volatile unsigned long *m)
-{
-	unsigned long temp, flags;
-	m += nr >> 5;
-
-	if (__builtin_constant_p(nr))
-		nr &= 0x1f;
-
-	bitops_lock(flags);
-
-	temp = *m;
-	*m = temp | (1UL << nr);
-
-	bitops_unlock(flags);
+#define BIT_OP(op, c_op, asm_op)					\
+static inline void op##_bit(unsigned long nr, volatile unsigned long *m)\
+{									\
+	unsigned long temp, flags;					\
+	m += nr >> 5;							\
+									\
+	if (__builtin_constant_p(nr))					\
+		nr &= 0x1f;						\
+									\
+	/*								\
+	 * spin lock/unlock provide the needed smp_mb() before/after	\
+	 */								\
+	bitops_lock(flags);						\
+									\
+	temp = *m;							\
+	*m = temp c_op (1UL << nr);					\
+									\
+	bitops_unlock(flags);						\
 }
 
-static inline void clear_bit(unsigned long nr, volatile unsigned long *m)
-{
-	unsigned long temp, flags;
-	m += nr >> 5;
-
-	if (__builtin_constant_p(nr))
-		nr &= 0x1f;
-
-	bitops_lock(flags);
-
-	temp = *m;
-	*m = temp & ~(1UL << nr);
-
-	bitops_unlock(flags);
-}
-
-static inline void change_bit(unsigned long nr, volatile unsigned long *m)
-{
-	unsigned long temp, flags;
-	m += nr >> 5;
-
-	if (__builtin_constant_p(nr))
-		nr &= 0x1f;
-
-	bitops_lock(flags);
-
-	temp = *m;
-	*m = temp ^ (1UL << nr);
-
-	bitops_unlock(flags);
-}
-
-static inline int test_and_set_bit(unsigned long nr, volatile unsigned long *m)
-{
-	unsigned long old, flags;
-	m += nr >> 5;
-
-	if (__builtin_constant_p(nr))
-		nr &= 0x1f;
-
-	bitops_lock(flags);
-
-	old = *m;
-	*m = old | (1 << nr);
-
-	bitops_unlock(flags);
-
-	return (old & (1 << nr)) != 0;
-}
-
-static inline int
-test_and_clear_bit(unsigned long nr, volatile unsigned long *m)
-{
-	unsigned long old, flags;
-	m += nr >> 5;
-
-	if (__builtin_constant_p(nr))
-		nr &= 0x1f;
-
-	bitops_lock(flags);
-
-	old = *m;
-	*m = old & ~(1 << nr);
-
-	bitops_unlock(flags);
-
-	return (old & (1 << nr)) != 0;
-}
-
-static inline int
-test_and_change_bit(unsigned long nr, volatile unsigned long *m)
-{
-	unsigned long old, flags;
-	m += nr >> 5;
-
-	if (__builtin_constant_p(nr))
-		nr &= 0x1f;
-
-	bitops_lock(flags);
-
-	old = *m;
-	*m = old ^ (1 << nr);
-
-	bitops_unlock(flags);
-
-	return (old & (1 << nr)) != 0;
+#define TEST_N_BIT_OP(op, c_op, asm_op)					\
+static inline int test_and_##op##_bit(unsigned long nr, volatile unsigned long *m)\
+{									\
+	unsigned long old, flags;					\
+	m += nr >> 5;							\
+									\
+	if (__builtin_constant_p(nr))					\
+		nr &= 0x1f;						\
+									\
+	bitops_lock(flags);						\
+									\
+	old = *m;							\
+	*m = old c_op (1 << nr);					\
+									\
+	bitops_unlock(flags);						\
+									\
+	return (old & (1 << nr)) != 0;					\
 }
 
 #endif /* CONFIG_ARC_HAS_LLSC */
@@ -303,86 +168,51 @@
  * Non atomic variants
  **************************************/
 
-static inline void __set_bit(unsigned long nr, volatile unsigned long *m)
-{
-	unsigned long temp;
-	m += nr >> 5;
-
-	if (__builtin_constant_p(nr))
-		nr &= 0x1f;
-
-	temp = *m;
-	*m = temp | (1UL << nr);
+#define __BIT_OP(op, c_op, asm_op)					\
+static inline void __##op##_bit(unsigned long nr, volatile unsigned long *m)	\
+{									\
+	unsigned long temp;						\
+	m += nr >> 5;							\
+									\
+	if (__builtin_constant_p(nr))					\
+		nr &= 0x1f;						\
+									\
+	temp = *m;							\
+	*m = temp c_op (1UL << nr);					\
 }
 
-static inline void __clear_bit(unsigned long nr, volatile unsigned long *m)
-{
-	unsigned long temp;
-	m += nr >> 5;
-
-	if (__builtin_constant_p(nr))
-		nr &= 0x1f;
-
-	temp = *m;
-	*m = temp & ~(1UL << nr);
+#define __TEST_N_BIT_OP(op, c_op, asm_op)				\
+static inline int __test_and_##op##_bit(unsigned long nr, volatile unsigned long *m)\
+{									\
+	unsigned long old;						\
+	m += nr >> 5;							\
+									\
+	if (__builtin_constant_p(nr))					\
+		nr &= 0x1f;						\
+									\
+	old = *m;							\
+	*m = old c_op (1 << nr);					\
+									\
+	return (old & (1 << nr)) != 0;					\
 }
 
-static inline void __change_bit(unsigned long nr, volatile unsigned long *m)
-{
-	unsigned long temp;
-	m += nr >> 5;
+#define BIT_OPS(op, c_op, asm_op)					\
+									\
+	/* set_bit(), clear_bit(), change_bit() */			\
+	BIT_OP(op, c_op, asm_op)					\
+									\
+	/* test_and_set_bit(), test_and_clear_bit(), test_and_change_bit() */\
+	TEST_N_BIT_OP(op, c_op, asm_op)					\
+									\
+	/* __set_bit(), __clear_bit(), __change_bit() */		\
+	__BIT_OP(op, c_op, asm_op)					\
+									\
+	/* __test_and_set_bit(), __test_and_clear_bit(), __test_and_change_bit() */\
+	__TEST_N_BIT_OP(op, c_op, asm_op)
 
-	if (__builtin_constant_p(nr))
-		nr &= 0x1f;
-
-	temp = *m;
-	*m = temp ^ (1UL << nr);
-}
-
-static inline int
-__test_and_set_bit(unsigned long nr, volatile unsigned long *m)
-{
-	unsigned long old;
-	m += nr >> 5;
-
-	if (__builtin_constant_p(nr))
-		nr &= 0x1f;
-
-	old = *m;
-	*m = old | (1 << nr);
-
-	return (old & (1 << nr)) != 0;
-}
-
-static inline int
-__test_and_clear_bit(unsigned long nr, volatile unsigned long *m)
-{
-	unsigned long old;
-	m += nr >> 5;
-
-	if (__builtin_constant_p(nr))
-		nr &= 0x1f;
-
-	old = *m;
-	*m = old & ~(1 << nr);
-
-	return (old & (1 << nr)) != 0;
-}
-
-static inline int
-__test_and_change_bit(unsigned long nr, volatile unsigned long *m)
-{
-	unsigned long old;
-	m += nr >> 5;
-
-	if (__builtin_constant_p(nr))
-		nr &= 0x1f;
-
-	old = *m;
-	*m = old ^ (1 << nr);
-
-	return (old & (1 << nr)) != 0;
-}
+BIT_OPS(set, |, bset)
+BIT_OPS(clear, & ~, bclr)
+BIT_OPS(change, ^, bxor)
 
 /*
  * This routine doesn't need to be atomic.
@@ -402,6 +232,8 @@
 	return ((mask & *addr) != 0);
 }
 
+#ifdef CONFIG_ISA_ARCOMPACT
+
 /*
  * Count the number of zeros, starting from MSB
  * Helper for fls( ) friends
@@ -494,6 +326,75 @@
 	return ffs(word) - 1;
 }
 
+#else	/* CONFIG_ISA_ARCV2 */
+
+/*
+ * fls = Find Last Set in word
+ * @result: [1-32]
+ * fls(1) = 1, fls(0x80000000) = 32, fls(0) = 0
+ */
+static inline __attribute__ ((const)) int fls(unsigned long x)
+{
+	int n;
+
+	asm volatile(
+	"	fls.f	%0, %1		\n"  /* 0:31; 0(Z) if src 0 */
+	"	add.nz	%0, %0, 1	\n"  /* 0:31 -> 1:32 */
+	: "=r"(n)	/* Early clobber not needed */
+	: "r"(x)
+	: "cc");
+
+	return n;
+}
+
+/*
+ * __fls: Similar to fls, but zero based (0-31). Also 0 if no bit set
+ */
+static inline __attribute__ ((const)) int __fls(unsigned long x)
+{
+	/* FLS insn has exactly same semantics as the API */
+	return	__builtin_arc_fls(x);
+}
+
+/*
+ * ffs = Find First Set in word (LSB to MSB)
+ * @result: [1-32], 0 if all 0's
+ */
+static inline __attribute__ ((const)) int ffs(unsigned long x)
+{
+	int n;
+
+	asm volatile(
+	"	ffs.f	%0, %1		\n"  /* 0:31; 31(Z) if src 0 */
+	"	add.nz	%0, %0, 1	\n"  /* 0:31 -> 1:32 */
+	"	mov.z	%0, 0		\n"  /* 31(Z)-> 0 */
+	: "=r"(n)	/* Early clobber not needed */
+	: "r"(x)
+	: "cc");
+
+	return n;
+}
+
+/*
+ * __ffs: Similar to ffs, but zero based (0-31)
+ */
+static inline __attribute__ ((const)) int __ffs(unsigned long x)
+{
+	int n;
+
+	asm volatile(
+	"	ffs.f	%0, %1		\n"  /* 0:31; 31(Z) if src 0 */
+	"	mov.z	%0, 0		\n"  /* 31(Z)-> 0 */
+	: "=r"(n)
+	: "r"(x)
+	: "cc");
+
+	return n;
+
+}
+
+#endif	/* CONFIG_ISA_ARCOMPACT */
+
 /*
  * ffz = Find First Zero in word.
  * @return:[0-31], 32 if all 1's
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index 7861255..d67345d 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -60,7 +60,7 @@
 #define ARC_REG_IC_IVIC		0x10
 #define ARC_REG_IC_CTRL		0x11
 #define ARC_REG_IC_IVIL		0x19
-#if defined(CONFIG_ARC_MMU_V3)
+#if defined(CONFIG_ARC_MMU_V3) || defined(CONFIG_ARC_MMU_V4)
 #define ARC_REG_IC_PTAG		0x1E
 #endif
 
@@ -74,12 +74,24 @@
 #define ARC_REG_DC_IVDL		0x4A
 #define ARC_REG_DC_FLSH		0x4B
 #define ARC_REG_DC_FLDL		0x4C
-#if defined(CONFIG_ARC_MMU_V3)
 #define ARC_REG_DC_PTAG		0x5C
-#endif
 
 /* Bit val in DC_CTRL */
 #define DC_CTRL_INV_MODE_FLUSH  0x40
 #define DC_CTRL_FLUSH_STATUS    0x100
 
+/*System-level cache (L2 cache) related Auxiliary registers */
+#define ARC_REG_SLC_CFG		0x901
+#define ARC_REG_SLC_CTRL	0x903
+#define ARC_REG_SLC_FLUSH	0x904
+#define ARC_REG_SLC_INVALIDATE	0x905
+#define ARC_REG_SLC_RGN_START	0x914
+#define ARC_REG_SLC_RGN_END	0x916
+
+/* Bit val in SLC_CONTROL */
+#define SLC_CTRL_IM		0x040
+#define SLC_CTRL_DISABLE	0x001
+#define SLC_CTRL_BUSY		0x100
+#define SLC_CTRL_RGN_OP_INV	0x200
+
 #endif /* _ASM_CACHE_H */
diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h
index 6abc497..0992d3d 100644
--- a/arch/arc/include/asm/cacheflush.h
+++ b/arch/arc/include/asm/cacheflush.h
@@ -34,9 +34,7 @@
 void flush_icache_range(unsigned long start, unsigned long end);
 void __sync_icache_dcache(unsigned long paddr, unsigned long vaddr, int len);
 void __inv_icache_page(unsigned long paddr, unsigned long vaddr);
-void ___flush_dcache_page(unsigned long paddr, unsigned long vaddr);
-#define __flush_dcache_page(p, v)	\
-		___flush_dcache_page((unsigned long)p, (unsigned long)v)
+void __flush_dcache_page(unsigned long paddr, unsigned long vaddr);
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 
diff --git a/arch/arc/include/asm/cmpxchg.h b/arch/arc/include/asm/cmpxchg.h
index 03cd689..44fd531 100644
--- a/arch/arc/include/asm/cmpxchg.h
+++ b/arch/arc/include/asm/cmpxchg.h
@@ -10,6 +10,8 @@
 #define __ASM_ARC_CMPXCHG_H
 
 #include <linux/types.h>
+
+#include <asm/barrier.h>
 #include <asm/smp.h>
 
 #ifdef CONFIG_ARC_HAS_LLSC
@@ -19,16 +21,25 @@
 {
 	unsigned long prev;
 
+	/*
+	 * Explicit full memory barrier needed before/after as
+	 * LLOCK/SCOND thmeselves don't provide any such semantics
+	 */
+	smp_mb();
+
 	__asm__ __volatile__(
 	"1:	llock   %0, [%1]	\n"
 	"	brne    %0, %2, 2f	\n"
 	"	scond   %3, [%1]	\n"
 	"	bnz     1b		\n"
 	"2:				\n"
-	: "=&r"(prev)
-	: "r"(ptr), "ir"(expected),
-	  "r"(new) /* can't be "ir". scond can't take limm for "b" */
-	: "cc");
+	: "=&r"(prev)	/* Early clobber, to prevent reg reuse */
+	: "r"(ptr),	/* Not "m": llock only supports reg direct addr mode */
+	  "ir"(expected),
+	  "r"(new)	/* can't be "ir". scond can't take LIMM for "b" */
+	: "cc", "memory"); /* so that gcc knows memory is being written here */
+
+	smp_mb();
 
 	return prev;
 }
@@ -42,6 +53,9 @@
 	int prev;
 	volatile unsigned long *p = ptr;
 
+	/*
+	 * spin lock/unlock provide the needed smp_mb() before/after
+	 */
 	atomic_ops_lock(flags);
 	prev = *p;
 	if (prev == expected)
@@ -77,12 +91,16 @@
 
 	switch (size) {
 	case 4:
+		smp_mb();
+
 		__asm__ __volatile__(
 		"	ex  %0, [%1]	\n"
 		: "+r"(val)
 		: "r"(ptr)
 		: "memory");
 
+		smp_mb();
+
 		return val;
 	}
 	return __xchg_bad_pointer();
diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h
index 43de302..08e7e2a 100644
--- a/arch/arc/include/asm/delay.h
+++ b/arch/arc/include/asm/delay.h
@@ -22,11 +22,10 @@
 static inline void __delay(unsigned long loops)
 {
 	__asm__ __volatile__(
-	"1:	sub.f %0, %0, 1	\n"
-	"	jpnz 1b		\n"
-	: "+r"(loops)
-	:
-	: "cc");
+	"	lp  1f	\n"
+	"	nop	\n"
+	"1:		\n"
+	: "+l"(loops));
 }
 
 extern void __bad_udelay(void);
diff --git a/arch/arc/include/asm/dma-mapping.h b/arch/arc/include/asm/dma-mapping.h
index 45b8e0c..2d28ba9 100644
--- a/arch/arc/include/asm/dma-mapping.h
+++ b/arch/arc/include/asm/dma-mapping.h
@@ -14,23 +14,6 @@
 #include <asm-generic/dma-coherent.h>
 #include <asm/cacheflush.h>
 
-#ifndef CONFIG_ARC_PLAT_NEEDS_CPU_TO_DMA
-/*
- * dma_map_* API take cpu addresses, which is kernel logical address in the
- * untranslated address space (0x8000_0000) based. The dma address (bus addr)
- * ideally needs to be 0x0000_0000 based hence these glue routines.
- * However given that intermediate bus bridges can ignore the high bit, we can
- * do with these routines being no-ops.
- * If a platform/device comes up which sriclty requires 0 based bus addr
- * (e.g. AHB-PCI bridge on Angel4 board), then it can provide it's own versions
- */
-#define plat_dma_addr_to_kernel(dev, addr) ((unsigned long)(addr))
-#define plat_kernel_addr_to_dma(dev, ptr) ((dma_addr_t)(ptr))
-
-#else
-#include <plat/dma_addr.h>
-#endif
-
 void *dma_alloc_noncoherent(struct device *dev, size_t size,
 			    dma_addr_t *dma_handle, gfp_t gfp);
 
@@ -94,7 +77,7 @@
 	       enum dma_data_direction dir)
 {
 	_dma_cache_sync((unsigned long)cpu_addr, size, dir);
-	return plat_kernel_addr_to_dma(dev, cpu_addr);
+	return (dma_addr_t)cpu_addr;
 }
 
 static inline void
@@ -147,16 +130,14 @@
 dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
 			size_t size, enum dma_data_direction dir)
 {
-	_dma_cache_sync(plat_dma_addr_to_kernel(dev, dma_handle), size,
-			DMA_FROM_DEVICE);
+	_dma_cache_sync(dma_handle, size, DMA_FROM_DEVICE);
 }
 
 static inline void
 dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle,
 			   size_t size, enum dma_data_direction dir)
 {
-	_dma_cache_sync(plat_dma_addr_to_kernel(dev, dma_handle), size,
-			DMA_TO_DEVICE);
+	_dma_cache_sync(dma_handle, size, DMA_TO_DEVICE);
 }
 
 static inline void
@@ -164,8 +145,7 @@
 			      unsigned long offset, size_t size,
 			      enum dma_data_direction direction)
 {
-	_dma_cache_sync(plat_dma_addr_to_kernel(dev, dma_handle) + offset,
-			size, DMA_FROM_DEVICE);
+	_dma_cache_sync(dma_handle + offset, size, DMA_FROM_DEVICE);
 }
 
 static inline void
@@ -173,27 +153,28 @@
 				 unsigned long offset, size_t size,
 				 enum dma_data_direction direction)
 {
-	_dma_cache_sync(plat_dma_addr_to_kernel(dev, dma_handle) + offset,
-			size, DMA_TO_DEVICE);
+	_dma_cache_sync(dma_handle + offset, size, DMA_TO_DEVICE);
 }
 
 static inline void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
+dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, int nelems,
 		    enum dma_data_direction dir)
 {
 	int i;
+	struct scatterlist *sg;
 
-	for (i = 0; i < nelems; i++, sg++)
+	for_each_sg(sglist, sg, nelems, i)
 		_dma_cache_sync((unsigned int)sg_virt(sg), sg->length, dir);
 }
 
 static inline void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems,
-		       enum dma_data_direction dir)
+dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist,
+		       int nelems, enum dma_data_direction dir)
 {
 	int i;
+	struct scatterlist *sg;
 
-	for (i = 0; i < nelems; i++, sg++)
+	for_each_sg(sglist, sg, nelems, i)
 		_dma_cache_sync((unsigned int)sg_virt(sg), sg->length, dir);
 }
 
diff --git a/arch/arc/include/asm/elf.h b/arch/arc/include/asm/elf.h
index a262828..51a99e2 100644
--- a/arch/arc/include/asm/elf.h
+++ b/arch/arc/include/asm/elf.h
@@ -15,6 +15,11 @@
 /* These ELF defines belong to uapi but libc elf.h already defines them */
 #define EM_ARCOMPACT		93
 
+#define EM_ARCV2		195	/* ARCv2 Cores */
+
+#define EM_ARC_INUSE		(IS_ENABLED(CONFIG_ISA_ARCOMPACT) ? \
+					EM_ARCOMPACT : EM_ARCV2)
+
 /* ARC Relocations (kernel Modules only) */
 #define  R_ARC_32		0x4
 #define  R_ARC_32_ME		0x1B
diff --git a/arch/arc/include/asm/entry-arcv2.h b/arch/arc/include/asm/entry-arcv2.h
new file mode 100644
index 0000000..b5ff87e
--- /dev/null
+++ b/arch/arc/include/asm/entry-arcv2.h
@@ -0,0 +1,190 @@
+
+#ifndef __ASM_ARC_ENTRY_ARCV2_H
+#define __ASM_ARC_ENTRY_ARCV2_H
+
+#include <asm/asm-offsets.h>
+#include <asm/irqflags-arcv2.h>
+#include <asm/thread_info.h>	/* For THREAD_SIZE */
+
+/*------------------------------------------------------------------------*/
+.macro INTERRUPT_PROLOGUE	called_from
+
+	; Before jumping to Interrupt Vector, hardware micro-ops did following:
+	;   1. SP auto-switched to kernel mode stack
+	;   2. STATUS32.Z flag set to U mode at time of interrupt (U:1, K:0)
+	;   3. Auto saved: r0-r11, blink, LPE,LPS,LPC, JLI,LDI,EI, PC, STAT32
+	;
+	; Now manually save: r12, sp, fp, gp, r25
+
+	PUSH	r12
+
+	; Saving pt_regs->sp correctly requires some extra work due to the way
+	; Auto stack switch works
+	;  - U mode: retrieve it from AUX_USER_SP
+	;  - K mode: add the offset from current SP where H/w starts auto push
+	;
+	; Utilize the fact that Z bit is set if Intr taken in U mode
+	mov.nz	r9, sp
+	add.nz	r9, r9, SZ_PT_REGS - PT_sp - 4
+	bnz	1f
+
+	lr	r9, [AUX_USER_SP]
+1:
+	PUSH	r9	; SP
+
+	PUSH	fp
+	PUSH	gp
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+	PUSH	r25			; user_r25
+	GET_CURR_TASK_ON_CPU	r25
+#else
+	sub	sp, sp, 4
+#endif
+
+.ifnc \called_from, exception
+	sub	sp, sp, 12	; BTA/ECR/orig_r0 placeholder per pt_regs
+.endif
+
+.endm
+
+/*------------------------------------------------------------------------*/
+.macro INTERRUPT_EPILOGUE	called_from
+
+.ifnc \called_from, exception
+	add	sp, sp, 12	; skip BTA/ECR/orig_r0 placeholderss
+.endif
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+	POP	r25
+#else
+	add	sp, sp, 4
+#endif
+
+	POP	gp
+	POP	fp
+
+	; Don't touch AUX_USER_SP if returning to K mode (Z bit set)
+	; (Z bit set on K mode is inverse of INTERRUPT_PROLOGUE)
+	add.z	sp, sp, 4
+	bz	1f
+
+	POPAX	AUX_USER_SP
+1:
+	POP	r12
+
+.endm
+
+/*------------------------------------------------------------------------*/
+.macro EXCEPTION_PROLOGUE
+
+	; Before jumping to Exception Vector, hardware micro-ops did following:
+	;   1. SP auto-switched to kernel mode stack
+	;   2. STATUS32.Z flag set to U mode at time of interrupt (U:1,K:0)
+	;
+	; Now manually save the complete reg file
+
+	PUSH	r9		; freeup a register: slot of erstatus
+
+	PUSHAX	eret
+	sub	sp, sp, 12	; skip JLI, LDI, EI
+	PUSH	lp_count
+	PUSHAX	lp_start
+	PUSHAX	lp_end
+	PUSH	blink
+
+	PUSH	r11
+	PUSH	r10
+
+	ld.as	r9,  [sp, 10]	; load stashed r9 (status32 stack slot)
+	lr	r10, [erstatus]
+	st.as	r10, [sp, 10]	; save status32 at it's right stack slot
+
+	PUSH	r9
+	PUSH	r8
+	PUSH	r7
+	PUSH	r6
+	PUSH	r5
+	PUSH	r4
+	PUSH	r3
+	PUSH	r2
+	PUSH	r1
+	PUSH	r0
+
+	; -- for interrupts, regs above are auto-saved by h/w in that order --
+	; Now do what ISR prologue does (manually save r12, sp, fp, gp, r25)
+	;
+	; Set Z flag if this was from U mode (expected by INTERRUPT_PROLOGUE)
+	; Although H/w exception micro-ops do set Z flag for U mode (just like
+	; for interrupts), it could get clobbered in case we soft land here from
+	; a TLB Miss exception handler (tlbex.S)
+
+	and	r10, r10, STATUS_U_MASK
+	xor.f	0, r10, STATUS_U_MASK
+
+	INTERRUPT_PROLOGUE  exception
+
+	PUSHAX	erbta
+	PUSHAX	ecr		; r9 contains ECR, expected by EV_Trap
+
+	PUSH	r0		; orig_r0
+.endm
+
+/*------------------------------------------------------------------------*/
+.macro EXCEPTION_EPILOGUE
+
+	; Assumes r0 has PT_status32
+	btst   r0, STATUS_U_BIT	; Z flag set if K, used in INTERRUPT_EPILOGUE
+
+	add	sp, sp, 8	; orig_r0/ECR don't need restoring
+	POPAX	erbta
+
+	INTERRUPT_EPILOGUE  exception
+
+	POP	r0
+	POP	r1
+	POP	r2
+	POP	r3
+	POP	r4
+	POP	r5
+	POP	r6
+	POP	r7
+	POP	r8
+	POP	r9
+	POP	r10
+	POP	r11
+
+	POP	blink
+	POPAX	lp_end
+	POPAX	lp_start
+
+	POP	r9
+	mov	lp_count, r9
+
+	add	sp, sp, 12	; skip JLI, LDI, EI
+	POPAX	eret
+	POPAX	erstatus
+
+	ld.as	r9, [sp, -12]	; reload r9 which got clobbered
+.endm
+
+.macro FAKE_RET_FROM_EXCPN
+	lr      r9, [status32]
+	bic     r9, r9, (STATUS_U_MASK|STATUS_DE_MASK|STATUS_AE_MASK)
+	or      r9, r9, (STATUS_L_MASK|STATUS_IE_MASK)
+	kflag   r9
+.endm
+
+/* Get thread_info of "current" tsk */
+.macro GET_CURR_THR_INFO_FROM_SP  reg
+	bmskn \reg, sp, THREAD_SHIFT - 1
+.endm
+
+/* Get CPU-ID of this core */
+.macro  GET_CPU_ID  reg
+	lr  \reg, [identity]
+	xbfu \reg, \reg, 0xE8	/* 00111    01000 */
+				/* M = 8-1  N = 8 */
+.endm
+
+#endif
diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h
new file mode 100644
index 0000000..415443c
--- /dev/null
+++ b/arch/arc/include/asm/entry-compact.h
@@ -0,0 +1,307 @@
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Vineetg: March 2009 (Supporting 2 levels of Interrupts)
+ *  Stack switching code can no longer reliably rely on the fact that
+ *  if we are NOT in user mode, stack is switched to kernel mode.
+ *  e.g. L2 IRQ interrupted a L1 ISR which had not yet completed
+ *  it's prologue including stack switching from user mode
+ *
+ * Vineetg: Aug 28th 2008: Bug #94984
+ *  -Zero Overhead Loop Context shd be cleared when entering IRQ/EXcp/Trap
+ *   Normally CPU does this automatically, however when doing FAKE rtie,
+ *   we also need to explicitly do this. The problem in macros
+ *   FAKE_RET_FROM_EXCPN and FAKE_RET_FROM_EXCPN_LOCK_IRQ was that this bit
+ *   was being "CLEARED" rather then "SET". Actually "SET" clears ZOL context
+ *
+ * Vineetg: May 5th 2008
+ *  -Modified CALLEE_REG save/restore macros to handle the fact that
+ *      r25 contains the kernel current task ptr
+ *  - Defined Stack Switching Macro to be reused in all intr/excp hdlrs
+ *  - Shaved off 11 instructions from RESTORE_ALL_INT1 by using the
+ *      address Write back load ld.ab instead of seperate ld/add instn
+ *
+ * Amit Bhor, Sameer Dhavale: Codito Technologies 2004
+ */
+
+#ifndef __ASM_ARC_ENTRY_COMPACT_H
+#define __ASM_ARC_ENTRY_COMPACT_H
+
+#include <asm/asm-offsets.h>
+#include <asm/irqflags-compact.h>
+#include <asm/thread_info.h>	/* For THREAD_SIZE */
+
+/*--------------------------------------------------------------
+ * Switch to Kernel Mode stack if SP points to User Mode stack
+ *
+ * Entry   : r9 contains pre-IRQ/exception/trap status32
+ * Exit    : SP set to K mode stack
+ *           SP at the time of entry (K/U) saved @ pt_regs->sp
+ * Clobbers: r9
+ *-------------------------------------------------------------*/
+
+.macro SWITCH_TO_KERNEL_STK
+
+	/* User Mode when this happened ? Yes: Proceed to switch stack */
+	bbit1   r9, STATUS_U_BIT, 88f
+
+	/* OK we were already in kernel mode when this event happened, thus can
+	 * assume SP is kernel mode SP. _NO_ need to do any stack switching
+	 */
+
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
+	/* However....
+	 * If Level 2 Interrupts enabled, we may end up with a corner case:
+	 * 1. User Task executing
+	 * 2. L1 IRQ taken, ISR starts (CPU auto-switched to KERNEL mode)
+	 * 3. But before it could switch SP from USER to KERNEL stack
+	 *      a L2 IRQ "Interrupts" L1
+	 * Thay way although L2 IRQ happened in Kernel mode, stack is still
+	 * not switched.
+	 * To handle this, we may need to switch stack even if in kernel mode
+	 * provided SP has values in range of USER mode stack ( < 0x7000_0000 )
+	 */
+	brlo sp, VMALLOC_START, 88f
+
+	/* TODO: vineetg:
+	 * We need to be a bit more cautious here. What if a kernel bug in
+	 * L1 ISR, caused SP to go whaco (some small value which looks like
+	 * USER stk) and then we take L2 ISR.
+	 * Above brlo alone would treat it as a valid L1-L2 sceanrio
+	 * instead of shouting alound
+	 * The only feasible way is to make sure this L2 happened in
+	 * L1 prelogue ONLY i.e. ilink2 is less than a pre-set marker in
+	 * L1 ISR before it switches stack
+	 */
+
+#endif
+
+    /*------Intr/Ecxp happened in kernel mode, SP already setup ------ */
+	/* save it nevertheless @ pt_regs->sp for uniformity */
+
+	b.d	66f
+	st	sp, [sp, PT_sp - SZ_PT_REGS]
+
+88: /*------Intr/Ecxp happened in user mode, "switch" stack ------ */
+
+	GET_CURR_TASK_ON_CPU   r9
+
+	/* With current tsk in r9, get it's kernel mode stack base */
+	GET_TSK_STACK_BASE  r9, r9
+
+	/* save U mode SP @ pt_regs->sp */
+	st	sp, [r9, PT_sp - SZ_PT_REGS]
+
+	/* final SP switch */
+	mov	sp, r9
+66:
+.endm
+
+/*------------------------------------------------------------
+ * "FAKE" a rtie to return from CPU Exception context
+ * This is to re-enable Exceptions within exception
+ * Look at EV_ProtV to see how this is actually used
+ *-------------------------------------------------------------*/
+
+.macro FAKE_RET_FROM_EXCPN
+
+	ld  r9, [sp, PT_status32]
+	bic r9, r9, (STATUS_U_MASK|STATUS_DE_MASK)
+	bset  r9, r9, STATUS_L_BIT
+	sr  r9, [erstatus]
+	mov r9, 55f
+	sr  r9, [eret]
+
+	rtie
+55:
+.endm
+
+/*--------------------------------------------------------------
+ * For early Exception/ISR Prologue, a core reg is temporarily needed to
+ * code the rest of prolog (stack switching). This is done by stashing
+ * it to memory (non-SMP case) or SCRATCH0 Aux Reg (SMP).
+ *
+ * Before saving the full regfile - this reg is restored back, only
+ * to be saved again on kernel mode stack, as part of pt_regs.
+ *-------------------------------------------------------------*/
+.macro PROLOG_FREEUP_REG	reg, mem
+#ifdef CONFIG_SMP
+	sr  \reg, [ARC_REG_SCRATCH_DATA0]
+#else
+	st  \reg, [\mem]
+#endif
+.endm
+
+.macro PROLOG_RESTORE_REG	reg, mem
+#ifdef CONFIG_SMP
+	lr  \reg, [ARC_REG_SCRATCH_DATA0]
+#else
+	ld  \reg, [\mem]
+#endif
+.endm
+
+/*--------------------------------------------------------------
+ * Exception Entry prologue
+ * -Switches stack to K mode (if not already)
+ * -Saves the register file
+ *
+ * After this it is safe to call the "C" handlers
+ *-------------------------------------------------------------*/
+.macro EXCEPTION_PROLOGUE
+
+	/* Need at least 1 reg to code the early exception prologue */
+	PROLOG_FREEUP_REG r9, @ex_saved_reg1
+
+	/* U/K mode at time of exception (stack not switched if already K) */
+	lr  r9, [erstatus]
+
+	/* ARC700 doesn't provide auto-stack switching */
+	SWITCH_TO_KERNEL_STK
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+	/* Treat r25 as scratch reg (save on stack) and load with "current" */
+	PUSH    r25
+	GET_CURR_TASK_ON_CPU   r25
+#else
+	sub     sp, sp, 4
+#endif
+
+	st.a	r0, [sp, -8]    /* orig_r0 needed for syscall (skip ECR slot) */
+	sub	sp, sp, 4	/* skip pt_regs->sp, already saved above */
+
+	/* Restore r9 used to code the early prologue */
+	PROLOG_RESTORE_REG  r9, @ex_saved_reg1
+
+	/* now we are ready to save the regfile */
+	SAVE_R0_TO_R12
+	PUSH	gp
+	PUSH	fp
+	PUSH	blink
+	PUSHAX	eret
+	PUSHAX	erstatus
+	PUSH	lp_count
+	PUSHAX	lp_end
+	PUSHAX	lp_start
+	PUSHAX	erbta
+
+	lr	r9, [ecr]
+	st      r9, [sp, PT_event]    /* EV_Trap expects r9 to have ECR */
+.endm
+
+/*--------------------------------------------------------------
+ * Restore all registers used by system call or Exceptions
+ * SP should always be pointing to the next free stack element
+ * when entering this macro.
+ *
+ * NOTE:
+ *
+ * It is recommended that lp_count/ilink1/ilink2 not be used as a dest reg
+ * for memory load operations. If used in that way interrupts are deffered
+ * by hardware and that is not good.
+ *-------------------------------------------------------------*/
+.macro EXCEPTION_EPILOGUE
+	POPAX	erbta
+	POPAX	lp_start
+	POPAX	lp_end
+
+	POP	r9
+	mov	lp_count, r9	;LD to lp_count is not allowed
+
+	POPAX	erstatus
+	POPAX	eret
+	POP	blink
+	POP	fp
+	POP	gp
+	RESTORE_R12_TO_R0
+
+	ld  sp, [sp] /* restore original sp */
+	/* orig_r0, ECR, user_r25 skipped automatically */
+.endm
+
+/* Dummy ECR values for Interrupts */
+#define event_IRQ1		0x0031abcd
+#define event_IRQ2		0x0032abcd
+
+.macro INTERRUPT_PROLOGUE  LVL
+
+	/* free up r9 as scratchpad */
+	PROLOG_FREEUP_REG r9, @int\LVL\()_saved_reg
+
+	/* Which mode (user/kernel) was the system in when intr occured */
+	lr  r9, [status32_l\LVL\()]
+
+	SWITCH_TO_KERNEL_STK
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+	/* Treat r25 as scratch reg (save on stack) and load with "current" */
+	PUSH    r25
+	GET_CURR_TASK_ON_CPU   r25
+#else
+	sub     sp, sp, 4
+#endif
+
+	PUSH	0x003\LVL\()abcd    /* Dummy ECR */
+	sub	sp, sp, 8	    /* skip orig_r0 (not needed)
+				       skip pt_regs->sp, already saved above */
+
+	/* Restore r9 used to code the early prologue */
+	PROLOG_RESTORE_REG  r9, @int\LVL\()_saved_reg
+
+	SAVE_R0_TO_R12
+	PUSH	gp
+	PUSH	fp
+	PUSH	blink
+	PUSH	ilink\LVL\()
+	PUSHAX	status32_l\LVL\()
+	PUSH	lp_count
+	PUSHAX	lp_end
+	PUSHAX	lp_start
+	PUSHAX	bta_l\LVL\()
+.endm
+
+/*--------------------------------------------------------------
+ * Restore all registers used by interrupt handlers.
+ *
+ * NOTE:
+ *
+ * It is recommended that lp_count/ilink1/ilink2 not be used as a dest reg
+ * for memory load operations. If used in that way interrupts are deffered
+ * by hardware and that is not good.
+ *-------------------------------------------------------------*/
+.macro INTERRUPT_EPILOGUE  LVL
+	POPAX	bta_l\LVL\()
+	POPAX	lp_start
+	POPAX	lp_end
+
+	POP	r9
+	mov	lp_count, r9	;LD to lp_count is not allowed
+
+	POPAX	status32_l\LVL\()
+	POP	ilink\LVL\()
+	POP	blink
+	POP	fp
+	POP	gp
+	RESTORE_R12_TO_R0
+
+	ld  sp, [sp] /* restore original sp */
+	/* orig_r0, ECR, user_r25 skipped automatically */
+.endm
+
+/* Get thread_info of "current" tsk */
+.macro GET_CURR_THR_INFO_FROM_SP  reg
+	bic \reg, sp, (THREAD_SIZE - 1)
+.endm
+
+/* Get CPU-ID of this core */
+.macro  GET_CPU_ID  reg
+	lr  \reg, [identity]
+	lsr \reg, \reg, 8
+	bmsk \reg, \reg, 7
+.endm
+
+#endif  /* __ASM_ARC_ENTRY_COMPACT_H */
diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h
index 8840810..ad7860c 100644
--- a/arch/arc/include/asm/entry.h
+++ b/arch/arc/include/asm/entry.h
@@ -1,45 +1,27 @@
 /*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
  * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * Vineetg: March 2009 (Supporting 2 levels of Interrupts)
- *  Stack switching code can no longer reliably rely on the fact that
- *  if we are NOT in user mode, stack is switched to kernel mode.
- *  e.g. L2 IRQ interrupted a L1 ISR which had not yet completed
- *  it's prologue including stack switching from user mode
- *
- * Vineetg: Aug 28th 2008: Bug #94984
- *  -Zero Overhead Loop Context shd be cleared when entering IRQ/EXcp/Trap
- *   Normally CPU does this automatically, however when doing FAKE rtie,
- *   we also need to explicitly do this. The problem in macros
- *   FAKE_RET_FROM_EXCPN and FAKE_RET_FROM_EXCPN_LOCK_IRQ was that this bit
- *   was being "CLEARED" rather then "SET". Actually "SET" clears ZOL context
- *
- * Vineetg: May 5th 2008
- *  -Modified CALLEE_REG save/restore macros to handle the fact that
- *      r25 contains the kernel current task ptr
- *  - Defined Stack Switching Macro to be reused in all intr/excp hdlrs
- *  - Shaved off 11 instructions from RESTORE_ALL_INT1 by using the
- *      address Write back load ld.ab instead of seperate ld/add instn
- *
- * Amit Bhor, Sameer Dhavale: Codito Technologies 2004
  */
 
 #ifndef __ASM_ARC_ENTRY_H
 #define __ASM_ARC_ENTRY_H
 
-#ifdef __ASSEMBLY__
 #include <asm/unistd.h>		/* For NR_syscalls defination */
-#include <asm/asm-offsets.h>
 #include <asm/arcregs.h>
 #include <asm/ptrace.h>
 #include <asm/processor.h>	/* For VMALLOC_START */
-#include <asm/thread_info.h>	/* For THREAD_SIZE */
 #include <asm/mmu.h>
 
+#ifdef CONFIG_ISA_ARCOMPACT
+#include <asm/entry-compact.h>	/* ISA specific bits */
+#else
+#include <asm/entry-arcv2.h>
+#endif
+
 /* Note on the LD/ST addr modes with addr reg wback
  *
  * LD.a same as LD.aw
@@ -143,8 +125,6 @@
 	POP	r13
 .endm
 
-#define OFF_USER_R25_FROM_R24	(SZ_CALLEE_REGS + SZ_PT_REGS - 8)/4
-
 /*--------------------------------------------------------------
  * Collect User Mode callee regs as struct callee_regs - needed by
  * fork/do_signal/unaligned-access-emulation.
@@ -157,12 +137,13 @@
  *-------------------------------------------------------------*/
 .macro SAVE_CALLEE_SAVED_USER
 
+	mov	r12, sp		; save SP as ref to pt_regs
 	SAVE_R13_TO_R24
 
 #ifdef CONFIG_ARC_CURR_IN_REG
-	; Retrieve orig r25 and save it on stack
-	ld.as   r12, [sp, OFF_USER_R25_FROM_R24]
-	st.a    r12, [sp, -4]
+	; Retrieve orig r25 and save it with rest of callee_regs
+	ld.as   r12, [r12, PT_user_r25]
+	PUSH	r12
 #else
 	PUSH	r25
 #endif
@@ -209,12 +190,16 @@
 .macro RESTORE_CALLEE_SAVED_USER
 
 #ifdef CONFIG_ARC_CURR_IN_REG
-	ld.ab   r12, [sp, 4]
-	st.as   r12, [sp, OFF_USER_R25_FROM_R24]
+	POP	r12
 #else
 	POP	r25
 #endif
 	RESTORE_R24_TO_R13
+
+	; SP is back to start of pt_regs
+#ifdef CONFIG_ARC_CURR_IN_REG
+	st.as   r12, [sp, PT_user_r25]
+#endif
 .endm
 
 /*--------------------------------------------------------------
@@ -240,117 +225,6 @@
 
 .endm
 
-/*--------------------------------------------------------------
- * Switch to Kernel Mode stack if SP points to User Mode stack
- *
- * Entry   : r9 contains pre-IRQ/exception/trap status32
- * Exit    : SP is set to kernel mode stack pointer
- *           If CURR_IN_REG, r25 set to "current" task pointer
- * Clobbers: r9
- *-------------------------------------------------------------*/
-
-.macro SWITCH_TO_KERNEL_STK
-
-	/* User Mode when this happened ? Yes: Proceed to switch stack */
-	bbit1   r9, STATUS_U_BIT, 88f
-
-	/* OK we were already in kernel mode when this event happened, thus can
-	 * assume SP is kernel mode SP. _NO_ need to do any stack switching
-	 */
-
-#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
-	/* However....
-	 * If Level 2 Interrupts enabled, we may end up with a corner case:
-	 * 1. User Task executing
-	 * 2. L1 IRQ taken, ISR starts (CPU auto-switched to KERNEL mode)
-	 * 3. But before it could switch SP from USER to KERNEL stack
-	 *      a L2 IRQ "Interrupts" L1
-	 * Thay way although L2 IRQ happened in Kernel mode, stack is still
-	 * not switched.
-	 * To handle this, we may need to switch stack even if in kernel mode
-	 * provided SP has values in range of USER mode stack ( < 0x7000_0000 )
-	 */
-	brlo sp, VMALLOC_START, 88f
-
-	/* TODO: vineetg:
-	 * We need to be a bit more cautious here. What if a kernel bug in
-	 * L1 ISR, caused SP to go whaco (some small value which looks like
-	 * USER stk) and then we take L2 ISR.
-	 * Above brlo alone would treat it as a valid L1-L2 sceanrio
-	 * instead of shouting alound
-	 * The only feasible way is to make sure this L2 happened in
-	 * L1 prelogue ONLY i.e. ilink2 is less than a pre-set marker in
-	 * L1 ISR before it switches stack
-	 */
-
-#endif
-
-	/* Save Pre Intr/Exception KERNEL MODE SP on kernel stack
-	 * safe-keeping not really needed, but it keeps the epilogue code
-	 * (SP restore) simpler/uniform.
-	 */
-	b.d	66f
-	mov	r9, sp
-
-88: /*------Intr/Ecxp happened in user mode, "switch" stack ------ */
-
-	GET_CURR_TASK_ON_CPU   r9
-
-	/* With current tsk in r9, get it's kernel mode stack base */
-	GET_TSK_STACK_BASE  r9, r9
-
-66:
-#ifdef CONFIG_ARC_CURR_IN_REG
-	/*
-	 * Treat r25 as scratch reg, save it on stack first
-	 * Load it with current task pointer
-	 */
-	st	r25, [r9, -4]
-	GET_CURR_TASK_ON_CPU   r25
-#endif
-
-	/* Save Pre Intr/Exception User SP on kernel stack */
-	st.a    sp, [r9, -16]	; Make room for orig_r0, ECR, user_r25
-
-	/* CAUTION:
-	 * SP should be set at the very end when we are done with everything
-	 * In case of 2 levels of interrupt we depend on value of SP to assume
-	 * that everything else is done (loading r25 etc)
-	 */
-
-	/* set SP to point to kernel mode stack */
-	mov sp, r9
-
-	/* ----- Stack Switched to kernel Mode, Now save REG FILE ----- */
-
-.endm
-
-/*------------------------------------------------------------
- * "FAKE" a rtie to return from CPU Exception context
- * This is to re-enable Exceptions within exception
- * Look at EV_ProtV to see how this is actually used
- *-------------------------------------------------------------*/
-
-.macro FAKE_RET_FROM_EXCPN  reg
-
-	ld  \reg, [sp, PT_status32]
-	bic  \reg, \reg, (STATUS_U_MASK|STATUS_DE_MASK)
-	bset \reg, \reg, STATUS_L_BIT
-	sr  \reg, [erstatus]
-	mov \reg, 55f
-	sr  \reg, [eret]
-
-	rtie
-55:
-.endm
-
-/*
- * @reg [OUT] &thread_info of "current"
- */
-.macro GET_CURR_THR_INFO_FROM_SP  reg
-	bic \reg, sp, (THREAD_SIZE - 1)
-.endm
-
 /*
  * @reg [OUT] thread_info->flags of "current"
  */
@@ -359,222 +233,6 @@
 	ld  \reg, [\reg, THREAD_INFO_FLAGS]
 .endm
 
-/*--------------------------------------------------------------
- * For early Exception Prologue, a core reg is temporarily needed to
- * code the rest of prolog (stack switching). This is done by stashing
- * it to memory (non-SMP case) or SCRATCH0 Aux Reg (SMP).
- *
- * Before saving the full regfile - this reg is restored back, only
- * to be saved again on kernel mode stack, as part of pt_regs.
- *-------------------------------------------------------------*/
-.macro EXCPN_PROLOG_FREEUP_REG	reg
-#ifdef CONFIG_SMP
-	sr  \reg, [ARC_REG_SCRATCH_DATA0]
-#else
-	st  \reg, [@ex_saved_reg1]
-#endif
-.endm
-
-.macro EXCPN_PROLOG_RESTORE_REG	reg
-#ifdef CONFIG_SMP
-	lr  \reg, [ARC_REG_SCRATCH_DATA0]
-#else
-	ld  \reg, [@ex_saved_reg1]
-#endif
-.endm
-
-/*--------------------------------------------------------------
- * Exception Entry prologue
- * -Switches stack to K mode (if not already)
- * -Saves the register file
- *
- * After this it is safe to call the "C" handlers
- *-------------------------------------------------------------*/
-.macro EXCEPTION_PROLOGUE
-
-	/* Need at least 1 reg to code the early exception prologue */
-	EXCPN_PROLOG_FREEUP_REG r9
-
-	/* U/K mode at time of exception (stack not switched if already K) */
-	lr  r9, [erstatus]
-
-	/* ARC700 doesn't provide auto-stack switching */
-	SWITCH_TO_KERNEL_STK
-
-	/* save the regfile */
-	SAVE_ALL_SYS
-.endm
-
-/*--------------------------------------------------------------
- * Save all registers used by Exceptions (TLB Miss, Prot-V, Mem err etc)
- * Requires SP to be already switched to kernel mode Stack
- * sp points to the next free element on the stack at exit of this macro.
- * Registers are pushed / popped in the order defined in struct ptregs
- * in asm/ptrace.h
- * Note that syscalls are implemented via TRAP which is also a exception
- * from CPU's point of view
- *-------------------------------------------------------------*/
-.macro SAVE_ALL_SYS
-
-	lr	r9, [ecr]
-	st      r9, [sp, 8]    /* ECR */
-	st      r0, [sp, 4]    /* orig_r0, needed only for sys calls */
-
-	/* Restore r9 used to code the early prologue */
-	EXCPN_PROLOG_RESTORE_REG  r9
-
-	SAVE_R0_TO_R12
-	PUSH	gp
-	PUSH	fp
-	PUSH	blink
-	PUSHAX	eret
-	PUSHAX	erstatus
-	PUSH	lp_count
-	PUSHAX	lp_end
-	PUSHAX	lp_start
-	PUSHAX	erbta
-.endm
-
-/*--------------------------------------------------------------
- * Restore all registers used by system call or Exceptions
- * SP should always be pointing to the next free stack element
- * when entering this macro.
- *
- * NOTE:
- *
- * It is recommended that lp_count/ilink1/ilink2 not be used as a dest reg
- * for memory load operations. If used in that way interrupts are deffered
- * by hardware and that is not good.
- *-------------------------------------------------------------*/
-.macro RESTORE_ALL_SYS
-	POPAX	erbta
-	POPAX	lp_start
-	POPAX	lp_end
-
-	POP	r9
-	mov	lp_count, r9	;LD to lp_count is not allowed
-
-	POPAX	erstatus
-	POPAX	eret
-	POP	blink
-	POP	fp
-	POP	gp
-	RESTORE_R12_TO_R0
-
-	ld  sp, [sp] /* restore original sp */
-	/* orig_r0, ECR, user_r25 skipped automatically */
-.endm
-
-
-/*--------------------------------------------------------------
- * Save all registers used by interrupt handlers.
- *-------------------------------------------------------------*/
-.macro SAVE_ALL_INT1
-
-	/* restore original r9 to be saved as part of reg-file */
-#ifdef CONFIG_SMP
-	lr  r9, [ARC_REG_SCRATCH_DATA0]
-#else
-	ld  r9, [@int1_saved_reg]
-#endif
-
-	/* now we are ready to save the remaining context :) */
-	st      event_IRQ1, [sp, 8]    /* Dummy ECR */
-	st      0, [sp, 4]    /* orig_r0 , N/A for IRQ */
-
-	SAVE_R0_TO_R12
-	PUSH	gp
-	PUSH	fp
-	PUSH	blink
-	PUSH	ilink1
-	PUSHAX	status32_l1
-	PUSH	lp_count
-	PUSHAX	lp_end
-	PUSHAX	lp_start
-	PUSHAX	bta_l1
-.endm
-
-.macro SAVE_ALL_INT2
-
-	/* TODO-vineetg: SMP we can't use global nor can we use
-	*   SCRATCH0 as we do for int1 because while int1 is using
-	*   it, int2 can come
-	*/
-	/* retsore original r9 , saved in sys_saved_r9 */
-	ld  r9, [@int2_saved_reg]
-
-	/* now we are ready to save the remaining context :) */
-	st      event_IRQ2, [sp, 8]    /* Dummy ECR */
-	st      0, [sp, 4]    /* orig_r0 , N/A for IRQ */
-
-	SAVE_R0_TO_R12
-	PUSH	gp
-	PUSH	fp
-	PUSH	blink
-	PUSH	ilink2
-	PUSHAX	status32_l2
-	PUSH	lp_count
-	PUSHAX	lp_end
-	PUSHAX	lp_start
-	PUSHAX	bta_l2
-.endm
-
-/*--------------------------------------------------------------
- * Restore all registers used by interrupt handlers.
- *
- * NOTE:
- *
- * It is recommended that lp_count/ilink1/ilink2 not be used as a dest reg
- * for memory load operations. If used in that way interrupts are deffered
- * by hardware and that is not good.
- *-------------------------------------------------------------*/
-
-.macro RESTORE_ALL_INT1
-	POPAX	bta_l1
-	POPAX	lp_start
-	POPAX	lp_end
-
-	POP	r9
-	mov	lp_count, r9	;LD to lp_count is not allowed
-
-	POPAX	status32_l1
-	POP	ilink1
-	POP	blink
-	POP	fp
-	POP	gp
-	RESTORE_R12_TO_R0
-
-	ld  sp, [sp] /* restore original sp */
-	/* orig_r0, ECR, user_r25 skipped automatically */
-.endm
-
-.macro RESTORE_ALL_INT2
-	POPAX	bta_l2
-	POPAX	lp_start
-	POPAX	lp_end
-
-	POP	r9
-	mov	lp_count, r9	;LD to lp_count is not allowed
-
-	POPAX	status32_l2
-	POP	ilink2
-	POP	blink
-	POP	fp
-	POP	gp
-	RESTORE_R12_TO_R0
-
-	ld  sp, [sp] /* restore original sp */
-	/* orig_r0, ECR, user_r25 skipped automatically */
-.endm
-
-
-/* Get CPU-ID of this core */
-.macro  GET_CPU_ID  reg
-	lr  \reg, [identity]
-	lsr \reg, \reg, 8
-	bmsk \reg, \reg, 7
-.endm
-
 #ifdef CONFIG_SMP
 
 /*-------------------------------------------------
@@ -643,6 +301,4 @@
 
 #endif	/* CONFIG_ARC_CURR_IN_REG */
 
-#endif  /* __ASSEMBLY__ */
-
 #endif  /* __ASM_ARC_ENTRY_H */
diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h
index 7cc4ced..694ece8 100644
--- a/arch/arc/include/asm/io.h
+++ b/arch/arc/include/asm/io.h
@@ -99,9 +99,45 @@
 
 }
 
-#define readb_relaxed readb
-#define readw_relaxed readw
-#define readl_relaxed readl
+#ifdef CONFIG_ISA_ARCV2
+#include <asm/barrier.h>
+#define __iormb()		rmb()
+#define __iowmb()		wmb()
+#else
+#define __iormb()		do { } while (0)
+#define __iowmb()		do { } while (0)
+#endif
+
+/*
+ * MMIO can also get buffered/optimized in micro-arch, so barriers needed
+ * Based on ARM model for the typical use case
+ *
+ *	<ST [DMA buffer]>
+ *	<writel MMIO "go" reg>
+ *  or:
+ *	<readl MMIO "status" reg>
+ *	<LD [DMA buffer]>
+ *
+ * http://lkml.kernel.org/r/20150622133656.GG1583@arm.com
+ */
+#define readb(c)		({ u8  __v = readb_relaxed(c); __iormb(); __v; })
+#define readw(c)		({ u16 __v = readw_relaxed(c); __iormb(); __v; })
+#define readl(c)		({ u32 __v = readl_relaxed(c); __iormb(); __v; })
+
+#define writeb(v,c)		({ __iowmb(); writeb_relaxed(v,c); })
+#define writew(v,c)		({ __iowmb(); writew_relaxed(v,c); })
+#define writel(v,c)		({ __iowmb(); writel_relaxed(v,c); })
+
+/*
+ * Relaxed API for drivers which can handle any ordering themselves
+ */
+#define readb_relaxed(c)	__raw_readb(c)
+#define readw_relaxed(c)	__raw_readw(c)
+#define readl_relaxed(c)	__raw_readl(c)
+
+#define writeb_relaxed(v,c)	__raw_writeb(v,c)
+#define writew_relaxed(v,c)	__raw_writew(v,c)
+#define writel_relaxed(v,c)	__raw_writel(v,c)
 
 #include <asm-generic/io.h>
 
diff --git a/arch/arc/include/asm/irq.h b/arch/arc/include/asm/irq.h
index f38652f..bc51036 100644
--- a/arch/arc/include/asm/irq.h
+++ b/arch/arc/include/asm/irq.h
@@ -13,8 +13,14 @@
 #define NR_IRQS		128 /* allow some CPU external IRQ handling */
 
 /* Platform Independent IRQs */
+#ifdef CONFIG_ISA_ARCOMPACT
 #define TIMER0_IRQ      3
 #define TIMER1_IRQ      4
+#else
+#define TIMER0_IRQ      16
+#define TIMER1_IRQ      17
+#define IPI_IRQ         19
+#endif
 
 #include <linux/interrupt.h>
 #include <asm-generic/irq.h>
diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h
new file mode 100644
index 0000000..ad481c2
--- /dev/null
+++ b/arch/arc/include/asm/irqflags-arcv2.h
@@ -0,0 +1,124 @@
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_IRQFLAGS_ARCV2_H
+#define __ASM_IRQFLAGS_ARCV2_H
+
+#include <asm/arcregs.h>
+
+/* status32 Bits */
+#define STATUS_AD_BIT	19   /* Disable Align chk: core supports non-aligned */
+#define STATUS_IE_BIT	31
+
+#define STATUS_AD_MASK		(1<<STATUS_AD_BIT)
+#define STATUS_IE_MASK		(1<<STATUS_IE_BIT)
+
+#define AUX_USER_SP		0x00D
+#define AUX_IRQ_CTRL		0x00E
+#define AUX_IRQ_ACT		0x043	/* Active Intr across all levels */
+#define AUX_IRQ_LVL_PEND	0x200	/* Pending Intr across all levels */
+#define AUX_IRQ_PRIORITY	0x206
+#define ICAUSE			0x40a
+#define AUX_IRQ_SELECT		0x40b
+#define AUX_IRQ_ENABLE		0x40c
+
+/* Was Intr taken in User Mode */
+#define AUX_IRQ_ACT_BIT_U	31
+
+/* 0 is highest level, but taken by FIRQs, if present in design */
+#define ARCV2_IRQ_DEF_PRIO		0
+
+/* seed value for status register */
+#define ISA_INIT_STATUS_BITS	(STATUS_IE_MASK | STATUS_AD_MASK | \
+					(ARCV2_IRQ_DEF_PRIO << 1))
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Save IRQ state and disable IRQs
+ */
+static inline long arch_local_irq_save(void)
+{
+	unsigned long flags;
+
+	__asm__ __volatile__("	clri %0	\n" : "=r" (flags) : : "memory");
+
+	return flags;
+}
+
+/*
+ * restore saved IRQ state
+ */
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	__asm__ __volatile__("	seti %0	\n" : : "r" (flags) : "memory");
+}
+
+/*
+ * Unconditionally Enable IRQs
+ */
+static inline void arch_local_irq_enable(void)
+{
+	unsigned int irqact = read_aux_reg(AUX_IRQ_ACT);
+
+	if (irqact & 0xffff)
+		write_aux_reg(AUX_IRQ_ACT, irqact & ~0xffff);
+
+	__asm__ __volatile__("	seti	\n" : : : "memory");
+}
+
+/*
+ * Unconditionally Disable IRQs
+ */
+static inline void arch_local_irq_disable(void)
+{
+	__asm__ __volatile__("	clri	\n" : : : "memory");
+}
+
+/*
+ * save IRQ state
+ */
+static inline long arch_local_save_flags(void)
+{
+	unsigned long temp;
+
+	__asm__ __volatile__(
+	"	lr  %0, [status32]	\n"
+	: "=&r"(temp)
+	:
+	: "memory");
+
+	return temp;
+}
+
+/*
+ * Query IRQ state
+ */
+static inline int arch_irqs_disabled_flags(unsigned long flags)
+{
+	return !(flags & (STATUS_IE_MASK));
+}
+
+static inline int arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+#else
+
+.macro IRQ_DISABLE  scratch
+	clri
+.endm
+
+.macro IRQ_ENABLE  scratch
+	seti
+.endm
+
+#endif	/* __ASSEMBLY__ */
+
+#endif
diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h
new file mode 100644
index 0000000..aa80557
--- /dev/null
+++ b/arch/arc/include/asm/irqflags-compact.h
@@ -0,0 +1,183 @@
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_IRQFLAGS_ARCOMPACT_H
+#define __ASM_IRQFLAGS_ARCOMPACT_H
+
+/* vineetg: March 2010 : local_irq_save( ) optimisation
+ *  -Remove explicit mov of current status32 into reg, that is not needed
+ *  -Use BIC  insn instead of INVERTED + AND
+ *  -Conditionally disable interrupts (if they are not enabled, don't disable)
+*/
+
+#include <asm/arcregs.h>
+
+/* status32 Reg bits related to Interrupt Handling */
+#define STATUS_E1_BIT		1	/* Int 1 enable */
+#define STATUS_E2_BIT		2	/* Int 2 enable */
+#define STATUS_A1_BIT		3	/* Int 1 active */
+#define STATUS_A2_BIT		4	/* Int 2 active */
+
+#define STATUS_E1_MASK		(1<<STATUS_E1_BIT)
+#define STATUS_E2_MASK		(1<<STATUS_E2_BIT)
+#define STATUS_A1_MASK		(1<<STATUS_A1_BIT)
+#define STATUS_A2_MASK		(1<<STATUS_A2_BIT)
+#define STATUS_IE_MASK		(STATUS_E1_MASK | STATUS_E2_MASK)
+
+/* Other Interrupt Handling related Aux regs */
+#define AUX_IRQ_LEV		0x200	/* IRQ Priority: L1 or L2 */
+#define AUX_IRQ_HINT		0x201	/* For generating Soft Interrupts */
+#define AUX_IRQ_LV12		0x43	/* interrupt level register */
+
+#define AUX_IENABLE		0x40c
+#define AUX_ITRIGGER		0x40d
+#define AUX_IPULSE		0x415
+
+#define ISA_INIT_STATUS_BITS	STATUS_IE_MASK
+
+#ifndef __ASSEMBLY__
+
+/******************************************************************
+ * IRQ Control Macros
+ *
+ * All of them have "memory" clobber (compiler barrier) which is needed to
+ * ensure that LD/ST requiring irq safetly (R-M-W when LLSC is not available)
+ * are redone after IRQs are re-enabled (and gcc doesn't reuse stale register)
+ *
+ * Noted at the time of Abilis Timer List corruption
+ *	Orig Bug + Rejected solution	: https://lkml.org/lkml/2013/3/29/67
+ *	Reasoning			: https://lkml.org/lkml/2013/4/8/15
+ *
+ ******************************************************************/
+
+/*
+ * Save IRQ state and disable IRQs
+ */
+static inline long arch_local_irq_save(void)
+{
+	unsigned long temp, flags;
+
+	__asm__ __volatile__(
+	"	lr  %1, [status32]	\n"
+	"	bic %0, %1, %2		\n"
+	"	and.f 0, %1, %2	\n"
+	"	flag.nz %0		\n"
+	: "=r"(temp), "=r"(flags)
+	: "n"((STATUS_E1_MASK | STATUS_E2_MASK))
+	: "memory", "cc");
+
+	return flags;
+}
+
+/*
+ * restore saved IRQ state
+ */
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+
+	__asm__ __volatile__(
+	"	flag %0			\n"
+	:
+	: "r"(flags)
+	: "memory");
+}
+
+/*
+ * Unconditionally Enable IRQs
+ */
+extern void arch_local_irq_enable(void);
+
+/*
+ * Unconditionally Disable IRQs
+ */
+static inline void arch_local_irq_disable(void)
+{
+	unsigned long temp;
+
+	__asm__ __volatile__(
+	"	lr  %0, [status32]	\n"
+	"	and %0, %0, %1		\n"
+	"	flag %0			\n"
+	: "=&r"(temp)
+	: "n"(~(STATUS_E1_MASK | STATUS_E2_MASK))
+	: "memory");
+}
+
+/*
+ * save IRQ state
+ */
+static inline long arch_local_save_flags(void)
+{
+	unsigned long temp;
+
+	__asm__ __volatile__(
+	"	lr  %0, [status32]	\n"
+	: "=&r"(temp)
+	:
+	: "memory");
+
+	return temp;
+}
+
+/*
+ * Query IRQ state
+ */
+static inline int arch_irqs_disabled_flags(unsigned long flags)
+{
+	return !(flags & (STATUS_E1_MASK
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
+			| STATUS_E2_MASK
+#endif
+		));
+}
+
+static inline int arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+#else
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+
+.macro TRACE_ASM_IRQ_DISABLE
+	bl	trace_hardirqs_off
+.endm
+
+.macro TRACE_ASM_IRQ_ENABLE
+	bl	trace_hardirqs_on
+.endm
+
+#else
+
+.macro TRACE_ASM_IRQ_DISABLE
+.endm
+
+.macro TRACE_ASM_IRQ_ENABLE
+.endm
+
+#endif
+
+.macro IRQ_DISABLE  scratch
+	lr	\scratch, [status32]
+	bic	\scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
+	flag	\scratch
+	TRACE_ASM_IRQ_DISABLE
+.endm
+
+.macro IRQ_ENABLE  scratch
+	lr	\scratch, [status32]
+	or	\scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
+	flag	\scratch
+	TRACE_ASM_IRQ_ENABLE
+.endm
+
+#endif	/* __ASSEMBLY__ */
+
+#endif
diff --git a/arch/arc/include/asm/irqflags.h b/arch/arc/include/asm/irqflags.h
index 27ecc69..59bc6a6 100644
--- a/arch/arc/include/asm/irqflags.h
+++ b/arch/arc/include/asm/irqflags.h
@@ -1,4 +1,5 @@
 /*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
  * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
  *
  * This program is free software; you can redistribute it and/or modify
@@ -9,171 +10,10 @@
 #ifndef __ASM_ARC_IRQFLAGS_H
 #define __ASM_ARC_IRQFLAGS_H
 
-/* vineetg: March 2010 : local_irq_save( ) optimisation
- *  -Remove explicit mov of current status32 into reg, that is not needed
- *  -Use BIC  insn instead of INVERTED + AND
- *  -Conditionally disable interrupts (if they are not enabled, don't disable)
-*/
-
-#include <asm/arcregs.h>
-
-/* status32 Reg bits related to Interrupt Handling */
-#define STATUS_E1_BIT		1	/* Int 1 enable */
-#define STATUS_E2_BIT		2	/* Int 2 enable */
-#define STATUS_A1_BIT		3	/* Int 1 active */
-#define STATUS_A2_BIT		4	/* Int 2 active */
-
-#define STATUS_E1_MASK		(1<<STATUS_E1_BIT)
-#define STATUS_E2_MASK		(1<<STATUS_E2_BIT)
-#define STATUS_A1_MASK		(1<<STATUS_A1_BIT)
-#define STATUS_A2_MASK		(1<<STATUS_A2_BIT)
-
-/* Other Interrupt Handling related Aux regs */
-#define AUX_IRQ_LEV		0x200	/* IRQ Priority: L1 or L2 */
-#define AUX_IRQ_HINT		0x201	/* For generating Soft Interrupts */
-#define AUX_IRQ_LV12		0x43	/* interrupt level register */
-
-#define AUX_IENABLE		0x40c
-#define AUX_ITRIGGER		0x40d
-#define AUX_IPULSE		0x415
-
-#ifndef __ASSEMBLY__
-
-/******************************************************************
- * IRQ Control Macros
- *
- * All of them have "memory" clobber (compiler barrier) which is needed to
- * ensure that LD/ST requiring irq safetly (R-M-W when LLSC is not available)
- * are redone after IRQs are re-enabled (and gcc doesn't reuse stale register)
- *
- * Noted at the time of Abilis Timer List corruption
- * 	Orig Bug + Rejected solution	: https://lkml.org/lkml/2013/3/29/67
- * 	Reasoning			: https://lkml.org/lkml/2013/4/8/15
- *
- ******************************************************************/
-
-/*
- * Save IRQ state and disable IRQs
- */
-static inline long arch_local_irq_save(void)
-{
-	unsigned long temp, flags;
-
-	__asm__ __volatile__(
-	"	lr  %1, [status32]	\n"
-	"	bic %0, %1, %2		\n"
-	"	and.f 0, %1, %2	\n"
-	"	flag.nz %0		\n"
-	: "=r"(temp), "=r"(flags)
-	: "n"((STATUS_E1_MASK | STATUS_E2_MASK))
-	: "memory", "cc");
-
-	return flags;
-}
-
-/*
- * restore saved IRQ state
- */
-static inline void arch_local_irq_restore(unsigned long flags)
-{
-
-	__asm__ __volatile__(
-	"	flag %0			\n"
-	:
-	: "r"(flags)
-	: "memory");
-}
-
-/*
- * Unconditionally Enable IRQs
- */
-extern void arch_local_irq_enable(void);
-
-/*
- * Unconditionally Disable IRQs
- */
-static inline void arch_local_irq_disable(void)
-{
-	unsigned long temp;
-
-	__asm__ __volatile__(
-	"	lr  %0, [status32]	\n"
-	"	and %0, %0, %1		\n"
-	"	flag %0			\n"
-	: "=&r"(temp)
-	: "n"(~(STATUS_E1_MASK | STATUS_E2_MASK))
-	: "memory");
-}
-
-/*
- * save IRQ state
- */
-static inline long arch_local_save_flags(void)
-{
-	unsigned long temp;
-
-	__asm__ __volatile__(
-	"	lr  %0, [status32]	\n"
-	: "=&r"(temp)
-	:
-	: "memory");
-
-	return temp;
-}
-
-/*
- * Query IRQ state
- */
-static inline int arch_irqs_disabled_flags(unsigned long flags)
-{
-	return !(flags & (STATUS_E1_MASK
-#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
-			| STATUS_E2_MASK
-#endif
-		));
-}
-
-static inline int arch_irqs_disabled(void)
-{
-	return arch_irqs_disabled_flags(arch_local_save_flags());
-}
-
+#ifdef CONFIG_ISA_ARCOMPACT
+#include <asm/irqflags-compact.h>
 #else
-
-#ifdef CONFIG_TRACE_IRQFLAGS
-
-.macro TRACE_ASM_IRQ_DISABLE
-	bl	trace_hardirqs_off
-.endm
-
-.macro TRACE_ASM_IRQ_ENABLE
-	bl	trace_hardirqs_on
-.endm
-
-#else
-
-.macro TRACE_ASM_IRQ_DISABLE
-.endm
-
-.macro TRACE_ASM_IRQ_ENABLE
-.endm
-
+#include <asm/irqflags-arcv2.h>
 #endif
 
-.macro IRQ_DISABLE  scratch
-	lr	\scratch, [status32]
-	bic	\scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
-	flag	\scratch
-	TRACE_ASM_IRQ_DISABLE
-.endm
-
-.macro IRQ_ENABLE  scratch
-	lr	\scratch, [status32]
-	or	\scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
-	flag	\scratch
-	TRACE_ASM_IRQ_ENABLE
-.endm
-
-#endif	/* __ASSEMBLY__ */
-
 #endif
diff --git a/arch/arc/include/asm/mcip.h b/arch/arc/include/asm/mcip.h
new file mode 100644
index 0000000..52c11f0
--- /dev/null
+++ b/arch/arc/include/asm/mcip.h
@@ -0,0 +1,94 @@
+/*
+ * ARConnect IP Support (Multi core enabler: Cross core IPI, RTC ...)
+ *
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_MCIP_H
+#define __ASM_MCIP_H
+
+#ifdef CONFIG_ISA_ARCV2
+
+#include <asm/arcregs.h>
+
+#define ARC_REG_MCIP_BCR	0x0d0
+#define ARC_REG_MCIP_CMD	0x600
+#define ARC_REG_MCIP_WDATA	0x601
+#define ARC_REG_MCIP_READBACK	0x602
+
+struct mcip_cmd {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad:8, param:16, cmd:8;
+#else
+	unsigned int cmd:8, param:16, pad:8;
+#endif
+
+#define CMD_INTRPT_GENERATE_IRQ		0x01
+#define CMD_INTRPT_GENERATE_ACK		0x02
+#define CMD_INTRPT_READ_STATUS		0x03
+#define CMD_INTRPT_CHECK_SOURCE		0x04
+
+/* Semaphore Commands */
+#define CMD_SEMA_CLAIM_AND_READ		0x11
+#define CMD_SEMA_RELEASE		0x12
+
+#define CMD_DEBUG_SET_MASK		0x34
+#define CMD_DEBUG_SET_SELECT		0x36
+
+#define CMD_GRTC_READ_LO		0x42
+#define CMD_GRTC_READ_HI		0x43
+
+#define CMD_IDU_ENABLE			0x71
+#define CMD_IDU_DISABLE			0x72
+#define CMD_IDU_SET_MODE		0x74
+#define CMD_IDU_SET_DEST		0x76
+#define CMD_IDU_SET_MASK		0x7C
+
+#define IDU_M_TRIG_LEVEL		0x0
+#define IDU_M_TRIG_EDGE			0x1
+
+#define IDU_M_DISTRI_RR			0x0
+#define IDU_M_DISTRI_DEST		0x2
+};
+
+/*
+ * MCIP programming model
+ *
+ * - Simple commands write {cmd:8,param:16} to MCIP_CMD aux reg
+ *   (param could be irq, common_irq, core_id ...)
+ * - More involved commands setup MCIP_WDATA with cmd specific data
+ *   before invoking the simple command
+ */
+static inline void __mcip_cmd(unsigned int cmd, unsigned int param)
+{
+	struct mcip_cmd buf;
+
+	buf.pad = 0;
+	buf.cmd = cmd;
+	buf.param = param;
+
+	WRITE_AUX(ARC_REG_MCIP_CMD, buf);
+}
+
+/*
+ * Setup additional data for a cmd
+ * Callers need to lock to ensure atomicity
+ */
+static inline void __mcip_cmd_data(unsigned int cmd, unsigned int param,
+				   unsigned int data)
+{
+	write_aux_reg(ARC_REG_MCIP_WDATA, data);
+
+	__mcip_cmd(cmd, param);
+}
+
+extern void mcip_init_early_smp(void);
+extern void mcip_init_smp(unsigned int cpu);
+
+#endif
+
+#endif
diff --git a/arch/arc/include/asm/mmu.h b/arch/arc/include/asm/mmu.h
index 8c84ae9..0f9c3eb 100644
--- a/arch/arc/include/asm/mmu.h
+++ b/arch/arc/include/asm/mmu.h
@@ -15,24 +15,41 @@
 #define CONFIG_ARC_MMU_VER 2
 #elif defined(CONFIG_ARC_MMU_V3)
 #define CONFIG_ARC_MMU_VER 3
+#elif defined(CONFIG_ARC_MMU_V4)
+#define CONFIG_ARC_MMU_VER 4
 #endif
 
 /* MMU Management regs */
 #define ARC_REG_MMU_BCR		0x06f
+#if (CONFIG_ARC_MMU_VER < 4)
 #define ARC_REG_TLBPD0		0x405
 #define ARC_REG_TLBPD1		0x406
 #define ARC_REG_TLBINDEX	0x407
 #define ARC_REG_TLBCOMMAND	0x408
 #define ARC_REG_PID		0x409
 #define ARC_REG_SCRATCH_DATA0	0x418
+#else
+#define ARC_REG_TLBPD0		0x460
+#define ARC_REG_TLBPD1		0x461
+#define ARC_REG_TLBINDEX	0x464
+#define ARC_REG_TLBCOMMAND	0x465
+#define ARC_REG_PID		0x468
+#define ARC_REG_SCRATCH_DATA0	0x46c
+#endif
 
 /* Bits in MMU PID register */
-#define MMU_ENABLE		(1 << 31)	/* Enable MMU for process */
+#define __TLB_ENABLE		(1 << 31)
+#define __PROG_ENABLE		(1 << 30)
+#define MMU_ENABLE		(__TLB_ENABLE | __PROG_ENABLE)
 
 /* Error code if probe fails */
 #define TLB_LKUP_ERR		0x80000000
 
+#if (CONFIG_ARC_MMU_VER < 4)
 #define TLB_DUP_ERR	(TLB_LKUP_ERR | 0x00000001)
+#else
+#define TLB_DUP_ERR	(TLB_LKUP_ERR | 0x40000000)
+#endif
 
 /* TLB Commands */
 #define TLBWrite    0x1
@@ -45,6 +62,11 @@
 #define TLBIVUTLB   0x6		/* explicitly inv uTLBs */
 #endif
 
+#if (CONFIG_ARC_MMU_VER >= 4)
+#define TLBInsertEntry	0x7
+#define TLBDeleteEntry	0x8
+#endif
+
 #ifndef __ASSEMBLY__
 
 typedef struct {
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 9615fe1..1281718 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -72,8 +72,18 @@
 #define _PAGE_READ          (1<<3)	/* Page has user read perm (H) */
 #define _PAGE_ACCESSED      (1<<4)	/* Page is accessed (S) */
 #define _PAGE_MODIFIED      (1<<5)	/* Page modified (dirty) (S) */
+
+#if (CONFIG_ARC_MMU_VER >= 4)
+#define _PAGE_WTHRU         (1<<7)	/* Page cache mode write-thru (H) */
+#endif
+
 #define _PAGE_GLOBAL        (1<<8)	/* Page is global (H) */
 #define _PAGE_PRESENT       (1<<9)	/* TLB entry is valid (H) */
+
+#if (CONFIG_ARC_MMU_VER >= 4)
+#define _PAGE_SZ            (1<<10)	/* Page Size indicator (H) */
+#endif
+
 #define _PAGE_SHARED_CODE   (1<<11)	/* Shared Code page with cmn vaddr
 					   usable for shared TLB entries (H) */
 #endif
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
index 52312cb..ee682d8 100644
--- a/arch/arc/include/asm/processor.h
+++ b/arch/arc/include/asm/processor.h
@@ -77,7 +77,7 @@
  */
 #define TSK_K_ESP(tsk)		(tsk->thread.ksp)
 
-#define TSK_K_REG(tsk, off)	(*((unsigned int *)(TSK_K_ESP(tsk) + \
+#define TSK_K_REG(tsk, off)	(*((unsigned long *)(TSK_K_ESP(tsk) + \
 					sizeof(struct callee_regs) + off)))
 
 #define TSK_K_BLINK(tsk)	TSK_K_REG(tsk, 4)
@@ -100,29 +100,26 @@
 
 #endif /* !__ASSEMBLY__ */
 
-/* Kernels Virtual memory area.
- * Unlike other architectures(MIPS, sh, cris ) ARC 700 does not have a
- * "kernel translated" region (like KSEG2 in MIPS). So we use a upper part
- * of the translated bottom 2GB for kernel virtual memory and protect
- * these pages from user accesses by disabling Ru, Eu and Wu.
+/*
+ * System Memory Map on ARC
+ *
+ * ---------------------------- (lower 2G, Translated) -------------------------
+ * 0x0000_0000		0x5FFF_FFFF	(user vaddr: TASK_SIZE)
+ * 0x6000_0000		0x6FFF_FFFF	(reserved gutter between U/K)
+ * 0x7000_0000		0x7FFF_FFFF	(kvaddr: vmalloc/modules/pkmap..)
+ *
+ * PAGE_OFFSET ---------------- (Upper 2G, Untranslated) -----------------------
+ * 0x8000_0000		0xBFFF_FFFF	(kernel direct mapped)
+ * 0xC000_0000		0xFFFF_FFFF	(peripheral uncached space)
+ * -----------------------------------------------------------------------------
  */
-#define VMALLOC_SIZE	(0x10000000)	/* 256M */
-#define VMALLOC_START	(PAGE_OFFSET - VMALLOC_SIZE)
-#define VMALLOC_END	(PAGE_OFFSET)
+#define VMALLOC_START	0x70000000
+#define VMALLOC_SIZE	(PAGE_OFFSET - VMALLOC_START)
+#define VMALLOC_END	(VMALLOC_START + VMALLOC_SIZE)
 
-/* Most of the architectures seem to be keeping some kind of padding between
- * userspace TASK_SIZE and PAGE_OFFSET. i.e TASK_SIZE != PAGE_OFFSET.
- */
 #define USER_KERNEL_GUTTER    0x10000000
 
-/* User address space:
- * On ARC700, CPU allows the entire lower half of 32 bit address space to be
- * translated. Thus potentially 2G (0:0x7FFF_FFFF) could be User vaddr space.
- * However we steal 256M for kernel addr (0x7000_0000:0x7FFF_FFFF) and another
- * 256M (0x6000_0000:0x6FFF_FFFF) is gutter between user/kernel spaces
- * Thus total User vaddr space is (0:0x5FFF_FFFF)
- */
-#define TASK_SIZE	(PAGE_OFFSET - VMALLOC_SIZE - USER_KERNEL_GUTTER)
+#define TASK_SIZE	(VMALLOC_START - USER_KERNEL_GUTTER)
 
 #define STACK_TOP       TASK_SIZE
 #define STACK_TOP_MAX   STACK_TOP
diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h
index 1bfeec2..9175597 100644
--- a/arch/arc/include/asm/ptrace.h
+++ b/arch/arc/include/asm/ptrace.h
@@ -16,6 +16,7 @@
 
 /* THE pt_regs: Defines how regs are saved during entry into kernel */
 
+#ifdef CONFIG_ISA_ARCOMPACT
 struct pt_regs {
 
 	/* Real registers */
@@ -56,6 +57,48 @@
 
 	long user_r25;
 };
+#else
+
+struct pt_regs {
+
+	long orig_r0;
+
+	union {
+		struct {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+			unsigned long state:8, ecr_vec:8,
+				      ecr_cause:8, ecr_param:8;
+#else
+			unsigned long ecr_param:8, ecr_cause:8,
+				      ecr_vec:8, state:8;
+#endif
+		};
+		unsigned long event;
+	};
+
+	long bta;	/* bta_l1, bta_l2, erbta */
+
+	long user_r25;
+
+	long r26;	/* gp */
+	long fp;
+	long sp;	/* user/kernel sp depending on where we came from  */
+
+	long r12;
+
+	/*------- Below list auto saved by h/w -----------*/
+	long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11;
+
+	long blink;
+	long lp_end, lp_start, lp_count;
+
+	long ei, ldi, jli;
+
+	long ret;
+	long status32;
+};
+
+#endif
 
 /* Callee saved registers - need to be saved only when you are scheduled out */
 
diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h
index b6a8c2d..e1651df 100644
--- a/arch/arc/include/asm/spinlock.h
+++ b/arch/arc/include/asm/spinlock.h
@@ -22,24 +22,46 @@
 {
 	unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__;
 
+	/*
+	 * This smp_mb() is technically superfluous, we only need the one
+	 * after the lock for providing the ACQUIRE semantics.
+	 * However doing the "right" thing was regressing hackbench
+	 * so keeping this, pending further investigation
+	 */
+	smp_mb();
+
 	__asm__ __volatile__(
 	"1:	ex  %0, [%1]		\n"
 	"	breq  %0, %2, 1b	\n"
 	: "+&r" (tmp)
 	: "r"(&(lock->slock)), "ir"(__ARCH_SPIN_LOCK_LOCKED__)
 	: "memory");
+
+	/*
+	 * ACQUIRE barrier to ensure load/store after taking the lock
+	 * don't "bleed-up" out of the critical section (leak-in is allowed)
+	 * http://www.spinics.net/lists/kernel/msg2010409.html
+	 *
+	 * ARCv2 only has load-load, store-store and all-all barrier
+	 * thus need the full all-all barrier
+	 */
+	smp_mb();
 }
 
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
 	unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__;
 
+	smp_mb();
+
 	__asm__ __volatile__(
 	"1:	ex  %0, [%1]		\n"
 	: "+r" (tmp)
 	: "r"(&(lock->slock))
 	: "memory");
 
+	smp_mb();
+
 	return (tmp == __ARCH_SPIN_LOCK_UNLOCKED__);
 }
 
@@ -47,12 +69,22 @@
 {
 	unsigned int tmp = __ARCH_SPIN_LOCK_UNLOCKED__;
 
+	/*
+	 * RELEASE barrier: given the instructions avail on ARCv2, full barrier
+	 * is the only option
+	 */
+	smp_mb();
+
 	__asm__ __volatile__(
 	"	ex  %0, [%1]		\n"
 	: "+r" (tmp)
 	: "r"(&(lock->slock))
 	: "memory");
 
+	/*
+	 * superfluous, but keeping for now - see pairing version in
+	 * arch_spin_lock above
+	 */
 	smp_mb();
 }
 
diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h
index aca0d5a..3af6745 100644
--- a/arch/arc/include/asm/thread_info.h
+++ b/arch/arc/include/asm/thread_info.h
@@ -25,6 +25,7 @@
 #endif
 
 #define THREAD_SIZE     (PAGE_SIZE << THREAD_SIZE_ORDER)
+#define THREAD_SHIFT	(PAGE_SHIFT << THREAD_SIZE_ORDER)
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h
index 30c9baf..d1da603 100644
--- a/arch/arc/include/asm/uaccess.h
+++ b/arch/arc/include/asm/uaccess.h
@@ -659,31 +659,30 @@
 static inline long
 __arc_strncpy_from_user(char *dst, const char __user *src, long count)
 {
-	long res = count;
+	long res = 0;
 	char val;
-	unsigned int hw_count;
 
 	if (count == 0)
 		return 0;
 
 	__asm__ __volatile__(
-	"	lp 2f		\n"
+	"	lp	3f			\n"
 	"1:	ldb.ab  %3, [%2, 1]		\n"
-	"	breq.d  %3, 0, 2f		\n"
+	"	breq.d	%3, 0, 3f               \n"
 	"	stb.ab  %3, [%1, 1]		\n"
-	"2:	sub %0, %6, %4			\n"
-	"3:	;nop				\n"
+	"	add	%0, %0, 1	# Num of NON NULL bytes copied	\n"
+	"3:								\n"
 	"	.section .fixup, \"ax\"		\n"
 	"	.align 4			\n"
-	"4:	mov %0, %5			\n"
+	"4:	mov %0, %4		# sets @res as -EFAULT	\n"
 	"	j   3b				\n"
 	"	.previous			\n"
 	"	.section __ex_table, \"a\"	\n"
 	"	.align 4			\n"
 	"	.word   1b, 4b			\n"
 	"	.previous			\n"
-	: "=r"(res), "+r"(dst), "+r"(src), "=&r"(val), "=l"(hw_count)
-	: "g"(-EFAULT), "ir"(count), "4"(count)	/* this "4" seeds lp_count */
+	: "+r"(res), "+r"(dst), "+r"(src), "=r"(val)
+	: "g"(-EFAULT), "l"(count)
 	: "memory");
 
 	return res;
diff --git a/arch/arc/include/uapi/asm/page.h b/arch/arc/include/uapi/asm/page.h
index e5d41e0..9d129a2 100644
--- a/arch/arc/include/uapi/asm/page.h
+++ b/arch/arc/include/uapi/asm/page.h
@@ -30,7 +30,7 @@
 #define PAGE_OFFSET	(0x80000000)
 #else
 #define PAGE_SIZE	(1UL << PAGE_SHIFT)	/* Default 8K */
-#define PAGE_OFFSET	(0x80000000UL)	/* Kernel starts at 2G onwards */
+#define PAGE_OFFSET	(0x80000000UL)		/* Kernel starts at 2G onwards */
 #endif
 
 #define PAGE_MASK	(~(PAGE_SIZE-1))
diff --git a/arch/arc/kernel/Makefile b/arch/arc/kernel/Makefile
index 113f203..e7f3625 100644
--- a/arch/arc/kernel/Makefile
+++ b/arch/arc/kernel/Makefile
@@ -8,12 +8,14 @@
 # Pass UTS_MACHINE for user_regset definition
 CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
-obj-y	:= arcksyms.o setup.o irq.o time.o reset.o ptrace.o entry.o process.o
+obj-y	:= arcksyms.o setup.o irq.o time.o reset.o ptrace.o process.o devtree.o
 obj-y	+= signal.o traps.o sys.o troubleshoot.o stacktrace.o disasm.o clk.o
-obj-y	+= devtree.o
+obj-$(CONFIG_ISA_ARCOMPACT)		+= entry-compact.o intc-compact.o
+obj-$(CONFIG_ISA_ARCV2)			+= entry-arcv2.o intc-arcv2.o
 
 obj-$(CONFIG_MODULES)			+= arcksyms.o module.o
 obj-$(CONFIG_SMP) 			+= smp.o
+obj-$(CONFIG_ARC_MCIP)			+= mcip.o
 obj-$(CONFIG_ARC_DW2_UNWIND)		+= unwind.o
 obj-$(CONFIG_KPROBES)      		+= kprobes.o
 obj-$(CONFIG_ARC_EMUL_UNALIGNED) 	+= unaligned.o
diff --git a/arch/arc/kernel/asm-offsets.c b/arch/arc/kernel/asm-offsets.c
index 6c3aa0e..ecaf34e 100644
--- a/arch/arc/kernel/asm-offsets.c
+++ b/arch/arc/kernel/asm-offsets.c
@@ -37,6 +37,8 @@
 
 	DEFINE(TASK_ACT_MM, offsetof(struct task_struct, active_mm));
 	DEFINE(TASK_TGID, offsetof(struct task_struct, tgid));
+	DEFINE(TASK_PID, offsetof(struct task_struct, pid));
+	DEFINE(TASK_COMM, offsetof(struct task_struct, comm));
 
 	DEFINE(MM_CTXT, offsetof(struct mm_struct, context));
 	DEFINE(MM_PGD, offsetof(struct mm_struct, pgd));
@@ -56,8 +58,11 @@
 	DEFINE(PT_r5, offsetof(struct pt_regs, r5));
 	DEFINE(PT_r6, offsetof(struct pt_regs, r6));
 	DEFINE(PT_r7, offsetof(struct pt_regs, r7));
+	DEFINE(PT_ret, offsetof(struct pt_regs, ret));
 
 	DEFINE(SZ_CALLEE_REGS, sizeof(struct callee_regs));
 	DEFINE(SZ_PT_REGS, sizeof(struct pt_regs));
+	DEFINE(PT_user_r25, offsetof(struct pt_regs, user_r25));
+
 	return 0;
 }
diff --git a/arch/arc/kernel/devtree.c b/arch/arc/kernel/devtree.c
index e32b54a..7e844fd 100644
--- a/arch/arc/kernel/devtree.c
+++ b/arch/arc/kernel/devtree.c
@@ -32,6 +32,8 @@
 
 	if (of_flat_dt_is_compatible(dt_root, "abilis,arc-tb10x"))
 		arc_base_baud = core_clk/3;
+	else if (of_flat_dt_is_compatible(dt_root, "snps,arc-sdp"))
+		arc_base_baud = 33333333;	/* Fixed 33MHz clk (AXS10x) */
 	else
 		arc_base_baud = core_clk;
 }
diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S
new file mode 100644
index 0000000..bd7105d
--- /dev/null
+++ b/arch/arc/kernel/entry-arcv2.S
@@ -0,0 +1,239 @@
+/*
+ * ARCv2 ISA based core Low Level Intr/Traps/Exceptions(non-TLB) Handling
+ *
+ * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>   /* ARC_{EXTRY,EXIT} */
+#include <asm/entry.h>       /* SAVE_ALL_{INT1,INT2,TRAP...} */
+#include <asm/errno.h>
+#include <asm/arcregs.h>
+#include <asm/irqflags.h>
+
+	.cpu HS
+
+#define VECTOR	.word
+
+;############################ Vector Table #################################
+
+	.section .vector,"a",@progbits
+	.align 4
+
+# Initial 16 slots are Exception Vectors
+VECTOR	stext			; Restart Vector (jump to entry point)
+VECTOR	mem_service		; Mem exception
+VECTOR	instr_service		; Instrn Error
+VECTOR	EV_MachineCheck		; Fatal Machine check
+VECTOR	EV_TLBMissI		; Intruction TLB miss
+VECTOR	EV_TLBMissD		; Data TLB miss
+VECTOR	EV_TLBProtV		; Protection Violation
+VECTOR	EV_PrivilegeV		; Privilege Violation
+VECTOR	EV_SWI			; Software Breakpoint
+VECTOR	EV_Trap			; Trap exception
+VECTOR	EV_Extension		; Extn Instruction Exception
+VECTOR	EV_DivZero		; Divide by Zero
+VECTOR	EV_DCError		; Data Cache Error
+VECTOR	EV_Misaligned		; Misaligned Data Access
+VECTOR	reserved		; Reserved slots
+VECTOR	reserved		; Reserved slots
+
+# Begin Interrupt Vectors
+VECTOR	handle_interrupt	; (16) Timer0
+VECTOR	handle_interrupt	; unused (Timer1)
+VECTOR	handle_interrupt	; unused (WDT)
+VECTOR	handle_interrupt	; (19) ICI (inter core interrupt)
+VECTOR	handle_interrupt
+VECTOR	handle_interrupt
+VECTOR	handle_interrupt
+VECTOR	handle_interrupt	; (23) End of fixed IRQs
+
+.rept CONFIG_ARC_NUMBER_OF_INTERRUPTS - 8
+	VECTOR	handle_interrupt
+.endr
+
+	.section .text, "ax",@progbits
+
+res_service:		; processor restart
+	flag    0x1     ; not implemented
+	nop
+	nop
+
+reserved:		; processor restart
+	rtie            ; jump to processor initializations
+
+;##################### Interrupt Handling ##############################
+
+ENTRY(handle_interrupt)
+
+	INTERRUPT_PROLOGUE  irq
+
+	clri		; To make status32.IE agree with CPU internal state
+
+	lr  r0, [ICAUSE]
+
+	mov   blink, ret_from_exception
+
+	b.d  arch_do_IRQ
+	mov r1, sp
+
+END(handle_interrupt)
+
+;################### Non TLB Exception Handling #############################
+
+ENTRY(EV_SWI)
+	flag 1
+END(EV_SWI)
+
+ENTRY(EV_DivZero)
+	flag 1
+END(EV_DivZero)
+
+ENTRY(EV_DCError)
+	flag 1
+END(EV_DCError)
+
+ENTRY(EV_Misaligned)
+
+	EXCEPTION_PROLOGUE
+
+	lr  r0, [efa]	; Faulting Data address
+	mov r1, sp
+
+	FAKE_RET_FROM_EXCPN
+
+	SAVE_CALLEE_SAVED_USER
+	mov r2, sp              ; callee_regs
+
+	bl  do_misaligned_access
+
+	; TBD: optimize - do this only if a callee reg was involved
+	; either a dst of emulated LD/ST or src with address-writeback
+	RESTORE_CALLEE_SAVED_USER
+
+	b   ret_from_exception
+END(EV_Misaligned)
+
+; ---------------------------------------------
+; Protection Violation Exception Handler
+; ---------------------------------------------
+
+ENTRY(EV_TLBProtV)
+
+	EXCEPTION_PROLOGUE
+
+	lr  r0, [efa]	; Faulting Data address
+	mov r1, sp	; pt_regs
+
+	FAKE_RET_FROM_EXCPN
+
+	mov blink, ret_from_exception
+	b   do_page_fault
+
+END(EV_TLBProtV)
+
+; From Linux standpoint Slow Path I/D TLB Miss is same a ProtV as they
+; need to call do_page_fault().
+; ECR in pt_regs provides whether access was R/W/X
+
+.global        call_do_page_fault
+.set call_do_page_fault, EV_TLBProtV
+
+;############# Common Handlers for ARCompact and ARCv2 ##############
+
+#include "entry.S"
+
+;############# Return from Intr/Excp/Trap (ARCv2 ISA Specifics) ##############
+;
+; Restore the saved sys context (common exit-path for EXCPN/IRQ/Trap)
+; IRQ shd definitely not happen between now and rtie
+; All 2 entry points to here already disable interrupts
+
+.Lrestore_regs:
+
+	ld	r0, [sp, PT_status32]	; U/K mode at time of entry
+	lr	r10, [AUX_IRQ_ACT]
+
+	bmsk	r11, r10, 15	; AUX_IRQ_ACT.ACTIVE
+	breq	r11, 0, .Lexcept_ret	; No intr active, ret from Exception
+
+;####### Return from Intr #######
+
+debug_marker_l1:
+	bbit1.nt r0, STATUS_DE_BIT, .Lintr_ret_to_delay_slot
+
+.Lisr_ret_fast_path:
+	; Handle special case #1: (Entry via Exception, Return via IRQ)
+	;
+	; Exception in U mode, preempted in kernel, Intr taken (K mode), orig
+	; task now returning to U mode (riding the Intr)
+	; AUX_IRQ_ACTIVE won't have U bit set (since intr in K mode), hence SP
+	; won't be switched to correct U mode value (from AUX_SP)
+	; So force AUX_IRQ_ACT.U for such a case
+
+	btst	r0, STATUS_U_BIT		; Z flag set if K (Z clear for U)
+	bset.nz	r11, r11, AUX_IRQ_ACT_BIT_U	; NZ means U
+	sr	r11, [AUX_IRQ_ACT]
+
+	INTERRUPT_EPILOGUE  irq
+	rtie
+
+;####### Return from Exception / pure kernel mode #######
+
+.Lexcept_ret:	; Expects r0 has PT_status32
+
+debug_marker_syscall:
+	EXCEPTION_EPILOGUE
+	rtie
+
+;####### Return from Intr to insn in delay slot #######
+
+; Handle special case #2: (Entry via Exception in Delay Slot, Return via IRQ)
+;
+; Intr returning to a Delay Slot (DS) insn
+; (since IRQ NOT allowed in DS in ARCv2, this can only happen if orig
+; entry was via Exception in DS which got preempted in kernel).
+;
+; IRQ RTIE won't reliably restore DE bit and/or BTA, needs handling
+.Lintr_ret_to_delay_slot:
+debug_marker_ds:
+
+	ld	r2, [@intr_to_DE_cnt]
+	add	r2, r2, 1
+	st	r2, [@intr_to_DE_cnt]
+
+	ld	r2, [sp, PT_ret]
+	ld	r3, [sp, PT_status32]
+
+	bic  	r0, r3, STATUS_U_MASK|STATUS_DE_MASK|STATUS_IE_MASK|STATUS_L_MASK
+	st	r0, [sp, PT_status32]
+
+	mov	r1, .Lintr_ret_to_delay_slot_2
+	st	r1, [sp, PT_ret]
+
+	st	r2, [sp, 0]
+	st	r3, [sp, 4]
+
+	b	.Lisr_ret_fast_path
+
+.Lintr_ret_to_delay_slot_2:
+	sub	sp, sp, SZ_PT_REGS
+	st	r9, [sp, -4]
+
+	ld	r9, [sp, 0]
+	sr	r9, [eret]
+
+	ld	r9, [sp, 4]
+	sr	r9, [erstatus]
+
+	ld	r9, [sp, 8]
+	sr	r9, [erbta]
+
+	ld	r9, [sp, -4]
+	add	sp, sp, SZ_PT_REGS
+	rtie
+
+END(ret_from_exception)
diff --git a/arch/arc/kernel/entry-compact.S b/arch/arc/kernel/entry-compact.S
new file mode 100644
index 0000000..15d457b
--- /dev/null
+++ b/arch/arc/kernel/entry-compact.S
@@ -0,0 +1,393 @@
+/*
+ * Low Level Interrupts/Traps/Exceptions(non-TLB) Handling for ARCompact ISA
+ *
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * vineetg: May 2011
+ *  -Userspace unaligned access emulation
+ *
+ * vineetg: Feb 2011 (ptrace low level code fixes)
+ *  -traced syscall return code (r0) was not saved into pt_regs for restoring
+ *   into user reg-file when traded task rets to user space.
+ *  -syscalls needing arch-wrappers (mainly for passing sp as pt_regs)
+ *   were not invoking post-syscall trace hook (jumping directly into
+ *   ret_from_system_call)
+ *
+ * vineetg: Nov 2010:
+ *  -Vector table jumps (@8 bytes) converted into branches (@4 bytes)
+ *  -To maintain the slot size of 8 bytes/vector, added nop, which is
+ *   not executed at runtime.
+ *
+ * vineetg: Nov 2009 (Everything needed for TIF_RESTORE_SIGMASK)
+ *  -do_signal()invoked upon TIF_RESTORE_SIGMASK as well
+ *  -Wrappers for sys_{,rt_}sigsuspend() nolonger needed as they don't
+ *   need ptregs anymore
+ *
+ * Vineetg: Oct 2009
+ *  -In a rare scenario, Process gets a Priv-V exception and gets scheduled
+ *   out. Since we don't do FAKE RTIE for Priv-V, CPU excpetion state remains
+ *   active (AE bit enabled).  This causes a double fault for a subseq valid
+ *   exception. Thus FAKE RTIE needed in low level Priv-Violation handler.
+ *   Instr Error could also cause similar scenario, so same there as well.
+ *
+ * Vineetg: March 2009 (Supporting 2 levels of Interrupts)
+ *
+ * Vineetg: Aug 28th 2008: Bug #94984
+ *  -Zero Overhead Loop Context shd be cleared when entering IRQ/EXcp/Trap
+ *   Normally CPU does this automatically, however when doing FAKE rtie,
+ *   we need to explicitly do this. The problem in macros
+ *   FAKE_RET_FROM_EXCPN and FAKE_RET_FROM_EXCPN_LOCK_IRQ was that this bit
+ *   was being "CLEARED" rather then "SET". Since it is Loop INHIBIT Bit,
+ *   setting it and not clearing it clears ZOL context
+ *
+ * Vineetg: May 16th, 2008
+ *  - r25 now contains the Current Task when in kernel
+ *
+ * Vineetg: Dec 22, 2007
+ *    Minor Surgery of Low Level ISR to make it SMP safe
+ *    - MMU_SCRATCH0 Reg used for freeing up r9 in Level 1 ISR
+ *    - _current_task is made an array of NR_CPUS
+ *    - Access of _current_task wrapped inside a macro so that if hardware
+ *       team agrees for a dedicated reg, no other code is touched
+ *
+ * Amit Bhor, Rahul Trivedi, Kanika Nema, Sameer Dhavale : Codito Tech 2004
+ */
+
+#include <linux/errno.h>
+#include <linux/linkage.h>	/* {EXTRY,EXIT} */
+#include <asm/entry.h>
+#include <asm/irqflags.h>
+
+	.cpu A7
+
+;############################ Vector Table #################################
+
+.macro VECTOR  lbl
+#if 1   /* Just in case, build breaks */
+	j   \lbl
+#else
+	b   \lbl
+	nop
+#endif
+.endm
+
+	.section .vector, "ax",@progbits
+	.align 4
+
+/* Each entry in the vector table must occupy 2 words. Since it is a jump
+ * across sections (.vector to .text) we are gauranteed that 'j somewhere'
+ * will use the 'j limm' form of the intrsuction as long as somewhere is in
+ * a section other than .vector.
+ */
+
+; ********* Critical System Events **********************
+VECTOR   res_service             ; 0x0, Restart Vector  (0x0)
+VECTOR   mem_service             ; 0x8, Mem exception   (0x1)
+VECTOR   instr_service           ; 0x10, Instrn Error   (0x2)
+
+; ******************** Device ISRs **********************
+#ifdef CONFIG_ARC_IRQ3_LV2
+VECTOR   handle_interrupt_level2
+#else
+VECTOR   handle_interrupt_level1
+#endif
+
+VECTOR   handle_interrupt_level1
+
+#ifdef CONFIG_ARC_IRQ5_LV2
+VECTOR   handle_interrupt_level2
+#else
+VECTOR   handle_interrupt_level1
+#endif
+
+#ifdef CONFIG_ARC_IRQ6_LV2
+VECTOR   handle_interrupt_level2
+#else
+VECTOR   handle_interrupt_level1
+#endif
+
+.rept   25
+VECTOR   handle_interrupt_level1 ; Other devices
+.endr
+
+/* FOR ARC600: timer = 0x3, uart = 0x8, emac = 0x10 */
+
+; ******************** Exceptions **********************
+VECTOR   EV_MachineCheck         ; 0x100, Fatal Machine check   (0x20)
+VECTOR   EV_TLBMissI             ; 0x108, Intruction TLB miss   (0x21)
+VECTOR   EV_TLBMissD             ; 0x110, Data TLB miss         (0x22)
+VECTOR   EV_TLBProtV             ; 0x118, Protection Violation  (0x23)
+				 ;         or Misaligned Access
+VECTOR   EV_PrivilegeV           ; 0x120, Privilege Violation   (0x24)
+VECTOR   EV_Trap                 ; 0x128, Trap exception        (0x25)
+VECTOR   EV_Extension            ; 0x130, Extn Intruction Excp  (0x26)
+
+.rept   24
+VECTOR   reserved                ; Reserved Exceptions
+.endr
+
+
+;##################### Scratch Mem for IRQ stack switching #############
+
+ARCFP_DATA int1_saved_reg
+	.align 32
+	.type   int1_saved_reg, @object
+	.size   int1_saved_reg, 4
+int1_saved_reg:
+	.zero 4
+
+/* Each Interrupt level needs its own scratch */
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
+
+ARCFP_DATA int2_saved_reg
+	.type   int2_saved_reg, @object
+	.size   int2_saved_reg, 4
+int2_saved_reg:
+	.zero 4
+
+#endif
+
+; ---------------------------------------------
+	.section .text, "ax",@progbits
+
+res_service:		; processor restart
+	flag    0x1     ; not implemented
+	nop
+	nop
+
+reserved:		; processor restart
+	rtie            ; jump to processor initializations
+
+;##################### Interrupt Handling ##############################
+
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
+; ---------------------------------------------
+;  Level 2 ISR: Can interrupt a Level 1 ISR
+; ---------------------------------------------
+ENTRY(handle_interrupt_level2)
+
+	INTERRUPT_PROLOGUE 2
+
+	;------------------------------------------------------
+	; if L2 IRQ interrupted a L1 ISR, disable preemption
+	;------------------------------------------------------
+
+	ld r9, [sp, PT_status32]        ; get statu32_l2 (saved in pt_regs)
+	bbit0 r9, STATUS_A1_BIT, 1f     ; L1 not active when L2 IRQ, so normal
+
+	; A1 is set in status32_l2
+	; bump thread_info->preempt_count (Disable preemption)
+	GET_CURR_THR_INFO_FROM_SP   r10
+	ld      r9, [r10, THREAD_INFO_PREEMPT_COUNT]
+	add     r9, r9, 1
+	st      r9, [r10, THREAD_INFO_PREEMPT_COUNT]
+
+1:
+	;------------------------------------------------------
+	; setup params for Linux common ISR and invoke it
+	;------------------------------------------------------
+	lr  r0, [icause2]
+	and r0, r0, 0x1f
+
+	bl.d  @arch_do_IRQ
+	mov r1, sp
+
+	mov r8,0x2
+	sr r8, [AUX_IRQ_LV12]       ; clear bit in Sticky Status Reg
+
+	b   ret_from_exception
+
+END(handle_interrupt_level2)
+
+#endif
+
+; ---------------------------------------------
+;  Level 1 ISR
+; ---------------------------------------------
+ENTRY(handle_interrupt_level1)
+
+	INTERRUPT_PROLOGUE 1
+
+	lr  r0, [icause1]
+	and r0, r0, 0x1f
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+	; icause1 needs to be read early, before calling tracing, which
+	; can clobber scratch regs, hence use of stack to stash it
+	push r0
+	TRACE_ASM_IRQ_DISABLE
+	pop  r0
+#endif
+
+	bl.d  @arch_do_IRQ
+	mov r1, sp
+
+	mov r8,0x1
+	sr r8, [AUX_IRQ_LV12]       ; clear bit in Sticky Status Reg
+
+	b   ret_from_exception
+END(handle_interrupt_level1)
+
+;################### Non TLB Exception Handling #############################
+
+; ---------------------------------------------
+; Protection Violation Exception Handler
+; ---------------------------------------------
+
+ENTRY(EV_TLBProtV)
+
+	EXCEPTION_PROLOGUE
+
+	lr  r2, [ecr]
+	lr  r0, [efa]	; Faulting Data address (not part of pt_regs saved above)
+
+	; Exception auto-disables further Intr/exceptions.
+	; Re-enable them by pretending to return from exception
+	; (so rest of handler executes in pure K mode)
+
+	FAKE_RET_FROM_EXCPN
+
+	mov   r1, sp	; Handle to pt_regs
+
+	;------ (5) Type of Protection Violation? ----------
+	;
+	; ProtV Hardware Exception is triggered for Access Faults of 2 types
+	;   -Access Violaton	: 00_23_(00|01|02|03)_00
+	;			         x  r  w  r+w
+	;   -Unaligned Access	: 00_23_04_00
+	;
+	bbit1 r2, ECR_C_BIT_PROTV_MISALIG_DATA, 4f
+
+	;========= (6a) Access Violation Processing ========
+	bl  do_page_fault
+	b   ret_from_exception
+
+	;========== (6b) Non aligned access ============
+4:
+
+	SAVE_CALLEE_SAVED_USER
+	mov r2, sp              ; callee_regs
+
+	bl  do_misaligned_access
+
+	; TBD: optimize - do this only if a callee reg was involved
+	; either a dst of emulated LD/ST or src with address-writeback
+	RESTORE_CALLEE_SAVED_USER
+
+	b   ret_from_exception
+
+END(EV_TLBProtV)
+
+; Wrapper for Linux page fault handler called from EV_TLBMiss*
+; Very similar to ProtV handler case (6a) above, but avoids the extra checks
+; for Misaligned access
+;
+ENTRY(call_do_page_fault)
+
+	EXCEPTION_PROLOGUE
+	lr  r0, [efa]	; Faulting Data address
+	mov   r1, sp
+	FAKE_RET_FROM_EXCPN
+
+	mov blink, ret_from_exception
+	b  do_page_fault
+
+END(call_do_page_fault)
+
+;############# Common Handlers for ARCompact and ARCv2 ##############
+
+#include "entry.S"
+
+;############# Return from Intr/Excp/Trap (ARC Specifics) ##############
+;
+; Restore the saved sys context (common exit-path for EXCPN/IRQ/Trap)
+; IRQ shd definitely not happen between now and rtie
+; All 2 entry points to here already disable interrupts
+
+.Lrestore_regs:
+
+	TRACE_ASM_IRQ_ENABLE
+
+	lr	r10, [status32]
+
+	; Restore REG File. In case multiple Events outstanding,
+	; use the same priorty as rtie: EXCPN, L2 IRQ, L1 IRQ, None
+	; Note that we use realtime STATUS32 (not pt_regs->status32) to
+	; decide that.
+
+	; if Returning from Exception
+	btst   r10, STATUS_AE_BIT
+	bnz    .Lexcep_ret
+
+	; Not Exception so maybe Interrupts (Level 1 or 2)
+
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
+
+	; Level 2 interrupt return Path - from hardware standpoint
+	bbit0  r10, STATUS_A2_BIT, not_level2_interrupt
+
+	;------------------------------------------------------------------
+	; However the context returning might not have taken L2 intr itself
+	; e.g. Task'A' user-code -> L2 intr -> schedule -> 'B' user-code ret
+	; Special considerations needed for the context which took L2 intr
+
+	ld   r9, [sp, PT_event]        ; Ensure this is L2 intr context
+	brne r9, event_IRQ2, 149f
+
+	;------------------------------------------------------------------
+	; if L2 IRQ interrupted an L1 ISR,  we'd disabled preemption earlier
+	; so that sched doesn't move to new task, causing L1 to be delayed
+	; undeterministically. Now that we've achieved that, let's reset
+	; things to what they were, before returning from L2 context
+	;----------------------------------------------------------------
+
+	ld r9, [sp, PT_status32]       ; get statu32_l2 (saved in pt_regs)
+	bbit0 r9, STATUS_A1_BIT, 149f  ; L1 not active when L2 IRQ, so normal
+
+	; decrement thread_info->preempt_count (re-enable preemption)
+	GET_CURR_THR_INFO_FROM_SP   r10
+	ld      r9, [r10, THREAD_INFO_PREEMPT_COUNT]
+
+	; paranoid check, given A1 was active when A2 happened, preempt count
+	; must not be 0 because we would have incremented it.
+	; If this does happen we simply HALT as it means a BUG !!!
+	cmp     r9, 0
+	bnz     2f
+	flag 1
+
+2:
+	sub     r9, r9, 1
+	st      r9, [r10, THREAD_INFO_PREEMPT_COUNT]
+
+149:
+	;return from level 2
+	INTERRUPT_EPILOGUE 2
+debug_marker_l2:
+	rtie
+
+not_level2_interrupt:
+
+#endif
+
+	bbit0  r10, STATUS_A1_BIT, .Lpure_k_mode_ret
+
+	;return from level 1
+	INTERRUPT_EPILOGUE 1
+debug_marker_l1:
+	rtie
+
+.Lexcep_ret:
+.Lpure_k_mode_ret:
+
+	;this case is for syscalls or Exceptions or pure kernel mode
+
+	EXCEPTION_EPILOGUE
+debug_marker_syscall:
+	rtie
+
+END(ret_from_exception)
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index d868289..f7a82fd 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -1,60 +1,13 @@
 /*
- * Low Level Interrupts/Traps/Exceptions(non-TLB) Handling for ARC
+ * Common Low Level Interrupts/Traps/Exceptions(non-TLB) Handling for ARC
+ * (included from entry-<isa>.S
  *
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
  * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * vineetg: May 2011
- *  -Userspace unaligned access emulation
- *
- * vineetg: Feb 2011 (ptrace low level code fixes)
- *  -traced syscall return code (r0) was not saved into pt_regs for restoring
- *   into user reg-file when traded task rets to user space.
- *  -syscalls needing arch-wrappers (mainly for passing sp as pt_regs)
- *   were not invoking post-syscall trace hook (jumping directly into
- *   ret_from_system_call)
- *
- * vineetg: Nov 2010:
- *  -Vector table jumps (@8 bytes) converted into branches (@4 bytes)
- *  -To maintain the slot size of 8 bytes/vector, added nop, which is
- *   not executed at runtime.
- *
- * vineetg: Nov 2009 (Everything needed for TIF_RESTORE_SIGMASK)
- *  -do_signal()invoked upon TIF_RESTORE_SIGMASK as well
- *  -Wrappers for sys_{,rt_}sigsuspend() nolonger needed as they don't
- *   need ptregs anymore
- *
- * Vineetg: Oct 2009
- *  -In a rare scenario, Process gets a Priv-V exception and gets scheduled
- *   out. Since we don't do FAKE RTIE for Priv-V, CPU excpetion state remains
- *   active (AE bit enabled).  This causes a double fault for a subseq valid
- *   exception. Thus FAKE RTIE needed in low level Priv-Violation handler.
- *   Instr Error could also cause similar scenario, so same there as well.
- *
- * Vineetg: March 2009 (Supporting 2 levels of Interrupts)
- *
- * Vineetg: Aug 28th 2008: Bug #94984
- *  -Zero Overhead Loop Context shd be cleared when entering IRQ/EXcp/Trap
- *   Normally CPU does this automatically, however when doing FAKE rtie,
- *   we need to explicitly do this. The problem in macros
- *   FAKE_RET_FROM_EXCPN and FAKE_RET_FROM_EXCPN_LOCK_IRQ was that this bit
- *   was being "CLEARED" rather then "SET". Since it is Loop INHIBIT Bit,
- *   setting it and not clearing it clears ZOL context
- *
- * Vineetg: May 16th, 2008
- *  - r25 now contains the Current Task when in kernel
- *
- * Vineetg: Dec 22, 2007
- *    Minor Surgery of Low Level ISR to make it SMP safe
- *    - MMU_SCRATCH0 Reg used for freeing up r9 in Level 1 ISR
- *    - _current_task is made an array of NR_CPUS
- *    - Access of _current_task wrapped inside a macro so that if hardware
- *       team agrees for a dedicated reg, no other code is touched
- *
- * Amit Bhor, Rahul Trivedi, Kanika Nema, Sameer Dhavale : Codito Tech 2004
  */
 
 /*------------------------------------------------------------------
@@ -67,206 +20,59 @@
  *  Global Pointer (gp)                 r26
  *  Frame Pointer (fp)                  r27
  *  Stack Pointer (sp)                  r28
- *  Interrupt link register (ilink1)    r29
- *  Interrupt link register (ilink2)    r30
  *  Branch link register (blink)        r31
  *------------------------------------------------------------------
  */
 
-	.cpu A7
+;################### Special Sys Call Wrappers ##########################
 
-;############################ Vector Table #################################
+ENTRY(sys_clone_wrapper)
+	SAVE_CALLEE_SAVED_USER
+	bl  @sys_clone
+	DISCARD_CALLEE_SAVED_USER
 
-.macro VECTOR  lbl
-#if 1   /* Just in case, build breaks */
-	j   \lbl
-#else
-	b   \lbl
-	nop
-#endif
-.endm
+	GET_CURR_THR_INFO_FLAGS   r10
+	btst r10, TIF_SYSCALL_TRACE
+	bnz  tracesys_exit
 
-	.section .vector, "ax",@progbits
-	.align 4
+	b ret_from_system_call
+END(sys_clone_wrapper)
 
-/* Each entry in the vector table must occupy 2 words. Since it is a jump
- * across sections (.vector to .text) we are gauranteed that 'j somewhere'
- * will use the 'j limm' form of the intrsuction as long as somewhere is in
- * a section other than .vector.
- */
+ENTRY(ret_from_fork)
+	; when the forked child comes here from the __switch_to function
+	; r0 has the last task pointer.
+	; put last task in scheduler queue
+	bl   @schedule_tail
 
-; ********* Critical System Events **********************
-VECTOR   res_service             ; 0x0, Restart Vector  (0x0)
-VECTOR   mem_service             ; 0x8, Mem exception   (0x1)
-VECTOR   instr_service           ; 0x10, Instrn Error   (0x2)
+	ld   r9, [sp, PT_status32]
+	brne r9, 0, 1f
 
-; ******************** Device ISRs **********************
-#ifdef CONFIG_ARC_IRQ3_LV2
-VECTOR   handle_interrupt_level2
-#else
-VECTOR   handle_interrupt_level1
-#endif
-
-VECTOR   handle_interrupt_level1
-
-#ifdef CONFIG_ARC_IRQ5_LV2
-VECTOR   handle_interrupt_level2
-#else
-VECTOR   handle_interrupt_level1
-#endif
-
-#ifdef CONFIG_ARC_IRQ6_LV2
-VECTOR   handle_interrupt_level2
-#else
-VECTOR   handle_interrupt_level1
-#endif
-
-.rept   25
-VECTOR   handle_interrupt_level1 ; Other devices
-.endr
-
-/* FOR ARC600: timer = 0x3, uart = 0x8, emac = 0x10 */
-
-; ******************** Exceptions **********************
-VECTOR   EV_MachineCheck         ; 0x100, Fatal Machine check   (0x20)
-VECTOR   EV_TLBMissI             ; 0x108, Intruction TLB miss   (0x21)
-VECTOR   EV_TLBMissD             ; 0x110, Data TLB miss         (0x22)
-VECTOR   EV_TLBProtV             ; 0x118, Protection Violation  (0x23)
-				 ;         or Misaligned Access
-VECTOR   EV_PrivilegeV           ; 0x120, Privilege Violation   (0x24)
-VECTOR   EV_Trap                 ; 0x128, Trap exception        (0x25)
-VECTOR   EV_Extension            ; 0x130, Extn Intruction Excp  (0x26)
-
-.rept   24
-VECTOR   reserved                ; Reserved Exceptions
-.endr
-
-#include <linux/linkage.h>   /* {EXTRY,EXIT} */
-#include <asm/entry.h>       /* SAVE_ALL_{INT1,INT2,SYS...} */
-#include <asm/errno.h>
-#include <asm/arcregs.h>
-#include <asm/irqflags.h>
-
-;##################### Scratch Mem for IRQ stack switching #############
-
-ARCFP_DATA int1_saved_reg
-	.align 32
-	.type   int1_saved_reg, @object
-	.size   int1_saved_reg, 4
-int1_saved_reg:
-	.zero 4
-
-/* Each Interrupt level needs its own scratch */
-#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
-
-ARCFP_DATA int2_saved_reg
-	.type   int2_saved_reg, @object
-	.size   int2_saved_reg, 4
-int2_saved_reg:
-	.zero 4
-
-#endif
-
-; ---------------------------------------------
-	.section .text, "ax",@progbits
-
-res_service:		; processor restart
-	flag    0x1     ; not implemented
-	nop
-	nop
-
-reserved:		; processor restart
-	rtie            ; jump to processor initializations
-
-;##################### Interrupt Handling ##############################
-
-#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
-; ---------------------------------------------
-;  Level 2 ISR: Can interrupt a Level 1 ISR
-; ---------------------------------------------
-ENTRY(handle_interrupt_level2)
-
-	; TODO-vineetg for SMP this wont work
-	; free up r9 as scratchpad
-	st  r9, [@int2_saved_reg]
-
-	;Which mode (user/kernel) was the system in when intr occured
-	lr  r9, [status32_l2]
-
-	SWITCH_TO_KERNEL_STK
-	SAVE_ALL_INT2
-
-	;------------------------------------------------------
-	; if L2 IRQ interrupted a L1 ISR, disable preemption
-	;------------------------------------------------------
-
-	ld r9, [sp, PT_status32]        ; get statu32_l2 (saved in pt_regs)
-	bbit0 r9, STATUS_A1_BIT, 1f     ; L1 not active when L2 IRQ, so normal
-
-	; A1 is set in status32_l2
-	; bump thread_info->preempt_count (Disable preemption)
-	GET_CURR_THR_INFO_FROM_SP   r10
-	ld      r9, [r10, THREAD_INFO_PREEMPT_COUNT]
-	add     r9, r9, 1
-	st      r9, [r10, THREAD_INFO_PREEMPT_COUNT]
+	jl.d [r14]		; kernel thread entry point
+	mov  r0, r13		; (see PF_KTHREAD block in copy_thread)
 
 1:
-	;------------------------------------------------------
-	; setup params for Linux common ISR and invoke it
-	;------------------------------------------------------
-	lr  r0, [icause2]
-	and r0, r0, 0x1f
+	; Return to user space
+	; 1. Any forked task (Reach here via BRne above)
+	; 2. First ever init task (Reach here via return from JL above)
+	;    This is the historic "kernel_execve" use-case, to return to init
+	;    user mode, in a round about way since that is always done from
+	;    a kernel thread which is executed via JL above but always returns
+	;    out whenever kernel_execve (now inline do_fork()) is involved
+	b    ret_from_exception
+END(ret_from_fork)
 
-	bl.d  @arch_do_IRQ
-	mov r1, sp
+#ifdef CONFIG_ARC_DW2_UNWIND
+; Workaround for bug 94179 (STAR ):
+; Despite -fasynchronous-unwind-tables, linker is not making dwarf2 unwinder
+; section (.debug_frame) as loadable. So we force it here.
+; This also fixes STAR 9000487933 where the prev-workaround (objcopy --setflag)
+; would not work after a clean build due to kernel build system dependencies.
+.section .debug_frame, "wa",@progbits
 
-	mov r8,0x2
-	sr r8, [AUX_IRQ_LV12]       ; clear bit in Sticky Status Reg
-
-	b   ret_from_exception
-
-END(handle_interrupt_level2)
-
+; Reset to .text as this file is included in entry-<isa>.S
+.section .text, "ax",@progbits
 #endif
 
-; ---------------------------------------------
-;  Level 1 ISR
-; ---------------------------------------------
-ENTRY(handle_interrupt_level1)
-
-	/* free up r9 as scratchpad */
-#ifdef CONFIG_SMP
-	sr  r9, [ARC_REG_SCRATCH_DATA0]
-#else
-	st   r9, [@int1_saved_reg]
-#endif
-
-	;Which mode (user/kernel) was the system in when intr occured
-	lr  r9, [status32_l1]
-
-	SWITCH_TO_KERNEL_STK
-	SAVE_ALL_INT1
-
-	lr  r0, [icause1]
-	and r0, r0, 0x1f
-
-#ifdef CONFIG_TRACE_IRQFLAGS
-	; icause1 needs to be read early, before calling tracing, which
-	; can clobber scratch regs, hence use of stack to stash it
-	push r0
-	TRACE_ASM_IRQ_DISABLE
-	pop  r0
-#endif
-
-	bl.d  @arch_do_IRQ
-	mov r1, sp
-
-	mov r8,0x1
-	sr r8, [AUX_IRQ_LV12]       ; clear bit in Sticky Status Reg
-
-	b   ret_from_exception
-END(handle_interrupt_level1)
-
 ;################### Non TLB Exception Handling #############################
 
 ; ---------------------------------------------
@@ -280,7 +86,7 @@
 	lr  r0, [efa]
 	mov r1, sp
 
-	FAKE_RET_FROM_EXCPN r9
+	FAKE_RET_FROM_EXCPN
 
 	bl  do_insterror_or_kprobe
 	b   ret_from_exception
@@ -297,7 +103,7 @@
 	lr  r0, [efa]
 	mov r1, sp
 
-	FAKE_RET_FROM_EXCPN r9
+	FAKE_RET_FROM_EXCPN
 
 	bl  do_memory_error
 	b   ret_from_exception
@@ -334,60 +140,6 @@
 END(EV_MachineCheck)
 
 ; ---------------------------------------------
-; Protection Violation Exception Handler
-; ---------------------------------------------
-
-ENTRY(EV_TLBProtV)
-
-	EXCEPTION_PROLOGUE
-
-	;---------(3) Save some more regs-----------------
-	;  vineetg: Mar 6th: Random Seg Fault issue #1
-	;  ecr and efa were not saved in case an Intr sneaks in
-	;  after fake rtie
-
-	lr  r2, [ecr]
-	lr  r0, [efa]	; Faulting Data address
-
-	; --------(4) Return from CPU Exception Mode ---------
-	;  Fake a rtie, but rtie to next label
-	;  That way, subsequently, do_page_fault ( ) executes in pure kernel
-	;  mode with further Exceptions enabled
-
-	FAKE_RET_FROM_EXCPN r9
-
-	mov   r1, sp
-
-	;------ (5) Type of Protection Violation? ----------
-	;
-	; ProtV Hardware Exception is triggered for Access Faults of 2 types
-	;   -Access Violaton	: 00_23_(00|01|02|03)_00
-	;			         x  r  w  r+w
-	;   -Unaligned Access	: 00_23_04_00
-	;
-	bbit1 r2, ECR_C_BIT_PROTV_MISALIG_DATA, 4f
-
-	;========= (6a) Access Violation Processing ========
-	bl  do_page_fault
-	b   ret_from_exception
-
-	;========== (6b) Non aligned access ============
-4:
-
-	SAVE_CALLEE_SAVED_USER
-	mov r2, sp              ; callee_regs
-
-	bl  do_misaligned_access
-
-	; TBD: optimize - do this only if a callee reg was involved
-	; either a dst of emulated LD/ST or src with address-writeback
-	RESTORE_CALLEE_SAVED_USER
-
-	b   ret_from_exception
-
-END(EV_TLBProtV)
-
-; ---------------------------------------------
 ; Privilege Violation Exception Handler
 ; ---------------------------------------------
 ENTRY(EV_PrivilegeV)
@@ -397,7 +149,7 @@
 	lr  r0, [efa]
 	mov r1, sp
 
-	FAKE_RET_FROM_EXCPN r9
+	FAKE_RET_FROM_EXCPN
 
 	bl  do_privilege_fault
 	b   ret_from_exception
@@ -413,14 +165,17 @@
 	lr  r0, [efa]
 	mov r1, sp
 
-	FAKE_RET_FROM_EXCPN r9
+	FAKE_RET_FROM_EXCPN
 
 	bl  do_extension_fault
 	b   ret_from_exception
 END(EV_Extension)
 
-;######################### System Call Tracing #########################
+;################ Trap Handling (Syscall, Breakpoint) ##################
 
+; ---------------------------------------------
+; syscall Tracing
+; ---------------------------------------------
 tracesys:
 	; save EFA in case tracer wants the PC of traced task
 	; using ERET won't work since next-PC has already committed
@@ -463,10 +218,9 @@
 	b   ret_from_exception ; NOT ret_from_system_call at is saves r0 which
 	; we'd done before calling post hook above
 
-;################### Break Point TRAP ##########################
-
-	; ======= (5b) Trap is due to Break-Point =========
-
+; ---------------------------------------------
+; Breakpoint TRAP
+; ---------------------------------------------
 trap_with_param:
 
 	; stop_pc info by gdb needs this info
@@ -475,7 +229,7 @@
 
 	; Now that we have read EFA, it is safe to do "fake" rtie
 	;   and get out of CPU exception mode
-	FAKE_RET_FROM_EXCPN r11
+	FAKE_RET_FROM_EXCPN
 
 	; Save callee regs in case gdb wants to have a look
 	; SP will grow up by size of CALLEE Reg-File
@@ -494,37 +248,33 @@
 
 	b   ret_from_exception
 
-;##################### Trap Handling ##############################
-;
-; EV_Trap caused by TRAP_S and TRAP0 instructions.
-;------------------------------------------------------------------
-;   (1) System Calls
-;       :parameters in r0-r7.
-;       :r8 has the system call number
-;   (2) Break Points
-;------------------------------------------------------------------
+; ---------------------------------------------
+; syscall TRAP
+; ABI: (r0-r7) upto 8 args, (r8) syscall number
+; ---------------------------------------------
 
 ENTRY(EV_Trap)
 
 	EXCEPTION_PROLOGUE
 
-	;------- (4) What caused the Trap --------------
-	lr     r12, [ecr]
-	bmsk.f 0, r12, 7
+	;============ TRAP 1   :breakpoints
+	; Check ECR for trap with arg (PROLOGUE ensures r9 has ECR)
+	bmsk.f 0, r9, 7
 	bnz    trap_with_param
 
-	; ======= (5a) Trap is due to System Call ========
+	;============ TRAP  (no param): syscall top level
 
-	; Before doing anything, return from CPU Exception Mode
-	FAKE_RET_FROM_EXCPN r11
+	; First return from Exception to pure K mode (Exception/IRQs renabled)
+	FAKE_RET_FROM_EXCPN
 
-	; If syscall tracing ongoing, invoke pre-pos-hooks
+	; If syscall tracing ongoing, invoke pre-post-hooks
 	GET_CURR_THR_INFO_FLAGS   r10
 	btst r10, TIF_SYSCALL_TRACE
 	bnz tracesys  ; this never comes back
 
-	;============ This is normal System Call case ==========
-	; Sys-call num shd not exceed the total system calls avail
+	;============ Normal syscall case
+
+	; syscall num shd not exceed the total system calls avail
 	cmp     r8,  NR_syscalls
 	mov.hi  r0, -ENOSYS
 	bhi     ret_from_system_call
@@ -565,7 +315,7 @@
 	; Fast Path return to user mode if no pending work
 	GET_CURR_THR_INFO_FLAGS   r9
 	and.f  0,  r9, _TIF_WORK_MASK
-	bz     restore_regs
+	bz     .Lrestore_regs
 
 	; --- (Slow Path #1) task preemption ---
 	bbit0  r9, TIF_NEED_RESCHED, .Lchk_pend_signals
@@ -624,11 +374,11 @@
 	; Can't preempt if preemption disabled
 	GET_CURR_THR_INFO_FROM_SP   r10
 	ld  r8, [r10, THREAD_INFO_PREEMPT_COUNT]
-	brne  r8, 0, restore_regs
+	brne  r8, 0, .Lrestore_regs
 
 	; check if this task's NEED_RESCHED flag set
 	ld  r9, [r10, THREAD_INFO_FLAGS]
-	bbit0  r9, TIF_NEED_RESCHED, restore_regs
+	bbit0  r9, TIF_NEED_RESCHED, .Lrestore_regs
 
 	; Invoke PREEMPTION
 	bl      preempt_schedule_irq
@@ -636,142 +386,7 @@
 	; preempt_schedule_irq() always returns with IRQ disabled
 #endif
 
-	; fall through
+	b	.Lrestore_regs
 
-;############# Return from Intr/Excp/Trap (ARC Specifics) ##############
-;
-; Restore the saved sys context (common exit-path for EXCPN/IRQ/Trap)
-; IRQ shd definitely not happen between now and rtie
-; All 2 entry points to here already disable interrupts
+##### DONT ADD CODE HERE - .Lrestore_regs actually follows in entry-<isa>.S
 
-restore_regs :
-
-	TRACE_ASM_IRQ_ENABLE
-
-	lr	r10, [status32]
-
-	; Restore REG File. In case multiple Events outstanding,
-	; use the same priorty as rtie: EXCPN, L2 IRQ, L1 IRQ, None
-	; Note that we use realtime STATUS32 (not pt_regs->status32) to
-	; decide that.
-
-	; if Returning from Exception
-	bbit0  r10, STATUS_AE_BIT, not_exception
-	RESTORE_ALL_SYS
-	rtie
-
-	; Not Exception so maybe Interrupts (Level 1 or 2)
-
-not_exception:
-
-#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
-
-	; Level 2 interrupt return Path - from hardware standpoint
-	bbit0  r10, STATUS_A2_BIT, not_level2_interrupt
-
-	;------------------------------------------------------------------
-	; However the context returning might not have taken L2 intr itself
-	; e.g. Task'A' user-code -> L2 intr -> schedule -> 'B' user-code ret
-	; Special considerations needed for the context which took L2 intr
-
-	ld   r9, [sp, PT_event]        ; Ensure this is L2 intr context
-	brne r9, event_IRQ2, 149f
-
-	;------------------------------------------------------------------
-	; if L2 IRQ interrupted an L1 ISR,  we'd disabled preemption earlier
-	; so that sched doesn't move to new task, causing L1 to be delayed
-	; undeterministically. Now that we've achieved that, let's reset
-	; things to what they were, before returning from L2 context
-	;----------------------------------------------------------------
-
-	ld r9, [sp, PT_status32]       ; get statu32_l2 (saved in pt_regs)
-	bbit0 r9, STATUS_A1_BIT, 149f  ; L1 not active when L2 IRQ, so normal
-
-	; decrement thread_info->preempt_count (re-enable preemption)
-	GET_CURR_THR_INFO_FROM_SP   r10
-	ld      r9, [r10, THREAD_INFO_PREEMPT_COUNT]
-
-	; paranoid check, given A1 was active when A2 happened, preempt count
-	; must not be 0 because we would have incremented it.
-	; If this does happen we simply HALT as it means a BUG !!!
-	cmp     r9, 0
-	bnz     2f
-	flag 1
-
-2:
-	sub     r9, r9, 1
-	st      r9, [r10, THREAD_INFO_PREEMPT_COUNT]
-
-149:
-	;return from level 2
-	RESTORE_ALL_INT2
-debug_marker_l2:
-	rtie
-
-not_level2_interrupt:
-
-#endif
-
-	bbit0  r10, STATUS_A1_BIT, not_level1_interrupt
-
-	;return from level 1
-
-	RESTORE_ALL_INT1
-debug_marker_l1:
-	rtie
-
-not_level1_interrupt:
-
-	;this case is for syscalls or Exceptions (with fake rtie)
-
-	RESTORE_ALL_SYS
-debug_marker_syscall:
-	rtie
-
-END(ret_from_exception)
-
-ENTRY(ret_from_fork)
-	; when the forked child comes here from the __switch_to function
-	; r0 has the last task pointer.
-	; put last task in scheduler queue
-	bl   @schedule_tail
-
-	ld   r9, [sp, PT_status32]
-	brne r9, 0, 1f
-
-	jl.d [r14]		; kernel thread entry point
-	mov  r0, r13		; (see PF_KTHREAD block in copy_thread)
-
-1:
-	; Return to user space
-	; 1. Any forked task (Reach here via BRne above)
-	; 2. First ever init task (Reach here via return from JL above)
-	;    This is the historic "kernel_execve" use-case, to return to init
-	;    user mode, in a round about way since that is always done from
-	;    a kernel thread which is executed via JL above but always returns
-	;    out whenever kernel_execve (now inline do_fork()) is involved
-	b    ret_from_exception
-END(ret_from_fork)
-
-;################### Special Sys Call Wrappers ##########################
-
-ENTRY(sys_clone_wrapper)
-	SAVE_CALLEE_SAVED_USER
-	bl  @sys_clone
-	DISCARD_CALLEE_SAVED_USER
-
-	GET_CURR_THR_INFO_FLAGS   r10
-	btst r10, TIF_SYSCALL_TRACE
-	bnz  tracesys_exit
-
-	b ret_from_system_call
-END(sys_clone_wrapper)
-
-#ifdef CONFIG_ARC_DW2_UNWIND
-; Workaround for bug 94179 (STAR ):
-; Despite -fasynchronous-unwind-tables, linker is not making dwarf2 unwinder
-; section (.debug_frame) as loadable. So we force it here.
-; This also fixes STAR 9000487933 where the prev-workaround (objcopy --setflag)
-; would not work after a clean build due to kernel build system dependencies.
-.section .debug_frame, "wa",@progbits
-#endif
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index b0e8666..812f95e 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -49,8 +49,6 @@
 1:
 .endm
 
-	.cpu A7
-
 	.section .init.text, "ax",@progbits
 	.type stext, @function
 	.globl stext
@@ -83,6 +81,7 @@
 	st.ab   0, [r5, 4]
 1:
 
+#ifdef CONFIG_ARC_UBOOT_SUPPORT
 	; Uboot - kernel ABI
 	;    r0 = [0] No uboot interaction, [1] cmdline in r2, [2] DTB in r2
 	;    r1 = magic number (board identity, unused as of now
@@ -90,6 +89,7 @@
 	; These are handled later in setup_arch()
 	st	r0, [@uboot_tag]
 	st	r2, [@uboot_arg]
+#endif
 
 	; setup "current" tsk and optionally cache it in dedicated r25
 	mov	r9, @init_task
diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c
new file mode 100644
index 0000000..6208c63
--- /dev/null
+++ b/arch/arc/kernel/intc-arcv2.c
@@ -0,0 +1,143 @@
+/*
+ * Copyright (C) 2014 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/irqdomain.h>
+#include <linux/irqchip.h>
+#include "../../drivers/irqchip/irqchip.h"
+#include <asm/irq.h>
+
+/*
+ * Early Hardware specific Interrupt setup
+ * -Called very early (start_kernel -> setup_arch -> setup_processor)
+ * -Platform Independent (must for any ARC Core)
+ * -Needed for each CPU (hence not foldable into init_IRQ)
+ */
+void arc_init_IRQ(void)
+{
+	unsigned int tmp;
+
+	struct aux_irq_ctrl {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+		unsigned int res3:18, save_idx_regs:1, res2:1,
+			     save_u_to_u:1, save_lp_regs:1, save_blink:1,
+			     res:4, save_nr_gpr_pairs:5;
+#else
+		unsigned int save_nr_gpr_pairs:5, res:4,
+			     save_blink:1, save_lp_regs:1, save_u_to_u:1,
+			     res2:1, save_idx_regs:1, res3:18;
+#endif
+	} ictrl;
+
+	*(unsigned int *)&ictrl = 0;
+
+	ictrl.save_nr_gpr_pairs = 6;	/* r0 to r11 (r12 saved manually) */
+	ictrl.save_blink = 1;
+	ictrl.save_lp_regs = 1;		/* LP_COUNT, LP_START, LP_END */
+	ictrl.save_u_to_u = 0;		/* user ctxt saved on kernel stack */
+	ictrl.save_idx_regs = 1;	/* JLI, LDI, EI */
+
+	WRITE_AUX(AUX_IRQ_CTRL, ictrl);
+
+	/* setup status32, don't enable intr yet as kernel doesn't want */
+	tmp = read_aux_reg(0xa);
+	tmp |= ISA_INIT_STATUS_BITS;
+	tmp &= ~STATUS_IE_MASK;
+	asm volatile("flag %0	\n"::"r"(tmp));
+
+	/*
+	 * ARCv2 core intc provides multiple interrupt priorities (upto 16).
+	 * Typical builds though have only two levels (0-high, 1-low)
+	 * Linux by default uses lower prio 1 for most irqs, reserving 0 for
+	 * NMI style interrupts in future (say perf)
+	 *
+	 * Read the intc BCR to confirm that Linux default priority is avail
+	 * in h/w
+	 *
+	 * Note:
+	 *  IRQ_BCR[27..24] contains N-1 (for N priority levels) and prio level
+	 *  is 0 based.
+	 */
+	tmp = (read_aux_reg(ARC_REG_IRQ_BCR) >> 24 ) & 0xF;
+	if (ARCV2_IRQ_DEF_PRIO > tmp)
+		panic("Linux default irq prio incorrect\n");
+}
+
+static void arcv2_irq_mask(struct irq_data *data)
+{
+	write_aux_reg(AUX_IRQ_SELECT, data->irq);
+	write_aux_reg(AUX_IRQ_ENABLE, 0);
+}
+
+static void arcv2_irq_unmask(struct irq_data *data)
+{
+	write_aux_reg(AUX_IRQ_SELECT, data->irq);
+	write_aux_reg(AUX_IRQ_ENABLE, 1);
+}
+
+void arcv2_irq_enable(struct irq_data *data)
+{
+	/* set default priority */
+	write_aux_reg(AUX_IRQ_SELECT, data->irq);
+	write_aux_reg(AUX_IRQ_PRIORITY, ARCV2_IRQ_DEF_PRIO);
+
+	/*
+	 * hw auto enables (linux unmask) all by default
+	 * So no need to do IRQ_ENABLE here
+	 * XXX: However OSCI LAN need it
+	 */
+	write_aux_reg(AUX_IRQ_ENABLE, 1);
+}
+
+static struct irq_chip arcv2_irq_chip = {
+	.name           = "ARCv2 core Intc",
+	.irq_mask	= arcv2_irq_mask,
+	.irq_unmask	= arcv2_irq_unmask,
+	.irq_enable	= arcv2_irq_enable
+};
+
+static int arcv2_irq_map(struct irq_domain *d, unsigned int irq,
+			 irq_hw_number_t hw)
+{
+	if (irq == TIMER0_IRQ || irq == IPI_IRQ)
+		irq_set_chip_and_handler(irq, &arcv2_irq_chip, handle_percpu_irq);
+	else
+		irq_set_chip_and_handler(irq, &arcv2_irq_chip, handle_level_irq);
+
+	return 0;
+}
+
+static const struct irq_domain_ops arcv2_irq_ops = {
+	.xlate = irq_domain_xlate_onecell,
+	.map = arcv2_irq_map,
+};
+
+static struct irq_domain *root_domain;
+
+static int __init
+init_onchip_IRQ(struct device_node *intc, struct device_node *parent)
+{
+	if (parent)
+		panic("DeviceTree incore intc not a root irq controller\n");
+
+	root_domain = irq_domain_add_legacy(intc, NR_CPU_IRQS, 0, 0,
+					    &arcv2_irq_ops, NULL);
+
+	if (!root_domain)
+		panic("root irq domain not avail\n");
+
+	/* with this we don't need to export root_domain */
+	irq_set_default_host(root_domain);
+
+	return 0;
+}
+
+IRQCHIP_DECLARE(arc_intc, "snps,archs-intc", init_onchip_IRQ);
diff --git a/arch/arc/kernel/intc-compact.c b/arch/arc/kernel/intc-compact.c
new file mode 100644
index 0000000..fcdddb6
--- /dev/null
+++ b/arch/arc/kernel/intc-compact.c
@@ -0,0 +1,226 @@
+/*
+ * Copyright (C) 2011-12 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/irqdomain.h>
+#include <linux/irqchip.h>
+#include "../../drivers/irqchip/irqchip.h"
+#include <asm/irq.h>
+
+/*
+ * Early Hardware specific Interrupt setup
+ * -Platform independent, needed for each CPU (not foldable into init_IRQ)
+ * -Called very early (start_kernel -> setup_arch -> setup_processor)
+ *
+ * what it does ?
+ * -Optionally, setup the High priority Interrupts as Level 2 IRQs
+ */
+void arc_init_IRQ(void)
+{
+	int level_mask = 0;
+
+       /* setup any high priority Interrupts (Level2 in ARCompact jargon) */
+	level_mask |= IS_ENABLED(CONFIG_ARC_IRQ3_LV2) << 3;
+	level_mask |= IS_ENABLED(CONFIG_ARC_IRQ5_LV2) << 5;
+	level_mask |= IS_ENABLED(CONFIG_ARC_IRQ6_LV2) << 6;
+
+	/*
+	 * Write to register, even if no LV2 IRQs configured to reset it
+	 * in case bootloader had mucked with it
+	 */
+	write_aux_reg(AUX_IRQ_LEV, level_mask);
+
+	if (level_mask)
+		pr_info("Level-2 interrupts bitset %x\n", level_mask);
+}
+
+/*
+ * ARC700 core includes a simple on-chip intc supporting
+ * -per IRQ enable/disable
+ * -2 levels of interrupts (high/low)
+ * -all interrupts being level triggered
+ *
+ * To reduce platform code, we assume all IRQs directly hooked-up into intc.
+ * Platforms with external intc, hence cascaded IRQs, are free to over-ride
+ * below, per IRQ.
+ */
+
+static void arc_irq_mask(struct irq_data *data)
+{
+	unsigned int ienb;
+
+	ienb = read_aux_reg(AUX_IENABLE);
+	ienb &= ~(1 << data->irq);
+	write_aux_reg(AUX_IENABLE, ienb);
+}
+
+static void arc_irq_unmask(struct irq_data *data)
+{
+	unsigned int ienb;
+
+	ienb = read_aux_reg(AUX_IENABLE);
+	ienb |= (1 << data->irq);
+	write_aux_reg(AUX_IENABLE, ienb);
+}
+
+static struct irq_chip onchip_intc = {
+	.name           = "ARC In-core Intc",
+	.irq_mask	= arc_irq_mask,
+	.irq_unmask	= arc_irq_unmask,
+};
+
+static int arc_intc_domain_map(struct irq_domain *d, unsigned int irq,
+			       irq_hw_number_t hw)
+{
+	/*
+	 * XXX: the IPI IRQ needs to be handled like TIMER too. However ARC core
+	 *      code doesn't own it (like TIMER0). ISS IDU / ezchip define it
+	 *      in platform header which can't be included here as it goes
+	 *      against multi-platform image philisophy
+	 */
+	if (irq == TIMER0_IRQ)
+		irq_set_chip_and_handler(irq, &onchip_intc, handle_percpu_irq);
+	else
+		irq_set_chip_and_handler(irq, &onchip_intc, handle_level_irq);
+
+	return 0;
+}
+
+static const struct irq_domain_ops arc_intc_domain_ops = {
+	.xlate = irq_domain_xlate_onecell,
+	.map = arc_intc_domain_map,
+};
+
+static struct irq_domain *root_domain;
+
+static int __init
+init_onchip_IRQ(struct device_node *intc, struct device_node *parent)
+{
+	if (parent)
+		panic("DeviceTree incore intc not a root irq controller\n");
+
+	root_domain = irq_domain_add_legacy(intc, NR_CPU_IRQS, 0, 0,
+					    &arc_intc_domain_ops, NULL);
+
+	if (!root_domain)
+		panic("root irq domain not avail\n");
+
+	/* with this we don't need to export root_domain */
+	irq_set_default_host(root_domain);
+
+	return 0;
+}
+
+IRQCHIP_DECLARE(arc_intc, "snps,arc700-intc", init_onchip_IRQ);
+
+/*
+ * arch_local_irq_enable - Enable interrupts.
+ *
+ * 1. Explicitly called to re-enable interrupts
+ * 2. Implicitly called from spin_unlock_irq, write_unlock_irq etc
+ *    which maybe in hard ISR itself
+ *
+ * Semantics of this function change depending on where it is called from:
+ *
+ * -If called from hard-ISR, it must not invert interrupt priorities
+ *  e.g. suppose TIMER is high priority (Level 2) IRQ
+ *    Time hard-ISR, timer_interrupt( ) calls spin_unlock_irq several times.
+ *    Here local_irq_enable( ) shd not re-enable lower priority interrupts
+ * -If called from soft-ISR, it must re-enable all interrupts
+ *    soft ISR are low prioity jobs which can be very slow, thus all IRQs
+ *    must be enabled while they run.
+ *    Now hardware context wise we may still be in L2 ISR (not done rtie)
+ *    still we must re-enable both L1 and L2 IRQs
+ *  Another twist is prev scenario with flow being
+ *     L1 ISR ==> interrupted by L2 ISR  ==> L2 soft ISR
+ *     here we must not re-enable Ll as prev Ll Interrupt's h/w context will get
+ *     over-written (this is deficiency in ARC700 Interrupt mechanism)
+ */
+
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS	/* Complex version for 2 IRQ levels */
+
+void arch_local_irq_enable(void)
+{
+
+	unsigned long flags = arch_local_save_flags();
+
+	/* Allow both L1 and L2 at the onset */
+	flags |= (STATUS_E1_MASK | STATUS_E2_MASK);
+
+	/* Called from hard ISR (between irq_enter and irq_exit) */
+	if (in_irq()) {
+
+		/* If in L2 ISR, don't re-enable any further IRQs as this can
+		 * cause IRQ priorities to get upside down. e.g. it could allow
+		 * L1 be taken while in L2 hard ISR which is wrong not only in
+		 * theory, it can also cause the dreaded L1-L2-L1 scenario
+		 */
+		if (flags & STATUS_A2_MASK)
+			flags &= ~(STATUS_E1_MASK | STATUS_E2_MASK);
+
+		/* Even if in L1 ISR, allowe Higher prio L2 IRQs */
+		else if (flags & STATUS_A1_MASK)
+			flags &= ~(STATUS_E1_MASK);
+	}
+
+	/* called from soft IRQ, ideally we want to re-enable all levels */
+
+	else if (in_softirq()) {
+
+		/* However if this is case of L1 interrupted by L2,
+		 * re-enabling both may cause whaco L1-L2-L1 scenario
+		 * because ARC700 allows level 1 to interrupt an active L2 ISR
+		 * Thus we disable both
+		 * However some code, executing in soft ISR wants some IRQs
+		 * to be enabled so we re-enable L2 only
+		 *
+		 * How do we determine L1 intr by L2
+		 *  -A2 is set (means in L2 ISR)
+		 *  -E1 is set in this ISR's pt_regs->status32 which is
+		 *      saved copy of status32_l2 when l2 ISR happened
+		 */
+		struct pt_regs *pt = get_irq_regs();
+
+		if ((flags & STATUS_A2_MASK) && pt &&
+		    (pt->status32 & STATUS_A1_MASK)) {
+			/*flags &= ~(STATUS_E1_MASK | STATUS_E2_MASK); */
+			flags &= ~(STATUS_E1_MASK);
+		}
+	}
+
+	arch_local_irq_restore(flags);
+}
+
+#else /* ! CONFIG_ARC_COMPACT_IRQ_LEVELS */
+
+/*
+ * Simpler version for only 1 level of interrupt
+ * Here we only Worry about Level 1 Bits
+ */
+void arch_local_irq_enable(void)
+{
+	unsigned long flags;
+
+	/*
+	 * ARC IDE Drivers tries to re-enable interrupts from hard-isr
+	 * context which is simply wrong
+	 */
+	if (in_irq()) {
+		WARN_ONCE(1, "IRQ enabled from hard-isr");
+		return;
+	}
+
+	flags = arch_local_save_flags();
+	flags |= (STATUS_E1_MASK | STATUS_E2_MASK);
+	arch_local_irq_restore(flags);
+}
+#endif
+EXPORT_SYMBOL(arch_local_irq_enable);
diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c
index 620ec2f..2989a7b 100644
--- a/arch/arc/kernel/irq.c
+++ b/arch/arc/kernel/irq.c
@@ -8,116 +8,10 @@
  */
 
 #include <linux/interrupt.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/irqdomain.h>
 #include <linux/irqchip.h>
-#include "../../drivers/irqchip/irqchip.h"
-#include <asm/sections.h>
-#include <asm/irq.h>
 #include <asm/mach_desc.h>
 
 /*
- * Early Hardware specific Interrupt setup
- * -Platform independent, needed for each CPU (not foldable into init_IRQ)
- * -Called very early (start_kernel -> setup_arch -> setup_processor)
- *
- * what it does ?
- * -Optionally, setup the High priority Interrupts as Level 2 IRQs
- */
-void arc_init_IRQ(void)
-{
-	int level_mask = 0;
-
-       /* setup any high priority Interrupts (Level2 in ARCompact jargon) */
-	level_mask |= IS_ENABLED(CONFIG_ARC_IRQ3_LV2) << 3;
-	level_mask |= IS_ENABLED(CONFIG_ARC_IRQ5_LV2) << 5;
-	level_mask |= IS_ENABLED(CONFIG_ARC_IRQ6_LV2) << 6;
-
-	/*
-	 * Write to register, even if no LV2 IRQs configured to reset it
-	 * in case bootloader had mucked with it
-	 */
-	write_aux_reg(AUX_IRQ_LEV, level_mask);
-
-	if (level_mask)
-		pr_info("Level-2 interrupts bitset %x\n", level_mask);
-}
-
-/*
- * ARC700 core includes a simple on-chip intc supporting
- * -per IRQ enable/disable
- * -2 levels of interrupts (high/low)
- * -all interrupts being level triggered
- *
- * To reduce platform code, we assume all IRQs directly hooked-up into intc.
- * Platforms with external intc, hence cascaded IRQs, are free to over-ride
- * below, per IRQ.
- */
-
-static void arc_irq_mask(struct irq_data *data)
-{
-	unsigned int ienb;
-
-	ienb = read_aux_reg(AUX_IENABLE);
-	ienb &= ~(1 << data->irq);
-	write_aux_reg(AUX_IENABLE, ienb);
-}
-
-static void arc_irq_unmask(struct irq_data *data)
-{
-	unsigned int ienb;
-
-	ienb = read_aux_reg(AUX_IENABLE);
-	ienb |= (1 << data->irq);
-	write_aux_reg(AUX_IENABLE, ienb);
-}
-
-static struct irq_chip onchip_intc = {
-	.name           = "ARC In-core Intc",
-	.irq_mask	= arc_irq_mask,
-	.irq_unmask	= arc_irq_unmask,
-};
-
-static int arc_intc_domain_map(struct irq_domain *d, unsigned int irq,
-				irq_hw_number_t hw)
-{
-	if (irq == TIMER0_IRQ)
-		irq_set_chip_and_handler(irq, &onchip_intc, handle_percpu_irq);
-	else
-		irq_set_chip_and_handler(irq, &onchip_intc, handle_level_irq);
-
-	return 0;
-}
-
-static const struct irq_domain_ops arc_intc_domain_ops = {
-	.xlate = irq_domain_xlate_onecell,
-	.map = arc_intc_domain_map,
-};
-
-static struct irq_domain *root_domain;
-
-static int __init
-init_onchip_IRQ(struct device_node *intc, struct device_node *parent)
-{
-	if (parent)
-		panic("DeviceTree incore intc not a root irq controller\n");
-
-	root_domain = irq_domain_add_legacy(intc, NR_CPU_IRQS, 0, 0,
-					    &arc_intc_domain_ops, NULL);
-
-	if (!root_domain)
-		panic("root irq domain not avail\n");
-
-	/* with this we don't need to export root_domain */
-	irq_set_default_host(root_domain);
-
-	return 0;
-}
-
-IRQCHIP_DECLARE(arc_intc, "snps,arc700-intc", init_onchip_IRQ);
-
-/*
  * Late Interrupt system init called from start_kernel for Boot CPU only
  *
  * Since slab must already be initialized, platforms can start doing any
@@ -178,107 +72,3 @@
 
 	enable_percpu_irq(irq, 0);
 }
-
-/*
- * arch_local_irq_enable - Enable interrupts.
- *
- * 1. Explicitly called to re-enable interrupts
- * 2. Implicitly called from spin_unlock_irq, write_unlock_irq etc
- *    which maybe in hard ISR itself
- *
- * Semantics of this function change depending on where it is called from:
- *
- * -If called from hard-ISR, it must not invert interrupt priorities
- *  e.g. suppose TIMER is high priority (Level 2) IRQ
- *    Time hard-ISR, timer_interrupt( ) calls spin_unlock_irq several times.
- *    Here local_irq_enable( ) shd not re-enable lower priority interrupts
- * -If called from soft-ISR, it must re-enable all interrupts
- *    soft ISR are low prioity jobs which can be very slow, thus all IRQs
- *    must be enabled while they run.
- *    Now hardware context wise we may still be in L2 ISR (not done rtie)
- *    still we must re-enable both L1 and L2 IRQs
- *  Another twist is prev scenario with flow being
- *     L1 ISR ==> interrupted by L2 ISR  ==> L2 soft ISR
- *     here we must not re-enable Ll as prev Ll Interrupt's h/w context will get
- *     over-written (this is deficiency in ARC700 Interrupt mechanism)
- */
-
-#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS	/* Complex version for 2 IRQ levels */
-
-void arch_local_irq_enable(void)
-{
-
-	unsigned long flags;
-	flags = arch_local_save_flags();
-
-	/* Allow both L1 and L2 at the onset */
-	flags |= (STATUS_E1_MASK | STATUS_E2_MASK);
-
-	/* Called from hard ISR (between irq_enter and irq_exit) */
-	if (in_irq()) {
-
-		/* If in L2 ISR, don't re-enable any further IRQs as this can
-		 * cause IRQ priorities to get upside down. e.g. it could allow
-		 * L1 be taken while in L2 hard ISR which is wrong not only in
-		 * theory, it can also cause the dreaded L1-L2-L1 scenario
-		 */
-		if (flags & STATUS_A2_MASK)
-			flags &= ~(STATUS_E1_MASK | STATUS_E2_MASK);
-
-		/* Even if in L1 ISR, allowe Higher prio L2 IRQs */
-		else if (flags & STATUS_A1_MASK)
-			flags &= ~(STATUS_E1_MASK);
-	}
-
-	/* called from soft IRQ, ideally we want to re-enable all levels */
-
-	else if (in_softirq()) {
-
-		/* However if this is case of L1 interrupted by L2,
-		 * re-enabling both may cause whaco L1-L2-L1 scenario
-		 * because ARC700 allows level 1 to interrupt an active L2 ISR
-		 * Thus we disable both
-		 * However some code, executing in soft ISR wants some IRQs
-		 * to be enabled so we re-enable L2 only
-		 *
-		 * How do we determine L1 intr by L2
-		 *  -A2 is set (means in L2 ISR)
-		 *  -E1 is set in this ISR's pt_regs->status32 which is
-		 *      saved copy of status32_l2 when l2 ISR happened
-		 */
-		struct pt_regs *pt = get_irq_regs();
-		if ((flags & STATUS_A2_MASK) && pt &&
-		    (pt->status32 & STATUS_A1_MASK)) {
-			/*flags &= ~(STATUS_E1_MASK | STATUS_E2_MASK); */
-			flags &= ~(STATUS_E1_MASK);
-		}
-	}
-
-	arch_local_irq_restore(flags);
-}
-
-#else /* ! CONFIG_ARC_COMPACT_IRQ_LEVELS */
-
-/*
- * Simpler version for only 1 level of interrupt
- * Here we only Worry about Level 1 Bits
- */
-void arch_local_irq_enable(void)
-{
-	unsigned long flags;
-
-	/*
-	 * ARC IDE Drivers tries to re-enable interrupts from hard-isr
-	 * context which is simply wrong
-	 */
-	if (in_irq()) {
-		WARN_ONCE(1, "IRQ enabled from hard-isr");
-		return;
-	}
-
-	flags = arch_local_save_flags();
-	flags |= (STATUS_E1_MASK | STATUS_E2_MASK);
-	arch_local_irq_restore(flags);
-}
-#endif
-EXPORT_SYMBOL(arch_local_irq_enable);
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
new file mode 100644
index 0000000..30284e8
--- /dev/null
+++ b/arch/arc/kernel/mcip.c
@@ -0,0 +1,341 @@
+/*
+ * ARC ARConnect (MultiCore IP) support (formerly known as MCIP)
+ *
+ * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/smp.h>
+#include <linux/irq.h>
+#include <linux/spinlock.h>
+#include <asm/mcip.h>
+
+static char smp_cpuinfo_buf[128];
+static int idu_detected;
+
+static DEFINE_RAW_SPINLOCK(mcip_lock);
+
+/*
+ * Any SMP specific init any CPU does when it comes up.
+ * Here we setup the CPU to enable Inter-Processor-Interrupts
+ * Called for each CPU
+ * -Master      : init_IRQ()
+ * -Other(s)    : start_kernel_secondary()
+ */
+void mcip_init_smp(unsigned int cpu)
+{
+	smp_ipi_irq_setup(cpu, IPI_IRQ);
+}
+
+static void mcip_ipi_send(int cpu)
+{
+	unsigned long flags;
+	int ipi_was_pending;
+
+	/*
+	 * NOTE: We must spin here if the other cpu hasn't yet
+	 * serviced a previous message. This can burn lots
+	 * of time, but we MUST follows this protocol or
+	 * ipi messages can be lost!!!
+	 * Also, we must release the lock in this loop because
+	 * the other side may get to this same loop and not
+	 * be able to ack -- thus causing deadlock.
+	 */
+
+	do {
+		raw_spin_lock_irqsave(&mcip_lock, flags);
+		__mcip_cmd(CMD_INTRPT_READ_STATUS, cpu);
+		ipi_was_pending = read_aux_reg(ARC_REG_MCIP_READBACK);
+		if (ipi_was_pending == 0)
+			break; /* break out but keep lock */
+		raw_spin_unlock_irqrestore(&mcip_lock, flags);
+	} while (1);
+
+	__mcip_cmd(CMD_INTRPT_GENERATE_IRQ, cpu);
+	raw_spin_unlock_irqrestore(&mcip_lock, flags);
+
+#ifdef CONFIG_ARC_IPI_DBG
+	if (ipi_was_pending)
+		pr_info("IPI ACK delayed from cpu %d\n", cpu);
+#endif
+}
+
+static void mcip_ipi_clear(int irq)
+{
+	unsigned int cpu, c;
+	unsigned long flags;
+	unsigned int __maybe_unused copy;
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+
+	/* Who sent the IPI */
+	__mcip_cmd(CMD_INTRPT_CHECK_SOURCE, 0);
+
+	copy = cpu = read_aux_reg(ARC_REG_MCIP_READBACK);	/* 1,2,4,8... */
+
+	/*
+	 * In rare case, multiple concurrent IPIs sent to same target can
+	 * possibly be coalesced by MCIP into 1 asserted IRQ, so @cpus can be
+	 * "vectored" (multiple bits sets) as opposed to typical single bit
+	 */
+	do {
+		c = __ffs(cpu);			/* 0,1,2,3 */
+		__mcip_cmd(CMD_INTRPT_GENERATE_ACK, c);
+		cpu &= ~(1U << c);
+	} while (cpu);
+
+	raw_spin_unlock_irqrestore(&mcip_lock, flags);
+
+#ifdef CONFIG_ARC_IPI_DBG
+	if (c != __ffs(copy))
+		pr_info("IPIs from %x coalesced to %x\n",
+			copy, raw_smp_processor_id());
+#endif
+}
+
+volatile int wake_flag;
+
+static void mcip_wakeup_cpu(int cpu, unsigned long pc)
+{
+	BUG_ON(cpu == 0);
+	wake_flag = cpu;
+}
+
+void arc_platform_smp_wait_to_boot(int cpu)
+{
+	while (wake_flag != cpu)
+		;
+
+	wake_flag = 0;
+	__asm__ __volatile__("j @first_lines_of_secondary	\n");
+}
+
+struct plat_smp_ops plat_smp_ops = {
+	.info		= smp_cpuinfo_buf,
+	.cpu_kick	= mcip_wakeup_cpu,
+	.ipi_send	= mcip_ipi_send,
+	.ipi_clear	= mcip_ipi_clear,
+};
+
+void mcip_init_early_smp(void)
+{
+#define IS_AVAIL1(var, str)    ((var) ? str : "")
+
+	struct mcip_bcr {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+		unsigned int pad3:8,
+			     idu:1, llm:1, num_cores:6,
+			     iocoh:1,  grtc:1, dbg:1, pad2:1,
+			     msg:1, sem:1, ipi:1, pad:1,
+			     ver:8;
+#else
+		unsigned int ver:8,
+			     pad:1, ipi:1, sem:1, msg:1,
+			     pad2:1, dbg:1, grtc:1, iocoh:1,
+			     num_cores:6, llm:1, idu:1,
+			     pad3:8;
+#endif
+	} mp;
+
+	READ_BCR(ARC_REG_MCIP_BCR, mp);
+
+	sprintf(smp_cpuinfo_buf,
+		"Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s\n",
+		mp.ver, mp.num_cores,
+		IS_AVAIL1(mp.ipi, "IPI "),
+		IS_AVAIL1(mp.idu, "IDU "),
+		IS_AVAIL1(mp.dbg, "DEBUG "),
+		IS_AVAIL1(mp.grtc, "GRTC"));
+
+	idu_detected = mp.idu;
+
+	if (mp.dbg) {
+		__mcip_cmd_data(CMD_DEBUG_SET_SELECT, 0, 0xf);
+		__mcip_cmd_data(CMD_DEBUG_SET_MASK, 0xf, 0xf);
+	}
+
+	if (IS_ENABLED(CONFIG_ARC_HAS_GRTC) && !mp.grtc)
+		panic("kernel trying to use non-existent GRTC\n");
+}
+
+/***************************************************************************
+ * ARCv2 Interrupt Distribution Unit (IDU)
+ *
+ * Connects external "COMMON" IRQs to core intc, providing:
+ *  -dynamic routing (IRQ affinity)
+ *  -load balancing (Round Robin interrupt distribution)
+ *  -1:N distribution
+ *
+ * It physically resides in the MCIP hw block
+ */
+
+#include <linux/irqchip.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include "../../drivers/irqchip/irqchip.h"
+
+/*
+ * Set the DEST for @cmn_irq to @cpu_mask (1 bit per core)
+ */
+static void idu_set_dest(unsigned int cmn_irq, unsigned int cpu_mask)
+{
+	__mcip_cmd_data(CMD_IDU_SET_DEST, cmn_irq, cpu_mask);
+}
+
+static void idu_set_mode(unsigned int cmn_irq, unsigned int lvl,
+			   unsigned int distr)
+{
+	union {
+		unsigned int word;
+		struct {
+			unsigned int distr:2, pad:2, lvl:1, pad2:27;
+		};
+	} data;
+
+	data.distr = distr;
+	data.lvl = lvl;
+	__mcip_cmd_data(CMD_IDU_SET_MODE, cmn_irq, data.word);
+}
+
+static void idu_irq_mask(struct irq_data *data)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+	__mcip_cmd_data(CMD_IDU_SET_MASK, data->hwirq, 1);
+	raw_spin_unlock_irqrestore(&mcip_lock, flags);
+}
+
+static void idu_irq_unmask(struct irq_data *data)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+	__mcip_cmd_data(CMD_IDU_SET_MASK, data->hwirq, 0);
+	raw_spin_unlock_irqrestore(&mcip_lock, flags);
+}
+
+static int
+idu_irq_set_affinity(struct irq_data *d, const struct cpumask *cpumask, bool f)
+{
+	return IRQ_SET_MASK_OK;
+}
+
+static struct irq_chip idu_irq_chip = {
+	.name			= "MCIP IDU Intc",
+	.irq_mask		= idu_irq_mask,
+	.irq_unmask		= idu_irq_unmask,
+#ifdef CONFIG_SMP
+	.irq_set_affinity       = idu_irq_set_affinity,
+#endif
+
+};
+
+static int idu_first_irq;
+
+static void idu_cascade_isr(unsigned int core_irq, struct irq_desc *desc)
+{
+	struct irq_domain *domain = irq_desc_get_handler_data(desc);
+	unsigned int idu_irq;
+
+	idu_irq = core_irq - idu_first_irq;
+	generic_handle_irq(irq_find_mapping(domain, idu_irq));
+}
+
+static int idu_irq_map(struct irq_domain *d, unsigned int virq, irq_hw_number_t hwirq)
+{
+	irq_set_chip_and_handler(virq, &idu_irq_chip, handle_level_irq);
+	irq_set_status_flags(virq, IRQ_MOVE_PCNTXT);
+
+	return 0;
+}
+
+static int idu_irq_xlate(struct irq_domain *d, struct device_node *n,
+			 const u32 *intspec, unsigned int intsize,
+			 irq_hw_number_t *out_hwirq, unsigned int *out_type)
+{
+	irq_hw_number_t hwirq = *out_hwirq = intspec[0];
+	int distri = intspec[1];
+	unsigned long flags;
+
+	*out_type = IRQ_TYPE_NONE;
+
+	/* XXX: validate distribution scheme again online cpu mask */
+	if (distri == 0) {
+		/* 0 - Round Robin to all cpus, otherwise 1 bit per core */
+		raw_spin_lock_irqsave(&mcip_lock, flags);
+		idu_set_dest(hwirq, BIT(num_online_cpus()) - 1);
+		idu_set_mode(hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_RR);
+		raw_spin_unlock_irqrestore(&mcip_lock, flags);
+	} else {
+		/*
+		 * DEST based distribution for Level Triggered intr can only
+		 * have 1 CPU, so generalize it to always contain 1 cpu
+		 */
+		int cpu = ffs(distri);
+
+		if (cpu != fls(distri))
+			pr_warn("IDU irq %lx distri mode set to cpu %x\n",
+				hwirq, cpu);
+
+		raw_spin_lock_irqsave(&mcip_lock, flags);
+		idu_set_dest(hwirq, cpu);
+		idu_set_mode(hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_DEST);
+		raw_spin_unlock_irqrestore(&mcip_lock, flags);
+	}
+
+	return 0;
+}
+
+static const struct irq_domain_ops idu_irq_ops = {
+	.xlate	= idu_irq_xlate,
+	.map	= idu_irq_map,
+};
+
+/*
+ * [16, 23]: Statically assigned always private-per-core (Timers, WDT, IPI)
+ * [24, 23+C]: If C > 0 then "C" common IRQs
+ * [24+C, N]: Not statically assigned, private-per-core
+ */
+
+
+static int __init
+idu_of_init(struct device_node *intc, struct device_node *parent)
+{
+	struct irq_domain *domain;
+	/* Read IDU BCR to confirm nr_irqs */
+	int nr_irqs = of_irq_count(intc);
+	int i, irq;
+
+	if (!idu_detected)
+		panic("IDU not detected, but DeviceTree using it");
+
+	pr_info("MCIP: IDU referenced from Devicetree %d irqs\n", nr_irqs);
+
+	domain = irq_domain_add_linear(intc, nr_irqs, &idu_irq_ops, NULL);
+
+	/* Parent interrupts (core-intc) are already mapped */
+
+	for (i = 0; i < nr_irqs; i++) {
+		/*
+		 * Return parent uplink IRQs (towards core intc) 24,25,.....
+		 * this step has been done before already
+		 * however we need it to get the parent virq and set IDU handler
+		 * as first level isr
+		 */
+		irq = irq_of_parse_and_map(intc, i);
+		if (!i)
+			idu_first_irq = irq;
+
+		irq_set_handler_data(irq, domain);
+		irq_set_chained_handler(irq, idu_cascade_isr);
+	}
+
+	__mcip_cmd(CMD_IDU_ENABLE, 0);
+
+	return 0;
+}
+IRQCHIP_DECLARE(arcv2_idu_intc, "snps,archs-idu-intc", idu_of_init);
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index fd2ec50..1287388 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -266,10 +266,9 @@
 
 static int arc_pmu_device_probe(struct platform_device *pdev)
 {
-	struct arc_pmu *arc_pmu;
 	struct arc_reg_pct_build pct_bcr;
 	struct arc_reg_cc_build cc_bcr;
-	int i, j, ret;
+	int i, j;
 
 	union cc_name {
 		struct {
@@ -336,9 +335,7 @@
 	/* ARC 700 PMU does not support sampling events */
 	arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
 
-	ret = perf_pmu_register(&arc_pmu->pmu, pdev->name, PERF_TYPE_RAW);
-
-	return ret;
+	return perf_pmu_register(&arc_pmu->pmu, pdev->name, PERF_TYPE_RAW);
 }
 
 #ifdef CONFIG_OF
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index e095c55..4409245 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -44,7 +44,11 @@
 void arch_cpu_idle(void)
 {
 	/* sleep, but enable all interrupts before committing */
-	__asm__("sleep 0x3");
+	if (is_isa_arcompact()) {
+		__asm__("sleep 0x3");
+	} else {
+		__asm__("sleep 0x10");
+	}
 }
 
 asmlinkage void ret_from_fork(void);
@@ -166,8 +170,7 @@
 	 * [L] ZOL loop inhibited to begin with - cleared by a LP insn
 	 * Interrupts enabled
 	 */
-	regs->status32 = STATUS_U_MASK | STATUS_L_MASK |
-			 STATUS_E1_MASK | STATUS_E2_MASK;
+	regs->status32 = STATUS_U_MASK | STATUS_L_MASK | ISA_INIT_STATUS_BITS;
 
 	/* bogus seed values for debugging */
 	regs->lp_start = 0x10;
@@ -197,8 +200,11 @@
 {
 	unsigned int eflags;
 
-	if (x->e_machine != EM_ARCOMPACT)
+	if (x->e_machine != EM_ARC_INUSE) {
+		pr_err("ELF not built for %s ISA\n",
+			is_isa_arcompact() ? "ARCompact":"ARCv2");
 		return 0;
+	}
 
 	eflags = x->e_flags;
 	if ((eflags & EF_ARC_OSABI_MSK) < EF_ARC_OSABI_CURRENT) {
diff --git a/arch/arc/kernel/ptrace.c b/arch/arc/kernel/ptrace.c
index 13b3ffb..4442204 100644
--- a/arch/arc/kernel/ptrace.c
+++ b/arch/arc/kernel/ptrace.c
@@ -47,10 +47,47 @@
 			offsetof(struct user_regs_struct, LOC) + 4);
 
 	REG_O_ZERO(pad);
-	REG_O_CHUNK(scratch, callee, ptregs);
+	REG_O_ONE(scratch.bta, &ptregs->bta);
+	REG_O_ONE(scratch.lp_start, &ptregs->lp_start);
+	REG_O_ONE(scratch.lp_end, &ptregs->lp_end);
+	REG_O_ONE(scratch.lp_count, &ptregs->lp_count);
+	REG_O_ONE(scratch.status32, &ptregs->status32);
+	REG_O_ONE(scratch.ret, &ptregs->ret);
+	REG_O_ONE(scratch.blink, &ptregs->blink);
+	REG_O_ONE(scratch.fp, &ptregs->fp);
+	REG_O_ONE(scratch.gp, &ptregs->r26);
+	REG_O_ONE(scratch.r12, &ptregs->r12);
+	REG_O_ONE(scratch.r11, &ptregs->r11);
+	REG_O_ONE(scratch.r10, &ptregs->r10);
+	REG_O_ONE(scratch.r9, &ptregs->r9);
+	REG_O_ONE(scratch.r8, &ptregs->r8);
+	REG_O_ONE(scratch.r7, &ptregs->r7);
+	REG_O_ONE(scratch.r6, &ptregs->r6);
+	REG_O_ONE(scratch.r5, &ptregs->r5);
+	REG_O_ONE(scratch.r4, &ptregs->r4);
+	REG_O_ONE(scratch.r3, &ptregs->r3);
+	REG_O_ONE(scratch.r2, &ptregs->r2);
+	REG_O_ONE(scratch.r1, &ptregs->r1);
+	REG_O_ONE(scratch.r0, &ptregs->r0);
+	REG_O_ONE(scratch.sp, &ptregs->sp);
+
 	REG_O_ZERO(pad2);
-	REG_O_CHUNK(callee, efa, cregs);
-	REG_O_CHUNK(efa, stop_pc, &target->thread.fault_address);
+
+	REG_O_ONE(callee.r25, &cregs->r25);
+	REG_O_ONE(callee.r24, &cregs->r24);
+	REG_O_ONE(callee.r23, &cregs->r23);
+	REG_O_ONE(callee.r22, &cregs->r22);
+	REG_O_ONE(callee.r21, &cregs->r21);
+	REG_O_ONE(callee.r20, &cregs->r20);
+	REG_O_ONE(callee.r19, &cregs->r19);
+	REG_O_ONE(callee.r18, &cregs->r18);
+	REG_O_ONE(callee.r17, &cregs->r17);
+	REG_O_ONE(callee.r16, &cregs->r16);
+	REG_O_ONE(callee.r15, &cregs->r15);
+	REG_O_ONE(callee.r14, &cregs->r14);
+	REG_O_ONE(callee.r13, &cregs->r13);
+
+	REG_O_ONE(efa, &target->thread.fault_address);
 
 	if (!ret) {
 		if (in_brkpt_trap(ptregs)) {
@@ -97,12 +134,51 @@
 			offsetof(struct user_regs_struct, LOC) + 4);
 
 	REG_IGNORE_ONE(pad);
-	/* TBD: disallow updates to STATUS32 etc*/
-	REG_IN_CHUNK(scratch, pad2, ptregs);	/* pt_regs[bta..sp] */
+
+	REG_IN_ONE(scratch.bta, &ptregs->bta);
+	REG_IN_ONE(scratch.lp_start, &ptregs->lp_start);
+	REG_IN_ONE(scratch.lp_end, &ptregs->lp_end);
+	REG_IN_ONE(scratch.lp_count, &ptregs->lp_count);
+
+	REG_IGNORE_ONE(scratch.status32);
+
+	REG_IN_ONE(scratch.ret, &ptregs->ret);
+	REG_IN_ONE(scratch.blink, &ptregs->blink);
+	REG_IN_ONE(scratch.fp, &ptregs->fp);
+	REG_IN_ONE(scratch.gp, &ptregs->r26);
+	REG_IN_ONE(scratch.r12, &ptregs->r12);
+	REG_IN_ONE(scratch.r11, &ptregs->r11);
+	REG_IN_ONE(scratch.r10, &ptregs->r10);
+	REG_IN_ONE(scratch.r9, &ptregs->r9);
+	REG_IN_ONE(scratch.r8, &ptregs->r8);
+	REG_IN_ONE(scratch.r7, &ptregs->r7);
+	REG_IN_ONE(scratch.r6, &ptregs->r6);
+	REG_IN_ONE(scratch.r5, &ptregs->r5);
+	REG_IN_ONE(scratch.r4, &ptregs->r4);
+	REG_IN_ONE(scratch.r3, &ptregs->r3);
+	REG_IN_ONE(scratch.r2, &ptregs->r2);
+	REG_IN_ONE(scratch.r1, &ptregs->r1);
+	REG_IN_ONE(scratch.r0, &ptregs->r0);
+	REG_IN_ONE(scratch.sp, &ptregs->sp);
+
 	REG_IGNORE_ONE(pad2);
-	REG_IN_CHUNK(callee, efa, cregs);	/* callee_regs[r25..r13] */
+
+	REG_IN_ONE(callee.r25, &cregs->r25);
+	REG_IN_ONE(callee.r24, &cregs->r24);
+	REG_IN_ONE(callee.r23, &cregs->r23);
+	REG_IN_ONE(callee.r22, &cregs->r22);
+	REG_IN_ONE(callee.r21, &cregs->r21);
+	REG_IN_ONE(callee.r20, &cregs->r20);
+	REG_IN_ONE(callee.r19, &cregs->r19);
+	REG_IN_ONE(callee.r18, &cregs->r18);
+	REG_IN_ONE(callee.r17, &cregs->r17);
+	REG_IN_ONE(callee.r16, &cregs->r16);
+	REG_IN_ONE(callee.r15, &cregs->r15);
+	REG_IN_ONE(callee.r14, &cregs->r14);
+	REG_IN_ONE(callee.r13, &cregs->r13);
+
 	REG_IGNORE_ONE(efa);			/* efa update invalid */
-	REG_IGNORE_ONE(stop_pc);			/* PC updated via @ret */
+	REG_IGNORE_ONE(stop_pc);		/* PC updated via @ret */
 
 	return ret;
 }
@@ -124,7 +200,7 @@
 
 static const struct user_regset_view user_arc_view = {
 	.name		= UTS_MACHINE,
-	.e_machine	= EM_ARCOMPACT,
+	.e_machine	= EM_ARC_INUSE,
 	.regsets	= arc_regsets,
 	.n		= ARRAY_SIZE(arc_regsets)
 };
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 1d167c6..a3d1862 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -30,6 +30,8 @@
 
 #define FIX_PTR(x)  __asm__ __volatile__(";" : "+r"(x))
 
+unsigned int intr_to_DE_cnt;
+
 /* Part of U-boot ABI: see head.S */
 int __initdata uboot_tag;
 char __initdata *uboot_arg;
@@ -54,7 +56,7 @@
 	cpu->vec_base = read_aux_reg(AUX_INTR_VEC_BASE);
 
 	READ_BCR(ARC_REG_D_UNCACH_BCR, uncached_space);
-	cpu->uncached_base = uncached_space.start << 24;
+	BUG_ON((uncached_space.start << 24) != ARC_UNCACHED_ADDR_SPACE);
 
 	READ_BCR(ARC_REG_MUL_BCR, cpu->extn_mpy);
 
@@ -96,7 +98,7 @@
 	read_decode_mmu_bcr();
 	read_decode_cache_bcr();
 
-	{
+	if (is_isa_arcompact()) {
 		struct bcr_fp_arcompact sp, dp;
 		struct bcr_bpu_arcompact bpu;
 
@@ -112,6 +114,19 @@
 			cpu->bpu.num_cache = 256 << (bpu.ent - 1);
 			cpu->bpu.num_pred = 256 << (bpu.ent - 1);
 		}
+	} else {
+		struct bcr_fp_arcv2 spdp;
+		struct bcr_bpu_arcv2 bpu;
+
+		READ_BCR(ARC_REG_FP_V2_BCR, spdp);
+		cpu->extn.fpu_sp = spdp.sp ? 1 : 0;
+		cpu->extn.fpu_dp = spdp.dp ? 1 : 0;
+
+		READ_BCR(ARC_REG_BPU_BCR, bpu);
+		cpu->bpu.ver = bpu.ver;
+		cpu->bpu.full = bpu.ft;
+		cpu->bpu.num_cache = 256 << bpu.bce;
+		cpu->bpu.num_pred = 2048 << bpu.pte;
 	}
 
 	READ_BCR(ARC_REG_AP_BCR, bcr);
@@ -131,6 +146,7 @@
 	{ {0x30, "ARC 700"      }, 0x33},
 	{ {0x34, "ARC 700 R4.10"}, 0x34},
 	{ {0x35, "ARC 700 R4.11"}, 0x35},
+	{ {0x50, "ARC HS38"	}, 0x51},
 	{ {0x00, NULL		} }
 };
 
@@ -149,13 +165,17 @@
 
 	FIX_PTR(cpu);
 
-	{
+	if (is_isa_arcompact()) {
 		isa_nm = "ARCompact";
 		be = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN);
 
 		atomic = cpu->isa.atomic1;
 		if (!cpu->isa.ver)	/* ISA BCR absent, use Kconfig info */
 			atomic = IS_ENABLED(CONFIG_ARC_HAS_LLSC);
+	} else {
+		isa_nm = "ARCv2";
+		be = cpu->isa.be;
+		atomic = cpu->isa.atomic;
 	}
 
 	n += scnprintf(buf + n, len - n,
@@ -183,16 +203,34 @@
 	n += scnprintf(buf + n, len - n, "Timers\t\t: %s%s%s%s\nISA Extn\t: ",
 		       IS_AVAIL1(cpu->timers.t0, "Timer0 "),
 		       IS_AVAIL1(cpu->timers.t1, "Timer1 "),
-		       IS_AVAIL2(cpu->timers.rtsc, "64-bit RTSC ", CONFIG_ARC_HAS_RTSC));
+		       IS_AVAIL2(cpu->timers.rtc, "64-bit RTC ",
+				 CONFIG_ARC_HAS_RTC));
 
-	n += i = scnprintf(buf + n, len - n, "%s%s",
-			   IS_AVAIL2(atomic, "atomic ", CONFIG_ARC_HAS_LLSC));
+	n += i = scnprintf(buf + n, len - n, "%s%s%s%s%s",
+			   IS_AVAIL2(atomic, "atomic ", CONFIG_ARC_HAS_LLSC),
+			   IS_AVAIL2(cpu->isa.ldd, "ll64 ", CONFIG_ARC_HAS_LL64),
+			   IS_AVAIL1(cpu->isa.unalign, "unalign (not used)"));
 
 	if (i)
 		n += scnprintf(buf + n, len - n, "\n\t\t: ");
 
+	if (cpu->extn_mpy.ver) {
+		if (cpu->extn_mpy.ver <= 0x2) {	/* ARCompact */
+			n += scnprintf(buf + n, len - n, "mpy ");
+		} else {
+			int opt = 2;	/* stock MPY/MPYH */
+
+			if (cpu->extn_mpy.dsp)	/* OPT 7-9 */
+				opt = cpu->extn_mpy.dsp + 6;
+
+			n += scnprintf(buf + n, len - n, "mpy[opt %d] ", opt);
+		}
+		n += scnprintf(buf + n, len - n, "%s",
+			       IS_USED(CONFIG_ARC_HAS_HW_MPY));
+	}
+
 	n += scnprintf(buf + n, len - n, "%s%s%s%s%s%s%s%s\n",
-		       IS_AVAIL1(cpu->extn_mpy.ver, "mpy "),
+		       IS_AVAIL1(cpu->isa.div_rem, "div_rem "),
 		       IS_AVAIL1(cpu->extn.norm, "norm "),
 		       IS_AVAIL1(cpu->extn.barrel, "barrel-shift "),
 		       IS_AVAIL1(cpu->extn.swap, "swap "),
@@ -219,7 +257,7 @@
 
 	n += scnprintf(buf + n, len - n,
 		       "Vector Table\t: %#x\nUncached Base\t: %#x\n",
-		       cpu->vec_base, cpu->uncached_base);
+		       cpu->vec_base, ARC_UNCACHED_ADDR_SPACE);
 
 	if (cpu->extn.fpu_sp || cpu->extn.fpu_dp)
 		n += scnprintf(buf + n, len - n, "FPU\t\t: %s%s\n",
@@ -254,8 +292,8 @@
 	if (!cpu->timers.t1)
 		panic("Timer1 is not present!\n");
 
-	if (IS_ENABLED(CONFIG_ARC_HAS_RTSC) && !cpu->timers.rtsc)
-		panic("RTSC is not present\n");
+	if (IS_ENABLED(CONFIG_ARC_HAS_RTC) && !cpu->timers.rtc)
+		panic("RTC is not present\n");
 
 #ifdef CONFIG_ARC_HAS_DCCM
 	/*
@@ -323,13 +361,16 @@
 
 void __init setup_arch(char **cmdline_p)
 {
+#ifdef CONFIG_ARC_UBOOT_SUPPORT
 	/* make sure that uboot passed pointer to cmdline/dtb is valid */
 	if (uboot_tag && is_kernel((unsigned long)uboot_arg))
 		panic("Invalid uboot arg\n");
 
 	/* See if u-boot passed an external Device Tree blob */
 	machine_desc = setup_machine_fdt(uboot_arg);	/* uboot_tag == 2 */
-	if (!machine_desc) {
+	if (!machine_desc)
+#endif
+	{
 		/* No, so try the embedded one */
 		machine_desc = setup_machine_fdt(__dtb_start);
 		if (!machine_desc)
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index 2251fb4..004b7f0 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -67,7 +67,33 @@
 	       sigset_t *set)
 {
 	int err;
-	err = __copy_to_user(&(sf->uc.uc_mcontext.regs.scratch), regs,
+	struct user_regs_struct uregs;
+
+	uregs.scratch.bta	= regs->bta;
+	uregs.scratch.lp_start	= regs->lp_start;
+	uregs.scratch.lp_end	= regs->lp_end;
+	uregs.scratch.lp_count	= regs->lp_count;
+	uregs.scratch.status32	= regs->status32;
+	uregs.scratch.ret	= regs->ret;
+	uregs.scratch.blink	= regs->blink;
+	uregs.scratch.fp	= regs->fp;
+	uregs.scratch.gp	= regs->r26;
+	uregs.scratch.r12	= regs->r12;
+	uregs.scratch.r11	= regs->r11;
+	uregs.scratch.r10	= regs->r10;
+	uregs.scratch.r9	= regs->r9;
+	uregs.scratch.r8	= regs->r8;
+	uregs.scratch.r7	= regs->r7;
+	uregs.scratch.r6	= regs->r6;
+	uregs.scratch.r5	= regs->r5;
+	uregs.scratch.r4	= regs->r4;
+	uregs.scratch.r3	= regs->r3;
+	uregs.scratch.r2	= regs->r2;
+	uregs.scratch.r1	= regs->r1;
+	uregs.scratch.r0	= regs->r0;
+	uregs.scratch.sp	= regs->sp;
+
+	err = __copy_to_user(&(sf->uc.uc_mcontext.regs.scratch), &uregs.scratch,
 			     sizeof(sf->uc.uc_mcontext.regs.scratch));
 	err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t));
 
@@ -78,14 +104,40 @@
 {
 	sigset_t set;
 	int err;
+	struct user_regs_struct uregs;
 
 	err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set));
 	if (!err)
 		set_current_blocked(&set);
 
-	err |= __copy_from_user(regs, &(sf->uc.uc_mcontext.regs.scratch),
+	err |= __copy_from_user(&uregs.scratch,
+				&(sf->uc.uc_mcontext.regs.scratch),
 				sizeof(sf->uc.uc_mcontext.regs.scratch));
 
+	regs->bta	= uregs.scratch.bta;
+	regs->lp_start	= uregs.scratch.lp_start;
+	regs->lp_end	= uregs.scratch.lp_end;
+	regs->lp_count	= uregs.scratch.lp_count;
+	regs->status32	= uregs.scratch.status32;
+	regs->ret	= uregs.scratch.ret;
+	regs->blink	= uregs.scratch.blink;
+	regs->fp	= uregs.scratch.fp;
+	regs->r26	= uregs.scratch.gp;
+	regs->r12	= uregs.scratch.r12;
+	regs->r11	= uregs.scratch.r11;
+	regs->r10	= uregs.scratch.r10;
+	regs->r9	= uregs.scratch.r9;
+	regs->r8	= uregs.scratch.r8;
+	regs->r7	= uregs.scratch.r7;
+	regs->r6	= uregs.scratch.r6;
+	regs->r5	= uregs.scratch.r5;
+	regs->r4	= uregs.scratch.r4;
+	regs->r3	= uregs.scratch.r3;
+	regs->r2	= uregs.scratch.r2;
+	regs->r1	= uregs.scratch.r1;
+	regs->r0	= uregs.scratch.r0;
+	regs->sp	= uregs.scratch.sp;
+
 	return err;
 }
 
@@ -284,7 +336,7 @@
 		 * their orig user space value when we ret from kernel
 		 */
 		regs->r0 = regs->orig_r0;
-		regs->ret -= 4;
+		regs->ret -= is_isa_arcv2() ? 2 : 4;
 		break;
 	}
 }
@@ -325,10 +377,10 @@
 		if (regs->r0 == -ERESTARTNOHAND ||
 		    regs->r0 == -ERESTARTSYS || regs->r0 == -ERESTARTNOINTR) {
 			regs->r0 = regs->orig_r0;
-			regs->ret -= 4;
+			regs->ret -= is_isa_arcv2() ? 2 : 4;
 		} else if (regs->r0 == -ERESTART_RESTARTBLOCK) {
 			regs->r8 = __NR_restart_syscall;
-			regs->ret -= 4;
+			regs->ret -= is_isa_arcv2() ? 2 : 4;
 		}
 		syscall_wont_restart(regs);	/* No more restarts */
 	}
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index 6a400b1..be13d12 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -31,7 +31,7 @@
 arch_spinlock_t smp_bitops_lock = __ARCH_SPIN_LOCK_UNLOCKED;
 #endif
 
-struct plat_smp_ops  plat_smp_ops;
+struct plat_smp_ops  __weak plat_smp_ops;
 
 /* XXX: per cpu ? Only needed once in early seconday boot */
 struct task_struct *secondary_idle_tsk;
@@ -182,7 +182,7 @@
 /*
  * not supported here
  */
-int __init setup_profiling_timer(unsigned int multiplier)
+int setup_profiling_timer(unsigned int multiplier)
 {
 	return -EINVAL;
 }
@@ -278,8 +278,10 @@
 	machine_halt();
 }
 
-static inline void __do_IPI(unsigned long msg)
+static inline int __do_IPI(unsigned long msg)
 {
+	int rc = 0;
+
 	switch (msg) {
 	case IPI_RESCHEDULE:
 		scheduler_ipi();
@@ -294,8 +296,10 @@
 		break;
 
 	default:
-		pr_warn("IPI with unexpected msg %ld\n", msg);
+		rc = 1;
 	}
+
+	return rc;
 }
 
 /*
@@ -305,6 +309,7 @@
 irqreturn_t do_IPI(int irq, void *dev_id)
 {
 	unsigned long pending;
+	unsigned long __maybe_unused copy;
 
 	pr_debug("IPI [%ld] received on cpu %d\n",
 		 *this_cpu_ptr(&ipi_data), smp_processor_id());
@@ -316,11 +321,18 @@
 	 * "dequeue" the msg corresponding to this IPI (and possibly other
 	 * piggybacked msg from elided IPIs: see ipi_send_msg_one() above)
 	 */
-	pending = xchg(this_cpu_ptr(&ipi_data), 0);
+	copy = pending = xchg(this_cpu_ptr(&ipi_data), 0);
 
 	do {
 		unsigned long msg = __ffs(pending);
-		__do_IPI(msg);
+		int rc;
+
+		rc = __do_IPI(msg);
+#ifdef CONFIG_ARC_IPI_DBG
+		/* IPI received but no valid @msg */
+		if (rc)
+			pr_info("IPI with bogus msg %ld in %ld\n", msg, copy);
+#endif
 		pending &= ~(1U << msg);
 	} while (pending);
 
diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c
index 92320d6..001de4c 100644
--- a/arch/arc/kernel/stacktrace.c
+++ b/arch/arc/kernel/stacktrace.c
@@ -122,19 +122,17 @@
 	while (1) {
 		address = UNW_PC(&frame_info);
 
-		if (address && __kernel_text_address(address)) {
-			if (consumer_fn(address, arg) == -1)
-				break;
-		}
+		if (!address || !__kernel_text_address(address))
+			break;
+
+		if (consumer_fn(address, arg) == -1)
+			break;
 
 		ret = arc_unwind(&frame_info);
-
-		if (ret == 0) {
-			frame_info.regs.r63 = frame_info.regs.r31;
-			continue;
-		} else {
+		if (ret)
 			break;
-		}
+
+		frame_info.regs.r63 = frame_info.regs.r31;
 	}
 
 	return address;		/* return the last address it saw */
diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c
index dbe74f4..3364d2b 100644
--- a/arch/arc/kernel/time.c
+++ b/arch/arc/kernel/time.c
@@ -26,6 +26,7 @@
  * while TIMER1 for free running (clocksource)
  *
  * Newer ARC700 cores have 64bit clk fetching RTSC insn, preferred over TIMER1
+ * which however is currently broken
  */
 
 #include <linux/spinlock.h>
@@ -44,6 +45,8 @@
 #include <asm/clk.h>
 #include <asm/mach_desc.h>
 
+#include <asm/mcip.h>
+
 /* Timer related Aux registers */
 #define ARC_REG_TIMER0_LIMIT	0x23	/* timer 0 limit */
 #define ARC_REG_TIMER0_CTRL	0x22	/* timer 0 control */
@@ -59,14 +62,10 @@
 
 /********** Clock Source Device *********/
 
-#ifdef CONFIG_ARC_HAS_RTSC
+#ifdef CONFIG_ARC_HAS_GRTC
 
-int arc_counter_setup(void)
+static int arc_counter_setup(void)
 {
-	/*
-	 * For SMP this needs to be 0. However Kconfig glue doesn't
-	 * enable this option for SMP configs
-	 */
 	return 1;
 }
 
@@ -75,6 +74,55 @@
 	unsigned long flags;
 	union {
 #ifdef CONFIG_CPU_BIG_ENDIAN
+		struct { u32 h, l; };
+#else
+		struct { u32 l, h; };
+#endif
+		cycle_t  full;
+	} stamp;
+
+	local_irq_save(flags);
+
+	__mcip_cmd(CMD_GRTC_READ_LO, 0);
+	stamp.l = read_aux_reg(ARC_REG_MCIP_READBACK);
+
+	__mcip_cmd(CMD_GRTC_READ_HI, 0);
+	stamp.h = read_aux_reg(ARC_REG_MCIP_READBACK);
+
+	local_irq_restore(flags);
+
+	return stamp.full;
+}
+
+static struct clocksource arc_counter = {
+	.name   = "ARConnect GRTC",
+	.rating = 400,
+	.read   = arc_counter_read,
+	.mask   = CLOCKSOURCE_MASK(64),
+	.flags  = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+#else
+
+#ifdef CONFIG_ARC_HAS_RTC
+
+#define AUX_RTC_CTRL	0x103
+#define AUX_RTC_LOW	0x104
+#define AUX_RTC_HIGH	0x105
+
+int arc_counter_setup(void)
+{
+	write_aux_reg(AUX_RTC_CTRL, 1);
+
+	/* Not usable in SMP */
+	return !IS_ENABLED(CONFIG_SMP);
+}
+
+static cycle_t arc_counter_read(struct clocksource *cs)
+{
+	unsigned long status;
+	union {
+#ifdef CONFIG_CPU_BIG_ENDIAN
 		struct { u32 high, low; };
 #else
 		struct { u32 low, high; };
@@ -82,37 +130,27 @@
 		cycle_t  full;
 	} stamp;
 
-	flags = arch_local_irq_save();
 
 	__asm__ __volatile(
-	"	.extCoreRegister tsch, 58,  r, cannot_shortcut	\n"
-	"	rtsc %0, 0	\n"
-	"	mov  %1, 0	\n"
-	: "=r" (stamp.low), "=r" (stamp.high));
-
-	arch_local_irq_restore(flags);
+	"1:						\n"
+	"	lr		%0, [AUX_RTC_LOW]	\n"
+	"	lr		%1, [AUX_RTC_HIGH]	\n"
+	"	lr		%2, [AUX_RTC_CTRL]	\n"
+	"	bbit0.nt	%2, 31, 1b		\n"
+	: "=r" (stamp.low), "=r" (stamp.high), "=r" (status));
 
 	return stamp.full;
 }
 
 static struct clocksource arc_counter = {
-	.name   = "ARC RTSC",
-	.rating = 300,
+	.name   = "ARCv2 RTC",
+	.rating = 350,
 	.read   = arc_counter_read,
-	.mask   = CLOCKSOURCE_MASK(32),
+	.mask   = CLOCKSOURCE_MASK(64),
 	.flags  = CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-#else /* !CONFIG_ARC_HAS_RTSC */
-
-static bool is_usable_as_clocksource(void)
-{
-#ifdef CONFIG_SMP
-	return 0;
-#else
-	return 1;
-#endif
-}
+#else /* !CONFIG_ARC_HAS_RTC */
 
 /*
  * set 32bit TIMER1 to keep counting monotonically and wraparound
@@ -123,7 +161,8 @@
 	write_aux_reg(ARC_REG_TIMER1_CNT, 0);
 	write_aux_reg(ARC_REG_TIMER1_CTRL, TIMER_CTRL_NH);
 
-	return is_usable_as_clocksource();
+	/* Not usable in SMP */
+	return !IS_ENABLED(CONFIG_SMP);
 }
 
 static cycle_t arc_counter_read(struct clocksource *cs)
@@ -140,6 +179,7 @@
 };
 
 #endif
+#endif
 
 /********** Clock Event Device *********/
 
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index e00a018..807f7d6 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -14,6 +14,7 @@
 #include <linux/proc_fs.h>
 #include <linux/file.h>
 #include <asm/arcregs.h>
+#include <asm/irqflags.h>
 
 /*
  * Common routine to print scratch regs (r0-r12) or callee regs (r13-r25)
@@ -34,7 +35,10 @@
 			n += scnprintf(buf + n, len - n, "\n");
 
 		/* because pt_regs has regs reversed: r12..r0, r25..r13 */
-		reg_rev--;
+		if (is_isa_arcv2() && start_num == 0)
+			reg_rev++;
+		else
+			reg_rev--;
 	}
 
 	if (start_num != 0)
@@ -67,15 +71,12 @@
 	mmput(mm);
 
 	if (exe_file) {
-		path = exe_file->f_path;
-		path_get(&exe_file->f_path);
+		path_nm = file_path(exe_file, buf, 255);
 		fput(exe_file);
-		path_nm = d_path(&path, buf, 255);
-		path_put(&path);
 	}
 
 done:
-	pr_info("Path: %s\n", path_nm);
+	pr_info("Path: %s\n", !IS_ERR(path_nm) ? path_nm : "?");
 }
 
 static void show_faulting_vma(unsigned long address, char *buf)
@@ -99,8 +100,7 @@
 	if (vma && (vma->vm_start <= address)) {
 		struct file *file = vma->vm_file;
 		if (file) {
-			struct path *path = &file->f_path;
-			nm = d_path(path, buf, PAGE_SIZE - 1);
+			nm = file_path(file, buf, PAGE_SIZE - 1);
 			inode = file_inode(vma->vm_file);
 			dev = inode->i_sb->s_dev;
 			ino = inode->i_ino;
@@ -152,6 +152,15 @@
 				((cause_code == 0x02) ? "Write" : "EX"));
 	} else if (vec == ECR_V_INSN_ERR) {
 		pr_cont("Illegal Insn\n");
+#ifdef CONFIG_ISA_ARCV2
+	} else if (vec == ECR_V_MEM_ERR) {
+		if (cause_code == 0x00)
+			pr_cont("Bus Error from Insn Mem\n");
+		else if (cause_code == 0x10)
+			pr_cont("Bus Error from Data Mem\n");
+		else
+			pr_cont("Bus Error, check PRM\n");
+#endif
 	} else {
 		pr_cont("Check Programmer's Manual\n");
 	}
@@ -185,12 +194,20 @@
 
 	pr_info("[STAT32]: 0x%08lx", regs->status32);
 
-#define STS_BIT(r, bit)	r->status32 & STATUS_##bit##_MASK ? #bit : ""
-	if (!user_mode(regs))
-		pr_cont(" : %2s %2s %2s %2s %2s\n",
-			STS_BIT(regs, AE), STS_BIT(regs, A2), STS_BIT(regs, A1),
-			STS_BIT(regs, E2), STS_BIT(regs, E1));
+#define STS_BIT(r, bit)	r->status32 & STATUS_##bit##_MASK ? #bit" " : ""
 
+#ifdef CONFIG_ISA_ARCOMPACT
+	pr_cont(" : %2s%2s%2s%2s%2s%2s%2s\n",
+			(regs->status32 & STATUS_U_MASK) ? "U " : "K ",
+			STS_BIT(regs, DE), STS_BIT(regs, AE),
+			STS_BIT(regs, A2), STS_BIT(regs, A1),
+			STS_BIT(regs, E2), STS_BIT(regs, E1));
+#else
+	pr_cont(" : %2s%2s%2s%2s\n",
+			STS_BIT(regs, IE),
+			(regs->status32 & STATUS_U_MASK) ? "U " : "K ",
+			STS_BIT(regs, DE), STS_BIT(regs, AE));
+#endif
 	pr_info("BTA: 0x%08lx\t SP: 0x%08lx\t FP: 0x%08lx\n",
 		regs->bta, regs->sp, regs->fp);
 	pr_info("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n",
diff --git a/arch/arc/lib/Makefile b/arch/arc/lib/Makefile
index db46e20..b1656d1 100644
--- a/arch/arc/lib/Makefile
+++ b/arch/arc/lib/Makefile
@@ -5,5 +5,7 @@
 # it under the terms of the GNU General Public License version 2 as
 # published by the Free Software Foundation.
 
-lib-y	:= strchr-700.o strcmp.o strcpy-700.o strlen.o
-lib-y	+= memcmp.o memcpy-700.o memset.o
+lib-y	:= strchr-700.o strcpy-700.o strlen.o memcmp.o
+
+lib-$(CONFIG_ISA_ARCOMPACT)	+= memcpy-700.o memset.o strcmp.o
+lib-$(CONFIG_ISA_ARCV2)		+= memcpy-archs.o memset-archs.o strcmp-archs.o
diff --git a/arch/arc/lib/memcmp.S b/arch/arc/lib/memcmp.S
index 978bf83..a4015e7 100644
--- a/arch/arc/lib/memcmp.S
+++ b/arch/arc/lib/memcmp.S
@@ -24,14 +24,32 @@
 	ld	r4,[r0,0]
 	ld	r5,[r1,0]
 	lsr.f	lp_count,r3,3
+#ifdef CONFIG_ISA_ARCV2
+	/* In ARCv2 a branch can't be the last instruction in a zero overhead
+	 * loop.
+	 * So we move the branch to the start of the loop, duplicate it
+	 * after the end, and set up r12 so that the branch isn't taken
+	 *  initially.
+	 */
+	mov_s	r12,WORD2
+	lpne	.Loop_end
+	brne	WORD2,r12,.Lodd
+	ld	WORD2,[r0,4]
+#else
 	lpne	.Loop_end
 	ld_s	WORD2,[r0,4]
+#endif
 	ld_s	r12,[r1,4]
 	brne	r4,r5,.Leven
 	ld.a	r4,[r0,8]
 	ld.a	r5,[r1,8]
+#ifdef CONFIG_ISA_ARCV2
+.Loop_end:
+	brne	WORD2,r12,.Lodd
+#else
 	brne	WORD2,r12,.Lodd
 .Loop_end:
+#endif
 	asl_s	SHIFT,SHIFT,3
 	bhs_s	.Last_cmp
 	brne	r4,r5,.Leven
@@ -89,7 +107,6 @@
 	bset.cs	r0,r0,31
 .Lodd:
 	cmp_s	WORD2,r12
-
 	mov_s	r0,1
 	j_s.d	[blink]
 	bset.cs	r0,r0,31
@@ -100,14 +117,25 @@
 	ldb	r4,[r0,0]
 	ldb	r5,[r1,0]
 	lsr.f	lp_count,r3
+#ifdef CONFIG_ISA_ARCV2
+	mov	r12,r3
 	lpne	.Lbyte_end
+	brne	r3,r12,.Lbyte_odd
+#else
+	lpne	.Lbyte_end
+#endif
 	ldb_s	r3,[r0,1]
 	ldb	r12,[r1,1]
 	brne	r4,r5,.Lbyte_even
 	ldb.a	r4,[r0,2]
 	ldb.a	r5,[r1,2]
+#ifdef CONFIG_ISA_ARCV2
+.Lbyte_end:
+	brne	r3,r12,.Lbyte_odd
+#else
 	brne	r3,r12,.Lbyte_odd
 .Lbyte_end:
+#endif
 	bcc	.Lbyte_even
 	brne	r4,r5,.Lbyte_even
 	ldb_s	r3,[r0,1]
diff --git a/arch/arc/lib/memcpy-archs.S b/arch/arc/lib/memcpy-archs.S
new file mode 100644
index 0000000..1b2b3ac
--- /dev/null
+++ b/arch/arc/lib/memcpy-archs.S
@@ -0,0 +1,236 @@
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+
+#ifdef __LITTLE_ENDIAN__
+# define SHIFT_1(RX,RY,IMM)	asl	RX, RY, IMM	; <<
+# define SHIFT_2(RX,RY,IMM)	lsr	RX, RY, IMM	; >>
+# define MERGE_1(RX,RY,IMM)	asl	RX, RY, IMM
+# define MERGE_2(RX,RY,IMM)
+# define EXTRACT_1(RX,RY,IMM)	and	RX, RY, 0xFFFF
+# define EXTRACT_2(RX,RY,IMM)	lsr	RX, RY, IMM
+#else
+# define SHIFT_1(RX,RY,IMM)	lsr	RX, RY, IMM	; >>
+# define SHIFT_2(RX,RY,IMM)	asl	RX, RY, IMM	; <<
+# define MERGE_1(RX,RY,IMM)	asl	RX, RY, IMM	; <<
+# define MERGE_2(RX,RY,IMM)	asl	RX, RY, IMM	; <<
+# define EXTRACT_1(RX,RY,IMM)	lsr	RX, RY, IMM
+# define EXTRACT_2(RX,RY,IMM)	lsr	RX, RY, 0x08
+#endif
+
+#ifdef CONFIG_ARC_HAS_LL64
+# define PREFETCH_READ(RX)	prefetch    [RX, 56]
+# define PREFETCH_WRITE(RX)	prefetchw   [RX, 64]
+# define LOADX(DST,RX)		ldd.ab	DST, [RX, 8]
+# define STOREX(SRC,RX)		std.ab	SRC, [RX, 8]
+# define ZOLSHFT		5
+# define ZOLAND			0x1F
+#else
+# define PREFETCH_READ(RX)	prefetch    [RX, 28]
+# define PREFETCH_WRITE(RX)	prefetchw   [RX, 32]
+# define LOADX(DST,RX)		ld.ab	DST, [RX, 4]
+# define STOREX(SRC,RX)		st.ab	SRC, [RX, 4]
+# define ZOLSHFT		4
+# define ZOLAND			0xF
+#endif
+
+ENTRY(memcpy)
+	prefetch [r1]		; Prefetch the read location
+	prefetchw [r0]		; Prefetch the write location
+	mov.f	0, r2
+;;; if size is zero
+	jz.d	[blink]
+	mov	r3, r0		; don;t clobber ret val
+
+;;; if size <= 8
+	cmp	r2, 8
+	bls.d	@smallchunk
+	mov.f	lp_count, r2
+
+	and.f	r4, r0, 0x03
+	rsub	lp_count, r4, 4
+	lpnz	@aligndestination
+	;; LOOP BEGIN
+	ldb.ab	r5, [r1,1]
+	sub	r2, r2, 1
+	stb.ab	r5, [r3,1]
+aligndestination:
+
+;;; Check the alignment of the source
+	and.f	r4, r1, 0x03
+	bnz.d	@sourceunaligned
+
+;;; CASE 0: Both source and destination are 32bit aligned
+;;; Convert len to Dwords, unfold x4
+	lsr.f	lp_count, r2, ZOLSHFT
+	lpnz	@copy32_64bytes
+	;; LOOP START
+	LOADX (r6, r1)
+	PREFETCH_READ (r1)
+	PREFETCH_WRITE (r3)
+	LOADX (r8, r1)
+	LOADX (r10, r1)
+	LOADX (r4, r1)
+	STOREX (r6, r3)
+	STOREX (r8, r3)
+	STOREX (r10, r3)
+	STOREX (r4, r3)
+copy32_64bytes:
+
+	and.f	lp_count, r2, ZOLAND ;Last remaining 31 bytes
+smallchunk:
+	lpnz	@copyremainingbytes
+	;; LOOP START
+	ldb.ab	r5, [r1,1]
+	stb.ab	r5, [r3,1]
+copyremainingbytes:
+
+	j	[blink]
+;;; END CASE 0
+
+sourceunaligned:
+	cmp	r4, 2
+	beq.d	@unalignedOffby2
+	sub	r2, r2, 1
+
+	bhi.d	@unalignedOffby3
+	ldb.ab	r5, [r1, 1]
+
+;;; CASE 1: The source is unaligned, off by 1
+	;; Hence I need to read 1 byte for a 16bit alignment
+	;; and 2bytes to reach 32bit alignment
+	ldh.ab	r6, [r1, 2]
+	sub	r2, r2, 2
+	;; Convert to words, unfold x2
+	lsr.f	lp_count, r2, 3
+	MERGE_1 (r6, r6, 8)
+	MERGE_2 (r5, r5, 24)
+	or	r5, r5, r6
+
+	;; Both src and dst are aligned
+	lpnz	@copy8bytes_1
+	;; LOOP START
+	ld.ab	r6, [r1, 4]
+	prefetch [r1, 28]	;Prefetch the next read location
+	ld.ab	r8, [r1,4]
+	prefetchw [r3, 32]	;Prefetch the next write location
+
+	SHIFT_1	(r7, r6, 24)
+	or	r7, r7, r5
+	SHIFT_2	(r5, r6, 8)
+
+	SHIFT_1	(r9, r8, 24)
+	or	r9, r9, r5
+	SHIFT_2	(r5, r8, 8)
+
+	st.ab	r7, [r3, 4]
+	st.ab	r9, [r3, 4]
+copy8bytes_1:
+
+	;; Write back the remaining 16bits
+	EXTRACT_1 (r6, r5, 16)
+	sth.ab	r6, [r3, 2]
+	;; Write back the remaining 8bits
+	EXTRACT_2 (r5, r5, 16)
+	stb.ab	r5, [r3, 1]
+
+	and.f	lp_count, r2, 0x07 ;Last 8bytes
+	lpnz	@copybytewise_1
+	;; LOOP START
+	ldb.ab	r6, [r1,1]
+	stb.ab	r6, [r3,1]
+copybytewise_1:
+	j	[blink]
+
+unalignedOffby2:
+;;; CASE 2: The source is unaligned, off by 2
+	ldh.ab	r5, [r1, 2]
+	sub	r2, r2, 1
+
+	;; Both src and dst are aligned
+	;; Convert to words, unfold x2
+	lsr.f	lp_count, r2, 3
+#ifdef __BIG_ENDIAN__
+	asl.nz	r5, r5, 16
+#endif
+	lpnz	@copy8bytes_2
+	;; LOOP START
+	ld.ab	r6, [r1, 4]
+	prefetch [r1, 28]	;Prefetch the next read location
+	ld.ab	r8, [r1,4]
+	prefetchw [r3, 32]	;Prefetch the next write location
+
+	SHIFT_1	(r7, r6, 16)
+	or	r7, r7, r5
+	SHIFT_2	(r5, r6, 16)
+
+	SHIFT_1	(r9, r8, 16)
+	or	r9, r9, r5
+	SHIFT_2	(r5, r8, 16)
+
+	st.ab	r7, [r3, 4]
+	st.ab	r9, [r3, 4]
+copy8bytes_2:
+
+#ifdef __BIG_ENDIAN__
+	lsr.nz	r5, r5, 16
+#endif
+	sth.ab	r5, [r3, 2]
+
+	and.f	lp_count, r2, 0x07 ;Last 8bytes
+	lpnz	@copybytewise_2
+	;; LOOP START
+	ldb.ab	r6, [r1,1]
+	stb.ab	r6, [r3,1]
+copybytewise_2:
+	j	[blink]
+
+unalignedOffby3:
+;;; CASE 3: The source is unaligned, off by 3
+;;; Hence, I need to read 1byte for achieve the 32bit alignment
+
+	;; Both src and dst are aligned
+	;; Convert to words, unfold x2
+	lsr.f	lp_count, r2, 3
+#ifdef __BIG_ENDIAN__
+	asl.ne	r5, r5, 24
+#endif
+	lpnz	@copy8bytes_3
+	;; LOOP START
+	ld.ab	r6, [r1, 4]
+	prefetch [r1, 28]	;Prefetch the next read location
+	ld.ab	r8, [r1,4]
+	prefetch [r3, 32]	;Prefetch the next write location
+
+	SHIFT_1	(r7, r6, 8)
+	or	r7, r7, r5
+	SHIFT_2	(r5, r6, 24)
+
+	SHIFT_1	(r9, r8, 8)
+	or	r9, r9, r5
+	SHIFT_2	(r5, r8, 24)
+
+	st.ab	r7, [r3, 4]
+	st.ab	r9, [r3, 4]
+copy8bytes_3:
+
+#ifdef __BIG_ENDIAN__
+	lsr.nz	r5, r5, 24
+#endif
+	stb.ab	r5, [r3, 1]
+
+	and.f	lp_count, r2, 0x07 ;Last 8bytes
+	lpnz	@copybytewise_3
+	;; LOOP START
+	ldb.ab	r6, [r1,1]
+	stb.ab	r6, [r3,1]
+copybytewise_3:
+	j	[blink]
+
+END(memcpy)
diff --git a/arch/arc/lib/memset-archs.S b/arch/arc/lib/memset-archs.S
new file mode 100644
index 0000000..92d573c
--- /dev/null
+++ b/arch/arc/lib/memset-archs.S
@@ -0,0 +1,93 @@
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+
+#undef PREALLOC_NOT_AVAIL
+
+#ifdef PREALLOC_NOT_AVAIL
+#define PREWRITE(A,B)	prefetchw [(A),(B)]
+#else
+#define PREWRITE(A,B)	prealloc [(A),(B)]
+#endif
+
+ENTRY(memset)
+	prefetchw [r0]		; Prefetch the write location
+	mov.f	0, r2
+;;; if size is zero
+	jz.d	[blink]
+	mov	r3, r0		; don't clobber ret val
+
+;;; if length < 8
+	brls.d.nt	r2, 8, .Lsmallchunk
+	mov.f	lp_count,r2
+
+	and.f	r4, r0, 0x03
+	rsub	lp_count, r4, 4
+	lpnz	@.Laligndestination
+	;; LOOP BEGIN
+	stb.ab	r1, [r3,1]
+	sub	r2, r2, 1
+.Laligndestination:
+
+;;; Destination is aligned
+	and	r1, r1, 0xFF
+	asl	r4, r1, 8
+	or	r4, r4, r1
+	asl	r5, r4, 16
+	or	r5, r5, r4
+	mov	r4, r5
+
+	sub3	lp_count, r2, 8
+	cmp     r2, 64
+	bmsk.hi	r2, r2, 5
+	mov.ls	lp_count, 0
+	add3.hi	r2, r2, 8
+
+;;; Convert len to Dwords, unfold x8
+	lsr.f	lp_count, lp_count, 6
+	lpnz	@.Lset64bytes
+	;; LOOP START
+	PREWRITE(r3, 64)	;Prefetch the next write location
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+.Lset64bytes:
+
+	lsr.f	lp_count, r2, 5 ;Last remaining  max 124 bytes
+	lpnz	.Lset32bytes
+	;; LOOP START
+	prefetchw   [r3, 32]	;Prefetch the next write location
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+.Lset32bytes:
+
+	and.f	lp_count, r2, 0x1F ;Last remaining 31 bytes
+.Lsmallchunk:
+	lpnz	.Lcopy3bytes
+	;; LOOP START
+	stb.ab	r1, [r3, 1]
+.Lcopy3bytes:
+
+	j	[blink]
+
+END(memset)
+
+ENTRY(memzero)
+    ; adjust bzero args to memset args
+    mov r2, r1
+    b.d  memset    ;tail call so need to tinker with blink
+    mov r1, 0
+END(memzero)
diff --git a/arch/arc/lib/strcmp-archs.S b/arch/arc/lib/strcmp-archs.S
new file mode 100644
index 0000000..4f338ee
--- /dev/null
+++ b/arch/arc/lib/strcmp-archs.S
@@ -0,0 +1,78 @@
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+
+ENTRY(strcmp)
+	or	r2, r0, r1
+	bmsk_s	r2, r2, 1
+	brne	r2, 0, @.Lcharloop
+
+;;; s1 and s2 are word aligned
+	ld.ab	r2, [r0, 4]
+
+	mov_s	r12, 0x01010101
+	ror	r11, r12
+	.align  4
+.LwordLoop:
+	ld.ab	r3, [r1, 4]
+	;; Detect NULL char in str1
+	sub	r4, r2, r12
+	ld.ab	r5, [r0, 4]
+	bic	r4, r4, r2
+	and	r4, r4, r11
+	brne.d.nt	r4, 0, .LfoundNULL
+	;; Check if the read locations are the same
+	cmp	r2, r3
+	beq.d	.LwordLoop
+	mov.eq	r2, r5
+
+	;; A match is found, spot it out
+#ifdef __LITTLE_ENDIAN__
+	swape	r3, r3
+	mov_s	r0, 1
+	swape	r2, r2
+#else
+	mov_s	r0, 1
+#endif
+	cmp_s	r2, r3
+	j_s.d	[blink]
+	bset.lo	r0, r0, 31
+
+	.align 4
+.LfoundNULL:
+#ifdef __BIG_ENDIAN__
+	swape	r4, r4
+	swape	r2, r2
+	swape	r3, r3
+#endif
+	;; Find null byte
+	ffs	r0, r4
+	bmsk	r2, r2, r0
+	bmsk	r3, r3, r0
+	swape	r2, r2
+	swape	r3, r3
+	;; make the return value
+	sub.f	r0, r2, r3
+	mov.hi	r0, 1
+	j_s.d	[blink]
+	bset.lo	r0, r0, 31
+
+	.align 4
+.Lcharloop:
+	ldb.ab	r2, [r0, 1]
+	ldb.ab	r3, [r1, 1]
+	nop
+	breq	r2, 0, .Lcmpend
+	breq	r2, r3, .Lcharloop
+
+	.align 4
+.Lcmpend:
+	j_s.d	[blink]
+	sub	r0, r2, r3
+END(strcmp)
diff --git a/arch/arc/mm/Makefile b/arch/arc/mm/Makefile
index ac95cc2..7beb941 100644
--- a/arch/arc/mm/Makefile
+++ b/arch/arc/mm/Makefile
@@ -7,4 +7,4 @@
 #
 
 obj-y	:= extable.o ioremap.o dma.o fault.o init.o
-obj-y	+= tlb.o tlbex.o cache_arc700.o mmap.o
+obj-y	+= tlb.o tlbex.o cache.o mmap.o
diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache.c
similarity index 67%
rename from arch/arc/mm/cache_arc700.c
rename to arch/arc/mm/cache.c
index 12b2100..b29d62e 100644
--- a/arch/arc/mm/cache_arc700.c
+++ b/arch/arc/mm/cache.c
@@ -1,64 +1,12 @@
 /*
- * ARC700 VIPT Cache Management
+ * ARC Cache Management
  *
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
  * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- *  vineetg: May 2011: for Non-aliasing VIPT D-cache following can be NOPs
- *   -flush_cache_dup_mm (fork)
- *   -likewise for flush_cache_mm (exit/execve)
- *   -likewise for flush_cache_range,flush_cache_page (munmap, exit, COW-break)
- *
- * vineetg: Apr 2011
- *  -Now that MMU can support larger pg sz (16K), the determiniation of
- *   aliasing shd not be based on assumption of 8k pg
- *
- * vineetg: Mar 2011
- *  -optimised version of flush_icache_range( ) for making I/D coherent
- *   when vaddr is available (agnostic of num of aliases)
- *
- * vineetg: Mar 2011
- *  -Added documentation about I-cache aliasing on ARC700 and the way it
- *   was handled up until MMU V2.
- *  -Spotted a three year old bug when killing the 4 aliases, which needs
- *   bottom 2 bits, so we need to do paddr | {0x00, 0x01, 0x02, 0x03}
- *                        instead of paddr | {0x00, 0x01, 0x10, 0x11}
- *   (Rajesh you owe me one now)
- *
- * vineetg: Dec 2010
- *  -Off-by-one error when computing num_of_lines to flush
- *   This broke signal handling with bionic which uses synthetic sigret stub
- *
- * vineetg: Mar 2010
- *  -GCC can't generate ZOL for core cache flush loops.
- *   Conv them into iterations based as opposed to while (start < end) types
- *
- * Vineetg: July 2009
- *  -In I-cache flush routine we used to chk for aliasing for every line INV.
- *   Instead now we setup routines per cache geometry and invoke them
- *   via function pointers.
- *
- * Vineetg: Jan 2009
- *  -Cache Line flush routines used to flush an extra line beyond end addr
- *   because check was while (end >= start) instead of (end > start)
- *     =Some call sites had to work around by doing -1, -4 etc to end param
- *     =Some callers didnt care. This was spec bad in case of INV routines
- *      which would discard valid data (cause of the horrible ext2 bug
- *      in ARC IDE driver)
- *
- * vineetg: June 11th 2008: Fixed flush_icache_range( )
- *  -Since ARC700 caches are not coherent (I$ doesnt snoop D$) both need
- *   to be flushed, which it was not doing.
- *  -load_module( ) passes vmalloc addr (Kernel Virtual Addr) to the API,
- *   however ARC cache maintenance OPs require PHY addr. Thus need to do
- *   vmalloc_to_phy.
- *  -Also added optimisation there, that for range > PAGE SIZE we flush the
- *   entire cache in one shot rather than line by line. For e.g. a module
- *   with Code sz 600k, old code flushed 600k worth of cache (line-by-line),
- *   while cache is only 16 or 32k.
  */
 
 #include <linux/module.h>
@@ -73,9 +21,15 @@
 #include <asm/cachectl.h>
 #include <asm/setup.h>
 
+static int l2_line_sz;
+
+void (*_cache_line_loop_ic_fn)(unsigned long paddr, unsigned long vaddr,
+			       unsigned long sz, const int cacheop);
+
 char *arc_cache_mumbojumbo(int c, char *buf, int len)
 {
 	int n = 0;
+	struct cpuinfo_arc_cache *p;
 
 #define PR_CACHE(p, cfg, str)						\
 	if (!(p)->ver)							\
@@ -91,6 +45,11 @@
 	PR_CACHE(&cpuinfo_arc700[c].icache, CONFIG_ARC_HAS_ICACHE, "I-Cache");
 	PR_CACHE(&cpuinfo_arc700[c].dcache, CONFIG_ARC_HAS_DCACHE, "D-Cache");
 
+	p = &cpuinfo_arc700[c].slc;
+	if (p->ver)
+		n += scnprintf(buf + n, len - n,
+			"SLC\t\t: %uK, %uB Line\n", p->sz_k, p->line_len);
+
 	return buf;
 }
 
@@ -101,7 +60,7 @@
  */
 void read_decode_cache_bcr(void)
 {
-	struct cpuinfo_arc_cache *p_ic, *p_dc;
+	struct cpuinfo_arc_cache *p_ic, *p_dc, *p_slc;
 	unsigned int cpu = smp_processor_id();
 	struct bcr_cache {
 #ifdef CONFIG_CPU_BIG_ENDIAN
@@ -111,14 +70,29 @@
 #endif
 	} ibcr, dbcr;
 
+	struct bcr_generic sbcr;
+
+	struct bcr_slc_cfg {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+		unsigned int pad:24, way:2, lsz:2, sz:4;
+#else
+		unsigned int sz:4, lsz:2, way:2, pad:24;
+#endif
+	} slc_cfg;
+
 	p_ic = &cpuinfo_arc700[cpu].icache;
 	READ_BCR(ARC_REG_IC_BCR, ibcr);
 
 	if (!ibcr.ver)
 		goto dc_chk;
 
-	BUG_ON(ibcr.config != 3);
-	p_ic->assoc = 2;		/* Fixed to 2w set assoc */
+	if (ibcr.ver <= 3) {
+		BUG_ON(ibcr.config != 3);
+		p_ic->assoc = 2;		/* Fixed to 2w set assoc */
+	} else if (ibcr.ver >= 4) {
+		p_ic->assoc = 1 << ibcr.config;	/* 1,2,4,8 */
+	}
+
 	p_ic->line_len = 8 << ibcr.line_len;
 	p_ic->sz_k = 1 << (ibcr.sz - 1);
 	p_ic->ver = ibcr.ver;
@@ -130,66 +104,40 @@
 	READ_BCR(ARC_REG_DC_BCR, dbcr);
 
 	if (!dbcr.ver)
-		return;
+		goto slc_chk;
 
-	BUG_ON(dbcr.config != 2);
-	p_dc->assoc = 4;		/* Fixed to 4w set assoc */
+	if (dbcr.ver <= 3) {
+		BUG_ON(dbcr.config != 2);
+		p_dc->assoc = 4;		/* Fixed to 4w set assoc */
+		p_dc->vipt = 1;
+		p_dc->alias = p_dc->sz_k/p_dc->assoc/TO_KB(PAGE_SIZE) > 1;
+	} else if (dbcr.ver >= 4) {
+		p_dc->assoc = 1 << dbcr.config;	/* 1,2,4,8 */
+		p_dc->vipt = 0;
+		p_dc->alias = 0;		/* PIPT so can't VIPT alias */
+	}
+
 	p_dc->line_len = 16 << dbcr.line_len;
 	p_dc->sz_k = 1 << (dbcr.sz - 1);
 	p_dc->ver = dbcr.ver;
-	p_dc->vipt = 1;
-	p_dc->alias = p_dc->sz_k/p_dc->assoc/TO_KB(PAGE_SIZE) > 1;
+
+slc_chk:
+	if (!is_isa_arcv2())
+		return;
+
+	p_slc = &cpuinfo_arc700[cpu].slc;
+	READ_BCR(ARC_REG_SLC_BCR, sbcr);
+	if (sbcr.ver) {
+		READ_BCR(ARC_REG_SLC_CFG, slc_cfg);
+		p_slc->ver = sbcr.ver;
+		p_slc->sz_k = 128 << slc_cfg.sz;
+		l2_line_sz = p_slc->line_len = (slc_cfg.lsz == 0) ? 128 : 64;
+	}
 }
 
 /*
- * 1. Validate the Cache Geomtery (compile time config matches hardware)
- * 2. If I-cache suffers from aliasing, setup work arounds (difft flush rtn)
- *    (aliasing D-cache configurations are not supported YET)
- * 3. Enable the Caches, setup default flush mode for D-Cache
- * 3. Calculate the SHMLBA used by user space
+ * Line Operation on {I,D}-Cache
  */
-void arc_cache_init(void)
-{
-	unsigned int __maybe_unused cpu = smp_processor_id();
-	char str[256];
-
-	printk(arc_cache_mumbojumbo(0, str, sizeof(str)));
-
-	if (IS_ENABLED(CONFIG_ARC_HAS_ICACHE)) {
-		struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache;
-
-		if (!ic->ver)
-			panic("cache support enabled but non-existent cache\n");
-
-		if (ic->line_len != L1_CACHE_BYTES)
-			panic("ICache line [%d] != kernel Config [%d]",
-			      ic->line_len, L1_CACHE_BYTES);
-
-		if (ic->ver != CONFIG_ARC_MMU_VER)
-			panic("Cache ver [%d] doesn't match MMU ver [%d]\n",
-			      ic->ver, CONFIG_ARC_MMU_VER);
-	}
-
-	if (IS_ENABLED(CONFIG_ARC_HAS_DCACHE)) {
-		struct cpuinfo_arc_cache *dc = &cpuinfo_arc700[cpu].dcache;
-		int handled;
-
-		if (!dc->ver)
-			panic("cache support enabled but non-existent cache\n");
-
-		if (dc->line_len != L1_CACHE_BYTES)
-			panic("DCache line [%d] != kernel Config [%d]",
-			      dc->line_len, L1_CACHE_BYTES);
-
-		/* check for D-Cache aliasing */
-		handled = IS_ENABLED(CONFIG_ARC_CACHE_VIPT_ALIASING);
-
-		if (dc->alias && !handled)
-			panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
-		else if (!dc->alias && handled)
-			panic("Don't need CONFIG_ARC_CACHE_VIPT_ALIASING\n");
-	}
-}
 
 #define OP_INV		0x1
 #define OP_FLUSH	0x2
@@ -197,162 +145,7 @@
 #define OP_INV_IC	0x4
 
 /*
- * Common Helper for Line Operations on {I,D}-Cache
- */
-static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr,
-				     unsigned long sz, const int cacheop)
-{
-	unsigned int aux_cmd, aux_tag;
-	int num_lines;
-	const int full_page_op = __builtin_constant_p(sz) && sz == PAGE_SIZE;
-
-	if (cacheop == OP_INV_IC) {
-		aux_cmd = ARC_REG_IC_IVIL;
-#if (CONFIG_ARC_MMU_VER > 2)
-		aux_tag = ARC_REG_IC_PTAG;
-#endif
-	}
-	else {
-		/* d$ cmd: INV (discard or wback-n-discard) OR FLUSH (wback) */
-		aux_cmd = cacheop & OP_INV ? ARC_REG_DC_IVDL : ARC_REG_DC_FLDL;
-#if (CONFIG_ARC_MMU_VER > 2)
-		aux_tag = ARC_REG_DC_PTAG;
-#endif
-	}
-
-	/* Ensure we properly floor/ceil the non-line aligned/sized requests
-	 * and have @paddr - aligned to cache line and integral @num_lines.
-	 * This however can be avoided for page sized since:
-	 *  -@paddr will be cache-line aligned already (being page aligned)
-	 *  -@sz will be integral multiple of line size (being page sized).
-	 */
-	if (!full_page_op) {
-		sz += paddr & ~CACHE_LINE_MASK;
-		paddr &= CACHE_LINE_MASK;
-		vaddr &= CACHE_LINE_MASK;
-	}
-
-	num_lines = DIV_ROUND_UP(sz, L1_CACHE_BYTES);
-
-#if (CONFIG_ARC_MMU_VER <= 2)
-	/* MMUv2 and before: paddr contains stuffed vaddrs bits */
-	paddr |= (vaddr >> PAGE_SHIFT) & 0x1F;
-#else
-	/* if V-P const for loop, PTAG can be written once outside loop */
-	if (full_page_op)
-		write_aux_reg(aux_tag, paddr);
-#endif
-
-	while (num_lines-- > 0) {
-#if (CONFIG_ARC_MMU_VER > 2)
-		/* MMUv3, cache ops require paddr seperately */
-		if (!full_page_op) {
-			write_aux_reg(aux_tag, paddr);
-			paddr += L1_CACHE_BYTES;
-		}
-
-		write_aux_reg(aux_cmd, vaddr);
-		vaddr += L1_CACHE_BYTES;
-#else
-		write_aux_reg(aux_cmd, paddr);
-		paddr += L1_CACHE_BYTES;
-#endif
-	}
-}
-
-#ifdef CONFIG_ARC_HAS_DCACHE
-
-/***************************************************************
- * Machine specific helpers for Entire D-Cache or Per Line ops
- */
-
-static inline unsigned int __before_dc_op(const int op)
-{
-	unsigned int reg = reg;
-
-	if (op == OP_FLUSH_N_INV) {
-		/* Dcache provides 2 cmd: FLUSH or INV
-		 * INV inturn has sub-modes: DISCARD or FLUSH-BEFORE
-		 * flush-n-inv is achieved by INV cmd but with IM=1
-		 * So toggle INV sub-mode depending on op request and default
-		 */
-		reg = read_aux_reg(ARC_REG_DC_CTRL);
-		write_aux_reg(ARC_REG_DC_CTRL, reg | DC_CTRL_INV_MODE_FLUSH)
-			;
-	}
-
-	return reg;
-}
-
-static inline void __after_dc_op(const int op, unsigned int reg)
-{
-	if (op & OP_FLUSH)	/* flush / flush-n-inv both wait */
-		while (read_aux_reg(ARC_REG_DC_CTRL) & DC_CTRL_FLUSH_STATUS);
-
-	/* Switch back to default Invalidate mode */
-	if (op == OP_FLUSH_N_INV)
-		write_aux_reg(ARC_REG_DC_CTRL, reg & ~DC_CTRL_INV_MODE_FLUSH);
-}
-
-/*
- * Operation on Entire D-Cache
- * @cacheop = {OP_INV, OP_FLUSH, OP_FLUSH_N_INV}
- * Note that constant propagation ensures all the checks are gone
- * in generated code
- */
-static inline void __dc_entire_op(const int cacheop)
-{
-	unsigned int ctrl_reg;
-	int aux;
-
-	ctrl_reg = __before_dc_op(cacheop);
-
-	if (cacheop & OP_INV)	/* Inv or flush-n-inv use same cmd reg */
-		aux = ARC_REG_DC_IVDC;
-	else
-		aux = ARC_REG_DC_FLSH;
-
-	write_aux_reg(aux, 0x1);
-
-	__after_dc_op(cacheop, ctrl_reg);
-}
-
-/* For kernel mappings cache operation: index is same as paddr */
-#define __dc_line_op_k(p, sz, op)	__dc_line_op(p, p, sz, op)
-
-/*
- * D-Cache : Per Line INV (discard or wback+discard) or FLUSH (wback)
- */
-static inline void __dc_line_op(unsigned long paddr, unsigned long vaddr,
-				unsigned long sz, const int cacheop)
-{
-	unsigned long flags;
-	unsigned int ctrl_reg;
-
-	local_irq_save(flags);
-
-	ctrl_reg = __before_dc_op(cacheop);
-
-	__cache_line_loop(paddr, vaddr, sz, cacheop);
-
-	__after_dc_op(cacheop, ctrl_reg);
-
-	local_irq_restore(flags);
-}
-
-#else
-
-#define __dc_entire_op(cacheop)
-#define __dc_line_op(paddr, vaddr, sz, cacheop)
-#define __dc_line_op_k(paddr, sz, cacheop)
-
-#endif /* CONFIG_ARC_HAS_DCACHE */
-
-
-#ifdef CONFIG_ARC_HAS_ICACHE
-
-/*
- *		I-Cache Aliasing in ARC700 VIPT caches
+ *		I-Cache Aliasing in ARC700 VIPT caches (MMU v1-v3)
  *
  * ARC VIPT I-cache uses vaddr to index into cache and paddr to match the tag.
  * The orig Cache Management Module "CDU" only required paddr to invalidate a
@@ -393,9 +186,228 @@
  * "tag" bits are provided in PTAG, index bits in existing IVIL/IVDL/FLDL regs
  */
 
-/***********************************************************
- * Machine specific helper for per line I-Cache invalidate.
+static inline
+void __cache_line_loop_v2(unsigned long paddr, unsigned long vaddr,
+			  unsigned long sz, const int op)
+{
+	unsigned int aux_cmd;
+	int num_lines;
+	const int full_page = __builtin_constant_p(sz) && sz == PAGE_SIZE;
+
+	if (op == OP_INV_IC) {
+		aux_cmd = ARC_REG_IC_IVIL;
+	} else {
+		/* d$ cmd: INV (discard or wback-n-discard) OR FLUSH (wback) */
+		aux_cmd = op & OP_INV ? ARC_REG_DC_IVDL : ARC_REG_DC_FLDL;
+	}
+
+	/* Ensure we properly floor/ceil the non-line aligned/sized requests
+	 * and have @paddr - aligned to cache line and integral @num_lines.
+	 * This however can be avoided for page sized since:
+	 *  -@paddr will be cache-line aligned already (being page aligned)
+	 *  -@sz will be integral multiple of line size (being page sized).
+	 */
+	if (!full_page) {
+		sz += paddr & ~CACHE_LINE_MASK;
+		paddr &= CACHE_LINE_MASK;
+		vaddr &= CACHE_LINE_MASK;
+	}
+
+	num_lines = DIV_ROUND_UP(sz, L1_CACHE_BYTES);
+
+	/* MMUv2 and before: paddr contains stuffed vaddrs bits */
+	paddr |= (vaddr >> PAGE_SHIFT) & 0x1F;
+
+	while (num_lines-- > 0) {
+		write_aux_reg(aux_cmd, paddr);
+		paddr += L1_CACHE_BYTES;
+	}
+}
+
+static inline
+void __cache_line_loop_v3(unsigned long paddr, unsigned long vaddr,
+			  unsigned long sz, const int op)
+{
+	unsigned int aux_cmd, aux_tag;
+	int num_lines;
+	const int full_page = __builtin_constant_p(sz) && sz == PAGE_SIZE;
+
+	if (op == OP_INV_IC) {
+		aux_cmd = ARC_REG_IC_IVIL;
+		aux_tag = ARC_REG_IC_PTAG;
+	} else {
+		aux_cmd = op & OP_INV ? ARC_REG_DC_IVDL : ARC_REG_DC_FLDL;
+		aux_tag = ARC_REG_DC_PTAG;
+	}
+
+	/* Ensure we properly floor/ceil the non-line aligned/sized requests
+	 * and have @paddr - aligned to cache line and integral @num_lines.
+	 * This however can be avoided for page sized since:
+	 *  -@paddr will be cache-line aligned already (being page aligned)
+	 *  -@sz will be integral multiple of line size (being page sized).
+	 */
+	if (!full_page) {
+		sz += paddr & ~CACHE_LINE_MASK;
+		paddr &= CACHE_LINE_MASK;
+		vaddr &= CACHE_LINE_MASK;
+	}
+	num_lines = DIV_ROUND_UP(sz, L1_CACHE_BYTES);
+
+	/*
+	 * MMUv3, cache ops require paddr in PTAG reg
+	 * if V-P const for loop, PTAG can be written once outside loop
+	 */
+	if (full_page)
+		write_aux_reg(aux_tag, paddr);
+
+	while (num_lines-- > 0) {
+		if (!full_page) {
+			write_aux_reg(aux_tag, paddr);
+			paddr += L1_CACHE_BYTES;
+		}
+
+		write_aux_reg(aux_cmd, vaddr);
+		vaddr += L1_CACHE_BYTES;
+	}
+}
+
+/*
+ * In HS38x (MMU v4), although icache is VIPT, only paddr is needed for cache
+ * maintenance ops (in IVIL reg), as long as icache doesn't alias.
+ *
+ * For Aliasing icache, vaddr is also needed (in IVIL), while paddr is
+ * specified in PTAG (similar to MMU v3)
  */
+static inline
+void __cache_line_loop_v4(unsigned long paddr, unsigned long vaddr,
+			  unsigned long sz, const int cacheop)
+{
+	unsigned int aux_cmd;
+	int num_lines;
+	const int full_page_op = __builtin_constant_p(sz) && sz == PAGE_SIZE;
+
+	if (cacheop == OP_INV_IC) {
+		aux_cmd = ARC_REG_IC_IVIL;
+	} else {
+		/* d$ cmd: INV (discard or wback-n-discard) OR FLUSH (wback) */
+		aux_cmd = cacheop & OP_INV ? ARC_REG_DC_IVDL : ARC_REG_DC_FLDL;
+	}
+
+	/* Ensure we properly floor/ceil the non-line aligned/sized requests
+	 * and have @paddr - aligned to cache line and integral @num_lines.
+	 * This however can be avoided for page sized since:
+	 *  -@paddr will be cache-line aligned already (being page aligned)
+	 *  -@sz will be integral multiple of line size (being page sized).
+	 */
+	if (!full_page_op) {
+		sz += paddr & ~CACHE_LINE_MASK;
+		paddr &= CACHE_LINE_MASK;
+	}
+
+	num_lines = DIV_ROUND_UP(sz, L1_CACHE_BYTES);
+
+	while (num_lines-- > 0) {
+		write_aux_reg(aux_cmd, paddr);
+		paddr += L1_CACHE_BYTES;
+	}
+}
+
+#if (CONFIG_ARC_MMU_VER < 3)
+#define __cache_line_loop	__cache_line_loop_v2
+#elif (CONFIG_ARC_MMU_VER == 3)
+#define __cache_line_loop	__cache_line_loop_v3
+#elif (CONFIG_ARC_MMU_VER > 3)
+#define __cache_line_loop	__cache_line_loop_v4
+#endif
+
+#ifdef CONFIG_ARC_HAS_DCACHE
+
+/***************************************************************
+ * Machine specific helpers for Entire D-Cache or Per Line ops
+ */
+
+static inline void __before_dc_op(const int op)
+{
+	if (op == OP_FLUSH_N_INV) {
+		/* Dcache provides 2 cmd: FLUSH or INV
+		 * INV inturn has sub-modes: DISCARD or FLUSH-BEFORE
+		 * flush-n-inv is achieved by INV cmd but with IM=1
+		 * So toggle INV sub-mode depending on op request and default
+		 */
+		const unsigned int ctl = ARC_REG_DC_CTRL;
+		write_aux_reg(ctl, read_aux_reg(ctl) | DC_CTRL_INV_MODE_FLUSH);
+	}
+}
+
+static inline void __after_dc_op(const int op)
+{
+	if (op & OP_FLUSH) {
+		const unsigned int ctl = ARC_REG_DC_CTRL;
+		unsigned int reg;
+
+		/* flush / flush-n-inv both wait */
+		while ((reg = read_aux_reg(ctl)) & DC_CTRL_FLUSH_STATUS)
+			;
+
+		/* Switch back to default Invalidate mode */
+		if (op == OP_FLUSH_N_INV)
+			write_aux_reg(ctl, reg & ~DC_CTRL_INV_MODE_FLUSH);
+	}
+}
+
+/*
+ * Operation on Entire D-Cache
+ * @op = {OP_INV, OP_FLUSH, OP_FLUSH_N_INV}
+ * Note that constant propagation ensures all the checks are gone
+ * in generated code
+ */
+static inline void __dc_entire_op(const int op)
+{
+	int aux;
+
+	__before_dc_op(op);
+
+	if (op & OP_INV)	/* Inv or flush-n-inv use same cmd reg */
+		aux = ARC_REG_DC_IVDC;
+	else
+		aux = ARC_REG_DC_FLSH;
+
+	write_aux_reg(aux, 0x1);
+
+	__after_dc_op(op);
+}
+
+/* For kernel mappings cache operation: index is same as paddr */
+#define __dc_line_op_k(p, sz, op)	__dc_line_op(p, p, sz, op)
+
+/*
+ * D-Cache Line ops: Per Line INV (discard or wback+discard) or FLUSH (wback)
+ */
+static inline void __dc_line_op(unsigned long paddr, unsigned long vaddr,
+				unsigned long sz, const int op)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	__before_dc_op(op);
+
+	__cache_line_loop(paddr, vaddr, sz, op);
+
+	__after_dc_op(op);
+
+	local_irq_restore(flags);
+}
+
+#else
+
+#define __dc_entire_op(op)
+#define __dc_line_op(paddr, vaddr, sz, op)
+#define __dc_line_op_k(paddr, sz, op)
+
+#endif /* CONFIG_ARC_HAS_DCACHE */
+
+#ifdef CONFIG_ARC_HAS_ICACHE
 
 static inline void __ic_entire_inv(void)
 {
@@ -410,7 +422,7 @@
 	unsigned long flags;
 
 	local_irq_save(flags);
-	__cache_line_loop(paddr, vaddr, sz, OP_INV_IC);
+	(*_cache_line_loop_ic_fn)(paddr, vaddr, sz, OP_INV_IC);
 	local_irq_restore(flags);
 }
 
@@ -453,6 +465,53 @@
 
 #endif /* CONFIG_ARC_HAS_ICACHE */
 
+noinline void slc_op(unsigned long paddr, unsigned long sz, const int op)
+{
+#ifdef CONFIG_ISA_ARCV2
+	unsigned long flags;
+	unsigned int ctrl;
+
+	local_irq_save(flags);
+
+	/*
+	 * The Region Flush operation is specified by CTRL.RGN_OP[11..9]
+	 *  - b'000 (default) is Flush,
+	 *  - b'001 is Invalidate if CTRL.IM == 0
+	 *  - b'001 is Flush-n-Invalidate if CTRL.IM == 1
+	 */
+	ctrl = read_aux_reg(ARC_REG_SLC_CTRL);
+
+	/* Don't rely on default value of IM bit */
+	if (!(op & OP_FLUSH))		/* i.e. OP_INV */
+		ctrl &= ~SLC_CTRL_IM;	/* clear IM: Disable flush before Inv */
+	else
+		ctrl |= SLC_CTRL_IM;
+
+	if (op & OP_INV)
+		ctrl |= SLC_CTRL_RGN_OP_INV;	/* Inv or flush-n-inv */
+	else
+		ctrl &= ~SLC_CTRL_RGN_OP_INV;
+
+	write_aux_reg(ARC_REG_SLC_CTRL, ctrl);
+
+	/*
+	 * Lower bits are ignored, no need to clip
+	 * END needs to be setup before START (latter triggers the operation)
+	 * END can't be same as START, so add (l2_line_sz - 1) to sz
+	 */
+	write_aux_reg(ARC_REG_SLC_RGN_END, (paddr + sz + l2_line_sz - 1));
+	write_aux_reg(ARC_REG_SLC_RGN_START, paddr);
+
+	while (read_aux_reg(ARC_REG_SLC_CTRL) & SLC_CTRL_BUSY);
+
+	local_irq_restore(flags);
+#endif
+}
+
+static inline int need_slc_flush(void)
+{
+	return is_isa_arcv2() && l2_line_sz;
+}
 
 /***********************************************************
  * Exported APIs
@@ -493,7 +552,7 @@
 	} else if (page_mapped(page)) {
 
 		/* kernel reading from page with U-mapping */
-		void *paddr = page_address(page);
+		unsigned long paddr = (unsigned long)page_address(page);
 		unsigned long vaddr = page->index << PAGE_CACHE_SHIFT;
 
 		if (addr_not_cache_congruent(paddr, vaddr))
@@ -502,22 +561,30 @@
 }
 EXPORT_SYMBOL(flush_dcache_page);
 
-
 void dma_cache_wback_inv(unsigned long start, unsigned long sz)
 {
 	__dc_line_op_k(start, sz, OP_FLUSH_N_INV);
+
+	if (need_slc_flush())
+		slc_op(start, sz, OP_FLUSH_N_INV);
 }
 EXPORT_SYMBOL(dma_cache_wback_inv);
 
 void dma_cache_inv(unsigned long start, unsigned long sz)
 {
 	__dc_line_op_k(start, sz, OP_INV);
+
+	if (need_slc_flush())
+		slc_op(start, sz, OP_INV);
 }
 EXPORT_SYMBOL(dma_cache_inv);
 
 void dma_cache_wback(unsigned long start, unsigned long sz)
 {
 	__dc_line_op_k(start, sz, OP_FLUSH);
+
+	if (need_slc_flush())
+		slc_op(start, sz, OP_FLUSH);
 }
 EXPORT_SYMBOL(dma_cache_wback);
 
@@ -605,7 +672,7 @@
  * wrapper to clearout kernel or userspace mappings of a page
  * For kernel mappings @vaddr == @paddr
  */
-void ___flush_dcache_page(unsigned long paddr, unsigned long vaddr)
+void __flush_dcache_page(unsigned long paddr, unsigned long vaddr)
 {
 	__dc_line_op(paddr, vaddr & PAGE_MASK, PAGE_SIZE, OP_FLUSH_N_INV);
 }
@@ -637,7 +704,7 @@
 
 	u_vaddr &= PAGE_MASK;
 
-	___flush_dcache_page(paddr, u_vaddr);
+	__flush_dcache_page(paddr, u_vaddr);
 
 	if (vma->vm_flags & VM_EXEC)
 		__inv_icache_page(paddr, u_vaddr);
@@ -663,8 +730,8 @@
 void copy_user_highpage(struct page *to, struct page *from,
 	unsigned long u_vaddr, struct vm_area_struct *vma)
 {
-	void *kfrom = page_address(from);
-	void *kto = page_address(to);
+	unsigned long kfrom = (unsigned long)page_address(from);
+	unsigned long kto = (unsigned long)page_address(to);
 	int clean_src_k_mappings = 0;
 
 	/*
@@ -680,7 +747,7 @@
 		clean_src_k_mappings = 1;
 	}
 
-	copy_page(kto, kfrom);
+	copy_page((void *)kto, (void *)kfrom);
 
 	/*
 	 * Mark DST page K-mapping as dirty for a later finalization by
@@ -721,3 +788,56 @@
 	flush_cache_all();
 	return 0;
 }
+
+void arc_cache_init(void)
+{
+	unsigned int __maybe_unused cpu = smp_processor_id();
+	char str[256];
+
+	printk(arc_cache_mumbojumbo(0, str, sizeof(str)));
+
+	if (IS_ENABLED(CONFIG_ARC_HAS_ICACHE)) {
+		struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache;
+
+		if (!ic->ver)
+			panic("cache support enabled but non-existent cache\n");
+
+		if (ic->line_len != L1_CACHE_BYTES)
+			panic("ICache line [%d] != kernel Config [%d]",
+			      ic->line_len, L1_CACHE_BYTES);
+
+		if (ic->ver != CONFIG_ARC_MMU_VER)
+			panic("Cache ver [%d] doesn't match MMU ver [%d]\n",
+			      ic->ver, CONFIG_ARC_MMU_VER);
+
+		/*
+		 * In MMU v4 (HS38x) the alising icache config uses IVIL/PTAG
+		 * pair to provide vaddr/paddr respectively, just as in MMU v3
+		 */
+		if (is_isa_arcv2() && ic->alias)
+			_cache_line_loop_ic_fn = __cache_line_loop_v3;
+		else
+			_cache_line_loop_ic_fn = __cache_line_loop;
+	}
+
+	if (IS_ENABLED(CONFIG_ARC_HAS_DCACHE)) {
+		struct cpuinfo_arc_cache *dc = &cpuinfo_arc700[cpu].dcache;
+
+		if (!dc->ver)
+			panic("cache support enabled but non-existent cache\n");
+
+		if (dc->line_len != L1_CACHE_BYTES)
+			panic("DCache line [%d] != kernel Config [%d]",
+			      dc->line_len, L1_CACHE_BYTES);
+
+		/* check for D-Cache aliasing on ARCompact: ARCv2 has PIPT */
+		if (is_isa_arcompact()) {
+			int handled = IS_ENABLED(CONFIG_ARC_CACHE_VIPT_ALIASING);
+
+			if (dc->alias && !handled)
+				panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
+			else if (!dc->alias && handled)
+				panic("Disable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
+		}
+	}
+}
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 12cc648..74a637a 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -14,8 +14,6 @@
  * Cache bit off in the TLB entry.
  *
  * The default DMA address == Phy address which is 0x8000_0000 based.
- * A platform/device can make it zero based, by over-riding
- * plat_{dma,kernel}_addr_to_{kernel,dma}
  */
 
 #include <linux/dma-mapping.h>
@@ -37,7 +35,7 @@
 		return NULL;
 
 	/* This is bus address, platform dependent */
-	*dma_handle = plat_kernel_addr_to_dma(dev, paddr);
+	*dma_handle = (dma_addr_t)paddr;
 
 	return paddr;
 }
@@ -46,8 +44,7 @@
 void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr,
 			  dma_addr_t dma_handle)
 {
-	free_pages_exact((void *)plat_dma_addr_to_kernel(dev, dma_handle),
-			 size);
+	free_pages_exact((void *)dma_handle, size);
 }
 EXPORT_SYMBOL(dma_free_noncoherent);
 
@@ -67,7 +64,19 @@
 		memset(kvaddr, 0, size);
 
 	/* This is bus address, platform dependent */
-	*dma_handle = plat_kernel_addr_to_dma(dev, paddr);
+	*dma_handle = (dma_addr_t)paddr;
+
+	/*
+	 * Evict any existing L1 and/or L2 lines for the backing page
+	 * in case it was used earlier as a normal "cached" page.
+	 * Yeah this bit us - STAR 9000898266
+	 *
+	 * Although core does call flush_cache_vmap(), it gets kvaddr hence
+	 * can't be used to efficiently flush L1 and/or L2 which need paddr
+	 * Currently flush_cache_vmap nukes the L1 cache completely which
+	 * will be optimized as a separate commit
+	 */
+	dma_cache_wback_inv((unsigned long)paddr, size);
 
 	return kvaddr;
 }
@@ -78,8 +87,7 @@
 {
 	iounmap((void __force __iomem *)kvaddr);
 
-	free_pages_exact((void *)plat_dma_addr_to_kernel(dev, dma_handle),
-			 size);
+	free_pages_exact((void *)dma_handle, size);
 }
 EXPORT_SYMBOL(dma_free_coherent);
 
diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c
index 7f47d2a..2c7ce8b 100644
--- a/arch/arc/mm/tlb.c
+++ b/arch/arc/mm/tlb.c
@@ -113,6 +113,8 @@
 	write_aux_reg(ARC_REG_TLBCOMMAND, TLBWrite);
 }
 
+#if (CONFIG_ARC_MMU_VER < 4)
+
 static inline unsigned int tlb_entry_lkup(unsigned long vaddr_n_asid)
 {
 	unsigned int idx;
@@ -210,6 +212,28 @@
 	write_aux_reg(ARC_REG_TLBCOMMAND, TLBWrite);
 }
 
+#else	/* CONFIG_ARC_MMU_VER >= 4) */
+
+static void utlb_invalidate(void)
+{
+	/* No need since uTLB is always in sync with JTLB */
+}
+
+static void tlb_entry_erase(unsigned int vaddr_n_asid)
+{
+	write_aux_reg(ARC_REG_TLBPD0, vaddr_n_asid | _PAGE_PRESENT);
+	write_aux_reg(ARC_REG_TLBCOMMAND, TLBDeleteEntry);
+}
+
+static void tlb_entry_insert(unsigned int pd0, unsigned int pd1)
+{
+	write_aux_reg(ARC_REG_TLBPD0, pd0);
+	write_aux_reg(ARC_REG_TLBPD1, pd1);
+	write_aux_reg(ARC_REG_TLBCOMMAND, TLBInsertEntry);
+}
+
+#endif
+
 /*
  * Un-conditionally (without lookup) erase the entire MMU contents
  */
@@ -582,23 +606,42 @@
 #endif
 	} *mmu3;
 
+	struct bcr_mmu_4 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int ver:8, sasid:1, sz1:4, sz0:4, res:2, pae:1,
+		     n_ways:2, n_entry:2, n_super:2, u_itlb:3, u_dtlb:3;
+#else
+	/*           DTLB      ITLB      JES        JE         JA      */
+	unsigned int u_dtlb:3, u_itlb:3, n_super:2, n_entry:2, n_ways:2,
+		     pae:1, res:2, sz0:4, sz1:4, sasid:1, ver:8;
+#endif
+	} *mmu4;
+
 	tmp = read_aux_reg(ARC_REG_MMU_BCR);
 	mmu->ver = (tmp >> 24);
 
 	if (mmu->ver <= 2) {
 		mmu2 = (struct bcr_mmu_1_2 *)&tmp;
-		mmu->pg_sz = PAGE_SIZE;
+		mmu->pg_sz_k = TO_KB(PAGE_SIZE);
 		mmu->sets = 1 << mmu2->sets;
 		mmu->ways = 1 << mmu2->ways;
 		mmu->u_dtlb = mmu2->u_dtlb;
 		mmu->u_itlb = mmu2->u_itlb;
-	} else {
+	} else if (mmu->ver == 3) {
 		mmu3 = (struct bcr_mmu_3 *)&tmp;
-		mmu->pg_sz = 512 << mmu3->pg_sz;
+		mmu->pg_sz_k = 1 << (mmu3->pg_sz - 1);
 		mmu->sets = 1 << mmu3->sets;
 		mmu->ways = 1 << mmu3->ways;
 		mmu->u_dtlb = mmu3->u_dtlb;
 		mmu->u_itlb = mmu3->u_itlb;
+	} else {
+		mmu4 = (struct bcr_mmu_4 *)&tmp;
+		mmu->pg_sz_k = 1 << (mmu4->sz0 - 1);
+		mmu->s_pg_sz_m = 1 << (mmu4->sz1 - 11);
+		mmu->sets = 64 << mmu4->n_entry;
+		mmu->ways = mmu4->n_ways * 2;
+		mmu->u_dtlb = mmu4->u_dtlb * 4;
+		mmu->u_itlb = mmu4->u_itlb * 4;
 	}
 
 	mmu->num_tlb = mmu->sets * mmu->ways;
@@ -608,10 +651,15 @@
 {
 	int n = 0;
 	struct cpuinfo_arc_mmu *p_mmu = &cpuinfo_arc700[cpu_id].mmu;
+	char super_pg[64] = "";
+
+	if (p_mmu->s_pg_sz_m)
+		scnprintf(super_pg, 64, "%dM Super Page%s, ",
+			  p_mmu->s_pg_sz_m, " (not used)");
 
 	n += scnprintf(buf + n, len - n,
-		      "MMU [v%x]\t: %dk PAGE, JTLB %d (%dx%d), uDTLB %d, uITLB %d %s\n",
-		       p_mmu->ver, TO_KB(p_mmu->pg_sz),
+		      "MMU [v%x]\t: %dk PAGE, %sJTLB %d (%dx%d), uDTLB %d, uITLB %d %s\n",
+		       p_mmu->ver, p_mmu->pg_sz_k, super_pg,
 		       p_mmu->num_tlb, p_mmu->sets, p_mmu->ways,
 		       p_mmu->u_dtlb, p_mmu->u_itlb,
 		       IS_ENABLED(CONFIG_ARC_MMU_SASID) ? ",SASID" : "");
@@ -639,7 +687,7 @@
 		      mmu->ver, CONFIG_ARC_MMU_VER);
 	}
 
-	if (mmu->pg_sz != PAGE_SIZE)
+	if (mmu->pg_sz_k != TO_KB(PAGE_SIZE))
 		panic("MMU pg size != PAGE_SIZE (%luk)\n", TO_KB(PAGE_SIZE));
 
 	/* Enable the MMU */
diff --git a/arch/arc/mm/tlbex.S b/arch/arc/mm/tlbex.S
index d572f1c..f6f4c3c 100644
--- a/arch/arc/mm/tlbex.S
+++ b/arch/arc/mm/tlbex.S
@@ -35,8 +35,6 @@
  * Rahul Trivedi, Amit Bhor: Codito Technologies 2004
  */
 
-	.cpu A7
-
 #include <linux/linkage.h>
 #include <asm/entry.h>
 #include <asm/mmu.h>
@@ -46,6 +44,7 @@
 #include <asm/processor.h>
 #include <asm/tlb-mmu1.h>
 
+#ifdef CONFIG_ISA_ARCOMPACT
 ;-----------------------------------------------------------------
 ; ARC700 Exception Handling doesn't auto-switch stack and it only provides
 ; ONE scratch AUX reg "ARC_REG_SCRATCH_DATA0"
@@ -123,6 +122,24 @@
 #endif
 .endm
 
+#else	/* ARCv2 */
+
+.macro TLBMISS_FREEUP_REGS
+	PUSH  r0
+	PUSH  r1
+	PUSH  r2
+	PUSH  r3
+.endm
+
+.macro TLBMISS_RESTORE_REGS
+	POP   r3
+	POP   r2
+	POP   r1
+	POP   r0
+.endm
+
+#endif
+
 ;============================================================================
 ;  Troubleshooting Stuff
 ;============================================================================
@@ -241,6 +258,7 @@
 ; Commit the TLB entry into MMU
 
 .macro COMMIT_ENTRY_TO_MMU
+#if (CONFIG_ARC_MMU_VER < 4)
 
 	/* Get free TLB slot: Set = computed from vaddr, way = random */
 	sr  TLBGetIndex, [ARC_REG_TLBCOMMAND]
@@ -251,6 +269,10 @@
 #else
 	sr TLBWrite, [ARC_REG_TLBCOMMAND]
 #endif
+
+#else
+	sr TLBInsertEntry, [ARC_REG_TLBCOMMAND]
+#endif
 .endm
 
 
@@ -291,6 +313,7 @@
 	CONV_PTE_TO_TLB
 	COMMIT_ENTRY_TO_MMU
 	TLBMISS_RESTORE_REGS
+EV_TLBMissI_fast_ret:	; additional label for VDK OS-kit instrumentation
 	rtie
 
 END(EV_TLBMissI)
@@ -356,6 +379,7 @@
 
 	COMMIT_ENTRY_TO_MMU
 	TLBMISS_RESTORE_REGS
+EV_TLBMissD_fast_ret:	; additional label for VDK OS-kit instrumentation
 	rtie
 
 ;-------- Common routine to call Linux Page Fault Handler -----------
@@ -366,19 +390,5 @@
 
 	; Slow path TLB Miss handled as a regular ARC Exception
 	; (stack switching / save the complete reg-file).
-	EXCEPTION_PROLOGUE
-
-	; ------- setup args for Linux Page fault Hanlder ---------
-	mov_s r1, sp
-	lr    r0, [efa]
-
-	; We don't want exceptions to be disabled while the fault is handled.
-	; Now that we have saved the context we return from exception hence
-	; exceptions get re-enable
-
-	FAKE_RET_FROM_EXCPN  r9
-
-	bl  do_page_fault
-	b   ret_from_exception
-
+	b  call_do_page_fault
 END(EV_TLBMissD)
diff --git a/arch/arc/plat-arcfpga/Kconfig b/arch/arc/plat-arcfpga/Kconfig
deleted file mode 100644
index 217593a..0000000
--- a/arch/arc/plat-arcfpga/Kconfig
+++ /dev/null
@@ -1,33 +0,0 @@
-#
-# Copyright (C) 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License version 2 as
-# published by the Free Software Foundation.
-#
-
-menuconfig ARC_PLAT_FPGA_LEGACY
-	bool "\"Legacy\" ARC FPGA dev Boards"
-	select ARC_HAS_COH_CACHES if SMP
-	help
-	  Support for ARC development boards, provided by Synopsys.
-	  These are based on FPGA or ISS. e.g.
-	  - ARCAngel4
-	  - ML509
-	  - MetaWare ISS
-
-if ARC_PLAT_FPGA_LEGACY
-
-config ISS_SMP_EXTN
-	bool "ARC SMP Extensions (ISS Models only)"
-	default n
-	depends on SMP
-	help
-	  SMP Extensions to ARC700, in a "simulation only" Model, supported in
-	  ARC ISS (Instruction Set Simulator).
-	  The SMP extensions include:
-	  -IDU (Interrupt Distribution Unit)
-	  -XTL (To enable CPU start/stop/set-PC for another CPU)
-	  It doesn't provide coherent Caches and/or Atomic Ops (LLOCK/SCOND)
-
-endif
diff --git a/arch/arc/plat-arcfpga/include/plat/smp.h b/arch/arc/plat-arcfpga/include/plat/smp.h
deleted file mode 100644
index c09eb4c..0000000
--- a/arch/arc/plat-arcfpga/include/plat/smp.h
+++ /dev/null
@@ -1,118 +0,0 @@
-/*
- * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- *  Rajeshwar Ranga: Interrupt Distribution Unit API's
- */
-
-#ifndef __PLAT_ARCFPGA_SMP_H
-#define __PLAT_ARCFPGA_SMP_H
-
-#ifdef CONFIG_SMP
-
-#include <linux/types.h>
-#include <asm/arcregs.h>
-
-#define ARC_AUX_IDU_REG_CMD		0x2000
-#define ARC_AUX_IDU_REG_PARAM		0x2001
-
-#define ARC_AUX_XTL_REG_CMD		0x2002
-#define ARC_AUX_XTL_REG_PARAM		0x2003
-
-#define ARC_REG_MP_BCR			0x2021
-
-#define ARC_XTL_CMD_WRITE_PC		0x04
-#define ARC_XTL_CMD_CLEAR_HALT		0x02
-
-/*
- * Build Configuration Register which identifies the sub-components
- */
-struct bcr_mp {
-#ifdef CONFIG_CPU_BIG_ENDIAN
-	unsigned int mp_arch:16, pad:5, sdu:1, idu:1, scu:1, ver:8;
-#else
-	unsigned int ver:8, scu:1, idu:1, sdu:1, pad:5, mp_arch:16;
-#endif
-};
-
-/* IDU supports 256 common interrupts */
-#define NR_IDU_IRQS			256
-
-/*
- * The Aux Regs layout is same bit-by-bit in both BE/LE modes.
- * However when casted as a bitfield encoded "C" struct, gcc treats it as
- * memory, generating different code for BE/LE, requiring strcture adj (see
- * include/asm/arcregs.h)
- *
- * However when manually "carving" the value for a Aux, no special handling
- * of BE is needed because of the property discribed above
- */
-#define IDU_SET_COMMAND(irq, cmd)			\
-do {							\
-	uint32_t __val;					\
-	__val = (((irq & 0xFF) << 8) | (cmd & 0xFF));	\
-	write_aux_reg(ARC_AUX_IDU_REG_CMD, __val);	\
-} while (0)
-
-#define IDU_SET_PARAM(par)  write_aux_reg(ARC_AUX_IDU_REG_PARAM, par)
-#define IDU_GET_PARAM()     read_aux_reg(ARC_AUX_IDU_REG_PARAM)
-
-/* IDU Commands */
-#define IDU_DISABLE			0x00
-#define IDU_ENABLE			0x01
-#define IDU_IRQ_CLEAR			0x02
-#define IDU_IRQ_ASSERT			0x03
-#define IDU_IRQ_WMODE			0x04
-#define IDU_IRQ_STATUS			0x05
-#define IDU_IRQ_ACK			0x06
-#define IDU_IRQ_PEND			0x07
-#define IDU_IRQ_RMODE			0x08
-#define IDU_IRQ_WBITMASK		0x09
-#define IDU_IRQ_RBITMASK		0x0A
-
-#define idu_enable()		IDU_SET_COMMAND(0, IDU_ENABLE)
-#define idu_disable()		IDU_SET_COMMAND(0, IDU_DISABLE)
-
-#define idu_irq_assert(irq)	IDU_SET_COMMAND((irq), IDU_IRQ_ASSERT)
-#define idu_irq_clear(irq)	IDU_SET_COMMAND((irq), IDU_IRQ_CLEAR)
-
-/* IDU Interrupt Mode - Destination Encoding */
-#define IDU_IRQ_MOD_DISABLE		0x00
-#define IDU_IRQ_MOD_ROUND_RECP		0x01
-#define IDU_IRQ_MOD_TCPU_FIRSTRECP	0x02
-#define IDU_IRQ_MOD_TCPU_ALLRECP	0x03
-
-/* IDU Interrupt Mode  - Triggering Mode */
-#define IDU_IRQ_MODE_LEVEL_TRIG		0x00
-#define IDU_IRQ_MODE_PULSE_TRIG		0x01
-
-#define IDU_IRQ_MODE_PARAM(dest_mode, trig_mode)   \
-	(((trig_mode & 0x01) << 15) | (dest_mode & 0xFF))
-
-struct idu_irq_config {
-	uint8_t irq;
-	uint8_t dest_mode;
-	uint8_t trig_mode;
-};
-
-struct idu_irq_status {
-	uint8_t irq;
-	bool enabled;
-	bool status;
-	bool ack;
-	bool pend;
-	uint8_t next_rr;
-};
-
-extern void idu_irq_set_tgtcpu(uint8_t irq, uint32_t mask);
-extern void idu_irq_set_mode(uint8_t irq, uint8_t dest_mode, uint8_t trig_mode);
-
-extern void iss_model_init_smp(unsigned int cpu);
-extern void iss_model_init_early_smp(void);
-
-#endif	/* CONFIG_SMP */
-
-#endif
diff --git a/arch/arc/plat-arcfpga/smp.c b/arch/arc/plat-arcfpga/smp.c
deleted file mode 100644
index 64797ba..0000000
--- a/arch/arc/plat-arcfpga/smp.c
+++ /dev/null
@@ -1,186 +0,0 @@
-/*
- * ARC700 Simulation-only Extensions for SMP
- *
- * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- *  Vineet Gupta    - 2012 : split off arch common and plat specific SMP
- *  Rajeshwar Ranga - 2007 : Interrupt Distribution Unit API's
- */
-
-#include <linux/smp.h>
-#include <linux/irq.h>
-#include <plat/smp.h>
-
-#define IDU_INTERRUPT_0 16
-
-static char smp_cpuinfo_buf[128];
-
-/*
- *-------------------------------------------------------------------
- * Platform specific callbacks expected by arch SMP code
- *-------------------------------------------------------------------
- */
-
-/*
- * Master kick starting another CPU
- */
-static void iss_model_smp_wakeup_cpu(int cpu, unsigned long pc)
-{
-	/* setup the start PC */
-	write_aux_reg(ARC_AUX_XTL_REG_PARAM, pc);
-
-	/* Trigger WRITE_PC cmd for this cpu */
-	write_aux_reg(ARC_AUX_XTL_REG_CMD,
-			(ARC_XTL_CMD_WRITE_PC | (cpu << 8)));
-
-	/* Take the cpu out of Halt */
-	write_aux_reg(ARC_AUX_XTL_REG_CMD,
-			(ARC_XTL_CMD_CLEAR_HALT | (cpu << 8)));
-
-}
-
-static inline int get_hw_config_num_irq(void)
-{
-	uint32_t val = read_aux_reg(ARC_REG_VECBASE_BCR);
-
-	switch (val & 0x03) {
-	case 0:
-		return 16;
-	case 1:
-		return 32;
-	case 2:
-		return 8;
-	default:
-		return 0;
-	}
-
-	return 0;
-}
-
-/*
- * Any SMP specific init any CPU does when it comes up.
- * Here we setup the CPU to enable Inter-Processor-Interrupts
- * Called for each CPU
- * -Master      : init_IRQ()
- * -Other(s)    : start_kernel_secondary()
- */
-void iss_model_init_smp(unsigned int cpu)
-{
-	/* Check if CPU is configured for more than 16 interrupts */
-	if (NR_IRQS <= 16 || get_hw_config_num_irq() <= 16)
-		panic("[arcfpga] IRQ system can't support IDU IPI\n");
-
-	idu_disable();
-
-	/****************************************************************
-	 * IDU provides a set of Common IRQs, each of which can be dynamically
-	 * attached to (1|many|all) CPUs.
-	 * The Common IRQs [0-15] are mapped as CPU pvt [16-31]
-	 *
-	 * Here we use a simple 1:1 mapping:
-	 * A CPU 'x' is wired to Common IRQ 'x'.
-	 * So an IDU ASSERT on IRQ 'x' will trigger Interupt on CPU 'x', which
-	 * makes up for our simple IPI plumbing.
-	 *
-	 * TBD: Have a dedicated multicast IRQ for sending IPIs to all CPUs
-	 *      w/o having to do one-at-a-time
-	 ******************************************************************/
-
-	/*
-	 * Claim an IRQ which would trigger IPI on this CPU.
-	 * In IDU parlance it involves setting up a cpu bitmask for the IRQ
-	 * The bitmap here contains only 1 CPU (self).
-	 */
-	idu_irq_set_tgtcpu(cpu, 0x1 << cpu);
-
-	/* Set the IRQ destination to use the bitmask above */
-	idu_irq_set_mode(cpu, 7, /* XXX: IDU_IRQ_MOD_TCPU_ALLRECP: ISS bug */
-			 IDU_IRQ_MODE_PULSE_TRIG);
-
-	idu_enable();
-
-	/* Attach the arch-common IPI ISR to our IDU IRQ */
-	smp_ipi_irq_setup(cpu, IDU_INTERRUPT_0 + cpu);
-}
-
-static void iss_model_ipi_send(int cpu)
-{
-	idu_irq_assert(cpu);
-}
-
-static void iss_model_ipi_clear(int irq)
-{
-	idu_irq_clear(IDU_INTERRUPT_0 + smp_processor_id());
-}
-
-void iss_model_init_early_smp(void)
-{
-#define IS_AVAIL1(var, str)    ((var) ? str : "")
-
-	struct bcr_mp mp;
-
-	READ_BCR(ARC_REG_MP_BCR, mp);
-
-	sprintf(smp_cpuinfo_buf, "Extn [ISS-SMP]: v%d, arch(%d) %s %s %s\n",
-		mp.ver, mp.mp_arch, IS_AVAIL1(mp.scu, "SCU"),
-		IS_AVAIL1(mp.idu, "IDU"), IS_AVAIL1(mp.sdu, "SDU"));
-
-	plat_smp_ops.info = smp_cpuinfo_buf;
-
-	plat_smp_ops.cpu_kick = iss_model_smp_wakeup_cpu;
-	plat_smp_ops.ipi_send = iss_model_ipi_send;
-	plat_smp_ops.ipi_clear = iss_model_ipi_clear;
-}
-
-/*
- *-------------------------------------------------------------------
- * Low level Platform IPI Providers
- *-------------------------------------------------------------------
- */
-
-/* Set the Mode for the Common IRQ */
-void idu_irq_set_mode(uint8_t irq, uint8_t dest_mode, uint8_t trig_mode)
-{
-	uint32_t par = IDU_IRQ_MODE_PARAM(dest_mode, trig_mode);
-
-	IDU_SET_PARAM(par);
-	IDU_SET_COMMAND(irq, IDU_IRQ_WMODE);
-}
-
-/* Set the target cpu Bitmask for Common IRQ */
-void idu_irq_set_tgtcpu(uint8_t irq, uint32_t mask)
-{
-	IDU_SET_PARAM(mask);
-	IDU_SET_COMMAND(irq, IDU_IRQ_WBITMASK);
-}
-
-/* Get the Interrupt Acknowledged status for IRQ (as CPU Bitmask) */
-bool idu_irq_get_ack(uint8_t irq)
-{
-	uint32_t val;
-
-	IDU_SET_COMMAND(irq, IDU_IRQ_ACK);
-	val = IDU_GET_PARAM();
-
-	return val & (1 << irq);
-}
-
-/*
- * Get the Interrupt Pending status for IRQ (as CPU Bitmask)
- * -Pending means CPU has not yet noticed the IRQ (e.g. disabled)
- * -After Interrupt has been taken, the IPI expcitily needs to be
- *  cleared, to be acknowledged.
- */
-bool idu_irq_get_pend(uint8_t irq)
-{
-	uint32_t val;
-
-	IDU_SET_COMMAND(irq, IDU_IRQ_PEND);
-	val = IDU_GET_PARAM();
-
-	return val & (1 << irq);
-}
diff --git a/arch/arc/plat-axs10x/Kconfig b/arch/arc/plat-axs10x/Kconfig
new file mode 100644
index 0000000..d475f9d
--- /dev/null
+++ b/arch/arc/plat-axs10x/Kconfig
@@ -0,0 +1,46 @@
+#
+# Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com)
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+#
+
+menuconfig ARC_PLAT_AXS10X
+	bool "Synopsys ARC AXS10x Software Development Platforms"
+	select DW_APB_ICTL
+	select GPIO_DWAPB
+	select OF_GPIO
+	select GENERIC_IRQ_CHIP
+	select ARCH_REQUIRE_GPIOLIB
+	help
+	  Support for the ARC AXS10x Software Development Platforms.
+
+	  The AXS10x Platforms consist of a mainboard with peripherals,
+	  on which several daughter cards can be placed. The daughter cards
+	  typically contain a CPU and memory.
+
+if ARC_PLAT_AXS10X
+
+config AXS101
+	depends on ISA_ARCOMPACT
+	bool "AXS101 with AXC001 CPU Card (ARC 770D/EM6/AS221)"
+	help
+	  This adds support for the 770D/EM6/AS221 CPU Card. Only the ARC
+	  770D is supported in Linux.
+
+	  The AXS101 Platform consists of an AXS10x mainboard with
+	  this daughtercard. Please use the axs101.dts device tree
+	  with this configuration.
+
+config AXS103
+	bool "AXS103 with AXC003 CPU Card (ARC HS38x)"
+	depends on ISA_ARCV2
+	help
+	  This adds support for the HS38x CPU Card.
+
+	  The AXS103 Platform consists of an AXS10x mainboard with
+	  this daughtercard. Please use the axs103.dts device tree
+	  with this configuration.
+
+endif
diff --git a/arch/arc/plat-axs10x/Makefile b/arch/arc/plat-axs10x/Makefile
new file mode 100644
index 0000000..d4748f2
--- /dev/null
+++ b/arch/arc/plat-axs10x/Makefile
@@ -0,0 +1,9 @@
+#
+# Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com)
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+#
+
+obj-$(CONFIG_ARC_PLAT_AXS10X) += axs10x.o
diff --git a/arch/arc/plat-axs10x/axs10x.c b/arch/arc/plat-axs10x/axs10x.c
new file mode 100644
index 0000000..99f7da5
--- /dev/null
+++ b/arch/arc/plat-axs10x/axs10x.c
@@ -0,0 +1,484 @@
+/*
+ * AXS101/AXS103 Software Development Platform
+ *
+ * Copyright (C) 2013-15 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/of_platform.h>
+
+#include <asm/asm-offsets.h>
+#include <asm/clk.h>
+#include <asm/io.h>
+#include <asm/mach_desc.h>
+#include <asm/mcip.h>
+
+#define AXS_MB_CGU		0xE0010000
+#define AXS_MB_CREG		0xE0011000
+
+#define CREG_MB_IRQ_MUX		(AXS_MB_CREG + 0x214)
+#define CREG_MB_SW_RESET	(AXS_MB_CREG + 0x220)
+#define CREG_MB_VER		(AXS_MB_CREG + 0x230)
+#define CREG_MB_CONFIG		(AXS_MB_CREG + 0x234)
+
+#define AXC001_CREG		0xF0001000
+#define AXC001_GPIO_INTC	0xF0003000
+
+static void __init axs10x_enable_gpio_intc_wire(void)
+{
+	/*
+	 * Peripherals on CPU Card and Mother Board are wired to cpu intc via
+	 * intermediate DW APB GPIO blocks (mainly for debouncing)
+	 *
+	 *         ---------------------
+	 *        |  snps,arc700-intc |
+	 *        ---------------------
+	 *          | #7          | #15
+	 * -------------------   -------------------
+	 * | snps,dw-apb-gpio |  | snps,dw-apb-gpio |
+	 * -------------------   -------------------
+	 *        |                         |
+	 *        |                 [ Debug UART on cpu card ]
+	 *        |
+	 * ------------------------
+	 * | snps,dw-apb-intc (MB)|
+	 * ------------------------
+	 *  |      |       |      |
+	 * [eth] [uart]        [... other perip on Main Board]
+	 *
+	 * Current implementation of "irq-dw-apb-ictl" driver doesn't work well
+	 * with stacked INTCs. In particular problem happens if its master INTC
+	 * not yet instantiated. See discussion here -
+	 * https://lkml.org/lkml/2015/3/4/755
+	 *
+	 * So setup the first gpio block as a passive pass thru and hide it from
+	 * DT hardware topology - connect MB intc directly to cpu intc
+	 * The GPIO "wire" needs to be init nevertheless (here)
+	 *
+	 * One side adv is that peripheral interrupt handling avoids one nested
+	 * intc ISR hop
+	 */
+#define GPIO_INTEN		(AXC001_GPIO_INTC + 0x30)
+#define GPIO_INTMASK		(AXC001_GPIO_INTC + 0x34)
+#define GPIO_INTTYPE_LEVEL	(AXC001_GPIO_INTC + 0x38)
+#define GPIO_INT_POLARITY	(AXC001_GPIO_INTC + 0x3c)
+#define MB_TO_GPIO_IRQ		12
+
+	iowrite32(~(1 << MB_TO_GPIO_IRQ), (void __iomem *) GPIO_INTMASK);
+	iowrite32(0, (void __iomem *) GPIO_INTTYPE_LEVEL);
+	iowrite32(~0, (void __iomem *) GPIO_INT_POLARITY);
+	iowrite32(1 << MB_TO_GPIO_IRQ, (void __iomem *) GPIO_INTEN);
+}
+
+static inline void __init
+write_cgu_reg(uint32_t value, void __iomem *reg, void __iomem *lock_reg)
+{
+	unsigned int loops = 128 * 1024, ctr;
+
+	iowrite32(value, reg);
+
+	ctr = loops;
+	while (((ioread32(lock_reg) & 1) == 1) && ctr--) /* wait for unlock */
+		cpu_relax();
+
+	ctr = loops;
+	while (((ioread32(lock_reg) & 1) == 0) && ctr--) /* wait for re-lock */
+		cpu_relax();
+}
+
+static void __init axs10x_print_board_ver(unsigned int creg, const char *str)
+{
+	union ver {
+		struct {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+			unsigned int pad:11, y:12, m:4, d:5;
+#else
+			unsigned int d:5, m:4, y:12, pad:11;
+#endif
+		};
+		unsigned int val;
+	} board;
+
+	board.val = ioread32((void __iomem *)creg);
+	pr_info("AXS: %s FPGA Date: %u-%u-%u\n", str, board.d, board.m,
+		board.y);
+}
+
+static void __init axs10x_early_init(void)
+{
+	int mb_rev;
+	char mb[32];
+
+	/* Determine motherboard version */
+	if (ioread32((void __iomem *) CREG_MB_CONFIG) & (1 << 28))
+		mb_rev = 3;	/* HT-3 (rev3.0) */
+	else
+		mb_rev = 2;	/* HT-2 (rev2.0) */
+
+	axs10x_enable_gpio_intc_wire();
+
+	scnprintf(mb, 32, "MainBoard v%d", mb_rev);
+	axs10x_print_board_ver(CREG_MB_VER, mb);
+}
+
+#ifdef CONFIG_AXS101
+
+#define CREG_CPU_ADDR_770	(AXC001_CREG + 0x20)
+#define CREG_CPU_ADDR_TUNN	(AXC001_CREG + 0x60)
+#define CREG_CPU_ADDR_770_UPD	(AXC001_CREG + 0x34)
+#define CREG_CPU_ADDR_TUNN_UPD	(AXC001_CREG + 0x74)
+
+#define CREG_CPU_ARC770_IRQ_MUX	(AXC001_CREG + 0x114)
+#define CREG_CPU_GPIO_UART_MUX	(AXC001_CREG + 0x120)
+
+/*
+ * Set up System Memory Map for ARC cpu / peripherals controllers
+ *
+ * Each AXI master has a 4GB memory map specified as 16 apertures of 256MB, each
+ * of which maps to a corresponding 256MB aperture in Target slave memory map.
+ *
+ * e.g. ARC cpu AXI Master's aperture 8 (0x8000_0000) is mapped to aperture 0
+ * (0x0000_0000) of DDR Port 0 (slave #1)
+ *
+ * Access from cpu to MB controllers such as GMAC is setup using AXI Tunnel:
+ * which has master/slaves on both ends.
+ * e.g. aperture 14 (0xE000_0000) of ARC cpu is mapped to aperture 14
+ * (0xE000_0000) of CPU Card AXI Tunnel slave (slave #3) which is mapped to
+ * MB AXI Tunnel Master, which also has a mem map setup
+ *
+ * In the reverse direction, MB AXI Masters (e.g. GMAC) mem map is setup
+ * to map to MB AXI Tunnel slave which connects to CPU Card AXI Tunnel Master
+ */
+struct aperture {
+	unsigned int slave_sel:4, slave_off:4, pad:24;
+};
+
+/* CPU Card target slaves */
+#define AXC001_SLV_NONE			0
+#define AXC001_SLV_DDR_PORT0		1
+#define AXC001_SLV_SRAM			2
+#define AXC001_SLV_AXI_TUNNEL		3
+#define AXC001_SLV_AXI2APB		6
+#define AXC001_SLV_DDR_PORT1		7
+
+/* MB AXI Target slaves */
+#define AXS_MB_SLV_NONE			0
+#define AXS_MB_SLV_AXI_TUNNEL_CPU	1
+#define AXS_MB_SLV_AXI_TUNNEL_HAPS	2
+#define AXS_MB_SLV_SRAM			3
+#define AXS_MB_SLV_CONTROL		4
+
+/* MB AXI masters */
+#define AXS_MB_MST_TUNNEL_CPU		0
+#define AXS_MB_MST_USB_OHCI		10
+
+/*
+ * memmap for ARC core on CPU Card
+ */
+static const struct aperture axc001_memmap[16] = {
+	{AXC001_SLV_AXI_TUNNEL,		0x0},
+	{AXC001_SLV_AXI_TUNNEL,		0x1},
+	{AXC001_SLV_SRAM,		0x0}, /* 0x2000_0000: Local SRAM */
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_DDR_PORT0,		0x0}, /* 0x8000_0000: DDR   0..256M */
+	{AXC001_SLV_DDR_PORT0,		0x1}, /* 0x9000_0000: DDR 256..512M */
+	{AXC001_SLV_DDR_PORT0,		0x2},
+	{AXC001_SLV_DDR_PORT0,		0x3},
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_AXI_TUNNEL,		0xD},
+	{AXC001_SLV_AXI_TUNNEL,		0xE}, /* MB: CREG, CGU... */
+	{AXC001_SLV_AXI2APB,		0x0}, /* CPU Card local CREG, CGU... */
+};
+
+/*
+ * memmap for CPU Card AXI Tunnel Master (for access by MB controllers)
+ * GMAC (MB) -> MB AXI Tunnel slave -> CPU Card AXI Tunnel Master -> DDR
+ */
+static const struct aperture axc001_axi_tunnel_memmap[16] = {
+	{AXC001_SLV_AXI_TUNNEL,		0x0},
+	{AXC001_SLV_AXI_TUNNEL,		0x1},
+	{AXC001_SLV_SRAM,		0x0},
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_DDR_PORT1,		0x0},
+	{AXC001_SLV_DDR_PORT1,		0x1},
+	{AXC001_SLV_DDR_PORT1,		0x2},
+	{AXC001_SLV_DDR_PORT1,		0x3},
+	{AXC001_SLV_NONE,		0x0},
+	{AXC001_SLV_AXI_TUNNEL,		0xD},
+	{AXC001_SLV_AXI_TUNNEL,		0xE},
+	{AXC001_SLV_AXI2APB,		0x0},
+};
+
+/*
+ * memmap for MB AXI Masters
+ * Same mem map for all perip controllers as well as MB AXI Tunnel Master
+ */
+static const struct aperture axs_mb_memmap[16] = {
+	{AXS_MB_SLV_SRAM,		0x0},
+	{AXS_MB_SLV_SRAM,		0x0},
+	{AXS_MB_SLV_NONE,		0x0},
+	{AXS_MB_SLV_NONE,		0x0},
+	{AXS_MB_SLV_NONE,		0x0},
+	{AXS_MB_SLV_NONE,		0x0},
+	{AXS_MB_SLV_NONE,		0x0},
+	{AXS_MB_SLV_NONE,		0x0},
+	{AXS_MB_SLV_AXI_TUNNEL_CPU,	0x8},	/* DDR on CPU Card */
+	{AXS_MB_SLV_AXI_TUNNEL_CPU,	0x9},	/* DDR on CPU Card */
+	{AXS_MB_SLV_AXI_TUNNEL_CPU,	0xA},
+	{AXS_MB_SLV_AXI_TUNNEL_CPU,	0xB},
+	{AXS_MB_SLV_NONE,		0x0},
+	{AXS_MB_SLV_AXI_TUNNEL_HAPS,	0xD},
+	{AXS_MB_SLV_CONTROL,		0x0},	/* MB Local CREG, CGU... */
+	{AXS_MB_SLV_AXI_TUNNEL_CPU,	0xF},
+};
+
+static noinline void __init
+axs101_set_memmap(void __iomem *base, const struct aperture map[16])
+{
+	unsigned int slave_select, slave_offset;
+	int i;
+
+	slave_select = slave_offset = 0;
+	for (i = 0; i < 8; i++) {
+		slave_select |= map[i].slave_sel << (i << 2);
+		slave_offset |= map[i].slave_off << (i << 2);
+	}
+
+	iowrite32(slave_select, base + 0x0);	/* SLV0 */
+	iowrite32(slave_offset, base + 0x8);	/* OFFSET0 */
+
+	slave_select = slave_offset = 0;
+	for (i = 0; i < 8; i++) {
+		slave_select |= map[i+8].slave_sel << (i << 2);
+		slave_offset |= map[i+8].slave_off << (i << 2);
+	}
+
+	iowrite32(slave_select, base + 0x4);	/* SLV1 */
+	iowrite32(slave_offset, base + 0xC);	/* OFFSET1 */
+}
+
+static void __init axs101_early_init(void)
+{
+	int i;
+
+	/* ARC 770D memory view */
+	axs101_set_memmap((void __iomem *) CREG_CPU_ADDR_770, axc001_memmap);
+	iowrite32(1, (void __iomem *) CREG_CPU_ADDR_770_UPD);
+
+	/* AXI tunnel memory map (incoming traffic from MB into CPU Card */
+	axs101_set_memmap((void __iomem *) CREG_CPU_ADDR_TUNN,
+			      axc001_axi_tunnel_memmap);
+	iowrite32(1, (void __iomem *) CREG_CPU_ADDR_TUNN_UPD);
+
+	/* MB peripherals memory map */
+	for (i = AXS_MB_MST_TUNNEL_CPU; i <= AXS_MB_MST_USB_OHCI; i++)
+		axs101_set_memmap((void __iomem *) AXS_MB_CREG + (i << 4),
+				      axs_mb_memmap);
+
+	iowrite32(0x3ff, (void __iomem *) AXS_MB_CREG + 0x100); /* Update */
+
+	/* GPIO pins 18 and 19 are used as UART rx and tx, respectively. */
+	iowrite32(0x01, (void __iomem *) CREG_CPU_GPIO_UART_MUX);
+
+	/* Set up the MB interrupt system: mux interrupts to GPIO7) */
+	iowrite32(0x01, (void __iomem *) CREG_MB_IRQ_MUX);
+
+	/* reset ethernet and ULPI interfaces */
+	iowrite32(0x18, (void __iomem *) CREG_MB_SW_RESET);
+
+	/* map GPIO 14:10 to ARC 9:5 (IRQ mux change for MB v2 onwards) */
+	iowrite32(0x52, (void __iomem *) CREG_CPU_ARC770_IRQ_MUX);
+
+	axs10x_early_init();
+}
+
+#endif	/* CONFIG_AXS101 */
+
+#ifdef CONFIG_AXS103
+
+#define AXC003_CGU	0xF0000000
+#define AXC003_CREG	0xF0001000
+#define AXC003_MST_AXI_TUNNEL	0
+#define AXC003_MST_HS38		1
+
+#define CREG_CPU_AXI_M0_IRQ_MUX	(AXC003_CREG + 0x440)
+#define CREG_CPU_GPIO_UART_MUX	(AXC003_CREG + 0x480)
+#define CREG_CPU_TUN_IO_CTRL	(AXC003_CREG + 0x494)
+
+
+union pll_reg {
+	struct {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+		unsigned int pad:17, noupd:1, bypass:1, edge:1, high:6, low:6;
+#else
+		unsigned int low:6, high:6, edge:1, bypass:1, noupd:1, pad:17;
+#endif
+	};
+	unsigned int val;
+};
+
+static unsigned int __init axs103_get_freq(void)
+{
+	union pll_reg idiv, fbdiv, odiv;
+	unsigned int f = 33333333;
+
+	idiv.val = ioread32((void __iomem *)AXC003_CGU + 0x80 + 0);
+	fbdiv.val = ioread32((void __iomem *)AXC003_CGU + 0x80 + 4);
+	odiv.val = ioread32((void __iomem *)AXC003_CGU + 0x80 + 8);
+
+	if (idiv.bypass != 1)
+		f = f / (idiv.low + idiv.high);
+
+	if (fbdiv.bypass != 1)
+		f = f * (fbdiv.low + fbdiv.high);
+
+	if (odiv.bypass != 1)
+		f = f / (odiv.low + odiv.high);
+
+	f = (f + 500000) / 1000000; /* Rounding */
+	return f;
+}
+
+static inline unsigned int __init encode_div(unsigned int id, int upd)
+{
+	union pll_reg div;
+
+	div.val = 0;
+
+	div.noupd = !upd;
+	div.bypass = id == 1 ? 1 : 0;
+	div.edge = (id%2 == 0) ? 0 : 1;  /* 0 = rising */
+	div.low = (id%2 == 0) ? id >> 1 : (id >> 1)+1;
+	div.high = id >> 1;
+
+	return div.val;
+}
+
+noinline static void __init
+axs103_set_freq(unsigned int id, unsigned int fd, unsigned int od)
+{
+	write_cgu_reg(encode_div(id, 0),
+		      (void __iomem *)AXC003_CGU + 0x80 + 0,
+		      (void __iomem *)AXC003_CGU + 0x110);
+
+	write_cgu_reg(encode_div(fd, 0),
+		      (void __iomem *)AXC003_CGU + 0x80 + 4,
+		      (void __iomem *)AXC003_CGU + 0x110);
+
+	write_cgu_reg(encode_div(od, 1),
+		      (void __iomem *)AXC003_CGU + 0x80 + 8,
+		      (void __iomem *)AXC003_CGU + 0x110);
+}
+
+static void __init axs103_early_init(void)
+{
+	switch (arc_get_core_freq()/1000000) {
+	case 33:
+		axs103_set_freq(1, 1, 1);
+		break;
+	case 50:
+		axs103_set_freq(1, 30, 20);
+		break;
+	case 75:
+		axs103_set_freq(2, 45, 10);
+		break;
+	case 90:
+		axs103_set_freq(2, 54, 10);
+		break;
+	case 100:
+		axs103_set_freq(1, 30, 10);
+		break;
+	case 125:
+		axs103_set_freq(2, 45,  6);
+		break;
+	default:
+		/*
+		 * In this case, core_frequency derived from
+		 * DT "clock-frequency" might not match with board value.
+		 * Hence update it to match the board value.
+		 */
+		arc_set_core_freq(axs103_get_freq() * 1000000);
+		break;
+	}
+
+	pr_info("Freq is %dMHz\n", axs103_get_freq());
+
+	/* Memory maps already config in pre-bootloader */
+
+	/* set GPIO mux to UART */
+	iowrite32(0x01, (void __iomem *) CREG_CPU_GPIO_UART_MUX);
+
+	iowrite32((0x00100000U | 0x000C0000U | 0x00003322U),
+		  (void __iomem *) CREG_CPU_TUN_IO_CTRL);
+
+	/* Set up the AXS_MB interrupt system.*/
+	iowrite32(12, (void __iomem *) (CREG_CPU_AXI_M0_IRQ_MUX
+					 + (AXC003_MST_HS38 << 2)));
+
+	/* connect ICTL - Main Board with GPIO line */
+	iowrite32(0x01, (void __iomem *) CREG_MB_IRQ_MUX);
+
+	axs10x_print_board_ver(AXC003_CREG + 4088, "AXC003 CPU Card");
+
+	axs10x_early_init();
+
+#ifdef CONFIG_ARC_MCIP
+	/* No Hardware init, but filling the smp ops callbacks */
+	mcip_init_early_smp();
+#endif
+}
+#endif
+
+#ifdef CONFIG_AXS101
+
+static const char *axs101_compat[] __initconst = {
+	"snps,axs101",
+	NULL,
+};
+
+MACHINE_START(AXS101, "axs101")
+	.dt_compat	= axs101_compat,
+	.init_early	= axs101_early_init,
+MACHINE_END
+
+#endif	/* CONFIG_AXS101 */
+
+#ifdef CONFIG_AXS103
+
+static const char *axs103_compat[] __initconst = {
+	"snps,axs103",
+	NULL,
+};
+
+MACHINE_START(AXS103, "axs103")
+	.dt_compat	= axs103_compat,
+	.init_early	= axs103_early_init,
+#ifdef CONFIG_ARC_MCIP
+	.init_smp	= mcip_init_smp,
+#endif
+MACHINE_END
+
+/*
+ * For the VDK OS-kit, to get the offset to pid and command fields
+ */
+char coware_swa_pid_offset[TASK_PID];
+char coware_swa_comm_offset[TASK_COMM];
+
+#endif	/* CONFIG_AXS103 */
diff --git a/arch/arc/plat-sim/Kconfig b/arch/arc/plat-sim/Kconfig
new file mode 100644
index 0000000..18e39fc
--- /dev/null
+++ b/arch/arc/plat-sim/Kconfig
@@ -0,0 +1,14 @@
+#
+# Copyright (C) 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+#
+
+menuconfig ARC_PLAT_SIM
+	bool "ARC nSIM based simulation virtual platforms"
+	select ARC_HAS_COH_CACHES if SMP
+	help
+	  Support for nSIM based ARC simulation platforms
+	  This includes the standalone nSIM (uart only) vs. System C OSCI VP
diff --git a/arch/arc/plat-arcfpga/Makefile b/arch/arc/plat-sim/Makefile
similarity index 75%
rename from arch/arc/plat-arcfpga/Makefile
rename to arch/arc/plat-sim/Makefile
index 66fd0ec..00b1a95 100644
--- a/arch/arc/plat-arcfpga/Makefile
+++ b/arch/arc/plat-sim/Makefile
@@ -6,7 +6,4 @@
 # published by the Free Software Foundation.
 #
 
-KBUILD_CFLAGS	+= -Iarch/arc/plat-arcfpga/include
-
 obj-y := platform.o
-obj-$(CONFIG_ISS_SMP_EXTN)		+= smp.o
diff --git a/arch/arc/plat-arcfpga/platform.c b/arch/arc/plat-sim/platform.c
similarity index 70%
rename from arch/arc/plat-arcfpga/platform.c
rename to arch/arc/plat-sim/platform.c
index afc8825..d9e35b4 100644
--- a/arch/arc/plat-arcfpga/platform.c
+++ b/arch/arc/plat-sim/platform.c
@@ -1,5 +1,5 @@
 /*
- * ARC FPGA Platform support code
+ * ARC simulation Platform support code
  *
  * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com)
  *
@@ -10,7 +10,7 @@
 
 #include <linux/init.h>
 #include <asm/mach_desc.h>
-#include <plat/smp.h>
+#include <asm/mcip.h>
 
 /*----------------------- Machine Descriptions ------------------------------
  *
@@ -20,26 +20,18 @@
  * callback set, by matching the DT compatible name.
  */
 
-static const char *legacy_fpga_compat[] __initconst = {
-	"snps,arc-angel4",
-	"snps,arc-ml509",
-	NULL,
-};
-
-MACHINE_START(LEGACY_FPGA, "legacy_fpga")
-	.dt_compat	= legacy_fpga_compat,
-#ifdef CONFIG_ISS_SMP_EXTN
-	.init_early	= iss_model_init_early_smp,
-	.init_smp	= iss_model_init_smp,
-#endif
-MACHINE_END
-
 static const char *simulation_compat[] __initconst = {
 	"snps,nsim",
+	"snps,nsim_hs",
 	"snps,nsimosci",
+	"snps,nsimosci_hs",
 	NULL,
 };
 
 MACHINE_START(SIMULATION, "simulation")
 	.dt_compat	= simulation_compat,
+#ifdef CONFIG_ARC_MCIP
+	.init_early	= mcip_init_early_smp,
+	.init_smp	= mcip_init_smp,
+#endif
 MACHINE_END
diff --git a/arch/arm/boot/compressed/libfdt_env.h b/arch/arm/boot/compressed/libfdt_env.h
index 1f4e718..17ae0f3 100644
--- a/arch/arm/boot/compressed/libfdt_env.h
+++ b/arch/arm/boot/compressed/libfdt_env.h
@@ -5,6 +5,10 @@
 #include <linux/string.h>
 #include <asm/byteorder.h>
 
+typedef __be16 fdt16_t;
+typedef __be32 fdt32_t;
+typedef __be64 fdt64_t;
+
 #define fdt16_to_cpu(x)		be16_to_cpu(x)
 #define cpu_to_fdt16(x)		cpu_to_be16(x)
 #define fdt32_to_cpu(x)		be32_to_cpu(x)
diff --git a/arch/arm/boot/dts/armada-370-xp.dtsi b/arch/arm/boot/dts/armada-370-xp.dtsi
index 7f0252c..a718866 100644
--- a/arch/arm/boot/dts/armada-370-xp.dtsi
+++ b/arch/arm/boot/dts/armada-370-xp.dtsi
@@ -268,7 +268,6 @@
 			};
 
 			eth0: ethernet@70000 {
-				compatible = "marvell,armada-370-neta";
 				reg = <0x70000 0x4000>;
 				interrupts = <8>;
 				clocks = <&gateclk 4>;
@@ -284,7 +283,6 @@
 			};
 
 			eth1: ethernet@74000 {
-				compatible = "marvell,armada-370-neta";
 				reg = <0x74000 0x4000>;
 				interrupts = <10>;
 				clocks = <&gateclk 3>;
diff --git a/arch/arm/boot/dts/armada-370.dtsi b/arch/arm/boot/dts/armada-370.dtsi
index 3f036bd..53a1a5a 100644
--- a/arch/arm/boot/dts/armada-370.dtsi
+++ b/arch/arm/boot/dts/armada-370.dtsi
@@ -311,6 +311,14 @@
 					dmacap,memset;
 				};
 			};
+
+			ethernet@70000 {
+				compatible = "marvell,armada-370-neta";
+			};
+
+			ethernet@74000 {
+				compatible = "marvell,armada-370-neta";
+			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/armada-xp-mv78260.dtsi b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
index 8479fdc..c5fdc99 100644
--- a/arch/arm/boot/dts/armada-xp-mv78260.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
@@ -318,7 +318,7 @@
 			};
 
 			eth3: ethernet@34000 {
-				compatible = "marvell,armada-370-neta";
+				compatible = "marvell,armada-xp-neta";
 				reg = <0x34000 0x4000>;
 				interrupts = <14>;
 				clocks = <&gateclk 1>;
diff --git a/arch/arm/boot/dts/armada-xp-mv78460.dtsi b/arch/arm/boot/dts/armada-xp-mv78460.dtsi
index 661d54c..0e24f1a 100644
--- a/arch/arm/boot/dts/armada-xp-mv78460.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78460.dtsi
@@ -356,7 +356,7 @@
 			};
 
 			eth3: ethernet@34000 {
-				compatible = "marvell,armada-370-neta";
+				compatible = "marvell,armada-xp-neta";
 				reg = <0x34000 0x4000>;
 				interrupts = <14>;
 				clocks = <&gateclk 1>;
diff --git a/arch/arm/boot/dts/armada-xp.dtsi b/arch/arm/boot/dts/armada-xp.dtsi
index e78ce4a..3de9b76 100644
--- a/arch/arm/boot/dts/armada-xp.dtsi
+++ b/arch/arm/boot/dts/armada-xp.dtsi
@@ -185,7 +185,7 @@
 			};
 
 			eth2: ethernet@30000 {
-				compatible = "marvell,armada-370-neta";
+				compatible = "marvell,armada-xp-neta";
 				reg = <0x30000 0x4000>;
 				interrupts = <12>;
 				clocks = <&gateclk 2>;
@@ -228,6 +228,14 @@
 				};
 			};
 
+			ethernet@70000 {
+				compatible = "marvell,armada-xp-neta";
+			};
+
+			ethernet@74000 {
+				compatible = "marvell,armada-xp-neta";
+			};
+
 			xor@f0900 {
 				compatible = "marvell,orion-xor";
 				reg = <0xF0900 0x100
@@ -297,7 +305,7 @@
 	spi0_pins: spi0-pins {
 		marvell,pins = "mpp36", "mpp37",
 			       "mpp38", "mpp39";
-		marvell,function = "spi";
+		marvell,function = "spi0";
 	};
 
 	uart2_pins: uart2-pins {
diff --git a/arch/arm/boot/dts/at91sam9g45.dtsi b/arch/arm/boot/dts/at91sam9g45.dtsi
index d260ba7..18177f5 100644
--- a/arch/arm/boot/dts/at91sam9g45.dtsi
+++ b/arch/arm/boot/dts/at91sam9g45.dtsi
@@ -1148,7 +1148,7 @@
 			usb2: gadget@fff78000 {
 				#address-cells = <1>;
 				#size-cells = <0>;
-				compatible = "atmel,at91sam9rl-udc";
+				compatible = "atmel,at91sam9g45-udc";
 				reg = <0x00600000 0x80000
 				       0xfff78000 0x400>;
 				interrupts = <27 IRQ_TYPE_LEVEL_HIGH 0>;
diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi
index 7521bdf..b6c8df8 100644
--- a/arch/arm/boot/dts/at91sam9x5.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5.dtsi
@@ -1108,7 +1108,7 @@
 			usb2: gadget@f803c000 {
 				#address-cells = <1>;
 				#size-cells = <0>;
-				compatible = "atmel,at91sam9rl-udc";
+				compatible = "atmel,at91sam9g45-udc";
 				reg = <0x00500000 0x80000
 				       0xf803c000 0x400>;
 				interrupts = <23 IRQ_TYPE_LEVEL_HIGH 0>;
diff --git a/arch/arm/boot/dts/atlas7.dtsi b/arch/arm/boot/dts/atlas7.dtsi
index a753178..5dfd3a4 100644
--- a/arch/arm/boot/dts/atlas7.dtsi
+++ b/arch/arm/boot/dts/atlas7.dtsi
@@ -38,6 +38,21 @@
 		};
 	};
 
+	clocks {
+		xinw {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <32768>;
+			clock-output-names = "xinw";
+		};
+		xin {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <26000000>;
+			clock-output-names = "xin";
+		};
+	};
+
 	noc {
 		compatible = "simple-bus";
 		#address-cells = <1>;
diff --git a/arch/arm/boot/dts/sama5d3.dtsi b/arch/arm/boot/dts/sama5d3.dtsi
index 5ab7548..9e2444b 100644
--- a/arch/arm/boot/dts/sama5d3.dtsi
+++ b/arch/arm/boot/dts/sama5d3.dtsi
@@ -1321,7 +1321,7 @@
 		usb0: gadget@00500000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
-			compatible = "atmel,at91sam9rl-udc";
+			compatible = "atmel,sama5d3-udc";
 			reg = <0x00500000 0x100000
 			       0xf8030000 0x4000>;
 			interrupts = <33 IRQ_TYPE_LEVEL_HIGH 2>;
diff --git a/arch/arm/boot/dts/sama5d4.dtsi b/arch/arm/boot/dts/sama5d4.dtsi
index 653a1f8..3ee22ee 100644
--- a/arch/arm/boot/dts/sama5d4.dtsi
+++ b/arch/arm/boot/dts/sama5d4.dtsi
@@ -127,7 +127,7 @@
 		usb0: gadget@00400000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
-			compatible = "atmel,at91sam9rl-udc";
+			compatible = "atmel,sama5d3-udc";
 			reg = <0x00400000 0x100000
 			       0xfc02c000 0x4000>;
 			interrupts = <47 IRQ_TYPE_LEVEL_HIGH 2>;
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index fd6a6d2..6d83a1b 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -169,6 +169,7 @@
 CONFIG_MTD_M25P80=y
 CONFIG_MTD_NAND=y
 CONFIG_MTD_NAND_ATMEL=y
+CONFIG_MTD_NAND_BRCMNAND=y
 CONFIG_MTD_NAND_DAVINCI=y
 CONFIG_MTD_SPI_NOR=y
 CONFIG_MTD_UBI=y
diff --git a/arch/arm/include/asm/xen/hypervisor.h b/arch/arm/include/asm/xen/hypervisor.h
index 1317ee4..04ff8e7 100644
--- a/arch/arm/include/asm/xen/hypervisor.h
+++ b/arch/arm/include/asm/xen/hypervisor.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_ARM_XEN_HYPERVISOR_H
 #define _ASM_ARM_XEN_HYPERVISOR_H
 
+#include <linux/init.h>
+
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
 
@@ -18,4 +20,10 @@
 
 extern struct dma_map_ops *xen_dma_ops;
 
+#ifdef CONFIG_XEN
+void __init xen_early_init(void);
+#else
+static inline void xen_early_init(void) { return; }
+#endif
+
 #endif /* _ASM_ARM_XEN_HYPERVISOR_H */
diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h
index 0b579b2..1bee8ca 100644
--- a/arch/arm/include/asm/xen/page.h
+++ b/arch/arm/include/asm/xen/page.h
@@ -12,7 +12,6 @@
 #include <xen/interface/grant_table.h>
 
 #define phys_to_machine_mapping_valid(pfn) (1)
-#define mfn_to_virt(m)			(__va(mfn_to_pfn(m) << PAGE_SHIFT))
 
 #define pte_mfn	    pte_pfn
 #define mfn_pte	    pfn_pte
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 7335fc6..cb4fb1e 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -15,6 +15,8 @@
  *  that causes it to save wrong values...  Be aware!
  */
 
+#include <linux/init.h>
+
 #include <asm/assembler.h>
 #include <asm/memory.h>
 #include <asm/glue-df.h>
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index e6d8c76..36c18b7 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -46,6 +46,7 @@
 #include <asm/cacheflush.h>
 #include <asm/cachetype.h>
 #include <asm/tlbflush.h>
+#include <asm/xen/hypervisor.h>
 
 #include <asm/prom.h>
 #include <asm/mach/arch.h>
@@ -972,6 +973,7 @@
 
 	arm_dt_init_cpu_maps();
 	psci_init();
+	xen_early_init();
 #ifdef CONFIG_SMP
 	if (is_smp()) {
 		if (!mdesc->smp_init || !mdesc->smp_init()) {
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index 1e18476..e24df77 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -369,7 +369,7 @@
 		return;
 	}
 
-	sram_pool = dev_get_gen_pool(&pdev->dev);
+	sram_pool = gen_pool_get(&pdev->dev);
 	if (!sram_pool) {
 		pr_warn("%s: sram pool unavailable!\n", __func__);
 		return;
diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig
index e9184fe..0ac9e4b3 100644
--- a/arch/arm/mach-bcm/Kconfig
+++ b/arch/arm/mach-bcm/Kconfig
@@ -19,7 +19,6 @@
 	select ARCH_REQUIRE_GPIOLIB
 	select ARM_AMBA
 	select PINCTRL
-	select MTD_NAND_BRCMNAND
 	help
 	  This enables support for systems based on Broadcom IPROC architected SoCs.
 	  The IPROC complex contains one or more ARM CPUs along with common
diff --git a/arch/arm/mach-dove/include/mach/irqs.h b/arch/arm/mach-dove/include/mach/irqs.h
index 03d401d..3f29e6bc 100644
--- a/arch/arm/mach-dove/include/mach/irqs.h
+++ b/arch/arm/mach-dove/include/mach/irqs.h
@@ -14,73 +14,73 @@
 /*
  * Dove Low Interrupt Controller
  */
-#define IRQ_DOVE_BRIDGE		0
-#define IRQ_DOVE_H2C		1
-#define IRQ_DOVE_C2H		2
-#define IRQ_DOVE_NAND		3
-#define IRQ_DOVE_PDMA		4
-#define IRQ_DOVE_SPI1		5
-#define IRQ_DOVE_SPI0		6
-#define IRQ_DOVE_UART_0		7
-#define IRQ_DOVE_UART_1		8
-#define IRQ_DOVE_UART_2		9
-#define IRQ_DOVE_UART_3		10
-#define IRQ_DOVE_I2C		11
-#define IRQ_DOVE_GPIO_0_7	12
-#define IRQ_DOVE_GPIO_8_15	13
-#define IRQ_DOVE_GPIO_16_23	14
-#define IRQ_DOVE_PCIE0_ERR	15
-#define IRQ_DOVE_PCIE0		16
-#define IRQ_DOVE_PCIE1_ERR	17
-#define IRQ_DOVE_PCIE1		18
-#define IRQ_DOVE_I2S0		19
-#define IRQ_DOVE_I2S0_ERR	20
-#define IRQ_DOVE_I2S1		21
-#define IRQ_DOVE_I2S1_ERR	22
-#define IRQ_DOVE_USB_ERR	23
-#define IRQ_DOVE_USB0		24
-#define IRQ_DOVE_USB1		25
-#define IRQ_DOVE_GE00_RX	26
-#define IRQ_DOVE_GE00_TX	27
-#define IRQ_DOVE_GE00_MISC	28
-#define IRQ_DOVE_GE00_SUM	29
-#define IRQ_DOVE_GE00_ERR	30
-#define IRQ_DOVE_CRYPTO		31
+#define IRQ_DOVE_BRIDGE		(1 + 0)
+#define IRQ_DOVE_H2C		(1 + 1)
+#define IRQ_DOVE_C2H		(1 + 2)
+#define IRQ_DOVE_NAND		(1 + 3)
+#define IRQ_DOVE_PDMA		(1 + 4)
+#define IRQ_DOVE_SPI1		(1 + 5)
+#define IRQ_DOVE_SPI0		(1 + 6)
+#define IRQ_DOVE_UART_0		(1 + 7)
+#define IRQ_DOVE_UART_1		(1 + 8)
+#define IRQ_DOVE_UART_2		(1 + 9)
+#define IRQ_DOVE_UART_3		(1 + 10)
+#define IRQ_DOVE_I2C		(1 + 11)
+#define IRQ_DOVE_GPIO_0_7	(1 + 12)
+#define IRQ_DOVE_GPIO_8_15	(1 + 13)
+#define IRQ_DOVE_GPIO_16_23	(1 + 14)
+#define IRQ_DOVE_PCIE0_ERR	(1 + 15)
+#define IRQ_DOVE_PCIE0		(1 + 16)
+#define IRQ_DOVE_PCIE1_ERR	(1 + 17)
+#define IRQ_DOVE_PCIE1		(1 + 18)
+#define IRQ_DOVE_I2S0		(1 + 19)
+#define IRQ_DOVE_I2S0_ERR	(1 + 20)
+#define IRQ_DOVE_I2S1		(1 + 21)
+#define IRQ_DOVE_I2S1_ERR	(1 + 22)
+#define IRQ_DOVE_USB_ERR	(1 + 23)
+#define IRQ_DOVE_USB0		(1 + 24)
+#define IRQ_DOVE_USB1		(1 + 25)
+#define IRQ_DOVE_GE00_RX	(1 + 26)
+#define IRQ_DOVE_GE00_TX	(1 + 27)
+#define IRQ_DOVE_GE00_MISC	(1 + 28)
+#define IRQ_DOVE_GE00_SUM	(1 + 29)
+#define IRQ_DOVE_GE00_ERR	(1 + 30)
+#define IRQ_DOVE_CRYPTO		(1 + 31)
 
 /*
  * Dove High Interrupt Controller
  */
-#define IRQ_DOVE_AC97		32
-#define IRQ_DOVE_PMU		33
-#define IRQ_DOVE_CAM		34
-#define IRQ_DOVE_SDIO0		35
-#define IRQ_DOVE_SDIO1		36
-#define IRQ_DOVE_SDIO0_WAKEUP	37
-#define IRQ_DOVE_SDIO1_WAKEUP	38
-#define IRQ_DOVE_XOR_00		39
-#define IRQ_DOVE_XOR_01		40
-#define IRQ_DOVE_XOR0_ERR	41
-#define IRQ_DOVE_XOR_10		42
-#define IRQ_DOVE_XOR_11		43
-#define IRQ_DOVE_XOR1_ERR	44
-#define IRQ_DOVE_LCD_DCON	45
-#define IRQ_DOVE_LCD1		46
-#define IRQ_DOVE_LCD0		47
-#define IRQ_DOVE_GPU		48
-#define IRQ_DOVE_PERFORM_MNTR	49
-#define IRQ_DOVE_VPRO_DMA1	51
-#define IRQ_DOVE_SSP_TIMER	54
-#define IRQ_DOVE_SSP		55
-#define IRQ_DOVE_MC_L2_ERR	56
-#define IRQ_DOVE_CRYPTO_ERR	59
-#define IRQ_DOVE_GPIO_24_31	60
-#define IRQ_DOVE_HIGH_GPIO	61
-#define IRQ_DOVE_SATA		62
+#define IRQ_DOVE_AC97		(1 + 32)
+#define IRQ_DOVE_PMU		(1 + 33)
+#define IRQ_DOVE_CAM		(1 + 34)
+#define IRQ_DOVE_SDIO0		(1 + 35)
+#define IRQ_DOVE_SDIO1		(1 + 36)
+#define IRQ_DOVE_SDIO0_WAKEUP	(1 + 37)
+#define IRQ_DOVE_SDIO1_WAKEUP	(1 + 38)
+#define IRQ_DOVE_XOR_00		(1 + 39)
+#define IRQ_DOVE_XOR_01		(1 + 40)
+#define IRQ_DOVE_XOR0_ERR	(1 + 41)
+#define IRQ_DOVE_XOR_10		(1 + 42)
+#define IRQ_DOVE_XOR_11		(1 + 43)
+#define IRQ_DOVE_XOR1_ERR	(1 + 44)
+#define IRQ_DOVE_LCD_DCON	(1 + 45)
+#define IRQ_DOVE_LCD1		(1 + 46)
+#define IRQ_DOVE_LCD0		(1 + 47)
+#define IRQ_DOVE_GPU		(1 + 48)
+#define IRQ_DOVE_PERFORM_MNTR	(1 + 49)
+#define IRQ_DOVE_VPRO_DMA1	(1 + 51)
+#define IRQ_DOVE_SSP_TIMER	(1 + 54)
+#define IRQ_DOVE_SSP		(1 + 55)
+#define IRQ_DOVE_MC_L2_ERR	(1 + 56)
+#define IRQ_DOVE_CRYPTO_ERR	(1 + 59)
+#define IRQ_DOVE_GPIO_24_31	(1 + 60)
+#define IRQ_DOVE_HIGH_GPIO	(1 + 61)
+#define IRQ_DOVE_SATA		(1 + 62)
 
 /*
  * DOVE General Purpose Pins
  */
-#define IRQ_DOVE_GPIO_START	64
+#define IRQ_DOVE_GPIO_START	65
 #define NR_GPIO_IRQS		64
 
 /*
diff --git a/arch/arm/mach-dove/irq.c b/arch/arm/mach-dove/irq.c
index 4a5a7ae..df0223f 100644
--- a/arch/arm/mach-dove/irq.c
+++ b/arch/arm/mach-dove/irq.c
@@ -126,14 +126,14 @@
 	stat = readl_relaxed(dove_irq_base + IRQ_CAUSE_LOW_OFF);
 	stat &= readl_relaxed(dove_irq_base + IRQ_MASK_LOW_OFF);
 	if (stat) {
-		unsigned int hwirq = __fls(stat);
+		unsigned int hwirq = 1 + __fls(stat);
 		handle_IRQ(hwirq, regs);
 		return;
 	}
 	stat = readl_relaxed(dove_irq_base + IRQ_CAUSE_HIGH_OFF);
 	stat &= readl_relaxed(dove_irq_base + IRQ_MASK_HIGH_OFF);
 	if (stat) {
-		unsigned int hwirq = 32 + __fls(stat);
+		unsigned int hwirq = 33 + __fls(stat);
 		handle_IRQ(hwirq, regs);
 		return;
 	}
@@ -144,8 +144,8 @@
 {
 	int i;
 
-	orion_irq_init(0, IRQ_VIRT_BASE + IRQ_MASK_LOW_OFF);
-	orion_irq_init(32, IRQ_VIRT_BASE + IRQ_MASK_HIGH_OFF);
+	orion_irq_init(1, IRQ_VIRT_BASE + IRQ_MASK_LOW_OFF);
+	orion_irq_init(33, IRQ_VIRT_BASE + IRQ_MASK_HIGH_OFF);
 
 #ifdef CONFIG_MULTI_IRQ_HANDLER
 	set_handle_irq(dove_legacy_handle_irq);
diff --git a/arch/arm/mach-exynos/exynos.c b/arch/arm/mach-exynos/exynos.c
index 4bd8b76..5f8ddcd 100644
--- a/arch/arm/mach-exynos/exynos.c
+++ b/arch/arm/mach-exynos/exynos.c
@@ -224,6 +224,25 @@
 	exynos_map_pmu();
 }
 
+static const struct of_device_id exynos_cpufreq_matches[] = {
+	{ .compatible = "samsung,exynos4210", .data = "cpufreq-dt" },
+	{ /* sentinel */ }
+};
+
+static void __init exynos_cpufreq_init(void)
+{
+	struct device_node *root = of_find_node_by_path("/");
+	const struct of_device_id *match;
+
+	match = of_match_node(exynos_cpufreq_matches, root);
+	if (!match) {
+		platform_device_register_simple("exynos-cpufreq", -1, NULL, 0);
+		return;
+	}
+
+	platform_device_register_simple(match->data, -1, NULL, 0);
+}
+
 static void __init exynos_dt_machine_init(void)
 {
 	/*
@@ -246,7 +265,7 @@
 	    of_machine_is_compatible("samsung,exynos5250"))
 		platform_device_register(&exynos_cpuidle);
 
-	platform_device_register_simple("exynos-cpufreq", -1, NULL, 0);
+	exynos_cpufreq_init();
 
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
diff --git a/arch/arm/mach-imx/pm-imx5.c b/arch/arm/mach-imx/pm-imx5.c
index 0309ccd..1885676 100644
--- a/arch/arm/mach-imx/pm-imx5.c
+++ b/arch/arm/mach-imx/pm-imx5.c
@@ -297,7 +297,7 @@
 		goto put_node;
 	}
 
-	ocram_pool = dev_get_gen_pool(&pdev->dev);
+	ocram_pool = gen_pool_get(&pdev->dev);
 	if (!ocram_pool) {
 		pr_warn("%s: ocram pool unavailable!\n", __func__);
 		ret = -ENODEV;
diff --git a/arch/arm/mach-imx/pm-imx6.c b/arch/arm/mach-imx/pm-imx6.c
index b01650d..93ecf55 100644
--- a/arch/arm/mach-imx/pm-imx6.c
+++ b/arch/arm/mach-imx/pm-imx6.c
@@ -451,7 +451,7 @@
 		goto put_node;
 	}
 
-	ocram_pool = dev_get_gen_pool(&pdev->dev);
+	ocram_pool = gen_pool_get(&pdev->dev);
 	if (!ocram_pool) {
 		pr_warn("%s: ocram pool unavailable!\n", __func__);
 		ret = -ENODEV;
diff --git a/arch/arm/mach-lpc32xx/irq.c b/arch/arm/mach-lpc32xx/irq.c
index 9ecb8f9..d4f7dc8 100644
--- a/arch/arm/mach-lpc32xx/irq.c
+++ b/arch/arm/mach-lpc32xx/irq.c
@@ -283,25 +283,25 @@
 	case IRQ_TYPE_EDGE_RISING:
 		/* Rising edge sensitive */
 		__lpc32xx_set_irq_type(d->hwirq, 1, 1);
-		__irq_set_handler_locked(d->hwirq, handle_edge_irq);
+		__irq_set_handler_locked(d->irq, handle_edge_irq);
 		break;
 
 	case IRQ_TYPE_EDGE_FALLING:
 		/* Falling edge sensitive */
 		__lpc32xx_set_irq_type(d->hwirq, 0, 1);
-		__irq_set_handler_locked(d->hwirq, handle_edge_irq);
+		__irq_set_handler_locked(d->irq, handle_edge_irq);
 		break;
 
 	case IRQ_TYPE_LEVEL_LOW:
 		/* Low level sensitive */
 		__lpc32xx_set_irq_type(d->hwirq, 0, 0);
-		__irq_set_handler_locked(d->hwirq, handle_level_irq);
+		__irq_set_handler_locked(d->irq, handle_level_irq);
 		break;
 
 	case IRQ_TYPE_LEVEL_HIGH:
 		/* High level sensitive */
 		__lpc32xx_set_irq_type(d->hwirq, 1, 0);
-		__irq_set_handler_locked(d->hwirq, handle_level_irq);
+		__irq_set_handler_locked(d->irq, handle_level_irq);
 		break;
 
 	/* Other modes are not supported */
diff --git a/arch/arm/mach-mvebu/headsmp-a9.S b/arch/arm/mach-mvebu/headsmp-a9.S
index 48e4c4b..b093a19 100644
--- a/arch/arm/mach-mvebu/headsmp-a9.S
+++ b/arch/arm/mach-mvebu/headsmp-a9.S
@@ -13,12 +13,9 @@
  */
 
 #include <linux/linkage.h>
-#include <linux/init.h>
 
 #include <asm/assembler.h>
 
-	__CPUINIT
-
 ENTRY(mvebu_cortex_a9_secondary_startup)
 ARM_BE8(setend	be)
 	bl	armada_38x_scu_power_up
diff --git a/arch/arm/mach-mvebu/platsmp-a9.c b/arch/arm/mach-mvebu/platsmp-a9.c
index df0a9cc..3d50004 100644
--- a/arch/arm/mach-mvebu/platsmp-a9.c
+++ b/arch/arm/mach-mvebu/platsmp-a9.c
@@ -24,7 +24,7 @@
 
 extern void mvebu_cortex_a9_secondary_startup(void);
 
-static int __cpuinit mvebu_cortex_a9_boot_secondary(unsigned int cpu,
+static int mvebu_cortex_a9_boot_secondary(unsigned int cpu,
 						    struct task_struct *idle)
 {
 	int ret, hw_cpu;
diff --git a/arch/arm/mach-mvebu/pm-board.c b/arch/arm/mach-mvebu/pm-board.c
index 6dfd4ab..301ab38 100644
--- a/arch/arm/mach-mvebu/pm-board.c
+++ b/arch/arm/mach-mvebu/pm-board.c
@@ -43,6 +43,9 @@
 	for (i = 0; i < ARMADA_XP_GP_PIC_NR_GPIOS; i++)
 		ackcmd |= BIT(pic_raw_gpios[i]);
 
+	srcmd = cpu_to_le32(srcmd);
+	ackcmd = cpu_to_le32(ackcmd);
+
 	/*
 	 * Wait a while, the PIC needs quite a bit of time between the
 	 * two GPIO commands.
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index f1a68c6..903c85b 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -274,8 +274,5 @@
 
 smsc911x-$(CONFIG_SMSC911X)		:= gpmc-smsc911x.o
 obj-y					+= $(smsc911x-m) $(smsc911x-y)
-ifneq ($(CONFIG_HWSPINLOCK_OMAP),)
-obj-y					+= hwspinlock.o
-endif
 
 obj-y					+= common-board-devices.o twl-common.o dss-common.o
diff --git a/arch/arm/mach-omap2/hwspinlock.c b/arch/arm/mach-omap2/hwspinlock.c
deleted file mode 100644
index ef175ac..0000000
--- a/arch/arm/mach-omap2/hwspinlock.c
+++ /dev/null
@@ -1,60 +0,0 @@
-/*
- * OMAP hardware spinlock device initialization
- *
- * Copyright (C) 2010 Texas Instruments Incorporated - http://www.ti.com
- *
- * Contact: Simon Que <sque@ti.com>
- *          Hari Kanigeri <h-kanigeri2@ti.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/err.h>
-#include <linux/hwspinlock.h>
-
-#include "soc.h"
-#include "omap_hwmod.h"
-#include "omap_device.h"
-
-static struct hwspinlock_pdata omap_hwspinlock_pdata __initdata = {
-	.base_id = 0,
-};
-
-static int __init hwspinlocks_init(void)
-{
-	int retval = 0;
-	struct omap_hwmod *oh;
-	struct platform_device *pdev;
-	const char *oh_name = "spinlock";
-	const char *dev_name = "omap_hwspinlock";
-
-	/*
-	 * Hwmod lookup will fail in case our platform doesn't support the
-	 * hardware spinlock module, so it is safe to run this initcall
-	 * on all omaps
-	 */
-	oh = omap_hwmod_lookup(oh_name);
-	if (oh == NULL)
-		return -EINVAL;
-
-	pdev = omap_device_build(dev_name, 0, oh, &omap_hwspinlock_pdata,
-				sizeof(struct hwspinlock_pdata));
-	if (IS_ERR(pdev)) {
-		pr_err("Can't build omap_device for %s:%s\n", dev_name,
-								oh_name);
-		retval = PTR_ERR(pdev);
-	}
-
-	return retval;
-}
-/* early board code might need to reserve specific hwspinlock instances */
-omap_postcore_initcall(hwspinlocks_init);
diff --git a/arch/arm/mach-rockchip/platsmp.c b/arch/arm/mach-rockchip/platsmp.c
index 2e6ab67..8fcec1c 100644
--- a/arch/arm/mach-rockchip/platsmp.c
+++ b/arch/arm/mach-rockchip/platsmp.c
@@ -119,8 +119,7 @@
  * Handling of CPU cores
  */
 
-static int __cpuinit rockchip_boot_secondary(unsigned int cpu,
-					     struct task_struct *idle)
+static int rockchip_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
 	int ret;
 
diff --git a/arch/arm/mach-socfpga/pm.c b/arch/arm/mach-socfpga/pm.c
index 1ed89fc..6a4199f 100644
--- a/arch/arm/mach-socfpga/pm.c
+++ b/arch/arm/mach-socfpga/pm.c
@@ -56,7 +56,7 @@
 		goto put_node;
 	}
 
-	ocram_pool = dev_get_gen_pool(&pdev->dev);
+	ocram_pool = gen_pool_get(&pdev->dev);
 	if (!ocram_pool) {
 		pr_warn("%s: ocram pool unavailable!\n", __func__);
 		ret = -ENODEV;
diff --git a/arch/arm/mach-vexpress/spc.c b/arch/arm/mach-vexpress/spc.c
index f61158c..5766ce2 100644
--- a/arch/arm/mach-vexpress/spc.c
+++ b/arch/arm/mach-vexpress/spc.c
@@ -589,4 +589,4 @@
 	platform_device_register_simple("vexpress-spc-cpufreq", -1, NULL, 0);
 	return 0;
 }
-module_init(ve_spc_clk_init);
+device_initcall(ve_spc_clk_init);
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 7d0f070..6c09cc4 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -24,6 +24,7 @@
 #include <linux/cpuidle.h>
 #include <linux/cpufreq.h>
 #include <linux/cpu.h>
+#include <linux/console.h>
 
 #include <linux/mm.h>
 
@@ -51,7 +52,9 @@
 int xen_platform_pci_unplug = XEN_UNPLUG_ALL;
 EXPORT_SYMBOL_GPL(xen_platform_pci_unplug);
 
-static __read_mostly int xen_events_irq = -1;
+static __read_mostly unsigned int xen_events_irq;
+
+static __initdata struct device_node *xen_node;
 
 int xen_remap_domain_mfn_array(struct vm_area_struct *vma,
 			       unsigned long addr,
@@ -150,40 +153,28 @@
  * documentation of the Xen Device Tree format.
  */
 #define GRANT_TABLE_PHYSADDR 0
-static int __init xen_guest_init(void)
+void __init xen_early_init(void)
 {
-	struct xen_add_to_physmap xatp;
-	static struct shared_info *shared_info_page = 0;
-	struct device_node *node;
 	int len;
 	const char *s = NULL;
 	const char *version = NULL;
 	const char *xen_prefix = "xen,xen-";
-	struct resource res;
-	phys_addr_t grant_frames;
 
-	node = of_find_compatible_node(NULL, NULL, "xen,xen");
-	if (!node) {
+	xen_node = of_find_compatible_node(NULL, NULL, "xen,xen");
+	if (!xen_node) {
 		pr_debug("No Xen support\n");
-		return 0;
+		return;
 	}
-	s = of_get_property(node, "compatible", &len);
+	s = of_get_property(xen_node, "compatible", &len);
 	if (strlen(xen_prefix) + 3  < len &&
 			!strncmp(xen_prefix, s, strlen(xen_prefix)))
 		version = s + strlen(xen_prefix);
 	if (version == NULL) {
 		pr_debug("Xen version not found\n");
-		return 0;
+		return;
 	}
-	if (of_address_to_resource(node, GRANT_TABLE_PHYSADDR, &res))
-		return 0;
-	grant_frames = res.start;
-	xen_events_irq = irq_of_parse_and_map(node, 0);
-	pr_info("Xen %s support found, events_irq=%d gnttab_frame=%pa\n",
-			version, xen_events_irq, &grant_frames);
 
-	if (xen_events_irq < 0)
-		return -ENODEV;
+	pr_info("Xen %s support found\n", version);
 
 	xen_domain_type = XEN_HVM_DOMAIN;
 
@@ -194,9 +185,34 @@
 	else
 		xen_start_info->flags &= ~(SIF_INITDOMAIN|SIF_PRIVILEGED);
 
-	if (!shared_info_page)
-		shared_info_page = (struct shared_info *)
-			get_zeroed_page(GFP_KERNEL);
+	if (!console_set_on_cmdline && !xen_initial_domain())
+		add_preferred_console("hvc", 0, NULL);
+}
+
+static int __init xen_guest_init(void)
+{
+	struct xen_add_to_physmap xatp;
+	struct shared_info *shared_info_page = NULL;
+	struct resource res;
+	phys_addr_t grant_frames;
+
+	if (!xen_domain())
+		return 0;
+
+	if (of_address_to_resource(xen_node, GRANT_TABLE_PHYSADDR, &res)) {
+		pr_err("Xen grant table base address not found\n");
+		return -ENODEV;
+	}
+	grant_frames = res.start;
+
+	xen_events_irq = irq_of_parse_and_map(xen_node, 0);
+	if (!xen_events_irq) {
+		pr_err("Xen event channel interrupt not found\n");
+		return -ENODEV;
+	}
+
+	shared_info_page = (struct shared_info *)get_zeroed_page(GFP_KERNEL);
+
 	if (!shared_info_page) {
 		pr_err("not enough memory\n");
 		return -ENOMEM;
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index 4983250..03e75fe 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -15,10 +15,10 @@
 #include <xen/xen.h>
 #include <xen/interface/grant_table.h>
 #include <xen/interface/memory.h>
+#include <xen/page.h>
 #include <xen/swiotlb-xen.h>
 
 #include <asm/cacheflush.h>
-#include <asm/xen/page.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/interface.h>
 
diff --git a/arch/arm/xen/p2m.c b/arch/arm/xen/p2m.c
index cb7a14c..887596c 100644
--- a/arch/arm/xen/p2m.c
+++ b/arch/arm/xen/p2m.c
@@ -10,10 +10,10 @@
 
 #include <xen/xen.h>
 #include <xen/interface/memory.h>
+#include <xen/page.h>
 #include <xen/swiotlb-xen.h>
 
 #include <asm/cacheflush.h>
-#include <asm/xen/page.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/interface.h>
 
diff --git a/arch/arm64/boot/dts/apm/apm-storm.dtsi b/arch/arm64/boot/dts/apm/apm-storm.dtsi
index 0bb287c..0689c3f 100644
--- a/arch/arm64/boot/dts/apm/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm/apm-storm.dtsi
@@ -717,6 +717,19 @@
 			phy-names = "sata-phy";
 		};
 
+		sbgpio: sbgpio@17001000{
+			compatible = "apm,xgene-gpio-sb";
+			reg = <0x0 0x17001000 0x0 0x400>;
+			#gpio-cells = <2>;
+			gpio-controller;
+			interrupts = 	<0x0 0x28 0x1>,
+					<0x0 0x29 0x1>,
+					<0x0 0x2a 0x1>,
+					<0x0 0x2b 0x1>,
+					<0x0 0x2c 0x1>,
+					<0x0 0x2d 0x1>;
+		};
+
 		rtc: rtc@10510000 {
 			compatible = "apm,xgene-rtc";
 			reg = <0x0 0x10510000 0x0 0x400>;
diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
index 7ce589c..9047cab6 100644
--- a/arch/arm64/kernel/cpuidle.c
+++ b/arch/arm64/kernel/cpuidle.c
@@ -15,7 +15,7 @@
 #include <asm/cpuidle.h>
 #include <asm/cpu_ops.h>
 
-int arm_cpuidle_init(unsigned int cpu)
+int __init arm_cpuidle_init(unsigned int cpu)
 {
 	int ret = -EOPNOTSUPP;
 
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index e7d934d..7a1a5da 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -31,7 +31,6 @@
 #include <asm/current.h>
 #include <asm/debug-monitors.h>
 #include <asm/hw_breakpoint.h>
-#include <asm/kdebug.h>
 #include <asm/traps.h>
 #include <asm/cputype.h>
 #include <asm/system_misc.h>
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 702591f..b31e9a4 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -1318,7 +1318,7 @@
 	/* Don't bother with PPIs; they're already affine */
 	irq = platform_get_irq(pdev, 0);
 	if (irq >= 0 && irq_is_percpu(irq))
-		return 0;
+		goto out;
 
 	irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
 	if (!irqs)
@@ -1340,12 +1340,13 @@
 			if (arch_find_n_match_cpu_physical_id(dn, cpu, NULL))
 				break;
 
-		of_node_put(dn);
 		if (cpu >= nr_cpu_ids) {
 			pr_warn("Failed to find logical CPU for %s\n",
 				dn->name);
+			of_node_put(dn);
 			break;
 		}
+		of_node_put(dn);
 
 		irqs[i] = cpu;
 	}
@@ -1355,6 +1356,7 @@
 	else
 		kfree(irqs);
 
+out:
 	cpu_pmu->plat_device = pdev;
 	return 0;
 }
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index ffd3970..f3067d4 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -64,6 +64,7 @@
 #include <asm/psci.h>
 #include <asm/efi.h>
 #include <asm/virt.h>
+#include <asm/xen/hypervisor.h>
 
 unsigned long elf_hwcap __read_mostly;
 EXPORT_SYMBOL_GPL(elf_hwcap);
@@ -401,6 +402,7 @@
 	} else {
 		psci_acpi_init();
 	}
+	xen_early_init();
 
 	cpu_read_bootcpu_ops();
 #ifdef CONFIG_SMP
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 4b2121b..695801a 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -396,13 +396,13 @@
 {
 	u64 hwid = processor->arm_mpidr;
 
-	if (hwid & ~MPIDR_HWID_BITMASK || hwid == INVALID_HWID) {
-		pr_err("skipping CPU entry with invalid MPIDR 0x%llx\n", hwid);
+	if (!(processor->flags & ACPI_MADT_ENABLED)) {
+		pr_debug("skipping disabled CPU entry with 0x%llx MPIDR\n", hwid);
 		return;
 	}
 
-	if (!(processor->flags & ACPI_MADT_ENABLED)) {
-		pr_err("skipping disabled CPU entry with 0x%llx MPIDR\n", hwid);
+	if (hwid & ~MPIDR_HWID_BITMASK || hwid == INVALID_HWID) {
+		pr_err("skipping CPU entry with invalid MPIDR 0x%llx\n", hwid);
 		return;
 	}
 
@@ -693,7 +693,7 @@
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
 	if ((unsigned)ipinr < NR_IPI) {
-		trace_ipi_entry(ipi_types[ipinr]);
+		trace_ipi_entry_rcuidle(ipi_types[ipinr]);
 		__inc_irq_stat(cpu, ipi_irqs[ipinr]);
 	}
 
@@ -736,7 +736,7 @@
 	}
 
 	if ((unsigned)ipinr < NR_IPI)
-		trace_ipi_exit(ipi_types[ipinr]);
+		trace_ipi_exit_rcuidle(ipi_types[ipinr]);
 	set_irq_regs(old_regs);
 }
 
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index a12251c..566bc4c 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -335,7 +335,7 @@
 	if (call_undef_hook(regs) == 0)
 		return;
 
-	if (show_unhandled_signals_ratelimited() && unhandled_signal(current, SIGILL)) {
+	if (unhandled_signal(current, SIGILL) && show_unhandled_signals_ratelimited()) {
 		pr_info("%s[%d]: undefined instruction: pc=%p\n",
 			current->comm, task_pid_nr(current), pc);
 		dump_instr(KERN_INFO, regs);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index b1fc69c..94d98cd 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -115,7 +115,7 @@
 {
 	struct siginfo si;
 
-	if (show_unhandled_signals_ratelimited() && unhandled_signal(tsk, sig)) {
+	if (unhandled_signal(tsk, sig) && show_unhandled_signals_ratelimited()) {
 		pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n",
 			tsk->comm, task_pid_nr(tsk), fault_name(esr), sig,
 			addr, esr);
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index cccc4af..831ec53 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -33,13 +33,13 @@
 
 int pmd_huge(pmd_t pmd)
 {
-	return !(pmd_val(pmd) & PMD_TABLE_BIT);
+	return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
 }
 
 int pud_huge(pud_t pud)
 {
 #ifndef __PAGETABLE_PMD_FOLDED
-	return !(pud_val(pud) & PUD_TABLE_BIT);
+	return pud_val(pud) && !(pud_val(pud) & PUD_TABLE_BIT);
 #else
 	return 0;
 #endif
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 82d3435..a4ede4e 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -117,7 +117,7 @@
 	int i = 0;
 
 	do {
-		set_pmd(pmd, __pmd(addr | prot));
+		set_pmd(pmd, __pmd(addr | pgprot_val(prot)));
 		addr += PMD_SIZE;
 	} while (pmd++, i++, i < PTRS_PER_PMD);
 }
diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index de0a81a..98a26ce 100644
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -110,6 +110,10 @@
 /* Rd = Rn >> shift; signed */
 #define A64_ASR(sf, Rd, Rn, shift) A64_SBFM(sf, Rd, Rn, shift, (sf) ? 63 : 31)
 
+/* Zero extend */
+#define A64_UXTH(sf, Rd, Rn) A64_UBFM(sf, Rd, Rn, 0, 15)
+#define A64_UXTW(sf, Rd, Rn) A64_UBFM(sf, Rd, Rn, 0, 31)
+
 /* Move wide (immediate) */
 #define A64_MOVEW(sf, Rd, imm16, shift, type) \
 	aarch64_insn_gen_movewide(Rd, imm16, shift, \
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index dc6a484..c047598 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -113,9 +113,9 @@
 static inline int bpf2a64_offset(int bpf_to, int bpf_from,
 				 const struct jit_ctx *ctx)
 {
-	int to = ctx->offset[bpf_to + 1];
+	int to = ctx->offset[bpf_to];
 	/* -1 to account for the Branch instruction */
-	int from = ctx->offset[bpf_from + 1] - 1;
+	int from = ctx->offset[bpf_from] - 1;
 
 	return to - from;
 }
@@ -289,23 +289,41 @@
 	case BPF_ALU | BPF_END | BPF_FROM_BE:
 #ifdef CONFIG_CPU_BIG_ENDIAN
 		if (BPF_SRC(code) == BPF_FROM_BE)
-			break;
+			goto emit_bswap_uxt;
 #else /* !CONFIG_CPU_BIG_ENDIAN */
 		if (BPF_SRC(code) == BPF_FROM_LE)
-			break;
+			goto emit_bswap_uxt;
 #endif
 		switch (imm) {
 		case 16:
 			emit(A64_REV16(is64, dst, dst), ctx);
+			/* zero-extend 16 bits into 64 bits */
+			emit(A64_UXTH(is64, dst, dst), ctx);
 			break;
 		case 32:
 			emit(A64_REV32(is64, dst, dst), ctx);
+			/* upper 32 bits already cleared */
 			break;
 		case 64:
 			emit(A64_REV64(dst, dst), ctx);
 			break;
 		}
 		break;
+emit_bswap_uxt:
+		switch (imm) {
+		case 16:
+			/* zero-extend 16 bits into 64 bits */
+			emit(A64_UXTH(is64, dst, dst), ctx);
+			break;
+		case 32:
+			/* zero-extend 32 bits into 64 bits */
+			emit(A64_UXTW(is64, dst, dst), ctx);
+			break;
+		case 64:
+			/* nop */
+			break;
+		}
+		break;
 	/* dst = imm */
 	case BPF_ALU | BPF_MOV | BPF_K:
 	case BPF_ALU64 | BPF_MOV | BPF_K:
@@ -640,10 +658,11 @@
 		const struct bpf_insn *insn = &prog->insnsi[i];
 		int ret;
 
+		ret = build_insn(insn, ctx);
+
 		if (ctx->image == NULL)
 			ctx->offset[i] = ctx->idx;
 
-		ret = build_insn(insn, ctx);
 		if (ret > 0) {
 			i++;
 			continue;
diff --git a/arch/avr32/mach-at32ap/extint.c b/arch/avr32/mach-at32ap/extint.c
index cfb298d..2d48b6a 100644
--- a/arch/avr32/mach-at32ap/extint.c
+++ b/arch/avr32/mach-at32ap/extint.c
@@ -231,8 +231,7 @@
 		irq_set_chip_data(eic->first_irq + i, eic);
 	}
 
-	irq_set_chained_handler(int_irq, demux_eic_irq);
-	irq_set_handler_data(int_irq, eic);
+	irq_set_chained_handler_and_data(int_irq, demux_eic_irq, eic);
 
 	if (pdev->id == 0) {
 		nmi_eic = eic;
diff --git a/arch/blackfin/kernel/trace.c b/arch/blackfin/kernel/trace.c
index c36efa0..719dd79 100644
--- a/arch/blackfin/kernel/trace.c
+++ b/arch/blackfin/kernel/trace.c
@@ -136,7 +136,7 @@
 				struct file *file = vma->vm_file;
 
 				if (file) {
-					char *d_name = d_path(&file->f_path, _tmpbuf,
+					char *d_name = file_path(file, _tmpbuf,
 						      sizeof(_tmpbuf));
 					if (!IS_ERR(d_name))
 						name = d_name;
diff --git a/arch/cris/arch-v10/drivers/eeprom.c b/arch/cris/arch-v10/drivers/eeprom.c
index 5047a33..f679a19 100644
--- a/arch/cris/arch-v10/drivers/eeprom.c
+++ b/arch/cris/arch-v10/drivers/eeprom.c
@@ -848,5 +848,4 @@
     /* Write protect disabled */
   }
 }
-
-module_init(eeprom_init);
+device_initcall(eeprom_init);
diff --git a/arch/cris/arch-v32/mm/intmem.c b/arch/cris/arch-v32/mm/intmem.c
index 1b17d92..9ef5609 100644
--- a/arch/cris/arch-v32/mm/intmem.c
+++ b/arch/cris/arch-v32/mm/intmem.c
@@ -145,6 +145,5 @@
 		(unsigned long)intmem_virtual + MEM_INTMEM_START +
 		RESERVED_SIZE);
 }
-
-module_init(crisv32_intmem_init);
+device_initcall(crisv32_intmem_init);
 
diff --git a/arch/frv/mb93090-mb00/flash.c b/arch/frv/mb93090-mb00/flash.c
index c0e3707..e1cf802 100644
--- a/arch/frv/mb93090-mb00/flash.c
+++ b/arch/frv/mb93090-mb00/flash.c
@@ -9,7 +9,7 @@
  * 2 of the Licence, or (at your option) any later version.
  */
 
-#include <linux/init.h>
+#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/physmap.h>
diff --git a/arch/ia64/hp/sim/simscsi.c b/arch/ia64/hp/sim/simscsi.c
index 3a428f1..085047f 100644
--- a/arch/ia64/hp/sim/simscsi.c
+++ b/arch/ia64/hp/sim/simscsi.c
@@ -368,13 +368,4 @@
 	scsi_host_put(host);
 	return error;
 }
-
-static void __exit
-simscsi_exit(void)
-{
-	scsi_remove_host(host);
-	scsi_host_put(host);
-}
-
-module_init(simscsi_init);
-module_exit(simscsi_exit);
+device_initcall(simscsi_init);
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 7f30289..97e48b0 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -215,10 +215,6 @@
 	pmd_t *pmd;
 	pte_t *pte;
 
-	if (!PageReserved(page))
-		printk(KERN_ERR "put_kernel_page: page at 0x%p not in reserved memory\n",
-		       page_address(page));
-
 	pgd = pgd_offset_k(address);		/* note: this is NOT pgd_offset()! */
 
 	{
diff --git a/arch/ia64/mm/numa.c b/arch/ia64/mm/numa.c
index ea21d4c..aa19b7a 100644
--- a/arch/ia64/mm/numa.c
+++ b/arch/ia64/mm/numa.c
@@ -58,27 +58,22 @@
  * SPARSEMEM to allocate the SPARSEMEM sectionmap on the NUMA node where
  * the section resides.
  */
-int __meminit __early_pfn_to_nid(unsigned long pfn)
+int __meminit __early_pfn_to_nid(unsigned long pfn,
+					struct mminit_pfnnid_cache *state)
 {
 	int i, section = pfn >> PFN_SECTION_SHIFT, ssec, esec;
-	/*
-	 * NOTE: The following SMP-unsafe globals are only used early in boot
-	 * when the kernel is running single-threaded.
-	 */
-	static int __meminitdata last_ssec, last_esec;
-	static int __meminitdata last_nid;
 
-	if (section >= last_ssec && section < last_esec)
-		return last_nid;
+	if (section >= state->last_start && section < state->last_end)
+		return state->last_nid;
 
 	for (i = 0; i < num_node_memblks; i++) {
 		ssec = node_memblk[i].start_paddr >> PA_SECTION_SHIFT;
 		esec = (node_memblk[i].start_paddr + node_memblk[i].size +
 			((1L << PA_SECTION_SHIFT) - 1)) >> PA_SECTION_SHIFT;
 		if (section >= ssec && section < esec) {
-			last_ssec = ssec;
-			last_esec = esec;
-			last_nid = node_memblk[i].nid;
+			state->last_start = ssec;
+			state->last_end = esec;
+			state->last_nid = node_memblk[i].nid;
 			return node_memblk[i].nid;
 		}
 	}
diff --git a/arch/ia64/sn/kernel/mca.c b/arch/ia64/sn/kernel/mca.c
index 27793f7..5b799d4d 100644
--- a/arch/ia64/sn/kernel/mca.c
+++ b/arch/ia64/sn/kernel/mca.c
@@ -142,5 +142,4 @@
 		salinfo_platform_oemdata = &sn_salinfo_platform_oemdata;
 	return 0;
 }
-
-module_init(sn_salinfo_init)
+device_initcall(sn_salinfo_init);
diff --git a/arch/m68k/mac/psc.c b/arch/m68k/mac/psc.c
index 835fa04..272dde4 100644
--- a/arch/m68k/mac/psc.c
+++ b/arch/m68k/mac/psc.c
@@ -148,14 +148,10 @@
 
 void __init psc_register_interrupts(void)
 {
-	irq_set_chained_handler(IRQ_AUTO_3, psc_irq);
-	irq_set_handler_data(IRQ_AUTO_3, (void *)0x30);
-	irq_set_chained_handler(IRQ_AUTO_4, psc_irq);
-	irq_set_handler_data(IRQ_AUTO_4, (void *)0x40);
-	irq_set_chained_handler(IRQ_AUTO_5, psc_irq);
-	irq_set_handler_data(IRQ_AUTO_5, (void *)0x50);
-	irq_set_chained_handler(IRQ_AUTO_6, psc_irq);
-	irq_set_handler_data(IRQ_AUTO_6, (void *)0x60);
+	irq_set_chained_handler_and_data(IRQ_AUTO_3, psc_irq, (void *)0x30);
+	irq_set_chained_handler_and_data(IRQ_AUTO_4, psc_irq, (void *)0x40);
+	irq_set_chained_handler_and_data(IRQ_AUTO_5, psc_irq, (void *)0x50);
+	irq_set_chained_handler_and_data(IRQ_AUTO_6, psc_irq, (void *)0x60);
 }
 
 void psc_irq_enable(int irq) {
diff --git a/arch/mips/ath25/ar2315.c b/arch/mips/ath25/ar2315.c
index 8742e1c..ec9a371 100644
--- a/arch/mips/ath25/ar2315.c
+++ b/arch/mips/ath25/ar2315.c
@@ -161,8 +161,8 @@
 	irq = irq_create_mapping(domain, AR2315_MISC_IRQ_AHB);
 	setup_irq(irq, &ar2315_ahb_err_interrupt);
 
-	irq_set_chained_handler(AR2315_IRQ_MISC, ar2315_misc_irq_handler);
-	irq_set_handler_data(AR2315_IRQ_MISC, domain);
+	irq_set_chained_handler_and_data(AR2315_IRQ_MISC,
+					 ar2315_misc_irq_handler, domain);
 
 	ar2315_misc_irq_domain = domain;
 }
diff --git a/arch/mips/ath25/ar5312.c b/arch/mips/ath25/ar5312.c
index 094b938..e63e38f 100644
--- a/arch/mips/ath25/ar5312.c
+++ b/arch/mips/ath25/ar5312.c
@@ -156,8 +156,8 @@
 	irq = irq_create_mapping(domain, AR5312_MISC_IRQ_AHB_PROC);
 	setup_irq(irq, &ar5312_ahb_err_interrupt);
 
-	irq_set_chained_handler(AR5312_IRQ_MISC, ar5312_misc_irq_handler);
-	irq_set_handler_data(AR5312_IRQ_MISC, domain);
+	irq_set_chained_handler_and_data(AR5312_IRQ_MISC,
+					 ar5312_misc_irq_handler, domain);
 
 	ar5312_misc_irq_domain = domain;
 }
diff --git a/arch/mips/cavium-octeon/Makefile b/arch/mips/cavium-octeon/Makefile
index 69a8a8d..2a59265 100644
--- a/arch/mips/cavium-octeon/Makefile
+++ b/arch/mips/cavium-octeon/Makefile
@@ -9,9 +9,6 @@
 # Copyright (C) 2005-2009 Cavium Networks
 #
 
-CFLAGS_octeon-platform.o = -I$(src)/../../../scripts/dtc/libfdt
-CFLAGS_setup.o = -I$(src)/../../../scripts/dtc/libfdt
-
 obj-y := cpu.o setup.o octeon-platform.o octeon-irq.o csrc-octeon.o
 obj-y += dma-octeon.o
 obj-y += octeon-memcpy.o
diff --git a/arch/mips/mti-sead3/Makefile b/arch/mips/mti-sead3/Makefile
index ecd71db..2e52cbd 100644
--- a/arch/mips/mti-sead3/Makefile
+++ b/arch/mips/mti-sead3/Makefile
@@ -15,5 +15,3 @@
 obj-y				+= leds-sead3.o
 
 obj-$(CONFIG_EARLY_PRINTK)	+= sead3-console.o
-
-CFLAGS_sead3-setup.o = -I$(src)/../../../scripts/dtc/libfdt
diff --git a/arch/mips/pci/pci-ar2315.c b/arch/mips/pci/pci-ar2315.c
index dadb303..f8d0acb 100644
--- a/arch/mips/pci/pci-ar2315.c
+++ b/arch/mips/pci/pci-ar2315.c
@@ -384,8 +384,8 @@
 
 	apc->irq_ext = irq_create_mapping(apc->domain, AR2315_PCI_IRQ_EXT);
 
-	irq_set_chained_handler(apc->irq, ar2315_pci_irq_handler);
-	irq_set_handler_data(apc->irq, apc);
+	irq_set_chained_handler_and_data(apc->irq, ar2315_pci_irq_handler,
+					 apc);
 
 	/* Clear any pending Abort or external Interrupts
 	 * and enable interrupt processing */
diff --git a/arch/mips/ralink/irq.c b/arch/mips/ralink/irq.c
index da301e0..53707aa 100644
--- a/arch/mips/ralink/irq.c
+++ b/arch/mips/ralink/irq.c
@@ -184,8 +184,7 @@
 
 	rt_intc_w32(INTC_INT_GLOBAL, INTC_REG_ENABLE);
 
-	irq_set_chained_handler(irq, ralink_intc_irq_handler);
-	irq_set_handler_data(irq, domain);
+	irq_set_chained_handler_and_data(irq, ralink_intc_irq_handler, domain);
 
 	/* tell the kernel which irq is used for performance monitoring */
 	rt_perfcount_irq = irq_create_mapping(domain, 9);
diff --git a/arch/mn10300/kernel/irq.c b/arch/mn10300/kernel/irq.c
index 6ab3b73..480de70 100644
--- a/arch/mn10300/kernel/irq.c
+++ b/arch/mn10300/kernel/irq.c
@@ -320,11 +320,11 @@
 		if (irqd_is_per_cpu(data))
 			continue;
 
-		if (cpumask_test_cpu(self, &data->affinity) &&
+		if (cpumask_test_cpu(self, data->affinity) &&
 		    !cpumask_intersects(&irq_affinity[irq], cpu_online_mask)) {
 			int cpu_id;
 			cpu_id = cpumask_first(cpu_online_mask);
-			cpumask_set_cpu(cpu_id, &data->affinity);
+			cpumask_set_cpu(cpu_id, data->affinity);
 		}
 		/* We need to operate irq_affinity_online atomically. */
 		arch_local_cli_save(flags);
@@ -335,7 +335,7 @@
 			GxICR(irq) = x & GxICR_LEVEL;
 			tmp = GxICR(irq);
 
-			new = cpumask_any_and(&data->affinity,
+			new = cpumask_any_and(data->affinity,
 					      cpu_online_mask);
 			irq_affinity_online[irq] = new;
 
diff --git a/arch/mn10300/unit-asb2303/flash.c b/arch/mn10300/unit-asb2303/flash.c
index 17fe083..b03d873 100644
--- a/arch/mn10300/unit-asb2303/flash.c
+++ b/arch/mn10300/unit-asb2303/flash.c
@@ -96,5 +96,4 @@
 	platform_device_register(&asb2303_sysflash);
 	return 0;
 }
-
-module_init(asb2303_mtd_init);
+device_initcall(asb2303_mtd_init);
diff --git a/arch/nios2/kernel/time.c b/arch/nios2/kernel/time.c
index be186a7..9e3cc8a 100644
--- a/arch/nios2/kernel/time.c
+++ b/arch/nios2/kernel/time.c
@@ -19,7 +19,9 @@
 #include <linux/io.h>
 #include <linux/slab.h>
 
-#define ALTERA_TIMER_STATUS_REG		0
+#define ALTR_TIMER_COMPATIBLE		"altr,timer-1.0"
+
+#define ALTERA_TIMER_STATUS_REG	0
 #define ALTERA_TIMER_CONTROL_REG	4
 #define ALTERA_TIMER_PERIODL_REG	8
 #define ALTERA_TIMER_PERIODH_REG	12
@@ -304,7 +306,16 @@
 
 void __init time_init(void)
 {
+	struct device_node *np;
+	int count = 0;
+
+	for_each_compatible_node(np, NULL,  ALTR_TIMER_COMPATIBLE)
+		count++;
+
+	if (count < 2)
+		panic("%d timer is found, it needs 2 timers in system\n", count);
+
 	clocksource_of_init();
 }
 
-CLOCKSOURCE_OF_DECLARE(nios2_timer, "altr,timer-1.0", nios2_time_init);
+CLOCKSOURCE_OF_DECLARE(nios2_timer, ALTR_TIMER_COMPATIBLE, nios2_time_init);
diff --git a/arch/parisc/kernel/pdc_cons.c b/arch/parisc/kernel/pdc_cons.c
index d5cae55..10a5ae9 100644
--- a/arch/parisc/kernel/pdc_cons.c
+++ b/arch/parisc/kernel/pdc_cons.c
@@ -207,8 +207,7 @@
 
 	return 0;
 }
-
-module_init(pdc_console_tty_driver_init);
+device_initcall(pdc_console_tty_driver_init);
 
 static struct tty_driver * pdc_console_device (struct console *c, int *index)
 {
diff --git a/arch/parisc/kernel/perf.c b/arch/parisc/kernel/perf.c
index ba0c053..518f4f5 100644
--- a/arch/parisc/kernel/perf.c
+++ b/arch/parisc/kernel/perf.c
@@ -543,6 +543,7 @@
 
 	return 0;
 }
+device_initcall(perf_init);
 
 /*
  * perf_start_counters(void)
@@ -847,5 +848,3 @@
 	}
 printk("perf_rdr_write done\n");
 }
-
-module_init(perf_init);
diff --git a/arch/powerpc/boot/libfdt_env.h b/arch/powerpc/boot/libfdt_env.h
index 8dcd744..7e3789e 100644
--- a/arch/powerpc/boot/libfdt_env.h
+++ b/arch/powerpc/boot/libfdt_env.h
@@ -10,6 +10,10 @@
 typedef u64 uint64_t;
 typedef unsigned long uintptr_t;
 
+typedef __be16 fdt16_t;
+typedef __be32 fdt32_t;
+typedef __be64 fdt64_t;
+
 #define fdt16_to_cpu(x)		be16_to_cpu(x)
 #define cpu_to_fdt16(x)		cpu_to_be16(x)
 #define fdt32_to_cpu(x)		be32_to_cpu(x)
diff --git a/arch/powerpc/boot/of.h b/arch/powerpc/boot/of.h
index 5603320..53f8f27 100644
--- a/arch/powerpc/boot/of.h
+++ b/arch/powerpc/boot/of.h
@@ -21,7 +21,9 @@
 /* Console functions */
 void of_console_init(void);
 
+typedef u16			__be16;
 typedef u32			__be32;
+typedef u64			__be64;
 
 #ifdef __LITTLE_ENDIAN__
 #define cpu_to_be16(x) swab16(x)
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 87c7d14..12868b1 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -2,7 +2,6 @@
 # Makefile for the linux kernel.
 #
 
-CFLAGS_prom.o		= -I$(src)/../../../scripts/dtc/libfdt
 CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
 subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 56f4484..4392250 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -1124,4 +1124,4 @@
 	return PTR_ERR_OR_ZERO(pdev);
 }
 
-module_init(rtc_init);
+device_initcall(rtc_init);
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 1f614d7..bb0bd70 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -928,7 +928,7 @@
 	return 0;
 }
 #endif
-module_init(hugetlbpage_init);
+arch_initcall(hugetlbpage_init);
 
 void flush_dcache_icache_hugepage(struct page *page)
 {
diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c
index c9adbfb..fcbea4b 100644
--- a/arch/powerpc/platforms/83xx/suspend.c
+++ b/arch/powerpc/platforms/83xx/suspend.c
@@ -445,5 +445,4 @@
 {
 	return platform_driver_register(&pmc_driver);
 }
-
-module_init(pmc_init);
+device_initcall(pmc_init);
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 1ba6307..11634fa 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -166,7 +166,7 @@
 	mutex_lock(&d_inode(dir)->i_mutex);
 	list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_child) {
 		spin_lock(&dentry->d_lock);
-		if (!(d_unhashed(dentry)) && d_really_is_positive(dentry)) {
+		if (simple_positive(dentry)) {
 			dget_dlock(dentry);
 			__d_drop(dentry);
 			spin_unlock(&dentry->d_lock);
diff --git a/arch/powerpc/platforms/ps3/time.c b/arch/powerpc/platforms/ps3/time.c
index ce73ce8..791c614 100644
--- a/arch/powerpc/platforms/ps3/time.c
+++ b/arch/powerpc/platforms/ps3/time.c
@@ -92,5 +92,4 @@
 
 	return PTR_ERR_OR_ZERO(pdev);
 }
-
-module_init(ps3_rtc_init);
+device_initcall(ps3_rtc_init);
diff --git a/arch/powerpc/sysdev/fsl_lbc.c b/arch/powerpc/sysdev/fsl_lbc.c
index d631022..38138cf 100644
--- a/arch/powerpc/sysdev/fsl_lbc.c
+++ b/arch/powerpc/sysdev/fsl_lbc.c
@@ -407,4 +407,4 @@
 {
 	return platform_driver_register(&fsl_lbc_ctrl_driver);
 }
-module_init(fsl_lbc_init);
+subsys_initcall(fsl_lbc_init);
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index d3f896a..b2e5902 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -62,18 +62,13 @@
 	hypfs_last_dentry = dentry;
 }
 
-static inline int hypfs_positive(struct dentry *dentry)
-{
-	return d_really_is_positive(dentry) && !d_unhashed(dentry);
-}
-
 static void hypfs_remove(struct dentry *dentry)
 {
 	struct dentry *parent;
 
 	parent = dentry->d_parent;
 	mutex_lock(&d_inode(parent)->i_mutex);
-	if (hypfs_positive(dentry)) {
+	if (simple_positive(dentry)) {
 		if (d_is_dir(dentry))
 			simple_rmdir(d_inode(parent), dentry);
 		else
@@ -456,8 +451,6 @@
 	.show_options	= hypfs_show_options,
 };
 
-static struct kobject *s390_kobj;
-
 static int __init hypfs_init(void)
 {
 	int rc;
@@ -481,18 +474,16 @@
 		rc = -ENODATA;
 		goto fail_hypfs_sprp_exit;
 	}
-	s390_kobj = kobject_create_and_add("s390", hypervisor_kobj);
-	if (!s390_kobj) {
-		rc = -ENOMEM;
+	rc = sysfs_create_mount_point(hypervisor_kobj, "s390");
+	if (rc)
 		goto fail_hypfs_diag0c_exit;
-	}
 	rc = register_filesystem(&hypfs_type);
 	if (rc)
 		goto fail_filesystem;
 	return 0;
 
 fail_filesystem:
-	kobject_put(s390_kobj);
+	sysfs_remove_mount_point(hypervisor_kobj, "s390");
 fail_hypfs_diag0c_exit:
 	hypfs_diag0c_exit();
 fail_hypfs_sprp_exit:
@@ -510,7 +501,7 @@
 static void __exit hypfs_exit(void)
 {
 	unregister_filesystem(&hypfs_type);
-	kobject_put(s390_kobj);
+	sysfs_remove_mount_point(hypervisor_kobj, "s390");
 	hypfs_diag0c_exit();
 	hypfs_sprp_exit();
 	hypfs_vm_exit();
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index e6a1578..afe05bf 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -1572,7 +1572,7 @@
 }
 
 #define param_check_sfb_size(name, p) __param_check(name, p, void)
-static struct kernel_param_ops param_ops_sfb_size = {
+static const struct kernel_param_ops param_ops_sfb_size = {
 	.set = param_set_sfb_size,
 	.get = param_get_sfb_size,
 };
diff --git a/arch/sh/boards/mach-highlander/psw.c b/arch/sh/boards/mach-highlander/psw.c
index 5227863..40e2b58 100644
--- a/arch/sh/boards/mach-highlander/psw.c
+++ b/arch/sh/boards/mach-highlander/psw.c
@@ -10,7 +10,7 @@
  * for more details.
  */
 #include <linux/io.h>
-#include <linux/init.h>
+#include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
 #include <mach/highlander.h>
diff --git a/arch/sh/boards/mach-landisk/psw.c b/arch/sh/boards/mach-landisk/psw.c
index bef8352..5192b1f 100644
--- a/arch/sh/boards/mach-landisk/psw.c
+++ b/arch/sh/boards/mach-landisk/psw.c
@@ -140,4 +140,4 @@
 {
 	return platform_add_devices(psw_devices, ARRAY_SIZE(psw_devices));
 }
-module_init(psw_init);
+device_initcall(psw_init);
diff --git a/arch/tile/kernel/stack.c b/arch/tile/kernel/stack.c
index 35d3463..402b9c8 100644
--- a/arch/tile/kernel/stack.c
+++ b/arch/tile/kernel/stack.c
@@ -332,7 +332,7 @@
 	}
 
 	if (vma->vm_file) {
-		p = d_path(&vma->vm_file->f_path, buf, bufsize);
+		p = file_path(vma->vm_file, buf, bufsize);
 		if (IS_ERR(p))
 			p = "?";
 		name = kbasename(p);
diff --git a/arch/tile/kernel/usb.c b/arch/tile/kernel/usb.c
index 5af8deb..f0da5a2 100644
--- a/arch/tile/kernel/usb.c
+++ b/arch/tile/kernel/usb.c
@@ -21,6 +21,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/platform_device.h>
 #include <linux/usb/tilegx.h>
+#include <linux/init.h>
 #include <linux/types.h>
 
 static u64 ehci_dmamask = DMA_BIT_MASK(32);
diff --git a/arch/tile/mm/elf.c b/arch/tile/mm/elf.c
index f7ddae3..6225cc9 100644
--- a/arch/tile/mm/elf.c
+++ b/arch/tile/mm/elf.c
@@ -56,7 +56,7 @@
 	if (exe_file == NULL)
 		goto done_free;
 
-	path = d_path(&exe_file->f_path, buf, PAGE_SIZE);
+	path = file_path(exe_file, buf, PAGE_SIZE);
 	if (IS_ERR(path))
 		goto done_put;
 
diff --git a/arch/um/drivers/hostaudio_kern.c b/arch/um/drivers/hostaudio_kern.c
index 9b90fdc..f6b911c 100644
--- a/arch/um/drivers/hostaudio_kern.c
+++ b/arch/um/drivers/hostaudio_kern.c
@@ -185,9 +185,9 @@
 	int ret;
 
 #ifdef DEBUG
-	kparam_block_sysfs_write(dsp);
+	kernel_param_lock(THIS_MODULE);
 	printk(KERN_DEBUG "hostaudio: open called (host: %s)\n", dsp);
-	kparam_unblock_sysfs_write(dsp);
+	kernel_param_unlock(THIS_MODULE);
 #endif
 
 	state = kmalloc(sizeof(struct hostaudio_state), GFP_KERNEL);
@@ -199,11 +199,11 @@
 	if (file->f_mode & FMODE_WRITE)
 		w = 1;
 
-	kparam_block_sysfs_write(dsp);
+	kernel_param_lock(THIS_MODULE);
 	mutex_lock(&hostaudio_mutex);
 	ret = os_open_file(dsp, of_set_rw(OPENFLAGS(), r, w), 0);
 	mutex_unlock(&hostaudio_mutex);
-	kparam_unblock_sysfs_write(dsp);
+	kernel_param_unlock(THIS_MODULE);
 
 	if (ret < 0) {
 		kfree(state);
@@ -260,17 +260,17 @@
 	if (file->f_mode & FMODE_WRITE)
 		w = 1;
 
-	kparam_block_sysfs_write(mixer);
+	kernel_param_lock(THIS_MODULE);
 	mutex_lock(&hostaudio_mutex);
 	ret = os_open_file(mixer, of_set_rw(OPENFLAGS(), r, w), 0);
 	mutex_unlock(&hostaudio_mutex);
-	kparam_unblock_sysfs_write(mixer);
+	kernel_param_unlock(THIS_MODULE);
 
 	if (ret < 0) {
-		kparam_block_sysfs_write(dsp);
+		kernel_param_lock(THIS_MODULE);
 		printk(KERN_ERR "hostaudio_open_mixdev failed to open '%s', "
 		       "err = %d\n", dsp, -ret);
-		kparam_unblock_sysfs_write(dsp);
+		kernel_param_unlock(THIS_MODULE);
 		kfree(state);
 		return ret;
 	}
@@ -326,10 +326,10 @@
 
 static int __init hostaudio_init_module(void)
 {
-	__kernel_param_lock();
+	kernel_param_lock(THIS_MODULE);
 	printk(KERN_INFO "UML Audio Relay (host dsp = %s, host mixer = %s)\n",
 	       dsp, mixer);
-	__kernel_param_unlock();
+	kernel_param_unlock(THIS_MODULE);
 
 	module_data.dev_audio = register_sound_dsp(&hostaudio_fops, -1);
 	if (module_data.dev_audio < 0) {
diff --git a/arch/unicore32/kernel/fpu-ucf64.c b/arch/unicore32/kernel/fpu-ucf64.c
index 282a60a..a53343a 100644
--- a/arch/unicore32/kernel/fpu-ucf64.c
+++ b/arch/unicore32/kernel/fpu-ucf64.c
@@ -90,8 +90,8 @@
 			tmp &= ~(FPSCR_CON);
 		exc &= ~(FPSCR_CMPINSTR_BIT | FPSCR_CON);
 	} else {
-		pr_debug(KERN_ERR "UniCore-F64 Error: unhandled exceptions\n");
-		pr_debug(KERN_ERR "UniCore-F64 FPSCR 0x%08x INST 0x%08x\n",
+		pr_debug("UniCore-F64 Error: unhandled exceptions\n");
+		pr_debug("UniCore-F64 FPSCR 0x%08x INST 0x%08x\n",
 				cff(FPSCR), inst);
 
 		ucf64_raise_sigfpe(0, regs);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d05a423..55bced1 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -34,6 +34,7 @@
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select ARCH_SUPPORTS_ATOMIC_RMW
+	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
 	select ARCH_SUPPORTS_INT128		if X86_64
 	select ARCH_SUPPORTS_NUMA_BALANCING	if X86_64
 	select ARCH_USE_BUILTIN_BSWAP
@@ -87,6 +88,7 @@
 	select HAVE_CMPXCHG_DOUBLE
 	select HAVE_CMPXCHG_LOCAL
 	select HAVE_CONTEXT_TRACKING		if X86_64
+	select HAVE_COPY_THREAD_TLS
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DEBUG_STACKOVERFLOW
diff --git a/arch/x86/configs/xen.config b/arch/x86/configs/xen.config
new file mode 100644
index 0000000..d9fc713
--- /dev/null
+++ b/arch/x86/configs/xen.config
@@ -0,0 +1,28 @@
+# global x86 required specific stuff
+# On 32-bit HIGHMEM4G is not allowed
+CONFIG_HIGHMEM64G=y
+CONFIG_64BIT=y
+
+# These enable us to allow some of the
+# not so generic stuff below
+CONFIG_HYPERVISOR_GUEST=y
+CONFIG_PCI=y
+CONFIG_PCI_MSI=y
+CONFIG_X86_MCE=y
+CONFIG_ACPI_PROCESSOR=y
+CONFIG_CPU_FREQ=y
+
+# x86 xen specific config options
+CONFIG_XEN_PVH=y
+CONFIG_XEN_MAX_DOMAIN_MEMORY=500
+CONFIG_XEN_SAVE_RESTORE=y
+# CONFIG_XEN_DEBUG_FS is not set
+CONFIG_XEN_MCE_LOG=y
+CONFIG_XEN_ACPI_PROCESSOR=m
+# x86 specific backend drivers
+CONFIG_XEN_PCIDEV_BACKEND=m
+# x86 specific frontend drivers
+CONFIG_XEN_PCIDEV_FRONTEND=m
+# depends on MEMORY_HOTPLUG, arm64 doesn't enable this yet,
+# move to generic config if it ever does.
+CONFIG_XEN_BALLOON_MEMORY_HOTPLUG=y
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 2bfc8a7..dccad38 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -1537,7 +1537,7 @@
 	crypto_fpu_exit();
 }
 
-module_init(aesni_init);
+late_initcall(aesni_init);
 module_exit(aesni_exit);
 
 MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, Intel AES-NI instructions optimized");
diff --git a/arch/x86/include/asm/intel_pmc_ipc.h b/arch/x86/include/asm/intel_pmc_ipc.h
new file mode 100644
index 0000000..200ec2e
--- /dev/null
+++ b/arch/x86/include/asm/intel_pmc_ipc.h
@@ -0,0 +1,82 @@
+#ifndef _ASM_X86_INTEL_PMC_IPC_H_
+#define  _ASM_X86_INTEL_PMC_IPC_H_
+
+/* Commands */
+#define PMC_IPC_PMIC_ACCESS		0xFF
+#define		PMC_IPC_PMIC_ACCESS_READ	0x0
+#define		PMC_IPC_PMIC_ACCESS_WRITE	0x1
+#define PMC_IPC_USB_PWR_CTRL		0xF0
+#define PMC_IPC_PMIC_BLACKLIST_SEL	0xEF
+#define PMC_IPC_PHY_CONFIG		0xEE
+#define PMC_IPC_NORTHPEAK_CTRL		0xED
+#define PMC_IPC_PM_DEBUG		0xEC
+#define PMC_IPC_PMC_TELEMTRY		0xEB
+#define PMC_IPC_PMC_FW_MSG_CTRL		0xEA
+
+/* IPC return code */
+#define IPC_ERR_NONE			0
+#define IPC_ERR_CMD_NOT_SUPPORTED	1
+#define IPC_ERR_CMD_NOT_SERVICED	2
+#define IPC_ERR_UNABLE_TO_SERVICE	3
+#define IPC_ERR_CMD_INVALID		4
+#define IPC_ERR_CMD_FAILED		5
+#define IPC_ERR_EMSECURITY		6
+#define IPC_ERR_UNSIGNEDKERNEL		7
+
+#if IS_ENABLED(CONFIG_INTEL_PMC_IPC)
+
+/*
+ * intel_pmc_ipc_simple_command
+ * @cmd: command
+ * @sub: sub type
+ */
+int intel_pmc_ipc_simple_command(int cmd, int sub);
+
+/*
+ * intel_pmc_ipc_raw_cmd
+ * @cmd: command
+ * @sub: sub type
+ * @in: input data
+ * @inlen: input length in bytes
+ * @out: output data
+ * @outlen: output length in dwords
+ * @sptr: data writing to SPTR register
+ * @dptr: data writing to DPTR register
+ */
+int intel_pmc_ipc_raw_cmd(u32 cmd, u32 sub, u8 *in, u32 inlen,
+		u32 *out, u32 outlen, u32 dptr, u32 sptr);
+
+/*
+ * intel_pmc_ipc_command
+ * @cmd: command
+ * @sub: sub type
+ * @in: input data
+ * @inlen: input length in bytes
+ * @out: output data
+ * @outlen: output length in dwords
+ */
+int intel_pmc_ipc_command(u32 cmd, u32 sub, u8 *in, u32 inlen,
+		u32 *out, u32 outlen);
+
+#else
+
+static inline int intel_pmc_ipc_simple_command(int cmd, int sub)
+{
+	return -EINVAL;
+}
+
+static inline int intel_pmc_ipc_raw_cmd(u32 cmd, u32 sub, u8 *in, u32 inlen,
+		u32 *out, u32 outlen, u32 dptr, u32 sptr)
+{
+	return -EINVAL;
+}
+
+static inline int intel_pmc_ipc_command(u32 cmd, u32 sub, u8 *in, u32 inlen,
+		u32 *out, u32 outlen)
+{
+	return -EINVAL;
+}
+
+#endif /*CONFIG_INTEL_PMC_IPC*/
+
+#endif
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c7fa57b..2a7f5d7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -607,7 +607,7 @@
 	struct kvm_pic *vpic;
 	struct kvm_ioapic *vioapic;
 	struct kvm_pit *vpit;
-	int vapics_in_nmi_mode;
+	atomic_t vapics_in_nmi_mode;
 	struct mutex apic_map_lock;
 	struct kvm_apic_map *apic_map;
 
diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index ce6068d..8fba544 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -199,6 +199,17 @@
 #define HV_X64_MSR_STIMER3_CONFIG		0x400000B6
 #define HV_X64_MSR_STIMER3_COUNT		0x400000B7
 
+/* Hyper-V guest crash notification MSR's */
+#define HV_X64_MSR_CRASH_P0			0x40000100
+#define HV_X64_MSR_CRASH_P1			0x40000101
+#define HV_X64_MSR_CRASH_P2			0x40000102
+#define HV_X64_MSR_CRASH_P3			0x40000103
+#define HV_X64_MSR_CRASH_P4			0x40000104
+#define HV_X64_MSR_CRASH_CTL			0x40000105
+#define HV_X64_MSR_CRASH_CTL_NOTIFY		(1ULL << 63)
+#define HV_X64_MSR_CRASH_PARAMS		\
+		(1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0))
+
 #define HV_X64_MSR_HYPERCALL_ENABLE		0x00000001
 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT	12
 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK	\
diff --git a/arch/x86/kernel/bootflag.c b/arch/x86/kernel/bootflag.c
index 5de7f4c..52c8e3c 100644
--- a/arch/x86/kernel/bootflag.c
+++ b/arch/x86/kernel/bootflag.c
@@ -98,4 +98,4 @@
 
 	return 0;
 }
-module_init(sbf_init);
+arch_initcall(sbf_init);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 9fc5e3d..922c5e0 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -742,7 +742,6 @@
 	cpu_detect(c);
 	get_cpu_vendor(c);
 	get_cpu_cap(c);
-	fpu__init_system(c);
 
 	if (this_cpu->c_early_init)
 		this_cpu->c_early_init(c);
@@ -754,6 +753,7 @@
 		this_cpu->c_bsp_init(c);
 
 	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
+	fpu__init_system(c);
 }
 
 void __init early_cpu_init(void)
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 5801a14..3658de4 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -357,34 +357,24 @@
  */
 int x86_add_exclusive(unsigned int what)
 {
-	int ret = -EBUSY, i;
+	int i;
 
-	if (atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what]))
-		return 0;
-
-	mutex_lock(&pmc_reserve_mutex);
-	for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) {
-		if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i]))
-			goto out;
+	if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) {
+		mutex_lock(&pmc_reserve_mutex);
+		for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) {
+			if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i]))
+				goto fail_unlock;
+		}
+		atomic_inc(&x86_pmu.lbr_exclusive[what]);
+		mutex_unlock(&pmc_reserve_mutex);
 	}
 
-	atomic_inc(&x86_pmu.lbr_exclusive[what]);
-	ret = 0;
+	atomic_inc(&active_events);
+	return 0;
 
-out:
+fail_unlock:
 	mutex_unlock(&pmc_reserve_mutex);
-
-	/*
-	 * Assuming that all exclusive events will share the PMI handler
-	 * (which checks active_events for whether there is work to do),
-	 * we can bump active_events counter right here, except for
-	 * x86_lbr_exclusive_lbr events that go through x86_pmu_event_init()
-	 * path, which already bumps active_events for them.
-	 */
-	if (!ret && what != x86_lbr_exclusive_lbr)
-		atomic_inc(&active_events);
-
-	return ret;
+	return -EBUSY;
 }
 
 void x86_del_exclusive(unsigned int what)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/kernel/cpu/perf_event_intel_bts.c
index 7795f3f..43dd672 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_bts.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_bts.c
@@ -530,5 +530,4 @@
 
 	return perf_pmu_register(&bts_pmu, "intel_bts", -1);
 }
-
-module_init(bts_init);
+arch_initcall(bts_init);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c
index 159887c..183de71 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_pt.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c
@@ -1106,5 +1106,4 @@
 
 	return ret;
 }
-
-module_init(pt_init);
+arch_initcall(pt_init);
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 5ee7718..1f4acd6 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -65,7 +65,7 @@
 
 	return of_platform_bus_probe(NULL, ce4100_ids, NULL);
 }
-module_init(add_bus_probe);
+device_initcall(add_bus_probe);
 
 #ifdef CONFIG_PCI
 struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus)
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index fc878fe..3282679 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -95,11 +95,12 @@
 	unsigned int mask = 0;
 
 	if (cpu_has_fxsr) {
-		struct fxregs_state fx_tmp __aligned(32) = { };
+		/* Static because GCC does not get 16-byte stack alignment right: */
+		static struct fxregs_state fxregs __initdata;
 
-		asm volatile("fxsave %0" : "+m" (fx_tmp));
+		asm volatile("fxsave %0" : "+m" (fxregs));
 
-		mask = fx_tmp.mxcsr_mask;
+		mask = fxregs.mxcsr_mask;
 
 		/*
 		 * If zero then use the default features mask,
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index ca05f86..ca83f7ac 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -72,15 +72,16 @@
 			 unsigned long cmdline_len)
 {
 	char *cmdline_ptr = ((char *)params) + cmdline_offset;
-	unsigned long cmdline_ptr_phys, len;
+	unsigned long cmdline_ptr_phys, len = 0;
 	uint32_t cmdline_low_32, cmdline_ext_32;
 
-	memcpy(cmdline_ptr, cmdline, cmdline_len);
 	if (image->type == KEXEC_TYPE_CRASH) {
-		len = sprintf(cmdline_ptr + cmdline_len - 1,
-			" elfcorehdr=0x%lx", image->arch.elf_load_addr);
-		cmdline_len += len;
+		len = sprintf(cmdline_ptr,
+			"elfcorehdr=0x%lx ", image->arch.elf_load_addr);
 	}
+	memcpy(cmdline_ptr + len, cmdline, cmdline_len);
+	cmdline_len += len;
+
 	cmdline_ptr[cmdline_len - 1] = '\0';
 
 	pr_debug("Final command line is: %s\n", cmdline_ptr);
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index c09c99c..f73c962 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -128,8 +128,8 @@
 	release_vm86_irqs(dead_task);
 }
 
-int copy_thread(unsigned long clone_flags, unsigned long sp,
-	unsigned long arg, struct task_struct *p)
+int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
+	unsigned long arg, struct task_struct *p, unsigned long tls)
 {
 	struct pt_regs *childregs = task_pt_regs(p);
 	struct task_struct *tsk;
@@ -184,7 +184,7 @@
 	 */
 	if (clone_flags & CLONE_SETTLS)
 		err = do_set_thread_area(p, -1,
-			(struct user_desc __user *)childregs->si, 0);
+			(struct user_desc __user *)tls, 0);
 
 	if (err && p->thread.io_bitmap_ptr) {
 		kfree(p->thread.io_bitmap_ptr);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 843f92e..71d7849 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -150,8 +150,8 @@
 	return get_desc_base(&t->thread.tls_array[tls]);
 }
 
-int copy_thread(unsigned long clone_flags, unsigned long sp,
-		unsigned long arg, struct task_struct *p)
+int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
+		unsigned long arg, struct task_struct *p, unsigned long tls)
 {
 	int err;
 	struct pt_regs *childregs;
@@ -207,10 +207,10 @@
 #ifdef CONFIG_IA32_EMULATION
 		if (is_ia32_task())
 			err = do_set_thread_area(p, -1,
-				(struct user_desc __user *)childregs->si, 0);
+				(struct user_desc __user *)tls, 0);
 		else
 #endif
-			err = do_arch_prctl(p, ARCH_SET_FS, childregs->r8);
+			err = do_arch_prctl(p, ARCH_SET_FS, tls);
 		if (err)
 			goto out;
 	}
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d3b95b8..80f874b 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -461,19 +461,18 @@
 {
 	struct setup_data *data;
 	u64 pa_data;
-	int found = 0;
 
 	pa_data = boot_params.hdr.setup_data;
+	if (!pa_data)
+		return;
+
 	while (pa_data) {
 		data = early_memremap(pa_data, sizeof(*data));
 		e820_update_range(pa_data, sizeof(*data)+data->len,
 			 E820_RAM, E820_RESERVED_KERN);
-		found = 1;
 		pa_data = data->next;
 		early_memunmap(data, sizeof(*data));
 	}
-	if (!found)
-		return;
 
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 	memcpy(&e820_saved, &e820, sizeof(struct e820map));
diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index ee22c1d..b034b1b 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -72,7 +72,7 @@
 }
 PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_enable);
 
-static unsigned __init_or_module vsmp_patch(u8 type, u16 clobbers, void *ibuf,
+static unsigned __init vsmp_patch(u8 type, u16 clobbers, void *ibuf,
 				  unsigned long addr, unsigned len)
 {
 	switch (type) {
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 4dce6f8..f90952f 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -305,7 +305,7 @@
 		 * LVT0 to NMI delivery. Other PIC interrupts are just sent to
 		 * VCPU0, and only if its LVT0 is in EXTINT mode.
 		 */
-		if (kvm->arch.vapics_in_nmi_mode > 0)
+		if (atomic_read(&kvm->arch.vapics_in_nmi_mode) > 0)
 			kvm_for_each_vcpu(i, vcpu, kvm)
 				kvm_apic_nmi_wd_deliver(vcpu);
 	}
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 36e9de1..954e98a 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1257,16 +1257,17 @@
 
 static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val)
 {
-	int nmi_wd_enabled = apic_lvt_nmi_mode(kvm_apic_get_reg(apic, APIC_LVT0));
+	bool lvt0_in_nmi_mode = apic_lvt_nmi_mode(lvt0_val);
 
-	if (apic_lvt_nmi_mode(lvt0_val)) {
-		if (!nmi_wd_enabled) {
+	if (apic->lvt0_in_nmi_mode != lvt0_in_nmi_mode) {
+		apic->lvt0_in_nmi_mode = lvt0_in_nmi_mode;
+		if (lvt0_in_nmi_mode) {
 			apic_debug("Receive NMI setting on APIC_LVT0 "
 				   "for cpu %d\n", apic->vcpu->vcpu_id);
-			apic->vcpu->kvm->arch.vapics_in_nmi_mode++;
-		}
-	} else if (nmi_wd_enabled)
-		apic->vcpu->kvm->arch.vapics_in_nmi_mode--;
+			atomic_inc(&apic->vcpu->kvm->arch.vapics_in_nmi_mode);
+		} else
+			atomic_dec(&apic->vcpu->kvm->arch.vapics_in_nmi_mode);
+	}
 }
 
 static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
@@ -1597,6 +1598,7 @@
 	if (!(vcpu->kvm->arch.disabled_quirks & KVM_QUIRK_LINT0_REENABLED))
 		apic_set_reg(apic, APIC_LVT0,
 			     SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
+	apic_manage_nmi_watchdog(apic, kvm_apic_get_reg(apic, APIC_LVT0));
 
 	apic_set_reg(apic, APIC_DFR, 0xffffffffU);
 	apic_set_spiv(apic, 0xff);
@@ -1822,6 +1824,7 @@
 	apic_update_ppr(apic);
 	hrtimer_cancel(&apic->lapic_timer.timer);
 	apic_update_lvtt(apic);
+	apic_manage_nmi_watchdog(apic, kvm_apic_get_reg(apic, APIC_LVT0));
 	update_divide_count(apic);
 	start_apic_timer(apic);
 	apic->irr_pending = true;
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index f2f4e10..7195274 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -26,6 +26,7 @@
 	struct kvm_vcpu *vcpu;
 	bool sw_enabled;
 	bool irr_pending;
+	bool lvt0_in_nmi_mode;
 	/* Number of bits set in ISR. */
 	s16 isr_count;
 	/* The highest vector set in ISR; if -1 - invalid, must scan ISR. */
diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c
index a4f62e6..03d518e 100644
--- a/arch/x86/kvm/mmu_audit.c
+++ b/arch/x86/kvm/mmu_audit.c
@@ -297,7 +297,7 @@
 	return 0;
 }
 
-static struct kernel_param_ops audit_param_ops = {
+static const struct kernel_param_ops audit_param_ops = {
 	.set = mmu_audit_set,
 	.get = param_get_bool,
 };
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ac165c2..bbaf44e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2379,8 +2379,6 @@
 
 int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
-	u64 data;
-
 	switch (msr_info->index) {
 	case MSR_IA32_PLATFORM_ID:
 	case MSR_IA32_EBL_CR_POWERON:
@@ -2453,7 +2451,7 @@
 		/* TSC increment by tick */
 		msr_info->data = 1000ULL;
 		/* CPU multiplier */
-		data |= (((uint64_t)4ULL) << 40);
+		msr_info->data |= (((uint64_t)4ULL) << 40);
 		break;
 	case MSR_EFER:
 		msr_info->data = vcpu->arch.efer;
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index ddf9ecb..e342586 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -20,7 +20,7 @@
 	unsigned long ret;
 
 	if (__range_not_ok(from, n, TASK_SIZE))
-		return 0;
+		return n;
 
 	/*
 	 * Even though this function is typically called from NMI/IRQ context
diff --git a/arch/x86/platform/intel-mid/intel_mid_vrtc.c b/arch/x86/platform/intel-mid/intel_mid_vrtc.c
index 32947ba..ee40fcb 100644
--- a/arch/x86/platform/intel-mid/intel_mid_vrtc.c
+++ b/arch/x86/platform/intel-mid/intel_mid_vrtc.c
@@ -173,5 +173,4 @@
 
 	return platform_device_register(&vrtc_device);
 }
-
-module_init(intel_mid_device_create);
+device_initcall(intel_mid_device_create);
diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c
index 7488caf..020c101 100644
--- a/arch/x86/platform/uv/uv_nmi.c
+++ b/arch/x86/platform/uv/uv_nmi.c
@@ -104,7 +104,7 @@
 	return 0;
 }
 
-static struct kernel_param_ops param_ops_local64 = {
+static const struct kernel_param_ops param_ops_local64 = {
 	.get = param_get_local64,
 	.set = param_set_local64,
 };
diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c
index 17b1ef3..8ab021b 100644
--- a/arch/xtensa/platforms/iss/network.c
+++ b/arch/xtensa/platforms/iss/network.c
@@ -681,6 +681,4 @@
 
 	return 1;
 }
-
-module_init(iss_net_init);
-
+device_initcall(iss_net_init);
diff --git a/crypto/asymmetric_keys/pkcs7_key_type.c b/crypto/asymmetric_keys/pkcs7_key_type.c
index 751f8fd..3d13b04 100644
--- a/crypto/asymmetric_keys/pkcs7_key_type.c
+++ b/crypto/asymmetric_keys/pkcs7_key_type.c
@@ -12,6 +12,7 @@
 #define pr_fmt(fmt) "PKCS7key: "fmt
 #include <linux/key.h>
 #include <linux/err.h>
+#include <linux/module.h>
 #include <linux/key-type.h>
 #include <crypto/pkcs7.h>
 #include <keys/user-type.h>
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index f15db00..114cf48 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -80,6 +80,26 @@
 
 	  Say N to delete power /proc/acpi/ directories that have moved to /sys/
 
+config ACPI_REV_OVERRIDE_POSSIBLE
+	bool "Allow supported ACPI revision to be overriden"
+	depends on X86
+	default y
+	help
+	  The platform firmware on some systems expects Linux to return "5" as
+	  the supported ACPI revision which makes it expose system configuration
+	  information in a special way.
+
+	  For example, based on what ACPI exports as the supported revision,
+	  Dell XPS 13 (2015) configures its audio device to either work in HDA
+	  mode or in I2S mode, where the former is supposed to be used on Linux
+	  until the latter is fully supported (in the kernel as well as in user
+	  space).
+
+	  This option enables a DMI-based quirk for the above Dell machine (so
+	  that HDA audio is exposed by the platform firmware to the kernel) and
+	  makes it possible to force the kernel to return "5" as the supported
+	  ACPI revision via the "acpi_rev_override" command line switch.
+
 config ACPI_EC_DEBUGFS
 	tristate "EC read/write access through /sys/kernel/debug/ec"
 	default n
diff --git a/drivers/acpi/acpica/accommon.h b/drivers/acpi/acpica/accommon.h
index 853aa2d..a8d8092 100644
--- a/drivers/acpi/acpica/accommon.h
+++ b/drivers/acpi/acpica/accommon.h
@@ -59,5 +59,8 @@
 #include "acglobal.h"		/* All global variables */
 #include "achware.h"		/* Hardware defines and interfaces */
 #include "acutils.h"		/* Utility interfaces */
+#ifndef ACPI_USE_SYSTEM_CLIBRARY
+#include "acclib.h"		/* C library interfaces */
+#endif				/* !ACPI_USE_SYSTEM_CLIBRARY */
 
 #endif				/* __ACCOMMON_H__ */
diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index a0c4787..53f96a3 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -61,6 +61,8 @@
 
 #if (!ACPI_REDUCED_HARDWARE)
 ACPI_GLOBAL(struct acpi_table_facs *, acpi_gbl_FACS);
+ACPI_GLOBAL(struct acpi_table_facs *, acpi_gbl_facs32);
+ACPI_GLOBAL(struct acpi_table_facs *, acpi_gbl_facs64);
 
 #endif				/* !ACPI_REDUCED_HARDWARE */
 
diff --git a/drivers/acpi/acpica/acinterp.h b/drivers/acpi/acpica/acinterp.h
index 1886bde..7ac9800 100644
--- a/drivers/acpi/acpica/acinterp.h
+++ b/drivers/acpi/acpica/acinterp.h
@@ -468,6 +468,8 @@
 
 void acpi_ex_integer_to_string(char *dest, u64 value);
 
+void acpi_ex_pci_cls_to_string(char *dest, u8 class_code[3]);
+
 u8 acpi_is_valid_space_id(u8 space_id);
 
 /*
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index ffdb956..bc60096 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -213,6 +213,7 @@
 
 #define ACPI_TABLE_INDEX_DSDT           (0)
 #define ACPI_TABLE_INDEX_FACS           (1)
+#define ACPI_TABLE_INDEX_X_FACS         (2)
 
 struct acpi_find_context {
 	char *search_for;
diff --git a/drivers/acpi/acpica/acnamesp.h b/drivers/acpi/acpica/acnamesp.h
index 952fbe0..0dd0882 100644
--- a/drivers/acpi/acpica/acnamesp.h
+++ b/drivers/acpi/acpica/acnamesp.h
@@ -66,6 +66,7 @@
 #define ACPI_NS_PREFIX_IS_SCOPE     0x10
 #define ACPI_NS_EXTERNAL            0x20
 #define ACPI_NS_TEMPORARY           0x40
+#define ACPI_NS_OVERRIDE_IF_FOUND   0x80
 
 /* Flags for acpi_ns_walk_namespace */
 
diff --git a/drivers/acpi/acpica/acobject.h b/drivers/acpi/acpica/acobject.h
index 3e9720e..c81d98d 100644
--- a/drivers/acpi/acpica/acobject.h
+++ b/drivers/acpi/acpica/acobject.h
@@ -335,6 +335,7 @@
 	void *object;		/* name_op=>HANDLE to obj, index_op=>union acpi_operand_object */
 	struct acpi_namespace_node *node;	/* ref_of or Namepath */
 	union acpi_operand_object **where;	/* Target of Index */
+	u8 *index_pointer;	/* Used for Buffers and Strings */
 	u32 value;		/* Used for Local/Arg/Index/ddb_handle */
 };
 
diff --git a/drivers/acpi/acpica/acstruct.h b/drivers/acpi/acpica/acstruct.h
index 87c7860..44997ca 100644
--- a/drivers/acpi/acpica/acstruct.h
+++ b/drivers/acpi/acpica/acstruct.h
@@ -82,6 +82,7 @@
 	u8 return_used;
 	u8 scope_depth;
 	u8 pass_number;		/* Parse pass during table load */
+	u8 namespace_override;	/* Override existing objects */
 	u8 result_size;		/* Total elements for the result stack */
 	u8 result_count;	/* Current number of occupied elements of result stack */
 	u32 aml_offset;
diff --git a/drivers/acpi/acpica/acutils.h b/drivers/acpi/acpica/acutils.h
index d49f5c7..6de0d35 100644
--- a/drivers/acpi/acpica/acutils.h
+++ b/drivers/acpi/acpica/acutils.h
@@ -205,66 +205,6 @@
 
 void acpi_ut_subsystem_shutdown(void);
 
-/*
- * utclib - Local implementations of C library functions
- */
-#ifndef ACPI_USE_SYSTEM_CLIBRARY
-
-acpi_size acpi_ut_strlen(const char *string);
-
-char *acpi_ut_strchr(const char *string, int ch);
-
-char *acpi_ut_strcpy(char *dst_string, const char *src_string);
-
-char *acpi_ut_strncpy(char *dst_string,
-		      const char *src_string, acpi_size count);
-
-int acpi_ut_memcmp(const char *buffer1, const char *buffer2, acpi_size count);
-
-int acpi_ut_strncmp(const char *string1, const char *string2, acpi_size count);
-
-int acpi_ut_strcmp(const char *string1, const char *string2);
-
-char *acpi_ut_strcat(char *dst_string, const char *src_string);
-
-char *acpi_ut_strncat(char *dst_string,
-		      const char *src_string, acpi_size count);
-
-u32 acpi_ut_strtoul(const char *string, char **terminator, u32 base);
-
-char *acpi_ut_strstr(char *string1, char *string2);
-
-void *acpi_ut_memcpy(void *dest, const void *src, acpi_size count);
-
-void *acpi_ut_memset(void *dest, u8 value, acpi_size count);
-
-int acpi_ut_to_upper(int c);
-
-int acpi_ut_to_lower(int c);
-
-extern const u8 _acpi_ctype[];
-
-#define _ACPI_XA     0x00	/* extra alphabetic - not supported */
-#define _ACPI_XS     0x40	/* extra space */
-#define _ACPI_BB     0x00	/* BEL, BS, etc. - not supported */
-#define _ACPI_CN     0x20	/* CR, FF, HT, NL, VT */
-#define _ACPI_DI     0x04	/* '0'-'9' */
-#define _ACPI_LO     0x02	/* 'a'-'z' */
-#define _ACPI_PU     0x10	/* punctuation */
-#define _ACPI_SP     0x08	/* space, tab, CR, LF, VT, FF */
-#define _ACPI_UP     0x01	/* 'A'-'Z' */
-#define _ACPI_XD     0x80	/* '0'-'9', 'A'-'F', 'a'-'f' */
-
-#define ACPI_IS_DIGIT(c)  (_acpi_ctype[(unsigned char)(c)] & (_ACPI_DI))
-#define ACPI_IS_SPACE(c)  (_acpi_ctype[(unsigned char)(c)] & (_ACPI_SP))
-#define ACPI_IS_XDIGIT(c) (_acpi_ctype[(unsigned char)(c)] & (_ACPI_XD))
-#define ACPI_IS_UPPER(c)  (_acpi_ctype[(unsigned char)(c)] & (_ACPI_UP))
-#define ACPI_IS_LOWER(c)  (_acpi_ctype[(unsigned char)(c)] & (_ACPI_LO))
-#define ACPI_IS_PRINT(c)  (_acpi_ctype[(unsigned char)(c)] & (_ACPI_LO | _ACPI_UP | _ACPI_DI | _ACPI_XS | _ACPI_PU))
-#define ACPI_IS_ALPHA(c)  (_acpi_ctype[(unsigned char)(c)] & (_ACPI_LO | _ACPI_UP))
-
-#endif				/* !ACPI_USE_SYSTEM_CLIBRARY */
-
 #define ACPI_IS_ASCII(c)  ((c) < 0x80)
 
 /*
@@ -430,6 +370,10 @@
 acpi_ut_execute_CID(struct acpi_namespace_node *device_node,
 		    struct acpi_pnp_device_id_list ** return_cid_list);
 
+acpi_status
+acpi_ut_execute_CLS(struct acpi_namespace_node *device_node,
+		    struct acpi_pnp_device_id **return_id);
+
 /*
  * utlock - reader/writer locks
  */
diff --git a/drivers/acpi/acpica/dsfield.c b/drivers/acpi/acpica/dsfield.c
index 43b40de..20de148 100644
--- a/drivers/acpi/acpica/dsfield.c
+++ b/drivers/acpi/acpica/dsfield.c
@@ -502,7 +502,7 @@
 		}
 	}
 
-	ACPI_MEMSET(&info, 0, sizeof(struct acpi_create_field_info));
+	memset(&info, 0, sizeof(struct acpi_create_field_info));
 
 	/* Second arg is the field flags */
 
diff --git a/drivers/acpi/acpica/dsinit.c b/drivers/acpi/acpica/dsinit.c
index bbe74bc..95779e8 100644
--- a/drivers/acpi/acpica/dsinit.c
+++ b/drivers/acpi/acpica/dsinit.c
@@ -207,7 +207,7 @@
 
 	/* Set all init info to zero */
 
-	ACPI_MEMSET(&info, 0, sizeof(struct acpi_init_walk_info));
+	memset(&info, 0, sizeof(struct acpi_init_walk_info));
 
 	info.owner_id = owner_id;
 	info.table_index = table_index;
diff --git a/drivers/acpi/acpica/dsobject.c b/drivers/acpi/acpica/dsobject.c
index 8a7b07b..2beb7fd 100644
--- a/drivers/acpi/acpica/dsobject.c
+++ b/drivers/acpi/acpica/dsobject.c
@@ -339,8 +339,8 @@
 		/* Initialize buffer from the byte_list (if present) */
 
 		if (byte_list) {
-			ACPI_MEMCPY(obj_desc->buffer.pointer,
-				    byte_list->named.data, byte_list_length);
+			memcpy(obj_desc->buffer.pointer, byte_list->named.data,
+			       byte_list_length);
 		}
 	}
 
@@ -750,8 +750,7 @@
 	case ACPI_TYPE_STRING:
 
 		obj_desc->string.pointer = op->common.value.string;
-		obj_desc->string.length =
-		    (u32) ACPI_STRLEN(op->common.value.string);
+		obj_desc->string.length = (u32)strlen(op->common.value.string);
 
 		/*
 		 * The string is contained in the ACPI table, don't ever try
diff --git a/drivers/acpi/acpica/dsutils.c b/drivers/acpi/acpica/dsutils.c
index deeddd6..ebc577b 100644
--- a/drivers/acpi/acpica/dsutils.c
+++ b/drivers/acpi/acpica/dsutils.c
@@ -572,8 +572,8 @@
 					obj_desc =
 					    acpi_ut_create_string_object((acpi_size) name_length);
 
-					ACPI_STRNCPY(obj_desc->string.pointer,
-						     name_string, name_length);
+					strncpy(obj_desc->string.pointer,
+						name_string, name_length);
 					status = AE_OK;
 				} else {
 					/*
diff --git a/drivers/acpi/acpica/dswload.c b/drivers/acpi/acpica/dswload.c
index 843942f..845ff44 100644
--- a/drivers/acpi/acpica/dswload.c
+++ b/drivers/acpi/acpica/dswload.c
@@ -315,10 +315,19 @@
 		flags = ACPI_NS_NO_UPSEARCH;
 		if ((walk_state->opcode != AML_SCOPE_OP) &&
 		    (!(walk_state->parse_flags & ACPI_PARSE_DEFERRED_OP))) {
-			flags |= ACPI_NS_ERROR_IF_FOUND;
-			ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH,
-					  "[%s] Cannot already exist\n",
-					  acpi_ut_get_type_name(object_type)));
+			if (walk_state->namespace_override) {
+				flags |= ACPI_NS_OVERRIDE_IF_FOUND;
+				ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH,
+						  "[%s] Override allowed\n",
+						  acpi_ut_get_type_name
+						  (object_type)));
+			} else {
+				flags |= ACPI_NS_ERROR_IF_FOUND;
+				ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH,
+						  "[%s] Cannot already exist\n",
+						  acpi_ut_get_type_name
+						  (object_type)));
+			}
 		} else {
 			ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH,
 					  "[%s] Both Find or Create allowed\n",
diff --git a/drivers/acpi/acpica/evgpeinit.c b/drivers/acpi/acpica/evgpeinit.c
index 8840296..ea4c0d3 100644
--- a/drivers/acpi/acpica/evgpeinit.c
+++ b/drivers/acpi/acpica/evgpeinit.c
@@ -377,7 +377,7 @@
 
 	/* 4) The last two characters of the name are the hex GPE Number */
 
-	gpe_number = ACPI_STRTOUL(&name[2], NULL, 16);
+	gpe_number = strtoul(&name[2], NULL, 16);
 	if (gpe_number == ACPI_UINT32_MAX) {
 
 		/* Conversion failed; invalid method, just ignore it */
diff --git a/drivers/acpi/acpica/exconfig.c b/drivers/acpi/acpica/exconfig.c
index 6e0df2b..24a4c5c 100644
--- a/drivers/acpi/acpica/exconfig.c
+++ b/drivers/acpi/acpica/exconfig.c
@@ -470,7 +470,7 @@
 			return_ACPI_STATUS(AE_NO_MEMORY);
 		}
 
-		ACPI_MEMCPY(table, table_header, length);
+		memcpy(table, table_header, length);
 		break;
 
 	default:
diff --git a/drivers/acpi/acpica/exconvrt.c b/drivers/acpi/acpica/exconvrt.c
index 89a976b..075d654 100644
--- a/drivers/acpi/acpica/exconvrt.c
+++ b/drivers/acpi/acpica/exconvrt.c
@@ -227,9 +227,8 @@
 		/* Copy the integer to the buffer, LSB first */
 
 		new_buf = return_desc->buffer.pointer;
-		ACPI_MEMCPY(new_buf,
-			    &obj_desc->integer.value,
-			    acpi_gbl_integer_byte_width);
+		memcpy(new_buf,
+		       &obj_desc->integer.value, acpi_gbl_integer_byte_width);
 		break;
 
 	case ACPI_TYPE_STRING:
@@ -252,8 +251,8 @@
 		/* Copy the string to the buffer */
 
 		new_buf = return_desc->buffer.pointer;
-		ACPI_STRNCPY((char *)new_buf, (char *)obj_desc->string.pointer,
-			     obj_desc->string.length);
+		strncpy((char *)new_buf, (char *)obj_desc->string.pointer,
+			obj_desc->string.length);
 		break;
 
 	default:
diff --git a/drivers/acpi/acpica/exdebug.c b/drivers/acpi/acpica/exdebug.c
index e67d0ac..815442b 100644
--- a/drivers/acpi/acpica/exdebug.c
+++ b/drivers/acpi/acpica/exdebug.c
@@ -76,6 +76,8 @@
 {
 	u32 i;
 	u32 timer;
+	union acpi_operand_object *object_desc;
+	u32 value;
 
 	ACPI_FUNCTION_TRACE_PTR(ex_do_debug_object, source_desc);
 
@@ -254,8 +256,44 @@
 							 object)->object,
 							level + 4, 0);
 			} else {
-				acpi_ex_do_debug_object(source_desc->reference.
-							object, level + 4, 0);
+				object_desc = source_desc->reference.object;
+				value = source_desc->reference.value;
+
+				switch (object_desc->common.type) {
+				case ACPI_TYPE_BUFFER:
+
+					acpi_os_printf("Buffer[%u] = 0x%2.2X\n",
+						       value,
+						       *source_desc->reference.
+						       index_pointer);
+					break;
+
+				case ACPI_TYPE_STRING:
+
+					acpi_os_printf
+					    ("String[%u] = \"%c\" (0x%2.2X)\n",
+					     value,
+					     *source_desc->reference.
+					     index_pointer,
+					     *source_desc->reference.
+					     index_pointer);
+					break;
+
+				case ACPI_TYPE_PACKAGE:
+
+					acpi_os_printf("Package[%u] = ", value);
+					acpi_ex_do_debug_object(*source_desc->
+								reference.where,
+								level + 4, 0);
+					break;
+
+				default:
+
+					acpi_os_printf
+					    ("Unknown Reference object type %X\n",
+					     object_desc->common.type);
+					break;
+				}
 			}
 		}
 		break;
diff --git a/drivers/acpi/acpica/exdump.c b/drivers/acpi/acpica/exdump.c
index 1da52be..401e7ed 100644
--- a/drivers/acpi/acpica/exdump.c
+++ b/drivers/acpi/acpica/exdump.c
@@ -224,7 +224,7 @@
 	{ACPI_EXD_POINTER, ACPI_EXD_OFFSET(index_field.data_obj), "Data Object"}
 };
 
-static struct acpi_exdump_info acpi_ex_dump_reference[8] = {
+static struct acpi_exdump_info acpi_ex_dump_reference[9] = {
 	{ACPI_EXD_INIT, ACPI_EXD_TABLE_SIZE(acpi_ex_dump_reference), NULL},
 	{ACPI_EXD_UINT8, ACPI_EXD_OFFSET(reference.class), "Class"},
 	{ACPI_EXD_UINT8, ACPI_EXD_OFFSET(reference.target_type), "Target Type"},
@@ -232,6 +232,8 @@
 	{ACPI_EXD_POINTER, ACPI_EXD_OFFSET(reference.object), "Object Desc"},
 	{ACPI_EXD_NODE, ACPI_EXD_OFFSET(reference.node), "Node"},
 	{ACPI_EXD_POINTER, ACPI_EXD_OFFSET(reference.where), "Where"},
+	{ACPI_EXD_POINTER, ACPI_EXD_OFFSET(reference.index_pointer),
+	 "Index Pointer"},
 	{ACPI_EXD_REFERENCE, 0, NULL}
 };
 
@@ -1005,14 +1007,13 @@
 	} else if (obj_desc->reference.object) {
 		if (ACPI_GET_DESCRIPTOR_TYPE(obj_desc) ==
 		    ACPI_DESC_TYPE_OPERAND) {
-			acpi_os_printf(" Target: %p",
+			acpi_os_printf("%22s %p", "Target :",
 				       obj_desc->reference.object);
 			if (obj_desc->reference.class == ACPI_REFCLASS_TABLE) {
 				acpi_os_printf(" Table Index: %X\n",
 					       obj_desc->reference.value);
 			} else {
-				acpi_os_printf(" Target: %p [%s]\n",
-					       obj_desc->reference.object,
+				acpi_os_printf(" [%s]\n",
 					       acpi_ut_get_type_name(((union
 								       acpi_operand_object
 								       *)
diff --git a/drivers/acpi/acpica/exfield.c b/drivers/acpi/acpica/exfield.c
index c161dd9..61fd9c7 100644
--- a/drivers/acpi/acpica/exfield.c
+++ b/drivers/acpi/acpica/exfield.c
@@ -428,7 +428,7 @@
 		}
 
 		buffer = buffer_desc->buffer.pointer;
-		ACPI_MEMCPY(buffer, source_desc->buffer.pointer, length);
+		memcpy(buffer, source_desc->buffer.pointer, length);
 
 		/* Lock entire transaction if requested */
 
diff --git a/drivers/acpi/acpica/exfldio.c b/drivers/acpi/acpica/exfldio.c
index 725a374..70b7bbb 100644
--- a/drivers/acpi/acpica/exfldio.c
+++ b/drivers/acpi/acpica/exfldio.c
@@ -416,22 +416,22 @@
 			 * Copy the data from the source buffer.
 			 * Length is the field width in bytes.
 			 */
-			ACPI_MEMCPY(value,
-				    (obj_desc->buffer_field.buffer_obj)->buffer.
-				    pointer +
-				    obj_desc->buffer_field.base_byte_offset +
-				    field_datum_byte_offset,
-				    obj_desc->common_field.access_byte_width);
+			memcpy(value,
+			       (obj_desc->buffer_field.buffer_obj)->buffer.
+			       pointer +
+			       obj_desc->buffer_field.base_byte_offset +
+			       field_datum_byte_offset,
+			       obj_desc->common_field.access_byte_width);
 		} else {
 			/*
 			 * Copy the data to the target buffer.
 			 * Length is the field width in bytes.
 			 */
-			ACPI_MEMCPY((obj_desc->buffer_field.buffer_obj)->buffer.
-				    pointer +
-				    obj_desc->buffer_field.base_byte_offset +
-				    field_datum_byte_offset, value,
-				    obj_desc->common_field.access_byte_width);
+			memcpy((obj_desc->buffer_field.buffer_obj)->buffer.
+			       pointer +
+			       obj_desc->buffer_field.base_byte_offset +
+			       field_datum_byte_offset, value,
+			       obj_desc->common_field.access_byte_width);
 		}
 
 		status = AE_OK;
@@ -703,7 +703,7 @@
 		return_ACPI_STATUS(AE_BUFFER_OVERFLOW);
 	}
 
-	ACPI_MEMSET(buffer, 0, buffer_length);
+	memset(buffer, 0, buffer_length);
 	access_bit_width = ACPI_MUL_8(obj_desc->common_field.access_byte_width);
 
 	/* Handle the simple case here */
@@ -720,7 +720,7 @@
 			status =
 			    acpi_ex_field_datum_io(obj_desc, 0, &raw_datum,
 						   ACPI_READ);
-			ACPI_MEMCPY(buffer, &raw_datum, buffer_length);
+			memcpy(buffer, &raw_datum, buffer_length);
 		}
 
 		return_ACPI_STATUS(status);
@@ -793,9 +793,9 @@
 
 		/* Write merged datum to target buffer */
 
-		ACPI_MEMCPY(((char *)buffer) + buffer_offset, &merged_datum,
-			    ACPI_MIN(obj_desc->common_field.access_byte_width,
-				     buffer_length - buffer_offset));
+		memcpy(((char *)buffer) + buffer_offset, &merged_datum,
+		       ACPI_MIN(obj_desc->common_field.access_byte_width,
+				buffer_length - buffer_offset));
 
 		buffer_offset += obj_desc->common_field.access_byte_width;
 		merged_datum =
@@ -811,9 +811,9 @@
 
 	/* Write the last datum to the buffer */
 
-	ACPI_MEMCPY(((char *)buffer) + buffer_offset, &merged_datum,
-		    ACPI_MIN(obj_desc->common_field.access_byte_width,
-			     buffer_length - buffer_offset));
+	memcpy(((char *)buffer) + buffer_offset, &merged_datum,
+	       ACPI_MIN(obj_desc->common_field.access_byte_width,
+			buffer_length - buffer_offset));
 
 	return_ACPI_STATUS(AE_OK);
 }
@@ -878,7 +878,7 @@
 		 * at Byte zero. All unused (upper) bytes of the
 		 * buffer will be 0.
 		 */
-		ACPI_MEMCPY((char *)new_buffer, (char *)buffer, buffer_length);
+		memcpy((char *)new_buffer, (char *)buffer, buffer_length);
 		buffer = new_buffer;
 		buffer_length = required_length;
 	}
@@ -918,9 +918,9 @@
 
 	/* Get initial Datum from the input buffer */
 
-	ACPI_MEMCPY(&raw_datum, buffer,
-		    ACPI_MIN(obj_desc->common_field.access_byte_width,
-			     buffer_length - buffer_offset));
+	memcpy(&raw_datum, buffer,
+	       ACPI_MIN(obj_desc->common_field.access_byte_width,
+			buffer_length - buffer_offset));
 
 	merged_datum =
 	    raw_datum << obj_desc->common_field.start_field_bit_offset;
@@ -970,9 +970,9 @@
 		/* Get the next input datum from the buffer */
 
 		buffer_offset += obj_desc->common_field.access_byte_width;
-		ACPI_MEMCPY(&raw_datum, ((char *)buffer) + buffer_offset,
-			    ACPI_MIN(obj_desc->common_field.access_byte_width,
-				     buffer_length - buffer_offset));
+		memcpy(&raw_datum, ((char *)buffer) + buffer_offset,
+		       ACPI_MIN(obj_desc->common_field.access_byte_width,
+				buffer_length - buffer_offset));
 
 		merged_datum |=
 		    raw_datum << obj_desc->common_field.start_field_bit_offset;
diff --git a/drivers/acpi/acpica/exmisc.c b/drivers/acpi/acpica/exmisc.c
index b56fc9d..d02afec 100644
--- a/drivers/acpi/acpica/exmisc.c
+++ b/drivers/acpi/acpica/exmisc.c
@@ -209,8 +209,8 @@
 	 * end_tag descriptor is copied from Operand1.
 	 */
 	new_buf = return_desc->buffer.pointer;
-	ACPI_MEMCPY(new_buf, operand0->buffer.pointer, length0);
-	ACPI_MEMCPY(new_buf + length0, operand1->buffer.pointer, length1);
+	memcpy(new_buf, operand0->buffer.pointer, length0);
+	memcpy(new_buf + length0, operand1->buffer.pointer, length1);
 
 	/* Insert end_tag and set the checksum to zero, means "ignore checksum" */
 
@@ -318,14 +318,14 @@
 
 		/* Copy the first integer, LSB first */
 
-		ACPI_MEMCPY(new_buf, &operand0->integer.value,
-			    acpi_gbl_integer_byte_width);
+		memcpy(new_buf, &operand0->integer.value,
+		       acpi_gbl_integer_byte_width);
 
 		/* Copy the second integer (LSB first) after the first */
 
-		ACPI_MEMCPY(new_buf + acpi_gbl_integer_byte_width,
-			    &local_operand1->integer.value,
-			    acpi_gbl_integer_byte_width);
+		memcpy(new_buf + acpi_gbl_integer_byte_width,
+		       &local_operand1->integer.value,
+		       acpi_gbl_integer_byte_width);
 		break;
 
 	case ACPI_TYPE_STRING:
@@ -346,9 +346,9 @@
 
 		/* Concatenate the strings */
 
-		ACPI_STRCPY(new_buf, operand0->string.pointer);
-		ACPI_STRCPY(new_buf + operand0->string.length,
-			    local_operand1->string.pointer);
+		strcpy(new_buf, operand0->string.pointer);
+		strcpy(new_buf + operand0->string.length,
+		       local_operand1->string.pointer);
 		break;
 
 	case ACPI_TYPE_BUFFER:
@@ -369,11 +369,11 @@
 
 		/* Concatenate the buffers */
 
-		ACPI_MEMCPY(new_buf, operand0->buffer.pointer,
-			    operand0->buffer.length);
-		ACPI_MEMCPY(new_buf + operand0->buffer.length,
-			    local_operand1->buffer.pointer,
-			    local_operand1->buffer.length);
+		memcpy(new_buf, operand0->buffer.pointer,
+		       operand0->buffer.length);
+		memcpy(new_buf + operand0->buffer.length,
+		       local_operand1->buffer.pointer,
+		       local_operand1->buffer.length);
 		break;
 
 	default:
@@ -660,9 +660,9 @@
 
 		/* Lexicographic compare: compare the data bytes */
 
-		compare = ACPI_MEMCMP(operand0->buffer.pointer,
-				      local_operand1->buffer.pointer,
-				      (length0 > length1) ? length1 : length0);
+		compare = memcmp(operand0->buffer.pointer,
+				 local_operand1->buffer.pointer,
+				 (length0 > length1) ? length1 : length0);
 
 		switch (opcode) {
 		case AML_LEQUAL_OP:	/* LEqual (Operand0, Operand1) */
diff --git a/drivers/acpi/acpica/exnames.c b/drivers/acpi/acpica/exnames.c
index 453b00c..20e8781 100644
--- a/drivers/acpi/acpica/exnames.c
+++ b/drivers/acpi/acpica/exnames.c
@@ -192,7 +192,7 @@
 		char_buf[4] = '\0';
 
 		if (name_string) {
-			ACPI_STRCAT(name_string, char_buf);
+			strcat(name_string, char_buf);
 			ACPI_DEBUG_PRINT((ACPI_DB_NAMES,
 					  "Appended to - %s\n", name_string));
 		} else {
diff --git a/drivers/acpi/acpica/exoparg2.c b/drivers/acpi/acpica/exoparg2.c
index fcc618a..b8944eb 100644
--- a/drivers/acpi/acpica/exoparg2.c
+++ b/drivers/acpi/acpica/exoparg2.c
@@ -337,8 +337,8 @@
 		 * Copy the raw buffer data with no transform.
 		 * (NULL terminated already)
 		 */
-		ACPI_MEMCPY(return_desc->string.pointer,
-			    operand[0]->buffer.pointer, length);
+		memcpy(return_desc->string.pointer,
+		       operand[0]->buffer.pointer, length);
 		break;
 
 	case AML_CONCAT_RES_OP:
@@ -380,6 +380,8 @@
 
 			return_desc->reference.target_type =
 			    ACPI_TYPE_BUFFER_FIELD;
+			return_desc->reference.index_pointer =
+			    &(operand[0]->buffer.pointer[index]);
 			break;
 
 		case ACPI_TYPE_BUFFER:
@@ -391,6 +393,8 @@
 
 			return_desc->reference.target_type =
 			    ACPI_TYPE_BUFFER_FIELD;
+			return_desc->reference.index_pointer =
+			    &(operand[0]->buffer.pointer[index]);
 			break;
 
 		case ACPI_TYPE_PACKAGE:
diff --git a/drivers/acpi/acpica/exoparg3.c b/drivers/acpi/acpica/exoparg3.c
index 1c64a98..fa100b3 100644
--- a/drivers/acpi/acpica/exoparg3.c
+++ b/drivers/acpi/acpica/exoparg3.c
@@ -237,8 +237,8 @@
 
 			/* We have a buffer, copy the portion requested */
 
-			ACPI_MEMCPY(buffer, operand[0]->string.pointer + index,
-				    length);
+			memcpy(buffer, operand[0]->string.pointer + index,
+			       length);
 		}
 
 		/* Set the length of the new String/Buffer */
diff --git a/drivers/acpi/acpica/exregion.c b/drivers/acpi/acpica/exregion.c
index f6c2f54..b4a5e44 100644
--- a/drivers/acpi/acpica/exregion.c
+++ b/drivers/acpi/acpica/exregion.c
@@ -517,15 +517,14 @@
 	switch (function) {
 	case ACPI_READ:
 
-		ACPI_MEMCPY(ACPI_CAST_PTR(char, value),
-			    ACPI_PHYSADDR_TO_PTR(address),
-			    ACPI_DIV_8(bit_width));
+		memcpy(ACPI_CAST_PTR(char, value),
+		       ACPI_PHYSADDR_TO_PTR(address), ACPI_DIV_8(bit_width));
 		break;
 
 	case ACPI_WRITE:
 
-		ACPI_MEMCPY(ACPI_PHYSADDR_TO_PTR(address),
-			    ACPI_CAST_PTR(char, value), ACPI_DIV_8(bit_width));
+		memcpy(ACPI_PHYSADDR_TO_PTR(address),
+		       ACPI_CAST_PTR(char, value), ACPI_DIV_8(bit_width));
 		break;
 
 	default:
diff --git a/drivers/acpi/acpica/exstorob.c b/drivers/acpi/acpica/exstorob.c
index 6fa3c8d..e1d4f4d 100644
--- a/drivers/acpi/acpica/exstorob.c
+++ b/drivers/acpi/acpica/exstorob.c
@@ -100,9 +100,9 @@
 
 		/* Clear existing buffer and copy in the new one */
 
-		ACPI_MEMSET(target_desc->buffer.pointer, 0,
-			    target_desc->buffer.length);
-		ACPI_MEMCPY(target_desc->buffer.pointer, buffer, length);
+		memset(target_desc->buffer.pointer, 0,
+		       target_desc->buffer.length);
+		memcpy(target_desc->buffer.pointer, buffer, length);
 
 #ifdef ACPI_OBSOLETE_BEHAVIOR
 		/*
@@ -129,8 +129,8 @@
 	} else {
 		/* Truncate the source, copy only what will fit */
 
-		ACPI_MEMCPY(target_desc->buffer.pointer, buffer,
-			    target_desc->buffer.length);
+		memcpy(target_desc->buffer.pointer, buffer,
+		       target_desc->buffer.length);
 
 		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 				  "Truncating source buffer from %X to %X\n",
@@ -187,9 +187,9 @@
 		 * String will fit in existing non-static buffer.
 		 * Clear old string and copy in the new one
 		 */
-		ACPI_MEMSET(target_desc->string.pointer, 0,
-			    (acpi_size) target_desc->string.length + 1);
-		ACPI_MEMCPY(target_desc->string.pointer, buffer, length);
+		memset(target_desc->string.pointer, 0,
+		       (acpi_size) target_desc->string.length + 1);
+		memcpy(target_desc->string.pointer, buffer, length);
 	} else {
 		/*
 		 * Free the current buffer, then allocate a new buffer
@@ -210,7 +210,7 @@
 		}
 
 		target_desc->common.flags &= ~AOPOBJ_STATIC_POINTER;
-		ACPI_MEMCPY(target_desc->string.pointer, buffer, length);
+		memcpy(target_desc->string.pointer, buffer, length);
 	}
 
 	/* Set the new target length */
diff --git a/drivers/acpi/acpica/exutils.c b/drivers/acpi/acpica/exutils.c
index 3f4225e..30c3f46 100644
--- a/drivers/acpi/acpica/exutils.c
+++ b/drivers/acpi/acpica/exutils.c
@@ -380,6 +380,38 @@
 
 /*******************************************************************************
  *
+ * FUNCTION:    acpi_ex_pci_cls_to_string
+ *
+ * PARAMETERS:  out_string      - Where to put the converted string (7 bytes)
+ * PARAMETERS:  class_code      - PCI class code to be converted (3 bytes)
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Convert 3-bytes PCI class code to string representation.
+ *              Return buffer must be large enough to hold the string. The
+ *              string returned is always exactly of length
+ *              ACPI_PCICLS_STRING_SIZE (includes null terminator).
+ *
+ ******************************************************************************/
+
+void acpi_ex_pci_cls_to_string(char *out_string, u8 class_code[3])
+{
+
+	ACPI_FUNCTION_ENTRY();
+
+	/* All 3 bytes are hexadecimal */
+
+	out_string[0] = acpi_ut_hex_to_ascii_char((u64)class_code[0], 4);
+	out_string[1] = acpi_ut_hex_to_ascii_char((u64)class_code[0], 0);
+	out_string[2] = acpi_ut_hex_to_ascii_char((u64)class_code[1], 4);
+	out_string[3] = acpi_ut_hex_to_ascii_char((u64)class_code[1], 0);
+	out_string[4] = acpi_ut_hex_to_ascii_char((u64)class_code[2], 4);
+	out_string[5] = acpi_ut_hex_to_ascii_char((u64)class_code[2], 0);
+	out_string[6] = 0;
+}
+
+/*******************************************************************************
+ *
  * FUNCTION:    acpi_is_valid_space_id
  *
  * PARAMETERS:  space_id            - ID to be validated
diff --git a/drivers/acpi/acpica/hwxfsleep.c b/drivers/acpi/acpica/hwxfsleep.c
index 3b37676..52dfd0d 100644
--- a/drivers/acpi/acpica/hwxfsleep.c
+++ b/drivers/acpi/acpica/hwxfsleep.c
@@ -50,6 +50,13 @@
 ACPI_MODULE_NAME("hwxfsleep")
 
 /* Local prototypes */
+#if (!ACPI_REDUCED_HARDWARE)
+static acpi_status
+acpi_hw_set_firmware_waking_vectors(struct acpi_table_facs *facs,
+				    acpi_physical_address physical_address,
+				    acpi_physical_address physical_address64);
+#endif
+
 static acpi_status acpi_hw_sleep_dispatch(u8 sleep_state, u32 function_id);
 
 /*
@@ -72,6 +79,7 @@
 
 /*
  * These functions are removed for the ACPI_REDUCED_HARDWARE case:
+ *      acpi_set_firmware_waking_vectors
  *      acpi_set_firmware_waking_vector
  *      acpi_set_firmware_waking_vector64
  *      acpi_enter_sleep_state_s4bios
@@ -80,20 +88,26 @@
 #if (!ACPI_REDUCED_HARDWARE)
 /*******************************************************************************
  *
- * FUNCTION:    acpi_set_firmware_waking_vector
+ * FUNCTION:    acpi_hw_set_firmware_waking_vectors
  *
- * PARAMETERS:  physical_address    - 32-bit physical address of ACPI real mode
+ * PARAMETERS:  facs                - Pointer to FACS table
+ *              physical_address    - 32-bit physical address of ACPI real mode
  *                                    entry point.
+ *              physical_address64  - 64-bit physical address of ACPI protected
+ *                                    mode entry point.
  *
  * RETURN:      Status
  *
- * DESCRIPTION: Sets the 32-bit firmware_waking_vector field of the FACS
+ * DESCRIPTION: Sets the firmware_waking_vector fields of the FACS
  *
  ******************************************************************************/
 
-acpi_status acpi_set_firmware_waking_vector(u32 physical_address)
+static acpi_status
+acpi_hw_set_firmware_waking_vectors(struct acpi_table_facs *facs,
+				    acpi_physical_address physical_address,
+				    acpi_physical_address physical_address64)
 {
-	ACPI_FUNCTION_TRACE(acpi_set_firmware_waking_vector);
+	ACPI_FUNCTION_TRACE(acpi_hw_set_firmware_waking_vectors);
 
 
 	/*
@@ -106,17 +120,92 @@
 
 	/* Set the 32-bit vector */
 
-	acpi_gbl_FACS->firmware_waking_vector = physical_address;
+	facs->firmware_waking_vector = (u32)physical_address;
 
-	/* Clear the 64-bit vector if it exists */
+	if (facs->length > 32) {
+		if (facs->version >= 1) {
 
-	if ((acpi_gbl_FACS->length > 32) && (acpi_gbl_FACS->version >= 1)) {
-		acpi_gbl_FACS->xfirmware_waking_vector = 0;
+			/* Set the 64-bit vector */
+
+			facs->xfirmware_waking_vector = physical_address64;
+		} else {
+			/* Clear the 64-bit vector if it exists */
+
+			facs->xfirmware_waking_vector = 0;
+		}
 	}
 
 	return_ACPI_STATUS(AE_OK);
 }
 
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_set_firmware_waking_vectors
+ *
+ * PARAMETERS:  physical_address    - 32-bit physical address of ACPI real mode
+ *                                    entry point.
+ *              physical_address64  - 64-bit physical address of ACPI protected
+ *                                    mode entry point.
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Sets the firmware_waking_vector fields of the FACS
+ *
+ ******************************************************************************/
+
+acpi_status
+acpi_set_firmware_waking_vectors(acpi_physical_address physical_address,
+				 acpi_physical_address physical_address64)
+{
+
+	ACPI_FUNCTION_TRACE(acpi_set_firmware_waking_vectors);
+
+	/* If Hardware Reduced flag is set, there is no FACS */
+
+	if (acpi_gbl_reduced_hardware) {
+		return_ACPI_STATUS (AE_OK);
+	}
+
+	if (acpi_gbl_facs32) {
+		(void)acpi_hw_set_firmware_waking_vectors(acpi_gbl_facs32,
+							  physical_address,
+							  physical_address64);
+	}
+	if (acpi_gbl_facs64) {
+		(void)acpi_hw_set_firmware_waking_vectors(acpi_gbl_facs64,
+							  physical_address,
+							  physical_address64);
+	}
+
+	return_ACPI_STATUS(AE_OK);
+}
+
+ACPI_EXPORT_SYMBOL(acpi_set_firmware_waking_vectors)
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_set_firmware_waking_vector
+ *
+ * PARAMETERS:  physical_address    - 32-bit physical address of ACPI real mode
+ *                                    entry point.
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Sets the 32-bit firmware_waking_vector field of the FACS
+ *
+ ******************************************************************************/
+acpi_status acpi_set_firmware_waking_vector(u32 physical_address)
+{
+	acpi_status status;
+
+	ACPI_FUNCTION_TRACE(acpi_set_firmware_waking_vector);
+
+	status = acpi_set_firmware_waking_vectors((acpi_physical_address)
+						  physical_address, 0);
+
+	return_ACPI_STATUS(status);
+}
+
 ACPI_EXPORT_SYMBOL(acpi_set_firmware_waking_vector)
 
 #if ACPI_MACHINE_WIDTH == 64
@@ -136,25 +225,19 @@
  ******************************************************************************/
 acpi_status acpi_set_firmware_waking_vector64(u64 physical_address)
 {
+	acpi_status status;
+
 	ACPI_FUNCTION_TRACE(acpi_set_firmware_waking_vector64);
 
+	status = acpi_set_firmware_waking_vectors(0,
+						  (acpi_physical_address)
+						  physical_address);
 
-	/* Determine if the 64-bit vector actually exists */
-
-	if ((acpi_gbl_FACS->length <= 32) || (acpi_gbl_FACS->version < 1)) {
-		return_ACPI_STATUS(AE_NOT_EXIST);
-	}
-
-	/* Clear 32-bit vector, set the 64-bit X_ vector */
-
-	acpi_gbl_FACS->firmware_waking_vector = 0;
-	acpi_gbl_FACS->xfirmware_waking_vector = physical_address;
-	return_ACPI_STATUS(AE_OK);
+	return_ACPI_STATUS(status);
 }
 
 ACPI_EXPORT_SYMBOL(acpi_set_firmware_waking_vector64)
 #endif
-
 /*******************************************************************************
  *
  * FUNCTION:    acpi_enter_sleep_state_s4bios
diff --git a/drivers/acpi/acpica/nsaccess.c b/drivers/acpi/acpica/nsaccess.c
index 24fa19a..c687b99 100644
--- a/drivers/acpi/acpica/nsaccess.c
+++ b/drivers/acpi/acpica/nsaccess.c
@@ -102,7 +102,7 @@
 
 		/* _OSI is optional for now, will be permanent later */
 
-		if (!ACPI_STRCMP(init_val->name, "_OSI")
+		if (!strcmp(init_val->name, "_OSI")
 		    && !acpi_gbl_create_osi_method) {
 			continue;
 		}
@@ -180,7 +180,7 @@
 
 				/* Build an object around the static string */
 
-				obj_desc->string.length = (u32)ACPI_STRLEN(val);
+				obj_desc->string.length = (u32)strlen(val);
 				obj_desc->string.pointer = val;
 				obj_desc->common.flags |= AOPOBJ_STATIC_POINTER;
 				break;
@@ -203,7 +203,7 @@
 
 				/* Special case for ACPI Global Lock */
 
-				if (ACPI_STRCMP(init_val->name, "_GL_") == 0) {
+				if (strcmp(init_val->name, "_GL_") == 0) {
 					acpi_gbl_global_lock_mutex = obj_desc;
 
 					/* Create additional counting semaphore for global lock */
@@ -304,7 +304,9 @@
 		return_ACPI_STATUS(AE_BAD_PARAMETER);
 	}
 
-	local_flags = flags & ~(ACPI_NS_ERROR_IF_FOUND | ACPI_NS_SEARCH_PARENT);
+	local_flags = flags &
+	    ~(ACPI_NS_ERROR_IF_FOUND | ACPI_NS_OVERRIDE_IF_FOUND |
+	      ACPI_NS_SEARCH_PARENT);
 	*return_node = ACPI_ENTRY_NOT_FOUND;
 	acpi_gbl_ns_lookup_count++;
 
@@ -547,6 +549,12 @@
 			if (flags & ACPI_NS_ERROR_IF_FOUND) {
 				local_flags |= ACPI_NS_ERROR_IF_FOUND;
 			}
+
+			/* Set override flag according to caller */
+
+			if (flags & ACPI_NS_OVERRIDE_IF_FOUND) {
+				local_flags |= ACPI_NS_OVERRIDE_IF_FOUND;
+			}
 		}
 
 		/* Extract one ACPI name from the front of the pathname */
diff --git a/drivers/acpi/acpica/nsconvert.c b/drivers/acpi/acpica/nsconvert.c
index 1a8b39c..da55a1c 100644
--- a/drivers/acpi/acpica/nsconvert.c
+++ b/drivers/acpi/acpica/nsconvert.c
@@ -187,8 +187,8 @@
 		 * Copy the raw buffer data with no transform. String is already NULL
 		 * terminated at Length+1.
 		 */
-		ACPI_MEMCPY(new_object->string.pointer,
-			    original_object->buffer.pointer, length);
+		memcpy(new_object->string.pointer,
+		       original_object->buffer.pointer, length);
 		break;
 
 	default:
@@ -251,9 +251,9 @@
 			return (AE_NO_MEMORY);
 		}
 
-		ACPI_MEMCPY(new_object->buffer.pointer,
-			    original_object->string.pointer,
-			    original_object->string.length);
+		memcpy(new_object->buffer.pointer,
+		       original_object->string.pointer,
+		       original_object->string.length);
 		break;
 
 	case ACPI_TYPE_PACKAGE:
diff --git a/drivers/acpi/acpica/nsdump.c b/drivers/acpi/acpica/nsdump.c
index d259393..0f1daba 100644
--- a/drivers/acpi/acpica/nsdump.c
+++ b/drivers/acpi/acpica/nsdump.c
@@ -101,7 +101,7 @@
 
 	while (num_segments) {
 		for (i = 0; i < 4; i++) {
-			ACPI_IS_PRINT(pathname[i]) ?
+			isprint((int)pathname[i]) ?
 			    acpi_os_printf("%c", pathname[i]) :
 			    acpi_os_printf("?");
 		}
diff --git a/drivers/acpi/acpica/nseval.c b/drivers/acpi/acpica/nseval.c
index 7bcc68f..80670cb 100644
--- a/drivers/acpi/acpica/nseval.c
+++ b/drivers/acpi/acpica/nseval.c
@@ -59,15 +59,14 @@
  *
  * FUNCTION:    acpi_ns_evaluate
  *
- * PARAMETERS:  info            - Evaluation info block, contains:
+ * PARAMETERS:  info            - Evaluation info block, contains these fields
+ *                                and more:
  *                  prefix_node     - Prefix or Method/Object Node to execute
  *                  relative_path   - Name of method to execute, If NULL, the
  *                                    Node is the object to execute
  *                  parameters      - List of parameters to pass to the method,
  *                                    terminated by NULL. Params itself may be
  *                                    NULL if no parameters are being passed.
- *                  return_object   - Where to put method's return value (if
- *                                    any). If NULL, no value is returned.
  *                  parameter_type  - Type of Parameter list
  *                  return_object   - Where to put method's return value (if
  *                                    any). If NULL, no value is returned.
@@ -440,7 +439,7 @@
 
 	/* Initialize the evaluation information block */
 
-	ACPI_MEMSET(info, 0, sizeof(struct acpi_evaluate_info));
+	memset(info, 0, sizeof(struct acpi_evaluate_info));
 	info->prefix_node = parent_node;
 
 	/*
diff --git a/drivers/acpi/acpica/nsinit.c b/drivers/acpi/acpica/nsinit.c
index 4a85c45..b744a53 100644
--- a/drivers/acpi/acpica/nsinit.c
+++ b/drivers/acpi/acpica/nsinit.c
@@ -90,7 +90,7 @@
 
 	/* Set all init info to zero */
 
-	ACPI_MEMSET(&info, 0, sizeof(struct acpi_init_walk_info));
+	memset(&info, 0, sizeof(struct acpi_init_walk_info));
 
 	/* Walk entire namespace from the supplied root */
 
@@ -566,7 +566,7 @@
 	ACPI_DEBUG_EXEC(acpi_ut_display_init_pathname
 			(ACPI_TYPE_METHOD, device_node, METHOD_NAME__INI));
 
-	ACPI_MEMSET(info, 0, sizeof(struct acpi_evaluate_info));
+	memset(info, 0, sizeof(struct acpi_evaluate_info));
 	info->prefix_node = device_node;
 	info->relative_pathname = METHOD_NAME__INI;
 	info->parameters = NULL;
diff --git a/drivers/acpi/acpica/nsparse.c b/drivers/acpi/acpica/nsparse.c
index c95a119..57a4cfe 100644
--- a/drivers/acpi/acpica/nsparse.c
+++ b/drivers/acpi/acpica/nsparse.c
@@ -117,6 +117,13 @@
 					       (u8) pass_number);
 	}
 
+	/* Found OSDT table, enable the namespace override feature */
+
+	if (ACPI_COMPARE_NAME(table->signature, ACPI_SIG_OSDT) &&
+	    pass_number == ACPI_IMODE_LOAD_PASS1) {
+		walk_state->namespace_override = TRUE;
+	}
+
 	if (ACPI_FAILURE(status)) {
 		acpi_ds_delete_walk_state(walk_state);
 		goto cleanup;
diff --git a/drivers/acpi/acpica/nsrepair2.c b/drivers/acpi/acpica/nsrepair2.c
index c30672d..0515a70 100644
--- a/drivers/acpi/acpica/nsrepair2.c
+++ b/drivers/acpi/acpica/nsrepair2.c
@@ -580,7 +580,7 @@
 	 * # is a hex digit.
 	 */
 	for (dest = new_string->string.pointer; *source; dest++, source++) {
-		*dest = (char)ACPI_TOUPPER(*source);
+		*dest = (char)toupper((int)*source);
 	}
 
 	acpi_ut_remove_reference(return_object);
diff --git a/drivers/acpi/acpica/nssearch.c b/drivers/acpi/acpica/nssearch.c
index 4a9d4a6..d739040 100644
--- a/drivers/acpi/acpica/nssearch.c
+++ b/drivers/acpi/acpica/nssearch.c
@@ -325,8 +325,41 @@
 		 * If we found it AND the request specifies that a find is an error,
 		 * return the error
 		 */
-		if ((status == AE_OK) && (flags & ACPI_NS_ERROR_IF_FOUND)) {
-			status = AE_ALREADY_EXISTS;
+		if (status == AE_OK) {
+
+			/* The node was found in the namespace */
+
+			/*
+			 * If the namespace override feature is enabled for this node,
+			 * delete any existing attached sub-object and make the node
+			 * look like a new node that is owned by the override table.
+			 */
+			if (flags & ACPI_NS_OVERRIDE_IF_FOUND) {
+				ACPI_DEBUG_PRINT((ACPI_DB_NAMES,
+						  "Namespace override: %4.4s pass %u type %X Owner %X\n",
+						  ACPI_CAST_PTR(char,
+								&target_name),
+						  interpreter_mode,
+						  (*return_node)->type,
+						  walk_state->owner_id));
+
+				acpi_ns_delete_children(*return_node);
+				if (acpi_gbl_runtime_namespace_override) {
+					acpi_ut_remove_reference((*return_node)->object);
+					(*return_node)->object = NULL;
+					(*return_node)->owner_id =
+					    walk_state->owner_id;
+				} else {
+					acpi_ns_remove_node(*return_node);
+					*return_node = ACPI_ENTRY_NOT_FOUND;
+				}
+			}
+
+			/* Return an error if we don't expect to find the object */
+
+			else if (flags & ACPI_NS_ERROR_IF_FOUND) {
+				status = AE_ALREADY_EXISTS;
+			}
 		}
 #ifdef ACPI_ASL_COMPILER
 		if (*return_node && (*return_node)->type == ACPI_TYPE_ANY) {
diff --git a/drivers/acpi/acpica/nsutils.c b/drivers/acpi/acpica/nsutils.c
index 6ad0200..8d8104b8 100644
--- a/drivers/acpi/acpica/nsutils.c
+++ b/drivers/acpi/acpica/nsutils.c
@@ -292,8 +292,7 @@
 			} else {
 				/* Convert the character to uppercase and save it */
 
-				result[i] =
-				    (char)ACPI_TOUPPER((int)*external_name);
+				result[i] = (char)toupper((int)*external_name);
 				external_name++;
 			}
 		}
diff --git a/drivers/acpi/acpica/nsxfeval.c b/drivers/acpi/acpica/nsxfeval.c
index b6030a2..6ee1e52 100644
--- a/drivers/acpi/acpica/nsxfeval.c
+++ b/drivers/acpi/acpica/nsxfeval.c
@@ -696,7 +696,7 @@
 			return (AE_CTRL_DEPTH);
 		}
 
-		no_match = ACPI_STRCMP(hid->string, info->hid);
+		no_match = strcmp(hid->string, info->hid);
 		ACPI_FREE(hid);
 
 		if (no_match) {
@@ -715,8 +715,7 @@
 
 			found = FALSE;
 			for (i = 0; i < cid->count; i++) {
-				if (ACPI_STRCMP(cid->ids[i].string, info->hid)
-				    == 0) {
+				if (strcmp(cid->ids[i].string, info->hid) == 0) {
 
 					/* Found a matching CID */
 
diff --git a/drivers/acpi/acpica/nsxfname.c b/drivers/acpi/acpica/nsxfname.c
index d66c326..9ff643b 100644
--- a/drivers/acpi/acpica/nsxfname.c
+++ b/drivers/acpi/acpica/nsxfname.c
@@ -114,7 +114,7 @@
 
 		/* Special case for root-only, since we can't search for it */
 
-		if (!ACPI_STRCMP(pathname, ACPI_NS_ROOT_PATH)) {
+		if (!strcmp(pathname, ACPI_NS_ROOT_PATH)) {
 			*ret_handle =
 			    ACPI_CAST_PTR(acpi_handle, acpi_gbl_root_node);
 			return (AE_OK);
@@ -242,7 +242,7 @@
 
 	/* Copy actual string and return a pointer to the next string area */
 
-	ACPI_MEMCPY(string_area, source->string, source->length);
+	memcpy(string_area, source->string, source->length);
 	return (string_area + source->length);
 }
 
@@ -260,7 +260,7 @@
  *              control methods (Such as in the case of a device.)
  *
  * For Device and Processor objects, run the Device _HID, _UID, _CID, _SUB,
- * _STA, _ADR, _sx_w, and _sx_d methods.
+ * _CLS, _STA, _ADR, _sx_w, and _sx_d methods.
  *
  * Note: Allocates the return buffer, must be freed by the caller.
  *
@@ -276,11 +276,12 @@
 	struct acpi_pnp_device_id *hid = NULL;
 	struct acpi_pnp_device_id *uid = NULL;
 	struct acpi_pnp_device_id *sub = NULL;
+	struct acpi_pnp_device_id *cls = NULL;
 	char *next_id_string;
 	acpi_object_type type;
 	acpi_name name;
 	u8 param_count = 0;
-	u8 valid = 0;
+	u16 valid = 0;
 	u32 info_size;
 	u32 i;
 	acpi_status status;
@@ -320,7 +321,7 @@
 	if ((type == ACPI_TYPE_DEVICE) || (type == ACPI_TYPE_PROCESSOR)) {
 		/*
 		 * Get extra info for ACPI Device/Processor objects only:
-		 * Run the Device _HID, _UID, _SUB, and _CID methods.
+		 * Run the Device _HID, _UID, _SUB, _CID, and _CLS methods.
 		 *
 		 * Note: none of these methods are required, so they may or may
 		 * not be present for this device. The Info->Valid bitfield is used
@@ -363,6 +364,14 @@
 			     sizeof(struct acpi_pnp_device_id_list));
 			valid |= ACPI_VALID_CID;
 		}
+
+		/* Execute the Device._CLS method */
+
+		status = acpi_ut_execute_CLS(node, &cls);
+		if (ACPI_SUCCESS(status)) {
+			info_size += cls->length;
+			valid |= ACPI_VALID_CLS;
+		}
 	}
 
 	/*
@@ -486,6 +495,11 @@
 		}
 	}
 
+	if (cls) {
+		next_id_string = acpi_ns_copy_device_id(&info->class_code,
+							cls, next_id_string);
+	}
+
 	/* Copy the fixed-length data */
 
 	info->info_size = info_size;
@@ -510,6 +524,9 @@
 	if (cid_list) {
 		ACPI_FREE(cid_list);
 	}
+	if (cls) {
+		ACPI_FREE(cls);
+	}
 	return (status);
 }
 
@@ -620,7 +637,7 @@
 
 	/* Copy the method AML to the local buffer */
 
-	ACPI_MEMCPY(aml_buffer, aml_start, aml_length);
+	memcpy(aml_buffer, aml_start, aml_length);
 
 	/* Initialize the method object with the new method's information */
 
diff --git a/drivers/acpi/acpica/psutils.c b/drivers/acpi/acpica/psutils.c
index 960505a..3244091 100644
--- a/drivers/acpi/acpica/psutils.c
+++ b/drivers/acpi/acpica/psutils.c
@@ -93,10 +93,9 @@
 	op->common.descriptor_type = ACPI_DESC_TYPE_PARSER;
 	op->common.aml_opcode = opcode;
 
-	ACPI_DISASM_ONLY_MEMBERS(ACPI_STRNCPY(op->common.aml_op_name,
-					      (acpi_ps_get_opcode_info
-					       (opcode))->name,
-					      sizeof(op->common.aml_op_name)));
+	ACPI_DISASM_ONLY_MEMBERS(strncpy(op->common.aml_op_name,
+					 (acpi_ps_get_opcode_info(opcode))->
+					 name, sizeof(op->common.aml_op_name)));
 }
 
 /*******************************************************************************
diff --git a/drivers/acpi/acpica/rscreate.c b/drivers/acpi/acpica/rscreate.c
index 15434e4..3fa829e 100644
--- a/drivers/acpi/acpica/rscreate.c
+++ b/drivers/acpi/acpica/rscreate.c
@@ -353,13 +353,13 @@
 				/* +1 to include null terminator */
 
 				user_prt->length +=
-				    (u32) ACPI_STRLEN(user_prt->source) + 1;
+				    (u32)strlen(user_prt->source) + 1;
 				break;
 
 			case ACPI_TYPE_STRING:
 
-				ACPI_STRCPY(user_prt->source,
-					    obj_desc->string.pointer);
+				strcpy(user_prt->source,
+				       obj_desc->string.pointer);
 
 				/*
 				 * Add to the Length field the length of the string
diff --git a/drivers/acpi/acpica/rsmisc.c b/drivers/acpi/acpica/rsmisc.c
index 1fe49d2..ac37852 100644
--- a/drivers/acpi/acpica/rsmisc.c
+++ b/drivers/acpi/acpica/rsmisc.c
@@ -119,7 +119,7 @@
 			/*
 			 * Get the resource type and the initial (minimum) length
 			 */
-			ACPI_MEMSET(resource, 0, INIT_RESOURCE_LENGTH(info));
+			memset(resource, 0, INIT_RESOURCE_LENGTH(info));
 			resource->type = INIT_RESOURCE_TYPE(info);
 			resource->length = INIT_RESOURCE_LENGTH(info);
 			break;
@@ -324,13 +324,13 @@
 
 		case ACPI_RSC_SET8:
 
-			ACPI_MEMSET(destination, info->aml_offset, info->value);
+			memset(destination, info->aml_offset, info->value);
 			break;
 
 		case ACPI_RSC_DATA8:
 
 			target = ACPI_ADD_PTR(char, resource, info->value);
-			ACPI_MEMCPY(destination, source, ACPI_GET16(target));
+			memcpy(destination, source, ACPI_GET16(target));
 			break;
 
 		case ACPI_RSC_ADDRESS:
@@ -502,7 +502,7 @@
 		switch (info->opcode) {
 		case ACPI_RSC_INITSET:
 
-			ACPI_MEMSET(aml, 0, INIT_RESOURCE_LENGTH(info));
+			memset(aml, 0, INIT_RESOURCE_LENGTH(info));
 			aml_length = INIT_RESOURCE_LENGTH(info);
 			acpi_rs_set_resource_header(INIT_RESOURCE_TYPE(info),
 						    aml_length, aml);
diff --git a/drivers/acpi/acpica/rsutils.c b/drivers/acpi/acpica/rsutils.c
index ece3cd6..52b024d 100644
--- a/drivers/acpi/acpica/rsutils.c
+++ b/drivers/acpi/acpica/rsutils.c
@@ -148,7 +148,7 @@
 		case ACPI_RSC_MOVE_SERIAL_VEN:
 		case ACPI_RSC_MOVE_SERIAL_RES:
 
-			ACPI_MEMCPY(destination, source, item_count);
+			memcpy(destination, source, item_count);
 			return;
 
 			/*
@@ -364,12 +364,11 @@
 		 * Zero the entire area of the buffer.
 		 */
 		total_length =
-		    (u32)
-		    ACPI_STRLEN(ACPI_CAST_PTR(char, &aml_resource_source[1])) +
+		    (u32)strlen(ACPI_CAST_PTR(char, &aml_resource_source[1])) +
 		    1;
-		total_length = (u32) ACPI_ROUND_UP_TO_NATIVE_WORD(total_length);
+		total_length = (u32)ACPI_ROUND_UP_TO_NATIVE_WORD(total_length);
 
-		ACPI_MEMSET(resource_source->string_ptr, 0, total_length);
+		memset(resource_source->string_ptr, 0, total_length);
 
 		/* Copy the resource_source string to the destination */
 
@@ -432,8 +431,8 @@
 
 		/* Copy the resource_source string */
 
-		ACPI_STRCPY(ACPI_CAST_PTR(char, &aml_resource_source[1]),
-			    resource_source->string_ptr);
+		strcpy(ACPI_CAST_PTR(char, &aml_resource_source[1]),
+		       resource_source->string_ptr);
 
 		/*
 		 * Add the length of the string (+ 1 for null terminator) to the
diff --git a/drivers/acpi/acpica/rsxface.c b/drivers/acpi/acpica/rsxface.c
index 8e6276df..de51f83 100644
--- a/drivers/acpi/acpica/rsxface.c
+++ b/drivers/acpi/acpica/rsxface.c
@@ -398,8 +398,8 @@
 
 		/* Simple copy for 64 bit source */
 
-		ACPI_MEMCPY(out, &resource->data,
-			    sizeof(struct acpi_resource_address64));
+		memcpy(out, &resource->data,
+		       sizeof(struct acpi_resource_address64));
 		break;
 
 	default:
@@ -499,7 +499,7 @@
 	 */
 	if ((vendor->byte_length < (ACPI_UUID_LENGTH + 1)) ||
 	    (vendor->uuid_subtype != info->uuid->subtype) ||
-	    (ACPI_MEMCMP(vendor->uuid, info->uuid->data, ACPI_UUID_LENGTH))) {
+	    (memcmp(vendor->uuid, info->uuid->data, ACPI_UUID_LENGTH))) {
 		return (AE_OK);
 	}
 
@@ -513,7 +513,7 @@
 
 	/* Found the correct resource, copy and return it */
 
-	ACPI_MEMCPY(buffer->pointer, resource, resource->length);
+	memcpy(buffer->pointer, resource, resource->length);
 	buffer->length = resource->length;
 
 	/* Found the desired descriptor, terminate resource walk */
diff --git a/drivers/acpi/acpica/tbdata.c b/drivers/acpi/acpica/tbdata.c
index d7f8386..5c9d5ab 100644
--- a/drivers/acpi/acpica/tbdata.c
+++ b/drivers/acpi/acpica/tbdata.c
@@ -73,7 +73,7 @@
 	 * Initialize the table descriptor. Set the pointer to NULL, since the
 	 * table is not fully mapped at this time.
 	 */
-	ACPI_MEMSET(table_desc, 0, sizeof(struct acpi_table_desc));
+	memset(table_desc, 0, sizeof(struct acpi_table_desc));
 	table_desc->address = address;
 	table_desc->length = table->length;
 	table_desc->flags = flags;
@@ -465,9 +465,9 @@
 	/* Copy and free the previous table array */
 
 	if (acpi_gbl_root_table_list.tables) {
-		ACPI_MEMCPY(tables, acpi_gbl_root_table_list.tables,
-			    (acpi_size) table_count *
-			    sizeof(struct acpi_table_desc));
+		memcpy(tables, acpi_gbl_root_table_list.tables,
+		       (acpi_size) table_count *
+		       sizeof(struct acpi_table_desc));
 
 		if (acpi_gbl_root_table_list.flags & ACPI_ROOT_ORIGIN_ALLOCATED) {
 			ACPI_FREE(acpi_gbl_root_table_list.tables);
diff --git a/drivers/acpi/acpica/tbfadt.c b/drivers/acpi/acpica/tbfadt.c
index 7d24860..6253001 100644
--- a/drivers/acpi/acpica/tbfadt.c
+++ b/drivers/acpi/acpica/tbfadt.c
@@ -350,9 +350,18 @@
 	/* If Hardware Reduced flag is set, there is no FACS */
 
 	if (!acpi_gbl_reduced_hardware) {
-		acpi_tb_install_fixed_table((acpi_physical_address)
-					    acpi_gbl_FADT.Xfacs, ACPI_SIG_FACS,
-					    ACPI_TABLE_INDEX_FACS);
+		if (acpi_gbl_FADT.facs) {
+			acpi_tb_install_fixed_table((acpi_physical_address)
+						    acpi_gbl_FADT.facs,
+						    ACPI_SIG_FACS,
+						    ACPI_TABLE_INDEX_FACS);
+		}
+		if (acpi_gbl_FADT.Xfacs) {
+			acpi_tb_install_fixed_table((acpi_physical_address)
+						    acpi_gbl_FADT.Xfacs,
+						    ACPI_SIG_FACS,
+						    ACPI_TABLE_INDEX_X_FACS);
+		}
 	}
 }
 
@@ -389,12 +398,12 @@
 
 	/* Clear the entire local FADT */
 
-	ACPI_MEMSET(&acpi_gbl_FADT, 0, sizeof(struct acpi_table_fadt));
+	memset(&acpi_gbl_FADT, 0, sizeof(struct acpi_table_fadt));
 
 	/* Copy the original FADT, up to sizeof (struct acpi_table_fadt) */
 
-	ACPI_MEMCPY(&acpi_gbl_FADT, table,
-		    ACPI_MIN(length, sizeof(struct acpi_table_fadt)));
+	memcpy(&acpi_gbl_FADT, table,
+	       ACPI_MIN(length, sizeof(struct acpi_table_fadt)));
 
 	/* Take a copy of the Hardware Reduced flag */
 
@@ -491,13 +500,9 @@
 	acpi_gbl_FADT.header.length = sizeof(struct acpi_table_fadt);
 
 	/*
-	 * Expand the 32-bit FACS and DSDT addresses to 64-bit as necessary.
+	 * Expand the 32-bit DSDT addresses to 64-bit as necessary.
 	 * Later ACPICA code will always use the X 64-bit field.
 	 */
-	acpi_gbl_FADT.Xfacs = acpi_tb_select_address("FACS",
-						     acpi_gbl_FADT.facs,
-						     acpi_gbl_FADT.Xfacs);
-
 	acpi_gbl_FADT.Xdsdt = acpi_tb_select_address("DSDT",
 						     acpi_gbl_FADT.dsdt,
 						     acpi_gbl_FADT.Xdsdt);
diff --git a/drivers/acpi/acpica/tbfind.c b/drivers/acpi/acpica/tbfind.c
index 0b879fc..119c84a 100644
--- a/drivers/acpi/acpica/tbfind.c
+++ b/drivers/acpi/acpica/tbfind.c
@@ -76,16 +76,16 @@
 
 	/* Normalize the input strings */
 
-	ACPI_MEMSET(&header, 0, sizeof(struct acpi_table_header));
+	memset(&header, 0, sizeof(struct acpi_table_header));
 	ACPI_MOVE_NAME(header.signature, signature);
-	ACPI_STRNCPY(header.oem_id, oem_id, ACPI_OEM_ID_SIZE);
-	ACPI_STRNCPY(header.oem_table_id, oem_table_id, ACPI_OEM_TABLE_ID_SIZE);
+	strncpy(header.oem_id, oem_id, ACPI_OEM_ID_SIZE);
+	strncpy(header.oem_table_id, oem_table_id, ACPI_OEM_TABLE_ID_SIZE);
 
 	/* Search for the table */
 
 	for (i = 0; i < acpi_gbl_root_table_list.current_table_count; ++i) {
-		if (ACPI_MEMCMP(&(acpi_gbl_root_table_list.tables[i].signature),
-				header.signature, ACPI_NAME_SIZE)) {
+		if (memcmp(&(acpi_gbl_root_table_list.tables[i].signature),
+			   header.signature, ACPI_NAME_SIZE)) {
 
 			/* Not the requested table */
 
@@ -112,21 +112,20 @@
 
 		/* Check for table match on all IDs */
 
-		if (!ACPI_MEMCMP
+		if (!memcmp
 		    (acpi_gbl_root_table_list.tables[i].pointer->signature,
 		     header.signature, ACPI_NAME_SIZE) && (!oem_id[0]
 							   ||
-							   !ACPI_MEMCMP
+							   !memcmp
 							   (acpi_gbl_root_table_list.
 							    tables[i].pointer->
 							    oem_id,
 							    header.oem_id,
 							    ACPI_OEM_ID_SIZE))
 		    && (!oem_table_id[0]
-			|| !ACPI_MEMCMP(acpi_gbl_root_table_list.tables[i].
-					pointer->oem_table_id,
-					header.oem_table_id,
-					ACPI_OEM_TABLE_ID_SIZE))) {
+			|| !memcmp(acpi_gbl_root_table_list.tables[i].pointer->
+				   oem_table_id, header.oem_table_id,
+				   ACPI_OEM_TABLE_ID_SIZE))) {
 			*table_index = i;
 
 			ACPI_DEBUG_PRINT((ACPI_DB_TABLES,
diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c
index 008a251..15ea98e 100644
--- a/drivers/acpi/acpica/tbinstal.c
+++ b/drivers/acpi/acpica/tbinstal.c
@@ -87,8 +87,8 @@
 	 * not just the header.
 	 */
 	is_identical = (u8)((table_desc->length != table_length ||
-			     ACPI_MEMCMP(table_desc->pointer, table,
-					 table_length)) ? FALSE : TRUE);
+			     memcmp(table_desc->pointer, table, table_length)) ?
+			    FALSE : TRUE);
 
 	/* Release the acquired table */
 
@@ -289,8 +289,7 @@
 		if ((new_table_desc.signature.ascii[0] != 0x00) &&
 		    (!ACPI_COMPARE_NAME
 		     (&new_table_desc.signature, ACPI_SIG_SSDT))
-		    && (ACPI_STRNCMP(new_table_desc.signature.ascii, "OEM", 3)))
-		{
+		    && (strncmp(new_table_desc.signature.ascii, "OEM", 3))) {
 			ACPI_BIOS_ERROR((AE_INFO,
 					 "Table has invalid signature [%4.4s] (0x%8.8X), "
 					 "must be SSDT or OEMx",
diff --git a/drivers/acpi/acpica/tbprint.c b/drivers/acpi/acpica/tbprint.c
index 77ba5c7..709d511 100644
--- a/drivers/acpi/acpica/tbprint.c
+++ b/drivers/acpi/acpica/tbprint.c
@@ -73,7 +73,7 @@
 {
 
 	while (length && *string) {
-		if (!ACPI_IS_PRINT(*string)) {
+		if (!isprint((int)*string)) {
 			*string = '?';
 		}
 		string++;
@@ -100,7 +100,7 @@
 			     struct acpi_table_header *header)
 {
 
-	ACPI_MEMCPY(out_header, header, sizeof(struct acpi_table_header));
+	memcpy(out_header, header, sizeof(struct acpi_table_header));
 
 	acpi_tb_fix_string(out_header->signature, ACPI_NAME_SIZE);
 	acpi_tb_fix_string(out_header->oem_id, ACPI_OEM_ID_SIZE);
@@ -138,9 +138,9 @@
 
 		/* RSDP has no common fields */
 
-		ACPI_MEMCPY(local_header.oem_id,
-			    ACPI_CAST_PTR(struct acpi_table_rsdp,
-					  header)->oem_id, ACPI_OEM_ID_SIZE);
+		memcpy(local_header.oem_id,
+		       ACPI_CAST_PTR(struct acpi_table_rsdp, header)->oem_id,
+		       ACPI_OEM_ID_SIZE);
 		acpi_tb_fix_string(local_header.oem_id, ACPI_OEM_ID_SIZE);
 
 		ACPI_INFO((AE_INFO, "RSDP 0x%8.8X%8.8X %06X (v%.2d %-6.6s)",
diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c
index 6559a58..568ac0e 100644
--- a/drivers/acpi/acpica/tbutils.c
+++ b/drivers/acpi/acpica/tbutils.c
@@ -68,7 +68,6 @@
 
 acpi_status acpi_tb_initialize_facs(void)
 {
-	acpi_status status;
 
 	/* If Hardware Reduced flag is set, there is no FACS */
 
@@ -77,11 +76,25 @@
 		return (AE_OK);
 	}
 
-	status = acpi_get_table_by_index(ACPI_TABLE_INDEX_FACS,
-					 ACPI_CAST_INDIRECT_PTR(struct
-								acpi_table_header,
-								&acpi_gbl_FACS));
-	return (status);
+	(void)acpi_get_table_by_index(ACPI_TABLE_INDEX_FACS,
+				      ACPI_CAST_INDIRECT_PTR(struct
+							     acpi_table_header,
+							     &acpi_gbl_facs32));
+	(void)acpi_get_table_by_index(ACPI_TABLE_INDEX_X_FACS,
+				      ACPI_CAST_INDIRECT_PTR(struct
+							     acpi_table_header,
+							     &acpi_gbl_facs64));
+
+	if (acpi_gbl_facs64
+	    && (!acpi_gbl_facs32 || !acpi_gbl_use32_bit_facs_addresses)) {
+		acpi_gbl_FACS = acpi_gbl_facs64;
+	} else if (acpi_gbl_facs32) {
+		acpi_gbl_FACS = acpi_gbl_facs32;
+	}
+
+	/* If there is no FACS, just continue. There was already an error msg */
+
+	return (AE_OK);
 }
 #endif				/* !ACPI_REDUCED_HARDWARE */
 
@@ -101,7 +114,7 @@
 u8 acpi_tb_tables_loaded(void)
 {
 
-	if (acpi_gbl_root_table_list.current_table_count >= 3) {
+	if (acpi_gbl_root_table_list.current_table_count >= 4) {
 		return (TRUE);
 	}
 
@@ -175,7 +188,7 @@
 		return (NULL);
 	}
 
-	ACPI_MEMCPY(new_table, table_desc->pointer, table_desc->length);
+	memcpy(new_table, table_desc->pointer, table_desc->length);
 	acpi_tb_uninstall_table(table_desc);
 
 	acpi_tb_init_table_descriptor(&acpi_gbl_root_table_list.
@@ -357,11 +370,11 @@
 	table_entry = ACPI_ADD_PTR(u8, table, sizeof(struct acpi_table_header));
 
 	/*
-	 * First two entries in the table array are reserved for the DSDT
-	 * and FACS, which are not actually present in the RSDT/XSDT - they
-	 * come from the FADT
+	 * First three entries in the table array are reserved for the DSDT
+	 * and 32bit/64bit FACS, which are not actually present in the
+	 * RSDT/XSDT - they come from the FADT
 	 */
-	acpi_gbl_root_table_list.current_table_count = 2;
+	acpi_gbl_root_table_list.current_table_count = 3;
 
 	/* Initialize the root table array from the RSDT/XSDT */
 
diff --git a/drivers/acpi/acpica/tbxface.c b/drivers/acpi/acpica/tbxface.c
index 60e94f8..5559e2c 100644
--- a/drivers/acpi/acpica/tbxface.c
+++ b/drivers/acpi/acpica/tbxface.c
@@ -119,9 +119,9 @@
 	} else {
 		/* Root Table Array has been statically allocated by the host */
 
-		ACPI_MEMSET(initial_table_array, 0,
-			    (acpi_size) initial_table_count *
-			    sizeof(struct acpi_table_desc));
+		memset(initial_table_array, 0,
+		       (acpi_size) initial_table_count *
+		       sizeof(struct acpi_table_desc));
 
 		acpi_gbl_root_table_list.tables = initial_table_array;
 		acpi_gbl_root_table_list.max_table_count = initial_table_count;
@@ -242,8 +242,9 @@
 				if (!header) {
 					return (AE_NO_MEMORY);
 				}
-				ACPI_MEMCPY(out_table_header, header,
-					    sizeof(struct acpi_table_header));
+
+				memcpy(out_table_header, header,
+				       sizeof(struct acpi_table_header));
 				acpi_os_unmap_memory(header,
 						     sizeof(struct
 							    acpi_table_header));
@@ -251,9 +252,9 @@
 				return (AE_NOT_FOUND);
 			}
 		} else {
-			ACPI_MEMCPY(out_table_header,
-				    acpi_gbl_root_table_list.tables[i].pointer,
-				    sizeof(struct acpi_table_header));
+			memcpy(out_table_header,
+			       acpi_gbl_root_table_list.tables[i].pointer,
+			       sizeof(struct acpi_table_header));
 		}
 		return (AE_OK);
 	}
diff --git a/drivers/acpi/acpica/tbxfload.c b/drivers/acpi/acpica/tbxfload.c
index aadb300..9682d40 100644
--- a/drivers/acpi/acpica/tbxfload.c
+++ b/drivers/acpi/acpica/tbxfload.c
@@ -150,8 +150,8 @@
 	 * Save the original DSDT header for detection of table corruption
 	 * and/or replacement of the DSDT from outside the OS.
 	 */
-	ACPI_MEMCPY(&acpi_gbl_original_dsdt_header, acpi_gbl_DSDT,
-		    sizeof(struct acpi_table_header));
+	memcpy(&acpi_gbl_original_dsdt_header, acpi_gbl_DSDT,
+	       sizeof(struct acpi_table_header));
 
 	(void)acpi_ut_release_mutex(ACPI_MTX_TABLES);
 
@@ -166,13 +166,18 @@
 
 	(void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES);
 	for (i = 0; i < acpi_gbl_root_table_list.current_table_count; ++i) {
-		if ((!ACPI_COMPARE_NAME
+		if (!acpi_gbl_root_table_list.tables[i].address ||
+		    (!ACPI_COMPARE_NAME
 		     (&(acpi_gbl_root_table_list.tables[i].signature),
 		      ACPI_SIG_SSDT)
 		     &&
 		     !ACPI_COMPARE_NAME(&
 					(acpi_gbl_root_table_list.tables[i].
-					 signature), ACPI_SIG_PSDT))
+					 signature), ACPI_SIG_PSDT)
+		     &&
+		     !ACPI_COMPARE_NAME(&
+					(acpi_gbl_root_table_list.tables[i].
+					 signature), ACPI_SIG_OSDT))
 		    ||
 		    ACPI_FAILURE(acpi_tb_validate_table
 				 (&acpi_gbl_root_table_list.tables[i]))) {
@@ -219,9 +224,9 @@
 	ACPI_FUNCTION_TRACE(acpi_install_table);
 
 	if (physical) {
-		flags = ACPI_TABLE_ORIGIN_EXTERNAL_VIRTUAL;
-	} else {
 		flags = ACPI_TABLE_ORIGIN_INTERNAL_PHYSICAL;
+	} else {
+		flags = ACPI_TABLE_ORIGIN_EXTERNAL_VIRTUAL;
 	}
 
 	status = acpi_tb_install_standard_table(address, flags,
diff --git a/drivers/acpi/acpica/utalloc.c b/drivers/acpi/acpica/utalloc.c
index 61d8f6d..7a4101f 100644
--- a/drivers/acpi/acpica/utalloc.c
+++ b/drivers/acpi/acpica/utalloc.c
@@ -73,7 +73,7 @@
 
 		/* Clear the memory block */
 
-		ACPI_MEMSET(allocation, 0, size);
+		memset(allocation, 0, size);
 	}
 
 	return (allocation);
@@ -181,7 +181,7 @@
 	char buffer[7];
 
 	if (acpi_gbl_display_final_mem_stats) {
-		ACPI_STRCPY(buffer, "MEMORY");
+		strcpy(buffer, "MEMORY");
 		(void)acpi_db_display_statistics(buffer);
 	}
 #endif
@@ -337,6 +337,6 @@
 
 	/* Have a valid buffer, clear it */
 
-	ACPI_MEMSET(buffer->pointer, 0, required_length);
+	memset(buffer->pointer, 0, required_length);
 	return (AE_OK);
 }
diff --git a/drivers/acpi/acpica/utbuffer.c b/drivers/acpi/acpica/utbuffer.c
index a8c3964..01c8709 100644
--- a/drivers/acpi/acpica/utbuffer.c
+++ b/drivers/acpi/acpica/utbuffer.c
@@ -159,7 +159,7 @@
 			}
 
 			buf_char = buffer[(acpi_size) i + j];
-			if (ACPI_IS_PRINT(buf_char)) {
+			if (isprint(buf_char)) {
 				acpi_os_printf("%c", buf_char);
 			} else {
 				acpi_os_printf(".");
@@ -319,7 +319,7 @@
 			}
 
 			buf_char = buffer[(acpi_size) i + j];
-			if (ACPI_IS_PRINT(buf_char)) {
+			if (isprint(buf_char)) {
 				acpi_ut_file_printf(file, "%c", buf_char);
 			} else {
 				acpi_ut_file_printf(file, ".");
diff --git a/drivers/acpi/acpica/utcache.c b/drivers/acpi/acpica/utcache.c
index eacc5ee..0d21fbd 100644
--- a/drivers/acpi/acpica/utcache.c
+++ b/drivers/acpi/acpica/utcache.c
@@ -84,7 +84,7 @@
 
 	/* Populate the cache object and return it */
 
-	ACPI_MEMSET(cache, 0, sizeof(struct acpi_memory_list));
+	memset(cache, 0, sizeof(struct acpi_memory_list));
 	cache->list_name = cache_name;
 	cache->object_size = object_size;
 	cache->max_depth = max_depth;
@@ -212,7 +212,7 @@
 
 		/* Mark the object as cached */
 
-		ACPI_MEMSET(object, 0xCA, cache->object_size);
+		memset(object, 0xCA, cache->object_size);
 		ACPI_SET_DESCRIPTOR_TYPE(object, ACPI_DESC_TYPE_CACHED);
 
 		/* Put the object at the head of the cache list */
@@ -281,7 +281,7 @@
 
 		/* Clear (zero) the previously used Object */
 
-		ACPI_MEMSET(object, 0, cache->object_size);
+		memset(object, 0, cache->object_size);
 	} else {
 		/* The cache is empty, create a new object */
 
diff --git a/drivers/acpi/acpica/utcopy.c b/drivers/acpi/acpica/utcopy.c
index c37ec50..257221d 100644
--- a/drivers/acpi/acpica/utcopy.c
+++ b/drivers/acpi/acpica/utcopy.c
@@ -129,7 +129,7 @@
 
 	/* Always clear the external object */
 
-	ACPI_MEMSET(external_object, 0, sizeof(union acpi_object));
+	memset(external_object, 0, sizeof(union acpi_object));
 
 	/*
 	 * In general, the external object will be the same type as
@@ -149,9 +149,9 @@
 								  string.
 								  length + 1);
 
-		ACPI_MEMCPY((void *)data_space,
-			    (void *)internal_object->string.pointer,
-			    (acpi_size) internal_object->string.length + 1);
+		memcpy((void *)data_space,
+		       (void *)internal_object->string.pointer,
+		       (acpi_size) internal_object->string.length + 1);
 		break;
 
 	case ACPI_TYPE_BUFFER:
@@ -162,9 +162,9 @@
 		    ACPI_ROUND_UP_TO_NATIVE_WORD(internal_object->string.
 						 length);
 
-		ACPI_MEMCPY((void *)data_space,
-			    (void *)internal_object->buffer.pointer,
-			    internal_object->buffer.length);
+		memcpy((void *)data_space,
+		       (void *)internal_object->buffer.pointer,
+		       internal_object->buffer.length);
 		break;
 
 	case ACPI_TYPE_INTEGER:
@@ -502,9 +502,9 @@
 			goto error_exit;
 		}
 
-		ACPI_MEMCPY(internal_object->string.pointer,
-			    external_object->string.pointer,
-			    external_object->string.length);
+		memcpy(internal_object->string.pointer,
+		       external_object->string.pointer,
+		       external_object->string.length);
 
 		internal_object->string.length = external_object->string.length;
 		break;
@@ -517,9 +517,9 @@
 			goto error_exit;
 		}
 
-		ACPI_MEMCPY(internal_object->buffer.pointer,
-			    external_object->buffer.pointer,
-			    external_object->buffer.length);
+		memcpy(internal_object->buffer.pointer,
+		       external_object->buffer.pointer,
+		       external_object->buffer.length);
 
 		internal_object->buffer.length = external_object->buffer.length;
 
@@ -694,8 +694,8 @@
 		copy_size = sizeof(struct acpi_namespace_node);
 	}
 
-	ACPI_MEMCPY(ACPI_CAST_PTR(char, dest_desc),
-		    ACPI_CAST_PTR(char, source_desc), copy_size);
+	memcpy(ACPI_CAST_PTR(char, dest_desc),
+	       ACPI_CAST_PTR(char, source_desc), copy_size);
 
 	/* Restore the saved fields */
 
@@ -725,9 +725,9 @@
 
 			/* Copy the actual buffer data */
 
-			ACPI_MEMCPY(dest_desc->buffer.pointer,
-				    source_desc->buffer.pointer,
-				    source_desc->buffer.length);
+			memcpy(dest_desc->buffer.pointer,
+			       source_desc->buffer.pointer,
+			       source_desc->buffer.length);
 		}
 		break;
 
@@ -747,9 +747,9 @@
 
 			/* Copy the actual string data */
 
-			ACPI_MEMCPY(dest_desc->string.pointer,
-				    source_desc->string.pointer,
-				    (acpi_size) source_desc->string.length + 1);
+			memcpy(dest_desc->string.pointer,
+			       source_desc->string.pointer,
+			       (acpi_size) source_desc->string.length + 1);
 		}
 		break;
 
diff --git a/drivers/acpi/acpica/utdebug.c b/drivers/acpi/acpica/utdebug.c
index 4f3f888..cd02693 100644
--- a/drivers/acpi/acpica/utdebug.c
+++ b/drivers/acpi/acpica/utdebug.c
@@ -111,8 +111,8 @@
  * RETURN:      Updated pointer to the function name
  *
  * DESCRIPTION: Remove the "Acpi" prefix from the function name, if present.
- *              This allows compiler macros such as __func__ to be used with no
- *              change to the debug output.
+ *              This allows compiler macros such as __func__ to be used
+ *              with no change to the debug output.
  *
  ******************************************************************************/
 
diff --git a/drivers/acpi/acpica/utglobal.c b/drivers/acpi/acpica/utglobal.c
index 5e8df91..a72685c 100644
--- a/drivers/acpi/acpica/utglobal.c
+++ b/drivers/acpi/acpica/utglobal.c
@@ -102,12 +102,19 @@
 	{"_SB_", ACPI_TYPE_DEVICE, NULL},
 	{"_SI_", ACPI_TYPE_LOCAL_SCOPE, NULL},
 	{"_TZ_", ACPI_TYPE_DEVICE, NULL},
-	{"_REV", ACPI_TYPE_INTEGER, (char *)ACPI_CA_SUPPORT_LEVEL},
+	/*
+	 * March, 2015:
+	 * The _REV object is in the process of being deprecated, because
+	 * other ACPI implementations permanently return 2. Thus, it
+	 * has little or no value. Return 2 for compatibility with
+	 * other ACPI implementations.
+	 */
+	{"_REV", ACPI_TYPE_INTEGER, ACPI_CAST_PTR(char, 2)},
 	{"_OS_", ACPI_TYPE_STRING, ACPI_OS_NAME},
-	{"_GL_", ACPI_TYPE_MUTEX, (char *)1},
+	{"_GL_", ACPI_TYPE_MUTEX, ACPI_CAST_PTR(char, 1)},
 
 #if !defined (ACPI_NO_METHOD_EXECUTION) || defined (ACPI_CONSTANT_EVAL_ONLY)
-	{"_OSI", ACPI_TYPE_METHOD, (char *)1},
+	{"_OSI", ACPI_TYPE_METHOD, ACPI_CAST_PTR(char, 1)},
 #endif
 
 	/* Table terminator */
diff --git a/drivers/acpi/acpica/utids.c b/drivers/acpi/acpica/utids.c
index 27431cf..7956df1e 100644
--- a/drivers/acpi/acpica/utids.c
+++ b/drivers/acpi/acpica/utids.c
@@ -1,6 +1,6 @@
 /******************************************************************************
  *
- * Module Name: utids - support for device Ids - HID, UID, CID
+ * Module Name: utids - support for device Ids - HID, UID, CID, SUB, CLS
  *
  *****************************************************************************/
 
@@ -111,7 +111,7 @@
 	if (obj_desc->common.type == ACPI_TYPE_INTEGER) {
 		acpi_ex_eisa_id_to_string(hid->string, obj_desc->integer.value);
 	} else {
-		ACPI_STRCPY(hid->string, obj_desc->string.pointer);
+		strcpy(hid->string, obj_desc->string.pointer);
 	}
 
 	hid->length = length;
@@ -180,7 +180,7 @@
 
 	/* Simply copy existing string */
 
-	ACPI_STRCPY(sub->string, obj_desc->string.pointer);
+	strcpy(sub->string, obj_desc->string.pointer);
 	sub->length = length;
 	*return_id = sub;
 
@@ -256,7 +256,7 @@
 	if (obj_desc->common.type == ACPI_TYPE_INTEGER) {
 		acpi_ex_integer_to_string(uid->string, obj_desc->integer.value);
 	} else {
-		ACPI_STRCPY(uid->string, obj_desc->string.pointer);
+		strcpy(uid->string, obj_desc->string.pointer);
 	}
 
 	uid->length = length;
@@ -393,8 +393,7 @@
 
 			/* Copy the String CID from the returned object */
 
-			ACPI_STRCPY(next_id_string,
-				    cid_objects[i]->string.pointer);
+			strcpy(next_id_string, cid_objects[i]->string.pointer);
 			length = cid_objects[i]->string.length + 1;
 		}
 
@@ -416,3 +415,92 @@
 	acpi_ut_remove_reference(obj_desc);
 	return_ACPI_STATUS(status);
 }
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ut_execute_CLS
+ *
+ * PARAMETERS:  device_node         - Node for the device
+ *              return_id           - Where the _CLS is returned
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Executes the _CLS control method that returns PCI-defined
+ *              class code of the device. The _CLS value is always a package
+ *              containing PCI class information as a list of integers.
+ *              The returned string has format "BBSSPP", where:
+ *                BB = Base-class code
+ *                SS = Sub-class code
+ *                PP = Programming Interface code
+ *
+ ******************************************************************************/
+
+acpi_status
+acpi_ut_execute_CLS(struct acpi_namespace_node *device_node,
+		    struct acpi_pnp_device_id **return_id)
+{
+	union acpi_operand_object *obj_desc;
+	union acpi_operand_object **cls_objects;
+	u32 count;
+	struct acpi_pnp_device_id *cls;
+	u32 length;
+	acpi_status status;
+	u8 class_code[3] = { 0, 0, 0 };
+
+	ACPI_FUNCTION_TRACE(ut_execute_CLS);
+
+	status = acpi_ut_evaluate_object(device_node, METHOD_NAME__CLS,
+					 ACPI_BTYPE_PACKAGE, &obj_desc);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	/* Get the size of the String to be returned, includes null terminator */
+
+	length = ACPI_PCICLS_STRING_SIZE;
+	cls_objects = obj_desc->package.elements;
+	count = obj_desc->package.count;
+
+	if (obj_desc->common.type == ACPI_TYPE_PACKAGE) {
+		if (count > 0
+		    && cls_objects[0]->common.type == ACPI_TYPE_INTEGER) {
+			class_code[0] = (u8)cls_objects[0]->integer.value;
+		}
+		if (count > 1
+		    && cls_objects[1]->common.type == ACPI_TYPE_INTEGER) {
+			class_code[1] = (u8)cls_objects[1]->integer.value;
+		}
+		if (count > 2
+		    && cls_objects[2]->common.type == ACPI_TYPE_INTEGER) {
+			class_code[2] = (u8)cls_objects[2]->integer.value;
+		}
+	}
+
+	/* Allocate a buffer for the CLS */
+
+	cls =
+	    ACPI_ALLOCATE_ZEROED(sizeof(struct acpi_pnp_device_id) +
+				 (acpi_size) length);
+	if (!cls) {
+		status = AE_NO_MEMORY;
+		goto cleanup;
+	}
+
+	/* Area for the string starts after PNP_DEVICE_ID struct */
+
+	cls->string =
+	    ACPI_ADD_PTR(char, cls, sizeof(struct acpi_pnp_device_id));
+
+	/* Simply copy existing string */
+
+	acpi_ex_pci_cls_to_string(cls->string, class_code);
+	cls->length = length;
+	*return_id = cls;
+
+cleanup:
+
+	/* On exit, we must delete the return object */
+
+	acpi_ut_remove_reference(obj_desc);
+	return_ACPI_STATUS(status);
+}
diff --git a/drivers/acpi/acpica/utmisc.c b/drivers/acpi/acpica/utmisc.c
index cbb7034..71b6653 100644
--- a/drivers/acpi/acpica/utmisc.c
+++ b/drivers/acpi/acpica/utmisc.c
@@ -66,9 +66,9 @@
 	 * Check if this is a PCI root bridge.
 	 * ACPI 3.0+: check for a PCI Express root also.
 	 */
-	if (!(ACPI_STRCMP(id,
-			  PCI_ROOT_HID_STRING)) ||
-	    !(ACPI_STRCMP(id, PCI_EXPRESS_ROOT_HID_STRING))) {
+	if (!(strcmp(id,
+		     PCI_ROOT_HID_STRING)) ||
+	    !(strcmp(id, PCI_EXPRESS_ROOT_HID_STRING))) {
 		return (TRUE);
 	}
 
@@ -97,7 +97,8 @@
 
 	if (ACPI_COMPARE_NAME(table->signature, ACPI_SIG_DSDT) ||
 	    ACPI_COMPARE_NAME(table->signature, ACPI_SIG_PSDT) ||
-	    ACPI_COMPARE_NAME(table->signature, ACPI_SIG_SSDT)) {
+	    ACPI_COMPARE_NAME(table->signature, ACPI_SIG_SSDT) ||
+	    ACPI_COMPARE_NAME(table->signature, ACPI_SIG_OSDT)) {
 		return (TRUE);
 	}
 
diff --git a/drivers/acpi/acpica/utosi.c b/drivers/acpi/acpica/utosi.c
index 44035ab..8f3d203a 100644
--- a/drivers/acpi/acpica/utosi.c
+++ b/drivers/acpi/acpica/utosi.c
@@ -232,8 +232,7 @@
 		return (AE_NO_MEMORY);
 	}
 
-	interface_info->name =
-	    ACPI_ALLOCATE_ZEROED(ACPI_STRLEN(interface_name) + 1);
+	interface_info->name = ACPI_ALLOCATE_ZEROED(strlen(interface_name) + 1);
 	if (!interface_info->name) {
 		ACPI_FREE(interface_info);
 		return (AE_NO_MEMORY);
@@ -241,7 +240,7 @@
 
 	/* Initialize new info and insert at the head of the global list */
 
-	ACPI_STRCPY(interface_info->name, interface_name);
+	strcpy(interface_info->name, interface_name);
 	interface_info->flags = ACPI_OSI_DYNAMIC;
 	interface_info->next = acpi_gbl_supported_interfaces;
 
@@ -269,7 +268,7 @@
 
 	previous_interface = next_interface = acpi_gbl_supported_interfaces;
 	while (next_interface) {
-		if (!ACPI_STRCMP(interface_name, next_interface->name)) {
+		if (!strcmp(interface_name, next_interface->name)) {
 
 			/* Found: name is in either the static list or was added at runtime */
 
@@ -373,7 +372,7 @@
 
 	next_interface = acpi_gbl_supported_interfaces;
 	while (next_interface) {
-		if (!ACPI_STRCMP(interface_name, next_interface->name)) {
+		if (!strcmp(interface_name, next_interface->name)) {
 			return (next_interface);
 		}
 
diff --git a/drivers/acpi/acpica/utpredef.c b/drivers/acpi/acpica/utpredef.c
index 29e4499..97898ed 100644
--- a/drivers/acpi/acpica/utpredef.c
+++ b/drivers/acpi/acpica/utpredef.c
@@ -148,7 +148,7 @@
 	u32 j;
 
 	if (!expected_btypes) {
-		ACPI_STRCPY(buffer, "NONE");
+		strcpy(buffer, "NONE");
 		return;
 	}
 
@@ -161,7 +161,7 @@
 		/* If one of the expected types, concatenate the name of this type */
 
 		if (expected_btypes & this_rtype) {
-			ACPI_STRCAT(buffer, &ut_rtype_names[i][j]);
+			strcat(buffer, &ut_rtype_names[i][j]);
 			j = 0;	/* Use name separator from now on */
 		}
 
diff --git a/drivers/acpi/acpica/utprint.c b/drivers/acpi/acpica/utprint.c
index 2be6bd4..b26297c 100644
--- a/drivers/acpi/acpica/utprint.c
+++ b/drivers/acpi/acpica/utprint.c
@@ -180,7 +180,7 @@
 {
 	u64 number = 0;
 
-	while (ACPI_IS_DIGIT(*string)) {
+	while (isdigit((int)*string)) {
 		number *= 10;
 		number += *(string++) - '0';
 	}
@@ -405,7 +405,7 @@
 		/* Process width */
 
 		width = -1;
-		if (ACPI_IS_DIGIT(*format)) {
+		if (isdigit((int)*format)) {
 			format = acpi_ut_scan_number(format, &number);
 			width = (s32) number;
 		} else if (*format == '*') {
@@ -422,7 +422,7 @@
 		precision = -1;
 		if (*format == '.') {
 			++format;
-			if (ACPI_IS_DIGIT(*format)) {
+			if (isdigit((int)*format)) {
 				format = acpi_ut_scan_number(format, &number);
 				precision = (s32) number;
 			} else if (*format == '*') {
diff --git a/drivers/acpi/acpica/utstring.c b/drivers/acpi/acpica/utstring.c
index 83b6c52..8f3c883 100644
--- a/drivers/acpi/acpica/utstring.c
+++ b/drivers/acpi/acpica/utstring.c
@@ -79,7 +79,7 @@
 	/* Walk entire string, lowercasing the letters */
 
 	for (string = src_string; *string; string++) {
-		*string = (char)ACPI_TOLOWER(*string);
+		*string = (char)tolower((int)*string);
 	}
 
 	return;
@@ -145,7 +145,7 @@
 	/* Walk entire string, uppercasing the letters */
 
 	for (string = src_string; *string; string++) {
-		*string = (char)ACPI_TOUPPER(*string);
+		*string = (char)toupper((int)*string);
 	}
 
 	return;
@@ -202,7 +202,7 @@
 
 	/* Skip over any white space in the buffer */
 
-	while ((*string) && (ACPI_IS_SPACE(*string) || *string == '\t')) {
+	while ((*string) && (isspace((int)*string) || *string == '\t')) {
 		string++;
 	}
 
@@ -211,7 +211,7 @@
 		 * Base equal to ACPI_ANY_BASE means 'ToInteger operation case'.
 		 * We need to determine if it is decimal or hexadecimal.
 		 */
-		if ((*string == '0') && (ACPI_TOLOWER(*(string + 1)) == 'x')) {
+		if ((*string == '0') && (tolower((int)*(string + 1)) == 'x')) {
 			sign_of0x = 1;
 			base = 16;
 
@@ -224,7 +224,7 @@
 
 	/* Any string left? Check that '0x' is not followed by white space. */
 
-	if (!(*string) || ACPI_IS_SPACE(*string) || *string == '\t') {
+	if (!(*string) || isspace((int)*string) || *string == '\t') {
 		if (to_integer_op) {
 			goto error_exit;
 		} else {
@@ -241,7 +241,7 @@
 	/* Main loop: convert the string to a 32- or 64-bit integer */
 
 	while (*string) {
-		if (ACPI_IS_DIGIT(*string)) {
+		if (isdigit((int)*string)) {
 
 			/* Convert ASCII 0-9 to Decimal value */
 
@@ -252,8 +252,8 @@
 
 			term = 1;
 		} else {
-			this_digit = (u8)ACPI_TOUPPER(*string);
-			if (ACPI_IS_XDIGIT((char)this_digit)) {
+			this_digit = (u8)toupper((int)*string);
+			if (isxdigit((int)this_digit)) {
 
 				/* Convert ASCII Hex char to value */
 
@@ -404,7 +404,7 @@
 
 			/* Check for printable character or hex escape */
 
-			if (ACPI_IS_PRINT(string[i])) {
+			if (isprint((int)string[i])) {
 				/* This is a normal character */
 
 				acpi_os_printf("%c", (int)string[i]);
@@ -609,22 +609,22 @@
 u8 acpi_ut_safe_strcpy(char *dest, acpi_size dest_size, char *source)
 {
 
-	if (ACPI_STRLEN(source) >= dest_size) {
+	if (strlen(source) >= dest_size) {
 		return (TRUE);
 	}
 
-	ACPI_STRCPY(dest, source);
+	strcpy(dest, source);
 	return (FALSE);
 }
 
 u8 acpi_ut_safe_strcat(char *dest, acpi_size dest_size, char *source)
 {
 
-	if ((ACPI_STRLEN(dest) + ACPI_STRLEN(source)) >= dest_size) {
+	if ((strlen(dest) + strlen(source)) >= dest_size) {
 		return (TRUE);
 	}
 
-	ACPI_STRCAT(dest, source);
+	strcat(dest, source);
 	return (FALSE);
 }
 
@@ -635,14 +635,13 @@
 {
 	acpi_size actual_transfer_length;
 
-	actual_transfer_length =
-	    ACPI_MIN(max_transfer_length, ACPI_STRLEN(source));
+	actual_transfer_length = ACPI_MIN(max_transfer_length, strlen(source));
 
-	if ((ACPI_STRLEN(dest) + actual_transfer_length) >= dest_size) {
+	if ((strlen(dest) + actual_transfer_length) >= dest_size) {
 		return (TRUE);
 	}
 
-	ACPI_STRNCAT(dest, source, max_transfer_length);
+	strncat(dest, source, max_transfer_length);
 	return (FALSE);
 }
 #endif
diff --git a/drivers/acpi/acpica/uttrack.c b/drivers/acpi/acpica/uttrack.c
index 130dd9f..9a7dc81 100644
--- a/drivers/acpi/acpica/uttrack.c
+++ b/drivers/acpi/acpica/uttrack.c
@@ -100,7 +100,7 @@
 		return (AE_NO_MEMORY);
 	}
 
-	ACPI_MEMSET(cache, 0, sizeof(struct acpi_memory_list));
+	memset(cache, 0, sizeof(struct acpi_memory_list));
 
 	cache->list_name = list_name;
 	cache->object_size = object_size;
@@ -402,7 +402,7 @@
 	allocation->component = component;
 	allocation->line = line;
 
-	ACPI_STRNCPY(allocation->module, module, ACPI_MAX_MODULE_NAME);
+	strncpy(allocation->module, module, ACPI_MAX_MODULE_NAME);
 	allocation->module[ACPI_MAX_MODULE_NAME - 1] = 0;
 
 	if (!element) {
@@ -497,7 +497,7 @@
 
 	/* Mark the segment as deleted */
 
-	ACPI_MEMSET(&allocation->user_space, 0xEA, allocation->size);
+	memset(&allocation->user_space, 0xEA, allocation->size);
 
 	status = acpi_ut_release_mutex(ACPI_MTX_MEMORY);
 	return (status);
@@ -595,7 +595,7 @@
 	while (element) {
 		if ((element->component & component) &&
 		    ((module == NULL)
-		     || (0 == ACPI_STRCMP(module, element->module)))) {
+		     || (0 == strcmp(module, element->module)))) {
 			descriptor =
 			    ACPI_CAST_PTR(union acpi_descriptor,
 					  &element->user_space);
diff --git a/drivers/acpi/acpica/utxface.c b/drivers/acpi/acpica/utxface.c
index 0929187..51cf52d 100644
--- a/drivers/acpi/acpica/utxface.c
+++ b/drivers/acpi/acpica/utxface.c
@@ -234,8 +234,8 @@
 	stats->sci_count = acpi_sci_count;
 	stats->gpe_count = acpi_gpe_count;
 
-	ACPI_MEMCPY(stats->fixed_event_count, acpi_fixed_event_count,
-		    sizeof(acpi_fixed_event_count));
+	memcpy(stats->fixed_event_count, acpi_fixed_event_count,
+	       sizeof(acpi_fixed_event_count));
 
 	/* Other counters */
 
@@ -322,7 +322,7 @@
 
 	/* Parameter validation */
 
-	if (!interface_name || (ACPI_STRLEN(interface_name) == 0)) {
+	if (!interface_name || (strlen(interface_name) == 0)) {
 		return (AE_BAD_PARAMETER);
 	}
 
@@ -374,7 +374,7 @@
 
 	/* Parameter validation */
 
-	if (!interface_name || (ACPI_STRLEN(interface_name) == 0)) {
+	if (!interface_name || (strlen(interface_name) == 0)) {
 		return (AE_BAD_PARAMETER);
 	}
 
diff --git a/drivers/acpi/acpica/utxfinit.c b/drivers/acpi/acpica/utxfinit.c
index 083a768..42a32a6 100644
--- a/drivers/acpi/acpica/utxfinit.c
+++ b/drivers/acpi/acpica/utxfinit.c
@@ -179,10 +179,12 @@
 	 * Obtain a permanent mapping for the FACS. This is required for the
 	 * Global Lock and the Firmware Waking Vector
 	 */
-	status = acpi_tb_initialize_facs();
-	if (ACPI_FAILURE(status)) {
-		ACPI_WARNING((AE_INFO, "Could not map the FACS table"));
-		return_ACPI_STATUS(status);
+	if (!(flags & ACPI_NO_FACS_INIT)) {
+		status = acpi_tb_initialize_facs();
+		if (ACPI_FAILURE(status)) {
+			ACPI_WARNING((AE_INFO, "Could not map the FACS table"));
+			return_ACPI_STATUS(status);
+		}
 	}
 #endif				/* !ACPI_REDUCED_HARDWARE */
 
diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c
index 1d17919..278dc4b 100644
--- a/drivers/acpi/blacklist.c
+++ b/drivers/acpi/blacklist.c
@@ -162,6 +162,15 @@
 	acpi_osi_setup("!Windows 2012");
 	return 0;
 }
+#ifdef CONFIG_ACPI_REV_OVERRIDE_POSSIBLE
+static int __init dmi_enable_rev_override(const struct dmi_system_id *d)
+{
+	printk(KERN_NOTICE PREFIX "DMI detected: %s (force ACPI _REV to 5)\n",
+	       d->ident);
+	acpi_rev_override_setup(NULL);
+	return 0;
+}
+#endif
 
 static struct dmi_system_id acpi_osi_dmi_table[] __initdata = {
 	{
@@ -325,6 +334,23 @@
 		     DMI_MATCH(DMI_PRODUCT_NAME, "1015PX"),
 		},
 	},
+
+#ifdef CONFIG_ACPI_REV_OVERRIDE_POSSIBLE
+	/*
+	 * DELL XPS 13 (2015) switches sound between HDA and I2S
+	 * depending on the ACPI _REV callback. If userspace supports
+	 * I2S sufficiently (or if you do not care about sound), you
+	 * can safely disable this quirk.
+	 */
+	{
+	 .callback = dmi_enable_rev_override,
+	 .ident = "DELL XPS 13 (2015)",
+	 .matches = {
+		      DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		      DMI_MATCH(DMI_PRODUCT_NAME, "XPS 13 9343"),
+		},
+	},
+#endif
 	{}
 };
 
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 787c629..4683a96 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -58,6 +58,7 @@
 #else
 static inline void acpi_cmos_rtc_init(void) {}
 #endif
+int acpi_rev_override_setup(char *str);
 
 extern bool acpi_force_hot_remove;
 
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index a5dc903..c262e4a 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -530,6 +530,19 @@
 }
 #endif
 
+#ifdef CONFIG_ACPI_REV_OVERRIDE_POSSIBLE
+static bool acpi_rev_override;
+
+int __init acpi_rev_override_setup(char *str)
+{
+	acpi_rev_override = true;
+	return 1;
+}
+__setup("acpi_rev_override", acpi_rev_override_setup);
+#else
+#define acpi_rev_override	false
+#endif
+
 #define ACPI_MAX_OVERRIDE_LEN 100
 
 static char acpi_os_name[ACPI_MAX_OVERRIDE_LEN];
@@ -548,6 +561,11 @@
 		*new_val = acpi_os_name;
 	}
 
+	if (!memcmp(init_val->name, "_REV", 4) && acpi_rev_override) {
+		printk(KERN_INFO PREFIX "Overriding _REV return value to 5\n");
+		*new_val = (char *)5;
+	}
+
 	return AE_OK;
 }
 
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index fcb7807..10561ce 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -660,8 +660,10 @@
 		return -ENOMEM;
 
 	error = request_range(start, end, space_id, flags, desc);
-	if (error)
+	if (error) {
+		kfree(reg);
 		return error;
+	}
 
 	reg->start = start;
 	reg->end = end;
diff --git a/drivers/base/node.c b/drivers/base/node.c
index a2aa65b..31df474d 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -359,12 +359,16 @@
 #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
 #define page_initialized(page)  (page->lru.next)
 
-static int get_nid_for_pfn(unsigned long pfn)
+static int __init_refok get_nid_for_pfn(unsigned long pfn)
 {
 	struct page *page;
 
 	if (!pfn_valid_within(pfn))
 		return -1;
+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+	if (system_state == SYSTEM_BOOTING)
+		return early_pfn_to_nid(pfn);
+#endif
 	page = pfn_to_page(pfn);
 	if (!page_initialized(page))
 		return -1;
diff --git a/drivers/base/property.c b/drivers/base/property.c
index e645852..f3f6d16 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -129,9 +129,9 @@
 bool fwnode_property_present(struct fwnode_handle *fwnode, const char *propname)
 {
 	if (is_of_node(fwnode))
-		return of_property_read_bool(of_node(fwnode), propname);
+		return of_property_read_bool(to_of_node(fwnode), propname);
 	else if (is_acpi_node(fwnode))
-		return !acpi_dev_prop_get(acpi_node(fwnode), propname, NULL);
+		return !acpi_dev_prop_get(to_acpi_node(fwnode), propname, NULL);
 
 	return !!pset_prop_get(to_pset(fwnode), propname);
 }
@@ -286,10 +286,10 @@
 ({ \
 	int _ret_; \
 	if (is_of_node(_fwnode_)) \
-		_ret_ = OF_DEV_PROP_READ_ARRAY(of_node(_fwnode_), _propname_, \
+		_ret_ = OF_DEV_PROP_READ_ARRAY(to_of_node(_fwnode_), _propname_, \
 					       _type_, _val_, _nval_); \
 	else if (is_acpi_node(_fwnode_)) \
-		_ret_ = acpi_dev_prop_read(acpi_node(_fwnode_), _propname_, \
+		_ret_ = acpi_dev_prop_read(to_acpi_node(_fwnode_), _propname_, \
 					   _proptype_, _val_, _nval_); \
 	else \
 		_ret_ = pset_prop_read_array(to_pset(_fwnode_), _propname_, \
@@ -425,11 +425,11 @@
 {
 	if (is_of_node(fwnode))
 		return val ?
-			of_property_read_string_array(of_node(fwnode), propname,
-						      val, nval) :
-			of_property_count_strings(of_node(fwnode), propname);
+			of_property_read_string_array(to_of_node(fwnode),
+						      propname, val, nval) :
+			of_property_count_strings(to_of_node(fwnode), propname);
 	else if (is_acpi_node(fwnode))
-		return acpi_dev_prop_read(acpi_node(fwnode), propname,
+		return acpi_dev_prop_read(to_acpi_node(fwnode), propname,
 					  DEV_PROP_STRING, val, nval);
 
 	return pset_prop_read_array(to_pset(fwnode), propname,
@@ -456,9 +456,9 @@
 				const char *propname, const char **val)
 {
 	if (is_of_node(fwnode))
-		return of_property_read_string(of_node(fwnode), propname, val);
+		return of_property_read_string(to_of_node(fwnode), propname, val);
 	else if (is_acpi_node(fwnode))
-		return acpi_dev_prop_read(acpi_node(fwnode), propname,
+		return acpi_dev_prop_read(to_acpi_node(fwnode), propname,
 					  DEV_PROP_STRING, val, 1);
 
 	return -ENXIO;
@@ -476,13 +476,13 @@
 	if (IS_ENABLED(CONFIG_OF) && dev->of_node) {
 		struct device_node *node;
 
-		node = of_get_next_available_child(dev->of_node, of_node(child));
+		node = of_get_next_available_child(dev->of_node, to_of_node(child));
 		if (node)
 			return &node->fwnode;
 	} else if (IS_ENABLED(CONFIG_ACPI)) {
 		struct acpi_device *node;
 
-		node = acpi_get_next_child(dev, acpi_node(child));
+		node = acpi_get_next_child(dev, to_acpi_node(child));
 		if (node)
 			return acpi_fwnode_handle(node);
 	}
@@ -501,7 +501,7 @@
 void fwnode_handle_put(struct fwnode_handle *fwnode)
 {
 	if (is_of_node(fwnode))
-		of_node_put(of_node(fwnode));
+		of_node_put(to_of_node(fwnode));
 }
 EXPORT_SYMBOL_GPL(fwnode_handle_put);
 
diff --git a/drivers/block/drbd/drbd_debugfs.c b/drivers/block/drbd/drbd_debugfs.c
index a6ee3d7..6b88a35 100644
--- a/drivers/block/drbd/drbd_debugfs.c
+++ b/drivers/block/drbd/drbd_debugfs.c
@@ -419,14 +419,6 @@
 	return 0;
 }
 
-/* simple_positive(file->f_path.dentry) respectively debugfs_positive(),
- * but neither is "reachable" from here.
- * So we have our own inline version of it above.  :-( */
-static inline int debugfs_positive(struct dentry *dentry)
-{
-        return d_really_is_positive(dentry) && !d_unhashed(dentry);
-}
-
 /* make sure at *open* time that the respective object won't go away. */
 static int drbd_single_open(struct file *file, int (*show)(struct seq_file *, void *),
 		                void *data, struct kref *kref,
@@ -444,7 +436,7 @@
 	/* serialize with d_delete() */
 	mutex_lock(&d_inode(parent)->i_mutex);
 	/* Make sure the object is still alive */
-	if (debugfs_positive(file->f_path.dentry)
+	if (simple_positive(file->f_path.dentry)
 	&& kref_get_unless_zero(kref))
 		ret = 0;
 	mutex_unlock(&d_inode(parent)->i_mutex);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 40580dc..f7a4c9d 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -588,7 +588,7 @@
 
 	spin_lock_irq(&lo->lo_lock);
 	if (lo->lo_backing_file)
-		p = d_path(&lo->lo_backing_file->f_path, buf, PAGE_SIZE - 1);
+		p = file_path(lo->lo_backing_file, buf, PAGE_SIZE - 1);
 	spin_unlock_irq(&lo->lo_lock);
 
 	if (IS_ERR_OR_NULL(p))
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 6f9b753..69de41a 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -99,7 +99,7 @@
 	return null_param_store_val(str, &queue_mode, NULL_Q_BIO, NULL_Q_MQ);
 }
 
-static struct kernel_param_ops null_queue_mode_param_ops = {
+static const struct kernel_param_ops null_queue_mode_param_ops = {
 	.set	= null_set_queue_mode,
 	.get	= param_get_int,
 };
@@ -127,7 +127,7 @@
 					NULL_IRQ_TIMER);
 }
 
-static struct kernel_param_ops null_irqmode_param_ops = {
+static const struct kernel_param_ops null_irqmode_param_ops = {
 	.set	= null_set_irqmode,
 	.get	= param_get_int,
 };
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index 34338d7..d1d6141 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -1474,6 +1474,7 @@
 	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
 	nvmeq->q_depth = depth;
 	nvmeq->qid = qid;
+	nvmeq->cq_vector = -1;
 	dev->queues[qid] = nvmeq;
 
 	/* make sure queue descriptor is set before queue count, for kthread */
@@ -1726,8 +1727,10 @@
 
 	nvmeq->cq_vector = 0;
 	result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
-	if (result)
+	if (result) {
+		nvmeq->cq_vector = -1;
 		goto free_nvmeq;
+	}
 
 	return result;
 
@@ -2213,8 +2216,10 @@
 	dev->max_qid = nr_io_queues;
 
 	result = queue_request_irq(dev, adminq, adminq->irqname);
-	if (result)
+	if (result) {
+		adminq->cq_vector = -1;
 		goto free_queues;
+	}
 
 	/* Free previously allocated queues that are no longer usable */
 	nvme_free_queues(dev, nr_io_queues + 1);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index ec6c5c6..d94529d 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -346,6 +346,7 @@
 	struct rbd_image_header	header;
 	unsigned long		flags;		/* possibly lock protected */
 	struct rbd_spec		*spec;
+	struct rbd_options	*opts;
 
 	char			*header_name;
 
@@ -724,34 +725,36 @@
 }
 
 /*
- * mount options
+ * (Per device) rbd map options
  */
 enum {
+	Opt_queue_depth,
 	Opt_last_int,
 	/* int args above */
 	Opt_last_string,
 	/* string args above */
 	Opt_read_only,
 	Opt_read_write,
-	/* Boolean args above */
-	Opt_last_bool,
+	Opt_err
 };
 
 static match_table_t rbd_opts_tokens = {
+	{Opt_queue_depth, "queue_depth=%d"},
 	/* int args above */
 	/* string args above */
 	{Opt_read_only, "read_only"},
 	{Opt_read_only, "ro"},		/* Alternate spelling */
 	{Opt_read_write, "read_write"},
 	{Opt_read_write, "rw"},		/* Alternate spelling */
-	/* Boolean args above */
-	{-1, NULL}
+	{Opt_err, NULL}
 };
 
 struct rbd_options {
+	int	queue_depth;
 	bool	read_only;
 };
 
+#define RBD_QUEUE_DEPTH_DEFAULT	BLKDEV_MAX_RQ
 #define RBD_READ_ONLY_DEFAULT	false
 
 static int parse_rbd_opts_token(char *c, void *private)
@@ -761,27 +764,27 @@
 	int token, intval, ret;
 
 	token = match_token(c, rbd_opts_tokens, argstr);
-	if (token < 0)
-		return -EINVAL;
-
 	if (token < Opt_last_int) {
 		ret = match_int(&argstr[0], &intval);
 		if (ret < 0) {
-			pr_err("bad mount option arg (not int) "
-			       "at '%s'\n", c);
+			pr_err("bad mount option arg (not int) at '%s'\n", c);
 			return ret;
 		}
 		dout("got int token %d val %d\n", token, intval);
 	} else if (token > Opt_last_int && token < Opt_last_string) {
-		dout("got string token %d val %s\n", token,
-		     argstr[0].from);
-	} else if (token > Opt_last_string && token < Opt_last_bool) {
-		dout("got Boolean token %d\n", token);
+		dout("got string token %d val %s\n", token, argstr[0].from);
 	} else {
 		dout("got token %d\n", token);
 	}
 
 	switch (token) {
+	case Opt_queue_depth:
+		if (intval < 1) {
+			pr_err("queue_depth out of range\n");
+			return -EINVAL;
+		}
+		rbd_opts->queue_depth = intval;
+		break;
 	case Opt_read_only:
 		rbd_opts->read_only = true;
 		break;
@@ -789,9 +792,10 @@
 		rbd_opts->read_only = false;
 		break;
 	default:
-		rbd_assert(false);
-		break;
+		/* libceph prints "bad option" msg */
+		return -EINVAL;
 	}
+
 	return 0;
 }
 
@@ -1563,22 +1567,39 @@
 /*
  * Wait for an object request to complete.  If interrupted, cancel the
  * underlying osd request.
+ *
+ * @timeout: in jiffies, 0 means "wait forever"
  */
-static int rbd_obj_request_wait(struct rbd_obj_request *obj_request)
+static int __rbd_obj_request_wait(struct rbd_obj_request *obj_request,
+				  unsigned long timeout)
 {
-	int ret;
+	long ret;
 
 	dout("%s %p\n", __func__, obj_request);
-
-	ret = wait_for_completion_interruptible(&obj_request->completion);
-	if (ret < 0) {
-		dout("%s %p interrupted\n", __func__, obj_request);
+	ret = wait_for_completion_interruptible_timeout(
+					&obj_request->completion,
+					ceph_timeout_jiffies(timeout));
+	if (ret <= 0) {
+		if (ret == 0)
+			ret = -ETIMEDOUT;
 		rbd_obj_request_end(obj_request);
-		return ret;
+	} else {
+		ret = 0;
 	}
 
-	dout("%s %p done\n", __func__, obj_request);
-	return 0;
+	dout("%s %p ret %d\n", __func__, obj_request, (int)ret);
+	return ret;
+}
+
+static int rbd_obj_request_wait(struct rbd_obj_request *obj_request)
+{
+	return __rbd_obj_request_wait(obj_request, 0);
+}
+
+static int rbd_obj_request_wait_timeout(struct rbd_obj_request *obj_request,
+					unsigned long timeout)
+{
+	return __rbd_obj_request_wait(obj_request, timeout);
 }
 
 static void rbd_img_request_complete(struct rbd_img_request *img_request)
@@ -2001,11 +2022,11 @@
 	rbd_assert(obj_request_type_valid(type));
 
 	size = strlen(object_name) + 1;
-	name = kmalloc(size, GFP_KERNEL);
+	name = kmalloc(size, GFP_NOIO);
 	if (!name)
 		return NULL;
 
-	obj_request = kmem_cache_zalloc(rbd_obj_request_cache, GFP_KERNEL);
+	obj_request = kmem_cache_zalloc(rbd_obj_request_cache, GFP_NOIO);
 	if (!obj_request) {
 		kfree(name);
 		return NULL;
@@ -2376,7 +2397,7 @@
 	}
 
 	if (opcode == CEPH_OSD_OP_DELETE)
-		osd_req_op_init(osd_request, num_ops, opcode);
+		osd_req_op_init(osd_request, num_ops, opcode, 0);
 	else
 		osd_req_op_extent_init(osd_request, num_ops, opcode,
 				       offset, length, 0, 0);
@@ -2848,7 +2869,7 @@
 		goto out;
 	stat_request->callback = rbd_img_obj_exists_callback;
 
-	osd_req_op_init(stat_request->osd_req, 0, CEPH_OSD_OP_STAT);
+	osd_req_op_init(stat_request->osd_req, 0, CEPH_OSD_OP_STAT, 0);
 	osd_req_op_raw_data_in_pages(stat_request->osd_req, 0, pages, size, 0,
 					false, false);
 	rbd_osd_req_format_read(stat_request);
@@ -3122,6 +3143,7 @@
 						bool watch)
 {
 	struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc;
+	struct ceph_options *opts = osdc->client->options;
 	struct rbd_obj_request *obj_request;
 	int ret;
 
@@ -3148,7 +3170,7 @@
 	if (ret)
 		goto out;
 
-	ret = rbd_obj_request_wait(obj_request);
+	ret = rbd_obj_request_wait_timeout(obj_request, opts->mount_timeout);
 	if (ret)
 		goto out;
 
@@ -3750,10 +3772,9 @@
 
 	memset(&rbd_dev->tag_set, 0, sizeof(rbd_dev->tag_set));
 	rbd_dev->tag_set.ops = &rbd_mq_ops;
-	rbd_dev->tag_set.queue_depth = BLKDEV_MAX_RQ;
+	rbd_dev->tag_set.queue_depth = rbd_dev->opts->queue_depth;
 	rbd_dev->tag_set.numa_node = NUMA_NO_NODE;
-	rbd_dev->tag_set.flags =
-		BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
+	rbd_dev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
 	rbd_dev->tag_set.nr_hw_queues = 1;
 	rbd_dev->tag_set.cmd_size = sizeof(struct work_struct);
 
@@ -3773,6 +3794,7 @@
 	/* set io sizes to object size */
 	segment_size = rbd_obj_bytes(&rbd_dev->header);
 	blk_queue_max_hw_sectors(q, segment_size / SECTOR_SIZE);
+	blk_queue_max_segments(q, segment_size / SECTOR_SIZE);
 	blk_queue_max_segment_size(q, segment_size);
 	blk_queue_io_min(q, segment_size);
 	blk_queue_io_opt(q, segment_size);
@@ -4044,7 +4066,8 @@
 }
 
 static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc,
-				struct rbd_spec *spec)
+					 struct rbd_spec *spec,
+					 struct rbd_options *opts)
 {
 	struct rbd_device *rbd_dev;
 
@@ -4058,8 +4081,9 @@
 	INIT_LIST_HEAD(&rbd_dev->node);
 	init_rwsem(&rbd_dev->header_rwsem);
 
-	rbd_dev->spec = spec;
 	rbd_dev->rbd_client = rbdc;
+	rbd_dev->spec = spec;
+	rbd_dev->opts = opts;
 
 	/* Initialize the layout used for all rbd requests */
 
@@ -4075,6 +4099,7 @@
 {
 	rbd_put_client(rbd_dev->rbd_client);
 	rbd_spec_put(rbd_dev->spec);
+	kfree(rbd_dev->opts);
 	kfree(rbd_dev);
 }
 
@@ -4933,6 +4958,7 @@
 		goto out_mem;
 
 	rbd_opts->read_only = RBD_READ_ONLY_DEFAULT;
+	rbd_opts->queue_depth = RBD_QUEUE_DEPTH_DEFAULT;
 
 	copts = ceph_parse_options(options, mon_addrs,
 					mon_addrs + mon_addrs_size - 1,
@@ -4963,8 +4989,8 @@
  */
 static int rbd_add_get_pool_id(struct rbd_client *rbdc, const char *pool_name)
 {
+	struct ceph_options *opts = rbdc->client->options;
 	u64 newest_epoch;
-	unsigned long timeout = rbdc->client->options->mount_timeout * HZ;
 	int tries = 0;
 	int ret;
 
@@ -4979,7 +5005,8 @@
 		if (rbdc->client->osdc.osdmap->epoch < newest_epoch) {
 			ceph_monc_request_next_osdmap(&rbdc->client->monc);
 			(void) ceph_monc_wait_osdmap(&rbdc->client->monc,
-						     newest_epoch, timeout);
+						     newest_epoch,
+						     opts->mount_timeout);
 			goto again;
 		} else {
 			/* the osdmap we have is new enough */
@@ -5148,7 +5175,7 @@
 	rbdc = __rbd_get_client(rbd_dev->rbd_client);
 
 	ret = -ENOMEM;
-	parent = rbd_dev_create(rbdc, parent_spec);
+	parent = rbd_dev_create(rbdc, parent_spec, NULL);
 	if (!parent)
 		goto out_err;
 
@@ -5394,9 +5421,6 @@
 	rc = rbd_add_parse_args(buf, &ceph_opts, &rbd_opts, &spec);
 	if (rc < 0)
 		goto err_out_module;
-	read_only = rbd_opts->read_only;
-	kfree(rbd_opts);
-	rbd_opts = NULL;	/* done with this */
 
 	rbdc = rbd_get_client(ceph_opts);
 	if (IS_ERR(rbdc)) {
@@ -5422,11 +5446,12 @@
 		goto err_out_client;
 	}
 
-	rbd_dev = rbd_dev_create(rbdc, spec);
+	rbd_dev = rbd_dev_create(rbdc, spec, rbd_opts);
 	if (!rbd_dev)
 		goto err_out_client;
 	rbdc = NULL;		/* rbd_dev now owns this */
 	spec = NULL;		/* rbd_dev now owns this */
+	rbd_opts = NULL;	/* rbd_dev now owns this */
 
 	rc = rbd_dev_image_probe(rbd_dev, true);
 	if (rc < 0)
@@ -5434,6 +5459,7 @@
 
 	/* If we are mapping a snapshot it must be marked read-only */
 
+	read_only = rbd_dev->opts->read_only;
 	if (rbd_dev->spec->snap_id != CEPH_NOSNAP)
 		read_only = true;
 	rbd_dev->mapping.read_only = read_only;
@@ -5458,6 +5484,7 @@
 	rbd_put_client(rbdc);
 err_out_args:
 	rbd_spec_put(spec);
+	kfree(rbd_opts);
 err_out_module:
 	module_put(THIS_MODULE);
 
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 2126842..ced9677 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -736,7 +736,7 @@
 	struct grant_page **pages = req->segments;
 	unsigned int invcount;
 
-	invcount = xen_blkbk_unmap_prepare(blkif, pages, req->nr_pages,
+	invcount = xen_blkbk_unmap_prepare(blkif, pages, req->nr_segs,
 					   req->unmap, req->unmap_pages);
 
 	work->data = req;
@@ -922,7 +922,7 @@
 	int rc;
 
 	rc = xen_blkbk_map(pending_req->blkif, pending_req->segments,
-			   pending_req->nr_pages,
+			   pending_req->nr_segs,
 	                   (pending_req->operation != BLKIF_OP_READ));
 
 	return rc;
@@ -938,7 +938,7 @@
 	int indirect_grefs, rc, n, nseg, i;
 	struct blkif_request_segment *segments = NULL;
 
-	nseg = pending_req->nr_pages;
+	nseg = pending_req->nr_segs;
 	indirect_grefs = INDIRECT_PAGES(nseg);
 	BUG_ON(indirect_grefs > BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST);
 
@@ -1258,7 +1258,7 @@
 	pending_req->id        = req->u.rw.id;
 	pending_req->operation = req_operation;
 	pending_req->status    = BLKIF_RSP_OKAY;
-	pending_req->nr_pages  = nseg;
+	pending_req->nr_segs   = nseg;
 
 	if (req->operation != BLKIF_OP_INDIRECT) {
 		preq.dev               = req->u.rw.handle;
@@ -1379,7 +1379,7 @@
 
  fail_flush:
 	xen_blkbk_unmap(blkif, pending_req->segments,
-	                pending_req->nr_pages);
+	                pending_req->nr_segs);
  fail_response:
 	/* Haven't submitted any bio's yet. */
 	make_response(blkif, req->u.rw.id, req_operation, BLKIF_RSP_ERROR);
diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index 8ccc49d..45a044a 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -345,7 +345,7 @@
 struct pending_req {
 	struct xen_blkif	*blkif;
 	u64			id;
-	int			nr_pages;
+	int			nr_segs;
 	atomic_t		pendcnt;
 	unsigned short		operation;
 	int			status;
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index fc770b7..6d89ed3 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -1074,12 +1074,6 @@
 		s->req.u.indirect.nr_segments : s->req.u.rw.nr_segments;
 
 	if (bret->operation == BLKIF_OP_READ && info->feature_persistent) {
-		/*
-		 * Copy the data received from the backend into the bvec.
-		 * Since bv_offset can be different than 0, and bv_len different
-		 * than PAGE_SIZE, we have to keep track of the current offset,
-		 * to be sure we are copying the data from the right shared page.
-		 */
 		for_each_sg(s->sg, sg, nseg, i) {
 			BUG_ON(sg->offset + sg->length > PAGE_SIZE);
 			shared_data = kmap_atomic(
diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c
index 0b4188b..c6dea3f 100644
--- a/drivers/char/agp/intel-gtt.c
+++ b/drivers/char/agp/intel-gtt.c
@@ -581,7 +581,7 @@
 	/* Query intel_iommu to see if we need the workaround. Presumably that
 	 * was loaded first.
 	 */
-	if ((gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_M_HB ||
+	if ((gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_D_IG ||
 	     gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_M_IG) &&
 	     intel_iommu_gfx_mapped)
 		return 1;
diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c
index 37b8be7..0ac3bd1 100644
--- a/drivers/char/ipmi/ipmi_watchdog.c
+++ b/drivers/char/ipmi/ipmi_watchdog.c
@@ -208,7 +208,7 @@
 	return rv;
 }
 
-static struct kernel_param_ops param_ops_timeout = {
+static const struct kernel_param_ops param_ops_timeout = {
 	.set = set_param_timeout,
 	.get = param_get_int,
 };
@@ -270,14 +270,14 @@
 	return 0;
 }
 
-static struct kernel_param_ops param_ops_wdog_ifnum = {
+static const struct kernel_param_ops param_ops_wdog_ifnum = {
 	.set = set_param_wdog_ifnum,
 	.get = param_get_int,
 };
 
 #define param_check_wdog_ifnum param_check_int
 
-static struct kernel_param_ops param_ops_str = {
+static const struct kernel_param_ops param_ops_str = {
 	.set = set_param_str,
 	.get = get_param_str,
 };
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index 9897f35..42f7120 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -78,6 +78,23 @@
 	  This driver supports Silicon Labs 570/571/598/599 programmable
 	  clock generators.
 
+config COMMON_CLK_CDCE925
+	tristate "Clock driver for TI CDCE925 devices"
+	depends on I2C
+	depends on OF
+	select REGMAP_I2C
+	help
+	---help---
+	  This driver supports the TI CDCE925 programmable clock synthesizer.
+	  The chip contains two PLLs with spread-spectrum clocking support and
+	  five output dividers. The driver only supports the following setup,
+	  and uses a fixed setting for the output muxes.
+	  Y1 is derived from the input clock
+	  Y2 and Y3 derive from PLL1
+	  Y4 and Y5 derive from PLL2
+	  Given a target output frequency, the driver will set the PLL and
+	  divider to best approximate the desired output.
+
 config COMMON_CLK_S2MPS11
 	tristate "Clock driver for S2MPS1X/S5M8767 MFD"
 	depends on MFD_SEC_CORE
@@ -150,11 +167,13 @@
 	---help---
 	  This driver supports TI CDCE706 programmable 3-PLL clock synthesizer.
 
+source "drivers/clk/bcm/Kconfig"
+source "drivers/clk/hisilicon/Kconfig"
 source "drivers/clk/qcom/Kconfig"
 
 endmenu
 
-source "drivers/clk/bcm/Kconfig"
 source "drivers/clk/mvebu/Kconfig"
 
 source "drivers/clk/samsung/Kconfig"
+source "drivers/clk/tegra/Kconfig"
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index 8732e4c..c4cf075 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -38,6 +38,8 @@
 obj-$(CONFIG_COMMON_CLK_S2MPS11)	+= clk-s2mps11.o
 obj-$(CONFIG_COMMON_CLK_SI5351)		+= clk-si5351.o
 obj-$(CONFIG_COMMON_CLK_SI570)		+= clk-si570.o
+obj-$(CONFIG_COMMON_CLK_CDCE925)	+= clk-cdce925.o
+obj-$(CONFIG_ARCH_STM32)		+= clk-stm32f4.o
 obj-$(CONFIG_CLK_TWL6040)		+= clk-twl6040.o
 obj-$(CONFIG_ARCH_U300)			+= clk-u300.o
 obj-$(CONFIG_ARCH_VT8500)		+= clk-vt8500.o
@@ -45,19 +47,20 @@
 obj-$(CONFIG_COMMON_CLK_XGENE)		+= clk-xgene.o
 obj-$(CONFIG_COMMON_CLK_PWM)		+= clk-pwm.o
 obj-$(CONFIG_COMMON_CLK_AT91)		+= at91/
-obj-$(CONFIG_ARCH_BCM_MOBILE)		+= bcm/
+obj-$(CONFIG_ARCH_BCM)			+= bcm/
 obj-$(CONFIG_ARCH_BERLIN)		+= berlin/
-obj-$(CONFIG_ARCH_HI3xxx)		+= hisilicon/
-obj-$(CONFIG_ARCH_HIP04)		+= hisilicon/
-obj-$(CONFIG_ARCH_HIX5HD2)		+= hisilicon/
+obj-$(CONFIG_ARCH_HISI)			+= hisilicon/
 obj-$(CONFIG_ARCH_MXC)			+= imx/
 obj-$(CONFIG_MACH_INGENIC)		+= ingenic/
 obj-$(CONFIG_COMMON_CLK_KEYSTONE)	+= keystone/
+obj-$(CONFIG_ARCH_MEDIATEK)		+= mediatek/
 ifeq ($(CONFIG_COMMON_CLK), y)
 obj-$(CONFIG_ARCH_MMP)			+= mmp/
 endif
 obj-$(CONFIG_PLAT_ORION)		+= mvebu/
+obj-$(CONFIG_ARCH_MESON)		+= meson/
 obj-$(CONFIG_ARCH_MXS)			+= mxs/
+obj-$(CONFIG_ARCH_LPC18XX)		+= nxp/
 obj-$(CONFIG_MACH_PISTACHIO)		+= pistachio/
 obj-$(CONFIG_COMMON_CLK_PXA)		+= pxa/
 obj-$(CONFIG_COMMON_CLK_QCOM)		+= qcom/
diff --git a/drivers/clk/at91/clk-main.c b/drivers/clk/at91/clk-main.c
index 59fa3cc..c240045 100644
--- a/drivers/clk/at91/clk-main.c
+++ b/drivers/clk/at91/clk-main.c
@@ -614,7 +614,7 @@
 	const char *name = np->name;
 	int i;
 
-	num_parents = of_count_phandle_with_args(np, "clocks", "#clock-cells");
+	num_parents = of_clk_get_parent_count(np);
 	if (num_parents <= 0 || num_parents > 2)
 		return;
 
diff --git a/drivers/clk/at91/clk-master.c b/drivers/clk/at91/clk-master.c
index c1af80b..f98eafe 100644
--- a/drivers/clk/at91/clk-master.c
+++ b/drivers/clk/at91/clk-master.c
@@ -224,7 +224,7 @@
 	const char *name = np->name;
 	struct clk_master_characteristics *characteristics;
 
-	num_parents = of_count_phandle_with_args(np, "clocks", "#clock-cells");
+	num_parents = of_clk_get_parent_count(np);
 	if (num_parents <= 0 || num_parents > MASTER_SOURCE_MAX)
 		return;
 
diff --git a/drivers/clk/at91/clk-programmable.c b/drivers/clk/at91/clk-programmable.c
index 86c8a07..8c86c0f7 100644
--- a/drivers/clk/at91/clk-programmable.c
+++ b/drivers/clk/at91/clk-programmable.c
@@ -237,7 +237,7 @@
 	const char *name;
 	struct device_node *progclknp;
 
-	num_parents = of_count_phandle_with_args(np, "clocks", "#clock-cells");
+	num_parents = of_clk_get_parent_count(np);
 	if (num_parents <= 0 || num_parents > PROG_SOURCE_MAX)
 		return;
 
diff --git a/drivers/clk/at91/clk-slow.c b/drivers/clk/at91/clk-slow.c
index 2f13bd5..98a84a8 100644
--- a/drivers/clk/at91/clk-slow.c
+++ b/drivers/clk/at91/clk-slow.c
@@ -373,7 +373,7 @@
 	const char *name = np->name;
 	int i;
 
-	num_parents = of_count_phandle_with_args(np, "clocks", "#clock-cells");
+	num_parents = of_clk_get_parent_count(np);
 	if (num_parents <= 0 || num_parents > 2)
 		return;
 
@@ -451,7 +451,7 @@
 	const char *name = np->name;
 	int i;
 
-	num_parents = of_count_phandle_with_args(np, "clocks", "#clock-cells");
+	num_parents = of_clk_get_parent_count(np);
 	if (num_parents != 2)
 		return;
 
diff --git a/drivers/clk/at91/clk-smd.c b/drivers/clk/at91/clk-smd.c
index 144d47e..3817ea8 100644
--- a/drivers/clk/at91/clk-smd.c
+++ b/drivers/clk/at91/clk-smd.c
@@ -150,7 +150,7 @@
 	const char *parent_names[SMD_SOURCE_MAX];
 	const char *name = np->name;
 
-	num_parents = of_count_phandle_with_args(np, "clocks", "#clock-cells");
+	num_parents = of_clk_get_parent_count(np);
 	if (num_parents <= 0 || num_parents > SMD_SOURCE_MAX)
 		return;
 
diff --git a/drivers/clk/at91/clk-usb.c b/drivers/clk/at91/clk-usb.c
index 0b7c3e8..b0cbd2b 100644
--- a/drivers/clk/at91/clk-usb.c
+++ b/drivers/clk/at91/clk-usb.c
@@ -378,7 +378,7 @@
 	const char *parent_names[USB_SOURCE_MAX];
 	const char *name = np->name;
 
-	num_parents = of_count_phandle_with_args(np, "clocks", "#clock-cells");
+	num_parents = of_clk_get_parent_count(np);
 	if (num_parents <= 0 || num_parents > USB_SOURCE_MAX)
 		return;
 
diff --git a/drivers/clk/at91/pmc.c b/drivers/clk/at91/pmc.c
index 3f27d21..39be2be 100644
--- a/drivers/clk/at91/pmc.c
+++ b/drivers/clk/at91/pmc.c
@@ -153,7 +153,7 @@
 	return 0;
 }
 
-static struct irq_domain_ops pmc_irq_ops = {
+static const struct irq_domain_ops pmc_irq_ops = {
 	.map	= pmc_irq_map,
 	.xlate	= pmc_irq_domain_xlate,
 };
diff --git a/drivers/clk/bcm/Kconfig b/drivers/clk/bcm/Kconfig
index 75506e5..88febf5 100644
--- a/drivers/clk/bcm/Kconfig
+++ b/drivers/clk/bcm/Kconfig
@@ -7,3 +7,12 @@
 	  Enable common clock framework support for Broadcom SoCs
 	  using "Kona" style clock control units, including those
 	  in the BCM281xx and BCM21664 families.
+
+config COMMON_CLK_IPROC
+	bool "Broadcom iProc clock support"
+	depends on ARCH_BCM_IPROC
+	depends on COMMON_CLK
+	default ARCH_BCM_IPROC
+	help
+	  Enable common clock framework support for Broadcom SoCs
+	  based on the iProc architecture
diff --git a/drivers/clk/bcm/Makefile b/drivers/clk/bcm/Makefile
index 6297d05..8a7a477 100644
--- a/drivers/clk/bcm/Makefile
+++ b/drivers/clk/bcm/Makefile
@@ -2,3 +2,5 @@
 obj-$(CONFIG_CLK_BCM_KONA)	+= clk-kona-setup.o
 obj-$(CONFIG_CLK_BCM_KONA)	+= clk-bcm281xx.o
 obj-$(CONFIG_CLK_BCM_KONA)	+= clk-bcm21664.o
+obj-$(CONFIG_COMMON_CLK_IPROC)	+= clk-iproc-armpll.o clk-iproc-pll.o clk-iproc-asiu.o
+obj-$(CONFIG_ARCH_BCM_CYGNUS)	+= clk-cygnus.o
diff --git a/drivers/clk/bcm/clk-cygnus.c b/drivers/clk/bcm/clk-cygnus.c
new file mode 100644
index 0000000..316c603
--- /dev/null
+++ b/drivers/clk/bcm/clk-cygnus.c
@@ -0,0 +1,265 @@
+/*
+ * Copyright (C) 2014 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/clk-provider.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/clkdev.h>
+#include <linux/of_address.h>
+#include <linux/delay.h>
+
+#include <dt-bindings/clock/bcm-cygnus.h>
+#include "clk-iproc.h"
+
+#define reg_val(o, s, w) { .offset = o, .shift = s, .width = w, }
+
+#define aon_val(o, pw, ps, is) { .offset = o, .pwr_width = pw, \
+	.pwr_shift = ps, .iso_shift = is }
+
+#define sw_ctrl_val(o, s) { .offset = o, .shift = s, }
+
+#define asiu_div_val(o, es, hs, hw, ls, lw) \
+		{ .offset = o, .en_shift = es, .high_shift = hs, \
+		.high_width = hw, .low_shift = ls, .low_width = lw }
+
+#define reset_val(o, rs, prs, kis, kiw, kps, kpw, kas, kaw) { .offset = o, \
+	.reset_shift = rs, .p_reset_shift = prs, .ki_shift = kis, \
+	.ki_width = kiw, .kp_shift = kps, .kp_width = kpw, .ka_shift = kas, \
+	.ka_width = kaw }
+
+#define vco_ctrl_val(uo, lo) { .u_offset = uo, .l_offset = lo }
+
+#define enable_val(o, es, hs, bs) { .offset = o, .enable_shift = es, \
+	.hold_shift = hs, .bypass_shift = bs }
+
+#define asiu_gate_val(o, es) { .offset = o, .en_shift = es }
+
+static void __init cygnus_armpll_init(struct device_node *node)
+{
+	iproc_armpll_setup(node);
+}
+CLK_OF_DECLARE(cygnus_armpll, "brcm,cygnus-armpll", cygnus_armpll_init);
+
+static const struct iproc_pll_ctrl genpll = {
+	.flags = IPROC_CLK_AON | IPROC_CLK_PLL_HAS_NDIV_FRAC |
+		IPROC_CLK_PLL_NEEDS_SW_CFG,
+	.aon = aon_val(0x0, 2, 1, 0),
+	.reset = reset_val(0x0, 11, 10, 4, 3, 0, 4, 7, 3),
+	.sw_ctrl = sw_ctrl_val(0x10, 31),
+	.ndiv_int = reg_val(0x10, 20, 10),
+	.ndiv_frac = reg_val(0x10, 0, 20),
+	.pdiv = reg_val(0x14, 0, 4),
+	.vco_ctrl = vco_ctrl_val(0x18, 0x1c),
+	.status = reg_val(0x28, 12, 1),
+};
+
+static const struct iproc_clk_ctrl genpll_clk[] = {
+	[BCM_CYGNUS_GENPLL_AXI21_CLK] = {
+		.channel = BCM_CYGNUS_GENPLL_AXI21_CLK,
+		.flags = IPROC_CLK_AON,
+		.enable = enable_val(0x4, 6, 0, 12),
+		.mdiv = reg_val(0x20, 0, 8),
+	},
+	[BCM_CYGNUS_GENPLL_250MHZ_CLK] = {
+		.channel = BCM_CYGNUS_GENPLL_250MHZ_CLK,
+		.flags = IPROC_CLK_AON,
+		.enable = enable_val(0x4, 7, 1, 13),
+		.mdiv = reg_val(0x20, 10, 8),
+	},
+	[BCM_CYGNUS_GENPLL_IHOST_SYS_CLK] = {
+		.channel = BCM_CYGNUS_GENPLL_IHOST_SYS_CLK,
+		.flags = IPROC_CLK_AON,
+		.enable = enable_val(0x4, 8, 2, 14),
+		.mdiv = reg_val(0x20, 20, 8),
+	},
+	[BCM_CYGNUS_GENPLL_ENET_SW_CLK] = {
+		.channel = BCM_CYGNUS_GENPLL_ENET_SW_CLK,
+		.flags = IPROC_CLK_AON,
+		.enable = enable_val(0x4, 9, 3, 15),
+		.mdiv = reg_val(0x24, 0, 8),
+	},
+	[BCM_CYGNUS_GENPLL_AUDIO_125_CLK] = {
+		.channel = BCM_CYGNUS_GENPLL_AUDIO_125_CLK,
+		.flags = IPROC_CLK_AON,
+		.enable = enable_val(0x4, 10, 4, 16),
+		.mdiv = reg_val(0x24, 10, 8),
+	},
+	[BCM_CYGNUS_GENPLL_CAN_CLK] = {
+		.channel = BCM_CYGNUS_GENPLL_CAN_CLK,
+		.flags = IPROC_CLK_AON,
+		.enable = enable_val(0x4, 11, 5, 17),
+		.mdiv = reg_val(0x24, 20, 8),
+	},
+};
+
+static void __init cygnus_genpll_clk_init(struct device_node *node)
+{
+	iproc_pll_clk_setup(node, &genpll, NULL, 0, genpll_clk,
+			    ARRAY_SIZE(genpll_clk));
+}
+CLK_OF_DECLARE(cygnus_genpll, "brcm,cygnus-genpll", cygnus_genpll_clk_init);
+
+static const struct iproc_pll_ctrl lcpll0 = {
+	.flags = IPROC_CLK_AON | IPROC_CLK_PLL_NEEDS_SW_CFG,
+	.aon = aon_val(0x0, 2, 5, 4),
+	.reset = reset_val(0x0, 31, 30, 27, 3, 23, 4, 19, 4),
+	.sw_ctrl = sw_ctrl_val(0x4, 31),
+	.ndiv_int = reg_val(0x4, 16, 10),
+	.pdiv = reg_val(0x4, 26, 4),
+	.vco_ctrl = vco_ctrl_val(0x10, 0x14),
+	.status = reg_val(0x18, 12, 1),
+};
+
+static const struct iproc_clk_ctrl lcpll0_clk[] = {
+	[BCM_CYGNUS_LCPLL0_PCIE_PHY_REF_CLK] = {
+		.channel = BCM_CYGNUS_LCPLL0_PCIE_PHY_REF_CLK,
+		.flags = IPROC_CLK_AON,
+		.enable = enable_val(0x0, 7, 1, 13),
+		.mdiv = reg_val(0x8, 0, 8),
+	},
+	[BCM_CYGNUS_LCPLL0_DDR_PHY_CLK] = {
+		.channel = BCM_CYGNUS_LCPLL0_DDR_PHY_CLK,
+		.flags = IPROC_CLK_AON,
+		.enable = enable_val(0x0, 8, 2, 14),
+		.mdiv = reg_val(0x8, 10, 8),
+	},
+	[BCM_CYGNUS_LCPLL0_SDIO_CLK] = {
+		.channel = BCM_CYGNUS_LCPLL0_SDIO_CLK,
+		.flags = IPROC_CLK_AON,
+		.enable = enable_val(0x0, 9, 3, 15),
+		.mdiv = reg_val(0x8, 20, 8),
+	},
+	[BCM_CYGNUS_LCPLL0_USB_PHY_REF_CLK] = {
+		.channel = BCM_CYGNUS_LCPLL0_USB_PHY_REF_CLK,
+		.flags = IPROC_CLK_AON,
+		.enable = enable_val(0x0, 10, 4, 16),
+		.mdiv = reg_val(0xc, 0, 8),
+	},
+	[BCM_CYGNUS_LCPLL0_SMART_CARD_CLK] = {
+		.channel = BCM_CYGNUS_LCPLL0_SMART_CARD_CLK,
+		.flags = IPROC_CLK_AON,
+		.enable = enable_val(0x0, 11, 5, 17),
+		.mdiv = reg_val(0xc, 10, 8),
+	},
+	[BCM_CYGNUS_LCPLL0_CH5_UNUSED] = {
+		.channel = BCM_CYGNUS_LCPLL0_CH5_UNUSED,
+		.flags = IPROC_CLK_AON,
+		.enable = enable_val(0x0, 12, 6, 18),
+		.mdiv = reg_val(0xc, 20, 8),
+	},
+};
+
+static void __init cygnus_lcpll0_clk_init(struct device_node *node)
+{
+	iproc_pll_clk_setup(node, &lcpll0, NULL, 0, lcpll0_clk,
+			    ARRAY_SIZE(lcpll0_clk));
+}
+CLK_OF_DECLARE(cygnus_lcpll0, "brcm,cygnus-lcpll0", cygnus_lcpll0_clk_init);
+
+/*
+ * MIPI PLL VCO frequency parameter table
+ */
+static const struct iproc_pll_vco_param mipipll_vco_params[] = {
+	/* rate (Hz) ndiv_int ndiv_frac pdiv */
+	{ 750000000UL,   30,     0,        1 },
+	{ 1000000000UL,  40,     0,        1 },
+	{ 1350000000ul,  54,     0,        1 },
+	{ 2000000000UL,  80,     0,        1 },
+	{ 2100000000UL,  84,     0,        1 },
+	{ 2250000000UL,  90,     0,        1 },
+	{ 2500000000UL,  100,    0,        1 },
+	{ 2700000000UL,  54,     0,        0 },
+	{ 2975000000UL,  119,    0,        1 },
+	{ 3100000000UL,  124,    0,        1 },
+	{ 3150000000UL,  126,    0,        1 },
+};
+
+static const struct iproc_pll_ctrl mipipll = {
+	.flags = IPROC_CLK_PLL_ASIU | IPROC_CLK_PLL_HAS_NDIV_FRAC |
+		 IPROC_CLK_NEEDS_READ_BACK,
+	.aon = aon_val(0x0, 4, 17, 16),
+	.asiu = asiu_gate_val(0x0, 3),
+	.reset = reset_val(0x0, 11, 10, 4, 3, 0, 4, 7, 4),
+	.ndiv_int = reg_val(0x10, 20, 10),
+	.ndiv_frac = reg_val(0x10, 0, 20),
+	.pdiv = reg_val(0x14, 0, 4),
+	.vco_ctrl = vco_ctrl_val(0x18, 0x1c),
+	.status = reg_val(0x28, 12, 1),
+};
+
+static const struct iproc_clk_ctrl mipipll_clk[] = {
+	[BCM_CYGNUS_MIPIPLL_CH0_UNUSED] = {
+		.channel = BCM_CYGNUS_MIPIPLL_CH0_UNUSED,
+		.flags = IPROC_CLK_NEEDS_READ_BACK,
+		.enable = enable_val(0x4, 12, 6, 18),
+		.mdiv = reg_val(0x20, 0, 8),
+	},
+	[BCM_CYGNUS_MIPIPLL_CH1_LCD] = {
+		.channel = BCM_CYGNUS_MIPIPLL_CH1_LCD,
+		.flags = IPROC_CLK_NEEDS_READ_BACK,
+		.enable = enable_val(0x4, 13, 7, 19),
+		.mdiv = reg_val(0x20, 10, 8),
+	},
+	[BCM_CYGNUS_MIPIPLL_CH2_V3D] = {
+		.channel = BCM_CYGNUS_MIPIPLL_CH2_V3D,
+		.flags = IPROC_CLK_NEEDS_READ_BACK,
+		.enable = enable_val(0x4, 14, 8, 20),
+		.mdiv = reg_val(0x20, 20, 8),
+	},
+	[BCM_CYGNUS_MIPIPLL_CH3_UNUSED] = {
+		.channel = BCM_CYGNUS_MIPIPLL_CH3_UNUSED,
+		.flags = IPROC_CLK_NEEDS_READ_BACK,
+		.enable = enable_val(0x4, 15, 9, 21),
+		.mdiv = reg_val(0x24, 0, 8),
+	},
+	[BCM_CYGNUS_MIPIPLL_CH4_UNUSED] = {
+		.channel = BCM_CYGNUS_MIPIPLL_CH4_UNUSED,
+		.flags = IPROC_CLK_NEEDS_READ_BACK,
+		.enable = enable_val(0x4, 16, 10, 22),
+		.mdiv = reg_val(0x24, 10, 8),
+	},
+	[BCM_CYGNUS_MIPIPLL_CH5_UNUSED] = {
+		.channel = BCM_CYGNUS_MIPIPLL_CH5_UNUSED,
+		.flags = IPROC_CLK_NEEDS_READ_BACK,
+		.enable = enable_val(0x4, 17, 11, 23),
+		.mdiv = reg_val(0x24, 20, 8),
+	},
+};
+
+static void __init cygnus_mipipll_clk_init(struct device_node *node)
+{
+	iproc_pll_clk_setup(node, &mipipll, mipipll_vco_params,
+			    ARRAY_SIZE(mipipll_vco_params), mipipll_clk,
+			    ARRAY_SIZE(mipipll_clk));
+}
+CLK_OF_DECLARE(cygnus_mipipll, "brcm,cygnus-mipipll", cygnus_mipipll_clk_init);
+
+static const struct iproc_asiu_div asiu_div[] = {
+	[BCM_CYGNUS_ASIU_KEYPAD_CLK] = asiu_div_val(0x0, 31, 16, 10, 0, 10),
+	[BCM_CYGNUS_ASIU_ADC_CLK] = asiu_div_val(0x4, 31, 16, 10, 0, 10),
+	[BCM_CYGNUS_ASIU_PWM_CLK] = asiu_div_val(0x8, 31, 16, 10, 0, 10),
+};
+
+static const struct iproc_asiu_gate asiu_gate[] = {
+	[BCM_CYGNUS_ASIU_KEYPAD_CLK] = asiu_gate_val(0x0, 7),
+	[BCM_CYGNUS_ASIU_ADC_CLK] = asiu_gate_val(0x0, 9),
+	[BCM_CYGNUS_ASIU_PWM_CLK] = asiu_gate_val(IPROC_CLK_INVALID_OFFSET, 0),
+};
+
+static void __init cygnus_asiu_init(struct device_node *node)
+{
+	iproc_asiu_setup(node, asiu_div, asiu_gate, ARRAY_SIZE(asiu_div));
+}
+CLK_OF_DECLARE(cygnus_asiu_clk, "brcm,cygnus-asiu-clk", cygnus_asiu_init);
diff --git a/drivers/clk/bcm/clk-iproc-armpll.c b/drivers/clk/bcm/clk-iproc-armpll.c
new file mode 100644
index 0000000..a196ee2
--- /dev/null
+++ b/drivers/clk/bcm/clk-iproc-armpll.c
@@ -0,0 +1,282 @@
+/*
+ * Copyright (C) 2014 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/clk-provider.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/clkdev.h>
+#include <linux/of_address.h>
+
+#define IPROC_CLK_MAX_FREQ_POLICY                    0x3
+#define IPROC_CLK_POLICY_FREQ_OFFSET                 0x008
+#define IPROC_CLK_POLICY_FREQ_POLICY_FREQ_SHIFT      8
+#define IPROC_CLK_POLICY_FREQ_POLICY_FREQ_MASK       0x7
+
+#define IPROC_CLK_PLLARMA_OFFSET                     0xc00
+#define IPROC_CLK_PLLARMA_LOCK_SHIFT                 28
+#define IPROC_CLK_PLLARMA_PDIV_SHIFT                 24
+#define IPROC_CLK_PLLARMA_PDIV_MASK                  0xf
+#define IPROC_CLK_PLLARMA_NDIV_INT_SHIFT             8
+#define IPROC_CLK_PLLARMA_NDIV_INT_MASK              0x3ff
+
+#define IPROC_CLK_PLLARMB_OFFSET                     0xc04
+#define IPROC_CLK_PLLARMB_NDIV_FRAC_MASK             0xfffff
+
+#define IPROC_CLK_PLLARMC_OFFSET                     0xc08
+#define IPROC_CLK_PLLARMC_BYPCLK_EN_SHIFT            8
+#define IPROC_CLK_PLLARMC_MDIV_MASK                  0xff
+
+#define IPROC_CLK_PLLARMCTL5_OFFSET                  0xc20
+#define IPROC_CLK_PLLARMCTL5_H_MDIV_MASK             0xff
+
+#define IPROC_CLK_PLLARM_OFFSET_OFFSET               0xc24
+#define IPROC_CLK_PLLARM_SW_CTL_SHIFT                29
+#define IPROC_CLK_PLLARM_NDIV_INT_OFFSET_SHIFT       20
+#define IPROC_CLK_PLLARM_NDIV_INT_OFFSET_MASK        0xff
+#define IPROC_CLK_PLLARM_NDIV_FRAC_OFFSET_MASK       0xfffff
+
+#define IPROC_CLK_ARM_DIV_OFFSET                     0xe00
+#define IPROC_CLK_ARM_DIV_PLL_SELECT_OVERRIDE_SHIFT  4
+#define IPROC_CLK_ARM_DIV_ARM_PLL_SELECT_MASK        0xf
+
+#define IPROC_CLK_POLICY_DBG_OFFSET                  0xec0
+#define IPROC_CLK_POLICY_DBG_ACT_FREQ_SHIFT          12
+#define IPROC_CLK_POLICY_DBG_ACT_FREQ_MASK           0x7
+
+enum iproc_arm_pll_fid {
+	ARM_PLL_FID_CRYSTAL_CLK   = 0,
+	ARM_PLL_FID_SYS_CLK       = 2,
+	ARM_PLL_FID_CH0_SLOW_CLK  = 6,
+	ARM_PLL_FID_CH1_FAST_CLK  = 7
+};
+
+struct iproc_arm_pll {
+	struct clk_hw hw;
+	void __iomem *base;
+	unsigned long rate;
+};
+
+#define to_iproc_arm_pll(hw) container_of(hw, struct iproc_arm_pll, hw)
+
+static unsigned int __get_fid(struct iproc_arm_pll *pll)
+{
+	u32 val;
+	unsigned int policy, fid, active_fid;
+
+	val = readl(pll->base + IPROC_CLK_ARM_DIV_OFFSET);
+	if (val & (1 << IPROC_CLK_ARM_DIV_PLL_SELECT_OVERRIDE_SHIFT))
+		policy = val & IPROC_CLK_ARM_DIV_ARM_PLL_SELECT_MASK;
+	else
+		policy = 0;
+
+	/* something is seriously wrong */
+	BUG_ON(policy > IPROC_CLK_MAX_FREQ_POLICY);
+
+	val = readl(pll->base + IPROC_CLK_POLICY_FREQ_OFFSET);
+	fid = (val >> (IPROC_CLK_POLICY_FREQ_POLICY_FREQ_SHIFT * policy)) &
+		IPROC_CLK_POLICY_FREQ_POLICY_FREQ_MASK;
+
+	val = readl(pll->base + IPROC_CLK_POLICY_DBG_OFFSET);
+	active_fid = IPROC_CLK_POLICY_DBG_ACT_FREQ_MASK &
+		(val >> IPROC_CLK_POLICY_DBG_ACT_FREQ_SHIFT);
+	if (fid != active_fid) {
+		pr_debug("%s: fid override %u->%u\n", __func__,	fid,
+				active_fid);
+		fid = active_fid;
+	}
+
+	pr_debug("%s: active fid: %u\n", __func__, fid);
+
+	return fid;
+}
+
+/*
+ * Determine the mdiv (post divider) based on the frequency ID being used.
+ * There are 4 sources that can be used to derive the output clock rate:
+ *    - 25 MHz Crystal
+ *    - System clock
+ *    - PLL channel 0 (slow clock)
+ *    - PLL channel 1 (fast clock)
+ */
+static int __get_mdiv(struct iproc_arm_pll *pll)
+{
+	unsigned int fid;
+	int mdiv;
+	u32 val;
+
+	fid = __get_fid(pll);
+
+	switch (fid) {
+	case ARM_PLL_FID_CRYSTAL_CLK:
+	case ARM_PLL_FID_SYS_CLK:
+		mdiv = 1;
+		break;
+
+	case ARM_PLL_FID_CH0_SLOW_CLK:
+		val = readl(pll->base + IPROC_CLK_PLLARMC_OFFSET);
+		mdiv = val & IPROC_CLK_PLLARMC_MDIV_MASK;
+		if (mdiv == 0)
+			mdiv = 256;
+		break;
+
+	case ARM_PLL_FID_CH1_FAST_CLK:
+		val = readl(pll->base +	IPROC_CLK_PLLARMCTL5_OFFSET);
+		mdiv = val & IPROC_CLK_PLLARMCTL5_H_MDIV_MASK;
+		if (mdiv == 0)
+			mdiv = 256;
+		break;
+
+	default:
+		mdiv = -EFAULT;
+	}
+
+	return mdiv;
+}
+
+static unsigned int __get_ndiv(struct iproc_arm_pll *pll)
+{
+	u32 val;
+	unsigned int ndiv_int, ndiv_frac, ndiv;
+
+	val = readl(pll->base + IPROC_CLK_PLLARM_OFFSET_OFFSET);
+	if (val & (1 << IPROC_CLK_PLLARM_SW_CTL_SHIFT)) {
+		/*
+		 * offset mode is active. Read the ndiv from the PLLARM OFFSET
+		 * register
+		 */
+		ndiv_int = (val >> IPROC_CLK_PLLARM_NDIV_INT_OFFSET_SHIFT) &
+			IPROC_CLK_PLLARM_NDIV_INT_OFFSET_MASK;
+		if (ndiv_int == 0)
+			ndiv_int = 256;
+
+		ndiv_frac = val & IPROC_CLK_PLLARM_NDIV_FRAC_OFFSET_MASK;
+	} else {
+		/* offset mode not active */
+		val = readl(pll->base + IPROC_CLK_PLLARMA_OFFSET);
+		ndiv_int = (val >> IPROC_CLK_PLLARMA_NDIV_INT_SHIFT) &
+			IPROC_CLK_PLLARMA_NDIV_INT_MASK;
+		if (ndiv_int == 0)
+			ndiv_int = 1024;
+
+		val = readl(pll->base + IPROC_CLK_PLLARMB_OFFSET);
+		ndiv_frac = val & IPROC_CLK_PLLARMB_NDIV_FRAC_MASK;
+	}
+
+	ndiv = (ndiv_int << 20) | ndiv_frac;
+
+	return ndiv;
+}
+
+/*
+ * The output frequency of the ARM PLL is calculated based on the ARM PLL
+ * divider values:
+ *   pdiv = ARM PLL pre-divider
+ *   ndiv = ARM PLL multiplier
+ *   mdiv = ARM PLL post divider
+ *
+ * The frequency is calculated by:
+ *   ((ndiv * parent clock rate) / pdiv) / mdiv
+ */
+static unsigned long iproc_arm_pll_recalc_rate(struct clk_hw *hw,
+		unsigned long parent_rate)
+{
+	struct iproc_arm_pll *pll = to_iproc_arm_pll(hw);
+	u32 val;
+	int mdiv;
+	u64 ndiv;
+	unsigned int pdiv;
+
+	/* in bypass mode, use parent rate */
+	val = readl(pll->base + IPROC_CLK_PLLARMC_OFFSET);
+	if (val & (1 << IPROC_CLK_PLLARMC_BYPCLK_EN_SHIFT)) {
+		pll->rate = parent_rate;
+		return pll->rate;
+	}
+
+	/* PLL needs to be locked */
+	val = readl(pll->base + IPROC_CLK_PLLARMA_OFFSET);
+	if (!(val & (1 << IPROC_CLK_PLLARMA_LOCK_SHIFT))) {
+		pll->rate = 0;
+		return 0;
+	}
+
+	pdiv = (val >> IPROC_CLK_PLLARMA_PDIV_SHIFT) &
+		IPROC_CLK_PLLARMA_PDIV_MASK;
+	if (pdiv == 0)
+		pdiv = 16;
+
+	ndiv = __get_ndiv(pll);
+	mdiv = __get_mdiv(pll);
+	if (mdiv <= 0) {
+		pll->rate = 0;
+		return 0;
+	}
+	pll->rate = (ndiv * parent_rate) >> 20;
+	pll->rate = (pll->rate / pdiv) / mdiv;
+
+	pr_debug("%s: ARM PLL rate: %lu. parent rate: %lu\n", __func__,
+		 pll->rate, parent_rate);
+	pr_debug("%s: ndiv_int: %u, pdiv: %u, mdiv: %d\n", __func__,
+		 (unsigned int)(ndiv >> 20), pdiv, mdiv);
+
+	return pll->rate;
+}
+
+static const struct clk_ops iproc_arm_pll_ops = {
+	.recalc_rate = iproc_arm_pll_recalc_rate,
+};
+
+void __init iproc_armpll_setup(struct device_node *node)
+{
+	int ret;
+	struct clk *clk;
+	struct iproc_arm_pll *pll;
+	struct clk_init_data init;
+	const char *parent_name;
+
+	pll = kzalloc(sizeof(*pll), GFP_KERNEL);
+	if (WARN_ON(!pll))
+		return;
+
+	pll->base = of_iomap(node, 0);
+	if (WARN_ON(!pll->base))
+		goto err_free_pll;
+
+	init.name = node->name;
+	init.ops = &iproc_arm_pll_ops;
+	init.flags = 0;
+	parent_name = of_clk_get_parent_name(node, 0);
+	init.parent_names = (parent_name ? &parent_name : NULL);
+	init.num_parents = (parent_name ? 1 : 0);
+	pll->hw.init = &init;
+
+	clk = clk_register(NULL, &pll->hw);
+	if (WARN_ON(IS_ERR(clk)))
+		goto err_iounmap;
+
+	ret = of_clk_add_provider(node, of_clk_src_simple_get, clk);
+	if (WARN_ON(ret))
+		goto err_clk_unregister;
+
+	return;
+
+err_clk_unregister:
+	clk_unregister(clk);
+err_iounmap:
+	iounmap(pll->base);
+err_free_pll:
+	kfree(pll);
+}
diff --git a/drivers/clk/bcm/clk-iproc-asiu.c b/drivers/clk/bcm/clk-iproc-asiu.c
new file mode 100644
index 0000000..e19c09c
--- /dev/null
+++ b/drivers/clk/bcm/clk-iproc-asiu.c
@@ -0,0 +1,276 @@
+/*
+ * Copyright (C) 2014 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/clk-provider.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/clkdev.h>
+#include <linux/of_address.h>
+#include <linux/delay.h>
+
+#include "clk-iproc.h"
+
+struct iproc_asiu;
+
+struct iproc_asiu_clk {
+	struct clk_hw hw;
+	const char *name;
+	struct iproc_asiu *asiu;
+	unsigned long rate;
+	struct iproc_asiu_div div;
+	struct iproc_asiu_gate gate;
+};
+
+struct iproc_asiu {
+	void __iomem *div_base;
+	void __iomem *gate_base;
+
+	struct clk_onecell_data clk_data;
+	struct iproc_asiu_clk *clks;
+};
+
+#define to_asiu_clk(hw) container_of(hw, struct iproc_asiu_clk, hw)
+
+static int iproc_asiu_clk_enable(struct clk_hw *hw)
+{
+	struct iproc_asiu_clk *clk = to_asiu_clk(hw);
+	struct iproc_asiu *asiu = clk->asiu;
+	u32 val;
+
+	/* some clocks at the ASIU level are always enabled */
+	if (clk->gate.offset == IPROC_CLK_INVALID_OFFSET)
+		return 0;
+
+	val = readl(asiu->gate_base + clk->gate.offset);
+	val |= (1 << clk->gate.en_shift);
+	writel(val, asiu->gate_base + clk->gate.offset);
+
+	return 0;
+}
+
+static void iproc_asiu_clk_disable(struct clk_hw *hw)
+{
+	struct iproc_asiu_clk *clk = to_asiu_clk(hw);
+	struct iproc_asiu *asiu = clk->asiu;
+	u32 val;
+
+	/* some clocks at the ASIU level are always enabled */
+	if (clk->gate.offset == IPROC_CLK_INVALID_OFFSET)
+		return;
+
+	val = readl(asiu->gate_base + clk->gate.offset);
+	val &= ~(1 << clk->gate.en_shift);
+	writel(val, asiu->gate_base + clk->gate.offset);
+}
+
+static unsigned long iproc_asiu_clk_recalc_rate(struct clk_hw *hw,
+						unsigned long parent_rate)
+{
+	struct iproc_asiu_clk *clk = to_asiu_clk(hw);
+	struct iproc_asiu *asiu = clk->asiu;
+	u32 val;
+	unsigned int div_h, div_l;
+
+	if (parent_rate == 0) {
+		clk->rate = 0;
+		return 0;
+	}
+
+	/* if clock divisor is not enabled, simply return parent rate */
+	val = readl(asiu->div_base + clk->div.offset);
+	if ((val & (1 << clk->div.en_shift)) == 0) {
+		clk->rate = parent_rate;
+		return parent_rate;
+	}
+
+	/* clock rate = parent rate / (high_div + 1) + (low_div + 1) */
+	div_h = (val >> clk->div.high_shift) & bit_mask(clk->div.high_width);
+	div_h++;
+	div_l = (val >> clk->div.low_shift) & bit_mask(clk->div.low_width);
+	div_l++;
+
+	clk->rate = parent_rate / (div_h + div_l);
+	pr_debug("%s: rate: %lu. parent rate: %lu div_h: %u div_l: %u\n",
+		 __func__, clk->rate, parent_rate, div_h, div_l);
+
+	return clk->rate;
+}
+
+static long iproc_asiu_clk_round_rate(struct clk_hw *hw, unsigned long rate,
+				      unsigned long *parent_rate)
+{
+	unsigned int div;
+
+	if (rate == 0 || *parent_rate == 0)
+		return -EINVAL;
+
+	if (rate == *parent_rate)
+		return *parent_rate;
+
+	div = DIV_ROUND_UP(*parent_rate, rate);
+	if (div < 2)
+		return *parent_rate;
+
+	return *parent_rate / div;
+}
+
+static int iproc_asiu_clk_set_rate(struct clk_hw *hw, unsigned long rate,
+				   unsigned long parent_rate)
+{
+	struct iproc_asiu_clk *clk = to_asiu_clk(hw);
+	struct iproc_asiu *asiu = clk->asiu;
+	unsigned int div, div_h, div_l;
+	u32 val;
+
+	if (rate == 0 || parent_rate == 0)
+		return -EINVAL;
+
+	/* simply disable the divisor if one wants the same rate as parent */
+	if (rate == parent_rate) {
+		val = readl(asiu->div_base + clk->div.offset);
+		val &= ~(1 << clk->div.en_shift);
+		writel(val, asiu->div_base + clk->div.offset);
+		return 0;
+	}
+
+	div = DIV_ROUND_UP(parent_rate, rate);
+	if (div < 2)
+		return -EINVAL;
+
+	div_h = div_l = div >> 1;
+	div_h--;
+	div_l--;
+
+	val = readl(asiu->div_base + clk->div.offset);
+	val |= 1 << clk->div.en_shift;
+	if (div_h) {
+		val &= ~(bit_mask(clk->div.high_width)
+			 << clk->div.high_shift);
+		val |= div_h << clk->div.high_shift;
+	} else {
+		val &= ~(bit_mask(clk->div.high_width)
+			 << clk->div.high_shift);
+	}
+	if (div_l) {
+		val &= ~(bit_mask(clk->div.low_width) << clk->div.low_shift);
+		val |= div_l << clk->div.low_shift;
+	} else {
+		val &= ~(bit_mask(clk->div.low_width) << clk->div.low_shift);
+	}
+	writel(val, asiu->div_base + clk->div.offset);
+
+	return 0;
+}
+
+static const struct clk_ops iproc_asiu_ops = {
+	.enable = iproc_asiu_clk_enable,
+	.disable = iproc_asiu_clk_disable,
+	.recalc_rate = iproc_asiu_clk_recalc_rate,
+	.round_rate = iproc_asiu_clk_round_rate,
+	.set_rate = iproc_asiu_clk_set_rate,
+};
+
+void __init iproc_asiu_setup(struct device_node *node,
+			     const struct iproc_asiu_div *div,
+			     const struct iproc_asiu_gate *gate,
+			     unsigned int num_clks)
+{
+	int i, ret;
+	struct iproc_asiu *asiu;
+
+	if (WARN_ON(!gate || !div))
+		return;
+
+	asiu = kzalloc(sizeof(*asiu), GFP_KERNEL);
+	if (WARN_ON(!asiu))
+		return;
+
+	asiu->clk_data.clk_num = num_clks;
+	asiu->clk_data.clks = kcalloc(num_clks, sizeof(*asiu->clk_data.clks),
+				      GFP_KERNEL);
+	if (WARN_ON(!asiu->clk_data.clks))
+		goto err_clks;
+
+	asiu->clks = kcalloc(num_clks, sizeof(*asiu->clks), GFP_KERNEL);
+	if (WARN_ON(!asiu->clks))
+		goto err_asiu_clks;
+
+	asiu->div_base = of_iomap(node, 0);
+	if (WARN_ON(!asiu->div_base))
+		goto err_iomap_div;
+
+	asiu->gate_base = of_iomap(node, 1);
+	if (WARN_ON(!asiu->gate_base))
+		goto err_iomap_gate;
+
+	for (i = 0; i < num_clks; i++) {
+		struct clk_init_data init;
+		struct clk *clk;
+		const char *parent_name;
+		struct iproc_asiu_clk *asiu_clk;
+		const char *clk_name;
+
+		clk_name = kzalloc(IPROC_CLK_NAME_LEN, GFP_KERNEL);
+		if (WARN_ON(!clk_name))
+			goto err_clk_register;
+
+		ret = of_property_read_string_index(node, "clock-output-names",
+						    i, &clk_name);
+		if (WARN_ON(ret))
+			goto err_clk_register;
+
+		asiu_clk = &asiu->clks[i];
+		asiu_clk->name = clk_name;
+		asiu_clk->asiu = asiu;
+		asiu_clk->div = div[i];
+		asiu_clk->gate = gate[i];
+		init.name = clk_name;
+		init.ops = &iproc_asiu_ops;
+		init.flags = 0;
+		parent_name = of_clk_get_parent_name(node, 0);
+		init.parent_names = (parent_name ? &parent_name : NULL);
+		init.num_parents = (parent_name ? 1 : 0);
+		asiu_clk->hw.init = &init;
+
+		clk = clk_register(NULL, &asiu_clk->hw);
+		if (WARN_ON(IS_ERR(clk)))
+			goto err_clk_register;
+		asiu->clk_data.clks[i] = clk;
+	}
+
+	ret = of_clk_add_provider(node, of_clk_src_onecell_get,
+				  &asiu->clk_data);
+	if (WARN_ON(ret))
+		goto err_clk_register;
+
+	return;
+
+err_clk_register:
+	for (i = 0; i < num_clks; i++)
+		kfree(asiu->clks[i].name);
+	iounmap(asiu->gate_base);
+
+err_iomap_gate:
+	iounmap(asiu->div_base);
+
+err_iomap_div:
+	kfree(asiu->clks);
+
+err_asiu_clks:
+	kfree(asiu->clk_data.clks);
+
+err_clks:
+	kfree(asiu);
+}
diff --git a/drivers/clk/bcm/clk-iproc-pll.c b/drivers/clk/bcm/clk-iproc-pll.c
new file mode 100644
index 0000000..46fb84b
--- /dev/null
+++ b/drivers/clk/bcm/clk-iproc-pll.c
@@ -0,0 +1,716 @@
+/*
+ * Copyright (C) 2014 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/clk-provider.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/clkdev.h>
+#include <linux/of_address.h>
+#include <linux/delay.h>
+
+#include "clk-iproc.h"
+
+#define PLL_VCO_HIGH_SHIFT 19
+#define PLL_VCO_LOW_SHIFT  30
+
+/* number of delay loops waiting for PLL to lock */
+#define LOCK_DELAY 100
+
+/* number of VCO frequency bands */
+#define NUM_FREQ_BANDS 8
+
+#define NUM_KP_BANDS 3
+enum kp_band {
+	KP_BAND_MID = 0,
+	KP_BAND_HIGH,
+	KP_BAND_HIGH_HIGH
+};
+
+static const unsigned int kp_table[NUM_KP_BANDS][NUM_FREQ_BANDS] = {
+	{ 5, 6, 6, 7, 7, 8, 9, 10 },
+	{ 4, 4, 5, 5, 6, 7, 8, 9  },
+	{ 4, 5, 5, 6, 7, 8, 9, 10 },
+};
+
+static const unsigned long ref_freq_table[NUM_FREQ_BANDS][2] = {
+	{ 10000000,  12500000  },
+	{ 12500000,  15000000  },
+	{ 15000000,  20000000  },
+	{ 20000000,  25000000  },
+	{ 25000000,  50000000  },
+	{ 50000000,  75000000  },
+	{ 75000000,  100000000 },
+	{ 100000000, 125000000 },
+};
+
+enum vco_freq_range {
+	VCO_LOW       = 700000000U,
+	VCO_MID       = 1200000000U,
+	VCO_HIGH      = 2200000000U,
+	VCO_HIGH_HIGH = 3100000000U,
+	VCO_MAX       = 4000000000U,
+};
+
+struct iproc_pll;
+
+struct iproc_clk {
+	struct clk_hw hw;
+	const char *name;
+	struct iproc_pll *pll;
+	unsigned long rate;
+	const struct iproc_clk_ctrl *ctrl;
+};
+
+struct iproc_pll {
+	void __iomem *pll_base;
+	void __iomem *pwr_base;
+	void __iomem *asiu_base;
+
+	const struct iproc_pll_ctrl *ctrl;
+	const struct iproc_pll_vco_param *vco_param;
+	unsigned int num_vco_entries;
+
+	struct clk_onecell_data clk_data;
+	struct iproc_clk *clks;
+};
+
+#define to_iproc_clk(hw) container_of(hw, struct iproc_clk, hw)
+
+/*
+ * Based on the target frequency, find a match from the VCO frequency parameter
+ * table and return its index
+ */
+static int pll_get_rate_index(struct iproc_pll *pll, unsigned int target_rate)
+{
+	int i;
+
+	for (i = 0; i < pll->num_vco_entries; i++)
+		if (target_rate == pll->vco_param[i].rate)
+			break;
+
+	if (i >= pll->num_vco_entries)
+		return -EINVAL;
+
+	return i;
+}
+
+static int get_kp(unsigned long ref_freq, enum kp_band kp_index)
+{
+	int i;
+
+	if (ref_freq < ref_freq_table[0][0])
+		return -EINVAL;
+
+	for (i = 0; i < NUM_FREQ_BANDS; i++) {
+		if (ref_freq >= ref_freq_table[i][0] &&
+		    ref_freq < ref_freq_table[i][1])
+			return kp_table[kp_index][i];
+	}
+	return -EINVAL;
+}
+
+static int pll_wait_for_lock(struct iproc_pll *pll)
+{
+	int i;
+	const struct iproc_pll_ctrl *ctrl = pll->ctrl;
+
+	for (i = 0; i < LOCK_DELAY; i++) {
+		u32 val = readl(pll->pll_base + ctrl->status.offset);
+
+		if (val & (1 << ctrl->status.shift))
+			return 0;
+		udelay(10);
+	}
+
+	return -EIO;
+}
+
+static void __pll_disable(struct iproc_pll *pll)
+{
+	const struct iproc_pll_ctrl *ctrl = pll->ctrl;
+	u32 val;
+
+	if (ctrl->flags & IPROC_CLK_PLL_ASIU) {
+		val = readl(pll->asiu_base + ctrl->asiu.offset);
+		val &= ~(1 << ctrl->asiu.en_shift);
+		writel(val, pll->asiu_base + ctrl->asiu.offset);
+	}
+
+	/* latch input value so core power can be shut down */
+	val = readl(pll->pwr_base + ctrl->aon.offset);
+	val |= (1 << ctrl->aon.iso_shift);
+	writel(val, pll->pwr_base + ctrl->aon.offset);
+
+	/* power down the core */
+	val &= ~(bit_mask(ctrl->aon.pwr_width) << ctrl->aon.pwr_shift);
+	writel(val, pll->pwr_base + ctrl->aon.offset);
+}
+
+static int __pll_enable(struct iproc_pll *pll)
+{
+	const struct iproc_pll_ctrl *ctrl = pll->ctrl;
+	u32 val;
+
+	/* power up the PLL and make sure it's not latched */
+	val = readl(pll->pwr_base + ctrl->aon.offset);
+	val |= bit_mask(ctrl->aon.pwr_width) << ctrl->aon.pwr_shift;
+	val &= ~(1 << ctrl->aon.iso_shift);
+	writel(val, pll->pwr_base + ctrl->aon.offset);
+
+	/* certain PLLs also need to be ungated from the ASIU top level */
+	if (ctrl->flags & IPROC_CLK_PLL_ASIU) {
+		val = readl(pll->asiu_base + ctrl->asiu.offset);
+		val |= (1 << ctrl->asiu.en_shift);
+		writel(val, pll->asiu_base + ctrl->asiu.offset);
+	}
+
+	return 0;
+}
+
+static void __pll_put_in_reset(struct iproc_pll *pll)
+{
+	u32 val;
+	const struct iproc_pll_ctrl *ctrl = pll->ctrl;
+	const struct iproc_pll_reset_ctrl *reset = &ctrl->reset;
+
+	val = readl(pll->pll_base + reset->offset);
+	val &= ~(1 << reset->reset_shift | 1 << reset->p_reset_shift);
+	writel(val, pll->pll_base + reset->offset);
+	if (unlikely(ctrl->flags & IPROC_CLK_NEEDS_READ_BACK))
+		readl(pll->pll_base + reset->offset);
+}
+
+static void __pll_bring_out_reset(struct iproc_pll *pll, unsigned int kp,
+				  unsigned int ka, unsigned int ki)
+{
+	u32 val;
+	const struct iproc_pll_ctrl *ctrl = pll->ctrl;
+	const struct iproc_pll_reset_ctrl *reset = &ctrl->reset;
+
+	val = readl(pll->pll_base + reset->offset);
+	val &= ~(bit_mask(reset->ki_width) << reset->ki_shift |
+		 bit_mask(reset->kp_width) << reset->kp_shift |
+		 bit_mask(reset->ka_width) << reset->ka_shift);
+	val |=  ki << reset->ki_shift | kp << reset->kp_shift |
+		ka << reset->ka_shift;
+	val |= 1 << reset->reset_shift | 1 << reset->p_reset_shift;
+	writel(val, pll->pll_base + reset->offset);
+	if (unlikely(ctrl->flags & IPROC_CLK_NEEDS_READ_BACK))
+		readl(pll->pll_base + reset->offset);
+}
+
+static int pll_set_rate(struct iproc_clk *clk, unsigned int rate_index,
+			unsigned long parent_rate)
+{
+	struct iproc_pll *pll = clk->pll;
+	const struct iproc_pll_vco_param *vco = &pll->vco_param[rate_index];
+	const struct iproc_pll_ctrl *ctrl = pll->ctrl;
+	int ka = 0, ki, kp, ret;
+	unsigned long rate = vco->rate;
+	u32 val;
+	enum kp_band kp_index;
+	unsigned long ref_freq;
+
+	/*
+	 * reference frequency = parent frequency / PDIV
+	 * If PDIV = 0, then it becomes a multiplier (x2)
+	 */
+	if (vco->pdiv == 0)
+		ref_freq = parent_rate * 2;
+	else
+		ref_freq = parent_rate / vco->pdiv;
+
+	/* determine Ki and Kp index based on target VCO frequency */
+	if (rate >= VCO_LOW && rate < VCO_HIGH) {
+		ki = 4;
+		kp_index = KP_BAND_MID;
+	} else if (rate >= VCO_HIGH && rate && rate < VCO_HIGH_HIGH) {
+		ki = 3;
+		kp_index = KP_BAND_HIGH;
+	} else if (rate >= VCO_HIGH_HIGH && rate < VCO_MAX) {
+		ki = 3;
+		kp_index = KP_BAND_HIGH_HIGH;
+	} else {
+		pr_err("%s: pll: %s has invalid rate: %lu\n", __func__,
+				clk->name, rate);
+		return -EINVAL;
+	}
+
+	kp = get_kp(ref_freq, kp_index);
+	if (kp < 0) {
+		pr_err("%s: pll: %s has invalid kp\n", __func__, clk->name);
+		return kp;
+	}
+
+	ret = __pll_enable(pll);
+	if (ret) {
+		pr_err("%s: pll: %s fails to enable\n", __func__, clk->name);
+		return ret;
+	}
+
+	/* put PLL in reset */
+	__pll_put_in_reset(pll);
+
+	writel(0, pll->pll_base + ctrl->vco_ctrl.u_offset);
+	if (unlikely(ctrl->flags & IPROC_CLK_NEEDS_READ_BACK))
+		readl(pll->pll_base + ctrl->vco_ctrl.u_offset);
+	val = readl(pll->pll_base + ctrl->vco_ctrl.l_offset);
+
+	if (rate >= VCO_LOW && rate < VCO_MID)
+		val |= (1 << PLL_VCO_LOW_SHIFT);
+
+	if (rate < VCO_HIGH)
+		val &= ~(1 << PLL_VCO_HIGH_SHIFT);
+	else
+		val |= (1 << PLL_VCO_HIGH_SHIFT);
+
+	writel(val, pll->pll_base + ctrl->vco_ctrl.l_offset);
+	if (unlikely(ctrl->flags & IPROC_CLK_NEEDS_READ_BACK))
+		readl(pll->pll_base + ctrl->vco_ctrl.l_offset);
+
+	/* program integer part of NDIV */
+	val = readl(pll->pll_base + ctrl->ndiv_int.offset);
+	val &= ~(bit_mask(ctrl->ndiv_int.width) << ctrl->ndiv_int.shift);
+	val |= vco->ndiv_int << ctrl->ndiv_int.shift;
+	writel(val, pll->pll_base + ctrl->ndiv_int.offset);
+	if (unlikely(ctrl->flags & IPROC_CLK_NEEDS_READ_BACK))
+		readl(pll->pll_base + ctrl->ndiv_int.offset);
+
+	/* program fractional part of NDIV */
+	if (ctrl->flags & IPROC_CLK_PLL_HAS_NDIV_FRAC) {
+		val = readl(pll->pll_base + ctrl->ndiv_frac.offset);
+		val &= ~(bit_mask(ctrl->ndiv_frac.width) <<
+			 ctrl->ndiv_frac.shift);
+		val |= vco->ndiv_frac << ctrl->ndiv_frac.shift;
+		writel(val, pll->pll_base + ctrl->ndiv_frac.offset);
+		if (unlikely(ctrl->flags & IPROC_CLK_NEEDS_READ_BACK))
+			readl(pll->pll_base + ctrl->ndiv_frac.offset);
+	}
+
+	/* program PDIV */
+	val = readl(pll->pll_base + ctrl->pdiv.offset);
+	val &= ~(bit_mask(ctrl->pdiv.width) << ctrl->pdiv.shift);
+	val |= vco->pdiv << ctrl->pdiv.shift;
+	writel(val, pll->pll_base + ctrl->pdiv.offset);
+	if (unlikely(ctrl->flags & IPROC_CLK_NEEDS_READ_BACK))
+		readl(pll->pll_base + ctrl->pdiv.offset);
+
+	__pll_bring_out_reset(pll, kp, ka, ki);
+
+	ret = pll_wait_for_lock(pll);
+	if (ret < 0) {
+		pr_err("%s: pll: %s failed to lock\n", __func__, clk->name);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int iproc_pll_enable(struct clk_hw *hw)
+{
+	struct iproc_clk *clk = to_iproc_clk(hw);
+	struct iproc_pll *pll = clk->pll;
+
+	return __pll_enable(pll);
+}
+
+static void iproc_pll_disable(struct clk_hw *hw)
+{
+	struct iproc_clk *clk = to_iproc_clk(hw);
+	struct iproc_pll *pll = clk->pll;
+	const struct iproc_pll_ctrl *ctrl = pll->ctrl;
+
+	if (ctrl->flags & IPROC_CLK_AON)
+		return;
+
+	__pll_disable(pll);
+}
+
+static unsigned long iproc_pll_recalc_rate(struct clk_hw *hw,
+					   unsigned long parent_rate)
+{
+	struct iproc_clk *clk = to_iproc_clk(hw);
+	struct iproc_pll *pll = clk->pll;
+	const struct iproc_pll_ctrl *ctrl = pll->ctrl;
+	u32 val;
+	u64 ndiv;
+	unsigned int ndiv_int, ndiv_frac, pdiv;
+
+	if (parent_rate == 0)
+		return 0;
+
+	/* PLL needs to be locked */
+	val = readl(pll->pll_base + ctrl->status.offset);
+	if ((val & (1 << ctrl->status.shift)) == 0) {
+		clk->rate = 0;
+		return 0;
+	}
+
+	/*
+	 * PLL output frequency =
+	 *
+	 * ((ndiv_int + ndiv_frac / 2^20) * (parent clock rate / pdiv)
+	 */
+	val = readl(pll->pll_base + ctrl->ndiv_int.offset);
+	ndiv_int = (val >> ctrl->ndiv_int.shift) &
+		bit_mask(ctrl->ndiv_int.width);
+	ndiv = ndiv_int << ctrl->ndiv_int.shift;
+
+	if (ctrl->flags & IPROC_CLK_PLL_HAS_NDIV_FRAC) {
+		val = readl(pll->pll_base + ctrl->ndiv_frac.offset);
+		ndiv_frac = (val >> ctrl->ndiv_frac.shift) &
+			bit_mask(ctrl->ndiv_frac.width);
+
+		if (ndiv_frac != 0)
+			ndiv = (ndiv_int << ctrl->ndiv_int.shift) | ndiv_frac;
+	}
+
+	val = readl(pll->pll_base + ctrl->pdiv.offset);
+	pdiv = (val >> ctrl->pdiv.shift) & bit_mask(ctrl->pdiv.width);
+
+	clk->rate = (ndiv * parent_rate) >> ctrl->ndiv_int.shift;
+
+	if (pdiv == 0)
+		clk->rate *= 2;
+	else
+		clk->rate /= pdiv;
+
+	return clk->rate;
+}
+
+static long iproc_pll_round_rate(struct clk_hw *hw, unsigned long rate,
+				 unsigned long *parent_rate)
+{
+	unsigned i;
+	struct iproc_clk *clk = to_iproc_clk(hw);
+	struct iproc_pll *pll = clk->pll;
+
+	if (rate == 0 || *parent_rate == 0 || !pll->vco_param)
+		return -EINVAL;
+
+	for (i = 0; i < pll->num_vco_entries; i++) {
+		if (rate <= pll->vco_param[i].rate)
+			break;
+	}
+
+	if (i == pll->num_vco_entries)
+		i--;
+
+	return pll->vco_param[i].rate;
+}
+
+static int iproc_pll_set_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long parent_rate)
+{
+	struct iproc_clk *clk = to_iproc_clk(hw);
+	struct iproc_pll *pll = clk->pll;
+	int rate_index, ret;
+
+	rate_index = pll_get_rate_index(pll, rate);
+	if (rate_index < 0)
+		return rate_index;
+
+	ret = pll_set_rate(clk, rate_index, parent_rate);
+	return ret;
+}
+
+static const struct clk_ops iproc_pll_ops = {
+	.enable = iproc_pll_enable,
+	.disable = iproc_pll_disable,
+	.recalc_rate = iproc_pll_recalc_rate,
+	.round_rate = iproc_pll_round_rate,
+	.set_rate = iproc_pll_set_rate,
+};
+
+static int iproc_clk_enable(struct clk_hw *hw)
+{
+	struct iproc_clk *clk = to_iproc_clk(hw);
+	const struct iproc_clk_ctrl *ctrl = clk->ctrl;
+	struct iproc_pll *pll = clk->pll;
+	u32 val;
+
+	/* channel enable is active low */
+	val = readl(pll->pll_base + ctrl->enable.offset);
+	val &= ~(1 << ctrl->enable.enable_shift);
+	writel(val, pll->pll_base + ctrl->enable.offset);
+
+	/* also make sure channel is not held */
+	val = readl(pll->pll_base + ctrl->enable.offset);
+	val &= ~(1 << ctrl->enable.hold_shift);
+	writel(val, pll->pll_base + ctrl->enable.offset);
+	if (unlikely(ctrl->flags & IPROC_CLK_NEEDS_READ_BACK))
+		readl(pll->pll_base + ctrl->enable.offset);
+
+	return 0;
+}
+
+static void iproc_clk_disable(struct clk_hw *hw)
+{
+	struct iproc_clk *clk = to_iproc_clk(hw);
+	const struct iproc_clk_ctrl *ctrl = clk->ctrl;
+	struct iproc_pll *pll = clk->pll;
+	u32 val;
+
+	if (ctrl->flags & IPROC_CLK_AON)
+		return;
+
+	val = readl(pll->pll_base + ctrl->enable.offset);
+	val |= 1 << ctrl->enable.enable_shift;
+	writel(val, pll->pll_base + ctrl->enable.offset);
+	if (unlikely(ctrl->flags & IPROC_CLK_NEEDS_READ_BACK))
+		readl(pll->pll_base + ctrl->enable.offset);
+}
+
+static unsigned long iproc_clk_recalc_rate(struct clk_hw *hw,
+		unsigned long parent_rate)
+{
+	struct iproc_clk *clk = to_iproc_clk(hw);
+	const struct iproc_clk_ctrl *ctrl = clk->ctrl;
+	struct iproc_pll *pll = clk->pll;
+	u32 val;
+	unsigned int mdiv;
+
+	if (parent_rate == 0)
+		return 0;
+
+	val = readl(pll->pll_base + ctrl->mdiv.offset);
+	mdiv = (val >> ctrl->mdiv.shift) & bit_mask(ctrl->mdiv.width);
+	if (mdiv == 0)
+		mdiv = 256;
+
+	clk->rate = parent_rate / mdiv;
+
+	return clk->rate;
+}
+
+static long iproc_clk_round_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long *parent_rate)
+{
+	unsigned int div;
+
+	if (rate == 0 || *parent_rate == 0)
+		return -EINVAL;
+
+	if (rate == *parent_rate)
+		return *parent_rate;
+
+	div = DIV_ROUND_UP(*parent_rate, rate);
+	if (div < 2)
+		return *parent_rate;
+
+	if (div > 256)
+		div = 256;
+
+	return *parent_rate / div;
+}
+
+static int iproc_clk_set_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long parent_rate)
+{
+	struct iproc_clk *clk = to_iproc_clk(hw);
+	const struct iproc_clk_ctrl *ctrl = clk->ctrl;
+	struct iproc_pll *pll = clk->pll;
+	u32 val;
+	unsigned int div;
+
+	if (rate == 0 || parent_rate == 0)
+		return -EINVAL;
+
+	div = DIV_ROUND_UP(parent_rate, rate);
+	if (div > 256)
+		return -EINVAL;
+
+	val = readl(pll->pll_base + ctrl->mdiv.offset);
+	if (div == 256) {
+		val &= ~(bit_mask(ctrl->mdiv.width) << ctrl->mdiv.shift);
+	} else {
+		val &= ~(bit_mask(ctrl->mdiv.width) << ctrl->mdiv.shift);
+		val |= div << ctrl->mdiv.shift;
+	}
+	writel(val, pll->pll_base + ctrl->mdiv.offset);
+	if (unlikely(ctrl->flags & IPROC_CLK_NEEDS_READ_BACK))
+		readl(pll->pll_base + ctrl->mdiv.offset);
+	clk->rate = parent_rate / div;
+
+	return 0;
+}
+
+static const struct clk_ops iproc_clk_ops = {
+	.enable = iproc_clk_enable,
+	.disable = iproc_clk_disable,
+	.recalc_rate = iproc_clk_recalc_rate,
+	.round_rate = iproc_clk_round_rate,
+	.set_rate = iproc_clk_set_rate,
+};
+
+/**
+ * Some PLLs require the PLL SW override bit to be set before changes can be
+ * applied to the PLL
+ */
+static void iproc_pll_sw_cfg(struct iproc_pll *pll)
+{
+	const struct iproc_pll_ctrl *ctrl = pll->ctrl;
+
+	if (ctrl->flags & IPROC_CLK_PLL_NEEDS_SW_CFG) {
+		u32 val;
+
+		val = readl(pll->pll_base + ctrl->sw_ctrl.offset);
+		val |= BIT(ctrl->sw_ctrl.shift);
+		writel(val, pll->pll_base + ctrl->sw_ctrl.offset);
+		if (unlikely(ctrl->flags & IPROC_CLK_NEEDS_READ_BACK))
+			readl(pll->pll_base + ctrl->sw_ctrl.offset);
+	}
+}
+
+void __init iproc_pll_clk_setup(struct device_node *node,
+				const struct iproc_pll_ctrl *pll_ctrl,
+				const struct iproc_pll_vco_param *vco,
+				unsigned int num_vco_entries,
+				const struct iproc_clk_ctrl *clk_ctrl,
+				unsigned int num_clks)
+{
+	int i, ret;
+	struct clk *clk;
+	struct iproc_pll *pll;
+	struct iproc_clk *iclk;
+	struct clk_init_data init;
+	const char *parent_name;
+
+	if (WARN_ON(!pll_ctrl) || WARN_ON(!clk_ctrl))
+		return;
+
+	pll = kzalloc(sizeof(*pll), GFP_KERNEL);
+	if (WARN_ON(!pll))
+		return;
+
+	pll->clk_data.clk_num = num_clks;
+	pll->clk_data.clks = kcalloc(num_clks, sizeof(*pll->clk_data.clks),
+				     GFP_KERNEL);
+	if (WARN_ON(!pll->clk_data.clks))
+		goto err_clk_data;
+
+	pll->clks = kcalloc(num_clks, sizeof(*pll->clks), GFP_KERNEL);
+	if (WARN_ON(!pll->clks))
+		goto err_clks;
+
+	pll->pll_base = of_iomap(node, 0);
+	if (WARN_ON(!pll->pll_base))
+		goto err_pll_iomap;
+
+	pll->pwr_base = of_iomap(node, 1);
+	if (WARN_ON(!pll->pwr_base))
+		goto err_pwr_iomap;
+
+	/* some PLLs require gating control at the top ASIU level */
+	if (pll_ctrl->flags & IPROC_CLK_PLL_ASIU) {
+		pll->asiu_base = of_iomap(node, 2);
+		if (WARN_ON(!pll->asiu_base))
+			goto err_asiu_iomap;
+	}
+
+	/* initialize and register the PLL itself */
+	pll->ctrl = pll_ctrl;
+
+	iclk = &pll->clks[0];
+	iclk->pll = pll;
+	iclk->name = node->name;
+
+	init.name = node->name;
+	init.ops = &iproc_pll_ops;
+	init.flags = 0;
+	parent_name = of_clk_get_parent_name(node, 0);
+	init.parent_names = (parent_name ? &parent_name : NULL);
+	init.num_parents = (parent_name ? 1 : 0);
+	iclk->hw.init = &init;
+
+	if (vco) {
+		pll->num_vco_entries = num_vco_entries;
+		pll->vco_param = vco;
+	}
+
+	iproc_pll_sw_cfg(pll);
+
+	clk = clk_register(NULL, &iclk->hw);
+	if (WARN_ON(IS_ERR(clk)))
+		goto err_pll_register;
+
+	pll->clk_data.clks[0] = clk;
+
+	/* now initialize and register all leaf clocks */
+	for (i = 1; i < num_clks; i++) {
+		const char *clk_name;
+
+		memset(&init, 0, sizeof(init));
+		parent_name = node->name;
+
+		clk_name = kzalloc(IPROC_CLK_NAME_LEN, GFP_KERNEL);
+		if (WARN_ON(!clk_name))
+			goto err_clk_register;
+
+		ret = of_property_read_string_index(node, "clock-output-names",
+						    i, &clk_name);
+		if (WARN_ON(ret))
+			goto err_clk_register;
+
+		iclk = &pll->clks[i];
+		iclk->name = clk_name;
+		iclk->pll = pll;
+		iclk->ctrl = &clk_ctrl[i];
+
+		init.name = clk_name;
+		init.ops = &iproc_clk_ops;
+		init.flags = 0;
+		init.parent_names = (parent_name ? &parent_name : NULL);
+		init.num_parents = (parent_name ? 1 : 0);
+		iclk->hw.init = &init;
+
+		clk = clk_register(NULL, &iclk->hw);
+		if (WARN_ON(IS_ERR(clk)))
+			goto err_clk_register;
+
+		pll->clk_data.clks[i] = clk;
+	}
+
+	ret = of_clk_add_provider(node, of_clk_src_onecell_get, &pll->clk_data);
+	if (WARN_ON(ret))
+		goto err_clk_register;
+
+	return;
+
+err_clk_register:
+	for (i = 0; i < num_clks; i++) {
+		kfree(pll->clks[i].name);
+		clk_unregister(pll->clk_data.clks[i]);
+	}
+
+err_pll_register:
+	if (pll->asiu_base)
+		iounmap(pll->asiu_base);
+
+err_asiu_iomap:
+	iounmap(pll->pwr_base);
+
+err_pwr_iomap:
+	iounmap(pll->pll_base);
+
+err_pll_iomap:
+	kfree(pll->clks);
+
+err_clks:
+	kfree(pll->clk_data.clks);
+
+err_clk_data:
+	kfree(pll);
+}
diff --git a/drivers/clk/bcm/clk-iproc.h b/drivers/clk/bcm/clk-iproc.h
new file mode 100644
index 0000000..d834b7a
--- /dev/null
+++ b/drivers/clk/bcm/clk-iproc.h
@@ -0,0 +1,178 @@
+/*
+ * Copyright (C) 2014 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CLK_IPROC_H
+#define _CLK_IPROC_H
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/device.h>
+#include <linux/of.h>
+#include <linux/clk-provider.h>
+
+#define IPROC_CLK_NAME_LEN 25
+#define IPROC_CLK_INVALID_OFFSET 0xffffffff
+#define bit_mask(width) ((1 << (width)) - 1)
+
+/* clocks that should not be disabled at runtime */
+#define IPROC_CLK_AON BIT(0)
+
+/* PLL that requires gating through ASIU */
+#define IPROC_CLK_PLL_ASIU BIT(1)
+
+/* PLL that has fractional part of the NDIV */
+#define IPROC_CLK_PLL_HAS_NDIV_FRAC BIT(2)
+
+/*
+ * Some of the iProc PLL/clocks may have an ASIC bug that requires read back
+ * of the same register following the write to flush the write transaction into
+ * the intended register
+ */
+#define IPROC_CLK_NEEDS_READ_BACK BIT(3)
+
+/*
+ * Some PLLs require the PLL SW override bit to be set before changes can be
+ * applied to the PLL
+ */
+#define IPROC_CLK_PLL_NEEDS_SW_CFG BIT(4)
+
+/*
+ * Parameters for VCO frequency configuration
+ *
+ * VCO frequency =
+ * ((ndiv_int + ndiv_frac / 2^20) * (ref freqeuncy  / pdiv)
+ */
+struct iproc_pll_vco_param {
+	unsigned long rate;
+	unsigned int ndiv_int;
+	unsigned int ndiv_frac;
+	unsigned int pdiv;
+};
+
+struct iproc_clk_reg_op {
+	unsigned int offset;
+	unsigned int shift;
+	unsigned int width;
+};
+
+/*
+ * Clock gating control at the top ASIU level
+ */
+struct iproc_asiu_gate {
+	unsigned int offset;
+	unsigned int en_shift;
+};
+
+/*
+ * Control of powering on/off of a PLL
+ *
+ * Before powering off a PLL, input isolation (ISO) needs to be enabled
+ */
+struct iproc_pll_aon_pwr_ctrl {
+	unsigned int offset;
+	unsigned int pwr_width;
+	unsigned int pwr_shift;
+	unsigned int iso_shift;
+};
+
+/*
+ * Control of the PLL reset, with Ki, Kp, and Ka parameters
+ */
+struct iproc_pll_reset_ctrl {
+	unsigned int offset;
+	unsigned int reset_shift;
+	unsigned int p_reset_shift;
+	unsigned int ki_shift;
+	unsigned int ki_width;
+	unsigned int kp_shift;
+	unsigned int kp_width;
+	unsigned int ka_shift;
+	unsigned int ka_width;
+};
+
+/*
+ * To enable SW control of the PLL
+ */
+struct iproc_pll_sw_ctrl {
+	unsigned int offset;
+	unsigned int shift;
+};
+
+struct iproc_pll_vco_ctrl {
+	unsigned int u_offset;
+	unsigned int l_offset;
+};
+
+/*
+ * Main PLL control parameters
+ */
+struct iproc_pll_ctrl {
+	unsigned long flags;
+	struct iproc_pll_aon_pwr_ctrl aon;
+	struct iproc_asiu_gate asiu;
+	struct iproc_pll_reset_ctrl reset;
+	struct iproc_pll_sw_ctrl sw_ctrl;
+	struct iproc_clk_reg_op ndiv_int;
+	struct iproc_clk_reg_op ndiv_frac;
+	struct iproc_clk_reg_op pdiv;
+	struct iproc_pll_vco_ctrl vco_ctrl;
+	struct iproc_clk_reg_op status;
+};
+
+/*
+ * Controls enabling/disabling a PLL derived clock
+ */
+struct iproc_clk_enable_ctrl {
+	unsigned int offset;
+	unsigned int enable_shift;
+	unsigned int hold_shift;
+	unsigned int bypass_shift;
+};
+
+/*
+ * Main clock control parameters for clocks derived from the PLLs
+ */
+struct iproc_clk_ctrl {
+	unsigned int channel;
+	unsigned long flags;
+	struct iproc_clk_enable_ctrl enable;
+	struct iproc_clk_reg_op mdiv;
+};
+
+/*
+ * Divisor of the ASIU clocks
+ */
+struct iproc_asiu_div {
+	unsigned int offset;
+	unsigned int en_shift;
+	unsigned int high_shift;
+	unsigned int high_width;
+	unsigned int low_shift;
+	unsigned int low_width;
+};
+
+void __init iproc_armpll_setup(struct device_node *node);
+void __init iproc_pll_clk_setup(struct device_node *node,
+				const struct iproc_pll_ctrl *pll_ctrl,
+				const struct iproc_pll_vco_param *vco,
+				unsigned int num_vco_entries,
+				const struct iproc_clk_ctrl *clk_ctrl,
+				unsigned int num_clks);
+void __init iproc_asiu_setup(struct device_node *node,
+			     const struct iproc_asiu_div *div,
+			     const struct iproc_asiu_gate *gate,
+			     unsigned int num_clks);
+
+#endif /* _CLK_IPROC_H */
diff --git a/drivers/clk/bcm/clk-kona-setup.c b/drivers/clk/bcm/clk-kona-setup.c
index e5aeded..deaa7f9 100644
--- a/drivers/clk/bcm/clk-kona-setup.c
+++ b/drivers/clk/bcm/clk-kona-setup.c
@@ -21,8 +21,6 @@
 #define selector_clear_exists(sel)	((sel)->width = 0)
 #define trigger_clear_exists(trig)	FLAG_CLEAR(trig, TRIG, EXISTS)
 
-LIST_HEAD(ccu_list);	/* The list of set up CCUs */
-
 /* Validity checking */
 
 static bool ccu_data_offsets_valid(struct ccu_data *ccu)
@@ -773,7 +771,6 @@
 
 	of_clk_del_provider(ccu->node);	/* safe if never added */
 	ccu_clks_teardown(ccu);
-	list_del(&ccu->links);
 	of_node_put(ccu->node);
 	ccu->node = NULL;
 	iounmap(ccu->base);
@@ -847,7 +844,6 @@
 		goto out_err;
 	}
 	ccu->node = of_node_get(node);
-	list_add_tail(&ccu->links, &ccu_list);
 
 	/*
 	 * Set up each defined kona clock and save the result in
diff --git a/drivers/clk/bcm/clk-kona.c b/drivers/clk/bcm/clk-kona.c
index a0ef4f7..79a9850 100644
--- a/drivers/clk/bcm/clk-kona.c
+++ b/drivers/clk/bcm/clk-kona.c
@@ -1240,7 +1240,7 @@
 	default:
 		BUG();
 	}
-	return -EINVAL;
+	return false;
 }
 
 /* Set a CCU and all its clocks into their desired initial state */
diff --git a/drivers/clk/bcm/clk-kona.h b/drivers/clk/bcm/clk-kona.h
index 6849a64..906576e 100644
--- a/drivers/clk/bcm/clk-kona.h
+++ b/drivers/clk/bcm/clk-kona.h
@@ -480,7 +480,6 @@
 	spinlock_t lock;	/* serialization lock */
 	bool write_enabled;	/* write access is currently enabled */
 	struct ccu_policy policy;
-	struct list_head links;	/* for ccu_list */
 	struct device_node *node;
 	struct clk_onecell_data clk_data;
 	const char *name;
@@ -492,7 +491,6 @@
 #define KONA_CCU_COMMON(_prefix, _name, _ccuname)			    \
 	.name		= #_name "_ccu",				    \
 	.lock		= __SPIN_LOCK_UNLOCKED(_name ## _ccu_data.lock),    \
-	.links		= LIST_HEAD_INIT(_name ## _ccu_data.links),	    \
 	.clk_data	= {						    \
 		.clk_num = _prefix ## _ ## _ccuname ## _CCU_CLOCK_COUNT,    \
 	}
diff --git a/drivers/clk/berlin/berlin2-pll.c b/drivers/clk/berlin/berlin2-pll.c
index bdc506b..f4b8d32 100644
--- a/drivers/clk/berlin/berlin2-pll.c
+++ b/drivers/clk/berlin/berlin2-pll.c
@@ -25,14 +25,7 @@
 #include <asm/div64.h>
 
 #include "berlin2-div.h"
-
-struct berlin2_pll_map {
-	const u8 vcodiv[16];
-	u8 mult;
-	u8 fbdiv_shift;
-	u8 rfdiv_shift;
-	u8 divsel_shift;
-};
+#include "berlin2-pll.h"
 
 struct berlin2_pll {
 	struct clk_hw hw;
diff --git a/drivers/clk/clk-asm9260.c b/drivers/clk/clk-asm9260.c
index 88f4ff6..90897af 100644
--- a/drivers/clk/clk-asm9260.c
+++ b/drivers/clk/clk-asm9260.c
@@ -274,7 +274,7 @@
 	u32 accuracy = 0;
 
 	base = of_io_request_and_map(np, 0, np->name);
-	if (!base)
+	if (IS_ERR(base))
 		panic("%s: unable to map resource", np->name);
 
 	/* register pll */
diff --git a/drivers/clk/clk-axm5516.c b/drivers/clk/clk-axm5516.c
index 0f6368c..c7c91a5 100644
--- a/drivers/clk/clk-axm5516.c
+++ b/drivers/clk/clk-axm5516.c
@@ -556,7 +556,7 @@
 		return PTR_ERR(regmap);
 
 	num_clks = ARRAY_SIZE(axmclk_clocks);
-	pr_info("axmclk: supporting %u clocks\n", num_clks);
+	pr_info("axmclk: supporting %zu clocks\n", num_clks);
 	priv = devm_kzalloc(dev, sizeof(*priv) + sizeof(*priv->clks) * num_clks,
 			    GFP_KERNEL);
 	if (!priv)
diff --git a/drivers/clk/clk-cdce706.c b/drivers/clk/clk-cdce706.c
index b8e4f8a..f01164f 100644
--- a/drivers/clk/clk-cdce706.c
+++ b/drivers/clk/clk-cdce706.c
@@ -94,7 +94,7 @@
 	"clk_in0", "clk_in1",
 };
 
-static const char *cdce706_clkin_name[] = {
+static const char * const cdce706_clkin_name[] = {
 	"clk_in",
 };
 
@@ -102,7 +102,7 @@
 	"pll1", "pll2", "pll3",
 };
 
-static const char *cdce706_divider_parent_name[] = {
+static const char * const cdce706_divider_parent_name[] = {
 	"clk_in", "pll1", "pll2", "pll2", "pll3",
 };
 
@@ -666,6 +666,7 @@
 
 static int cdce706_remove(struct i2c_client *client)
 {
+	of_clk_del_provider(client->dev.of_node);
 	return 0;
 }
 
diff --git a/drivers/clk/clk-cdce925.c b/drivers/clk/clk-cdce925.c
new file mode 100644
index 0000000..85fafb4
--- /dev/null
+++ b/drivers/clk/clk-cdce925.c
@@ -0,0 +1,749 @@
+/*
+ * Driver for TI Dual PLL CDCE925 clock synthesizer
+ *
+ * This driver always connects the Y1 to the input clock, Y2/Y3 to PLL1
+ * and Y4/Y5 to PLL2. PLL frequency is set on a first-come-first-serve
+ * basis. Clients can directly request any frequency that the chip can
+ * deliver using the standard clk framework. In addition, the device can
+ * be configured and activated via the devicetree.
+ *
+ * Copyright (C) 2014, Topic Embedded Products
+ * Licenced under GPL
+ */
+#include <linux/clk-provider.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/i2c.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/gcd.h>
+
+/* The chip has 2 PLLs which can be routed through dividers to 5 outputs.
+ * Model this as 2 PLL clocks which are parents to the outputs.
+ */
+#define NUMBER_OF_PLLS	2
+#define NUMBER_OF_OUTPUTS	5
+
+#define CDCE925_REG_GLOBAL1	0x01
+#define CDCE925_REG_Y1SPIPDIVH	0x02
+#define CDCE925_REG_PDIVL	0x03
+#define CDCE925_REG_XCSEL	0x05
+/* PLL parameters start at 0x10, steps of 0x10 */
+#define CDCE925_OFFSET_PLL	0x10
+/* Add CDCE925_OFFSET_PLL * (pll) to these registers before sending */
+#define CDCE925_PLL_MUX_OUTPUTS	0x14
+#define CDCE925_PLL_MULDIV	0x18
+
+#define CDCE925_PLL_FREQUENCY_MIN	 80000000ul
+#define CDCE925_PLL_FREQUENCY_MAX	230000000ul
+struct clk_cdce925_chip;
+
+struct clk_cdce925_output {
+	struct clk_hw hw;
+	struct clk_cdce925_chip *chip;
+	u8 index;
+	u16 pdiv; /* 1..127 for Y2-Y5; 1..1023 for Y1 */
+};
+#define to_clk_cdce925_output(_hw) \
+	container_of(_hw, struct clk_cdce925_output, hw)
+
+struct clk_cdce925_pll {
+	struct clk_hw hw;
+	struct clk_cdce925_chip *chip;
+	u8 index;
+	u16 m;   /* 1..511 */
+	u16 n;   /* 1..4095 */
+};
+#define to_clk_cdce925_pll(_hw)	container_of(_hw, struct clk_cdce925_pll, hw)
+
+struct clk_cdce925_chip {
+	struct regmap *regmap;
+	struct i2c_client *i2c_client;
+	struct clk_cdce925_pll pll[NUMBER_OF_PLLS];
+	struct clk_cdce925_output clk[NUMBER_OF_OUTPUTS];
+	struct clk *dt_clk[NUMBER_OF_OUTPUTS];
+	struct clk_onecell_data onecell;
+};
+
+/* ** ** ** ** ** ** ** ** ** ** ** ** ** ** ** ** ** ** ** ** ** ** */
+
+static unsigned long cdce925_pll_calculate_rate(unsigned long parent_rate,
+	u16 n, u16 m)
+{
+	if ((!m || !n) || (m == n))
+		return parent_rate; /* In bypass mode runs at same frequency */
+	return mult_frac(parent_rate, (unsigned long)n, (unsigned long)m);
+}
+
+static unsigned long cdce925_pll_recalc_rate(struct clk_hw *hw,
+		unsigned long parent_rate)
+{
+	/* Output frequency of PLL is Fout = (Fin/Pdiv)*(N/M) */
+	struct clk_cdce925_pll *data = to_clk_cdce925_pll(hw);
+
+	return cdce925_pll_calculate_rate(parent_rate, data->n, data->m);
+}
+
+static void cdce925_pll_find_rate(unsigned long rate,
+		unsigned long parent_rate, u16 *n, u16 *m)
+{
+	unsigned long un;
+	unsigned long um;
+	unsigned long g;
+
+	if (rate <= parent_rate) {
+		/* Can always deliver parent_rate in bypass mode */
+		rate = parent_rate;
+		*n = 0;
+		*m = 0;
+	} else {
+		/* In PLL mode, need to apply min/max range */
+		if (rate < CDCE925_PLL_FREQUENCY_MIN)
+			rate = CDCE925_PLL_FREQUENCY_MIN;
+		else if (rate > CDCE925_PLL_FREQUENCY_MAX)
+			rate = CDCE925_PLL_FREQUENCY_MAX;
+
+		g = gcd(rate, parent_rate);
+		um = parent_rate / g;
+		un = rate / g;
+		/* When outside hw range, reduce to fit (rounding errors) */
+		while ((un > 4095) || (um > 511)) {
+			un >>= 1;
+			um >>= 1;
+		}
+		if (un == 0)
+			un = 1;
+		if (um == 0)
+			um = 1;
+
+		*n = un;
+		*m = um;
+	}
+}
+
+static long cdce925_pll_round_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long *parent_rate)
+{
+	u16 n, m;
+
+	cdce925_pll_find_rate(rate, *parent_rate, &n, &m);
+	return (long)cdce925_pll_calculate_rate(*parent_rate, n, m);
+}
+
+static int cdce925_pll_set_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long parent_rate)
+{
+	struct clk_cdce925_pll *data = to_clk_cdce925_pll(hw);
+
+	if (!rate || (rate == parent_rate)) {
+		data->m = 0; /* Bypass mode */
+		data->n = 0;
+		return 0;
+	}
+
+	if ((rate < CDCE925_PLL_FREQUENCY_MIN) ||
+		(rate > CDCE925_PLL_FREQUENCY_MAX)) {
+		pr_debug("%s: rate %lu outside PLL range.\n", __func__, rate);
+		return -EINVAL;
+	}
+
+	if (rate < parent_rate) {
+		pr_debug("%s: rate %lu less than parent rate %lu.\n", __func__,
+			rate, parent_rate);
+		return -EINVAL;
+	}
+
+	cdce925_pll_find_rate(rate, parent_rate, &data->n, &data->m);
+	return 0;
+}
+
+
+/* calculate p = max(0, 4 - int(log2 (n/m))) */
+static u8 cdce925_pll_calc_p(u16 n, u16 m)
+{
+	u8 p;
+	u16 r = n / m;
+
+	if (r >= 16)
+		return 0;
+	p = 4;
+	while (r > 1) {
+		r >>= 1;
+		--p;
+	}
+	return p;
+}
+
+/* Returns VCO range bits for VCO1_0_RANGE */
+static u8 cdce925_pll_calc_range_bits(struct clk_hw *hw, u16 n, u16 m)
+{
+	struct clk *parent = clk_get_parent(hw->clk);
+	unsigned long rate = clk_get_rate(parent);
+
+	rate = mult_frac(rate, (unsigned long)n, (unsigned long)m);
+	if (rate >= 175000000)
+		return 0x3;
+	if (rate >= 150000000)
+		return 0x02;
+	if (rate >= 125000000)
+		return 0x01;
+	return 0x00;
+}
+
+/* I2C clock, hence everything must happen in (un)prepare because this
+ * may sleep */
+static int cdce925_pll_prepare(struct clk_hw *hw)
+{
+	struct clk_cdce925_pll *data = to_clk_cdce925_pll(hw);
+	u16 n = data->n;
+	u16 m = data->m;
+	u16 r;
+	u8 q;
+	u8 p;
+	u16 nn;
+	u8 pll[4]; /* Bits are spread out over 4 byte registers */
+	u8 reg_ofs = data->index * CDCE925_OFFSET_PLL;
+	unsigned i;
+
+	if ((!m || !n) || (m == n)) {
+		/* Set PLL mux to bypass mode, leave the rest as is */
+		regmap_update_bits(data->chip->regmap,
+			reg_ofs + CDCE925_PLL_MUX_OUTPUTS, 0x80, 0x80);
+	} else {
+		/* According to data sheet: */
+		/* p = max(0, 4 - int(log2 (n/m))) */
+		p = cdce925_pll_calc_p(n, m);
+		/* nn = n * 2^p */
+		nn = n * BIT(p);
+		/* q = int(nn/m) */
+		q = nn / m;
+		if ((q < 16) || (1 > 64)) {
+			pr_debug("%s invalid q=%d\n", __func__, q);
+			return -EINVAL;
+		}
+		r = nn - (m*q);
+		if (r > 511) {
+			pr_debug("%s invalid r=%d\n", __func__, r);
+			return -EINVAL;
+		}
+		pr_debug("%s n=%d m=%d p=%d q=%d r=%d\n", __func__,
+			n, m, p, q, r);
+		/* encode into register bits */
+		pll[0] = n >> 4;
+		pll[1] = ((n & 0x0F) << 4) | ((r >> 5) & 0x0F);
+		pll[2] = ((r & 0x1F) << 3) | ((q >> 3) & 0x07);
+		pll[3] = ((q & 0x07) << 5) | (p << 2) |
+				cdce925_pll_calc_range_bits(hw, n, m);
+		/* Write to registers */
+		for (i = 0; i < ARRAY_SIZE(pll); ++i)
+			regmap_write(data->chip->regmap,
+				reg_ofs + CDCE925_PLL_MULDIV + i, pll[i]);
+		/* Enable PLL */
+		regmap_update_bits(data->chip->regmap,
+			reg_ofs + CDCE925_PLL_MUX_OUTPUTS, 0x80, 0x00);
+	}
+
+	return 0;
+}
+
+static void cdce925_pll_unprepare(struct clk_hw *hw)
+{
+	struct clk_cdce925_pll *data = to_clk_cdce925_pll(hw);
+	u8 reg_ofs = data->index * CDCE925_OFFSET_PLL;
+
+	regmap_update_bits(data->chip->regmap,
+			reg_ofs + CDCE925_PLL_MUX_OUTPUTS, 0x80, 0x80);
+}
+
+static const struct clk_ops cdce925_pll_ops = {
+	.prepare = cdce925_pll_prepare,
+	.unprepare = cdce925_pll_unprepare,
+	.recalc_rate = cdce925_pll_recalc_rate,
+	.round_rate = cdce925_pll_round_rate,
+	.set_rate = cdce925_pll_set_rate,
+};
+
+
+static void cdce925_clk_set_pdiv(struct clk_cdce925_output *data, u16 pdiv)
+{
+	switch (data->index) {
+	case 0:
+		regmap_update_bits(data->chip->regmap,
+			CDCE925_REG_Y1SPIPDIVH,
+			0x03, (pdiv >> 8) & 0x03);
+		regmap_write(data->chip->regmap, 0x03, pdiv & 0xFF);
+		break;
+	case 1:
+		regmap_update_bits(data->chip->regmap, 0x16, 0x7F, pdiv);
+		break;
+	case 2:
+		regmap_update_bits(data->chip->regmap, 0x17, 0x7F, pdiv);
+		break;
+	case 3:
+		regmap_update_bits(data->chip->regmap, 0x26, 0x7F, pdiv);
+		break;
+	case 4:
+		regmap_update_bits(data->chip->regmap, 0x27, 0x7F, pdiv);
+		break;
+	}
+}
+
+static void cdce925_clk_activate(struct clk_cdce925_output *data)
+{
+	switch (data->index) {
+	case 0:
+		regmap_update_bits(data->chip->regmap,
+			CDCE925_REG_Y1SPIPDIVH, 0x0c, 0x0c);
+		break;
+	case 1:
+	case 2:
+		regmap_update_bits(data->chip->regmap, 0x14, 0x03, 0x03);
+		break;
+	case 3:
+	case 4:
+		regmap_update_bits(data->chip->regmap, 0x24, 0x03, 0x03);
+		break;
+	}
+}
+
+static int cdce925_clk_prepare(struct clk_hw *hw)
+{
+	struct clk_cdce925_output *data = to_clk_cdce925_output(hw);
+
+	cdce925_clk_set_pdiv(data, data->pdiv);
+	cdce925_clk_activate(data);
+	return 0;
+}
+
+static void cdce925_clk_unprepare(struct clk_hw *hw)
+{
+	struct clk_cdce925_output *data = to_clk_cdce925_output(hw);
+
+	/* Disable clock by setting divider to "0" */
+	cdce925_clk_set_pdiv(data, 0);
+}
+
+static unsigned long cdce925_clk_recalc_rate(struct clk_hw *hw,
+		unsigned long parent_rate)
+{
+	struct clk_cdce925_output *data = to_clk_cdce925_output(hw);
+
+	if (data->pdiv)
+		return parent_rate / data->pdiv;
+	return 0;
+}
+
+static u16 cdce925_calc_divider(unsigned long rate,
+		unsigned long parent_rate)
+{
+	unsigned long divider;
+
+	if (!rate)
+		return 0;
+	if (rate >= parent_rate)
+		return 1;
+
+	divider = DIV_ROUND_CLOSEST(parent_rate, rate);
+	if (divider > 0x7F)
+		divider = 0x7F;
+
+	return (u16)divider;
+}
+
+static unsigned long cdce925_clk_best_parent_rate(
+	struct clk_hw *hw, unsigned long rate)
+{
+	struct clk *pll = clk_get_parent(hw->clk);
+	struct clk *root = clk_get_parent(pll);
+	unsigned long root_rate = clk_get_rate(root);
+	unsigned long best_rate_error = rate;
+	u16 pdiv_min;
+	u16 pdiv_max;
+	u16 pdiv_best;
+	u16 pdiv_now;
+
+	if (root_rate % rate == 0)
+		return root_rate; /* Don't need the PLL, use bypass */
+
+	pdiv_min = (u16)max(1ul, DIV_ROUND_UP(CDCE925_PLL_FREQUENCY_MIN, rate));
+	pdiv_max = (u16)min(127ul, CDCE925_PLL_FREQUENCY_MAX / rate);
+
+	if (pdiv_min > pdiv_max)
+		return 0; /* No can do? */
+
+	pdiv_best = pdiv_min;
+	for (pdiv_now = pdiv_min; pdiv_now < pdiv_max; ++pdiv_now) {
+		unsigned long target_rate = rate * pdiv_now;
+		long pll_rate = clk_round_rate(pll, target_rate);
+		unsigned long actual_rate;
+		unsigned long rate_error;
+
+		if (pll_rate <= 0)
+			continue;
+		actual_rate = pll_rate / pdiv_now;
+		rate_error = abs((long)actual_rate - (long)rate);
+		if (rate_error < best_rate_error) {
+			pdiv_best = pdiv_now;
+			best_rate_error = rate_error;
+		}
+		/* TODO: Consider PLL frequency based on smaller n/m values
+		 * and pick the better one if the error is equal */
+	}
+
+	return rate * pdiv_best;
+}
+
+static long cdce925_clk_round_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long *parent_rate)
+{
+	unsigned long l_parent_rate = *parent_rate;
+	u16 divider = cdce925_calc_divider(rate, l_parent_rate);
+
+	if (l_parent_rate / divider != rate) {
+		l_parent_rate = cdce925_clk_best_parent_rate(hw, rate);
+		divider = cdce925_calc_divider(rate, l_parent_rate);
+		*parent_rate = l_parent_rate;
+	}
+
+	if (divider)
+		return (long)(l_parent_rate / divider);
+	return 0;
+}
+
+static int cdce925_clk_set_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long parent_rate)
+{
+	struct clk_cdce925_output *data = to_clk_cdce925_output(hw);
+
+	data->pdiv = cdce925_calc_divider(rate, parent_rate);
+
+	return 0;
+}
+
+static const struct clk_ops cdce925_clk_ops = {
+	.prepare = cdce925_clk_prepare,
+	.unprepare = cdce925_clk_unprepare,
+	.recalc_rate = cdce925_clk_recalc_rate,
+	.round_rate = cdce925_clk_round_rate,
+	.set_rate = cdce925_clk_set_rate,
+};
+
+
+static u16 cdce925_y1_calc_divider(unsigned long rate,
+		unsigned long parent_rate)
+{
+	unsigned long divider;
+
+	if (!rate)
+		return 0;
+	if (rate >= parent_rate)
+		return 1;
+
+	divider = DIV_ROUND_CLOSEST(parent_rate, rate);
+	if (divider > 0x3FF) /* Y1 has 10-bit divider */
+		divider = 0x3FF;
+
+	return (u16)divider;
+}
+
+static long cdce925_clk_y1_round_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long *parent_rate)
+{
+	unsigned long l_parent_rate = *parent_rate;
+	u16 divider = cdce925_y1_calc_divider(rate, l_parent_rate);
+
+	if (divider)
+		return (long)(l_parent_rate / divider);
+	return 0;
+}
+
+static int cdce925_clk_y1_set_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long parent_rate)
+{
+	struct clk_cdce925_output *data = to_clk_cdce925_output(hw);
+
+	data->pdiv = cdce925_y1_calc_divider(rate, parent_rate);
+
+	return 0;
+}
+
+static const struct clk_ops cdce925_clk_y1_ops = {
+	.prepare = cdce925_clk_prepare,
+	.unprepare = cdce925_clk_unprepare,
+	.recalc_rate = cdce925_clk_recalc_rate,
+	.round_rate = cdce925_clk_y1_round_rate,
+	.set_rate = cdce925_clk_y1_set_rate,
+};
+
+
+static struct regmap_config cdce925_regmap_config = {
+	.name = "configuration0",
+	.reg_bits = 8,
+	.val_bits = 8,
+	.cache_type = REGCACHE_RBTREE,
+	.max_register = 0x2F,
+};
+
+#define CDCE925_I2C_COMMAND_BLOCK_TRANSFER	0x00
+#define CDCE925_I2C_COMMAND_BYTE_TRANSFER	0x80
+
+static int cdce925_regmap_i2c_write(
+	void *context, const void *data, size_t count)
+{
+	struct device *dev = context;
+	struct i2c_client *i2c = to_i2c_client(dev);
+	int ret;
+	u8 reg_data[2];
+
+	if (count != 2)
+		return -ENOTSUPP;
+
+	/* First byte is command code */
+	reg_data[0] = CDCE925_I2C_COMMAND_BYTE_TRANSFER | ((u8 *)data)[0];
+	reg_data[1] = ((u8 *)data)[1];
+
+	dev_dbg(&i2c->dev, "%s(%zu) %#x %#x\n", __func__, count,
+			reg_data[0], reg_data[1]);
+
+	ret = i2c_master_send(i2c, reg_data, count);
+	if (likely(ret == count))
+		return 0;
+	else if (ret < 0)
+		return ret;
+	else
+		return -EIO;
+}
+
+static int cdce925_regmap_i2c_read(void *context,
+	   const void *reg, size_t reg_size, void *val, size_t val_size)
+{
+	struct device *dev = context;
+	struct i2c_client *i2c = to_i2c_client(dev);
+	struct i2c_msg xfer[2];
+	int ret;
+	u8 reg_data[2];
+
+	if (reg_size != 1)
+		return -ENOTSUPP;
+
+	xfer[0].addr = i2c->addr;
+	xfer[0].flags = 0;
+	xfer[0].buf = reg_data;
+	if (val_size == 1) {
+		reg_data[0] =
+			CDCE925_I2C_COMMAND_BYTE_TRANSFER | ((u8 *)reg)[0];
+		xfer[0].len = 1;
+	} else {
+		reg_data[0] =
+			CDCE925_I2C_COMMAND_BLOCK_TRANSFER | ((u8 *)reg)[0];
+		reg_data[1] = val_size;
+		xfer[0].len = 2;
+	}
+
+	xfer[1].addr = i2c->addr;
+	xfer[1].flags = I2C_M_RD;
+	xfer[1].len = val_size;
+	xfer[1].buf = val;
+
+	ret = i2c_transfer(i2c->adapter, xfer, 2);
+	if (likely(ret == 2)) {
+		dev_dbg(&i2c->dev, "%s(%zu, %zu) %#x %#x\n", __func__,
+				reg_size, val_size, reg_data[0], *((u8 *)val));
+		return 0;
+	} else if (ret < 0)
+		return ret;
+	else
+		return -EIO;
+}
+
+/* The CDCE925 uses a funky way to read/write registers. Bulk mode is
+ * just weird, so just use the single byte mode exclusively. */
+static struct regmap_bus regmap_cdce925_bus = {
+	.write = cdce925_regmap_i2c_write,
+	.read = cdce925_regmap_i2c_read,
+};
+
+static int cdce925_probe(struct i2c_client *client,
+		const struct i2c_device_id *id)
+{
+	struct clk_cdce925_chip *data;
+	struct device_node *node = client->dev.of_node;
+	const char *parent_name;
+	const char *pll_clk_name[NUMBER_OF_PLLS] = {NULL,};
+	struct clk_init_data init;
+	struct clk *clk;
+	u32 value;
+	int i;
+	int err;
+	struct device_node *np_output;
+	char child_name[6];
+
+	dev_dbg(&client->dev, "%s\n", __func__);
+	data = devm_kzalloc(&client->dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->i2c_client = client;
+	data->regmap = devm_regmap_init(&client->dev, &regmap_cdce925_bus,
+			&client->dev, &cdce925_regmap_config);
+	if (IS_ERR(data->regmap)) {
+		dev_err(&client->dev, "failed to allocate register map\n");
+		return PTR_ERR(data->regmap);
+	}
+	i2c_set_clientdata(client, data);
+
+	parent_name = of_clk_get_parent_name(node, 0);
+	if (!parent_name) {
+		dev_err(&client->dev, "missing parent clock\n");
+		return -ENODEV;
+	}
+	dev_dbg(&client->dev, "parent is: %s\n", parent_name);
+
+	if (of_property_read_u32(node, "xtal-load-pf", &value) == 0)
+		regmap_write(data->regmap,
+			CDCE925_REG_XCSEL, (value << 3) & 0xF8);
+	/* PWDN bit */
+	regmap_update_bits(data->regmap, CDCE925_REG_GLOBAL1, BIT(4), 0);
+
+	/* Set input source for Y1 to be the XTAL */
+	regmap_update_bits(data->regmap, 0x02, BIT(7), 0);
+
+	init.ops = &cdce925_pll_ops;
+	init.flags = 0;
+	init.parent_names = &parent_name;
+	init.num_parents = parent_name ? 1 : 0;
+
+	/* Register PLL clocks */
+	for (i = 0; i < NUMBER_OF_PLLS; ++i) {
+		pll_clk_name[i] = kasprintf(GFP_KERNEL, "%s.pll%d",
+			client->dev.of_node->name, i);
+		init.name = pll_clk_name[i];
+		data->pll[i].chip = data;
+		data->pll[i].hw.init = &init;
+		data->pll[i].index = i;
+		clk = devm_clk_register(&client->dev, &data->pll[i].hw);
+		if (IS_ERR(clk)) {
+			dev_err(&client->dev, "Failed register PLL %d\n", i);
+			err = PTR_ERR(clk);
+			goto error;
+		}
+		sprintf(child_name, "PLL%d", i+1);
+		np_output = of_get_child_by_name(node, child_name);
+		if (!np_output)
+			continue;
+		if (!of_property_read_u32(np_output,
+			"clock-frequency", &value)) {
+			err = clk_set_rate(clk, value);
+			if (err)
+				dev_err(&client->dev,
+					"unable to set PLL frequency %ud\n",
+					value);
+		}
+		if (!of_property_read_u32(np_output,
+			"spread-spectrum", &value)) {
+			u8 flag = of_property_read_bool(np_output,
+				"spread-spectrum-center") ? 0x80 : 0x00;
+			regmap_update_bits(data->regmap,
+				0x16 + (i*CDCE925_OFFSET_PLL),
+				0x80, flag);
+			regmap_update_bits(data->regmap,
+				0x12 + (i*CDCE925_OFFSET_PLL),
+				0x07, value & 0x07);
+		}
+	}
+
+	/* Register output clock Y1 */
+	init.ops = &cdce925_clk_y1_ops;
+	init.flags = 0;
+	init.num_parents = 1;
+	init.parent_names = &parent_name; /* Mux Y1 to input */
+	init.name = kasprintf(GFP_KERNEL, "%s.Y1", client->dev.of_node->name);
+	data->clk[0].chip = data;
+	data->clk[0].hw.init = &init;
+	data->clk[0].index = 0;
+	data->clk[0].pdiv = 1;
+	clk = devm_clk_register(&client->dev, &data->clk[0].hw);
+	kfree(init.name); /* clock framework made a copy of the name */
+	if (IS_ERR(clk)) {
+		dev_err(&client->dev, "clock registration Y1 failed\n");
+		err = PTR_ERR(clk);
+		goto error;
+	}
+	data->dt_clk[0] = clk;
+
+	/* Register output clocks Y2 .. Y5*/
+	init.ops = &cdce925_clk_ops;
+	init.flags = CLK_SET_RATE_PARENT;
+	init.num_parents = 1;
+	for (i = 1; i < NUMBER_OF_OUTPUTS; ++i) {
+		init.name = kasprintf(GFP_KERNEL, "%s.Y%d",
+			client->dev.of_node->name, i+1);
+		data->clk[i].chip = data;
+		data->clk[i].hw.init = &init;
+		data->clk[i].index = i;
+		data->clk[i].pdiv = 1;
+		switch (i) {
+		case 1:
+		case 2:
+			/* Mux Y2/3 to PLL1 */
+			init.parent_names = &pll_clk_name[0];
+			break;
+		case 3:
+		case 4:
+			/* Mux Y4/5 to PLL2 */
+			init.parent_names = &pll_clk_name[1];
+			break;
+		}
+		clk = devm_clk_register(&client->dev, &data->clk[i].hw);
+		kfree(init.name); /* clock framework made a copy of the name */
+		if (IS_ERR(clk)) {
+			dev_err(&client->dev, "clock registration failed\n");
+			err = PTR_ERR(clk);
+			goto error;
+		}
+		data->dt_clk[i] = clk;
+	}
+
+	/* Register the output clocks */
+	data->onecell.clk_num = NUMBER_OF_OUTPUTS;
+	data->onecell.clks = data->dt_clk;
+	err = of_clk_add_provider(client->dev.of_node, of_clk_src_onecell_get,
+		&data->onecell);
+	if (err)
+		dev_err(&client->dev, "unable to add OF clock provider\n");
+
+	err = 0;
+
+error:
+	for (i = 0; i < NUMBER_OF_PLLS; ++i)
+		/* clock framework made a copy of the name */
+		kfree(pll_clk_name[i]);
+
+	return err;
+}
+
+static const struct i2c_device_id cdce925_id[] = {
+	{ "cdce925", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, cdce925_id);
+
+static const struct of_device_id clk_cdce925_of_match[] = {
+	{ .compatible = "ti,cdce925" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, clk_cdce925_of_match);
+
+static struct i2c_driver cdce925_driver = {
+	.driver = {
+		.name = "cdce925",
+		.of_match_table = of_match_ptr(clk_cdce925_of_match),
+	},
+	.probe		= cdce925_probe,
+	.id_table	= cdce925_id,
+};
+module_i2c_driver(cdce925_driver);
+
+MODULE_AUTHOR("Mike Looijmans <mike.looijmans@topic.nl>");
+MODULE_DESCRIPTION("cdce925 driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/clk/clk-composite.c b/drivers/clk/clk-composite.c
index 956b7e5..616f5ae 100644
--- a/drivers/clk/clk-composite.c
+++ b/drivers/clk/clk-composite.c
@@ -188,7 +188,7 @@
 }
 
 struct clk *clk_register_composite(struct device *dev, const char *name,
-			const char **parent_names, int num_parents,
+			const char * const *parent_names, int num_parents,
 			struct clk_hw *mux_hw, const struct clk_ops *mux_ops,
 			struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
 			struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
@@ -200,10 +200,8 @@
 	struct clk_ops *clk_composite_ops;
 
 	composite = kzalloc(sizeof(*composite), GFP_KERNEL);
-	if (!composite) {
-		pr_err("%s: could not allocate composite clk\n", __func__);
+	if (!composite)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	init.name = name;
 	init.flags = flags | CLK_IS_BASIC;
diff --git a/drivers/clk/clk-conf.c b/drivers/clk/clk-conf.c
index 48a65b2..43a218f 100644
--- a/drivers/clk/clk-conf.c
+++ b/drivers/clk/clk-conf.c
@@ -106,8 +106,9 @@
 
 			rc = clk_set_rate(clk, rate);
 			if (rc < 0)
-				pr_err("clk: couldn't set %s clock rate: %d\n",
-				       __clk_get_name(clk), rc);
+				pr_err("clk: couldn't set %s clk rate to %d (%d), current rate: %ld\n",
+				       __clk_get_name(clk), rate, rc,
+				       clk_get_rate(clk));
 			clk_put(clk);
 		}
 		index++;
@@ -124,7 +125,7 @@
  * and sets any specified clock parents and rates. The @clk_supplier argument
  * should be set to true if @node may be also a clock supplier of any clock
  * listed in its 'assigned-clocks' or 'assigned-clock-parents' properties.
- * If @clk_supplier is false the function exits returnning 0 as soon as it
+ * If @clk_supplier is false the function exits returning 0 as soon as it
  * determines the @node is also a supplier of any of the clocks.
  */
 int of_clk_set_defaults(struct device_node *node, bool clk_supplier)
diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c
index 25006a8..706b578 100644
--- a/drivers/clk/clk-divider.c
+++ b/drivers/clk/clk-divider.c
@@ -430,11 +430,9 @@
 	}
 
 	/* allocate the divider */
-	div = kzalloc(sizeof(struct clk_divider), GFP_KERNEL);
-	if (!div) {
-		pr_err("%s: could not allocate divider clk\n", __func__);
+	div = kzalloc(sizeof(*div), GFP_KERNEL);
+	if (!div)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	init.name = name;
 	init.ops = &clk_divider_ops;
diff --git a/drivers/clk/clk-fixed-factor.c b/drivers/clk/clk-fixed-factor.c
index d9e3f67..fccabe4 100644
--- a/drivers/clk/clk-fixed-factor.c
+++ b/drivers/clk/clk-fixed-factor.c
@@ -55,10 +55,16 @@
 static int clk_factor_set_rate(struct clk_hw *hw, unsigned long rate,
 				unsigned long parent_rate)
 {
+	/*
+	 * We must report success but we can do so unconditionally because
+	 * clk_factor_round_rate returns values that ensure this call is a
+	 * nop.
+	 */
+
 	return 0;
 }
 
-struct clk_ops clk_fixed_factor_ops = {
+const struct clk_ops clk_fixed_factor_ops = {
 	.round_rate = clk_factor_round_rate,
 	.set_rate = clk_factor_set_rate,
 	.recalc_rate = clk_factor_recalc_rate,
@@ -74,10 +80,8 @@
 	struct clk *clk;
 
 	fix = kmalloc(sizeof(*fix), GFP_KERNEL);
-	if (!fix) {
-		pr_err("%s: could not allocate fixed factor clk\n", __func__);
+	if (!fix)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	/* struct clk_fixed_factor assignments */
 	fix->mult = mult;
diff --git a/drivers/clk/clk-fixed-rate.c b/drivers/clk/clk-fixed-rate.c
index 0fc56ab..f85ec8d 100644
--- a/drivers/clk/clk-fixed-rate.c
+++ b/drivers/clk/clk-fixed-rate.c
@@ -65,11 +65,9 @@
 	struct clk_init_data init;
 
 	/* allocate fixed-rate clock */
-	fixed = kzalloc(sizeof(struct clk_fixed_rate), GFP_KERNEL);
-	if (!fixed) {
-		pr_err("%s: could not allocate fixed clk\n", __func__);
+	fixed = kzalloc(sizeof(*fixed), GFP_KERNEL);
+	if (!fixed)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	init.name = name;
 	init.ops = &clk_fixed_rate_ops;
diff --git a/drivers/clk/clk-fractional-divider.c b/drivers/clk/clk-fractional-divider.c
index 6aa72d9..140eb58 100644
--- a/drivers/clk/clk-fractional-divider.c
+++ b/drivers/clk/clk-fractional-divider.c
@@ -109,10 +109,8 @@
 	struct clk *clk;
 
 	fd = kzalloc(sizeof(*fd), GFP_KERNEL);
-	if (!fd) {
-		dev_err(dev, "could not allocate fractional divider clk\n");
+	if (!fd)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	init.name = name;
 	init.ops = &clk_fractional_divider_ops;
diff --git a/drivers/clk/clk-gate.c b/drivers/clk/clk-gate.c
index 3f0e420..551dd06 100644
--- a/drivers/clk/clk-gate.c
+++ b/drivers/clk/clk-gate.c
@@ -135,11 +135,9 @@
 	}
 
 	/* allocate the gate */
-	gate = kzalloc(sizeof(struct clk_gate), GFP_KERNEL);
-	if (!gate) {
-		pr_err("%s: could not allocate gated clk\n", __func__);
+	gate = kzalloc(sizeof(*gate), GFP_KERNEL);
+	if (!gate)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	init.name = name;
 	init.ops = &clk_gate_ops;
diff --git a/drivers/clk/clk-gpio-gate.c b/drivers/clk/clk-gpio-gate.c
index a71cabe..f564e62 100644
--- a/drivers/clk/clk-gpio-gate.c
+++ b/drivers/clk/clk-gpio-gate.c
@@ -189,7 +189,7 @@
 /**
  * of_gpio_gate_clk_setup() - Setup function for gpio controlled clock
  */
-void __init of_gpio_gate_clk_setup(struct device_node *node)
+static void __init of_gpio_gate_clk_setup(struct device_node *node)
 {
 	struct clk_gpio_gate_delayed_register_data *data;
 
@@ -203,6 +203,5 @@
 
 	of_clk_add_provider(node, of_clk_gpio_gate_delayed_register_get, data);
 }
-EXPORT_SYMBOL_GPL(of_gpio_gate_clk_setup);
 CLK_OF_DECLARE(gpio_gate_clk, "gpio-gate-clock", of_gpio_gate_clk_setup);
 #endif
diff --git a/drivers/clk/clk-ls1x.c b/drivers/clk/clk-ls1x.c
index ca80103..d4c6198 100644
--- a/drivers/clk/clk-ls1x.c
+++ b/drivers/clk/clk-ls1x.c
@@ -80,9 +80,9 @@
 	return clk;
 }
 
-static const char const *cpu_parents[] = { "cpu_clk_div", "osc_33m_clk", };
-static const char const *ahb_parents[] = { "ahb_clk_div", "osc_33m_clk", };
-static const char const *dc_parents[] = { "dc_clk_div", "osc_33m_clk", };
+static const char * const cpu_parents[] = { "cpu_clk_div", "osc_33m_clk", };
+static const char * const ahb_parents[] = { "ahb_clk_div", "osc_33m_clk", };
+static const char * const dc_parents[] = { "dc_clk_div", "osc_33m_clk", };
 
 void __init ls1x_clk_init(void)
 {
diff --git a/drivers/clk/clk-max-gen.c b/drivers/clk/clk-max-gen.c
index 6505049..35af9cb 100644
--- a/drivers/clk/clk-max-gen.c
+++ b/drivers/clk/clk-max-gen.c
@@ -31,6 +31,8 @@
 #include <linux/of.h>
 #include <linux/export.h>
 
+#include "clk-max-gen.h"
+
 struct max_gen_clk {
 	struct regmap *regmap;
 	u32 mask;
diff --git a/drivers/clk/clk-max77686.c b/drivers/clk/clk-max77686.c
index 86cdb3a..446c2fe 100644
--- a/drivers/clk/clk-max77686.c
+++ b/drivers/clk/clk-max77686.c
@@ -23,6 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/err.h>
+#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/mfd/max77686.h>
 #include <linux/mfd/max77686-private.h>
diff --git a/drivers/clk/clk-max77802.c b/drivers/clk/clk-max77802.c
index 0729dc7..74c49b9 100644
--- a/drivers/clk/clk-max77802.c
+++ b/drivers/clk/clk-max77802.c
@@ -22,6 +22,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/err.h>
+#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/mfd/max77686-private.h>
 #include <linux/clk-provider.h>
diff --git a/drivers/clk/clk-moxart.c b/drivers/clk/clk-moxart.c
index 30a3b69..5181b89 100644
--- a/drivers/clk/clk-moxart.c
+++ b/drivers/clk/clk-moxart.c
@@ -15,7 +15,7 @@
 #include <linux/of_address.h>
 #include <linux/clkdev.h>
 
-void __init moxart_of_pll_clk_init(struct device_node *node)
+static void __init moxart_of_pll_clk_init(struct device_node *node)
 {
 	static void __iomem *base;
 	struct clk *clk, *ref_clk;
@@ -53,7 +53,7 @@
 CLK_OF_DECLARE(moxart_pll_clock, "moxa,moxart-pll-clock",
 	       moxart_of_pll_clk_init);
 
-void __init moxart_of_apb_clk_init(struct device_node *node)
+static void __init moxart_of_apb_clk_init(struct device_node *node)
 {
 	static void __iomem *base;
 	struct clk *clk, *pll_clk;
diff --git a/drivers/clk/clk-mux.c b/drivers/clk/clk-mux.c
index 69a094c..6066a01 100644
--- a/drivers/clk/clk-mux.c
+++ b/drivers/clk/clk-mux.c
@@ -114,7 +114,8 @@
 EXPORT_SYMBOL_GPL(clk_mux_ro_ops);
 
 struct clk *clk_register_mux_table(struct device *dev, const char *name,
-		const char **parent_names, u8 num_parents, unsigned long flags,
+		const char * const *parent_names, u8 num_parents,
+		unsigned long flags,
 		void __iomem *reg, u8 shift, u32 mask,
 		u8 clk_mux_flags, u32 *table, spinlock_t *lock)
 {
@@ -166,7 +167,8 @@
 EXPORT_SYMBOL_GPL(clk_register_mux_table);
 
 struct clk *clk_register_mux(struct device *dev, const char *name,
-		const char **parent_names, u8 num_parents, unsigned long flags,
+		const char * const *parent_names, u8 num_parents,
+		unsigned long flags,
 		void __iomem *reg, u8 shift, u8 width,
 		u8 clk_mux_flags, spinlock_t *lock)
 {
diff --git a/drivers/clk/clk-nomadik.c b/drivers/clk/clk-nomadik.c
index 05e04ce..c948717 100644
--- a/drivers/clk/clk-nomadik.c
+++ b/drivers/clk/clk-nomadik.c
@@ -503,8 +503,7 @@
 			    NULL, NULL, &nomadik_src_clk_debugfs_ops);
 	return 0;
 }
-
-module_init(nomadik_src_clk_init_debugfs);
+device_initcall(nomadik_src_clk_init_debugfs);
 
 #endif
 
diff --git a/drivers/clk/clk-si5351.c b/drivers/clk/clk-si5351.c
index 30335d3b..e39e1e6 100644
--- a/drivers/clk/clk-si5351.c
+++ b/drivers/clk/clk-si5351.c
@@ -552,7 +552,8 @@
  * MSx_P2[19:0] = 128 * b - c * floor(128 * b/c) = (128*b) mod c
  * MSx_P3[19:0] = c
  *
- * MS[6,7] are integer (P1) divide only, P2 = 0, P3 = 0
+ * MS[6,7] are integer (P1) divide only, P1 = divide value,
+ * P2 and P3 are not applicable
  *
  * for 150MHz < fOUT <= 160MHz:
  *
@@ -606,9 +607,6 @@
 	if (!hwdata->params.valid)
 		si5351_read_parameters(hwdata->drvdata, reg, &hwdata->params);
 
-	if (hwdata->params.p3 == 0)
-		return parent_rate;
-
 	/*
 	 * multisync0-5: fOUT = (128 * P3 * fIN) / (P1*P3 + P2 + 512*P3)
 	 * multisync6-7: fOUT = fIN / P1
@@ -616,6 +614,8 @@
 	rate = parent_rate;
 	if (hwdata->num > 5) {
 		m = hwdata->params.p1;
+	} else if (hwdata->params.p3 == 0) {
+		return parent_rate;
 	} else if ((si5351_reg_read(hwdata->drvdata, reg + 2) &
 		    SI5351_OUTPUT_CLK_DIVBY4) == SI5351_OUTPUT_CLK_DIVBY4) {
 		m = 4;
@@ -679,6 +679,16 @@
 		c = 1;
 
 		*parent_rate = a * rate;
+	} else if (hwdata->num >= 6) {
+		/* determine the closest integer divider */
+		a = DIV_ROUND_CLOSEST(*parent_rate, rate);
+		if (a < SI5351_MULTISYNTH_A_MIN)
+			a = SI5351_MULTISYNTH_A_MIN;
+		if (a > SI5351_MULTISYNTH67_A_MAX)
+			a = SI5351_MULTISYNTH67_A_MAX;
+
+		b = 0;
+		c = 1;
 	} else {
 		unsigned long rfrac, denom;
 
@@ -692,9 +702,7 @@
 		a = *parent_rate / rate;
 		if (a < SI5351_MULTISYNTH_A_MIN)
 			a = SI5351_MULTISYNTH_A_MIN;
-		if (hwdata->num >= 6 && a > SI5351_MULTISYNTH67_A_MAX)
-			a = SI5351_MULTISYNTH67_A_MAX;
-		else if (a > SI5351_MULTISYNTH_A_MAX)
+		if (a > SI5351_MULTISYNTH_A_MAX)
 			a = SI5351_MULTISYNTH_A_MAX;
 
 		/* find best approximation for b/c = fVCO mod fOUT */
@@ -723,6 +731,10 @@
 		hwdata->params.p3 = 1;
 		hwdata->params.p2 = 0;
 		hwdata->params.p1 = 0;
+	} else if (hwdata->num >= 6) {
+		hwdata->params.p3 = 0;
+		hwdata->params.p2 = 0;
+		hwdata->params.p1 = a;
 	} else {
 		hwdata->params.p3  = c;
 		hwdata->params.p2  = (128 * b) % c;
diff --git a/drivers/clk/clk-stm32f4.c b/drivers/clk/clk-stm32f4.c
new file mode 100644
index 0000000..b9b12a7
--- /dev/null
+++ b/drivers/clk/clk-stm32f4.c
@@ -0,0 +1,380 @@
+/*
+ * Author: Daniel Thompson <daniel.thompson@linaro.org>
+ *
+ * Inspired by clk-asm9260.c .
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+
+#define STM32F4_RCC_PLLCFGR		0x04
+#define STM32F4_RCC_CFGR		0x08
+#define STM32F4_RCC_AHB1ENR		0x30
+#define STM32F4_RCC_AHB2ENR		0x34
+#define STM32F4_RCC_AHB3ENR		0x38
+#define STM32F4_RCC_APB1ENR		0x40
+#define STM32F4_RCC_APB2ENR		0x44
+
+struct stm32f4_gate_data {
+	u8	offset;
+	u8	bit_idx;
+	const char *name;
+	const char *parent_name;
+	unsigned long flags;
+};
+
+static const struct stm32f4_gate_data stm32f4_gates[] __initconst = {
+	{ STM32F4_RCC_AHB1ENR,  0,	"gpioa",	"ahb_div" },
+	{ STM32F4_RCC_AHB1ENR,  1,	"gpiob",	"ahb_div" },
+	{ STM32F4_RCC_AHB1ENR,  2,	"gpioc",	"ahb_div" },
+	{ STM32F4_RCC_AHB1ENR,  3,	"gpiod",	"ahb_div" },
+	{ STM32F4_RCC_AHB1ENR,  4,	"gpioe",	"ahb_div" },
+	{ STM32F4_RCC_AHB1ENR,  5,	"gpiof",	"ahb_div" },
+	{ STM32F4_RCC_AHB1ENR,  6,	"gpiog",	"ahb_div" },
+	{ STM32F4_RCC_AHB1ENR,  7,	"gpioh",	"ahb_div" },
+	{ STM32F4_RCC_AHB1ENR,  8,	"gpioi",	"ahb_div" },
+	{ STM32F4_RCC_AHB1ENR,  9,	"gpioj",	"ahb_div" },
+	{ STM32F4_RCC_AHB1ENR, 10,	"gpiok",	"ahb_div" },
+	{ STM32F4_RCC_AHB1ENR, 12,	"crc",		"ahb_div" },
+	{ STM32F4_RCC_AHB1ENR, 18,	"bkpsra",	"ahb_div" },
+	{ STM32F4_RCC_AHB1ENR, 20,	"ccmdatam",	"ahb_div" },
+	{ STM32F4_RCC_AHB1ENR, 21,	"dma1",		"ahb_div" },
+	{ STM32F4_RCC_AHB1ENR, 22,	"dma2",		"ahb_div" },
+	{ STM32F4_RCC_AHB1ENR, 23,	"dma2d",	"ahb_div" },
+	{ STM32F4_RCC_AHB1ENR, 25,	"ethmac",	"ahb_div" },
+	{ STM32F4_RCC_AHB1ENR, 26,	"ethmactx",	"ahb_div" },
+	{ STM32F4_RCC_AHB1ENR, 27,	"ethmacrx",	"ahb_div" },
+	{ STM32F4_RCC_AHB1ENR, 28,	"ethmacptp",	"ahb_div" },
+	{ STM32F4_RCC_AHB1ENR, 29,	"otghs",	"ahb_div" },
+	{ STM32F4_RCC_AHB1ENR, 30,	"otghsulpi",	"ahb_div" },
+
+	{ STM32F4_RCC_AHB2ENR,  0,	"dcmi",		"ahb_div" },
+	{ STM32F4_RCC_AHB2ENR,  4,	"cryp",		"ahb_div" },
+	{ STM32F4_RCC_AHB2ENR,  5,	"hash",		"ahb_div" },
+	{ STM32F4_RCC_AHB2ENR,  6,	"rng",		"pll48" },
+	{ STM32F4_RCC_AHB2ENR,  7,	"otgfs",	"pll48" },
+
+	{ STM32F4_RCC_AHB3ENR,  0,	"fmc",		"ahb_div",
+		CLK_IGNORE_UNUSED },
+
+	{ STM32F4_RCC_APB1ENR,  0,	"tim2",		"apb1_mul" },
+	{ STM32F4_RCC_APB1ENR,  1,	"tim3",		"apb1_mul" },
+	{ STM32F4_RCC_APB1ENR,  2,	"tim4",		"apb1_mul" },
+	{ STM32F4_RCC_APB1ENR,  3,	"tim5",		"apb1_mul" },
+	{ STM32F4_RCC_APB1ENR,  4,	"tim6",		"apb1_mul" },
+	{ STM32F4_RCC_APB1ENR,  5,	"tim7",		"apb1_mul" },
+	{ STM32F4_RCC_APB1ENR,  6,	"tim12",	"apb1_mul" },
+	{ STM32F4_RCC_APB1ENR,  7,	"tim13",	"apb1_mul" },
+	{ STM32F4_RCC_APB1ENR,  8,	"tim14",	"apb1_mul" },
+	{ STM32F4_RCC_APB1ENR, 11,	"wwdg",		"apb1_div" },
+	{ STM32F4_RCC_APB1ENR, 14,	"spi2",		"apb1_div" },
+	{ STM32F4_RCC_APB1ENR, 15,	"spi3",		"apb1_div" },
+	{ STM32F4_RCC_APB1ENR, 17,	"uart2",	"apb1_div" },
+	{ STM32F4_RCC_APB1ENR, 18,	"uart3",	"apb1_div" },
+	{ STM32F4_RCC_APB1ENR, 19,	"uart4",	"apb1_div" },
+	{ STM32F4_RCC_APB1ENR, 20,	"uart5",	"apb1_div" },
+	{ STM32F4_RCC_APB1ENR, 21,	"i2c1",		"apb1_div" },
+	{ STM32F4_RCC_APB1ENR, 22,	"i2c2",		"apb1_div" },
+	{ STM32F4_RCC_APB1ENR, 23,	"i2c3",		"apb1_div" },
+	{ STM32F4_RCC_APB1ENR, 25,	"can1",		"apb1_div" },
+	{ STM32F4_RCC_APB1ENR, 26,	"can2",		"apb1_div" },
+	{ STM32F4_RCC_APB1ENR, 28,	"pwr",		"apb1_div" },
+	{ STM32F4_RCC_APB1ENR, 29,	"dac",		"apb1_div" },
+	{ STM32F4_RCC_APB1ENR, 30,	"uart7",	"apb1_div" },
+	{ STM32F4_RCC_APB1ENR, 31,	"uart8",	"apb1_div" },
+
+	{ STM32F4_RCC_APB2ENR,  0,	"tim1",		"apb2_mul" },
+	{ STM32F4_RCC_APB2ENR,  1,	"tim8",		"apb2_mul" },
+	{ STM32F4_RCC_APB2ENR,  4,	"usart1",	"apb2_div" },
+	{ STM32F4_RCC_APB2ENR,  5,	"usart6",	"apb2_div" },
+	{ STM32F4_RCC_APB2ENR,  8,	"adc1",		"apb2_div" },
+	{ STM32F4_RCC_APB2ENR,  9,	"adc2",		"apb2_div" },
+	{ STM32F4_RCC_APB2ENR, 10,	"adc3",		"apb2_div" },
+	{ STM32F4_RCC_APB2ENR, 11,	"sdio",		"pll48" },
+	{ STM32F4_RCC_APB2ENR, 12,	"spi1",		"apb2_div" },
+	{ STM32F4_RCC_APB2ENR, 13,	"spi4",		"apb2_div" },
+	{ STM32F4_RCC_APB2ENR, 14,	"syscfg",	"apb2_div" },
+	{ STM32F4_RCC_APB2ENR, 16,	"tim9",		"apb2_mul" },
+	{ STM32F4_RCC_APB2ENR, 17,	"tim10",	"apb2_mul" },
+	{ STM32F4_RCC_APB2ENR, 18,	"tim11",	"apb2_mul" },
+	{ STM32F4_RCC_APB2ENR, 20,	"spi5",		"apb2_div" },
+	{ STM32F4_RCC_APB2ENR, 21,	"spi6",		"apb2_div" },
+	{ STM32F4_RCC_APB2ENR, 22,	"sai1",		"apb2_div" },
+	{ STM32F4_RCC_APB2ENR, 26,	"ltdc",		"apb2_div" },
+};
+
+/*
+ * MAX_CLKS is the maximum value in the enumeration below plus the combined
+ * hweight of stm32f42xx_gate_map (plus one).
+ */
+#define MAX_CLKS 74
+
+enum { SYSTICK, FCLK };
+
+/*
+ * This bitmask tells us which bit offsets (0..192) on STM32F4[23]xxx
+ * have gate bits associated with them. Its combined hweight is 71.
+ */
+static const u64 stm32f42xx_gate_map[] = { 0x000000f17ef417ffull,
+					   0x0000000000000001ull,
+					   0x04777f33f6fec9ffull };
+
+static struct clk *clks[MAX_CLKS];
+static DEFINE_SPINLOCK(stm32f4_clk_lock);
+static void __iomem *base;
+
+/*
+ * "Multiplier" device for APBx clocks.
+ *
+ * The APBx dividers are power-of-two dividers and, if *not* running in 1:1
+ * mode, they also tap out the one of the low order state bits to run the
+ * timers. ST datasheets represent this feature as a (conditional) clock
+ * multiplier.
+ */
+struct clk_apb_mul {
+	struct clk_hw hw;
+	u8 bit_idx;
+};
+
+#define to_clk_apb_mul(_hw) container_of(_hw, struct clk_apb_mul, hw)
+
+static unsigned long clk_apb_mul_recalc_rate(struct clk_hw *hw,
+					     unsigned long parent_rate)
+{
+	struct clk_apb_mul *am = to_clk_apb_mul(hw);
+
+	if (readl(base + STM32F4_RCC_CFGR) & BIT(am->bit_idx))
+		return parent_rate * 2;
+
+	return parent_rate;
+}
+
+static long clk_apb_mul_round_rate(struct clk_hw *hw, unsigned long rate,
+				   unsigned long *prate)
+{
+	struct clk_apb_mul *am = to_clk_apb_mul(hw);
+	unsigned long mult = 1;
+
+	if (readl(base + STM32F4_RCC_CFGR) & BIT(am->bit_idx))
+		mult = 2;
+
+	if (__clk_get_flags(hw->clk) & CLK_SET_RATE_PARENT) {
+		unsigned long best_parent = rate / mult;
+
+		*prate =
+		    __clk_round_rate(__clk_get_parent(hw->clk), best_parent);
+	}
+
+	return *prate * mult;
+}
+
+static int clk_apb_mul_set_rate(struct clk_hw *hw, unsigned long rate,
+				unsigned long parent_rate)
+{
+	/*
+	 * We must report success but we can do so unconditionally because
+	 * clk_apb_mul_round_rate returns values that ensure this call is a
+	 * nop.
+	 */
+
+	return 0;
+}
+
+static const struct clk_ops clk_apb_mul_factor_ops = {
+	.round_rate = clk_apb_mul_round_rate,
+	.set_rate = clk_apb_mul_set_rate,
+	.recalc_rate = clk_apb_mul_recalc_rate,
+};
+
+static struct clk *clk_register_apb_mul(struct device *dev, const char *name,
+					const char *parent_name,
+					unsigned long flags, u8 bit_idx)
+{
+	struct clk_apb_mul *am;
+	struct clk_init_data init;
+	struct clk *clk;
+
+	am = kzalloc(sizeof(*am), GFP_KERNEL);
+	if (!am)
+		return ERR_PTR(-ENOMEM);
+
+	am->bit_idx = bit_idx;
+	am->hw.init = &init;
+
+	init.name = name;
+	init.ops = &clk_apb_mul_factor_ops;
+	init.flags = flags;
+	init.parent_names = &parent_name;
+	init.num_parents = 1;
+
+	clk = clk_register(dev, &am->hw);
+
+	if (IS_ERR(clk))
+		kfree(am);
+
+	return clk;
+}
+
+/*
+ * Decode current PLL state and (statically) model the state we inherit from
+ * the bootloader.
+ */
+static void stm32f4_rcc_register_pll(const char *hse_clk, const char *hsi_clk)
+{
+	unsigned long pllcfgr = readl(base + STM32F4_RCC_PLLCFGR);
+
+	unsigned long pllm   = pllcfgr & 0x3f;
+	unsigned long plln   = (pllcfgr >> 6) & 0x1ff;
+	unsigned long pllp   = BIT(((pllcfgr >> 16) & 3) + 1);
+	const char   *pllsrc = pllcfgr & BIT(22) ? hse_clk : hsi_clk;
+	unsigned long pllq   = (pllcfgr >> 24) & 0xf;
+
+	clk_register_fixed_factor(NULL, "vco", pllsrc, 0, plln, pllm);
+	clk_register_fixed_factor(NULL, "pll", "vco", 0, 1, pllp);
+	clk_register_fixed_factor(NULL, "pll48", "vco", 0, 1, pllq);
+}
+
+/*
+ * Converts the primary and secondary indices (as they appear in DT) to an
+ * offset into our struct clock array.
+ */
+static int stm32f4_rcc_lookup_clk_idx(u8 primary, u8 secondary)
+{
+	u64 table[ARRAY_SIZE(stm32f42xx_gate_map)];
+
+	if (primary == 1) {
+		if (WARN_ON(secondary > FCLK))
+			return -EINVAL;
+		return secondary;
+	}
+
+	memcpy(table, stm32f42xx_gate_map, sizeof(table));
+
+	/* only bits set in table can be used as indices */
+	if (WARN_ON(secondary > 8 * sizeof(table) ||
+		    0 == (table[BIT_ULL_WORD(secondary)] &
+			  BIT_ULL_MASK(secondary))))
+		return -EINVAL;
+
+	/* mask out bits above our current index */
+	table[BIT_ULL_WORD(secondary)] &=
+	    GENMASK_ULL(secondary % BITS_PER_LONG_LONG, 0);
+
+	return FCLK + hweight64(table[0]) +
+	       (BIT_ULL_WORD(secondary) >= 1 ? hweight64(table[1]) : 0) +
+	       (BIT_ULL_WORD(secondary) >= 2 ? hweight64(table[2]) : 0);
+}
+
+static struct clk *
+stm32f4_rcc_lookup_clk(struct of_phandle_args *clkspec, void *data)
+{
+	int i = stm32f4_rcc_lookup_clk_idx(clkspec->args[0], clkspec->args[1]);
+
+	if (i < 0)
+		return ERR_PTR(-EINVAL);
+
+	return clks[i];
+}
+
+static const char *sys_parents[] __initdata =   { "hsi", NULL, "pll" };
+
+static const struct clk_div_table ahb_div_table[] = {
+	{ 0x0,   1 }, { 0x1,   1 }, { 0x2,   1 }, { 0x3,   1 },
+	{ 0x4,   1 }, { 0x5,   1 }, { 0x6,   1 }, { 0x7,   1 },
+	{ 0x8,   2 }, { 0x9,   4 }, { 0xa,   8 }, { 0xb,  16 },
+	{ 0xc,  64 }, { 0xd, 128 }, { 0xe, 256 }, { 0xf, 512 },
+	{ 0 },
+};
+
+static const struct clk_div_table apb_div_table[] = {
+	{ 0,  1 }, { 0,  1 }, { 0,  1 }, { 0,  1 },
+	{ 4,  2 }, { 5,  4 }, { 6,  8 }, { 7, 16 },
+	{ 0 },
+};
+
+static void __init stm32f4_rcc_init(struct device_node *np)
+{
+	const char *hse_clk;
+	int n;
+
+	base = of_iomap(np, 0);
+	if (!base) {
+		pr_err("%s: unable to map resource", np->name);
+		return;
+	}
+
+	hse_clk = of_clk_get_parent_name(np, 0);
+
+	clk_register_fixed_rate_with_accuracy(NULL, "hsi", NULL, 0,
+			16000000, 160000);
+	stm32f4_rcc_register_pll(hse_clk, "hsi");
+
+	sys_parents[1] = hse_clk;
+	clk_register_mux_table(
+	    NULL, "sys", sys_parents, ARRAY_SIZE(sys_parents), 0,
+	    base + STM32F4_RCC_CFGR, 0, 3, 0, NULL, &stm32f4_clk_lock);
+
+	clk_register_divider_table(NULL, "ahb_div", "sys",
+				   CLK_SET_RATE_PARENT, base + STM32F4_RCC_CFGR,
+				   4, 4, 0, ahb_div_table, &stm32f4_clk_lock);
+
+	clk_register_divider_table(NULL, "apb1_div", "ahb_div",
+				   CLK_SET_RATE_PARENT, base + STM32F4_RCC_CFGR,
+				   10, 3, 0, apb_div_table, &stm32f4_clk_lock);
+	clk_register_apb_mul(NULL, "apb1_mul", "apb1_div",
+			     CLK_SET_RATE_PARENT, 12);
+
+	clk_register_divider_table(NULL, "apb2_div", "ahb_div",
+				   CLK_SET_RATE_PARENT, base + STM32F4_RCC_CFGR,
+				   13, 3, 0, apb_div_table, &stm32f4_clk_lock);
+	clk_register_apb_mul(NULL, "apb2_mul", "apb2_div",
+			     CLK_SET_RATE_PARENT, 15);
+
+	clks[SYSTICK] = clk_register_fixed_factor(NULL, "systick", "ahb_div",
+						  0, 1, 8);
+	clks[FCLK] = clk_register_fixed_factor(NULL, "fclk", "ahb_div",
+					       0, 1, 1);
+
+	for (n = 0; n < ARRAY_SIZE(stm32f4_gates); n++) {
+		const struct stm32f4_gate_data *gd = &stm32f4_gates[n];
+		unsigned int secondary =
+		    8 * (gd->offset - STM32F4_RCC_AHB1ENR) + gd->bit_idx;
+		int idx = stm32f4_rcc_lookup_clk_idx(0, secondary);
+
+		if (idx < 0)
+			goto fail;
+
+		clks[idx] = clk_register_gate(
+		    NULL, gd->name, gd->parent_name, gd->flags,
+		    base + gd->offset, gd->bit_idx, 0, &stm32f4_clk_lock);
+
+		if (IS_ERR(clks[n])) {
+			pr_err("%s: Unable to register leaf clock %s\n",
+			       np->full_name, gd->name);
+			goto fail;
+		}
+	}
+
+	of_clk_add_provider(np, stm32f4_rcc_lookup_clk, NULL);
+	return;
+fail:
+	iounmap(base);
+}
+CLK_OF_DECLARE(stm32f4_rcc, "st,stm32f42xx-rcc", stm32f4_rcc_init);
diff --git a/drivers/clk/clk-u300.c b/drivers/clk/clk-u300.c
index 406bfc1..18bf5e5 100644
--- a/drivers/clk/clk-u300.c
+++ b/drivers/clk/clk-u300.c
@@ -12,6 +12,7 @@
 #include <linux/clk-provider.h>
 #include <linux/spinlock.h>
 #include <linux/of.h>
+#include <linux/platform_data/clk-u300.h>
 
 /* APP side SYSCON registers */
 /* CLK Control Register 16bit (R/W) */
diff --git a/drivers/clk/clk-xgene.c b/drivers/clk/clk-xgene.c
index dd8a62d..f26b3ac 100644
--- a/drivers/clk/clk-xgene.c
+++ b/drivers/clk/clk-xgene.c
@@ -42,12 +42,12 @@
 
 static DEFINE_SPINLOCK(clk_lock);
 
-static inline u32 xgene_clk_read(void *csr)
+static inline u32 xgene_clk_read(void __iomem *csr)
 {
 	return readl_relaxed(csr);
 }
 
-static inline void xgene_clk_write(u32 data, void *csr)
+static inline void xgene_clk_write(u32 data, void __iomem *csr)
 {
 	return writel_relaxed(data, csr);
 }
@@ -119,7 +119,7 @@
 	return fvco / nout;
 }
 
-const struct clk_ops xgene_clk_pll_ops = {
+static const struct clk_ops xgene_clk_pll_ops = {
 	.is_enabled = xgene_clk_pll_is_enabled,
 	.recalc_rate = xgene_clk_pll_recalc_rate,
 };
@@ -167,7 +167,7 @@
 {
         const char *clk_name = np->full_name;
         struct clk *clk;
-        void *reg;
+        void __iomem *reg;
 
         reg = of_iomap(np, 0);
         if (reg == NULL) {
@@ -222,20 +222,22 @@
 	struct xgene_clk *pclk = to_xgene_clk(hw);
 	unsigned long flags = 0;
 	u32 data;
+	phys_addr_t reg;
 
 	if (pclk->lock)
 		spin_lock_irqsave(pclk->lock, flags);
 
 	if (pclk->param.csr_reg != NULL) {
 		pr_debug("%s clock enabled\n", pclk->name);
+		reg = __pa(pclk->param.csr_reg);
 		/* First enable the clock */
 		data = xgene_clk_read(pclk->param.csr_reg +
 					pclk->param.reg_clk_offset);
 		data |= pclk->param.reg_clk_mask;
 		xgene_clk_write(data, pclk->param.csr_reg +
 					pclk->param.reg_clk_offset);
-		pr_debug("%s clock PADDR base 0x%016LX clk offset 0x%08X mask 0x%08X value 0x%08X\n",
-			pclk->name, __pa(pclk->param.csr_reg),
+		pr_debug("%s clock PADDR base %pa clk offset 0x%08X mask 0x%08X value 0x%08X\n",
+			pclk->name, &reg,
 			pclk->param.reg_clk_offset, pclk->param.reg_clk_mask,
 			data);
 
@@ -245,8 +247,8 @@
 		data &= ~pclk->param.reg_csr_mask;
 		xgene_clk_write(data, pclk->param.csr_reg +
 					pclk->param.reg_csr_offset);
-		pr_debug("%s CSR RESET PADDR base 0x%016LX csr offset 0x%08X mask 0x%08X value 0x%08X\n",
-			pclk->name, __pa(pclk->param.csr_reg),
+		pr_debug("%s CSR RESET PADDR base %pa csr offset 0x%08X mask 0x%08X value 0x%08X\n",
+			pclk->name, &reg,
 			pclk->param.reg_csr_offset, pclk->param.reg_csr_mask,
 			data);
 	}
@@ -386,7 +388,7 @@
 	return parent_rate / divider;
 }
 
-const struct clk_ops xgene_clk_ops = {
+static const struct clk_ops xgene_clk_ops = {
 	.enable = xgene_clk_enable,
 	.disable = xgene_clk_disable,
 	.is_enabled = xgene_clk_is_enabled,
@@ -456,7 +458,7 @@
 	parameters.csr_reg = NULL;
 	parameters.divider_reg = NULL;
 	for (i = 0; i < 2; i++) {
-		void *map_res;
+		void __iomem *map_res;
 		rc = of_address_to_resource(np, i, &res);
 		if (rc != 0) {
 			if (i == 0) {
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 5b0f418..ddb4b54 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -21,6 +21,7 @@
 #include <linux/device.h>
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/clkdev.h>
 
 #include "clk.h"
 
@@ -37,13 +38,6 @@
 static HLIST_HEAD(clk_orphan_list);
 static LIST_HEAD(clk_notifier_list);
 
-static long clk_core_get_accuracy(struct clk_core *clk);
-static unsigned long clk_core_get_rate(struct clk_core *clk);
-static int clk_core_get_phase(struct clk_core *clk);
-static bool clk_core_is_prepared(struct clk_core *clk);
-static bool clk_core_is_enabled(struct clk_core *clk);
-static struct clk_core *clk_core_lookup(const char *name);
-
 /***    private data structures    ***/
 
 struct clk_core {
@@ -68,11 +62,11 @@
 	int			phase;
 	struct hlist_head	children;
 	struct hlist_node	child_node;
-	struct hlist_node	debug_node;
 	struct hlist_head	clks;
 	unsigned int		notifier_count;
 #ifdef CONFIG_DEBUG_FS
 	struct dentry		*dentry;
+	struct hlist_node	debug_node;
 #endif
 	struct kref		ref;
 };
@@ -145,382 +139,71 @@
 	spin_unlock_irqrestore(&enable_lock, flags);
 }
 
-/***        debugfs support        ***/
-
-#ifdef CONFIG_DEBUG_FS
-#include <linux/debugfs.h>
-
-static struct dentry *rootdir;
-static int inited = 0;
-static DEFINE_MUTEX(clk_debug_lock);
-static HLIST_HEAD(clk_debug_list);
-
-static struct hlist_head *all_lists[] = {
-	&clk_root_list,
-	&clk_orphan_list,
-	NULL,
-};
-
-static struct hlist_head *orphan_list[] = {
-	&clk_orphan_list,
-	NULL,
-};
-
-static void clk_summary_show_one(struct seq_file *s, struct clk_core *c,
-				 int level)
+static bool clk_core_is_prepared(struct clk_core *core)
 {
-	if (!c)
-		return;
+	/*
+	 * .is_prepared is optional for clocks that can prepare
+	 * fall back to software usage counter if it is missing
+	 */
+	if (!core->ops->is_prepared)
+		return core->prepare_count;
 
-	seq_printf(s, "%*s%-*s %11d %12d %11lu %10lu %-3d\n",
-		   level * 3 + 1, "",
-		   30 - level * 3, c->name,
-		   c->enable_count, c->prepare_count, clk_core_get_rate(c),
-		   clk_core_get_accuracy(c), clk_core_get_phase(c));
+	return core->ops->is_prepared(core->hw);
 }
 
-static void clk_summary_show_subtree(struct seq_file *s, struct clk_core *c,
-				     int level)
+static bool clk_core_is_enabled(struct clk_core *core)
 {
-	struct clk_core *child;
+	/*
+	 * .is_enabled is only mandatory for clocks that gate
+	 * fall back to software usage counter if .is_enabled is missing
+	 */
+	if (!core->ops->is_enabled)
+		return core->enable_count;
 
-	if (!c)
-		return;
-
-	clk_summary_show_one(s, c, level);
-
-	hlist_for_each_entry(child, &c->children, child_node)
-		clk_summary_show_subtree(s, child, level + 1);
+	return core->ops->is_enabled(core->hw);
 }
 
-static int clk_summary_show(struct seq_file *s, void *data)
-{
-	struct clk_core *c;
-	struct hlist_head **lists = (struct hlist_head **)s->private;
-
-	seq_puts(s, "   clock                         enable_cnt  prepare_cnt        rate   accuracy   phase\n");
-	seq_puts(s, "----------------------------------------------------------------------------------------\n");
-
-	clk_prepare_lock();
-
-	for (; *lists; lists++)
-		hlist_for_each_entry(c, *lists, child_node)
-			clk_summary_show_subtree(s, c, 0);
-
-	clk_prepare_unlock();
-
-	return 0;
-}
-
-
-static int clk_summary_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, clk_summary_show, inode->i_private);
-}
-
-static const struct file_operations clk_summary_fops = {
-	.open		= clk_summary_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static void clk_dump_one(struct seq_file *s, struct clk_core *c, int level)
-{
-	if (!c)
-		return;
-
-	seq_printf(s, "\"%s\": { ", c->name);
-	seq_printf(s, "\"enable_count\": %d,", c->enable_count);
-	seq_printf(s, "\"prepare_count\": %d,", c->prepare_count);
-	seq_printf(s, "\"rate\": %lu", clk_core_get_rate(c));
-	seq_printf(s, "\"accuracy\": %lu", clk_core_get_accuracy(c));
-	seq_printf(s, "\"phase\": %d", clk_core_get_phase(c));
-}
-
-static void clk_dump_subtree(struct seq_file *s, struct clk_core *c, int level)
-{
-	struct clk_core *child;
-
-	if (!c)
-		return;
-
-	clk_dump_one(s, c, level);
-
-	hlist_for_each_entry(child, &c->children, child_node) {
-		seq_printf(s, ",");
-		clk_dump_subtree(s, child, level + 1);
-	}
-
-	seq_printf(s, "}");
-}
-
-static int clk_dump(struct seq_file *s, void *data)
-{
-	struct clk_core *c;
-	bool first_node = true;
-	struct hlist_head **lists = (struct hlist_head **)s->private;
-
-	seq_printf(s, "{");
-
-	clk_prepare_lock();
-
-	for (; *lists; lists++) {
-		hlist_for_each_entry(c, *lists, child_node) {
-			if (!first_node)
-				seq_puts(s, ",");
-			first_node = false;
-			clk_dump_subtree(s, c, 0);
-		}
-	}
-
-	clk_prepare_unlock();
-
-	seq_printf(s, "}");
-	return 0;
-}
-
-
-static int clk_dump_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, clk_dump, inode->i_private);
-}
-
-static const struct file_operations clk_dump_fops = {
-	.open		= clk_dump_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int clk_debug_create_one(struct clk_core *clk, struct dentry *pdentry)
-{
-	struct dentry *d;
-	int ret = -ENOMEM;
-
-	if (!clk || !pdentry) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	d = debugfs_create_dir(clk->name, pdentry);
-	if (!d)
-		goto out;
-
-	clk->dentry = d;
-
-	d = debugfs_create_u32("clk_rate", S_IRUGO, clk->dentry,
-			(u32 *)&clk->rate);
-	if (!d)
-		goto err_out;
-
-	d = debugfs_create_u32("clk_accuracy", S_IRUGO, clk->dentry,
-			(u32 *)&clk->accuracy);
-	if (!d)
-		goto err_out;
-
-	d = debugfs_create_u32("clk_phase", S_IRUGO, clk->dentry,
-			(u32 *)&clk->phase);
-	if (!d)
-		goto err_out;
-
-	d = debugfs_create_x32("clk_flags", S_IRUGO, clk->dentry,
-			(u32 *)&clk->flags);
-	if (!d)
-		goto err_out;
-
-	d = debugfs_create_u32("clk_prepare_count", S_IRUGO, clk->dentry,
-			(u32 *)&clk->prepare_count);
-	if (!d)
-		goto err_out;
-
-	d = debugfs_create_u32("clk_enable_count", S_IRUGO, clk->dentry,
-			(u32 *)&clk->enable_count);
-	if (!d)
-		goto err_out;
-
-	d = debugfs_create_u32("clk_notifier_count", S_IRUGO, clk->dentry,
-			(u32 *)&clk->notifier_count);
-	if (!d)
-		goto err_out;
-
-	if (clk->ops->debug_init) {
-		ret = clk->ops->debug_init(clk->hw, clk->dentry);
-		if (ret)
-			goto err_out;
-	}
-
-	ret = 0;
-	goto out;
-
-err_out:
-	debugfs_remove_recursive(clk->dentry);
-	clk->dentry = NULL;
-out:
-	return ret;
-}
-
-/**
- * clk_debug_register - add a clk node to the debugfs clk tree
- * @clk: the clk being added to the debugfs clk tree
- *
- * Dynamically adds a clk to the debugfs clk tree if debugfs has been
- * initialized.  Otherwise it bails out early since the debugfs clk tree
- * will be created lazily by clk_debug_init as part of a late_initcall.
- */
-static int clk_debug_register(struct clk_core *clk)
-{
-	int ret = 0;
-
-	mutex_lock(&clk_debug_lock);
-	hlist_add_head(&clk->debug_node, &clk_debug_list);
-
-	if (!inited)
-		goto unlock;
-
-	ret = clk_debug_create_one(clk, rootdir);
-unlock:
-	mutex_unlock(&clk_debug_lock);
-
-	return ret;
-}
-
- /**
- * clk_debug_unregister - remove a clk node from the debugfs clk tree
- * @clk: the clk being removed from the debugfs clk tree
- *
- * Dynamically removes a clk and all it's children clk nodes from the
- * debugfs clk tree if clk->dentry points to debugfs created by
- * clk_debug_register in __clk_init.
- */
-static void clk_debug_unregister(struct clk_core *clk)
-{
-	mutex_lock(&clk_debug_lock);
-	hlist_del_init(&clk->debug_node);
-	debugfs_remove_recursive(clk->dentry);
-	clk->dentry = NULL;
-	mutex_unlock(&clk_debug_lock);
-}
-
-struct dentry *clk_debugfs_add_file(struct clk_hw *hw, char *name, umode_t mode,
-				void *data, const struct file_operations *fops)
-{
-	struct dentry *d = NULL;
-
-	if (hw->core->dentry)
-		d = debugfs_create_file(name, mode, hw->core->dentry, data,
-					fops);
-
-	return d;
-}
-EXPORT_SYMBOL_GPL(clk_debugfs_add_file);
-
-/**
- * clk_debug_init - lazily create the debugfs clk tree visualization
- *
- * clks are often initialized very early during boot before memory can
- * be dynamically allocated and well before debugfs is setup.
- * clk_debug_init walks the clk tree hierarchy while holding
- * prepare_lock and creates the topology as part of a late_initcall,
- * thus insuring that clks initialized very early will still be
- * represented in the debugfs clk tree.  This function should only be
- * called once at boot-time, and all other clks added dynamically will
- * be done so with clk_debug_register.
- */
-static int __init clk_debug_init(void)
-{
-	struct clk_core *clk;
-	struct dentry *d;
-
-	rootdir = debugfs_create_dir("clk", NULL);
-
-	if (!rootdir)
-		return -ENOMEM;
-
-	d = debugfs_create_file("clk_summary", S_IRUGO, rootdir, &all_lists,
-				&clk_summary_fops);
-	if (!d)
-		return -ENOMEM;
-
-	d = debugfs_create_file("clk_dump", S_IRUGO, rootdir, &all_lists,
-				&clk_dump_fops);
-	if (!d)
-		return -ENOMEM;
-
-	d = debugfs_create_file("clk_orphan_summary", S_IRUGO, rootdir,
-				&orphan_list, &clk_summary_fops);
-	if (!d)
-		return -ENOMEM;
-
-	d = debugfs_create_file("clk_orphan_dump", S_IRUGO, rootdir,
-				&orphan_list, &clk_dump_fops);
-	if (!d)
-		return -ENOMEM;
-
-	mutex_lock(&clk_debug_lock);
-	hlist_for_each_entry(clk, &clk_debug_list, debug_node)
-		clk_debug_create_one(clk, rootdir);
-
-	inited = 1;
-	mutex_unlock(&clk_debug_lock);
-
-	return 0;
-}
-late_initcall(clk_debug_init);
-#else
-static inline int clk_debug_register(struct clk_core *clk) { return 0; }
-static inline void clk_debug_reparent(struct clk_core *clk,
-				      struct clk_core *new_parent)
-{
-}
-static inline void clk_debug_unregister(struct clk_core *clk)
-{
-}
-#endif
-
-/* caller must hold prepare_lock */
-static void clk_unprepare_unused_subtree(struct clk_core *clk)
+static void clk_unprepare_unused_subtree(struct clk_core *core)
 {
 	struct clk_core *child;
 
 	lockdep_assert_held(&prepare_lock);
 
-	hlist_for_each_entry(child, &clk->children, child_node)
+	hlist_for_each_entry(child, &core->children, child_node)
 		clk_unprepare_unused_subtree(child);
 
-	if (clk->prepare_count)
+	if (core->prepare_count)
 		return;
 
-	if (clk->flags & CLK_IGNORE_UNUSED)
+	if (core->flags & CLK_IGNORE_UNUSED)
 		return;
 
-	if (clk_core_is_prepared(clk)) {
-		trace_clk_unprepare(clk);
-		if (clk->ops->unprepare_unused)
-			clk->ops->unprepare_unused(clk->hw);
-		else if (clk->ops->unprepare)
-			clk->ops->unprepare(clk->hw);
-		trace_clk_unprepare_complete(clk);
+	if (clk_core_is_prepared(core)) {
+		trace_clk_unprepare(core);
+		if (core->ops->unprepare_unused)
+			core->ops->unprepare_unused(core->hw);
+		else if (core->ops->unprepare)
+			core->ops->unprepare(core->hw);
+		trace_clk_unprepare_complete(core);
 	}
 }
 
-/* caller must hold prepare_lock */
-static void clk_disable_unused_subtree(struct clk_core *clk)
+static void clk_disable_unused_subtree(struct clk_core *core)
 {
 	struct clk_core *child;
 	unsigned long flags;
 
 	lockdep_assert_held(&prepare_lock);
 
-	hlist_for_each_entry(child, &clk->children, child_node)
+	hlist_for_each_entry(child, &core->children, child_node)
 		clk_disable_unused_subtree(child);
 
 	flags = clk_enable_lock();
 
-	if (clk->enable_count)
+	if (core->enable_count)
 		goto unlock_out;
 
-	if (clk->flags & CLK_IGNORE_UNUSED)
+	if (core->flags & CLK_IGNORE_UNUSED)
 		goto unlock_out;
 
 	/*
@@ -528,13 +211,13 @@
 	 * sequence.  call .disable_unused if available, otherwise fall
 	 * back to .disable
 	 */
-	if (clk_core_is_enabled(clk)) {
-		trace_clk_disable(clk);
-		if (clk->ops->disable_unused)
-			clk->ops->disable_unused(clk->hw);
-		else if (clk->ops->disable)
-			clk->ops->disable(clk->hw);
-		trace_clk_disable_complete(clk);
+	if (clk_core_is_enabled(core)) {
+		trace_clk_disable(core);
+		if (core->ops->disable_unused)
+			core->ops->disable_unused(core->hw);
+		else if (core->ops->disable)
+			core->ops->disable(core->hw);
+		trace_clk_disable_complete(core);
 	}
 
 unlock_out:
@@ -551,7 +234,7 @@
 
 static int clk_disable_unused(void)
 {
-	struct clk_core *clk;
+	struct clk_core *core;
 
 	if (clk_ignore_unused) {
 		pr_warn("clk: Not disabling unused clocks\n");
@@ -560,17 +243,17 @@
 
 	clk_prepare_lock();
 
-	hlist_for_each_entry(clk, &clk_root_list, child_node)
-		clk_disable_unused_subtree(clk);
+	hlist_for_each_entry(core, &clk_root_list, child_node)
+		clk_disable_unused_subtree(core);
 
-	hlist_for_each_entry(clk, &clk_orphan_list, child_node)
-		clk_disable_unused_subtree(clk);
+	hlist_for_each_entry(core, &clk_orphan_list, child_node)
+		clk_disable_unused_subtree(core);
 
-	hlist_for_each_entry(clk, &clk_root_list, child_node)
-		clk_unprepare_unused_subtree(clk);
+	hlist_for_each_entry(core, &clk_root_list, child_node)
+		clk_unprepare_unused_subtree(core);
 
-	hlist_for_each_entry(clk, &clk_orphan_list, child_node)
-		clk_unprepare_unused_subtree(clk);
+	hlist_for_each_entry(core, &clk_orphan_list, child_node)
+		clk_unprepare_unused_subtree(core);
 
 	clk_prepare_unlock();
 
@@ -608,151 +291,16 @@
 }
 EXPORT_SYMBOL_GPL(__clk_get_parent);
 
-static struct clk_core *clk_core_get_parent_by_index(struct clk_core *clk,
-							 u8 index)
-{
-	if (!clk || index >= clk->num_parents)
-		return NULL;
-	else if (!clk->parents)
-		return clk_core_lookup(clk->parent_names[index]);
-	else if (!clk->parents[index])
-		return clk->parents[index] =
-			clk_core_lookup(clk->parent_names[index]);
-	else
-		return clk->parents[index];
-}
-
-struct clk *clk_get_parent_by_index(struct clk *clk, u8 index)
-{
-	struct clk_core *parent;
-
-	if (!clk)
-		return NULL;
-
-	parent = clk_core_get_parent_by_index(clk->core, index);
-
-	return !parent ? NULL : parent->hw->clk;
-}
-EXPORT_SYMBOL_GPL(clk_get_parent_by_index);
-
-unsigned int __clk_get_enable_count(struct clk *clk)
-{
-	return !clk ? 0 : clk->core->enable_count;
-}
-
-static unsigned long clk_core_get_rate_nolock(struct clk_core *clk)
-{
-	unsigned long ret;
-
-	if (!clk) {
-		ret = 0;
-		goto out;
-	}
-
-	ret = clk->rate;
-
-	if (clk->flags & CLK_IS_ROOT)
-		goto out;
-
-	if (!clk->parent)
-		ret = 0;
-
-out:
-	return ret;
-}
-
-unsigned long __clk_get_rate(struct clk *clk)
-{
-	if (!clk)
-		return 0;
-
-	return clk_core_get_rate_nolock(clk->core);
-}
-EXPORT_SYMBOL_GPL(__clk_get_rate);
-
-static unsigned long __clk_get_accuracy(struct clk_core *clk)
-{
-	if (!clk)
-		return 0;
-
-	return clk->accuracy;
-}
-
-unsigned long __clk_get_flags(struct clk *clk)
-{
-	return !clk ? 0 : clk->core->flags;
-}
-EXPORT_SYMBOL_GPL(__clk_get_flags);
-
-static bool clk_core_is_prepared(struct clk_core *clk)
-{
-	int ret;
-
-	if (!clk)
-		return false;
-
-	/*
-	 * .is_prepared is optional for clocks that can prepare
-	 * fall back to software usage counter if it is missing
-	 */
-	if (!clk->ops->is_prepared) {
-		ret = clk->prepare_count ? 1 : 0;
-		goto out;
-	}
-
-	ret = clk->ops->is_prepared(clk->hw);
-out:
-	return !!ret;
-}
-
-bool __clk_is_prepared(struct clk *clk)
-{
-	if (!clk)
-		return false;
-
-	return clk_core_is_prepared(clk->core);
-}
-
-static bool clk_core_is_enabled(struct clk_core *clk)
-{
-	int ret;
-
-	if (!clk)
-		return false;
-
-	/*
-	 * .is_enabled is only mandatory for clocks that gate
-	 * fall back to software usage counter if .is_enabled is missing
-	 */
-	if (!clk->ops->is_enabled) {
-		ret = clk->enable_count ? 1 : 0;
-		goto out;
-	}
-
-	ret = clk->ops->is_enabled(clk->hw);
-out:
-	return !!ret;
-}
-
-bool __clk_is_enabled(struct clk *clk)
-{
-	if (!clk)
-		return false;
-
-	return clk_core_is_enabled(clk->core);
-}
-EXPORT_SYMBOL_GPL(__clk_is_enabled);
-
 static struct clk_core *__clk_lookup_subtree(const char *name,
-					     struct clk_core *clk)
+					     struct clk_core *core)
 {
 	struct clk_core *child;
 	struct clk_core *ret;
 
-	if (!strcmp(clk->name, name))
-		return clk;
+	if (!strcmp(core->name, name))
+		return core;
 
-	hlist_for_each_entry(child, &clk->children, child_node) {
+	hlist_for_each_entry(child, &core->children, child_node) {
 		ret = __clk_lookup_subtree(name, child);
 		if (ret)
 			return ret;
@@ -786,6 +334,99 @@
 	return NULL;
 }
 
+static struct clk_core *clk_core_get_parent_by_index(struct clk_core *core,
+							 u8 index)
+{
+	if (!core || index >= core->num_parents)
+		return NULL;
+	else if (!core->parents)
+		return clk_core_lookup(core->parent_names[index]);
+	else if (!core->parents[index])
+		return core->parents[index] =
+			clk_core_lookup(core->parent_names[index]);
+	else
+		return core->parents[index];
+}
+
+struct clk *clk_get_parent_by_index(struct clk *clk, u8 index)
+{
+	struct clk_core *parent;
+
+	if (!clk)
+		return NULL;
+
+	parent = clk_core_get_parent_by_index(clk->core, index);
+
+	return !parent ? NULL : parent->hw->clk;
+}
+EXPORT_SYMBOL_GPL(clk_get_parent_by_index);
+
+unsigned int __clk_get_enable_count(struct clk *clk)
+{
+	return !clk ? 0 : clk->core->enable_count;
+}
+
+static unsigned long clk_core_get_rate_nolock(struct clk_core *core)
+{
+	unsigned long ret;
+
+	if (!core) {
+		ret = 0;
+		goto out;
+	}
+
+	ret = core->rate;
+
+	if (core->flags & CLK_IS_ROOT)
+		goto out;
+
+	if (!core->parent)
+		ret = 0;
+
+out:
+	return ret;
+}
+
+unsigned long __clk_get_rate(struct clk *clk)
+{
+	if (!clk)
+		return 0;
+
+	return clk_core_get_rate_nolock(clk->core);
+}
+EXPORT_SYMBOL_GPL(__clk_get_rate);
+
+static unsigned long __clk_get_accuracy(struct clk_core *core)
+{
+	if (!core)
+		return 0;
+
+	return core->accuracy;
+}
+
+unsigned long __clk_get_flags(struct clk *clk)
+{
+	return !clk ? 0 : clk->core->flags;
+}
+EXPORT_SYMBOL_GPL(__clk_get_flags);
+
+bool __clk_is_prepared(struct clk *clk)
+{
+	if (!clk)
+		return false;
+
+	return clk_core_is_prepared(clk->core);
+}
+
+bool __clk_is_enabled(struct clk *clk)
+{
+	if (!clk)
+		return false;
+
+	return clk_core_is_enabled(clk->core);
+}
+EXPORT_SYMBOL_GPL(__clk_is_enabled);
+
 static bool mux_is_better_rate(unsigned long rate, unsigned long now,
 			   unsigned long best, unsigned long flags)
 {
@@ -853,7 +494,7 @@
 	return !core ? NULL : core->hw->clk;
 }
 
-static void clk_core_get_boundaries(struct clk_core *clk,
+static void clk_core_get_boundaries(struct clk_core *core,
 				    unsigned long *min_rate,
 				    unsigned long *max_rate)
 {
@@ -862,10 +503,10 @@
 	*min_rate = 0;
 	*max_rate = ULONG_MAX;
 
-	hlist_for_each_entry(clk_user, &clk->clks, clks_node)
+	hlist_for_each_entry(clk_user, &core->clks, clks_node)
 		*min_rate = max(*min_rate, clk_user->min_rate);
 
-	hlist_for_each_entry(clk_user, &clk->clks, clks_node)
+	hlist_for_each_entry(clk_user, &core->clks, clks_node)
 		*max_rate = min(*max_rate, clk_user->max_rate);
 }
 
@@ -901,26 +542,28 @@
 
 /***        clk api        ***/
 
-static void clk_core_unprepare(struct clk_core *clk)
+static void clk_core_unprepare(struct clk_core *core)
 {
-	if (!clk)
+	lockdep_assert_held(&prepare_lock);
+
+	if (!core)
 		return;
 
-	if (WARN_ON(clk->prepare_count == 0))
+	if (WARN_ON(core->prepare_count == 0))
 		return;
 
-	if (--clk->prepare_count > 0)
+	if (--core->prepare_count > 0)
 		return;
 
-	WARN_ON(clk->enable_count > 0);
+	WARN_ON(core->enable_count > 0);
 
-	trace_clk_unprepare(clk);
+	trace_clk_unprepare(core);
 
-	if (clk->ops->unprepare)
-		clk->ops->unprepare(clk->hw);
+	if (core->ops->unprepare)
+		core->ops->unprepare(core->hw);
 
-	trace_clk_unprepare_complete(clk);
-	clk_core_unprepare(clk->parent);
+	trace_clk_unprepare_complete(core);
+	clk_core_unprepare(core->parent);
 }
 
 /**
@@ -945,32 +588,34 @@
 }
 EXPORT_SYMBOL_GPL(clk_unprepare);
 
-static int clk_core_prepare(struct clk_core *clk)
+static int clk_core_prepare(struct clk_core *core)
 {
 	int ret = 0;
 
-	if (!clk)
+	lockdep_assert_held(&prepare_lock);
+
+	if (!core)
 		return 0;
 
-	if (clk->prepare_count == 0) {
-		ret = clk_core_prepare(clk->parent);
+	if (core->prepare_count == 0) {
+		ret = clk_core_prepare(core->parent);
 		if (ret)
 			return ret;
 
-		trace_clk_prepare(clk);
+		trace_clk_prepare(core);
 
-		if (clk->ops->prepare)
-			ret = clk->ops->prepare(clk->hw);
+		if (core->ops->prepare)
+			ret = core->ops->prepare(core->hw);
 
-		trace_clk_prepare_complete(clk);
+		trace_clk_prepare_complete(core);
 
 		if (ret) {
-			clk_core_unprepare(clk->parent);
+			clk_core_unprepare(core->parent);
 			return ret;
 		}
 	}
 
-	clk->prepare_count++;
+	core->prepare_count++;
 
 	return 0;
 }
@@ -1002,33 +647,27 @@
 }
 EXPORT_SYMBOL_GPL(clk_prepare);
 
-static void clk_core_disable(struct clk_core *clk)
+static void clk_core_disable(struct clk_core *core)
 {
-	if (!clk)
+	lockdep_assert_held(&enable_lock);
+
+	if (!core)
 		return;
 
-	if (WARN_ON(clk->enable_count == 0))
+	if (WARN_ON(core->enable_count == 0))
 		return;
 
-	if (--clk->enable_count > 0)
+	if (--core->enable_count > 0)
 		return;
 
-	trace_clk_disable(clk);
+	trace_clk_disable(core);
 
-	if (clk->ops->disable)
-		clk->ops->disable(clk->hw);
+	if (core->ops->disable)
+		core->ops->disable(core->hw);
 
-	trace_clk_disable_complete(clk);
+	trace_clk_disable_complete(core);
 
-	clk_core_disable(clk->parent);
-}
-
-static void __clk_disable(struct clk *clk)
-{
-	if (!clk)
-		return;
-
-	clk_core_disable(clk->core);
+	clk_core_disable(core->parent);
 }
 
 /**
@@ -1051,52 +690,46 @@
 		return;
 
 	flags = clk_enable_lock();
-	__clk_disable(clk);
+	clk_core_disable(clk->core);
 	clk_enable_unlock(flags);
 }
 EXPORT_SYMBOL_GPL(clk_disable);
 
-static int clk_core_enable(struct clk_core *clk)
+static int clk_core_enable(struct clk_core *core)
 {
 	int ret = 0;
 
-	if (!clk)
+	lockdep_assert_held(&enable_lock);
+
+	if (!core)
 		return 0;
 
-	if (WARN_ON(clk->prepare_count == 0))
+	if (WARN_ON(core->prepare_count == 0))
 		return -ESHUTDOWN;
 
-	if (clk->enable_count == 0) {
-		ret = clk_core_enable(clk->parent);
+	if (core->enable_count == 0) {
+		ret = clk_core_enable(core->parent);
 
 		if (ret)
 			return ret;
 
-		trace_clk_enable(clk);
+		trace_clk_enable(core);
 
-		if (clk->ops->enable)
-			ret = clk->ops->enable(clk->hw);
+		if (core->ops->enable)
+			ret = core->ops->enable(core->hw);
 
-		trace_clk_enable_complete(clk);
+		trace_clk_enable_complete(core);
 
 		if (ret) {
-			clk_core_disable(clk->parent);
+			clk_core_disable(core->parent);
 			return ret;
 		}
 	}
 
-	clk->enable_count++;
+	core->enable_count++;
 	return 0;
 }
 
-static int __clk_enable(struct clk *clk)
-{
-	if (!clk)
-		return 0;
-
-	return clk_core_enable(clk->core);
-}
-
 /**
  * clk_enable - ungate a clock
  * @clk: the clk being ungated
@@ -1115,15 +748,18 @@
 	unsigned long flags;
 	int ret;
 
+	if (!clk)
+		return 0;
+
 	flags = clk_enable_lock();
-	ret = __clk_enable(clk);
+	ret = clk_core_enable(clk->core);
 	clk_enable_unlock(flags);
 
 	return ret;
 }
 EXPORT_SYMBOL_GPL(clk_enable);
 
-static unsigned long clk_core_round_rate_nolock(struct clk_core *clk,
+static unsigned long clk_core_round_rate_nolock(struct clk_core *core,
 						unsigned long rate,
 						unsigned long min_rate,
 						unsigned long max_rate)
@@ -1134,25 +770,25 @@
 
 	lockdep_assert_held(&prepare_lock);
 
-	if (!clk)
+	if (!core)
 		return 0;
 
-	parent = clk->parent;
+	parent = core->parent;
 	if (parent)
 		parent_rate = parent->rate;
 
-	if (clk->ops->determine_rate) {
+	if (core->ops->determine_rate) {
 		parent_hw = parent ? parent->hw : NULL;
-		return clk->ops->determine_rate(clk->hw, rate,
+		return core->ops->determine_rate(core->hw, rate,
 						min_rate, max_rate,
 						&parent_rate, &parent_hw);
-	} else if (clk->ops->round_rate)
-		return clk->ops->round_rate(clk->hw, rate, &parent_rate);
-	else if (clk->flags & CLK_SET_RATE_PARENT)
-		return clk_core_round_rate_nolock(clk->parent, rate, min_rate,
+	} else if (core->ops->round_rate)
+		return core->ops->round_rate(core->hw, rate, &parent_rate);
+	else if (core->flags & CLK_SET_RATE_PARENT)
+		return clk_core_round_rate_nolock(core->parent, rate, min_rate,
 						  max_rate);
 	else
-		return clk->rate;
+		return core->rate;
 }
 
 /**
@@ -1162,8 +798,7 @@
  * @min_rate: returned rate must be greater than this rate
  * @max_rate: returned rate must be less than this rate
  *
- * Caller must hold prepare_lock.  Useful for clk_ops such as .set_rate and
- * .determine_rate.
+ * Useful for clk_ops such as .set_rate and .determine_rate.
  */
 unsigned long __clk_determine_rate(struct clk_hw *hw,
 				   unsigned long rate,
@@ -1182,7 +817,7 @@
  * @clk: round the rate of this clock
  * @rate: the rate which is to be rounded
  *
- * Caller must hold prepare_lock.  Useful for clk_ops such as .set_rate
+ * Useful for clk_ops such as .set_rate
  */
 unsigned long __clk_round_rate(struct clk *clk, unsigned long rate)
 {
@@ -1224,7 +859,7 @@
 
 /**
  * __clk_notify - call clk notifier chain
- * @clk: struct clk * that is changing rate
+ * @core: clk that is changing rate
  * @msg: clk notifier type (see include/linux/clk.h)
  * @old_rate: old clk rate
  * @new_rate: new clk rate
@@ -1236,7 +871,7 @@
  * called if all went well, or NOTIFY_STOP or NOTIFY_BAD immediately if
  * a driver returns that.
  */
-static int __clk_notify(struct clk_core *clk, unsigned long msg,
+static int __clk_notify(struct clk_core *core, unsigned long msg,
 		unsigned long old_rate, unsigned long new_rate)
 {
 	struct clk_notifier *cn;
@@ -1247,7 +882,7 @@
 	cnd.new_rate = new_rate;
 
 	list_for_each_entry(cn, &clk_notifier_list, node) {
-		if (cn->clk->core == clk) {
+		if (cn->clk->core == core) {
 			cnd.clk = cn->clk;
 			ret = srcu_notifier_call_chain(&cn->notifier_head, msg,
 					&cnd);
@@ -1259,44 +894,42 @@
 
 /**
  * __clk_recalc_accuracies
- * @clk: first clk in the subtree
+ * @core: first clk in the subtree
  *
  * Walks the subtree of clks starting with clk and recalculates accuracies as
  * it goes.  Note that if a clk does not implement the .recalc_accuracy
- * callback then it is assumed that the clock will take on the accuracy of it's
+ * callback then it is assumed that the clock will take on the accuracy of its
  * parent.
- *
- * Caller must hold prepare_lock.
  */
-static void __clk_recalc_accuracies(struct clk_core *clk)
+static void __clk_recalc_accuracies(struct clk_core *core)
 {
 	unsigned long parent_accuracy = 0;
 	struct clk_core *child;
 
 	lockdep_assert_held(&prepare_lock);
 
-	if (clk->parent)
-		parent_accuracy = clk->parent->accuracy;
+	if (core->parent)
+		parent_accuracy = core->parent->accuracy;
 
-	if (clk->ops->recalc_accuracy)
-		clk->accuracy = clk->ops->recalc_accuracy(clk->hw,
+	if (core->ops->recalc_accuracy)
+		core->accuracy = core->ops->recalc_accuracy(core->hw,
 							  parent_accuracy);
 	else
-		clk->accuracy = parent_accuracy;
+		core->accuracy = parent_accuracy;
 
-	hlist_for_each_entry(child, &clk->children, child_node)
+	hlist_for_each_entry(child, &core->children, child_node)
 		__clk_recalc_accuracies(child);
 }
 
-static long clk_core_get_accuracy(struct clk_core *clk)
+static long clk_core_get_accuracy(struct clk_core *core)
 {
 	unsigned long accuracy;
 
 	clk_prepare_lock();
-	if (clk && (clk->flags & CLK_GET_ACCURACY_NOCACHE))
-		__clk_recalc_accuracies(clk);
+	if (core && (core->flags & CLK_GET_ACCURACY_NOCACHE))
+		__clk_recalc_accuracies(core);
 
-	accuracy = __clk_get_accuracy(clk);
+	accuracy = __clk_get_accuracy(core);
 	clk_prepare_unlock();
 
 	return accuracy;
@@ -1320,17 +953,17 @@
 }
 EXPORT_SYMBOL_GPL(clk_get_accuracy);
 
-static unsigned long clk_recalc(struct clk_core *clk,
+static unsigned long clk_recalc(struct clk_core *core,
 				unsigned long parent_rate)
 {
-	if (clk->ops->recalc_rate)
-		return clk->ops->recalc_rate(clk->hw, parent_rate);
+	if (core->ops->recalc_rate)
+		return core->ops->recalc_rate(core->hw, parent_rate);
 	return parent_rate;
 }
 
 /**
  * __clk_recalc_rates
- * @clk: first clk in the subtree
+ * @core: first clk in the subtree
  * @msg: notification type (see include/linux/clk.h)
  *
  * Walks the subtree of clks starting with clk and recalculates rates as it
@@ -1339,10 +972,8 @@
  *
  * clk_recalc_rates also propagates the POST_RATE_CHANGE notification,
  * if necessary.
- *
- * Caller must hold prepare_lock.
  */
-static void __clk_recalc_rates(struct clk_core *clk, unsigned long msg)
+static void __clk_recalc_rates(struct clk_core *core, unsigned long msg)
 {
 	unsigned long old_rate;
 	unsigned long parent_rate = 0;
@@ -1350,34 +981,34 @@
 
 	lockdep_assert_held(&prepare_lock);
 
-	old_rate = clk->rate;
+	old_rate = core->rate;
 
-	if (clk->parent)
-		parent_rate = clk->parent->rate;
+	if (core->parent)
+		parent_rate = core->parent->rate;
 
-	clk->rate = clk_recalc(clk, parent_rate);
+	core->rate = clk_recalc(core, parent_rate);
 
 	/*
 	 * ignore NOTIFY_STOP and NOTIFY_BAD return values for POST_RATE_CHANGE
 	 * & ABORT_RATE_CHANGE notifiers
 	 */
-	if (clk->notifier_count && msg)
-		__clk_notify(clk, msg, old_rate, clk->rate);
+	if (core->notifier_count && msg)
+		__clk_notify(core, msg, old_rate, core->rate);
 
-	hlist_for_each_entry(child, &clk->children, child_node)
+	hlist_for_each_entry(child, &core->children, child_node)
 		__clk_recalc_rates(child, msg);
 }
 
-static unsigned long clk_core_get_rate(struct clk_core *clk)
+static unsigned long clk_core_get_rate(struct clk_core *core)
 {
 	unsigned long rate;
 
 	clk_prepare_lock();
 
-	if (clk && (clk->flags & CLK_GET_RATE_NOCACHE))
-		__clk_recalc_rates(clk, 0);
+	if (core && (core->flags & CLK_GET_RATE_NOCACHE))
+		__clk_recalc_rates(core, 0);
 
-	rate = clk_core_get_rate_nolock(clk);
+	rate = clk_core_get_rate_nolock(core);
 	clk_prepare_unlock();
 
 	return rate;
@@ -1400,15 +1031,15 @@
 }
 EXPORT_SYMBOL_GPL(clk_get_rate);
 
-static int clk_fetch_parent_index(struct clk_core *clk,
+static int clk_fetch_parent_index(struct clk_core *core,
 				  struct clk_core *parent)
 {
 	int i;
 
-	if (!clk->parents) {
-		clk->parents = kcalloc(clk->num_parents,
+	if (!core->parents) {
+		core->parents = kcalloc(core->num_parents,
 					sizeof(struct clk *), GFP_KERNEL);
-		if (!clk->parents)
+		if (!core->parents)
 			return -ENOMEM;
 	}
 
@@ -1417,15 +1048,15 @@
 	 * or if not yet cached, use string name comparison and cache
 	 * them now to avoid future calls to clk_core_lookup.
 	 */
-	for (i = 0; i < clk->num_parents; i++) {
-		if (clk->parents[i] == parent)
+	for (i = 0; i < core->num_parents; i++) {
+		if (core->parents[i] == parent)
 			return i;
 
-		if (clk->parents[i])
+		if (core->parents[i])
 			continue;
 
-		if (!strcmp(clk->parent_names[i], parent->name)) {
-			clk->parents[i] = clk_core_lookup(parent->name);
+		if (!strcmp(core->parent_names[i], parent->name)) {
+			core->parents[i] = clk_core_lookup(parent->name);
 			return i;
 		}
 	}
@@ -1433,28 +1064,28 @@
 	return -EINVAL;
 }
 
-static void clk_reparent(struct clk_core *clk, struct clk_core *new_parent)
+static void clk_reparent(struct clk_core *core, struct clk_core *new_parent)
 {
-	hlist_del(&clk->child_node);
+	hlist_del(&core->child_node);
 
 	if (new_parent) {
 		/* avoid duplicate POST_RATE_CHANGE notifications */
-		if (new_parent->new_child == clk)
+		if (new_parent->new_child == core)
 			new_parent->new_child = NULL;
 
-		hlist_add_head(&clk->child_node, &new_parent->children);
+		hlist_add_head(&core->child_node, &new_parent->children);
 	} else {
-		hlist_add_head(&clk->child_node, &clk_orphan_list);
+		hlist_add_head(&core->child_node, &clk_orphan_list);
 	}
 
-	clk->parent = new_parent;
+	core->parent = new_parent;
 }
 
-static struct clk_core *__clk_set_parent_before(struct clk_core *clk,
+static struct clk_core *__clk_set_parent_before(struct clk_core *core,
 					   struct clk_core *parent)
 {
 	unsigned long flags;
-	struct clk_core *old_parent = clk->parent;
+	struct clk_core *old_parent = core->parent;
 
 	/*
 	 * Migrate prepare state between parents and prevent race with
@@ -1473,17 +1104,17 @@
 	 *
 	 * See also: Comment for clk_set_parent() below.
 	 */
-	if (clk->prepare_count) {
+	if (core->prepare_count) {
 		clk_core_prepare(parent);
 		flags = clk_enable_lock();
 		clk_core_enable(parent);
-		clk_core_enable(clk);
+		clk_core_enable(core);
 		clk_enable_unlock(flags);
 	}
 
 	/* update the clk tree topology */
 	flags = clk_enable_lock();
-	clk_reparent(clk, parent);
+	clk_reparent(core, parent);
 	clk_enable_unlock(flags);
 
 	return old_parent;
@@ -1508,31 +1139,31 @@
 	}
 }
 
-static int __clk_set_parent(struct clk_core *clk, struct clk_core *parent,
+static int __clk_set_parent(struct clk_core *core, struct clk_core *parent,
 			    u8 p_index)
 {
 	unsigned long flags;
 	int ret = 0;
 	struct clk_core *old_parent;
 
-	old_parent = __clk_set_parent_before(clk, parent);
+	old_parent = __clk_set_parent_before(core, parent);
 
-	trace_clk_set_parent(clk, parent);
+	trace_clk_set_parent(core, parent);
 
 	/* change clock input source */
-	if (parent && clk->ops->set_parent)
-		ret = clk->ops->set_parent(clk->hw, p_index);
+	if (parent && core->ops->set_parent)
+		ret = core->ops->set_parent(core->hw, p_index);
 
-	trace_clk_set_parent_complete(clk, parent);
+	trace_clk_set_parent_complete(core, parent);
 
 	if (ret) {
 		flags = clk_enable_lock();
-		clk_reparent(clk, old_parent);
+		clk_reparent(core, old_parent);
 		clk_enable_unlock(flags);
 
-		if (clk->prepare_count) {
+		if (core->prepare_count) {
 			flags = clk_enable_lock();
-			clk_core_disable(clk);
+			clk_core_disable(core);
 			clk_core_disable(parent);
 			clk_enable_unlock(flags);
 			clk_core_unprepare(parent);
@@ -1540,14 +1171,14 @@
 		return ret;
 	}
 
-	__clk_set_parent_after(clk, parent, old_parent);
+	__clk_set_parent_after(core, parent, old_parent);
 
 	return 0;
 }
 
 /**
  * __clk_speculate_rates
- * @clk: first clk in the subtree
+ * @core: first clk in the subtree
  * @parent_rate: the "future" rate of clk's parent
  *
  * Walks the subtree of clks starting with clk, speculating rates as it
@@ -1558,10 +1189,8 @@
  * subtree have subscribed to the notifications.  Note that if a clk does not
  * implement the .recalc_rate callback then it is assumed that the clock will
  * take on the rate of its parent.
- *
- * Caller must hold prepare_lock.
  */
-static int __clk_speculate_rates(struct clk_core *clk,
+static int __clk_speculate_rates(struct clk_core *core,
 				 unsigned long parent_rate)
 {
 	struct clk_core *child;
@@ -1570,19 +1199,19 @@
 
 	lockdep_assert_held(&prepare_lock);
 
-	new_rate = clk_recalc(clk, parent_rate);
+	new_rate = clk_recalc(core, parent_rate);
 
 	/* abort rate change if a driver returns NOTIFY_BAD or NOTIFY_STOP */
-	if (clk->notifier_count)
-		ret = __clk_notify(clk, PRE_RATE_CHANGE, clk->rate, new_rate);
+	if (core->notifier_count)
+		ret = __clk_notify(core, PRE_RATE_CHANGE, core->rate, new_rate);
 
 	if (ret & NOTIFY_STOP_MASK) {
 		pr_debug("%s: clk notifier callback for clock %s aborted with error %d\n",
-				__func__, clk->name, ret);
+				__func__, core->name, ret);
 		goto out;
 	}
 
-	hlist_for_each_entry(child, &clk->children, child_node) {
+	hlist_for_each_entry(child, &core->children, child_node) {
 		ret = __clk_speculate_rates(child, new_rate);
 		if (ret & NOTIFY_STOP_MASK)
 			break;
@@ -1592,20 +1221,20 @@
 	return ret;
 }
 
-static void clk_calc_subtree(struct clk_core *clk, unsigned long new_rate,
+static void clk_calc_subtree(struct clk_core *core, unsigned long new_rate,
 			     struct clk_core *new_parent, u8 p_index)
 {
 	struct clk_core *child;
 
-	clk->new_rate = new_rate;
-	clk->new_parent = new_parent;
-	clk->new_parent_index = p_index;
+	core->new_rate = new_rate;
+	core->new_parent = new_parent;
+	core->new_parent_index = p_index;
 	/* include clk in new parent's PRE_RATE_CHANGE notifications */
-	clk->new_child = NULL;
-	if (new_parent && new_parent != clk->parent)
-		new_parent->new_child = clk;
+	core->new_child = NULL;
+	if (new_parent && new_parent != core->parent)
+		new_parent->new_child = core;
 
-	hlist_for_each_entry(child, &clk->children, child_node) {
+	hlist_for_each_entry(child, &core->children, child_node) {
 		child->new_rate = clk_recalc(child, new_rate);
 		clk_calc_subtree(child, child->new_rate, NULL, 0);
 	}
@@ -1615,10 +1244,10 @@
  * calculate the new rates returning the topmost clock that has to be
  * changed.
  */
-static struct clk_core *clk_calc_new_rates(struct clk_core *clk,
+static struct clk_core *clk_calc_new_rates(struct clk_core *core,
 					   unsigned long rate)
 {
-	struct clk_core *top = clk;
+	struct clk_core *top = core;
 	struct clk_core *old_parent, *parent;
 	struct clk_hw *parent_hw;
 	unsigned long best_parent_rate = 0;
@@ -1629,20 +1258,20 @@
 	long ret;
 
 	/* sanity */
-	if (IS_ERR_OR_NULL(clk))
+	if (IS_ERR_OR_NULL(core))
 		return NULL;
 
 	/* save parent rate, if it exists */
-	parent = old_parent = clk->parent;
+	parent = old_parent = core->parent;
 	if (parent)
 		best_parent_rate = parent->rate;
 
-	clk_core_get_boundaries(clk, &min_rate, &max_rate);
+	clk_core_get_boundaries(core, &min_rate, &max_rate);
 
 	/* find the closest rate and parent clk/rate */
-	if (clk->ops->determine_rate) {
+	if (core->ops->determine_rate) {
 		parent_hw = parent ? parent->hw : NULL;
-		ret = clk->ops->determine_rate(clk->hw, rate,
+		ret = core->ops->determine_rate(core->hw, rate,
 					       min_rate,
 					       max_rate,
 					       &best_parent_rate,
@@ -1652,8 +1281,8 @@
 
 		new_rate = ret;
 		parent = parent_hw ? parent_hw->core : NULL;
-	} else if (clk->ops->round_rate) {
-		ret = clk->ops->round_rate(clk->hw, rate,
+	} else if (core->ops->round_rate) {
+		ret = core->ops->round_rate(core->hw, rate,
 					   &best_parent_rate);
 		if (ret < 0)
 			return NULL;
@@ -1661,9 +1290,9 @@
 		new_rate = ret;
 		if (new_rate < min_rate || new_rate > max_rate)
 			return NULL;
-	} else if (!parent || !(clk->flags & CLK_SET_RATE_PARENT)) {
+	} else if (!parent || !(core->flags & CLK_SET_RATE_PARENT)) {
 		/* pass-through clock without adjustable parent */
-		clk->new_rate = clk->rate;
+		core->new_rate = core->rate;
 		return NULL;
 	} else {
 		/* pass-through clock with adjustable parent */
@@ -1674,28 +1303,28 @@
 
 	/* some clocks must be gated to change parent */
 	if (parent != old_parent &&
-	    (clk->flags & CLK_SET_PARENT_GATE) && clk->prepare_count) {
+	    (core->flags & CLK_SET_PARENT_GATE) && core->prepare_count) {
 		pr_debug("%s: %s not gated but wants to reparent\n",
-			 __func__, clk->name);
+			 __func__, core->name);
 		return NULL;
 	}
 
 	/* try finding the new parent index */
-	if (parent && clk->num_parents > 1) {
-		p_index = clk_fetch_parent_index(clk, parent);
+	if (parent && core->num_parents > 1) {
+		p_index = clk_fetch_parent_index(core, parent);
 		if (p_index < 0) {
 			pr_debug("%s: clk %s can not be parent of clk %s\n",
-				 __func__, parent->name, clk->name);
+				 __func__, parent->name, core->name);
 			return NULL;
 		}
 	}
 
-	if ((clk->flags & CLK_SET_RATE_PARENT) && parent &&
+	if ((core->flags & CLK_SET_RATE_PARENT) && parent &&
 	    best_parent_rate != parent->rate)
 		top = clk_calc_new_rates(parent, best_parent_rate);
 
 out:
-	clk_calc_subtree(clk, new_rate, parent, p_index);
+	clk_calc_subtree(core, new_rate, parent, p_index);
 
 	return top;
 }
@@ -1705,33 +1334,33 @@
  * so that in case of an error we can walk down the whole tree again and
  * abort the change.
  */
-static struct clk_core *clk_propagate_rate_change(struct clk_core *clk,
+static struct clk_core *clk_propagate_rate_change(struct clk_core *core,
 						  unsigned long event)
 {
 	struct clk_core *child, *tmp_clk, *fail_clk = NULL;
 	int ret = NOTIFY_DONE;
 
-	if (clk->rate == clk->new_rate)
+	if (core->rate == core->new_rate)
 		return NULL;
 
-	if (clk->notifier_count) {
-		ret = __clk_notify(clk, event, clk->rate, clk->new_rate);
+	if (core->notifier_count) {
+		ret = __clk_notify(core, event, core->rate, core->new_rate);
 		if (ret & NOTIFY_STOP_MASK)
-			fail_clk = clk;
+			fail_clk = core;
 	}
 
-	hlist_for_each_entry(child, &clk->children, child_node) {
+	hlist_for_each_entry(child, &core->children, child_node) {
 		/* Skip children who will be reparented to another clock */
-		if (child->new_parent && child->new_parent != clk)
+		if (child->new_parent && child->new_parent != core)
 			continue;
 		tmp_clk = clk_propagate_rate_change(child, event);
 		if (tmp_clk)
 			fail_clk = tmp_clk;
 	}
 
-	/* handle the new child who might not be in clk->children yet */
-	if (clk->new_child) {
-		tmp_clk = clk_propagate_rate_change(clk->new_child, event);
+	/* handle the new child who might not be in core->children yet */
+	if (core->new_child) {
+		tmp_clk = clk_propagate_rate_change(core->new_child, event);
 		if (tmp_clk)
 			fail_clk = tmp_clk;
 	}
@@ -1743,7 +1372,7 @@
  * walk down a subtree and set the new rates notifying the rate
  * change on the way
  */
-static void clk_change_rate(struct clk_core *clk)
+static void clk_change_rate(struct clk_core *core)
 {
 	struct clk_core *child;
 	struct hlist_node *tmp;
@@ -1752,77 +1381,80 @@
 	bool skip_set_rate = false;
 	struct clk_core *old_parent;
 
-	old_rate = clk->rate;
+	old_rate = core->rate;
 
-	if (clk->new_parent)
-		best_parent_rate = clk->new_parent->rate;
-	else if (clk->parent)
-		best_parent_rate = clk->parent->rate;
+	if (core->new_parent)
+		best_parent_rate = core->new_parent->rate;
+	else if (core->parent)
+		best_parent_rate = core->parent->rate;
 
-	if (clk->new_parent && clk->new_parent != clk->parent) {
-		old_parent = __clk_set_parent_before(clk, clk->new_parent);
-		trace_clk_set_parent(clk, clk->new_parent);
+	if (core->new_parent && core->new_parent != core->parent) {
+		old_parent = __clk_set_parent_before(core, core->new_parent);
+		trace_clk_set_parent(core, core->new_parent);
 
-		if (clk->ops->set_rate_and_parent) {
+		if (core->ops->set_rate_and_parent) {
 			skip_set_rate = true;
-			clk->ops->set_rate_and_parent(clk->hw, clk->new_rate,
+			core->ops->set_rate_and_parent(core->hw, core->new_rate,
 					best_parent_rate,
-					clk->new_parent_index);
-		} else if (clk->ops->set_parent) {
-			clk->ops->set_parent(clk->hw, clk->new_parent_index);
+					core->new_parent_index);
+		} else if (core->ops->set_parent) {
+			core->ops->set_parent(core->hw, core->new_parent_index);
 		}
 
-		trace_clk_set_parent_complete(clk, clk->new_parent);
-		__clk_set_parent_after(clk, clk->new_parent, old_parent);
+		trace_clk_set_parent_complete(core, core->new_parent);
+		__clk_set_parent_after(core, core->new_parent, old_parent);
 	}
 
-	trace_clk_set_rate(clk, clk->new_rate);
+	trace_clk_set_rate(core, core->new_rate);
 
-	if (!skip_set_rate && clk->ops->set_rate)
-		clk->ops->set_rate(clk->hw, clk->new_rate, best_parent_rate);
+	if (!skip_set_rate && core->ops->set_rate)
+		core->ops->set_rate(core->hw, core->new_rate, best_parent_rate);
 
-	trace_clk_set_rate_complete(clk, clk->new_rate);
+	trace_clk_set_rate_complete(core, core->new_rate);
 
-	clk->rate = clk_recalc(clk, best_parent_rate);
+	core->rate = clk_recalc(core, best_parent_rate);
 
-	if (clk->notifier_count && old_rate != clk->rate)
-		__clk_notify(clk, POST_RATE_CHANGE, old_rate, clk->rate);
+	if (core->notifier_count && old_rate != core->rate)
+		__clk_notify(core, POST_RATE_CHANGE, old_rate, core->rate);
+
+	if (core->flags & CLK_RECALC_NEW_RATES)
+		(void)clk_calc_new_rates(core, core->new_rate);
 
 	/*
 	 * Use safe iteration, as change_rate can actually swap parents
 	 * for certain clock types.
 	 */
-	hlist_for_each_entry_safe(child, tmp, &clk->children, child_node) {
+	hlist_for_each_entry_safe(child, tmp, &core->children, child_node) {
 		/* Skip children who will be reparented to another clock */
-		if (child->new_parent && child->new_parent != clk)
+		if (child->new_parent && child->new_parent != core)
 			continue;
 		clk_change_rate(child);
 	}
 
-	/* handle the new child who might not be in clk->children yet */
-	if (clk->new_child)
-		clk_change_rate(clk->new_child);
+	/* handle the new child who might not be in core->children yet */
+	if (core->new_child)
+		clk_change_rate(core->new_child);
 }
 
-static int clk_core_set_rate_nolock(struct clk_core *clk,
+static int clk_core_set_rate_nolock(struct clk_core *core,
 				    unsigned long req_rate)
 {
 	struct clk_core *top, *fail_clk;
 	unsigned long rate = req_rate;
 	int ret = 0;
 
-	if (!clk)
+	if (!core)
 		return 0;
 
 	/* bail early if nothing to do */
-	if (rate == clk_core_get_rate_nolock(clk))
+	if (rate == clk_core_get_rate_nolock(core))
 		return 0;
 
-	if ((clk->flags & CLK_SET_RATE_GATE) && clk->prepare_count)
+	if ((core->flags & CLK_SET_RATE_GATE) && core->prepare_count)
 		return -EBUSY;
 
 	/* calculate new rates and get the topmost changed clock */
-	top = clk_calc_new_rates(clk, rate);
+	top = clk_calc_new_rates(core, rate);
 	if (!top)
 		return -EINVAL;
 
@@ -1838,7 +1470,7 @@
 	/* change the rates */
 	clk_change_rate(top);
 
-	clk->req_rate = req_rate;
+	core->req_rate = req_rate;
 
 	return ret;
 }
@@ -1977,55 +1609,63 @@
  * .parents array exists, and if so use it to avoid an expensive tree
  * traversal.  If .parents does not exist then walk the tree.
  */
-static struct clk_core *__clk_init_parent(struct clk_core *clk)
+static struct clk_core *__clk_init_parent(struct clk_core *core)
 {
 	struct clk_core *ret = NULL;
 	u8 index;
 
 	/* handle the trivial cases */
 
-	if (!clk->num_parents)
+	if (!core->num_parents)
 		goto out;
 
-	if (clk->num_parents == 1) {
-		if (IS_ERR_OR_NULL(clk->parent))
-			clk->parent = clk_core_lookup(clk->parent_names[0]);
-		ret = clk->parent;
+	if (core->num_parents == 1) {
+		if (IS_ERR_OR_NULL(core->parent))
+			core->parent = clk_core_lookup(core->parent_names[0]);
+		ret = core->parent;
 		goto out;
 	}
 
-	if (!clk->ops->get_parent) {
-		WARN(!clk->ops->get_parent,
+	if (!core->ops->get_parent) {
+		WARN(!core->ops->get_parent,
 			"%s: multi-parent clocks must implement .get_parent\n",
 			__func__);
 		goto out;
 	};
 
 	/*
-	 * Do our best to cache parent clocks in clk->parents.  This prevents
-	 * unnecessary and expensive lookups.  We don't set clk->parent here;
+	 * Do our best to cache parent clocks in core->parents.  This prevents
+	 * unnecessary and expensive lookups.  We don't set core->parent here;
 	 * that is done by the calling function.
 	 */
 
-	index = clk->ops->get_parent(clk->hw);
+	index = core->ops->get_parent(core->hw);
 
-	if (!clk->parents)
-		clk->parents =
-			kcalloc(clk->num_parents, sizeof(struct clk *),
+	if (!core->parents)
+		core->parents =
+			kcalloc(core->num_parents, sizeof(struct clk *),
 					GFP_KERNEL);
 
-	ret = clk_core_get_parent_by_index(clk, index);
+	ret = clk_core_get_parent_by_index(core, index);
 
 out:
 	return ret;
 }
 
-static void clk_core_reparent(struct clk_core *clk,
+static void clk_core_reparent(struct clk_core *core,
 				  struct clk_core *new_parent)
 {
-	clk_reparent(clk, new_parent);
-	__clk_recalc_accuracies(clk);
-	__clk_recalc_rates(clk, POST_RATE_CHANGE);
+	clk_reparent(core, new_parent);
+	__clk_recalc_accuracies(core);
+	__clk_recalc_rates(core, POST_RATE_CHANGE);
+}
+
+void clk_hw_reparent(struct clk_hw *hw, struct clk_hw *new_parent)
+{
+	if (!hw)
+		return;
+
+	clk_core_reparent(hw->core, !new_parent ? NULL : new_parent->core);
 }
 
 /**
@@ -2062,61 +1702,61 @@
 }
 EXPORT_SYMBOL_GPL(clk_has_parent);
 
-static int clk_core_set_parent(struct clk_core *clk, struct clk_core *parent)
+static int clk_core_set_parent(struct clk_core *core, struct clk_core *parent)
 {
 	int ret = 0;
 	int p_index = 0;
 	unsigned long p_rate = 0;
 
-	if (!clk)
+	if (!core)
 		return 0;
 
 	/* prevent racing with updates to the clock topology */
 	clk_prepare_lock();
 
-	if (clk->parent == parent)
+	if (core->parent == parent)
 		goto out;
 
 	/* verify ops for for multi-parent clks */
-	if ((clk->num_parents > 1) && (!clk->ops->set_parent)) {
+	if ((core->num_parents > 1) && (!core->ops->set_parent)) {
 		ret = -ENOSYS;
 		goto out;
 	}
 
 	/* check that we are allowed to re-parent if the clock is in use */
-	if ((clk->flags & CLK_SET_PARENT_GATE) && clk->prepare_count) {
+	if ((core->flags & CLK_SET_PARENT_GATE) && core->prepare_count) {
 		ret = -EBUSY;
 		goto out;
 	}
 
 	/* try finding the new parent index */
 	if (parent) {
-		p_index = clk_fetch_parent_index(clk, parent);
+		p_index = clk_fetch_parent_index(core, parent);
 		p_rate = parent->rate;
 		if (p_index < 0) {
 			pr_debug("%s: clk %s can not be parent of clk %s\n",
-					__func__, parent->name, clk->name);
+					__func__, parent->name, core->name);
 			ret = p_index;
 			goto out;
 		}
 	}
 
 	/* propagate PRE_RATE_CHANGE notifications */
-	ret = __clk_speculate_rates(clk, p_rate);
+	ret = __clk_speculate_rates(core, p_rate);
 
 	/* abort if a driver objects */
 	if (ret & NOTIFY_STOP_MASK)
 		goto out;
 
 	/* do the re-parent */
-	ret = __clk_set_parent(clk, parent, p_index);
+	ret = __clk_set_parent(core, parent, p_index);
 
 	/* propagate rate an accuracy recalculation accordingly */
 	if (ret) {
-		__clk_recalc_rates(clk, ABORT_RATE_CHANGE);
+		__clk_recalc_rates(core, ABORT_RATE_CHANGE);
 	} else {
-		__clk_recalc_rates(clk, POST_RATE_CHANGE);
-		__clk_recalc_accuracies(clk);
+		__clk_recalc_rates(core, POST_RATE_CHANGE);
+		__clk_recalc_accuracies(core);
 	}
 
 out:
@@ -2201,21 +1841,16 @@
 }
 EXPORT_SYMBOL_GPL(clk_set_phase);
 
-static int clk_core_get_phase(struct clk_core *clk)
+static int clk_core_get_phase(struct clk_core *core)
 {
-	int ret = 0;
-
-	if (!clk)
-		goto out;
+	int ret;
 
 	clk_prepare_lock();
-	ret = clk->phase;
+	ret = core->phase;
 	clk_prepare_unlock();
 
-out:
 	return ret;
 }
-EXPORT_SYMBOL_GPL(clk_get_phase);
 
 /**
  * clk_get_phase - return the phase shift of a clock signal
@@ -2231,6 +1866,7 @@
 
 	return clk_core_get_phase(clk->core);
 }
+EXPORT_SYMBOL_GPL(clk_get_phase);
 
 /**
  * clk_is_match - check if two clk's point to the same hardware clock
@@ -2258,6 +1894,337 @@
 }
 EXPORT_SYMBOL_GPL(clk_is_match);
 
+/***        debugfs support        ***/
+
+#ifdef CONFIG_DEBUG_FS
+#include <linux/debugfs.h>
+
+static struct dentry *rootdir;
+static int inited = 0;
+static DEFINE_MUTEX(clk_debug_lock);
+static HLIST_HEAD(clk_debug_list);
+
+static struct hlist_head *all_lists[] = {
+	&clk_root_list,
+	&clk_orphan_list,
+	NULL,
+};
+
+static struct hlist_head *orphan_list[] = {
+	&clk_orphan_list,
+	NULL,
+};
+
+static void clk_summary_show_one(struct seq_file *s, struct clk_core *c,
+				 int level)
+{
+	if (!c)
+		return;
+
+	seq_printf(s, "%*s%-*s %11d %12d %11lu %10lu %-3d\n",
+		   level * 3 + 1, "",
+		   30 - level * 3, c->name,
+		   c->enable_count, c->prepare_count, clk_core_get_rate(c),
+		   clk_core_get_accuracy(c), clk_core_get_phase(c));
+}
+
+static void clk_summary_show_subtree(struct seq_file *s, struct clk_core *c,
+				     int level)
+{
+	struct clk_core *child;
+
+	if (!c)
+		return;
+
+	clk_summary_show_one(s, c, level);
+
+	hlist_for_each_entry(child, &c->children, child_node)
+		clk_summary_show_subtree(s, child, level + 1);
+}
+
+static int clk_summary_show(struct seq_file *s, void *data)
+{
+	struct clk_core *c;
+	struct hlist_head **lists = (struct hlist_head **)s->private;
+
+	seq_puts(s, "   clock                         enable_cnt  prepare_cnt        rate   accuracy   phase\n");
+	seq_puts(s, "----------------------------------------------------------------------------------------\n");
+
+	clk_prepare_lock();
+
+	for (; *lists; lists++)
+		hlist_for_each_entry(c, *lists, child_node)
+			clk_summary_show_subtree(s, c, 0);
+
+	clk_prepare_unlock();
+
+	return 0;
+}
+
+
+static int clk_summary_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, clk_summary_show, inode->i_private);
+}
+
+static const struct file_operations clk_summary_fops = {
+	.open		= clk_summary_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static void clk_dump_one(struct seq_file *s, struct clk_core *c, int level)
+{
+	if (!c)
+		return;
+
+	/* This should be JSON format, i.e. elements separated with a comma */
+	seq_printf(s, "\"%s\": { ", c->name);
+	seq_printf(s, "\"enable_count\": %d,", c->enable_count);
+	seq_printf(s, "\"prepare_count\": %d,", c->prepare_count);
+	seq_printf(s, "\"rate\": %lu,", clk_core_get_rate(c));
+	seq_printf(s, "\"accuracy\": %lu,", clk_core_get_accuracy(c));
+	seq_printf(s, "\"phase\": %d", clk_core_get_phase(c));
+}
+
+static void clk_dump_subtree(struct seq_file *s, struct clk_core *c, int level)
+{
+	struct clk_core *child;
+
+	if (!c)
+		return;
+
+	clk_dump_one(s, c, level);
+
+	hlist_for_each_entry(child, &c->children, child_node) {
+		seq_printf(s, ",");
+		clk_dump_subtree(s, child, level + 1);
+	}
+
+	seq_printf(s, "}");
+}
+
+static int clk_dump(struct seq_file *s, void *data)
+{
+	struct clk_core *c;
+	bool first_node = true;
+	struct hlist_head **lists = (struct hlist_head **)s->private;
+
+	seq_printf(s, "{");
+
+	clk_prepare_lock();
+
+	for (; *lists; lists++) {
+		hlist_for_each_entry(c, *lists, child_node) {
+			if (!first_node)
+				seq_puts(s, ",");
+			first_node = false;
+			clk_dump_subtree(s, c, 0);
+		}
+	}
+
+	clk_prepare_unlock();
+
+	seq_puts(s, "}\n");
+	return 0;
+}
+
+
+static int clk_dump_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, clk_dump, inode->i_private);
+}
+
+static const struct file_operations clk_dump_fops = {
+	.open		= clk_dump_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int clk_debug_create_one(struct clk_core *core, struct dentry *pdentry)
+{
+	struct dentry *d;
+	int ret = -ENOMEM;
+
+	if (!core || !pdentry) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	d = debugfs_create_dir(core->name, pdentry);
+	if (!d)
+		goto out;
+
+	core->dentry = d;
+
+	d = debugfs_create_u32("clk_rate", S_IRUGO, core->dentry,
+			(u32 *)&core->rate);
+	if (!d)
+		goto err_out;
+
+	d = debugfs_create_u32("clk_accuracy", S_IRUGO, core->dentry,
+			(u32 *)&core->accuracy);
+	if (!d)
+		goto err_out;
+
+	d = debugfs_create_u32("clk_phase", S_IRUGO, core->dentry,
+			(u32 *)&core->phase);
+	if (!d)
+		goto err_out;
+
+	d = debugfs_create_x32("clk_flags", S_IRUGO, core->dentry,
+			(u32 *)&core->flags);
+	if (!d)
+		goto err_out;
+
+	d = debugfs_create_u32("clk_prepare_count", S_IRUGO, core->dentry,
+			(u32 *)&core->prepare_count);
+	if (!d)
+		goto err_out;
+
+	d = debugfs_create_u32("clk_enable_count", S_IRUGO, core->dentry,
+			(u32 *)&core->enable_count);
+	if (!d)
+		goto err_out;
+
+	d = debugfs_create_u32("clk_notifier_count", S_IRUGO, core->dentry,
+			(u32 *)&core->notifier_count);
+	if (!d)
+		goto err_out;
+
+	if (core->ops->debug_init) {
+		ret = core->ops->debug_init(core->hw, core->dentry);
+		if (ret)
+			goto err_out;
+	}
+
+	ret = 0;
+	goto out;
+
+err_out:
+	debugfs_remove_recursive(core->dentry);
+	core->dentry = NULL;
+out:
+	return ret;
+}
+
+/**
+ * clk_debug_register - add a clk node to the debugfs clk directory
+ * @core: the clk being added to the debugfs clk directory
+ *
+ * Dynamically adds a clk to the debugfs clk directory if debugfs has been
+ * initialized.  Otherwise it bails out early since the debugfs clk directory
+ * will be created lazily by clk_debug_init as part of a late_initcall.
+ */
+static int clk_debug_register(struct clk_core *core)
+{
+	int ret = 0;
+
+	mutex_lock(&clk_debug_lock);
+	hlist_add_head(&core->debug_node, &clk_debug_list);
+
+	if (!inited)
+		goto unlock;
+
+	ret = clk_debug_create_one(core, rootdir);
+unlock:
+	mutex_unlock(&clk_debug_lock);
+
+	return ret;
+}
+
+ /**
+ * clk_debug_unregister - remove a clk node from the debugfs clk directory
+ * @core: the clk being removed from the debugfs clk directory
+ *
+ * Dynamically removes a clk and all its child nodes from the
+ * debugfs clk directory if clk->dentry points to debugfs created by
+ * clk_debug_register in __clk_init.
+ */
+static void clk_debug_unregister(struct clk_core *core)
+{
+	mutex_lock(&clk_debug_lock);
+	hlist_del_init(&core->debug_node);
+	debugfs_remove_recursive(core->dentry);
+	core->dentry = NULL;
+	mutex_unlock(&clk_debug_lock);
+}
+
+struct dentry *clk_debugfs_add_file(struct clk_hw *hw, char *name, umode_t mode,
+				void *data, const struct file_operations *fops)
+{
+	struct dentry *d = NULL;
+
+	if (hw->core->dentry)
+		d = debugfs_create_file(name, mode, hw->core->dentry, data,
+					fops);
+
+	return d;
+}
+EXPORT_SYMBOL_GPL(clk_debugfs_add_file);
+
+/**
+ * clk_debug_init - lazily populate the debugfs clk directory
+ *
+ * clks are often initialized very early during boot before memory can be
+ * dynamically allocated and well before debugfs is setup. This function
+ * populates the debugfs clk directory once at boot-time when we know that
+ * debugfs is setup. It should only be called once at boot-time, all other clks
+ * added dynamically will be done so with clk_debug_register.
+ */
+static int __init clk_debug_init(void)
+{
+	struct clk_core *core;
+	struct dentry *d;
+
+	rootdir = debugfs_create_dir("clk", NULL);
+
+	if (!rootdir)
+		return -ENOMEM;
+
+	d = debugfs_create_file("clk_summary", S_IRUGO, rootdir, &all_lists,
+				&clk_summary_fops);
+	if (!d)
+		return -ENOMEM;
+
+	d = debugfs_create_file("clk_dump", S_IRUGO, rootdir, &all_lists,
+				&clk_dump_fops);
+	if (!d)
+		return -ENOMEM;
+
+	d = debugfs_create_file("clk_orphan_summary", S_IRUGO, rootdir,
+				&orphan_list, &clk_summary_fops);
+	if (!d)
+		return -ENOMEM;
+
+	d = debugfs_create_file("clk_orphan_dump", S_IRUGO, rootdir,
+				&orphan_list, &clk_dump_fops);
+	if (!d)
+		return -ENOMEM;
+
+	mutex_lock(&clk_debug_lock);
+	hlist_for_each_entry(core, &clk_debug_list, debug_node)
+		clk_debug_create_one(core, rootdir);
+
+	inited = 1;
+	mutex_unlock(&clk_debug_lock);
+
+	return 0;
+}
+late_initcall(clk_debug_init);
+#else
+static inline int clk_debug_register(struct clk_core *core) { return 0; }
+static inline void clk_debug_reparent(struct clk_core *core,
+				      struct clk_core *new_parent)
+{
+}
+static inline void clk_debug_unregister(struct clk_core *core)
+{
+}
+#endif
+
 /**
  * __clk_init - initialize the data structures in a struct clk
  * @dev:	device initializing this clk, placeholder for now
@@ -2271,67 +2238,67 @@
 	int i, ret = 0;
 	struct clk_core *orphan;
 	struct hlist_node *tmp2;
-	struct clk_core *clk;
+	struct clk_core *core;
 	unsigned long rate;
 
 	if (!clk_user)
 		return -EINVAL;
 
-	clk = clk_user->core;
+	core = clk_user->core;
 
 	clk_prepare_lock();
 
 	/* check to see if a clock with this name is already registered */
-	if (clk_core_lookup(clk->name)) {
+	if (clk_core_lookup(core->name)) {
 		pr_debug("%s: clk %s already initialized\n",
-				__func__, clk->name);
+				__func__, core->name);
 		ret = -EEXIST;
 		goto out;
 	}
 
 	/* check that clk_ops are sane.  See Documentation/clk.txt */
-	if (clk->ops->set_rate &&
-	    !((clk->ops->round_rate || clk->ops->determine_rate) &&
-	      clk->ops->recalc_rate)) {
+	if (core->ops->set_rate &&
+	    !((core->ops->round_rate || core->ops->determine_rate) &&
+	      core->ops->recalc_rate)) {
 		pr_warning("%s: %s must implement .round_rate or .determine_rate in addition to .recalc_rate\n",
-				__func__, clk->name);
+				__func__, core->name);
 		ret = -EINVAL;
 		goto out;
 	}
 
-	if (clk->ops->set_parent && !clk->ops->get_parent) {
+	if (core->ops->set_parent && !core->ops->get_parent) {
 		pr_warning("%s: %s must implement .get_parent & .set_parent\n",
-				__func__, clk->name);
+				__func__, core->name);
 		ret = -EINVAL;
 		goto out;
 	}
 
-	if (clk->ops->set_rate_and_parent &&
-			!(clk->ops->set_parent && clk->ops->set_rate)) {
+	if (core->ops->set_rate_and_parent &&
+			!(core->ops->set_parent && core->ops->set_rate)) {
 		pr_warn("%s: %s must implement .set_parent & .set_rate\n",
-				__func__, clk->name);
+				__func__, core->name);
 		ret = -EINVAL;
 		goto out;
 	}
 
 	/* throw a WARN if any entries in parent_names are NULL */
-	for (i = 0; i < clk->num_parents; i++)
-		WARN(!clk->parent_names[i],
+	for (i = 0; i < core->num_parents; i++)
+		WARN(!core->parent_names[i],
 				"%s: invalid NULL in %s's .parent_names\n",
-				__func__, clk->name);
+				__func__, core->name);
 
 	/*
 	 * Allocate an array of struct clk *'s to avoid unnecessary string
 	 * look-ups of clk's possible parents.  This can fail for clocks passed
-	 * in to clk_init during early boot; thus any access to clk->parents[]
+	 * in to clk_init during early boot; thus any access to core->parents[]
 	 * must always check for a NULL pointer and try to populate it if
 	 * necessary.
 	 *
-	 * If clk->parents is not NULL we skip this entire block.  This allows
-	 * for clock drivers to statically initialize clk->parents.
+	 * If core->parents is not NULL we skip this entire block.  This allows
+	 * for clock drivers to statically initialize core->parents.
 	 */
-	if (clk->num_parents > 1 && !clk->parents) {
-		clk->parents = kcalloc(clk->num_parents, sizeof(struct clk *),
+	if (core->num_parents > 1 && !core->parents) {
+		core->parents = kcalloc(core->num_parents, sizeof(struct clk *),
 					GFP_KERNEL);
 		/*
 		 * clk_core_lookup returns NULL for parents that have not been
@@ -2339,16 +2306,16 @@
 		 * for a NULL pointer.  We can always perform lazy lookups for
 		 * missing parents later on.
 		 */
-		if (clk->parents)
-			for (i = 0; i < clk->num_parents; i++)
-				clk->parents[i] =
-					clk_core_lookup(clk->parent_names[i]);
+		if (core->parents)
+			for (i = 0; i < core->num_parents; i++)
+				core->parents[i] =
+					clk_core_lookup(core->parent_names[i]);
 	}
 
-	clk->parent = __clk_init_parent(clk);
+	core->parent = __clk_init_parent(core);
 
 	/*
-	 * Populate clk->parent if parent has already been __clk_init'd.  If
+	 * Populate core->parent if parent has already been __clk_init'd.  If
 	 * parent has not yet been __clk_init'd then place clk in the orphan
 	 * list.  If clk has set the CLK_IS_ROOT flag then place it in the root
 	 * clk list.
@@ -2357,13 +2324,13 @@
 	 * clocks and re-parent any that are children of the clock currently
 	 * being clk_init'd.
 	 */
-	if (clk->parent)
-		hlist_add_head(&clk->child_node,
-				&clk->parent->children);
-	else if (clk->flags & CLK_IS_ROOT)
-		hlist_add_head(&clk->child_node, &clk_root_list);
+	if (core->parent)
+		hlist_add_head(&core->child_node,
+				&core->parent->children);
+	else if (core->flags & CLK_IS_ROOT)
+		hlist_add_head(&core->child_node, &clk_root_list);
 	else
-		hlist_add_head(&clk->child_node, &clk_orphan_list);
+		hlist_add_head(&core->child_node, &clk_orphan_list);
 
 	/*
 	 * Set clk's accuracy.  The preferred method is to use
@@ -2372,23 +2339,23 @@
 	 * parent (or is orphaned) then accuracy is set to zero (perfect
 	 * clock).
 	 */
-	if (clk->ops->recalc_accuracy)
-		clk->accuracy = clk->ops->recalc_accuracy(clk->hw,
-					__clk_get_accuracy(clk->parent));
-	else if (clk->parent)
-		clk->accuracy = clk->parent->accuracy;
+	if (core->ops->recalc_accuracy)
+		core->accuracy = core->ops->recalc_accuracy(core->hw,
+					__clk_get_accuracy(core->parent));
+	else if (core->parent)
+		core->accuracy = core->parent->accuracy;
 	else
-		clk->accuracy = 0;
+		core->accuracy = 0;
 
 	/*
 	 * Set clk's phase.
 	 * Since a phase is by definition relative to its parent, just
 	 * query the current clock phase, or just assume it's in phase.
 	 */
-	if (clk->ops->get_phase)
-		clk->phase = clk->ops->get_phase(clk->hw);
+	if (core->ops->get_phase)
+		core->phase = core->ops->get_phase(core->hw);
 	else
-		clk->phase = 0;
+		core->phase = 0;
 
 	/*
 	 * Set clk's rate.  The preferred method is to use .recalc_rate.  For
@@ -2396,14 +2363,14 @@
 	 * parent's rate.  If a clock doesn't have a parent (or is orphaned)
 	 * then rate is set to zero.
 	 */
-	if (clk->ops->recalc_rate)
-		rate = clk->ops->recalc_rate(clk->hw,
-				clk_core_get_rate_nolock(clk->parent));
-	else if (clk->parent)
-		rate = clk->parent->rate;
+	if (core->ops->recalc_rate)
+		rate = core->ops->recalc_rate(core->hw,
+				clk_core_get_rate_nolock(core->parent));
+	else if (core->parent)
+		rate = core->parent->rate;
 	else
 		rate = 0;
-	clk->rate = clk->req_rate = rate;
+	core->rate = core->req_rate = rate;
 
 	/*
 	 * walk the list of orphan clocks and reparent any that are children of
@@ -2412,14 +2379,14 @@
 	hlist_for_each_entry_safe(orphan, tmp2, &clk_orphan_list, child_node) {
 		if (orphan->num_parents && orphan->ops->get_parent) {
 			i = orphan->ops->get_parent(orphan->hw);
-			if (!strcmp(clk->name, orphan->parent_names[i]))
-				clk_core_reparent(orphan, clk);
+			if (!strcmp(core->name, orphan->parent_names[i]))
+				clk_core_reparent(orphan, core);
 			continue;
 		}
 
 		for (i = 0; i < orphan->num_parents; i++)
-			if (!strcmp(clk->name, orphan->parent_names[i])) {
-				clk_core_reparent(orphan, clk);
+			if (!strcmp(core->name, orphan->parent_names[i])) {
+				clk_core_reparent(orphan, core);
 				break;
 			}
 	 }
@@ -2432,15 +2399,15 @@
 	 * Please consider other ways of solving initialization problems before
 	 * using this callback, as its use is discouraged.
 	 */
-	if (clk->ops->init)
-		clk->ops->init(clk->hw);
+	if (core->ops->init)
+		core->ops->init(core->hw);
 
-	kref_init(&clk->ref);
+	kref_init(&core->ref);
 out:
 	clk_prepare_unlock();
 
 	if (!ret)
-		clk_debug_register(clk);
+		clk_debug_register(core);
 
 	return ret;
 }
@@ -2486,63 +2453,58 @@
  *
  * clk_register is the primary interface for populating the clock tree with new
  * clock nodes.  It returns a pointer to the newly allocated struct clk which
- * cannot be dereferenced by driver code but may be used in conjuction with the
+ * cannot be dereferenced by driver code but may be used in conjunction with the
  * rest of the clock API.  In the event of an error clk_register will return an
  * error code; drivers must test for an error code after calling clk_register.
  */
 struct clk *clk_register(struct device *dev, struct clk_hw *hw)
 {
 	int i, ret;
-	struct clk_core *clk;
+	struct clk_core *core;
 
-	clk = kzalloc(sizeof(*clk), GFP_KERNEL);
-	if (!clk) {
-		pr_err("%s: could not allocate clk\n", __func__);
+	core = kzalloc(sizeof(*core), GFP_KERNEL);
+	if (!core) {
 		ret = -ENOMEM;
 		goto fail_out;
 	}
 
-	clk->name = kstrdup_const(hw->init->name, GFP_KERNEL);
-	if (!clk->name) {
-		pr_err("%s: could not allocate clk->name\n", __func__);
+	core->name = kstrdup_const(hw->init->name, GFP_KERNEL);
+	if (!core->name) {
 		ret = -ENOMEM;
 		goto fail_name;
 	}
-	clk->ops = hw->init->ops;
+	core->ops = hw->init->ops;
 	if (dev && dev->driver)
-		clk->owner = dev->driver->owner;
-	clk->hw = hw;
-	clk->flags = hw->init->flags;
-	clk->num_parents = hw->init->num_parents;
-	hw->core = clk;
+		core->owner = dev->driver->owner;
+	core->hw = hw;
+	core->flags = hw->init->flags;
+	core->num_parents = hw->init->num_parents;
+	hw->core = core;
 
 	/* allocate local copy in case parent_names is __initdata */
-	clk->parent_names = kcalloc(clk->num_parents, sizeof(char *),
+	core->parent_names = kcalloc(core->num_parents, sizeof(char *),
 					GFP_KERNEL);
 
-	if (!clk->parent_names) {
-		pr_err("%s: could not allocate clk->parent_names\n", __func__);
+	if (!core->parent_names) {
 		ret = -ENOMEM;
 		goto fail_parent_names;
 	}
 
 
 	/* copy each string name in case parent_names is __initdata */
-	for (i = 0; i < clk->num_parents; i++) {
-		clk->parent_names[i] = kstrdup_const(hw->init->parent_names[i],
+	for (i = 0; i < core->num_parents; i++) {
+		core->parent_names[i] = kstrdup_const(hw->init->parent_names[i],
 						GFP_KERNEL);
-		if (!clk->parent_names[i]) {
-			pr_err("%s: could not copy parent_names\n", __func__);
+		if (!core->parent_names[i]) {
 			ret = -ENOMEM;
 			goto fail_parent_names_copy;
 		}
 	}
 
-	INIT_HLIST_HEAD(&clk->clks);
+	INIT_HLIST_HEAD(&core->clks);
 
 	hw->clk = __clk_create_clk(hw, NULL, NULL);
 	if (IS_ERR(hw->clk)) {
-		pr_err("%s: could not allocate per-user clk\n", __func__);
 		ret = PTR_ERR(hw->clk);
 		goto fail_parent_names_copy;
 	}
@@ -2556,35 +2518,32 @@
 
 fail_parent_names_copy:
 	while (--i >= 0)
-		kfree_const(clk->parent_names[i]);
-	kfree(clk->parent_names);
+		kfree_const(core->parent_names[i]);
+	kfree(core->parent_names);
 fail_parent_names:
-	kfree_const(clk->name);
+	kfree_const(core->name);
 fail_name:
-	kfree(clk);
+	kfree(core);
 fail_out:
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(clk_register);
 
-/*
- * Free memory allocated for a clock.
- * Caller must hold prepare_lock.
- */
+/* Free memory allocated for a clock. */
 static void __clk_release(struct kref *ref)
 {
-	struct clk_core *clk = container_of(ref, struct clk_core, ref);
-	int i = clk->num_parents;
+	struct clk_core *core = container_of(ref, struct clk_core, ref);
+	int i = core->num_parents;
 
 	lockdep_assert_held(&prepare_lock);
 
-	kfree(clk->parents);
+	kfree(core->parents);
 	while (--i >= 0)
-		kfree_const(clk->parent_names[i]);
+		kfree_const(core->parent_names[i]);
 
-	kfree(clk->parent_names);
-	kfree_const(clk->name);
-	kfree(clk);
+	kfree(core->parent_names);
+	kfree_const(core->name);
+	kfree(core);
 }
 
 /*
@@ -3068,6 +3027,27 @@
 }
 EXPORT_SYMBOL_GPL(of_clk_get_parent_name);
 
+/**
+ * of_clk_parent_fill() - Fill @parents with names of @np's parents and return
+ * number of parents
+ * @np: Device node pointer associated with clock provider
+ * @parents: pointer to char array that hold the parents' names
+ * @size: size of the @parents array
+ *
+ * Return: number of parents for the clock node.
+ */
+int of_clk_parent_fill(struct device_node *np, const char **parents,
+		       unsigned int size)
+{
+	unsigned int i = 0;
+
+	while (i < size && (parents[i] = of_clk_get_parent_name(np, i)) != NULL)
+		i++;
+
+	return i;
+}
+EXPORT_SYMBOL_GPL(of_clk_parent_fill);
+
 struct clock_provider {
 	of_clk_init_cb_t clk_init_cb;
 	struct device_node *np;
diff --git a/drivers/clk/hisilicon/Kconfig b/drivers/clk/hisilicon/Kconfig
new file mode 100644
index 0000000..b4165ba
--- /dev/null
+++ b/drivers/clk/hisilicon/Kconfig
@@ -0,0 +1,6 @@
+config COMMON_CLK_HI6220
+	bool "Hi6220 Clock Driver"
+	depends on ARCH_HISI || COMPILE_TEST
+	default ARCH_HISI
+	help
+	  Build the Hisilicon Hi6220 clock driver based on the common clock framework.
diff --git a/drivers/clk/hisilicon/Makefile b/drivers/clk/hisilicon/Makefile
index 038c02f..48f0116 100644
--- a/drivers/clk/hisilicon/Makefile
+++ b/drivers/clk/hisilicon/Makefile
@@ -2,8 +2,9 @@
 # Hisilicon Clock specific Makefile
 #
 
-obj-y	+= clk.o clkgate-separated.o
+obj-y	+= clk.o clkgate-separated.o clkdivider-hi6220.o
 
 obj-$(CONFIG_ARCH_HI3xxx)	+= clk-hi3620.o
 obj-$(CONFIG_ARCH_HIP04)	+= clk-hip04.o
 obj-$(CONFIG_ARCH_HIX5HD2)	+= clk-hix5hd2.o
+obj-$(CONFIG_COMMON_CLK_HI6220)	+= clk-hi6220.o
diff --git a/drivers/clk/hisilicon/clk-hi3620.c b/drivers/clk/hisilicon/clk-hi3620.c
index 472dd2c..715d34a 100644
--- a/drivers/clk/hisilicon/clk-hi3620.c
+++ b/drivers/clk/hisilicon/clk-hi3620.c
@@ -38,44 +38,44 @@
 #include "clk.h"
 
 /* clock parent list */
-static const char *timer0_mux_p[] __initdata = { "osc32k", "timerclk01", };
-static const char *timer1_mux_p[] __initdata = { "osc32k", "timerclk01", };
-static const char *timer2_mux_p[] __initdata = { "osc32k", "timerclk23", };
-static const char *timer3_mux_p[] __initdata = { "osc32k", "timerclk23", };
-static const char *timer4_mux_p[] __initdata = { "osc32k", "timerclk45", };
-static const char *timer5_mux_p[] __initdata = { "osc32k", "timerclk45", };
-static const char *timer6_mux_p[] __initdata = { "osc32k", "timerclk67", };
-static const char *timer7_mux_p[] __initdata = { "osc32k", "timerclk67", };
-static const char *timer8_mux_p[] __initdata = { "osc32k", "timerclk89", };
-static const char *timer9_mux_p[] __initdata = { "osc32k", "timerclk89", };
-static const char *uart0_mux_p[] __initdata = { "osc26m", "pclk", };
-static const char *uart1_mux_p[] __initdata = { "osc26m", "pclk", };
-static const char *uart2_mux_p[] __initdata = { "osc26m", "pclk", };
-static const char *uart3_mux_p[] __initdata = { "osc26m", "pclk", };
-static const char *uart4_mux_p[] __initdata = { "osc26m", "pclk", };
-static const char *spi0_mux_p[] __initdata = { "osc26m", "rclk_cfgaxi", };
-static const char *spi1_mux_p[] __initdata = { "osc26m", "rclk_cfgaxi", };
-static const char *spi2_mux_p[] __initdata = { "osc26m", "rclk_cfgaxi", };
+static const char *const timer0_mux_p[] __initconst = { "osc32k", "timerclk01", };
+static const char *const timer1_mux_p[] __initconst = { "osc32k", "timerclk01", };
+static const char *const timer2_mux_p[] __initconst = { "osc32k", "timerclk23", };
+static const char *const timer3_mux_p[] __initconst = { "osc32k", "timerclk23", };
+static const char *const timer4_mux_p[] __initconst = { "osc32k", "timerclk45", };
+static const char *const timer5_mux_p[] __initconst = { "osc32k", "timerclk45", };
+static const char *const timer6_mux_p[] __initconst = { "osc32k", "timerclk67", };
+static const char *const timer7_mux_p[] __initconst = { "osc32k", "timerclk67", };
+static const char *const timer8_mux_p[] __initconst = { "osc32k", "timerclk89", };
+static const char *const timer9_mux_p[] __initconst = { "osc32k", "timerclk89", };
+static const char *const uart0_mux_p[] __initconst = { "osc26m", "pclk", };
+static const char *const uart1_mux_p[] __initconst = { "osc26m", "pclk", };
+static const char *const uart2_mux_p[] __initconst = { "osc26m", "pclk", };
+static const char *const uart3_mux_p[] __initconst = { "osc26m", "pclk", };
+static const char *const uart4_mux_p[] __initconst = { "osc26m", "pclk", };
+static const char *const spi0_mux_p[] __initconst = { "osc26m", "rclk_cfgaxi", };
+static const char *const spi1_mux_p[] __initconst = { "osc26m", "rclk_cfgaxi", };
+static const char *const spi2_mux_p[] __initconst = { "osc26m", "rclk_cfgaxi", };
 /* share axi parent */
-static const char *saxi_mux_p[] __initdata = { "armpll3", "armpll2", };
-static const char *pwm0_mux_p[] __initdata = { "osc32k", "osc26m", };
-static const char *pwm1_mux_p[] __initdata = { "osc32k", "osc26m", };
-static const char *sd_mux_p[] __initdata = { "armpll2", "armpll3", };
-static const char *mmc1_mux_p[] __initdata = { "armpll2", "armpll3", };
-static const char *mmc1_mux2_p[] __initdata = { "osc26m", "mmc1_div", };
-static const char *g2d_mux_p[] __initdata = { "armpll2", "armpll3", };
-static const char *venc_mux_p[] __initdata = { "armpll2", "armpll3", };
-static const char *vdec_mux_p[] __initdata = { "armpll2", "armpll3", };
-static const char *vpp_mux_p[] __initdata = { "armpll2", "armpll3", };
-static const char *edc0_mux_p[] __initdata = { "armpll2", "armpll3", };
-static const char *ldi0_mux_p[] __initdata = { "armpll2", "armpll4",
+static const char *const saxi_mux_p[] __initconst = { "armpll3", "armpll2", };
+static const char *const pwm0_mux_p[] __initconst = { "osc32k", "osc26m", };
+static const char *const pwm1_mux_p[] __initconst = { "osc32k", "osc26m", };
+static const char *const sd_mux_p[] __initconst = { "armpll2", "armpll3", };
+static const char *const mmc1_mux_p[] __initconst = { "armpll2", "armpll3", };
+static const char *const mmc1_mux2_p[] __initconst = { "osc26m", "mmc1_div", };
+static const char *const g2d_mux_p[] __initconst = { "armpll2", "armpll3", };
+static const char *const venc_mux_p[] __initconst = { "armpll2", "armpll3", };
+static const char *const vdec_mux_p[] __initconst = { "armpll2", "armpll3", };
+static const char *const vpp_mux_p[] __initconst = { "armpll2", "armpll3", };
+static const char *const edc0_mux_p[] __initconst = { "armpll2", "armpll3", };
+static const char *const ldi0_mux_p[] __initconst = { "armpll2", "armpll4",
 					     "armpll3", "armpll5", };
-static const char *edc1_mux_p[] __initdata = { "armpll2", "armpll3", };
-static const char *ldi1_mux_p[] __initdata = { "armpll2", "armpll4",
+static const char *const edc1_mux_p[] __initconst = { "armpll2", "armpll3", };
+static const char *const ldi1_mux_p[] __initconst = { "armpll2", "armpll4",
 					     "armpll3", "armpll5", };
-static const char *rclk_hsic_p[] __initdata = { "armpll3", "armpll2", };
-static const char *mmc2_mux_p[] __initdata = { "armpll2", "armpll3", };
-static const char *mmc3_mux_p[] __initdata = { "armpll2", "armpll3", };
+static const char *const rclk_hsic_p[] __initconst = { "armpll3", "armpll2", };
+static const char *const mmc2_mux_p[] __initconst = { "armpll2", "armpll3", };
+static const char *const mmc3_mux_p[] __initconst = { "armpll2", "armpll3", };
 
 
 /* fixed rate clocks */
diff --git a/drivers/clk/hisilicon/clk-hi6220.c b/drivers/clk/hisilicon/clk-hi6220.c
new file mode 100644
index 0000000..4563343
--- /dev/null
+++ b/drivers/clk/hisilicon/clk-hi6220.c
@@ -0,0 +1,284 @@
+/*
+ * Hisilicon Hi6220 clock driver
+ *
+ * Copyright (c) 2015 Hisilicon Limited.
+ *
+ * Author: Bintian Wang <bintian.wang@huawei.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/slab.h>
+
+#include <dt-bindings/clock/hi6220-clock.h>
+
+#include "clk.h"
+
+
+/* clocks in AO (always on) controller */
+static struct hisi_fixed_rate_clock hi6220_fixed_rate_clks[] __initdata = {
+	{ HI6220_REF32K,	"ref32k",	NULL, CLK_IS_ROOT, 32764,     },
+	{ HI6220_CLK_TCXO,	"clk_tcxo",	NULL, CLK_IS_ROOT, 19200000,  },
+	{ HI6220_MMC1_PAD,	"mmc1_pad",	NULL, CLK_IS_ROOT, 100000000, },
+	{ HI6220_MMC2_PAD,	"mmc2_pad",	NULL, CLK_IS_ROOT, 100000000, },
+	{ HI6220_MMC0_PAD,	"mmc0_pad",	NULL, CLK_IS_ROOT, 200000000, },
+	{ HI6220_PLL_BBP,	"bbppll0",	NULL, CLK_IS_ROOT, 245760000, },
+	{ HI6220_PLL_GPU,	"gpupll",	NULL, CLK_IS_ROOT, 1000000000,},
+	{ HI6220_PLL1_DDR,	"ddrpll1",	NULL, CLK_IS_ROOT, 1066000000,},
+	{ HI6220_PLL_SYS,	"syspll",	NULL, CLK_IS_ROOT, 1200000000,},
+	{ HI6220_PLL_SYS_MEDIA,	"media_syspll",	NULL, CLK_IS_ROOT, 1200000000,},
+	{ HI6220_DDR_SRC,	"ddr_sel_src",  NULL, CLK_IS_ROOT, 1200000000,},
+	{ HI6220_PLL_MEDIA,	"media_pll",    NULL, CLK_IS_ROOT, 1440000000,},
+	{ HI6220_PLL_DDR,	"ddrpll0",      NULL, CLK_IS_ROOT, 1600000000,},
+};
+
+static struct hisi_fixed_factor_clock hi6220_fixed_factor_clks[] __initdata = {
+	{ HI6220_300M,         "clk_300m",    "syspll",          1, 4, 0, },
+	{ HI6220_150M,         "clk_150m",    "clk_300m",        1, 2, 0, },
+	{ HI6220_PICOPHY_SRC,  "picophy_src", "clk_150m",        1, 4, 0, },
+	{ HI6220_MMC0_SRC_SEL, "mmc0srcsel",  "mmc0_sel",        1, 8, 0, },
+	{ HI6220_MMC1_SRC_SEL, "mmc1srcsel",  "mmc1_sel",        1, 8, 0, },
+	{ HI6220_MMC2_SRC_SEL, "mmc2srcsel",  "mmc2_sel",        1, 8, 0, },
+	{ HI6220_VPU_CODEC,    "vpucodec",    "codec_jpeg_aclk", 1, 2, 0, },
+	{ HI6220_MMC0_SMP,     "mmc0_sample", "mmc0_sel",        1, 8, 0, },
+	{ HI6220_MMC1_SMP,     "mmc1_sample", "mmc1_sel",        1, 8, 0, },
+	{ HI6220_MMC2_SMP,     "mmc2_sample", "mmc2_sel",        1, 8, 0, },
+};
+
+static struct hisi_gate_clock hi6220_separated_gate_clks_ao[] __initdata = {
+	{ HI6220_WDT0_PCLK,   "wdt0_pclk",   "clk_tcxo", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x630, 12, 0, },
+	{ HI6220_WDT1_PCLK,   "wdt1_pclk",   "clk_tcxo", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x630, 13, 0, },
+	{ HI6220_WDT2_PCLK,   "wdt2_pclk",   "clk_tcxo", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x630, 14, 0, },
+	{ HI6220_TIMER0_PCLK, "timer0_pclk", "clk_tcxo", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x630, 15, 0, },
+	{ HI6220_TIMER1_PCLK, "timer1_pclk", "clk_tcxo", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x630, 16, 0, },
+	{ HI6220_TIMER2_PCLK, "timer2_pclk", "clk_tcxo", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x630, 17, 0, },
+	{ HI6220_TIMER3_PCLK, "timer3_pclk", "clk_tcxo", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x630, 18, 0, },
+	{ HI6220_TIMER4_PCLK, "timer4_pclk", "clk_tcxo", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x630, 19, 0, },
+	{ HI6220_TIMER5_PCLK, "timer5_pclk", "clk_tcxo", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x630, 20, 0, },
+	{ HI6220_TIMER6_PCLK, "timer6_pclk", "clk_tcxo", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x630, 21, 0, },
+	{ HI6220_TIMER7_PCLK, "timer7_pclk", "clk_tcxo", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x630, 22, 0, },
+	{ HI6220_TIMER8_PCLK, "timer8_pclk", "clk_tcxo", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x630, 23, 0, },
+	{ HI6220_UART0_PCLK,  "uart0_pclk",  "clk_tcxo", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x630, 24, 0, },
+};
+
+static void __init hi6220_clk_ao_init(struct device_node *np)
+{
+	struct hisi_clock_data *clk_data_ao;
+
+	clk_data_ao = hisi_clk_init(np, HI6220_AO_NR_CLKS);
+	if (!clk_data_ao)
+		return;
+
+	hisi_clk_register_fixed_rate(hi6220_fixed_rate_clks,
+				ARRAY_SIZE(hi6220_fixed_rate_clks), clk_data_ao);
+
+	hisi_clk_register_fixed_factor(hi6220_fixed_factor_clks,
+				ARRAY_SIZE(hi6220_fixed_factor_clks), clk_data_ao);
+
+	hisi_clk_register_gate_sep(hi6220_separated_gate_clks_ao,
+				ARRAY_SIZE(hi6220_separated_gate_clks_ao), clk_data_ao);
+}
+CLK_OF_DECLARE(hi6220_clk_ao, "hisilicon,hi6220-aoctrl", hi6220_clk_ao_init);
+
+
+/* clocks in sysctrl */
+static const char *mmc0_mux0_p[] __initdata = { "pll_ddr_gate", "syspll", };
+static const char *mmc0_mux1_p[] __initdata = { "mmc0_mux0", "pll_media_gate", };
+static const char *mmc0_src_p[] __initdata = { "mmc0srcsel", "mmc0_div", };
+static const char *mmc1_mux0_p[] __initdata = { "pll_ddr_gate", "syspll", };
+static const char *mmc1_mux1_p[] __initdata = { "mmc1_mux0", "pll_media_gate", };
+static const char *mmc1_src_p[]  __initdata = { "mmc1srcsel", "mmc1_div", };
+static const char *mmc2_mux0_p[] __initdata = { "pll_ddr_gate", "syspll", };
+static const char *mmc2_mux1_p[] __initdata = { "mmc2_mux0", "pll_media_gate", };
+static const char *mmc2_src_p[]  __initdata = { "mmc2srcsel", "mmc2_div", };
+static const char *mmc0_sample_in[] __initdata = { "mmc0_sample", "mmc0_pad", };
+static const char *mmc1_sample_in[] __initdata = { "mmc1_sample", "mmc1_pad", };
+static const char *mmc2_sample_in[] __initdata = { "mmc2_sample", "mmc2_pad", };
+static const char *uart1_src[] __initdata = { "clk_tcxo", "clk_150m", };
+static const char *uart2_src[] __initdata = { "clk_tcxo", "clk_150m", };
+static const char *uart3_src[] __initdata = { "clk_tcxo", "clk_150m", };
+static const char *uart4_src[] __initdata = { "clk_tcxo", "clk_150m", };
+static const char *hifi_src[] __initdata = { "syspll", "pll_media_gate", };
+
+static struct hisi_gate_clock hi6220_separated_gate_clks_sys[] __initdata = {
+	{ HI6220_MMC0_CLK,      "mmc0_clk",      "mmc0_src",       CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x200, 0,  0, },
+	{ HI6220_MMC0_CIUCLK,   "mmc0_ciuclk",   "mmc0_smp_in",    CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x200, 0,  0, },
+	{ HI6220_MMC1_CLK,      "mmc1_clk",      "mmc1_src",       CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x200, 1,  0, },
+	{ HI6220_MMC1_CIUCLK,   "mmc1_ciuclk",   "mmc1_smp_in",    CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x200, 1,  0, },
+	{ HI6220_MMC2_CLK,      "mmc2_clk",      "mmc2_src",       CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x200, 2,  0, },
+	{ HI6220_MMC2_CIUCLK,   "mmc2_ciuclk",   "mmc2_smp_in",    CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x200, 2,  0, },
+	{ HI6220_USBOTG_HCLK,   "usbotg_hclk",   "clk_bus",        CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x200, 4,  0, },
+	{ HI6220_CLK_PICOPHY,   "clk_picophy",   "cs_dapb",        CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x200, 5,  0, },
+	{ HI6220_HIFI,          "hifi_clk",      "hifi_div",       CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x210, 0,  0, },
+	{ HI6220_DACODEC_PCLK,  "dacodec_pclk",  "clk_bus",        CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x210, 5,  0, },
+	{ HI6220_EDMAC_ACLK,    "edmac_aclk",    "clk_bus",        CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x220, 2,  0, },
+	{ HI6220_CS_ATB,        "cs_atb",        "cs_atb_div",     CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x230, 0,  0, },
+	{ HI6220_I2C0_CLK,      "i2c0_clk",      "clk_150m",       CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x230, 1,  0, },
+	{ HI6220_I2C1_CLK,      "i2c1_clk",      "clk_150m",       CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x230, 2,  0, },
+	{ HI6220_I2C2_CLK,      "i2c2_clk",      "clk_150m",       CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x230, 3,  0, },
+	{ HI6220_I2C3_CLK,      "i2c3_clk",      "clk_150m",       CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x230, 4,  0, },
+	{ HI6220_UART1_PCLK,    "uart1_pclk",    "uart1_src",      CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x230, 5,  0, },
+	{ HI6220_UART2_PCLK,    "uart2_pclk",    "uart2_src",      CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x230, 6,  0, },
+	{ HI6220_UART3_PCLK,    "uart3_pclk",    "uart3_src",      CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x230, 7,  0, },
+	{ HI6220_UART4_PCLK,    "uart4_pclk",    "uart4_src",      CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x230, 8,  0, },
+	{ HI6220_SPI_CLK,       "spi_clk",       "clk_150m",       CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x230, 9,  0, },
+	{ HI6220_TSENSOR_CLK,   "tsensor_clk",   "clk_bus",        CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x230, 12, 0, },
+	{ HI6220_MMU_CLK,       "mmu_clk",       "ddrc_axi1",      CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x240, 11, 0, },
+	{ HI6220_HIFI_SEL,      "hifi_sel",      "hifi_src",       CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x270, 0,  0, },
+	{ HI6220_MMC0_SYSPLL,   "mmc0_syspll",   "syspll",         CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x270, 1,  0, },
+	{ HI6220_MMC1_SYSPLL,   "mmc1_syspll",   "syspll",         CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x270, 2,  0, },
+	{ HI6220_MMC2_SYSPLL,   "mmc2_syspll",   "syspll",         CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x270, 3,  0, },
+	{ HI6220_MMC0_SEL,      "mmc0_sel",      "mmc0_mux1",      CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x270, 6,  0, },
+	{ HI6220_MMC1_SEL,      "mmc1_sel",      "mmc1_mux1",      CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x270, 7,  0, },
+	{ HI6220_BBPPLL_SEL,    "bbppll_sel",    "pll0_bbp_gate",  CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x270, 9,  0, },
+	{ HI6220_MEDIA_PLL_SRC, "media_pll_src", "pll_media_gate", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x270, 10, 0, },
+	{ HI6220_MMC2_SEL,      "mmc2_sel",      "mmc2_mux1",      CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x270, 11, 0, },
+	{ HI6220_CS_ATB_SYSPLL, "cs_atb_syspll", "syspll",         CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x270, 12, 0, },
+};
+
+static struct hisi_mux_clock hi6220_mux_clks_sys[] __initdata = {
+	{ HI6220_MMC0_SRC,    "mmc0_src",    mmc0_src_p,     ARRAY_SIZE(mmc0_src_p),     CLK_SET_RATE_PARENT, 0x4,   0,  1, 0, },
+	{ HI6220_MMC0_SMP_IN, "mmc0_smp_in", mmc0_sample_in, ARRAY_SIZE(mmc0_sample_in), CLK_SET_RATE_PARENT, 0x4,   0,  1, 0, },
+	{ HI6220_MMC1_SRC,    "mmc1_src",    mmc1_src_p,     ARRAY_SIZE(mmc1_src_p),     CLK_SET_RATE_PARENT, 0x4,   2,  1, 0, },
+	{ HI6220_MMC1_SMP_IN, "mmc1_smp_in", mmc1_sample_in, ARRAY_SIZE(mmc1_sample_in), CLK_SET_RATE_PARENT, 0x4,   2,  1, 0, },
+	{ HI6220_MMC2_SRC,    "mmc2_src",    mmc2_src_p,     ARRAY_SIZE(mmc2_src_p),     CLK_SET_RATE_PARENT, 0x4,   4,  1, 0, },
+	{ HI6220_MMC2_SMP_IN, "mmc2_smp_in", mmc2_sample_in, ARRAY_SIZE(mmc2_sample_in), CLK_SET_RATE_PARENT, 0x4,   4,  1, 0, },
+	{ HI6220_HIFI_SRC,    "hifi_src",    hifi_src,       ARRAY_SIZE(hifi_src),       CLK_SET_RATE_PARENT, 0x400, 0,  1, CLK_MUX_HIWORD_MASK,},
+	{ HI6220_UART1_SRC,   "uart1_src",   uart1_src,      ARRAY_SIZE(uart1_src),      CLK_SET_RATE_PARENT, 0x400, 1,  1, CLK_MUX_HIWORD_MASK,},
+	{ HI6220_UART2_SRC,   "uart2_src",   uart2_src,      ARRAY_SIZE(uart2_src),      CLK_SET_RATE_PARENT, 0x400, 2,  1, CLK_MUX_HIWORD_MASK,},
+	{ HI6220_UART3_SRC,   "uart3_src",   uart3_src,      ARRAY_SIZE(uart3_src),      CLK_SET_RATE_PARENT, 0x400, 3,  1, CLK_MUX_HIWORD_MASK,},
+	{ HI6220_UART4_SRC,   "uart4_src",   uart4_src,      ARRAY_SIZE(uart4_src),      CLK_SET_RATE_PARENT, 0x400, 4,  1, CLK_MUX_HIWORD_MASK,},
+	{ HI6220_MMC0_MUX0,   "mmc0_mux0",   mmc0_mux0_p,    ARRAY_SIZE(mmc0_mux0_p),    CLK_SET_RATE_PARENT, 0x400, 5,  1, CLK_MUX_HIWORD_MASK,},
+	{ HI6220_MMC1_MUX0,   "mmc1_mux0",   mmc1_mux0_p,    ARRAY_SIZE(mmc1_mux0_p),    CLK_SET_RATE_PARENT, 0x400, 11, 1, CLK_MUX_HIWORD_MASK,},
+	{ HI6220_MMC2_MUX0,   "mmc2_mux0",   mmc2_mux0_p,    ARRAY_SIZE(mmc2_mux0_p),    CLK_SET_RATE_PARENT, 0x400, 12, 1, CLK_MUX_HIWORD_MASK,},
+	{ HI6220_MMC0_MUX1,   "mmc0_mux1",   mmc0_mux1_p,    ARRAY_SIZE(mmc0_mux1_p),    CLK_SET_RATE_PARENT, 0x400, 13, 1, CLK_MUX_HIWORD_MASK,},
+	{ HI6220_MMC1_MUX1,   "mmc1_mux1",   mmc1_mux1_p,    ARRAY_SIZE(mmc1_mux1_p),    CLK_SET_RATE_PARENT, 0x400, 14, 1, CLK_MUX_HIWORD_MASK,},
+	{ HI6220_MMC2_MUX1,   "mmc2_mux1",   mmc2_mux1_p,    ARRAY_SIZE(mmc2_mux1_p),    CLK_SET_RATE_PARENT, 0x400, 15, 1, CLK_MUX_HIWORD_MASK,},
+};
+
+static struct hi6220_divider_clock hi6220_div_clks_sys[] __initdata = {
+	{ HI6220_CLK_BUS,     "clk_bus",     "clk_300m",      CLK_SET_RATE_PARENT, 0x490, 0,  4, 7, },
+	{ HI6220_MMC0_DIV,    "mmc0_div",    "mmc0_syspll",   CLK_SET_RATE_PARENT, 0x494, 0,  6, 7, },
+	{ HI6220_MMC1_DIV,    "mmc1_div",    "mmc1_syspll",   CLK_SET_RATE_PARENT, 0x498, 0,  6, 7, },
+	{ HI6220_MMC2_DIV,    "mmc2_div",    "mmc2_syspll",   CLK_SET_RATE_PARENT, 0x49c, 0,  6, 7, },
+	{ HI6220_HIFI_DIV,    "hifi_div",    "hifi_sel",      CLK_SET_RATE_PARENT, 0x4a0, 0,  4, 7, },
+	{ HI6220_BBPPLL0_DIV, "bbppll0_div", "bbppll_sel",    CLK_SET_RATE_PARENT, 0x4a0, 8,  6, 15,},
+	{ HI6220_CS_DAPB,     "cs_dapb",     "picophy_src",   CLK_SET_RATE_PARENT, 0x4a0, 24, 2, 31,},
+	{ HI6220_CS_ATB_DIV,  "cs_atb_div",  "cs_atb_syspll", CLK_SET_RATE_PARENT, 0x4a4, 0,  4, 7, },
+};
+
+static void __init hi6220_clk_sys_init(struct device_node *np)
+{
+	struct hisi_clock_data *clk_data;
+
+	clk_data = hisi_clk_init(np, HI6220_SYS_NR_CLKS);
+	if (!clk_data)
+		return;
+
+	hisi_clk_register_gate_sep(hi6220_separated_gate_clks_sys,
+			ARRAY_SIZE(hi6220_separated_gate_clks_sys), clk_data);
+
+	hisi_clk_register_mux(hi6220_mux_clks_sys,
+			ARRAY_SIZE(hi6220_mux_clks_sys), clk_data);
+
+	hi6220_clk_register_divider(hi6220_div_clks_sys,
+			ARRAY_SIZE(hi6220_div_clks_sys), clk_data);
+}
+CLK_OF_DECLARE(hi6220_clk_sys, "hisilicon,hi6220-sysctrl", hi6220_clk_sys_init);
+
+
+/* clocks in media controller */
+static const char *clk_1000_1200_src[] __initdata = { "pll_gpu_gate", "media_syspll_src", };
+static const char *clk_1440_1200_src[] __initdata = { "media_syspll_src", "media_pll_src", };
+static const char *clk_1000_1440_src[] __initdata = { "pll_gpu_gate", "media_pll_src", };
+
+static struct hisi_gate_clock hi6220_separated_gate_clks_media[] __initdata = {
+	{ HI6220_DSI_PCLK,       "dsi_pclk",         "vpucodec",      CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x520, 0,  0, },
+	{ HI6220_G3D_PCLK,       "g3d_pclk",         "vpucodec",      CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x520, 1,  0, },
+	{ HI6220_ACLK_CODEC_VPU, "aclk_codec_vpu",   "ade_core_src",  CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x520, 3,  0, },
+	{ HI6220_ISP_SCLK,       "isp_sclk",         "isp_sclk_src",  CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x520, 5,  0, },
+	{ HI6220_ADE_CORE,	 "ade_core",	     "ade_core_src",  CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x520, 6,  0, },
+	{ HI6220_MED_MMU,        "media_mmu",        "mmu_clk",       CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x520, 8,  0, },
+	{ HI6220_CFG_CSI4PHY,    "cfg_csi4phy",      "clk_tcxo",      CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x520, 9,  0, },
+	{ HI6220_CFG_CSI2PHY,    "cfg_csi2phy",      "clk_tcxo",      CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x520, 10, 0, },
+	{ HI6220_ISP_SCLK_GATE,  "isp_sclk_gate",    "media_pll_src", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x520, 11, 0, },
+	{ HI6220_ISP_SCLK_GATE1, "isp_sclk_gate1",   "media_pll_src", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x520, 12, 0, },
+	{ HI6220_ADE_CORE_GATE,  "ade_core_gate",    "media_pll_src", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x520, 14, 0, },
+	{ HI6220_CODEC_VPU_GATE, "codec_vpu_gate",   "clk_1000_1440", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x520, 15, 0, },
+	{ HI6220_MED_SYSPLL,     "media_syspll_src", "media_syspll",  CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x520, 17, 0, },
+};
+
+static struct hisi_mux_clock hi6220_mux_clks_media[] __initdata = {
+	{ HI6220_1440_1200, "clk_1440_1200", clk_1440_1200_src, ARRAY_SIZE(clk_1440_1200_src), CLK_SET_RATE_PARENT, 0x51c, 0, 1, 0, },
+	{ HI6220_1000_1200, "clk_1000_1200", clk_1000_1200_src, ARRAY_SIZE(clk_1000_1200_src), CLK_SET_RATE_PARENT, 0x51c, 1, 1, 0, },
+	{ HI6220_1000_1440, "clk_1000_1440", clk_1000_1440_src, ARRAY_SIZE(clk_1000_1440_src), CLK_SET_RATE_PARENT, 0x51c, 6, 1, 0, },
+};
+
+static struct hi6220_divider_clock hi6220_div_clks_media[] __initdata = {
+	{ HI6220_CODEC_JPEG,    "codec_jpeg_aclk", "media_pll_src",  CLK_SET_RATE_PARENT, 0xcbc, 0,  4, 23, },
+	{ HI6220_ISP_SCLK_SRC,  "isp_sclk_src",    "isp_sclk_gate",  CLK_SET_RATE_PARENT, 0xcbc, 8,  4, 15, },
+	{ HI6220_ISP_SCLK1,     "isp_sclk1",       "isp_sclk_gate1", CLK_SET_RATE_PARENT, 0xcbc, 24, 4, 31, },
+	{ HI6220_ADE_CORE_SRC,  "ade_core_src",    "ade_core_gate",  CLK_SET_RATE_PARENT, 0xcc0, 16, 3, 23, },
+	{ HI6220_ADE_PIX_SRC,   "ade_pix_src",     "clk_1440_1200",  CLK_SET_RATE_PARENT, 0xcc0, 24, 6, 31, },
+	{ HI6220_G3D_CLK,       "g3d_clk",         "clk_1000_1200",  CLK_SET_RATE_PARENT, 0xcc4, 8,  4, 15, },
+	{ HI6220_CODEC_VPU_SRC, "codec_vpu_src",   "codec_vpu_gate", CLK_SET_RATE_PARENT, 0xcc4, 24, 6, 31, },
+};
+
+static void __init hi6220_clk_media_init(struct device_node *np)
+{
+	struct hisi_clock_data *clk_data;
+
+	clk_data = hisi_clk_init(np, HI6220_MEDIA_NR_CLKS);
+	if (!clk_data)
+		return;
+
+	hisi_clk_register_gate_sep(hi6220_separated_gate_clks_media,
+				ARRAY_SIZE(hi6220_separated_gate_clks_media), clk_data);
+
+	hisi_clk_register_mux(hi6220_mux_clks_media,
+				ARRAY_SIZE(hi6220_mux_clks_media), clk_data);
+
+	hi6220_clk_register_divider(hi6220_div_clks_media,
+				ARRAY_SIZE(hi6220_div_clks_media), clk_data);
+}
+CLK_OF_DECLARE(hi6220_clk_media, "hisilicon,hi6220-mediactrl", hi6220_clk_media_init);
+
+
+/* clocks in pmctrl */
+static struct hisi_gate_clock hi6220_gate_clks_power[] __initdata = {
+	{ HI6220_PLL_GPU_GATE,   "pll_gpu_gate",   "gpupll",    CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x8,  0,  0, },
+	{ HI6220_PLL1_DDR_GATE,  "pll1_ddr_gate",  "ddrpll1",   CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x10, 0,  0, },
+	{ HI6220_PLL_DDR_GATE,   "pll_ddr_gate",   "ddrpll0",   CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x18, 0,  0, },
+	{ HI6220_PLL_MEDIA_GATE, "pll_media_gate", "media_pll", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x38, 0,  0, },
+	{ HI6220_PLL0_BBP_GATE,  "pll0_bbp_gate",  "bbppll0",   CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x48, 0,  0, },
+};
+
+static struct hi6220_divider_clock hi6220_div_clks_power[] __initdata = {
+	{ HI6220_DDRC_SRC,  "ddrc_src",  "ddr_sel_src", CLK_SET_RATE_PARENT, 0x5a8, 0, 4, 0, },
+	{ HI6220_DDRC_AXI1, "ddrc_axi1", "ddrc_src",    CLK_SET_RATE_PARENT, 0x5a8, 8, 2, 0, },
+};
+
+static void __init hi6220_clk_power_init(struct device_node *np)
+{
+	struct hisi_clock_data *clk_data;
+
+	clk_data = hisi_clk_init(np, HI6220_POWER_NR_CLKS);
+	if (!clk_data)
+		return;
+
+	hisi_clk_register_gate(hi6220_gate_clks_power,
+				ARRAY_SIZE(hi6220_gate_clks_power), clk_data);
+
+	hi6220_clk_register_divider(hi6220_div_clks_power,
+				ARRAY_SIZE(hi6220_div_clks_power), clk_data);
+}
+CLK_OF_DECLARE(hi6220_clk_power, "hisilicon,hi6220-pmctrl", hi6220_clk_power_init);
diff --git a/drivers/clk/hisilicon/clk-hix5hd2.c b/drivers/clk/hisilicon/clk-hix5hd2.c
index f1d2394..0aaf29d 100644
--- a/drivers/clk/hisilicon/clk-hix5hd2.c
+++ b/drivers/clk/hisilicon/clk-hix5hd2.c
@@ -46,15 +46,15 @@
 	{ HIX5HD2_FIXED_83M, "83m", NULL, CLK_IS_ROOT, 83333333, },
 };
 
-static const char *sfc_mux_p[] __initdata = {
+static const char *const sfc_mux_p[] __initconst = {
 		"24m", "150m", "200m", "100m", "75m", };
 static u32 sfc_mux_table[] = {0, 4, 5, 6, 7};
 
-static const char *sdio_mux_p[] __initdata = {
+static const char *const sdio_mux_p[] __initconst = {
 		"75m", "100m", "50m", "15m", };
 static u32 sdio_mux_table[] = {0, 1, 2, 3};
 
-static const char *fephy_mux_p[] __initdata = { "25m", "125m"};
+static const char *const fephy_mux_p[] __initconst = { "25m", "125m"};
 static u32 fephy_mux_table[] = {0, 1};
 
 
@@ -252,8 +252,9 @@
 	.disable = clk_complex_disable,
 };
 
-void __init hix5hd2_clk_register_complex(struct hix5hd2_complex_clock *clks,
-					 int nums, struct hisi_clock_data *data)
+static void __init
+hix5hd2_clk_register_complex(struct hix5hd2_complex_clock *clks, int nums,
+			     struct hisi_clock_data *data)
 {
 	void __iomem *base = data->base;
 	int i;
diff --git a/drivers/clk/hisilicon/clk.c b/drivers/clk/hisilicon/clk.c
index a078e84..c90a897 100644
--- a/drivers/clk/hisilicon/clk.c
+++ b/drivers/clk/hisilicon/clk.c
@@ -232,3 +232,32 @@
 		data->clk_data.clks[clks[i].id] = clk;
 	}
 }
+
+void __init hi6220_clk_register_divider(struct hi6220_divider_clock *clks,
+					int nums, struct hisi_clock_data *data)
+{
+	struct clk *clk;
+	void __iomem *base = data->base;
+	int i;
+
+	for (i = 0; i < nums; i++) {
+		clk = hi6220_register_clkdiv(NULL, clks[i].name,
+						clks[i].parent_name,
+						clks[i].flags,
+						base + clks[i].offset,
+						clks[i].shift,
+						clks[i].width,
+						clks[i].mask_bit,
+						&hisi_clk_lock);
+		if (IS_ERR(clk)) {
+			pr_err("%s: failed to register clock %s\n",
+			       __func__, clks[i].name);
+			continue;
+		}
+
+		if (clks[i].alias)
+			clk_register_clkdev(clk, clks[i].alias, NULL);
+
+		data->clk_data.clks[clks[i].id] = clk;
+	}
+}
diff --git a/drivers/clk/hisilicon/clk.h b/drivers/clk/hisilicon/clk.h
index 31083ff..b56fbc1 100644
--- a/drivers/clk/hisilicon/clk.h
+++ b/drivers/clk/hisilicon/clk.h
@@ -55,7 +55,7 @@
 struct hisi_mux_clock {
 	unsigned int		id;
 	const char		*name;
-	const char		**parent_names;
+	const char		*const *parent_names;
 	u8			num_parents;
 	unsigned long		flags;
 	unsigned long		offset;
@@ -79,6 +79,18 @@
 	const char		*alias;
 };
 
+struct hi6220_divider_clock {
+	unsigned int		id;
+	const char		*name;
+	const char		*parent_name;
+	unsigned long		flags;
+	unsigned long		offset;
+	u8			shift;
+	u8			width;
+	u32			mask_bit;
+	const char		*alias;
+};
+
 struct hisi_gate_clock {
 	unsigned int		id;
 	const char		*name;
@@ -94,18 +106,23 @@
 				const char *, unsigned long,
 				void __iomem *, u8,
 				u8, spinlock_t *);
+struct clk *hi6220_register_clkdiv(struct device *dev, const char *name,
+	const char *parent_name, unsigned long flags, void __iomem *reg,
+	u8 shift, u8 width, u32 mask_bit, spinlock_t *lock);
 
-struct hisi_clock_data __init *hisi_clk_init(struct device_node *, int);
-void __init hisi_clk_register_fixed_rate(struct hisi_fixed_rate_clock *,
-					int, struct hisi_clock_data *);
-void __init hisi_clk_register_fixed_factor(struct hisi_fixed_factor_clock *,
-					int, struct hisi_clock_data *);
-void __init hisi_clk_register_mux(struct hisi_mux_clock *, int,
-				struct hisi_clock_data *);
-void __init hisi_clk_register_divider(struct hisi_divider_clock *,
+struct hisi_clock_data *hisi_clk_init(struct device_node *, int);
+void hisi_clk_register_fixed_rate(struct hisi_fixed_rate_clock *,
 				int, struct hisi_clock_data *);
-void __init hisi_clk_register_gate(struct hisi_gate_clock *,
-					int, struct hisi_clock_data *);
-void __init hisi_clk_register_gate_sep(struct hisi_gate_clock *,
-					int, struct hisi_clock_data *);
+void hisi_clk_register_fixed_factor(struct hisi_fixed_factor_clock *,
+				int, struct hisi_clock_data *);
+void hisi_clk_register_mux(struct hisi_mux_clock *, int,
+				struct hisi_clock_data *);
+void hisi_clk_register_divider(struct hisi_divider_clock *,
+				int, struct hisi_clock_data *);
+void hisi_clk_register_gate(struct hisi_gate_clock *,
+				int, struct hisi_clock_data *);
+void hisi_clk_register_gate_sep(struct hisi_gate_clock *,
+				int, struct hisi_clock_data *);
+void hi6220_clk_register_divider(struct hi6220_divider_clock *,
+				int, struct hisi_clock_data *);
 #endif	/* __HISI_CLK_H */
diff --git a/drivers/clk/hisilicon/clkdivider-hi6220.c b/drivers/clk/hisilicon/clkdivider-hi6220.c
new file mode 100644
index 0000000..113eee8
--- /dev/null
+++ b/drivers/clk/hisilicon/clkdivider-hi6220.c
@@ -0,0 +1,156 @@
+/*
+ * Hisilicon hi6220 SoC divider clock driver
+ *
+ * Copyright (c) 2015 Hisilicon Limited.
+ *
+ * Author: Bintian Wang <bintian.wang@huawei.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/clk-provider.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/spinlock.h>
+
+#define div_mask(width)	((1 << (width)) - 1)
+
+/**
+ * struct hi6220_clk_divider - divider clock for hi6220
+ *
+ * @hw:		handle between common and hardware-specific interfaces
+ * @reg:	register containing divider
+ * @shift:	shift to the divider bit field
+ * @width:	width of the divider bit field
+ * @mask:	mask for setting divider rate
+ * @table:	the div table that the divider supports
+ * @lock:	register lock
+ */
+struct hi6220_clk_divider {
+	struct clk_hw	hw;
+	void __iomem	*reg;
+	u8		shift;
+	u8		width;
+	u32		mask;
+	const struct clk_div_table *table;
+	spinlock_t	*lock;
+};
+
+#define to_hi6220_clk_divider(_hw)	\
+	container_of(_hw, struct hi6220_clk_divider, hw)
+
+static unsigned long hi6220_clkdiv_recalc_rate(struct clk_hw *hw,
+					unsigned long parent_rate)
+{
+	unsigned int val;
+	struct hi6220_clk_divider *dclk = to_hi6220_clk_divider(hw);
+
+	val = readl_relaxed(dclk->reg) >> dclk->shift;
+	val &= div_mask(dclk->width);
+
+	return divider_recalc_rate(hw, parent_rate, val, dclk->table,
+				   CLK_DIVIDER_ROUND_CLOSEST);
+}
+
+static long hi6220_clkdiv_round_rate(struct clk_hw *hw, unsigned long rate,
+					unsigned long *prate)
+{
+	struct hi6220_clk_divider *dclk = to_hi6220_clk_divider(hw);
+
+	return divider_round_rate(hw, rate, prate, dclk->table,
+				  dclk->width, CLK_DIVIDER_ROUND_CLOSEST);
+}
+
+static int hi6220_clkdiv_set_rate(struct clk_hw *hw, unsigned long rate,
+					unsigned long parent_rate)
+{
+	int value;
+	unsigned long flags = 0;
+	u32 data;
+	struct hi6220_clk_divider *dclk = to_hi6220_clk_divider(hw);
+
+	value = divider_get_val(rate, parent_rate, dclk->table,
+				dclk->width, CLK_DIVIDER_ROUND_CLOSEST);
+
+	if (dclk->lock)
+		spin_lock_irqsave(dclk->lock, flags);
+
+	data = readl_relaxed(dclk->reg);
+	data &= ~(div_mask(dclk->width) << dclk->shift);
+	data |= value << dclk->shift;
+	data |= dclk->mask;
+
+	writel_relaxed(data, dclk->reg);
+
+	if (dclk->lock)
+		spin_unlock_irqrestore(dclk->lock, flags);
+
+	return 0;
+}
+
+static const struct clk_ops hi6220_clkdiv_ops = {
+	.recalc_rate = hi6220_clkdiv_recalc_rate,
+	.round_rate = hi6220_clkdiv_round_rate,
+	.set_rate = hi6220_clkdiv_set_rate,
+};
+
+struct clk *hi6220_register_clkdiv(struct device *dev, const char *name,
+	const char *parent_name, unsigned long flags, void __iomem *reg,
+	u8 shift, u8 width, u32 mask_bit, spinlock_t *lock)
+{
+	struct hi6220_clk_divider *div;
+	struct clk *clk;
+	struct clk_init_data init;
+	struct clk_div_table *table;
+	u32 max_div, min_div;
+	int i;
+
+	/* allocate the divider */
+	div = kzalloc(sizeof(*div), GFP_KERNEL);
+	if (!div)
+		return ERR_PTR(-ENOMEM);
+
+	/* Init the divider table */
+	max_div = div_mask(width) + 1;
+	min_div = 1;
+
+	table = kcalloc(max_div + 1, sizeof(*table), GFP_KERNEL);
+	if (!table) {
+		kfree(div);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	for (i = 0; i < max_div; i++) {
+		table[i].div = min_div + i;
+		table[i].val = table[i].div - 1;
+	}
+
+	init.name = name;
+	init.ops = &hi6220_clkdiv_ops;
+	init.flags = flags;
+	init.parent_names = parent_name ? &parent_name : NULL;
+	init.num_parents = parent_name ? 1 : 0;
+
+	/* struct hi6220_clk_divider assignments */
+	div->reg = reg;
+	div->shift = shift;
+	div->width = width;
+	div->mask = mask_bit ? BIT(mask_bit) : 0;
+	div->lock = lock;
+	div->hw.init = &init;
+	div->table = table;
+
+	/* register the clock */
+	clk = clk_register(dev, &div->hw);
+	if (IS_ERR(clk)) {
+		kfree(table);
+		kfree(div);
+	}
+
+	return clk;
+}
diff --git a/drivers/clk/keystone/pll.c b/drivers/clk/keystone/pll.c
index 0dd8a4b..4a375ea 100644
--- a/drivers/clk/keystone/pll.c
+++ b/drivers/clk/keystone/pll.c
@@ -37,7 +37,8 @@
  *	Main PLL or any other PLLs in the device such as ARM PLL, DDR PLL
  *	or PA PLL available on keystone2. These PLLs are controlled by
  *	this register. Main PLL is controlled by a PLL controller.
- * @pllm: PLL register map address
+ * @pllm: PLL register map address for multiplier bits
+ * @pllod: PLL register map address for post divider bits
  * @pll_ctl0: PLL controller map address
  * @pllm_lower_mask: multiplier lower mask
  * @pllm_upper_mask: multiplier upper mask
@@ -53,6 +54,7 @@
 	u32 phy_pllm;
 	u32 phy_pll_ctl0;
 	void __iomem *pllm;
+	void __iomem *pllod;
 	void __iomem *pll_ctl0;
 	u32 pllm_lower_mask;
 	u32 pllm_upper_mask;
@@ -102,7 +104,11 @@
 		/* read post divider from od bits*/
 		postdiv = ((val & pll_data->clkod_mask) >>
 				 pll_data->clkod_shift) + 1;
-	else
+	else if (pll_data->pllod) {
+		postdiv = readl(pll_data->pllod);
+		postdiv = ((postdiv & pll_data->clkod_mask) >>
+				pll_data->clkod_shift) + 1;
+	} else
 		postdiv = pll_data->postdiv;
 
 	rate /= (prediv + 1);
@@ -172,12 +178,21 @@
 		/* assume the PLL has output divider register bits */
 		pll_data->clkod_mask = CLKOD_MASK;
 		pll_data->clkod_shift = CLKOD_SHIFT;
+
+		/*
+		 * Check if there is an post-divider register. If not
+		 * assume od bits are part of control register.
+		 */
+		i = of_property_match_string(node, "reg-names",
+					     "post-divider");
+		pll_data->pllod = of_iomap(node, i);
 	}
 
 	i = of_property_match_string(node, "reg-names", "control");
 	pll_data->pll_ctl0 = of_iomap(node, i);
 	if (!pll_data->pll_ctl0) {
 		pr_err("%s: ioremap failed\n", __func__);
+		iounmap(pll_data->pllod);
 		goto out;
 	}
 
@@ -193,6 +208,7 @@
 		pll_data->pllm = of_iomap(node, i);
 		if (!pll_data->pllm) {
 			iounmap(pll_data->pll_ctl0);
+			iounmap(pll_data->pllod);
 			goto out;
 		}
 	}
diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile
new file mode 100644
index 0000000..8e4b2a4
--- /dev/null
+++ b/drivers/clk/mediatek/Makefile
@@ -0,0 +1,4 @@
+obj-y += clk-mtk.o clk-pll.o clk-gate.o
+obj-$(CONFIG_RESET_CONTROLLER) += reset.o
+obj-y += clk-mt8135.o
+obj-y += clk-mt8173.o
diff --git a/drivers/clk/mediatek/clk-gate.c b/drivers/clk/mediatek/clk-gate.c
new file mode 100644
index 0000000..5702036
--- /dev/null
+++ b/drivers/clk/mediatek/clk-gate.c
@@ -0,0 +1,137 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ * Author: James Liao <jamesjj.liao@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/of.h>
+#include <linux/of_address.h>
+
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/clkdev.h>
+
+#include "clk-mtk.h"
+#include "clk-gate.h"
+
+static int mtk_cg_bit_is_cleared(struct clk_hw *hw)
+{
+	struct mtk_clk_gate *cg = to_clk_gate(hw);
+	u32 val;
+
+	regmap_read(cg->regmap, cg->sta_ofs, &val);
+
+	val &= BIT(cg->bit);
+
+	return val == 0;
+}
+
+static int mtk_cg_bit_is_set(struct clk_hw *hw)
+{
+	struct mtk_clk_gate *cg = to_clk_gate(hw);
+	u32 val;
+
+	regmap_read(cg->regmap, cg->sta_ofs, &val);
+
+	val &= BIT(cg->bit);
+
+	return val != 0;
+}
+
+static void mtk_cg_set_bit(struct clk_hw *hw)
+{
+	struct mtk_clk_gate *cg = to_clk_gate(hw);
+
+	regmap_write(cg->regmap, cg->set_ofs, BIT(cg->bit));
+}
+
+static void mtk_cg_clr_bit(struct clk_hw *hw)
+{
+	struct mtk_clk_gate *cg = to_clk_gate(hw);
+
+	regmap_write(cg->regmap, cg->clr_ofs, BIT(cg->bit));
+}
+
+static int mtk_cg_enable(struct clk_hw *hw)
+{
+	mtk_cg_clr_bit(hw);
+
+	return 0;
+}
+
+static void mtk_cg_disable(struct clk_hw *hw)
+{
+	mtk_cg_set_bit(hw);
+}
+
+static int mtk_cg_enable_inv(struct clk_hw *hw)
+{
+	mtk_cg_set_bit(hw);
+
+	return 0;
+}
+
+static void mtk_cg_disable_inv(struct clk_hw *hw)
+{
+	mtk_cg_clr_bit(hw);
+}
+
+const struct clk_ops mtk_clk_gate_ops_setclr = {
+	.is_enabled	= mtk_cg_bit_is_cleared,
+	.enable		= mtk_cg_enable,
+	.disable	= mtk_cg_disable,
+};
+
+const struct clk_ops mtk_clk_gate_ops_setclr_inv = {
+	.is_enabled	= mtk_cg_bit_is_set,
+	.enable		= mtk_cg_enable_inv,
+	.disable	= mtk_cg_disable_inv,
+};
+
+struct clk *mtk_clk_register_gate(
+		const char *name,
+		const char *parent_name,
+		struct regmap *regmap,
+		int set_ofs,
+		int clr_ofs,
+		int sta_ofs,
+		u8 bit,
+		const struct clk_ops *ops)
+{
+	struct mtk_clk_gate *cg;
+	struct clk *clk;
+	struct clk_init_data init = {};
+
+	cg = kzalloc(sizeof(*cg), GFP_KERNEL);
+	if (!cg)
+		return ERR_PTR(-ENOMEM);
+
+	init.name = name;
+	init.flags = CLK_SET_RATE_PARENT;
+	init.parent_names = parent_name ? &parent_name : NULL;
+	init.num_parents = parent_name ? 1 : 0;
+	init.ops = ops;
+
+	cg->regmap = regmap;
+	cg->set_ofs = set_ofs;
+	cg->clr_ofs = clr_ofs;
+	cg->sta_ofs = sta_ofs;
+	cg->bit = bit;
+
+	cg->hw.init = &init;
+
+	clk = clk_register(NULL, &cg->hw);
+	if (IS_ERR(clk))
+		kfree(cg);
+
+	return clk;
+}
diff --git a/drivers/clk/mediatek/clk-gate.h b/drivers/clk/mediatek/clk-gate.h
new file mode 100644
index 0000000..6b6780b
--- /dev/null
+++ b/drivers/clk/mediatek/clk-gate.h
@@ -0,0 +1,49 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ * Author: James Liao <jamesjj.liao@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __DRV_CLK_GATE_H
+#define __DRV_CLK_GATE_H
+
+#include <linux/regmap.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+
+struct mtk_clk_gate {
+	struct clk_hw	hw;
+	struct regmap	*regmap;
+	int		set_ofs;
+	int		clr_ofs;
+	int		sta_ofs;
+	u8		bit;
+};
+
+static inline struct mtk_clk_gate *to_clk_gate(struct clk_hw *hw)
+{
+	return container_of(hw, struct mtk_clk_gate, hw);
+}
+
+extern const struct clk_ops mtk_clk_gate_ops_setclr;
+extern const struct clk_ops mtk_clk_gate_ops_setclr_inv;
+
+struct clk *mtk_clk_register_gate(
+		const char *name,
+		const char *parent_name,
+		struct regmap *regmap,
+		int set_ofs,
+		int clr_ofs,
+		int sta_ofs,
+		u8 bit,
+		const struct clk_ops *ops);
+
+#endif /* __DRV_CLK_GATE_H */
diff --git a/drivers/clk/mediatek/clk-mt8135.c b/drivers/clk/mediatek/clk-mt8135.c
new file mode 100644
index 0000000..08b4b84
--- /dev/null
+++ b/drivers/clk/mediatek/clk-mt8135.c
@@ -0,0 +1,644 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ * Author: James Liao <jamesjj.liao@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+#include <linux/mfd/syscon.h>
+#include <dt-bindings/clock/mt8135-clk.h>
+
+#include "clk-mtk.h"
+#include "clk-gate.h"
+
+static DEFINE_SPINLOCK(mt8135_clk_lock);
+
+static const struct mtk_fixed_factor root_clk_alias[] __initconst = {
+	FACTOR(CLK_TOP_DSI0_LNTC_DSICLK, "dsi0_lntc_dsiclk", "clk_null", 1, 1),
+	FACTOR(CLK_TOP_HDMITX_CLKDIG_CTS, "hdmitx_clkdig_cts", "clk_null", 1, 1),
+	FACTOR(CLK_TOP_CLKPH_MCK, "clkph_mck", "clk_null", 1, 1),
+	FACTOR(CLK_TOP_CPUM_TCK_IN, "cpum_tck_in", "clk_null", 1, 1),
+};
+
+static const struct mtk_fixed_factor top_divs[] __initconst = {
+	FACTOR(CLK_TOP_MAINPLL_806M, "mainpll_806m", "mainpll", 1, 2),
+	FACTOR(CLK_TOP_MAINPLL_537P3M, "mainpll_537p3m", "mainpll", 1, 3),
+	FACTOR(CLK_TOP_MAINPLL_322P4M, "mainpll_322p4m", "mainpll", 1, 5),
+	FACTOR(CLK_TOP_MAINPLL_230P3M, "mainpll_230p3m", "mainpll", 1, 7),
+
+	FACTOR(CLK_TOP_UNIVPLL_624M, "univpll_624m", "univpll", 1, 2),
+	FACTOR(CLK_TOP_UNIVPLL_416M, "univpll_416m", "univpll", 1, 3),
+	FACTOR(CLK_TOP_UNIVPLL_249P6M, "univpll_249p6m", "univpll", 1, 5),
+	FACTOR(CLK_TOP_UNIVPLL_178P3M, "univpll_178p3m", "univpll", 1, 7),
+	FACTOR(CLK_TOP_UNIVPLL_48M, "univpll_48m", "univpll", 1, 26),
+
+	FACTOR(CLK_TOP_MMPLL_D2, "mmpll_d2", "mmpll", 1, 2),
+	FACTOR(CLK_TOP_MMPLL_D3, "mmpll_d3", "mmpll", 1, 3),
+	FACTOR(CLK_TOP_MMPLL_D5, "mmpll_d5", "mmpll", 1, 5),
+	FACTOR(CLK_TOP_MMPLL_D7, "mmpll_d7", "mmpll", 1, 7),
+	FACTOR(CLK_TOP_MMPLL_D4, "mmpll_d4", "mmpll_d2", 1, 2),
+	FACTOR(CLK_TOP_MMPLL_D6, "mmpll_d6", "mmpll_d3", 1, 2),
+
+	FACTOR(CLK_TOP_SYSPLL_D2, "syspll_d2", "mainpll_806m", 1, 1),
+	FACTOR(CLK_TOP_SYSPLL_D4, "syspll_d4", "mainpll_806m", 1, 2),
+	FACTOR(CLK_TOP_SYSPLL_D6, "syspll_d6", "mainpll_806m", 1, 3),
+	FACTOR(CLK_TOP_SYSPLL_D8, "syspll_d8", "mainpll_806m", 1, 4),
+	FACTOR(CLK_TOP_SYSPLL_D10, "syspll_d10", "mainpll_806m", 1, 5),
+	FACTOR(CLK_TOP_SYSPLL_D12, "syspll_d12", "mainpll_806m", 1, 6),
+	FACTOR(CLK_TOP_SYSPLL_D16, "syspll_d16", "mainpll_806m", 1, 8),
+	FACTOR(CLK_TOP_SYSPLL_D24, "syspll_d24", "mainpll_806m", 1, 12),
+
+	FACTOR(CLK_TOP_SYSPLL_D3, "syspll_d3", "mainpll_537p3m", 1, 1),
+
+	FACTOR(CLK_TOP_SYSPLL_D2P5, "syspll_d2p5", "mainpll_322p4m", 2, 1),
+	FACTOR(CLK_TOP_SYSPLL_D5, "syspll_d5", "mainpll_322p4m", 1, 1),
+
+	FACTOR(CLK_TOP_SYSPLL_D3P5, "syspll_d3p5", "mainpll_230p3m", 2, 1),
+
+	FACTOR(CLK_TOP_UNIVPLL1_D2, "univpll1_d2", "univpll_624m", 1, 2),
+	FACTOR(CLK_TOP_UNIVPLL1_D4, "univpll1_d4", "univpll_624m", 1, 4),
+	FACTOR(CLK_TOP_UNIVPLL1_D6, "univpll1_d6", "univpll_624m", 1, 6),
+	FACTOR(CLK_TOP_UNIVPLL1_D8, "univpll1_d8", "univpll_624m", 1, 8),
+	FACTOR(CLK_TOP_UNIVPLL1_D10, "univpll1_d10", "univpll_624m", 1, 10),
+
+	FACTOR(CLK_TOP_UNIVPLL2_D2, "univpll2_d2", "univpll_416m", 1, 2),
+	FACTOR(CLK_TOP_UNIVPLL2_D4, "univpll2_d4", "univpll_416m", 1, 4),
+	FACTOR(CLK_TOP_UNIVPLL2_D6, "univpll2_d6", "univpll_416m", 1, 6),
+	FACTOR(CLK_TOP_UNIVPLL2_D8, "univpll2_d8", "univpll_416m", 1, 8),
+
+	FACTOR(CLK_TOP_UNIVPLL_D3, "univpll_d3", "univpll_416m", 1, 1),
+	FACTOR(CLK_TOP_UNIVPLL_D5, "univpll_d5", "univpll_249p6m", 1, 1),
+	FACTOR(CLK_TOP_UNIVPLL_D7, "univpll_d7", "univpll_178p3m", 1, 1),
+	FACTOR(CLK_TOP_UNIVPLL_D10, "univpll_d10", "univpll_249p6m", 1, 2),
+	FACTOR(CLK_TOP_UNIVPLL_D26, "univpll_d26", "univpll_48m", 1, 1),
+
+	FACTOR(CLK_TOP_APLL, "apll_ck", "audpll", 1, 1),
+	FACTOR(CLK_TOP_APLL_D4, "apll_d4", "audpll", 1, 4),
+	FACTOR(CLK_TOP_APLL_D8, "apll_d8", "audpll", 1, 8),
+	FACTOR(CLK_TOP_APLL_D16, "apll_d16", "audpll", 1, 16),
+	FACTOR(CLK_TOP_APLL_D24, "apll_d24", "audpll", 1, 24),
+
+	FACTOR(CLK_TOP_LVDSPLL_D2, "lvdspll_d2", "lvdspll", 1, 2),
+	FACTOR(CLK_TOP_LVDSPLL_D4, "lvdspll_d4", "lvdspll", 1, 4),
+	FACTOR(CLK_TOP_LVDSPLL_D8, "lvdspll_d8", "lvdspll", 1, 8),
+
+	FACTOR(CLK_TOP_LVDSTX_CLKDIG_CT, "lvdstx_clkdig_cts", "lvdspll", 1, 1),
+	FACTOR(CLK_TOP_VPLL_DPIX, "vpll_dpix_ck", "lvdspll", 1, 1),
+
+	FACTOR(CLK_TOP_TVHDMI_H, "tvhdmi_h_ck", "tvdpll", 1, 1),
+
+	FACTOR(CLK_TOP_HDMITX_CLKDIG_D2, "hdmitx_clkdig_d2", "hdmitx_clkdig_cts", 1, 2),
+	FACTOR(CLK_TOP_HDMITX_CLKDIG_D3, "hdmitx_clkdig_d3", "hdmitx_clkdig_cts", 1, 3),
+
+	FACTOR(CLK_TOP_TVHDMI_D2, "tvhdmi_d2", "tvhdmi_h_ck", 1, 2),
+	FACTOR(CLK_TOP_TVHDMI_D4, "tvhdmi_d4", "tvhdmi_h_ck", 1, 4),
+
+	FACTOR(CLK_TOP_MEMPLL_MCK_D4, "mempll_mck_d4", "clkph_mck", 1, 4),
+};
+
+static const char * const axi_parents[] __initconst = {
+	"clk26m",
+	"syspll_d3",
+	"syspll_d4",
+	"syspll_d6",
+	"univpll_d5",
+	"univpll2_d2",
+	"syspll_d3p5"
+};
+
+static const char * const smi_parents[] __initconst = {
+	"clk26m",
+	"clkph_mck",
+	"syspll_d2p5",
+	"syspll_d3",
+	"syspll_d8",
+	"univpll_d5",
+	"univpll1_d2",
+	"univpll1_d6",
+	"mmpll_d3",
+	"mmpll_d4",
+	"mmpll_d5",
+	"mmpll_d6",
+	"mmpll_d7",
+	"vdecpll",
+	"lvdspll"
+};
+
+static const char * const mfg_parents[] __initconst = {
+	"clk26m",
+	"univpll1_d4",
+	"syspll_d2",
+	"syspll_d2p5",
+	"syspll_d3",
+	"univpll_d5",
+	"univpll1_d2",
+	"mmpll_d2",
+	"mmpll_d3",
+	"mmpll_d4",
+	"mmpll_d5",
+	"mmpll_d6",
+	"mmpll_d7"
+};
+
+static const char * const irda_parents[] __initconst = {
+	"clk26m",
+	"univpll2_d8",
+	"univpll1_d6"
+};
+
+static const char * const cam_parents[] __initconst = {
+	"clk26m",
+	"syspll_d3",
+	"syspll_d3p5",
+	"syspll_d4",
+	"univpll_d5",
+	"univpll2_d2",
+	"univpll_d7",
+	"univpll1_d4"
+};
+
+static const char * const aud_intbus_parents[] __initconst = {
+	"clk26m",
+	"syspll_d6",
+	"univpll_d10"
+};
+
+static const char * const jpg_parents[] __initconst = {
+	"clk26m",
+	"syspll_d5",
+	"syspll_d4",
+	"syspll_d3",
+	"univpll_d7",
+	"univpll2_d2",
+	"univpll_d5"
+};
+
+static const char * const disp_parents[] __initconst = {
+	"clk26m",
+	"syspll_d3p5",
+	"syspll_d3",
+	"univpll2_d2",
+	"univpll_d5",
+	"univpll1_d2",
+	"lvdspll",
+	"vdecpll"
+};
+
+static const char * const msdc30_parents[] __initconst = {
+	"clk26m",
+	"syspll_d6",
+	"syspll_d5",
+	"univpll1_d4",
+	"univpll2_d4",
+	"msdcpll"
+};
+
+static const char * const usb20_parents[] __initconst = {
+	"clk26m",
+	"univpll2_d6",
+	"univpll1_d10"
+};
+
+static const char * const venc_parents[] __initconst = {
+	"clk26m",
+	"syspll_d3",
+	"syspll_d8",
+	"univpll_d5",
+	"univpll1_d6",
+	"mmpll_d4",
+	"mmpll_d5",
+	"mmpll_d6"
+};
+
+static const char * const spi_parents[] __initconst = {
+	"clk26m",
+	"syspll_d6",
+	"syspll_d8",
+	"syspll_d10",
+	"univpll1_d6",
+	"univpll1_d8"
+};
+
+static const char * const uart_parents[] __initconst = {
+	"clk26m",
+	"univpll2_d8"
+};
+
+static const char * const mem_parents[] __initconst = {
+	"clk26m",
+	"clkph_mck"
+};
+
+static const char * const camtg_parents[] __initconst = {
+	"clk26m",
+	"univpll_d26",
+	"univpll1_d6",
+	"syspll_d16",
+	"syspll_d8"
+};
+
+static const char * const audio_parents[] __initconst = {
+	"clk26m",
+	"syspll_d24"
+};
+
+static const char * const fix_parents[] __initconst = {
+	"rtc32k",
+	"clk26m",
+	"univpll_d5",
+	"univpll_d7",
+	"univpll1_d2",
+	"univpll1_d4",
+	"univpll1_d6",
+	"univpll1_d8"
+};
+
+static const char * const vdec_parents[] __initconst = {
+	"clk26m",
+	"vdecpll",
+	"clkph_mck",
+	"syspll_d2p5",
+	"syspll_d3",
+	"syspll_d3p5",
+	"syspll_d4",
+	"syspll_d5",
+	"syspll_d6",
+	"syspll_d8",
+	"univpll1_d2",
+	"univpll2_d2",
+	"univpll_d7",
+	"univpll_d10",
+	"univpll2_d4",
+	"lvdspll"
+};
+
+static const char * const ddrphycfg_parents[] __initconst = {
+	"clk26m",
+	"axi_sel",
+	"syspll_d12"
+};
+
+static const char * const dpilvds_parents[] __initconst = {
+	"clk26m",
+	"lvdspll",
+	"lvdspll_d2",
+	"lvdspll_d4",
+	"lvdspll_d8"
+};
+
+static const char * const pmicspi_parents[] __initconst = {
+	"clk26m",
+	"univpll2_d6",
+	"syspll_d8",
+	"syspll_d10",
+	"univpll1_d10",
+	"mempll_mck_d4",
+	"univpll_d26",
+	"syspll_d24"
+};
+
+static const char * const smi_mfg_as_parents[] __initconst = {
+	"clk26m",
+	"smi_sel",
+	"mfg_sel",
+	"mem_sel"
+};
+
+static const char * const gcpu_parents[] __initconst = {
+	"clk26m",
+	"syspll_d4",
+	"univpll_d7",
+	"syspll_d5",
+	"syspll_d6"
+};
+
+static const char * const dpi1_parents[] __initconst = {
+	"clk26m",
+	"tvhdmi_h_ck",
+	"tvhdmi_d2",
+	"tvhdmi_d4"
+};
+
+static const char * const cci_parents[] __initconst = {
+	"clk26m",
+	"mainpll_537p3m",
+	"univpll_d3",
+	"syspll_d2p5",
+	"syspll_d3",
+	"syspll_d5"
+};
+
+static const char * const apll_parents[] __initconst = {
+	"clk26m",
+	"apll_ck",
+	"apll_d4",
+	"apll_d8",
+	"apll_d16",
+	"apll_d24"
+};
+
+static const char * const hdmipll_parents[] __initconst = {
+	"clk26m",
+	"hdmitx_clkdig_cts",
+	"hdmitx_clkdig_d2",
+	"hdmitx_clkdig_d3"
+};
+
+static const struct mtk_composite top_muxes[] __initconst = {
+	/* CLK_CFG_0 */
+	MUX_GATE(CLK_TOP_AXI_SEL, "axi_sel", axi_parents,
+		0x0140, 0, 3, INVALID_MUX_GATE_BIT),
+	MUX_GATE(CLK_TOP_SMI_SEL, "smi_sel", smi_parents, 0x0140, 8, 4, 15),
+	MUX_GATE(CLK_TOP_MFG_SEL, "mfg_sel", mfg_parents, 0x0140, 16, 4, 23),
+	MUX_GATE(CLK_TOP_IRDA_SEL, "irda_sel", irda_parents, 0x0140, 24, 2, 31),
+	/* CLK_CFG_1 */
+	MUX_GATE(CLK_TOP_CAM_SEL, "cam_sel", cam_parents, 0x0144, 0, 3, 7),
+	MUX_GATE(CLK_TOP_AUD_INTBUS_SEL, "aud_intbus_sel", aud_intbus_parents,
+		0x0144, 8, 2, 15),
+	MUX_GATE(CLK_TOP_JPG_SEL, "jpg_sel", jpg_parents, 0x0144, 16, 3, 23),
+	MUX_GATE(CLK_TOP_DISP_SEL, "disp_sel", disp_parents, 0x0144, 24, 3, 31),
+	/* CLK_CFG_2 */
+	MUX_GATE(CLK_TOP_MSDC30_1_SEL, "msdc30_1_sel", msdc30_parents, 0x0148, 0, 3, 7),
+	MUX_GATE(CLK_TOP_MSDC30_2_SEL, "msdc30_2_sel", msdc30_parents, 0x0148, 8, 3, 15),
+	MUX_GATE(CLK_TOP_MSDC30_3_SEL, "msdc30_3_sel", msdc30_parents, 0x0148, 16, 3, 23),
+	MUX_GATE(CLK_TOP_MSDC30_4_SEL, "msdc30_4_sel", msdc30_parents, 0x0148, 24, 3, 31),
+	/* CLK_CFG_3 */
+	MUX_GATE(CLK_TOP_USB20_SEL, "usb20_sel", usb20_parents, 0x014c, 0, 2, 7),
+	/* CLK_CFG_4 */
+	MUX_GATE(CLK_TOP_VENC_SEL, "venc_sel", venc_parents, 0x0150, 8, 3, 15),
+	MUX_GATE(CLK_TOP_SPI_SEL, "spi_sel", spi_parents, 0x0150, 16, 3, 23),
+	MUX_GATE(CLK_TOP_UART_SEL, "uart_sel", uart_parents, 0x0150, 24, 2, 31),
+	/* CLK_CFG_6 */
+	MUX_GATE(CLK_TOP_MEM_SEL, "mem_sel", mem_parents, 0x0158, 0, 2, 7),
+	MUX_GATE(CLK_TOP_CAMTG_SEL, "camtg_sel", camtg_parents, 0x0158, 8, 3, 15),
+	MUX_GATE(CLK_TOP_AUDIO_SEL, "audio_sel", audio_parents, 0x0158, 24, 2, 31),
+	/* CLK_CFG_7 */
+	MUX_GATE(CLK_TOP_FIX_SEL, "fix_sel", fix_parents, 0x015c, 0, 3, 7),
+	MUX_GATE(CLK_TOP_VDEC_SEL, "vdec_sel", vdec_parents, 0x015c, 8, 4, 15),
+	MUX_GATE(CLK_TOP_DDRPHYCFG_SEL, "ddrphycfg_sel", ddrphycfg_parents,
+		0x015c, 16, 2, 23),
+	MUX_GATE(CLK_TOP_DPILVDS_SEL, "dpilvds_sel", dpilvds_parents, 0x015c, 24, 3, 31),
+	/* CLK_CFG_8 */
+	MUX_GATE(CLK_TOP_PMICSPI_SEL, "pmicspi_sel", pmicspi_parents, 0x0164, 0, 3, 7),
+	MUX_GATE(CLK_TOP_MSDC30_0_SEL, "msdc30_0_sel", msdc30_parents, 0x0164, 8, 3, 15),
+	MUX_GATE(CLK_TOP_SMI_MFG_AS_SEL, "smi_mfg_as_sel", smi_mfg_as_parents,
+		0x0164, 16, 2, 23),
+	MUX_GATE(CLK_TOP_GCPU_SEL, "gcpu_sel", gcpu_parents, 0x0164, 24, 3, 31),
+	/* CLK_CFG_9 */
+	MUX_GATE(CLK_TOP_DPI1_SEL, "dpi1_sel", dpi1_parents, 0x0168, 0, 2, 7),
+	MUX_GATE(CLK_TOP_CCI_SEL, "cci_sel", cci_parents, 0x0168, 8, 3, 15),
+	MUX_GATE(CLK_TOP_APLL_SEL, "apll_sel", apll_parents, 0x0168, 16, 3, 23),
+	MUX_GATE(CLK_TOP_HDMIPLL_SEL, "hdmipll_sel", hdmipll_parents, 0x0168, 24, 2, 31),
+};
+
+static const struct mtk_gate_regs infra_cg_regs = {
+	.set_ofs = 0x0040,
+	.clr_ofs = 0x0044,
+	.sta_ofs = 0x0048,
+};
+
+#define GATE_ICG(_id, _name, _parent, _shift) {	\
+		.id = _id,					\
+		.name = _name,					\
+		.parent_name = _parent,				\
+		.regs = &infra_cg_regs,				\
+		.shift = _shift,				\
+		.ops = &mtk_clk_gate_ops_setclr,		\
+	}
+
+static const struct mtk_gate infra_clks[] __initconst = {
+	GATE_ICG(CLK_INFRA_PMIC_WRAP, "pmic_wrap_ck", "axi_sel", 23),
+	GATE_ICG(CLK_INFRA_PMICSPI, "pmicspi_ck", "pmicspi_sel", 22),
+	GATE_ICG(CLK_INFRA_CCIF1_AP_CTRL, "ccif1_ap_ctrl", "axi_sel", 21),
+	GATE_ICG(CLK_INFRA_CCIF0_AP_CTRL, "ccif0_ap_ctrl", "axi_sel", 20),
+	GATE_ICG(CLK_INFRA_KP, "kp_ck", "axi_sel", 16),
+	GATE_ICG(CLK_INFRA_CPUM, "cpum_ck", "cpum_tck_in", 15),
+	GATE_ICG(CLK_INFRA_M4U, "m4u_ck", "mem_sel", 8),
+	GATE_ICG(CLK_INFRA_MFGAXI, "mfgaxi_ck", "axi_sel", 7),
+	GATE_ICG(CLK_INFRA_DEVAPC, "devapc_ck", "axi_sel", 6),
+	GATE_ICG(CLK_INFRA_AUDIO, "audio_ck", "aud_intbus_sel", 5),
+	GATE_ICG(CLK_INFRA_MFG_BUS, "mfg_bus_ck", "axi_sel", 2),
+	GATE_ICG(CLK_INFRA_SMI, "smi_ck", "smi_sel", 1),
+	GATE_ICG(CLK_INFRA_DBGCLK, "dbgclk_ck", "axi_sel", 0),
+};
+
+static const struct mtk_gate_regs peri0_cg_regs = {
+	.set_ofs = 0x0008,
+	.clr_ofs = 0x0010,
+	.sta_ofs = 0x0018,
+};
+
+static const struct mtk_gate_regs peri1_cg_regs = {
+	.set_ofs = 0x000c,
+	.clr_ofs = 0x0014,
+	.sta_ofs = 0x001c,
+};
+
+#define GATE_PERI0(_id, _name, _parent, _shift) {	\
+		.id = _id,					\
+		.name = _name,					\
+		.parent_name = _parent,				\
+		.regs = &peri0_cg_regs,				\
+		.shift = _shift,				\
+		.ops = &mtk_clk_gate_ops_setclr,		\
+	}
+
+#define GATE_PERI1(_id, _name, _parent, _shift) {	\
+		.id = _id,					\
+		.name = _name,					\
+		.parent_name = _parent,				\
+		.regs = &peri1_cg_regs,				\
+		.shift = _shift,				\
+		.ops = &mtk_clk_gate_ops_setclr,		\
+	}
+
+static const struct mtk_gate peri_gates[] __initconst = {
+	/* PERI0 */
+	GATE_PERI0(CLK_PERI_I2C5, "i2c5_ck", "axi_sel", 31),
+	GATE_PERI0(CLK_PERI_I2C4, "i2c4_ck", "axi_sel", 30),
+	GATE_PERI0(CLK_PERI_I2C3, "i2c3_ck", "axi_sel", 29),
+	GATE_PERI0(CLK_PERI_I2C2, "i2c2_ck", "axi_sel", 28),
+	GATE_PERI0(CLK_PERI_I2C1, "i2c1_ck", "axi_sel", 27),
+	GATE_PERI0(CLK_PERI_I2C0, "i2c0_ck", "axi_sel", 26),
+	GATE_PERI0(CLK_PERI_UART3, "uart3_ck", "axi_sel", 25),
+	GATE_PERI0(CLK_PERI_UART2, "uart2_ck", "axi_sel", 24),
+	GATE_PERI0(CLK_PERI_UART1, "uart1_ck", "axi_sel", 23),
+	GATE_PERI0(CLK_PERI_UART0, "uart0_ck", "axi_sel", 22),
+	GATE_PERI0(CLK_PERI_IRDA, "irda_ck", "irda_sel", 21),
+	GATE_PERI0(CLK_PERI_NLI, "nli_ck", "axi_sel", 20),
+	GATE_PERI0(CLK_PERI_MD_HIF, "md_hif_ck", "axi_sel", 19),
+	GATE_PERI0(CLK_PERI_AP_HIF, "ap_hif_ck", "axi_sel", 18),
+	GATE_PERI0(CLK_PERI_MSDC30_3, "msdc30_3_ck", "msdc30_4_sel", 17),
+	GATE_PERI0(CLK_PERI_MSDC30_2, "msdc30_2_ck", "msdc30_3_sel", 16),
+	GATE_PERI0(CLK_PERI_MSDC30_1, "msdc30_1_ck", "msdc30_2_sel", 15),
+	GATE_PERI0(CLK_PERI_MSDC20_2, "msdc20_2_ck", "msdc30_1_sel", 14),
+	GATE_PERI0(CLK_PERI_MSDC20_1, "msdc20_1_ck", "msdc30_0_sel", 13),
+	GATE_PERI0(CLK_PERI_AP_DMA, "ap_dma_ck", "axi_sel", 12),
+	GATE_PERI0(CLK_PERI_USB1, "usb1_ck", "usb20_sel", 11),
+	GATE_PERI0(CLK_PERI_USB0, "usb0_ck", "usb20_sel", 10),
+	GATE_PERI0(CLK_PERI_PWM, "pwm_ck", "axi_sel", 9),
+	GATE_PERI0(CLK_PERI_PWM7, "pwm7_ck", "axi_sel", 8),
+	GATE_PERI0(CLK_PERI_PWM6, "pwm6_ck", "axi_sel", 7),
+	GATE_PERI0(CLK_PERI_PWM5, "pwm5_ck", "axi_sel", 6),
+	GATE_PERI0(CLK_PERI_PWM4, "pwm4_ck", "axi_sel", 5),
+	GATE_PERI0(CLK_PERI_PWM3, "pwm3_ck", "axi_sel", 4),
+	GATE_PERI0(CLK_PERI_PWM2, "pwm2_ck", "axi_sel", 3),
+	GATE_PERI0(CLK_PERI_PWM1, "pwm1_ck", "axi_sel", 2),
+	GATE_PERI0(CLK_PERI_THERM, "therm_ck", "axi_sel", 1),
+	GATE_PERI0(CLK_PERI_NFI, "nfi_ck", "axi_sel", 0),
+	/* PERI1 */
+	GATE_PERI1(CLK_PERI_USBSLV, "usbslv_ck", "axi_sel", 8),
+	GATE_PERI1(CLK_PERI_USB1_MCU, "usb1_mcu_ck", "axi_sel", 7),
+	GATE_PERI1(CLK_PERI_USB0_MCU, "usb0_mcu_ck", "axi_sel", 6),
+	GATE_PERI1(CLK_PERI_GCPU, "gcpu_ck", "gcpu_sel", 5),
+	GATE_PERI1(CLK_PERI_FHCTL, "fhctl_ck", "clk26m", 4),
+	GATE_PERI1(CLK_PERI_SPI1, "spi1_ck", "spi_sel", 3),
+	GATE_PERI1(CLK_PERI_AUXADC, "auxadc_ck", "clk26m", 2),
+	GATE_PERI1(CLK_PERI_PERI_PWRAP, "peri_pwrap_ck", "axi_sel", 1),
+	GATE_PERI1(CLK_PERI_I2C6, "i2c6_ck", "axi_sel", 0),
+};
+
+static const char * const uart_ck_sel_parents[] __initconst = {
+	"clk26m",
+	"uart_sel",
+};
+
+static const struct mtk_composite peri_clks[] __initconst = {
+	MUX(CLK_PERI_UART0_SEL, "uart0_ck_sel", uart_ck_sel_parents, 0x40c, 0, 1),
+	MUX(CLK_PERI_UART1_SEL, "uart1_ck_sel", uart_ck_sel_parents, 0x40c, 1, 1),
+	MUX(CLK_PERI_UART2_SEL, "uart2_ck_sel", uart_ck_sel_parents, 0x40c, 2, 1),
+	MUX(CLK_PERI_UART3_SEL, "uart3_ck_sel", uart_ck_sel_parents, 0x40c, 3, 1),
+};
+
+static void __init mtk_topckgen_init(struct device_node *node)
+{
+	struct clk_onecell_data *clk_data;
+	void __iomem *base;
+	int r;
+
+	base = of_iomap(node, 0);
+	if (!base) {
+		pr_err("%s(): ioremap failed\n", __func__);
+		return;
+	}
+
+	clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK);
+
+	mtk_clk_register_factors(root_clk_alias, ARRAY_SIZE(root_clk_alias), clk_data);
+	mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), clk_data);
+	mtk_clk_register_composites(top_muxes, ARRAY_SIZE(top_muxes), base,
+			&mt8135_clk_lock, clk_data);
+
+	clk_prepare_enable(clk_data->clks[CLK_TOP_CCI_SEL]);
+
+	r = of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
+	if (r)
+		pr_err("%s(): could not register clock provider: %d\n",
+			__func__, r);
+}
+CLK_OF_DECLARE(mtk_topckgen, "mediatek,mt8135-topckgen", mtk_topckgen_init);
+
+static void __init mtk_infrasys_init(struct device_node *node)
+{
+	struct clk_onecell_data *clk_data;
+	int r;
+
+	clk_data = mtk_alloc_clk_data(CLK_INFRA_NR_CLK);
+
+	mtk_clk_register_gates(node, infra_clks, ARRAY_SIZE(infra_clks),
+						clk_data);
+
+	clk_prepare_enable(clk_data->clks[CLK_INFRA_M4U]);
+
+	r = of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
+	if (r)
+		pr_err("%s(): could not register clock provider: %d\n",
+			__func__, r);
+
+	mtk_register_reset_controller(node, 2, 0x30);
+}
+CLK_OF_DECLARE(mtk_infrasys, "mediatek,mt8135-infracfg", mtk_infrasys_init);
+
+static void __init mtk_pericfg_init(struct device_node *node)
+{
+	struct clk_onecell_data *clk_data;
+	int r;
+	void __iomem *base;
+
+	base = of_iomap(node, 0);
+	if (!base) {
+		pr_err("%s(): ioremap failed\n", __func__);
+		return;
+	}
+
+	clk_data = mtk_alloc_clk_data(CLK_PERI_NR_CLK);
+
+	mtk_clk_register_gates(node, peri_gates, ARRAY_SIZE(peri_gates),
+						clk_data);
+	mtk_clk_register_composites(peri_clks, ARRAY_SIZE(peri_clks), base,
+			&mt8135_clk_lock, clk_data);
+
+	r = of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
+	if (r)
+		pr_err("%s(): could not register clock provider: %d\n",
+			__func__, r);
+
+	mtk_register_reset_controller(node, 2, 0);
+}
+CLK_OF_DECLARE(mtk_pericfg, "mediatek,mt8135-pericfg", mtk_pericfg_init);
+
+#define MT8135_PLL_FMAX		(2000 * MHZ)
+#define CON0_MT8135_RST_BAR	BIT(27)
+
+#define PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, _pcw_shift) { \
+		.id = _id,						\
+		.name = _name,						\
+		.reg = _reg,						\
+		.pwr_reg = _pwr_reg,					\
+		.en_mask = _en_mask,					\
+		.flags = _flags,					\
+		.rst_bar_mask = CON0_MT8135_RST_BAR,			\
+		.fmax = MT8135_PLL_FMAX,				\
+		.pcwbits = _pcwbits,					\
+		.pd_reg = _pd_reg,					\
+		.pd_shift = _pd_shift,					\
+		.tuner_reg = _tuner_reg,				\
+		.pcw_reg = _pcw_reg,					\
+		.pcw_shift = _pcw_shift,				\
+	}
+
+static const struct mtk_pll_data plls[] = {
+	PLL(CLK_APMIXED_ARMPLL1, "armpll1", 0x200, 0x218, 0x80000001, 0, 21, 0x204, 24, 0x0, 0x204, 0),
+	PLL(CLK_APMIXED_ARMPLL2, "armpll2", 0x2cc, 0x2e4, 0x80000001, 0, 21, 0x2d0, 24, 0x0, 0x2d0, 0),
+	PLL(CLK_APMIXED_MAINPLL, "mainpll", 0x21c, 0x234, 0xf0000001, HAVE_RST_BAR, 21, 0x21c, 6, 0x0, 0x220, 0),
+	PLL(CLK_APMIXED_UNIVPLL, "univpll", 0x238, 0x250, 0xf3000001, HAVE_RST_BAR, 7, 0x238, 6, 0x0, 0x238, 9),
+	PLL(CLK_APMIXED_MMPLL, "mmpll", 0x254, 0x26c, 0xf0000001, HAVE_RST_BAR, 21, 0x254, 6, 0x0, 0x258, 0),
+	PLL(CLK_APMIXED_MSDCPLL, "msdcpll", 0x278, 0x290, 0x80000001, 0, 21, 0x278, 6, 0x0, 0x27c, 0),
+	PLL(CLK_APMIXED_TVDPLL, "tvdpll", 0x294, 0x2ac, 0x80000001, 0, 31, 0x294, 6, 0x0, 0x298, 0),
+	PLL(CLK_APMIXED_LVDSPLL, "lvdspll", 0x2b0, 0x2c8,	0x80000001, 0, 21, 0x2b0, 6, 0x0, 0x2b4, 0),
+	PLL(CLK_APMIXED_AUDPLL, "audpll", 0x2e8, 0x300, 0x80000001, 0, 31, 0x2e8, 6, 0x2f8, 0x2ec, 0),
+	PLL(CLK_APMIXED_VDECPLL, "vdecpll", 0x304, 0x31c,	0x80000001, 0, 21, 0x2b0, 6, 0x0, 0x308, 0),
+};
+
+static void __init mtk_apmixedsys_init(struct device_node *node)
+{
+	struct clk_onecell_data *clk_data;
+
+	clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK);
+	if (!clk_data)
+		return;
+
+	mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data);
+}
+CLK_OF_DECLARE(mtk_apmixedsys, "mediatek,mt8135-apmixedsys",
+		mtk_apmixedsys_init);
diff --git a/drivers/clk/mediatek/clk-mt8173.c b/drivers/clk/mediatek/clk-mt8173.c
new file mode 100644
index 0000000..4b9e04c
--- /dev/null
+++ b/drivers/clk/mediatek/clk-mt8173.c
@@ -0,0 +1,830 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ * Author: James Liao <jamesjj.liao@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+#include <linux/mfd/syscon.h>
+
+#include "clk-mtk.h"
+#include "clk-gate.h"
+
+#include <dt-bindings/clock/mt8173-clk.h>
+
+static DEFINE_SPINLOCK(mt8173_clk_lock);
+
+static const struct mtk_fixed_factor root_clk_alias[] __initconst = {
+	FACTOR(CLK_TOP_CLKPH_MCK_O, "clkph_mck_o", "clk_null", 1, 1),
+	FACTOR(CLK_TOP_DPI, "dpi_ck", "clk_null", 1, 1),
+	FACTOR(CLK_TOP_USB_SYSPLL_125M, "usb_syspll_125m", "clk_null", 1, 1),
+	FACTOR(CLK_TOP_HDMITX_DIG_CTS, "hdmitx_dig_cts", "clk_null", 1, 1),
+};
+
+static const struct mtk_fixed_factor top_divs[] __initconst = {
+	FACTOR(CLK_TOP_ARMCA7PLL_754M, "armca7pll_754m", "armca7pll", 1, 2),
+	FACTOR(CLK_TOP_ARMCA7PLL_502M, "armca7pll_502m", "armca7pll", 1, 3),
+
+	FACTOR(CLK_TOP_MAIN_H546M, "main_h546m", "mainpll", 1, 2),
+	FACTOR(CLK_TOP_MAIN_H364M, "main_h364m", "mainpll", 1, 3),
+	FACTOR(CLK_TOP_MAIN_H218P4M, "main_h218p4m", "mainpll", 1, 5),
+	FACTOR(CLK_TOP_MAIN_H156M, "main_h156m", "mainpll", 1, 7),
+
+	FACTOR(CLK_TOP_TVDPLL_445P5M, "tvdpll_445p5m", "tvdpll", 1, 4),
+	FACTOR(CLK_TOP_TVDPLL_594M, "tvdpll_594m", "tvdpll", 1, 3),
+
+	FACTOR(CLK_TOP_UNIV_624M, "univ_624m", "univpll", 1, 2),
+	FACTOR(CLK_TOP_UNIV_416M, "univ_416m", "univpll", 1, 3),
+	FACTOR(CLK_TOP_UNIV_249P6M, "univ_249p6m", "univpll", 1, 5),
+	FACTOR(CLK_TOP_UNIV_178P3M, "univ_178p3m", "univpll", 1, 7),
+	FACTOR(CLK_TOP_UNIV_48M, "univ_48m", "univpll", 1, 26),
+
+	FACTOR(CLK_TOP_CLKRTC_EXT, "clkrtc_ext", "clk32k", 1, 1),
+	FACTOR(CLK_TOP_CLKRTC_INT, "clkrtc_int", "clk26m", 1, 793),
+	FACTOR(CLK_TOP_FPC, "fpc_ck", "clk26m", 1, 1),
+
+	FACTOR(CLK_TOP_HDMITXPLL_D2, "hdmitxpll_d2", "hdmitx_dig_cts", 1, 2),
+	FACTOR(CLK_TOP_HDMITXPLL_D3, "hdmitxpll_d3", "hdmitx_dig_cts", 1, 3),
+
+	FACTOR(CLK_TOP_ARMCA7PLL_D2, "armca7pll_d2", "armca7pll_754m", 1, 1),
+	FACTOR(CLK_TOP_ARMCA7PLL_D3, "armca7pll_d3", "armca7pll_502m", 1, 1),
+
+	FACTOR(CLK_TOP_APLL1, "apll1_ck", "apll1", 1, 1),
+	FACTOR(CLK_TOP_APLL2, "apll2_ck", "apll2", 1, 1),
+
+	FACTOR(CLK_TOP_DMPLL, "dmpll_ck", "clkph_mck_o", 1, 1),
+	FACTOR(CLK_TOP_DMPLL_D2, "dmpll_d2", "clkph_mck_o", 1, 2),
+	FACTOR(CLK_TOP_DMPLL_D4, "dmpll_d4", "clkph_mck_o", 1, 4),
+	FACTOR(CLK_TOP_DMPLL_D8, "dmpll_d8", "clkph_mck_o", 1, 8),
+	FACTOR(CLK_TOP_DMPLL_D16, "dmpll_d16", "clkph_mck_o", 1, 16),
+
+	FACTOR(CLK_TOP_LVDSPLL_D2, "lvdspll_d2", "lvdspll", 1, 2),
+	FACTOR(CLK_TOP_LVDSPLL_D4, "lvdspll_d4", "lvdspll", 1, 4),
+	FACTOR(CLK_TOP_LVDSPLL_D8, "lvdspll_d8", "lvdspll", 1, 8),
+
+	FACTOR(CLK_TOP_MMPLL, "mmpll_ck", "mmpll", 1, 1),
+	FACTOR(CLK_TOP_MMPLL_D2, "mmpll_d2", "mmpll", 1, 2),
+
+	FACTOR(CLK_TOP_MSDCPLL, "msdcpll_ck", "msdcpll", 1, 1),
+	FACTOR(CLK_TOP_MSDCPLL_D2, "msdcpll_d2", "msdcpll", 1, 2),
+	FACTOR(CLK_TOP_MSDCPLL_D4, "msdcpll_d4", "msdcpll", 1, 4),
+	FACTOR(CLK_TOP_MSDCPLL2, "msdcpll2_ck", "msdcpll2", 1, 1),
+	FACTOR(CLK_TOP_MSDCPLL2_D2, "msdcpll2_d2", "msdcpll2", 1, 2),
+	FACTOR(CLK_TOP_MSDCPLL2_D4, "msdcpll2_d4", "msdcpll2", 1, 4),
+
+	FACTOR(CLK_TOP_SYSPLL_D2, "syspll_d2", "main_h546m", 1, 1),
+	FACTOR(CLK_TOP_SYSPLL1_D2, "syspll1_d2", "main_h546m", 1, 2),
+	FACTOR(CLK_TOP_SYSPLL1_D4, "syspll1_d4", "main_h546m", 1, 4),
+	FACTOR(CLK_TOP_SYSPLL1_D8, "syspll1_d8", "main_h546m", 1, 8),
+	FACTOR(CLK_TOP_SYSPLL1_D16, "syspll1_d16", "main_h546m", 1, 16),
+	FACTOR(CLK_TOP_SYSPLL_D3, "syspll_d3", "main_h364m", 1, 1),
+	FACTOR(CLK_TOP_SYSPLL2_D2, "syspll2_d2", "main_h364m", 1, 2),
+	FACTOR(CLK_TOP_SYSPLL2_D4, "syspll2_d4", "main_h364m", 1, 4),
+	FACTOR(CLK_TOP_SYSPLL_D5, "syspll_d5", "main_h218p4m", 1, 1),
+	FACTOR(CLK_TOP_SYSPLL3_D2, "syspll3_d2", "main_h218p4m", 1, 2),
+	FACTOR(CLK_TOP_SYSPLL3_D4, "syspll3_d4", "main_h218p4m", 1, 4),
+	FACTOR(CLK_TOP_SYSPLL_D7, "syspll_d7", "main_h156m", 1, 1),
+	FACTOR(CLK_TOP_SYSPLL4_D2, "syspll4_d2", "main_h156m", 1, 2),
+	FACTOR(CLK_TOP_SYSPLL4_D4, "syspll4_d4", "main_h156m", 1, 4),
+
+	FACTOR(CLK_TOP_TVDPLL, "tvdpll_ck", "tvdpll_594m", 1, 1),
+	FACTOR(CLK_TOP_TVDPLL_D2, "tvdpll_d2", "tvdpll_594m", 1, 2),
+	FACTOR(CLK_TOP_TVDPLL_D4, "tvdpll_d4", "tvdpll_594m", 1, 4),
+	FACTOR(CLK_TOP_TVDPLL_D8, "tvdpll_d8", "tvdpll_594m", 1, 8),
+	FACTOR(CLK_TOP_TVDPLL_D16, "tvdpll_d16", "tvdpll_594m", 1, 16),
+
+	FACTOR(CLK_TOP_UNIVPLL_D2, "univpll_d2", "univ_624m", 1, 1),
+	FACTOR(CLK_TOP_UNIVPLL1_D2, "univpll1_d2", "univ_624m", 1, 2),
+	FACTOR(CLK_TOP_UNIVPLL1_D4, "univpll1_d4", "univ_624m", 1, 4),
+	FACTOR(CLK_TOP_UNIVPLL1_D8, "univpll1_d8", "univ_624m", 1, 8),
+	FACTOR(CLK_TOP_UNIVPLL_D3, "univpll_d3", "univ_416m", 1, 1),
+	FACTOR(CLK_TOP_UNIVPLL2_D2, "univpll2_d2", "univ_416m", 1, 2),
+	FACTOR(CLK_TOP_UNIVPLL2_D4, "univpll2_d4", "univ_416m", 1, 4),
+	FACTOR(CLK_TOP_UNIVPLL2_D8, "univpll2_d8", "univ_416m", 1, 8),
+	FACTOR(CLK_TOP_UNIVPLL_D5, "univpll_d5", "univ_249p6m", 1, 1),
+	FACTOR(CLK_TOP_UNIVPLL3_D2, "univpll3_d2", "univ_249p6m", 1, 2),
+	FACTOR(CLK_TOP_UNIVPLL3_D4, "univpll3_d4", "univ_249p6m", 1, 4),
+	FACTOR(CLK_TOP_UNIVPLL3_D8, "univpll3_d8", "univ_249p6m", 1, 8),
+	FACTOR(CLK_TOP_UNIVPLL_D7, "univpll_d7", "univ_178p3m", 1, 1),
+	FACTOR(CLK_TOP_UNIVPLL_D26, "univpll_d26", "univ_48m", 1, 1),
+	FACTOR(CLK_TOP_UNIVPLL_D52, "univpll_d52", "univ_48m", 1, 2),
+
+	FACTOR(CLK_TOP_VCODECPLL, "vcodecpll_ck", "vcodecpll", 1, 3),
+	FACTOR(CLK_TOP_VCODECPLL_370P5, "vcodecpll_370p5", "vcodecpll", 1, 4),
+
+	FACTOR(CLK_TOP_VENCPLL, "vencpll_ck", "vencpll", 1, 1),
+	FACTOR(CLK_TOP_VENCPLL_D2, "vencpll_d2", "vencpll", 1, 2),
+	FACTOR(CLK_TOP_VENCPLL_D4, "vencpll_d4", "vencpll", 1, 4),
+};
+
+static const char * const axi_parents[] __initconst = {
+	"clk26m",
+	"syspll1_d2",
+	"syspll_d5",
+	"syspll1_d4",
+	"univpll_d5",
+	"univpll2_d2",
+	"dmpll_d2",
+	"dmpll_d4"
+};
+
+static const char * const mem_parents[] __initconst = {
+	"clk26m",
+	"dmpll_ck"
+};
+
+static const char * const ddrphycfg_parents[] __initconst = {
+	"clk26m",
+	"syspll1_d8"
+};
+
+static const char * const mm_parents[] __initconst = {
+	"clk26m",
+	"vencpll_d2",
+	"main_h364m",
+	"syspll1_d2",
+	"syspll_d5",
+	"syspll1_d4",
+	"univpll1_d2",
+	"univpll2_d2",
+	"dmpll_d2"
+};
+
+static const char * const pwm_parents[] __initconst = {
+	"clk26m",
+	"univpll2_d4",
+	"univpll3_d2",
+	"univpll1_d4"
+};
+
+static const char * const vdec_parents[] __initconst = {
+	"clk26m",
+	"vcodecpll_ck",
+	"tvdpll_445p5m",
+	"univpll_d3",
+	"vencpll_d2",
+	"syspll_d3",
+	"univpll1_d2",
+	"mmpll_d2",
+	"dmpll_d2",
+	"dmpll_d4"
+};
+
+static const char * const venc_parents[] __initconst = {
+	"clk26m",
+	"vcodecpll_ck",
+	"tvdpll_445p5m",
+	"univpll_d3",
+	"vencpll_d2",
+	"syspll_d3",
+	"univpll1_d2",
+	"univpll2_d2",
+	"dmpll_d2",
+	"dmpll_d4"
+};
+
+static const char * const mfg_parents[] __initconst = {
+	"clk26m",
+	"mmpll_ck",
+	"dmpll_ck",
+	"clk26m",
+	"clk26m",
+	"clk26m",
+	"clk26m",
+	"clk26m",
+	"clk26m",
+	"syspll_d3",
+	"syspll1_d2",
+	"syspll_d5",
+	"univpll_d3",
+	"univpll1_d2",
+	"univpll_d5",
+	"univpll2_d2"
+};
+
+static const char * const camtg_parents[] __initconst = {
+	"clk26m",
+	"univpll_d26",
+	"univpll2_d2",
+	"syspll3_d2",
+	"syspll3_d4",
+	"univpll1_d4"
+};
+
+static const char * const uart_parents[] __initconst = {
+	"clk26m",
+	"univpll2_d8"
+};
+
+static const char * const spi_parents[] __initconst = {
+	"clk26m",
+	"syspll3_d2",
+	"syspll1_d4",
+	"syspll4_d2",
+	"univpll3_d2",
+	"univpll2_d4",
+	"univpll1_d8"
+};
+
+static const char * const usb20_parents[] __initconst = {
+	"clk26m",
+	"univpll1_d8",
+	"univpll3_d4"
+};
+
+static const char * const usb30_parents[] __initconst = {
+	"clk26m",
+	"univpll3_d2",
+	"usb_syspll_125m",
+	"univpll2_d4"
+};
+
+static const char * const msdc50_0_h_parents[] __initconst = {
+	"clk26m",
+	"syspll1_d2",
+	"syspll2_d2",
+	"syspll4_d2",
+	"univpll_d5",
+	"univpll1_d4"
+};
+
+static const char * const msdc50_0_parents[] __initconst = {
+	"clk26m",
+	"msdcpll_ck",
+	"msdcpll_d2",
+	"univpll1_d4",
+	"syspll2_d2",
+	"syspll_d7",
+	"msdcpll_d4",
+	"vencpll_d4",
+	"tvdpll_ck",
+	"univpll_d2",
+	"univpll1_d2",
+	"mmpll_ck",
+	"msdcpll2_ck",
+	"msdcpll2_d2",
+	"msdcpll2_d4"
+};
+
+static const char * const msdc30_1_parents[] __initconst = {
+	"clk26m",
+	"univpll2_d2",
+	"msdcpll_d4",
+	"univpll1_d4",
+	"syspll2_d2",
+	"syspll_d7",
+	"univpll_d7",
+	"vencpll_d4"
+};
+
+static const char * const msdc30_2_parents[] __initconst = {
+	"clk26m",
+	"univpll2_d2",
+	"msdcpll_d4",
+	"univpll1_d4",
+	"syspll2_d2",
+	"syspll_d7",
+	"univpll_d7",
+	"vencpll_d2"
+};
+
+static const char * const msdc30_3_parents[] __initconst = {
+	"clk26m",
+	"msdcpll2_ck",
+	"msdcpll2_d2",
+	"univpll2_d2",
+	"msdcpll2_d4",
+	"msdcpll_d4",
+	"univpll1_d4",
+	"syspll2_d2",
+	"syspll_d7",
+	"univpll_d7",
+	"vencpll_d4",
+	"msdcpll_ck",
+	"msdcpll_d2",
+	"msdcpll_d4"
+};
+
+static const char * const audio_parents[] __initconst = {
+	"clk26m",
+	"syspll3_d4",
+	"syspll4_d4",
+	"syspll1_d16"
+};
+
+static const char * const aud_intbus_parents[] __initconst = {
+	"clk26m",
+	"syspll1_d4",
+	"syspll4_d2",
+	"univpll3_d2",
+	"univpll2_d8",
+	"dmpll_d4",
+	"dmpll_d8"
+};
+
+static const char * const pmicspi_parents[] __initconst = {
+	"clk26m",
+	"syspll1_d8",
+	"syspll3_d4",
+	"syspll1_d16",
+	"univpll3_d4",
+	"univpll_d26",
+	"dmpll_d8",
+	"dmpll_d16"
+};
+
+static const char * const scp_parents[] __initconst = {
+	"clk26m",
+	"syspll1_d2",
+	"univpll_d5",
+	"syspll_d5",
+	"dmpll_d2",
+	"dmpll_d4"
+};
+
+static const char * const atb_parents[] __initconst = {
+	"clk26m",
+	"syspll1_d2",
+	"univpll_d5",
+	"dmpll_d2"
+};
+
+static const char * const venc_lt_parents[] __initconst = {
+	"clk26m",
+	"univpll_d3",
+	"vcodecpll_ck",
+	"tvdpll_445p5m",
+	"vencpll_d2",
+	"syspll_d3",
+	"univpll1_d2",
+	"univpll2_d2",
+	"syspll1_d2",
+	"univpll_d5",
+	"vcodecpll_370p5",
+	"dmpll_ck"
+};
+
+static const char * const dpi0_parents[] __initconst = {
+	"clk26m",
+	"tvdpll_d2",
+	"tvdpll_d4",
+	"clk26m",
+	"clk26m",
+	"tvdpll_d8",
+	"tvdpll_d16"
+};
+
+static const char * const irda_parents[] __initconst = {
+	"clk26m",
+	"univpll2_d4",
+	"syspll2_d4"
+};
+
+static const char * const cci400_parents[] __initconst = {
+	"clk26m",
+	"vencpll_ck",
+	"armca7pll_754m",
+	"armca7pll_502m",
+	"univpll_d2",
+	"syspll_d2",
+	"msdcpll_ck",
+	"dmpll_ck"
+};
+
+static const char * const aud_1_parents[] __initconst = {
+	"clk26m",
+	"apll1_ck",
+	"univpll2_d4",
+	"univpll2_d8"
+};
+
+static const char * const aud_2_parents[] __initconst = {
+	"clk26m",
+	"apll2_ck",
+	"univpll2_d4",
+	"univpll2_d8"
+};
+
+static const char * const mem_mfg_in_parents[] __initconst = {
+	"clk26m",
+	"mmpll_ck",
+	"dmpll_ck",
+	"clk26m"
+};
+
+static const char * const axi_mfg_in_parents[] __initconst = {
+	"clk26m",
+	"axi_sel",
+	"dmpll_d2"
+};
+
+static const char * const scam_parents[] __initconst = {
+	"clk26m",
+	"syspll3_d2",
+	"univpll2_d4",
+	"dmpll_d4"
+};
+
+static const char * const spinfi_ifr_parents[] __initconst = {
+	"clk26m",
+	"univpll2_d8",
+	"univpll3_d4",
+	"syspll4_d2",
+	"univpll2_d4",
+	"univpll3_d2",
+	"syspll1_d4",
+	"univpll1_d4"
+};
+
+static const char * const hdmi_parents[] __initconst = {
+	"clk26m",
+	"hdmitx_dig_cts",
+	"hdmitxpll_d2",
+	"hdmitxpll_d3"
+};
+
+static const char * const dpilvds_parents[] __initconst = {
+	"clk26m",
+	"lvdspll",
+	"lvdspll_d2",
+	"lvdspll_d4",
+	"lvdspll_d8",
+	"fpc_ck"
+};
+
+static const char * const msdc50_2_h_parents[] __initconst = {
+	"clk26m",
+	"syspll1_d2",
+	"syspll2_d2",
+	"syspll4_d2",
+	"univpll_d5",
+	"univpll1_d4"
+};
+
+static const char * const hdcp_parents[] __initconst = {
+	"clk26m",
+	"syspll4_d2",
+	"syspll3_d4",
+	"univpll2_d4"
+};
+
+static const char * const hdcp_24m_parents[] __initconst = {
+	"clk26m",
+	"univpll_d26",
+	"univpll_d52",
+	"univpll2_d8"
+};
+
+static const char * const rtc_parents[] __initconst = {
+	"clkrtc_int",
+	"clkrtc_ext",
+	"clk26m",
+	"univpll3_d8"
+};
+
+static const char * const i2s0_m_ck_parents[] __initconst = {
+	"apll1_div1",
+	"apll2_div1"
+};
+
+static const char * const i2s1_m_ck_parents[] __initconst = {
+	"apll1_div2",
+	"apll2_div2"
+};
+
+static const char * const i2s2_m_ck_parents[] __initconst = {
+	"apll1_div3",
+	"apll2_div3"
+};
+
+static const char * const i2s3_m_ck_parents[] __initconst = {
+	"apll1_div4",
+	"apll2_div4"
+};
+
+static const char * const i2s3_b_ck_parents[] __initconst = {
+	"apll1_div5",
+	"apll2_div5"
+};
+
+static const struct mtk_composite top_muxes[] __initconst = {
+	/* CLK_CFG_0 */
+	MUX(CLK_TOP_AXI_SEL, "axi_sel", axi_parents, 0x0040, 0, 3),
+	MUX(CLK_TOP_MEM_SEL, "mem_sel", mem_parents, 0x0040, 8, 1),
+	MUX_GATE(CLK_TOP_DDRPHYCFG_SEL, "ddrphycfg_sel", ddrphycfg_parents, 0x0040, 16, 1, 23),
+	MUX_GATE(CLK_TOP_MM_SEL, "mm_sel", mm_parents, 0x0040, 24, 4, 31),
+	/* CLK_CFG_1 */
+	MUX_GATE(CLK_TOP_PWM_SEL, "pwm_sel", pwm_parents, 0x0050, 0, 2, 7),
+	MUX_GATE(CLK_TOP_VDEC_SEL, "vdec_sel", vdec_parents, 0x0050, 8, 4, 15),
+	MUX_GATE(CLK_TOP_VENC_SEL, "venc_sel", venc_parents, 0x0050, 16, 4, 23),
+	MUX_GATE(CLK_TOP_MFG_SEL, "mfg_sel", mfg_parents, 0x0050, 24, 4, 31),
+	/* CLK_CFG_2 */
+	MUX_GATE(CLK_TOP_CAMTG_SEL, "camtg_sel", camtg_parents, 0x0060, 0, 3, 7),
+	MUX_GATE(CLK_TOP_UART_SEL, "uart_sel", uart_parents, 0x0060, 8, 1, 15),
+	MUX_GATE(CLK_TOP_SPI_SEL, "spi_sel", spi_parents, 0x0060, 16, 3, 23),
+	MUX_GATE(CLK_TOP_USB20_SEL, "usb20_sel", usb20_parents, 0x0060, 24, 2, 31),
+	/* CLK_CFG_3 */
+	MUX_GATE(CLK_TOP_USB30_SEL, "usb30_sel", usb30_parents, 0x0070, 0, 2, 7),
+	MUX_GATE(CLK_TOP_MSDC50_0_H_SEL, "msdc50_0_h_sel", msdc50_0_h_parents, 0x0070, 8, 3, 15),
+	MUX_GATE(CLK_TOP_MSDC50_0_SEL, "msdc50_0_sel", msdc50_0_parents, 0x0070, 16, 4, 23),
+	MUX_GATE(CLK_TOP_MSDC30_1_SEL, "msdc30_1_sel", msdc30_1_parents, 0x0070, 24, 3, 31),
+	/* CLK_CFG_4 */
+	MUX_GATE(CLK_TOP_MSDC30_2_SEL, "msdc30_2_sel", msdc30_2_parents, 0x0080, 0, 3, 7),
+	MUX_GATE(CLK_TOP_MSDC30_3_SEL, "msdc30_3_sel", msdc30_3_parents, 0x0080, 8, 4, 15),
+	MUX_GATE(CLK_TOP_AUDIO_SEL, "audio_sel", audio_parents, 0x0080, 16, 2, 23),
+	MUX_GATE(CLK_TOP_AUD_INTBUS_SEL, "aud_intbus_sel", aud_intbus_parents, 0x0080, 24, 3, 31),
+	/* CLK_CFG_5 */
+	MUX_GATE(CLK_TOP_PMICSPI_SEL, "pmicspi_sel", pmicspi_parents, 0x0090, 0, 3, 7 /* 7:5 */),
+	MUX_GATE(CLK_TOP_SCP_SEL, "scp_sel", scp_parents, 0x0090, 8, 3, 15),
+	MUX_GATE(CLK_TOP_ATB_SEL, "atb_sel", atb_parents, 0x0090, 16, 2, 23),
+	MUX_GATE(CLK_TOP_VENC_LT_SEL, "venclt_sel", venc_lt_parents, 0x0090, 24, 4, 31),
+	/* CLK_CFG_6 */
+	MUX_GATE(CLK_TOP_DPI0_SEL, "dpi0_sel", dpi0_parents, 0x00a0, 0, 3, 7),
+	MUX_GATE(CLK_TOP_IRDA_SEL, "irda_sel", irda_parents, 0x00a0, 8, 2, 15),
+	MUX_GATE(CLK_TOP_CCI400_SEL, "cci400_sel", cci400_parents, 0x00a0, 16, 3, 23),
+	MUX_GATE(CLK_TOP_AUD_1_SEL, "aud_1_sel", aud_1_parents, 0x00a0, 24, 2, 31),
+	/* CLK_CFG_7 */
+	MUX_GATE(CLK_TOP_AUD_2_SEL, "aud_2_sel", aud_2_parents, 0x00b0, 0, 2, 7),
+	MUX_GATE(CLK_TOP_MEM_MFG_IN_SEL, "mem_mfg_in_sel", mem_mfg_in_parents, 0x00b0, 8, 2, 15),
+	MUX_GATE(CLK_TOP_AXI_MFG_IN_SEL, "axi_mfg_in_sel", axi_mfg_in_parents, 0x00b0, 16, 2, 23),
+	MUX_GATE(CLK_TOP_SCAM_SEL, "scam_sel", scam_parents, 0x00b0, 24, 2, 31),
+	/* CLK_CFG_12 */
+	MUX_GATE(CLK_TOP_SPINFI_IFR_SEL, "spinfi_ifr_sel", spinfi_ifr_parents, 0x00c0, 0, 3, 7),
+	MUX_GATE(CLK_TOP_HDMI_SEL, "hdmi_sel", hdmi_parents, 0x00c0, 8, 2, 15),
+	MUX_GATE(CLK_TOP_DPILVDS_SEL, "dpilvds_sel", dpilvds_parents, 0x00c0, 24, 3, 31),
+	/* CLK_CFG_13 */
+	MUX_GATE(CLK_TOP_MSDC50_2_H_SEL, "msdc50_2_h_sel", msdc50_2_h_parents, 0x00d0, 0, 3, 7),
+	MUX_GATE(CLK_TOP_HDCP_SEL, "hdcp_sel", hdcp_parents, 0x00d0, 8, 2, 15),
+	MUX_GATE(CLK_TOP_HDCP_24M_SEL, "hdcp_24m_sel", hdcp_24m_parents, 0x00d0, 16, 2, 23),
+	MUX(CLK_TOP_RTC_SEL, "rtc_sel", rtc_parents, 0x00d0, 24, 2),
+
+	DIV_GATE(CLK_TOP_APLL1_DIV0, "apll1_div0", "aud_1_sel", 0x12c, 8, 0x120, 4, 24),
+	DIV_GATE(CLK_TOP_APLL1_DIV1, "apll1_div1", "aud_1_sel", 0x12c, 9, 0x124, 8, 0),
+	DIV_GATE(CLK_TOP_APLL1_DIV2, "apll1_div2", "aud_1_sel", 0x12c, 10, 0x124, 8, 8),
+	DIV_GATE(CLK_TOP_APLL1_DIV3, "apll1_div3", "aud_1_sel", 0x12c, 11, 0x124, 8, 16),
+	DIV_GATE(CLK_TOP_APLL1_DIV4, "apll1_div4", "aud_1_sel", 0x12c, 12, 0x124, 8, 24),
+	DIV_GATE(CLK_TOP_APLL1_DIV5, "apll1_div5", "apll1_div4", 0x12c, 13, 0x12c, 4, 0),
+
+	DIV_GATE(CLK_TOP_APLL2_DIV0, "apll2_div0", "aud_2_sel", 0x12c, 16, 0x120, 4, 28),
+	DIV_GATE(CLK_TOP_APLL2_DIV1, "apll2_div1", "aud_2_sel", 0x12c, 17, 0x128, 8, 0),
+	DIV_GATE(CLK_TOP_APLL2_DIV2, "apll2_div2", "aud_2_sel", 0x12c, 18, 0x128, 8, 8),
+	DIV_GATE(CLK_TOP_APLL2_DIV3, "apll2_div3", "aud_2_sel", 0x12c, 19, 0x128, 8, 16),
+	DIV_GATE(CLK_TOP_APLL2_DIV4, "apll2_div4", "aud_2_sel", 0x12c, 20, 0x128, 8, 24),
+	DIV_GATE(CLK_TOP_APLL2_DIV5, "apll2_div5", "apll2_div4", 0x12c, 21, 0x12c, 4, 4),
+
+	MUX(CLK_TOP_I2S0_M_SEL, "i2s0_m_ck_sel", i2s0_m_ck_parents, 0x120, 4, 1),
+	MUX(CLK_TOP_I2S1_M_SEL, "i2s1_m_ck_sel", i2s1_m_ck_parents, 0x120, 5, 1),
+	MUX(CLK_TOP_I2S2_M_SEL, "i2s2_m_ck_sel", i2s2_m_ck_parents, 0x120, 6, 1),
+	MUX(CLK_TOP_I2S3_M_SEL, "i2s3_m_ck_sel", i2s3_m_ck_parents, 0x120, 7, 1),
+	MUX(CLK_TOP_I2S3_B_SEL, "i2s3_b_ck_sel", i2s3_b_ck_parents, 0x120, 8, 1),
+};
+
+static const struct mtk_gate_regs infra_cg_regs = {
+	.set_ofs = 0x0040,
+	.clr_ofs = 0x0044,
+	.sta_ofs = 0x0048,
+};
+
+#define GATE_ICG(_id, _name, _parent, _shift) {	\
+		.id = _id,					\
+		.name = _name,					\
+		.parent_name = _parent,				\
+		.regs = &infra_cg_regs,				\
+		.shift = _shift,				\
+		.ops = &mtk_clk_gate_ops_setclr,		\
+	}
+
+static const struct mtk_gate infra_clks[] __initconst = {
+	GATE_ICG(CLK_INFRA_DBGCLK, "infra_dbgclk", "axi_sel", 0),
+	GATE_ICG(CLK_INFRA_SMI, "infra_smi", "mm_sel", 1),
+	GATE_ICG(CLK_INFRA_AUDIO, "infra_audio", "aud_intbus_sel", 5),
+	GATE_ICG(CLK_INFRA_GCE, "infra_gce", "axi_sel", 6),
+	GATE_ICG(CLK_INFRA_L2C_SRAM, "infra_l2c_sram", "axi_sel", 7),
+	GATE_ICG(CLK_INFRA_M4U, "infra_m4u", "mem_sel", 8),
+	GATE_ICG(CLK_INFRA_CPUM, "infra_cpum", "clk_null", 15),
+	GATE_ICG(CLK_INFRA_KP, "infra_kp", "axi_sel", 16),
+	GATE_ICG(CLK_INFRA_CEC, "infra_cec", "clk26m", 18),
+	GATE_ICG(CLK_INFRA_PMICSPI, "infra_pmicspi", "pmicspi_sel", 22),
+	GATE_ICG(CLK_INFRA_PMICWRAP, "infra_pmicwrap", "axi_sel", 23),
+};
+
+static const struct mtk_gate_regs peri0_cg_regs = {
+	.set_ofs = 0x0008,
+	.clr_ofs = 0x0010,
+	.sta_ofs = 0x0018,
+};
+
+static const struct mtk_gate_regs peri1_cg_regs = {
+	.set_ofs = 0x000c,
+	.clr_ofs = 0x0014,
+	.sta_ofs = 0x001c,
+};
+
+#define GATE_PERI0(_id, _name, _parent, _shift) {	\
+		.id = _id,					\
+		.name = _name,					\
+		.parent_name = _parent,				\
+		.regs = &peri0_cg_regs,				\
+		.shift = _shift,				\
+		.ops = &mtk_clk_gate_ops_setclr,		\
+	}
+
+#define GATE_PERI1(_id, _name, _parent, _shift) {	\
+		.id = _id,					\
+		.name = _name,					\
+		.parent_name = _parent,				\
+		.regs = &peri1_cg_regs,				\
+		.shift = _shift,				\
+		.ops = &mtk_clk_gate_ops_setclr,		\
+	}
+
+static const struct mtk_gate peri_gates[] __initconst = {
+	/* PERI0 */
+	GATE_PERI0(CLK_PERI_NFI, "peri_nfi", "axi_sel", 0),
+	GATE_PERI0(CLK_PERI_THERM, "peri_therm", "axi_sel", 1),
+	GATE_PERI0(CLK_PERI_PWM1, "peri_pwm1", "axi_sel", 2),
+	GATE_PERI0(CLK_PERI_PWM2, "peri_pwm2", "axi_sel", 3),
+	GATE_PERI0(CLK_PERI_PWM3, "peri_pwm3", "axi_sel", 4),
+	GATE_PERI0(CLK_PERI_PWM4, "peri_pwm4", "axi_sel", 5),
+	GATE_PERI0(CLK_PERI_PWM5, "peri_pwm5", "axi_sel", 6),
+	GATE_PERI0(CLK_PERI_PWM6, "peri_pwm6", "axi_sel", 7),
+	GATE_PERI0(CLK_PERI_PWM7, "peri_pwm7", "axi_sel", 8),
+	GATE_PERI0(CLK_PERI_PWM, "peri_pwm", "axi_sel", 9),
+	GATE_PERI0(CLK_PERI_USB0, "peri_usb0", "usb20_sel", 10),
+	GATE_PERI0(CLK_PERI_USB1, "peri_usb1", "usb20_sel", 11),
+	GATE_PERI0(CLK_PERI_AP_DMA, "peri_ap_dma", "axi_sel", 12),
+	GATE_PERI0(CLK_PERI_MSDC30_0, "peri_msdc30_0", "msdc50_0_sel", 13),
+	GATE_PERI0(CLK_PERI_MSDC30_1, "peri_msdc30_1", "msdc30_1_sel", 14),
+	GATE_PERI0(CLK_PERI_MSDC30_2, "peri_msdc30_2", "msdc30_2_sel", 15),
+	GATE_PERI0(CLK_PERI_MSDC30_3, "peri_msdc30_3", "msdc30_3_sel", 16),
+	GATE_PERI0(CLK_PERI_NLI_ARB, "peri_nli_arb", "axi_sel", 17),
+	GATE_PERI0(CLK_PERI_IRDA, "peri_irda", "irda_sel", 18),
+	GATE_PERI0(CLK_PERI_UART0, "peri_uart0", "axi_sel", 19),
+	GATE_PERI0(CLK_PERI_UART1, "peri_uart1", "axi_sel", 20),
+	GATE_PERI0(CLK_PERI_UART2, "peri_uart2", "axi_sel", 21),
+	GATE_PERI0(CLK_PERI_UART3, "peri_uart3", "axi_sel", 22),
+	GATE_PERI0(CLK_PERI_I2C0, "peri_i2c0", "axi_sel", 23),
+	GATE_PERI0(CLK_PERI_I2C1, "peri_i2c1", "axi_sel", 24),
+	GATE_PERI0(CLK_PERI_I2C2, "peri_i2c2", "axi_sel", 25),
+	GATE_PERI0(CLK_PERI_I2C3, "peri_i2c3", "axi_sel", 26),
+	GATE_PERI0(CLK_PERI_I2C4, "peri_i2c4", "axi_sel", 27),
+	GATE_PERI0(CLK_PERI_AUXADC, "peri_auxadc", "clk26m", 28),
+	GATE_PERI0(CLK_PERI_SPI0, "peri_spi0", "spi_sel", 29),
+	GATE_PERI0(CLK_PERI_I2C5, "peri_i2c5", "axi_sel", 30),
+	GATE_PERI0(CLK_PERI_NFIECC, "peri_nfiecc", "axi_sel", 31),
+	/* PERI1 */
+	GATE_PERI1(CLK_PERI_SPI, "peri_spi", "spi_sel", 0),
+	GATE_PERI1(CLK_PERI_IRRX, "peri_irrx", "spi_sel", 1),
+	GATE_PERI1(CLK_PERI_I2C6, "peri_i2c6", "axi_sel", 2),
+};
+
+static const char * const uart_ck_sel_parents[] __initconst = {
+	"clk26m",
+	"uart_sel",
+};
+
+static const struct mtk_composite peri_clks[] __initconst = {
+	MUX(CLK_PERI_UART0_SEL, "uart0_ck_sel", uart_ck_sel_parents, 0x40c, 0, 1),
+	MUX(CLK_PERI_UART1_SEL, "uart1_ck_sel", uart_ck_sel_parents, 0x40c, 1, 1),
+	MUX(CLK_PERI_UART2_SEL, "uart2_ck_sel", uart_ck_sel_parents, 0x40c, 2, 1),
+	MUX(CLK_PERI_UART3_SEL, "uart3_ck_sel", uart_ck_sel_parents, 0x40c, 3, 1),
+};
+
+static void __init mtk_topckgen_init(struct device_node *node)
+{
+	struct clk_onecell_data *clk_data;
+	void __iomem *base;
+	int r;
+
+	base = of_iomap(node, 0);
+	if (!base) {
+		pr_err("%s(): ioremap failed\n", __func__);
+		return;
+	}
+
+	clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK);
+
+	mtk_clk_register_factors(root_clk_alias, ARRAY_SIZE(root_clk_alias), clk_data);
+	mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), clk_data);
+	mtk_clk_register_composites(top_muxes, ARRAY_SIZE(top_muxes), base,
+			&mt8173_clk_lock, clk_data);
+
+	clk_prepare_enable(clk_data->clks[CLK_TOP_CCI400_SEL]);
+
+	r = of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
+	if (r)
+		pr_err("%s(): could not register clock provider: %d\n",
+			__func__, r);
+}
+CLK_OF_DECLARE(mtk_topckgen, "mediatek,mt8173-topckgen", mtk_topckgen_init);
+
+static void __init mtk_infrasys_init(struct device_node *node)
+{
+	struct clk_onecell_data *clk_data;
+	int r;
+
+	clk_data = mtk_alloc_clk_data(CLK_INFRA_NR_CLK);
+
+	mtk_clk_register_gates(node, infra_clks, ARRAY_SIZE(infra_clks),
+						clk_data);
+
+	r = of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
+	if (r)
+		pr_err("%s(): could not register clock provider: %d\n",
+			__func__, r);
+
+	mtk_register_reset_controller(node, 2, 0x30);
+}
+CLK_OF_DECLARE(mtk_infrasys, "mediatek,mt8173-infracfg", mtk_infrasys_init);
+
+static void __init mtk_pericfg_init(struct device_node *node)
+{
+	struct clk_onecell_data *clk_data;
+	int r;
+	void __iomem *base;
+
+	base = of_iomap(node, 0);
+	if (!base) {
+		pr_err("%s(): ioremap failed\n", __func__);
+		return;
+	}
+
+	clk_data = mtk_alloc_clk_data(CLK_PERI_NR_CLK);
+
+	mtk_clk_register_gates(node, peri_gates, ARRAY_SIZE(peri_gates),
+						clk_data);
+	mtk_clk_register_composites(peri_clks, ARRAY_SIZE(peri_clks), base,
+			&mt8173_clk_lock, clk_data);
+
+	r = of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
+	if (r)
+		pr_err("%s(): could not register clock provider: %d\n",
+			__func__, r);
+
+	mtk_register_reset_controller(node, 2, 0);
+}
+CLK_OF_DECLARE(mtk_pericfg, "mediatek,mt8173-pericfg", mtk_pericfg_init);
+
+#define MT8173_PLL_FMAX		(3000UL * MHZ)
+
+#define CON0_MT8173_RST_BAR	BIT(24)
+
+#define PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, _pd_reg, _pd_shift, \
+			_tuner_reg, _pcw_reg, _pcw_shift) { \
+		.id = _id,						\
+		.name = _name,						\
+		.reg = _reg,						\
+		.pwr_reg = _pwr_reg,					\
+		.en_mask = _en_mask,					\
+		.flags = _flags,					\
+		.rst_bar_mask = CON0_MT8173_RST_BAR,			\
+		.fmax = MT8173_PLL_FMAX,				\
+		.pcwbits = _pcwbits,					\
+		.pd_reg = _pd_reg,					\
+		.pd_shift = _pd_shift,					\
+		.tuner_reg = _tuner_reg,				\
+		.pcw_reg = _pcw_reg,					\
+		.pcw_shift = _pcw_shift,				\
+	}
+
+static const struct mtk_pll_data plls[] = {
+	PLL(CLK_APMIXED_ARMCA15PLL, "armca15pll", 0x200, 0x20c, 0x00000001, 0, 21, 0x204, 24, 0x0, 0x204, 0),
+	PLL(CLK_APMIXED_ARMCA7PLL, "armca7pll", 0x210, 0x21c, 0x00000001, 0, 21, 0x214, 24, 0x0, 0x214, 0),
+	PLL(CLK_APMIXED_MAINPLL, "mainpll", 0x220, 0x22c, 0xf0000101, HAVE_RST_BAR, 21, 0x220, 4, 0x0, 0x224, 0),
+	PLL(CLK_APMIXED_UNIVPLL, "univpll", 0x230, 0x23c, 0xfe000001, HAVE_RST_BAR, 7, 0x230, 4, 0x0, 0x234, 14),
+	PLL(CLK_APMIXED_MMPLL, "mmpll", 0x240, 0x24c, 0x00000001, 0, 21, 0x244, 24, 0x0, 0x244, 0),
+	PLL(CLK_APMIXED_MSDCPLL, "msdcpll", 0x250, 0x25c, 0x00000001, 0, 21, 0x250, 4, 0x0, 0x254, 0),
+	PLL(CLK_APMIXED_VENCPLL, "vencpll", 0x260, 0x26c, 0x00000001, 0, 21, 0x260, 4, 0x0, 0x264, 0),
+	PLL(CLK_APMIXED_TVDPLL, "tvdpll", 0x270, 0x27c, 0x00000001, 0, 21, 0x270, 4, 0x0, 0x274, 0),
+	PLL(CLK_APMIXED_MPLL, "mpll", 0x280, 0x28c, 0x00000001, 0, 21, 0x280, 4, 0x0, 0x284, 0),
+	PLL(CLK_APMIXED_VCODECPLL, "vcodecpll", 0x290, 0x29c, 0x00000001, 0, 21, 0x290, 4, 0x0, 0x294, 0),
+	PLL(CLK_APMIXED_APLL1, "apll1", 0x2a0, 0x2b0, 0x00000001, 0, 31, 0x2a0, 4, 0x2a4, 0x2a4, 0),
+	PLL(CLK_APMIXED_APLL2, "apll2", 0x2b4, 0x2c4, 0x00000001, 0, 31, 0x2b4, 4, 0x2b8, 0x2b8, 0),
+	PLL(CLK_APMIXED_LVDSPLL, "lvdspll", 0x2d0, 0x2dc, 0x00000001, 0, 21, 0x2d0, 4, 0x0, 0x2d4, 0),
+	PLL(CLK_APMIXED_MSDCPLL2, "msdcpll2", 0x2f0, 0x2fc, 0x00000001, 0, 21, 0x2f0, 4, 0x0, 0x2f4, 0),
+};
+
+static void __init mtk_apmixedsys_init(struct device_node *node)
+{
+	struct clk_onecell_data *clk_data;
+
+	clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK);
+	if (!clk_data)
+		return;
+
+	mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data);
+
+	clk_prepare_enable(clk_data->clks[CLK_APMIXED_ARMCA15PLL]);
+}
+CLK_OF_DECLARE(mtk_apmixedsys, "mediatek,mt8173-apmixedsys",
+		mtk_apmixedsys_init);
diff --git a/drivers/clk/mediatek/clk-mtk.c b/drivers/clk/mediatek/clk-mtk.c
new file mode 100644
index 0000000..18444ae
--- /dev/null
+++ b/drivers/clk/mediatek/clk-mtk.c
@@ -0,0 +1,220 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ * Author: James Liao <jamesjj.liao@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/clkdev.h>
+#include <linux/mfd/syscon.h>
+
+#include "clk-mtk.h"
+#include "clk-gate.h"
+
+struct clk_onecell_data *mtk_alloc_clk_data(unsigned int clk_num)
+{
+	int i;
+	struct clk_onecell_data *clk_data;
+
+	clk_data = kzalloc(sizeof(*clk_data), GFP_KERNEL);
+	if (!clk_data)
+		return NULL;
+
+	clk_data->clks = kcalloc(clk_num, sizeof(*clk_data->clks), GFP_KERNEL);
+	if (!clk_data->clks)
+		goto err_out;
+
+	clk_data->clk_num = clk_num;
+
+	for (i = 0; i < clk_num; i++)
+		clk_data->clks[i] = ERR_PTR(-ENOENT);
+
+	return clk_data;
+err_out:
+	kfree(clk_data);
+
+	return NULL;
+}
+
+void mtk_clk_register_factors(const struct mtk_fixed_factor *clks, int num,
+		struct clk_onecell_data *clk_data)
+{
+	int i;
+	struct clk *clk;
+
+	for (i = 0; i < num; i++) {
+		const struct mtk_fixed_factor *ff = &clks[i];
+
+		clk = clk_register_fixed_factor(NULL, ff->name, ff->parent_name,
+				CLK_SET_RATE_PARENT, ff->mult, ff->div);
+
+		if (IS_ERR(clk)) {
+			pr_err("Failed to register clk %s: %ld\n",
+					ff->name, PTR_ERR(clk));
+			continue;
+		}
+
+		if (clk_data)
+			clk_data->clks[ff->id] = clk;
+	}
+}
+
+int mtk_clk_register_gates(struct device_node *node, const struct mtk_gate *clks,
+		int num, struct clk_onecell_data *clk_data)
+{
+	int i;
+	struct clk *clk;
+	struct regmap *regmap;
+
+	if (!clk_data)
+		return -ENOMEM;
+
+	regmap = syscon_node_to_regmap(node);
+	if (IS_ERR(regmap)) {
+		pr_err("Cannot find regmap for %s: %ld\n", node->full_name,
+				PTR_ERR(regmap));
+		return PTR_ERR(regmap);
+	}
+
+	for (i = 0; i < num; i++) {
+		const struct mtk_gate *gate = &clks[i];
+
+		clk = mtk_clk_register_gate(gate->name, gate->parent_name,
+				regmap,
+				gate->regs->set_ofs,
+				gate->regs->clr_ofs,
+				gate->regs->sta_ofs,
+				gate->shift, gate->ops);
+
+		if (IS_ERR(clk)) {
+			pr_err("Failed to register clk %s: %ld\n",
+					gate->name, PTR_ERR(clk));
+			continue;
+		}
+
+		clk_data->clks[gate->id] = clk;
+	}
+
+	return 0;
+}
+
+struct clk *mtk_clk_register_composite(const struct mtk_composite *mc,
+		void __iomem *base, spinlock_t *lock)
+{
+	struct clk *clk;
+	struct clk_mux *mux = NULL;
+	struct clk_gate *gate = NULL;
+	struct clk_divider *div = NULL;
+	struct clk_hw *mux_hw = NULL, *gate_hw = NULL, *div_hw = NULL;
+	const struct clk_ops *mux_ops = NULL, *gate_ops = NULL, *div_ops = NULL;
+	const char * const *parent_names;
+	const char *parent;
+	int num_parents;
+	int ret;
+
+	if (mc->mux_shift >= 0) {
+		mux = kzalloc(sizeof(*mux), GFP_KERNEL);
+		if (!mux)
+			return ERR_PTR(-ENOMEM);
+
+		mux->reg = base + mc->mux_reg;
+		mux->mask = BIT(mc->mux_width) - 1;
+		mux->shift = mc->mux_shift;
+		mux->lock = lock;
+
+		mux_hw = &mux->hw;
+		mux_ops = &clk_mux_ops;
+
+		parent_names = mc->parent_names;
+		num_parents = mc->num_parents;
+	} else {
+		parent = mc->parent;
+		parent_names = &parent;
+		num_parents = 1;
+	}
+
+	if (mc->gate_shift >= 0) {
+		gate = kzalloc(sizeof(*gate), GFP_KERNEL);
+		if (!gate) {
+			ret = -ENOMEM;
+			goto err_out;
+		}
+
+		gate->reg = base + mc->gate_reg;
+		gate->bit_idx = mc->gate_shift;
+		gate->flags = CLK_GATE_SET_TO_DISABLE;
+		gate->lock = lock;
+
+		gate_hw = &gate->hw;
+		gate_ops = &clk_gate_ops;
+	}
+
+	if (mc->divider_shift >= 0) {
+		div = kzalloc(sizeof(*div), GFP_KERNEL);
+		if (!div) {
+			ret = -ENOMEM;
+			goto err_out;
+		}
+
+		div->reg = base + mc->divider_reg;
+		div->shift = mc->divider_shift;
+		div->width = mc->divider_width;
+		div->lock = lock;
+
+		div_hw = &div->hw;
+		div_ops = &clk_divider_ops;
+	}
+
+	clk = clk_register_composite(NULL, mc->name, parent_names, num_parents,
+		mux_hw, mux_ops,
+		div_hw, div_ops,
+		gate_hw, gate_ops,
+		mc->flags);
+
+	if (IS_ERR(clk)) {
+		kfree(gate);
+		kfree(mux);
+	}
+
+	return clk;
+err_out:
+	kfree(mux);
+
+	return ERR_PTR(ret);
+}
+
+void mtk_clk_register_composites(const struct mtk_composite *mcs,
+		int num, void __iomem *base, spinlock_t *lock,
+		struct clk_onecell_data *clk_data)
+{
+	struct clk *clk;
+	int i;
+
+	for (i = 0; i < num; i++) {
+		const struct mtk_composite *mc = &mcs[i];
+
+		clk = mtk_clk_register_composite(mc, base, lock);
+
+		if (IS_ERR(clk)) {
+			pr_err("Failed to register clk %s: %ld\n",
+					mc->name, PTR_ERR(clk));
+			continue;
+		}
+
+		if (clk_data)
+			clk_data->clks[mc->id] = clk;
+	}
+}
diff --git a/drivers/clk/mediatek/clk-mtk.h b/drivers/clk/mediatek/clk-mtk.h
new file mode 100644
index 0000000..9dda9d8
--- /dev/null
+++ b/drivers/clk/mediatek/clk-mtk.h
@@ -0,0 +1,169 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ * Author: James Liao <jamesjj.liao@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __DRV_CLK_MTK_H
+#define __DRV_CLK_MTK_H
+
+#include <linux/regmap.h>
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+
+#define MAX_MUX_GATE_BIT	31
+#define INVALID_MUX_GATE_BIT	(MAX_MUX_GATE_BIT + 1)
+
+#define MHZ (1000 * 1000)
+
+struct mtk_fixed_factor {
+	int id;
+	const char *name;
+	const char *parent_name;
+	int mult;
+	int div;
+};
+
+#define FACTOR(_id, _name, _parent, _mult, _div) {	\
+		.id = _id,				\
+		.name = _name,				\
+		.parent_name = _parent,			\
+		.mult = _mult,				\
+		.div = _div,				\
+	}
+
+extern void mtk_clk_register_factors(const struct mtk_fixed_factor *clks,
+		int num, struct clk_onecell_data *clk_data);
+
+struct mtk_composite {
+	int id;
+	const char *name;
+	const char * const *parent_names;
+	const char *parent;
+	unsigned flags;
+
+	uint32_t mux_reg;
+	uint32_t divider_reg;
+	uint32_t gate_reg;
+
+	signed char mux_shift;
+	signed char mux_width;
+	signed char gate_shift;
+
+	signed char divider_shift;
+	signed char divider_width;
+
+	signed char num_parents;
+};
+
+#define MUX_GATE(_id, _name, _parents, _reg, _shift, _width, _gate) {	\
+		.id = _id,						\
+		.name = _name,						\
+		.mux_reg = _reg,					\
+		.mux_shift = _shift,					\
+		.mux_width = _width,					\
+		.gate_reg = _reg,					\
+		.gate_shift = _gate,					\
+		.divider_shift = -1,					\
+		.parent_names = _parents,				\
+		.num_parents = ARRAY_SIZE(_parents),			\
+		.flags = CLK_SET_RATE_PARENT,				\
+	}
+
+#define MUX(_id, _name, _parents, _reg, _shift, _width) {		\
+		.id = _id,						\
+		.name = _name,						\
+		.mux_reg = _reg,					\
+		.mux_shift = _shift,					\
+		.mux_width = _width,					\
+		.gate_shift = -1,					\
+		.divider_shift = -1,					\
+		.parent_names = _parents,				\
+		.num_parents = ARRAY_SIZE(_parents),			\
+		.flags = CLK_SET_RATE_PARENT,				\
+	}
+
+#define DIV_GATE(_id, _name, _parent, _gate_reg, _gate_shift, _div_reg, _div_width, _div_shift) {	\
+		.id = _id,						\
+		.parent = _parent,					\
+		.name = _name,						\
+		.divider_reg = _div_reg,				\
+		.divider_shift = _div_shift,				\
+		.divider_width = _div_width,				\
+		.gate_reg = _gate_reg,					\
+		.gate_shift = _gate_shift,				\
+		.mux_shift = -1,					\
+		.flags = 0,						\
+	}
+
+struct clk *mtk_clk_register_composite(const struct mtk_composite *mc,
+		void __iomem *base, spinlock_t *lock);
+
+void mtk_clk_register_composites(const struct mtk_composite *mcs,
+		int num, void __iomem *base, spinlock_t *lock,
+		struct clk_onecell_data *clk_data);
+
+struct mtk_gate_regs {
+	u32 sta_ofs;
+	u32 clr_ofs;
+	u32 set_ofs;
+};
+
+struct mtk_gate {
+	int id;
+	const char *name;
+	const char *parent_name;
+	const struct mtk_gate_regs *regs;
+	int shift;
+	const struct clk_ops *ops;
+};
+
+int mtk_clk_register_gates(struct device_node *node, const struct mtk_gate *clks,
+		int num, struct clk_onecell_data *clk_data);
+
+struct clk_onecell_data *mtk_alloc_clk_data(unsigned int clk_num);
+
+#define HAVE_RST_BAR	BIT(0)
+
+struct mtk_pll_data {
+	int id;
+	const char *name;
+	uint32_t reg;
+	uint32_t pwr_reg;
+	uint32_t en_mask;
+	uint32_t pd_reg;
+	uint32_t tuner_reg;
+	int pd_shift;
+	unsigned int flags;
+	const struct clk_ops *ops;
+	u32 rst_bar_mask;
+	unsigned long fmax;
+	int pcwbits;
+	uint32_t pcw_reg;
+	int pcw_shift;
+};
+
+void __init mtk_clk_register_plls(struct device_node *node,
+		const struct mtk_pll_data *plls, int num_plls,
+		struct clk_onecell_data *clk_data);
+
+#ifdef CONFIG_RESET_CONTROLLER
+void mtk_register_reset_controller(struct device_node *np,
+			unsigned int num_regs, int regofs);
+#else
+static inline void mtk_register_reset_controller(struct device_node *np,
+			unsigned int num_regs, int regofs)
+{
+}
+#endif
+
+#endif /* __DRV_CLK_MTK_H */
diff --git a/drivers/clk/mediatek/clk-pll.c b/drivers/clk/mediatek/clk-pll.c
new file mode 100644
index 0000000..44409e9
--- /dev/null
+++ b/drivers/clk/mediatek/clk-pll.c
@@ -0,0 +1,332 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ * Author: James Liao <jamesjj.liao@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/clkdev.h>
+#include <linux/delay.h>
+
+#include "clk-mtk.h"
+
+#define REG_CON0		0
+#define REG_CON1		4
+
+#define CON0_BASE_EN		BIT(0)
+#define CON0_PWR_ON		BIT(0)
+#define CON0_ISO_EN		BIT(1)
+#define CON0_PCW_CHG		BIT(31)
+
+#define AUDPLL_TUNER_EN		BIT(31)
+
+#define POSTDIV_MASK		0x7
+#define INTEGER_BITS		7
+
+/*
+ * MediaTek PLLs are configured through their pcw value. The pcw value describes
+ * a divider in the PLL feedback loop which consists of 7 bits for the integer
+ * part and the remaining bits (if present) for the fractional part. Also they
+ * have a 3 bit power-of-two post divider.
+ */
+
+struct mtk_clk_pll {
+	struct clk_hw	hw;
+	void __iomem	*base_addr;
+	void __iomem	*pd_addr;
+	void __iomem	*pwr_addr;
+	void __iomem	*tuner_addr;
+	void __iomem	*pcw_addr;
+	const struct mtk_pll_data *data;
+};
+
+static inline struct mtk_clk_pll *to_mtk_clk_pll(struct clk_hw *hw)
+{
+	return container_of(hw, struct mtk_clk_pll, hw);
+}
+
+static int mtk_pll_is_prepared(struct clk_hw *hw)
+{
+	struct mtk_clk_pll *pll = to_mtk_clk_pll(hw);
+
+	return (readl(pll->base_addr + REG_CON0) & CON0_BASE_EN) != 0;
+}
+
+static unsigned long __mtk_pll_recalc_rate(struct mtk_clk_pll *pll, u32 fin,
+		u32 pcw, int postdiv)
+{
+	int pcwbits = pll->data->pcwbits;
+	int pcwfbits;
+	u64 vco;
+	u8 c = 0;
+
+	/* The fractional part of the PLL divider. */
+	pcwfbits = pcwbits > INTEGER_BITS ? pcwbits - INTEGER_BITS : 0;
+
+	vco = (u64)fin * pcw;
+
+	if (pcwfbits && (vco & GENMASK(pcwfbits - 1, 0)))
+		c = 1;
+
+	vco >>= pcwfbits;
+
+	if (c)
+		vco++;
+
+	return ((unsigned long)vco + postdiv - 1) / postdiv;
+}
+
+static void mtk_pll_set_rate_regs(struct mtk_clk_pll *pll, u32 pcw,
+		int postdiv)
+{
+	u32 con1, pd, val;
+	int pll_en;
+
+	/* set postdiv */
+	pd = readl(pll->pd_addr);
+	pd &= ~(POSTDIV_MASK << pll->data->pd_shift);
+	pd |= (ffs(postdiv) - 1) << pll->data->pd_shift;
+	writel(pd, pll->pd_addr);
+
+	pll_en = readl(pll->base_addr + REG_CON0) & CON0_BASE_EN;
+
+	/* set pcw */
+	val = readl(pll->pcw_addr);
+
+	val &= ~GENMASK(pll->data->pcw_shift + pll->data->pcwbits - 1,
+			pll->data->pcw_shift);
+	val |= pcw << pll->data->pcw_shift;
+	writel(val, pll->pcw_addr);
+
+	con1 = readl(pll->base_addr + REG_CON1);
+
+	if (pll_en)
+		con1 |= CON0_PCW_CHG;
+
+	writel(con1, pll->base_addr + REG_CON1);
+	if (pll->tuner_addr)
+		writel(con1 + 1, pll->tuner_addr);
+
+	if (pll_en)
+		udelay(20);
+}
+
+/*
+ * mtk_pll_calc_values - calculate good values for a given input frequency.
+ * @pll:	The pll
+ * @pcw:	The pcw value (output)
+ * @postdiv:	The post divider (output)
+ * @freq:	The desired target frequency
+ * @fin:	The input frequency
+ *
+ */
+static void mtk_pll_calc_values(struct mtk_clk_pll *pll, u32 *pcw, u32 *postdiv,
+		u32 freq, u32 fin)
+{
+	unsigned long fmin = 1000 * MHZ;
+	u64 _pcw;
+	u32 val;
+
+	if (freq > pll->data->fmax)
+		freq = pll->data->fmax;
+
+	for (val = 0; val < 4; val++) {
+		*postdiv = 1 << val;
+		if (freq * *postdiv >= fmin)
+			break;
+	}
+
+	/* _pcw = freq * postdiv / fin * 2^pcwfbits */
+	_pcw = ((u64)freq << val) << (pll->data->pcwbits - INTEGER_BITS);
+	do_div(_pcw, fin);
+
+	*pcw = (u32)_pcw;
+}
+
+static int mtk_pll_set_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long parent_rate)
+{
+	struct mtk_clk_pll *pll = to_mtk_clk_pll(hw);
+	u32 pcw = 0;
+	u32 postdiv;
+
+	mtk_pll_calc_values(pll, &pcw, &postdiv, rate, parent_rate);
+	mtk_pll_set_rate_regs(pll, pcw, postdiv);
+
+	return 0;
+}
+
+static unsigned long mtk_pll_recalc_rate(struct clk_hw *hw,
+		unsigned long parent_rate)
+{
+	struct mtk_clk_pll *pll = to_mtk_clk_pll(hw);
+	u32 postdiv;
+	u32 pcw;
+
+	postdiv = (readl(pll->pd_addr) >> pll->data->pd_shift) & POSTDIV_MASK;
+	postdiv = 1 << postdiv;
+
+	pcw = readl(pll->pcw_addr) >> pll->data->pcw_shift;
+	pcw &= GENMASK(pll->data->pcwbits - 1, 0);
+
+	return __mtk_pll_recalc_rate(pll, parent_rate, pcw, postdiv);
+}
+
+static long mtk_pll_round_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long *prate)
+{
+	struct mtk_clk_pll *pll = to_mtk_clk_pll(hw);
+	u32 pcw = 0;
+	int postdiv;
+
+	mtk_pll_calc_values(pll, &pcw, &postdiv, rate, *prate);
+
+	return __mtk_pll_recalc_rate(pll, *prate, pcw, postdiv);
+}
+
+static int mtk_pll_prepare(struct clk_hw *hw)
+{
+	struct mtk_clk_pll *pll = to_mtk_clk_pll(hw);
+	u32 r;
+
+	r = readl(pll->pwr_addr) | CON0_PWR_ON;
+	writel(r, pll->pwr_addr);
+	udelay(1);
+
+	r = readl(pll->pwr_addr) & ~CON0_ISO_EN;
+	writel(r, pll->pwr_addr);
+	udelay(1);
+
+	r = readl(pll->base_addr + REG_CON0);
+	r |= pll->data->en_mask;
+	writel(r, pll->base_addr + REG_CON0);
+
+	if (pll->tuner_addr) {
+		r = readl(pll->tuner_addr) | AUDPLL_TUNER_EN;
+		writel(r, pll->tuner_addr);
+	}
+
+	udelay(20);
+
+	if (pll->data->flags & HAVE_RST_BAR) {
+		r = readl(pll->base_addr + REG_CON0);
+		r |= pll->data->rst_bar_mask;
+		writel(r, pll->base_addr + REG_CON0);
+	}
+
+	return 0;
+}
+
+static void mtk_pll_unprepare(struct clk_hw *hw)
+{
+	struct mtk_clk_pll *pll = to_mtk_clk_pll(hw);
+	u32 r;
+
+	if (pll->data->flags & HAVE_RST_BAR) {
+		r = readl(pll->base_addr + REG_CON0);
+		r &= ~pll->data->rst_bar_mask;
+		writel(r, pll->base_addr + REG_CON0);
+	}
+
+	if (pll->tuner_addr) {
+		r = readl(pll->tuner_addr) & ~AUDPLL_TUNER_EN;
+		writel(r, pll->tuner_addr);
+	}
+
+	r = readl(pll->base_addr + REG_CON0);
+	r &= ~CON0_BASE_EN;
+	writel(r, pll->base_addr + REG_CON0);
+
+	r = readl(pll->pwr_addr) | CON0_ISO_EN;
+	writel(r, pll->pwr_addr);
+
+	r = readl(pll->pwr_addr) & ~CON0_PWR_ON;
+	writel(r, pll->pwr_addr);
+}
+
+static const struct clk_ops mtk_pll_ops = {
+	.is_prepared	= mtk_pll_is_prepared,
+	.prepare	= mtk_pll_prepare,
+	.unprepare	= mtk_pll_unprepare,
+	.recalc_rate	= mtk_pll_recalc_rate,
+	.round_rate	= mtk_pll_round_rate,
+	.set_rate	= mtk_pll_set_rate,
+};
+
+static struct clk *mtk_clk_register_pll(const struct mtk_pll_data *data,
+		void __iomem *base)
+{
+	struct mtk_clk_pll *pll;
+	struct clk_init_data init = {};
+	struct clk *clk;
+	const char *parent_name = "clk26m";
+
+	pll = kzalloc(sizeof(*pll), GFP_KERNEL);
+	if (!pll)
+		return ERR_PTR(-ENOMEM);
+
+	pll->base_addr = base + data->reg;
+	pll->pwr_addr = base + data->pwr_reg;
+	pll->pd_addr = base + data->pd_reg;
+	pll->pcw_addr = base + data->pcw_reg;
+	if (data->tuner_reg)
+		pll->tuner_addr = base + data->tuner_reg;
+	pll->hw.init = &init;
+	pll->data = data;
+
+	init.name = data->name;
+	init.ops = &mtk_pll_ops;
+	init.parent_names = &parent_name;
+	init.num_parents = 1;
+
+	clk = clk_register(NULL, &pll->hw);
+
+	if (IS_ERR(clk))
+		kfree(pll);
+
+	return clk;
+}
+
+void __init mtk_clk_register_plls(struct device_node *node,
+		const struct mtk_pll_data *plls, int num_plls, struct clk_onecell_data *clk_data)
+{
+	void __iomem *base;
+	int r, i;
+	struct clk *clk;
+
+	base = of_iomap(node, 0);
+	if (!base) {
+		pr_err("%s(): ioremap failed\n", __func__);
+		return;
+	}
+
+	for (i = 0; i < num_plls; i++) {
+		const struct mtk_pll_data *pll = &plls[i];
+
+		clk = mtk_clk_register_pll(pll, base);
+
+		if (IS_ERR(clk)) {
+			pr_err("Failed to register clk %s: %ld\n",
+					pll->name, PTR_ERR(clk));
+			continue;
+		}
+
+		clk_data->clks[pll->id] = clk;
+	}
+
+	r = of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
+	if (r)
+		pr_err("%s(): could not register clock provider: %d\n",
+			__func__, r);
+}
diff --git a/drivers/clk/mediatek/reset.c b/drivers/clk/mediatek/reset.c
new file mode 100644
index 0000000..9e9fe4b
--- /dev/null
+++ b/drivers/clk/mediatek/reset.c
@@ -0,0 +1,97 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/reset-controller.h>
+#include <linux/slab.h>
+
+#include "clk-mtk.h"
+
+struct mtk_reset {
+	struct regmap *regmap;
+	int regofs;
+	struct reset_controller_dev rcdev;
+};
+
+static int mtk_reset_assert(struct reset_controller_dev *rcdev,
+			      unsigned long id)
+{
+	struct mtk_reset *data = container_of(rcdev, struct mtk_reset, rcdev);
+
+	return regmap_update_bits(data->regmap, data->regofs + ((id / 32) << 2),
+			BIT(id % 32), ~0);
+}
+
+static int mtk_reset_deassert(struct reset_controller_dev *rcdev,
+				unsigned long id)
+{
+	struct mtk_reset *data = container_of(rcdev, struct mtk_reset, rcdev);
+
+	return regmap_update_bits(data->regmap, data->regofs + ((id / 32) << 2),
+			BIT(id % 32), 0);
+}
+
+static int mtk_reset(struct reset_controller_dev *rcdev,
+			      unsigned long id)
+{
+	int ret;
+
+	ret = mtk_reset_assert(rcdev, id);
+	if (ret)
+		return ret;
+
+	return mtk_reset_deassert(rcdev, id);
+}
+
+static struct reset_control_ops mtk_reset_ops = {
+	.assert = mtk_reset_assert,
+	.deassert = mtk_reset_deassert,
+	.reset = mtk_reset,
+};
+
+void mtk_register_reset_controller(struct device_node *np,
+			unsigned int num_regs, int regofs)
+{
+	struct mtk_reset *data;
+	int ret;
+	struct regmap *regmap;
+
+	regmap = syscon_node_to_regmap(np);
+	if (IS_ERR(regmap)) {
+		pr_err("Cannot find regmap for %s: %ld\n", np->full_name,
+				PTR_ERR(regmap));
+		return;
+	}
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return;
+
+	data->regmap = regmap;
+	data->regofs = regofs;
+	data->rcdev.owner = THIS_MODULE;
+	data->rcdev.nr_resets = num_regs * 32;
+	data->rcdev.ops = &mtk_reset_ops;
+	data->rcdev.of_node = np;
+
+	ret = reset_controller_register(&data->rcdev);
+	if (ret) {
+		pr_err("could not register reset controller: %d\n", ret);
+		kfree(data);
+		return;
+	}
+}
diff --git a/drivers/clk/meson/Makefile b/drivers/clk/meson/Makefile
new file mode 100644
index 0000000..6d45531
--- /dev/null
+++ b/drivers/clk/meson/Makefile
@@ -0,0 +1,6 @@
+#
+# Makefile for Meson specific clk
+#
+
+obj-y += clkc.o clk-pll.o clk-cpu.o
+obj-y += meson8b-clkc.o
diff --git a/drivers/clk/meson/clk-cpu.c b/drivers/clk/meson/clk-cpu.c
new file mode 100644
index 0000000..71ad493
--- /dev/null
+++ b/drivers/clk/meson/clk-cpu.c
@@ -0,0 +1,242 @@
+/*
+ * Copyright (c) 2015 Endless Mobile, Inc.
+ * Author: Carlo Caione <carlo@endlessm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * CPU clock path:
+ *
+ *                           +-[/N]-----|3|
+ *             MUX2  +--[/3]-+----------|2| MUX1
+ * [sys_pll]---|1|   |--[/2]------------|1|-|1|
+ *             | |---+------------------|0| | |----- [a5_clk]
+ *          +--|0|                          | |
+ * [xtal]---+-------------------------------|0|
+ *
+ *
+ *
+ */
+
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+#include <linux/clk-provider.h>
+
+#define MESON_CPU_CLK_CNTL1		0x00
+#define MESON_CPU_CLK_CNTL		0x40
+
+#define MESON_CPU_CLK_MUX1		BIT(7)
+#define MESON_CPU_CLK_MUX2		BIT(0)
+
+#define MESON_N_WIDTH			9
+#define MESON_N_SHIFT			20
+#define MESON_SEL_WIDTH			2
+#define MESON_SEL_SHIFT			2
+
+#include "clkc.h"
+
+struct meson_clk_cpu {
+	struct notifier_block		clk_nb;
+	const struct clk_div_table	*div_table;
+	struct clk_hw			hw;
+	void __iomem			*base;
+	u16				reg_off;
+};
+#define to_meson_clk_cpu_hw(_hw) container_of(_hw, struct meson_clk_cpu, hw)
+#define to_meson_clk_cpu_nb(_nb) container_of(_nb, struct meson_clk_cpu, clk_nb)
+
+static long meson_clk_cpu_round_rate(struct clk_hw *hw, unsigned long rate,
+				     unsigned long *prate)
+{
+	struct meson_clk_cpu *clk_cpu = to_meson_clk_cpu_hw(hw);
+
+	return divider_round_rate(hw, rate, prate, clk_cpu->div_table,
+				  MESON_N_WIDTH, CLK_DIVIDER_ROUND_CLOSEST);
+}
+
+static int meson_clk_cpu_set_rate(struct clk_hw *hw, unsigned long rate,
+				  unsigned long parent_rate)
+{
+	struct meson_clk_cpu *clk_cpu = to_meson_clk_cpu_hw(hw);
+	unsigned int div, sel, N = 0;
+	u32 reg;
+
+	div = DIV_ROUND_UP(parent_rate, rate);
+
+	if (div <= 3) {
+		sel = div - 1;
+	} else {
+		sel = 3;
+		N = div / 2;
+	}
+
+	reg = readl(clk_cpu->base + clk_cpu->reg_off + MESON_CPU_CLK_CNTL1);
+	reg = PARM_SET(MESON_N_WIDTH, MESON_N_SHIFT, reg, N);
+	writel(reg, clk_cpu->base + clk_cpu->reg_off + MESON_CPU_CLK_CNTL1);
+
+	reg = readl(clk_cpu->base + clk_cpu->reg_off + MESON_CPU_CLK_CNTL);
+	reg = PARM_SET(MESON_SEL_WIDTH, MESON_SEL_SHIFT, reg, sel);
+	writel(reg, clk_cpu->base + clk_cpu->reg_off + MESON_CPU_CLK_CNTL);
+
+	return 0;
+}
+
+static unsigned long meson_clk_cpu_recalc_rate(struct clk_hw *hw,
+					       unsigned long parent_rate)
+{
+	struct meson_clk_cpu *clk_cpu = to_meson_clk_cpu_hw(hw);
+	unsigned int N, sel;
+	unsigned int div = 1;
+	u32 reg;
+
+	reg = readl(clk_cpu->base + clk_cpu->reg_off + MESON_CPU_CLK_CNTL1);
+	N = PARM_GET(MESON_N_WIDTH, MESON_N_SHIFT, reg);
+
+	reg = readl(clk_cpu->base + clk_cpu->reg_off + MESON_CPU_CLK_CNTL);
+	sel = PARM_GET(MESON_SEL_WIDTH, MESON_SEL_SHIFT, reg);
+
+	if (sel < 3)
+		div = sel + 1;
+	else
+		div = 2 * N;
+
+	return parent_rate / div;
+}
+
+static int meson_clk_cpu_pre_rate_change(struct meson_clk_cpu *clk_cpu,
+					 struct clk_notifier_data *ndata)
+{
+	u32 cpu_clk_cntl;
+
+	/* switch MUX1 to xtal */
+	cpu_clk_cntl = readl(clk_cpu->base + clk_cpu->reg_off
+				+ MESON_CPU_CLK_CNTL);
+	cpu_clk_cntl &= ~MESON_CPU_CLK_MUX1;
+	writel(cpu_clk_cntl, clk_cpu->base + clk_cpu->reg_off
+				+ MESON_CPU_CLK_CNTL);
+	udelay(100);
+
+	/* switch MUX2 to sys-pll */
+	cpu_clk_cntl |= MESON_CPU_CLK_MUX2;
+	writel(cpu_clk_cntl, clk_cpu->base + clk_cpu->reg_off
+				+ MESON_CPU_CLK_CNTL);
+
+	return 0;
+}
+
+static int meson_clk_cpu_post_rate_change(struct meson_clk_cpu *clk_cpu,
+					  struct clk_notifier_data *ndata)
+{
+	u32 cpu_clk_cntl;
+
+	/* switch MUX1 to divisors' output */
+	cpu_clk_cntl = readl(clk_cpu->base + clk_cpu->reg_off
+				+ MESON_CPU_CLK_CNTL);
+	cpu_clk_cntl |= MESON_CPU_CLK_MUX1;
+	writel(cpu_clk_cntl, clk_cpu->base + clk_cpu->reg_off
+				+ MESON_CPU_CLK_CNTL);
+	udelay(100);
+
+	return 0;
+}
+
+/*
+ * This clock notifier is called when the frequency of the of the parent
+ * PLL clock is to be changed. We use the xtal input as temporary parent
+ * while the PLL frequency is stabilized.
+ */
+static int meson_clk_cpu_notifier_cb(struct notifier_block *nb,
+				     unsigned long event, void *data)
+{
+	struct clk_notifier_data *ndata = data;
+	struct meson_clk_cpu *clk_cpu = to_meson_clk_cpu_nb(nb);
+	int ret = 0;
+
+	if (event == PRE_RATE_CHANGE)
+		ret = meson_clk_cpu_pre_rate_change(clk_cpu, ndata);
+	else if (event == POST_RATE_CHANGE)
+		ret = meson_clk_cpu_post_rate_change(clk_cpu, ndata);
+
+	return notifier_from_errno(ret);
+}
+
+static const struct clk_ops meson_clk_cpu_ops = {
+	.recalc_rate	= meson_clk_cpu_recalc_rate,
+	.round_rate	= meson_clk_cpu_round_rate,
+	.set_rate	= meson_clk_cpu_set_rate,
+};
+
+struct clk *meson_clk_register_cpu(const struct clk_conf *clk_conf,
+				   void __iomem *reg_base,
+				   spinlock_t *lock)
+{
+	struct clk *clk;
+	struct clk *pclk;
+	struct meson_clk_cpu *clk_cpu;
+	struct clk_init_data init;
+	int ret;
+
+	clk_cpu = kzalloc(sizeof(*clk_cpu), GFP_KERNEL);
+	if (!clk_cpu)
+		return ERR_PTR(-ENOMEM);
+
+	clk_cpu->base = reg_base;
+	clk_cpu->reg_off = clk_conf->reg_off;
+	clk_cpu->div_table = clk_conf->conf.div_table;
+	clk_cpu->clk_nb.notifier_call = meson_clk_cpu_notifier_cb;
+
+	init.name = clk_conf->clk_name;
+	init.ops = &meson_clk_cpu_ops;
+	init.flags = clk_conf->flags | CLK_GET_RATE_NOCACHE;
+	init.flags |= CLK_SET_RATE_PARENT;
+	init.parent_names = clk_conf->clks_parent;
+	init.num_parents = 1;
+
+	clk_cpu->hw.init = &init;
+
+	pclk = __clk_lookup(clk_conf->clks_parent[0]);
+	if (!pclk) {
+		pr_err("%s: could not lookup parent clock %s\n",
+				__func__, clk_conf->clks_parent[0]);
+		ret = -EINVAL;
+		goto free_clk;
+	}
+
+	ret = clk_notifier_register(pclk, &clk_cpu->clk_nb);
+	if (ret) {
+		pr_err("%s: failed to register clock notifier for %s\n",
+				__func__, clk_conf->clk_name);
+		goto free_clk;
+	}
+
+	clk = clk_register(NULL, &clk_cpu->hw);
+	if (IS_ERR(clk)) {
+		ret = PTR_ERR(clk);
+		goto unregister_clk_nb;
+	}
+
+	return clk;
+
+unregister_clk_nb:
+	clk_notifier_unregister(pclk, &clk_cpu->clk_nb);
+free_clk:
+	kfree(clk_cpu);
+
+	return ERR_PTR(ret);
+}
+
diff --git a/drivers/clk/meson/clk-pll.c b/drivers/clk/meson/clk-pll.c
new file mode 100644
index 0000000..664edf0
--- /dev/null
+++ b/drivers/clk/meson/clk-pll.c
@@ -0,0 +1,227 @@
+/*
+ * Copyright (c) 2015 Endless Mobile, Inc.
+ * Author: Carlo Caione <carlo@endlessm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * In the most basic form, a Meson PLL is composed as follows:
+ *
+ *                     PLL
+ *      +------------------------------+
+ *      |                              |
+ * in -----[ /N ]---[ *M ]---[ >>OD ]----->> out
+ *      |         ^        ^           |
+ *      +------------------------------+
+ *                |        |
+ *               FREF     VCO
+ *
+ * out = (in * M / N) >> OD
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+
+#include "clkc.h"
+
+#define MESON_PLL_RESET				BIT(29)
+#define MESON_PLL_LOCK				BIT(31)
+
+struct meson_clk_pll {
+	struct clk_hw	hw;
+	void __iomem	*base;
+	struct pll_conf	*conf;
+	unsigned int	rate_count;
+	spinlock_t	*lock;
+};
+#define to_meson_clk_pll(_hw) container_of(_hw, struct meson_clk_pll, hw)
+
+static unsigned long meson_clk_pll_recalc_rate(struct clk_hw *hw,
+						unsigned long parent_rate)
+{
+	struct meson_clk_pll *pll = to_meson_clk_pll(hw);
+	struct parm *p;
+	unsigned long parent_rate_mhz = parent_rate / 1000000;
+	unsigned long rate_mhz;
+	u16 n, m, od;
+	u32 reg;
+
+	p = &pll->conf->n;
+	reg = readl(pll->base + p->reg_off);
+	n = PARM_GET(p->width, p->shift, reg);
+
+	p = &pll->conf->m;
+	reg = readl(pll->base + p->reg_off);
+	m = PARM_GET(p->width, p->shift, reg);
+
+	p = &pll->conf->od;
+	reg = readl(pll->base + p->reg_off);
+	od = PARM_GET(p->width, p->shift, reg);
+
+	rate_mhz = (parent_rate_mhz * m / n) >> od;
+
+	return rate_mhz * 1000000;
+}
+
+static long meson_clk_pll_round_rate(struct clk_hw *hw, unsigned long rate,
+				     unsigned long *parent_rate)
+{
+	struct meson_clk_pll *pll = to_meson_clk_pll(hw);
+	const struct pll_rate_table *rate_table = pll->conf->rate_table;
+	int i;
+
+	for (i = 0; i < pll->rate_count; i++) {
+		if (rate <= rate_table[i].rate)
+			return rate_table[i].rate;
+	}
+
+	/* else return the smallest value */
+	return rate_table[0].rate;
+}
+
+static const struct pll_rate_table *meson_clk_get_pll_settings(struct meson_clk_pll *pll,
+							       unsigned long rate)
+{
+	const struct pll_rate_table *rate_table = pll->conf->rate_table;
+	int i;
+
+	for (i = 0; i < pll->rate_count; i++) {
+		if (rate == rate_table[i].rate)
+			return &rate_table[i];
+	}
+	return NULL;
+}
+
+static int meson_clk_pll_wait_lock(struct meson_clk_pll *pll,
+				   struct parm *p_n)
+{
+	int delay = 24000000;
+	u32 reg;
+
+	while (delay > 0) {
+		reg = readl(pll->base + p_n->reg_off);
+
+		if (reg & MESON_PLL_LOCK)
+			return 0;
+		delay--;
+	}
+	return -ETIMEDOUT;
+}
+
+static int meson_clk_pll_set_rate(struct clk_hw *hw, unsigned long rate,
+				  unsigned long parent_rate)
+{
+	struct meson_clk_pll *pll = to_meson_clk_pll(hw);
+	struct parm *p;
+	const struct pll_rate_table *rate_set;
+	unsigned long old_rate;
+	int ret = 0;
+	u32 reg;
+
+	if (parent_rate == 0 || rate == 0)
+		return -EINVAL;
+
+	old_rate = rate;
+
+	rate_set = meson_clk_get_pll_settings(pll, rate);
+	if (!rate_set)
+		return -EINVAL;
+
+	/* PLL reset */
+	p = &pll->conf->n;
+	reg = readl(pll->base + p->reg_off);
+	writel(reg | MESON_PLL_RESET, pll->base + p->reg_off);
+
+	reg = PARM_SET(p->width, p->shift, reg, rate_set->n);
+	writel(reg, pll->base + p->reg_off);
+
+	p = &pll->conf->m;
+	reg = readl(pll->base + p->reg_off);
+	reg = PARM_SET(p->width, p->shift, reg, rate_set->m);
+	writel(reg, pll->base + p->reg_off);
+
+	p = &pll->conf->od;
+	reg = readl(pll->base + p->reg_off);
+	reg = PARM_SET(p->width, p->shift, reg, rate_set->od);
+	writel(reg, pll->base + p->reg_off);
+
+	p = &pll->conf->n;
+	ret = meson_clk_pll_wait_lock(pll, p);
+	if (ret) {
+		pr_warn("%s: pll did not lock, trying to restore old rate %lu\n",
+			__func__, old_rate);
+		meson_clk_pll_set_rate(hw, old_rate, parent_rate);
+	}
+
+	return ret;
+}
+
+static const struct clk_ops meson_clk_pll_ops = {
+	.recalc_rate	= meson_clk_pll_recalc_rate,
+	.round_rate	= meson_clk_pll_round_rate,
+	.set_rate	= meson_clk_pll_set_rate,
+};
+
+static const struct clk_ops meson_clk_pll_ro_ops = {
+	.recalc_rate	= meson_clk_pll_recalc_rate,
+};
+
+struct clk *meson_clk_register_pll(const struct clk_conf *clk_conf,
+				   void __iomem *reg_base,
+				   spinlock_t *lock)
+{
+	struct clk *clk;
+	struct meson_clk_pll *clk_pll;
+	struct clk_init_data init;
+
+	clk_pll = kzalloc(sizeof(*clk_pll), GFP_KERNEL);
+	if (!clk_pll)
+		return ERR_PTR(-ENOMEM);
+
+	clk_pll->base = reg_base + clk_conf->reg_off;
+	clk_pll->lock = lock;
+	clk_pll->conf = clk_conf->conf.pll;
+
+	init.name = clk_conf->clk_name;
+	init.flags = clk_conf->flags | CLK_GET_RATE_NOCACHE;
+
+	init.parent_names = &clk_conf->clks_parent[0];
+	init.num_parents = 1;
+	init.ops = &meson_clk_pll_ro_ops;
+
+	/* If no rate_table is specified we assume the PLL is read-only */
+	if (clk_pll->conf->rate_table) {
+		int len;
+
+		for (len = 0; clk_pll->conf->rate_table[len].rate != 0; )
+			len++;
+
+		 clk_pll->rate_count = len;
+		 init.ops = &meson_clk_pll_ops;
+	}
+
+	clk_pll->hw.init = &init;
+
+	clk = clk_register(NULL, &clk_pll->hw);
+	if (IS_ERR(clk))
+		kfree(clk_pll);
+
+	return clk;
+}
diff --git a/drivers/clk/meson/clkc.c b/drivers/clk/meson/clkc.c
new file mode 100644
index 0000000..b8c511c
--- /dev/null
+++ b/drivers/clk/meson/clkc.c
@@ -0,0 +1,250 @@
+/*
+ * Copyright (c) 2015 Endless Mobile, Inc.
+ * Author: Carlo Caione <carlo@endlessm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/mfd/syscon.h>
+#include <linux/slab.h>
+
+#include "clkc.h"
+
+static DEFINE_SPINLOCK(clk_lock);
+
+static struct clk **clks;
+static struct clk_onecell_data clk_data;
+
+struct clk ** __init meson_clk_init(struct device_node *np,
+				   unsigned long nr_clks)
+{
+	clks = kcalloc(nr_clks, sizeof(*clks), GFP_KERNEL);
+	if (!clks)
+		return ERR_PTR(-ENOMEM);
+
+	clk_data.clks = clks;
+	clk_data.clk_num = nr_clks;
+	of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data);
+
+	return clks;
+}
+
+static void meson_clk_add_lookup(struct clk *clk, unsigned int id)
+{
+	if (clks && id)
+		clks[id] = clk;
+}
+
+static struct clk * __init
+meson_clk_register_composite(const struct clk_conf *clk_conf,
+			     void __iomem *clk_base)
+{
+	struct clk *clk;
+	struct clk_mux *mux = NULL;
+	struct clk_divider *div = NULL;
+	struct clk_gate *gate = NULL;
+	const struct clk_ops *mux_ops = NULL;
+	const struct composite_conf *composite_conf;
+
+	composite_conf = clk_conf->conf.composite;
+
+	if (clk_conf->num_parents > 1) {
+		mux = kzalloc(sizeof(*mux), GFP_KERNEL);
+		if (!mux)
+			return ERR_PTR(-ENOMEM);
+
+		mux->reg = clk_base + clk_conf->reg_off
+				+ composite_conf->mux_parm.reg_off;
+		mux->shift = composite_conf->mux_parm.shift;
+		mux->mask = BIT(composite_conf->mux_parm.width) - 1;
+		mux->flags = composite_conf->mux_flags;
+		mux->lock = &clk_lock;
+		mux->table = composite_conf->mux_table;
+		mux_ops = (composite_conf->mux_flags & CLK_MUX_READ_ONLY) ?
+			  &clk_mux_ro_ops : &clk_mux_ops;
+	}
+
+	if (MESON_PARM_APPLICABLE(&composite_conf->div_parm)) {
+		div = kzalloc(sizeof(*div), GFP_KERNEL);
+		if (!div) {
+			clk = ERR_PTR(-ENOMEM);
+			goto error;
+		}
+
+		div->reg = clk_base + clk_conf->reg_off
+				+ composite_conf->div_parm.reg_off;
+		div->shift = composite_conf->div_parm.shift;
+		div->width = composite_conf->div_parm.width;
+		div->lock = &clk_lock;
+		div->flags = composite_conf->div_flags;
+		div->table = composite_conf->div_table;
+	}
+
+	if (MESON_PARM_APPLICABLE(&composite_conf->gate_parm)) {
+		gate = kzalloc(sizeof(*gate), GFP_KERNEL);
+		if (!gate) {
+			clk = ERR_PTR(-ENOMEM);
+			goto error;
+		}
+
+		gate->reg = clk_base + clk_conf->reg_off
+				+ composite_conf->div_parm.reg_off;
+		gate->bit_idx = composite_conf->gate_parm.shift;
+		gate->flags = composite_conf->gate_flags;
+		gate->lock = &clk_lock;
+	}
+
+	clk = clk_register_composite(NULL, clk_conf->clk_name,
+				    clk_conf->clks_parent,
+				    clk_conf->num_parents,
+				    mux ? &mux->hw : NULL, mux_ops,
+				    div ? &div->hw : NULL, &clk_divider_ops,
+				    gate ? &gate->hw : NULL, &clk_gate_ops,
+				    clk_conf->flags);
+	if (IS_ERR(clk))
+		goto error;
+
+	return clk;
+
+error:
+	kfree(gate);
+	kfree(div);
+	kfree(mux);
+
+	return clk;
+}
+
+static struct clk * __init
+meson_clk_register_fixed_factor(const struct clk_conf *clk_conf,
+				void __iomem *clk_base)
+{
+	struct clk *clk;
+	const struct fixed_fact_conf *fixed_fact_conf;
+	const struct parm *p;
+	unsigned int mult, div;
+	u32 reg;
+
+	fixed_fact_conf = &clk_conf->conf.fixed_fact;
+
+	mult = clk_conf->conf.fixed_fact.mult;
+	div = clk_conf->conf.fixed_fact.div;
+
+	if (!mult) {
+		mult = 1;
+		p = &fixed_fact_conf->mult_parm;
+		if (MESON_PARM_APPLICABLE(p)) {
+			reg = readl(clk_base + clk_conf->reg_off + p->reg_off);
+			mult = PARM_GET(p->width, p->shift, reg);
+		}
+	}
+
+	if (!div) {
+		div = 1;
+		p = &fixed_fact_conf->div_parm;
+		if (MESON_PARM_APPLICABLE(p)) {
+			reg = readl(clk_base + clk_conf->reg_off + p->reg_off);
+			mult = PARM_GET(p->width, p->shift, reg);
+		}
+	}
+
+	clk = clk_register_fixed_factor(NULL,
+			clk_conf->clk_name,
+			clk_conf->clks_parent[0],
+			clk_conf->flags,
+			mult, div);
+
+	return clk;
+}
+
+static struct clk * __init
+meson_clk_register_fixed_rate(const struct clk_conf *clk_conf,
+			      void __iomem *clk_base)
+{
+	struct clk *clk;
+	const struct fixed_rate_conf *fixed_rate_conf;
+	const struct parm *r;
+	unsigned long rate;
+	u32 reg;
+
+	fixed_rate_conf = &clk_conf->conf.fixed_rate;
+	rate = fixed_rate_conf->rate;
+
+	if (!rate) {
+		r = &fixed_rate_conf->rate_parm;
+		reg = readl(clk_base + clk_conf->reg_off + r->reg_off);
+		rate = PARM_GET(r->width, r->shift, reg);
+	}
+
+	rate *= 1000000;
+
+	clk = clk_register_fixed_rate(NULL,
+			clk_conf->clk_name,
+			clk_conf->num_parents
+				? clk_conf->clks_parent[0] : NULL,
+			clk_conf->flags, rate);
+
+	return clk;
+}
+
+void __init meson_clk_register_clks(const struct clk_conf *clk_confs,
+				    size_t nr_confs,
+				    void __iomem *clk_base)
+{
+	unsigned int i;
+	struct clk *clk = NULL;
+
+	for (i = 0; i < nr_confs; i++) {
+		const struct clk_conf *clk_conf = &clk_confs[i];
+
+		switch (clk_conf->clk_type) {
+		case CLK_FIXED_RATE:
+			clk = meson_clk_register_fixed_rate(clk_conf,
+							    clk_base);
+			break;
+		case CLK_FIXED_FACTOR:
+			clk = meson_clk_register_fixed_factor(clk_conf,
+							      clk_base);
+			break;
+		case CLK_COMPOSITE:
+			clk = meson_clk_register_composite(clk_conf,
+							   clk_base);
+			break;
+		case CLK_CPU:
+			clk = meson_clk_register_cpu(clk_conf, clk_base,
+						     &clk_lock);
+			break;
+		case CLK_PLL:
+			clk = meson_clk_register_pll(clk_conf, clk_base,
+						     &clk_lock);
+			break;
+		default:
+			clk = NULL;
+		}
+
+		if (!clk) {
+			pr_err("%s: unknown clock type %d\n", __func__,
+			       clk_conf->clk_type);
+			continue;
+		}
+
+		if (IS_ERR(clk)) {
+			pr_warn("%s: Unable to create %s clock\n", __func__,
+				clk_conf->clk_name);
+			continue;
+		}
+
+		meson_clk_add_lookup(clk, clk_conf->clk_id);
+	}
+}
diff --git a/drivers/clk/meson/clkc.h b/drivers/clk/meson/clkc.h
new file mode 100644
index 0000000..609ae92
--- /dev/null
+++ b/drivers/clk/meson/clkc.h
@@ -0,0 +1,187 @@
+/*
+ * Copyright (c) 2015 Endless Mobile, Inc.
+ * Author: Carlo Caione <carlo@endlessm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __CLKC_H
+#define __CLKC_H
+
+#define PMASK(width)			GENMASK(width - 1, 0)
+#define SETPMASK(width, shift)		GENMASK(shift + width - 1, shift)
+#define CLRPMASK(width, shift)		(~SETPMASK(width, shift))
+
+#define PARM_GET(width, shift, reg)					\
+	(((reg) & SETPMASK(width, shift)) >> (shift))
+#define PARM_SET(width, shift, reg, val)				\
+	(((reg) & CLRPMASK(width, shift)) | (val << (shift)))
+
+#define MESON_PARM_APPLICABLE(p)		(!!((p)->width))
+
+struct parm {
+	u16	reg_off;
+	u8	shift;
+	u8	width;
+};
+#define PARM(_r, _s, _w)						\
+	{								\
+		.reg_off	= (_r),					\
+		.shift		= (_s),					\
+		.width		= (_w),					\
+	}								\
+
+struct pll_rate_table {
+	unsigned long	rate;
+	u16		m;
+	u16		n;
+	u16		od;
+};
+#define PLL_RATE(_r, _m, _n, _od)					\
+	{								\
+		.rate		= (_r),					\
+		.m		= (_m),					\
+		.n		= (_n),					\
+		.od		= (_od),				\
+	}								\
+
+struct pll_conf {
+	const struct pll_rate_table	*rate_table;
+	struct parm			m;
+	struct parm			n;
+	struct parm			od;
+};
+
+struct fixed_fact_conf {
+	unsigned int	div;
+	unsigned int	mult;
+	struct parm	div_parm;
+	struct parm	mult_parm;
+};
+
+struct fixed_rate_conf {
+	unsigned long	rate;
+	struct parm	rate_parm;
+};
+
+struct composite_conf {
+	struct parm		mux_parm;
+	struct parm		div_parm;
+	struct parm		gate_parm;
+	struct clk_div_table	*div_table;
+	u32			*mux_table;
+	u8			mux_flags;
+	u8			div_flags;
+	u8			gate_flags;
+};
+
+#define PNAME(x) static const char *x[]
+
+enum clk_type {
+	CLK_FIXED_FACTOR,
+	CLK_FIXED_RATE,
+	CLK_COMPOSITE,
+	CLK_CPU,
+	CLK_PLL,
+};
+
+struct clk_conf {
+	u16				reg_off;
+	enum clk_type			clk_type;
+	unsigned int			clk_id;
+	const char			*clk_name;
+	const char			**clks_parent;
+	int				num_parents;
+	unsigned long			flags;
+	union {
+		struct fixed_fact_conf		fixed_fact;
+		struct fixed_rate_conf		fixed_rate;
+		const struct composite_conf		*composite;
+		struct pll_conf			*pll;
+		const struct clk_div_table	*div_table;
+	} conf;
+};
+
+#define FIXED_RATE_P(_ro, _ci, _cn, _f, _c)				\
+	{								\
+		.reg_off			= (_ro),		\
+		.clk_type			= CLK_FIXED_RATE,	\
+		.clk_id				= (_ci),		\
+		.clk_name			= (_cn),		\
+		.flags				= (_f),			\
+		.conf.fixed_rate.rate_parm	= _c,			\
+	}								\
+
+#define FIXED_RATE(_ci, _cn, _f, _r)					\
+	{								\
+		.clk_type			= CLK_FIXED_RATE,	\
+		.clk_id				= (_ci),		\
+		.clk_name			= (_cn),		\
+		.flags				= (_f),			\
+		.conf.fixed_rate.rate		= (_r),			\
+	}								\
+
+#define PLL(_ro, _ci, _cn, _cp, _f, _c)					\
+	{								\
+		.reg_off			= (_ro),		\
+		.clk_type			= CLK_PLL,		\
+		.clk_id				= (_ci),		\
+		.clk_name			= (_cn),		\
+		.clks_parent			= (_cp),		\
+		.num_parents			= ARRAY_SIZE(_cp),	\
+		.flags				= (_f),			\
+		.conf.pll			= (_c),			\
+	}								\
+
+#define FIXED_FACTOR_DIV(_ci, _cn, _cp, _f, _d)				\
+	{								\
+		.clk_type			= CLK_FIXED_FACTOR,	\
+		.clk_id				= (_ci),		\
+		.clk_name			= (_cn),		\
+		.clks_parent			= (_cp),		\
+		.num_parents			= ARRAY_SIZE(_cp),	\
+		.conf.fixed_fact.div		= (_d),			\
+	}								\
+
+#define CPU(_ro, _ci, _cn, _cp, _dt)					\
+	{								\
+		.reg_off			= (_ro),		\
+		.clk_type			= CLK_CPU,		\
+		.clk_id				= (_ci),		\
+		.clk_name			= (_cn),		\
+		.clks_parent			= (_cp),		\
+		.num_parents			= ARRAY_SIZE(_cp),	\
+		.conf.div_table			= (_dt),		\
+	}								\
+
+#define COMPOSITE(_ro, _ci, _cn, _cp, _f, _c)				\
+	{								\
+		.reg_off			= (_ro),		\
+		.clk_type			= CLK_COMPOSITE,	\
+		.clk_id				= (_ci),		\
+		.clk_name			= (_cn),		\
+		.clks_parent			= (_cp),		\
+		.num_parents			= ARRAY_SIZE(_cp),	\
+		.flags				= (_f),			\
+		.conf.composite			= (_c),			\
+	}								\
+
+struct clk **meson_clk_init(struct device_node *np, unsigned long nr_clks);
+void meson_clk_register_clks(const struct clk_conf *clk_confs,
+			     unsigned int nr_confs, void __iomem *clk_base);
+struct clk *meson_clk_register_cpu(const struct clk_conf *clk_conf,
+				   void __iomem *reg_base, spinlock_t *lock);
+struct clk *meson_clk_register_pll(const struct clk_conf *clk_conf,
+				   void __iomem *reg_base, spinlock_t *lock);
+
+#endif /* __CLKC_H */
diff --git a/drivers/clk/meson/meson8b-clkc.c b/drivers/clk/meson/meson8b-clkc.c
new file mode 100644
index 0000000..61f6d55
--- /dev/null
+++ b/drivers/clk/meson/meson8b-clkc.c
@@ -0,0 +1,196 @@
+/*
+ * Copyright (c) 2015 Endless Mobile, Inc.
+ * Author: Carlo Caione <carlo@endlessm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+#include <dt-bindings/clock/meson8b-clkc.h>
+
+#include "clkc.h"
+
+#define MESON8B_REG_CTL0_ADDR		0x0000
+#define MESON8B_REG_SYS_CPU_CNTL1	0x015c
+#define MESON8B_REG_HHI_MPEG		0x0174
+#define MESON8B_REG_MALI		0x01b0
+#define MESON8B_REG_PLL_FIXED		0x0280
+#define MESON8B_REG_PLL_SYS		0x0300
+#define MESON8B_REG_PLL_VID		0x0320
+
+static const struct pll_rate_table sys_pll_rate_table[] = {
+	PLL_RATE(312000000, 52, 1, 2),
+	PLL_RATE(336000000, 56, 1, 2),
+	PLL_RATE(360000000, 60, 1, 2),
+	PLL_RATE(384000000, 64, 1, 2),
+	PLL_RATE(408000000, 68, 1, 2),
+	PLL_RATE(432000000, 72, 1, 2),
+	PLL_RATE(456000000, 76, 1, 2),
+	PLL_RATE(480000000, 80, 1, 2),
+	PLL_RATE(504000000, 84, 1, 2),
+	PLL_RATE(528000000, 88, 1, 2),
+	PLL_RATE(552000000, 92, 1, 2),
+	PLL_RATE(576000000, 96, 1, 2),
+	PLL_RATE(600000000, 50, 1, 1),
+	PLL_RATE(624000000, 52, 1, 1),
+	PLL_RATE(648000000, 54, 1, 1),
+	PLL_RATE(672000000, 56, 1, 1),
+	PLL_RATE(696000000, 58, 1, 1),
+	PLL_RATE(720000000, 60, 1, 1),
+	PLL_RATE(744000000, 62, 1, 1),
+	PLL_RATE(768000000, 64, 1, 1),
+	PLL_RATE(792000000, 66, 1, 1),
+	PLL_RATE(816000000, 68, 1, 1),
+	PLL_RATE(840000000, 70, 1, 1),
+	PLL_RATE(864000000, 72, 1, 1),
+	PLL_RATE(888000000, 74, 1, 1),
+	PLL_RATE(912000000, 76, 1, 1),
+	PLL_RATE(936000000, 78, 1, 1),
+	PLL_RATE(960000000, 80, 1, 1),
+	PLL_RATE(984000000, 82, 1, 1),
+	PLL_RATE(1008000000, 84, 1, 1),
+	PLL_RATE(1032000000, 86, 1, 1),
+	PLL_RATE(1056000000, 88, 1, 1),
+	PLL_RATE(1080000000, 90, 1, 1),
+	PLL_RATE(1104000000, 92, 1, 1),
+	PLL_RATE(1128000000, 94, 1, 1),
+	PLL_RATE(1152000000, 96, 1, 1),
+	PLL_RATE(1176000000, 98, 1, 1),
+	PLL_RATE(1200000000, 50, 1, 0),
+	PLL_RATE(1224000000, 51, 1, 0),
+	PLL_RATE(1248000000, 52, 1, 0),
+	PLL_RATE(1272000000, 53, 1, 0),
+	PLL_RATE(1296000000, 54, 1, 0),
+	PLL_RATE(1320000000, 55, 1, 0),
+	PLL_RATE(1344000000, 56, 1, 0),
+	PLL_RATE(1368000000, 57, 1, 0),
+	PLL_RATE(1392000000, 58, 1, 0),
+	PLL_RATE(1416000000, 59, 1, 0),
+	PLL_RATE(1440000000, 60, 1, 0),
+	PLL_RATE(1464000000, 61, 1, 0),
+	PLL_RATE(1488000000, 62, 1, 0),
+	PLL_RATE(1512000000, 63, 1, 0),
+	PLL_RATE(1536000000, 64, 1, 0),
+	{ /* sentinel */ },
+};
+
+static const struct clk_div_table cpu_div_table[] = {
+	{ .val = 1, .div = 1 },
+	{ .val = 2, .div = 2 },
+	{ .val = 3, .div = 3 },
+	{ .val = 2, .div = 4 },
+	{ .val = 3, .div = 6 },
+	{ .val = 4, .div = 8 },
+	{ .val = 5, .div = 10 },
+	{ .val = 6, .div = 12 },
+	{ .val = 7, .div = 14 },
+	{ .val = 8, .div = 16 },
+	{ /* sentinel */ },
+};
+
+PNAME(p_xtal)		= { "xtal" };
+PNAME(p_fclk_div)	= { "fixed_pll" };
+PNAME(p_cpu_clk)	= { "sys_pll" };
+PNAME(p_clk81)		= { "fclk_div3", "fclk_div4", "fclk_div5" };
+PNAME(p_mali)		= { "fclk_div3", "fclk_div4", "fclk_div5",
+			    "fclk_div7", "zero" };
+
+static u32 mux_table_clk81[]	= { 6, 5, 7 };
+static u32 mux_table_mali[]	= { 6, 5, 7, 4, 0 };
+
+static struct pll_conf pll_confs = {
+	.m		= PARM(0x00, 0,  9),
+	.n		= PARM(0x00, 9,  5),
+	.od		= PARM(0x00, 16, 2),
+};
+
+static struct pll_conf sys_pll_conf = {
+	.m		= PARM(0x00, 0,  9),
+	.n		= PARM(0x00, 9,  5),
+	.od		= PARM(0x00, 16, 2),
+	.rate_table	= sys_pll_rate_table,
+};
+
+static const struct composite_conf clk81_conf __initconst = {
+	.mux_table		= mux_table_clk81,
+	.mux_flags		= CLK_MUX_READ_ONLY,
+	.mux_parm		= PARM(0x00, 12, 3),
+	.div_parm		= PARM(0x00, 0, 7),
+	.gate_parm		= PARM(0x00, 7, 1),
+};
+
+static const struct composite_conf mali_conf __initconst = {
+	.mux_table		= mux_table_mali,
+	.mux_parm		= PARM(0x00, 9, 3),
+	.div_parm		= PARM(0x00, 0, 7),
+	.gate_parm		= PARM(0x00, 8, 1),
+};
+
+static const struct clk_conf meson8b_xtal_conf __initconst =
+	FIXED_RATE_P(MESON8B_REG_CTL0_ADDR, CLKID_XTAL, "xtal",
+		     CLK_IS_ROOT, PARM(0x00, 4, 7));
+
+static const struct clk_conf meson8b_clk_confs[] __initconst = {
+	FIXED_RATE(CLKID_ZERO, "zero", CLK_IS_ROOT, 0),
+	PLL(MESON8B_REG_PLL_FIXED, CLKID_PLL_FIXED, "fixed_pll",
+	    p_xtal, 0, &pll_confs),
+	PLL(MESON8B_REG_PLL_VID, CLKID_PLL_VID, "vid_pll",
+	    p_xtal, 0, &pll_confs),
+	PLL(MESON8B_REG_PLL_SYS, CLKID_PLL_SYS, "sys_pll",
+	    p_xtal, 0, &sys_pll_conf),
+	FIXED_FACTOR_DIV(CLKID_FCLK_DIV2, "fclk_div2", p_fclk_div, 0, 2),
+	FIXED_FACTOR_DIV(CLKID_FCLK_DIV3, "fclk_div3", p_fclk_div, 0, 3),
+	FIXED_FACTOR_DIV(CLKID_FCLK_DIV4, "fclk_div4", p_fclk_div, 0, 4),
+	FIXED_FACTOR_DIV(CLKID_FCLK_DIV5, "fclk_div5", p_fclk_div, 0, 5),
+	FIXED_FACTOR_DIV(CLKID_FCLK_DIV7, "fclk_div7", p_fclk_div, 0, 7),
+	CPU(MESON8B_REG_SYS_CPU_CNTL1, CLKID_CPUCLK, "a5_clk", p_cpu_clk,
+	    cpu_div_table),
+	COMPOSITE(MESON8B_REG_HHI_MPEG, CLKID_CLK81, "clk81", p_clk81,
+		  CLK_SET_RATE_NO_REPARENT | CLK_IGNORE_UNUSED, &clk81_conf),
+	COMPOSITE(MESON8B_REG_MALI, CLKID_MALI, "mali", p_mali,
+		  CLK_IGNORE_UNUSED, &mali_conf),
+};
+
+static void __init meson8b_clkc_init(struct device_node *np)
+{
+	void __iomem *clk_base;
+
+	if (!meson_clk_init(np, CLK_NR_CLKS))
+		return;
+
+	/* XTAL */
+	clk_base = of_iomap(np, 0);
+	if (!clk_base) {
+		pr_err("%s: Unable to map xtal base\n", __func__);
+		return;
+	}
+
+	meson_clk_register_clks(&meson8b_xtal_conf, 1, clk_base);
+	iounmap(clk_base);
+
+	/*  Generic clocks and PLLs */
+	clk_base = of_iomap(np, 1);
+	if (!clk_base) {
+		pr_err("%s: Unable to map clk base\n", __func__);
+		return;
+	}
+
+	meson_clk_register_clks(meson8b_clk_confs,
+				ARRAY_SIZE(meson8b_clk_confs),
+				clk_base);
+}
+CLK_OF_DECLARE(meson8b_clock, "amlogic,meson8b-clkc", meson8b_clkc_init);
diff --git a/drivers/clk/mmp/Makefile b/drivers/clk/mmp/Makefile
index 3caaf7c..9d4bc41 100644
--- a/drivers/clk/mmp/Makefile
+++ b/drivers/clk/mmp/Makefile
@@ -12,3 +12,5 @@
 obj-$(CONFIG_CPU_PXA168) += clk-pxa168.o
 obj-$(CONFIG_CPU_PXA910) += clk-pxa910.o
 obj-$(CONFIG_CPU_MMP2) += clk-mmp2.o
+
+obj-y += clk-of-pxa1928.o
diff --git a/drivers/clk/mmp/clk-apbc.c b/drivers/clk/mmp/clk-apbc.c
index d14120e..09d41c7 100644
--- a/drivers/clk/mmp/clk-apbc.c
+++ b/drivers/clk/mmp/clk-apbc.c
@@ -115,7 +115,7 @@
 		spin_unlock_irqrestore(apbc->lock, flags);
 }
 
-struct clk_ops clk_apbc_ops = {
+static struct clk_ops clk_apbc_ops = {
 	.prepare = clk_apbc_prepare,
 	.unprepare = clk_apbc_unprepare,
 };
diff --git a/drivers/clk/mmp/clk-apmu.c b/drivers/clk/mmp/clk-apmu.c
index abe182b..cdcf2d7 100644
--- a/drivers/clk/mmp/clk-apmu.c
+++ b/drivers/clk/mmp/clk-apmu.c
@@ -61,7 +61,7 @@
 		spin_unlock_irqrestore(apmu->lock, flags);
 }
 
-struct clk_ops clk_apmu_ops = {
+static struct clk_ops clk_apmu_ops = {
 	.enable = clk_apmu_enable,
 	.disable = clk_apmu_disable,
 };
diff --git a/drivers/clk/mmp/clk-mmp2.c b/drivers/clk/mmp/clk-mmp2.c
index 5c90a42..09d2832 100644
--- a/drivers/clk/mmp/clk-mmp2.c
+++ b/drivers/clk/mmp/clk-mmp2.c
@@ -63,10 +63,8 @@
 };
 
 static struct mmp_clk_factor_tbl uart_factor_tbl[] = {
-	{.num = 14634, .den = 2165},	/*14.745MHZ */
+	{.num = 8125, .den = 1536},	/*14.745MHZ */
 	{.num = 3521, .den = 689},	/*19.23MHZ */
-	{.num = 9679, .den = 5728},	/*58.9824MHZ */
-	{.num = 15850, .den = 9451},	/*59.429MHZ */
 };
 
 static const char *uart_parent[] = {"uart_pll", "vctcxo"};
diff --git a/drivers/clk/mmp/clk-of-mmp2.c b/drivers/clk/mmp/clk-of-mmp2.c
index 2cbc2b4..251533d 100644
--- a/drivers/clk/mmp/clk-of-mmp2.c
+++ b/drivers/clk/mmp/clk-of-mmp2.c
@@ -30,6 +30,7 @@
 #define APBC_TWSI4	0x7c
 #define APBC_TWSI5	0x80
 #define APBC_KPC	0x18
+#define APBC_TIMER	0x24
 #define APBC_UART0	0x2c
 #define APBC_UART1	0x30
 #define APBC_UART2	0x34
@@ -98,10 +99,8 @@
 };
 
 static struct mmp_clk_factor_tbl uart_factor_tbl[] = {
-	{.num = 14634, .den = 2165},	/*14.745MHZ */
+	{.num = 8125, .den = 1536},	/*14.745MHZ */
 	{.num = 3521, .den = 689},	/*19.23MHZ */
-	{.num = 9679, .den = 5728},	/*58.9824MHZ */
-	{.num = 15850, .den = 9451},	/*59.429MHZ */
 };
 
 static void mmp2_pll_init(struct mmp2_clk_unit *pxa_unit)
@@ -134,6 +133,9 @@
 static DEFINE_SPINLOCK(ssp3_lock);
 static const char *ssp_parent_names[] = {"vctcxo_4", "vctcxo_2", "vctcxo", "pll1_16"};
 
+static DEFINE_SPINLOCK(timer_lock);
+static const char *timer_parent_names[] = {"clk32", "vctcxo_2", "vctcxo_4", "vctcxo"};
+
 static DEFINE_SPINLOCK(reset_lock);
 
 static struct mmp_param_mux_clk apbc_mux_clks[] = {
@@ -145,6 +147,7 @@
 	{0, "ssp1_mux", ssp_parent_names, ARRAY_SIZE(ssp_parent_names), CLK_SET_RATE_PARENT, APBC_SSP1, 4, 3, 0, &ssp1_lock},
 	{0, "ssp2_mux", ssp_parent_names, ARRAY_SIZE(ssp_parent_names), CLK_SET_RATE_PARENT, APBC_SSP2, 4, 3, 0, &ssp2_lock},
 	{0, "ssp3_mux", ssp_parent_names, ARRAY_SIZE(ssp_parent_names), CLK_SET_RATE_PARENT, APBC_SSP3, 4, 3, 0, &ssp3_lock},
+	{0, "timer_mux", timer_parent_names, ARRAY_SIZE(timer_parent_names), CLK_SET_RATE_PARENT, APBC_TIMER, 4, 3, 0, &timer_lock},
 };
 
 static struct mmp_param_gate_clk apbc_gate_clks[] = {
@@ -170,6 +173,7 @@
 	{MMP2_CLK_SSP1, "ssp1_clk", "ssp1_mux", CLK_SET_RATE_PARENT, APBC_SSP1, 0x7, 0x3, 0x0, 0, &ssp1_lock},
 	{MMP2_CLK_SSP2, "ssp2_clk", "ssp2_mux", CLK_SET_RATE_PARENT, APBC_SSP2, 0x7, 0x3, 0x0, 0, &ssp2_lock},
 	{MMP2_CLK_SSP3, "ssp3_clk", "ssp3_mux", CLK_SET_RATE_PARENT, APBC_SSP3, 0x7, 0x3, 0x0, 0, &ssp3_lock},
+	{MMP2_CLK_TIMER, "timer_clk", "timer_mux", CLK_SET_RATE_PARENT, APBC_TIMER, 0x7, 0x3, 0x0, 0, &timer_lock},
 };
 
 static void mmp2_apb_periph_clk_init(struct mmp2_clk_unit *pxa_unit)
diff --git a/drivers/clk/mmp/clk-of-pxa168.c b/drivers/clk/mmp/clk-of-pxa168.c
index 5b1810d..64eaf41 100644
--- a/drivers/clk/mmp/clk-of-pxa168.c
+++ b/drivers/clk/mmp/clk-of-pxa168.c
@@ -32,6 +32,7 @@
 #define APBC_PWM1	0x10
 #define APBC_PWM2	0x14
 #define APBC_PWM3	0x18
+#define APBC_TIMER	0x34
 #define APBC_SSP0	0x81c
 #define APBC_SSP1	0x820
 #define APBC_SSP2	0x84c
@@ -58,6 +59,7 @@
 	{PXA168_CLK_CLK32, "clk32", NULL, CLK_IS_ROOT, 32768},
 	{PXA168_CLK_VCTCXO, "vctcxo", NULL, CLK_IS_ROOT, 26000000},
 	{PXA168_CLK_PLL1, "pll1", NULL, CLK_IS_ROOT, 624000000},
+	{PXA168_CLK_USB_PLL, "usb_pll", NULL, CLK_IS_ROOT, 480000000},
 };
 
 static struct mmp_param_fixed_factor_clk fixed_factor_clks[] = {
@@ -70,6 +72,7 @@
 	{PXA168_CLK_PLL1_24, "pll1_24", "pll1_12", 1, 2, 0},
 	{PXA168_CLK_PLL1_48, "pll1_48", "pll1_24", 1, 2, 0},
 	{PXA168_CLK_PLL1_96, "pll1_96", "pll1_48", 1, 2, 0},
+	{PXA168_CLK_PLL1_192, "pll1_192", "pll1_96", 1, 2, 0},
 	{PXA168_CLK_PLL1_13, "pll1_13", "pll1", 1, 13, 0},
 	{PXA168_CLK_PLL1_13_1_5, "pll1_13_1_5", "pll1_13", 2, 3, 0},
 	{PXA168_CLK_PLL1_2_1_5, "pll1_2_1_5", "pll1_2", 2, 3, 0},
@@ -119,6 +122,9 @@
 static DEFINE_SPINLOCK(ssp4_lock);
 static const char *ssp_parent_names[] = {"pll1_96", "pll1_48", "pll1_24", "pll1_12"};
 
+static DEFINE_SPINLOCK(timer_lock);
+static const char *timer_parent_names[] = {"pll1_48", "clk32", "pll1_96", "pll1_192"};
+
 static DEFINE_SPINLOCK(reset_lock);
 
 static struct mmp_param_mux_clk apbc_mux_clks[] = {
@@ -130,6 +136,7 @@
 	{0, "ssp2_mux", ssp_parent_names, ARRAY_SIZE(ssp_parent_names), CLK_SET_RATE_PARENT, APBC_SSP2, 4, 3, 0, &ssp2_lock},
 	{0, "ssp3_mux", ssp_parent_names, ARRAY_SIZE(ssp_parent_names), CLK_SET_RATE_PARENT, APBC_SSP3, 4, 3, 0, &ssp3_lock},
 	{0, "ssp4_mux", ssp_parent_names, ARRAY_SIZE(ssp_parent_names), CLK_SET_RATE_PARENT, APBC_SSP4, 4, 3, 0, &ssp4_lock},
+	{0, "timer_mux", timer_parent_names, ARRAY_SIZE(timer_parent_names), CLK_SET_RATE_PARENT, APBC_TIMER, 4, 3, 0, &timer_lock},
 };
 
 static struct mmp_param_gate_clk apbc_gate_clks[] = {
@@ -151,6 +158,7 @@
 	{PXA168_CLK_SSP2, "ssp2_clk", "ssp2_mux", CLK_SET_RATE_PARENT, APBC_SSP2, 0x3, 0x3, 0x0, 0, &ssp2_lock},
 	{PXA168_CLK_SSP3, "ssp3_clk", "ssp3_mux", CLK_SET_RATE_PARENT, APBC_SSP3, 0x3, 0x3, 0x0, 0, &ssp3_lock},
 	{PXA168_CLK_SSP4, "ssp4_clk", "ssp4_mux", CLK_SET_RATE_PARENT, APBC_SSP4, 0x3, 0x3, 0x0, 0, &ssp4_lock},
+	{PXA168_CLK_TIMER, "timer_clk", "timer_mux", CLK_SET_RATE_PARENT, APBC_TIMER, 0x3, 0x3, 0x0, 0, &timer_lock},
 };
 
 static void pxa168_apb_periph_clk_init(struct pxa168_clk_unit *pxa_unit)
diff --git a/drivers/clk/mmp/clk-of-pxa1928.c b/drivers/clk/mmp/clk-of-pxa1928.c
new file mode 100644
index 0000000..433a5ae
--- /dev/null
+++ b/drivers/clk/mmp/clk-of-pxa1928.c
@@ -0,0 +1,265 @@
+/*
+ * pxa1928 clock framework source file
+ *
+ * Copyright (C) 2015 Linaro, Ltd.
+ * Rob Herring <robh@kernel.org>
+ *
+ * Based on drivers/clk/mmp/clk-of-mmp2.c:
+ * Copyright (C) 2012 Marvell
+ * Chao Xie <xiechao.mail@gmail.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include <dt-bindings/clock/marvell,pxa1928.h>
+
+#include "clk.h"
+#include "reset.h"
+
+#define MPMU_UART_PLL	0x14
+
+struct pxa1928_clk_unit {
+	struct mmp_clk_unit unit;
+	void __iomem *mpmu_base;
+	void __iomem *apmu_base;
+	void __iomem *apbc_base;
+	void __iomem *apbcp_base;
+};
+
+static struct mmp_param_fixed_rate_clk fixed_rate_clks[] = {
+	{0, "clk32", NULL, CLK_IS_ROOT, 32768},
+	{0, "vctcxo", NULL, CLK_IS_ROOT, 26000000},
+	{0, "pll1_624", NULL, CLK_IS_ROOT, 624000000},
+	{0, "pll5p", NULL, CLK_IS_ROOT, 832000000},
+	{0, "pll5", NULL, CLK_IS_ROOT, 1248000000},
+	{0, "usb_pll", NULL, CLK_IS_ROOT, 480000000},
+};
+
+static struct mmp_param_fixed_factor_clk fixed_factor_clks[] = {
+	{0, "pll1_d2", "pll1_624", 1, 2, 0},
+	{0, "pll1_d9", "pll1_624", 1, 9, 0},
+	{0, "pll1_d12", "pll1_624", 1, 12, 0},
+	{0, "pll1_d16", "pll1_624", 1, 16, 0},
+	{0, "pll1_d20", "pll1_624", 1, 20, 0},
+	{0, "pll1_416", "pll1_624", 2, 3, 0},
+	{0, "vctcxo_d2", "vctcxo", 1, 2, 0},
+	{0, "vctcxo_d4", "vctcxo", 1, 4, 0},
+};
+
+static struct mmp_clk_factor_masks uart_factor_masks = {
+	.factor = 2,
+	.num_mask = 0x1fff,
+	.den_mask = 0x1fff,
+	.num_shift = 16,
+	.den_shift = 0,
+};
+
+static struct mmp_clk_factor_tbl uart_factor_tbl[] = {
+	{.num = 832, .den = 234},	/*58.5MHZ */
+	{.num = 1, .den = 1},		/*26MHZ */
+};
+
+static void pxa1928_pll_init(struct pxa1928_clk_unit *pxa_unit)
+{
+	struct clk *clk;
+	struct mmp_clk_unit *unit = &pxa_unit->unit;
+
+	mmp_register_fixed_rate_clks(unit, fixed_rate_clks,
+					ARRAY_SIZE(fixed_rate_clks));
+
+	mmp_register_fixed_factor_clks(unit, fixed_factor_clks,
+					ARRAY_SIZE(fixed_factor_clks));
+
+	clk = mmp_clk_register_factor("uart_pll", "pll1_416",
+				CLK_SET_RATE_PARENT,
+				pxa_unit->mpmu_base + MPMU_UART_PLL,
+				&uart_factor_masks, uart_factor_tbl,
+				ARRAY_SIZE(uart_factor_tbl), NULL);
+}
+
+static DEFINE_SPINLOCK(uart0_lock);
+static DEFINE_SPINLOCK(uart1_lock);
+static DEFINE_SPINLOCK(uart2_lock);
+static DEFINE_SPINLOCK(uart3_lock);
+static const char *uart_parent_names[] = {"uart_pll", "vctcxo"};
+
+static DEFINE_SPINLOCK(ssp0_lock);
+static DEFINE_SPINLOCK(ssp1_lock);
+static const char *ssp_parent_names[] = {"vctcxo_d4", "vctcxo_d2", "vctcxo", "pll1_d12"};
+
+static DEFINE_SPINLOCK(reset_lock);
+
+static struct mmp_param_mux_clk apbc_mux_clks[] = {
+	{0, "uart0_mux", uart_parent_names, ARRAY_SIZE(uart_parent_names), CLK_SET_RATE_PARENT, PXA1928_CLK_UART0 * 4, 4, 3, 0, &uart0_lock},
+	{0, "uart1_mux", uart_parent_names, ARRAY_SIZE(uart_parent_names), CLK_SET_RATE_PARENT, PXA1928_CLK_UART1 * 4, 4, 3, 0, &uart1_lock},
+	{0, "uart2_mux", uart_parent_names, ARRAY_SIZE(uart_parent_names), CLK_SET_RATE_PARENT, PXA1928_CLK_UART2 * 4, 4, 3, 0, &uart2_lock},
+	{0, "uart3_mux", uart_parent_names, ARRAY_SIZE(uart_parent_names), CLK_SET_RATE_PARENT, PXA1928_CLK_UART3 * 4, 4, 3, 0, &uart3_lock},
+	{0, "ssp0_mux", ssp_parent_names, ARRAY_SIZE(ssp_parent_names), CLK_SET_RATE_PARENT, PXA1928_CLK_SSP0 * 4, 4, 3, 0, &ssp0_lock},
+	{0, "ssp1_mux", ssp_parent_names, ARRAY_SIZE(ssp_parent_names), CLK_SET_RATE_PARENT, PXA1928_CLK_SSP1 * 4, 4, 3, 0, &ssp1_lock},
+};
+
+static struct mmp_param_gate_clk apbc_gate_clks[] = {
+	{PXA1928_CLK_TWSI0, "twsi0_clk", "vctcxo", CLK_SET_RATE_PARENT, PXA1928_CLK_TWSI0 * 4, 0x3, 0x3, 0x0, 0, &reset_lock},
+	{PXA1928_CLK_TWSI1, "twsi1_clk", "vctcxo", CLK_SET_RATE_PARENT, PXA1928_CLK_TWSI1 * 4, 0x3, 0x3, 0x0, 0, &reset_lock},
+	{PXA1928_CLK_TWSI2, "twsi2_clk", "vctcxo", CLK_SET_RATE_PARENT, PXA1928_CLK_TWSI2 * 4, 0x3, 0x3, 0x0, 0, &reset_lock},
+	{PXA1928_CLK_TWSI3, "twsi3_clk", "vctcxo", CLK_SET_RATE_PARENT, PXA1928_CLK_TWSI3 * 4, 0x3, 0x3, 0x0, 0, &reset_lock},
+	{PXA1928_CLK_TWSI4, "twsi4_clk", "vctcxo", CLK_SET_RATE_PARENT, PXA1928_CLK_TWSI4 * 4, 0x3, 0x3, 0x0, 0, &reset_lock},
+	{PXA1928_CLK_TWSI5, "twsi5_clk", "vctcxo", CLK_SET_RATE_PARENT, PXA1928_CLK_TWSI5 * 4, 0x3, 0x3, 0x0, 0, &reset_lock},
+	{PXA1928_CLK_GPIO, "gpio_clk", "vctcxo", CLK_SET_RATE_PARENT, PXA1928_CLK_GPIO * 4, 0x3, 0x3, 0x0, 0, &reset_lock},
+	{PXA1928_CLK_KPC, "kpc_clk", "clk32", CLK_SET_RATE_PARENT, PXA1928_CLK_KPC * 4, 0x3, 0x3, 0x0, MMP_CLK_GATE_NEED_DELAY, NULL},
+	{PXA1928_CLK_RTC, "rtc_clk", "clk32", CLK_SET_RATE_PARENT, PXA1928_CLK_RTC * 4, 0x83, 0x83, 0x0, MMP_CLK_GATE_NEED_DELAY, NULL},
+	{PXA1928_CLK_PWM0, "pwm0_clk", "vctcxo", CLK_SET_RATE_PARENT, PXA1928_CLK_PWM0 * 4, 0x3, 0x3, 0x0, 0, &reset_lock},
+	{PXA1928_CLK_PWM1, "pwm1_clk", "vctcxo", CLK_SET_RATE_PARENT, PXA1928_CLK_PWM1 * 4, 0x3, 0x3, 0x0, 0, &reset_lock},
+	{PXA1928_CLK_PWM2, "pwm2_clk", "vctcxo", CLK_SET_RATE_PARENT, PXA1928_CLK_PWM2 * 4, 0x3, 0x3, 0x0, 0, &reset_lock},
+	{PXA1928_CLK_PWM3, "pwm3_clk", "vctcxo", CLK_SET_RATE_PARENT, PXA1928_CLK_PWM3 * 4, 0x3, 0x3, 0x0, 0, &reset_lock},
+	/* The gate clocks has mux parent. */
+	{PXA1928_CLK_UART0, "uart0_clk", "uart0_mux", CLK_SET_RATE_PARENT, PXA1928_CLK_UART0 * 4, 0x3, 0x3, 0x0, 0, &uart0_lock},
+	{PXA1928_CLK_UART1, "uart1_clk", "uart1_mux", CLK_SET_RATE_PARENT, PXA1928_CLK_UART1 * 4, 0x3, 0x3, 0x0, 0, &uart1_lock},
+	{PXA1928_CLK_UART2, "uart2_clk", "uart2_mux", CLK_SET_RATE_PARENT, PXA1928_CLK_UART2 * 4, 0x3, 0x3, 0x0, 0, &uart2_lock},
+	{PXA1928_CLK_UART3, "uart3_clk", "uart3_mux", CLK_SET_RATE_PARENT, PXA1928_CLK_UART3 * 4, 0x3, 0x3, 0x0, 0, &uart3_lock},
+	{PXA1928_CLK_SSP0, "ssp0_clk", "ssp0_mux", CLK_SET_RATE_PARENT, PXA1928_CLK_SSP0 * 4, 0x3, 0x3, 0x0, 0, &ssp0_lock},
+	{PXA1928_CLK_SSP1, "ssp1_clk", "ssp1_mux", CLK_SET_RATE_PARENT, PXA1928_CLK_SSP1 * 4, 0x3, 0x3, 0x0, 0, &ssp1_lock},
+};
+
+static void pxa1928_apb_periph_clk_init(struct pxa1928_clk_unit *pxa_unit)
+{
+	struct mmp_clk_unit *unit = &pxa_unit->unit;
+
+	mmp_register_mux_clks(unit, apbc_mux_clks, pxa_unit->apbc_base,
+				ARRAY_SIZE(apbc_mux_clks));
+
+	mmp_register_gate_clks(unit, apbc_gate_clks, pxa_unit->apbc_base,
+				ARRAY_SIZE(apbc_gate_clks));
+}
+
+static DEFINE_SPINLOCK(sdh0_lock);
+static DEFINE_SPINLOCK(sdh1_lock);
+static DEFINE_SPINLOCK(sdh2_lock);
+static DEFINE_SPINLOCK(sdh3_lock);
+static DEFINE_SPINLOCK(sdh4_lock);
+static const char *sdh_parent_names[] = {"pll1_624", "pll5p", "pll5", "pll1_416"};
+
+static DEFINE_SPINLOCK(usb_lock);
+
+static struct mmp_param_mux_clk apmu_mux_clks[] = {
+	{0, "sdh_mux", sdh_parent_names, ARRAY_SIZE(sdh_parent_names), CLK_SET_RATE_PARENT, PXA1928_CLK_SDH0 * 4, 8, 2, 0, &sdh0_lock},
+};
+
+static struct mmp_param_div_clk apmu_div_clks[] = {
+	{0, "sdh_div", "sdh_mux", 0, PXA1928_CLK_SDH0 * 4, 10, 4, CLK_DIVIDER_ONE_BASED, &sdh0_lock},
+};
+
+static struct mmp_param_gate_clk apmu_gate_clks[] = {
+	{PXA1928_CLK_USB, "usb_clk", "usb_pll", 0, PXA1928_CLK_USB * 4, 0x9, 0x9, 0x0, 0, &usb_lock},
+	{PXA1928_CLK_HSIC, "hsic_clk", "usb_pll", 0, PXA1928_CLK_HSIC * 4, 0x9, 0x9, 0x0, 0, &usb_lock},
+	/* The gate clocks has mux parent. */
+	{PXA1928_CLK_SDH0, "sdh0_clk", "sdh_div", CLK_SET_RATE_PARENT, PXA1928_CLK_SDH0 * 4, 0x1b, 0x1b, 0x0, 0, &sdh0_lock},
+	{PXA1928_CLK_SDH1, "sdh1_clk", "sdh_div", CLK_SET_RATE_PARENT, PXA1928_CLK_SDH1 * 4, 0x1b, 0x1b, 0x0, 0, &sdh1_lock},
+	{PXA1928_CLK_SDH2, "sdh2_clk", "sdh_div", CLK_SET_RATE_PARENT, PXA1928_CLK_SDH2 * 4, 0x1b, 0x1b, 0x0, 0, &sdh2_lock},
+	{PXA1928_CLK_SDH3, "sdh3_clk", "sdh_div", CLK_SET_RATE_PARENT, PXA1928_CLK_SDH3 * 4, 0x1b, 0x1b, 0x0, 0, &sdh3_lock},
+	{PXA1928_CLK_SDH4, "sdh4_clk", "sdh_div", CLK_SET_RATE_PARENT, PXA1928_CLK_SDH4 * 4, 0x1b, 0x1b, 0x0, 0, &sdh4_lock},
+};
+
+static void pxa1928_axi_periph_clk_init(struct pxa1928_clk_unit *pxa_unit)
+{
+	struct mmp_clk_unit *unit = &pxa_unit->unit;
+
+	mmp_register_mux_clks(unit, apmu_mux_clks, pxa_unit->apmu_base,
+				ARRAY_SIZE(apmu_mux_clks));
+
+	mmp_register_div_clks(unit, apmu_div_clks, pxa_unit->apmu_base,
+				ARRAY_SIZE(apmu_div_clks));
+
+	mmp_register_gate_clks(unit, apmu_gate_clks, pxa_unit->apmu_base,
+				ARRAY_SIZE(apmu_gate_clks));
+}
+
+static void pxa1928_clk_reset_init(struct device_node *np,
+				struct pxa1928_clk_unit *pxa_unit)
+{
+	struct mmp_clk_reset_cell *cells;
+	int i, base, nr_resets;
+
+	nr_resets = ARRAY_SIZE(apbc_gate_clks);
+	cells = kcalloc(nr_resets, sizeof(*cells), GFP_KERNEL);
+	if (!cells)
+		return;
+
+	base = 0;
+	for (i = 0; i < nr_resets; i++) {
+		cells[base + i].clk_id = apbc_gate_clks[i].id;
+		cells[base + i].reg =
+			pxa_unit->apbc_base + apbc_gate_clks[i].offset;
+		cells[base + i].flags = 0;
+		cells[base + i].lock = apbc_gate_clks[i].lock;
+		cells[base + i].bits = 0x4;
+	}
+
+	mmp_clk_reset_register(np, cells, nr_resets);
+}
+
+static void __init pxa1928_mpmu_clk_init(struct device_node *np)
+{
+	struct pxa1928_clk_unit *pxa_unit;
+
+	pxa_unit = kzalloc(sizeof(*pxa_unit), GFP_KERNEL);
+	if (!pxa_unit)
+		return;
+
+	pxa_unit->mpmu_base = of_iomap(np, 0);
+	if (!pxa_unit->mpmu_base) {
+		pr_err("failed to map mpmu registers\n");
+		return;
+	}
+
+	pxa1928_pll_init(pxa_unit);
+}
+CLK_OF_DECLARE(pxa1928_mpmu_clk, "marvell,pxa1928-mpmu", pxa1928_mpmu_clk_init);
+
+static void __init pxa1928_apmu_clk_init(struct device_node *np)
+{
+	struct pxa1928_clk_unit *pxa_unit;
+
+	pxa_unit = kzalloc(sizeof(*pxa_unit), GFP_KERNEL);
+	if (!pxa_unit)
+		return;
+
+	pxa_unit->apmu_base = of_iomap(np, 0);
+	if (!pxa_unit->apmu_base) {
+		pr_err("failed to map apmu registers\n");
+		return;
+	}
+
+	mmp_clk_init(np, &pxa_unit->unit, PXA1928_APMU_NR_CLKS);
+
+	pxa1928_axi_periph_clk_init(pxa_unit);
+}
+CLK_OF_DECLARE(pxa1928_apmu_clk, "marvell,pxa1928-apmu", pxa1928_apmu_clk_init);
+
+static void __init pxa1928_apbc_clk_init(struct device_node *np)
+{
+	struct pxa1928_clk_unit *pxa_unit;
+
+	pxa_unit = kzalloc(sizeof(*pxa_unit), GFP_KERNEL);
+	if (!pxa_unit)
+		return;
+
+	pxa_unit->apbc_base = of_iomap(np, 0);
+	if (!pxa_unit->apbc_base) {
+		pr_err("failed to map apbc registers\n");
+		return;
+	}
+
+	mmp_clk_init(np, &pxa_unit->unit, PXA1928_APBC_NR_CLKS);
+
+	pxa1928_apb_periph_clk_init(pxa_unit);
+	pxa1928_clk_reset_init(np, pxa_unit);
+}
+CLK_OF_DECLARE(pxa1928_apbc_clk, "marvell,pxa1928-apbc", pxa1928_apbc_clk_init);
diff --git a/drivers/clk/mmp/clk-of-pxa910.c b/drivers/clk/mmp/clk-of-pxa910.c
index 5e3c80d..13d6173 100644
--- a/drivers/clk/mmp/clk-of-pxa910.c
+++ b/drivers/clk/mmp/clk-of-pxa910.c
@@ -35,6 +35,8 @@
 #define APBC_SSP0	0x1c
 #define APBC_SSP1	0x20
 #define APBC_SSP2	0x4c
+#define APBC_TIMER0	0x30
+#define APBC_TIMER1	0x44
 #define APBCP_TWSI1	0x28
 #define APBCP_UART2	0x1c
 #define APMU_SDH0	0x54
@@ -57,6 +59,7 @@
 	{PXA910_CLK_CLK32, "clk32", NULL, CLK_IS_ROOT, 32768},
 	{PXA910_CLK_VCTCXO, "vctcxo", NULL, CLK_IS_ROOT, 26000000},
 	{PXA910_CLK_PLL1, "pll1", NULL, CLK_IS_ROOT, 624000000},
+	{PXA910_CLK_USB_PLL, "usb_pll", NULL, CLK_IS_ROOT, 480000000},
 };
 
 static struct mmp_param_fixed_factor_clk fixed_factor_clks[] = {
@@ -69,6 +72,7 @@
 	{PXA910_CLK_PLL1_24, "pll1_24", "pll1_12", 1, 2, 0},
 	{PXA910_CLK_PLL1_48, "pll1_48", "pll1_24", 1, 2, 0},
 	{PXA910_CLK_PLL1_96, "pll1_96", "pll1_48", 1, 2, 0},
+	{PXA910_CLK_PLL1_192, "pll1_192", "pll1_96", 1, 2, 0},
 	{PXA910_CLK_PLL1_13, "pll1_13", "pll1", 1, 13, 0},
 	{PXA910_CLK_PLL1_13_1_5, "pll1_13_1_5", "pll1_13", 2, 3, 0},
 	{PXA910_CLK_PLL1_2_1_5, "pll1_2_1_5", "pll1_2", 2, 3, 0},
@@ -115,6 +119,10 @@
 static DEFINE_SPINLOCK(ssp1_lock);
 static const char *ssp_parent_names[] = {"pll1_96", "pll1_48", "pll1_24", "pll1_12"};
 
+static DEFINE_SPINLOCK(timer0_lock);
+static DEFINE_SPINLOCK(timer1_lock);
+static const char *timer_parent_names[] = {"pll1_48", "clk32", "pll1_96"};
+
 static DEFINE_SPINLOCK(reset_lock);
 
 static struct mmp_param_mux_clk apbc_mux_clks[] = {
@@ -122,6 +130,8 @@
 	{0, "uart1_mux", uart_parent_names, ARRAY_SIZE(uart_parent_names), CLK_SET_RATE_PARENT, APBC_UART1, 4, 3, 0, &uart1_lock},
 	{0, "ssp0_mux", ssp_parent_names, ARRAY_SIZE(ssp_parent_names), CLK_SET_RATE_PARENT, APBC_SSP0, 4, 3, 0, &ssp0_lock},
 	{0, "ssp1_mux", ssp_parent_names, ARRAY_SIZE(ssp_parent_names), CLK_SET_RATE_PARENT, APBC_SSP1, 4, 3, 0, &ssp1_lock},
+	{0, "timer0_mux", timer_parent_names, ARRAY_SIZE(timer_parent_names), CLK_SET_RATE_PARENT, APBC_TIMER0, 4, 3, 0, &timer0_lock},
+	{0, "timer1_mux", timer_parent_names, ARRAY_SIZE(timer_parent_names), CLK_SET_RATE_PARENT, APBC_TIMER1, 4, 3, 0, &timer1_lock},
 };
 
 static struct mmp_param_mux_clk apbcp_mux_clks[] = {
@@ -142,6 +152,8 @@
 	{PXA910_CLK_UART1, "uart1_clk", "uart1_mux", CLK_SET_RATE_PARENT, APBC_UART1, 0x3, 0x3, 0x0, 0, &uart1_lock},
 	{PXA910_CLK_SSP0, "ssp0_clk", "ssp0_mux", CLK_SET_RATE_PARENT, APBC_SSP0, 0x3, 0x3, 0x0, 0, &ssp0_lock},
 	{PXA910_CLK_SSP1, "ssp1_clk", "ssp1_mux", CLK_SET_RATE_PARENT, APBC_SSP1, 0x3, 0x3, 0x0, 0, &ssp1_lock},
+	{PXA910_CLK_TIMER0, "timer0_clk", "timer0_mux", CLK_SET_RATE_PARENT, APBC_TIMER0, 0x3, 0x3, 0x0, 0, &timer0_lock},
+	{PXA910_CLK_TIMER1, "timer1_clk", "timer1_mux", CLK_SET_RATE_PARENT, APBC_TIMER1, 0x3, 0x3, 0x0, 0, &timer1_lock},
 };
 
 static struct mmp_param_gate_clk apbcp_gate_clks[] = {
diff --git a/drivers/clk/mvebu/armada-370.c b/drivers/clk/mvebu/armada-370.c
index 756f0f3..2c7c108 100644
--- a/drivers/clk/mvebu/armada-370.c
+++ b/drivers/clk/mvebu/armada-370.c
@@ -163,6 +163,7 @@
 	{ "pex1", "pex1_en", 9, 0 },
 	{ "sata0", NULL, 15, 0 },
 	{ "sdio", NULL, 17, 0 },
+	{ "crypto", NULL, 23, CLK_IGNORE_UNUSED },
 	{ "tdm", NULL, 25, 0 },
 	{ "ddr", NULL, 28, CLK_IGNORE_UNUSED },
 	{ "sata1", NULL, 30, 0 },
diff --git a/drivers/clk/mxs/clk-imx23.c b/drivers/clk/mxs/clk-imx23.c
index 22d136aa..32216f9 100644
--- a/drivers/clk/mxs/clk-imx23.c
+++ b/drivers/clk/mxs/clk-imx23.c
@@ -77,12 +77,12 @@
 	writel_relaxed(30 << BP_FRAC_IOFRAC, FRAC + SET);
 }
 
-static const char *sel_pll[]  __initdata = { "pll", "ref_xtal", };
-static const char *sel_cpu[]  __initdata = { "ref_cpu", "ref_xtal", };
-static const char *sel_pix[]  __initdata = { "ref_pix", "ref_xtal", };
-static const char *sel_io[]   __initdata = { "ref_io", "ref_xtal", };
-static const char *cpu_sels[] __initdata = { "cpu_pll", "cpu_xtal", };
-static const char *emi_sels[] __initdata = { "emi_pll", "emi_xtal", };
+static const char *const sel_pll[]  __initconst = { "pll", "ref_xtal", };
+static const char *const sel_cpu[]  __initconst = { "ref_cpu", "ref_xtal", };
+static const char *const sel_pix[]  __initconst = { "ref_pix", "ref_xtal", };
+static const char *const sel_io[]   __initconst = { "ref_io", "ref_xtal", };
+static const char *const cpu_sels[] __initconst = { "cpu_pll", "cpu_xtal", };
+static const char *const emi_sels[] __initconst = { "emi_pll", "emi_xtal", };
 
 enum imx23_clk {
 	ref_xtal, pll, ref_cpu, ref_emi, ref_pix, ref_io, saif_sel,
diff --git a/drivers/clk/mxs/clk-imx28.c b/drivers/clk/mxs/clk-imx28.c
index b1be374..a686708 100644
--- a/drivers/clk/mxs/clk-imx28.c
+++ b/drivers/clk/mxs/clk-imx28.c
@@ -125,15 +125,15 @@
 	writel_relaxed(val, FRAC0);
 }
 
-static const char *sel_cpu[]  __initdata = { "ref_cpu", "ref_xtal", };
-static const char *sel_io0[]  __initdata = { "ref_io0", "ref_xtal", };
-static const char *sel_io1[]  __initdata = { "ref_io1", "ref_xtal", };
-static const char *sel_pix[]  __initdata = { "ref_pix", "ref_xtal", };
-static const char *sel_gpmi[] __initdata = { "ref_gpmi", "ref_xtal", };
-static const char *sel_pll0[] __initdata = { "pll0", "ref_xtal", };
-static const char *cpu_sels[] __initdata = { "cpu_pll", "cpu_xtal", };
-static const char *emi_sels[] __initdata = { "emi_pll", "emi_xtal", };
-static const char *ptp_sels[] __initdata = { "ref_xtal", "pll0", };
+static const char *const sel_cpu[]  __initconst = { "ref_cpu", "ref_xtal", };
+static const char *const sel_io0[]  __initconst = { "ref_io0", "ref_xtal", };
+static const char *const sel_io1[]  __initconst = { "ref_io1", "ref_xtal", };
+static const char *const sel_pix[]  __initconst = { "ref_pix", "ref_xtal", };
+static const char *const sel_gpmi[] __initconst = { "ref_gpmi", "ref_xtal", };
+static const char *const sel_pll0[] __initconst = { "pll0", "ref_xtal", };
+static const char *const cpu_sels[] __initconst = { "cpu_pll", "cpu_xtal", };
+static const char *const emi_sels[] __initconst = { "emi_pll", "emi_xtal", };
+static const char *const ptp_sels[] __initconst = { "ref_xtal", "pll0", };
 
 enum imx28_clk {
 	ref_xtal, pll0, pll1, pll2, ref_cpu, ref_emi, ref_io0, ref_io1,
diff --git a/drivers/clk/mxs/clk.h b/drivers/clk/mxs/clk.h
index ef10ad9..f07d821 100644
--- a/drivers/clk/mxs/clk.h
+++ b/drivers/clk/mxs/clk.h
@@ -49,7 +49,7 @@
 }
 
 static inline struct clk *mxs_clk_mux(const char *name, void __iomem *reg,
-		u8 shift, u8 width, const char **parent_names, int num_parents)
+		u8 shift, u8 width, const char *const *parent_names, int num_parents)
 {
 	return clk_register_mux(NULL, name, parent_names, num_parents,
 				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
diff --git a/drivers/clk/nxp/Makefile b/drivers/clk/nxp/Makefile
new file mode 100644
index 0000000..7f608b0
--- /dev/null
+++ b/drivers/clk/nxp/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_ARCH_LPC18XX)	+= clk-lpc18xx-cgu.o
+obj-$(CONFIG_ARCH_LPC18XX)	+= clk-lpc18xx-ccu.o
diff --git a/drivers/clk/nxp/clk-lpc18xx-ccu.c b/drivers/clk/nxp/clk-lpc18xx-ccu.c
new file mode 100644
index 0000000..eeaee97
--- /dev/null
+++ b/drivers/clk/nxp/clk-lpc18xx-ccu.c
@@ -0,0 +1,293 @@
+/*
+ * Clk driver for NXP LPC18xx/LPC43xx Clock Control Unit (CCU)
+ *
+ * Copyright (C) 2015 Joachim Eastwood <manabian@gmail.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+
+#include <dt-bindings/clock/lpc18xx-ccu.h>
+
+/* Bit defines for CCU branch configuration register */
+#define LPC18XX_CCU_RUN		BIT(0)
+#define LPC18XX_CCU_AUTO	BIT(1)
+#define LPC18XX_CCU_DIV		BIT(5)
+#define LPC18XX_CCU_DIVSTAT	BIT(27)
+
+/* CCU branch feature bits */
+#define CCU_BRANCH_IS_BUS	BIT(0)
+#define CCU_BRANCH_HAVE_DIV2	BIT(1)
+
+#define to_clk_gate(_hw) container_of(_hw, struct clk_gate, hw)
+
+struct lpc18xx_branch_clk_data {
+	const char **name;
+	int num;
+};
+
+struct lpc18xx_clk_branch {
+	const char *base_name;
+	const char *name;
+	u16 offset;
+	u16 flags;
+	struct clk *clk;
+	struct clk_gate gate;
+};
+
+static struct lpc18xx_clk_branch clk_branches[] = {
+	{"base_apb3_clk", "apb3_bus",		CLK_APB3_BUS,		CCU_BRANCH_IS_BUS},
+	{"base_apb3_clk", "apb3_i2c1",		CLK_APB3_I2C1,		0},
+	{"base_apb3_clk", "apb3_dac",		CLK_APB3_DAC,		0},
+	{"base_apb3_clk", "apb3_adc0",		CLK_APB3_ADC0,		0},
+	{"base_apb3_clk", "apb3_adc1",		CLK_APB3_ADC1,		0},
+	{"base_apb3_clk", "apb3_can0",		CLK_APB3_CAN0,		0},
+
+	{"base_apb1_clk", "apb1_bus",		CLK_APB1_BUS,		CCU_BRANCH_IS_BUS},
+	{"base_apb1_clk", "apb1_mc_pwm",	CLK_APB1_MOTOCON_PWM,	0},
+	{"base_apb1_clk", "apb1_i2c0",		CLK_APB1_I2C0,		0},
+	{"base_apb1_clk", "apb1_i2s",		CLK_APB1_I2S,		0},
+	{"base_apb1_clk", "apb1_can1",		CLK_APB1_CAN1,		0},
+
+	{"base_spifi_clk", "spifi",		CLK_SPIFI,		0},
+
+	{"base_cpu_clk", "cpu_bus",		CLK_CPU_BUS,		CCU_BRANCH_IS_BUS},
+	{"base_cpu_clk", "cpu_spifi",		CLK_CPU_SPIFI,		0},
+	{"base_cpu_clk", "cpu_gpio",		CLK_CPU_GPIO,		0},
+	{"base_cpu_clk", "cpu_lcd",		CLK_CPU_LCD,		0},
+	{"base_cpu_clk", "cpu_ethernet",	CLK_CPU_ETHERNET,	0},
+	{"base_cpu_clk", "cpu_usb0",		CLK_CPU_USB0,		0},
+	{"base_cpu_clk", "cpu_emc",		CLK_CPU_EMC,		0},
+	{"base_cpu_clk", "cpu_sdio",		CLK_CPU_SDIO,		0},
+	{"base_cpu_clk", "cpu_dma",		CLK_CPU_DMA,		0},
+	{"base_cpu_clk", "cpu_core",		CLK_CPU_CORE,		0},
+	{"base_cpu_clk", "cpu_sct",		CLK_CPU_SCT,		0},
+	{"base_cpu_clk", "cpu_usb1",		CLK_CPU_USB1,		0},
+	{"base_cpu_clk", "cpu_emcdiv",		CLK_CPU_EMCDIV,		CCU_BRANCH_HAVE_DIV2},
+	{"base_cpu_clk", "cpu_flasha",		CLK_CPU_FLASHA,		CCU_BRANCH_HAVE_DIV2},
+	{"base_cpu_clk", "cpu_flashb",		CLK_CPU_FLASHB,		CCU_BRANCH_HAVE_DIV2},
+	{"base_cpu_clk", "cpu_m0app",		CLK_CPU_M0APP,		CCU_BRANCH_HAVE_DIV2},
+	{"base_cpu_clk", "cpu_adchs",		CLK_CPU_ADCHS,		CCU_BRANCH_HAVE_DIV2},
+	{"base_cpu_clk", "cpu_eeprom",		CLK_CPU_EEPROM,		CCU_BRANCH_HAVE_DIV2},
+	{"base_cpu_clk", "cpu_wwdt",		CLK_CPU_WWDT,		0},
+	{"base_cpu_clk", "cpu_uart0",		CLK_CPU_UART0,		0},
+	{"base_cpu_clk", "cpu_uart1",		CLK_CPU_UART1,		0},
+	{"base_cpu_clk", "cpu_ssp0",		CLK_CPU_SSP0,		0},
+	{"base_cpu_clk", "cpu_timer0",		CLK_CPU_TIMER0,		0},
+	{"base_cpu_clk", "cpu_timer1",		CLK_CPU_TIMER1,		0},
+	{"base_cpu_clk", "cpu_scu",		CLK_CPU_SCU,		0},
+	{"base_cpu_clk", "cpu_creg",		CLK_CPU_CREG,		0},
+	{"base_cpu_clk", "cpu_ritimer",		CLK_CPU_RITIMER,	0},
+	{"base_cpu_clk", "cpu_uart2",		CLK_CPU_UART2,		0},
+	{"base_cpu_clk", "cpu_uart3",		CLK_CPU_UART3,		0},
+	{"base_cpu_clk", "cpu_timer2",		CLK_CPU_TIMER2,		0},
+	{"base_cpu_clk", "cpu_timer3",		CLK_CPU_TIMER3,		0},
+	{"base_cpu_clk", "cpu_ssp1",		CLK_CPU_SSP1,		0},
+	{"base_cpu_clk", "cpu_qei",		CLK_CPU_QEI,		0},
+
+	{"base_periph_clk", "periph_bus",	CLK_PERIPH_BUS,		CCU_BRANCH_IS_BUS},
+	{"base_periph_clk", "periph_core",	CLK_PERIPH_CORE,	0},
+	{"base_periph_clk", "periph_sgpio",	CLK_PERIPH_SGPIO,	0},
+
+	{"base_usb0_clk",  "usb0",		CLK_USB0,		0},
+	{"base_usb1_clk",  "usb1",		CLK_USB1,		0},
+	{"base_spi_clk",   "spi",		CLK_SPI,		0},
+	{"base_adchs_clk", "adchs",		CLK_ADCHS,		0},
+
+	{"base_audio_clk", "audio",		CLK_AUDIO,		0},
+	{"base_uart3_clk", "apb2_uart3",	CLK_APB2_UART3,		0},
+	{"base_uart2_clk", "apb2_uart2",	CLK_APB2_UART2,		0},
+	{"base_uart1_clk", "apb0_uart1",	CLK_APB0_UART1,		0},
+	{"base_uart0_clk", "apb0_uart0",	CLK_APB0_UART0,		0},
+	{"base_ssp1_clk",  "apb2_ssp1",		CLK_APB2_SSP1,		0},
+	{"base_ssp0_clk",  "apb0_ssp0",		CLK_APB0_SSP0,		0},
+	{"base_sdio_clk",  "sdio",		CLK_SDIO,		0},
+};
+
+static struct clk *lpc18xx_ccu_branch_clk_get(struct of_phandle_args *clkspec,
+					      void *data)
+{
+	struct lpc18xx_branch_clk_data *clk_data = data;
+	unsigned int offset = clkspec->args[0];
+	int i, j;
+
+	for (i = 0; i < ARRAY_SIZE(clk_branches); i++) {
+		if (clk_branches[i].offset != offset)
+			continue;
+
+		for (j = 0; j < clk_data->num; j++) {
+			if (!strcmp(clk_branches[i].base_name, clk_data->name[j]))
+				return clk_branches[i].clk;
+		}
+	}
+
+	pr_err("%s: invalid clock offset %d\n", __func__, offset);
+
+	return ERR_PTR(-EINVAL);
+}
+
+static int lpc18xx_ccu_gate_endisable(struct clk_hw *hw, bool enable)
+{
+	struct clk_gate *gate = to_clk_gate(hw);
+	u32 val;
+
+	/*
+	 * Divider field is write only, so divider stat field must
+	 * be read so divider field can be set accordingly.
+	 */
+	val = clk_readl(gate->reg);
+	if (val & LPC18XX_CCU_DIVSTAT)
+		val |= LPC18XX_CCU_DIV;
+
+	if (enable) {
+		val |= LPC18XX_CCU_RUN;
+	} else {
+		/*
+		 * To safely disable a branch clock a squence of two separate
+		 * writes must be used. First write should set the AUTO bit
+		 * and the next write should clear the RUN bit.
+		 */
+		val |= LPC18XX_CCU_AUTO;
+		clk_writel(val, gate->reg);
+
+		val &= ~LPC18XX_CCU_RUN;
+	}
+
+	clk_writel(val, gate->reg);
+
+	return 0;
+}
+
+static int lpc18xx_ccu_gate_enable(struct clk_hw *hw)
+{
+	return lpc18xx_ccu_gate_endisable(hw, true);
+}
+
+static void lpc18xx_ccu_gate_disable(struct clk_hw *hw)
+{
+	lpc18xx_ccu_gate_endisable(hw, false);
+}
+
+static int lpc18xx_ccu_gate_is_enabled(struct clk_hw *hw)
+{
+	struct clk_gate *gate = to_clk_gate(hw);
+
+	return clk_readl(gate->reg) & LPC18XX_CCU_RUN;
+}
+
+static const struct clk_ops lpc18xx_ccu_gate_ops = {
+	.enable		= lpc18xx_ccu_gate_enable,
+	.disable	= lpc18xx_ccu_gate_disable,
+	.is_enabled	= lpc18xx_ccu_gate_is_enabled,
+};
+
+static void lpc18xx_ccu_register_branch_gate_div(struct lpc18xx_clk_branch *branch,
+						 void __iomem *reg_base,
+						 const char *parent)
+{
+	const struct clk_ops *div_ops = NULL;
+	struct clk_divider *div = NULL;
+	struct clk_hw *div_hw = NULL;
+
+	if (branch->flags & CCU_BRANCH_HAVE_DIV2) {
+		div = kzalloc(sizeof(*div), GFP_KERNEL);
+		if (!div)
+			return;
+
+		div->reg = branch->offset + reg_base;
+		div->flags = CLK_DIVIDER_READ_ONLY;
+		div->shift = 27;
+		div->width = 1;
+
+		div_hw = &div->hw;
+		div_ops = &clk_divider_ops;
+	}
+
+	branch->gate.reg = branch->offset + reg_base;
+	branch->gate.bit_idx = 0;
+
+	branch->clk = clk_register_composite(NULL, branch->name, &parent, 1,
+					     NULL, NULL,
+					     div_hw, div_ops,
+					     &branch->gate.hw, &lpc18xx_ccu_gate_ops, 0);
+	if (IS_ERR(branch->clk)) {
+		kfree(div);
+		pr_warn("%s: failed to register %s\n", __func__, branch->name);
+		return;
+	}
+
+	/* Grab essential branch clocks for CPU and SDRAM */
+	switch (branch->offset) {
+	case CLK_CPU_EMC:
+	case CLK_CPU_CORE:
+	case CLK_CPU_CREG:
+	case CLK_CPU_EMCDIV:
+		clk_prepare_enable(branch->clk);
+	}
+}
+
+static void lpc18xx_ccu_register_branch_clks(void __iomem *reg_base,
+					     const char *base_name)
+{
+	const char *parent = base_name;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(clk_branches); i++) {
+		if (strcmp(clk_branches[i].base_name, base_name))
+			continue;
+
+		lpc18xx_ccu_register_branch_gate_div(&clk_branches[i], reg_base,
+						     parent);
+
+		if (clk_branches[i].flags & CCU_BRANCH_IS_BUS)
+			parent = clk_branches[i].name;
+	}
+}
+
+static void __init lpc18xx_ccu_init(struct device_node *np)
+{
+	struct lpc18xx_branch_clk_data *clk_data;
+	void __iomem *reg_base;
+	int i, ret;
+
+	reg_base = of_iomap(np, 0);
+	if (!reg_base) {
+		pr_warn("%s: failed to map address range\n", __func__);
+		return;
+	}
+
+	clk_data = kzalloc(sizeof(*clk_data), GFP_KERNEL);
+	if (!clk_data)
+		return;
+
+	clk_data->num = of_property_count_strings(np, "clock-names");
+	clk_data->name = kcalloc(clk_data->num, sizeof(char *), GFP_KERNEL);
+	if (!clk_data->name) {
+		kfree(clk_data);
+		return;
+	}
+
+	for (i = 0; i < clk_data->num; i++) {
+		ret = of_property_read_string_index(np, "clock-names", i,
+						    &clk_data->name[i]);
+		if (ret) {
+			pr_warn("%s: failed to get clock name at idx %d\n",
+				__func__, i);
+			continue;
+		}
+
+		lpc18xx_ccu_register_branch_clks(reg_base, clk_data->name[i]);
+	}
+
+	of_clk_add_provider(np, lpc18xx_ccu_branch_clk_get, clk_data);
+}
+CLK_OF_DECLARE(lpc18xx_ccu, "nxp,lpc1850-ccu", lpc18xx_ccu_init);
diff --git a/drivers/clk/nxp/clk-lpc18xx-cgu.c b/drivers/clk/nxp/clk-lpc18xx-cgu.c
new file mode 100644
index 0000000..81e9e1c
--- /dev/null
+++ b/drivers/clk/nxp/clk-lpc18xx-cgu.c
@@ -0,0 +1,635 @@
+/*
+ * Clk driver for NXP LPC18xx/LPC43xx Clock Generation Unit (CGU)
+ *
+ * Copyright (C) 2015 Joachim Eastwood <manabian@gmail.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/delay.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+
+#include <dt-bindings/clock/lpc18xx-cgu.h>
+
+/* Clock Generation Unit (CGU) registers */
+#define LPC18XX_CGU_XTAL_OSC_CTRL	0x018
+#define LPC18XX_CGU_PLL0USB_STAT	0x01c
+#define LPC18XX_CGU_PLL0USB_CTRL	0x020
+#define LPC18XX_CGU_PLL0USB_MDIV	0x024
+#define LPC18XX_CGU_PLL0USB_NP_DIV	0x028
+#define LPC18XX_CGU_PLL0AUDIO_STAT	0x02c
+#define LPC18XX_CGU_PLL0AUDIO_CTRL	0x030
+#define LPC18XX_CGU_PLL0AUDIO_MDIV	0x034
+#define LPC18XX_CGU_PLL0AUDIO_NP_DIV	0x038
+#define LPC18XX_CGU_PLL0AUDIO_FRAC	0x03c
+#define LPC18XX_CGU_PLL1_STAT		0x040
+#define LPC18XX_CGU_PLL1_CTRL		0x044
+#define  LPC18XX_PLL1_CTRL_FBSEL	BIT(6)
+#define  LPC18XX_PLL1_CTRL_DIRECT	BIT(7)
+#define LPC18XX_CGU_IDIV_CTRL(n)	(0x048 + (n) * sizeof(u32))
+#define LPC18XX_CGU_BASE_CLK(id)	(0x05c + (id) * sizeof(u32))
+#define LPC18XX_CGU_PLL_CTRL_OFFSET	0x4
+
+/* PLL0 bits common to both audio and USB PLL */
+#define LPC18XX_PLL0_STAT_LOCK		BIT(0)
+#define LPC18XX_PLL0_CTRL_PD		BIT(0)
+#define LPC18XX_PLL0_CTRL_BYPASS	BIT(1)
+#define LPC18XX_PLL0_CTRL_DIRECTI	BIT(2)
+#define LPC18XX_PLL0_CTRL_DIRECTO	BIT(3)
+#define LPC18XX_PLL0_CTRL_CLKEN		BIT(4)
+#define LPC18XX_PLL0_MDIV_MDEC_MASK	0x1ffff
+#define LPC18XX_PLL0_MDIV_SELP_SHIFT	17
+#define LPC18XX_PLL0_MDIV_SELI_SHIFT	22
+#define LPC18XX_PLL0_MSEL_MAX		BIT(15)
+
+/* Register value that gives PLL0 post/pre dividers equal to 1 */
+#define LPC18XX_PLL0_NP_DIVS_1		0x00302062
+
+enum {
+	CLK_SRC_OSC32,
+	CLK_SRC_IRC,
+	CLK_SRC_ENET_RX_CLK,
+	CLK_SRC_ENET_TX_CLK,
+	CLK_SRC_GP_CLKIN,
+	CLK_SRC_RESERVED1,
+	CLK_SRC_OSC,
+	CLK_SRC_PLL0USB,
+	CLK_SRC_PLL0AUDIO,
+	CLK_SRC_PLL1,
+	CLK_SRC_RESERVED2,
+	CLK_SRC_RESERVED3,
+	CLK_SRC_IDIVA,
+	CLK_SRC_IDIVB,
+	CLK_SRC_IDIVC,
+	CLK_SRC_IDIVD,
+	CLK_SRC_IDIVE,
+	CLK_SRC_MAX
+};
+
+static const char *clk_src_names[CLK_SRC_MAX] = {
+	[CLK_SRC_OSC32]		= "osc32",
+	[CLK_SRC_IRC]		= "irc",
+	[CLK_SRC_ENET_RX_CLK]	= "enet_rx_clk",
+	[CLK_SRC_ENET_TX_CLK]	= "enet_tx_clk",
+	[CLK_SRC_GP_CLKIN]	= "gp_clkin",
+	[CLK_SRC_OSC]		= "osc",
+	[CLK_SRC_PLL0USB]	= "pll0usb",
+	[CLK_SRC_PLL0AUDIO]	= "pll0audio",
+	[CLK_SRC_PLL1]		= "pll1",
+	[CLK_SRC_IDIVA]		= "idiva",
+	[CLK_SRC_IDIVB]		= "idivb",
+	[CLK_SRC_IDIVC]		= "idivc",
+	[CLK_SRC_IDIVD]		= "idivd",
+	[CLK_SRC_IDIVE]		= "idive",
+};
+
+static const char *clk_base_names[BASE_CLK_MAX] = {
+	[BASE_SAFE_CLK]		= "base_safe_clk",
+	[BASE_USB0_CLK]		= "base_usb0_clk",
+	[BASE_PERIPH_CLK]	= "base_periph_clk",
+	[BASE_USB1_CLK]		= "base_usb1_clk",
+	[BASE_CPU_CLK]		= "base_cpu_clk",
+	[BASE_SPIFI_CLK]	= "base_spifi_clk",
+	[BASE_SPI_CLK]		= "base_spi_clk",
+	[BASE_PHY_RX_CLK]	= "base_phy_rx_clk",
+	[BASE_PHY_TX_CLK]	= "base_phy_tx_clk",
+	[BASE_APB1_CLK]		= "base_apb1_clk",
+	[BASE_APB3_CLK]		= "base_apb3_clk",
+	[BASE_LCD_CLK]		= "base_lcd_clk",
+	[BASE_ADCHS_CLK]	= "base_adchs_clk",
+	[BASE_SDIO_CLK]		= "base_sdio_clk",
+	[BASE_SSP0_CLK]		= "base_ssp0_clk",
+	[BASE_SSP1_CLK]		= "base_ssp1_clk",
+	[BASE_UART0_CLK]	= "base_uart0_clk",
+	[BASE_UART1_CLK]	= "base_uart1_clk",
+	[BASE_UART2_CLK]	= "base_uart2_clk",
+	[BASE_UART3_CLK]	= "base_uart3_clk",
+	[BASE_OUT_CLK]		= "base_out_clk",
+	[BASE_AUDIO_CLK]	= "base_audio_clk",
+	[BASE_CGU_OUT0_CLK]	= "base_cgu_out0_clk",
+	[BASE_CGU_OUT1_CLK]	= "base_cgu_out1_clk",
+};
+
+static u32 lpc18xx_cgu_pll0_src_ids[] = {
+	CLK_SRC_OSC32, CLK_SRC_IRC, CLK_SRC_ENET_RX_CLK,
+	CLK_SRC_ENET_TX_CLK, CLK_SRC_GP_CLKIN, CLK_SRC_OSC,
+	CLK_SRC_PLL1, CLK_SRC_IDIVA, CLK_SRC_IDIVB, CLK_SRC_IDIVC,
+	CLK_SRC_IDIVD, CLK_SRC_IDIVE,
+};
+
+static u32 lpc18xx_cgu_pll1_src_ids[] = {
+	CLK_SRC_OSC32, CLK_SRC_IRC, CLK_SRC_ENET_RX_CLK,
+	CLK_SRC_ENET_TX_CLK, CLK_SRC_GP_CLKIN, CLK_SRC_OSC,
+	CLK_SRC_PLL0USB, CLK_SRC_PLL0AUDIO, CLK_SRC_IDIVA,
+	CLK_SRC_IDIVB, CLK_SRC_IDIVC, CLK_SRC_IDIVD, CLK_SRC_IDIVE,
+};
+
+static u32 lpc18xx_cgu_idiva_src_ids[] = {
+	CLK_SRC_OSC32, CLK_SRC_IRC, CLK_SRC_ENET_RX_CLK,
+	CLK_SRC_ENET_TX_CLK, CLK_SRC_GP_CLKIN, CLK_SRC_OSC,
+	CLK_SRC_PLL0USB, CLK_SRC_PLL0AUDIO, CLK_SRC_PLL1
+};
+
+static u32 lpc18xx_cgu_idivbcde_src_ids[] = {
+	CLK_SRC_OSC32, CLK_SRC_IRC, CLK_SRC_ENET_RX_CLK,
+	CLK_SRC_ENET_TX_CLK, CLK_SRC_GP_CLKIN, CLK_SRC_OSC,
+	CLK_SRC_PLL0AUDIO, CLK_SRC_PLL1, CLK_SRC_IDIVA,
+};
+
+static u32 lpc18xx_cgu_base_irc_src_ids[] = {CLK_SRC_IRC};
+
+static u32 lpc18xx_cgu_base_usb0_src_ids[] = {CLK_SRC_PLL0USB};
+
+static u32 lpc18xx_cgu_base_common_src_ids[] = {
+	CLK_SRC_OSC32, CLK_SRC_IRC, CLK_SRC_ENET_RX_CLK,
+	CLK_SRC_ENET_TX_CLK, CLK_SRC_GP_CLKIN, CLK_SRC_OSC,
+	CLK_SRC_PLL0AUDIO, CLK_SRC_PLL1, CLK_SRC_IDIVA,
+	CLK_SRC_IDIVB, CLK_SRC_IDIVC, CLK_SRC_IDIVD, CLK_SRC_IDIVE,
+};
+
+static u32 lpc18xx_cgu_base_all_src_ids[] = {
+	CLK_SRC_OSC32, CLK_SRC_IRC, CLK_SRC_ENET_RX_CLK,
+	CLK_SRC_ENET_TX_CLK, CLK_SRC_GP_CLKIN, CLK_SRC_OSC,
+	CLK_SRC_PLL0USB, CLK_SRC_PLL0AUDIO, CLK_SRC_PLL1,
+	CLK_SRC_IDIVA, CLK_SRC_IDIVB, CLK_SRC_IDIVC,
+	CLK_SRC_IDIVD, CLK_SRC_IDIVE,
+};
+
+struct lpc18xx_cgu_src_clk_div {
+	u8 clk_id;
+	u8 n_parents;
+	struct clk_divider	div;
+	struct clk_mux		mux;
+	struct clk_gate		gate;
+};
+
+#define LPC1XX_CGU_SRC_CLK_DIV(_id, _width, _table)	\
+{							\
+	.clk_id = CLK_SRC_ ##_id,			\
+	.n_parents = ARRAY_SIZE(lpc18xx_cgu_ ##_table),	\
+	.div = {					\
+		.shift = 2,				\
+		.width = _width,			\
+	},						\
+	.mux = {					\
+		.mask = 0x1f,				\
+		.shift = 24,				\
+		.table = lpc18xx_cgu_ ##_table,		\
+	},						\
+	.gate = {					\
+		.bit_idx = 0,				\
+		.flags = CLK_GATE_SET_TO_DISABLE,	\
+	},						\
+}
+
+static struct lpc18xx_cgu_src_clk_div lpc18xx_cgu_src_clk_divs[] = {
+	LPC1XX_CGU_SRC_CLK_DIV(IDIVA, 2, idiva_src_ids),
+	LPC1XX_CGU_SRC_CLK_DIV(IDIVB, 4, idivbcde_src_ids),
+	LPC1XX_CGU_SRC_CLK_DIV(IDIVC, 4, idivbcde_src_ids),
+	LPC1XX_CGU_SRC_CLK_DIV(IDIVD, 4, idivbcde_src_ids),
+	LPC1XX_CGU_SRC_CLK_DIV(IDIVE, 8, idivbcde_src_ids),
+};
+
+struct lpc18xx_cgu_base_clk {
+	u8 clk_id;
+	u8 n_parents;
+	struct clk_mux mux;
+	struct clk_gate gate;
+};
+
+#define LPC1XX_CGU_BASE_CLK(_id, _table, _flags)	\
+{							\
+	.clk_id = BASE_ ##_id ##_CLK,			\
+	.n_parents = ARRAY_SIZE(lpc18xx_cgu_ ##_table),	\
+	.mux = {					\
+		.mask = 0x1f,				\
+		.shift = 24,				\
+		.table = lpc18xx_cgu_ ##_table,		\
+		.flags = _flags,			\
+	},						\
+	.gate = {					\
+		.bit_idx = 0,				\
+		.flags = CLK_GATE_SET_TO_DISABLE,	\
+	},						\
+}
+
+static struct lpc18xx_cgu_base_clk lpc18xx_cgu_base_clks[] = {
+	LPC1XX_CGU_BASE_CLK(SAFE,	base_irc_src_ids, CLK_MUX_READ_ONLY),
+	LPC1XX_CGU_BASE_CLK(USB0,	base_usb0_src_ids,   0),
+	LPC1XX_CGU_BASE_CLK(PERIPH,	base_common_src_ids, 0),
+	LPC1XX_CGU_BASE_CLK(USB1,	base_all_src_ids,    0),
+	LPC1XX_CGU_BASE_CLK(CPU,	base_common_src_ids, 0),
+	LPC1XX_CGU_BASE_CLK(SPIFI,	base_common_src_ids, 0),
+	LPC1XX_CGU_BASE_CLK(SPI,	base_common_src_ids, 0),
+	LPC1XX_CGU_BASE_CLK(PHY_RX,	base_common_src_ids, 0),
+	LPC1XX_CGU_BASE_CLK(PHY_TX,	base_common_src_ids, 0),
+	LPC1XX_CGU_BASE_CLK(APB1,	base_common_src_ids, 0),
+	LPC1XX_CGU_BASE_CLK(APB3,	base_common_src_ids, 0),
+	LPC1XX_CGU_BASE_CLK(LCD,	base_common_src_ids, 0),
+	LPC1XX_CGU_BASE_CLK(ADCHS,	base_common_src_ids, 0),
+	LPC1XX_CGU_BASE_CLK(SDIO,	base_common_src_ids, 0),
+	LPC1XX_CGU_BASE_CLK(SSP0,	base_common_src_ids, 0),
+	LPC1XX_CGU_BASE_CLK(SSP1,	base_common_src_ids, 0),
+	LPC1XX_CGU_BASE_CLK(UART0,	base_common_src_ids, 0),
+	LPC1XX_CGU_BASE_CLK(UART1,	base_common_src_ids, 0),
+	LPC1XX_CGU_BASE_CLK(UART2,	base_common_src_ids, 0),
+	LPC1XX_CGU_BASE_CLK(UART3,	base_common_src_ids, 0),
+	LPC1XX_CGU_BASE_CLK(OUT,	base_all_src_ids,    0),
+	{ /* 21 reserved */ },
+	{ /* 22 reserved */ },
+	{ /* 23 reserved */ },
+	{ /* 24 reserved */ },
+	LPC1XX_CGU_BASE_CLK(AUDIO,	base_common_src_ids, 0),
+	LPC1XX_CGU_BASE_CLK(CGU_OUT0,	base_all_src_ids,    0),
+	LPC1XX_CGU_BASE_CLK(CGU_OUT1,	base_all_src_ids,    0),
+};
+
+struct lpc18xx_pll {
+	struct		clk_hw hw;
+	void __iomem	*reg;
+	spinlock_t	*lock;
+	u8		flags;
+};
+
+#define to_lpc_pll(hw) container_of(hw, struct lpc18xx_pll, hw)
+
+struct lpc18xx_cgu_pll_clk {
+	u8 clk_id;
+	u8 n_parents;
+	u8 reg_offset;
+	struct clk_mux mux;
+	struct clk_gate gate;
+	struct lpc18xx_pll pll;
+	const struct clk_ops *pll_ops;
+};
+
+#define LPC1XX_CGU_CLK_PLL(_id, _table, _pll_ops)	\
+{							\
+	.clk_id = CLK_SRC_ ##_id,			\
+	.n_parents = ARRAY_SIZE(lpc18xx_cgu_ ##_table),	\
+	.reg_offset = LPC18XX_CGU_ ##_id ##_STAT,	\
+	.mux = {					\
+		.mask = 0x1f,				\
+		.shift = 24,				\
+		.table = lpc18xx_cgu_ ##_table,		\
+	},						\
+	.gate = {					\
+		.bit_idx = 0,				\
+		.flags = CLK_GATE_SET_TO_DISABLE,	\
+	},						\
+	.pll_ops = &lpc18xx_ ##_pll_ops,		\
+}
+
+/*
+ * PLL0 uses a special register value encoding. The compute functions below
+ * are taken or derived from the LPC1850 user manual (section 12.6.3.3).
+ */
+
+/* Compute PLL0 multiplier from decoded version */
+static u32 lpc18xx_pll0_mdec2msel(u32 x)
+{
+	int i;
+
+	switch (x) {
+	case 0x18003: return 1;
+	case 0x10003: return 2;
+	default:
+		for (i = LPC18XX_PLL0_MSEL_MAX + 1; x != 0x4000 && i > 0; i--)
+			x = ((x ^ x >> 14) & 1) | (x << 1 & 0x7fff);
+		return i;
+	}
+}
+/* Compute PLL0 decoded multiplier from binary version */
+static u32 lpc18xx_pll0_msel2mdec(u32 msel)
+{
+	u32 i, x = 0x4000;
+
+	switch (msel) {
+	case 0: return 0;
+	case 1: return 0x18003;
+	case 2: return 0x10003;
+	default:
+		for (i = msel; i <= LPC18XX_PLL0_MSEL_MAX; i++)
+			x = ((x ^ x >> 1) & 1) << 14 | (x >> 1 & 0xffff);
+		return x;
+	}
+}
+
+/* Compute PLL0 bandwidth SELI reg from multiplier */
+static u32 lpc18xx_pll0_msel2seli(u32 msel)
+{
+	u32 tmp;
+
+	if (msel > 16384) return 1;
+	if (msel >  8192) return 2;
+	if (msel >  2048) return 4;
+	if (msel >=  501) return 8;
+	if (msel >=   60) {
+		tmp = 1024 / (msel + 9);
+		return ((1024 == (tmp * (msel + 9))) == 0) ? tmp * 4 : (tmp + 1) * 4;
+	}
+
+	return (msel & 0x3c) + 4;
+}
+
+/* Compute PLL0 bandwidth SELP reg from multiplier */
+static u32 lpc18xx_pll0_msel2selp(u32 msel)
+{
+	if (msel < 60)
+		return (msel >> 1) + 1;
+
+	return 31;
+}
+
+static unsigned long lpc18xx_pll0_recalc_rate(struct clk_hw *hw,
+					      unsigned long parent_rate)
+{
+	struct lpc18xx_pll *pll = to_lpc_pll(hw);
+	u32 ctrl, mdiv, msel, npdiv;
+
+	ctrl = clk_readl(pll->reg + LPC18XX_CGU_PLL0USB_CTRL);
+	mdiv = clk_readl(pll->reg + LPC18XX_CGU_PLL0USB_MDIV);
+	npdiv = clk_readl(pll->reg + LPC18XX_CGU_PLL0USB_NP_DIV);
+
+	if (ctrl & LPC18XX_PLL0_CTRL_BYPASS)
+		return parent_rate;
+
+	if (npdiv != LPC18XX_PLL0_NP_DIVS_1) {
+		pr_warn("%s: pre/post dividers not supported\n", __func__);
+		return 0;
+	}
+
+	msel = lpc18xx_pll0_mdec2msel(mdiv & LPC18XX_PLL0_MDIV_MDEC_MASK);
+	if (msel)
+		return 2 * msel * parent_rate;
+
+	pr_warn("%s: unable to calculate rate\n", __func__);
+
+	return 0;
+}
+
+static long lpc18xx_pll0_round_rate(struct clk_hw *hw, unsigned long rate,
+				    unsigned long *prate)
+{
+	unsigned long m;
+
+	if (*prate < rate) {
+		pr_warn("%s: pll dividers not supported\n", __func__);
+		return -EINVAL;
+	}
+
+	m = DIV_ROUND_UP_ULL(*prate, rate * 2);
+	if (m <= 0 && m > LPC18XX_PLL0_MSEL_MAX) {
+		pr_warn("%s: unable to support rate %lu\n", __func__, rate);
+		return -EINVAL;
+	}
+
+	return 2 * *prate * m;
+}
+
+static int lpc18xx_pll0_set_rate(struct clk_hw *hw, unsigned long rate,
+				 unsigned long parent_rate)
+{
+	struct lpc18xx_pll *pll = to_lpc_pll(hw);
+	u32 ctrl, stat, m;
+	int retry = 3;
+
+	if (parent_rate < rate) {
+		pr_warn("%s: pll dividers not supported\n", __func__);
+		return -EINVAL;
+	}
+
+	m = DIV_ROUND_UP_ULL(parent_rate, rate * 2);
+	if (m <= 0 && m > LPC18XX_PLL0_MSEL_MAX) {
+		pr_warn("%s: unable to support rate %lu\n", __func__, rate);
+		return -EINVAL;
+	}
+
+	m  = lpc18xx_pll0_msel2mdec(m);
+	m |= lpc18xx_pll0_msel2selp(m) << LPC18XX_PLL0_MDIV_SELP_SHIFT;
+	m |= lpc18xx_pll0_msel2seli(m) << LPC18XX_PLL0_MDIV_SELI_SHIFT;
+
+	/* Power down PLL, disable clk output and dividers */
+	ctrl = clk_readl(pll->reg + LPC18XX_CGU_PLL0USB_CTRL);
+	ctrl |= LPC18XX_PLL0_CTRL_PD;
+	ctrl &= ~(LPC18XX_PLL0_CTRL_BYPASS | LPC18XX_PLL0_CTRL_DIRECTI |
+		  LPC18XX_PLL0_CTRL_DIRECTO | LPC18XX_PLL0_CTRL_CLKEN);
+	clk_writel(ctrl, pll->reg + LPC18XX_CGU_PLL0USB_CTRL);
+
+	/* Configure new PLL settings */
+	clk_writel(m, pll->reg + LPC18XX_CGU_PLL0USB_MDIV);
+	clk_writel(LPC18XX_PLL0_NP_DIVS_1, pll->reg + LPC18XX_CGU_PLL0USB_NP_DIV);
+
+	/* Power up PLL and wait for lock */
+	ctrl &= ~LPC18XX_PLL0_CTRL_PD;
+	clk_writel(ctrl, pll->reg + LPC18XX_CGU_PLL0USB_CTRL);
+	do {
+		udelay(10);
+		stat = clk_readl(pll->reg + LPC18XX_CGU_PLL0USB_STAT);
+		if (stat & LPC18XX_PLL0_STAT_LOCK) {
+			ctrl |= LPC18XX_PLL0_CTRL_CLKEN;
+			clk_writel(ctrl, pll->reg + LPC18XX_CGU_PLL0USB_CTRL);
+
+			return 0;
+		}
+	} while (retry--);
+
+	pr_warn("%s: unable to lock pll\n", __func__);
+
+	return -EINVAL;
+}
+
+static const struct clk_ops lpc18xx_pll0_ops = {
+	.recalc_rate	= lpc18xx_pll0_recalc_rate,
+	.round_rate	= lpc18xx_pll0_round_rate,
+	.set_rate	= lpc18xx_pll0_set_rate,
+};
+
+static unsigned long lpc18xx_pll1_recalc_rate(struct clk_hw *hw,
+					      unsigned long parent_rate)
+{
+	struct lpc18xx_pll *pll = to_lpc_pll(hw);
+	u16 msel, nsel, psel;
+	bool direct, fbsel;
+	u32 stat, ctrl;
+
+	stat = clk_readl(pll->reg + LPC18XX_CGU_PLL1_STAT);
+	ctrl = clk_readl(pll->reg + LPC18XX_CGU_PLL1_CTRL);
+
+	direct = (ctrl & LPC18XX_PLL1_CTRL_DIRECT) ? true : false;
+	fbsel = (ctrl & LPC18XX_PLL1_CTRL_FBSEL) ? true : false;
+
+	msel = ((ctrl >> 16) & 0xff) + 1;
+	nsel = ((ctrl >> 12) & 0x3) + 1;
+
+	if (direct || fbsel)
+		return msel * (parent_rate / nsel);
+
+	psel = (ctrl >>  8) & 0x3;
+	psel = 1 << psel;
+
+	return (msel / (2 * psel)) * (parent_rate / nsel);
+}
+
+static const struct clk_ops lpc18xx_pll1_ops = {
+	.recalc_rate = lpc18xx_pll1_recalc_rate,
+};
+
+static struct lpc18xx_cgu_pll_clk lpc18xx_cgu_src_clk_plls[] = {
+	LPC1XX_CGU_CLK_PLL(PLL0USB,	pll0_src_ids, pll0_ops),
+	LPC1XX_CGU_CLK_PLL(PLL0AUDIO,	pll0_src_ids, pll0_ops),
+	LPC1XX_CGU_CLK_PLL(PLL1,	pll1_src_ids, pll1_ops),
+};
+
+static void lpc18xx_fill_parent_names(const char **parent, u32 *id, int size)
+{
+	int i;
+
+	for (i = 0; i < size; i++)
+		parent[i] = clk_src_names[id[i]];
+}
+
+static struct clk *lpc18xx_cgu_register_div(struct lpc18xx_cgu_src_clk_div *clk,
+					    void __iomem *base, int n)
+{
+	void __iomem *reg = base + LPC18XX_CGU_IDIV_CTRL(n);
+	const char *name = clk_src_names[clk->clk_id];
+	const char *parents[CLK_SRC_MAX];
+
+	clk->div.reg = reg;
+	clk->mux.reg = reg;
+	clk->gate.reg = reg;
+
+	lpc18xx_fill_parent_names(parents, clk->mux.table, clk->n_parents);
+
+	return clk_register_composite(NULL, name, parents, clk->n_parents,
+				      &clk->mux.hw, &clk_mux_ops,
+				      &clk->div.hw, &clk_divider_ops,
+				      &clk->gate.hw, &clk_gate_ops, 0);
+}
+
+
+static struct clk *lpc18xx_register_base_clk(struct lpc18xx_cgu_base_clk *clk,
+					     void __iomem *reg_base, int n)
+{
+	void __iomem *reg = reg_base + LPC18XX_CGU_BASE_CLK(n);
+	const char *name = clk_base_names[clk->clk_id];
+	const char *parents[CLK_SRC_MAX];
+
+	if (clk->n_parents == 0)
+		return ERR_PTR(-ENOENT);
+
+	clk->mux.reg = reg;
+	clk->gate.reg = reg;
+
+	lpc18xx_fill_parent_names(parents, clk->mux.table, clk->n_parents);
+
+	/* SAFE_CLK can not be turned off */
+	if (n == BASE_SAFE_CLK)
+		return clk_register_composite(NULL, name, parents, clk->n_parents,
+					      &clk->mux.hw, &clk_mux_ops,
+					      NULL, NULL, NULL, NULL, 0);
+
+	return clk_register_composite(NULL, name, parents, clk->n_parents,
+				      &clk->mux.hw, &clk_mux_ops,
+				      NULL,  NULL,
+				      &clk->gate.hw, &clk_gate_ops, 0);
+}
+
+
+static struct clk *lpc18xx_cgu_register_pll(struct lpc18xx_cgu_pll_clk *clk,
+					    void __iomem *base)
+{
+	const char *name = clk_src_names[clk->clk_id];
+	const char *parents[CLK_SRC_MAX];
+
+	clk->pll.reg  = base;
+	clk->mux.reg  = base + clk->reg_offset + LPC18XX_CGU_PLL_CTRL_OFFSET;
+	clk->gate.reg = base + clk->reg_offset + LPC18XX_CGU_PLL_CTRL_OFFSET;
+
+	lpc18xx_fill_parent_names(parents, clk->mux.table, clk->n_parents);
+
+	return clk_register_composite(NULL, name, parents, clk->n_parents,
+				      &clk->mux.hw, &clk_mux_ops,
+				      &clk->pll.hw, clk->pll_ops,
+				      &clk->gate.hw, &clk_gate_ops, 0);
+}
+
+static void __init lpc18xx_cgu_register_source_clks(struct device_node *np,
+						    void __iomem *base)
+{
+	const char *parents[CLK_SRC_MAX];
+	struct clk *clk;
+	int i;
+
+	/* Register the internal 12 MHz RC oscillator (IRC) */
+	clk = clk_register_fixed_rate(NULL, clk_src_names[CLK_SRC_IRC],
+				      NULL, CLK_IS_ROOT, 12000000);
+	if (IS_ERR(clk))
+		pr_warn("%s: failed to register irc clk\n", __func__);
+
+	/* Register crystal oscillator controlller */
+	parents[0] = of_clk_get_parent_name(np, 0);
+	clk = clk_register_gate(NULL, clk_src_names[CLK_SRC_OSC], parents[0],
+				0, base + LPC18XX_CGU_XTAL_OSC_CTRL,
+				0, CLK_GATE_SET_TO_DISABLE, NULL);
+	if (IS_ERR(clk))
+		pr_warn("%s: failed to register osc clk\n", __func__);
+
+	/* Register all PLLs */
+	for (i = 0; i < ARRAY_SIZE(lpc18xx_cgu_src_clk_plls); i++) {
+		clk = lpc18xx_cgu_register_pll(&lpc18xx_cgu_src_clk_plls[i],
+						   base);
+		if (IS_ERR(clk))
+			pr_warn("%s: failed to register pll (%d)\n", __func__, i);
+	}
+
+	/* Register all clock dividers A-E */
+	for (i = 0; i < ARRAY_SIZE(lpc18xx_cgu_src_clk_divs); i++) {
+		clk = lpc18xx_cgu_register_div(&lpc18xx_cgu_src_clk_divs[i],
+					       base, i);
+		if (IS_ERR(clk))
+			pr_warn("%s: failed to register div %d\n", __func__, i);
+	}
+}
+
+static struct clk *clk_base[BASE_CLK_MAX];
+static struct clk_onecell_data clk_base_data = {
+	.clks = clk_base,
+	.clk_num = BASE_CLK_MAX,
+};
+
+static void __init lpc18xx_cgu_register_base_clks(void __iomem *reg_base)
+{
+	int i;
+
+	for (i = BASE_SAFE_CLK; i < BASE_CLK_MAX; i++) {
+		clk_base[i] = lpc18xx_register_base_clk(&lpc18xx_cgu_base_clks[i],
+							reg_base, i);
+		if (IS_ERR(clk_base[i]) && PTR_ERR(clk_base[i]) != -ENOENT)
+			pr_warn("%s: register base clk %d failed\n", __func__, i);
+	}
+}
+
+static void __init lpc18xx_cgu_init(struct device_node *np)
+{
+	void __iomem *reg_base;
+
+	reg_base = of_iomap(np, 0);
+	if (!reg_base) {
+		pr_warn("%s: failed to map address range\n", __func__);
+		return;
+	}
+
+	lpc18xx_cgu_register_source_clks(np, reg_base);
+	lpc18xx_cgu_register_base_clks(reg_base);
+
+	of_clk_add_provider(np, of_clk_src_onecell_get, &clk_base_data);
+}
+CLK_OF_DECLARE(lpc18xx_cgu, "nxp,lpc1850-cgu", lpc18xx_cgu_init);
diff --git a/drivers/clk/pistachio/clk-pll.c b/drivers/clk/pistachio/clk-pll.c
index de53756..e17dada 100644
--- a/drivers/clk/pistachio/clk-pll.c
+++ b/drivers/clk/pistachio/clk-pll.c
@@ -6,9 +6,12 @@
  * version 2, as published by the Free Software Foundation.
  */
 
+#define pr_fmt(fmt) "%s: " fmt, __func__
+
 #include <linux/clk-provider.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
+#include <linux/printk.h>
 #include <linux/slab.h>
 
 #include "clk.h"
@@ -50,6 +53,18 @@
 #define PLL_CTRL4			0x10
 #define PLL_FRAC_CTRL4_BYPASS		BIT(28)
 
+#define MIN_PFD				9600000UL
+#define MIN_VCO_LA			400000000UL
+#define MAX_VCO_LA			1600000000UL
+#define MIN_VCO_FRAC_INT		600000000UL
+#define MAX_VCO_FRAC_INT		1600000000UL
+#define MIN_VCO_FRAC_FRAC		600000000UL
+#define MAX_VCO_FRAC_FRAC		2400000000UL
+#define MIN_OUTPUT_LA			8000000UL
+#define MAX_OUTPUT_LA			1600000000UL
+#define MIN_OUTPUT_FRAC			12000000UL
+#define MAX_OUTPUT_FRAC			1600000000UL
+
 struct pistachio_clk_pll {
 	struct clk_hw hw;
 	void __iomem *base;
@@ -67,6 +82,12 @@
 	writel(val, pll->base + reg);
 }
 
+static inline void pll_lock(struct pistachio_clk_pll *pll)
+{
+	while (!(pll_readl(pll, PLL_STATUS) & PLL_STATUS_LOCK))
+		cpu_relax();
+}
+
 static inline u32 do_div_round_closest(u64 dividend, u32 divisor)
 {
 	dividend += divisor / 2;
@@ -124,6 +145,8 @@
 	val &= ~PLL_FRAC_CTRL4_BYPASS;
 	pll_writel(pll, val, PLL_CTRL4);
 
+	pll_lock(pll);
+
 	return 0;
 }
 
@@ -149,16 +172,29 @@
 {
 	struct pistachio_clk_pll *pll = to_pistachio_pll(hw);
 	struct pistachio_pll_rate_table *params;
-	bool was_enabled;
-	u32 val;
+	int enabled = pll_gf40lp_frac_is_enabled(hw);
+	u32 val, vco, old_postdiv1, old_postdiv2;
+	const char *name = __clk_get_name(hw->clk);
 
-	params = pll_get_params(pll, parent_rate, rate);
-	if (!params)
+	if (rate < MIN_OUTPUT_FRAC || rate > MAX_OUTPUT_FRAC)
 		return -EINVAL;
 
-	was_enabled = pll_gf40lp_frac_is_enabled(hw);
-	if (!was_enabled)
-		pll_gf40lp_frac_enable(hw);
+	params = pll_get_params(pll, parent_rate, rate);
+	if (!params || !params->refdiv)
+		return -EINVAL;
+
+	vco = params->fref * params->fbdiv / params->refdiv;
+	if (vco < MIN_VCO_FRAC_FRAC || vco > MAX_VCO_FRAC_FRAC)
+		pr_warn("%s: VCO %u is out of range %lu..%lu\n", name, vco,
+			MIN_VCO_FRAC_FRAC, MAX_VCO_FRAC_FRAC);
+
+	val = params->fref / params->refdiv;
+	if (val < MIN_PFD)
+		pr_warn("%s: PFD %u is too low (min %lu)\n",
+			name, val, MIN_PFD);
+	if (val > vco / 16)
+		pr_warn("%s: PFD %u is too high (max %u)\n",
+			name, val, vco / 16);
 
 	val = pll_readl(pll, PLL_CTRL1);
 	val &= ~((PLL_CTRL1_REFDIV_MASK << PLL_CTRL1_REFDIV_SHIFT) |
@@ -168,6 +204,19 @@
 	pll_writel(pll, val, PLL_CTRL1);
 
 	val = pll_readl(pll, PLL_CTRL2);
+
+	old_postdiv1 = (val >> PLL_FRAC_CTRL2_POSTDIV1_SHIFT) &
+		       PLL_FRAC_CTRL2_POSTDIV1_MASK;
+	old_postdiv2 = (val >> PLL_FRAC_CTRL2_POSTDIV2_SHIFT) &
+		       PLL_FRAC_CTRL2_POSTDIV2_MASK;
+	if (enabled &&
+	    (params->postdiv1 != old_postdiv1 ||
+	     params->postdiv2 != old_postdiv2))
+		pr_warn("%s: changing postdiv while PLL is enabled\n", name);
+
+	if (params->postdiv2 > params->postdiv1)
+		pr_warn("%s: postdiv2 should not exceed postdiv1\n", name);
+
 	val &= ~((PLL_FRAC_CTRL2_FRAC_MASK << PLL_FRAC_CTRL2_FRAC_SHIFT) |
 		 (PLL_FRAC_CTRL2_POSTDIV1_MASK <<
 		  PLL_FRAC_CTRL2_POSTDIV1_SHIFT) |
@@ -178,11 +227,8 @@
 		(params->postdiv2 << PLL_FRAC_CTRL2_POSTDIV2_SHIFT);
 	pll_writel(pll, val, PLL_CTRL2);
 
-	while (!(pll_readl(pll, PLL_STATUS) & PLL_STATUS_LOCK))
-		cpu_relax();
-
-	if (!was_enabled)
-		pll_gf40lp_frac_disable(hw);
+	if (enabled)
+		pll_lock(pll);
 
 	return 0;
 }
@@ -241,6 +287,8 @@
 	val &= ~PLL_INT_CTRL2_BYPASS;
 	pll_writel(pll, val, PLL_CTRL2);
 
+	pll_lock(pll);
+
 	return 0;
 }
 
@@ -266,18 +314,44 @@
 {
 	struct pistachio_clk_pll *pll = to_pistachio_pll(hw);
 	struct pistachio_pll_rate_table *params;
-	bool was_enabled;
-	u32 val;
+	int enabled = pll_gf40lp_laint_is_enabled(hw);
+	u32 val, vco, old_postdiv1, old_postdiv2;
+	const char *name = __clk_get_name(hw->clk);
 
-	params = pll_get_params(pll, parent_rate, rate);
-	if (!params)
+	if (rate < MIN_OUTPUT_LA || rate > MAX_OUTPUT_LA)
 		return -EINVAL;
 
-	was_enabled = pll_gf40lp_laint_is_enabled(hw);
-	if (!was_enabled)
-		pll_gf40lp_laint_enable(hw);
+	params = pll_get_params(pll, parent_rate, rate);
+	if (!params || !params->refdiv)
+		return -EINVAL;
+
+	vco = params->fref * params->fbdiv / params->refdiv;
+	if (vco < MIN_VCO_LA || vco > MAX_VCO_LA)
+		pr_warn("%s: VCO %u is out of range %lu..%lu\n", name, vco,
+			MIN_VCO_LA, MAX_VCO_LA);
+
+	val = params->fref / params->refdiv;
+	if (val < MIN_PFD)
+		pr_warn("%s: PFD %u is too low (min %lu)\n",
+			name, val, MIN_PFD);
+	if (val > vco / 16)
+		pr_warn("%s: PFD %u is too high (max %u)\n",
+			name, val, vco / 16);
 
 	val = pll_readl(pll, PLL_CTRL1);
+
+	old_postdiv1 = (val >> PLL_INT_CTRL1_POSTDIV1_SHIFT) &
+		       PLL_INT_CTRL1_POSTDIV1_MASK;
+	old_postdiv2 = (val >> PLL_INT_CTRL1_POSTDIV2_SHIFT) &
+		       PLL_INT_CTRL1_POSTDIV2_MASK;
+	if (enabled &&
+	    (params->postdiv1 != old_postdiv1 ||
+	     params->postdiv2 != old_postdiv2))
+		pr_warn("%s: changing postdiv while PLL is enabled\n", name);
+
+	if (params->postdiv2 > params->postdiv1)
+		pr_warn("%s: postdiv2 should not exceed postdiv1\n", name);
+
 	val &= ~((PLL_CTRL1_REFDIV_MASK << PLL_CTRL1_REFDIV_SHIFT) |
 		 (PLL_CTRL1_FBDIV_MASK << PLL_CTRL1_FBDIV_SHIFT) |
 		 (PLL_INT_CTRL1_POSTDIV1_MASK << PLL_INT_CTRL1_POSTDIV1_SHIFT) |
@@ -288,11 +362,8 @@
 		(params->postdiv2 << PLL_INT_CTRL1_POSTDIV2_SHIFT);
 	pll_writel(pll, val, PLL_CTRL1);
 
-	while (!(pll_readl(pll, PLL_STATUS) & PLL_STATUS_LOCK))
-		cpu_relax();
-
-	if (!was_enabled)
-		pll_gf40lp_laint_disable(hw);
+	if (enabled)
+		pll_lock(pll);
 
 	return 0;
 }
diff --git a/drivers/clk/pxa/clk-pxa.h b/drivers/clk/pxa/clk-pxa.h
index b04c5b9..d1de805 100644
--- a/drivers/clk/pxa/clk-pxa.h
+++ b/drivers/clk/pxa/clk-pxa.h
@@ -14,7 +14,7 @@
 #define _CLK_PXA_
 
 #define PARENTS(name) \
-	static const char *name ## _parents[] __initdata
+	static const char *const name ## _parents[] __initconst
 #define MUX_RO_RATE_RO_OPS(name, clk_name)			\
 	static struct clk_hw name ## _mux_hw;			\
 	static struct clk_hw name ## _rate_hw;			\
@@ -72,7 +72,7 @@
 	const char *name;
 	const char *dev_id;
 	const char *con_id;
-	const char **parent_names;
+	const char * const *parent_names;
 	struct clk_fixed_factor lp;
 	struct clk_fixed_factor hp;
 	struct clk_gate gate;
diff --git a/drivers/clk/rockchip/clk-cpu.c b/drivers/clk/rockchip/clk-cpu.c
index 8539c4f..fb7721b 100644
--- a/drivers/clk/rockchip/clk-cpu.c
+++ b/drivers/clk/rockchip/clk-cpu.c
@@ -231,7 +231,7 @@
 }
 
 struct clk *rockchip_clk_register_cpuclk(const char *name,
-			const char **parent_names, u8 num_parents,
+			const char *const *parent_names, u8 num_parents,
 			const struct rockchip_cpuclk_reg_data *reg_data,
 			const struct rockchip_cpuclk_rate_table *rates,
 			int nrates, void __iomem *reg_base, spinlock_t *lock)
diff --git a/drivers/clk/rockchip/clk-mmc-phase.c b/drivers/clk/rockchip/clk-mmc-phase.c
index c842e3b..e9f8df32 100644
--- a/drivers/clk/rockchip/clk-mmc-phase.c
+++ b/drivers/clk/rockchip/clk-mmc-phase.c
@@ -120,7 +120,7 @@
 };
 
 struct clk *rockchip_clk_register_mmc(const char *name,
-				const char **parent_names, u8 num_parents,
+				const char *const *parent_names, u8 num_parents,
 				void __iomem *reg, int shift)
 {
 	struct clk_init_data init;
diff --git a/drivers/clk/rockchip/clk-pll.c b/drivers/clk/rockchip/clk-pll.c
index f8d3baf..7602726 100644
--- a/drivers/clk/rockchip/clk-pll.c
+++ b/drivers/clk/rockchip/clk-pll.c
@@ -329,10 +329,10 @@
  */
 
 struct clk *rockchip_clk_register_pll(enum rockchip_pll_type pll_type,
-		const char *name, const char **parent_names, u8 num_parents,
-		void __iomem *base, int con_offset, int grf_lock_offset,
-		int lock_shift, int mode_offset, int mode_shift,
-		struct rockchip_pll_rate_table *rate_table,
+		const char *name, const char *const *parent_names,
+		u8 num_parents, void __iomem *base, int con_offset,
+		int grf_lock_offset, int lock_shift, int mode_offset,
+		int mode_shift, struct rockchip_pll_rate_table *rate_table,
 		u8 clk_pll_flags, spinlock_t *lock)
 {
 	const char *pll_parents[3];
diff --git a/drivers/clk/rockchip/clk-rk3188.c b/drivers/clk/rockchip/clk-rk3188.c
index 556ce04..e4f9d47 100644
--- a/drivers/clk/rockchip/clk-rk3188.c
+++ b/drivers/clk/rockchip/clk-rk3188.c
@@ -26,7 +26,7 @@
 	apll, cpll, dpll, gpll,
 };
 
-struct rockchip_pll_rate_table rk3188_pll_rates[] = {
+static struct rockchip_pll_rate_table rk3188_pll_rates[] = {
 	RK3066_PLL_RATE(2208000000, 1, 92, 1),
 	RK3066_PLL_RATE(2184000000, 1, 91, 1),
 	RK3066_PLL_RATE(2160000000, 1, 90, 1),
diff --git a/drivers/clk/rockchip/clk-rk3288.c b/drivers/clk/rockchip/clk-rk3288.c
index d17eb45..4f817ed 100644
--- a/drivers/clk/rockchip/clk-rk3288.c
+++ b/drivers/clk/rockchip/clk-rk3288.c
@@ -27,7 +27,7 @@
 	apll, dpll, cpll, gpll, npll,
 };
 
-struct rockchip_pll_rate_table rk3288_pll_rates[] = {
+static struct rockchip_pll_rate_table rk3288_pll_rates[] = {
 	RK3066_PLL_RATE(2208000000, 1, 92, 1),
 	RK3066_PLL_RATE(2184000000, 1, 91, 1),
 	RK3066_PLL_RATE(2160000000, 1, 90, 1),
diff --git a/drivers/clk/rockchip/clk.c b/drivers/clk/rockchip/clk.c
index edb5d48..052b94d 100644
--- a/drivers/clk/rockchip/clk.c
+++ b/drivers/clk/rockchip/clk.c
@@ -39,7 +39,7 @@
  * sometimes without one of those components.
  */
 static struct clk *rockchip_clk_register_branch(const char *name,
-		const char **parent_names, u8 num_parents, void __iomem *base,
+		const char *const *parent_names, u8 num_parents, void __iomem *base,
 		int muxdiv_offset, u8 mux_shift, u8 mux_width, u8 mux_flags,
 		u8 div_shift, u8 div_width, u8 div_flags,
 		struct clk_div_table *div_table, int gate_offset,
@@ -103,8 +103,8 @@
 }
 
 static struct clk *rockchip_clk_register_frac_branch(const char *name,
-		const char **parent_names, u8 num_parents, void __iomem *base,
-		int muxdiv_offset, u8 div_flags,
+		const char *const *parent_names, u8 num_parents,
+		void __iomem *base, int muxdiv_offset, u8 div_flags,
 		int gate_offset, u8 gate_shift, u8 gate_flags,
 		unsigned long flags, spinlock_t *lock)
 {
@@ -297,7 +297,7 @@
 }
 
 void __init rockchip_clk_register_armclk(unsigned int lookup_id,
-			const char *name, const char **parent_names,
+			const char *name, const char *const *parent_names,
 			u8 num_parents,
 			const struct rockchip_cpuclk_reg_data *reg_data,
 			const struct rockchip_cpuclk_rate_table *rates,
diff --git a/drivers/clk/rockchip/clk.h b/drivers/clk/rockchip/clk.h
index e63cafe..6b09267 100644
--- a/drivers/clk/rockchip/clk.h
+++ b/drivers/clk/rockchip/clk.h
@@ -108,7 +108,7 @@
 struct rockchip_pll_clock {
 	unsigned int		id;
 	const char		*name;
-	const char		**parent_names;
+	const char		*const *parent_names;
 	u8			num_parents;
 	unsigned long		flags;
 	int			con_offset;
@@ -140,10 +140,10 @@
 	}
 
 struct clk *rockchip_clk_register_pll(enum rockchip_pll_type pll_type,
-		const char *name, const char **parent_names, u8 num_parents,
-		void __iomem *base, int con_offset, int grf_lock_offset,
-		int lock_shift, int reg_mode, int mode_shift,
-		struct rockchip_pll_rate_table *rate_table,
+		const char *name, const char *const *parent_names,
+		u8 num_parents, void __iomem *base, int con_offset,
+		int grf_lock_offset, int lock_shift, int reg_mode,
+		int mode_shift, struct rockchip_pll_rate_table *rate_table,
 		u8 clk_pll_flags, spinlock_t *lock);
 
 struct rockchip_cpuclk_clksel {
@@ -173,16 +173,16 @@
 };
 
 struct clk *rockchip_clk_register_cpuclk(const char *name,
-			const char **parent_names, u8 num_parents,
+			const char *const *parent_names, u8 num_parents,
 			const struct rockchip_cpuclk_reg_data *reg_data,
 			const struct rockchip_cpuclk_rate_table *rates,
 			int nrates, void __iomem *reg_base, spinlock_t *lock);
 
 struct clk *rockchip_clk_register_mmc(const char *name,
-				const char **parent_names, u8 num_parents,
+				const char *const *parent_names, u8 num_parents,
 				void __iomem *reg, int shift);
 
-#define PNAME(x) static const char *x[] __initdata
+#define PNAME(x) static const char *const x[] __initconst
 
 enum rockchip_clk_branch_type {
 	branch_composite,
@@ -197,7 +197,7 @@
 	unsigned int			id;
 	enum rockchip_clk_branch_type	branch_type;
 	const char			*name;
-	const char			**parent_names;
+	const char			*const *parent_names;
 	u8				num_parents;
 	unsigned long			flags;
 	int				muxdiv_offset;
@@ -403,7 +403,7 @@
 void rockchip_clk_register_plls(struct rockchip_pll_clock *pll_list,
 				unsigned int nr_pll, int grf_lock_offset);
 void rockchip_clk_register_armclk(unsigned int lookup_id, const char *name,
-			const char **parent_names, u8 num_parents,
+			const char *const *parent_names, u8 num_parents,
 			const struct rockchip_cpuclk_reg_data *reg_data,
 			const struct rockchip_cpuclk_rate_table *rates,
 			int nrates);
diff --git a/drivers/clk/samsung/Makefile b/drivers/clk/samsung/Makefile
index a17683b2..5f6833e 100644
--- a/drivers/clk/samsung/Makefile
+++ b/drivers/clk/samsung/Makefile
@@ -2,7 +2,7 @@
 # Samsung Clock specific Makefile
 #
 
-obj-$(CONFIG_COMMON_CLK)	+= clk.o clk-pll.o
+obj-$(CONFIG_COMMON_CLK)	+= clk.o clk-pll.o clk-cpu.o
 obj-$(CONFIG_SOC_EXYNOS3250)	+= clk-exynos3250.o
 obj-$(CONFIG_ARCH_EXYNOS4)	+= clk-exynos4.o
 obj-$(CONFIG_SOC_EXYNOS4415)	+= clk-exynos4415.o
diff --git a/drivers/clk/samsung/clk-cpu.c b/drivers/clk/samsung/clk-cpu.c
new file mode 100644
index 0000000..3a1fe07
--- /dev/null
+++ b/drivers/clk/samsung/clk-cpu.c
@@ -0,0 +1,349 @@
+/*
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd.
+ * Author: Thomas Abraham <thomas.ab@samsung.com>
+ *
+ * Copyright (c) 2015 Samsung Electronics Co., Ltd.
+ * Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This file contains the utility function to register CPU clock for Samsung
+ * Exynos platforms. A CPU clock is defined as a clock supplied to a CPU or a
+ * group of CPUs. The CPU clock is typically derived from a hierarchy of clock
+ * blocks which includes mux and divider blocks. There are a number of other
+ * auxiliary clocks supplied to the CPU domain such as the debug blocks and AXI
+ * clock for CPU domain. The rates of these auxiliary clocks are related to the
+ * CPU clock rate and this relation is usually specified in the hardware manual
+ * of the SoC or supplied after the SoC characterization.
+ *
+ * The below implementation of the CPU clock allows the rate changes of the CPU
+ * clock and the corresponding rate changes of the auxillary clocks of the CPU
+ * domain. The platform clock driver provides a clock register configuration
+ * for each configurable rate which is then used to program the clock hardware
+ * registers to acheive a fast co-oridinated rate change for all the CPU domain
+ * clocks.
+ *
+ * On a rate change request for the CPU clock, the rate change is propagated
+ * upto the PLL supplying the clock to the CPU domain clock blocks. While the
+ * CPU domain PLL is reconfigured, the CPU domain clocks are driven using an
+ * alternate clock source. If required, the alternate clock source is divided
+ * down in order to keep the output clock rate within the previous OPP limits.
+*/
+
+#include <linux/errno.h>
+#include "clk-cpu.h"
+
+#define E4210_SRC_CPU		0x0
+#define E4210_STAT_CPU		0x200
+#define E4210_DIV_CPU0		0x300
+#define E4210_DIV_CPU1		0x304
+#define E4210_DIV_STAT_CPU0	0x400
+#define E4210_DIV_STAT_CPU1	0x404
+
+#define E4210_DIV0_RATIO0_MASK	0x7
+#define E4210_DIV1_HPM_MASK	(0x7 << 4)
+#define E4210_DIV1_COPY_MASK	(0x7 << 0)
+#define E4210_MUX_HPM_MASK	(1 << 20)
+#define E4210_DIV0_ATB_SHIFT	16
+#define E4210_DIV0_ATB_MASK	(DIV_MASK << E4210_DIV0_ATB_SHIFT)
+
+#define MAX_DIV			8
+#define DIV_MASK		7
+#define DIV_MASK_ALL		0xffffffff
+#define MUX_MASK		7
+
+/*
+ * Helper function to wait until divider(s) have stabilized after the divider
+ * value has changed.
+ */
+static void wait_until_divider_stable(void __iomem *div_reg, unsigned long mask)
+{
+	unsigned long timeout = jiffies + msecs_to_jiffies(10);
+
+	do {
+		if (!(readl(div_reg) & mask))
+			return;
+	} while (time_before(jiffies, timeout));
+
+	if (!(readl(div_reg) & mask))
+		return;
+
+	pr_err("%s: timeout in divider stablization\n", __func__);
+}
+
+/*
+ * Helper function to wait until mux has stabilized after the mux selection
+ * value was changed.
+ */
+static void wait_until_mux_stable(void __iomem *mux_reg, u32 mux_pos,
+					unsigned long mux_value)
+{
+	unsigned long timeout = jiffies + msecs_to_jiffies(10);
+
+	do {
+		if (((readl(mux_reg) >> mux_pos) & MUX_MASK) == mux_value)
+			return;
+	} while (time_before(jiffies, timeout));
+
+	if (((readl(mux_reg) >> mux_pos) & MUX_MASK) == mux_value)
+		return;
+
+	pr_err("%s: re-parenting mux timed-out\n", __func__);
+}
+
+/* common round rate callback useable for all types of CPU clocks */
+static long exynos_cpuclk_round_rate(struct clk_hw *hw,
+			unsigned long drate, unsigned long *prate)
+{
+	struct clk *parent = __clk_get_parent(hw->clk);
+	*prate = __clk_round_rate(parent, drate);
+	return *prate;
+}
+
+/* common recalc rate callback useable for all types of CPU clocks */
+static unsigned long exynos_cpuclk_recalc_rate(struct clk_hw *hw,
+			unsigned long parent_rate)
+{
+	/*
+	 * The CPU clock output (armclk) rate is the same as its parent
+	 * rate. Although there exist certain dividers inside the CPU
+	 * clock block that could be used to divide the parent clock,
+	 * the driver does not make use of them currently, except during
+	 * frequency transitions.
+	 */
+	return parent_rate;
+}
+
+static const struct clk_ops exynos_cpuclk_clk_ops = {
+	.recalc_rate = exynos_cpuclk_recalc_rate,
+	.round_rate = exynos_cpuclk_round_rate,
+};
+
+/*
+ * Helper function to set the 'safe' dividers for the CPU clock. The parameters
+ * div and mask contain the divider value and the register bit mask of the
+ * dividers to be programmed.
+ */
+static void exynos_set_safe_div(void __iomem *base, unsigned long div,
+					unsigned long mask)
+{
+	unsigned long div0;
+
+	div0 = readl(base + E4210_DIV_CPU0);
+	div0 = (div0 & ~mask) | (div & mask);
+	writel(div0, base + E4210_DIV_CPU0);
+	wait_until_divider_stable(base + E4210_DIV_STAT_CPU0, mask);
+}
+
+/* handler for pre-rate change notification from parent clock */
+static int exynos_cpuclk_pre_rate_change(struct clk_notifier_data *ndata,
+			struct exynos_cpuclk *cpuclk, void __iomem *base)
+{
+	const struct exynos_cpuclk_cfg_data *cfg_data = cpuclk->cfg;
+	unsigned long alt_prate = clk_get_rate(cpuclk->alt_parent);
+	unsigned long alt_div = 0, alt_div_mask = DIV_MASK;
+	unsigned long div0, div1 = 0, mux_reg;
+
+	/* find out the divider values to use for clock data */
+	while ((cfg_data->prate * 1000) != ndata->new_rate) {
+		if (cfg_data->prate == 0)
+			return -EINVAL;
+		cfg_data++;
+	}
+
+	spin_lock(cpuclk->lock);
+
+	/*
+	 * For the selected PLL clock frequency, get the pre-defined divider
+	 * values. If the clock for sclk_hpm is not sourced from apll, then
+	 * the values for DIV_COPY and DIV_HPM dividers need not be set.
+	 */
+	div0 = cfg_data->div0;
+	if (test_bit(CLK_CPU_HAS_DIV1, &cpuclk->flags)) {
+		div1 = cfg_data->div1;
+		if (readl(base + E4210_SRC_CPU) & E4210_MUX_HPM_MASK)
+			div1 = readl(base + E4210_DIV_CPU1) &
+				(E4210_DIV1_HPM_MASK | E4210_DIV1_COPY_MASK);
+	}
+
+	/*
+	 * If the old parent clock speed is less than the clock speed of
+	 * the alternate parent, then it should be ensured that at no point
+	 * the armclk speed is more than the old_prate until the dividers are
+	 * set.  Also workaround the issue of the dividers being set to lower
+	 * values before the parent clock speed is set to new lower speed
+	 * (this can result in too high speed of armclk output clocks).
+	 */
+	if (alt_prate > ndata->old_rate || ndata->old_rate > ndata->new_rate) {
+		unsigned long tmp_rate = min(ndata->old_rate, ndata->new_rate);
+
+		alt_div = DIV_ROUND_UP(alt_prate, tmp_rate) - 1;
+		WARN_ON(alt_div >= MAX_DIV);
+
+		if (test_bit(CLK_CPU_NEEDS_DEBUG_ALT_DIV, &cpuclk->flags)) {
+			/*
+			 * In Exynos4210, ATB clock parent is also mout_core. So
+			 * ATB clock also needs to be mantained at safe speed.
+			 */
+			alt_div |= E4210_DIV0_ATB_MASK;
+			alt_div_mask |= E4210_DIV0_ATB_MASK;
+		}
+		exynos_set_safe_div(base, alt_div, alt_div_mask);
+		div0 |= alt_div;
+	}
+
+	/* select sclk_mpll as the alternate parent */
+	mux_reg = readl(base + E4210_SRC_CPU);
+	writel(mux_reg | (1 << 16), base + E4210_SRC_CPU);
+	wait_until_mux_stable(base + E4210_STAT_CPU, 16, 2);
+
+	/* alternate parent is active now. set the dividers */
+	writel(div0, base + E4210_DIV_CPU0);
+	wait_until_divider_stable(base + E4210_DIV_STAT_CPU0, DIV_MASK_ALL);
+
+	if (test_bit(CLK_CPU_HAS_DIV1, &cpuclk->flags)) {
+		writel(div1, base + E4210_DIV_CPU1);
+		wait_until_divider_stable(base + E4210_DIV_STAT_CPU1,
+				DIV_MASK_ALL);
+	}
+
+	spin_unlock(cpuclk->lock);
+	return 0;
+}
+
+/* handler for post-rate change notification from parent clock */
+static int exynos_cpuclk_post_rate_change(struct clk_notifier_data *ndata,
+			struct exynos_cpuclk *cpuclk, void __iomem *base)
+{
+	const struct exynos_cpuclk_cfg_data *cfg_data = cpuclk->cfg;
+	unsigned long div = 0, div_mask = DIV_MASK;
+	unsigned long mux_reg;
+
+	/* find out the divider values to use for clock data */
+	if (test_bit(CLK_CPU_NEEDS_DEBUG_ALT_DIV, &cpuclk->flags)) {
+		while ((cfg_data->prate * 1000) != ndata->new_rate) {
+			if (cfg_data->prate == 0)
+				return -EINVAL;
+			cfg_data++;
+		}
+	}
+
+	spin_lock(cpuclk->lock);
+
+	/* select mout_apll as the alternate parent */
+	mux_reg = readl(base + E4210_SRC_CPU);
+	writel(mux_reg & ~(1 << 16), base + E4210_SRC_CPU);
+	wait_until_mux_stable(base + E4210_STAT_CPU, 16, 1);
+
+	if (test_bit(CLK_CPU_NEEDS_DEBUG_ALT_DIV, &cpuclk->flags)) {
+		div |= (cfg_data->div0 & E4210_DIV0_ATB_MASK);
+		div_mask |= E4210_DIV0_ATB_MASK;
+	}
+
+	exynos_set_safe_div(base, div, div_mask);
+	spin_unlock(cpuclk->lock);
+	return 0;
+}
+
+/*
+ * This notifier function is called for the pre-rate and post-rate change
+ * notifications of the parent clock of cpuclk.
+ */
+static int exynos_cpuclk_notifier_cb(struct notifier_block *nb,
+				unsigned long event, void *data)
+{
+	struct clk_notifier_data *ndata = data;
+	struct exynos_cpuclk *cpuclk;
+	void __iomem *base;
+	int err = 0;
+
+	cpuclk = container_of(nb, struct exynos_cpuclk, clk_nb);
+	base = cpuclk->ctrl_base;
+
+	if (event == PRE_RATE_CHANGE)
+		err = exynos_cpuclk_pre_rate_change(ndata, cpuclk, base);
+	else if (event == POST_RATE_CHANGE)
+		err = exynos_cpuclk_post_rate_change(ndata, cpuclk, base);
+
+	return notifier_from_errno(err);
+}
+
+/* helper function to register a CPU clock */
+int __init exynos_register_cpu_clock(struct samsung_clk_provider *ctx,
+		unsigned int lookup_id, const char *name, const char *parent,
+		const char *alt_parent, unsigned long offset,
+		const struct exynos_cpuclk_cfg_data *cfg,
+		unsigned long num_cfgs, unsigned long flags)
+{
+	struct exynos_cpuclk *cpuclk;
+	struct clk_init_data init;
+	struct clk *clk;
+	int ret = 0;
+
+	cpuclk = kzalloc(sizeof(*cpuclk), GFP_KERNEL);
+	if (!cpuclk)
+		return -ENOMEM;
+
+	init.name = name;
+	init.flags = CLK_SET_RATE_PARENT;
+	init.parent_names = &parent;
+	init.num_parents = 1;
+	init.ops = &exynos_cpuclk_clk_ops;
+
+	cpuclk->hw.init = &init;
+	cpuclk->ctrl_base = ctx->reg_base + offset;
+	cpuclk->lock = &ctx->lock;
+	cpuclk->flags = flags;
+	cpuclk->clk_nb.notifier_call = exynos_cpuclk_notifier_cb;
+
+	cpuclk->alt_parent = __clk_lookup(alt_parent);
+	if (!cpuclk->alt_parent) {
+		pr_err("%s: could not lookup alternate parent %s\n",
+				__func__, alt_parent);
+		ret = -EINVAL;
+		goto free_cpuclk;
+	}
+
+	clk = __clk_lookup(parent);
+	if (!clk) {
+		pr_err("%s: could not lookup parent clock %s\n",
+				__func__, parent);
+		ret = -EINVAL;
+		goto free_cpuclk;
+	}
+
+	ret = clk_notifier_register(clk, &cpuclk->clk_nb);
+	if (ret) {
+		pr_err("%s: failed to register clock notifier for %s\n",
+				__func__, name);
+		goto free_cpuclk;
+	}
+
+	cpuclk->cfg = kmemdup(cfg, sizeof(*cfg) * num_cfgs, GFP_KERNEL);
+	if (!cpuclk->cfg) {
+		pr_err("%s: could not allocate memory for cpuclk data\n",
+				__func__);
+		ret = -ENOMEM;
+		goto unregister_clk_nb;
+	}
+
+	clk = clk_register(NULL, &cpuclk->hw);
+	if (IS_ERR(clk)) {
+		pr_err("%s: could not register cpuclk %s\n", __func__,	name);
+		ret = PTR_ERR(clk);
+		goto free_cpuclk_data;
+	}
+
+	samsung_clk_add_lookup(ctx, clk, lookup_id);
+	return 0;
+
+free_cpuclk_data:
+	kfree(cpuclk->cfg);
+unregister_clk_nb:
+	clk_notifier_unregister(__clk_lookup(parent), &cpuclk->clk_nb);
+free_cpuclk:
+	kfree(cpuclk);
+	return ret;
+}
diff --git a/drivers/clk/samsung/clk-cpu.h b/drivers/clk/samsung/clk-cpu.h
new file mode 100644
index 0000000..37874d3
--- /dev/null
+++ b/drivers/clk/samsung/clk-cpu.h
@@ -0,0 +1,73 @@
+/*
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Common Clock Framework support for all PLL's in Samsung platforms
+*/
+
+#ifndef __SAMSUNG_CLK_CPU_H
+#define __SAMSUNG_CLK_CPU_H
+
+#include "clk.h"
+
+/**
+ * struct exynos_cpuclk_data: config data to setup cpu clocks.
+ * @prate: frequency of the primary parent clock (in KHz).
+ * @div0: value to be programmed in the div_cpu0 register.
+ * @div1: value to be programmed in the div_cpu1 register.
+ *
+ * This structure holds the divider configuration data for dividers in the CPU
+ * clock domain. The parent frequency at which these divider values are valid is
+ * specified in @prate. The @prate is the frequency of the primary parent clock.
+ * For CPU clock domains that do not have a DIV1 register, the @div1 member
+ * value is not used.
+ */
+struct exynos_cpuclk_cfg_data {
+	unsigned long	prate;
+	unsigned long	div0;
+	unsigned long	div1;
+};
+
+/**
+ * struct exynos_cpuclk: information about clock supplied to a CPU core.
+ * @hw:	handle between CCF and CPU clock.
+ * @alt_parent: alternate parent clock to use when switching the speed
+ *	of the primary parent clock.
+ * @ctrl_base:	base address of the clock controller.
+ * @lock: cpu clock domain register access lock.
+ * @cfg: cpu clock rate configuration data.
+ * @num_cfgs: number of array elements in @cfg array.
+ * @clk_nb: clock notifier registered for changes in clock speed of the
+ *	primary parent clock.
+ * @flags: configuration flags for the CPU clock.
+ *
+ * This structure holds information required for programming the CPU clock for
+ * various clock speeds.
+ */
+struct exynos_cpuclk {
+	struct clk_hw				hw;
+	struct clk				*alt_parent;
+	void __iomem				*ctrl_base;
+	spinlock_t				*lock;
+	const struct exynos_cpuclk_cfg_data	*cfg;
+	const unsigned long			num_cfgs;
+	struct notifier_block			clk_nb;
+	unsigned long				flags;
+
+/* The CPU clock registers has DIV1 configuration register */
+#define CLK_CPU_HAS_DIV1		(1 << 0)
+/* When ALT parent is active, debug clocks need safe divider values */
+#define CLK_CPU_NEEDS_DEBUG_ALT_DIV	(1 << 1)
+};
+
+extern int __init exynos_register_cpu_clock(struct samsung_clk_provider *ctx,
+			unsigned int lookup_id, const char *name,
+			const char *parent, const char *alt_parent,
+			unsigned long offset,
+			const struct exynos_cpuclk_cfg_data *cfg,
+			unsigned long num_cfgs, unsigned long flags);
+
+#endif /* __SAMSUNG_CLK_CPU_H */
diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c
index 714d6ba..cae2c04 100644
--- a/drivers/clk/samsung/clk-exynos4.c
+++ b/drivers/clk/samsung/clk-exynos4.c
@@ -19,6 +19,7 @@
 #include <linux/syscore_ops.h>
 
 #include "clk.h"
+#include "clk-cpu.h"
 
 /* Exynos4 clock controller register offsets */
 #define SRC_LEFTBUS		0x4200
@@ -534,7 +535,8 @@
 /* list of mux clocks supported in all exynos4 soc's */
 static struct samsung_mux_clock exynos4_mux_clks[] __initdata = {
 	MUX_FA(CLK_MOUT_APLL, "mout_apll", mout_apll_p, SRC_CPU, 0, 1,
-			CLK_SET_RATE_PARENT, 0, "mout_apll"),
+			CLK_SET_RATE_PARENT | CLK_RECALC_NEW_RATES, 0,
+			"mout_apll"),
 	MUX(CLK_MOUT_HDMI, "mout_hdmi", mout_hdmi_p, SRC_TV, 0, 1),
 	MUX(0, "mout_mfc1", sclk_evpll_p, SRC_MFC, 4, 1),
 	MUX(0, "mout_mfc", mout_mfc_p, SRC_MFC, 8, 1),
@@ -1378,6 +1380,22 @@
 	__raw_writel(0x0, reg_base + E4X12_PWR_CTRL2);
 }
 
+#define E4210_CPU_DIV0(apll, pclk_dbg, atb, periph, corem1, corem0)	\
+		(((apll) << 24) | ((pclk_dbg) << 20) | ((atb) << 16) |	\
+		((periph) << 12) | ((corem1) << 8) | ((corem0) <<  4))
+#define E4210_CPU_DIV1(hpm, copy)					\
+		(((hpm) << 4) | ((copy) << 0))
+
+static const struct exynos_cpuclk_cfg_data e4210_armclk_d[] __initconst = {
+	{ 1200000, E4210_CPU_DIV0(7, 1, 4, 3, 7, 3), E4210_CPU_DIV1(0, 5), },
+	{ 1000000, E4210_CPU_DIV0(7, 1, 4, 3, 7, 3), E4210_CPU_DIV1(0, 4), },
+	{  800000, E4210_CPU_DIV0(7, 1, 3, 3, 7, 3), E4210_CPU_DIV1(0, 3), },
+	{  500000, E4210_CPU_DIV0(7, 1, 3, 3, 7, 3), E4210_CPU_DIV1(0, 3), },
+	{  400000, E4210_CPU_DIV0(7, 1, 3, 3, 7, 3), E4210_CPU_DIV1(0, 3), },
+	{  200000, E4210_CPU_DIV0(0, 1, 1, 1, 3, 1), E4210_CPU_DIV1(0, 3), },
+	{  0 },
+};
+
 /* register exynos4 clocks */
 static void __init exynos4_clk_init(struct device_node *np,
 				    enum exynos4_soc soc)
@@ -1455,6 +1473,10 @@
 		samsung_clk_register_fixed_factor(ctx,
 			exynos4210_fixed_factor_clks,
 			ARRAY_SIZE(exynos4210_fixed_factor_clks));
+		exynos_register_cpu_clock(ctx, CLK_ARM_CLK, "armclk",
+			mout_core_p4210[0], mout_core_p4210[1], 0x14200,
+			e4210_armclk_d, ARRAY_SIZE(e4210_armclk_d),
+			CLK_CPU_NEEDS_DEBUG_ALT_DIV | CLK_CPU_HAS_DIV1);
 	} else {
 		samsung_clk_register_mux(ctx, exynos4x12_mux_clks,
 			ARRAY_SIZE(exynos4x12_mux_clks));
diff --git a/drivers/clk/samsung/clk-exynos5260.c b/drivers/clk/samsung/clk-exynos5260.c
index e2e5193..06f96eb 100644
--- a/drivers/clk/samsung/clk-exynos5260.c
+++ b/drivers/clk/samsung/clk-exynos5260.c
@@ -94,7 +94,7 @@
 PNAME(mout_sclk_aud_i2s_p) = {"mout_aud_pll_user", "ioclk_i2s_cdclk"};
 PNAME(mout_sclk_aud_pcm_p) = {"mout_aud_pll_user", "ioclk_pcm_extclk"};
 
-struct samsung_mux_clock aud_mux_clks[] __initdata = {
+static struct samsung_mux_clock aud_mux_clks[] __initdata = {
 	MUX(AUD_MOUT_AUD_PLL_USER, "mout_aud_pll_user", mout_aud_pll_user_p,
 			MUX_SEL_AUD, 0, 1),
 	MUX(AUD_MOUT_SCLK_AUD_I2S, "mout_sclk_aud_i2s", mout_sclk_aud_i2s_p,
@@ -103,7 +103,7 @@
 			MUX_SEL_AUD, 8, 1),
 };
 
-struct samsung_div_clock aud_div_clks[] __initdata = {
+static struct samsung_div_clock aud_div_clks[] __initdata = {
 	DIV(AUD_DOUT_ACLK_AUD_131, "dout_aclk_aud_131", "mout_aud_pll_user",
 			DIV_AUD0, 0, 4),
 
@@ -115,7 +115,7 @@
 			DIV_AUD1, 12, 4),
 };
 
-struct samsung_gate_clock aud_gate_clks[] __initdata = {
+static struct samsung_gate_clock aud_gate_clks[] __initdata = {
 	GATE(AUD_SCLK_I2S, "sclk_aud_i2s", "dout_sclk_aud_i2s",
 			EN_SCLK_AUD, 0, CLK_SET_RATE_PARENT, 0),
 	GATE(AUD_SCLK_PCM, "sclk_aud_pcm", "dout_sclk_aud_pcm",
@@ -135,7 +135,7 @@
 
 static void __init exynos5260_clk_aud_init(struct device_node *np)
 {
-	struct samsung_cmu_info cmu = {0};
+	struct samsung_cmu_info cmu = { NULL };
 
 	cmu.mux_clks = aud_mux_clks;
 	cmu.nr_mux_clks = ARRAY_SIZE(aud_mux_clks);
@@ -203,7 +203,7 @@
 PNAME(mout_sclk_hdmi_spdif_p) = {"fin_pll", "ioclk_spdif_extclk",
 			"dout_aclk_peri_aud", "phyclk_hdmi_phy_ref_cko"};
 
-struct samsung_mux_clock disp_mux_clks[] __initdata = {
+static struct samsung_mux_clock disp_mux_clks[] __initdata = {
 	MUX(DISP_MOUT_ACLK_DISP_333_USER, "mout_aclk_disp_333_user",
 			mout_aclk_disp_333_user_p,
 			MUX_SEL_DISP0, 0, 1),
@@ -272,7 +272,7 @@
 			MUX_SEL_DISP4, 4, 2),
 };
 
-struct samsung_div_clock disp_div_clks[] __initdata = {
+static struct samsung_div_clock disp_div_clks[] __initdata = {
 	DIV(DISP_DOUT_PCLK_DISP_111, "dout_pclk_disp_111",
 			"mout_aclk_disp_222_user",
 			DIV_DISP, 8, 4),
@@ -285,7 +285,7 @@
 			DIV_DISP, 16, 4),
 };
 
-struct samsung_gate_clock disp_gate_clks[] __initdata = {
+static struct samsung_gate_clock disp_gate_clks[] __initdata = {
 	GATE(DISP_MOUT_HDMI_PHY_PIXEL_USER, "sclk_hdmi_link_i_pixel",
 			"mout_phyclk_hdmi_phy_pixel_clko_user",
 			EN_SCLK_DISP0, 26, CLK_SET_RATE_PARENT, 0),
@@ -325,7 +325,7 @@
 
 static void __init exynos5260_clk_disp_init(struct device_node *np)
 {
-	struct samsung_cmu_info cmu = {0};
+	struct samsung_cmu_info cmu = { NULL };
 
 	cmu.mux_clks = disp_mux_clks;
 	cmu.nr_mux_clks = ARRAY_SIZE(disp_mux_clks);
@@ -363,13 +363,13 @@
 PNAME(mout_egl_b_p) = {"mout_egl_pll", "dout_bus_pll"};
 PNAME(mout_egl_pll_p) = {"fin_pll", "fout_egl_pll"};
 
-struct samsung_mux_clock egl_mux_clks[] __initdata = {
+static struct samsung_mux_clock egl_mux_clks[] __initdata = {
 	MUX(EGL_MOUT_EGL_PLL, "mout_egl_pll", mout_egl_pll_p,
 			MUX_SEL_EGL, 4, 1),
 	MUX(EGL_MOUT_EGL_B, "mout_egl_b", mout_egl_b_p, MUX_SEL_EGL, 16, 1),
 };
 
-struct samsung_div_clock egl_div_clks[] __initdata = {
+static struct samsung_div_clock egl_div_clks[] __initdata = {
 	DIV(EGL_DOUT_EGL1, "dout_egl1", "mout_egl_b", DIV_EGL, 0, 3),
 	DIV(EGL_DOUT_EGL2, "dout_egl2", "dout_egl1", DIV_EGL, 4, 3),
 	DIV(EGL_DOUT_ACLK_EGL, "dout_aclk_egl", "dout_egl2", DIV_EGL, 8, 3),
@@ -389,7 +389,7 @@
 
 static void __init exynos5260_clk_egl_init(struct device_node *np)
 {
-	struct samsung_cmu_info cmu = {0};
+	struct samsung_cmu_info cmu = { NULL };
 
 	cmu.pll_clks = egl_pll_clks;
 	cmu.nr_pll_clks =  ARRAY_SIZE(egl_pll_clks);
@@ -433,7 +433,7 @@
 PNAME(mout_phyclk_usbdrd30_phyclock_user_p) = {"fin_pll",
 			"phyclk_usbdrd30_udrd30_phyclock"};
 
-struct samsung_mux_clock fsys_mux_clks[] __initdata = {
+static struct samsung_mux_clock fsys_mux_clks[] __initdata = {
 	MUX(FSYS_MOUT_PHYCLK_USBDRD30_PHYCLOCK_USER,
 			"mout_phyclk_usbdrd30_phyclock_user",
 			mout_phyclk_usbdrd30_phyclock_user_p,
@@ -456,7 +456,7 @@
 			MUX_SEL_FSYS1, 16, 1),
 };
 
-struct samsung_gate_clock fsys_gate_clks[] __initdata = {
+static struct samsung_gate_clock fsys_gate_clks[] __initdata = {
 	GATE(FSYS_PHYCLK_USBHOST20, "phyclk_usbhost20_phyclock",
 			"mout_phyclk_usbdrd30_phyclock_user",
 			EN_SCLK_FSYS, 1, 0, 0),
@@ -491,7 +491,7 @@
 
 static void __init exynos5260_clk_fsys_init(struct device_node *np)
 {
-	struct samsung_cmu_info cmu = {0};
+	struct samsung_cmu_info cmu = { NULL };
 
 	cmu.mux_clks = fsys_mux_clks;
 	cmu.nr_mux_clks = ARRAY_SIZE(fsys_mux_clks);
@@ -537,18 +537,18 @@
 
 PNAME(mout_aclk_g2d_333_user_p) = {"fin_pll", "dout_aclk_g2d_333"};
 
-struct samsung_mux_clock g2d_mux_clks[] __initdata = {
+static struct samsung_mux_clock g2d_mux_clks[] __initdata = {
 	MUX(G2D_MOUT_ACLK_G2D_333_USER, "mout_aclk_g2d_333_user",
 			mout_aclk_g2d_333_user_p,
 			MUX_SEL_G2D, 0, 1),
 };
 
-struct samsung_div_clock g2d_div_clks[] __initdata = {
+static struct samsung_div_clock g2d_div_clks[] __initdata = {
 	DIV(G2D_DOUT_PCLK_G2D_83, "dout_pclk_g2d_83", "mout_aclk_g2d_333_user",
 			DIV_G2D, 0, 3),
 };
 
-struct samsung_gate_clock g2d_gate_clks[] __initdata = {
+static struct samsung_gate_clock g2d_gate_clks[] __initdata = {
 	GATE(G2D_CLK_G2D, "clk_g2d", "mout_aclk_g2d_333_user",
 			EN_IP_G2D, 4, 0, 0),
 	GATE(G2D_CLK_JPEG, "clk_jpeg", "mout_aclk_g2d_333_user",
@@ -580,7 +580,7 @@
 
 static void __init exynos5260_clk_g2d_init(struct device_node *np)
 {
-	struct samsung_cmu_info cmu = {0};
+	struct samsung_cmu_info cmu = { NULL };
 
 	cmu.mux_clks = g2d_mux_clks;
 	cmu.nr_mux_clks = ARRAY_SIZE(g2d_mux_clks);
@@ -617,17 +617,17 @@
 
 PNAME(mout_g3d_pll_p) = {"fin_pll", "fout_g3d_pll"};
 
-struct samsung_mux_clock g3d_mux_clks[] __initdata = {
+static struct samsung_mux_clock g3d_mux_clks[] __initdata = {
 	MUX(G3D_MOUT_G3D_PLL, "mout_g3d_pll", mout_g3d_pll_p,
 			MUX_SEL_G3D, 0, 1),
 };
 
-struct samsung_div_clock g3d_div_clks[] __initdata = {
+static struct samsung_div_clock g3d_div_clks[] __initdata = {
 	DIV(G3D_DOUT_PCLK_G3D, "dout_pclk_g3d", "dout_aclk_g3d", DIV_G3D, 0, 3),
 	DIV(G3D_DOUT_ACLK_G3D, "dout_aclk_g3d", "mout_g3d_pll", DIV_G3D, 4, 3),
 };
 
-struct samsung_gate_clock g3d_gate_clks[] __initdata = {
+static struct samsung_gate_clock g3d_gate_clks[] __initdata = {
 	GATE(G3D_CLK_G3D, "clk_g3d", "dout_aclk_g3d", EN_IP_G3D, 2, 0, 0),
 	GATE(G3D_CLK_G3D_HPM, "clk_g3d_hpm", "dout_aclk_g3d",
 			EN_IP_G3D, 3, 0, 0),
@@ -641,7 +641,7 @@
 
 static void __init exynos5260_clk_g3d_init(struct device_node *np)
 {
-	struct samsung_cmu_info cmu = {0};
+	struct samsung_cmu_info cmu = { NULL };
 
 	cmu.pll_clks = g3d_pll_clks;
 	cmu.nr_pll_clks =  ARRAY_SIZE(g3d_pll_clks);
@@ -694,7 +694,7 @@
 PNAME(mout_aclk_gscl_fimc_user_p) = {"fin_pll", "dout_aclk_gscl_400"};
 PNAME(mout_aclk_csis_p) = {"dout_aclk_csis_200", "mout_aclk_gscl_fimc_user"};
 
-struct samsung_mux_clock gscl_mux_clks[] __initdata = {
+static struct samsung_mux_clock gscl_mux_clks[] __initdata = {
 	MUX(GSCL_MOUT_ACLK_GSCL_333_USER, "mout_aclk_gscl_333_user",
 			mout_aclk_gscl_333_user_p,
 			MUX_SEL_GSCL, 0, 1),
@@ -708,7 +708,7 @@
 			MUX_SEL_GSCL, 24, 1),
 };
 
-struct samsung_div_clock gscl_div_clks[] __initdata = {
+static struct samsung_div_clock gscl_div_clks[] __initdata = {
 	DIV(GSCL_DOUT_PCLK_M2M_100, "dout_pclk_m2m_100",
 			"mout_aclk_m2m_400_user",
 			DIV_GSCL, 0, 3),
@@ -717,7 +717,7 @@
 			DIV_GSCL, 4, 3),
 };
 
-struct samsung_gate_clock gscl_gate_clks[] __initdata = {
+static struct samsung_gate_clock gscl_gate_clks[] __initdata = {
 	GATE(GSCL_SCLK_CSIS0_WRAP, "sclk_csis0_wrap", "dout_aclk_csis_200",
 			EN_SCLK_GSCL_FIMC, 0, CLK_SET_RATE_PARENT, 0),
 	GATE(GSCL_SCLK_CSIS1_WRAP, "sclk_csis1_wrap", "dout_aclk_csis_200",
@@ -776,7 +776,7 @@
 
 static void __init exynos5260_clk_gscl_init(struct device_node *np)
 {
-	struct samsung_cmu_info cmu = {0};
+	struct samsung_cmu_info cmu = { NULL };
 
 	cmu.mux_clks = gscl_mux_clks;
 	cmu.nr_mux_clks = ARRAY_SIZE(gscl_mux_clks);
@@ -813,14 +813,14 @@
 PNAME(mout_isp_400_user_p) = {"fin_pll", "dout_aclk_isp1_400"};
 PNAME(mout_isp_266_user_p)	 = {"fin_pll", "dout_aclk_isp1_266"};
 
-struct samsung_mux_clock isp_mux_clks[] __initdata = {
+static struct samsung_mux_clock isp_mux_clks[] __initdata = {
 	MUX(ISP_MOUT_ISP_266_USER, "mout_isp_266_user", mout_isp_266_user_p,
 			MUX_SEL_ISP0, 0, 1),
 	MUX(ISP_MOUT_ISP_400_USER, "mout_isp_400_user", mout_isp_400_user_p,
 			MUX_SEL_ISP0, 4, 1),
 };
 
-struct samsung_div_clock isp_div_clks[] __initdata = {
+static struct samsung_div_clock isp_div_clks[] __initdata = {
 	DIV(ISP_DOUT_PCLK_ISP_66, "dout_pclk_isp_66", "mout_kfc",
 			DIV_ISP, 0, 3),
 	DIV(ISP_DOUT_PCLK_ISP_133, "dout_pclk_isp_133", "mout_kfc",
@@ -832,7 +832,7 @@
 	DIV(ISP_DOUT_SCLK_MPWM, "dout_sclk_mpwm", "mout_kfc", DIV_ISP, 20, 2),
 };
 
-struct samsung_gate_clock isp_gate_clks[] __initdata = {
+static struct samsung_gate_clock isp_gate_clks[] __initdata = {
 	GATE(ISP_CLK_GIC, "clk_isp_gic", "mout_aclk_isp1_266",
 			EN_IP_ISP0, 15, 0, 0),
 
@@ -895,7 +895,7 @@
 
 static void __init exynos5260_clk_isp_init(struct device_node *np)
 {
-	struct samsung_cmu_info cmu = {0};
+	struct samsung_cmu_info cmu = { NULL };
 
 	cmu.mux_clks = isp_mux_clks;
 	cmu.nr_mux_clks = ARRAY_SIZE(isp_mux_clks);
@@ -934,13 +934,13 @@
 PNAME(mout_kfc_pll_p) = {"fin_pll", "fout_kfc_pll"};
 PNAME(mout_kfc_p)	 = {"mout_kfc_pll", "dout_media_pll"};
 
-struct samsung_mux_clock kfc_mux_clks[] __initdata = {
+static struct samsung_mux_clock kfc_mux_clks[] __initdata = {
 	MUX(KFC_MOUT_KFC_PLL, "mout_kfc_pll", mout_kfc_pll_p,
 			MUX_SEL_KFC0, 0, 1),
 	MUX(KFC_MOUT_KFC, "mout_kfc", mout_kfc_p, MUX_SEL_KFC2, 0, 1),
 };
 
-struct samsung_div_clock kfc_div_clks[] __initdata = {
+static struct samsung_div_clock kfc_div_clks[] __initdata = {
 	DIV(KFC_DOUT_KFC1, "dout_kfc1", "mout_kfc", DIV_KFC, 0, 3),
 	DIV(KFC_DOUT_KFC2, "dout_kfc2", "dout_kfc1", DIV_KFC, 4, 3),
 	DIV(KFC_DOUT_KFC_ATCLK, "dout_kfc_atclk", "dout_kfc2", DIV_KFC, 8, 3),
@@ -959,7 +959,7 @@
 
 static void __init exynos5260_clk_kfc_init(struct device_node *np)
 {
-	struct samsung_cmu_info cmu = {0};
+	struct samsung_cmu_info cmu = { NULL };
 
 	cmu.pll_clks = kfc_pll_clks;
 	cmu.nr_pll_clks =  ARRAY_SIZE(kfc_pll_clks);
@@ -993,18 +993,18 @@
 
 PNAME(mout_aclk_mfc_333_user_p) = {"fin_pll", "dout_aclk_mfc_333"};
 
-struct samsung_mux_clock mfc_mux_clks[] __initdata = {
+static struct samsung_mux_clock mfc_mux_clks[] __initdata = {
 	MUX(MFC_MOUT_ACLK_MFC_333_USER, "mout_aclk_mfc_333_user",
 			mout_aclk_mfc_333_user_p,
 			MUX_SEL_MFC, 0, 1),
 };
 
-struct samsung_div_clock mfc_div_clks[] __initdata = {
+static struct samsung_div_clock mfc_div_clks[] __initdata = {
 	DIV(MFC_DOUT_PCLK_MFC_83, "dout_pclk_mfc_83", "mout_aclk_mfc_333_user",
 			DIV_MFC, 0, 3),
 };
 
-struct samsung_gate_clock mfc_gate_clks[] __initdata = {
+static struct samsung_gate_clock mfc_gate_clks[] __initdata = {
 	GATE(MFC_CLK_MFC, "clk_mfc", "mout_aclk_mfc_333_user",
 			EN_IP_MFC, 1, 0, 0),
 	GATE(MFC_CLK_SMMU2_MFCM0, "clk_smmu2_mfcm0", "mout_aclk_mfc_333_user",
@@ -1015,7 +1015,7 @@
 
 static void __init exynos5260_clk_mfc_init(struct device_node *np)
 {
-	struct samsung_cmu_info cmu = {0};
+	struct samsung_cmu_info cmu = { NULL };
 
 	cmu.mux_clks = mfc_mux_clks;
 	cmu.nr_mux_clks = ARRAY_SIZE(mfc_mux_clks);
@@ -1078,7 +1078,7 @@
 PNAME(mout_clkm_phy_p) = {"mout_mif_drex", "dout_media_pll"};
 PNAME(mout_clk2x_phy_p) = {"mout_mif_drex2x", "dout_media_pll"};
 
-struct samsung_mux_clock mif_mux_clks[] __initdata = {
+static struct samsung_mux_clock mif_mux_clks[] __initdata = {
 	MUX(MIF_MOUT_MEM_PLL, "mout_mem_pll", mout_mem_pll_p,
 			MUX_SEL_MIF, 0, 1),
 	MUX(MIF_MOUT_BUS_PLL, "mout_bus_pll", mout_bus_pll_p,
@@ -1095,7 +1095,7 @@
 			MUX_SEL_MIF, 24, 1),
 };
 
-struct samsung_div_clock mif_div_clks[] __initdata = {
+static struct samsung_div_clock mif_div_clks[] __initdata = {
 	DIV(MIF_DOUT_MEDIA_PLL, "dout_media_pll", "mout_media_pll",
 			DIV_MIF, 0, 3),
 	DIV(MIF_DOUT_MEM_PLL, "dout_mem_pll", "mout_mem_pll",
@@ -1114,7 +1114,7 @@
 			DIV_MIF, 28, 4),
 };
 
-struct samsung_gate_clock mif_gate_clks[] __initdata = {
+static struct samsung_gate_clock mif_gate_clks[] __initdata = {
 	GATE(MIF_CLK_LPDDR3PHY_WRAP0, "clk_lpddr3phy_wrap0", "dout_clk2x_phy",
 			EN_IP_MIF, 12, CLK_IGNORE_UNUSED, 0),
 	GATE(MIF_CLK_LPDDR3PHY_WRAP1, "clk_lpddr3phy_wrap1", "dout_clk2x_phy",
@@ -1162,7 +1162,7 @@
 
 static void __init exynos5260_clk_mif_init(struct device_node *np)
 {
-	struct samsung_cmu_info cmu = {0};
+	struct samsung_cmu_info cmu = { NULL };
 
 	cmu.pll_clks = mif_pll_clks;
 	cmu.nr_pll_clks =  ARRAY_SIZE(mif_pll_clks);
@@ -1221,7 +1221,7 @@
 PNAME(mout_sclk_spdif_p) = {"ioclk_spdif_extclk", "fin_pll",
 			"dout_aclk_peri_aud", "phyclk_hdmi_phy_ref_cko"};
 
-struct samsung_mux_clock peri_mux_clks[] __initdata = {
+static struct samsung_mux_clock peri_mux_clks[] __initdata = {
 	MUX(PERI_MOUT_SCLK_PCM, "mout_sclk_pcm", mout_sclk_pcm_p,
 			MUX_SEL_PERI1, 4, 2),
 	MUX(PERI_MOUT_SCLK_I2SCOD, "mout_sclk_i2scod", mout_sclk_i2scod_p,
@@ -1230,12 +1230,12 @@
 			MUX_SEL_PERI1, 20, 2),
 };
 
-struct samsung_div_clock peri_div_clks[] __initdata = {
+static struct samsung_div_clock peri_div_clks[] __initdata = {
 	DIV(PERI_DOUT_PCM, "dout_pcm", "mout_sclk_pcm", DIV_PERI, 0, 8),
 	DIV(PERI_DOUT_I2S, "dout_i2s", "mout_sclk_i2scod", DIV_PERI, 8, 6),
 };
 
-struct samsung_gate_clock peri_gate_clks[] __initdata = {
+static struct samsung_gate_clock peri_gate_clks[] __initdata = {
 	GATE(PERI_SCLK_PCM1, "sclk_pcm1", "dout_pcm", EN_SCLK_PERI, 0,
 			CLK_SET_RATE_PARENT, 0),
 	GATE(PERI_SCLK_I2S, "sclk_i2s", "dout_i2s", EN_SCLK_PERI, 1,
@@ -1370,7 +1370,7 @@
 
 static void __init exynos5260_clk_peri_init(struct device_node *np)
 {
-	struct samsung_cmu_info cmu = {0};
+	struct samsung_cmu_info cmu = { NULL };
 
 	cmu.mux_clks = peri_mux_clks;
 	cmu.nr_mux_clks = ARRAY_SIZE(peri_mux_clks);
@@ -1432,7 +1432,7 @@
 };
 
 /* fixed rate clocks generated inside the soc */
-struct samsung_fixed_rate_clock fixed_rate_clks[] __initdata = {
+static struct samsung_fixed_rate_clock fixed_rate_clks[] __initdata = {
 	FRATE(PHYCLK_DPTX_PHY_CH3_TXD_CLK, "phyclk_dptx_phy_ch3_txd_clk", NULL,
 			CLK_IS_ROOT, 270000000),
 	FRATE(PHYCLK_DPTX_PHY_CH2_TXD_CLK, "phyclk_dptx_phy_ch2_txd_clk", NULL,
@@ -1519,7 +1519,7 @@
 PNAME(mout_sclk_fsys_mmc2_sdclkin_b_p) = {"mout_sclk_fsys_mmc2_sdclkin_a",
 			"mout_mediatop_pll_user"};
 
-struct samsung_mux_clock top_mux_clks[] __initdata = {
+static struct samsung_mux_clock top_mux_clks[] __initdata = {
 	MUX(TOP_MOUT_MEDIATOP_PLL_USER, "mout_mediatop_pll_user",
 			mout_mediatop_pll_user_p,
 			MUX_SEL_TOP_PLL0, 0, 1),
@@ -1679,7 +1679,7 @@
 			MUX_SEL_TOP_GSCL, 20, 1),
 };
 
-struct samsung_div_clock top_div_clks[] __initdata = {
+static struct samsung_div_clock top_div_clks[] __initdata = {
 	DIV(TOP_DOUT_ACLK_G2D_333, "dout_aclk_g2d_333", "mout_aclk_g2d_333",
 			DIV_TOP_G2D_MFC, 0, 3),
 	DIV(TOP_DOUT_ACLK_MFC_333, "dout_aclk_mfc_333", "mout_aclk_mfc_333",
@@ -1800,7 +1800,7 @@
 
 };
 
-struct samsung_gate_clock top_gate_clks[] __initdata = {
+static struct samsung_gate_clock top_gate_clks[] __initdata = {
 	GATE(TOP_SCLK_MMC0, "sclk_fsys_mmc0_sdclkin",
 			"dout_sclk_fsys_mmc0_sdclkin_b",
 			EN_SCLK_TOP, 7, CLK_SET_RATE_PARENT, 0),
@@ -1826,7 +1826,7 @@
 
 static void __init exynos5260_clk_top_init(struct device_node *np)
 {
-	struct samsung_cmu_info cmu = {0};
+	struct samsung_cmu_info cmu = { NULL };
 
 	cmu.pll_clks = top_pll_clks;
 	cmu.nr_pll_clks =  ARRAY_SIZE(top_pll_clks);
diff --git a/drivers/clk/samsung/clk-exynos5420.c b/drivers/clk/samsung/clk-exynos5420.c
index bea4a17..a1d731c 100644
--- a/drivers/clk/samsung/clk-exynos5420.c
+++ b/drivers/clk/samsung/clk-exynos5420.c
@@ -504,7 +504,7 @@
 	FFACTOR(0, "ff_dout_spll2", "mout_sclk_spll", 1, 2, 0),
 };
 
-struct samsung_mux_clock exynos5800_mux_clks[] __initdata = {
+static struct samsung_mux_clock exynos5800_mux_clks[] __initdata = {
 	MUX(0, "mout_aclk400_isp", mout_group3_5800_p, SRC_TOP0, 0, 3),
 	MUX(0, "mout_aclk400_mscl", mout_group3_5800_p, SRC_TOP0, 4, 3),
 	MUX(0, "mout_aclk400_wcore", mout_group2_5800_p, SRC_TOP0, 16, 3),
@@ -553,7 +553,7 @@
 	MUX(0, "mout_fimd1", mout_group2_p, SRC_DISP10, 4, 3),
 };
 
-struct samsung_div_clock exynos5800_div_clks[] __initdata = {
+static struct samsung_div_clock exynos5800_div_clks[] __initdata = {
 	DIV(0, "dout_aclk400_wcore", "mout_aclk400_wcore", DIV_TOP0, 16, 3),
 
 	DIV(0, "dout_aclk550_cam", "mout_aclk550_cam",
@@ -569,14 +569,14 @@
 	DIV(0, "dout_sclk_sw", "sclk_spll", DIV_TOP9, 24, 6),
 };
 
-struct samsung_gate_clock exynos5800_gate_clks[] __initdata = {
+static struct samsung_gate_clock exynos5800_gate_clks[] __initdata = {
 	GATE(CLK_ACLK550_CAM, "aclk550_cam", "mout_user_aclk550_cam",
 				GATE_BUS_TOP, 24, 0, 0),
 	GATE(CLK_ACLK432_SCALER, "aclk432_scaler", "mout_user_aclk432_scaler",
 				GATE_BUS_TOP, 27, 0, 0),
 };
 
-struct samsung_mux_clock exynos5420_mux_clks[] __initdata = {
+static struct samsung_mux_clock exynos5420_mux_clks[] __initdata = {
 	MUX(0, "sclk_bpll", mout_bpll_p, TOP_SPARE2, 0, 1),
 	MUX(0, "mout_aclk400_wcore_bpll", mout_aclk400_wcore_bpll_p,
 				TOP_SPARE2, 4, 1),
@@ -606,7 +606,7 @@
 	MUX(0, "mout_fimd1", mout_group3_p, SRC_DISP10, 4, 1),
 };
 
-struct samsung_div_clock exynos5420_div_clks[] __initdata = {
+static struct samsung_div_clock exynos5420_div_clks[] __initdata = {
 	DIV(0, "dout_aclk400_wcore", "mout_aclk400_wcore_bpll",
 			DIV_TOP0, 16, 3),
 };
diff --git a/drivers/clk/samsung/clk-exynos5433.c b/drivers/clk/samsung/clk-exynos5433.c
index 9e04ae2..39c9564 100644
--- a/drivers/clk/samsung/clk-exynos5433.c
+++ b/drivers/clk/samsung/clk-exynos5433.c
@@ -835,6 +835,7 @@
 	MPHY_PLL_CON1,
 	MPHY_PLL_FREQ_DET,
 	MUX_SEL_CPIF0,
+	DIV_CPIF,
 	ENABLE_SCLK_CPIF,
 };
 
@@ -1389,7 +1390,7 @@
 
 	/* ENABLE_ACLK_MIF2 */
 	GATE(CLK_ACLK_MIFND_266, "aclk_mifnd_266", "div_aclk_mif_266",
-			ENABLE_ACLK_MIF2, 20, 0, 0),
+			ENABLE_ACLK_MIF2, 20, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_ACLK_PPMU_DREX1S3, "aclk_ppmu_drex1s3", "div_aclk_drex1",
 			ENABLE_ACLK_MIF2, 17, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_ACLK_PPMU_DREX1S1, "aclk_ppmu_drex1s1", "div_aclk_drex1",
@@ -1832,39 +1833,39 @@
 
 	/* ENABLE_PCLK_PERIS_SECURE_TZPC */
 	GATE(CLK_PCLK_TZPC12, "pclk_tzpc12", "aclk_peris_66",
-			ENABLE_PCLK_PERIS_SECURE_TZPC, 12, 0, 0),
+			ENABLE_PCLK_PERIS_SECURE_TZPC, 12, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_PCLK_TZPC11, "pclk_tzpc11", "aclk_peris_66",
-			ENABLE_PCLK_PERIS_SECURE_TZPC, 11, 0, 0),
+			ENABLE_PCLK_PERIS_SECURE_TZPC, 11, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_PCLK_TZPC10, "pclk_tzpc10", "aclk_peris_66",
-			ENABLE_PCLK_PERIS_SECURE_TZPC, 10, 0, 0),
+			ENABLE_PCLK_PERIS_SECURE_TZPC, 10, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_PCLK_TZPC9, "pclk_tzpc9", "aclk_peris_66",
-			ENABLE_PCLK_PERIS_SECURE_TZPC, 9, 0, 0),
+			ENABLE_PCLK_PERIS_SECURE_TZPC, 9, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_PCLK_TZPC8, "pclk_tzpc8", "aclk_peris_66",
-			ENABLE_PCLK_PERIS_SECURE_TZPC, 8, 0, 0),
+			ENABLE_PCLK_PERIS_SECURE_TZPC, 8, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_PCLK_TZPC7, "pclk_tzpc7", "aclk_peris_66",
-			ENABLE_PCLK_PERIS_SECURE_TZPC, 7, 0, 0),
+			ENABLE_PCLK_PERIS_SECURE_TZPC, 7, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_PCLK_TZPC6, "pclk_tzpc6", "aclk_peris_66",
-			ENABLE_PCLK_PERIS_SECURE_TZPC, 6, 0, 0),
+			ENABLE_PCLK_PERIS_SECURE_TZPC, 6, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_PCLK_TZPC5, "pclk_tzpc5", "aclk_peris_66",
-			ENABLE_PCLK_PERIS_SECURE_TZPC, 5, 0, 0),
+			ENABLE_PCLK_PERIS_SECURE_TZPC, 5, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_PCLK_TZPC4, "pclk_tzpc4", "aclk_peris_66",
-			ENABLE_PCLK_PERIS_SECURE_TZPC, 4, 0, 0),
+			ENABLE_PCLK_PERIS_SECURE_TZPC, 4, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_PCLK_TZPC3, "pclk_tzpc3", "aclk_peris_66",
-			ENABLE_PCLK_PERIS_SECURE_TZPC, 3, 0, 0),
+			ENABLE_PCLK_PERIS_SECURE_TZPC, 3, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_PCLK_TZPC2, "pclk_tzpc2", "aclk_peris_66",
-			ENABLE_PCLK_PERIS_SECURE_TZPC, 2, 0, 0),
+			ENABLE_PCLK_PERIS_SECURE_TZPC, 2, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_PCLK_TZPC1, "pclk_tzpc1", "aclk_peris_66",
-			ENABLE_PCLK_PERIS_SECURE_TZPC, 1, 0, 0),
+			ENABLE_PCLK_PERIS_SECURE_TZPC, 1, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_PCLK_TZPC0, "pclk_tzpc0", "aclk_peris_66",
-			ENABLE_PCLK_PERIS_SECURE_TZPC, 0, 0, 0),
+			ENABLE_PCLK_PERIS_SECURE_TZPC, 0, CLK_IGNORE_UNUSED, 0),
 
 	/* ENABLE_PCLK_PERIS_SECURE_SECKEY_APBIF */
 	GATE(CLK_PCLK_SECKEY_APBIF, "pclk_seckey_apbif", "aclk_peris_66",
-			ENABLE_PCLK_PERIS_SECURE_SECKEY_APBIF, 0, 0, 0),
+			ENABLE_PCLK_PERIS_SECURE_SECKEY_APBIF, 0, CLK_IGNORE_UNUSED, 0),
 
 	/* ENABLE_PCLK_PERIS_SECURE_CHIPID_APBIF */
 	GATE(CLK_PCLK_CHIPID_APBIF, "pclk_chipid_apbif", "aclk_peris_66",
-			ENABLE_PCLK_PERIS_SECURE_CHIPID_APBIF, 0, 0, 0),
+			ENABLE_PCLK_PERIS_SECURE_CHIPID_APBIF, 0, CLK_IGNORE_UNUSED, 0),
 
 	/* ENABLE_PCLK_PERIS_SECURE_TOPRTC */
 	GATE(CLK_PCLK_TOPRTC, "pclk_toprtc", "aclk_peris_66",
@@ -1895,11 +1896,11 @@
 
 	/* ENABLE_SCLK_PERIS_SECURE_SECKEY */
 	GATE(CLK_SCLK_SECKEY, "sclk_seckey", "oscclk_efuse_common",
-			ENABLE_SCLK_PERIS_SECURE_SECKEY, 0, 0, 0),
+			ENABLE_SCLK_PERIS_SECURE_SECKEY, 0, CLK_IGNORE_UNUSED, 0),
 
 	/* ENABLE_SCLK_PERIS_SECURE_CHIPID */
 	GATE(CLK_SCLK_CHIPID, "sclk_chipid", "oscclk_efuse_common",
-			ENABLE_SCLK_PERIS_SECURE_CHIPID, 0, 0, 0),
+			ENABLE_SCLK_PERIS_SECURE_CHIPID, 0, CLK_IGNORE_UNUSED, 0),
 
 	/* ENABLE_SCLK_PERIS_SECURE_TOPRTC */
 	GATE(CLK_SCLK_TOPRTC, "sclk_toprtc", "oscclk_efuse_common",
@@ -3286,10 +3287,10 @@
 
 static struct samsung_mux_clock g3d_mux_clks[] __initdata = {
 	/* MUX_SEL_G3D */
-	MUX(CLK_MOUT_ACLK_G3D_400, "mout_aclk_g3d_400", mout_aclk_g3d_400_p,
-			MUX_SEL_G3D, 8, 1),
-	MUX(CLK_MOUT_G3D_PLL, "mout_g3d_pll", mout_g3d_pll_p,
-			MUX_SEL_G3D, 0, 1),
+	MUX_F(CLK_MOUT_ACLK_G3D_400, "mout_aclk_g3d_400", mout_aclk_g3d_400_p,
+			MUX_SEL_G3D, 8, 1, CLK_SET_RATE_PARENT, 0),
+	MUX_F(CLK_MOUT_G3D_PLL, "mout_g3d_pll", mout_g3d_pll_p,
+			MUX_SEL_G3D, 0, 1, CLK_SET_RATE_PARENT, 0),
 };
 
 static struct samsung_div_clock g3d_div_clks[] __initdata = {
@@ -3298,8 +3299,8 @@
 			8, 2),
 	DIV(CLK_DIV_PCLK_G3D, "div_pclk_g3d", "div_aclk_g3d", DIV_G3D,
 			4, 3),
-	DIV(CLK_DIV_ACLK_G3D, "div_aclk_g3d", "mout_aclk_g3d_400", DIV_G3D,
-			0, 3),
+	DIV_F(CLK_DIV_ACLK_G3D, "div_aclk_g3d", "mout_aclk_g3d_400", DIV_G3D,
+			0, 3, CLK_SET_RATE_PARENT, 0),
 };
 
 static struct samsung_gate_clock g3d_gate_clks[] __initdata = {
@@ -3309,9 +3310,9 @@
 	GATE(CLK_ACLK_BTS_G3D0, "aclk_bts_g3d0", "div_aclk_g3d",
 			ENABLE_ACLK_G3D, 6, 0, 0),
 	GATE(CLK_ACLK_ASYNCAPBS_G3D, "aclk_asyncapbs_g3d", "div_pclk_g3d",
-			ENABLE_ACLK_G3D, 5, 0, 0),
+			ENABLE_ACLK_G3D, 5, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_ACLK_ASYNCAPBM_G3D, "aclk_asyncapbm_g3d", "div_aclk_g3d",
-			ENABLE_ACLK_G3D, 4, 0, 0),
+			ENABLE_ACLK_G3D, 4, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_ACLK_AHB2APB_G3DP, "aclk_ahb2apb_g3dp", "div_pclk_g3d",
 			ENABLE_ACLK_G3D, 3, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_ACLK_G3DNP_150, "aclk_g3dnp_150", "div_pclk_g3d",
@@ -3319,7 +3320,7 @@
 	GATE(CLK_ACLK_G3DND_600, "aclk_g3dnd_600", "div_aclk_g3d",
 			ENABLE_ACLK_G3D, 1, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_ACLK_G3D, "aclk_g3d", "div_aclk_g3d",
-			ENABLE_ACLK_G3D, 0, 0, 0),
+			ENABLE_ACLK_G3D, 0, CLK_SET_RATE_PARENT, 0),
 
 	/* ENABLE_PCLK_G3D */
 	GATE(CLK_PCLK_BTS_G3D1, "pclk_bts_g3d1", "div_pclk_g3d",
@@ -3582,7 +3583,7 @@
 static struct samsung_mux_clock apollo_mux_clks[] __initdata = {
 	/* MUX_SEL_APOLLO0 */
 	MUX_F(CLK_MOUT_APOLLO_PLL, "mout_apollo_pll", mout_apollo_pll_p,
-			MUX_SEL_APOLLO0, 0, 1, 0, CLK_MUX_READ_ONLY),
+			MUX_SEL_APOLLO0, 0, 1, CLK_SET_RATE_PARENT, 0),
 
 	/* MUX_SEL_APOLLO1 */
 	MUX(CLK_MOUT_BUS_PLL_APOLLO_USER, "mout_bus_pll_apollo_user",
@@ -3590,7 +3591,7 @@
 
 	/* MUX_SEL_APOLLO2 */
 	MUX_F(CLK_MOUT_APOLLO, "mout_apollo", mout_apollo_p, MUX_SEL_APOLLO2,
-			0, 1, 0, CLK_MUX_READ_ONLY),
+			0, 1, CLK_SET_RATE_PARENT, 0),
 };
 
 static struct samsung_div_clock apollo_div_clks[] __initdata = {
@@ -3611,11 +3612,9 @@
 			DIV_APOLLO0, 8, 3, CLK_GET_RATE_NOCACHE,
 			CLK_DIVIDER_READ_ONLY),
 	DIV_F(CLK_DIV_APOLLO2, "div_apollo2", "div_apollo1",
-			DIV_APOLLO0, 4, 3, CLK_GET_RATE_NOCACHE,
-			CLK_DIVIDER_READ_ONLY),
+			DIV_APOLLO0, 4, 3, CLK_SET_RATE_PARENT, 0),
 	DIV_F(CLK_DIV_APOLLO1, "div_apollo1", "mout_apollo",
-			DIV_APOLLO0, 0, 3, CLK_GET_RATE_NOCACHE,
-			CLK_DIVIDER_READ_ONLY),
+			DIV_APOLLO0, 0, 3, CLK_SET_RATE_PARENT, 0),
 
 	/* DIV_APOLLO1 */
 	DIV_F(CLK_DIV_SCLK_HPM_APOLLO, "div_sclk_hpm_apollo", "mout_apollo",
@@ -3666,7 +3665,8 @@
 	GATE(CLK_SCLK_HPM_APOLLO, "sclk_hpm_apollo", "div_sclk_hpm_apollo",
 			ENABLE_SCLK_APOLLO, 1, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_SCLK_APOLLO, "sclk_apollo", "div_apollo2",
-			ENABLE_SCLK_APOLLO, 0, CLK_IGNORE_UNUSED, 0),
+			ENABLE_SCLK_APOLLO, 0,
+			CLK_IGNORE_UNUSED | CLK_SET_RATE_PARENT, 0),
 };
 
 static struct samsung_cmu_info apollo_cmu_info __initdata = {
@@ -3775,7 +3775,7 @@
 static struct samsung_mux_clock atlas_mux_clks[] __initdata = {
 	/* MUX_SEL_ATLAS0 */
 	MUX_F(CLK_MOUT_ATLAS_PLL, "mout_atlas_pll", mout_atlas_pll_p,
-			MUX_SEL_ATLAS0, 0, 1, 0, CLK_MUX_READ_ONLY),
+			MUX_SEL_ATLAS0, 0, 1, CLK_SET_RATE_PARENT, 0),
 
 	/* MUX_SEL_ATLAS1 */
 	MUX(CLK_MOUT_BUS_PLL_ATLAS_USER, "mout_bus_pll_atlas_user",
@@ -3783,7 +3783,7 @@
 
 	/* MUX_SEL_ATLAS2 */
 	MUX_F(CLK_MOUT_ATLAS, "mout_atlas", mout_atlas_p, MUX_SEL_ATLAS2,
-			0, 1, 0, CLK_MUX_READ_ONLY),
+			0, 1, CLK_SET_RATE_PARENT, 0),
 };
 
 static struct samsung_div_clock atlas_div_clks[] __initdata = {
@@ -3804,11 +3804,9 @@
 			DIV_ATLAS0, 8, 3, CLK_GET_RATE_NOCACHE,
 			CLK_DIVIDER_READ_ONLY),
 	DIV_F(CLK_DIV_ATLAS2, "div_atlas2", "div_atlas1",
-			DIV_ATLAS0, 4, 3, CLK_GET_RATE_NOCACHE,
-			CLK_DIVIDER_READ_ONLY),
+			DIV_ATLAS0, 4, 3, CLK_SET_RATE_PARENT, 0),
 	DIV_F(CLK_DIV_ATLAS1, "div_atlas1", "mout_atlas",
-			DIV_ATLAS0, 0, 3, CLK_GET_RATE_NOCACHE,
-			CLK_DIVIDER_READ_ONLY),
+			DIV_ATLAS0, 0, 3, CLK_SET_RATE_PARENT, 0),
 
 	/* DIV_ATLAS1 */
 	DIV_F(CLK_DIV_SCLK_HPM_ATLAS, "div_sclk_hpm_atlas", "mout_atlas",
@@ -3885,7 +3883,8 @@
 	GATE(CLK_ATCLK, "atclk", "div_atclk_atlas",
 			ENABLE_SCLK_ATLAS, 1, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_SCLK_ATLAS, "sclk_atlas", "div_atlas2",
-			ENABLE_SCLK_ATLAS, 0, CLK_IGNORE_UNUSED, 0),
+			ENABLE_SCLK_ATLAS, 0,
+			CLK_IGNORE_UNUSED | CLK_SET_RATE_PARENT, 0),
 };
 
 static struct samsung_cmu_info atlas_cmu_info __initdata = {
diff --git a/drivers/clk/samsung/clk-pll.c b/drivers/clk/samsung/clk-pll.c
index 9d70e5c..bebc61b 100644
--- a/drivers/clk/samsung/clk-pll.c
+++ b/drivers/clk/samsung/clk-pll.c
@@ -1156,7 +1156,7 @@
 };
 
 static void __init _samsung_clk_register_pll(struct samsung_clk_provider *ctx,
-				struct samsung_pll_clock *pll_clk,
+				const struct samsung_pll_clock *pll_clk,
 				void __iomem *base)
 {
 	struct samsung_clk_pll *pll;
@@ -1303,7 +1303,7 @@
 }
 
 void __init samsung_clk_register_pll(struct samsung_clk_provider *ctx,
-			struct samsung_pll_clock *pll_list,
+			const struct samsung_pll_clock *pll_list,
 			unsigned int nr_pll, void __iomem *base)
 {
 	int cnt;
diff --git a/drivers/clk/samsung/clk-s3c2410-dclk.c b/drivers/clk/samsung/clk-s3c2410-dclk.c
index f4f29ed6..e56df50 100644
--- a/drivers/clk/samsung/clk-s3c2410-dclk.c
+++ b/drivers/clk/samsung/clk-s3c2410-dclk.c
@@ -81,13 +81,13 @@
 	return ret;
 }
 
-const struct clk_ops s3c24xx_clkout_ops = {
+static const struct clk_ops s3c24xx_clkout_ops = {
 	.get_parent = s3c24xx_clkout_get_parent,
 	.set_parent = s3c24xx_clkout_set_parent,
 	.determine_rate = __clk_mux_determine_rate,
 };
 
-struct clk *s3c24xx_register_clkout(struct device *dev, const char *name,
+static struct clk *s3c24xx_register_clkout(struct device *dev, const char *name,
 		const char **parent_names, u8 num_parents,
 		u8 shift, u32 mask)
 {
@@ -404,7 +404,7 @@
 	},
 };
 
-static struct platform_device_id s3c24xx_dclk_driver_ids[] = {
+static const struct platform_device_id s3c24xx_dclk_driver_ids[] = {
 	{
 		.name		= "s3c2410-dclk",
 		.driver_data	= (kernel_ulong_t)&dclk_variants[S3C2410],
diff --git a/drivers/clk/samsung/clk-s5pv210.c b/drivers/clk/samsung/clk-s5pv210.c
index e668e47..cf7e8fa 100644
--- a/drivers/clk/samsung/clk-s5pv210.c
+++ b/drivers/clk/samsung/clk-s5pv210.c
@@ -169,44 +169,44 @@
 #endif
 
 /* Mux parent lists. */
-static const char *fin_pll_p[] __initdata = {
+static const char *const fin_pll_p[] __initconst = {
 	"xxti",
 	"xusbxti"
 };
 
-static const char *mout_apll_p[] __initdata = {
+static const char *const mout_apll_p[] __initconst = {
 	"fin_pll",
 	"fout_apll"
 };
 
-static const char *mout_mpll_p[] __initdata = {
+static const char *const mout_mpll_p[] __initconst = {
 	"fin_pll",
 	"fout_mpll"
 };
 
-static const char *mout_epll_p[] __initdata = {
+static const char *const mout_epll_p[] __initconst = {
 	"fin_pll",
 	"fout_epll"
 };
 
-static const char *mout_vpllsrc_p[] __initdata = {
+static const char *const mout_vpllsrc_p[] __initconst = {
 	"fin_pll",
 	"sclk_hdmi27m"
 };
 
-static const char *mout_vpll_p[] __initdata = {
+static const char *const mout_vpll_p[] __initconst = {
 	"mout_vpllsrc",
 	"fout_vpll"
 };
 
-static const char *mout_group1_p[] __initdata = {
+static const char *const mout_group1_p[] __initconst = {
 	"dout_a2m",
 	"mout_mpll",
 	"mout_epll",
 	"mout_vpll"
 };
 
-static const char *mout_group2_p[] __initdata = {
+static const char *const mout_group2_p[] __initconst = {
 	"xxti",
 	"xusbxti",
 	"sclk_hdmi27m",
@@ -218,7 +218,7 @@
 	"mout_vpll",
 };
 
-static const char *mout_audio0_p[] __initdata = {
+static const char *const mout_audio0_p[] __initconst = {
 	"xxti",
 	"pcmcdclk0",
 	"sclk_hdmi27m",
@@ -230,7 +230,7 @@
 	"mout_vpll",
 };
 
-static const char *mout_audio1_p[] __initdata = {
+static const char *const mout_audio1_p[] __initconst = {
 	"i2scdclk1",
 	"pcmcdclk1",
 	"sclk_hdmi27m",
@@ -242,7 +242,7 @@
 	"mout_vpll",
 };
 
-static const char *mout_audio2_p[] __initdata = {
+static const char *const mout_audio2_p[] __initconst = {
 	"i2scdclk2",
 	"pcmcdclk2",
 	"sclk_hdmi27m",
@@ -254,63 +254,63 @@
 	"mout_vpll",
 };
 
-static const char *mout_spdif_p[] __initdata = {
+static const char *const mout_spdif_p[] __initconst = {
 	"dout_audio0",
 	"dout_audio1",
 	"dout_audio3",
 };
 
-static const char *mout_group3_p[] __initdata = {
+static const char *const mout_group3_p[] __initconst = {
 	"mout_apll",
 	"mout_mpll"
 };
 
-static const char *mout_group4_p[] __initdata = {
+static const char *const mout_group4_p[] __initconst = {
 	"mout_mpll",
 	"dout_a2m"
 };
 
-static const char *mout_flash_p[] __initdata = {
+static const char *const mout_flash_p[] __initconst = {
 	"dout_hclkd",
 	"dout_hclkp"
 };
 
-static const char *mout_dac_p[] __initdata = {
+static const char *const mout_dac_p[] __initconst = {
 	"mout_vpll",
 	"sclk_hdmiphy"
 };
 
-static const char *mout_hdmi_p[] __initdata = {
+static const char *const mout_hdmi_p[] __initconst = {
 	"sclk_hdmiphy",
 	"dout_tblk"
 };
 
-static const char *mout_mixer_p[] __initdata = {
+static const char *const mout_mixer_p[] __initconst = {
 	"mout_dac",
 	"mout_hdmi"
 };
 
-static const char *mout_vpll_6442_p[] __initdata = {
+static const char *const mout_vpll_6442_p[] __initconst = {
 	"fin_pll",
 	"fout_vpll"
 };
 
-static const char *mout_mixer_6442_p[] __initdata = {
+static const char *const mout_mixer_6442_p[] __initconst = {
 	"mout_vpll",
 	"dout_mixer"
 };
 
-static const char *mout_d0sync_6442_p[] __initdata = {
+static const char *const mout_d0sync_6442_p[] __initconst = {
 	"mout_dsys",
 	"div_apll"
 };
 
-static const char *mout_d1sync_6442_p[] __initdata = {
+static const char *const mout_d1sync_6442_p[] __initconst = {
 	"mout_psys",
 	"div_apll"
 };
 
-static const char *mout_group2_6442_p[] __initdata = {
+static const char *const mout_group2_6442_p[] __initconst = {
 	"fin_pll",
 	"none",
 	"none",
@@ -322,7 +322,7 @@
 	"mout_vpll",
 };
 
-static const char *mout_audio0_6442_p[] __initdata = {
+static const char *const mout_audio0_6442_p[] __initconst = {
 	"fin_pll",
 	"pcmcdclk0",
 	"none",
@@ -334,7 +334,7 @@
 	"mout_vpll",
 };
 
-static const char *mout_audio1_6442_p[] __initdata = {
+static const char *const mout_audio1_6442_p[] __initconst = {
 	"i2scdclk1",
 	"pcmcdclk1",
 	"none",
@@ -347,7 +347,7 @@
 	"fin_pll",
 };
 
-static const char *mout_clksel_p[] __initdata = {
+static const char *const mout_clksel_p[] __initconst = {
 	"fout_apll_clkout",
 	"fout_mpll_clkout",
 	"fout_epll",
@@ -370,7 +370,7 @@
 	"div_dclk"
 };
 
-static const char *mout_clksel_6442_p[] __initdata = {
+static const char *const mout_clksel_6442_p[] __initconst = {
 	"fout_apll_clkout",
 	"fout_mpll_clkout",
 	"fout_epll",
@@ -393,7 +393,7 @@
 	"div_dclk"
 };
 
-static const char *mout_clkout_p[] __initdata = {
+static const char *const mout_clkout_p[] __initconst = {
 	"dout_clkout",
 	"none",
 	"xxti",
@@ -401,20 +401,20 @@
 };
 
 /* Common fixed factor clocks. */
-static struct samsung_fixed_factor_clock ffactor_clks[] __initdata = {
+static const struct samsung_fixed_factor_clock ffactor_clks[] __initconst = {
 	FFACTOR(FOUT_APLL_CLKOUT, "fout_apll_clkout", "fout_apll", 1, 4, 0),
 	FFACTOR(FOUT_MPLL_CLKOUT, "fout_mpll_clkout", "fout_mpll", 1, 2, 0),
 	FFACTOR(DOUT_APLL_CLKOUT, "dout_apll_clkout", "dout_apll", 1, 4, 0),
 };
 
 /* PLL input mux (fin_pll), which needs to be registered before PLLs. */
-static struct samsung_mux_clock early_mux_clks[] __initdata = {
+static const struct samsung_mux_clock early_mux_clks[] __initconst = {
 	MUX_F(FIN_PLL, "fin_pll", fin_pll_p, OM_STAT, 0, 1,
 					CLK_MUX_READ_ONLY, 0),
 };
 
 /* Common clock muxes. */
-static struct samsung_mux_clock mux_clks[] __initdata = {
+static const struct samsung_mux_clock mux_clks[] __initconst = {
 	MUX(MOUT_FLASH, "mout_flash", mout_flash_p, CLK_SRC0, 28, 1),
 	MUX(MOUT_PSYS, "mout_psys", mout_group4_p, CLK_SRC0, 24, 1),
 	MUX(MOUT_DSYS, "mout_dsys", mout_group4_p, CLK_SRC0, 20, 1),
@@ -427,7 +427,7 @@
 };
 
 /* S5PV210-specific clock muxes. */
-static struct samsung_mux_clock s5pv210_mux_clks[] __initdata = {
+static const struct samsung_mux_clock s5pv210_mux_clks[] __initconst = {
 	MUX(MOUT_VPLL, "mout_vpll", mout_vpll_p, CLK_SRC0, 12, 1),
 
 	MUX(MOUT_VPLLSRC, "mout_vpllsrc", mout_vpllsrc_p, CLK_SRC1, 28, 1),
@@ -472,7 +472,7 @@
 };
 
 /* S5P6442-specific clock muxes. */
-static struct samsung_mux_clock s5p6442_mux_clks[] __initdata = {
+static const struct samsung_mux_clock s5p6442_mux_clks[] __initconst = {
 	MUX(MOUT_VPLL, "mout_vpll", mout_vpll_6442_p, CLK_SRC0, 12, 1),
 
 	MUX(MOUT_FIMD, "mout_fimd", mout_group2_6442_p, CLK_SRC1, 20, 4),
@@ -504,7 +504,7 @@
 };
 
 /* S5PV210-specific fixed rate clocks generated inside the SoC. */
-static struct samsung_fixed_rate_clock s5pv210_frate_clks[] __initdata = {
+static const struct samsung_fixed_rate_clock s5pv210_frate_clks[] __initconst = {
 	FRATE(SCLK_HDMI27M, "sclk_hdmi27m", NULL, CLK_IS_ROOT, 27000000),
 	FRATE(SCLK_HDMIPHY, "sclk_hdmiphy", NULL, CLK_IS_ROOT, 27000000),
 	FRATE(SCLK_USBPHY0, "sclk_usbphy0", NULL, CLK_IS_ROOT, 48000000),
@@ -512,12 +512,12 @@
 };
 
 /* S5P6442-specific fixed rate clocks generated inside the SoC. */
-static struct samsung_fixed_rate_clock s5p6442_frate_clks[] __initdata = {
+static const struct samsung_fixed_rate_clock s5p6442_frate_clks[] __initconst = {
 	FRATE(SCLK_USBPHY0, "sclk_usbphy0", NULL, CLK_IS_ROOT, 30000000),
 };
 
 /* Common clock dividers. */
-static struct samsung_div_clock div_clks[] __initdata = {
+static const struct samsung_div_clock div_clks[] __initconst = {
 	DIV(DOUT_PCLKP, "dout_pclkp", "dout_hclkp", CLK_DIV0, 28, 3),
 	DIV(DOUT_PCLKD, "dout_pclkd", "dout_hclkd", CLK_DIV0, 20, 3),
 	DIV(DOUT_A2M, "dout_a2m", "mout_apll", CLK_DIV0, 4, 3),
@@ -549,7 +549,7 @@
 };
 
 /* S5PV210-specific clock dividers. */
-static struct samsung_div_clock s5pv210_div_clks[] __initdata = {
+static const struct samsung_div_clock s5pv210_div_clks[] __initconst = {
 	DIV(DOUT_HCLKP, "dout_hclkp", "mout_psys", CLK_DIV0, 24, 4),
 	DIV(DOUT_HCLKD, "dout_hclkd", "mout_dsys", CLK_DIV0, 16, 4),
 	DIV(DOUT_PCLKM, "dout_pclkm", "dout_hclkm", CLK_DIV0, 12, 3),
@@ -578,7 +578,7 @@
 };
 
 /* S5P6442-specific clock dividers. */
-static struct samsung_div_clock s5p6442_div_clks[] __initdata = {
+static const struct samsung_div_clock s5p6442_div_clks[] __initconst = {
 	DIV(DOUT_HCLKP, "dout_hclkp", "mout_d1sync", CLK_DIV0, 24, 4),
 	DIV(DOUT_HCLKD, "dout_hclkd", "mout_d0sync", CLK_DIV0, 16, 4),
 
@@ -586,7 +586,7 @@
 };
 
 /* Common clock gates. */
-static struct samsung_gate_clock gate_clks[] __initdata = {
+static const struct samsung_gate_clock gate_clks[] __initconst = {
 	GATE(CLK_ROTATOR, "rotator", "dout_hclkd", CLK_GATE_IP0, 29, 0, 0),
 	GATE(CLK_FIMC2, "fimc2", "dout_hclkd", CLK_GATE_IP0, 26, 0, 0),
 	GATE(CLK_FIMC1, "fimc1", "dout_hclkd", CLK_GATE_IP0, 25, 0, 0),
@@ -666,7 +666,7 @@
 };
 
 /* S5PV210-specific clock gates. */
-static struct samsung_gate_clock s5pv210_gate_clks[] __initdata = {
+static const struct samsung_gate_clock s5pv210_gate_clks[] __initconst = {
 	GATE(CLK_CSIS, "clk_csis", "dout_hclkd", CLK_GATE_IP0, 31, 0, 0),
 	GATE(CLK_MFC, "mfc", "dout_hclkm", CLK_GATE_IP0, 16, 0, 0),
 	GATE(CLK_G2D, "g2d", "dout_hclkd", CLK_GATE_IP0, 12, 0, 0),
@@ -728,7 +728,7 @@
 };
 
 /* S5P6442-specific clock gates. */
-static struct samsung_gate_clock s5p6442_gate_clks[] __initdata = {
+static const struct samsung_gate_clock s5p6442_gate_clks[] __initconst = {
 	GATE(CLK_JPEG, "jpeg", "dout_hclkd", CLK_GATE_IP0, 28, 0, 0),
 	GATE(CLK_MFC, "mfc", "dout_hclkd", CLK_GATE_IP0, 16, 0, 0),
 	GATE(CLK_G2D, "g2d", "dout_hclkd", CLK_GATE_IP0, 12, 0, 0),
@@ -748,14 +748,14 @@
  * Clock aliases for legacy clkdev look-up.
  * NOTE: Needed only to support legacy board files.
  */
-static struct samsung_clock_alias s5pv210_aliases[] = {
+static const struct samsung_clock_alias s5pv210_aliases[] __initconst = {
 	ALIAS(DOUT_APLL, NULL, "armclk"),
 	ALIAS(DOUT_HCLKM, NULL, "hclk_msys"),
 	ALIAS(MOUT_DMC0, NULL, "sclk_dmc0"),
 };
 
 /* S5PV210-specific PLLs. */
-static struct samsung_pll_clock s5pv210_pll_clks[] __initdata = {
+static const struct samsung_pll_clock s5pv210_pll_clks[] __initconst = {
 	[apll] = PLL(pll_4508, FOUT_APLL, "fout_apll", "fin_pll",
 						APLL_LOCK, APLL_CON0, NULL),
 	[mpll] = PLL(pll_4502, FOUT_MPLL, "fout_mpll", "fin_pll",
@@ -767,7 +767,7 @@
 };
 
 /* S5P6442-specific PLLs. */
-static struct samsung_pll_clock s5p6442_pll_clks[] __initdata = {
+static const struct samsung_pll_clock s5p6442_pll_clks[] __initconst = {
 	[apll] = PLL(pll_4502, FOUT_APLL, "fout_apll", "fin_pll",
 						APLL_LOCK, APLL_CON0, NULL),
 	[mpll] = PLL(pll_4502, FOUT_MPLL, "fout_mpll", "fin_pll",
diff --git a/drivers/clk/samsung/clk.c b/drivers/clk/samsung/clk.c
index 9e1f88c..0117238 100644
--- a/drivers/clk/samsung/clk.c
+++ b/drivers/clk/samsung/clk.c
@@ -98,7 +98,7 @@
 
 /* register a list of aliases */
 void __init samsung_clk_register_alias(struct samsung_clk_provider *ctx,
-				struct samsung_clock_alias *list,
+				const struct samsung_clock_alias *list,
 				unsigned int nr_clk)
 {
 	struct clk *clk;
@@ -132,7 +132,8 @@
 
 /* register a list of fixed clocks */
 void __init samsung_clk_register_fixed_rate(struct samsung_clk_provider *ctx,
-		struct samsung_fixed_rate_clock *list, unsigned int nr_clk)
+		const struct samsung_fixed_rate_clock *list,
+		unsigned int nr_clk)
 {
 	struct clk *clk;
 	unsigned int idx, ret;
@@ -161,7 +162,7 @@
 
 /* register a list of fixed factor clocks */
 void __init samsung_clk_register_fixed_factor(struct samsung_clk_provider *ctx,
-		struct samsung_fixed_factor_clock *list, unsigned int nr_clk)
+		const struct samsung_fixed_factor_clock *list, unsigned int nr_clk)
 {
 	struct clk *clk;
 	unsigned int idx;
@@ -181,7 +182,7 @@
 
 /* register a list of mux clocks */
 void __init samsung_clk_register_mux(struct samsung_clk_provider *ctx,
-				struct samsung_mux_clock *list,
+				const struct samsung_mux_clock *list,
 				unsigned int nr_clk)
 {
 	struct clk *clk;
@@ -213,7 +214,7 @@
 
 /* register a list of div clocks */
 void __init samsung_clk_register_div(struct samsung_clk_provider *ctx,
-				struct samsung_div_clock *list,
+				const struct samsung_div_clock *list,
 				unsigned int nr_clk)
 {
 	struct clk *clk;
@@ -252,7 +253,7 @@
 
 /* register a list of gate clocks */
 void __init samsung_clk_register_gate(struct samsung_clk_provider *ctx,
-				struct samsung_gate_clock *list,
+				const struct samsung_gate_clock *list,
 				unsigned int nr_clk)
 {
 	struct clk *clk;
@@ -389,7 +390,7 @@
 
 	ctx = samsung_clk_init(np, reg_base, cmu->nr_clk_ids);
 	if (!ctx) {
-		panic("%s: unable to alllocate ctx\n", __func__);
+		panic("%s: unable to allocate ctx\n", __func__);
 		return ctx;
 	}
 
diff --git a/drivers/clk/samsung/clk.h b/drivers/clk/samsung/clk.h
index e4c7538..b775fc2 100644
--- a/drivers/clk/samsung/clk.h
+++ b/drivers/clk/samsung/clk.h
@@ -121,7 +121,7 @@
 	unsigned int		id;
 	const char		*dev_name;
 	const char		*name;
-	const char		**parent_names;
+	const char		*const *parent_names;
 	u8			num_parents;
 	unsigned long		flags;
 	unsigned long		offset;
@@ -368,28 +368,28 @@
 extern void samsung_clk_add_lookup(struct samsung_clk_provider *ctx,
 			struct clk *clk, unsigned int id);
 
-extern void samsung_clk_register_alias(struct samsung_clk_provider *ctx,
-			struct samsung_clock_alias *list,
+extern void __init samsung_clk_register_alias(struct samsung_clk_provider *ctx,
+			const struct samsung_clock_alias *list,
 			unsigned int nr_clk);
 extern void __init samsung_clk_register_fixed_rate(
 			struct samsung_clk_provider *ctx,
-			struct samsung_fixed_rate_clock *clk_list,
+			const struct samsung_fixed_rate_clock *clk_list,
 			unsigned int nr_clk);
 extern void __init samsung_clk_register_fixed_factor(
 			struct samsung_clk_provider *ctx,
-			struct samsung_fixed_factor_clock *list,
+			const struct samsung_fixed_factor_clock *list,
 			unsigned int nr_clk);
 extern void __init samsung_clk_register_mux(struct samsung_clk_provider *ctx,
-			struct samsung_mux_clock *clk_list,
+			const struct samsung_mux_clock *clk_list,
 			unsigned int nr_clk);
 extern void __init samsung_clk_register_div(struct samsung_clk_provider *ctx,
-			struct samsung_div_clock *clk_list,
+			const struct samsung_div_clock *clk_list,
 			unsigned int nr_clk);
 extern void __init samsung_clk_register_gate(struct samsung_clk_provider *ctx,
-			struct samsung_gate_clock *clk_list,
+			const struct samsung_gate_clock *clk_list,
 			unsigned int nr_clk);
 extern void __init samsung_clk_register_pll(struct samsung_clk_provider *ctx,
-			struct samsung_pll_clock *pll_list,
+			const struct samsung_pll_clock *pll_list,
 			unsigned int nr_clk, void __iomem *base);
 
 extern struct samsung_clk_provider __init *samsung_cmu_register_one(
diff --git a/drivers/clk/shmobile/clk-emev2.c b/drivers/clk/shmobile/clk-emev2.c
index 6c7c929..5b60beb 100644
--- a/drivers/clk/shmobile/clk-emev2.c
+++ b/drivers/clk/shmobile/clk-emev2.c
@@ -34,7 +34,7 @@
 static DEFINE_SPINLOCK(lock);
 
 /* not pretty, but hey */
-void __iomem *smu_base;
+static void __iomem *smu_base;
 
 static void __init emev2_smu_write(unsigned long value, int offs)
 {
diff --git a/drivers/clk/sirf/Makefile b/drivers/clk/sirf/Makefile
index 36b8e20..09b4210 100644
--- a/drivers/clk/sirf/Makefile
+++ b/drivers/clk/sirf/Makefile
@@ -2,4 +2,4 @@
 # Makefile for sirf specific clk
 #
 
-obj-$(CONFIG_ARCH_SIRF) += clk-prima2.o clk-atlas6.o
+obj-$(CONFIG_ARCH_SIRF) += clk-prima2.o clk-atlas6.o clk-atlas7.o
diff --git a/drivers/clk/sirf/clk-atlas7.c b/drivers/clk/sirf/clk-atlas7.c
new file mode 100644
index 0000000..db8ab69
--- /dev/null
+++ b/drivers/clk/sirf/clk-atlas7.c
@@ -0,0 +1,1632 @@
+/*
+ * Clock tree for CSR SiRFAtlas7
+ *
+ * Copyright (c) 2014 Cambridge Silicon Radio Limited, a CSR plc group company.
+ *
+ * Licensed under GPLv2 or later.
+ */
+
+#include <linux/bitops.h>
+#include <linux/io.h>
+#include <linux/clk-provider.h>
+#include <linux/delay.h>
+#include <linux/of_address.h>
+#include <linux/reset-controller.h>
+#include <linux/slab.h>
+
+#define SIRFSOC_CLKC_MEMPLL_AB_FREQ          0x0000
+#define SIRFSOC_CLKC_MEMPLL_AB_SSC           0x0004
+#define SIRFSOC_CLKC_MEMPLL_AB_CTRL0         0x0008
+#define SIRFSOC_CLKC_MEMPLL_AB_CTRL1         0x000c
+#define SIRFSOC_CLKC_MEMPLL_AB_STATUS        0x0010
+#define SIRFSOC_CLKC_MEMPLL_AB_SSRAM_ADDR    0x0014
+#define SIRFSOC_CLKC_MEMPLL_AB_SSRAM_DATA    0x0018
+
+#define SIRFSOC_CLKC_CPUPLL_AB_FREQ          0x001c
+#define SIRFSOC_CLKC_CPUPLL_AB_SSC           0x0020
+#define SIRFSOC_CLKC_CPUPLL_AB_CTRL0         0x0024
+#define SIRFSOC_CLKC_CPUPLL_AB_CTRL1         0x0028
+#define SIRFSOC_CLKC_CPUPLL_AB_STATUS        0x002c
+
+#define SIRFSOC_CLKC_SYS0PLL_AB_FREQ         0x0030
+#define SIRFSOC_CLKC_SYS0PLL_AB_SSC          0x0034
+#define SIRFSOC_CLKC_SYS0PLL_AB_CTRL0        0x0038
+#define SIRFSOC_CLKC_SYS0PLL_AB_CTRL1        0x003c
+#define SIRFSOC_CLKC_SYS0PLL_AB_STATUS       0x0040
+
+#define SIRFSOC_CLKC_SYS1PLL_AB_FREQ         0x0044
+#define SIRFSOC_CLKC_SYS1PLL_AB_SSC          0x0048
+#define SIRFSOC_CLKC_SYS1PLL_AB_CTRL0        0x004c
+#define SIRFSOC_CLKC_SYS1PLL_AB_CTRL1        0x0050
+#define SIRFSOC_CLKC_SYS1PLL_AB_STATUS       0x0054
+
+#define SIRFSOC_CLKC_SYS2PLL_AB_FREQ         0x0058
+#define SIRFSOC_CLKC_SYS2PLL_AB_SSC          0x005c
+#define SIRFSOC_CLKC_SYS2PLL_AB_CTRL0        0x0060
+#define SIRFSOC_CLKC_SYS2PLL_AB_CTRL1        0x0064
+#define SIRFSOC_CLKC_SYS2PLL_AB_STATUS       0x0068
+
+#define SIRFSOC_CLKC_SYS3PLL_AB_FREQ         0x006c
+#define SIRFSOC_CLKC_SYS3PLL_AB_SSC          0x0070
+#define SIRFSOC_CLKC_SYS3PLL_AB_CTRL0        0x0074
+#define SIRFSOC_CLKC_SYS3PLL_AB_CTRL1        0x0078
+#define SIRFSOC_CLKC_SYS3PLL_AB_STATUS       0x007c
+
+#define SIRFSOC_ABPLL_CTRL0_SSEN     0x00001000
+#define SIRFSOC_ABPLL_CTRL0_BYPASS   0x00000010
+#define SIRFSOC_ABPLL_CTRL0_RESET    0x00000001
+
+#define SIRFSOC_CLKC_AUDIO_DTO_INC           0x0088
+#define SIRFSOC_CLKC_DISP0_DTO_INC           0x008c
+#define SIRFSOC_CLKC_DISP1_DTO_INC           0x0090
+
+#define SIRFSOC_CLKC_AUDIO_DTO_SRC           0x0094
+#define SIRFSOC_CLKC_AUDIO_DTO_ENA           0x0098
+#define SIRFSOC_CLKC_AUDIO_DTO_DROFF         0x009c
+
+#define SIRFSOC_CLKC_DISP0_DTO_SRC           0x00a0
+#define SIRFSOC_CLKC_DISP0_DTO_ENA           0x00a4
+#define SIRFSOC_CLKC_DISP0_DTO_DROFF         0x00a8
+
+#define SIRFSOC_CLKC_DISP1_DTO_SRC           0x00ac
+#define SIRFSOC_CLKC_DISP1_DTO_ENA           0x00b0
+#define SIRFSOC_CLKC_DISP1_DTO_DROFF         0x00b4
+
+#define SIRFSOC_CLKC_I2S_CLK_SEL             0x00b8
+#define SIRFSOC_CLKC_I2S_SEL_STAT            0x00bc
+
+#define SIRFSOC_CLKC_USBPHY_CLKDIV_CFG       0x00c0
+#define SIRFSOC_CLKC_USBPHY_CLKDIV_ENA       0x00c4
+#define SIRFSOC_CLKC_USBPHY_CLK_SEL          0x00c8
+#define SIRFSOC_CLKC_USBPHY_CLK_SEL_STAT     0x00cc
+
+#define SIRFSOC_CLKC_BTSS_CLKDIV_CFG         0x00d0
+#define SIRFSOC_CLKC_BTSS_CLKDIV_ENA         0x00d4
+#define SIRFSOC_CLKC_BTSS_CLK_SEL            0x00d8
+#define SIRFSOC_CLKC_BTSS_CLK_SEL_STAT       0x00dc
+
+#define SIRFSOC_CLKC_RGMII_CLKDIV_CFG        0x00e0
+#define SIRFSOC_CLKC_RGMII_CLKDIV_ENA        0x00e4
+#define SIRFSOC_CLKC_RGMII_CLK_SEL           0x00e8
+#define SIRFSOC_CLKC_RGMII_CLK_SEL_STAT      0x00ec
+
+#define SIRFSOC_CLKC_CPU_CLKDIV_CFG          0x00f0
+#define SIRFSOC_CLKC_CPU_CLKDIV_ENA          0x00f4
+#define SIRFSOC_CLKC_CPU_CLK_SEL             0x00f8
+#define SIRFSOC_CLKC_CPU_CLK_SEL_STAT        0x00fc
+
+#define SIRFSOC_CLKC_SDPHY01_CLKDIV_CFG      0x0100
+#define SIRFSOC_CLKC_SDPHY01_CLKDIV_ENA      0x0104
+#define SIRFSOC_CLKC_SDPHY01_CLK_SEL         0x0108
+#define SIRFSOC_CLKC_SDPHY01_CLK_SEL_STAT    0x010c
+
+#define SIRFSOC_CLKC_SDPHY23_CLKDIV_CFG      0x0110
+#define SIRFSOC_CLKC_SDPHY23_CLKDIV_ENA      0x0114
+#define SIRFSOC_CLKC_SDPHY23_CLK_SEL         0x0118
+#define SIRFSOC_CLKC_SDPHY23_CLK_SEL_STAT    0x011c
+
+#define SIRFSOC_CLKC_SDPHY45_CLKDIV_CFG      0x0120
+#define SIRFSOC_CLKC_SDPHY45_CLKDIV_ENA      0x0124
+#define SIRFSOC_CLKC_SDPHY45_CLK_SEL         0x0128
+#define SIRFSOC_CLKC_SDPHY45_CLK_SEL_STAT    0x012c
+
+#define SIRFSOC_CLKC_SDPHY67_CLKDIV_CFG      0x0130
+#define SIRFSOC_CLKC_SDPHY67_CLKDIV_ENA      0x0134
+#define SIRFSOC_CLKC_SDPHY67_CLK_SEL         0x0138
+#define SIRFSOC_CLKC_SDPHY67_CLK_SEL_STAT    0x013c
+
+#define SIRFSOC_CLKC_CAN_CLKDIV_CFG          0x0140
+#define SIRFSOC_CLKC_CAN_CLKDIV_ENA          0x0144
+#define SIRFSOC_CLKC_CAN_CLK_SEL             0x0148
+#define SIRFSOC_CLKC_CAN_CLK_SEL_STAT        0x014c
+
+#define SIRFSOC_CLKC_DEINT_CLKDIV_CFG        0x0150
+#define SIRFSOC_CLKC_DEINT_CLKDIV_ENA        0x0154
+#define SIRFSOC_CLKC_DEINT_CLK_SEL           0x0158
+#define SIRFSOC_CLKC_DEINT_CLK_SEL_STAT      0x015c
+
+#define SIRFSOC_CLKC_NAND_CLKDIV_CFG         0x0160
+#define SIRFSOC_CLKC_NAND_CLKDIV_ENA         0x0164
+#define SIRFSOC_CLKC_NAND_CLK_SEL            0x0168
+#define SIRFSOC_CLKC_NAND_CLK_SEL_STAT       0x016c
+
+#define SIRFSOC_CLKC_DISP0_CLKDIV_CFG        0x0170
+#define SIRFSOC_CLKC_DISP0_CLKDIV_ENA        0x0174
+#define SIRFSOC_CLKC_DISP0_CLK_SEL           0x0178
+#define SIRFSOC_CLKC_DISP0_CLK_SEL_STAT      0x017c
+
+#define SIRFSOC_CLKC_DISP1_CLKDIV_CFG        0x0180
+#define SIRFSOC_CLKC_DISP1_CLKDIV_ENA        0x0184
+#define SIRFSOC_CLKC_DISP1_CLK_SEL           0x0188
+#define SIRFSOC_CLKC_DISP1_CLK_SEL_STAT      0x018c
+
+#define SIRFSOC_CLKC_GPU_CLKDIV_CFG          0x0190
+#define SIRFSOC_CLKC_GPU_CLKDIV_ENA          0x0194
+#define SIRFSOC_CLKC_GPU_CLK_SEL             0x0198
+#define SIRFSOC_CLKC_GPU_CLK_SEL_STAT        0x019c
+
+#define SIRFSOC_CLKC_GNSS_CLKDIV_CFG         0x01a0
+#define SIRFSOC_CLKC_GNSS_CLKDIV_ENA         0x01a4
+#define SIRFSOC_CLKC_GNSS_CLK_SEL            0x01a8
+#define SIRFSOC_CLKC_GNSS_CLK_SEL_STAT       0x01ac
+
+#define SIRFSOC_CLKC_SHARED_DIVIDER_CFG0     0x01b0
+#define SIRFSOC_CLKC_SHARED_DIVIDER_CFG1     0x01b4
+#define SIRFSOC_CLKC_SHARED_DIVIDER_ENA      0x01b8
+
+#define SIRFSOC_CLKC_SYS_CLK_SEL             0x01bc
+#define SIRFSOC_CLKC_SYS_CLK_SEL_STAT        0x01c0
+#define SIRFSOC_CLKC_IO_CLK_SEL              0x01c4
+#define SIRFSOC_CLKC_IO_CLK_SEL_STAT         0x01c8
+#define SIRFSOC_CLKC_G2D_CLK_SEL             0x01cc
+#define SIRFSOC_CLKC_G2D_CLK_SEL_STAT        0x01d0
+#define SIRFSOC_CLKC_JPENC_CLK_SEL           0x01d4
+#define SIRFSOC_CLKC_JPENC_CLK_SEL_STAT      0x01d8
+#define SIRFSOC_CLKC_VDEC_CLK_SEL            0x01dc
+#define SIRFSOC_CLKC_VDEC_CLK_SEL_STAT       0x01e0
+#define SIRFSOC_CLKC_GMAC_CLK_SEL            0x01e4
+#define SIRFSOC_CLKC_GMAC_CLK_SEL_STAT       0x01e8
+#define SIRFSOC_CLKC_USB_CLK_SEL             0x01ec
+#define SIRFSOC_CLKC_USB_CLK_SEL_STAT        0x01f0
+#define SIRFSOC_CLKC_KAS_CLK_SEL             0x01f4
+#define SIRFSOC_CLKC_KAS_CLK_SEL_STAT        0x01f8
+#define SIRFSOC_CLKC_SEC_CLK_SEL             0x01fc
+#define SIRFSOC_CLKC_SEC_CLK_SEL_STAT        0x0200
+#define SIRFSOC_CLKC_SDR_CLK_SEL             0x0204
+#define SIRFSOC_CLKC_SDR_CLK_SEL_STAT        0x0208
+#define SIRFSOC_CLKC_VIP_CLK_SEL             0x020c
+#define SIRFSOC_CLKC_VIP_CLK_SEL_STAT        0x0210
+#define SIRFSOC_CLKC_NOCD_CLK_SEL            0x0214
+#define SIRFSOC_CLKC_NOCD_CLK_SEL_STAT       0x0218
+#define SIRFSOC_CLKC_NOCR_CLK_SEL            0x021c
+#define SIRFSOC_CLKC_NOCR_CLK_SEL_STAT       0x0220
+#define SIRFSOC_CLKC_TPIU_CLK_SEL            0x0224
+#define SIRFSOC_CLKC_TPIU_CLK_SEL_STAT       0x0228
+
+#define SIRFSOC_CLKC_ROOT_CLK_EN0_SET        0x022c
+#define SIRFSOC_CLKC_ROOT_CLK_EN0_CLR        0x0230
+#define SIRFSOC_CLKC_ROOT_CLK_EN0_STAT       0x0234
+#define SIRFSOC_CLKC_ROOT_CLK_EN1_SET        0x0238
+#define SIRFSOC_CLKC_ROOT_CLK_EN1_CLR        0x023c
+#define SIRFSOC_CLKC_ROOT_CLK_EN1_STAT       0x0240
+
+#define SIRFSOC_CLKC_LEAF_CLK_EN0_SET        0x0244
+#define SIRFSOC_CLKC_LEAF_CLK_EN0_CLR        0x0248
+#define SIRFSOC_CLKC_LEAF_CLK_EN0_STAT       0x024c
+
+#define SIRFSOC_CLKC_RSTC_A7_SW_RST          0x0308
+
+#define SIRFSOC_CLKC_LEAF_CLK_EN1_SET        0x04a0
+#define SIRFSOC_CLKC_LEAF_CLK_EN2_SET        0x04b8
+#define SIRFSOC_CLKC_LEAF_CLK_EN3_SET        0x04d0
+#define SIRFSOC_CLKC_LEAF_CLK_EN4_SET        0x04e8
+#define SIRFSOC_CLKC_LEAF_CLK_EN5_SET        0x0500
+#define SIRFSOC_CLKC_LEAF_CLK_EN6_SET        0x0518
+#define SIRFSOC_CLKC_LEAF_CLK_EN7_SET        0x0530
+#define SIRFSOC_CLKC_LEAF_CLK_EN8_SET        0x0548
+
+
+static void __iomem *sirfsoc_clk_vbase;
+static struct clk_onecell_data clk_data;
+
+static const struct clk_div_table pll_div_table[] = {
+	{ .val = 0, .div = 1 },
+	{ .val = 1, .div = 2 },
+	{ .val = 2, .div = 4 },
+	{ .val = 3, .div = 8 },
+	{ .val = 4, .div = 16 },
+	{ .val = 5, .div = 32 },
+};
+
+struct clk_pll {
+	struct clk_hw hw;
+	u16 regofs;  /* register offset */
+};
+#define to_pllclk(_hw) container_of(_hw, struct clk_pll, hw)
+
+struct clk_dto {
+	struct clk_hw hw;
+	u16 inc_offset;  /* dto increment offset */
+	u16 src_offset;  /* dto src offset */
+};
+#define to_dtoclk(_hw) container_of(_hw, struct clk_dto, hw)
+
+struct clk_unit {
+	struct clk_hw hw;
+	u16 regofs;
+	u16 bit;
+	spinlock_t *lock;
+};
+#define to_unitclk(_hw) container_of(_hw, struct clk_unit, hw)
+
+struct atlas7_div_init_data {
+	const char *div_name;
+	const char *parent_name;
+	const char *gate_name;
+	unsigned long flags;
+	u8 divider_flags;
+	u8 gate_flags;
+	u32 div_offset;
+	u8 shift;
+	u8 width;
+	u32 gate_offset;
+	u8 gate_bit;
+	spinlock_t *lock;
+};
+
+struct atlas7_mux_init_data {
+	const char *mux_name;
+	const char * const *parent_names;
+	u8 parent_num;
+	unsigned long flags;
+	u8 mux_flags;
+	u32 mux_offset;
+	u8 shift;
+	u8 width;
+};
+
+struct atlas7_unit_init_data {
+	u32 index;
+	const char *unit_name;
+	const char *parent_name;
+	unsigned long flags;
+	u32 regofs;
+	u8 bit;
+	spinlock_t *lock;
+};
+
+struct atlas7_reset_desc {
+	const char *name;
+	u32 clk_ofs;
+	u8  clk_bit;
+	u32 rst_ofs;
+	u8  rst_bit;
+	spinlock_t *lock;
+};
+
+static DEFINE_SPINLOCK(cpupll_ctrl1_lock);
+static DEFINE_SPINLOCK(mempll_ctrl1_lock);
+static DEFINE_SPINLOCK(sys0pll_ctrl1_lock);
+static DEFINE_SPINLOCK(sys1pll_ctrl1_lock);
+static DEFINE_SPINLOCK(sys2pll_ctrl1_lock);
+static DEFINE_SPINLOCK(sys3pll_ctrl1_lock);
+static DEFINE_SPINLOCK(usbphy_div_lock);
+static DEFINE_SPINLOCK(btss_div_lock);
+static DEFINE_SPINLOCK(rgmii_div_lock);
+static DEFINE_SPINLOCK(cpu_div_lock);
+static DEFINE_SPINLOCK(sdphy01_div_lock);
+static DEFINE_SPINLOCK(sdphy23_div_lock);
+static DEFINE_SPINLOCK(sdphy45_div_lock);
+static DEFINE_SPINLOCK(sdphy67_div_lock);
+static DEFINE_SPINLOCK(can_div_lock);
+static DEFINE_SPINLOCK(deint_div_lock);
+static DEFINE_SPINLOCK(nand_div_lock);
+static DEFINE_SPINLOCK(disp0_div_lock);
+static DEFINE_SPINLOCK(disp1_div_lock);
+static DEFINE_SPINLOCK(gpu_div_lock);
+static DEFINE_SPINLOCK(gnss_div_lock);
+/* gate register shared */
+static DEFINE_SPINLOCK(share_div_lock);
+static DEFINE_SPINLOCK(root0_gate_lock);
+static DEFINE_SPINLOCK(root1_gate_lock);
+static DEFINE_SPINLOCK(leaf0_gate_lock);
+static DEFINE_SPINLOCK(leaf1_gate_lock);
+static DEFINE_SPINLOCK(leaf2_gate_lock);
+static DEFINE_SPINLOCK(leaf3_gate_lock);
+static DEFINE_SPINLOCK(leaf4_gate_lock);
+static DEFINE_SPINLOCK(leaf5_gate_lock);
+static DEFINE_SPINLOCK(leaf6_gate_lock);
+static DEFINE_SPINLOCK(leaf7_gate_lock);
+static DEFINE_SPINLOCK(leaf8_gate_lock);
+
+static inline unsigned long clkc_readl(unsigned reg)
+{
+	return readl(sirfsoc_clk_vbase + reg);
+}
+
+static inline void clkc_writel(u32 val, unsigned reg)
+{
+	writel(val, sirfsoc_clk_vbase + reg);
+}
+
+/*
+*  ABPLL
+*  integer mode: Fvco = Fin * 2 * NF / NR
+*  Spread Spectrum mode: Fvco = Fin * SSN / NR
+*  SSN = 2^24 / (256 * ((ssdiv >> ssdepth) << ssdepth) + (ssmod << ssdepth))
+*/
+static unsigned long pll_clk_recalc_rate(struct clk_hw *hw,
+	unsigned long parent_rate)
+{
+	unsigned long fin = parent_rate;
+	struct clk_pll *clk = to_pllclk(hw);
+	u64 rate;
+	u32 regctrl0 = clkc_readl(clk->regofs + SIRFSOC_CLKC_MEMPLL_AB_CTRL0 -
+			SIRFSOC_CLKC_MEMPLL_AB_FREQ);
+	u32 regfreq = clkc_readl(clk->regofs);
+	u32 regssc = clkc_readl(clk->regofs + SIRFSOC_CLKC_MEMPLL_AB_SSC -
+			SIRFSOC_CLKC_MEMPLL_AB_FREQ);
+	u32 nr = (regfreq  >> 16 & (BIT(3) - 1)) + 1;
+	u32 nf = (regfreq & (BIT(9) - 1)) + 1;
+	u32 ssdiv = regssc >> 8 & (BIT(12) - 1);
+	u32 ssdepth = regssc >> 20 & (BIT(2) - 1);
+	u32 ssmod = regssc & (BIT(8) - 1);
+
+	if (regctrl0 & SIRFSOC_ABPLL_CTRL0_BYPASS)
+		return fin;
+
+	if (regctrl0 & SIRFSOC_ABPLL_CTRL0_SSEN) {
+		rate = fin;
+		rate *= 1 << 24;
+		do_div(rate, (256 * ((ssdiv >> ssdepth) << ssdepth)
+			+ (ssmod << ssdepth)));
+	} else {
+		rate = 2 * fin;
+		rate *= nf;
+		do_div(rate, nr);
+	}
+	return rate;
+}
+
+static const struct clk_ops ab_pll_ops = {
+	.recalc_rate = pll_clk_recalc_rate,
+};
+
+static const char * const pll_clk_parents[] = {
+	"xin",
+};
+
+static struct clk_init_data clk_cpupll_init = {
+	.name = "cpupll_vco",
+	.ops = &ab_pll_ops,
+	.parent_names = pll_clk_parents,
+	.num_parents = ARRAY_SIZE(pll_clk_parents),
+};
+
+static struct clk_pll clk_cpupll = {
+	.regofs = SIRFSOC_CLKC_CPUPLL_AB_FREQ,
+	.hw = {
+		.init = &clk_cpupll_init,
+	},
+};
+
+static struct clk_init_data clk_mempll_init = {
+	.name = "mempll_vco",
+	.ops = &ab_pll_ops,
+	.parent_names = pll_clk_parents,
+	.num_parents = ARRAY_SIZE(pll_clk_parents),
+};
+
+static struct clk_pll clk_mempll = {
+	.regofs = SIRFSOC_CLKC_MEMPLL_AB_FREQ,
+	.hw = {
+		.init = &clk_mempll_init,
+	},
+};
+
+static struct clk_init_data clk_sys0pll_init = {
+	.name = "sys0pll_vco",
+	.ops = &ab_pll_ops,
+	.parent_names = pll_clk_parents,
+	.num_parents = ARRAY_SIZE(pll_clk_parents),
+};
+
+static struct clk_pll clk_sys0pll = {
+	.regofs = SIRFSOC_CLKC_SYS0PLL_AB_FREQ,
+	.hw = {
+		.init = &clk_sys0pll_init,
+	},
+};
+
+static struct clk_init_data clk_sys1pll_init = {
+	.name = "sys1pll_vco",
+	.ops = &ab_pll_ops,
+	.parent_names = pll_clk_parents,
+	.num_parents = ARRAY_SIZE(pll_clk_parents),
+};
+
+static struct clk_pll clk_sys1pll = {
+	.regofs = SIRFSOC_CLKC_SYS1PLL_AB_FREQ,
+	.hw = {
+		.init = &clk_sys1pll_init,
+	},
+};
+
+static struct clk_init_data clk_sys2pll_init = {
+	.name = "sys2pll_vco",
+	.ops = &ab_pll_ops,
+	.parent_names = pll_clk_parents,
+	.num_parents = ARRAY_SIZE(pll_clk_parents),
+};
+
+static struct clk_pll clk_sys2pll = {
+	.regofs = SIRFSOC_CLKC_SYS2PLL_AB_FREQ,
+	.hw = {
+		.init = &clk_sys2pll_init,
+	},
+};
+
+static struct clk_init_data clk_sys3pll_init = {
+	.name = "sys3pll_vco",
+	.ops = &ab_pll_ops,
+	.parent_names = pll_clk_parents,
+	.num_parents = ARRAY_SIZE(pll_clk_parents),
+};
+
+static struct clk_pll clk_sys3pll = {
+	.regofs = SIRFSOC_CLKC_SYS3PLL_AB_FREQ,
+	.hw = {
+		.init = &clk_sys3pll_init,
+	},
+};
+
+/*
+ *  DTO in clkc, default enable double resolution mode
+ *  double resolution mode:fout = fin * finc / 2^29
+ *  normal mode:fout = fin * finc / 2^28
+ */
+static int dto_clk_is_enabled(struct clk_hw *hw)
+{
+	struct clk_dto *clk = to_dtoclk(hw);
+	int reg;
+
+	reg = clk->src_offset + SIRFSOC_CLKC_AUDIO_DTO_ENA - SIRFSOC_CLKC_AUDIO_DTO_SRC;
+
+	return !!(clkc_readl(reg) & BIT(0));
+}
+
+static int dto_clk_enable(struct clk_hw *hw)
+{
+	u32 val, reg;
+	struct clk_dto *clk = to_dtoclk(hw);
+
+	reg = clk->src_offset + SIRFSOC_CLKC_AUDIO_DTO_ENA - SIRFSOC_CLKC_AUDIO_DTO_SRC;
+
+	val = clkc_readl(reg) | BIT(0);
+	clkc_writel(val, reg);
+	return 0;
+}
+
+static void dto_clk_disable(struct clk_hw *hw)
+{
+	u32 val, reg;
+	struct clk_dto *clk = to_dtoclk(hw);
+
+	reg = clk->src_offset + SIRFSOC_CLKC_AUDIO_DTO_ENA - SIRFSOC_CLKC_AUDIO_DTO_SRC;
+
+	val = clkc_readl(reg) & ~BIT(0);
+	clkc_writel(val, reg);
+}
+
+static unsigned long dto_clk_recalc_rate(struct clk_hw *hw,
+	unsigned long parent_rate)
+{
+	u64 rate = parent_rate;
+	struct clk_dto *clk = to_dtoclk(hw);
+	u32 finc = clkc_readl(clk->inc_offset);
+	u32 droff = clkc_readl(clk->src_offset + SIRFSOC_CLKC_AUDIO_DTO_DROFF - SIRFSOC_CLKC_AUDIO_DTO_SRC);
+
+	rate *= finc;
+	if (droff & BIT(0))
+		/* Double resolution off */
+		do_div(rate, 1 << 28);
+	else
+		do_div(rate, 1 << 29);
+
+	return rate;
+}
+
+static long dto_clk_round_rate(struct clk_hw *hw, unsigned long rate,
+	unsigned long *parent_rate)
+{
+	u64 dividend = rate * (1 << 29);
+
+	do_div(dividend, *parent_rate);
+	dividend *= *parent_rate;
+	do_div(dividend, 1 << 29);
+
+	return dividend;
+}
+
+static int dto_clk_set_rate(struct clk_hw *hw, unsigned long rate,
+	unsigned long parent_rate)
+{
+	u64 dividend = rate * (1 << 29);
+	struct clk_dto *clk = to_dtoclk(hw);
+
+	do_div(dividend, parent_rate);
+	clkc_writel(0, clk->src_offset + SIRFSOC_CLKC_AUDIO_DTO_DROFF - SIRFSOC_CLKC_AUDIO_DTO_SRC);
+	clkc_writel(dividend, clk->inc_offset);
+
+	return 0;
+}
+
+static u8 dto_clk_get_parent(struct clk_hw *hw)
+{
+	struct clk_dto *clk = to_dtoclk(hw);
+
+	return clkc_readl(clk->src_offset);
+}
+
+/*
+ *   dto need CLK_SET_PARENT_GATE
+ */
+static int dto_clk_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct clk_dto *clk = to_dtoclk(hw);
+
+	clkc_writel(index, clk->src_offset);
+	return 0;
+}
+
+static const struct clk_ops dto_ops = {
+	.is_enabled = dto_clk_is_enabled,
+	.enable = dto_clk_enable,
+	.disable = dto_clk_disable,
+	.recalc_rate = dto_clk_recalc_rate,
+	.round_rate = dto_clk_round_rate,
+	.set_rate = dto_clk_set_rate,
+	.get_parent = dto_clk_get_parent,
+	.set_parent = dto_clk_set_parent,
+};
+
+/* dto parent clock as syspllvco/clk1 */
+static const char * const audiodto_clk_parents[] = {
+	"sys0pll_clk1",
+	"sys1pll_clk1",
+	"sys3pll_clk1",
+};
+
+static struct clk_init_data clk_audiodto_init = {
+	.name = "audio_dto",
+	.ops = &dto_ops,
+	.parent_names = audiodto_clk_parents,
+	.num_parents = ARRAY_SIZE(audiodto_clk_parents),
+};
+
+static struct clk_dto clk_audio_dto = {
+	.inc_offset = SIRFSOC_CLKC_AUDIO_DTO_INC,
+	.src_offset = SIRFSOC_CLKC_AUDIO_DTO_SRC,
+	.hw = {
+		.init = &clk_audiodto_init,
+	},
+};
+
+static const char * const disp0dto_clk_parents[] = {
+	"sys0pll_clk1",
+	"sys1pll_clk1",
+	"sys3pll_clk1",
+};
+
+static struct clk_init_data clk_disp0dto_init = {
+	.name = "disp0_dto",
+	.ops = &dto_ops,
+	.parent_names = disp0dto_clk_parents,
+	.num_parents = ARRAY_SIZE(disp0dto_clk_parents),
+};
+
+static struct clk_dto clk_disp0_dto = {
+	.inc_offset = SIRFSOC_CLKC_DISP0_DTO_INC,
+	.src_offset = SIRFSOC_CLKC_DISP0_DTO_SRC,
+	.hw = {
+		.init = &clk_disp0dto_init,
+	},
+};
+
+static const char * const disp1dto_clk_parents[] = {
+	"sys0pll_clk1",
+	"sys1pll_clk1",
+	"sys3pll_clk1",
+};
+
+static struct clk_init_data clk_disp1dto_init = {
+	.name = "disp1_dto",
+	.ops = &dto_ops,
+	.parent_names = disp1dto_clk_parents,
+	.num_parents = ARRAY_SIZE(disp1dto_clk_parents),
+};
+
+static struct clk_dto clk_disp1_dto = {
+	.inc_offset = SIRFSOC_CLKC_DISP1_DTO_INC,
+	.src_offset = SIRFSOC_CLKC_DISP1_DTO_SRC,
+	.hw = {
+		.init = &clk_disp1dto_init,
+	},
+};
+
+static struct atlas7_div_init_data divider_list[] __initdata = {
+	/* div_name, parent_name, gate_name, clk_flag, divider_flag, gate_flag, div_offset, shift, wdith, gate_offset, bit_enable, lock */
+	{ "sys0pll_qa1", "sys0pll_fixdiv", "sys0pll_a1", 0, 0, 0, SIRFSOC_CLKC_USBPHY_CLKDIV_CFG, 0, 6, SIRFSOC_CLKC_USBPHY_CLKDIV_ENA, 0, &usbphy_div_lock },
+	{ "sys1pll_qa1", "sys1pll_fixdiv", "sys1pll_a1", 0, 0, 0, SIRFSOC_CLKC_USBPHY_CLKDIV_CFG, 8, 6, SIRFSOC_CLKC_USBPHY_CLKDIV_ENA, 4, &usbphy_div_lock },
+	{ "sys2pll_qa1", "sys2pll_fixdiv", "sys2pll_a1", 0, 0, 0, SIRFSOC_CLKC_USBPHY_CLKDIV_CFG, 16, 6, SIRFSOC_CLKC_USBPHY_CLKDIV_ENA, 8, &usbphy_div_lock },
+	{ "sys3pll_qa1", "sys3pll_fixdiv", "sys3pll_a1", 0, 0, 0, SIRFSOC_CLKC_USBPHY_CLKDIV_CFG, 24, 6, SIRFSOC_CLKC_USBPHY_CLKDIV_ENA, 12, &usbphy_div_lock },
+	{ "sys0pll_qa2", "sys0pll_fixdiv", "sys0pll_a2", 0, 0, 0, SIRFSOC_CLKC_BTSS_CLKDIV_CFG, 0, 6, SIRFSOC_CLKC_BTSS_CLKDIV_ENA, 0, &btss_div_lock },
+	{ "sys1pll_qa2", "sys1pll_fixdiv", "sys1pll_a2", 0, 0, 0, SIRFSOC_CLKC_BTSS_CLKDIV_CFG, 8, 6, SIRFSOC_CLKC_BTSS_CLKDIV_ENA, 4, &btss_div_lock },
+	{ "sys2pll_qa2", "sys2pll_fixdiv", "sys2pll_a2", 0, 0, 0, SIRFSOC_CLKC_BTSS_CLKDIV_CFG, 16, 6, SIRFSOC_CLKC_BTSS_CLKDIV_ENA, 8, &btss_div_lock },
+	{ "sys3pll_qa2", "sys3pll_fixdiv", "sys3pll_a2", 0, 0, 0, SIRFSOC_CLKC_BTSS_CLKDIV_CFG, 24, 6, SIRFSOC_CLKC_BTSS_CLKDIV_ENA, 12, &btss_div_lock },
+	{ "sys0pll_qa3", "sys0pll_fixdiv", "sys0pll_a3", 0, 0, 0, SIRFSOC_CLKC_RGMII_CLKDIV_CFG, 0, 6, SIRFSOC_CLKC_RGMII_CLKDIV_ENA, 0, &rgmii_div_lock },
+	{ "sys1pll_qa3", "sys1pll_fixdiv", "sys1pll_a3", 0, 0, 0, SIRFSOC_CLKC_RGMII_CLKDIV_CFG, 8, 6, SIRFSOC_CLKC_RGMII_CLKDIV_ENA, 4, &rgmii_div_lock },
+	{ "sys2pll_qa3", "sys2pll_fixdiv", "sys2pll_a3", 0, 0, 0, SIRFSOC_CLKC_RGMII_CLKDIV_CFG, 16, 6, SIRFSOC_CLKC_RGMII_CLKDIV_ENA, 8, &rgmii_div_lock },
+	{ "sys3pll_qa3", "sys3pll_fixdiv", "sys3pll_a3", 0, 0, 0, SIRFSOC_CLKC_RGMII_CLKDIV_CFG, 24, 6, SIRFSOC_CLKC_RGMII_CLKDIV_ENA, 12, &rgmii_div_lock },
+	{ "sys0pll_qa4", "sys0pll_fixdiv", "sys0pll_a4", 0, 0, 0, SIRFSOC_CLKC_CPU_CLKDIV_CFG, 0, 6, SIRFSOC_CLKC_CPU_CLKDIV_ENA, 0, &cpu_div_lock },
+	{ "sys1pll_qa4", "sys1pll_fixdiv", "sys1pll_a4", 0, 0, CLK_IGNORE_UNUSED, SIRFSOC_CLKC_CPU_CLKDIV_CFG, 8, 6, SIRFSOC_CLKC_CPU_CLKDIV_ENA, 4, &cpu_div_lock },
+	{ "sys0pll_qa5", "sys0pll_fixdiv", "sys0pll_a5", 0, 0, 0, SIRFSOC_CLKC_SDPHY01_CLKDIV_CFG, 0, 6, SIRFSOC_CLKC_SDPHY01_CLKDIV_ENA, 0, &sdphy01_div_lock },
+	{ "sys1pll_qa5", "sys1pll_fixdiv", "sys1pll_a5", 0, 0, 0, SIRFSOC_CLKC_SDPHY01_CLKDIV_CFG, 8, 6, SIRFSOC_CLKC_SDPHY01_CLKDIV_ENA, 4, &sdphy01_div_lock },
+	{ "sys2pll_qa5", "sys2pll_fixdiv", "sys2pll_a5", 0, 0, 0, SIRFSOC_CLKC_SDPHY01_CLKDIV_CFG, 16, 6, SIRFSOC_CLKC_SDPHY01_CLKDIV_ENA, 8, &sdphy01_div_lock },
+	{ "sys3pll_qa5", "sys3pll_fixdiv", "sys3pll_a5", 0, 0, 0, SIRFSOC_CLKC_SDPHY01_CLKDIV_CFG, 24, 6, SIRFSOC_CLKC_SDPHY01_CLKDIV_ENA, 12, &sdphy01_div_lock },
+	{ "sys0pll_qa6", "sys0pll_fixdiv", "sys0pll_a6", 0, 0, 0, SIRFSOC_CLKC_SDPHY23_CLKDIV_CFG, 0, 6, SIRFSOC_CLKC_SDPHY23_CLKDIV_ENA, 0, &sdphy23_div_lock },
+	{ "sys1pll_qa6", "sys1pll_fixdiv", "sys1pll_a6", 0, 0, 0, SIRFSOC_CLKC_SDPHY23_CLKDIV_CFG, 8, 6, SIRFSOC_CLKC_SDPHY23_CLKDIV_ENA, 4, &sdphy23_div_lock },
+	{ "sys2pll_qa6", "sys2pll_fixdiv", "sys2pll_a6", 0, 0, 0, SIRFSOC_CLKC_SDPHY23_CLKDIV_CFG, 16, 6, SIRFSOC_CLKC_SDPHY23_CLKDIV_ENA, 8, &sdphy23_div_lock },
+	{ "sys3pll_qa6", "sys3pll_fixdiv", "sys3pll_a6", 0, 0, 0, SIRFSOC_CLKC_SDPHY23_CLKDIV_CFG, 24, 6, SIRFSOC_CLKC_SDPHY23_CLKDIV_ENA, 12, &sdphy23_div_lock },
+	{ "sys0pll_qa7", "sys0pll_fixdiv", "sys0pll_a7", 0, 0, 0, SIRFSOC_CLKC_SDPHY45_CLKDIV_CFG, 0, 6, SIRFSOC_CLKC_SDPHY45_CLKDIV_ENA, 0, &sdphy45_div_lock },
+	{ "sys1pll_qa7", "sys1pll_fixdiv", "sys1pll_a7", 0, 0, 0, SIRFSOC_CLKC_SDPHY45_CLKDIV_CFG, 8, 6, SIRFSOC_CLKC_SDPHY45_CLKDIV_ENA, 4, &sdphy45_div_lock },
+	{ "sys2pll_qa7", "sys2pll_fixdiv", "sys2pll_a7", 0, 0, 0, SIRFSOC_CLKC_SDPHY45_CLKDIV_CFG, 16, 6, SIRFSOC_CLKC_SDPHY45_CLKDIV_ENA, 8, &sdphy45_div_lock },
+	{ "sys3pll_qa7", "sys3pll_fixdiv", "sys3pll_a7", 0, 0, 0, SIRFSOC_CLKC_SDPHY45_CLKDIV_CFG, 24, 6, SIRFSOC_CLKC_SDPHY45_CLKDIV_ENA, 12, &sdphy45_div_lock },
+	{ "sys0pll_qa8", "sys0pll_fixdiv", "sys0pll_a8", 0, 0, 0, SIRFSOC_CLKC_SDPHY67_CLKDIV_CFG, 0, 6, SIRFSOC_CLKC_SDPHY67_CLKDIV_ENA, 0, &sdphy67_div_lock },
+	{ "sys1pll_qa8", "sys1pll_fixdiv", "sys1pll_a8", 0, 0, 0, SIRFSOC_CLKC_SDPHY67_CLKDIV_CFG, 8, 6, SIRFSOC_CLKC_SDPHY67_CLKDIV_ENA, 4, &sdphy67_div_lock },
+	{ "sys2pll_qa8", "sys2pll_fixdiv", "sys2pll_a8", 0, 0, 0, SIRFSOC_CLKC_SDPHY67_CLKDIV_CFG, 16, 6, SIRFSOC_CLKC_SDPHY67_CLKDIV_ENA, 8, &sdphy67_div_lock },
+	{ "sys3pll_qa8", "sys3pll_fixdiv", "sys3pll_a8", 0, 0, 0, SIRFSOC_CLKC_SDPHY67_CLKDIV_CFG, 24, 6, SIRFSOC_CLKC_SDPHY67_CLKDIV_ENA, 12, &sdphy67_div_lock },
+	{ "sys0pll_qa9", "sys0pll_fixdiv", "sys0pll_a9", 0, 0, 0, SIRFSOC_CLKC_CAN_CLKDIV_CFG, 0, 6, SIRFSOC_CLKC_CAN_CLKDIV_ENA, 0, &can_div_lock },
+	{ "sys1pll_qa9", "sys1pll_fixdiv", "sys1pll_a9", 0, 0, 0, SIRFSOC_CLKC_CAN_CLKDIV_CFG, 8, 6, SIRFSOC_CLKC_CAN_CLKDIV_ENA, 4, &can_div_lock },
+	{ "sys2pll_qa9", "sys2pll_fixdiv", "sys2pll_a9", 0, 0, 0, SIRFSOC_CLKC_CAN_CLKDIV_CFG, 16, 6, SIRFSOC_CLKC_CAN_CLKDIV_ENA, 8, &can_div_lock },
+	{ "sys3pll_qa9", "sys3pll_fixdiv", "sys3pll_a9", 0, 0, 0, SIRFSOC_CLKC_CAN_CLKDIV_CFG, 24, 6, SIRFSOC_CLKC_CAN_CLKDIV_ENA, 12, &can_div_lock },
+	{ "sys0pll_qa10", "sys0pll_fixdiv", "sys0pll_a10", 0, 0, 0, SIRFSOC_CLKC_DEINT_CLKDIV_CFG, 0, 6, SIRFSOC_CLKC_DEINT_CLKDIV_ENA, 0, &deint_div_lock },
+	{ "sys1pll_qa10", "sys1pll_fixdiv", "sys1pll_a10", 0, 0, 0, SIRFSOC_CLKC_DEINT_CLKDIV_CFG, 8, 6, SIRFSOC_CLKC_DEINT_CLKDIV_ENA, 4, &deint_div_lock },
+	{ "sys2pll_qa10", "sys2pll_fixdiv", "sys2pll_a10", 0, 0, 0, SIRFSOC_CLKC_DEINT_CLKDIV_CFG, 16, 6, SIRFSOC_CLKC_DEINT_CLKDIV_ENA, 8, &deint_div_lock },
+	{ "sys3pll_qa10", "sys3pll_fixdiv", "sys3pll_a10", 0, 0, 0, SIRFSOC_CLKC_DEINT_CLKDIV_CFG, 24, 6, SIRFSOC_CLKC_DEINT_CLKDIV_ENA, 12, &deint_div_lock },
+	{ "sys0pll_qa11", "sys0pll_fixdiv", "sys0pll_a11", 0, 0, 0, SIRFSOC_CLKC_NAND_CLKDIV_CFG, 0, 6, SIRFSOC_CLKC_NAND_CLKDIV_ENA, 0, &nand_div_lock },
+	{ "sys1pll_qa11", "sys1pll_fixdiv", "sys1pll_a11", 0, 0, 0, SIRFSOC_CLKC_NAND_CLKDIV_CFG, 8, 6, SIRFSOC_CLKC_NAND_CLKDIV_ENA, 4, &nand_div_lock },
+	{ "sys2pll_qa11", "sys2pll_fixdiv", "sys2pll_a11", 0, 0, 0, SIRFSOC_CLKC_NAND_CLKDIV_CFG, 16, 6, SIRFSOC_CLKC_NAND_CLKDIV_ENA, 8, &nand_div_lock },
+	{ "sys3pll_qa11", "sys3pll_fixdiv", "sys3pll_a11", 0, 0, 0, SIRFSOC_CLKC_NAND_CLKDIV_CFG, 24, 6, SIRFSOC_CLKC_NAND_CLKDIV_ENA, 12, &nand_div_lock },
+	{ "sys0pll_qa12", "sys0pll_fixdiv", "sys0pll_a12", 0, 0, 0, SIRFSOC_CLKC_DISP0_CLKDIV_CFG, 0, 6, SIRFSOC_CLKC_DISP0_CLKDIV_ENA, 0, &disp0_div_lock },
+	{ "sys1pll_qa12", "sys1pll_fixdiv", "sys1pll_a12", 0, 0, 0, SIRFSOC_CLKC_DISP0_CLKDIV_CFG, 8, 6, SIRFSOC_CLKC_DISP0_CLKDIV_ENA, 4, &disp0_div_lock },
+	{ "sys2pll_qa12", "sys2pll_fixdiv", "sys2pll_a12", 0, 0, 0, SIRFSOC_CLKC_DISP0_CLKDIV_CFG, 16, 6, SIRFSOC_CLKC_DISP0_CLKDIV_ENA, 8, &disp0_div_lock },
+	{ "sys3pll_qa12", "sys3pll_fixdiv", "sys3pll_a12", 0, 0, 0, SIRFSOC_CLKC_DISP0_CLKDIV_CFG, 24, 6, SIRFSOC_CLKC_DISP0_CLKDIV_ENA, 12, &disp0_div_lock },
+	{ "sys0pll_qa13", "sys0pll_fixdiv", "sys0pll_a13", 0, 0, 0, SIRFSOC_CLKC_DISP1_CLKDIV_CFG, 0, 6, SIRFSOC_CLKC_DISP1_CLKDIV_ENA, 0, &disp1_div_lock },
+	{ "sys1pll_qa13", "sys1pll_fixdiv", "sys1pll_a13", 0, 0, 0, SIRFSOC_CLKC_DISP1_CLKDIV_CFG, 8, 6, SIRFSOC_CLKC_DISP1_CLKDIV_ENA, 4, &disp1_div_lock },
+	{ "sys2pll_qa13", "sys2pll_fixdiv", "sys2pll_a13", 0, 0, 0, SIRFSOC_CLKC_DISP1_CLKDIV_CFG, 16, 6, SIRFSOC_CLKC_DISP1_CLKDIV_ENA, 8, &disp1_div_lock },
+	{ "sys3pll_qa13", "sys3pll_fixdiv", "sys3pll_a13", 0, 0, 0, SIRFSOC_CLKC_DISP1_CLKDIV_CFG, 24, 6, SIRFSOC_CLKC_DISP1_CLKDIV_ENA, 12, &disp1_div_lock },
+	{ "sys0pll_qa14", "sys0pll_fixdiv", "sys0pll_a14", 0, 0, 0, SIRFSOC_CLKC_GPU_CLKDIV_CFG, 0, 6, SIRFSOC_CLKC_GPU_CLKDIV_ENA, 0, &gpu_div_lock },
+	{ "sys1pll_qa14", "sys1pll_fixdiv", "sys1pll_a14", 0, 0, 0, SIRFSOC_CLKC_GPU_CLKDIV_CFG, 8, 6, SIRFSOC_CLKC_GPU_CLKDIV_ENA, 4, &gpu_div_lock },
+	{ "sys2pll_qa14", "sys2pll_fixdiv", "sys2pll_a14", 0, 0, 0, SIRFSOC_CLKC_GPU_CLKDIV_CFG, 16, 6, SIRFSOC_CLKC_GPU_CLKDIV_ENA, 8, &gpu_div_lock },
+	{ "sys3pll_qa14", "sys3pll_fixdiv", "sys3pll_a14", 0, 0, 0, SIRFSOC_CLKC_GPU_CLKDIV_CFG, 24, 6, SIRFSOC_CLKC_GPU_CLKDIV_ENA, 12, &gpu_div_lock },
+	{ "sys0pll_qa15", "sys0pll_fixdiv", "sys0pll_a15", 0, 0, 0, SIRFSOC_CLKC_GNSS_CLKDIV_CFG, 0, 6, SIRFSOC_CLKC_GNSS_CLKDIV_ENA, 0, &gnss_div_lock },
+	{ "sys1pll_qa15", "sys1pll_fixdiv", "sys1pll_a15", 0, 0, 0, SIRFSOC_CLKC_GNSS_CLKDIV_CFG, 8, 6, SIRFSOC_CLKC_GNSS_CLKDIV_ENA, 4, &gnss_div_lock },
+	{ "sys2pll_qa15", "sys2pll_fixdiv", "sys2pll_a15", 0, 0, 0, SIRFSOC_CLKC_GNSS_CLKDIV_CFG, 16, 6, SIRFSOC_CLKC_GNSS_CLKDIV_ENA, 8, &gnss_div_lock },
+	{ "sys3pll_qa15", "sys3pll_fixdiv", "sys3pll_a15", 0, 0, 0, SIRFSOC_CLKC_GNSS_CLKDIV_CFG, 24, 6, SIRFSOC_CLKC_GNSS_CLKDIV_ENA, 12, &gnss_div_lock },
+	{ "sys1pll_qa18", "sys1pll_fixdiv", "sys1pll_a18", 0, 0, 0, SIRFSOC_CLKC_SHARED_DIVIDER_CFG0, 24, 6, SIRFSOC_CLKC_SHARED_DIVIDER_ENA, 12, &share_div_lock },
+	{ "sys1pll_qa19", "sys1pll_fixdiv", "sys1pll_a19", 0, 0, CLK_IGNORE_UNUSED, SIRFSOC_CLKC_SHARED_DIVIDER_CFG0, 16, 6, SIRFSOC_CLKC_SHARED_DIVIDER_ENA, 8, &share_div_lock },
+	{ "sys1pll_qa20", "sys1pll_fixdiv", "sys1pll_a20", 0, 0, 0, SIRFSOC_CLKC_SHARED_DIVIDER_CFG0, 8, 6, SIRFSOC_CLKC_SHARED_DIVIDER_ENA, 4, &share_div_lock },
+	{ "sys2pll_qa20", "sys2pll_fixdiv", "sys2pll_a20", 0, 0, 0, SIRFSOC_CLKC_SHARED_DIVIDER_CFG0, 0, 6, SIRFSOC_CLKC_SHARED_DIVIDER_ENA, 0, &share_div_lock },
+	{ "sys1pll_qa17", "sys1pll_fixdiv", "sys1pll_a17", 0, 0, CLK_IGNORE_UNUSED, SIRFSOC_CLKC_SHARED_DIVIDER_CFG1, 8, 6, SIRFSOC_CLKC_SHARED_DIVIDER_ENA, 20, &share_div_lock },
+	{ "sys0pll_qa20", "sys0pll_fixdiv", "sys0pll_a20", 0, 0, 0, SIRFSOC_CLKC_SHARED_DIVIDER_CFG1, 0, 6, SIRFSOC_CLKC_SHARED_DIVIDER_ENA, 16, &share_div_lock },
+};
+
+static const char * const i2s_clk_parents[] = {
+	"xin",
+	"xinw",
+	"audio_dto",
+	/* "pwm_i2s01" */
+};
+
+static const char * const usbphy_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys0pll_a1",
+	"sys1pll_a1",
+	"sys2pll_a1",
+	"sys3pll_a1",
+};
+
+static const char * const btss_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys0pll_a2",
+	"sys1pll_a2",
+	"sys2pll_a2",
+	"sys3pll_a2",
+};
+
+static const char * const rgmii_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys0pll_a3",
+	"sys1pll_a3",
+	"sys2pll_a3",
+	"sys3pll_a3",
+};
+
+static const char * const cpu_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys0pll_a4",
+	"sys1pll_a4",
+	"cpupll_clk1",
+};
+
+static const char * const sdphy01_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys0pll_a5",
+	"sys1pll_a5",
+	"sys2pll_a5",
+	"sys3pll_a5",
+};
+
+static const char * const sdphy23_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys0pll_a6",
+	"sys1pll_a6",
+	"sys2pll_a6",
+	"sys3pll_a6",
+};
+
+static const char * const sdphy45_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys0pll_a7",
+	"sys1pll_a7",
+	"sys2pll_a7",
+	"sys3pll_a7",
+};
+
+static const char * const sdphy67_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys0pll_a8",
+	"sys1pll_a8",
+	"sys2pll_a8",
+	"sys3pll_a8",
+};
+
+static const char * const can_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys0pll_a9",
+	"sys1pll_a9",
+	"sys2pll_a9",
+	"sys3pll_a9",
+};
+
+static const char * const deint_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys0pll_a10",
+	"sys1pll_a10",
+	"sys2pll_a10",
+	"sys3pll_a10",
+};
+
+static const char * const nand_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys0pll_a11",
+	"sys1pll_a11",
+	"sys2pll_a11",
+	"sys3pll_a11",
+};
+
+static const char * const disp0_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys0pll_a12",
+	"sys1pll_a12",
+	"sys2pll_a12",
+	"sys3pll_a12",
+	"disp0_dto",
+};
+
+static const char * const disp1_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys0pll_a13",
+	"sys1pll_a13",
+	"sys2pll_a13",
+	"sys3pll_a13",
+	"disp1_dto",
+};
+
+static const char * const gpu_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys0pll_a14",
+	"sys1pll_a14",
+	"sys2pll_a14",
+	"sys3pll_a14",
+};
+
+static const char * const gnss_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys0pll_a15",
+	"sys1pll_a15",
+	"sys2pll_a15",
+	"sys3pll_a15",
+};
+
+static const char * const sys_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys2pll_a20",
+	"sys1pll_a20",
+	"sys1pll_a19",
+	"sys1pll_a18",
+	"sys0pll_a20",
+	"sys1pll_a17",
+};
+
+static const char * const io_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys2pll_a20",
+	"sys1pll_a20",
+	"sys1pll_a19",
+	"sys1pll_a18",
+	"sys0pll_a20",
+	"sys1pll_a17",
+};
+
+static const char * const g2d_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys2pll_a20",
+	"sys1pll_a20",
+	"sys1pll_a19",
+	"sys1pll_a18",
+	"sys0pll_a20",
+	"sys1pll_a17",
+};
+
+static const char * const jpenc_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys2pll_a20",
+	"sys1pll_a20",
+	"sys1pll_a19",
+	"sys1pll_a18",
+	"sys0pll_a20",
+	"sys1pll_a17",
+};
+
+static const char * const vdec_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys2pll_a20",
+	"sys1pll_a20",
+	"sys1pll_a19",
+	"sys1pll_a18",
+	"sys0pll_a20",
+	"sys1pll_a17",
+};
+
+static const char * const gmac_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys2pll_a20",
+	"sys1pll_a20",
+	"sys1pll_a19",
+	"sys1pll_a18",
+	"sys0pll_a20",
+	"sys1pll_a17",
+};
+
+static const char * const usb_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys2pll_a20",
+	"sys1pll_a20",
+	"sys1pll_a19",
+	"sys1pll_a18",
+	"sys0pll_a20",
+	"sys1pll_a17",
+};
+
+static const char * const kas_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys2pll_a20",
+	"sys1pll_a20",
+	"sys1pll_a19",
+	"sys1pll_a18",
+	"sys0pll_a20",
+	"sys1pll_a17",
+};
+
+static const char * const sec_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys2pll_a20",
+	"sys1pll_a20",
+	"sys1pll_a19",
+	"sys1pll_a18",
+	"sys0pll_a20",
+	"sys1pll_a17",
+};
+
+static const char * const sdr_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys2pll_a20",
+	"sys1pll_a20",
+	"sys1pll_a19",
+	"sys1pll_a18",
+	"sys0pll_a20",
+	"sys1pll_a17",
+};
+
+static const char * const vip_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys2pll_a20",
+	"sys1pll_a20",
+	"sys1pll_a19",
+	"sys1pll_a18",
+	"sys0pll_a20",
+	"sys1pll_a17",
+};
+
+static const char * const nocd_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys2pll_a20",
+	"sys1pll_a20",
+	"sys1pll_a19",
+	"sys1pll_a18",
+	"sys0pll_a20",
+	"sys1pll_a17",
+};
+
+static const char * const nocr_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys2pll_a20",
+	"sys1pll_a20",
+	"sys1pll_a19",
+	"sys1pll_a18",
+	"sys0pll_a20",
+	"sys1pll_a17",
+};
+
+static const char * const tpiu_clk_parents[] = {
+	"xin",
+	"xinw",
+	"sys2pll_a20",
+	"sys1pll_a20",
+	"sys1pll_a19",
+	"sys1pll_a18",
+	"sys0pll_a20",
+	"sys1pll_a17",
+};
+
+static struct atlas7_mux_init_data mux_list[] __initdata = {
+	/* mux_name, parent_names, parent_num, flags, mux_flags, mux_offset, shift, width */
+	{ "i2s_mux", i2s_clk_parents, ARRAY_SIZE(i2s_clk_parents), 0, 0, SIRFSOC_CLKC_I2S_CLK_SEL, 0, 2 },
+	{ "usbphy_mux", usbphy_clk_parents, ARRAY_SIZE(usbphy_clk_parents), 0, 0, SIRFSOC_CLKC_I2S_CLK_SEL, 0, 3 },
+	{ "btss_mux", btss_clk_parents, ARRAY_SIZE(btss_clk_parents), 0, 0, SIRFSOC_CLKC_BTSS_CLK_SEL, 0, 3 },
+	{ "rgmii_mux", rgmii_clk_parents, ARRAY_SIZE(rgmii_clk_parents), 0, 0, SIRFSOC_CLKC_RGMII_CLK_SEL, 0, 3 },
+	{ "cpu_mux", cpu_clk_parents, ARRAY_SIZE(cpu_clk_parents), 0, 0, SIRFSOC_CLKC_CPU_CLK_SEL, 0, 3 },
+	{ "sdphy01_mux", sdphy01_clk_parents, ARRAY_SIZE(sdphy01_clk_parents), 0, 0, SIRFSOC_CLKC_SDPHY01_CLK_SEL, 0, 3 },
+	{ "sdphy23_mux", sdphy23_clk_parents, ARRAY_SIZE(sdphy23_clk_parents), 0, 0, SIRFSOC_CLKC_SDPHY23_CLK_SEL, 0, 3 },
+	{ "sdphy45_mux", sdphy45_clk_parents, ARRAY_SIZE(sdphy45_clk_parents), 0, 0, SIRFSOC_CLKC_SDPHY45_CLK_SEL, 0, 3 },
+	{ "sdphy67_mux", sdphy67_clk_parents, ARRAY_SIZE(sdphy67_clk_parents), 0, 0, SIRFSOC_CLKC_SDPHY67_CLK_SEL, 0, 3 },
+	{ "can_mux", can_clk_parents, ARRAY_SIZE(can_clk_parents), 0, 0, SIRFSOC_CLKC_CAN_CLK_SEL, 0, 3 },
+	{ "deint_mux", deint_clk_parents, ARRAY_SIZE(deint_clk_parents), 0, 0, SIRFSOC_CLKC_DEINT_CLK_SEL, 0, 3 },
+	{ "nand_mux", nand_clk_parents, ARRAY_SIZE(nand_clk_parents), 0, 0, SIRFSOC_CLKC_NAND_CLK_SEL, 0, 3 },
+	{ "disp0_mux", disp0_clk_parents, ARRAY_SIZE(disp0_clk_parents), 0, 0, SIRFSOC_CLKC_DISP0_CLK_SEL, 0, 3 },
+	{ "disp1_mux", disp1_clk_parents, ARRAY_SIZE(disp1_clk_parents), 0, 0, SIRFSOC_CLKC_DISP1_CLK_SEL, 0, 3 },
+	{ "gpu_mux", gpu_clk_parents, ARRAY_SIZE(gpu_clk_parents), 0, 0, SIRFSOC_CLKC_GPU_CLK_SEL, 0, 3 },
+	{ "gnss_mux", gnss_clk_parents, ARRAY_SIZE(gnss_clk_parents), 0, 0, SIRFSOC_CLKC_GNSS_CLK_SEL, 0, 3 },
+	{ "sys_mux", sys_clk_parents, ARRAY_SIZE(sys_clk_parents), 0, 0, SIRFSOC_CLKC_SYS_CLK_SEL, 0, 3 },
+	{ "io_mux", io_clk_parents, ARRAY_SIZE(io_clk_parents), 0, 0, SIRFSOC_CLKC_IO_CLK_SEL, 0, 3 },
+	{ "g2d_mux", g2d_clk_parents, ARRAY_SIZE(g2d_clk_parents), 0, 0, SIRFSOC_CLKC_G2D_CLK_SEL, 0, 3 },
+	{ "jpenc_mux", jpenc_clk_parents, ARRAY_SIZE(jpenc_clk_parents), 0, 0, SIRFSOC_CLKC_JPENC_CLK_SEL, 0, 3 },
+	{ "vdec_mux", vdec_clk_parents, ARRAY_SIZE(vdec_clk_parents), 0, 0, SIRFSOC_CLKC_VDEC_CLK_SEL, 0, 3 },
+	{ "gmac_mux", gmac_clk_parents, ARRAY_SIZE(gmac_clk_parents), 0, 0, SIRFSOC_CLKC_GMAC_CLK_SEL, 0, 3 },
+	{ "usb_mux", usb_clk_parents, ARRAY_SIZE(usb_clk_parents), 0, 0, SIRFSOC_CLKC_USB_CLK_SEL, 0, 3 },
+	{ "kas_mux", kas_clk_parents, ARRAY_SIZE(kas_clk_parents), 0, 0, SIRFSOC_CLKC_KAS_CLK_SEL, 0, 3 },
+	{ "sec_mux", sec_clk_parents, ARRAY_SIZE(sec_clk_parents), 0, 0, SIRFSOC_CLKC_SEC_CLK_SEL, 0, 3 },
+	{ "sdr_mux", sdr_clk_parents, ARRAY_SIZE(sdr_clk_parents), 0, 0, SIRFSOC_CLKC_SDR_CLK_SEL, 0, 3 },
+	{ "vip_mux", vip_clk_parents, ARRAY_SIZE(vip_clk_parents), 0, 0, SIRFSOC_CLKC_VIP_CLK_SEL, 0, 3 },
+	{ "nocd_mux", nocd_clk_parents, ARRAY_SIZE(nocd_clk_parents), 0, 0, SIRFSOC_CLKC_NOCD_CLK_SEL, 0, 3 },
+	{ "nocr_mux", nocr_clk_parents, ARRAY_SIZE(nocr_clk_parents), 0, 0, SIRFSOC_CLKC_NOCR_CLK_SEL, 0, 3 },
+	{ "tpiu_mux", tpiu_clk_parents, ARRAY_SIZE(tpiu_clk_parents), 0, 0, SIRFSOC_CLKC_TPIU_CLK_SEL, 0, 3 },
+};
+
+	/* new unit should add start from the tail of list */
+static struct atlas7_unit_init_data unit_list[] __initdata = {
+	/* unit_name, parent_name, flags, regofs, bit, lock */
+	{ 0, "audmscm_kas", "kas_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 0, &root0_gate_lock },
+	{ 1, "gnssm_gnss", "gnss_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 1, &root0_gate_lock },
+	{ 2, "gpum_gpu", "gpu_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 2, &root0_gate_lock },
+	{ 3, "mediam_g2d", "g2d_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 3, &root0_gate_lock },
+	{ 4, "mediam_jpenc", "jpenc_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 4, &root0_gate_lock },
+	{ 5, "vdifm_disp0", "disp0_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 5, &root0_gate_lock },
+	{ 6, "vdifm_disp1", "disp1_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 6, &root0_gate_lock },
+	{ 7, "audmscm_i2s", "i2s_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 8, &root0_gate_lock },
+	{ 8, "audmscm_io", "io_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 11, &root0_gate_lock },
+	{ 9, "vdifm_io", "io_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 12, &root0_gate_lock },
+	{ 10, "gnssm_io", "io_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 13, &root0_gate_lock },
+	{ 11, "mediam_io", "io_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 14, &root0_gate_lock },
+	{ 12, "btm_io", "io_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 17, &root0_gate_lock },
+	{ 13, "mediam_sdphy01", "sdphy01_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 18, &root0_gate_lock },
+	{ 14, "vdifm_sdphy23", "sdphy23_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 19, &root0_gate_lock },
+	{ 15, "vdifm_sdphy45", "sdphy45_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 20, &root0_gate_lock },
+	{ 16, "vdifm_sdphy67", "sdphy67_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 21, &root0_gate_lock },
+	{ 17, "audmscm_xin", "xin", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 22, &root0_gate_lock },
+	{ 18, "mediam_nand", "nand_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 27, &root0_gate_lock },
+	{ 19, "gnssm_sec", "sec_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 28, &root0_gate_lock },
+	{ 20, "cpum_cpu", "cpu_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 29, &root0_gate_lock },
+	{ 21, "gnssm_xin", "xin", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 30, &root0_gate_lock },
+	{ 22, "vdifm_vip", "vip_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN0_SET, 31, &root0_gate_lock },
+	{ 23, "btm_btss", "btss_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 0, &root1_gate_lock },
+	{ 24, "mediam_usbphy", "usbphy_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 1, &root1_gate_lock },
+	{ 25, "rtcm_kas", "kas_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 2, &root1_gate_lock },
+	{ 26, "audmscm_nocd", "nocd_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 3, &root1_gate_lock },
+	{ 27, "vdifm_nocd", "nocd_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 4, &root1_gate_lock },
+	{ 28, "gnssm_nocd", "nocd_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 5, &root1_gate_lock },
+	{ 29, "mediam_nocd", "nocd_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 6, &root1_gate_lock },
+	{ 30, "cpum_nocd", "nocd_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 8, &root1_gate_lock },
+	{ 31, "gpum_nocd", "nocd_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 9, &root1_gate_lock },
+	{ 32, "audmscm_nocr", "nocr_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 11, &root1_gate_lock },
+	{ 33, "vdifm_nocr", "nocr_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 12, &root1_gate_lock },
+	{ 34, "gnssm_nocr", "nocr_mux", CLK_IGNORE_UNUSED, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 13, &root1_gate_lock },
+	{ 35, "mediam_nocr", "nocr_mux", CLK_IGNORE_UNUSED, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 14, &root1_gate_lock },
+	{ 36, "ddrm_nocr", "nocr_mux", CLK_IGNORE_UNUSED, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 15, &root1_gate_lock },
+	{ 37, "cpum_tpiu", "tpiu_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 16, &root1_gate_lock },
+	{ 38, "gpum_nocr", "nocr_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 17, &root1_gate_lock },
+	{ 39, "gnssm_rgmii", "rgmii_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 20, &root1_gate_lock },
+	{ 40, "mediam_vdec", "vdec_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 21, &root1_gate_lock },
+	{ 41, "gpum_sdr", "sdr_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 22, &root1_gate_lock },
+	{ 42, "vdifm_deint", "deint_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 23, &root1_gate_lock },
+	{ 43, "gnssm_can", "can_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 26, &root1_gate_lock },
+	{ 44, "mediam_usb", "usb_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 28, &root1_gate_lock },
+	{ 45, "gnssm_gmac", "gmac_mux", 0, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 29, &root1_gate_lock },
+	{ 46, "cvd_io", "audmscm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN1_SET, 0, &leaf1_gate_lock },
+	{ 47, "timer_io", "audmscm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN1_SET, 1, &leaf1_gate_lock },
+	{ 48, "pulse_io", "audmscm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN1_SET, 2, &leaf1_gate_lock },
+	{ 49, "tsc_io", "audmscm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN1_SET, 3, &leaf1_gate_lock },
+	{ 50, "tsc_xin", "audmscm_xin", 0, SIRFSOC_CLKC_LEAF_CLK_EN1_SET, 21, &leaf1_gate_lock },
+	{ 51, "ioctop_io", "audmscm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN1_SET, 4, &leaf1_gate_lock },
+	{ 52, "rsc_io", "audmscm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN1_SET, 5, &leaf1_gate_lock },
+	{ 53, "dvm_io", "audmscm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN1_SET, 6, &leaf1_gate_lock },
+	{ 54, "lvds_xin", "audmscm_xin", 0, SIRFSOC_CLKC_LEAF_CLK_EN1_SET, 7, &leaf1_gate_lock },
+	{ 55, "kas_kas", "audmscm_kas", 0, SIRFSOC_CLKC_LEAF_CLK_EN1_SET, 8, &leaf1_gate_lock },
+	{ 56, "ac97_kas", "audmscm_kas", 0, SIRFSOC_CLKC_LEAF_CLK_EN1_SET, 9, &leaf1_gate_lock },
+	{ 57, "usp0_kas", "audmscm_kas", 0, SIRFSOC_CLKC_LEAF_CLK_EN1_SET, 10, &leaf1_gate_lock },
+	{ 58, "usp1_kas", "audmscm_kas", 0, SIRFSOC_CLKC_LEAF_CLK_EN1_SET, 11, &leaf1_gate_lock },
+	{ 59, "usp2_kas", "audmscm_kas", 0, SIRFSOC_CLKC_LEAF_CLK_EN1_SET, 12, &leaf1_gate_lock },
+	{ 60, "dmac2_kas", "audmscm_kas", 0, SIRFSOC_CLKC_LEAF_CLK_EN1_SET, 13, &leaf1_gate_lock },
+	{ 61, "dmac3_kas", "audmscm_kas", 0, SIRFSOC_CLKC_LEAF_CLK_EN1_SET, 14, &leaf1_gate_lock },
+	{ 62, "audioif_kas", "audmscm_kas", 0, SIRFSOC_CLKC_LEAF_CLK_EN1_SET, 15, &leaf1_gate_lock },
+	{ 63, "i2s1_kas", "audmscm_kas", 0, SIRFSOC_CLKC_LEAF_CLK_EN1_SET, 17, &leaf1_gate_lock },
+	{ 64, "thaudmscm_io", "audmscm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN1_SET, 22, &leaf1_gate_lock },
+	{ 65, "analogtest_xin", "audmscm_xin", 0, SIRFSOC_CLKC_LEAF_CLK_EN1_SET, 23, &leaf1_gate_lock },
+	{ 66, "sys2pci_io", "vdifm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN2_SET, 0, &leaf2_gate_lock },
+	{ 67, "pciarb_io", "vdifm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN2_SET, 1, &leaf2_gate_lock },
+	{ 68, "pcicopy_io", "vdifm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN2_SET, 2, &leaf2_gate_lock },
+	{ 69, "rom_io", "vdifm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN2_SET, 3, &leaf2_gate_lock },
+	{ 70, "sdio23_io", "vdifm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN2_SET, 4, &leaf2_gate_lock },
+	{ 71, "sdio45_io", "vdifm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN2_SET, 5, &leaf2_gate_lock },
+	{ 72, "sdio67_io", "vdifm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN2_SET, 6, &leaf2_gate_lock },
+	{ 73, "vip1_io", "vdifm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN2_SET, 7, &leaf2_gate_lock },
+	{ 74, "vip1_vip", "vdifm_vip", 0, SIRFSOC_CLKC_LEAF_CLK_EN2_SET, 16, &leaf2_gate_lock },
+	{ 75, "sdio23_sdphy23", "vdifm_sdphy23", 0, SIRFSOC_CLKC_LEAF_CLK_EN2_SET, 8, &leaf2_gate_lock },
+	{ 76, "sdio45_sdphy45", "vdifm_sdphy45", 0, SIRFSOC_CLKC_LEAF_CLK_EN2_SET, 9, &leaf2_gate_lock },
+	{ 77, "sdio67_sdphy67", "vdifm_sdphy67", 0, SIRFSOC_CLKC_LEAF_CLK_EN2_SET, 10, &leaf2_gate_lock },
+	{ 78, "vpp0_disp0", "vdifm_disp0", 0, SIRFSOC_CLKC_LEAF_CLK_EN2_SET, 11, &leaf2_gate_lock },
+	{ 79, "lcd0_disp0", "vdifm_disp0", 0, SIRFSOC_CLKC_LEAF_CLK_EN2_SET, 12, &leaf2_gate_lock },
+	{ 80, "vpp1_disp1", "vdifm_disp1", 0, SIRFSOC_CLKC_LEAF_CLK_EN2_SET, 13, &leaf2_gate_lock },
+	{ 81, "lcd1_disp1", "vdifm_disp1", 0, SIRFSOC_CLKC_LEAF_CLK_EN2_SET, 14, &leaf2_gate_lock },
+	{ 82, "dcu_deint", "vdifm_deint", 0, SIRFSOC_CLKC_LEAF_CLK_EN2_SET, 15, &leaf2_gate_lock },
+	{ 83, "vdifm_dapa_r_nocr", "vdifm_nocr", 0, SIRFSOC_CLKC_LEAF_CLK_EN2_SET, 17, &leaf2_gate_lock },
+	{ 84, "gpio1_io", "vdifm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN2_SET, 18, &leaf2_gate_lock },
+	{ 85, "thvdifm_io", "vdifm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN2_SET, 19, &leaf2_gate_lock },
+	{ 86, "gmac_rgmii", "gnssm_rgmii", 0, SIRFSOC_CLKC_LEAF_CLK_EN3_SET, 0, &leaf3_gate_lock },
+	{ 87, "gmac_gmac", "gnssm_gmac", 0, SIRFSOC_CLKC_LEAF_CLK_EN3_SET, 1, &leaf3_gate_lock },
+	{ 88, "uart1_io", "gnssm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN3_SET, 2, &leaf3_gate_lock },
+	{ 89, "dmac0_io", "gnssm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN3_SET, 3, &leaf3_gate_lock },
+	{ 90, "uart0_io", "gnssm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN3_SET, 4, &leaf3_gate_lock },
+	{ 91, "uart2_io", "gnssm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN3_SET, 5, &leaf3_gate_lock },
+	{ 92, "uart3_io", "gnssm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN3_SET, 6, &leaf3_gate_lock },
+	{ 93, "uart4_io", "gnssm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN3_SET, 7, &leaf3_gate_lock },
+	{ 94, "uart5_io", "gnssm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN3_SET, 8, &leaf3_gate_lock },
+	{ 95, "spi1_io", "gnssm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN3_SET, 9, &leaf3_gate_lock },
+	{ 96, "gnss_gnss", "gnssm_gnss", 0, SIRFSOC_CLKC_LEAF_CLK_EN3_SET, 10, &leaf3_gate_lock },
+	{ 97, "canbus1_can", "gnssm_can", 0, SIRFSOC_CLKC_LEAF_CLK_EN3_SET, 12, &leaf3_gate_lock },
+	{ 98, "ccsec_sec", "gnssm_sec", 0, SIRFSOC_CLKC_LEAF_CLK_EN3_SET, 15, &leaf3_gate_lock },
+	{ 99,  "ccpub_sec", "gnssm_sec", 0, SIRFSOC_CLKC_LEAF_CLK_EN3_SET, 16, &leaf3_gate_lock },
+	{ 100, "gnssm_dapa_r_nocr", "gnssm_nocr", 0, SIRFSOC_CLKC_LEAF_CLK_EN3_SET, 13, &leaf3_gate_lock },
+	{ 101, "thgnssm_io", "gnssm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN3_SET, 14, &leaf3_gate_lock },
+	{ 102, "media_vdec", "mediam_vdec", 0, SIRFSOC_CLKC_LEAF_CLK_EN4_SET, 0, &leaf4_gate_lock },
+	{ 103, "media_jpenc", "mediam_jpenc", 0, SIRFSOC_CLKC_LEAF_CLK_EN4_SET, 1, &leaf4_gate_lock },
+	{ 104, "g2d_g2d", "mediam_g2d", 0, SIRFSOC_CLKC_LEAF_CLK_EN4_SET, 2, &leaf4_gate_lock },
+	{ 105, "i2c0_io", "mediam_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN4_SET, 3, &leaf4_gate_lock },
+	{ 106, "i2c1_io", "mediam_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN4_SET, 4, &leaf4_gate_lock },
+	{ 107, "gpio0_io", "mediam_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN4_SET, 5, &leaf4_gate_lock },
+	{ 108, "nand_io", "mediam_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN4_SET, 6, &leaf4_gate_lock },
+	{ 109, "sdio01_io", "mediam_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN4_SET, 7, &leaf4_gate_lock },
+	{ 110, "sys2pci2_io", "mediam_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN4_SET, 8, &leaf4_gate_lock },
+	{ 111, "sdio01_sdphy01", "mediam_sdphy01", 0, SIRFSOC_CLKC_LEAF_CLK_EN4_SET, 9, &leaf4_gate_lock },
+	{ 112, "nand_nand", "mediam_nand", 0, SIRFSOC_CLKC_LEAF_CLK_EN4_SET, 10, &leaf4_gate_lock },
+	{ 113, "usb0_usb", "mediam_usb", 0, SIRFSOC_CLKC_LEAF_CLK_EN4_SET, 11, &leaf4_gate_lock },
+	{ 114, "usb1_usb", "mediam_usb", 0, SIRFSOC_CLKC_LEAF_CLK_EN4_SET, 12, &leaf4_gate_lock },
+	{ 115, "usbphy0_usbphy", "mediam_usbphy", 0, SIRFSOC_CLKC_LEAF_CLK_EN4_SET, 13, &leaf4_gate_lock },
+	{ 116, "usbphy1_usbphy", "mediam_usbphy", 0, SIRFSOC_CLKC_LEAF_CLK_EN4_SET, 14, &leaf4_gate_lock },
+	{ 117, "thmediam_io", "mediam_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN4_SET, 15, &leaf4_gate_lock },
+	{ 118, "memc_mem", "mempll_clk1", CLK_IGNORE_UNUSED, SIRFSOC_CLKC_LEAF_CLK_EN5_SET, 0, &leaf5_gate_lock },
+	{ 119, "dapa_mem", "mempll_clk1", 0, SIRFSOC_CLKC_LEAF_CLK_EN5_SET, 1, &leaf5_gate_lock },
+	{ 120, "nocddrm_nocr", "ddrm_nocr", 0, SIRFSOC_CLKC_LEAF_CLK_EN5_SET, 2, &leaf5_gate_lock },
+	{ 121, "thddrm_nocr", "ddrm_nocr", 0, SIRFSOC_CLKC_LEAF_CLK_EN5_SET, 3, &leaf5_gate_lock },
+	{ 122, "spram1_cpudiv2", "cpum_cpu", 0, SIRFSOC_CLKC_LEAF_CLK_EN6_SET, 0, &leaf6_gate_lock },
+	{ 123, "spram2_cpudiv2", "cpum_cpu", 0, SIRFSOC_CLKC_LEAF_CLK_EN6_SET, 1, &leaf6_gate_lock },
+	{ 124, "coresight_cpudiv2", "cpum_cpu", 0, SIRFSOC_CLKC_LEAF_CLK_EN6_SET, 2, &leaf6_gate_lock },
+	{ 125, "thcpum_cpudiv4", "cpum_cpu", 0, SIRFSOC_CLKC_LEAF_CLK_EN6_SET, 3, &leaf6_gate_lock },
+	{ 126, "graphic_gpu", "gpum_gpu", 0, SIRFSOC_CLKC_LEAF_CLK_EN7_SET, 0, &leaf7_gate_lock },
+	{ 127, "vss_sdr", "gpum_sdr", 0, SIRFSOC_CLKC_LEAF_CLK_EN7_SET, 1, &leaf7_gate_lock },
+	{ 128, "thgpum_nocr", "gpum_nocr", 0, SIRFSOC_CLKC_LEAF_CLK_EN7_SET, 2, &leaf7_gate_lock },
+	{ 129, "a7ca_btss", "btm_btss", 0, SIRFSOC_CLKC_LEAF_CLK_EN8_SET, 1, &leaf8_gate_lock },
+	{ 130, "dmac4_io", "btm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN8_SET, 2, &leaf8_gate_lock },
+	{ 131, "uart6_io", "btm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN8_SET, 3, &leaf8_gate_lock },
+	{ 132, "usp3_io", "btm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN8_SET, 4, &leaf8_gate_lock },
+	{ 133, "a7ca_io", "btm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN8_SET, 5, &leaf8_gate_lock },
+	{ 134, "noc_btm_io", "btm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN8_SET, 6, &leaf8_gate_lock },
+	{ 135, "thbtm_io", "btm_io", 0, SIRFSOC_CLKC_LEAF_CLK_EN8_SET, 7, &leaf8_gate_lock },
+	{ 136, "btslow", "xinw_fixdiv_btslow", 0, SIRFSOC_CLKC_ROOT_CLK_EN1_SET, 25, &root1_gate_lock },
+	{ 137, "a7ca_btslow", "btslow", 0, SIRFSOC_CLKC_LEAF_CLK_EN8_SET, 0, &leaf8_gate_lock },
+};
+
+static struct clk *atlas7_clks[ARRAY_SIZE(unit_list)];
+
+static int unit_clk_is_enabled(struct clk_hw *hw)
+{
+	struct clk_unit *clk = to_unitclk(hw);
+	u32 reg;
+
+	reg = clk->regofs + SIRFSOC_CLKC_ROOT_CLK_EN0_STAT - SIRFSOC_CLKC_ROOT_CLK_EN0_SET;
+
+	return !!(clkc_readl(reg) & BIT(clk->bit));
+}
+
+static int unit_clk_enable(struct clk_hw *hw)
+{
+	u32 reg;
+	struct clk_unit *clk = to_unitclk(hw);
+	unsigned long flags;
+
+	reg = clk->regofs;
+
+	spin_lock_irqsave(clk->lock, flags);
+	clkc_writel(BIT(clk->bit), reg);
+	spin_unlock_irqrestore(clk->lock, flags);
+	return 0;
+}
+
+static void unit_clk_disable(struct clk_hw *hw)
+{
+	u32  reg;
+	struct clk_unit *clk = to_unitclk(hw);
+	unsigned long flags;
+
+	reg = clk->regofs + SIRFSOC_CLKC_ROOT_CLK_EN0_CLR - SIRFSOC_CLKC_ROOT_CLK_EN0_SET;
+
+	spin_lock_irqsave(clk->lock, flags);
+	clkc_writel(BIT(clk->bit), reg);
+	spin_unlock_irqrestore(clk->lock, flags);
+}
+
+static const struct clk_ops unit_clk_ops = {
+	.is_enabled = unit_clk_is_enabled,
+	.enable = unit_clk_enable,
+	.disable = unit_clk_disable,
+};
+
+static struct clk * __init
+atlas7_unit_clk_register(struct device *dev, const char *name,
+		 const char * const parent_name, unsigned long flags,
+		 u32 regofs, u8 bit, spinlock_t *lock)
+{
+	struct clk *clk;
+	struct clk_unit *unit;
+	struct clk_init_data init;
+
+	unit = kzalloc(sizeof(*unit), GFP_KERNEL);
+	if (!unit)
+		return ERR_PTR(-ENOMEM);
+
+	init.name = name;
+	init.parent_names = &parent_name;
+	init.num_parents = 1;
+	init.ops = &unit_clk_ops;
+	init.flags = flags;
+
+	unit->hw.init = &init;
+	unit->regofs = regofs;
+	unit->bit = bit;
+	unit->lock = lock;
+
+	clk = clk_register(dev, &unit->hw);
+	if (IS_ERR(clk))
+		kfree(unit);
+
+	return clk;
+}
+
+static struct atlas7_reset_desc atlas7_reset_unit[] = {
+	{ "PWM", 0x0244, 0, 0x0320, 0, &leaf0_gate_lock }, /* 0-5 */
+	{ "THCGUM", 0x0244, 3, 0x0320, 1, &leaf0_gate_lock },
+	{ "CVD", 0x04A0, 0, 0x032C, 0, &leaf1_gate_lock },
+	{ "TIMER", 0x04A0, 1, 0x032C, 1, &leaf1_gate_lock },
+	{ "PULSEC", 0x04A0, 2, 0x032C, 2, &leaf1_gate_lock },
+	{ "TSC", 0x04A0, 3, 0x032C, 3, &leaf1_gate_lock },
+	{ "IOCTOP", 0x04A0, 4, 0x032C, 4, &leaf1_gate_lock }, /* 6-10 */
+	{ "RSC", 0x04A0, 5, 0x032C, 5, &leaf1_gate_lock },
+	{ "DVM", 0x04A0, 6, 0x032C, 6, &leaf1_gate_lock },
+	{ "LVDS", 0x04A0, 7, 0x032C, 7, &leaf1_gate_lock },
+	{ "KAS", 0x04A0, 8, 0x032C, 8, &leaf1_gate_lock },
+	{ "AC97", 0x04A0, 9, 0x032C, 9, &leaf1_gate_lock }, /* 11-15 */
+	{ "USP0", 0x04A0, 10, 0x032C, 10, &leaf1_gate_lock },
+	{ "USP1", 0x04A0, 11, 0x032C, 11, &leaf1_gate_lock },
+	{ "USP2", 0x04A0, 12, 0x032C, 12, &leaf1_gate_lock },
+	{ "DMAC2", 0x04A0, 13, 0x032C, 13, &leaf1_gate_lock },
+	{ "DMAC3", 0x04A0, 14, 0x032C, 14, &leaf1_gate_lock }, /* 16-20 */
+	{ "AUDIO", 0x04A0, 15, 0x032C, 15, &leaf1_gate_lock },
+	{ "I2S1", 0x04A0, 17, 0x032C, 16, &leaf1_gate_lock },
+	{ "PMU_AUDIO", 0x04A0, 22, 0x032C, 17, &leaf1_gate_lock },
+	{ "THAUDMSCM", 0x04A0, 23, 0x032C, 18, &leaf1_gate_lock },
+	{ "SYS2PCI", 0x04B8, 0, 0x0338, 0, &leaf2_gate_lock }, /* 21-25 */
+	{ "PCIARB", 0x04B8, 1, 0x0338, 1, &leaf2_gate_lock },
+	{ "PCICOPY", 0x04B8, 2, 0x0338, 2, &leaf2_gate_lock },
+	{ "ROM", 0x04B8, 3, 0x0338, 3, &leaf2_gate_lock },
+	{ "SDIO23", 0x04B8, 4, 0x0338, 4, &leaf2_gate_lock },
+	{ "SDIO45", 0x04B8, 5, 0x0338, 5, &leaf2_gate_lock }, /* 26-30 */
+	{ "SDIO67", 0x04B8, 6, 0x0338, 6, &leaf2_gate_lock },
+	{ "VIP1", 0x04B8, 7, 0x0338, 7, &leaf2_gate_lock },
+	{ "VPP0", 0x04B8, 11, 0x0338, 8, &leaf2_gate_lock },
+	{ "LCD0", 0x04B8, 12, 0x0338, 9, &leaf2_gate_lock },
+	{ "VPP1", 0x04B8, 13, 0x0338, 10, &leaf2_gate_lock }, /* 31-35 */
+	{ "LCD1", 0x04B8, 14, 0x0338, 11, &leaf2_gate_lock },
+	{ "DCU", 0x04B8, 15, 0x0338, 12, &leaf2_gate_lock },
+	{ "GPIO", 0x04B8, 18, 0x0338, 13, &leaf2_gate_lock },
+	{ "DAPA_VDIFM", 0x04B8, 17, 0x0338, 15, &leaf2_gate_lock },
+	{ "THVDIFM", 0x04B8, 19, 0x0338, 16, &leaf2_gate_lock }, /* 36-40 */
+	{ "RGMII", 0x04D0, 0, 0x0344, 0, &leaf3_gate_lock },
+	{ "GMAC", 0x04D0, 1, 0x0344, 1, &leaf3_gate_lock },
+	{ "UART1", 0x04D0, 2, 0x0344, 2, &leaf3_gate_lock },
+	{ "DMAC0", 0x04D0, 3, 0x0344, 3, &leaf3_gate_lock },
+	{ "UART0", 0x04D0, 4, 0x0344, 4, &leaf3_gate_lock }, /* 41-45 */
+	{ "UART2", 0x04D0, 5, 0x0344, 5, &leaf3_gate_lock },
+	{ "UART3", 0x04D0, 6, 0x0344, 6, &leaf3_gate_lock },
+	{ "UART4", 0x04D0, 7, 0x0344, 7, &leaf3_gate_lock },
+	{ "UART5", 0x04D0, 8, 0x0344, 8, &leaf3_gate_lock },
+	{ "SPI1", 0x04D0, 9, 0x0344, 9, &leaf3_gate_lock }, /* 46-50 */
+	{ "GNSS_SYS_M0", 0x04D0, 10, 0x0344, 10, &leaf3_gate_lock },
+	{ "CANBUS1", 0x04D0, 12, 0x0344, 11, &leaf3_gate_lock },
+	{ "CCSEC", 0x04D0, 15, 0x0344, 12, &leaf3_gate_lock },
+	{ "CCPUB", 0x04D0, 16, 0x0344, 13, &leaf3_gate_lock },
+	{ "DAPA_GNSSM", 0x04D0, 13, 0x0344, 14, &leaf3_gate_lock }, /* 51-55 */
+	{ "THGNSSM", 0x04D0, 14, 0x0344, 15, &leaf3_gate_lock },
+	{ "VDEC", 0x04E8, 0, 0x0350, 0, &leaf4_gate_lock },
+	{ "JPENC", 0x04E8, 1, 0x0350, 1, &leaf4_gate_lock },
+	{ "G2D", 0x04E8, 2, 0x0350, 2, &leaf4_gate_lock },
+	{ "I2C0", 0x04E8, 3, 0x0350, 3, &leaf4_gate_lock }, /* 56-60 */
+	{ "I2C1", 0x04E8, 4, 0x0350, 4, &leaf4_gate_lock },
+	{ "GPIO0", 0x04E8, 5, 0x0350, 5, &leaf4_gate_lock },
+	{ "NAND", 0x04E8, 6, 0x0350, 6, &leaf4_gate_lock },
+	{ "SDIO01", 0x04E8, 7, 0x0350, 7, &leaf4_gate_lock },
+	{ "SYS2PCI2", 0x04E8, 8, 0x0350, 8, &leaf4_gate_lock }, /* 61-65 */
+	{ "USB0", 0x04E8, 11, 0x0350, 9, &leaf4_gate_lock },
+	{ "USB1", 0x04E8, 12, 0x0350, 10, &leaf4_gate_lock },
+	{ "THMEDIAM", 0x04E8, 15, 0x0350, 11, &leaf4_gate_lock },
+	{ "MEMC_DDRPHY", 0x0500, 0, 0x035C, 0, &leaf5_gate_lock },
+	{ "MEMC_UPCTL", 0x0500, 0, 0x035C, 1, &leaf5_gate_lock }, /* 66-70 */
+	{ "DAPA_MEM", 0x0500, 1, 0x035C, 2, &leaf5_gate_lock },
+	{ "MEMC_MEMDIV", 0x0500, 0, 0x035C, 3, &leaf5_gate_lock },
+	{ "THDDRM", 0x0500, 3, 0x035C, 4, &leaf5_gate_lock },
+	{ "CORESIGHT", 0x0518, 3, 0x0368, 13, &leaf6_gate_lock },
+	{ "THCPUM", 0x0518, 4, 0x0368, 17, &leaf6_gate_lock }, /* 71-75 */
+	{ "GRAPHIC", 0x0530, 0, 0x0374, 0, &leaf7_gate_lock },
+	{ "VSS_SDR", 0x0530, 1, 0x0374, 1, &leaf7_gate_lock },
+	{ "THGPUM", 0x0530, 2, 0x0374, 2, &leaf7_gate_lock },
+	{ "DMAC4", 0x0548, 2, 0x0380, 1, &leaf8_gate_lock },
+	{ "UART6", 0x0548, 3, 0x0380, 2, &leaf8_gate_lock }, /* 76- */
+	{ "USP3", 0x0548, 4, 0x0380, 3, &leaf8_gate_lock },
+	{ "THBTM", 0x0548, 5, 0x0380, 5, &leaf8_gate_lock },
+	{ "A7CA", 0x0548, 1, 0x0380, 0, &leaf8_gate_lock },
+	{ "A7CA_APB", 0x0548, 5, 0x0380, 4, &leaf8_gate_lock },
+};
+
+static int atlas7_reset_module(struct reset_controller_dev *rcdev,
+					unsigned long reset_idx)
+{
+	struct atlas7_reset_desc *reset = &atlas7_reset_unit[reset_idx];
+	unsigned long flags;
+
+	/*
+	 * HW suggest unit reset sequence:
+	 * assert sw reset (0)
+	 * setting sw clk_en to if the clock was disabled before reset
+	 * delay 16 clocks
+	 * disable clock (sw clk_en = 0)
+	 * de-assert reset (1)
+	 * after this sequence, restore clock or not is decided by SW
+	 */
+
+	spin_lock_irqsave(reset->lock, flags);
+	/* clock enable or not */
+	if (clkc_readl(reset->clk_ofs + 8) & (1 << reset->clk_bit)) {
+		clkc_writel(1 << reset->rst_bit, reset->rst_ofs + 4);
+		udelay(2);
+		clkc_writel(1 << reset->clk_bit, reset->clk_ofs + 4);
+		clkc_writel(1 << reset->rst_bit, reset->rst_ofs);
+		/* restore clock enable */
+		clkc_writel(1 << reset->clk_bit, reset->clk_ofs);
+	} else {
+		clkc_writel(1 << reset->rst_bit, reset->rst_ofs + 4);
+		clkc_writel(1 << reset->clk_bit, reset->clk_ofs);
+		udelay(2);
+		clkc_writel(1 << reset->clk_bit, reset->clk_ofs + 4);
+		clkc_writel(1 << reset->rst_bit, reset->rst_ofs);
+	}
+	spin_unlock_irqrestore(reset->lock, flags);
+
+	return 0;
+}
+
+static struct reset_control_ops atlas7_rst_ops = {
+	.reset = atlas7_reset_module,
+};
+
+static struct reset_controller_dev atlas7_rst_ctlr = {
+	.ops = &atlas7_rst_ops,
+	.owner = THIS_MODULE,
+	.of_reset_n_cells = 1,
+};
+
+static void __init atlas7_clk_init(struct device_node *np)
+{
+	struct clk *clk;
+	struct atlas7_div_init_data *div;
+	struct atlas7_mux_init_data *mux;
+	struct atlas7_unit_init_data *unit;
+	int i;
+	int ret;
+
+	sirfsoc_clk_vbase = of_iomap(np, 0);
+	if (!sirfsoc_clk_vbase)
+		panic("unable to map clkc registers\n");
+
+	of_node_put(np);
+
+	clk = clk_register(NULL, &clk_cpupll.hw);
+	BUG_ON(!clk);
+	clk = clk_register(NULL, &clk_mempll.hw);
+	BUG_ON(!clk);
+	clk = clk_register(NULL, &clk_sys0pll.hw);
+	BUG_ON(!clk);
+	clk = clk_register(NULL, &clk_sys1pll.hw);
+	BUG_ON(!clk);
+	clk = clk_register(NULL, &clk_sys2pll.hw);
+	BUG_ON(!clk);
+	clk = clk_register(NULL, &clk_sys3pll.hw);
+	BUG_ON(!clk);
+
+	clk = clk_register_divider_table(NULL, "cpupll_div1", "cpupll_vco", 0,
+			 sirfsoc_clk_vbase + SIRFSOC_CLKC_CPUPLL_AB_CTRL1, 0, 3, 0,
+			 pll_div_table, &cpupll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_divider_table(NULL, "cpupll_div2", "cpupll_vco", 0,
+			 sirfsoc_clk_vbase + SIRFSOC_CLKC_CPUPLL_AB_CTRL1, 4, 3, 0,
+			 pll_div_table, &cpupll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_divider_table(NULL, "cpupll_div3", "cpupll_vco", 0,
+			 sirfsoc_clk_vbase + SIRFSOC_CLKC_CPUPLL_AB_CTRL1, 8, 3, 0,
+			 pll_div_table, &cpupll_ctrl1_lock);
+	BUG_ON(!clk);
+
+	clk = clk_register_divider_table(NULL, "mempll_div1", "mempll_vco", 0,
+			 sirfsoc_clk_vbase + SIRFSOC_CLKC_MEMPLL_AB_CTRL1, 0, 3, 0,
+			 pll_div_table, &mempll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_divider_table(NULL, "mempll_div2", "mempll_vco", 0,
+			 sirfsoc_clk_vbase + SIRFSOC_CLKC_MEMPLL_AB_CTRL1, 4, 3, 0,
+			 pll_div_table, &mempll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_divider_table(NULL, "mempll_div3", "mempll_vco", 0,
+			 sirfsoc_clk_vbase + SIRFSOC_CLKC_MEMPLL_AB_CTRL1, 8, 3, 0,
+			 pll_div_table, &mempll_ctrl1_lock);
+	BUG_ON(!clk);
+
+	clk = clk_register_divider_table(NULL, "sys0pll_div1", "sys0pll_vco", 0,
+			 sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS0PLL_AB_CTRL1, 0, 3, 0,
+			 pll_div_table, &sys0pll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_divider_table(NULL, "sys0pll_div2", "sys0pll_vco", 0,
+			 sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS0PLL_AB_CTRL1, 4, 3, 0,
+			 pll_div_table, &sys0pll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_divider_table(NULL, "sys0pll_div3", "sys0pll_vco", 0,
+			 sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS0PLL_AB_CTRL1, 8, 3, 0,
+			 pll_div_table, &sys0pll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_fixed_factor(NULL, "sys0pll_fixdiv", "sys0pll_vco",
+					CLK_SET_RATE_PARENT, 1, 2);
+
+	clk = clk_register_divider_table(NULL, "sys1pll_div1", "sys1pll_vco", 0,
+			 sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS1PLL_AB_CTRL1, 0, 3, 0,
+			 pll_div_table, &sys1pll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_divider_table(NULL, "sys1pll_div2", "sys1pll_vco", 0,
+			 sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS1PLL_AB_CTRL1, 4, 3, 0,
+			 pll_div_table, &sys1pll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_divider_table(NULL, "sys1pll_div3", "sys1pll_vco", 0,
+			 sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS1PLL_AB_CTRL1, 8, 3, 0,
+			 pll_div_table, &sys1pll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_fixed_factor(NULL, "sys1pll_fixdiv", "sys1pll_vco",
+					CLK_SET_RATE_PARENT, 1, 2);
+
+	clk = clk_register_divider_table(NULL, "sys2pll_div1", "sys2pll_vco", 0,
+			 sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS2PLL_AB_CTRL1, 0, 3, 0,
+			 pll_div_table, &sys2pll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_divider_table(NULL, "sys2pll_div2", "sys2pll_vco", 0,
+			 sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS2PLL_AB_CTRL1, 4, 3, 0,
+			 pll_div_table, &sys2pll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_divider_table(NULL, "sys2pll_div3", "sys2pll_vco", 0,
+			 sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS2PLL_AB_CTRL1, 8, 3, 0,
+			 pll_div_table, &sys2pll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_fixed_factor(NULL, "sys2pll_fixdiv", "sys2pll_vco",
+					CLK_SET_RATE_PARENT, 1, 2);
+
+	clk = clk_register_divider_table(NULL, "sys3pll_div1", "sys3pll_vco", 0,
+			 sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS3PLL_AB_CTRL1, 0, 3, 0,
+			 pll_div_table, &sys3pll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_divider_table(NULL, "sys3pll_div2", "sys3pll_vco", 0,
+			 sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS3PLL_AB_CTRL1, 4, 3, 0,
+			 pll_div_table, &sys3pll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_divider_table(NULL, "sys3pll_div3", "sys3pll_vco", 0,
+			 sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS3PLL_AB_CTRL1, 8, 3, 0,
+			 pll_div_table, &sys3pll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_fixed_factor(NULL, "sys3pll_fixdiv", "sys3pll_vco",
+					CLK_SET_RATE_PARENT, 1, 2);
+
+	BUG_ON(!clk);
+	clk = clk_register_fixed_factor(NULL, "xinw_fixdiv_btslow", "xinw",
+					CLK_SET_RATE_PARENT, 1, 4);
+
+	BUG_ON(!clk);
+	clk = clk_register_gate(NULL, "cpupll_clk1", "cpupll_div1",
+		CLK_SET_RATE_PARENT, sirfsoc_clk_vbase + SIRFSOC_CLKC_CPUPLL_AB_CTRL1,
+				12, 0, &cpupll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_gate(NULL, "cpupll_clk2", "cpupll_div2",
+		CLK_SET_RATE_PARENT, sirfsoc_clk_vbase + SIRFSOC_CLKC_CPUPLL_AB_CTRL1,
+				13, 0, &cpupll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_gate(NULL, "cpupll_clk3", "cpupll_div3",
+		CLK_SET_RATE_PARENT, sirfsoc_clk_vbase + SIRFSOC_CLKC_CPUPLL_AB_CTRL1,
+				14, 0, &cpupll_ctrl1_lock);
+	BUG_ON(!clk);
+
+	clk = clk_register_gate(NULL, "mempll_clk1", "mempll_div1",
+		CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+		sirfsoc_clk_vbase + SIRFSOC_CLKC_MEMPLL_AB_CTRL1,
+		12, 0, &mempll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_gate(NULL, "mempll_clk2", "mempll_div2",
+		CLK_SET_RATE_PARENT, sirfsoc_clk_vbase + SIRFSOC_CLKC_MEMPLL_AB_CTRL1,
+				13, 0, &mempll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_gate(NULL, "mempll_clk3", "mempll_div3",
+		CLK_SET_RATE_PARENT, sirfsoc_clk_vbase + SIRFSOC_CLKC_MEMPLL_AB_CTRL1,
+				14, 0, &mempll_ctrl1_lock);
+	BUG_ON(!clk);
+
+	clk = clk_register_gate(NULL, "sys0pll_clk1", "sys0pll_div1",
+		CLK_SET_RATE_PARENT, sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS0PLL_AB_CTRL1,
+				12, 0, &sys0pll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_gate(NULL, "sys0pll_clk2", "sys0pll_div2",
+		CLK_SET_RATE_PARENT, sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS0PLL_AB_CTRL1,
+				13, 0, &sys0pll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_gate(NULL, "sys0pll_clk3", "sys0pll_div3",
+		CLK_SET_RATE_PARENT, sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS0PLL_AB_CTRL1,
+				14, 0, &sys0pll_ctrl1_lock);
+	BUG_ON(!clk);
+
+	clk = clk_register_gate(NULL, "sys1pll_clk1", "sys1pll_div1",
+		CLK_SET_RATE_PARENT, sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS1PLL_AB_CTRL1,
+				12, 0, &sys1pll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_gate(NULL, "sys1pll_clk2", "sys1pll_div2",
+		CLK_SET_RATE_PARENT, sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS1PLL_AB_CTRL1,
+				13, 0, &sys1pll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_gate(NULL, "sys1pll_clk3", "sys1pll_div3",
+		CLK_SET_RATE_PARENT, sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS1PLL_AB_CTRL1,
+				14, 0, &sys1pll_ctrl1_lock);
+	BUG_ON(!clk);
+
+	clk = clk_register_gate(NULL, "sys2pll_clk1", "sys2pll_div1",
+		CLK_SET_RATE_PARENT, sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS2PLL_AB_CTRL1,
+				12, 0, &sys2pll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_gate(NULL, "sys2pll_clk2", "sys2pll_div2",
+		CLK_SET_RATE_PARENT, sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS2PLL_AB_CTRL1,
+				13, 0, &sys2pll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_gate(NULL, "sys2pll_clk3", "sys2pll_div3",
+		CLK_SET_RATE_PARENT, sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS2PLL_AB_CTRL1,
+				14, 0, &sys2pll_ctrl1_lock);
+	BUG_ON(!clk);
+
+	clk = clk_register_gate(NULL, "sys3pll_clk1", "sys3pll_div1",
+		CLK_SET_RATE_PARENT, sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS3PLL_AB_CTRL1,
+				12, 0, &sys3pll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_gate(NULL, "sys3pll_clk2", "sys3pll_div2",
+		CLK_SET_RATE_PARENT, sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS3PLL_AB_CTRL1,
+				13, 0, &sys3pll_ctrl1_lock);
+	BUG_ON(!clk);
+	clk = clk_register_gate(NULL, "sys3pll_clk3", "sys3pll_div3",
+		CLK_SET_RATE_PARENT, sirfsoc_clk_vbase + SIRFSOC_CLKC_SYS3PLL_AB_CTRL1,
+				14, 0, &sys3pll_ctrl1_lock);
+	BUG_ON(!clk);
+
+	clk = clk_register(NULL, &clk_audio_dto.hw);
+	BUG_ON(!clk);
+
+	clk = clk_register(NULL, &clk_disp0_dto.hw);
+	BUG_ON(!clk);
+
+	clk = clk_register(NULL, &clk_disp1_dto.hw);
+	BUG_ON(!clk);
+
+	for (i = 0; i < ARRAY_SIZE(divider_list); i++) {
+		div = &divider_list[i];
+		clk = clk_register_divider(NULL, div->div_name,
+			div->parent_name, div->divider_flags, sirfsoc_clk_vbase + div->div_offset,
+			div->shift, div->width, 0, div->lock);
+		BUG_ON(!clk);
+		clk = clk_register_gate(NULL, div->gate_name, div->div_name,
+			div->gate_flags, sirfsoc_clk_vbase + div->gate_offset,
+				div->gate_bit, 0, div->lock);
+		BUG_ON(!clk);
+	}
+	/* ignore selector status register check */
+	for (i = 0; i < ARRAY_SIZE(mux_list); i++) {
+		mux = &mux_list[i];
+		clk = clk_register_mux(NULL, mux->mux_name, mux->parent_names,
+			       mux->parent_num, mux->flags,
+			       sirfsoc_clk_vbase + mux->mux_offset,
+			       mux->shift, mux->width,
+			       mux->mux_flags, NULL);
+		BUG_ON(!clk);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(unit_list); i++) {
+		unit = &unit_list[i];
+		atlas7_clks[i] = atlas7_unit_clk_register(NULL, unit->unit_name, unit->parent_name,
+				unit->flags, unit->regofs, unit->bit, unit->lock);
+		BUG_ON(!atlas7_clks[i]);
+	}
+
+	clk_data.clks = atlas7_clks;
+	clk_data.clk_num = ARRAY_SIZE(unit_list);
+
+	ret = of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data);
+	BUG_ON(ret);
+
+	atlas7_rst_ctlr.of_node = np;
+	atlas7_rst_ctlr.nr_resets = ARRAY_SIZE(atlas7_reset_unit);
+	reset_controller_register(&atlas7_rst_ctlr);
+}
+CLK_OF_DECLARE(atlas7_clk, "sirf,atlas7-car", atlas7_clk_init);
diff --git a/drivers/clk/sirf/clk-common.c b/drivers/clk/sirf/clk-common.c
index 37af51c..9fc285d 100644
--- a/drivers/clk/sirf/clk-common.c
+++ b/drivers/clk/sirf/clk-common.c
@@ -10,8 +10,8 @@
 #define KHZ     1000
 #define MHZ     (KHZ * KHZ)
 
-static void *sirfsoc_clk_vbase;
-static void *sirfsoc_rsc_vbase;
+static void __iomem *sirfsoc_clk_vbase;
+static void __iomem *sirfsoc_rsc_vbase;
 static struct clk_onecell_data clk_data;
 
 /*
@@ -188,7 +188,7 @@
 	.set_rate = pll_clk_set_rate,
 };
 
-static const char *pll_clk_parents[] = {
+static const char * const pll_clk_parents[] = {
 	"osc",
 };
 
@@ -284,7 +284,7 @@
  * clock domains - cpu, mem, sys/io, dsp, gfx
  */
 
-static const char *dmn_clk_parents[] = {
+static const char * const dmn_clk_parents[] = {
 	"rtc",
 	"osc",
 	"pll1",
@@ -673,7 +673,7 @@
 	clkc_writel(val, reg);
 }
 
-static const char *std_clk_io_parents[] = {
+static const char * const std_clk_io_parents[] = {
 	"io",
 };
 
@@ -949,7 +949,7 @@
 	},
 };
 
-static const char *std_clk_dsp_parents[] = {
+static const char * const std_clk_dsp_parents[] = {
 	"dsp",
 };
 
@@ -981,7 +981,7 @@
 	},
 };
 
-static const char *std_clk_sys_parents[] = {
+static const char * const std_clk_sys_parents[] = {
 	"sys",
 };
 
@@ -999,7 +999,7 @@
 	},
 };
 
-static const char *std_clk_usb_parents[] = {
+static const char * const std_clk_usb_parents[] = {
 	"usb_pll",
 };
 
diff --git a/drivers/clk/socfpga/Makefile b/drivers/clk/socfpga/Makefile
index 7e2d15a..d8bb239 100644
--- a/drivers/clk/socfpga/Makefile
+++ b/drivers/clk/socfpga/Makefile
@@ -2,3 +2,4 @@
 obj-y += clk-gate.o
 obj-y += clk-pll.o
 obj-y += clk-periph.o
+obj-y += clk-pll-a10.o clk-periph-a10.o clk-gate-a10.o
diff --git a/drivers/clk/socfpga/clk-gate-a10.c b/drivers/clk/socfpga/clk-gate-a10.c
new file mode 100644
index 0000000..83c6780
--- /dev/null
+++ b/drivers/clk/socfpga/clk-gate-a10.c
@@ -0,0 +1,190 @@
+/*
+ * Copyright (C) 2015 Altera Corporation. All rights reserved
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/clk-provider.h>
+#include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/of.h>
+#include <linux/regmap.h>
+
+#include "clk.h"
+
+#define streq(a, b) (strcmp((a), (b)) == 0)
+
+#define to_socfpga_gate_clk(p) container_of(p, struct socfpga_gate_clk, hw.hw)
+
+/* SDMMC Group for System Manager defines */
+#define SYSMGR_SDMMCGRP_CTRL_OFFSET	0x28
+
+static unsigned long socfpga_gate_clk_recalc_rate(struct clk_hw *hwclk,
+	unsigned long parent_rate)
+{
+	struct socfpga_gate_clk *socfpgaclk = to_socfpga_gate_clk(hwclk);
+	u32 div = 1, val;
+
+	if (socfpgaclk->fixed_div)
+		div = socfpgaclk->fixed_div;
+	else if (socfpgaclk->div_reg) {
+		val = readl(socfpgaclk->div_reg) >> socfpgaclk->shift;
+		val &= div_mask(socfpgaclk->width);
+		div = (1 << val);
+	}
+
+	return parent_rate / div;
+}
+
+static int socfpga_clk_prepare(struct clk_hw *hwclk)
+{
+	struct socfpga_gate_clk *socfpgaclk = to_socfpga_gate_clk(hwclk);
+	int i;
+	u32 hs_timing;
+	u32 clk_phase[2];
+
+	if (socfpgaclk->clk_phase[0] || socfpgaclk->clk_phase[1]) {
+		for (i = 0; i < ARRAY_SIZE(clk_phase); i++) {
+			switch (socfpgaclk->clk_phase[i]) {
+			case 0:
+				clk_phase[i] = 0;
+				break;
+			case 45:
+				clk_phase[i] = 1;
+				break;
+			case 90:
+				clk_phase[i] = 2;
+				break;
+			case 135:
+				clk_phase[i] = 3;
+				break;
+			case 180:
+				clk_phase[i] = 4;
+				break;
+			case 225:
+				clk_phase[i] = 5;
+				break;
+			case 270:
+				clk_phase[i] = 6;
+				break;
+			case 315:
+				clk_phase[i] = 7;
+				break;
+			default:
+				clk_phase[i] = 0;
+				break;
+			}
+		}
+
+		hs_timing = SYSMGR_SDMMC_CTRL_SET(clk_phase[0], clk_phase[1]);
+		if (!IS_ERR(socfpgaclk->sys_mgr_base_addr))
+			regmap_write(socfpgaclk->sys_mgr_base_addr,
+				     SYSMGR_SDMMCGRP_CTRL_OFFSET, hs_timing);
+		else
+			pr_err("%s: cannot set clk_phase because sys_mgr_base_addr is not available!\n",
+					__func__);
+	}
+	return 0;
+}
+
+static struct clk_ops gateclk_ops = {
+	.prepare = socfpga_clk_prepare,
+	.recalc_rate = socfpga_gate_clk_recalc_rate,
+};
+
+static void __init __socfpga_gate_init(struct device_node *node,
+	const struct clk_ops *ops)
+{
+	u32 clk_gate[2];
+	u32 div_reg[3];
+	u32 clk_phase[2];
+	u32 fixed_div;
+	struct clk *clk;
+	struct socfpga_gate_clk *socfpga_clk;
+	const char *clk_name = node->name;
+	const char *parent_name[SOCFPGA_MAX_PARENTS];
+	struct clk_init_data init;
+	int rc;
+	int i = 0;
+
+	socfpga_clk = kzalloc(sizeof(*socfpga_clk), GFP_KERNEL);
+	if (WARN_ON(!socfpga_clk))
+		return;
+
+	rc = of_property_read_u32_array(node, "clk-gate", clk_gate, 2);
+	if (rc)
+		clk_gate[0] = 0;
+
+	if (clk_gate[0]) {
+		socfpga_clk->hw.reg = clk_mgr_a10_base_addr + clk_gate[0];
+		socfpga_clk->hw.bit_idx = clk_gate[1];
+
+		gateclk_ops.enable = clk_gate_ops.enable;
+		gateclk_ops.disable = clk_gate_ops.disable;
+	}
+
+	rc = of_property_read_u32(node, "fixed-divider", &fixed_div);
+	if (rc)
+		socfpga_clk->fixed_div = 0;
+	else
+		socfpga_clk->fixed_div = fixed_div;
+
+	rc = of_property_read_u32_array(node, "div-reg", div_reg, 3);
+	if (!rc) {
+		socfpga_clk->div_reg = clk_mgr_a10_base_addr + div_reg[0];
+		socfpga_clk->shift = div_reg[1];
+		socfpga_clk->width = div_reg[2];
+	} else {
+		socfpga_clk->div_reg = NULL;
+	}
+
+	rc = of_property_read_u32_array(node, "clk-phase", clk_phase, 2);
+	if (!rc) {
+		socfpga_clk->clk_phase[0] = clk_phase[0];
+		socfpga_clk->clk_phase[1] = clk_phase[1];
+
+		socfpga_clk->sys_mgr_base_addr =
+			syscon_regmap_lookup_by_compatible("altr,sys-mgr");
+		if (IS_ERR(socfpga_clk->sys_mgr_base_addr)) {
+			pr_err("%s: failed to find altr,sys-mgr regmap!\n",
+					__func__);
+			return;
+		}
+	}
+
+	of_property_read_string(node, "clock-output-names", &clk_name);
+
+	init.name = clk_name;
+	init.ops = ops;
+	init.flags = 0;
+	while (i < SOCFPGA_MAX_PARENTS && (parent_name[i] =
+			of_clk_get_parent_name(node, i)) != NULL)
+		i++;
+
+	init.parent_names = parent_name;
+	init.num_parents = i;
+	socfpga_clk->hw.hw.init = &init;
+
+	clk = clk_register(NULL, &socfpga_clk->hw.hw);
+	if (WARN_ON(IS_ERR(clk))) {
+		kfree(socfpga_clk);
+		return;
+	}
+	rc = of_clk_add_provider(node, of_clk_src_simple_get, clk);
+	if (WARN_ON(rc))
+		return;
+}
+
+void __init socfpga_a10_gate_init(struct device_node *node)
+{
+	__socfpga_gate_init(node, &gateclk_ops);
+}
diff --git a/drivers/clk/socfpga/clk-gate.c b/drivers/clk/socfpga/clk-gate.c
index dd3a78c..82449cd 100644
--- a/drivers/clk/socfpga/clk-gate.c
+++ b/drivers/clk/socfpga/clk-gate.c
@@ -32,14 +32,10 @@
 #define SOCFPGA_MMC_CLK			"sdmmc_clk"
 #define SOCFPGA_GPIO_DB_CLK_OFFSET	0xA8
 
-#define streq(a, b) (strcmp((a), (b)) == 0)
-
 #define to_socfpga_gate_clk(p) container_of(p, struct socfpga_gate_clk, hw.hw)
 
 /* SDMMC Group for System Manager defines */
 #define SYSMGR_SDMMCGRP_CTRL_OFFSET    0x108
-#define SYSMGR_SDMMC_CTRL_SET(smplsel, drvsel) \
-	((((smplsel) & 0x7) << 3) | (((drvsel) & 0x7) << 0))
 
 static u8 socfpga_clk_get_parent(struct clk_hw *hwclk)
 {
@@ -194,7 +190,6 @@
 	const char *parent_name[SOCFPGA_MAX_PARENTS];
 	struct clk_init_data init;
 	int rc;
-	int i = 0;
 
 	socfpga_clk = kzalloc(sizeof(*socfpga_clk), GFP_KERNEL);
 	if (WARN_ON(!socfpga_clk))
@@ -224,7 +219,7 @@
 		socfpga_clk->shift = div_reg[1];
 		socfpga_clk->width = div_reg[2];
 	} else {
-		socfpga_clk->div_reg = 0;
+		socfpga_clk->div_reg = NULL;
 	}
 
 	rc = of_property_read_u32_array(node, "clk-phase", clk_phase, 2);
@@ -238,12 +233,9 @@
 	init.name = clk_name;
 	init.ops = ops;
 	init.flags = 0;
-	while (i < SOCFPGA_MAX_PARENTS && (parent_name[i] =
-			of_clk_get_parent_name(node, i)) != NULL)
-		i++;
 
+	init.num_parents = of_clk_parent_fill(node, parent_name, SOCFPGA_MAX_PARENTS);
 	init.parent_names = parent_name;
-	init.num_parents = i;
 	socfpga_clk->hw.hw.init = &init;
 
 	clk = clk_register(NULL, &socfpga_clk->hw.hw);
diff --git a/drivers/clk/socfpga/clk-periph-a10.c b/drivers/clk/socfpga/clk-periph-a10.c
new file mode 100644
index 0000000..9d0181b
--- /dev/null
+++ b/drivers/clk/socfpga/clk-periph-a10.c
@@ -0,0 +1,138 @@
+/*
+ * Copyright (C) 2015 Altera Corporation. All rights reserved
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/clk-provider.h>
+#include <linux/io.h>
+#include <linux/of.h>
+
+#include "clk.h"
+
+#define CLK_MGR_FREE_SHIFT		16
+#define CLK_MGR_FREE_MASK		0x7
+
+#define SOCFPGA_MPU_FREE_CLK		"mpu_free_clk"
+#define SOCFPGA_NOC_FREE_CLK		"noc_free_clk"
+#define SOCFPGA_SDMMC_FREE_CLK		"sdmmc_free_clk"
+#define to_socfpga_periph_clk(p) container_of(p, struct socfpga_periph_clk, hw.hw)
+
+static unsigned long clk_periclk_recalc_rate(struct clk_hw *hwclk,
+					     unsigned long parent_rate)
+{
+	struct socfpga_periph_clk *socfpgaclk = to_socfpga_periph_clk(hwclk);
+	u32 div;
+
+	if (socfpgaclk->fixed_div) {
+		div = socfpgaclk->fixed_div;
+	} else if (socfpgaclk->div_reg) {
+		div = readl(socfpgaclk->div_reg) >> socfpgaclk->shift;
+		div &= div_mask(socfpgaclk->width);
+		div += 1;
+	} else {
+		div = ((readl(socfpgaclk->hw.reg) & 0x7ff) + 1);
+	}
+
+	return parent_rate / div;
+}
+
+static u8 clk_periclk_get_parent(struct clk_hw *hwclk)
+{
+	struct socfpga_periph_clk *socfpgaclk = to_socfpga_periph_clk(hwclk);
+	u32 clk_src;
+
+	clk_src = readl(socfpgaclk->hw.reg);
+	if (streq(hwclk->init->name, SOCFPGA_MPU_FREE_CLK) ||
+	    streq(hwclk->init->name, SOCFPGA_NOC_FREE_CLK) ||
+	    streq(hwclk->init->name, SOCFPGA_SDMMC_FREE_CLK))
+		return (clk_src >> CLK_MGR_FREE_SHIFT) &
+			CLK_MGR_FREE_MASK;
+	else
+		return 0;
+}
+
+static const struct clk_ops periclk_ops = {
+	.recalc_rate = clk_periclk_recalc_rate,
+	.get_parent = clk_periclk_get_parent,
+};
+
+static __init void __socfpga_periph_init(struct device_node *node,
+	const struct clk_ops *ops)
+{
+	u32 reg;
+	struct clk *clk;
+	struct socfpga_periph_clk *periph_clk;
+	const char *clk_name = node->name;
+	const char *parent_name;
+	struct clk_init_data init;
+	int rc;
+	u32 fixed_div;
+	u32 div_reg[3];
+
+	of_property_read_u32(node, "reg", &reg);
+
+	periph_clk = kzalloc(sizeof(*periph_clk), GFP_KERNEL);
+	if (WARN_ON(!periph_clk))
+		return;
+
+	periph_clk->hw.reg = clk_mgr_a10_base_addr + reg;
+
+	rc = of_property_read_u32_array(node, "div-reg", div_reg, 3);
+	if (!rc) {
+		periph_clk->div_reg = clk_mgr_a10_base_addr + div_reg[0];
+		periph_clk->shift = div_reg[1];
+		periph_clk->width = div_reg[2];
+	} else {
+		periph_clk->div_reg = NULL;
+	}
+
+	rc = of_property_read_u32(node, "fixed-divider", &fixed_div);
+	if (rc)
+		periph_clk->fixed_div = 0;
+	else
+		periph_clk->fixed_div = fixed_div;
+
+	of_property_read_string(node, "clock-output-names", &clk_name);
+
+	init.name = clk_name;
+	init.ops = ops;
+	init.flags = 0;
+
+	parent_name = of_clk_get_parent_name(node, 0);
+	init.num_parents = 1;
+	init.parent_names = &parent_name;
+
+	periph_clk->hw.hw.init = &init;
+
+	clk = clk_register(NULL, &periph_clk->hw.hw);
+	if (WARN_ON(IS_ERR(clk))) {
+		kfree(periph_clk);
+		return;
+	}
+	rc = of_clk_add_provider(node, of_clk_src_simple_get, clk);
+	if (rc < 0) {
+		pr_err("Could not register clock provider for node:%s\n",
+		       clk_name);
+		goto err_clk;
+	}
+
+	return;
+
+err_clk:
+	clk_unregister(clk);
+}
+
+void __init socfpga_a10_periph_init(struct device_node *node)
+{
+	__socfpga_periph_init(node, &periclk_ops);
+}
diff --git a/drivers/clk/socfpga/clk-periph.c b/drivers/clk/socfpga/clk-periph.c
index 46531c3..83aeaa2 100644
--- a/drivers/clk/socfpga/clk-periph.c
+++ b/drivers/clk/socfpga/clk-periph.c
@@ -76,7 +76,7 @@
 		periph_clk->shift = div_reg[1];
 		periph_clk->width = div_reg[2];
 	} else {
-		periph_clk->div_reg = 0;
+		periph_clk->div_reg = NULL;
 	}
 
 	rc = of_property_read_u32(node, "fixed-divider", &fixed_div);
diff --git a/drivers/clk/socfpga/clk-pll-a10.c b/drivers/clk/socfpga/clk-pll-a10.c
new file mode 100644
index 0000000..1178b11
--- /dev/null
+++ b/drivers/clk/socfpga/clk-pll-a10.c
@@ -0,0 +1,129 @@
+/*
+ * Copyright (C) 2015 Altera Corporation. All rights reserved
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/clk-provider.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+
+#include "clk.h"
+
+/* Clock Manager offsets */
+#define CLK_MGR_PLL_CLK_SRC_SHIFT	8
+#define CLK_MGR_PLL_CLK_SRC_MASK	0x3
+
+/* Clock bypass bits */
+#define SOCFPGA_PLL_BG_PWRDWN		0
+#define SOCFPGA_PLL_PWR_DOWN		1
+#define SOCFPGA_PLL_EXT_ENA		2
+#define SOCFPGA_PLL_DIVF_MASK		0x00001FFF
+#define SOCFPGA_PLL_DIVF_SHIFT	0
+#define SOCFPGA_PLL_DIVQ_MASK		0x003F0000
+#define SOCFPGA_PLL_DIVQ_SHIFT	16
+#define SOCFGPA_MAX_PARENTS	5
+
+#define SOCFPGA_MAIN_PLL_CLK		"main_pll"
+#define SOCFPGA_PERIP_PLL_CLK		"periph_pll"
+
+#define to_socfpga_clk(p) container_of(p, struct socfpga_pll, hw.hw)
+
+void __iomem *clk_mgr_a10_base_addr;
+
+static unsigned long clk_pll_recalc_rate(struct clk_hw *hwclk,
+					 unsigned long parent_rate)
+{
+	struct socfpga_pll *socfpgaclk = to_socfpga_clk(hwclk);
+	unsigned long divf, divq, reg;
+	unsigned long long vco_freq;
+
+	/* read VCO1 reg for numerator and denominator */
+	reg = readl(socfpgaclk->hw.reg + 0x4);
+	divf = (reg & SOCFPGA_PLL_DIVF_MASK) >> SOCFPGA_PLL_DIVF_SHIFT;
+	divq = (reg & SOCFPGA_PLL_DIVQ_MASK) >> SOCFPGA_PLL_DIVQ_SHIFT;
+	vco_freq = (unsigned long long)parent_rate * (divf + 1);
+	do_div(vco_freq, (1 + divq));
+	return (unsigned long)vco_freq;
+}
+
+static u8 clk_pll_get_parent(struct clk_hw *hwclk)
+{
+	struct socfpga_pll *socfpgaclk = to_socfpga_clk(hwclk);
+	u32 pll_src;
+
+	pll_src = readl(socfpgaclk->hw.reg);
+
+	return (pll_src >> CLK_MGR_PLL_CLK_SRC_SHIFT) &
+		CLK_MGR_PLL_CLK_SRC_MASK;
+}
+
+static struct clk_ops clk_pll_ops = {
+	.recalc_rate = clk_pll_recalc_rate,
+	.get_parent = clk_pll_get_parent,
+};
+
+static struct __init clk * __socfpga_pll_init(struct device_node *node,
+	const struct clk_ops *ops)
+{
+	u32 reg;
+	struct clk *clk;
+	struct socfpga_pll *pll_clk;
+	const char *clk_name = node->name;
+	const char *parent_name[SOCFGPA_MAX_PARENTS];
+	struct clk_init_data init;
+	struct device_node *clkmgr_np;
+	int rc;
+	int i = 0;
+
+	of_property_read_u32(node, "reg", &reg);
+
+	pll_clk = kzalloc(sizeof(*pll_clk), GFP_KERNEL);
+	if (WARN_ON(!pll_clk))
+		return NULL;
+
+	clkmgr_np = of_find_compatible_node(NULL, NULL, "altr,clk-mgr");
+	clk_mgr_a10_base_addr = of_iomap(clkmgr_np, 0);
+	BUG_ON(!clk_mgr_a10_base_addr);
+	pll_clk->hw.reg = clk_mgr_a10_base_addr + reg;
+
+	of_property_read_string(node, "clock-output-names", &clk_name);
+
+	init.name = clk_name;
+	init.ops = ops;
+	init.flags = 0;
+
+	while (i < SOCFGPA_MAX_PARENTS && (parent_name[i] =
+			of_clk_get_parent_name(node, i)) != NULL)
+		i++;
+	init.num_parents = i;
+	init.parent_names = parent_name;
+	pll_clk->hw.hw.init = &init;
+
+	pll_clk->hw.bit_idx = SOCFPGA_PLL_EXT_ENA;
+	clk_pll_ops.enable = clk_gate_ops.enable;
+	clk_pll_ops.disable = clk_gate_ops.disable;
+
+	clk = clk_register(NULL, &pll_clk->hw.hw);
+	if (WARN_ON(IS_ERR(clk))) {
+		kfree(pll_clk);
+		return NULL;
+	}
+	rc = of_clk_add_provider(node, of_clk_src_simple_get, clk);
+	return clk;
+}
+
+void __init socfpga_a10_pll_init(struct device_node *node)
+{
+	__socfpga_pll_init(node, &clk_pll_ops);
+}
diff --git a/drivers/clk/socfpga/clk-pll.c b/drivers/clk/socfpga/clk-pll.c
index de6da95..8f26b52 100644
--- a/drivers/clk/socfpga/clk-pll.c
+++ b/drivers/clk/socfpga/clk-pll.c
@@ -92,7 +92,6 @@
 	struct clk_init_data init;
 	struct device_node *clkmgr_np;
 	int rc;
-	int i = 0;
 
 	of_property_read_u32(node, "reg", &reg);
 
@@ -111,11 +110,7 @@
 	init.ops = ops;
 	init.flags = 0;
 
-	while (i < SOCFPGA_MAX_PARENTS && (parent_name[i] =
-			of_clk_get_parent_name(node, i)) != NULL)
-		i++;
-
-	init.num_parents = i;
+	init.num_parents = of_clk_parent_fill(node, parent_name, SOCFPGA_MAX_PARENTS);
 	init.parent_names = parent_name;
 	pll_clk->hw.hw.init = &init;
 
diff --git a/drivers/clk/socfpga/clk.c b/drivers/clk/socfpga/clk.c
index 43db947..7564d2e 100644
--- a/drivers/clk/socfpga/clk.c
+++ b/drivers/clk/socfpga/clk.c
@@ -24,4 +24,9 @@
 CLK_OF_DECLARE(socfpga_pll_clk, "altr,socfpga-pll-clock", socfpga_pll_init);
 CLK_OF_DECLARE(socfpga_perip_clk, "altr,socfpga-perip-clk", socfpga_periph_init);
 CLK_OF_DECLARE(socfpga_gate_clk, "altr,socfpga-gate-clk", socfpga_gate_init);
-
+CLK_OF_DECLARE(socfpga_a10_pll_clk, "altr,socfpga-a10-pll-clock",
+	       socfpga_a10_pll_init);
+CLK_OF_DECLARE(socfpga_a10_perip_clk, "altr,socfpga-a10-perip-clk",
+	       socfpga_a10_periph_init);
+CLK_OF_DECLARE(socfpga_a10_gate_clk, "altr,socfpga-a10-gate-clk",
+	       socfpga_a10_gate_init);
diff --git a/drivers/clk/socfpga/clk.h b/drivers/clk/socfpga/clk.h
index d291f60..603973a 100644
--- a/drivers/clk/socfpga/clk.h
+++ b/drivers/clk/socfpga/clk.h
@@ -26,14 +26,22 @@
 #define CLKMGR_L4SRC		0x70
 #define CLKMGR_PERPLL_SRC	0xAC
 
-#define SOCFPGA_MAX_PARENTS		3
+#define SOCFPGA_MAX_PARENTS		5
 #define div_mask(width) ((1 << (width)) - 1)
 
+#define streq(a, b) (strcmp((a), (b)) == 0)
+#define SYSMGR_SDMMC_CTRL_SET(smplsel, drvsel) \
+	((((smplsel) & 0x7) << 3) | (((drvsel) & 0x7) << 0))
+
 extern void __iomem *clk_mgr_base_addr;
+extern void __iomem *clk_mgr_a10_base_addr;
 
 void __init socfpga_pll_init(struct device_node *node);
 void __init socfpga_periph_init(struct device_node *node);
 void __init socfpga_gate_init(struct device_node *node);
+void socfpga_a10_pll_init(struct device_node *node);
+void socfpga_a10_periph_init(struct device_node *node);
+void socfpga_a10_gate_init(struct device_node *node);
 
 struct socfpga_pll {
 	struct clk_gate	hw;
@@ -44,6 +52,7 @@
 	char *parent_name;
 	u32 fixed_div;
 	void __iomem *div_reg;
+	struct regmap *sys_mgr_base_addr;
 	u32 width;	/* only valid if div_reg != 0 */
 	u32 shift;	/* only valid if div_reg != 0 */
 	u32 clk_phase[2];
diff --git a/drivers/clk/st/clk-flexgen.c b/drivers/clk/st/clk-flexgen.c
index bf12a25..657ca14 100644
--- a/drivers/clk/st/clk-flexgen.c
+++ b/drivers/clk/st/clk-flexgen.c
@@ -116,7 +116,7 @@
 	return *prate / div;
 }
 
-unsigned long flexgen_recalc_rate(struct clk_hw *hw,
+static unsigned long flexgen_recalc_rate(struct clk_hw *hw,
 		unsigned long parent_rate)
 {
 	struct flexgen *flexgen = to_flexgen(hw);
@@ -174,7 +174,7 @@
 	.set_rate = flexgen_set_rate,
 };
 
-struct clk *clk_register_flexgen(const char *name,
+static struct clk *clk_register_flexgen(const char *name,
 				const char **parent_names, u8 num_parents,
 				void __iomem *reg, spinlock_t *lock, u32 idx,
 				unsigned long flexgen_flags) {
@@ -245,7 +245,7 @@
 	const char **parents;
 	int nparents, i;
 
-	nparents = of_count_phandle_with_args(np, "clocks", "#clock-cells");
+	nparents = of_clk_get_parent_count(np);
 	if (WARN_ON(nparents <= 0))
 		return NULL;
 
@@ -260,7 +260,7 @@
 	return parents;
 }
 
-void __init st_of_flexgen_setup(struct device_node *np)
+static void __init st_of_flexgen_setup(struct device_node *np)
 {
 	struct device_node *pnode;
 	void __iomem *reg;
diff --git a/drivers/clk/st/clkgen-fsyn.c b/drivers/clk/st/clkgen-fsyn.c
index a917c4c..e94197f 100644
--- a/drivers/clk/st/clkgen-fsyn.c
+++ b/drivers/clk/st/clkgen-fsyn.c
@@ -492,7 +492,7 @@
 	return !!npda;
 }
 
-int clk_fs660c32_vco_get_rate(unsigned long input, struct stm_fs *fs,
+static int clk_fs660c32_vco_get_rate(unsigned long input, struct stm_fs *fs,
 			   unsigned long *rate)
 {
 	unsigned long nd = fs->ndiv + 16; /* ndiv value */
@@ -519,7 +519,7 @@
 	return rate;
 }
 
-int clk_fs660c32_vco_get_params(unsigned long input,
+static int clk_fs660c32_vco_get_params(unsigned long input,
 				unsigned long output, struct stm_fs *fs)
 {
 /* Formula
diff --git a/drivers/clk/st/clkgen-mux.c b/drivers/clk/st/clkgen-mux.c
index fdcff10..4fbe6e0 100644
--- a/drivers/clk/st/clkgen-mux.c
+++ b/drivers/clk/st/clkgen-mux.c
@@ -26,7 +26,7 @@
 	const char **parents;
 	int nparents, i;
 
-	nparents = of_count_phandle_with_args(np, "clocks", "#clock-cells");
+	nparents = of_clk_get_parent_count(np);
 	if (WARN_ON(nparents <= 0))
 		return ERR_PTR(-EINVAL);
 
@@ -131,7 +131,7 @@
 	return (s8)clk_mux_ops.get_parent(mux_hw) > 0;
 }
 
-u8 clkgena_divmux_get_parent(struct clk_hw *hw)
+static u8 clkgena_divmux_get_parent(struct clk_hw *hw)
 {
 	struct clkgena_divmux *genamux = to_clkgena_divmux(hw);
 	struct clk_hw *mux_hw = &genamux->mux.hw;
@@ -168,7 +168,7 @@
 	return 0;
 }
 
-unsigned long clkgena_divmux_recalc_rate(struct clk_hw *hw,
+static unsigned long clkgena_divmux_recalc_rate(struct clk_hw *hw,
 		unsigned long parent_rate)
 {
 	struct clkgena_divmux *genamux = to_clkgena_divmux(hw);
@@ -215,7 +215,7 @@
 /**
  * clk_register_genamux - register a genamux clock with the clock framework
  */
-struct clk *clk_register_genamux(const char *name,
+static struct clk *clk_register_genamux(const char *name,
 				const char **parent_names, u8 num_parents,
 				void __iomem *reg,
 				const struct clkgena_divmux_data *muxdata,
@@ -385,7 +385,7 @@
 	return reg;
 }
 
-void __init st_of_clkgena_divmux_setup(struct device_node *np)
+static void __init st_of_clkgena_divmux_setup(struct device_node *np)
 {
 	const struct of_device_id *match;
 	const struct clkgena_divmux_data *data;
@@ -485,7 +485,7 @@
 	{}
 };
 
-void __init st_of_clkgena_prediv_setup(struct device_node *np)
+static void __init st_of_clkgena_prediv_setup(struct device_node *np)
 {
 	const struct of_device_id *match;
 	void __iomem *reg;
@@ -622,7 +622,7 @@
 	{}
 };
 
-void __init st_of_clkgen_mux_setup(struct device_node *np)
+static void __init st_of_clkgen_mux_setup(struct device_node *np)
 {
 	const struct of_device_id *match;
 	struct clk *clk;
@@ -699,7 +699,7 @@
 	{}
 };
 
-void __init st_of_clkgen_vcc_setup(struct device_node *np)
+static void __init st_of_clkgen_vcc_setup(struct device_node *np)
 {
 	const struct of_device_id *match;
 	void __iomem *reg;
diff --git a/drivers/clk/st/clkgen-pll.c b/drivers/clk/st/clkgen-pll.c
index d204ba8..1065322 100644
--- a/drivers/clk/st/clkgen-pll.c
+++ b/drivers/clk/st/clkgen-pll.c
@@ -270,7 +270,7 @@
 	return !poweroff;
 }
 
-unsigned long recalc_stm_pll800c65(struct clk_hw *hw,
+static unsigned long recalc_stm_pll800c65(struct clk_hw *hw,
 		unsigned long parent_rate)
 {
 	struct clkgen_pll *pll = to_clkgen_pll(hw);
@@ -297,7 +297,7 @@
 
 }
 
-unsigned long recalc_stm_pll1600c65(struct clk_hw *hw,
+static unsigned long recalc_stm_pll1600c65(struct clk_hw *hw,
 		unsigned long parent_rate)
 {
 	struct clkgen_pll *pll = to_clkgen_pll(hw);
@@ -321,7 +321,7 @@
 	return rate;
 }
 
-unsigned long recalc_stm_pll3200c32(struct clk_hw *hw,
+static unsigned long recalc_stm_pll3200c32(struct clk_hw *hw,
 		unsigned long parent_rate)
 {
 	struct clkgen_pll *pll = to_clkgen_pll(hw);
@@ -343,7 +343,7 @@
 	return rate;
 }
 
-unsigned long recalc_stm_pll1200c32(struct clk_hw *hw,
+static unsigned long recalc_stm_pll1200c32(struct clk_hw *hw,
 		unsigned long parent_rate)
 {
 	struct clkgen_pll *pll = to_clkgen_pll(hw);
@@ -544,7 +544,7 @@
 	       "st,clkgena-plls-c65", clkgena_c65_pll_setup);
 
 static struct clk * __init clkgen_odf_register(const char *parent_name,
-					       void * __iomem reg,
+					       void __iomem *reg,
 					       struct clkgen_pll_data *pll_data,
 					       int odf,
 					       spinlock_t *odf_lock,
diff --git a/drivers/clk/sunxi/clk-mod0.c b/drivers/clk/sunxi/clk-mod0.c
index ec8f5a1..9d028ae 100644
--- a/drivers/clk/sunxi/clk-mod0.c
+++ b/drivers/clk/sunxi/clk-mod0.c
@@ -128,7 +128,7 @@
 	},
 	.probe = sun4i_a10_mod0_clk_probe,
 };
-module_platform_driver(sun4i_a10_mod0_clk_driver);
+builtin_platform_driver(sun4i_a10_mod0_clk_driver);
 
 static const struct factors_data sun9i_a80_mod0_data __initconst = {
 	.enable = 31,
diff --git a/drivers/clk/sunxi/clk-sun9i-core.c b/drivers/clk/sunxi/clk-sun9i-core.c
index d8da77d..887f4ea 100644
--- a/drivers/clk/sunxi/clk-sun9i-core.c
+++ b/drivers/clk/sunxi/clk-sun9i-core.c
@@ -93,7 +93,7 @@
 	void __iomem *reg;
 
 	reg = of_io_request_and_map(node, 0, of_node_full_name(node));
-	if (!reg) {
+	if (IS_ERR(reg)) {
 		pr_err("Could not get registers for a80-pll4-clk: %s\n",
 		       node->name);
 		return;
@@ -154,7 +154,7 @@
 	struct clk *gt;
 
 	reg = of_io_request_and_map(node, 0, of_node_full_name(node));
-	if (!reg) {
+	if (IS_ERR(reg)) {
 		pr_err("Could not get registers for a80-gt-clk: %s\n",
 		       node->name);
 		return;
@@ -218,7 +218,7 @@
 	void __iomem *reg;
 
 	reg = of_io_request_and_map(node, 0, of_node_full_name(node));
-	if (!reg) {
+	if (IS_ERR(reg)) {
 		pr_err("Could not get registers for a80-ahb-clk: %s\n",
 		       node->name);
 		return;
@@ -244,7 +244,7 @@
 	void __iomem *reg;
 
 	reg = of_io_request_and_map(node, 0, of_node_full_name(node));
-	if (!reg) {
+	if (IS_ERR(reg)) {
 		pr_err("Could not get registers for a80-apb0-clk: %s\n",
 		       node->name);
 		return;
@@ -310,7 +310,7 @@
 	void __iomem *reg;
 
 	reg = of_io_request_and_map(node, 0, of_node_full_name(node));
-	if (!reg) {
+	if (IS_ERR(reg)) {
 		pr_err("Could not get registers for a80-apb1-clk: %s\n",
 		       node->name);
 		return;
diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c
index 7e1e2bd..9a82f17 100644
--- a/drivers/clk/sunxi/clk-sunxi.c
+++ b/drivers/clk/sunxi/clk-sunxi.c
@@ -198,6 +198,8 @@
 	int i = 0;
 
 	reg = of_io_request_and_map(node, 0, of_node_full_name(node));
+	if (IS_ERR(reg))
+		return;
 
 	/* we have a mux, we will have >1 parents */
 	while (i < SUN6I_AHB1_MAX_PARENTS &&
diff --git a/drivers/clk/sunxi/clk-usb.c b/drivers/clk/sunxi/clk-usb.c
index a86ed2f..3a25f95 100644
--- a/drivers/clk/sunxi/clk-usb.c
+++ b/drivers/clk/sunxi/clk-usb.c
@@ -204,6 +204,17 @@
 }
 CLK_OF_DECLARE(sun6i_a31_usb, "allwinner,sun6i-a31-usb-clk", sun6i_a31_usb_setup);
 
+static const struct usb_clk_data sun8i_a23_usb_clk_data __initconst = {
+	.clk_mask = BIT(16) | BIT(11) | BIT(10) | BIT(9) | BIT(8),
+	.reset_mask = BIT(2) | BIT(1) | BIT(0),
+};
+
+static void __init sun8i_a23_usb_setup(struct device_node *node)
+{
+	sunxi_usb_clk_setup(node, &sun8i_a23_usb_clk_data, &sun4i_a10_usb_lock);
+}
+CLK_OF_DECLARE(sun8i_a23_usb, "allwinner,sun8i-a23-usb-clk", sun8i_a23_usb_setup);
+
 static const struct usb_clk_data sun9i_a80_usb_mod_data __initconst = {
 	.clk_mask = BIT(6) | BIT(5) | BIT(4) | BIT(3) | BIT(2) | BIT(1),
 	.reset_mask = BIT(19) | BIT(18) | BIT(17),
diff --git a/drivers/clk/tegra/Kconfig b/drivers/clk/tegra/Kconfig
new file mode 100644
index 0000000..1ba30d1
--- /dev/null
+++ b/drivers/clk/tegra/Kconfig
@@ -0,0 +1,3 @@
+config TEGRA_CLK_EMC
+	def_bool y
+	depends on TEGRA124_EMC
diff --git a/drivers/clk/tegra/Makefile b/drivers/clk/tegra/Makefile
index edb8358..aec862b 100644
--- a/drivers/clk/tegra/Makefile
+++ b/drivers/clk/tegra/Makefile
@@ -11,6 +11,7 @@
 obj-y					+= clk-tegra-pmc.o
 obj-y					+= clk-tegra-fixed.o
 obj-y					+= clk-tegra-super-gen4.o
+obj-$(CONFIG_TEGRA_CLK_EMC)		+= clk-emc.o
 obj-$(CONFIG_ARCH_TEGRA_2x_SOC)         += clk-tegra20.o
 obj-$(CONFIG_ARCH_TEGRA_3x_SOC)         += clk-tegra30.o
 obj-$(CONFIG_ARCH_TEGRA_114_SOC)	+= clk-tegra114.o
diff --git a/drivers/clk/tegra/clk-emc.c b/drivers/clk/tegra/clk-emc.c
new file mode 100644
index 0000000..7649685
--- /dev/null
+++ b/drivers/clk/tegra/clk-emc.c
@@ -0,0 +1,538 @@
+/*
+ * drivers/clk/tegra/clk-emc.c
+ *
+ * Copyright (c) 2014, NVIDIA CORPORATION.  All rights reserved.
+ *
+ * Author:
+ *	Mikko Perttunen <mperttunen@nvidia.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/clk.h>
+#include <linux/clkdev.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/sort.h>
+#include <linux/string.h>
+
+#include <soc/tegra/fuse.h>
+#include <soc/tegra/emc.h>
+
+#include "clk.h"
+
+#define CLK_SOURCE_EMC 0x19c
+
+#define CLK_SOURCE_EMC_EMC_2X_CLK_DIVISOR_SHIFT 0
+#define CLK_SOURCE_EMC_EMC_2X_CLK_DIVISOR_MASK 0xff
+#define CLK_SOURCE_EMC_EMC_2X_CLK_DIVISOR(x) (((x) & CLK_SOURCE_EMC_EMC_2X_CLK_DIVISOR_MASK) << \
+					      CLK_SOURCE_EMC_EMC_2X_CLK_DIVISOR_SHIFT)
+
+#define CLK_SOURCE_EMC_EMC_2X_CLK_SRC_SHIFT 29
+#define CLK_SOURCE_EMC_EMC_2X_CLK_SRC_MASK 0x7
+#define CLK_SOURCE_EMC_EMC_2X_CLK_SRC(x) (((x) & CLK_SOURCE_EMC_EMC_2X_CLK_SRC_MASK) << \
+					  CLK_SOURCE_EMC_EMC_2X_CLK_SRC_SHIFT)
+
+static const char * const emc_parent_clk_names[] = {
+	"pll_m", "pll_c", "pll_p", "clk_m", "pll_m_ud",
+	"pll_c2", "pll_c3", "pll_c_ud"
+};
+
+/*
+ * List of clock sources for various parents the EMC clock can have.
+ * When we change the timing to a timing with a parent that has the same
+ * clock source as the current parent, we must first change to a backup
+ * timing that has a different clock source.
+ */
+
+#define EMC_SRC_PLL_M 0
+#define EMC_SRC_PLL_C 1
+#define EMC_SRC_PLL_P 2
+#define EMC_SRC_CLK_M 3
+#define EMC_SRC_PLL_C2 4
+#define EMC_SRC_PLL_C3 5
+
+static const char emc_parent_clk_sources[] = {
+	EMC_SRC_PLL_M, EMC_SRC_PLL_C, EMC_SRC_PLL_P, EMC_SRC_CLK_M,
+	EMC_SRC_PLL_M, EMC_SRC_PLL_C2, EMC_SRC_PLL_C3, EMC_SRC_PLL_C
+};
+
+struct emc_timing {
+	unsigned long rate, parent_rate;
+	u8 parent_index;
+	struct clk *parent;
+	u32 ram_code;
+};
+
+struct tegra_clk_emc {
+	struct clk_hw hw;
+	void __iomem *clk_regs;
+	struct clk *prev_parent;
+	bool changing_timing;
+
+	struct device_node *emc_node;
+	struct tegra_emc *emc;
+
+	int num_timings;
+	struct emc_timing *timings;
+	spinlock_t *lock;
+};
+
+/* Common clock framework callback implementations */
+
+static unsigned long emc_recalc_rate(struct clk_hw *hw,
+				     unsigned long parent_rate)
+{
+	struct tegra_clk_emc *tegra;
+	u32 val, div;
+
+	tegra = container_of(hw, struct tegra_clk_emc, hw);
+
+	/*
+	 * CCF wrongly assumes that the parent won't change during set_rate,
+	 * so get the parent rate explicitly.
+	 */
+	parent_rate = __clk_get_rate(__clk_get_parent(hw->clk));
+
+	val = readl(tegra->clk_regs + CLK_SOURCE_EMC);
+	div = val & CLK_SOURCE_EMC_EMC_2X_CLK_DIVISOR_MASK;
+
+	return parent_rate / (div + 2) * 2;
+}
+
+/*
+ * Rounds up unless no higher rate exists, in which case down. This way is
+ * safer since things have EMC rate floors. Also don't touch parent_rate
+ * since we don't want the CCF to play with our parent clocks.
+ */
+static long emc_determine_rate(struct clk_hw *hw, unsigned long rate,
+			       unsigned long min_rate,
+			       unsigned long max_rate,
+			       unsigned long *best_parent_rate,
+			       struct clk_hw **best_parent_hw)
+{
+	struct tegra_clk_emc *tegra;
+	u8 ram_code = tegra_read_ram_code();
+	struct emc_timing *timing = NULL;
+	int i;
+
+	tegra = container_of(hw, struct tegra_clk_emc, hw);
+
+	for (i = 0; i < tegra->num_timings; i++) {
+		if (tegra->timings[i].ram_code != ram_code)
+			continue;
+
+		timing = tegra->timings + i;
+
+		if (timing->rate > max_rate) {
+			i = min(i, 1);
+			return tegra->timings[i - 1].rate;
+		}
+
+		if (timing->rate < min_rate)
+			continue;
+
+		if (timing->rate >= rate)
+			return timing->rate;
+	}
+
+	if (timing)
+		return timing->rate;
+
+	return __clk_get_rate(hw->clk);
+}
+
+static u8 emc_get_parent(struct clk_hw *hw)
+{
+	struct tegra_clk_emc *tegra;
+	u32 val;
+
+	tegra = container_of(hw, struct tegra_clk_emc, hw);
+
+	val = readl(tegra->clk_regs + CLK_SOURCE_EMC);
+
+	return (val >> CLK_SOURCE_EMC_EMC_2X_CLK_SRC_SHIFT)
+		& CLK_SOURCE_EMC_EMC_2X_CLK_SRC_MASK;
+}
+
+static struct tegra_emc *emc_ensure_emc_driver(struct tegra_clk_emc *tegra)
+{
+	struct platform_device *pdev;
+
+	if (tegra->emc)
+		return tegra->emc;
+
+	if (!tegra->emc_node)
+		return NULL;
+
+	pdev = of_find_device_by_node(tegra->emc_node);
+	if (!pdev) {
+		pr_err("%s: could not get external memory controller\n",
+		       __func__);
+		return NULL;
+	}
+
+	of_node_put(tegra->emc_node);
+	tegra->emc_node = NULL;
+
+	tegra->emc = platform_get_drvdata(pdev);
+	if (!tegra->emc) {
+		pr_err("%s: cannot find EMC driver\n", __func__);
+		return NULL;
+	}
+
+	return tegra->emc;
+}
+
+static int emc_set_timing(struct tegra_clk_emc *tegra,
+			  struct emc_timing *timing)
+{
+	int err;
+	u8 div;
+	u32 car_value;
+	unsigned long flags = 0;
+	struct tegra_emc *emc = emc_ensure_emc_driver(tegra);
+
+	if (!emc)
+		return -ENOENT;
+
+	pr_debug("going to rate %ld prate %ld p %s\n", timing->rate,
+		 timing->parent_rate, __clk_get_name(timing->parent));
+
+	if (emc_get_parent(&tegra->hw) == timing->parent_index &&
+	    clk_get_rate(timing->parent) != timing->parent_rate) {
+		BUG();
+		return -EINVAL;
+	}
+
+	tegra->changing_timing = true;
+
+	err = clk_set_rate(timing->parent, timing->parent_rate);
+	if (err) {
+		pr_err("cannot change parent %s rate to %ld: %d\n",
+		       __clk_get_name(timing->parent), timing->parent_rate,
+		       err);
+
+		return err;
+	}
+
+	err = clk_prepare_enable(timing->parent);
+	if (err) {
+		pr_err("cannot enable parent clock: %d\n", err);
+		return err;
+	}
+
+	div = timing->parent_rate / (timing->rate / 2) - 2;
+
+	err = tegra_emc_prepare_timing_change(emc, timing->rate);
+	if (err)
+		return err;
+
+	spin_lock_irqsave(tegra->lock, flags);
+
+	car_value = readl(tegra->clk_regs + CLK_SOURCE_EMC);
+
+	car_value &= ~CLK_SOURCE_EMC_EMC_2X_CLK_SRC(~0);
+	car_value |= CLK_SOURCE_EMC_EMC_2X_CLK_SRC(timing->parent_index);
+
+	car_value &= ~CLK_SOURCE_EMC_EMC_2X_CLK_DIVISOR(~0);
+	car_value |= CLK_SOURCE_EMC_EMC_2X_CLK_DIVISOR(div);
+
+	writel(car_value, tegra->clk_regs + CLK_SOURCE_EMC);
+
+	spin_unlock_irqrestore(tegra->lock, flags);
+
+	tegra_emc_complete_timing_change(emc, timing->rate);
+
+	clk_hw_reparent(&tegra->hw, __clk_get_hw(timing->parent));
+	clk_disable_unprepare(tegra->prev_parent);
+
+	tegra->prev_parent = timing->parent;
+	tegra->changing_timing = false;
+
+	return 0;
+}
+
+/*
+ * Get backup timing to use as an intermediate step when a change between
+ * two timings with the same clock source has been requested. First try to
+ * find a timing with a higher clock rate to avoid a rate below any set rate
+ * floors. If that is not possible, find a lower rate.
+ */
+static struct emc_timing *get_backup_timing(struct tegra_clk_emc *tegra,
+					    int timing_index)
+{
+	int i;
+	u32 ram_code = tegra_read_ram_code();
+	struct emc_timing *timing;
+
+	for (i = timing_index+1; i < tegra->num_timings; i++) {
+		timing = tegra->timings + i;
+		if (timing->ram_code != ram_code)
+			continue;
+
+		if (emc_parent_clk_sources[timing->parent_index] !=
+		    emc_parent_clk_sources[
+		      tegra->timings[timing_index].parent_index])
+			return timing;
+	}
+
+	for (i = timing_index-1; i >= 0; --i) {
+		timing = tegra->timings + i;
+		if (timing->ram_code != ram_code)
+			continue;
+
+		if (emc_parent_clk_sources[timing->parent_index] !=
+		    emc_parent_clk_sources[
+		      tegra->timings[timing_index].parent_index])
+			return timing;
+	}
+
+	return NULL;
+}
+
+static int emc_set_rate(struct clk_hw *hw, unsigned long rate,
+			unsigned long parent_rate)
+{
+	struct tegra_clk_emc *tegra;
+	struct emc_timing *timing = NULL;
+	int i, err;
+	u32 ram_code = tegra_read_ram_code();
+
+	tegra = container_of(hw, struct tegra_clk_emc, hw);
+
+	if (__clk_get_rate(hw->clk) == rate)
+		return 0;
+
+	/*
+	 * When emc_set_timing changes the parent rate, CCF will propagate
+	 * that downward to us, so ignore any set_rate calls while a rate
+	 * change is already going on.
+	 */
+	if (tegra->changing_timing)
+		return 0;
+
+	for (i = 0; i < tegra->num_timings; i++) {
+		if (tegra->timings[i].rate == rate &&
+		    tegra->timings[i].ram_code == ram_code) {
+			timing = tegra->timings + i;
+			break;
+		}
+	}
+
+	if (!timing) {
+		pr_err("cannot switch to rate %ld without emc table\n", rate);
+		return -EINVAL;
+	}
+
+	if (emc_parent_clk_sources[emc_get_parent(hw)] ==
+	    emc_parent_clk_sources[timing->parent_index] &&
+	    clk_get_rate(timing->parent) != timing->parent_rate) {
+		/*
+		 * Parent clock source not changed but parent rate has changed,
+		 * need to temporarily switch to another parent
+		 */
+
+		struct emc_timing *backup_timing;
+
+		backup_timing = get_backup_timing(tegra, i);
+		if (!backup_timing) {
+			pr_err("cannot find backup timing\n");
+			return -EINVAL;
+		}
+
+		pr_debug("using %ld as backup rate when going to %ld\n",
+			 backup_timing->rate, rate);
+
+		err = emc_set_timing(tegra, backup_timing);
+		if (err) {
+			pr_err("cannot set backup timing: %d\n", err);
+			return err;
+		}
+	}
+
+	return emc_set_timing(tegra, timing);
+}
+
+/* Initialization and deinitialization */
+
+static int load_one_timing_from_dt(struct tegra_clk_emc *tegra,
+				   struct emc_timing *timing,
+				   struct device_node *node)
+{
+	int err, i;
+	u32 tmp;
+
+	err = of_property_read_u32(node, "clock-frequency", &tmp);
+	if (err) {
+		pr_err("timing %s: failed to read rate\n", node->full_name);
+		return err;
+	}
+
+	timing->rate = tmp;
+
+	err = of_property_read_u32(node, "nvidia,parent-clock-frequency", &tmp);
+	if (err) {
+		pr_err("timing %s: failed to read parent rate\n",
+		       node->full_name);
+		return err;
+	}
+
+	timing->parent_rate = tmp;
+
+	timing->parent = of_clk_get_by_name(node, "emc-parent");
+	if (IS_ERR(timing->parent)) {
+		pr_err("timing %s: failed to get parent clock\n",
+		       node->full_name);
+		return PTR_ERR(timing->parent);
+	}
+
+	timing->parent_index = 0xff;
+	for (i = 0; i < ARRAY_SIZE(emc_parent_clk_names); i++) {
+		if (!strcmp(emc_parent_clk_names[i],
+			    __clk_get_name(timing->parent))) {
+			timing->parent_index = i;
+			break;
+		}
+	}
+	if (timing->parent_index == 0xff) {
+		pr_err("timing %s: %s is not a valid parent\n",
+		       node->full_name, __clk_get_name(timing->parent));
+		clk_put(timing->parent);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int cmp_timings(const void *_a, const void *_b)
+{
+	const struct emc_timing *a = _a;
+	const struct emc_timing *b = _b;
+
+	if (a->rate < b->rate)
+		return -1;
+	else if (a->rate == b->rate)
+		return 0;
+	else
+		return 1;
+}
+
+static int load_timings_from_dt(struct tegra_clk_emc *tegra,
+				struct device_node *node,
+				u32 ram_code)
+{
+	struct device_node *child;
+	int child_count = of_get_child_count(node);
+	int i = 0, err;
+
+	tegra->timings = kcalloc(child_count, sizeof(struct emc_timing),
+				 GFP_KERNEL);
+	if (!tegra->timings)
+		return -ENOMEM;
+
+	tegra->num_timings = child_count;
+
+	for_each_child_of_node(node, child) {
+		struct emc_timing *timing = tegra->timings + (i++);
+
+		err = load_one_timing_from_dt(tegra, timing, child);
+		if (err)
+			return err;
+
+		timing->ram_code = ram_code;
+	}
+
+	sort(tegra->timings, tegra->num_timings, sizeof(struct emc_timing),
+	     cmp_timings, NULL);
+
+	return 0;
+}
+
+static const struct clk_ops tegra_clk_emc_ops = {
+	.recalc_rate = emc_recalc_rate,
+	.determine_rate = emc_determine_rate,
+	.set_rate = emc_set_rate,
+	.get_parent = emc_get_parent,
+};
+
+struct clk *tegra_clk_register_emc(void __iomem *base, struct device_node *np,
+				   spinlock_t *lock)
+{
+	struct tegra_clk_emc *tegra;
+	struct clk_init_data init;
+	struct device_node *node;
+	u32 node_ram_code;
+	struct clk *clk;
+	int err;
+
+	tegra = kcalloc(1, sizeof(*tegra), GFP_KERNEL);
+	if (!tegra)
+		return ERR_PTR(-ENOMEM);
+
+	tegra->clk_regs = base;
+	tegra->lock = lock;
+
+	tegra->num_timings = 0;
+
+	for_each_child_of_node(np, node) {
+		err = of_property_read_u32(node, "nvidia,ram-code",
+					   &node_ram_code);
+		if (err) {
+			of_node_put(node);
+			continue;
+		}
+
+		/*
+		 * Store timings for all ram codes as we cannot read the
+		 * fuses until the apbmisc driver is loaded.
+		 */
+		err = load_timings_from_dt(tegra, node, node_ram_code);
+		if (err)
+			return ERR_PTR(err);
+		of_node_put(node);
+		break;
+	}
+
+	if (tegra->num_timings == 0)
+		pr_warn("%s: no memory timings registered\n", __func__);
+
+	tegra->emc_node = of_parse_phandle(np,
+			"nvidia,external-memory-controller", 0);
+	if (!tegra->emc_node)
+		pr_warn("%s: couldn't find node for EMC driver\n", __func__);
+
+	init.name = "emc";
+	init.ops = &tegra_clk_emc_ops;
+	init.flags = 0;
+	init.parent_names = emc_parent_clk_names;
+	init.num_parents = ARRAY_SIZE(emc_parent_clk_names);
+
+	tegra->hw.init = &init;
+
+	clk = clk_register(NULL, &tegra->hw);
+	if (IS_ERR(clk))
+		return clk;
+
+	tegra->prev_parent = clk_get_parent_by_index(
+		tegra->hw.clk, emc_get_parent(&tegra->hw));
+	tegra->changing_timing = false;
+
+	/* Allow debugging tools to see the EMC clock */
+	clk_register_clkdev(clk, "emc", "tegra-clk-debug");
+
+	clk_prepare_enable(clk);
+
+	return clk;
+};
diff --git a/drivers/clk/tegra/clk-tegra124.c b/drivers/clk/tegra/clk-tegra124.c
index 11f857c..e8cca3e 100644
--- a/drivers/clk/tegra/clk-tegra124.c
+++ b/drivers/clk/tegra/clk-tegra124.c
@@ -152,11 +152,6 @@
 	[12] = 260000000,
 };
 
-static const char *mux_pllmcp_clkm[] = {
-	"pll_m", "pll_c", "pll_p", "clk_m", "pll_m_ud", "pll_c2", "pll_c3",
-};
-#define mux_pllmcp_clkm_idx NULL
-
 static struct div_nmp pllxc_nmp = {
 	.divm_shift = 0,
 	.divm_width = 8,
@@ -791,7 +786,6 @@
 	[tegra_clk_i2c2] = { .dt_id = TEGRA124_CLK_I2C2, .present = true },
 	[tegra_clk_uartc] = { .dt_id = TEGRA124_CLK_UARTC, .present = true },
 	[tegra_clk_mipi_cal] = { .dt_id = TEGRA124_CLK_MIPI_CAL, .present = true },
-	[tegra_clk_emc] = { .dt_id = TEGRA124_CLK_EMC, .present = true },
 	[tegra_clk_usb2] = { .dt_id = TEGRA124_CLK_USB2, .present = true },
 	[tegra_clk_usb3] = { .dt_id = TEGRA124_CLK_USB3, .present = true },
 	[tegra_clk_vde_8] = { .dt_id = TEGRA124_CLK_VDE, .present = true },
@@ -1127,13 +1121,7 @@
 					     periph_clk_enb_refcnt);
 	clks[TEGRA124_CLK_DSIB] = clk;
 
-	/* emc mux */
-	clk = clk_register_mux(NULL, "emc_mux", mux_pllmcp_clkm,
-			       ARRAY_SIZE(mux_pllmcp_clkm), 0,
-			       clk_base + CLK_SOURCE_EMC,
-			       29, 3, 0, &emc_lock);
-
-	clk = tegra_clk_register_mc("mc", "emc_mux", clk_base + CLK_SOURCE_EMC,
+	clk = tegra_clk_register_mc("mc", "emc", clk_base + CLK_SOURCE_EMC,
 				    &emc_lock);
 	clks[TEGRA124_CLK_MC] = clk;
 
@@ -1389,7 +1377,6 @@
 	{TEGRA124_CLK_XUSB_HOST_SRC, TEGRA124_CLK_PLL_RE_OUT, 112000000, 0},
 	{TEGRA124_CLK_SATA, TEGRA124_CLK_PLL_P, 104000000, 0},
 	{TEGRA124_CLK_SATA_OOB, TEGRA124_CLK_PLL_P, 204000000, 0},
-	{TEGRA124_CLK_EMC, TEGRA124_CLK_CLK_MAX, 0, 1},
 	{TEGRA124_CLK_MSELECT, TEGRA124_CLK_CLK_MAX, 0, 1},
 	{TEGRA124_CLK_CSITE, TEGRA124_CLK_CLK_MAX, 0, 1},
 	{TEGRA124_CLK_TSENSOR, TEGRA124_CLK_CLK_M, 400000, 0},
@@ -1513,6 +1500,10 @@
 	tegra_super_clk_gen4_init(clk_base, pmc_base, tegra124_clks,
 				  &pll_x_params);
 	tegra_add_of_provider(np);
+
+	clks[TEGRA124_CLK_EMC] = tegra_clk_register_emc(clk_base, np,
+							&emc_lock);
+
 	tegra_register_devclks(devclks, ARRAY_SIZE(devclks));
 
 	tegra_cpu_car_ops = &tegra124_cpu_car_ops;
diff --git a/drivers/clk/tegra/clk-tegra30.c b/drivers/clk/tegra/clk-tegra30.c
index 4b26509..0af3e83 100644
--- a/drivers/clk/tegra/clk-tegra30.c
+++ b/drivers/clk/tegra/clk-tegra30.c
@@ -679,7 +679,7 @@
 	{ .dev_id = "tegra30-dam.1", .dt_id = TEGRA30_CLK_DAM1 },
 	{ .dev_id = "tegra30-dam.2", .dt_id = TEGRA30_CLK_DAM2 },
 	{ .con_id = "hda", .dev_id = "tegra30-hda", .dt_id = TEGRA30_CLK_HDA },
-	{ .con_id = "hda2codec", .dev_id = "tegra30-hda", .dt_id = TEGRA30_CLK_HDA2CODEC_2X },
+	{ .con_id = "hda2codec_2x", .dev_id = "tegra30-hda", .dt_id = TEGRA30_CLK_HDA2CODEC_2X },
 	{ .dev_id = "spi_tegra.0", .dt_id = TEGRA30_CLK_SBC1 },
 	{ .dev_id = "spi_tegra.1", .dt_id = TEGRA30_CLK_SBC2 },
 	{ .dev_id = "spi_tegra.2", .dt_id = TEGRA30_CLK_SBC3 },
diff --git a/drivers/clk/tegra/clk.h b/drivers/clk/tegra/clk.h
index d6ac006..75ddc8ff 100644
--- a/drivers/clk/tegra/clk.h
+++ b/drivers/clk/tegra/clk.h
@@ -623,6 +623,18 @@
 			void __iomem *pmc_base, struct tegra_clk *tegra_clks,
 			struct tegra_clk_pll_params *pll_params);
 
+#ifdef CONFIG_TEGRA_CLK_EMC
+struct clk *tegra_clk_register_emc(void __iomem *base, struct device_node *np,
+				   spinlock_t *lock);
+#else
+static inline struct clk *tegra_clk_register_emc(void __iomem *base,
+						 struct device_node *np,
+						 spinlock_t *lock)
+{
+	return NULL;
+}
+#endif
+
 void tegra114_clock_tune_cpu_trimmers_high(void);
 void tegra114_clock_tune_cpu_trimmers_low(void);
 void tegra114_clock_tune_cpu_trimmers_init(void);
diff --git a/drivers/clk/ti/clk-dra7-atl.c b/drivers/clk/ti/clk-dra7-atl.c
index d86bc46..19e543a 100644
--- a/drivers/clk/ti/clk-dra7-atl.c
+++ b/drivers/clk/ti/clk-dra7-atl.c
@@ -155,7 +155,7 @@
 	return 0;
 }
 
-const struct clk_ops atl_clk_ops = {
+static const struct clk_ops atl_clk_ops = {
 	.enable		= atl_clk_enable,
 	.disable	= atl_clk_disable,
 	.is_enabled	= atl_clk_is_enabled,
@@ -167,7 +167,7 @@
 static void __init of_dra7_atl_clock_setup(struct device_node *node)
 {
 	struct dra7_atl_desc *clk_hw = NULL;
-	struct clk_init_data init = { 0 };
+	struct clk_init_data init = { NULL };
 	const char **parent_names = NULL;
 	struct clk *clk;
 
@@ -252,6 +252,11 @@
 		}
 
 		clk = of_clk_get_from_provider(&clkspec);
+		if (IS_ERR(clk)) {
+			pr_err("%s: failed to get atl clock %d from provider\n",
+			       __func__, i);
+			return PTR_ERR(clk);
+		}
 
 		cdesc = to_atl_desc(__clk_get_hw(clk));
 		cdesc->cinfo = cinfo;
diff --git a/drivers/clk/ti/clk.c b/drivers/clk/ti/clk.c
index 0ebe5c5..64bb5e8 100644
--- a/drivers/clk/ti/clk.c
+++ b/drivers/clk/ti/clk.c
@@ -122,14 +122,14 @@
 
 	if (i == CLK_MAX_MEMMAPS) {
 		pr_err("clk-provider not found for %s!\n", node->name);
-		return ERR_PTR(-ENOENT);
+		return IOMEM_ERR_PTR(-ENOENT);
 	}
 
 	reg->index = i;
 
 	if (of_property_read_u32_index(node, "reg", index, &val)) {
 		pr_err("%s must have reg[%d]!\n", node->name, index);
-		return ERR_PTR(-EINVAL);
+		return IOMEM_ERR_PTR(-EINVAL);
 	}
 
 	reg->offset = val;
diff --git a/drivers/clk/ti/clockdomain.c b/drivers/clk/ti/clockdomain.c
index 35fe108..b82ef07 100644
--- a/drivers/clk/ti/clockdomain.c
+++ b/drivers/clk/ti/clockdomain.c
@@ -32,7 +32,7 @@
 	int i;
 	int num_clks;
 
-	num_clks = of_count_phandle_with_args(node, "clocks", "#clock-cells");
+	num_clks = of_clk_get_parent_count(node);
 
 	for (i = 0; i < num_clks; i++) {
 		clk = of_clk_get(node, i);
diff --git a/drivers/clk/ti/dpll.c b/drivers/clk/ti/dpll.c
index 11478a5..2aacf7a 100644
--- a/drivers/clk/ti/dpll.c
+++ b/drivers/clk/ti/dpll.c
@@ -177,7 +177,7 @@
 }
 
 #if defined(CONFIG_ARCH_OMAP3) && defined(CONFIG_ATAGS)
-void __iomem *_get_reg(u8 module, u16 offset)
+static void __iomem *_get_reg(u8 module, u16 offset)
 {
 	u32 reg;
 	struct clk_omap_reg *reg_setup;
diff --git a/drivers/clk/ti/fapll.c b/drivers/clk/ti/fapll.c
index ffcd8e0..730aa62 100644
--- a/drivers/clk/ti/fapll.c
+++ b/drivers/clk/ti/fapll.c
@@ -621,13 +621,13 @@
 
 		/* Check for hardwired audio_pll_clk1 */
 		if (is_audio_pll_clk1(freq)) {
-			freq = 0;
-			div = 0;
+			freq = NULL;
+			div = NULL;
 		} else {
 			/* Does the synthesizer have a FREQ register? */
 			v = readl_relaxed(freq);
 			if (!v)
-				freq = 0;
+				freq = NULL;
 		}
 		synth_clk = ti_fapll_synth_setup(fd, freq, div, output_instance,
 						 output_name, node->name,
diff --git a/drivers/clk/ux500/u8500_clk.c b/drivers/clk/ux500/u8500_clk.c
index 80069c3..4626b97 100644
--- a/drivers/clk/ux500/u8500_clk.c
+++ b/drivers/clk/ux500/u8500_clk.c
@@ -116,11 +116,12 @@
 	clk_register_clkdev(clk, NULL, "hdmi");
 	clk_register_clkdev(clk, "hdmi", "mcde");
 
-	clk = clk_reg_prcmu_gate("apeatclk", NULL, PRCMU_APEATCLK, CLK_IS_ROOT);
+	clk = clk_reg_prcmu_scalable("apeatclk", NULL, PRCMU_APEATCLK, 0,
+				     CLK_IS_ROOT|CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "apeat");
 
-	clk = clk_reg_prcmu_gate("apetraceclk", NULL, PRCMU_APETRACECLK,
-				CLK_IS_ROOT);
+	clk = clk_reg_prcmu_scalable("apetraceclk", NULL, PRCMU_APETRACECLK, 0,
+				CLK_IS_ROOT|CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "apetrace");
 
 	clk = clk_reg_prcmu_gate("mcdeclk", NULL, PRCMU_MCDECLK, CLK_IS_ROOT);
diff --git a/drivers/clk/ux500/u8500_of_clk.c b/drivers/clk/ux500/u8500_of_clk.c
index 7b55ef8..e319ef9 100644
--- a/drivers/clk/ux500/u8500_of_clk.c
+++ b/drivers/clk/ux500/u8500_of_clk.c
@@ -166,8 +166,8 @@
 	clk = clk_reg_prcmu_gate("apeatclk", NULL, PRCMU_APEATCLK, CLK_IS_ROOT);
 	prcmu_clk[PRCMU_APEATCLK] = clk;
 
-	clk = clk_reg_prcmu_gate("apetraceclk", NULL, PRCMU_APETRACECLK,
-				CLK_IS_ROOT);
+	clk = clk_reg_prcmu_scalable("apetraceclk", NULL, PRCMU_APETRACECLK, 0,
+				CLK_IS_ROOT|CLK_SET_RATE_GATE);
 	prcmu_clk[PRCMU_APETRACECLK] = clk;
 
 	clk = clk_reg_prcmu_gate("mcdeclk", NULL, PRCMU_MCDECLK, CLK_IS_ROOT);
diff --git a/drivers/clk/versatile/clk-sp810.c b/drivers/clk/versatile/clk-sp810.c
index c6e86a9..a96dd8e 100644
--- a/drivers/clk/versatile/clk-sp810.c
+++ b/drivers/clk/versatile/clk-sp810.c
@@ -135,7 +135,7 @@
 	return sp810->timerclken[clkspec->args[0]].clk;
 }
 
-void __init clk_sp810_of_setup(struct device_node *node)
+static void __init clk_sp810_of_setup(struct device_node *node)
 {
 	struct clk_sp810 *sp810 = kzalloc(sizeof(*sp810), GFP_KERNEL);
 	const char *parent_names[2];
@@ -156,7 +156,7 @@
 			"timclk");
 	parent_names[1] = of_clk_get_parent_name(node, sp810->timclk_index);
 
-	if (parent_names[0] <= 0 || parent_names[1] <= 0) {
+	if (!parent_names[0] || !parent_names[1]) {
 		pr_warn("Failed to obtain parent clocks for SP810!\n");
 		return;
 	}
diff --git a/drivers/clk/zynq/clkc.c b/drivers/clk/zynq/clkc.c
index 40cb113..de61438 100644
--- a/drivers/clk/zynq/clkc.c
+++ b/drivers/clk/zynq/clkc.c
@@ -85,22 +85,29 @@
 static DEFINE_SPINLOCK(dbgclk_lock);
 static DEFINE_SPINLOCK(aperclk_lock);
 
-static const char *armpll_parents[] __initdata = {"armpll_int", "ps_clk"};
-static const char *ddrpll_parents[] __initdata = {"ddrpll_int", "ps_clk"};
-static const char *iopll_parents[] __initdata = {"iopll_int", "ps_clk"};
+static const char *const armpll_parents[] __initconst = {"armpll_int",
+	"ps_clk"};
+static const char *const ddrpll_parents[] __initconst = {"ddrpll_int",
+	"ps_clk"};
+static const char *const iopll_parents[] __initconst = {"iopll_int",
+	"ps_clk"};
 static const char *gem0_mux_parents[] __initdata = {"gem0_div1", "dummy_name"};
 static const char *gem1_mux_parents[] __initdata = {"gem1_div1", "dummy_name"};
-static const char *can0_mio_mux2_parents[] __initdata = {"can0_gate",
+static const char *const can0_mio_mux2_parents[] __initconst = {"can0_gate",
 	"can0_mio_mux"};
-static const char *can1_mio_mux2_parents[] __initdata = {"can1_gate",
+static const char *const can1_mio_mux2_parents[] __initconst = {"can1_gate",
 	"can1_mio_mux"};
 static const char *dbg_emio_mux_parents[] __initdata = {"dbg_div",
 	"dummy_name"};
 
-static const char *dbgtrc_emio_input_names[] __initdata = {"trace_emio_clk"};
-static const char *gem0_emio_input_names[] __initdata = {"gem0_emio_clk"};
-static const char *gem1_emio_input_names[] __initdata = {"gem1_emio_clk"};
-static const char *swdt_ext_clk_input_names[] __initdata = {"swdt_ext_clk"};
+static const char *const dbgtrc_emio_input_names[] __initconst = {
+	"trace_emio_clk"};
+static const char *const gem0_emio_input_names[] __initconst = {
+	"gem0_emio_clk"};
+static const char *const gem1_emio_input_names[] __initconst = {
+	"gem1_emio_clk"};
+static const char *const swdt_ext_clk_input_names[] __initconst = {
+	"swdt_ext_clk"};
 
 static void __init zynq_clk_register_fclk(enum zynq_clk fclk,
 		const char *clk_name, void __iomem *fclk_ctrl_reg,
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index 935b059..9064ff7 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -462,15 +462,12 @@
 	exynos4_mct_write(TICK_BASE_CNT, mevt->base + MCT_L_TCNTB_OFFSET);
 
 	if (mct_int_type == MCT_INT_SPI) {
-		evt->irq = mct_irqs[MCT_L0_IRQ + cpu];
-		if (request_irq(evt->irq, exynos4_mct_tick_isr,
-				IRQF_TIMER | IRQF_NOBALANCING,
-				evt->name, mevt)) {
-			pr_err("exynos-mct: cannot register IRQ %d\n",
-				evt->irq);
+
+		if (evt->irq == -1)
 			return -EIO;
-		}
-		irq_force_affinity(mct_irqs[MCT_L0_IRQ + cpu], cpumask_of(cpu));
+
+		irq_force_affinity(evt->irq, cpumask_of(cpu));
+		enable_irq(evt->irq);
 	} else {
 		enable_percpu_irq(mct_irqs[MCT_L0_IRQ], 0);
 	}
@@ -483,10 +480,12 @@
 static void exynos4_local_timer_stop(struct clock_event_device *evt)
 {
 	evt->set_mode(CLOCK_EVT_MODE_UNUSED, evt);
-	if (mct_int_type == MCT_INT_SPI)
-		free_irq(evt->irq, this_cpu_ptr(&percpu_mct_tick));
-	else
+	if (mct_int_type == MCT_INT_SPI) {
+		if (evt->irq != -1)
+			disable_irq_nosync(evt->irq);
+	} else {
 		disable_percpu_irq(mct_irqs[MCT_L0_IRQ]);
+	}
 }
 
 static int exynos4_mct_cpu_notify(struct notifier_block *self,
@@ -518,7 +517,7 @@
 
 static void __init exynos4_timer_resources(struct device_node *np, void __iomem *base)
 {
-	int err;
+	int err, cpu;
 	struct mct_clock_event_device *mevt = this_cpu_ptr(&percpu_mct_tick);
 	struct clk *mct_clk, *tick_clk;
 
@@ -545,7 +544,25 @@
 		WARN(err, "MCT: can't request IRQ %d (%d)\n",
 		     mct_irqs[MCT_L0_IRQ], err);
 	} else {
-		irq_set_affinity(mct_irqs[MCT_L0_IRQ], cpumask_of(0));
+		for_each_possible_cpu(cpu) {
+			int mct_irq = mct_irqs[MCT_L0_IRQ + cpu];
+			struct mct_clock_event_device *pcpu_mevt =
+				per_cpu_ptr(&percpu_mct_tick, cpu);
+
+			pcpu_mevt->evt.irq = -1;
+
+			irq_set_status_flags(mct_irq, IRQ_NOAUTOEN);
+			if (request_irq(mct_irq,
+					exynos4_mct_tick_isr,
+					IRQF_TIMER | IRQF_NOBALANCING,
+					pcpu_mevt->name, pcpu_mevt)) {
+				pr_err("exynos-mct: cannot register IRQ (cpu%d)\n",
+									cpu);
+
+				continue;
+			}
+			pcpu_mevt->evt.irq = mct_irq;
+		}
 	}
 
 	err = register_cpu_notifier(&exynos4_mct_cpu_nb);
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 611cb09..cc8a71c 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -36,17 +36,6 @@
 
 	  If in doubt, say N.
 
-config ARM_EXYNOS4210_CPUFREQ
-	bool "SAMSUNG EXYNOS4210"
-	depends on CPU_EXYNOS4210
-	depends on ARM_EXYNOS_CPUFREQ
-	default y
-	help
-	  This adds the CPUFreq driver for Samsung EXYNOS4210
-	  SoC (S5PV310 or S5PC210).
-
-	  If in doubt, say N.
-
 config ARM_EXYNOS4X12_CPUFREQ
 	bool "SAMSUNG EXYNOS4x12"
 	depends on SOC_EXYNOS4212 || SOC_EXYNOS4412
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index cdce92a..2169bf7 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -54,7 +54,6 @@
 obj-$(CONFIG_UX500_SOC_DB8500)		+= dbx500-cpufreq.o
 obj-$(CONFIG_ARM_EXYNOS_CPUFREQ)	+= arm-exynos-cpufreq.o
 arm-exynos-cpufreq-y					:= exynos-cpufreq.o
-arm-exynos-cpufreq-$(CONFIG_ARM_EXYNOS4210_CPUFREQ)	+= exynos4210-cpufreq.o
 arm-exynos-cpufreq-$(CONFIG_ARM_EXYNOS4X12_CPUFREQ)	+= exynos4x12-cpufreq.o
 arm-exynos-cpufreq-$(CONFIG_ARM_EXYNOS5250_CPUFREQ)	+= exynos5250-cpufreq.o
 obj-$(CONFIG_ARM_EXYNOS5440_CPUFREQ)	+= exynos5440-cpufreq.o
diff --git a/drivers/cpufreq/exynos-cpufreq.c b/drivers/cpufreq/exynos-cpufreq.c
index 82d2fbb..ae5b2bd 100644
--- a/drivers/cpufreq/exynos-cpufreq.c
+++ b/drivers/cpufreq/exynos-cpufreq.c
@@ -10,6 +10,7 @@
 */
 
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/err.h>
 #include <linux/clk.h>
 #include <linux/io.h>
@@ -168,10 +169,7 @@
 
 	exynos_info->dev = &pdev->dev;
 
-	if (of_machine_is_compatible("samsung,exynos4210")) {
-		exynos_info->type = EXYNOS_SOC_4210;
-		ret = exynos4210_cpufreq_init(exynos_info);
-	} else if (of_machine_is_compatible("samsung,exynos4212")) {
+	if (of_machine_is_compatible("samsung,exynos4212")) {
 		exynos_info->type = EXYNOS_SOC_4212;
 		ret = exynos4x12_cpufreq_init(exynos_info);
 	} else if (of_machine_is_compatible("samsung,exynos4412")) {
diff --git a/drivers/cpufreq/exynos-cpufreq.h b/drivers/cpufreq/exynos-cpufreq.h
index 9f2062a..a3855e4 100644
--- a/drivers/cpufreq/exynos-cpufreq.h
+++ b/drivers/cpufreq/exynos-cpufreq.h
@@ -18,7 +18,6 @@
 };
 
 enum exynos_soc_type {
-	EXYNOS_SOC_4210,
 	EXYNOS_SOC_4212,
 	EXYNOS_SOC_4412,
 	EXYNOS_SOC_5250,
@@ -53,14 +52,6 @@
 	void __iomem	*cmu_regs;
 };
 
-#ifdef CONFIG_ARM_EXYNOS4210_CPUFREQ
-extern int exynos4210_cpufreq_init(struct exynos_dvfs_info *);
-#else
-static inline int exynos4210_cpufreq_init(struct exynos_dvfs_info *info)
-{
-	return -EOPNOTSUPP;
-}
-#endif
 #ifdef CONFIG_ARM_EXYNOS4X12_CPUFREQ
 extern int exynos4x12_cpufreq_init(struct exynos_dvfs_info *);
 #else
diff --git a/drivers/cpufreq/exynos4210-cpufreq.c b/drivers/cpufreq/exynos4210-cpufreq.c
deleted file mode 100644
index 843ec82..0000000
--- a/drivers/cpufreq/exynos4210-cpufreq.c
+++ /dev/null
@@ -1,184 +0,0 @@
-/*
- * Copyright (c) 2010-2011 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- *
- * EXYNOS4210 - CPU frequency scaling support
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/err.h>
-#include <linux/clk.h>
-#include <linux/io.h>
-#include <linux/slab.h>
-#include <linux/cpufreq.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-
-#include "exynos-cpufreq.h"
-
-static struct clk *cpu_clk;
-static struct clk *moutcore;
-static struct clk *mout_mpll;
-static struct clk *mout_apll;
-static struct exynos_dvfs_info *cpufreq;
-
-static unsigned int exynos4210_volt_table[] = {
-	1250000, 1150000, 1050000, 975000, 950000,
-};
-
-static struct cpufreq_frequency_table exynos4210_freq_table[] = {
-	{0, L0, 1200 * 1000},
-	{0, L1, 1000 * 1000},
-	{0, L2,  800 * 1000},
-	{0, L3,  500 * 1000},
-	{0, L4,  200 * 1000},
-	{0, 0, CPUFREQ_TABLE_END},
-};
-
-static struct apll_freq apll_freq_4210[] = {
-	/*
-	 * values:
-	 * freq
-	 * clock divider for CORE, COREM0, COREM1, PERIPH, ATB, PCLK_DBG, APLL, RESERVED
-	 * clock divider for COPY, HPM, RESERVED
-	 * PLL M, P, S
-	 */
-	APLL_FREQ(1200, 0, 3, 7, 3, 4, 1, 7, 0, 5, 0, 0, 150, 3, 1),
-	APLL_FREQ(1000, 0, 3, 7, 3, 4, 1, 7, 0, 4, 0, 0, 250, 6, 1),
-	APLL_FREQ(800,  0, 3, 7, 3, 3, 1, 7, 0, 3, 0, 0, 200, 6, 1),
-	APLL_FREQ(500,  0, 3, 7, 3, 3, 1, 7, 0, 3, 0, 0, 250, 6, 2),
-	APLL_FREQ(200,  0, 1, 3, 1, 3, 1, 0, 0, 3, 0, 0, 200, 6, 3),
-};
-
-static void exynos4210_set_clkdiv(unsigned int div_index)
-{
-	unsigned int tmp;
-
-	/* Change Divider - CPU0 */
-
-	tmp = apll_freq_4210[div_index].clk_div_cpu0;
-
-	__raw_writel(tmp, cpufreq->cmu_regs + EXYNOS4_CLKDIV_CPU);
-
-	do {
-		tmp = __raw_readl(cpufreq->cmu_regs + EXYNOS4_CLKDIV_STATCPU);
-	} while (tmp & 0x1111111);
-
-	/* Change Divider - CPU1 */
-
-	tmp = apll_freq_4210[div_index].clk_div_cpu1;
-
-	__raw_writel(tmp, cpufreq->cmu_regs + EXYNOS4_CLKDIV_CPU1);
-
-	do {
-		tmp = __raw_readl(cpufreq->cmu_regs + EXYNOS4_CLKDIV_STATCPU1);
-	} while (tmp & 0x11);
-}
-
-static void exynos4210_set_apll(unsigned int index)
-{
-	unsigned int tmp, freq = apll_freq_4210[index].freq;
-
-	/* MUX_CORE_SEL = MPLL, ARMCLK uses MPLL for lock time */
-	clk_set_parent(moutcore, mout_mpll);
-
-	do {
-		tmp = (__raw_readl(cpufreq->cmu_regs + EXYNOS4_CLKMUX_STATCPU)
-			>> EXYNOS4_CLKSRC_CPU_MUXCORE_SHIFT);
-		tmp &= 0x7;
-	} while (tmp != 0x2);
-
-	clk_set_rate(mout_apll, freq * 1000);
-
-	/* MUX_CORE_SEL = APLL */
-	clk_set_parent(moutcore, mout_apll);
-
-	do {
-		tmp = __raw_readl(cpufreq->cmu_regs + EXYNOS4_CLKMUX_STATCPU);
-		tmp &= EXYNOS4_CLKMUX_STATCPU_MUXCORE_MASK;
-	} while (tmp != (0x1 << EXYNOS4_CLKSRC_CPU_MUXCORE_SHIFT));
-}
-
-static void exynos4210_set_frequency(unsigned int old_index,
-				     unsigned int new_index)
-{
-	if (old_index > new_index) {
-		exynos4210_set_clkdiv(new_index);
-		exynos4210_set_apll(new_index);
-	} else if (old_index < new_index) {
-		exynos4210_set_apll(new_index);
-		exynos4210_set_clkdiv(new_index);
-	}
-}
-
-int exynos4210_cpufreq_init(struct exynos_dvfs_info *info)
-{
-	struct device_node *np;
-	unsigned long rate;
-
-	/*
-	 * HACK: This is a temporary workaround to get access to clock
-	 * controller registers directly and remove static mappings and
-	 * dependencies on platform headers. It is necessary to enable
-	 * Exynos multi-platform support and will be removed together with
-	 * this whole driver as soon as Exynos gets migrated to use
-	 * cpufreq-dt driver.
-	 */
-	np = of_find_compatible_node(NULL, NULL, "samsung,exynos4210-clock");
-	if (!np) {
-		pr_err("%s: failed to find clock controller DT node\n",
-			__func__);
-		return -ENODEV;
-	}
-
-	info->cmu_regs = of_iomap(np, 0);
-	if (!info->cmu_regs) {
-		pr_err("%s: failed to map CMU registers\n", __func__);
-		return -EFAULT;
-	}
-
-	cpu_clk = clk_get(NULL, "armclk");
-	if (IS_ERR(cpu_clk))
-		return PTR_ERR(cpu_clk);
-
-	moutcore = clk_get(NULL, "moutcore");
-	if (IS_ERR(moutcore))
-		goto err_moutcore;
-
-	mout_mpll = clk_get(NULL, "mout_mpll");
-	if (IS_ERR(mout_mpll))
-		goto err_mout_mpll;
-
-	rate = clk_get_rate(mout_mpll) / 1000;
-
-	mout_apll = clk_get(NULL, "mout_apll");
-	if (IS_ERR(mout_apll))
-		goto err_mout_apll;
-
-	info->mpll_freq_khz = rate;
-	/* 800Mhz */
-	info->pll_safe_idx = L2;
-	info->cpu_clk = cpu_clk;
-	info->volt_table = exynos4210_volt_table;
-	info->freq_table = exynos4210_freq_table;
-	info->set_freq = exynos4210_set_frequency;
-
-	cpufreq = info;
-
-	return 0;
-
-err_mout_apll:
-	clk_put(mout_mpll);
-err_mout_mpll:
-	clk_put(moutcore);
-err_moutcore:
-	clk_put(cpu_clk);
-
-	pr_debug("%s: failed initialization\n", __func__);
-	return -EINVAL;
-}
diff --git a/drivers/cpufreq/s5pv210-cpufreq.c b/drivers/cpufreq/s5pv210-cpufreq.c
index b0dac7d..9e231f5 100644
--- a/drivers/cpufreq/s5pv210-cpufreq.c
+++ b/drivers/cpufreq/s5pv210-cpufreq.c
@@ -659,4 +659,4 @@
 	},
 	.probe = s5pv210_cpufreq_probe,
 };
-module_platform_driver(s5pv210_cpufreq_platdrv);
+builtin_platform_driver(s5pv210_cpufreq_platdrv);
diff --git a/drivers/cpuidle/cpuidle-at91.c b/drivers/cpuidle/cpuidle-at91.c
index f2446c7..9c5853b 100644
--- a/drivers/cpuidle/cpuidle-at91.c
+++ b/drivers/cpuidle/cpuidle-at91.c
@@ -62,5 +62,4 @@
 	},
 	.probe = at91_cpuidle_probe,
 };
-
-module_platform_driver(at91_cpuidle_driver);
+builtin_platform_driver(at91_cpuidle_driver);
diff --git a/drivers/cpuidle/cpuidle-calxeda.c b/drivers/cpuidle/cpuidle-calxeda.c
index 9445e6c..c13feec 100644
--- a/drivers/cpuidle/cpuidle-calxeda.c
+++ b/drivers/cpuidle/cpuidle-calxeda.c
@@ -75,5 +75,4 @@
         },
         .probe = calxeda_cpuidle_probe,
 };
-
-module_platform_driver(calxeda_cpuidle_plat_driver);
+builtin_platform_driver(calxeda_cpuidle_plat_driver);
diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index 1e3ef5e..845bafc 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -67,6 +67,8 @@
 	return index;
 }
 
+/* Register for fastsleep only in oneshot mode of broadcast */
+#ifdef CONFIG_TICK_ONESHOT
 static int fastsleep_loop(struct cpuidle_device *dev,
 				struct cpuidle_driver *drv,
 				int index)
@@ -90,7 +92,7 @@
 
 	return index;
 }
-
+#endif
 /*
  * States for dedicated partition case.
  */
@@ -216,7 +218,14 @@
 			powernv_states[nr_idle_states].flags = 0;
 			powernv_states[nr_idle_states].target_residency = 100;
 			powernv_states[nr_idle_states].enter = &nap_loop;
-		} else if (flags[i] & OPAL_PM_SLEEP_ENABLED ||
+		}
+
+		/*
+		 * All cpuidle states with CPUIDLE_FLAG_TIMER_STOP set must come
+		 * within this config dependency check.
+		 */
+#ifdef CONFIG_TICK_ONESHOT
+		if (flags[i] & OPAL_PM_SLEEP_ENABLED ||
 			flags[i] & OPAL_PM_SLEEP_ENABLED_ER1) {
 			/* Add FASTSLEEP state */
 			strcpy(powernv_states[nr_idle_states].name, "FastSleep");
@@ -225,7 +234,7 @@
 			powernv_states[nr_idle_states].target_residency = 300000;
 			powernv_states[nr_idle_states].enter = &fastsleep_loop;
 		}
-
+#endif
 		powernv_states[nr_idle_states].exit_latency =
 				((unsigned int)latency_ns[i]) / 1000;
 
diff --git a/drivers/cpuidle/cpuidle-zynq.c b/drivers/cpuidle/cpuidle-zynq.c
index 543292b..6f4257f 100644
--- a/drivers/cpuidle/cpuidle-zynq.c
+++ b/drivers/cpuidle/cpuidle-zynq.c
@@ -73,5 +73,4 @@
 	},
 	.probe = zynq_cpuidle_probe,
 };
-
-module_platform_driver(zynq_cpuidle_driver);
+builtin_platform_driver(zynq_cpuidle_driver);
diff --git a/drivers/crypto/marvell/cesa.c b/drivers/crypto/marvell/cesa.c
index a432633..1c6f98d 100644
--- a/drivers/crypto/marvell/cesa.c
+++ b/drivers/crypto/marvell/cesa.c
@@ -321,9 +321,8 @@
 	const char *res_name = "sram";
 	struct resource *res;
 
-	engine->pool = of_get_named_gen_pool(cesa->dev->of_node,
-					     "marvell,crypto-srams",
-					     idx);
+	engine->pool = of_gen_pool_get(cesa->dev->of_node,
+				       "marvell,crypto-srams", idx);
 	if (engine->pool) {
 		engine->sram = gen_pool_dma_alloc(engine->pool,
 						  cesa->sram_size,
diff --git a/drivers/crypto/mv_cesa.c b/drivers/crypto/mv_cesa.c
index 5bcd575..e6b658f 100644
--- a/drivers/crypto/mv_cesa.c
+++ b/drivers/crypto/mv_cesa.c
@@ -1034,8 +1034,8 @@
 			     &sram_size);
 
 	cp->sram_size = sram_size;
-	cp->sram_pool = of_get_named_gen_pool(pdev->dev.of_node,
-					      "marvell,crypto-srams", 0);
+	cp->sram_pool = of_gen_pool_get(pdev->dev.of_node,
+					"marvell,crypto-srams", 0);
 	if (cp->sram_pool) {
 		cp->sram = gen_pool_dma_alloc(cp->sram_pool, sram_size,
 					      &cp->sram_dma);
diff --git a/drivers/crypto/qat/qat_common/adf_accel_engine.c b/drivers/crypto/qat/qat_common/adf_accel_engine.c
index 7f8b66c..fdda8e7 100644
--- a/drivers/crypto/qat/qat_common/adf_accel_engine.c
+++ b/drivers/crypto/qat/qat_common/adf_accel_engine.c
@@ -88,10 +88,7 @@
 
 	qat_uclo_del_uof_obj(loader_data->fw_loader);
 	qat_hal_deinit(loader_data->fw_loader);
-
-	if (loader_data->uof_fw)
-		release_firmware(loader_data->uof_fw);
-
+	release_firmware(loader_data->uof_fw);
 	loader_data->uof_fw = NULL;
 	loader_data->fw_loader = NULL;
 }
diff --git a/drivers/crypto/qat/qat_common/adf_transport.c b/drivers/crypto/qat/qat_common/adf_transport.c
index ccec3274..db2926b 100644
--- a/drivers/crypto/qat/qat_common/adf_transport.c
+++ b/drivers/crypto/qat/qat_common/adf_transport.c
@@ -449,7 +449,7 @@
 err:
 	for (i = 0; i < ADF_ETR_MAX_RINGS_PER_BANK; i++) {
 		ring = &bank->rings[i];
-		if (hw_data->tx_rings_mask & (1 << i) && ring->inflights)
+		if (hw_data->tx_rings_mask & (1 << i))
 			kfree(ring->inflights);
 	}
 	return -ENOMEM;
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index 220ee49..b8576fd 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -120,7 +120,7 @@
 
 static int dmatest_run_set(const char *val, const struct kernel_param *kp);
 static int dmatest_run_get(char *val, const struct kernel_param *kp);
-static struct kernel_param_ops run_ops = {
+static const struct kernel_param_ops run_ops = {
 	.set = dmatest_run_set,
 	.get = dmatest_run_get,
 };
@@ -195,7 +195,7 @@
 	return param_get_bool(val, kp);
 }
 
-static struct kernel_param_ops wait_ops = {
+static const struct kernel_param_ops wait_ops = {
 	.get = dmatest_wait_get,
 	.set = param_set_bool,
 };
diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c
index 449e785..e683761 100644
--- a/drivers/dma/mmp_tdma.c
+++ b/drivers/dma/mmp_tdma.c
@@ -657,7 +657,7 @@
 	INIT_LIST_HEAD(&tdev->device.channels);
 
 	if (pdev->dev.of_node)
-		pool = of_get_named_gen_pool(pdev->dev.of_node, "asram", 0);
+		pool = of_gen_pool_get(pdev->dev.of_node, "asram", 0);
 	else
 		pool = sram_get_gpool("asram");
 	if (!pool) {
diff --git a/drivers/edac/octeon_edac-l2c.c b/drivers/edac/octeon_edac-l2c.c
index 7e98084..afea7fc 100644
--- a/drivers/edac/octeon_edac-l2c.c
+++ b/drivers/edac/octeon_edac-l2c.c
@@ -151,7 +151,7 @@
 	l2c->ctl_name = "octeon_l2c_err";
 
 
-	if (OCTEON_IS_MODEL(OCTEON_FAM_1_PLUS)) {
+	if (OCTEON_IS_OCTEON1PLUS()) {
 		union cvmx_l2t_err l2t_err;
 		union cvmx_l2d_err l2d_err;
 
diff --git a/drivers/edac/octeon_edac-lmc.c b/drivers/edac/octeon_edac-lmc.c
index bb19e07..cda6dab 100644
--- a/drivers/edac/octeon_edac-lmc.c
+++ b/drivers/edac/octeon_edac-lmc.c
@@ -234,7 +234,7 @@
 	layers[0].size = 1;
 	layers[0].is_virt_csrow = false;
 
-	if (OCTEON_IS_MODEL(OCTEON_FAM_1_PLUS)) {
+	if (OCTEON_IS_OCTEON1PLUS()) {
 		union cvmx_lmcx_mem_cfg0 cfg0;
 
 		cfg0.u64 = cvmx_read_csr(CVMX_LMCX_MEM_CFG0(0));
diff --git a/drivers/edac/octeon_edac-pc.c b/drivers/edac/octeon_edac-pc.c
index 0f83c33..2ab6cf2 100644
--- a/drivers/edac/octeon_edac-pc.c
+++ b/drivers/edac/octeon_edac-pc.c
@@ -73,7 +73,7 @@
 			edac_device_handle_ce(p->ed, cpu, 0, "dcache");
 
 		/* Clear the error indication */
-		if (OCTEON_IS_MODEL(OCTEON_FAM_2))
+		if (OCTEON_IS_OCTEON2())
 			write_octeon_c0_dcacheerr(1);
 		else
 			write_octeon_c0_dcacheerr(0);
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index ca617f4..9fa8084 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -66,7 +66,6 @@
 early_param("efi", parse_efi_cmdline);
 
 struct kobject *efi_kobj;
-static struct kobject *efivars_kobj;
 
 /*
  * Let's not leave out systab information that snuck into
@@ -218,10 +217,9 @@
 		goto err_remove_group;
 
 	/* and the standard mountpoint for efivarfs */
-	efivars_kobj = kobject_create_and_add("efivars", efi_kobj);
-	if (!efivars_kobj) {
+	error = sysfs_create_mount_point(efi_kobj, "efivars");
+	if (error) {
 		pr_err("efivars: Subsystem registration failed.\n");
-		error = -ENOMEM;
 		goto err_remove_group;
 	}
 
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index 280bc0a..816dbe9 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -24,8 +24,6 @@
 lib-y				:= efi-stub-helper.o
 lib-$(CONFIG_EFI_ARMSTUB)	+= arm-stub.o fdt.o
 
-CFLAGS_fdt.o			+= -I$(srctree)/scripts/dtc/libfdt/
-
 #
 # arm64 puts the stub in the kernel proper, which will unnecessarily retain all
 # code indefinitely unless it is annotated as __init/__initdata/__initconst etc.
diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c
index 8333f87..40343fa 100644
--- a/drivers/gpio/gpio-bcm-kona.c
+++ b/drivers/gpio/gpio-bcm-kona.c
@@ -657,8 +657,9 @@
 	}
 	for (i = 0; i < kona_gpio->num_bank; i++) {
 		bank = &kona_gpio->banks[i];
-		irq_set_chained_handler(bank->irq, bcm_kona_gpio_irq_handler);
-		irq_set_handler_data(bank->irq, bank);
+		irq_set_chained_handler_and_data(bank->irq,
+						 bcm_kona_gpio_irq_handler,
+						 bank);
 	}
 
 	spin_lock_init(&kona_gpio->lock);
diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c
index 58faf04..55fa985 100644
--- a/drivers/gpio/gpio-dwapb.c
+++ b/drivers/gpio/gpio-dwapb.c
@@ -348,8 +348,8 @@
 	irq_gc->chip_types[1].handler = handle_edge_irq;
 
 	if (!pp->irq_shared) {
-		irq_set_chained_handler(pp->irq, dwapb_irq_handler);
-		irq_set_handler_data(pp->irq, gpio);
+		irq_set_chained_handler_and_data(pp->irq, dwapb_irq_handler,
+						 gpio);
 	} else {
 		/*
 		 * Request a shared IRQ since where MFD would have devices
diff --git a/drivers/gpio/gpio-msic.c b/drivers/gpio/gpio-msic.c
index 01acf0a..7bcfb87 100644
--- a/drivers/gpio/gpio-msic.c
+++ b/drivers/gpio/gpio-msic.c
@@ -309,8 +309,7 @@
 					 &msic_irqchip,
 					 handle_simple_irq);
 	}
-	irq_set_chained_handler(mg->irq, msic_gpio_irq_handler);
-	irq_set_handler_data(mg->irq, mg);
+	irq_set_chained_handler_and_data(mg->irq, msic_gpio_irq_handler, mg);
 
 	return 0;
 err:
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index be42ab3..bf4bd1d 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -2052,14 +2052,14 @@
 	if (is_of_node(fwnode)) {
 		enum of_gpio_flags flags;
 
-		desc = of_get_named_gpiod_flags(of_node(fwnode), propname, 0,
+		desc = of_get_named_gpiod_flags(to_of_node(fwnode), propname, 0,
 						&flags);
 		if (!IS_ERR(desc))
 			active_low = flags & OF_GPIO_ACTIVE_LOW;
 	} else if (is_acpi_node(fwnode)) {
 		struct acpi_gpio_info info;
 
-		desc = acpi_get_gpiod_by_index(acpi_node(fwnode), propname, 0,
+		desc = acpi_get_gpiod_by_index(to_acpi_node(fwnode), propname, 0,
 					       &info);
 		if (!IS_ERR(desc))
 			active_low = info.active_low;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 22866d1..0165783 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -425,6 +425,8 @@
 				   unsigned irq_type);
 int amdgpu_fence_emit(struct amdgpu_ring *ring, void *owner,
 		      struct amdgpu_fence **fence);
+int amdgpu_fence_recreate(struct amdgpu_ring *ring, void *owner,
+			  uint64_t seq, struct amdgpu_fence **fence);
 void amdgpu_fence_process(struct amdgpu_ring *ring);
 int amdgpu_fence_wait_next(struct amdgpu_ring *ring);
 int amdgpu_fence_wait_empty(struct amdgpu_ring *ring);
@@ -435,9 +437,6 @@
 int amdgpu_fence_wait_any(struct amdgpu_device *adev,
 			  struct amdgpu_fence **fences,
 			  bool intr);
-long amdgpu_fence_wait_seq_timeout(struct amdgpu_device *adev,
-				   u64 *target_seq, bool intr,
-				   long timeout);
 struct amdgpu_fence *amdgpu_fence_ref(struct amdgpu_fence *fence);
 void amdgpu_fence_unref(struct amdgpu_fence **fence);
 
@@ -1622,6 +1621,7 @@
 	unsigned		fb_version;
 	atomic_t		handles[AMDGPU_MAX_VCE_HANDLES];
 	struct drm_file		*filp[AMDGPU_MAX_VCE_HANDLES];
+	uint32_t		img_size[AMDGPU_MAX_VCE_HANDLES];
 	struct delayed_work	idle_work;
 	const struct firmware	*fw;	/* VCE firmware */
 	struct amdgpu_ring	ring[AMDGPU_MAX_VCE_RINGS];
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index 36d34e0..f82a2dd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -30,6 +30,7 @@
 
 #include <drm/drmP.h>
 #include "amdgpu.h"
+#include "amdgpu_trace.h"
 
 static int amdgpu_bo_list_create(struct amdgpu_fpriv *fpriv,
 				 struct amdgpu_bo_list **result,
@@ -124,6 +125,8 @@
 			gws_obj = entry->robj;
 		if (entry->prefered_domains == AMDGPU_GEM_DOMAIN_OA)
 			oa_obj = entry->robj;
+
+		trace_amdgpu_bo_list_set(list, entry->robj);
 	}
 
 	for (i = 0; i < list->num_entries; ++i)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index f09b2cb..d63135b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -181,8 +181,6 @@
 		}
 		p->chunks[i].chunk_id = user_chunk.chunk_id;
 		p->chunks[i].length_dw = user_chunk.length_dw;
-		if (p->chunks[i].chunk_id == AMDGPU_CHUNK_ID_IB)
-			p->num_ibs++;
 
 		size = p->chunks[i].length_dw;
 		cdata = (void __user *)(unsigned long)user_chunk.chunk_data;
@@ -199,7 +197,12 @@
 			goto out;
 		}
 
-		if (p->chunks[i].chunk_id == AMDGPU_CHUNK_ID_FENCE) {
+		switch (p->chunks[i].chunk_id) {
+		case AMDGPU_CHUNK_ID_IB:
+			p->num_ibs++;
+			break;
+
+		case AMDGPU_CHUNK_ID_FENCE:
 			size = sizeof(struct drm_amdgpu_cs_chunk_fence);
 			if (p->chunks[i].length_dw * sizeof(uint32_t) >= size) {
 				uint32_t handle;
@@ -221,6 +224,14 @@
 				r = -EINVAL;
 				goto out;
 			}
+			break;
+
+		case AMDGPU_CHUNK_ID_DEPENDENCIES:
+			break;
+
+		default:
+			r = -EINVAL;
+			goto out;
 		}
 	}
 
@@ -445,8 +456,9 @@
 	for (i = 0; i < parser->nchunks; i++)
 		drm_free_large(parser->chunks[i].kdata);
 	kfree(parser->chunks);
-	for (i = 0; i < parser->num_ibs; i++)
-		amdgpu_ib_free(parser->adev, &parser->ibs[i]);
+	if (parser->ibs)
+		for (i = 0; i < parser->num_ibs; i++)
+			amdgpu_ib_free(parser->adev, &parser->ibs[i]);
 	kfree(parser->ibs);
 	if (parser->uf.bo)
 		drm_gem_object_unreference_unlocked(&parser->uf.bo->gem_base);
@@ -654,6 +666,55 @@
 	return 0;
 }
 
+static int amdgpu_cs_dependencies(struct amdgpu_device *adev,
+				  struct amdgpu_cs_parser *p)
+{
+	struct amdgpu_ib *ib;
+	int i, j, r;
+
+	if (!p->num_ibs)
+		return 0;
+
+	/* Add dependencies to first IB */
+	ib = &p->ibs[0];
+	for (i = 0; i < p->nchunks; ++i) {
+		struct drm_amdgpu_cs_chunk_dep *deps;
+		struct amdgpu_cs_chunk *chunk;
+		unsigned num_deps;
+
+		chunk = &p->chunks[i];
+
+		if (chunk->chunk_id != AMDGPU_CHUNK_ID_DEPENDENCIES)
+			continue;
+
+		deps = (struct drm_amdgpu_cs_chunk_dep *)chunk->kdata;
+		num_deps = chunk->length_dw * 4 /
+			sizeof(struct drm_amdgpu_cs_chunk_dep);
+
+		for (j = 0; j < num_deps; ++j) {
+			struct amdgpu_fence *fence;
+			struct amdgpu_ring *ring;
+
+			r = amdgpu_cs_get_ring(adev, deps[j].ip_type,
+					       deps[j].ip_instance,
+					       deps[j].ring, &ring);
+			if (r)
+				return r;
+
+			r = amdgpu_fence_recreate(ring, p->filp,
+						  deps[j].handle,
+						  &fence);
+			if (r)
+				return r;
+
+			amdgpu_sync_fence(&ib->sync, fence);
+			amdgpu_fence_unref(&fence);
+		}
+	}
+
+	return 0;
+}
+
 int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 {
 	struct amdgpu_device *adev = dev->dev_private;
@@ -688,11 +749,16 @@
 			else
 				DRM_ERROR("Failed to process the buffer list %d!\n", r);
 		}
-	} else {
+	}
+
+	if (!r) {
 		reserved_buffers = true;
 		r = amdgpu_cs_ib_fill(adev, &parser);
 	}
 
+	if (!r)
+		r = amdgpu_cs_dependencies(adev, &parser);
+
 	if (r) {
 		amdgpu_cs_parser_fini(&parser, r, reserved_buffers);
 		up_read(&adev->exclusive_lock);
@@ -730,9 +796,9 @@
 {
 	union drm_amdgpu_wait_cs *wait = data;
 	struct amdgpu_device *adev = dev->dev_private;
-	uint64_t seq[AMDGPU_MAX_RINGS] = {0};
-	struct amdgpu_ring *ring = NULL;
 	unsigned long timeout = amdgpu_gem_timeout(wait->in.timeout);
+	struct amdgpu_fence *fence = NULL;
+	struct amdgpu_ring *ring = NULL;
 	struct amdgpu_ctx *ctx;
 	long r;
 
@@ -745,9 +811,12 @@
 	if (r)
 		return r;
 
-	seq[ring->idx] = wait->in.handle;
+	r = amdgpu_fence_recreate(ring, filp, wait->in.handle, &fence);
+	if (r)
+		return r;
 
-	r = amdgpu_fence_wait_seq_timeout(adev, seq, true, timeout);
+	r = fence_wait_timeout(&fence->base, true, timeout);
+	amdgpu_fence_unref(&fence);
 	amdgpu_ctx_put(ctx);
 	if (r < 0)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index fec487d..ba46be3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1191,7 +1191,9 @@
 		return -EINVAL;
 	}
 
-
+	adev->ip_block_enabled = kcalloc(adev->num_ip_blocks, sizeof(bool), GFP_KERNEL);
+	if (adev->ip_block_enabled == NULL)
+		return -ENOMEM;
 
 	if (adev->ip_blocks == NULL) {
 		DRM_ERROR("No IP blocks found!\n");
@@ -1575,8 +1577,7 @@
 	amdgpu_fence_driver_fini(adev);
 	amdgpu_fbdev_fini(adev);
 	r = amdgpu_fini(adev);
-	if (adev->ip_block_enabled)
-		kfree(adev->ip_block_enabled);
+	kfree(adev->ip_block_enabled);
 	adev->ip_block_enabled = NULL;
 	adev->accel_working = false;
 	/* free i2c buses */
@@ -2000,4 +2001,10 @@
 void amdgpu_debugfs_cleanup(struct drm_minor *minor)
 {
 }
+#else
+static int amdgpu_debugfs_regs_init(struct amdgpu_device *adev)
+{
+	return 0;
+}
+static void amdgpu_debugfs_regs_cleanup(struct amdgpu_device *adev) { }
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 5c9918d..a7189a1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -136,6 +136,38 @@
 }
 
 /**
+ * amdgpu_fence_recreate - recreate a fence from an user fence
+ *
+ * @ring: ring the fence is associated with
+ * @owner: creator of the fence
+ * @seq: user fence sequence number
+ * @fence: resulting amdgpu fence object
+ *
+ * Recreates a fence command from the user fence sequence number (all asics).
+ * Returns 0 on success, -ENOMEM on failure.
+ */
+int amdgpu_fence_recreate(struct amdgpu_ring *ring, void *owner,
+			  uint64_t seq, struct amdgpu_fence **fence)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	if (seq > ring->fence_drv.sync_seq[ring->idx])
+		return -EINVAL;
+
+	*fence = kmalloc(sizeof(struct amdgpu_fence), GFP_KERNEL);
+	if ((*fence) == NULL)
+		return -ENOMEM;
+
+	(*fence)->seq = seq;
+	(*fence)->ring = ring;
+	(*fence)->owner = owner;
+	fence_init(&(*fence)->base, &amdgpu_fence_ops,
+		&adev->fence_queue.lock, adev->fence_context + ring->idx,
+		(*fence)->seq);
+	return 0;
+}
+
+/**
  * amdgpu_fence_check_signaled - callback from fence_queue
  *
  * this function is called with fence_queue lock held, which is also used
@@ -517,12 +549,14 @@
  * the wait timeout, or an error for all other cases.
  * -EDEADLK is returned when a GPU lockup has been detected.
  */
-long amdgpu_fence_wait_seq_timeout(struct amdgpu_device *adev, u64 *target_seq,
-				   bool intr, long timeout)
+static long amdgpu_fence_wait_seq_timeout(struct amdgpu_device *adev,
+					  u64 *target_seq, bool intr,
+					  long timeout)
 {
 	uint64_t last_seq[AMDGPU_MAX_RINGS];
 	bool signaled;
-	int i, r;
+	int i;
+	long r;
 
 	if (timeout == 0) {
 		return amdgpu_fence_any_seq_signaled(adev, target_seq);
@@ -1023,7 +1057,7 @@
 
 		amdgpu_fence_process(ring);
 
-		seq_printf(m, "--- ring %d ---\n", i);
+		seq_printf(m, "--- ring %d (%s) ---\n", i, ring->name);
 		seq_printf(m, "Last signaled fence 0x%016llx\n",
 			   (unsigned long long)atomic64_read(&ring->fence_drv.last_seq));
 		seq_printf(m, "Last emitted        0x%016llx\n",
@@ -1031,7 +1065,8 @@
 
 		for (j = 0; j < AMDGPU_MAX_RINGS; ++j) {
 			struct amdgpu_ring *other = adev->rings[j];
-			if (i != j && other && other->fence_drv.initialized)
+			if (i != j && other && other->fence_drv.initialized &&
+			    ring->fence_drv.sync_seq[j])
 				seq_printf(m, "Last sync to ring %d 0x%016llx\n",
 					   j, ring->fence_drv.sync_seq[j]);
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 0ec2222..975edb1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -496,7 +496,7 @@
 error_free:
 	drm_free_large(vm_bos);
 
-	if (r)
+	if (r && r != -ERESTARTSYS)
 		DRM_ERROR("Couldn't update BO_VA (%d)\n", r);
 }
 
@@ -525,8 +525,8 @@
 		return -EINVAL;
 	}
 
-	invalid_flags = ~(AMDGPU_VM_PAGE_READABLE | AMDGPU_VM_PAGE_WRITEABLE |
-			AMDGPU_VM_PAGE_EXECUTABLE);
+	invalid_flags = ~(AMDGPU_VM_DELAY_UPDATE | AMDGPU_VM_PAGE_READABLE |
+			AMDGPU_VM_PAGE_WRITEABLE | AMDGPU_VM_PAGE_EXECUTABLE);
 	if ((args->flags & invalid_flags)) {
 		dev_err(&dev->pdev->dev, "invalid flags 0x%08X vs 0x%08X\n",
 			args->flags, invalid_flags);
@@ -579,7 +579,7 @@
 		break;
 	}
 
-	if (!r)
+	if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE))
 		amdgpu_gem_va_update_vm(adev, bo_va);
 
 	drm_gem_object_unreference_unlocked(gobj);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
index b56dd64..961d726 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -30,19 +30,21 @@
 	    TP_PROTO(struct amdgpu_cs_parser *p, int i),
 	    TP_ARGS(p, i),
 	    TP_STRUCT__entry(
+			     __field(struct amdgpu_bo_list *, bo_list)
 			     __field(u32, ring)
 			     __field(u32, dw)
 			     __field(u32, fences)
 			     ),
 
 	    TP_fast_assign(
+			   __entry->bo_list = p->bo_list;
 			   __entry->ring = p->ibs[i].ring->idx;
 			   __entry->dw = p->ibs[i].length_dw;
 			   __entry->fences = amdgpu_fence_count_emitted(
 				p->ibs[i].ring);
 			   ),
-	    TP_printk("ring=%u, dw=%u, fences=%u",
-		      __entry->ring, __entry->dw,
+	    TP_printk("bo_list=%p, ring=%u, dw=%u, fences=%u",
+		      __entry->bo_list, __entry->ring, __entry->dw,
 		      __entry->fences)
 );
 
@@ -61,6 +63,54 @@
 	    TP_printk("vmid=%u, ring=%u", __entry->vmid, __entry->ring)
 );
 
+TRACE_EVENT(amdgpu_vm_bo_map,
+	    TP_PROTO(struct amdgpu_bo_va *bo_va,
+		     struct amdgpu_bo_va_mapping *mapping),
+	    TP_ARGS(bo_va, mapping),
+	    TP_STRUCT__entry(
+			     __field(struct amdgpu_bo *, bo)
+			     __field(long, start)
+			     __field(long, last)
+			     __field(u64, offset)
+			     __field(u32, flags)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->bo = bo_va->bo;
+			   __entry->start = mapping->it.start;
+			   __entry->last = mapping->it.last;
+			   __entry->offset = mapping->offset;
+			   __entry->flags = mapping->flags;
+			   ),
+	    TP_printk("bo=%p, start=%lx, last=%lx, offset=%010llx, flags=%08x",
+		      __entry->bo, __entry->start, __entry->last,
+		      __entry->offset, __entry->flags)
+);
+
+TRACE_EVENT(amdgpu_vm_bo_unmap,
+	    TP_PROTO(struct amdgpu_bo_va *bo_va,
+		     struct amdgpu_bo_va_mapping *mapping),
+	    TP_ARGS(bo_va, mapping),
+	    TP_STRUCT__entry(
+			     __field(struct amdgpu_bo *, bo)
+			     __field(long, start)
+			     __field(long, last)
+			     __field(u64, offset)
+			     __field(u32, flags)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->bo = bo_va->bo;
+			   __entry->start = mapping->it.start;
+			   __entry->last = mapping->it.last;
+			   __entry->offset = mapping->offset;
+			   __entry->flags = mapping->flags;
+			   ),
+	    TP_printk("bo=%p, start=%lx, last=%lx, offset=%010llx, flags=%08x",
+		      __entry->bo, __entry->start, __entry->last,
+		      __entry->offset, __entry->flags)
+);
+
 TRACE_EVENT(amdgpu_vm_bo_update,
 	    TP_PROTO(struct amdgpu_bo_va_mapping *mapping),
 	    TP_ARGS(mapping),
@@ -121,6 +171,21 @@
 		      __entry->pd_addr, __entry->ring, __entry->id)
 );
 
+TRACE_EVENT(amdgpu_bo_list_set,
+	    TP_PROTO(struct amdgpu_bo_list *list, struct amdgpu_bo *bo),
+	    TP_ARGS(list, bo),
+	    TP_STRUCT__entry(
+			     __field(struct amdgpu_bo_list *, list)
+			     __field(struct amdgpu_bo *, bo)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->list = list;
+			   __entry->bo = bo;
+			   ),
+	    TP_printk("list=%p, bo=%p", __entry->list, __entry->bo)
+);
+
 DECLARE_EVENT_CLASS(amdgpu_fence_request,
 
 	    TP_PROTO(struct drm_device *dev, int ring, u32 seqno),
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index d3706a4..dd3415d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -674,7 +674,7 @@
 		return 0;
 
 	if (gtt && gtt->userptr) {
-		ttm->sg = kcalloc(1, sizeof(struct sg_table), GFP_KERNEL);
+		ttm->sg = kzalloc(sizeof(struct sg_table), GFP_KERNEL);
 		if (!ttm->sg)
 			return -ENOMEM;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 1127a50..d3ca730 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -464,28 +464,42 @@
  * @p: parser context
  * @lo: address of lower dword
  * @hi: address of higher dword
+ * @size: minimum size
  *
  * Patch relocation inside command stream with real buffer address
  */
-int amdgpu_vce_cs_reloc(struct amdgpu_cs_parser *p, uint32_t ib_idx, int lo, int hi)
+static int amdgpu_vce_cs_reloc(struct amdgpu_cs_parser *p, uint32_t ib_idx,
+			       int lo, int hi, unsigned size, uint32_t index)
 {
 	struct amdgpu_bo_va_mapping *mapping;
 	struct amdgpu_ib *ib = &p->ibs[ib_idx];
 	struct amdgpu_bo *bo;
 	uint64_t addr;
 
+	if (index == 0xffffffff)
+		index = 0;
+
 	addr = ((uint64_t)amdgpu_get_ib_value(p, ib_idx, lo)) |
 	       ((uint64_t)amdgpu_get_ib_value(p, ib_idx, hi)) << 32;
+	addr += ((uint64_t)size) * ((uint64_t)index);
 
 	mapping = amdgpu_cs_find_mapping(p, addr, &bo);
 	if (mapping == NULL) {
-		DRM_ERROR("Can't find BO for addr 0x%010Lx %d %d\n",
+		DRM_ERROR("Can't find BO for addr 0x%010Lx %d %d %d %d\n",
+			  addr, lo, hi, size, index);
+		return -EINVAL;
+	}
+
+	if ((addr + (uint64_t)size) >
+	    ((uint64_t)mapping->it.last + 1) * AMDGPU_GPU_PAGE_SIZE) {
+		DRM_ERROR("BO to small for addr 0x%010Lx %d %d\n",
 			  addr, lo, hi);
 		return -EINVAL;
 	}
 
 	addr -= ((uint64_t)mapping->it.start) * AMDGPU_GPU_PAGE_SIZE;
 	addr += amdgpu_bo_gpu_offset(bo);
+	addr -= ((uint64_t)size) * ((uint64_t)index);
 
 	ib->ptr[lo] = addr & 0xFFFFFFFF;
 	ib->ptr[hi] = addr >> 32;
@@ -494,6 +508,48 @@
 }
 
 /**
+ * amdgpu_vce_validate_handle - validate stream handle
+ *
+ * @p: parser context
+ * @handle: handle to validate
+ * @allocated: allocated a new handle?
+ *
+ * Validates the handle and return the found session index or -EINVAL
+ * we we don't have another free session index.
+ */
+static int amdgpu_vce_validate_handle(struct amdgpu_cs_parser *p,
+				      uint32_t handle, bool *allocated)
+{
+	unsigned i;
+
+	*allocated = false;
+
+	/* validate the handle */
+	for (i = 0; i < AMDGPU_MAX_VCE_HANDLES; ++i) {
+		if (atomic_read(&p->adev->vce.handles[i]) == handle) {
+			if (p->adev->vce.filp[i] != p->filp) {
+				DRM_ERROR("VCE handle collision detected!\n");
+				return -EINVAL;
+			}
+			return i;
+		}
+	}
+
+	/* handle not found try to alloc a new one */
+	for (i = 0; i < AMDGPU_MAX_VCE_HANDLES; ++i) {
+		if (!atomic_cmpxchg(&p->adev->vce.handles[i], 0, handle)) {
+			p->adev->vce.filp[i] = p->filp;
+			p->adev->vce.img_size[i] = 0;
+			*allocated = true;
+			return i;
+		}
+	}
+
+	DRM_ERROR("No more free VCE handles!\n");
+	return -EINVAL;
+}
+
+/**
  * amdgpu_vce_cs_parse - parse and validate the command stream
  *
  * @p: parser context
@@ -501,10 +557,15 @@
  */
 int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx)
 {
-	uint32_t handle = 0;
-	bool destroy = false;
-	int i, r, idx = 0;
 	struct amdgpu_ib *ib = &p->ibs[ib_idx];
+	unsigned fb_idx = 0, bs_idx = 0;
+	int session_idx = -1;
+	bool destroyed = false;
+	bool created = false;
+	bool allocated = false;
+	uint32_t tmp, handle = 0;
+	uint32_t *size = &tmp;
+	int i, r = 0, idx = 0;
 
 	amdgpu_vce_note_usage(p->adev);
 
@@ -514,16 +575,44 @@
 
 		if ((len < 8) || (len & 3)) {
 			DRM_ERROR("invalid VCE command length (%d)!\n", len);
-			return -EINVAL;
+			r = -EINVAL;
+			goto out;
+		}
+
+		if (destroyed) {
+			DRM_ERROR("No other command allowed after destroy!\n");
+			r = -EINVAL;
+			goto out;
 		}
 
 		switch (cmd) {
 		case 0x00000001: // session
 			handle = amdgpu_get_ib_value(p, ib_idx, idx + 2);
+			session_idx = amdgpu_vce_validate_handle(p, handle,
+								 &allocated);
+			if (session_idx < 0)
+				return session_idx;
+			size = &p->adev->vce.img_size[session_idx];
 			break;
 
 		case 0x00000002: // task info
+			fb_idx = amdgpu_get_ib_value(p, ib_idx, idx + 6);
+			bs_idx = amdgpu_get_ib_value(p, ib_idx, idx + 7);
+			break;
+
 		case 0x01000001: // create
+			created = true;
+			if (!allocated) {
+				DRM_ERROR("Handle already in use!\n");
+				r = -EINVAL;
+				goto out;
+			}
+
+			*size = amdgpu_get_ib_value(p, ib_idx, idx + 8) *
+				amdgpu_get_ib_value(p, ib_idx, idx + 10) *
+				8 * 3 / 2;
+			break;
+
 		case 0x04000001: // config extension
 		case 0x04000002: // pic control
 		case 0x04000005: // rate control
@@ -534,60 +623,74 @@
 			break;
 
 		case 0x03000001: // encode
-			r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 10, idx + 9);
+			r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 10, idx + 9,
+						*size, 0);
 			if (r)
-				return r;
+				goto out;
 
-			r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 12, idx + 11);
+			r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 12, idx + 11,
+						*size / 3, 0);
 			if (r)
-				return r;
+				goto out;
 			break;
 
 		case 0x02000001: // destroy
-			destroy = true;
+			destroyed = true;
 			break;
 
 		case 0x05000001: // context buffer
-		case 0x05000004: // video bitstream buffer
-		case 0x05000005: // feedback buffer
-			r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 3, idx + 2);
+			r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 3, idx + 2,
+						*size * 2, 0);
 			if (r)
-				return r;
+				goto out;
+			break;
+
+		case 0x05000004: // video bitstream buffer
+			tmp = amdgpu_get_ib_value(p, ib_idx, idx + 4);
+			r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 3, idx + 2,
+						tmp, bs_idx);
+			if (r)
+				goto out;
+			break;
+
+		case 0x05000005: // feedback buffer
+			r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 3, idx + 2,
+						4096, fb_idx);
+			if (r)
+				goto out;
 			break;
 
 		default:
 			DRM_ERROR("invalid VCE command (0x%x)!\n", cmd);
-			return -EINVAL;
+			r = -EINVAL;
+			goto out;
+		}
+
+		if (session_idx == -1) {
+			DRM_ERROR("no session command at start of IB\n");
+			r = -EINVAL;
+			goto out;
 		}
 
 		idx += len / 4;
 	}
 
-	if (destroy) {
-		/* IB contains a destroy msg, free the handle */
+	if (allocated && !created) {
+		DRM_ERROR("New session without create command!\n");
+		r = -ENOENT;
+	}
+
+out:
+	if ((!r && destroyed) || (r && allocated)) {
+		/*
+		 * IB contains a destroy msg or we have allocated an
+		 * handle and got an error, anyway free the handle
+		 */
 		for (i = 0; i < AMDGPU_MAX_VCE_HANDLES; ++i)
 			atomic_cmpxchg(&p->adev->vce.handles[i], handle, 0);
-
-		return 0;
 	}
 
-	/* create or encode, validate the handle */
-	for (i = 0; i < AMDGPU_MAX_VCE_HANDLES; ++i) {
-		if (atomic_read(&p->adev->vce.handles[i]) == handle)
-			return 0;
-	}
-
-	/* handle not found try to alloc a new one */
-	for (i = 0; i < AMDGPU_MAX_VCE_HANDLES; ++i) {
-		if (!atomic_cmpxchg(&p->adev->vce.handles[i], 0, handle)) {
-			p->adev->vce.filp[i] = p->filp;
-			return 0;
-		}
-	}
-
-	DRM_ERROR("No more free VCE handles!\n");
-
-	return -EINVAL;
+	return r;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
index b6a9d09..7ccdb59 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
@@ -33,7 +33,6 @@
 int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 			       struct amdgpu_fence **fence);
 void amdgpu_vce_free_handles(struct amdgpu_device *adev, struct drm_file *filp);
-int amdgpu_vce_cs_reloc(struct amdgpu_cs_parser *p, uint32_t ib_idx, int lo, int hi);
 int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx);
 bool amdgpu_vce_ring_emit_semaphore(struct amdgpu_ring *ring,
 				    struct amdgpu_semaphore *semaphore,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 407882b..9a4e3b6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1001,6 +1001,7 @@
 
 	list_add(&mapping->list, &bo_va->mappings);
 	interval_tree_insert(&mapping->it, &vm->va);
+	trace_amdgpu_vm_bo_map(bo_va, mapping);
 
 	bo_va->addr = 0;
 
@@ -1058,6 +1059,7 @@
 	mutex_lock(&vm->mutex);
 	list_del(&mapping->list);
 	interval_tree_remove(&mapping->it, &vm->va);
+	trace_amdgpu_vm_bo_unmap(bo_va, mapping);
 	kfree(mapping);
 
 error_unlock:
@@ -1099,6 +1101,7 @@
 	mutex_lock(&vm->mutex);
 	list_del(&mapping->list);
 	interval_tree_remove(&mapping->it, &vm->va);
+	trace_amdgpu_vm_bo_unmap(bo_va, mapping);
 
 	if (bo_va->addr) {
 		/* clear the old address */
@@ -1139,6 +1142,7 @@
 	list_for_each_entry_safe(mapping, next, &bo_va->mappings, list) {
 		list_del(&mapping->list);
 		interval_tree_remove(&mapping->it, &vm->va);
+		trace_amdgpu_vm_bo_unmap(bo_va, mapping);
 		if (bo_va->addr)
 			list_add(&mapping->list, &vm->freed);
 		else
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 5dab578..341c566 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -2256,10 +2256,6 @@
 		return -EINVAL;
 	}
 
-	adev->ip_block_enabled = kcalloc(adev->num_ip_blocks, sizeof(bool), GFP_KERNEL);
-	if (adev->ip_block_enabled == NULL)
-		return -ENOMEM;
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/cikd.h b/drivers/gpu/drm/amd/amdgpu/cikd.h
index 220865a..d19085a 100644
--- a/drivers/gpu/drm/amd/amdgpu/cikd.h
+++ b/drivers/gpu/drm/amd/amdgpu/cikd.h
@@ -552,4 +552,10 @@
 #define VCE_CMD_IB_AUTO		0x00000005
 #define VCE_CMD_SEMAPHORE	0x00000006
 
+/* valid for both DEFAULT_MTYPE and APE1_MTYPE */
+enum {
+	MTYPE_CACHED = 0,
+	MTYPE_NONCACHED = 3
+};
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
index e4936a4..f75a31d 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
@@ -425,7 +425,7 @@
 	pi->mgcg_cgtt_local1 = 0x0;
 	pi->clock_slow_down_step = 25000;
 	pi->skip_clock_slow_down = 1;
-	pi->enable_nb_ps_policy = 1;
+	pi->enable_nb_ps_policy = 0;
 	pi->caps_power_containment = true;
 	pi->caps_cac = true;
 	pi->didt_enabled = false;
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_dpm.h b/drivers/gpu/drm/amd/amdgpu/cz_dpm.h
index 782a741..99e1afc 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_dpm.h
+++ b/drivers/gpu/drm/amd/amdgpu/cz_dpm.h
@@ -46,7 +46,7 @@
 
 /* Do not change the following, it is also defined in SMU8.h */
 #define SMU_EnabledFeatureScoreboard_AcpDpmOn		0x00000001
-#define SMU_EnabledFeatureScoreboard_SclkDpmOn		0x00100000
+#define SMU_EnabledFeatureScoreboard_SclkDpmOn		0x00200000
 #define SMU_EnabledFeatureScoreboard_UvdDpmOn		0x00800000
 #define SMU_EnabledFeatureScoreboard_VceDpmOn		0x01000000
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index 72c27ac..aaca8d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -3379,7 +3379,7 @@
 	uint32_t disp_int, mask, int_control, tmp;
 	unsigned hpd;
 
-	if (entry->src_data > 6) {
+	if (entry->src_data >= adev->mode_info.num_hpd) {
 		DRM_DEBUG("Unhandled interrupt: %d %d\n", entry->src_id, entry->src_data);
 		return 0;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index cb790744..2c188fb 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -2010,6 +2010,46 @@
 }
 
 /**
+ * gmc_v7_0_init_compute_vmid - gart enable
+ *
+ * @rdev: amdgpu_device pointer
+ *
+ * Initialize compute vmid sh_mem registers
+ *
+ */
+#define DEFAULT_SH_MEM_BASES	(0x6000)
+#define FIRST_COMPUTE_VMID	(8)
+#define LAST_COMPUTE_VMID	(16)
+static void gmc_v7_0_init_compute_vmid(struct amdgpu_device *adev)
+{
+	int i;
+	uint32_t sh_mem_config;
+	uint32_t sh_mem_bases;
+
+	/*
+	 * Configure apertures:
+	 * LDS:         0x60000000'00000000 - 0x60000001'00000000 (4GB)
+	 * Scratch:     0x60000001'00000000 - 0x60000002'00000000 (4GB)
+	 * GPUVM:       0x60010000'00000000 - 0x60020000'00000000 (1TB)
+	*/
+	sh_mem_bases = DEFAULT_SH_MEM_BASES | (DEFAULT_SH_MEM_BASES << 16);
+	sh_mem_config = SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
+			SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT;
+	sh_mem_config |= MTYPE_NONCACHED << SH_MEM_CONFIG__DEFAULT_MTYPE__SHIFT;
+	mutex_lock(&adev->srbm_mutex);
+	for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) {
+		cik_srbm_select(adev, 0, 0, 0, i);
+		/* CP and shaders */
+		WREG32(mmSH_MEM_CONFIG, sh_mem_config);
+		WREG32(mmSH_MEM_APE1_BASE, 1);
+		WREG32(mmSH_MEM_APE1_LIMIT, 0);
+		WREG32(mmSH_MEM_BASES, sh_mem_bases);
+	}
+	cik_srbm_select(adev, 0, 0, 0, 0);
+	mutex_unlock(&adev->srbm_mutex);
+}
+
+/**
  * gfx_v7_0_gpu_init - setup the 3D engine
  *
  * @adev: amdgpu_device pointer
@@ -2230,6 +2270,8 @@
 	cik_srbm_select(adev, 0, 0, 0, 0);
 	mutex_unlock(&adev->srbm_mutex);
 
+	gmc_v7_0_init_compute_vmid(adev);
+
 	WREG32(mmSX_DEBUG_1, 0x20);
 
 	WREG32(mmTA_CNTL_AUX, 0x00010000);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 14242bd..7b683fb 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -1894,6 +1894,51 @@
 	mutex_unlock(&adev->grbm_idx_mutex);
 }
 
+/**
+ * gmc_v8_0_init_compute_vmid - gart enable
+ *
+ * @rdev: amdgpu_device pointer
+ *
+ * Initialize compute vmid sh_mem registers
+ *
+ */
+#define DEFAULT_SH_MEM_BASES	(0x6000)
+#define FIRST_COMPUTE_VMID	(8)
+#define LAST_COMPUTE_VMID	(16)
+static void gmc_v8_0_init_compute_vmid(struct amdgpu_device *adev)
+{
+	int i;
+	uint32_t sh_mem_config;
+	uint32_t sh_mem_bases;
+
+	/*
+	 * Configure apertures:
+	 * LDS:         0x60000000'00000000 - 0x60000001'00000000 (4GB)
+	 * Scratch:     0x60000001'00000000 - 0x60000002'00000000 (4GB)
+	 * GPUVM:       0x60010000'00000000 - 0x60020000'00000000 (1TB)
+	 */
+	sh_mem_bases = DEFAULT_SH_MEM_BASES | (DEFAULT_SH_MEM_BASES << 16);
+
+	sh_mem_config = SH_MEM_ADDRESS_MODE_HSA64 <<
+			SH_MEM_CONFIG__ADDRESS_MODE__SHIFT |
+			SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
+			SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT |
+			MTYPE_CC << SH_MEM_CONFIG__DEFAULT_MTYPE__SHIFT |
+			SH_MEM_CONFIG__PRIVATE_ATC_MASK;
+
+	mutex_lock(&adev->srbm_mutex);
+	for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) {
+		vi_srbm_select(adev, 0, 0, 0, i);
+		/* CP and shaders */
+		WREG32(mmSH_MEM_CONFIG, sh_mem_config);
+		WREG32(mmSH_MEM_APE1_BASE, 1);
+		WREG32(mmSH_MEM_APE1_LIMIT, 0);
+		WREG32(mmSH_MEM_BASES, sh_mem_bases);
+	}
+	vi_srbm_select(adev, 0, 0, 0, 0);
+	mutex_unlock(&adev->srbm_mutex);
+}
+
 static void gfx_v8_0_gpu_init(struct amdgpu_device *adev)
 {
 	u32 gb_addr_config;
@@ -2113,6 +2158,8 @@
 	vi_srbm_select(adev, 0, 0, 0, 0);
 	mutex_unlock(&adev->srbm_mutex);
 
+	gmc_v8_0_init_compute_vmid(adev);
+
 	mutex_lock(&adev->grbm_idx_mutex);
 	/*
 	 * making sure that the following register writes will be broadcasted
@@ -3081,7 +3128,7 @@
 				WREG32(mmCP_MEC_DOORBELL_RANGE_LOWER,
 				       AMDGPU_DOORBELL_KIQ << 2);
 				WREG32(mmCP_MEC_DOORBELL_RANGE_UPPER,
-				       AMDGPU_DOORBELL_MEC_RING7 << 2);
+						0x7FFFF << 2);
 			}
 			tmp = RREG32(mmCP_HQD_PQ_DOORBELL_CONTROL);
 			tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL,
@@ -3097,6 +3144,12 @@
 		WREG32(mmCP_HQD_PQ_DOORBELL_CONTROL,
 		       mqd->cp_hqd_pq_doorbell_control);
 
+		/* reset read and write pointers, similar to CP_RB0_WPTR/_RPTR */
+		ring->wptr = 0;
+		mqd->cp_hqd_pq_wptr = ring->wptr;
+		WREG32(mmCP_HQD_PQ_WPTR, mqd->cp_hqd_pq_wptr);
+		mqd->cp_hqd_pq_rptr = RREG32(mmCP_HQD_PQ_RPTR);
+
 		/* set the vmid for the queue */
 		mqd->cp_hqd_vmid = 0;
 		WREG32(mmCP_HQD_VMID, mqd->cp_hqd_vmid);
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index e3c1fde..7bb37b9 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -439,6 +439,31 @@
 }
 
 /**
+ * sdma_v3_0_ctx_switch_enable - stop the async dma engines context switch
+ *
+ * @adev: amdgpu_device pointer
+ * @enable: enable/disable the DMA MEs context switch.
+ *
+ * Halt or unhalt the async dma engines context switch (VI).
+ */
+static void sdma_v3_0_ctx_switch_enable(struct amdgpu_device *adev, bool enable)
+{
+	u32 f32_cntl;
+	int i;
+
+	for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
+		f32_cntl = RREG32(mmSDMA0_CNTL + sdma_offsets[i]);
+		if (enable)
+			f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_CNTL,
+					AUTO_CTXSW_ENABLE, 1);
+		else
+			f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_CNTL,
+					AUTO_CTXSW_ENABLE, 0);
+		WREG32(mmSDMA0_CNTL + sdma_offsets[i], f32_cntl);
+	}
+}
+
+/**
  * sdma_v3_0_enable - stop the async dma engines
  *
  * @adev: amdgpu_device pointer
@@ -648,6 +673,8 @@
 
 	/* unhalt the MEs */
 	sdma_v3_0_enable(adev, true);
+	/* enable sdma ring preemption */
+	sdma_v3_0_ctx_switch_enable(adev, true);
 
 	/* start the gfx rings and rlc compute queues */
 	r = sdma_v3_0_gfx_resume(adev);
@@ -1079,6 +1106,7 @@
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	sdma_v3_0_ctx_switch_enable(adev, false);
 	sdma_v3_0_enable(adev, false);
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 90fc93c2..fa5a444 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -1189,10 +1189,6 @@
 		return -EINVAL;
 	}
 
-	adev->ip_block_enabled = kcalloc(adev->num_ip_blocks, sizeof(bool), GFP_KERNEL);
-	if (adev->ip_block_enabled == NULL)
-		return -ENOMEM;
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index b69ed97..b9ba061 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -4732,7 +4732,7 @@
 		return 0;
 
 	if (edid)
-		size = EDID_LENGTH + (1 + edid->extensions);
+		size = EDID_LENGTH * (1 + edid->extensions);
 
 	ret = drm_property_replace_global_blob(dev,
 					       &connector->edid_blob_ptr,
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 619dad1..9daa288 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -516,17 +516,17 @@
 		struct page *page_table;
 
 		if (WARN_ON(!ppgtt->pdp.page_directory[pdpe]))
-			continue;
+			break;
 
 		pd = ppgtt->pdp.page_directory[pdpe];
 
 		if (WARN_ON(!pd->page_table[pde]))
-			continue;
+			break;
 
 		pt = pd->page_table[pde];
 
 		if (WARN_ON(!pt->page))
-			continue;
+			break;
 
 		page_table = pt->page;
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index f5edb35..2030f60 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3491,6 +3491,7 @@
 #define   BLM_POLARITY_PNV			(1 << 0) /* pnv only */
 
 #define BLC_HIST_CTL	(dev_priv->info.display_mmio_offset + 0x61260)
+#define  BLM_HISTOGRAM_ENABLE			(1 << 31)
 
 /* New registers for PCH-split platforms. Safe where new bits show up, the
  * register layout machtes with gen4 BLC_PWM_CTL[12]. */
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index dcb1d25..1b61f98 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -13303,6 +13303,16 @@
 				intel_crtc->atomic.wait_vblank = true;
 		}
 
+		/*
+		 * FIXME: Actually if we will still have any other plane enabled
+		 * on the pipe we could let IPS enabled still, but for
+		 * now lets consider that when we make primary invisible
+		 * by setting DSPCNTR to 0 on update_primary_plane function
+		 * IPS needs to be disable.
+		 */
+		if (!state->visible || !fb)
+			intel_crtc->atomic.disable_ips = true;
+
 		intel_crtc->atomic.fb_bits |=
 			INTEL_FRONTBUFFER_PRIMARY(intel_crtc->pipe);
 
@@ -13400,6 +13410,9 @@
 	if (intel_crtc->atomic.disable_fbc)
 		intel_fbc_disable(dev);
 
+	if (intel_crtc->atomic.disable_ips)
+		hsw_disable_ips(intel_crtc);
+
 	if (intel_crtc->atomic.pre_disable_primary)
 		intel_pre_disable_primary(crtc);
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 76afc62..6e8faa2 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1140,6 +1140,9 @@
 static void
 hsw_dp_set_ddi_pll_sel(struct intel_crtc_state *pipe_config, int link_bw)
 {
+	memset(&pipe_config->dpll_hw_state, 0,
+	       sizeof(pipe_config->dpll_hw_state));
+
 	switch (link_bw) {
 	case DP_LINK_BW_1_62:
 		pipe_config->ddi_pll_sel = PORT_CLK_SEL_LCPLL_810;
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 2afb31a..1059283 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -485,6 +485,7 @@
 	/* Sleepable operations to perform before commit */
 	bool wait_for_flips;
 	bool disable_fbc;
+	bool disable_ips;
 	bool pre_disable_primary;
 	bool update_wm;
 	unsigned disabled_planes;
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 7d83527..55aad23 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -907,6 +907,14 @@
 
 	/* XXX: combine this into above write? */
 	intel_panel_actually_set_backlight(connector, panel->backlight.level);
+
+	/*
+	 * Needed to enable backlight on some 855gm models. BLC_HIST_CTL is
+	 * 855gm only, but checking for gen2 is safe, as 855gm is the only gen2
+	 * that has backlight.
+	 */
+	if (IS_GEN2(dev))
+		I915_WRITE(BLC_HIST_CTL, BLM_HISTOGRAM_ENABLE);
 }
 
 static void i965_enable_backlight(struct intel_connector *connector)
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 0e690bf..af1ee51 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -555,10 +555,7 @@
 static inline void
 u_free(void *addr)
 {
-	if (!is_vmalloc_addr(addr))
-		kfree(addr);
-	else
-		vfree(addr);
+	kvfree(addr);
 }
 
 static inline void *
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index b0688b0..4ecf5ca 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -4604,6 +4604,31 @@
 	WDOORBELL32(ring->doorbell_index, ring->wptr);
 }
 
+static void cik_compute_stop(struct radeon_device *rdev,
+			     struct radeon_ring *ring)
+{
+	u32 j, tmp;
+
+	cik_srbm_select(rdev, ring->me, ring->pipe, ring->queue, 0);
+	/* Disable wptr polling. */
+	tmp = RREG32(CP_PQ_WPTR_POLL_CNTL);
+	tmp &= ~WPTR_POLL_EN;
+	WREG32(CP_PQ_WPTR_POLL_CNTL, tmp);
+	/* Disable HQD. */
+	if (RREG32(CP_HQD_ACTIVE) & 1) {
+		WREG32(CP_HQD_DEQUEUE_REQUEST, 1);
+		for (j = 0; j < rdev->usec_timeout; j++) {
+			if (!(RREG32(CP_HQD_ACTIVE) & 1))
+				break;
+			udelay(1);
+		}
+		WREG32(CP_HQD_DEQUEUE_REQUEST, 0);
+		WREG32(CP_HQD_PQ_RPTR, 0);
+		WREG32(CP_HQD_PQ_WPTR, 0);
+	}
+	cik_srbm_select(rdev, 0, 0, 0, 0);
+}
+
 /**
  * cik_cp_compute_enable - enable/disable the compute CP MEs
  *
@@ -4617,6 +4642,15 @@
 	if (enable)
 		WREG32(CP_MEC_CNTL, 0);
 	else {
+		/*
+		 * To make hibernation reliable we need to clear compute ring
+		 * configuration before halting the compute ring.
+		 */
+		mutex_lock(&rdev->srbm_mutex);
+		cik_compute_stop(rdev,&rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX]);
+		cik_compute_stop(rdev,&rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX]);
+		mutex_unlock(&rdev->srbm_mutex);
+
 		WREG32(CP_MEC_CNTL, (MEC_ME1_HALT | MEC_ME2_HALT));
 		rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX].ready = false;
 		rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX].ready = false;
diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c
index f86eb54..d16f2ee 100644
--- a/drivers/gpu/drm/radeon/cik_sdma.c
+++ b/drivers/gpu/drm/radeon/cik_sdma.c
@@ -268,6 +268,17 @@
 	}
 	rdev->ring[R600_RING_TYPE_DMA_INDEX].ready = false;
 	rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX].ready = false;
+
+	/* FIXME use something else than big hammer but after few days can not
+	 * seem to find good combination so reset SDMA blocks as it seems we
+	 * do not shut them down properly. This fix hibernation and does not
+	 * affect suspend to ram.
+	 */
+	WREG32(SRBM_SOFT_RESET, SOFT_RESET_SDMA | SOFT_RESET_SDMA1);
+	(void)RREG32(SRBM_SOFT_RESET);
+	udelay(50);
+	WREG32(SRBM_SOFT_RESET, 0);
+	(void)RREG32(SRBM_SOFT_RESET);
 }
 
 /**
diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c
index c892152..fa719c5 100644
--- a/drivers/gpu/drm/radeon/radeon_audio.c
+++ b/drivers/gpu/drm/radeon/radeon_audio.c
@@ -469,22 +469,22 @@
 	dig = radeon_encoder->enc_priv;
 
 	if (status == connector_status_connected) {
-		struct radeon_connector *radeon_connector;
-		int sink_type;
-
 		if (!drm_detect_monitor_audio(radeon_connector_edid(connector))) {
 			radeon_encoder->audio = NULL;
 			return;
 		}
 
-		radeon_connector = to_radeon_connector(connector);
-		sink_type = radeon_dp_getsinktype(radeon_connector);
+		if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort) {
+			struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 
-		if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort &&
-			sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT)
-			radeon_encoder->audio = rdev->audio.dp_funcs;
-		else
+			if (radeon_dp_getsinktype(radeon_connector) ==
+			    CONNECTOR_OBJECT_ID_DISPLAYPORT)
+				radeon_encoder->audio = rdev->audio.dp_funcs;
+			else
+				radeon_encoder->audio = rdev->audio.hdmi_funcs;
+		} else {
 			radeon_encoder->audio = rdev->audio.hdmi_funcs;
+		}
 
 		dig->afmt->pin = radeon_audio_get_pin(connector->encoder);
 		radeon_audio_enable(rdev, dig->afmt->pin, 0xf);
diff --git a/drivers/gpu/drm/radeon/radeon_fb.c b/drivers/gpu/drm/radeon/radeon_fb.c
index aeb6767..634793e 100644
--- a/drivers/gpu/drm/radeon/radeon_fb.c
+++ b/drivers/gpu/drm/radeon/radeon_fb.c
@@ -257,7 +257,6 @@
 	}
 
 	info->par = rfbdev;
-	info->skip_vt_switch = true;
 
 	ret = radeon_framebuffer_init(rdev->ddev, &rfbdev->rfb, &mode_cmd, gobj);
 	if (ret) {
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index edafd3c..06ac59f 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -719,7 +719,7 @@
 		return 0;
 
 	if (gtt && gtt->userptr) {
-		ttm->sg = kcalloc(1, sizeof(struct sg_table), GFP_KERNEL);
+		ttm->sg = kzalloc(sizeof(struct sg_table), GFP_KERNEL);
 		if (!ttm->sg)
 			return -ENOMEM;
 
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index 3662157..ec10533 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -1129,12 +1129,12 @@
 		interval_tree_remove(&bo_va->it, &vm->va);
 
 	spin_lock(&vm->status_lock);
-	if (list_empty(&bo_va->vm_status)) {
+	list_del(&bo_va->vm_status);
+	if (bo_va->it.start || bo_va->it.last) {
 		bo_va->bo = radeon_bo_ref(bo_va->bo);
 		list_add(&bo_va->vm_status, &vm->freed);
 	} else {
 		radeon_fence_unref(&bo_va->last_pt_update);
-		list_del(&bo_va->vm_status);
 		kfree(bo_va);
 	}
 	spin_unlock(&vm->status_lock);
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
index 3962176..01b558f 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
@@ -21,6 +21,7 @@
 #include <drm/drm_fb_helper.h>
 #include <linux/dma-mapping.h>
 #include <linux/pm_runtime.h>
+#include <linux/module.h>
 #include <linux/of_graph.h>
 #include <linux/component.h>
 
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index 4557f33..dc65161 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -19,6 +19,7 @@
 #include <drm/drm_plane_helper.h>
 
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/of.h>
diff --git a/drivers/hsi/controllers/omap_ssi.h b/drivers/hsi/controllers/omap_ssi.h
index 9d05641..f9aaf37 100644
--- a/drivers/hsi/controllers/omap_ssi.h
+++ b/drivers/hsi/controllers/omap_ssi.h
@@ -24,6 +24,7 @@
 #define __LINUX_HSI_OMAP_SSI_H__
 
 #include <linux/device.h>
+#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/hsi/hsi.h>
 #include <linux/gpio.h>
diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c
index 2a80882..37c16af 100644
--- a/drivers/hwmon/dell-smm-hwmon.c
+++ b/drivers/hwmon/dell-smm-hwmon.c
@@ -777,7 +777,7 @@
 	if (err >= 0)
 		i8k_hwmon_flags |= I8K_HWMON_HAVE_FAN2;
 
-	i8k_hwmon_dev = hwmon_device_register_with_groups(NULL, "dell-smm",
+	i8k_hwmon_dev = hwmon_device_register_with_groups(NULL, "dell_smm",
 							  NULL, i8k_groups);
 	if (IS_ERR(i8k_hwmon_dev)) {
 		err = PTR_ERR(i8k_hwmon_dev);
diff --git a/drivers/hwmon/mcp3021.c b/drivers/hwmon/mcp3021.c
index d219c06..972444a 100644
--- a/drivers/hwmon/mcp3021.c
+++ b/drivers/hwmon/mcp3021.c
@@ -31,14 +31,11 @@
 /* output format */
 #define MCP3021_SAR_SHIFT	2
 #define MCP3021_SAR_MASK	0x3ff
-
 #define MCP3021_OUTPUT_RES	10	/* 10-bit resolution */
-#define MCP3021_OUTPUT_SCALE	4
 
 #define MCP3221_SAR_SHIFT	0
 #define MCP3221_SAR_MASK	0xfff
 #define MCP3221_OUTPUT_RES	12	/* 12-bit resolution */
-#define MCP3221_OUTPUT_SCALE	1
 
 enum chips {
 	mcp3021,
@@ -54,7 +51,6 @@
 	u16 sar_shift;
 	u16 sar_mask;
 	u8 output_res;
-	u8 output_scale;
 };
 
 static int mcp3021_read16(struct i2c_client *client)
@@ -84,13 +80,7 @@
 
 static inline u16 volts_from_reg(struct mcp3021_data *data, u16 val)
 {
-	if (val == 0)
-		return 0;
-
-	val = val * data->output_scale - data->output_scale / 2;
-
-	return val * DIV_ROUND_CLOSEST(data->vdd,
-			(1 << data->output_res) * data->output_scale);
+	return DIV_ROUND_CLOSEST(data->vdd * val, 1 << data->output_res);
 }
 
 static ssize_t show_in_input(struct device *dev, struct device_attribute *attr,
@@ -132,14 +122,12 @@
 		data->sar_shift = MCP3021_SAR_SHIFT;
 		data->sar_mask = MCP3021_SAR_MASK;
 		data->output_res = MCP3021_OUTPUT_RES;
-		data->output_scale = MCP3021_OUTPUT_SCALE;
 		break;
 
 	case mcp3221:
 		data->sar_shift = MCP3221_SAR_SHIFT;
 		data->sar_mask = MCP3221_SAR_MASK;
 		data->output_res = MCP3221_OUTPUT_RES;
-		data->output_scale = MCP3221_OUTPUT_SCALE;
 		break;
 	}
 
diff --git a/drivers/hwmon/nct7802.c b/drivers/hwmon/nct7802.c
index 5576579..28fcb2e 100644
--- a/drivers/hwmon/nct7802.c
+++ b/drivers/hwmon/nct7802.c
@@ -547,7 +547,7 @@
 	if (index >= 9 && index < 18 &&
 	    (reg & 0x0c) != 0x04 && (reg & 0x0c) != 0x08)	/* RD2 */
 		return 0;
-	if (index >= 18 && index < 27 && (reg & 0x30) != 0x10)	/* RD3 */
+	if (index >= 18 && index < 27 && (reg & 0x30) != 0x20)	/* RD3 */
 		return 0;
 	if (index >= 27 && index < 35)				/* local */
 		return attr->mode;
diff --git a/drivers/hwmon/w83627ehf.c b/drivers/hwmon/w83627ehf.c
index b10353b..697007a 100644
--- a/drivers/hwmon/w83627ehf.c
+++ b/drivers/hwmon/w83627ehf.c
@@ -1937,27 +1937,11 @@
 static void w82627ehf_swap_tempreg(struct w83627ehf_data *data,
 				   int r1, int r2)
 {
-	u16 tmp;
-
-	tmp = data->temp_src[r1];
-	data->temp_src[r1] = data->temp_src[r2];
-	data->temp_src[r2] = tmp;
-
-	tmp = data->reg_temp[r1];
-	data->reg_temp[r1] = data->reg_temp[r2];
-	data->reg_temp[r2] = tmp;
-
-	tmp = data->reg_temp_over[r1];
-	data->reg_temp_over[r1] = data->reg_temp_over[r2];
-	data->reg_temp_over[r2] = tmp;
-
-	tmp = data->reg_temp_hyst[r1];
-	data->reg_temp_hyst[r1] = data->reg_temp_hyst[r2];
-	data->reg_temp_hyst[r2] = tmp;
-
-	tmp = data->reg_temp_config[r1];
-	data->reg_temp_config[r1] = data->reg_temp_config[r2];
-	data->reg_temp_config[r2] = tmp;
+	swap(data->temp_src[r1], data->temp_src[r2]);
+	swap(data->reg_temp[r1], data->reg_temp[r2]);
+	swap(data->reg_temp_over[r1], data->reg_temp_over[r2]);
+	swap(data->reg_temp_hyst[r1], data->reg_temp_hyst[r2]);
+	swap(data->reg_temp_config[r1], data->reg_temp_config[r2]);
 }
 
 static void
diff --git a/drivers/hwmon/w83792d.c b/drivers/hwmon/w83792d.c
index 4068db4..0a8bce7 100644
--- a/drivers/hwmon/w83792d.c
+++ b/drivers/hwmon/w83792d.c
@@ -289,10 +289,7 @@
 	u8 temp1[3];		/* current, over, thyst */
 	u8 temp_add[2][6];	/* Register value */
 	u8 fan_div[7];		/* Register encoding, shifted right */
-	u8 pwm[7];		/*
-				 * We only consider the first 3 set of pwm,
-				 * although 792 chip has 7 set of pwm.
-				 */
+	u8 pwm[7];		/* The 7 PWM outputs */
 	u8 pwmenable[3];
 	u32 alarms;		/* realtime status register encoding,combined */
 	u8 chassis;		/* Chassis status */
@@ -1075,6 +1072,10 @@
 static SENSOR_DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 0);
 static SENSOR_DEVICE_ATTR(pwm2, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 1);
 static SENSOR_DEVICE_ATTR(pwm3, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 2);
+static SENSOR_DEVICE_ATTR(pwm4, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 3);
+static SENSOR_DEVICE_ATTR(pwm5, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 4);
+static SENSOR_DEVICE_ATTR(pwm6, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 5);
+static SENSOR_DEVICE_ATTR(pwm7, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 6);
 static SENSOR_DEVICE_ATTR(pwm1_enable, S_IWUSR | S_IRUGO,
 			show_pwmenable, store_pwmenable, 1);
 static SENSOR_DEVICE_ATTR(pwm2_enable, S_IWUSR | S_IRUGO,
@@ -1087,6 +1088,14 @@
 			show_pwm_mode, store_pwm_mode, 1);
 static SENSOR_DEVICE_ATTR(pwm3_mode, S_IWUSR | S_IRUGO,
 			show_pwm_mode, store_pwm_mode, 2);
+static SENSOR_DEVICE_ATTR(pwm4_mode, S_IWUSR | S_IRUGO,
+			show_pwm_mode, store_pwm_mode, 3);
+static SENSOR_DEVICE_ATTR(pwm5_mode, S_IWUSR | S_IRUGO,
+			show_pwm_mode, store_pwm_mode, 4);
+static SENSOR_DEVICE_ATTR(pwm6_mode, S_IWUSR | S_IRUGO,
+			show_pwm_mode, store_pwm_mode, 5);
+static SENSOR_DEVICE_ATTR(pwm7_mode, S_IWUSR | S_IRUGO,
+			show_pwm_mode, store_pwm_mode, 6);
 static SENSOR_DEVICE_ATTR(tolerance1, S_IWUSR | S_IRUGO,
 			show_tolerance, store_tolerance, 1);
 static SENSOR_DEVICE_ATTR(tolerance2, S_IWUSR | S_IRUGO,
@@ -1177,30 +1186,38 @@
 static SENSOR_DEVICE_ATTR(fan7_div, S_IWUSR | S_IRUGO,
 			show_fan_div, store_fan_div, 7);
 
-static struct attribute *w83792d_attributes_fan[4][5] = {
+static struct attribute *w83792d_attributes_fan[4][7] = {
 	{
 		&sensor_dev_attr_fan4_input.dev_attr.attr,
 		&sensor_dev_attr_fan4_min.dev_attr.attr,
 		&sensor_dev_attr_fan4_div.dev_attr.attr,
 		&sensor_dev_attr_fan4_alarm.dev_attr.attr,
+		&sensor_dev_attr_pwm4.dev_attr.attr,
+		&sensor_dev_attr_pwm4_mode.dev_attr.attr,
 		NULL
 	}, {
 		&sensor_dev_attr_fan5_input.dev_attr.attr,
 		&sensor_dev_attr_fan5_min.dev_attr.attr,
 		&sensor_dev_attr_fan5_div.dev_attr.attr,
 		&sensor_dev_attr_fan5_alarm.dev_attr.attr,
+		&sensor_dev_attr_pwm5.dev_attr.attr,
+		&sensor_dev_attr_pwm5_mode.dev_attr.attr,
 		NULL
 	}, {
 		&sensor_dev_attr_fan6_input.dev_attr.attr,
 		&sensor_dev_attr_fan6_min.dev_attr.attr,
 		&sensor_dev_attr_fan6_div.dev_attr.attr,
 		&sensor_dev_attr_fan6_alarm.dev_attr.attr,
+		&sensor_dev_attr_pwm6.dev_attr.attr,
+		&sensor_dev_attr_pwm6_mode.dev_attr.attr,
 		NULL
 	}, {
 		&sensor_dev_attr_fan7_input.dev_attr.attr,
 		&sensor_dev_attr_fan7_min.dev_attr.attr,
 		&sensor_dev_attr_fan7_div.dev_attr.attr,
 		&sensor_dev_attr_fan7_alarm.dev_attr.attr,
+		&sensor_dev_attr_pwm7.dev_attr.attr,
+		&sensor_dev_attr_pwm7_mode.dev_attr.attr,
 		NULL
 	}
 };
diff --git a/drivers/hwspinlock/Kconfig b/drivers/hwspinlock/Kconfig
index 3612cb5..73a4016 100644
--- a/drivers/hwspinlock/Kconfig
+++ b/drivers/hwspinlock/Kconfig
@@ -18,6 +18,30 @@
 
 	  If unsure, say N.
 
+config HWSPINLOCK_QCOM
+	tristate "Qualcomm Hardware Spinlock device"
+	depends on ARCH_QCOM
+	select HWSPINLOCK
+	select MFD_SYSCON
+	help
+	  Say y here to support the Qualcomm Hardware Mutex functionality, which
+	  provides a synchronisation mechanism for the various processors on
+	  the SoC.
+
+	  If unsure, say N.
+
+config HWSPINLOCK_SIRF
+	tristate "SIRF Hardware Spinlock device"
+	depends on ARCH_SIRF
+	select HWSPINLOCK
+	help
+	  Say y here to support the SIRF Hardware Spinlock device, which
+	  provides a synchronisation mechanism for the various processors
+	  on the SoC.
+
+	  It's safe to say n here if you're not interested in SIRF hardware
+	  spinlock or just want a bare minimum kernel.
+
 config HSEM_U8500
 	tristate "STE Hardware Semaphore functionality"
 	depends on ARCH_U8500
diff --git a/drivers/hwspinlock/Makefile b/drivers/hwspinlock/Makefile
index 93eb64b..6b59cb5a 100644
--- a/drivers/hwspinlock/Makefile
+++ b/drivers/hwspinlock/Makefile
@@ -4,4 +4,6 @@
 
 obj-$(CONFIG_HWSPINLOCK)		+= hwspinlock_core.o
 obj-$(CONFIG_HWSPINLOCK_OMAP)		+= omap_hwspinlock.o
+obj-$(CONFIG_HWSPINLOCK_QCOM)		+= qcom_hwspinlock.o
+obj-$(CONFIG_HWSPINLOCK_SIRF)		+= sirf_hwspinlock.o
 obj-$(CONFIG_HSEM_U8500)		+= u8500_hsem.o
diff --git a/drivers/hwspinlock/hwspinlock_core.c b/drivers/hwspinlock/hwspinlock_core.c
index 461a0d7..52f708b 100644
--- a/drivers/hwspinlock/hwspinlock_core.c
+++ b/drivers/hwspinlock/hwspinlock_core.c
@@ -27,6 +27,7 @@
 #include <linux/hwspinlock.h>
 #include <linux/pm_runtime.h>
 #include <linux/mutex.h>
+#include <linux/of.h>
 
 #include "hwspinlock_internal.h"
 
@@ -257,6 +258,84 @@
 }
 EXPORT_SYMBOL_GPL(__hwspin_unlock);
 
+/**
+ * of_hwspin_lock_simple_xlate - translate hwlock_spec to return a lock id
+ * @bank: the hwspinlock device bank
+ * @hwlock_spec: hwlock specifier as found in the device tree
+ *
+ * This is a simple translation function, suitable for hwspinlock platform
+ * drivers that only has a lock specifier length of 1.
+ *
+ * Returns a relative index of the lock within a specified bank on success,
+ * or -EINVAL on invalid specifier cell count.
+ */
+static inline int
+of_hwspin_lock_simple_xlate(const struct of_phandle_args *hwlock_spec)
+{
+	if (WARN_ON(hwlock_spec->args_count != 1))
+		return -EINVAL;
+
+	return hwlock_spec->args[0];
+}
+
+/**
+ * of_hwspin_lock_get_id() - get lock id for an OF phandle-based specific lock
+ * @np: device node from which to request the specific hwlock
+ * @index: index of the hwlock in the list of values
+ *
+ * This function provides a means for DT users of the hwspinlock module to
+ * get the global lock id of a specific hwspinlock using the phandle of the
+ * hwspinlock device, so that it can be requested using the normal
+ * hwspin_lock_request_specific() API.
+ *
+ * Returns the global lock id number on success, -EPROBE_DEFER if the hwspinlock
+ * device is not yet registered, -EINVAL on invalid args specifier value or an
+ * appropriate error as returned from the OF parsing of the DT client node.
+ */
+int of_hwspin_lock_get_id(struct device_node *np, int index)
+{
+	struct of_phandle_args args;
+	struct hwspinlock *hwlock;
+	struct radix_tree_iter iter;
+	void **slot;
+	int id;
+	int ret;
+
+	ret = of_parse_phandle_with_args(np, "hwlocks", "#hwlock-cells", index,
+					 &args);
+	if (ret)
+		return ret;
+
+	/* Find the hwspinlock device: we need its base_id */
+	ret = -EPROBE_DEFER;
+	rcu_read_lock();
+	radix_tree_for_each_slot(slot, &hwspinlock_tree, &iter, 0) {
+		hwlock = radix_tree_deref_slot(slot);
+		if (unlikely(!hwlock))
+			continue;
+
+		if (hwlock->bank->dev->of_node == args.np) {
+			ret = 0;
+			break;
+		}
+	}
+	rcu_read_unlock();
+	if (ret < 0)
+		goto out;
+
+	id = of_hwspin_lock_simple_xlate(&args);
+	if (id < 0 || id >= hwlock->bank->num_locks) {
+		ret = -EINVAL;
+		goto out;
+	}
+	id += hwlock->bank->base_id;
+
+out:
+	of_node_put(args.np);
+	return ret ? ret : id;
+}
+EXPORT_SYMBOL_GPL(of_hwspin_lock_get_id);
+
 static int hwspin_lock_register_single(struct hwspinlock *hwlock, int id)
 {
 	struct hwspinlock *tmp;
diff --git a/drivers/hwspinlock/omap_hwspinlock.c b/drivers/hwspinlock/omap_hwspinlock.c
index 47a275c..ad2f8ca 100644
--- a/drivers/hwspinlock/omap_hwspinlock.c
+++ b/drivers/hwspinlock/omap_hwspinlock.c
@@ -1,7 +1,7 @@
 /*
  * OMAP hardware spinlock driver
  *
- * Copyright (C) 2010 Texas Instruments Incorporated - http://www.ti.com
+ * Copyright (C) 2010-2015 Texas Instruments Incorporated - http://www.ti.com
  *
  * Contact: Simon Que <sque@ti.com>
  *          Hari Kanigeri <h-kanigeri2@ti.com>
@@ -27,6 +27,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/hwspinlock.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 
 #include "hwspinlock_internal.h"
@@ -80,14 +81,16 @@
 
 static int omap_hwspinlock_probe(struct platform_device *pdev)
 {
-	struct hwspinlock_pdata *pdata = pdev->dev.platform_data;
+	struct device_node *node = pdev->dev.of_node;
 	struct hwspinlock_device *bank;
 	struct hwspinlock *hwlock;
 	struct resource *res;
 	void __iomem *io_base;
 	int num_locks, i, ret;
+	/* Only a single hwspinlock block device is supported */
+	int base_id = 0;
 
-	if (!pdata)
+	if (!node)
 		return -ENODEV;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -141,7 +144,7 @@
 		hwlock->priv = io_base + LOCK_BASE_OFFSET + sizeof(u32) * i;
 
 	ret = hwspin_lock_register(bank, &pdev->dev, &omap_hwspinlock_ops,
-						pdata->base_id, num_locks);
+						base_id, num_locks);
 	if (ret)
 		goto reg_fail;
 
@@ -174,11 +177,18 @@
 	return 0;
 }
 
+static const struct of_device_id omap_hwspinlock_of_match[] = {
+	{ .compatible = "ti,omap4-hwspinlock", },
+	{ /* end */ },
+};
+MODULE_DEVICE_TABLE(of, omap_hwspinlock_of_match);
+
 static struct platform_driver omap_hwspinlock_driver = {
 	.probe		= omap_hwspinlock_probe,
 	.remove		= omap_hwspinlock_remove,
 	.driver		= {
 		.name	= "omap_hwspinlock",
+		.of_match_table = of_match_ptr(omap_hwspinlock_of_match),
 	},
 };
 
diff --git a/drivers/hwspinlock/qcom_hwspinlock.c b/drivers/hwspinlock/qcom_hwspinlock.c
new file mode 100644
index 0000000..c752447
--- /dev/null
+++ b/drivers/hwspinlock/qcom_hwspinlock.c
@@ -0,0 +1,181 @@
+/*
+ * Copyright (c) 2013, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2015, Sony Mobile Communications AB
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/hwspinlock.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/regmap.h>
+
+#include "hwspinlock_internal.h"
+
+#define QCOM_MUTEX_APPS_PROC_ID	1
+#define QCOM_MUTEX_NUM_LOCKS	32
+
+static int qcom_hwspinlock_trylock(struct hwspinlock *lock)
+{
+	struct regmap_field *field = lock->priv;
+	u32 lock_owner;
+	int ret;
+
+	ret = regmap_field_write(field, QCOM_MUTEX_APPS_PROC_ID);
+	if (ret)
+		return ret;
+
+	ret = regmap_field_read(field, &lock_owner);
+	if (ret)
+		return ret;
+
+	return lock_owner == QCOM_MUTEX_APPS_PROC_ID;
+}
+
+static void qcom_hwspinlock_unlock(struct hwspinlock *lock)
+{
+	struct regmap_field *field = lock->priv;
+	u32 lock_owner;
+	int ret;
+
+	ret = regmap_field_read(field, &lock_owner);
+	if (ret) {
+		pr_err("%s: unable to query spinlock owner\n", __func__);
+		return;
+	}
+
+	if (lock_owner != QCOM_MUTEX_APPS_PROC_ID) {
+		pr_err("%s: spinlock not owned by us (actual owner is %d)\n",
+				__func__, lock_owner);
+	}
+
+	ret = regmap_field_write(field, 0);
+	if (ret)
+		pr_err("%s: failed to unlock spinlock\n", __func__);
+}
+
+static const struct hwspinlock_ops qcom_hwspinlock_ops = {
+	.trylock	= qcom_hwspinlock_trylock,
+	.unlock		= qcom_hwspinlock_unlock,
+};
+
+static const struct of_device_id qcom_hwspinlock_of_match[] = {
+	{ .compatible = "qcom,sfpb-mutex" },
+	{ .compatible = "qcom,tcsr-mutex" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, qcom_hwspinlock_of_match);
+
+static int qcom_hwspinlock_probe(struct platform_device *pdev)
+{
+	struct hwspinlock_device *bank;
+	struct device_node *syscon;
+	struct reg_field field;
+	struct regmap *regmap;
+	size_t array_size;
+	u32 stride;
+	u32 base;
+	int ret;
+	int i;
+
+	syscon = of_parse_phandle(pdev->dev.of_node, "syscon", 0);
+	if (!syscon) {
+		dev_err(&pdev->dev, "no syscon property\n");
+		return -ENODEV;
+	}
+
+	regmap = syscon_node_to_regmap(syscon);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	ret = of_property_read_u32_index(pdev->dev.of_node, "syscon", 1, &base);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "no offset in syscon\n");
+		return -EINVAL;
+	}
+
+	ret = of_property_read_u32_index(pdev->dev.of_node, "syscon", 2, &stride);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "no stride syscon\n");
+		return -EINVAL;
+	}
+
+	array_size = QCOM_MUTEX_NUM_LOCKS * sizeof(struct hwspinlock);
+	bank = devm_kzalloc(&pdev->dev, sizeof(*bank) + array_size, GFP_KERNEL);
+	if (!bank)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, bank);
+
+	for (i = 0; i < QCOM_MUTEX_NUM_LOCKS; i++) {
+		field.reg = base + i * stride;
+		field.lsb = 0;
+		field.msb = 31;
+
+		bank->lock[i].priv = devm_regmap_field_alloc(&pdev->dev,
+							     regmap, field);
+	}
+
+	pm_runtime_enable(&pdev->dev);
+
+	ret = hwspin_lock_register(bank, &pdev->dev, &qcom_hwspinlock_ops,
+				   0, QCOM_MUTEX_NUM_LOCKS);
+	if (ret)
+		pm_runtime_disable(&pdev->dev);
+
+	return ret;
+}
+
+static int qcom_hwspinlock_remove(struct platform_device *pdev)
+{
+	struct hwspinlock_device *bank = platform_get_drvdata(pdev);
+	int ret;
+
+	ret = hwspin_lock_unregister(bank);
+	if (ret) {
+		dev_err(&pdev->dev, "%s failed: %d\n", __func__, ret);
+		return ret;
+	}
+
+	pm_runtime_disable(&pdev->dev);
+
+	return 0;
+}
+
+static struct platform_driver qcom_hwspinlock_driver = {
+	.probe		= qcom_hwspinlock_probe,
+	.remove		= qcom_hwspinlock_remove,
+	.driver		= {
+		.name	= "qcom_hwspinlock",
+		.of_match_table = qcom_hwspinlock_of_match,
+	},
+};
+
+static int __init qcom_hwspinlock_init(void)
+{
+	return platform_driver_register(&qcom_hwspinlock_driver);
+}
+/* board init code might need to reserve hwspinlocks for predefined purposes */
+postcore_initcall(qcom_hwspinlock_init);
+
+static void __exit qcom_hwspinlock_exit(void)
+{
+	platform_driver_unregister(&qcom_hwspinlock_driver);
+}
+module_exit(qcom_hwspinlock_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Hardware spinlock driver for Qualcomm SoCs");
diff --git a/drivers/hwspinlock/sirf_hwspinlock.c b/drivers/hwspinlock/sirf_hwspinlock.c
new file mode 100644
index 0000000..1601854
--- /dev/null
+++ b/drivers/hwspinlock/sirf_hwspinlock.c
@@ -0,0 +1,136 @@
+/*
+ * SIRF hardware spinlock driver
+ *
+ * Copyright (c) 2015 Cambridge Silicon Radio Limited, a CSR plc group company.
+ *
+ * Licensed under GPLv2.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/hwspinlock.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+
+#include "hwspinlock_internal.h"
+
+struct sirf_hwspinlock {
+	void __iomem *io_base;
+	struct hwspinlock_device bank;
+};
+
+/* Number of Hardware Spinlocks*/
+#define	HW_SPINLOCK_NUMBER	30
+
+/* Hardware spinlock register offsets */
+#define HW_SPINLOCK_BASE	0x404
+#define HW_SPINLOCK_OFFSET(x)	(HW_SPINLOCK_BASE + 0x4 * (x))
+
+static int sirf_hwspinlock_trylock(struct hwspinlock *lock)
+{
+	void __iomem *lock_addr = lock->priv;
+
+	/* attempt to acquire the lock by reading value == 1 from it */
+	return !!readl(lock_addr);
+}
+
+static void sirf_hwspinlock_unlock(struct hwspinlock *lock)
+{
+	void __iomem *lock_addr = lock->priv;
+
+	/* release the lock by writing 0 to it */
+	writel(0, lock_addr);
+}
+
+static const struct hwspinlock_ops sirf_hwspinlock_ops = {
+	.trylock = sirf_hwspinlock_trylock,
+	.unlock = sirf_hwspinlock_unlock,
+};
+
+static int sirf_hwspinlock_probe(struct platform_device *pdev)
+{
+	struct sirf_hwspinlock *hwspin;
+	struct hwspinlock *hwlock;
+	int idx, ret;
+
+	if (!pdev->dev.of_node)
+		return -ENODEV;
+
+	hwspin = devm_kzalloc(&pdev->dev, sizeof(*hwspin) +
+			sizeof(*hwlock) * HW_SPINLOCK_NUMBER, GFP_KERNEL);
+	if (!hwspin)
+		return -ENOMEM;
+
+	/* retrieve io base */
+	hwspin->io_base = of_iomap(pdev->dev.of_node, 0);
+	if (!hwspin->io_base)
+		return -ENOMEM;
+
+	for (idx = 0; idx < HW_SPINLOCK_NUMBER; idx++) {
+		hwlock = &hwspin->bank.lock[idx];
+		hwlock->priv = hwspin->io_base + HW_SPINLOCK_OFFSET(idx);
+	}
+
+	platform_set_drvdata(pdev, hwspin);
+
+	pm_runtime_enable(&pdev->dev);
+
+	ret = hwspin_lock_register(&hwspin->bank, &pdev->dev,
+				   &sirf_hwspinlock_ops, 0,
+				   HW_SPINLOCK_NUMBER);
+	if (ret)
+		goto reg_failed;
+
+	return 0;
+
+reg_failed:
+	pm_runtime_disable(&pdev->dev);
+	iounmap(hwspin->io_base);
+
+	return ret;
+}
+
+static int sirf_hwspinlock_remove(struct platform_device *pdev)
+{
+	struct sirf_hwspinlock *hwspin = platform_get_drvdata(pdev);
+	int ret;
+
+	ret = hwspin_lock_unregister(&hwspin->bank);
+	if (ret) {
+		dev_err(&pdev->dev, "%s failed: %d\n", __func__, ret);
+		return ret;
+	}
+
+	pm_runtime_disable(&pdev->dev);
+
+	iounmap(hwspin->io_base);
+
+	return 0;
+}
+
+static const struct of_device_id sirf_hwpinlock_ids[] = {
+	{ .compatible = "sirf,hwspinlock", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, sirf_hwpinlock_ids);
+
+static struct platform_driver sirf_hwspinlock_driver = {
+	.probe = sirf_hwspinlock_probe,
+	.remove = sirf_hwspinlock_remove,
+	.driver = {
+		.name = "atlas7_hwspinlock",
+		.of_match_table = of_match_ptr(sirf_hwpinlock_ids),
+	},
+};
+
+module_platform_driver(sirf_hwspinlock_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("SIRF Hardware spinlock driver");
+MODULE_AUTHOR("Wei Chen <wei.chen@csr.com>");
diff --git a/drivers/ide/ide.c b/drivers/ide/ide.c
index e29b02c..f086ef3 100644
--- a/drivers/ide/ide.c
+++ b/drivers/ide/ide.c
@@ -199,7 +199,7 @@
 	return 0;
 }
 
-static struct kernel_param_ops param_ops_ide_dev_mask = {
+static const struct kernel_param_ops param_ops_ide_dev_mask = {
 	.set = ide_set_dev_param_mask
 };
 
diff --git a/drivers/infiniband/hw/ehca/ipz_pt_fn.c b/drivers/infiniband/hw/ehca/ipz_pt_fn.c
index 8d59451..7ffc748 100644
--- a/drivers/infiniband/hw/ehca/ipz_pt_fn.c
+++ b/drivers/infiniband/hw/ehca/ipz_pt_fn.c
@@ -245,10 +245,7 @@
 ipz_queue_ctor_exit0:
 	ehca_gen_err("Couldn't alloc pages queue=%p "
 		 "nr_of_pages=%x",  queue, nr_of_pages);
-	if (is_vmalloc_addr(queue->queue_pages))
-		vfree(queue->queue_pages);
-	else
-		kfree(queue->queue_pages);
+	kvfree(queue->queue_pages);
 
 	return 0;
 }
@@ -270,10 +267,7 @@
 			free_page((unsigned long)queue->queue_pages[i]);
 	}
 
-	if (is_vmalloc_addr(queue->queue_pages))
-		vfree(queue->queue_pages);
-	else
-		kfree(queue->queue_pages);
+	kvfree(queue->queue_pages);
 
 	return 1;
 }
diff --git a/drivers/infiniband/hw/ipath/ipath_fs.c b/drivers/infiniband/hw/ipath/ipath_fs.c
index 1ca8e32..25422a3 100644
--- a/drivers/infiniband/hw/ipath/ipath_fs.c
+++ b/drivers/infiniband/hw/ipath/ipath_fs.c
@@ -277,7 +277,7 @@
 	}
 
 	spin_lock(&tmp->d_lock);
-	if (!d_unhashed(tmp) && d_really_is_positive(tmp)) {
+	if (simple_positive(tmp)) {
 		dget_dlock(tmp);
 		__d_drop(tmp);
 		spin_unlock(&tmp->d_lock);
diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c
index bdd5d38..13ef22b 100644
--- a/drivers/infiniband/hw/qib/qib_fs.c
+++ b/drivers/infiniband/hw/qib/qib_fs.c
@@ -455,7 +455,7 @@
 	}
 
 	spin_lock(&tmp->d_lock);
-	if (!d_unhashed(tmp) && d_really_is_positive(tmp)) {
+	if (simple_positive(tmp)) {
 		__d_drop(tmp);
 		spin_unlock(&tmp->d_lock);
 		simple_unlink(d_inode(parent), tmp);
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index f3b7a34..7717009 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -1356,7 +1356,7 @@
 	if (!rc && dump_payload == false && unsol_data)
 		iscsit_set_unsoliticed_dataout(cmd);
 	else if (dump_payload && imm_data)
-		target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd);
+		target_put_sess_cmd(&cmd->se_cmd);
 
 	return 0;
 }
@@ -1781,7 +1781,7 @@
 			    cmd->se_cmd.t_state == TRANSPORT_WRITE_PENDING) {
 				struct se_cmd *se_cmd = &cmd->se_cmd;
 
-				target_put_sess_cmd(se_cmd->se_sess, se_cmd);
+				target_put_sess_cmd(se_cmd);
 			}
 		}
 
@@ -1954,7 +1954,7 @@
 	spin_unlock_bh(&cmd->istate_lock);
 
 	if (ret) {
-		target_put_sess_cmd(se_cmd->se_sess, se_cmd);
+		target_put_sess_cmd(se_cmd);
 		transport_send_check_condition_and_sense(se_cmd,
 							 se_cmd->pi_err, 0);
 	} else {
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index eada8f7..267dc4f 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -99,7 +99,7 @@
 MODULE_PARM_DESC(register_always,
 		 "Use memory registration even for contiguous memory regions");
 
-static struct kernel_param_ops srp_tmo_ops;
+static const struct kernel_param_ops srp_tmo_ops;
 
 static int srp_reconnect_delay = 10;
 module_param_cb(reconnect_delay, &srp_tmo_ops, &srp_reconnect_delay,
@@ -184,7 +184,7 @@
 	return res;
 }
 
-static struct kernel_param_ops srp_tmo_ops = {
+static const struct kernel_param_ops srp_tmo_ops = {
 	.get = srp_tmo_get,
 	.set = srp_tmo_set,
 };
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 4556cd1..82897ca 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -47,7 +47,6 @@
 #include <target/target_core_base.h>
 #include <target/target_core_fabric_configfs.h>
 #include <target/target_core_fabric.h>
-#include <target/target_core_configfs.h>
 #include "ib_srpt.h"
 
 /* Name of this kernel module. */
@@ -94,7 +93,6 @@
 		 " instead of using the node_guid of the first HCA.");
 
 static struct ib_client srpt_client;
-static const struct target_core_fabric_ops srpt_template;
 static void srpt_release_channel(struct srpt_rdma_ch *ch);
 static int srpt_queue_status(struct se_cmd *cmd);
 
@@ -1336,12 +1334,12 @@
 
 		BUG_ON(ch->sess == NULL);
 
-		target_put_sess_cmd(ch->sess, &ioctx->cmd);
+		target_put_sess_cmd(&ioctx->cmd);
 		goto out;
 	}
 
 	pr_debug("Aborting cmd with state %d and tag %lld\n", state,
-		 ioctx->tag);
+		 ioctx->cmd.tag);
 
 	switch (state) {
 	case SRPT_STATE_NEW:
@@ -1367,11 +1365,11 @@
 		 * not been received in time.
 		 */
 		srpt_unmap_sg_to_ib_sge(ioctx->ch, ioctx);
-		target_put_sess_cmd(ioctx->ch->sess, &ioctx->cmd);
+		target_put_sess_cmd(&ioctx->cmd);
 		break;
 	case SRPT_STATE_MGMT_RSP_SENT:
 		srpt_set_cmd_state(ioctx, SRPT_STATE_DONE);
-		target_put_sess_cmd(ioctx->ch->sess, &ioctx->cmd);
+		target_put_sess_cmd(&ioctx->cmd);
 		break;
 	default:
 		WARN(1, "Unexpected command state (%d)", state);
@@ -1389,7 +1387,6 @@
 {
 	struct srpt_send_ioctx *ioctx;
 	enum srpt_command_state state;
-	struct se_cmd *cmd;
 	u32 index;
 
 	atomic_inc(&ch->sq_wr_avail);
@@ -1397,7 +1394,6 @@
 	index = idx_from_wr_id(wr_id);
 	ioctx = ch->ioctx_ring[index];
 	state = srpt_get_cmd_state(ioctx);
-	cmd = &ioctx->cmd;
 
 	WARN_ON(state != SRPT_STATE_CMD_RSP_SENT
 		&& state != SRPT_STATE_MGMT_RSP_SENT
@@ -1474,10 +1470,8 @@
 				      struct srpt_send_ioctx *ioctx,
 				      enum srpt_opcode opcode)
 {
-	struct se_cmd *cmd;
 	enum srpt_command_state state;
 
-	cmd = &ioctx->cmd;
 	state = srpt_get_cmd_state(ioctx);
 	switch (opcode) {
 	case SRPT_RDMA_READ_LAST:
@@ -1681,7 +1675,7 @@
 	struct srpt_send_ioctx *ioctx = container_of(cmd,
 				struct srpt_send_ioctx, cmd);
 
-	return target_put_sess_cmd(ioctx->ch->sess, &ioctx->cmd);
+	return target_put_sess_cmd(&ioctx->cmd);
 }
 
 /**
@@ -1703,7 +1697,7 @@
 
 	srp_cmd = recv_ioctx->ioctx.buf;
 	cmd = &send_ioctx->cmd;
-	send_ioctx->tag = srp_cmd->tag;
+	cmd->tag = srp_cmd->tag;
 
 	switch (srp_cmd->task_attr) {
 	case SRP_CMD_SIMPLE_Q:
@@ -1774,7 +1768,7 @@
 	for (i = 0; i < ch->rq_size; ++i) {
 		target = ch->ioctx_ring[i];
 		if (target->cmd.se_lun == ioctx->cmd.se_lun &&
-		    target->tag == tag &&
+		    target->cmd.tag == tag &&
 		    srpt_get_cmd_state(target) != SRPT_STATE_DONE) {
 			ret = 0;
 			/* now let the target core abort &target->cmd; */
@@ -1833,7 +1827,7 @@
 		 srp_tsk->task_tag, srp_tsk->tag, ch->cm_id, ch->sess);
 
 	srpt_set_cmd_state(send_ioctx, SRPT_STATE_MGMT);
-	send_ioctx->tag = srp_tsk->tag;
+	send_ioctx->cmd.tag = srp_tsk->tag;
 	tcm_tmr = srp_tmr_to_tcm(srp_tsk->tsk_mgmt_func);
 	if (tcm_tmr < 0) {
 		send_ioctx->cmd.se_tmr_req->response =
@@ -2180,12 +2174,9 @@
  */
 static void __srpt_close_ch(struct srpt_rdma_ch *ch)
 {
-	struct srpt_device *sdev;
 	enum rdma_ch_state prev_state;
 	unsigned long flags;
 
-	sdev = ch->sport->sdev;
-
 	spin_lock_irqsave(&ch->spinlock, flags);
 	prev_state = ch->state;
 	switch (prev_state) {
@@ -2983,7 +2974,7 @@
 	case CH_DRAINING:
 	case CH_RELEASING:
 		pr_debug("cmd with tag %lld: channel disconnecting\n",
-			 ioctx->tag);
+			 ioctx->cmd.tag);
 		srpt_set_cmd_state(ioctx, SRPT_STATE_DATA_IN);
 		ret = -EINVAL;
 		goto out;
@@ -3058,27 +3049,27 @@
 		ret = srpt_xfer_data(ch, ioctx);
 		if (ret) {
 			pr_err("xfer_data failed for tag %llu\n",
-			       ioctx->tag);
+			       ioctx->cmd.tag);
 			return;
 		}
 	}
 
 	if (state != SRPT_STATE_MGMT)
-		resp_len = srpt_build_cmd_rsp(ch, ioctx, ioctx->tag,
+		resp_len = srpt_build_cmd_rsp(ch, ioctx, ioctx->cmd.tag,
 					      cmd->scsi_status);
 	else {
 		srp_tm_status
 			= tcm_to_srp_tsk_mgmt_status(cmd->se_tmr_req->response);
 		resp_len = srpt_build_tskmgmt_rsp(ch, ioctx, srp_tm_status,
-						 ioctx->tag);
+						 ioctx->cmd.tag);
 	}
 	ret = srpt_post_send(ch, ioctx, resp_len);
 	if (ret) {
 		pr_err("sending cmd response failed for tag %llu\n",
-		       ioctx->tag);
+		       ioctx->cmd.tag);
 		srpt_unmap_sg_to_ib_sge(ch, ioctx);
 		srpt_set_cmd_state(ioctx, SRPT_STATE_DONE);
-		target_put_sess_cmd(ioctx->ch->sess, &ioctx->cmd);
+		target_put_sess_cmd(&ioctx->cmd);
 	}
 }
 
@@ -3398,11 +3389,6 @@
 	return "srpt";
 }
 
-static u8 srpt_get_fabric_proto_ident(struct se_portal_group *se_tpg)
-{
-	return SCSI_TRANSPORTID_PROTOCOLID_SRP;
-}
-
 static char *srpt_get_fabric_wwn(struct se_portal_group *tpg)
 {
 	struct srpt_port *sport = container_of(tpg, struct srpt_port, port_tpg_1);
@@ -3415,69 +3401,6 @@
 	return 1;
 }
 
-static u32 srpt_get_default_depth(struct se_portal_group *se_tpg)
-{
-	return 1;
-}
-
-static u32 srpt_get_pr_transport_id(struct se_portal_group *se_tpg,
-				    struct se_node_acl *se_nacl,
-				    struct t10_pr_registration *pr_reg,
-				    int *format_code, unsigned char *buf)
-{
-	struct srpt_node_acl *nacl;
-	struct spc_rdma_transport_id *tr_id;
-
-	nacl = container_of(se_nacl, struct srpt_node_acl, nacl);
-	tr_id = (void *)buf;
-	tr_id->protocol_identifier = SCSI_TRANSPORTID_PROTOCOLID_SRP;
-	memcpy(tr_id->i_port_id, nacl->i_port_id, sizeof(tr_id->i_port_id));
-	return sizeof(*tr_id);
-}
-
-static u32 srpt_get_pr_transport_id_len(struct se_portal_group *se_tpg,
-					struct se_node_acl *se_nacl,
-					struct t10_pr_registration *pr_reg,
-					int *format_code)
-{
-	*format_code = 0;
-	return sizeof(struct spc_rdma_transport_id);
-}
-
-static char *srpt_parse_pr_out_transport_id(struct se_portal_group *se_tpg,
-					    const char *buf, u32 *out_tid_len,
-					    char **port_nexus_ptr)
-{
-	struct spc_rdma_transport_id *tr_id;
-
-	*port_nexus_ptr = NULL;
-	*out_tid_len = sizeof(struct spc_rdma_transport_id);
-	tr_id = (void *)buf;
-	return (char *)tr_id->i_port_id;
-}
-
-static struct se_node_acl *srpt_alloc_fabric_acl(struct se_portal_group *se_tpg)
-{
-	struct srpt_node_acl *nacl;
-
-	nacl = kzalloc(sizeof(struct srpt_node_acl), GFP_KERNEL);
-	if (!nacl) {
-		pr_err("Unable to allocate struct srpt_node_acl\n");
-		return NULL;
-	}
-
-	return &nacl->nacl;
-}
-
-static void srpt_release_fabric_acl(struct se_portal_group *se_tpg,
-				    struct se_node_acl *se_nacl)
-{
-	struct srpt_node_acl *nacl;
-
-	nacl = container_of(se_nacl, struct srpt_node_acl, nacl);
-	kfree(nacl);
-}
-
 static u32 srpt_tpg_get_inst_index(struct se_portal_group *se_tpg)
 {
 	return 1;
@@ -3551,14 +3474,6 @@
 {
 }
 
-static u32 srpt_get_task_tag(struct se_cmd *se_cmd)
-{
-	struct srpt_send_ioctx *ioctx;
-
-	ioctx = container_of(se_cmd, struct srpt_send_ioctx, cmd);
-	return ioctx->tag;
-}
-
 /* Note: only used from inside debug printk's by the TCM core. */
 static int srpt_get_tcm_cmd_state(struct se_cmd *se_cmd)
 {
@@ -3601,40 +3516,19 @@
  * configfs callback function invoked for
  * mkdir /sys/kernel/config/target/$driver/$port/$tpg/acls/$i_port_id
  */
-static struct se_node_acl *srpt_make_nodeacl(struct se_portal_group *tpg,
-					     struct config_group *group,
-					     const char *name)
+static int srpt_init_nodeacl(struct se_node_acl *se_nacl, const char *name)
 {
-	struct srpt_port *sport = container_of(tpg, struct srpt_port, port_tpg_1);
-	struct se_node_acl *se_nacl, *se_nacl_new;
-	struct srpt_node_acl *nacl;
-	int ret = 0;
-	u32 nexus_depth = 1;
+	struct srpt_port *sport =
+		container_of(se_nacl->se_tpg, struct srpt_port, port_tpg_1);
+	struct srpt_node_acl *nacl =
+		container_of(se_nacl, struct srpt_node_acl, nacl);
 	u8 i_port_id[16];
 
 	if (srpt_parse_i_port_id(i_port_id, name) < 0) {
 		pr_err("invalid initiator port ID %s\n", name);
-		ret = -EINVAL;
-		goto err;
+		return -EINVAL;
 	}
 
-	se_nacl_new = srpt_alloc_fabric_acl(tpg);
-	if (!se_nacl_new) {
-		ret = -ENOMEM;
-		goto err;
-	}
-	/*
-	 * nacl_new may be released by core_tpg_add_initiator_node_acl()
-	 * when converting a node ACL from demo mode to explict
-	 */
-	se_nacl = core_tpg_add_initiator_node_acl(tpg, se_nacl_new, name,
-						  nexus_depth);
-	if (IS_ERR(se_nacl)) {
-		ret = PTR_ERR(se_nacl);
-		goto err;
-	}
-	/* Locate our struct srpt_node_acl and set sdev and i_port_id. */
-	nacl = container_of(se_nacl, struct srpt_node_acl, nacl);
 	memcpy(&nacl->i_port_id[0], &i_port_id[0], 16);
 	nacl->sport = sport;
 
@@ -3642,29 +3536,22 @@
 	list_add_tail(&nacl->list, &sport->port_acl_list);
 	spin_unlock_irq(&sport->port_acl_lock);
 
-	return se_nacl;
-err:
-	return ERR_PTR(ret);
+	return 0;
 }
 
 /*
  * configfs callback function invoked for
  * rmdir /sys/kernel/config/target/$driver/$port/$tpg/acls/$i_port_id
  */
-static void srpt_drop_nodeacl(struct se_node_acl *se_nacl)
+static void srpt_cleanup_nodeacl(struct se_node_acl *se_nacl)
 {
-	struct srpt_node_acl *nacl;
-	struct srpt_device *sdev;
-	struct srpt_port *sport;
+	struct srpt_node_acl *nacl =
+		container_of(se_nacl, struct srpt_node_acl, nacl);
+	struct srpt_port *sport = nacl->sport;
 
-	nacl = container_of(se_nacl, struct srpt_node_acl, nacl);
-	sport = nacl->sport;
-	sdev = sport->sdev;
 	spin_lock_irq(&sport->port_acl_lock);
 	list_del(&nacl->list);
 	spin_unlock_irq(&sport->port_acl_lock);
-	core_tpg_del_initiator_node_acl(&sport->port_tpg_1, se_nacl, 1);
-	srpt_release_fabric_acl(NULL, se_nacl);
 }
 
 static ssize_t srpt_tpg_attrib_show_srp_max_rdma_size(
@@ -3849,8 +3736,7 @@
 	int res;
 
 	/* Initialize sport->port_wwn and sport->port_tpg_1 */
-	res = core_tpg_register(&srpt_template, &sport->port_wwn,
-			&sport->port_tpg_1, sport, TRANSPORT_TPG_TYPE_NORMAL);
+	res = core_tpg_register(&sport->port_wwn, &sport->port_tpg_1, SCSI_PROTOCOL_SRP);
 	if (res)
 		return ERR_PTR(res);
 
@@ -3920,20 +3806,14 @@
 static const struct target_core_fabric_ops srpt_template = {
 	.module				= THIS_MODULE,
 	.name				= "srpt",
+	.node_acl_size			= sizeof(struct srpt_node_acl),
 	.get_fabric_name		= srpt_get_fabric_name,
-	.get_fabric_proto_ident		= srpt_get_fabric_proto_ident,
 	.tpg_get_wwn			= srpt_get_fabric_wwn,
 	.tpg_get_tag			= srpt_get_tag,
-	.tpg_get_default_depth		= srpt_get_default_depth,
-	.tpg_get_pr_transport_id	= srpt_get_pr_transport_id,
-	.tpg_get_pr_transport_id_len	= srpt_get_pr_transport_id_len,
-	.tpg_parse_pr_out_transport_id	= srpt_parse_pr_out_transport_id,
 	.tpg_check_demo_mode		= srpt_check_false,
 	.tpg_check_demo_mode_cache	= srpt_check_true,
 	.tpg_check_demo_mode_write_protect = srpt_check_true,
 	.tpg_check_prod_mode_write_protect = srpt_check_false,
-	.tpg_alloc_fabric_acl		= srpt_alloc_fabric_acl,
-	.tpg_release_fabric_acl		= srpt_release_fabric_acl,
 	.tpg_get_inst_index		= srpt_tpg_get_inst_index,
 	.release_cmd			= srpt_release_cmd,
 	.check_stop_free		= srpt_check_stop_free,
@@ -3944,7 +3824,6 @@
 	.write_pending			= srpt_write_pending,
 	.write_pending_status		= srpt_write_pending_status,
 	.set_default_node_attributes	= srpt_set_default_node_attrs,
-	.get_task_tag			= srpt_get_task_tag,
 	.get_cmd_state			= srpt_get_tcm_cmd_state,
 	.queue_data_in			= srpt_queue_data_in,
 	.queue_status			= srpt_queue_status,
@@ -3958,12 +3837,8 @@
 	.fabric_drop_wwn		= srpt_drop_tport,
 	.fabric_make_tpg		= srpt_make_tpg,
 	.fabric_drop_tpg		= srpt_drop_tpg,
-	.fabric_post_link		= NULL,
-	.fabric_pre_unlink		= NULL,
-	.fabric_make_np			= NULL,
-	.fabric_drop_np			= NULL,
-	.fabric_make_nodeacl		= srpt_make_nodeacl,
-	.fabric_drop_nodeacl		= srpt_drop_nodeacl,
+	.fabric_init_nodeacl		= srpt_init_nodeacl,
+	.fabric_cleanup_nodeacl		= srpt_cleanup_nodeacl,
 
 	.tfc_wwn_attrs			= srpt_wwn_attrs,
 	.tfc_tpg_base_attrs		= srpt_tpg_attrs,
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.h b/drivers/infiniband/ulp/srpt/ib_srpt.h
index d85c0c2..21f8df6 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.h
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.h
@@ -238,7 +238,6 @@
 	bool			rdma_aborted;
 	struct se_cmd		cmd;
 	struct completion	tx_done;
-	u64			tag;
 	int			sg_cnt;
 	int			mapped_sg_count;
 	u16			n_rdma_ius;
@@ -410,34 +409,16 @@
 
 /**
  * struct srpt_node_acl - Per-initiator ACL data (managed via configfs).
+ * @nacl:      Target core node ACL information.
  * @i_port_id: 128-bit SRP initiator port ID.
  * @sport:     port information.
- * @nacl:      Target core node ACL information.
  * @list:      Element of the per-HCA ACL list.
  */
 struct srpt_node_acl {
+	struct se_node_acl	nacl;
 	u8			i_port_id[16];
 	struct srpt_port	*sport;
-	struct se_node_acl	nacl;
 	struct list_head	list;
 };
 
-/*
- * SRP-releated SCSI persistent reservation definitions.
- *
- * See also SPC4r28, section 7.6.1 (Protocol specific parameters introduction).
- * See also SPC4r28, section 7.6.4.5 (TransportID for initiator ports using
- * SCSI over an RDMA interface).
- */
-
-enum {
-	SCSI_TRANSPORTID_PROTOCOLID_SRP	= 4,
-};
-
-struct spc_rdma_transport_id {
-	uint8_t protocol_identifier;
-	uint8_t reserved[7];
-	uint8_t i_port_id[16];
-};
-
 #endif				/* IB_SRPT_H */
diff --git a/drivers/input/input.c b/drivers/input/input.c
index f315784..78d2499 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -677,12 +677,9 @@
 	int code;
 
 	if (is_event_supported(EV_KEY, dev->evbit, EV_MAX)) {
-		for (code = 0; code <= KEY_MAX; code++) {
-			if (is_event_supported(code, dev->keybit, KEY_MAX) &&
-			    __test_and_clear_bit(code, dev->key)) {
-				input_pass_event(dev, EV_KEY, code, 0);
-			}
-		}
+		for_each_set_bit(code, dev->key, KEY_CNT)
+			input_pass_event(dev, EV_KEY, code, 0);
+		memset(dev->key, 0, sizeof(dev->key));
 		input_pass_event(dev, EV_SYN, SYN_REPORT, 1);
 	}
 }
@@ -1626,10 +1623,7 @@
 		if (!test_bit(EV_##type, dev->evbit))			\
 			break;						\
 									\
-		for (i = 0; i < type##_MAX; i++) {			\
-			if (!test_bit(i, dev->bits##bit))		\
-				continue;				\
-									\
+		for_each_set_bit(i, dev->bits##bit, type##_CNT) {	\
 			active = test_bit(i, dev->bits);		\
 			if (!active && !on)				\
 				continue;				\
@@ -1980,22 +1974,12 @@
 
 	events = mt_slots + 1; /* count SYN_MT_REPORT and SYN_REPORT */
 
-	if (test_bit(EV_ABS, dev->evbit)) {
-		for (i = 0; i < ABS_CNT; i++) {
-			if (test_bit(i, dev->absbit)) {
-				if (input_is_mt_axis(i))
-					events += mt_slots;
-				else
-					events++;
-			}
-		}
-	}
+	if (test_bit(EV_ABS, dev->evbit))
+		for_each_set_bit(i, dev->absbit, ABS_CNT)
+			events += input_is_mt_axis(i) ? mt_slots : 1;
 
-	if (test_bit(EV_REL, dev->evbit)) {
-		for (i = 0; i < REL_CNT; i++)
-			if (test_bit(i, dev->relbit))
-				events++;
-	}
+	if (test_bit(EV_REL, dev->evbit))
+		events += bitmap_weight(dev->relbit, REL_CNT);
 
 	/* Make room for KEY and MSC events */
 	events += 7;
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 61c7611..f8850f9 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -344,6 +344,7 @@
 
 	int mapping;			/* map d-pad to buttons or to axes */
 	int xtype;			/* type of xbox device */
+	unsigned long led_no;		/* led to lit on xbox360 controllers */
 };
 
 /*
@@ -488,6 +489,8 @@
 	input_sync(dev);
 }
 
+static void xpad_identify_controller(struct usb_xpad *xpad);
+
 /*
  * xpad360w_process_packet
  *
@@ -510,6 +513,11 @@
 		if (data[1] & 0x80) {
 			xpad->pad_present = 1;
 			usb_submit_urb(xpad->bulk_out, GFP_ATOMIC);
+			/*
+			 * Light up the segment corresponding to
+			 * controller number.
+			 */
+			xpad_identify_controller(xpad);
 		} else
 			xpad->pad_present = 0;
 	}
@@ -881,17 +889,63 @@
 	struct usb_xpad *xpad;
 };
 
+/**
+ * @param command
+ *  0: off
+ *  1: all blink, then previous setting
+ *  2: 1/top-left blink, then on
+ *  3: 2/top-right blink, then on
+ *  4: 3/bottom-left blink, then on
+ *  5: 4/bottom-right blink, then on
+ *  6: 1/top-left on
+ *  7: 2/top-right on
+ *  8: 3/bottom-left on
+ *  9: 4/bottom-right on
+ * 10: rotate
+ * 11: blink, based on previous setting
+ * 12: slow blink, based on previous setting
+ * 13: rotate with two lights
+ * 14: persistent slow all blink
+ * 15: blink once, then previous setting
+ */
 static void xpad_send_led_command(struct usb_xpad *xpad, int command)
 {
-	if (command >= 0 && command < 14) {
-		mutex_lock(&xpad->odata_mutex);
+	command %= 16;
+
+	mutex_lock(&xpad->odata_mutex);
+
+	switch (xpad->xtype) {
+	case XTYPE_XBOX360:
 		xpad->odata[0] = 0x01;
 		xpad->odata[1] = 0x03;
 		xpad->odata[2] = command;
 		xpad->irq_out->transfer_buffer_length = 3;
-		usb_submit_urb(xpad->irq_out, GFP_KERNEL);
-		mutex_unlock(&xpad->odata_mutex);
+		break;
+	case XTYPE_XBOX360W:
+		xpad->odata[0] = 0x00;
+		xpad->odata[1] = 0x00;
+		xpad->odata[2] = 0x08;
+		xpad->odata[3] = 0x40 + command;
+		xpad->odata[4] = 0x00;
+		xpad->odata[5] = 0x00;
+		xpad->odata[6] = 0x00;
+		xpad->odata[7] = 0x00;
+		xpad->odata[8] = 0x00;
+		xpad->odata[9] = 0x00;
+		xpad->odata[10] = 0x00;
+		xpad->odata[11] = 0x00;
+		xpad->irq_out->transfer_buffer_length = 12;
+		break;
 	}
+
+	usb_submit_urb(xpad->irq_out, GFP_KERNEL);
+	mutex_unlock(&xpad->odata_mutex);
+}
+
+static void xpad_identify_controller(struct usb_xpad *xpad)
+{
+	/* Light up the segment corresponding to controller number */
+	xpad_send_led_command(xpad, (xpad->led_no % 4) + 2);
 }
 
 static void xpad_led_set(struct led_classdev *led_cdev,
@@ -905,22 +959,21 @@
 
 static int xpad_led_probe(struct usb_xpad *xpad)
 {
-	static atomic_t led_seq	= ATOMIC_INIT(-1);
-	unsigned long led_no;
+	static atomic_t led_seq = ATOMIC_INIT(-1);
 	struct xpad_led *led;
 	struct led_classdev *led_cdev;
 	int error;
 
-	if (xpad->xtype != XTYPE_XBOX360)
+	if (xpad->xtype != XTYPE_XBOX360 && xpad->xtype != XTYPE_XBOX360W)
 		return 0;
 
 	xpad->led = led = kzalloc(sizeof(struct xpad_led), GFP_KERNEL);
 	if (!led)
 		return -ENOMEM;
 
-	led_no = atomic_inc_return(&led_seq);
+	xpad->led_no = atomic_inc_return(&led_seq);
 
-	snprintf(led->name, sizeof(led->name), "xpad%lu", led_no);
+	snprintf(led->name, sizeof(led->name), "xpad%lu", xpad->led_no);
 	led->xpad = xpad;
 
 	led_cdev = &led->led_cdev;
@@ -934,10 +987,8 @@
 		return error;
 	}
 
-	/*
-	 * Light up the segment corresponding to controller number
-	 */
-	xpad_send_led_command(xpad, (led_no % 4) + 2);
+	/* Light up the segment corresponding to controller number */
+	xpad_identify_controller(xpad);
 
 	return 0;
 }
@@ -954,6 +1005,7 @@
 #else
 static int xpad_led_probe(struct usb_xpad *xpad) { return 0; }
 static void xpad_led_disconnect(struct usb_xpad *xpad) { }
+static void xpad_identify_controller(struct usb_xpad *xpad) { }
 #endif
 
 
diff --git a/drivers/input/keyboard/imx_keypad.c b/drivers/input/keyboard/imx_keypad.c
index 2e855e6..d2ea863 100644
--- a/drivers/input/keyboard/imx_keypad.c
+++ b/drivers/input/keyboard/imx_keypad.c
@@ -506,7 +506,9 @@
 	input_set_drvdata(input_dev, keypad);
 
 	/* Ensure that the keypad will stay dormant until opened */
-	clk_prepare_enable(keypad->clk);
+	error = clk_prepare_enable(keypad->clk);
+	if (error)
+		return error;
 	imx_keypad_inhibit(keypad);
 	clk_disable_unprepare(keypad->clk);
 
diff --git a/drivers/input/misc/ati_remote2.c b/drivers/input/misc/ati_remote2.c
index f63341f..cfd58e8 100644
--- a/drivers/input/misc/ati_remote2.c
+++ b/drivers/input/misc/ati_remote2.c
@@ -94,7 +94,7 @@
 
 static unsigned int channel_mask = ATI_REMOTE2_MAX_CHANNEL_MASK;
 #define param_check_channel_mask(name, p) __param_check(name, p, unsigned int)
-static struct kernel_param_ops param_ops_channel_mask = {
+static const struct kernel_param_ops param_ops_channel_mask = {
 	.set = ati_remote2_set_channel_mask,
 	.get = ati_remote2_get_channel_mask,
 };
@@ -103,7 +103,7 @@
 
 static unsigned int mode_mask = ATI_REMOTE2_MAX_MODE_MASK;
 #define param_check_mode_mask(name, p) __param_check(name, p, unsigned int)
-static struct kernel_param_ops param_ops_mode_mask = {
+static const struct kernel_param_ops param_ops_mode_mask = {
 	.set = ati_remote2_set_mode_mask,
 	.get = ati_remote2_get_mode_mask,
 };
diff --git a/drivers/input/misc/axp20x-pek.c b/drivers/input/misc/axp20x-pek.c
index f1c8447..10e140a 100644
--- a/drivers/input/misc/axp20x-pek.c
+++ b/drivers/input/misc/axp20x-pek.c
@@ -167,9 +167,13 @@
 	struct input_dev *idev = pwr;
 	struct axp20x_pek *axp20x_pek = input_get_drvdata(idev);
 
-	if (irq == axp20x_pek->irq_dbr)
+	/*
+	 * The power-button is connected to ground so a falling edge (dbf)
+	 * means it is pressed.
+	 */
+	if (irq == axp20x_pek->irq_dbf)
 		input_report_key(idev, KEY_POWER, true);
-	else if (irq == axp20x_pek->irq_dbf)
+	else if (irq == axp20x_pek->irq_dbr)
 		input_report_key(idev, KEY_POWER, false);
 
 	input_sync(idev);
diff --git a/drivers/input/mouse/psmouse-base.c b/drivers/input/mouse/psmouse-base.c
index 7c4ba43..ec347703 100644
--- a/drivers/input/mouse/psmouse-base.c
+++ b/drivers/input/mouse/psmouse-base.c
@@ -47,7 +47,7 @@
 static unsigned int psmouse_max_proto = PSMOUSE_AUTO;
 static int psmouse_set_maxproto(const char *val, const struct kernel_param *);
 static int psmouse_get_maxproto(char *buffer, const struct kernel_param *kp);
-static struct kernel_param_ops param_ops_proto_abbrev = {
+static const struct kernel_param_ops param_ops_proto_abbrev = {
 	.set = psmouse_set_maxproto,
 	.get = psmouse_get_maxproto,
 };
diff --git a/drivers/input/serio/Kconfig b/drivers/input/serio/Kconfig
index 77833d7..200841b 100644
--- a/drivers/input/serio/Kconfig
+++ b/drivers/input/serio/Kconfig
@@ -244,6 +244,7 @@
 
 config SERIO_ARC_PS2
 	tristate "ARC PS/2 support"
+	depends on HAS_IOMEM
 	help
 	  Say Y here if you have an ARC FPGA platform with a PS/2
 	  controller in it.
diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig
index d20fe1d..a854c6e 100644
--- a/drivers/input/touchscreen/Kconfig
+++ b/drivers/input/touchscreen/Kconfig
@@ -658,6 +658,18 @@
 	  To compile this driver as a module, choose M here: the
 	  module will be called pixcir_i2c_ts.
 
+config TOUCHSCREEN_WDT87XX_I2C
+	tristate "Weida HiTech I2C touchscreen"
+	depends on I2C
+	help
+	  Say Y here if you have a Weida WDT87XX I2C touchscreen
+	  connected to your system.
+
+	  If unsure, say N.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called wdt87xx_i2c.
+
 config TOUCHSCREEN_WM831X
 	tristate "Support for WM831x touchscreen controllers"
 	depends on MFD_WM831X
diff --git a/drivers/input/touchscreen/Makefile b/drivers/input/touchscreen/Makefile
index 44deea7..fa3d33b 100644
--- a/drivers/input/touchscreen/Makefile
+++ b/drivers/input/touchscreen/Makefile
@@ -72,6 +72,7 @@
 obj-$(CONFIG_TOUCHSCREEN_UCB1400)	+= ucb1400_ts.o
 obj-$(CONFIG_TOUCHSCREEN_WACOM_W8001)	+= wacom_w8001.o
 obj-$(CONFIG_TOUCHSCREEN_WACOM_I2C)	+= wacom_i2c.o
+obj-$(CONFIG_TOUCHSCREEN_WDT87XX_I2C)	+= wdt87xx_i2c.o
 obj-$(CONFIG_TOUCHSCREEN_WM831X)	+= wm831x-ts.o
 obj-$(CONFIG_TOUCHSCREEN_WM97XX)	+= wm97xx-ts.o
 wm97xx-ts-$(CONFIG_TOUCHSCREEN_WM9705)	+= wm9705.o
diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c
index e6aef3e..394b1de 100644
--- a/drivers/input/touchscreen/edt-ft5x06.c
+++ b/drivers/input/touchscreen/edt-ft5x06.c
@@ -1035,20 +1035,15 @@
 	input->id.bustype = BUS_I2C;
 	input->dev.parent = &client->dev;
 
-	__set_bit(EV_KEY, input->evbit);
-	__set_bit(EV_ABS, input->evbit);
-	__set_bit(BTN_TOUCH, input->keybit);
-	input_set_abs_params(input, ABS_X, 0, tsdata->num_x * 64 - 1, 0, 0);
-	input_set_abs_params(input, ABS_Y, 0, tsdata->num_y * 64 - 1, 0, 0);
 	input_set_abs_params(input, ABS_MT_POSITION_X,
 			     0, tsdata->num_x * 64 - 1, 0, 0);
 	input_set_abs_params(input, ABS_MT_POSITION_Y,
 			     0, tsdata->num_y * 64 - 1, 0, 0);
 
 	if (!pdata)
-		touchscreen_parse_of_params(input);
+		touchscreen_parse_of_params(input, true);
 
-	error = input_mt_init_slots(input, MAX_SUPPORT_POINTS, 0);
+	error = input_mt_init_slots(input, MAX_SUPPORT_POINTS, INPUT_MT_DIRECT);
 	if (error) {
 		dev_err(&client->dev, "Unable to init MT slots.\n");
 		return error;
diff --git a/drivers/input/touchscreen/of_touchscreen.c b/drivers/input/touchscreen/of_touchscreen.c
index b82b520..806cd0a 100644
--- a/drivers/input/touchscreen/of_touchscreen.c
+++ b/drivers/input/touchscreen/of_touchscreen.c
@@ -14,14 +14,22 @@
 #include <linux/input/mt.h>
 #include <linux/input/touchscreen.h>
 
-static u32 of_get_optional_u32(struct device_node *np,
-			       const char *property)
+static bool touchscreen_get_prop_u32(struct device_node *np,
+				     const char *property,
+				     unsigned int default_value,
+				     unsigned int *value)
 {
-	u32 val = 0;
+	u32 val;
+	int error;
 
-	of_property_read_u32(np, property, &val);
+	error = of_property_read_u32(np, property, &val);
+	if (error) {
+		*value = default_value;
+		return false;
+	}
 
-	return val;
+	*value = val;
+	return true;
 }
 
 static void touchscreen_set_params(struct input_dev *dev,
@@ -54,34 +62,45 @@
  * input device accordingly. The function keeps previously setuped default
  * values if no value is specified via DT.
  */
-void touchscreen_parse_of_params(struct input_dev *dev)
+void touchscreen_parse_of_params(struct input_dev *dev, bool multitouch)
 {
 	struct device_node *np = dev->dev.parent->of_node;
-	u32 maximum, fuzz;
+	unsigned int axis;
+	unsigned int maximum, fuzz;
+	bool data_present;
 
 	input_alloc_absinfo(dev);
 	if (!dev->absinfo)
 		return;
 
-	maximum = of_get_optional_u32(np, "touchscreen-size-x");
-	fuzz = of_get_optional_u32(np, "touchscreen-fuzz-x");
-	if (maximum || fuzz) {
-		touchscreen_set_params(dev, ABS_X, maximum, fuzz);
-		touchscreen_set_params(dev, ABS_MT_POSITION_X, maximum, fuzz);
-	}
+	axis = multitouch ? ABS_MT_POSITION_X : ABS_X;
+	data_present = touchscreen_get_prop_u32(np, "touchscreen-size-x",
+						input_abs_get_max(dev, axis),
+						&maximum) |
+		       touchscreen_get_prop_u32(np, "touchscreen-fuzz-x",
+						input_abs_get_fuzz(dev, axis),
+						&fuzz);
+	if (data_present)
+		touchscreen_set_params(dev, axis, maximum, fuzz);
 
-	maximum = of_get_optional_u32(np, "touchscreen-size-y");
-	fuzz = of_get_optional_u32(np, "touchscreen-fuzz-y");
-	if (maximum || fuzz) {
-		touchscreen_set_params(dev, ABS_Y, maximum, fuzz);
-		touchscreen_set_params(dev, ABS_MT_POSITION_Y, maximum, fuzz);
-	}
+	axis = multitouch ? ABS_MT_POSITION_Y : ABS_Y;
+	data_present = touchscreen_get_prop_u32(np, "touchscreen-size-y",
+						input_abs_get_max(dev, axis),
+						&maximum) |
+		       touchscreen_get_prop_u32(np, "touchscreen-fuzz-y",
+						input_abs_get_fuzz(dev, axis),
+						&fuzz);
+	if (data_present)
+		touchscreen_set_params(dev, axis, maximum, fuzz);
 
-	maximum = of_get_optional_u32(np, "touchscreen-max-pressure");
-	fuzz = of_get_optional_u32(np, "touchscreen-fuzz-pressure");
-	if (maximum || fuzz) {
-		touchscreen_set_params(dev, ABS_PRESSURE, maximum, fuzz);
-		touchscreen_set_params(dev, ABS_MT_PRESSURE, maximum, fuzz);
-	}
+	axis = multitouch ? ABS_MT_PRESSURE : ABS_PRESSURE;
+	data_present = touchscreen_get_prop_u32(np, "touchscreen-max-pressure",
+						input_abs_get_max(dev, axis),
+						&maximum) |
+		       touchscreen_get_prop_u32(np, "touchscreen-fuzz-pressure",
+						input_abs_get_fuzz(dev, axis),
+						&fuzz);
+	if (data_present)
+		touchscreen_set_params(dev, axis, maximum, fuzz);
 }
 EXPORT_SYMBOL(touchscreen_parse_of_params);
diff --git a/drivers/input/touchscreen/tsc2005.c b/drivers/input/touchscreen/tsc2005.c
index 72657c5..d8c025b 100644
--- a/drivers/input/touchscreen/tsc2005.c
+++ b/drivers/input/touchscreen/tsc2005.c
@@ -709,7 +709,7 @@
 	input_set_abs_params(input_dev, ABS_PRESSURE, 0, max_p, fudge_p, 0);
 
 	if (np)
-		touchscreen_parse_of_params(input_dev);
+		touchscreen_parse_of_params(input_dev, false);
 
 	input_dev->open = tsc2005_open;
 	input_dev->close = tsc2005_close;
diff --git a/drivers/input/touchscreen/wdt87xx_i2c.c b/drivers/input/touchscreen/wdt87xx_i2c.c
new file mode 100644
index 0000000..fb92ae1
--- /dev/null
+++ b/drivers/input/touchscreen/wdt87xx_i2c.c
@@ -0,0 +1,1149 @@
+/*
+ * Weida HiTech WDT87xx TouchScreen I2C driver
+ *
+ * Copyright (c) 2015  Weida Hi-Tech Co., Ltd.
+ * HN Chen <hn.chen@weidahitech.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ */
+
+#include <linux/i2c.h>
+#include <linux/input.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/firmware.h>
+#include <linux/input/mt.h>
+#include <linux/acpi.h>
+#include <asm/unaligned.h>
+
+#define WDT87XX_NAME		"wdt87xx_i2c"
+#define WDT87XX_DRV_VER		"0.9.6"
+#define WDT87XX_FW_NAME		"wdt87xx_fw.bin"
+#define WDT87XX_CFG_NAME	"wdt87xx_cfg.bin"
+
+#define MODE_ACTIVE			0x01
+#define MODE_READY			0x02
+#define MODE_IDLE			0x03
+#define MODE_SLEEP			0x04
+#define MODE_STOP			0xFF
+
+#define WDT_MAX_FINGER			10
+#define WDT_RAW_BUF_COUNT		54
+#define WDT_V1_RAW_BUF_COUNT		74
+#define WDT_FIRMWARE_ID			0xa9e368f5
+
+#define PG_SIZE				0x1000
+#define MAX_RETRIES			3
+
+#define MAX_UNIT_AXIS			0x7FFF
+
+#define PKT_READ_SIZE			72
+#define PKT_WRITE_SIZE			80
+
+/* the finger definition of the report event */
+#define FINGER_EV_OFFSET_ID		0
+#define FINGER_EV_OFFSET_X		1
+#define FINGER_EV_OFFSET_Y		3
+#define FINGER_EV_SIZE			5
+
+#define FINGER_EV_V1_OFFSET_ID		0
+#define FINGER_EV_V1_OFFSET_W		1
+#define FINGER_EV_V1_OFFSET_P		2
+#define FINGER_EV_V1_OFFSET_X		3
+#define FINGER_EV_V1_OFFSET_Y		5
+#define FINGER_EV_V1_SIZE		7
+
+/* The definition of a report packet */
+#define TOUCH_PK_OFFSET_REPORT_ID	0
+#define TOUCH_PK_OFFSET_EVENT		1
+#define TOUCH_PK_OFFSET_SCAN_TIME	51
+#define TOUCH_PK_OFFSET_FNGR_NUM	53
+
+#define TOUCH_PK_V1_OFFSET_REPORT_ID	0
+#define TOUCH_PK_V1_OFFSET_EVENT	1
+#define TOUCH_PK_V1_OFFSET_SCAN_TIME	71
+#define TOUCH_PK_V1_OFFSET_FNGR_NUM	73
+
+/* The definition of the controller parameters */
+#define CTL_PARAM_OFFSET_FW_ID		0
+#define CTL_PARAM_OFFSET_PLAT_ID	2
+#define CTL_PARAM_OFFSET_XMLS_ID1	4
+#define CTL_PARAM_OFFSET_XMLS_ID2	6
+#define CTL_PARAM_OFFSET_PHY_CH_X	8
+#define CTL_PARAM_OFFSET_PHY_CH_Y	10
+#define CTL_PARAM_OFFSET_PHY_X0		12
+#define CTL_PARAM_OFFSET_PHY_X1		14
+#define CTL_PARAM_OFFSET_PHY_Y0		16
+#define CTL_PARAM_OFFSET_PHY_Y1		18
+#define CTL_PARAM_OFFSET_PHY_W		22
+#define CTL_PARAM_OFFSET_PHY_H		24
+#define CTL_PARAM_OFFSET_FACTOR		32
+
+/* Communication commands */
+#define PACKET_SIZE			56
+#define VND_REQ_READ			0x06
+#define VND_READ_DATA			0x07
+#define VND_REQ_WRITE			0x08
+
+#define VND_CMD_START			0x00
+#define VND_CMD_STOP			0x01
+#define VND_CMD_RESET			0x09
+
+#define VND_CMD_ERASE			0x1A
+
+#define VND_GET_CHECKSUM		0x66
+
+#define VND_SET_DATA			0x83
+#define VND_SET_COMMAND_DATA		0x84
+#define VND_SET_CHECKSUM_CALC		0x86
+#define VND_SET_CHECKSUM_LENGTH		0x87
+
+#define VND_CMD_SFLCK			0xFC
+#define VND_CMD_SFUNL			0xFD
+
+#define CMD_SFLCK_KEY			0xC39B
+#define CMD_SFUNL_KEY			0x95DA
+
+#define STRIDX_PLATFORM_ID		0x80
+#define STRIDX_PARAMETERS		0x81
+
+#define CMD_BUF_SIZE			8
+#define PKT_BUF_SIZE			64
+
+/* The definition of the command packet */
+#define CMD_REPORT_ID_OFFSET		0x0
+#define CMD_TYPE_OFFSET			0x1
+#define CMD_INDEX_OFFSET		0x2
+#define CMD_KEY_OFFSET			0x3
+#define CMD_LENGTH_OFFSET		0x4
+#define CMD_DATA_OFFSET			0x8
+
+/* The definition of firmware chunk tags */
+#define FOURCC_ID_RIFF			0x46464952
+#define FOURCC_ID_WHIF			0x46494857
+#define FOURCC_ID_FRMT			0x544D5246
+#define FOURCC_ID_FRWR			0x52575246
+#define FOURCC_ID_CNFG			0x47464E43
+
+#define CHUNK_ID_FRMT			FOURCC_ID_FRMT
+#define CHUNK_ID_FRWR			FOURCC_ID_FRWR
+#define CHUNK_ID_CNFG			FOURCC_ID_CNFG
+
+#define FW_FOURCC1_OFFSET		0
+#define FW_SIZE_OFFSET			4
+#define FW_FOURCC2_OFFSET		8
+#define FW_PAYLOAD_OFFSET		40
+
+#define FW_CHUNK_ID_OFFSET		0
+#define FW_CHUNK_SIZE_OFFSET		4
+#define FW_CHUNK_TGT_START_OFFSET	8
+#define FW_CHUNK_PAYLOAD_LEN_OFFSET	12
+#define FW_CHUNK_SRC_START_OFFSET	16
+#define FW_CHUNK_VERSION_OFFSET		20
+#define FW_CHUNK_ATTR_OFFSET		24
+#define FW_CHUNK_PAYLOAD_OFFSET		32
+
+/* Controller requires minimum 300us between commands */
+#define WDT_COMMAND_DELAY_MS		2
+#define WDT_FLASH_WRITE_DELAY_MS	4
+
+struct wdt87xx_sys_param {
+	u16	fw_id;
+	u16	plat_id;
+	u16	xmls_id1;
+	u16	xmls_id2;
+	u16	phy_ch_x;
+	u16	phy_ch_y;
+	u16	phy_w;
+	u16	phy_h;
+	u16	scaling_factor;
+	u32	max_x;
+	u32	max_y;
+};
+
+struct wdt87xx_data {
+	struct i2c_client		*client;
+	struct input_dev		*input;
+	/* Mutex for fw update to prevent concurrent access */
+	struct mutex			fw_mutex;
+	struct wdt87xx_sys_param	param;
+	u8				phys[32];
+};
+
+static int wdt87xx_i2c_xfer(struct i2c_client *client,
+			    void *txdata, size_t txlen,
+			    void *rxdata, size_t rxlen)
+{
+	struct i2c_msg msgs[] = {
+		{
+			.addr	= client->addr,
+			.flags	= 0,
+			.len	= txlen,
+			.buf	= txdata,
+		},
+		{
+			.addr	= client->addr,
+			.flags	= I2C_M_RD,
+			.len	= rxlen,
+			.buf	= rxdata,
+		},
+	};
+	int error;
+	int ret;
+
+	ret = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs));
+	if (ret != ARRAY_SIZE(msgs)) {
+		error = ret < 0 ? ret : -EIO;
+		dev_err(&client->dev, "%s: i2c transfer failed: %d\n",
+			__func__, error);
+		return error;
+	}
+
+	return 0;
+}
+
+static int wdt87xx_get_string(struct i2c_client *client, u8 str_idx,
+			      u8 *buf, size_t len)
+{
+	u8 tx_buf[] = { 0x22, 0x00, 0x13, 0x0E, str_idx, 0x23, 0x00 };
+	u8 rx_buf[PKT_WRITE_SIZE];
+	size_t rx_len = len + 2;
+	int error;
+
+	if (rx_len > sizeof(rx_buf))
+		return -EINVAL;
+
+	error = wdt87xx_i2c_xfer(client, tx_buf, sizeof(tx_buf),
+				 rx_buf, rx_len);
+	if (error) {
+		dev_err(&client->dev, "get string failed: %d\n", error);
+		return error;
+	}
+
+	if (rx_buf[1] != 0x03) {
+		dev_err(&client->dev, "unexpected response to get string: %d\n",
+			rx_buf[1]);
+		return -EINVAL;
+	}
+
+	rx_len = min_t(size_t, len, rx_buf[0]);
+	memcpy(buf, &rx_buf[2], rx_len);
+
+	mdelay(WDT_COMMAND_DELAY_MS);
+
+	return 0;
+}
+
+static int wdt87xx_get_feature(struct i2c_client *client,
+			       u8 *buf, size_t buf_size)
+{
+	u8 tx_buf[8];
+	u8 rx_buf[PKT_WRITE_SIZE];
+	size_t tx_len = 0;
+	size_t rx_len = buf_size + 2;
+	int error;
+
+	if (rx_len > sizeof(rx_buf))
+		return -EINVAL;
+
+	/* Get feature command packet */
+	tx_buf[tx_len++] = 0x22;
+	tx_buf[tx_len++] = 0x00;
+	if (buf[CMD_REPORT_ID_OFFSET] > 0xF) {
+		tx_buf[tx_len++] = 0x30;
+		tx_buf[tx_len++] = 0x02;
+		tx_buf[tx_len++] = buf[CMD_REPORT_ID_OFFSET];
+	} else {
+		tx_buf[tx_len++] = 0x30 | buf[CMD_REPORT_ID_OFFSET];
+		tx_buf[tx_len++] = 0x02;
+	}
+	tx_buf[tx_len++] = 0x23;
+	tx_buf[tx_len++] = 0x00;
+
+	error = wdt87xx_i2c_xfer(client, tx_buf, tx_len, rx_buf, rx_len);
+	if (error) {
+		dev_err(&client->dev, "get feature failed: %d\n", error);
+		return error;
+	}
+
+	rx_len = min_t(size_t, buf_size, get_unaligned_le16(rx_buf));
+	memcpy(buf, &rx_buf[2], rx_len);
+
+	mdelay(WDT_COMMAND_DELAY_MS);
+
+	return 0;
+}
+
+static int wdt87xx_set_feature(struct i2c_client *client,
+			       const u8 *buf, size_t buf_size)
+{
+	u8 tx_buf[PKT_WRITE_SIZE];
+	int tx_len = 0;
+	int error;
+
+	/* Set feature command packet */
+	tx_buf[tx_len++] = 0x22;
+	tx_buf[tx_len++] = 0x00;
+	if (buf[CMD_REPORT_ID_OFFSET] > 0xF) {
+		tx_buf[tx_len++] = 0x30;
+		tx_buf[tx_len++] = 0x03;
+		tx_buf[tx_len++] = buf[CMD_REPORT_ID_OFFSET];
+	} else {
+		tx_buf[tx_len++] = 0x30 | buf[CMD_REPORT_ID_OFFSET];
+		tx_buf[tx_len++] = 0x03;
+	}
+	tx_buf[tx_len++] = 0x23;
+	tx_buf[tx_len++] = 0x00;
+	tx_buf[tx_len++] = (buf_size & 0xFF);
+	tx_buf[tx_len++] = ((buf_size & 0xFF00) >> 8);
+
+	if (tx_len + buf_size > sizeof(tx_buf))
+		return -EINVAL;
+
+	memcpy(&tx_buf[tx_len], buf, buf_size);
+	tx_len += buf_size;
+
+	error = i2c_master_send(client, tx_buf, tx_len);
+	if (error < 0) {
+		dev_err(&client->dev, "set feature failed: %d\n", error);
+		return error;
+	}
+
+	mdelay(WDT_COMMAND_DELAY_MS);
+
+	return 0;
+}
+
+static int wdt87xx_send_command(struct i2c_client *client, int cmd, int value)
+{
+	u8 cmd_buf[CMD_BUF_SIZE];
+
+	/* Set the command packet */
+	cmd_buf[CMD_REPORT_ID_OFFSET] = VND_REQ_WRITE;
+	cmd_buf[CMD_TYPE_OFFSET] = VND_SET_COMMAND_DATA;
+	put_unaligned_le16((u16)cmd, &cmd_buf[CMD_INDEX_OFFSET]);
+
+	switch (cmd) {
+	case VND_CMD_START:
+	case VND_CMD_STOP:
+	case VND_CMD_RESET:
+		/* Mode selector */
+		put_unaligned_le32((value & 0xFF), &cmd_buf[CMD_LENGTH_OFFSET]);
+		break;
+
+	case VND_CMD_SFLCK:
+		put_unaligned_le16(CMD_SFLCK_KEY, &cmd_buf[CMD_KEY_OFFSET]);
+		break;
+
+	case VND_CMD_SFUNL:
+		put_unaligned_le16(CMD_SFUNL_KEY, &cmd_buf[CMD_KEY_OFFSET]);
+		break;
+
+	case VND_CMD_ERASE:
+	case VND_SET_CHECKSUM_CALC:
+	case VND_SET_CHECKSUM_LENGTH:
+		put_unaligned_le32(value, &cmd_buf[CMD_KEY_OFFSET]);
+		break;
+
+	default:
+		cmd_buf[CMD_REPORT_ID_OFFSET] = 0;
+		dev_err(&client->dev, "Invalid command: %d\n", cmd);
+		return -EINVAL;
+	}
+
+	return wdt87xx_set_feature(client, cmd_buf, sizeof(cmd_buf));
+}
+
+static int wdt87xx_sw_reset(struct i2c_client *client)
+{
+	int error;
+
+	dev_dbg(&client->dev, "resetting device now\n");
+
+	error = wdt87xx_send_command(client, VND_CMD_RESET, 0);
+	if (error) {
+		dev_err(&client->dev, "reset failed\n");
+		return error;
+	}
+
+	/* Wait the device to be ready */
+	msleep(200);
+
+	return 0;
+}
+
+static const void *wdt87xx_get_fw_chunk(const struct firmware *fw, u32 id)
+{
+	size_t pos = FW_PAYLOAD_OFFSET;
+	u32 chunk_id, chunk_size;
+
+	while (pos < fw->size) {
+		chunk_id = get_unaligned_le32(fw->data +
+					      pos + FW_CHUNK_ID_OFFSET);
+		if (chunk_id == id)
+			return fw->data + pos;
+
+		chunk_size = get_unaligned_le32(fw->data +
+						pos + FW_CHUNK_SIZE_OFFSET);
+		pos += chunk_size + 2 * sizeof(u32); /* chunk ID + size */
+	}
+
+	return NULL;
+}
+
+static int wdt87xx_get_sysparam(struct i2c_client *client,
+				struct wdt87xx_sys_param *param)
+{
+	u8 buf[PKT_READ_SIZE];
+	int error;
+
+	error = wdt87xx_get_string(client, STRIDX_PARAMETERS, buf, 34);
+	if (error) {
+		dev_err(&client->dev, "failed to get parameters\n");
+		return error;
+	}
+
+	param->xmls_id1 = get_unaligned_le16(buf + CTL_PARAM_OFFSET_XMLS_ID1);
+	param->xmls_id2 = get_unaligned_le16(buf + CTL_PARAM_OFFSET_XMLS_ID2);
+	param->phy_ch_x = get_unaligned_le16(buf + CTL_PARAM_OFFSET_PHY_CH_X);
+	param->phy_ch_y = get_unaligned_le16(buf + CTL_PARAM_OFFSET_PHY_CH_Y);
+	param->phy_w = get_unaligned_le16(buf + CTL_PARAM_OFFSET_PHY_W) / 10;
+	param->phy_h = get_unaligned_le16(buf + CTL_PARAM_OFFSET_PHY_H) / 10;
+
+	/* Get the scaling factor of pixel to logical coordinate */
+	param->scaling_factor =
+			get_unaligned_le16(buf + CTL_PARAM_OFFSET_FACTOR);
+
+	param->max_x = MAX_UNIT_AXIS;
+	param->max_y = DIV_ROUND_CLOSEST(MAX_UNIT_AXIS * param->phy_h,
+					 param->phy_w);
+
+	error = wdt87xx_get_string(client, STRIDX_PLATFORM_ID, buf, 8);
+	if (error) {
+		dev_err(&client->dev, "failed to get platform id\n");
+		return error;
+	}
+
+	param->plat_id = buf[1];
+
+	buf[0] = 0xf2;
+	error = wdt87xx_get_feature(client, buf, 16);
+	if (error) {
+		dev_err(&client->dev, "failed to get firmware id\n");
+		return error;
+	}
+
+	if (buf[0] != 0xf2) {
+		dev_err(&client->dev, "wrong id of fw response: 0x%x\n",
+			buf[0]);
+		return -EINVAL;
+	}
+
+	param->fw_id = get_unaligned_le16(&buf[1]);
+
+	dev_info(&client->dev,
+		 "fw_id: 0x%x, plat_id: 0x%x, xml_id1: %04x, xml_id2: %04x\n",
+		 param->fw_id, param->plat_id,
+		 param->xmls_id1, param->xmls_id2);
+
+	return 0;
+}
+
+static int wdt87xx_validate_firmware(struct wdt87xx_data *wdt,
+				     const struct firmware *fw)
+{
+	const void *fw_chunk;
+	u32 data1, data2;
+	u32 size;
+	u8 fw_chip_id;
+	u8 chip_id;
+
+	data1 = get_unaligned_le32(fw->data + FW_FOURCC1_OFFSET);
+	data2 = get_unaligned_le32(fw->data + FW_FOURCC2_OFFSET);
+	if (data1 != FOURCC_ID_RIFF || data2 != FOURCC_ID_WHIF) {
+		dev_err(&wdt->client->dev, "check fw tag failed\n");
+		return -EINVAL;
+	}
+
+	size = get_unaligned_le32(fw->data + FW_SIZE_OFFSET);
+	if (size != fw->size) {
+		dev_err(&wdt->client->dev,
+			"fw size mismatch: expected %d, actual %zu\n",
+			size, fw->size);
+		return -EINVAL;
+	}
+
+	/*
+	 * Get the chip_id from the firmware. Make sure that it is the
+	 * right controller to do the firmware and config update.
+	 */
+	fw_chunk = wdt87xx_get_fw_chunk(fw, CHUNK_ID_FRWR);
+	if (!fw_chunk) {
+		dev_err(&wdt->client->dev,
+			"unable to locate firmware chunk\n");
+		return -EINVAL;
+	}
+
+	fw_chip_id = (get_unaligned_le32(fw_chunk +
+					 FW_CHUNK_VERSION_OFFSET) >> 12) & 0xF;
+	chip_id = (wdt->param.fw_id >> 12) & 0xF;
+
+	if (fw_chip_id != chip_id) {
+		dev_err(&wdt->client->dev,
+			"fw version mismatch: fw %d vs. chip %d\n",
+			fw_chip_id, chip_id);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static int wdt87xx_validate_fw_chunk(const void *data, int id)
+{
+	if (id == CHUNK_ID_FRWR) {
+		u32 fw_id;
+
+		fw_id = get_unaligned_le32(data + FW_CHUNK_PAYLOAD_OFFSET);
+		if (fw_id != WDT_FIRMWARE_ID)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int wdt87xx_write_data(struct i2c_client *client, const char *data,
+			      u32 address, int length)
+{
+	u16 packet_size;
+	int count = 0;
+	int error;
+	u8 pkt_buf[PKT_BUF_SIZE];
+
+	/* Address and length should be 4 bytes aligned */
+	if ((address & 0x3) != 0 || (length & 0x3) != 0) {
+		dev_err(&client->dev,
+			"addr & len must be 4 bytes aligned %x, %x\n",
+			address, length);
+		return -EINVAL;
+	}
+
+	while (length) {
+		packet_size = min(length, PACKET_SIZE);
+
+		pkt_buf[CMD_REPORT_ID_OFFSET] = VND_REQ_WRITE;
+		pkt_buf[CMD_TYPE_OFFSET] = VND_SET_DATA;
+		put_unaligned_le16(packet_size, &pkt_buf[CMD_INDEX_OFFSET]);
+		put_unaligned_le32(address, &pkt_buf[CMD_LENGTH_OFFSET]);
+		memcpy(&pkt_buf[CMD_DATA_OFFSET], data, packet_size);
+
+		error = wdt87xx_set_feature(client, pkt_buf, sizeof(pkt_buf));
+		if (error)
+			return error;
+
+		length -= packet_size;
+		data += packet_size;
+		address += packet_size;
+
+		/* Wait for the controller to finish the write */
+		mdelay(WDT_FLASH_WRITE_DELAY_MS);
+
+		if ((++count % 32) == 0) {
+			/* Delay for fw to clear watch dog */
+			msleep(20);
+		}
+	}
+
+	return 0;
+}
+
+static u16 misr(u16 cur_value, u8 new_value)
+{
+	u32 a, b;
+	u32 bit0;
+	u32 y;
+
+	a = cur_value;
+	b = new_value;
+	bit0 = a ^ (b & 1);
+	bit0 ^= a >> 1;
+	bit0 ^= a >> 2;
+	bit0 ^= a >> 4;
+	bit0 ^= a >> 5;
+	bit0 ^= a >> 7;
+	bit0 ^= a >> 11;
+	bit0 ^= a >> 15;
+	y = (a << 1) ^ b;
+	y = (y & ~1) | (bit0 & 1);
+
+	return (u16)y;
+}
+
+static u16 wdt87xx_calculate_checksum(const u8 *data, size_t length)
+{
+	u16 checksum = 0;
+	size_t i;
+
+	for (i = 0; i < length; i++)
+		checksum = misr(checksum, data[i]);
+
+	return checksum;
+}
+
+static int wdt87xx_get_checksum(struct i2c_client *client, u16 *checksum,
+				u32 address, int length)
+{
+	int error;
+	int time_delay;
+	u8 pkt_buf[PKT_BUF_SIZE];
+	u8 cmd_buf[CMD_BUF_SIZE];
+
+	error = wdt87xx_send_command(client, VND_SET_CHECKSUM_LENGTH, length);
+	if (error) {
+		dev_err(&client->dev, "failed to set checksum length\n");
+		return error;
+	}
+
+	error = wdt87xx_send_command(client, VND_SET_CHECKSUM_CALC, address);
+	if (error) {
+		dev_err(&client->dev, "failed to set checksum address\n");
+		return error;
+	}
+
+	/* Wait the operation to complete */
+	time_delay = DIV_ROUND_UP(length, 1024);
+	msleep(time_delay * 30);
+
+	memset(cmd_buf, 0, sizeof(cmd_buf));
+	cmd_buf[CMD_REPORT_ID_OFFSET] = VND_REQ_READ;
+	cmd_buf[CMD_TYPE_OFFSET] = VND_GET_CHECKSUM;
+	error = wdt87xx_set_feature(client, cmd_buf, sizeof(cmd_buf));
+	if (error) {
+		dev_err(&client->dev, "failed to request checksum\n");
+		return error;
+	}
+
+	memset(pkt_buf, 0, sizeof(pkt_buf));
+	pkt_buf[CMD_REPORT_ID_OFFSET] = VND_READ_DATA;
+	error = wdt87xx_get_feature(client, pkt_buf, sizeof(pkt_buf));
+	if (error) {
+		dev_err(&client->dev, "failed to read checksum\n");
+		return error;
+	}
+
+	*checksum = get_unaligned_le16(&pkt_buf[CMD_DATA_OFFSET]);
+	return 0;
+}
+
+static int wdt87xx_write_firmware(struct i2c_client *client, const void *chunk)
+{
+	u32 start_addr = get_unaligned_le32(chunk + FW_CHUNK_TGT_START_OFFSET);
+	u32 size = get_unaligned_le32(chunk + FW_CHUNK_PAYLOAD_LEN_OFFSET);
+	const void *data = chunk + FW_CHUNK_PAYLOAD_OFFSET;
+	int error;
+	int err1;
+	int page_size;
+	int retry = 0;
+	u16 device_checksum, firmware_checksum;
+
+	dev_dbg(&client->dev, "start 4k page program\n");
+
+	error = wdt87xx_send_command(client, VND_CMD_STOP, MODE_STOP);
+	if (error) {
+		dev_err(&client->dev, "stop report mode failed\n");
+		return error;
+	}
+
+	error = wdt87xx_send_command(client, VND_CMD_SFUNL, 0);
+	if (error) {
+		dev_err(&client->dev, "unlock failed\n");
+		goto out_enable_reporting;
+	}
+
+	mdelay(10);
+
+	while (size) {
+		dev_dbg(&client->dev, "%s: %x, %x\n", __func__,
+			start_addr, size);
+
+		page_size = min_t(u32, size, PG_SIZE);
+		size -= page_size;
+
+		for (retry = 0; retry < MAX_RETRIES; retry++) {
+			error = wdt87xx_send_command(client, VND_CMD_ERASE,
+						     start_addr);
+			if (error) {
+				dev_err(&client->dev,
+					"erase failed at %#08x\n", start_addr);
+				break;
+			}
+
+			msleep(50);
+
+			error = wdt87xx_write_data(client, data, start_addr,
+						   page_size);
+			if (error) {
+				dev_err(&client->dev,
+					"write failed at %#08x (%d bytes)\n",
+					start_addr, page_size);
+				break;
+			}
+
+			error = wdt87xx_get_checksum(client, &device_checksum,
+						     start_addr, page_size);
+			if (error) {
+				dev_err(&client->dev,
+					"failed to retrieve checksum for %#08x (len: %d)\n",
+					start_addr, page_size);
+				break;
+			}
+
+			firmware_checksum =
+				wdt87xx_calculate_checksum(data, page_size);
+
+			if (device_checksum == firmware_checksum)
+				break;
+
+			dev_err(&client->dev,
+				"checksum fail: %d vs %d, retry %d\n",
+				device_checksum, firmware_checksum, retry);
+		}
+
+		if (retry == MAX_RETRIES) {
+			dev_err(&client->dev, "page write failed\n");
+			error = -EIO;
+			goto out_lock_device;
+		}
+
+		start_addr = start_addr + page_size;
+		data = data + page_size;
+	}
+
+out_lock_device:
+	err1 = wdt87xx_send_command(client, VND_CMD_SFLCK, 0);
+	if (err1)
+		dev_err(&client->dev, "lock failed\n");
+
+	mdelay(10);
+
+out_enable_reporting:
+	err1 = wdt87xx_send_command(client, VND_CMD_START, 0);
+	if (err1)
+		dev_err(&client->dev, "start to report failed\n");
+
+	return error ? error : err1;
+}
+
+static int wdt87xx_load_chunk(struct i2c_client *client,
+			      const struct firmware *fw, u32 ck_id)
+{
+	const void *chunk;
+	int error;
+
+	chunk = wdt87xx_get_fw_chunk(fw, ck_id);
+	if (!chunk) {
+		dev_err(&client->dev, "unable to locate chunk (type %d)\n",
+			ck_id);
+		return -EINVAL;
+	}
+
+	error = wdt87xx_validate_fw_chunk(chunk, ck_id);
+	if (error) {
+		dev_err(&client->dev, "invalid chunk (type %d): %d\n",
+			ck_id, error);
+		return error;
+	}
+
+	error = wdt87xx_write_firmware(client, chunk);
+	if (error) {
+		dev_err(&client->dev,
+			"failed to write fw chunk (type %d): %d\n",
+			ck_id, error);
+		return error;
+	}
+
+	return 0;
+}
+
+static int wdt87xx_do_update_firmware(struct i2c_client *client,
+				      const struct firmware *fw,
+				      unsigned int chunk_id)
+{
+	struct wdt87xx_data *wdt = i2c_get_clientdata(client);
+	int error;
+
+	error = wdt87xx_validate_firmware(wdt, fw);
+	if (error)
+		return error;
+
+	error = mutex_lock_interruptible(&wdt->fw_mutex);
+	if (error)
+		return error;
+
+	disable_irq(client->irq);
+
+	error = wdt87xx_load_chunk(client, fw, chunk_id);
+	if (error) {
+		dev_err(&client->dev,
+			"firmware load failed (type: %d): %d\n",
+			chunk_id, error);
+		goto out;
+	}
+
+	error = wdt87xx_sw_reset(client);
+	if (error) {
+		dev_err(&client->dev, "soft reset failed: %d\n", error);
+		goto out;
+	}
+
+	/* Refresh the parameters */
+	error = wdt87xx_get_sysparam(client, &wdt->param);
+	if (error)
+		dev_err(&client->dev,
+			"failed to refresh system paramaters: %d\n", error);
+out:
+	enable_irq(client->irq);
+	mutex_unlock(&wdt->fw_mutex);
+
+	return error ? error : 0;
+}
+
+static int wdt87xx_update_firmware(struct device *dev,
+				   const char *fw_name, unsigned int chunk_id)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	const struct firmware *fw;
+	int error;
+
+	error = request_firmware(&fw, fw_name, dev);
+	if (error) {
+		dev_err(&client->dev, "unable to retrieve firmware %s: %d\n",
+			fw_name, error);
+		return error;
+	}
+
+	error = wdt87xx_do_update_firmware(client, fw, chunk_id);
+
+	release_firmware(fw);
+
+	return error ? error : 0;
+}
+
+static ssize_t config_csum_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct wdt87xx_data *wdt = i2c_get_clientdata(client);
+	u32 cfg_csum;
+
+	cfg_csum = wdt->param.xmls_id1;
+	cfg_csum = (cfg_csum << 16) | wdt->param.xmls_id2;
+
+	return scnprintf(buf, PAGE_SIZE, "%x\n", cfg_csum);
+}
+
+static ssize_t fw_version_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct wdt87xx_data *wdt = i2c_get_clientdata(client);
+
+	return scnprintf(buf, PAGE_SIZE, "%x\n", wdt->param.fw_id);
+}
+
+static ssize_t plat_id_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct wdt87xx_data *wdt = i2c_get_clientdata(client);
+
+	return scnprintf(buf, PAGE_SIZE, "%x\n", wdt->param.plat_id);
+}
+
+static ssize_t update_config_store(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf, size_t count)
+{
+	int error;
+
+	error = wdt87xx_update_firmware(dev, WDT87XX_CFG_NAME, CHUNK_ID_CNFG);
+
+	return error ? error : count;
+}
+
+static ssize_t update_fw_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t count)
+{
+	int error;
+
+	error = wdt87xx_update_firmware(dev, WDT87XX_FW_NAME, CHUNK_ID_FRWR);
+
+	return error ? error : count;
+}
+
+static DEVICE_ATTR_RO(config_csum);
+static DEVICE_ATTR_RO(fw_version);
+static DEVICE_ATTR_RO(plat_id);
+static DEVICE_ATTR_WO(update_config);
+static DEVICE_ATTR_WO(update_fw);
+
+static struct attribute *wdt87xx_attrs[] = {
+	&dev_attr_config_csum.attr,
+	&dev_attr_fw_version.attr,
+	&dev_attr_plat_id.attr,
+	&dev_attr_update_config.attr,
+	&dev_attr_update_fw.attr,
+	NULL
+};
+
+static const struct attribute_group wdt87xx_attr_group = {
+	.attrs = wdt87xx_attrs,
+};
+
+static void wdt87xx_report_contact(struct input_dev *input,
+				   struct wdt87xx_sys_param *param,
+				   u8 *buf)
+{
+	int finger_id;
+	u32 x, y, w;
+	u8 p;
+
+	finger_id = (buf[FINGER_EV_V1_OFFSET_ID] >> 3) - 1;
+	if (finger_id < 0)
+		return;
+
+	/* Check if this is an active contact */
+	if (!(buf[FINGER_EV_V1_OFFSET_ID] & 0x1))
+		return;
+
+	w = buf[FINGER_EV_V1_OFFSET_W];
+	w *= param->scaling_factor;
+
+	p = buf[FINGER_EV_V1_OFFSET_P];
+
+	x = get_unaligned_le16(buf + FINGER_EV_V1_OFFSET_X);
+
+	y = get_unaligned_le16(buf + FINGER_EV_V1_OFFSET_Y);
+	y = DIV_ROUND_CLOSEST(y * param->phy_h, param->phy_w);
+
+	/* Refuse incorrect coordinates */
+	if (x > param->max_x || y > param->max_y)
+		return;
+
+	dev_dbg(input->dev.parent, "tip on (%d), x(%d), y(%d)\n",
+		finger_id, x, y);
+
+	input_mt_slot(input, finger_id);
+	input_mt_report_slot_state(input, MT_TOOL_FINGER, 1);
+	input_report_abs(input, ABS_MT_TOUCH_MAJOR, w);
+	input_report_abs(input, ABS_MT_PRESSURE, p);
+	input_report_abs(input, ABS_MT_POSITION_X, x);
+	input_report_abs(input, ABS_MT_POSITION_Y, y);
+}
+
+static irqreturn_t wdt87xx_ts_interrupt(int irq, void *dev_id)
+{
+	struct wdt87xx_data *wdt = dev_id;
+	struct i2c_client *client = wdt->client;
+	int i, fingers;
+	int error;
+	u8 raw_buf[WDT_V1_RAW_BUF_COUNT] = {0};
+
+	error = i2c_master_recv(client, raw_buf, WDT_V1_RAW_BUF_COUNT);
+	if (error < 0) {
+		dev_err(&client->dev, "read v1 raw data failed: %d\n", error);
+		goto irq_exit;
+	}
+
+	fingers = raw_buf[TOUCH_PK_V1_OFFSET_FNGR_NUM];
+	if (!fingers)
+		goto irq_exit;
+
+	for (i = 0; i < WDT_MAX_FINGER; i++)
+		wdt87xx_report_contact(wdt->input,
+				       &wdt->param,
+				       &raw_buf[TOUCH_PK_V1_OFFSET_EVENT +
+						i * FINGER_EV_V1_SIZE]);
+
+	input_mt_sync_frame(wdt->input);
+	input_sync(wdt->input);
+
+irq_exit:
+	return IRQ_HANDLED;
+}
+
+static int wdt87xx_ts_create_input_device(struct wdt87xx_data *wdt)
+{
+	struct device *dev = &wdt->client->dev;
+	struct input_dev *input;
+	unsigned int res = DIV_ROUND_CLOSEST(MAX_UNIT_AXIS, wdt->param.phy_w);
+	int error;
+
+	input = devm_input_allocate_device(dev);
+	if (!input) {
+		dev_err(dev, "failed to allocate input device\n");
+		return -ENOMEM;
+	}
+	wdt->input = input;
+
+	input->name = "WDT87xx Touchscreen";
+	input->id.bustype = BUS_I2C;
+	input->phys = wdt->phys;
+
+	input_set_abs_params(input, ABS_MT_POSITION_X, 0,
+			     wdt->param.max_x, 0, 0);
+	input_set_abs_params(input, ABS_MT_POSITION_Y, 0,
+			     wdt->param.max_y, 0, 0);
+	input_abs_set_res(input, ABS_MT_POSITION_X, res);
+	input_abs_set_res(input, ABS_MT_POSITION_Y, res);
+
+	input_set_abs_params(input, ABS_MT_TOUCH_MAJOR,
+			     0, wdt->param.max_x, 0, 0);
+	input_set_abs_params(input, ABS_MT_PRESSURE, 0, 0xFF, 0, 0);
+
+	input_mt_init_slots(input, WDT_MAX_FINGER,
+			    INPUT_MT_DIRECT | INPUT_MT_DROP_UNUSED);
+
+	error = input_register_device(input);
+	if (error) {
+		dev_err(dev, "failed to register input device: %d\n", error);
+		return error;
+	}
+
+	return 0;
+}
+
+static int wdt87xx_ts_probe(struct i2c_client *client,
+			    const struct i2c_device_id *id)
+{
+	struct wdt87xx_data *wdt;
+	int error;
+
+	dev_dbg(&client->dev, "adapter=%d, client irq: %d\n",
+		client->adapter->nr, client->irq);
+
+	/* Check if the I2C function is ok in this adaptor */
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C))
+		return -ENXIO;
+
+	wdt = devm_kzalloc(&client->dev, sizeof(*wdt), GFP_KERNEL);
+	if (!wdt)
+		return -ENOMEM;
+
+	wdt->client = client;
+	mutex_init(&wdt->fw_mutex);
+	i2c_set_clientdata(client, wdt);
+
+	snprintf(wdt->phys, sizeof(wdt->phys), "i2c-%u-%04x/input0",
+		 client->adapter->nr, client->addr);
+
+	error = wdt87xx_get_sysparam(client, &wdt->param);
+	if (error)
+		return error;
+
+	error = wdt87xx_ts_create_input_device(wdt);
+	if (error)
+		return error;
+
+	error = devm_request_threaded_irq(&client->dev, client->irq,
+					  NULL, wdt87xx_ts_interrupt,
+					  IRQF_ONESHOT,
+					  client->name, wdt);
+	if (error) {
+		dev_err(&client->dev, "request irq failed: %d\n", error);
+		return error;
+	}
+
+	error = sysfs_create_group(&client->dev.kobj, &wdt87xx_attr_group);
+	if (error) {
+		dev_err(&client->dev, "create sysfs failed: %d\n", error);
+		return error;
+	}
+
+	return 0;
+}
+
+static int wdt87xx_ts_remove(struct i2c_client *client)
+{
+	sysfs_remove_group(&client->dev.kobj, &wdt87xx_attr_group);
+
+	return 0;
+}
+
+static int __maybe_unused wdt87xx_suspend(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	int error;
+
+	disable_irq(client->irq);
+
+	error = wdt87xx_send_command(client, VND_CMD_STOP, MODE_IDLE);
+	if (error) {
+		enable_irq(client->irq);
+		dev_err(&client->dev,
+			"failed to stop device when suspending: %d\n",
+			error);
+		return error;
+	}
+
+	return 0;
+}
+
+static int __maybe_unused wdt87xx_resume(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	int error;
+
+	/*
+	 * The chip may have been reset while system is resuming,
+	 * give it some time to settle.
+	 */
+	mdelay(100);
+
+	error = wdt87xx_send_command(client, VND_CMD_START, 0);
+	if (error)
+		dev_err(&client->dev,
+			"failed to start device when resuming: %d\n",
+			error);
+
+	enable_irq(client->irq);
+
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(wdt87xx_pm_ops, wdt87xx_suspend, wdt87xx_resume);
+
+static const struct i2c_device_id wdt87xx_dev_id[] = {
+	{ WDT87XX_NAME, 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, wdt87xx_dev_id);
+
+static const struct acpi_device_id wdt87xx_acpi_id[] = {
+	{ "WDHT0001", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, wdt87xx_acpi_id);
+
+static struct i2c_driver wdt87xx_driver = {
+	.probe		= wdt87xx_ts_probe,
+	.remove		= wdt87xx_ts_remove,
+	.id_table	= wdt87xx_dev_id,
+	.driver	= {
+		.name	= WDT87XX_NAME,
+		.pm     = &wdt87xx_pm_ops,
+		.acpi_match_table = ACPI_PTR(wdt87xx_acpi_id),
+	},
+};
+module_i2c_driver(wdt87xx_driver);
+
+MODULE_AUTHOR("HN Chen <hn.chen@weidahitech.com>");
+MODULE_DESCRIPTION("WeidaHiTech WDT87XX Touchscreen driver");
+MODULE_VERSION(WDT87XX_DRV_VER);
+MODULE_LICENSE("GPL");
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index d3e5e9a..a57e9b7 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -117,6 +117,7 @@
 
 static void update_domain(struct protection_domain *domain);
 static int alloc_passthrough_domain(void);
+static int protection_domain_init(struct protection_domain *domain);
 
 /****************************************************************************
  *
@@ -1881,12 +1882,9 @@
 	if (!dma_dom)
 		return NULL;
 
-	spin_lock_init(&dma_dom->domain.lock);
-
-	dma_dom->domain.id = domain_id_alloc();
-	if (dma_dom->domain.id == 0)
+	if (protection_domain_init(&dma_dom->domain))
 		goto free_dma_dom;
-	INIT_LIST_HEAD(&dma_dom->domain.dev_list);
+
 	dma_dom->domain.mode = PAGE_MODE_2_LEVEL;
 	dma_dom->domain.pt_root = (void *)get_zeroed_page(GFP_KERNEL);
 	dma_dom->domain.flags = PD_DMA_OPS_MASK;
@@ -2916,6 +2914,18 @@
 	kfree(domain);
 }
 
+static int protection_domain_init(struct protection_domain *domain)
+{
+	spin_lock_init(&domain->lock);
+	mutex_init(&domain->api_lock);
+	domain->id = domain_id_alloc();
+	if (!domain->id)
+		return -ENOMEM;
+	INIT_LIST_HEAD(&domain->dev_list);
+
+	return 0;
+}
+
 static struct protection_domain *protection_domain_alloc(void)
 {
 	struct protection_domain *domain;
@@ -2924,12 +2934,8 @@
 	if (!domain)
 		return NULL;
 
-	spin_lock_init(&domain->lock);
-	mutex_init(&domain->api_lock);
-	domain->id = domain_id_alloc();
-	if (!domain->id)
+	if (protection_domain_init(domain))
 		goto out_err;
-	INIT_LIST_HEAD(&domain->dev_list);
 
 	add_domain_to_list(domain);
 
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index f141301..8e9ec81 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -1389,8 +1389,7 @@
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 
-	if (smmu_domain->pgtbl_ops)
-		free_io_pgtable_ops(smmu_domain->pgtbl_ops);
+	free_io_pgtable_ops(smmu_domain->pgtbl_ops);
 
 	/* Free the CD and ASID, if we allocated them */
 	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index dce041b..4cd0c29 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -1566,7 +1566,7 @@
 		return -ENODEV;
 	}
 
-	if ((id & ID0_S1TS) && ((smmu->version == 1) || (id & ID0_ATOSNS))) {
+	if ((id & ID0_S1TS) && ((smmu->version == 1) || !(id & ID0_ATOSNS))) {
 		smmu->features |= ARM_SMMU_FEAT_TRANS_OPS;
 		dev_notice(smmu->dev, "\taddress translation ops\n");
 	}
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 49e7542..f286090 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -847,13 +847,24 @@
 {
 	struct iommu_callback_data *cb = data;
 	const struct iommu_ops *ops = cb->ops;
+	int ret;
 
 	if (!ops->add_device)
 		return 0;
 
 	WARN_ON(dev->iommu_group);
 
-	return ops->add_device(dev);
+	ret = ops->add_device(dev);
+
+	/*
+	 * We ignore -ENODEV errors for now, as they just mean that the
+	 * device is not translated by an IOMMU. We still care about
+	 * other errors and fail to initialize when they happen.
+	 */
+	if (ret == -ENODEV)
+		ret = 0;
+
+	return ret;
 }
 
 static int remove_iommu_group(struct device *dev, void *data)
diff --git a/drivers/irqchip/irqchip.h b/drivers/irqchip/irqchip.h
index 0f6486d..0f67ae32 100644
--- a/drivers/irqchip/irqchip.h
+++ b/drivers/irqchip/irqchip.h
@@ -8,21 +8,4 @@
  * warranty of any kind, whether express or implied.
  */
 
-#ifndef _IRQCHIP_H
-#define _IRQCHIP_H
-
-#include <linux/of.h>
-
-/*
- * This macro must be used by the different irqchip drivers to declare
- * the association between their DT compatible string and their
- * initialization function.
- *
- * @name: name that must be unique accross all IRQCHIP_DECLARE of the
- * same file.
- * @compstr: compatible string of the irqchip driver
- * @fn: initialization function
- */
-#define IRQCHIP_DECLARE(name, compat, fn) OF_DECLARE_2(irqchip, name, compat, fn)
-
-#endif
+#include <linux/irqchip.h>
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 4191614..9ad35f7 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -39,6 +39,32 @@
 	  This option enables support for on-chip LED drivers found on Marvell
 	  Semiconductor 88PM8606 PMIC.
 
+config LEDS_AAT1290
+	tristate "LED support for the AAT1290"
+	depends on LEDS_CLASS_FLASH
+	depends on V4L2_FLASH_LED_CLASS || !V4L2_FLASH_LED_CLASS
+	depends on GPIOLIB
+	depends on OF
+	depends on PINCTRL
+	help
+	 This option enables support for the LEDs on the AAT1290.
+
+config LEDS_BCM6328
+	tristate "LED Support for Broadcom BCM6328"
+	depends on LEDS_CLASS
+	depends on OF
+	help
+	  This option enables support for LEDs connected to the BCM6328
+	  LED HW controller accessed via MMIO registers.
+
+config LEDS_BCM6358
+	tristate "LED Support for Broadcom BCM6358"
+	depends on LEDS_CLASS
+	depends on OF
+	help
+	  This option enables support for LEDs connected to the BCM6358
+	  LED HW controller accessed via MMIO registers.
+
 config LEDS_LM3530
 	tristate "LCD Backlight driver for LM3530"
 	depends on LEDS_CLASS
@@ -179,7 +205,7 @@
 config LEDS_GPIO
 	tristate "LED Support for GPIO connected LEDs"
 	depends on LEDS_CLASS
-	depends on GPIOLIB
+	depends on GPIOLIB || COMPILE_TEST
 	help
 	  This option enables support for the LEDs connected to GPIO
 	  outputs. To be useful the particular board must have LEDs
@@ -203,6 +229,7 @@
 	tristate "Common Driver for TI/National LP5521/5523/55231/5562/8501"
 	depends on LEDS_LP5521 || LEDS_LP5523 || LEDS_LP5562 || LEDS_LP8501
 	select FW_LOADER
+	select FW_LOADER_USER_HELPER_FALLBACK
 	help
 	  This option supports common operations for LP5521/5523/55231/5562/8501
 	  devices.
@@ -464,6 +491,25 @@
 	  LED driver chips accessed via the I2C bus.
 	  Driver support brightness control and hardware-assisted blinking.
 
+config LEDS_TLC591XX
+	tristate "LED driver for TLC59108 and TLC59116 controllers"
+	depends on LEDS_CLASS && I2C
+	select REGMAP_I2C
+	help
+	  This option enables support for Texas Instruments TLC59108
+	  and TLC59116 LED controllers.
+
+config LEDS_MAX77693
+	tristate "LED support for MAX77693 Flash"
+	depends on LEDS_CLASS_FLASH
+	depends on V4L2_FLASH_LED_CLASS || !V4L2_FLASH_LED_CLASS
+	depends on MFD_MAX77693
+	depends on OF
+	help
+	  This option enables support for the flash part of the MAX77693
+	  multifunction device. It has build in control for two leds in flash
+	  and torch mode.
+
 config LEDS_MAX8997
 	tristate "LED support for MAX8997 PMIC"
 	depends on LEDS_CLASS && MFD_MAX8997
@@ -495,6 +541,15 @@
 	  This driver can also be built as a module. If so the module
 	  will be called leds-menf21bmc.
 
+config LEDS_KTD2692
+	tristate "LED support for KTD2692 flash LED controller"
+	depends on LEDS_CLASS_FLASH && GPIOLIB && OF
+	help
+	  This option enables support for KTD2692 LED flash connected
+	  through ExpressWire interface.
+
+	  Say Y to enable this driver.
+
 comment "LED driver for blink(1) USB RGB LED is under Special HID drivers (HID_THINGM)"
 
 config LEDS_BLINKM
diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile
index bf46093..8d6a24a 100644
--- a/drivers/leds/Makefile
+++ b/drivers/leds/Makefile
@@ -7,6 +7,9 @@
 
 # LED Platform Drivers
 obj-$(CONFIG_LEDS_88PM860X)		+= leds-88pm860x.o
+obj-$(CONFIG_LEDS_AAT1290)		+= leds-aat1290.o
+obj-$(CONFIG_LEDS_BCM6328)		+= leds-bcm6328.o
+obj-$(CONFIG_LEDS_BCM6358)		+= leds-bcm6358.o
 obj-$(CONFIG_LEDS_BD2802)		+= leds-bd2802.o
 obj-$(CONFIG_LEDS_LOCOMO)		+= leds-locomo.o
 obj-$(CONFIG_LEDS_LM3530)		+= leds-lm3530.o
@@ -31,6 +34,7 @@
 obj-$(CONFIG_LEDS_LP8788)		+= leds-lp8788.o
 obj-$(CONFIG_LEDS_LP8860)		+= leds-lp8860.o
 obj-$(CONFIG_LEDS_TCA6507)		+= leds-tca6507.o
+obj-$(CONFIG_LEDS_TLC591XX)		+= leds-tlc591xx.o
 obj-$(CONFIG_LEDS_CLEVO_MAIL)		+= leds-clevo-mail.o
 obj-$(CONFIG_LEDS_IPAQ_MICRO)		+= leds-ipaq-micro.o
 obj-$(CONFIG_LEDS_HP6XX)		+= leds-hp6xx.o
@@ -52,6 +56,7 @@
 obj-$(CONFIG_LEDS_NS2)			+= leds-ns2.o
 obj-$(CONFIG_LEDS_NETXBIG)		+= leds-netxbig.o
 obj-$(CONFIG_LEDS_ASIC3)		+= leds-asic3.o
+obj-$(CONFIG_LEDS_MAX77693)		+= leds-max77693.o
 obj-$(CONFIG_LEDS_MAX8997)		+= leds-max8997.o
 obj-$(CONFIG_LEDS_LM355x)		+= leds-lm355x.o
 obj-$(CONFIG_LEDS_BLINKM)		+= leds-blinkm.o
@@ -59,6 +64,7 @@
 obj-$(CONFIG_LEDS_VERSATILE)		+= leds-versatile.o
 obj-$(CONFIG_LEDS_MENF21BMC)		+= leds-menf21bmc.o
 obj-$(CONFIG_LEDS_PM8941_WLED)		+= leds-pm8941-wled.o
+obj-$(CONFIG_LEDS_KTD2692)		+= leds-ktd2692.o
 
 # LED SPI Drivers
 obj-$(CONFIG_LEDS_DAC124S085)		+= leds-dac124s085.o
diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index 7fb2a19..beabfbc 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -121,6 +121,11 @@
 	brightness = led_get_brightness(led_cdev);
 	if (!brightness) {
 		/* Time to switch the LED on. */
+		if (led_cdev->delayed_set_value) {
+			led_cdev->blink_brightness =
+					led_cdev->delayed_set_value;
+			led_cdev->delayed_set_value = 0;
+		}
 		brightness = led_cdev->blink_brightness;
 		delay = led_cdev->blink_delay_on;
 	} else {
diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c
index 9886dac..549de7e 100644
--- a/drivers/leds/led-core.c
+++ b/drivers/leds/led-core.c
@@ -119,10 +119,11 @@
 {
 	int ret = 0;
 
-	/* delay brightness setting if need to stop soft-blink timer */
+	/* delay brightness if soft-blink is active */
 	if (led_cdev->blink_delay_on || led_cdev->blink_delay_off) {
 		led_cdev->delayed_set_value = brightness;
-		schedule_work(&led_cdev->set_brightness_work);
+		if (brightness == LED_OFF)
+			schedule_work(&led_cdev->set_brightness_work);
 		return;
 	}
 
diff --git a/drivers/leds/leds-aat1290.c b/drivers/leds/leds-aat1290.c
new file mode 100644
index 0000000..fd7c25f
--- /dev/null
+++ b/drivers/leds/leds-aat1290.c
@@ -0,0 +1,576 @@
+/*
+ *	LED Flash class driver for the AAT1290
+ *	1.5A Step-Up Current Regulator for Flash LEDs
+ *
+ *	Copyright (C) 2015, Samsung Electronics Co., Ltd.
+ *	Author: Jacek Anaszewski <j.anaszewski@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ */
+
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/led-class-flash.h>
+#include <linux/leds.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+#include <media/v4l2-flash-led-class.h>
+
+#define AAT1290_MOVIE_MODE_CURRENT_ADDR	17
+#define AAT1290_MAX_MM_CURR_PERCENT_0	16
+#define AAT1290_MAX_MM_CURR_PERCENT_100	1
+
+#define AAT1290_FLASH_SAFETY_TIMER_ADDR	18
+
+#define AAT1290_MOVIE_MODE_CONFIG_ADDR	19
+#define AAT1290_MOVIE_MODE_OFF		1
+#define AAT1290_MOVIE_MODE_ON		3
+
+#define AAT1290_MM_CURRENT_RATIO_ADDR	20
+#define AAT1290_MM_TO_FL_1_92		1
+
+#define AAT1290_MM_TO_FL_RATIO		1000 / 1920
+#define AAT1290_MAX_MM_CURRENT(fl_max)	(fl_max * AAT1290_MM_TO_FL_RATIO)
+
+#define AAT1290_LATCH_TIME_MIN_US	500
+#define AAT1290_LATCH_TIME_MAX_US	1000
+#define AAT1290_EN_SET_TICK_TIME_US	1
+#define AAT1290_FLEN_OFF_DELAY_TIME_US	10
+#define AAT1290_FLASH_TM_NUM_LEVELS	16
+#define AAT1290_MM_CURRENT_SCALE_SIZE	15
+
+
+struct aat1290_led_config_data {
+	/* maximum LED current in movie mode */
+	u32 max_mm_current;
+	/* maximum LED current in flash mode */
+	u32 max_flash_current;
+	/* maximum flash timeout */
+	u32 max_flash_tm;
+	/* external strobe capability */
+	bool has_external_strobe;
+	/* max LED brightness level */
+	enum led_brightness max_brightness;
+};
+
+struct aat1290_led {
+	/* platform device data */
+	struct platform_device *pdev;
+	/* secures access to the device */
+	struct mutex lock;
+
+	/* corresponding LED Flash class device */
+	struct led_classdev_flash fled_cdev;
+	/* V4L2 Flash device */
+	struct v4l2_flash *v4l2_flash;
+
+	/* FLEN pin */
+	struct gpio_desc *gpio_fl_en;
+	/* EN|SET pin  */
+	struct gpio_desc *gpio_en_set;
+	/* movie mode current scale */
+	int *mm_current_scale;
+	/* device mode */
+	bool movie_mode;
+
+	/* brightness cache */
+	unsigned int torch_brightness;
+	/* assures led-triggers compatibility */
+	struct work_struct work_brightness_set;
+};
+
+static struct aat1290_led *fled_cdev_to_led(
+				struct led_classdev_flash *fled_cdev)
+{
+	return container_of(fled_cdev, struct aat1290_led, fled_cdev);
+}
+
+static void aat1290_as2cwire_write(struct aat1290_led *led, int addr, int value)
+{
+	int i;
+
+	gpiod_direction_output(led->gpio_fl_en, 0);
+	gpiod_direction_output(led->gpio_en_set, 0);
+
+	udelay(AAT1290_FLEN_OFF_DELAY_TIME_US);
+
+	/* write address */
+	for (i = 0; i < addr; ++i) {
+		udelay(AAT1290_EN_SET_TICK_TIME_US);
+		gpiod_direction_output(led->gpio_en_set, 0);
+		udelay(AAT1290_EN_SET_TICK_TIME_US);
+		gpiod_direction_output(led->gpio_en_set, 1);
+	}
+
+	usleep_range(AAT1290_LATCH_TIME_MIN_US, AAT1290_LATCH_TIME_MAX_US);
+
+	/* write data */
+	for (i = 0; i < value; ++i) {
+		udelay(AAT1290_EN_SET_TICK_TIME_US);
+		gpiod_direction_output(led->gpio_en_set, 0);
+		udelay(AAT1290_EN_SET_TICK_TIME_US);
+		gpiod_direction_output(led->gpio_en_set, 1);
+	}
+
+	usleep_range(AAT1290_LATCH_TIME_MIN_US, AAT1290_LATCH_TIME_MAX_US);
+}
+
+static void aat1290_set_flash_safety_timer(struct aat1290_led *led,
+					unsigned int micro_sec)
+{
+	struct led_classdev_flash *fled_cdev = &led->fled_cdev;
+	struct led_flash_setting *flash_tm = &fled_cdev->timeout;
+	int flash_tm_reg = AAT1290_FLASH_TM_NUM_LEVELS -
+				(micro_sec / flash_tm->step) + 1;
+
+	aat1290_as2cwire_write(led, AAT1290_FLASH_SAFETY_TIMER_ADDR,
+							flash_tm_reg);
+}
+
+static void aat1290_brightness_set(struct aat1290_led *led,
+					enum led_brightness brightness)
+{
+	mutex_lock(&led->lock);
+
+	if (brightness == 0) {
+		gpiod_direction_output(led->gpio_fl_en, 0);
+		gpiod_direction_output(led->gpio_en_set, 0);
+		led->movie_mode = false;
+	} else {
+		if (!led->movie_mode) {
+			aat1290_as2cwire_write(led,
+				AAT1290_MM_CURRENT_RATIO_ADDR,
+				AAT1290_MM_TO_FL_1_92);
+			led->movie_mode = true;
+		}
+
+		aat1290_as2cwire_write(led, AAT1290_MOVIE_MODE_CURRENT_ADDR,
+				AAT1290_MAX_MM_CURR_PERCENT_0 - brightness);
+		aat1290_as2cwire_write(led, AAT1290_MOVIE_MODE_CONFIG_ADDR,
+				AAT1290_MOVIE_MODE_ON);
+	}
+
+	mutex_unlock(&led->lock);
+}
+
+/* LED subsystem callbacks */
+
+static void aat1290_brightness_set_work(struct work_struct *work)
+{
+	struct aat1290_led *led =
+		container_of(work, struct aat1290_led, work_brightness_set);
+
+	aat1290_brightness_set(led, led->torch_brightness);
+}
+
+static void aat1290_led_brightness_set(struct led_classdev *led_cdev,
+					enum led_brightness brightness)
+{
+	struct led_classdev_flash *fled_cdev = lcdev_to_flcdev(led_cdev);
+	struct aat1290_led *led = fled_cdev_to_led(fled_cdev);
+
+	led->torch_brightness = brightness;
+	schedule_work(&led->work_brightness_set);
+}
+
+static int aat1290_led_brightness_set_sync(struct led_classdev *led_cdev,
+					enum led_brightness brightness)
+{
+	struct led_classdev_flash *fled_cdev = lcdev_to_flcdev(led_cdev);
+	struct aat1290_led *led = fled_cdev_to_led(fled_cdev);
+
+	aat1290_brightness_set(led, brightness);
+
+	return 0;
+}
+
+static int aat1290_led_flash_strobe_set(struct led_classdev_flash *fled_cdev,
+					 bool state)
+
+{
+	struct aat1290_led *led = fled_cdev_to_led(fled_cdev);
+	struct led_classdev *led_cdev = &fled_cdev->led_cdev;
+	struct led_flash_setting *timeout = &fled_cdev->timeout;
+
+	mutex_lock(&led->lock);
+
+	if (state) {
+		aat1290_set_flash_safety_timer(led, timeout->val);
+		gpiod_direction_output(led->gpio_fl_en, 1);
+	} else {
+		gpiod_direction_output(led->gpio_fl_en, 0);
+		gpiod_direction_output(led->gpio_en_set, 0);
+	}
+
+	/*
+	 * To reenter movie mode after a flash event the part must be cycled
+	 * off and back on to reset the movie mode and reprogrammed via the
+	 * AS2Cwire. Therefore the brightness and movie_mode properties needs
+	 * to be updated here to reflect the actual state.
+	 */
+	led_cdev->brightness = 0;
+	led->movie_mode = false;
+
+	mutex_unlock(&led->lock);
+
+	return 0;
+}
+
+static int aat1290_led_flash_timeout_set(struct led_classdev_flash *fled_cdev,
+						u32 timeout)
+{
+	/*
+	 * Don't do anything - flash timeout is cached in the led-class-flash
+	 * core and will be applied in the strobe_set op, as writing the
+	 * safety timer register spuriously turns the torch mode on.
+	 */
+
+	return 0;
+}
+
+static int aat1290_led_parse_dt(struct aat1290_led *led,
+			struct aat1290_led_config_data *cfg,
+			struct device_node **sub_node)
+{
+	struct led_classdev *led_cdev = &led->fled_cdev.led_cdev;
+	struct device *dev = &led->pdev->dev;
+	struct device_node *child_node;
+#if IS_ENABLED(CONFIG_V4L2_FLASH_LED_CLASS)
+	struct pinctrl *pinctrl;
+#endif
+	int ret = 0;
+
+	led->gpio_fl_en = devm_gpiod_get(dev, "flen", GPIOD_ASIS);
+	if (IS_ERR(led->gpio_fl_en)) {
+		ret = PTR_ERR(led->gpio_fl_en);
+		dev_err(dev, "Unable to claim gpio \"flen\".\n");
+		return ret;
+	}
+
+	led->gpio_en_set = devm_gpiod_get(dev, "enset", GPIOD_ASIS);
+	if (IS_ERR(led->gpio_en_set)) {
+		ret = PTR_ERR(led->gpio_en_set);
+		dev_err(dev, "Unable to claim gpio \"enset\".\n");
+		return ret;
+	}
+
+#if IS_ENABLED(CONFIG_V4L2_FLASH_LED_CLASS)
+	pinctrl = devm_pinctrl_get_select_default(&led->pdev->dev);
+	if (IS_ERR(pinctrl)) {
+		cfg->has_external_strobe = false;
+		dev_info(dev,
+			 "No support for external strobe detected.\n");
+	} else {
+		cfg->has_external_strobe = true;
+	}
+#endif
+
+	child_node = of_get_next_available_child(dev->of_node, NULL);
+	if (!child_node) {
+		dev_err(dev, "No DT child node found for connected LED.\n");
+		return -EINVAL;
+	}
+
+	led_cdev->name = of_get_property(child_node, "label", NULL) ? :
+						child_node->name;
+
+	ret = of_property_read_u32(child_node, "led-max-microamp",
+				&cfg->max_mm_current);
+	/*
+	 * led-max-microamp will default to 1/20 of flash-max-microamp
+	 * in case it is missing.
+	 */
+	if (ret < 0)
+		dev_warn(dev,
+			"led-max-microamp DT property missing\n");
+
+	ret = of_property_read_u32(child_node, "flash-max-microamp",
+				&cfg->max_flash_current);
+	if (ret < 0) {
+		dev_err(dev,
+			"flash-max-microamp DT property missing\n");
+		return ret;
+	}
+
+	ret = of_property_read_u32(child_node, "flash-max-timeout-us",
+				&cfg->max_flash_tm);
+	if (ret < 0) {
+		dev_err(dev,
+			"flash-max-timeout-us DT property missing\n");
+		return ret;
+	}
+
+	of_node_put(child_node);
+
+	*sub_node = child_node;
+
+	return ret;
+}
+
+static void aat1290_led_validate_mm_current(struct aat1290_led *led,
+					struct aat1290_led_config_data *cfg)
+{
+	int i, b = 0, e = AAT1290_MM_CURRENT_SCALE_SIZE;
+
+	while (e - b > 1) {
+		i = b + (e - b) / 2;
+		if (cfg->max_mm_current < led->mm_current_scale[i])
+			e = i;
+		else
+			b = i;
+	}
+
+	cfg->max_mm_current = led->mm_current_scale[b];
+	cfg->max_brightness = b + 1;
+}
+
+int init_mm_current_scale(struct aat1290_led *led,
+			struct aat1290_led_config_data *cfg)
+{
+	int max_mm_current_percent[] = { 20, 22, 25, 28, 32, 36, 40, 45, 50, 56,
+						63, 71, 79, 89, 100 };
+	int i, max_mm_current =
+			AAT1290_MAX_MM_CURRENT(cfg->max_flash_current);
+
+	led->mm_current_scale = devm_kzalloc(&led->pdev->dev,
+					sizeof(max_mm_current_percent),
+					GFP_KERNEL);
+	if (!led->mm_current_scale)
+		return -ENOMEM;
+
+	for (i = 0; i < AAT1290_MM_CURRENT_SCALE_SIZE; ++i)
+		led->mm_current_scale[i] = max_mm_current *
+					  max_mm_current_percent[i] / 100;
+
+	return 0;
+}
+
+static int aat1290_led_get_configuration(struct aat1290_led *led,
+					struct aat1290_led_config_data *cfg,
+					struct device_node **sub_node)
+{
+	int ret;
+
+	ret = aat1290_led_parse_dt(led, cfg, sub_node);
+	if (ret < 0)
+		return ret;
+	/*
+	 * Init non-linear movie mode current scale basing
+	 * on the max flash current from led configuration.
+	 */
+	ret = init_mm_current_scale(led, cfg);
+	if (ret < 0)
+		return ret;
+
+	aat1290_led_validate_mm_current(led, cfg);
+
+#if IS_ENABLED(CONFIG_V4L2_FLASH_LED_CLASS)
+#else
+	devm_kfree(&led->pdev->dev, led->mm_current_scale);
+#endif
+
+	return 0;
+}
+
+static void aat1290_init_flash_timeout(struct aat1290_led *led,
+				struct aat1290_led_config_data *cfg)
+{
+	struct led_classdev_flash *fled_cdev = &led->fled_cdev;
+	struct led_flash_setting *setting;
+
+	/* Init flash timeout setting */
+	setting = &fled_cdev->timeout;
+	setting->min = cfg->max_flash_tm / AAT1290_FLASH_TM_NUM_LEVELS;
+	setting->max = cfg->max_flash_tm;
+	setting->step = setting->min;
+	setting->val = setting->max;
+}
+
+#if IS_ENABLED(CONFIG_V4L2_FLASH_LED_CLASS)
+static enum led_brightness aat1290_intensity_to_brightness(
+					struct v4l2_flash *v4l2_flash,
+					s32 intensity)
+{
+	struct led_classdev_flash *fled_cdev = v4l2_flash->fled_cdev;
+	struct aat1290_led *led = fled_cdev_to_led(fled_cdev);
+	int i;
+
+	for (i = AAT1290_MM_CURRENT_SCALE_SIZE - 1; i >= 0; --i)
+		if (intensity >= led->mm_current_scale[i])
+			return i + 1;
+
+	return 1;
+}
+
+static s32 aat1290_brightness_to_intensity(struct v4l2_flash *v4l2_flash,
+					enum led_brightness brightness)
+{
+	struct led_classdev_flash *fled_cdev = v4l2_flash->fled_cdev;
+	struct aat1290_led *led = fled_cdev_to_led(fled_cdev);
+
+	return led->mm_current_scale[brightness - 1];
+}
+
+static int aat1290_led_external_strobe_set(struct v4l2_flash *v4l2_flash,
+						bool enable)
+{
+	struct aat1290_led *led = fled_cdev_to_led(v4l2_flash->fled_cdev);
+	struct led_classdev_flash *fled_cdev = v4l2_flash->fled_cdev;
+	struct led_classdev *led_cdev = &fled_cdev->led_cdev;
+	struct pinctrl *pinctrl;
+
+	gpiod_direction_output(led->gpio_fl_en, 0);
+	gpiod_direction_output(led->gpio_en_set, 0);
+
+	led->movie_mode = false;
+	led_cdev->brightness = 0;
+
+	pinctrl = devm_pinctrl_get_select(&led->pdev->dev,
+						enable ? "isp" : "host");
+	if (IS_ERR(pinctrl)) {
+		dev_warn(&led->pdev->dev, "Unable to switch strobe source.\n");
+		return PTR_ERR(pinctrl);
+	}
+
+	return 0;
+}
+
+static void aat1290_init_v4l2_flash_config(struct aat1290_led *led,
+					struct aat1290_led_config_data *led_cfg,
+					struct v4l2_flash_config *v4l2_sd_cfg)
+{
+	struct led_classdev *led_cdev = &led->fled_cdev.led_cdev;
+	struct led_flash_setting *s;
+
+	strlcpy(v4l2_sd_cfg->dev_name, led_cdev->name,
+		sizeof(v4l2_sd_cfg->dev_name));
+
+	s = &v4l2_sd_cfg->torch_intensity;
+	s->min = led->mm_current_scale[0];
+	s->max = led_cfg->max_mm_current;
+	s->step = 1;
+	s->val = s->max;
+
+	v4l2_sd_cfg->has_external_strobe = led_cfg->has_external_strobe;
+}
+
+static const struct v4l2_flash_ops v4l2_flash_ops = {
+	.external_strobe_set = aat1290_led_external_strobe_set,
+	.intensity_to_led_brightness = aat1290_intensity_to_brightness,
+	.led_brightness_to_intensity = aat1290_brightness_to_intensity,
+};
+#else
+static inline void aat1290_init_v4l2_flash_config(struct aat1290_led *led,
+				struct aat1290_led_config_data *led_cfg,
+				struct v4l2_flash_config *v4l2_sd_cfg)
+{
+}
+static const struct v4l2_flash_ops v4l2_flash_ops;
+#endif
+
+static const struct led_flash_ops flash_ops = {
+	.strobe_set = aat1290_led_flash_strobe_set,
+	.timeout_set = aat1290_led_flash_timeout_set,
+};
+
+static int aat1290_led_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *sub_node = NULL;
+	struct aat1290_led *led;
+	struct led_classdev *led_cdev;
+	struct led_classdev_flash *fled_cdev;
+	struct aat1290_led_config_data led_cfg = {};
+	struct v4l2_flash_config v4l2_sd_cfg = {};
+	int ret;
+
+	led = devm_kzalloc(dev, sizeof(*led), GFP_KERNEL);
+	if (!led)
+		return -ENOMEM;
+
+	led->pdev = pdev;
+	platform_set_drvdata(pdev, led);
+
+	fled_cdev = &led->fled_cdev;
+	fled_cdev->ops = &flash_ops;
+	led_cdev = &fled_cdev->led_cdev;
+
+	ret = aat1290_led_get_configuration(led, &led_cfg, &sub_node);
+	if (ret < 0)
+		return ret;
+
+	mutex_init(&led->lock);
+
+	/* Initialize LED Flash class device */
+	led_cdev->brightness_set = aat1290_led_brightness_set;
+	led_cdev->brightness_set_sync = aat1290_led_brightness_set_sync;
+	led_cdev->max_brightness = led_cfg.max_brightness;
+	led_cdev->flags |= LED_DEV_CAP_FLASH;
+	INIT_WORK(&led->work_brightness_set, aat1290_brightness_set_work);
+
+	aat1290_init_flash_timeout(led, &led_cfg);
+
+	/* Register LED Flash class device */
+	ret = led_classdev_flash_register(&pdev->dev, fled_cdev);
+	if (ret < 0)
+		goto err_flash_register;
+
+	aat1290_init_v4l2_flash_config(led, &led_cfg, &v4l2_sd_cfg);
+
+	/* Create V4L2 Flash subdev. */
+	led->v4l2_flash = v4l2_flash_init(dev, sub_node, fled_cdev, NULL,
+					  &v4l2_flash_ops, &v4l2_sd_cfg);
+	if (IS_ERR(led->v4l2_flash)) {
+		ret = PTR_ERR(led->v4l2_flash);
+		goto error_v4l2_flash_init;
+	}
+
+	return 0;
+
+error_v4l2_flash_init:
+	led_classdev_flash_unregister(fled_cdev);
+err_flash_register:
+	mutex_destroy(&led->lock);
+
+	return ret;
+}
+
+static int aat1290_led_remove(struct platform_device *pdev)
+{
+	struct aat1290_led *led = platform_get_drvdata(pdev);
+
+	v4l2_flash_release(led->v4l2_flash);
+	led_classdev_flash_unregister(&led->fled_cdev);
+	cancel_work_sync(&led->work_brightness_set);
+
+	mutex_destroy(&led->lock);
+
+	return 0;
+}
+
+static const struct of_device_id aat1290_led_dt_match[] = {
+	{ .compatible = "skyworks,aat1290" },
+	{},
+};
+
+static struct platform_driver aat1290_led_driver = {
+	.probe		= aat1290_led_probe,
+	.remove		= aat1290_led_remove,
+	.driver		= {
+		.name	= "aat1290",
+		.of_match_table = aat1290_led_dt_match,
+	},
+};
+
+module_platform_driver(aat1290_led_driver);
+
+MODULE_AUTHOR("Jacek Anaszewski <j.anaszewski@samsung.com>");
+MODULE_DESCRIPTION("Skyworks Current Regulator for Flash LEDs");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/leds-bcm6328.c b/drivers/leds/leds-bcm6328.c
new file mode 100644
index 0000000..986fe1e
--- /dev/null
+++ b/drivers/leds/leds-bcm6328.c
@@ -0,0 +1,413 @@
+/*
+ * Driver for BCM6328 memory-mapped LEDs, based on leds-syscon.c
+ *
+ * Copyright 2015 Álvaro Fernández Rojas <noltari@gmail.com>
+ * Copyright 2015 Jonas Gorski <jogo@openwrt.org>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+#include <linux/io.h>
+#include <linux/leds.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+
+#define BCM6328_REG_INIT		0x00
+#define BCM6328_REG_MODE_HI		0x04
+#define BCM6328_REG_MODE_LO		0x08
+#define BCM6328_REG_HWDIS		0x0c
+#define BCM6328_REG_STROBE		0x10
+#define BCM6328_REG_LNKACTSEL_HI	0x14
+#define BCM6328_REG_LNKACTSEL_LO	0x18
+#define BCM6328_REG_RBACK		0x1c
+#define BCM6328_REG_SERMUX		0x20
+
+#define BCM6328_LED_MAX_COUNT		24
+#define BCM6328_LED_DEF_DELAY		500
+#define BCM6328_LED_INTERVAL_MS		20
+
+#define BCM6328_LED_INTV_MASK		0x3f
+#define BCM6328_LED_FAST_INTV_SHIFT	6
+#define BCM6328_LED_FAST_INTV_MASK	(BCM6328_LED_INTV_MASK << \
+					 BCM6328_LED_FAST_INTV_SHIFT)
+#define BCM6328_SERIAL_LED_EN		BIT(12)
+#define BCM6328_SERIAL_LED_MUX		BIT(13)
+#define BCM6328_SERIAL_LED_CLK_NPOL	BIT(14)
+#define BCM6328_SERIAL_LED_DATA_PPOL	BIT(15)
+#define BCM6328_SERIAL_LED_SHIFT_DIR	BIT(16)
+#define BCM6328_LED_SHIFT_TEST		BIT(30)
+#define BCM6328_LED_TEST		BIT(31)
+
+#define BCM6328_LED_MODE_MASK		3
+#define BCM6328_LED_MODE_OFF		0
+#define BCM6328_LED_MODE_FAST		1
+#define BCM6328_LED_MODE_BLINK		2
+#define BCM6328_LED_MODE_ON		3
+#define BCM6328_LED_SHIFT(X)		((X) << 1)
+
+/**
+ * struct bcm6328_led - state container for bcm6328 based LEDs
+ * @cdev: LED class device for this LED
+ * @mem: memory resource
+ * @lock: memory lock
+ * @pin: LED pin number
+ * @blink_leds: blinking LEDs
+ * @blink_delay: blinking delay
+ * @active_low: LED is active low
+ */
+struct bcm6328_led {
+	struct led_classdev cdev;
+	void __iomem *mem;
+	spinlock_t *lock;
+	unsigned long pin;
+	unsigned long *blink_leds;
+	unsigned long *blink_delay;
+	bool active_low;
+};
+
+static void bcm6328_led_write(void __iomem *reg, unsigned long data)
+{
+	iowrite32be(data, reg);
+}
+
+static unsigned long bcm6328_led_read(void __iomem *reg)
+{
+	return ioread32be(reg);
+}
+
+/**
+ * LEDMode 64 bits / 24 LEDs
+ * bits [31:0] -> LEDs 8-23
+ * bits [47:32] -> LEDs 0-7
+ * bits [63:48] -> unused
+ */
+static unsigned long bcm6328_pin2shift(unsigned long pin)
+{
+	if (pin < 8)
+		return pin + 16; /* LEDs 0-7 (bits 47:32) */
+	else
+		return pin - 8; /* LEDs 8-23 (bits 31:0) */
+}
+
+static void bcm6328_led_mode(struct bcm6328_led *led, unsigned long value)
+{
+	void __iomem *mode;
+	unsigned long val, shift;
+
+	shift = bcm6328_pin2shift(led->pin);
+	if (shift / 16)
+		mode = led->mem + BCM6328_REG_MODE_HI;
+	else
+		mode = led->mem + BCM6328_REG_MODE_LO;
+
+	val = bcm6328_led_read(mode);
+	val &= ~(BCM6328_LED_MODE_MASK << BCM6328_LED_SHIFT(shift % 16));
+	val |= (value << BCM6328_LED_SHIFT(shift % 16));
+	bcm6328_led_write(mode, val);
+}
+
+static void bcm6328_led_set(struct led_classdev *led_cdev,
+			    enum led_brightness value)
+{
+	struct bcm6328_led *led =
+		container_of(led_cdev, struct bcm6328_led, cdev);
+	unsigned long flags;
+
+	spin_lock_irqsave(led->lock, flags);
+	*(led->blink_leds) &= ~BIT(led->pin);
+	if ((led->active_low && value == LED_OFF) ||
+	    (!led->active_low && value != LED_OFF))
+		bcm6328_led_mode(led, BCM6328_LED_MODE_OFF);
+	else
+		bcm6328_led_mode(led, BCM6328_LED_MODE_ON);
+	spin_unlock_irqrestore(led->lock, flags);
+}
+
+static int bcm6328_blink_set(struct led_classdev *led_cdev,
+			     unsigned long *delay_on, unsigned long *delay_off)
+{
+	struct bcm6328_led *led =
+		container_of(led_cdev, struct bcm6328_led, cdev);
+	unsigned long delay, flags;
+
+	if (!*delay_on)
+		*delay_on = BCM6328_LED_DEF_DELAY;
+	if (!*delay_off)
+		*delay_off = BCM6328_LED_DEF_DELAY;
+
+	if (*delay_on != *delay_off) {
+		dev_dbg(led_cdev->dev,
+			"fallback to soft blinking (delay_on != delay_off)\n");
+		return -EINVAL;
+	}
+
+	delay = *delay_on / BCM6328_LED_INTERVAL_MS;
+	if (delay == 0)
+		delay = 1;
+	else if (delay > BCM6328_LED_INTV_MASK) {
+		dev_dbg(led_cdev->dev,
+			"fallback to soft blinking (delay > %ums)\n",
+			BCM6328_LED_INTV_MASK * BCM6328_LED_INTERVAL_MS);
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(led->lock, flags);
+	if (*(led->blink_leds) == 0 ||
+	    *(led->blink_leds) == BIT(led->pin) ||
+	    *(led->blink_delay) == delay) {
+		unsigned long val;
+
+		*(led->blink_leds) |= BIT(led->pin);
+		*(led->blink_delay) = delay;
+
+		val = bcm6328_led_read(led->mem + BCM6328_REG_INIT);
+		val &= ~BCM6328_LED_FAST_INTV_MASK;
+		val |= (delay << BCM6328_LED_FAST_INTV_SHIFT);
+		bcm6328_led_write(led->mem + BCM6328_REG_INIT, val);
+
+		bcm6328_led_mode(led, BCM6328_LED_MODE_BLINK);
+
+		spin_unlock_irqrestore(led->lock, flags);
+	} else {
+		spin_unlock_irqrestore(led->lock, flags);
+		dev_dbg(led_cdev->dev,
+			"fallback to soft blinking (delay already set)\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int bcm6328_hwled(struct device *dev, struct device_node *nc, u32 reg,
+			 void __iomem *mem, spinlock_t *lock)
+{
+	int i, cnt;
+	unsigned long flags, val;
+
+	spin_lock_irqsave(lock, flags);
+	val = bcm6328_led_read(mem + BCM6328_REG_HWDIS);
+	val &= ~BIT(reg);
+	bcm6328_led_write(mem + BCM6328_REG_HWDIS, val);
+	spin_unlock_irqrestore(lock, flags);
+
+	/* Only LEDs 0-7 can be activity/link controlled */
+	if (reg >= 8)
+		return 0;
+
+	cnt = of_property_count_elems_of_size(nc, "brcm,link-signal-sources",
+					      sizeof(u32));
+	for (i = 0; i < cnt; i++) {
+		u32 sel;
+		void __iomem *addr;
+
+		if (reg < 4)
+			addr = mem + BCM6328_REG_LNKACTSEL_LO;
+		else
+			addr = mem + BCM6328_REG_LNKACTSEL_HI;
+
+		of_property_read_u32_index(nc, "brcm,link-signal-sources", i,
+					   &sel);
+
+		if (reg / 4 != sel / 4) {
+			dev_warn(dev, "invalid link signal source\n");
+			continue;
+		}
+
+		spin_lock_irqsave(lock, flags);
+		val = bcm6328_led_read(addr);
+		val |= (BIT(reg) << (((sel % 4) * 4) + 16));
+		bcm6328_led_write(addr, val);
+		spin_unlock_irqrestore(lock, flags);
+	}
+
+	cnt = of_property_count_elems_of_size(nc,
+					      "brcm,activity-signal-sources",
+					      sizeof(u32));
+	for (i = 0; i < cnt; i++) {
+		u32 sel;
+		void __iomem *addr;
+
+		if (reg < 4)
+			addr = mem + BCM6328_REG_LNKACTSEL_LO;
+		else
+			addr = mem + BCM6328_REG_LNKACTSEL_HI;
+
+		of_property_read_u32_index(nc, "brcm,activity-signal-sources",
+					   i, &sel);
+
+		if (reg / 4 != sel / 4) {
+			dev_warn(dev, "invalid activity signal source\n");
+			continue;
+		}
+
+		spin_lock_irqsave(lock, flags);
+		val = bcm6328_led_read(addr);
+		val |= (BIT(reg) << ((sel % 4) * 4));
+		bcm6328_led_write(addr, val);
+		spin_unlock_irqrestore(lock, flags);
+	}
+
+	return 0;
+}
+
+static int bcm6328_led(struct device *dev, struct device_node *nc, u32 reg,
+		       void __iomem *mem, spinlock_t *lock,
+		       unsigned long *blink_leds, unsigned long *blink_delay)
+{
+	struct bcm6328_led *led;
+	unsigned long flags;
+	const char *state;
+	int rc;
+
+	led = devm_kzalloc(dev, sizeof(*led), GFP_KERNEL);
+	if (!led)
+		return -ENOMEM;
+
+	led->pin = reg;
+	led->mem = mem;
+	led->lock = lock;
+	led->blink_leds = blink_leds;
+	led->blink_delay = blink_delay;
+
+	if (of_property_read_bool(nc, "active-low"))
+		led->active_low = true;
+
+	led->cdev.name = of_get_property(nc, "label", NULL) ? : nc->name;
+	led->cdev.default_trigger = of_get_property(nc,
+						    "linux,default-trigger",
+						    NULL);
+
+	if (!of_property_read_string(nc, "default-state", &state)) {
+		spin_lock_irqsave(lock, flags);
+		if (!strcmp(state, "on")) {
+			led->cdev.brightness = LED_FULL;
+			bcm6328_led_mode(led, BCM6328_LED_MODE_ON);
+		} else if (!strcmp(state, "keep")) {
+			void __iomem *mode;
+			unsigned long val, shift;
+
+			shift = bcm6328_pin2shift(led->pin);
+			if (shift / 16)
+				mode = mem + BCM6328_REG_MODE_HI;
+			else
+				mode = mem + BCM6328_REG_MODE_LO;
+
+			val = bcm6328_led_read(mode) >> (shift % 16);
+			val &= BCM6328_LED_MODE_MASK;
+			if (val == BCM6328_LED_MODE_ON)
+				led->cdev.brightness = LED_FULL;
+			else {
+				led->cdev.brightness = LED_OFF;
+				bcm6328_led_mode(led, BCM6328_LED_MODE_OFF);
+			}
+		} else {
+			led->cdev.brightness = LED_OFF;
+			bcm6328_led_mode(led, BCM6328_LED_MODE_OFF);
+		}
+		spin_unlock_irqrestore(lock, flags);
+	}
+
+	led->cdev.brightness_set = bcm6328_led_set;
+	led->cdev.blink_set = bcm6328_blink_set;
+
+	rc = led_classdev_register(dev, &led->cdev);
+	if (rc < 0)
+		return rc;
+
+	dev_dbg(dev, "registered LED %s\n", led->cdev.name);
+
+	return 0;
+}
+
+static int bcm6328_leds_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = pdev->dev.of_node;
+	struct device_node *child;
+	struct resource *mem_r;
+	void __iomem *mem;
+	spinlock_t *lock;
+	unsigned long val, *blink_leds, *blink_delay;
+
+	mem_r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!mem_r)
+		return -EINVAL;
+
+	mem = devm_ioremap_resource(dev, mem_r);
+	if (IS_ERR(mem))
+		return PTR_ERR(mem);
+
+	lock = devm_kzalloc(dev, sizeof(*lock), GFP_KERNEL);
+	if (!lock)
+		return -ENOMEM;
+
+	blink_leds = devm_kzalloc(dev, sizeof(*blink_leds), GFP_KERNEL);
+	if (!blink_leds)
+		return -ENOMEM;
+
+	blink_delay = devm_kzalloc(dev, sizeof(*blink_delay), GFP_KERNEL);
+	if (!blink_delay)
+		return -ENOMEM;
+
+	spin_lock_init(lock);
+
+	bcm6328_led_write(mem + BCM6328_REG_HWDIS, ~0);
+	bcm6328_led_write(mem + BCM6328_REG_LNKACTSEL_HI, 0);
+	bcm6328_led_write(mem + BCM6328_REG_LNKACTSEL_LO, 0);
+
+	val = bcm6328_led_read(mem + BCM6328_REG_INIT);
+	val &= ~BCM6328_SERIAL_LED_EN;
+	if (of_property_read_bool(np, "brcm,serial-leds"))
+		val |= BCM6328_SERIAL_LED_EN;
+	bcm6328_led_write(mem + BCM6328_REG_INIT, val);
+
+	for_each_available_child_of_node(np, child) {
+		int rc;
+		u32 reg;
+
+		if (of_property_read_u32(child, "reg", &reg))
+			continue;
+
+		if (reg >= BCM6328_LED_MAX_COUNT) {
+			dev_err(dev, "invalid LED (>= %d)\n",
+				BCM6328_LED_MAX_COUNT);
+			continue;
+		}
+
+		if (of_property_read_bool(child, "brcm,hardware-controlled"))
+			rc = bcm6328_hwled(dev, child, reg, mem, lock);
+		else
+			rc = bcm6328_led(dev, child, reg, mem, lock,
+					 blink_leds, blink_delay);
+
+		if (rc < 0)
+			return rc;
+	}
+
+	return 0;
+}
+
+static const struct of_device_id bcm6328_leds_of_match[] = {
+	{ .compatible = "brcm,bcm6328-leds", },
+	{ },
+};
+
+static struct platform_driver bcm6328_leds_driver = {
+	.probe = bcm6328_leds_probe,
+	.driver = {
+		.name = "leds-bcm6328",
+		.of_match_table = bcm6328_leds_of_match,
+	},
+};
+
+module_platform_driver(bcm6328_leds_driver);
+
+MODULE_AUTHOR("Álvaro Fernández Rojas <noltari@gmail.com>");
+MODULE_AUTHOR("Jonas Gorski <jogo@openwrt.org>");
+MODULE_DESCRIPTION("LED driver for BCM6328 controllers");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:leds-bcm6328");
diff --git a/drivers/leds/leds-bcm6358.c b/drivers/leds/leds-bcm6358.c
new file mode 100644
index 0000000..21f9693
--- /dev/null
+++ b/drivers/leds/leds-bcm6358.c
@@ -0,0 +1,243 @@
+/*
+ * Driver for BCM6358 memory-mapped LEDs, based on leds-syscon.c
+ *
+ * Copyright 2015 Álvaro Fernández Rojas <noltari@gmail.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/leds.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+
+#define BCM6358_REG_MODE		0x0
+#define BCM6358_REG_CTRL		0x4
+
+#define BCM6358_SLED_CLKDIV_MASK	3
+#define BCM6358_SLED_CLKDIV_1		0
+#define BCM6358_SLED_CLKDIV_2		1
+#define BCM6358_SLED_CLKDIV_4		2
+#define BCM6358_SLED_CLKDIV_8		3
+
+#define BCM6358_SLED_POLARITY		BIT(2)
+#define BCM6358_SLED_BUSY		BIT(3)
+
+#define BCM6358_SLED_MAX_COUNT		32
+#define BCM6358_SLED_WAIT		100
+
+/**
+ * struct bcm6358_led - state container for bcm6358 based LEDs
+ * @cdev: LED class device for this LED
+ * @mem: memory resource
+ * @lock: memory lock
+ * @pin: LED pin number
+ * @active_low: LED is active low
+ */
+struct bcm6358_led {
+	struct led_classdev cdev;
+	void __iomem *mem;
+	spinlock_t *lock;
+	unsigned long pin;
+	bool active_low;
+};
+
+static void bcm6358_led_write(void __iomem *reg, unsigned long data)
+{
+	iowrite32be(data, reg);
+}
+
+static unsigned long bcm6358_led_read(void __iomem *reg)
+{
+	return ioread32be(reg);
+}
+
+static unsigned long bcm6358_led_busy(void __iomem *mem)
+{
+	unsigned long val;
+
+	while ((val = bcm6358_led_read(mem + BCM6358_REG_CTRL)) &
+		BCM6358_SLED_BUSY)
+		udelay(BCM6358_SLED_WAIT);
+
+	return val;
+}
+
+static void bcm6358_led_mode(struct bcm6358_led *led, unsigned long value)
+{
+	unsigned long val;
+
+	bcm6358_led_busy(led->mem);
+
+	val = bcm6358_led_read(led->mem + BCM6358_REG_MODE);
+	if ((led->active_low && value == LED_OFF) ||
+	    (!led->active_low && value != LED_OFF))
+		val |= BIT(led->pin);
+	else
+		val &= ~(BIT(led->pin));
+	bcm6358_led_write(led->mem + BCM6358_REG_MODE, val);
+}
+
+static void bcm6358_led_set(struct led_classdev *led_cdev,
+			    enum led_brightness value)
+{
+	struct bcm6358_led *led =
+		container_of(led_cdev, struct bcm6358_led, cdev);
+	unsigned long flags;
+
+	spin_lock_irqsave(led->lock, flags);
+	bcm6358_led_mode(led, value);
+	spin_unlock_irqrestore(led->lock, flags);
+}
+
+static int bcm6358_led(struct device *dev, struct device_node *nc, u32 reg,
+		       void __iomem *mem, spinlock_t *lock)
+{
+	struct bcm6358_led *led;
+	unsigned long flags;
+	const char *state;
+	int rc;
+
+	led = devm_kzalloc(dev, sizeof(*led), GFP_KERNEL);
+	if (!led)
+		return -ENOMEM;
+
+	led->pin = reg;
+	led->mem = mem;
+	led->lock = lock;
+
+	if (of_property_read_bool(nc, "active-low"))
+		led->active_low = true;
+
+	led->cdev.name = of_get_property(nc, "label", NULL) ? : nc->name;
+	led->cdev.default_trigger = of_get_property(nc,
+						    "linux,default-trigger",
+						    NULL);
+
+	spin_lock_irqsave(lock, flags);
+	if (!of_property_read_string(nc, "default-state", &state)) {
+		if (!strcmp(state, "on")) {
+			led->cdev.brightness = LED_FULL;
+		} else if (!strcmp(state, "keep")) {
+			unsigned long val;
+
+			bcm6358_led_busy(led->mem);
+
+			val = bcm6358_led_read(led->mem + BCM6358_REG_MODE);
+			val &= BIT(led->pin);
+			if ((led->active_low && !val) ||
+			    (!led->active_low && val))
+				led->cdev.brightness = LED_FULL;
+			else
+				led->cdev.brightness = LED_OFF;
+		} else {
+			led->cdev.brightness = LED_OFF;
+		}
+	} else {
+		led->cdev.brightness = LED_OFF;
+	}
+	bcm6358_led_mode(led, led->cdev.brightness);
+	spin_unlock_irqrestore(lock, flags);
+
+	led->cdev.brightness_set = bcm6358_led_set;
+
+	rc = led_classdev_register(dev, &led->cdev);
+	if (rc < 0)
+		return rc;
+
+	dev_dbg(dev, "registered LED %s\n", led->cdev.name);
+
+	return 0;
+}
+
+static int bcm6358_leds_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = pdev->dev.of_node;
+	struct device_node *child;
+	struct resource *mem_r;
+	void __iomem *mem;
+	spinlock_t *lock; /* memory lock */
+	unsigned long val;
+	u32 clk_div;
+
+	mem_r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!mem_r)
+		return -EINVAL;
+
+	mem = devm_ioremap_resource(dev, mem_r);
+	if (IS_ERR(mem))
+		return PTR_ERR(mem);
+
+	lock = devm_kzalloc(dev, sizeof(*lock), GFP_KERNEL);
+	if (!lock)
+		return -ENOMEM;
+
+	spin_lock_init(lock);
+
+	val = bcm6358_led_busy(mem);
+	val &= ~(BCM6358_SLED_POLARITY | BCM6358_SLED_CLKDIV_MASK);
+	if (of_property_read_bool(np, "brcm,clk-dat-low"))
+		val |= BCM6358_SLED_POLARITY;
+	of_property_read_u32(np, "brcm,clk-div", &clk_div);
+	switch (clk_div) {
+	case 8:
+		val |= BCM6358_SLED_CLKDIV_8;
+		break;
+	case 4:
+		val |= BCM6358_SLED_CLKDIV_4;
+		break;
+	case 2:
+		val |= BCM6358_SLED_CLKDIV_2;
+		break;
+	default:
+		val |= BCM6358_SLED_CLKDIV_1;
+		break;
+	}
+	bcm6358_led_write(mem + BCM6358_REG_CTRL, val);
+
+	for_each_available_child_of_node(np, child) {
+		int rc;
+		u32 reg;
+
+		if (of_property_read_u32(child, "reg", &reg))
+			continue;
+
+		if (reg >= BCM6358_SLED_MAX_COUNT) {
+			dev_err(dev, "invalid LED (%u >= %d)\n", reg,
+				BCM6358_SLED_MAX_COUNT);
+			continue;
+		}
+
+		rc = bcm6358_led(dev, child, reg, mem, lock);
+		if (rc < 0)
+			return rc;
+	}
+
+	return 0;
+}
+
+static const struct of_device_id bcm6358_leds_of_match[] = {
+	{ .compatible = "brcm,bcm6358-leds", },
+	{ },
+};
+
+static struct platform_driver bcm6358_leds_driver = {
+	.probe = bcm6358_leds_probe,
+	.driver = {
+		.name = "leds-bcm6358",
+		.of_match_table = bcm6358_leds_of_match,
+	},
+};
+
+module_platform_driver(bcm6358_leds_driver);
+
+MODULE_AUTHOR("Álvaro Fernández Rojas <noltari@gmail.com>");
+MODULE_DESCRIPTION("LED driver for BCM6358 controllers");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:leds-bcm6358");
diff --git a/drivers/leds/leds-cobalt-raq.c b/drivers/leds/leds-cobalt-raq.c
index 06dbe18..b316df4 100644
--- a/drivers/leds/leds-cobalt-raq.c
+++ b/drivers/leds/leds-cobalt-raq.c
@@ -108,20 +108,8 @@
 	return retval;
 }
 
-static int cobalt_raq_led_remove(struct platform_device *pdev)
-{
-	led_classdev_unregister(&raq_power_off_led);
-	led_classdev_unregister(&raq_web_led);
-
-	if (led_port)
-		led_port = NULL;
-
-	return 0;
-}
-
 static struct platform_driver cobalt_raq_led_driver = {
 	.probe	= cobalt_raq_led_probe,
-	.remove	= cobalt_raq_led_remove,
 	.driver = {
 		.name	= "cobalt-raq-leds",
 	},
@@ -131,5 +119,4 @@
 {
 	return platform_driver_register(&cobalt_raq_led_driver);
 }
-
-module_init(cobalt_raq_led_init);
+device_initcall(cobalt_raq_led_init);
diff --git a/drivers/leds/leds-gpio.c b/drivers/leds/leds-gpio.c
index 15eb3f8..af1876a 100644
--- a/drivers/leds/leds-gpio.c
+++ b/drivers/leds/leds-gpio.c
@@ -16,6 +16,7 @@
 #include <linux/kernel.h>
 #include <linux/leds.h>
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/property.h>
 #include <linux/slab.h>
@@ -191,15 +192,17 @@
 			goto err;
 		}
 
-		np = of_node(child);
+		np = to_of_node(child);
 
 		if (fwnode_property_present(child, "label")) {
 			fwnode_property_read_string(child, "label", &led.name);
 		} else {
 			if (IS_ENABLED(CONFIG_OF) && !led.name && np)
 				led.name = np->name;
-			if (!led.name)
-				return ERR_PTR(-EINVAL);
+			if (!led.name) {
+				ret = -EINVAL;
+				goto err;
+			}
 		}
 		fwnode_property_read_string(child, "linux,default-trigger",
 					    &led.default_trigger);
@@ -217,18 +220,19 @@
 		if (fwnode_property_present(child, "retain-state-suspended"))
 			led.retain_state_suspended = 1;
 
-		ret = create_gpio_led(&led, &priv->leds[priv->num_leds++],
+		ret = create_gpio_led(&led, &priv->leds[priv->num_leds],
 				      dev, NULL);
 		if (ret < 0) {
 			fwnode_handle_put(child);
 			goto err;
 		}
+		priv->num_leds++;
 	}
 
 	return priv;
 
 err:
-	for (count = priv->num_leds - 2; count >= 0; count--)
+	for (count = priv->num_leds - 1; count >= 0; count--)
 		delete_gpio_led(&priv->leds[count]);
 	return ERR_PTR(ret);
 }
diff --git a/drivers/leds/leds-ktd2692.c b/drivers/leds/leds-ktd2692.c
new file mode 100644
index 0000000..2ae8c4d
--- /dev/null
+++ b/drivers/leds/leds-ktd2692.c
@@ -0,0 +1,443 @@
+/*
+ * LED driver : leds-ktd2692.c
+ *
+ * Copyright (C) 2015 Samsung Electronics
+ * Ingi Kim <ingi2.kim@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/gpio/consumer.h>
+#include <linux/led-class-flash.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/consumer.h>
+#include <linux/workqueue.h>
+
+/* Value related the movie mode */
+#define KTD2692_MOVIE_MODE_CURRENT_LEVELS	16
+#define KTD2692_MM_TO_FL_RATIO(x)		((x) / 3)
+#define KTD2962_MM_MIN_CURR_THRESHOLD_SCALE	8
+
+/* Value related the flash mode */
+#define KTD2692_FLASH_MODE_TIMEOUT_LEVELS	8
+#define KTD2692_FLASH_MODE_TIMEOUT_DISABLE	0
+#define KTD2692_FLASH_MODE_CURR_PERCENT(x)	(((x) * 16) / 100)
+
+/* Macro for getting offset of flash timeout */
+#define GET_TIMEOUT_OFFSET(timeout, step)	((timeout) / (step))
+
+/* Base register address */
+#define KTD2692_REG_LVP_BASE			0x00
+#define KTD2692_REG_FLASH_TIMEOUT_BASE		0x20
+#define KTD2692_REG_MM_MIN_CURR_THRESHOLD_BASE	0x40
+#define KTD2692_REG_MOVIE_CURRENT_BASE		0x60
+#define KTD2692_REG_FLASH_CURRENT_BASE		0x80
+#define KTD2692_REG_MODE_BASE			0xA0
+
+/* Set bit coding time for expresswire interface */
+#define KTD2692_TIME_RESET_US			700
+#define KTD2692_TIME_DATA_START_TIME_US		10
+#define KTD2692_TIME_HIGH_END_OF_DATA_US	350
+#define KTD2692_TIME_LOW_END_OF_DATA_US		10
+#define KTD2692_TIME_SHORT_BITSET_US		4
+#define KTD2692_TIME_LONG_BITSET_US		12
+
+/* KTD2692 default length of name */
+#define KTD2692_NAME_LENGTH			20
+
+enum ktd2692_bitset {
+	KTD2692_LOW = 0,
+	KTD2692_HIGH,
+};
+
+/* Movie / Flash Mode Control */
+enum ktd2692_led_mode {
+	KTD2692_MODE_DISABLE = 0,	/* default */
+	KTD2692_MODE_MOVIE,
+	KTD2692_MODE_FLASH,
+};
+
+struct ktd2692_led_config_data {
+	/* maximum LED current in movie mode */
+	u32 movie_max_microamp;
+	/* maximum LED current in flash mode */
+	u32 flash_max_microamp;
+	/* maximum flash timeout */
+	u32 flash_max_timeout;
+	/* max LED brightness level */
+	enum led_brightness max_brightness;
+};
+
+struct ktd2692_context {
+	/* Related LED Flash class device */
+	struct led_classdev_flash fled_cdev;
+
+	/* secures access to the device */
+	struct mutex lock;
+	struct regulator *regulator;
+	struct work_struct work_brightness_set;
+
+	struct gpio_desc *aux_gpio;
+	struct gpio_desc *ctrl_gpio;
+
+	enum ktd2692_led_mode mode;
+	enum led_brightness torch_brightness;
+};
+
+static struct ktd2692_context *fled_cdev_to_led(
+				struct led_classdev_flash *fled_cdev)
+{
+	return container_of(fled_cdev, struct ktd2692_context, fled_cdev);
+}
+
+static void ktd2692_expresswire_start(struct ktd2692_context *led)
+{
+	gpiod_direction_output(led->ctrl_gpio, KTD2692_HIGH);
+	udelay(KTD2692_TIME_DATA_START_TIME_US);
+}
+
+static void ktd2692_expresswire_reset(struct ktd2692_context *led)
+{
+	gpiod_direction_output(led->ctrl_gpio, KTD2692_LOW);
+	udelay(KTD2692_TIME_RESET_US);
+}
+
+static void ktd2692_expresswire_end(struct ktd2692_context *led)
+{
+	gpiod_direction_output(led->ctrl_gpio, KTD2692_LOW);
+	udelay(KTD2692_TIME_LOW_END_OF_DATA_US);
+	gpiod_direction_output(led->ctrl_gpio, KTD2692_HIGH);
+	udelay(KTD2692_TIME_HIGH_END_OF_DATA_US);
+}
+
+static void ktd2692_expresswire_set_bit(struct ktd2692_context *led, bool bit)
+{
+	/*
+	 * The Low Bit(0) and High Bit(1) is based on a time detection
+	 * algorithm between time low and time high
+	 * Time_(L_LB) : Low time of the Low Bit(0)
+	 * Time_(H_LB) : High time of the LOW Bit(0)
+	 * Time_(L_HB) : Low time of the High Bit(1)
+	 * Time_(H_HB) : High time of the High Bit(1)
+	 *
+	 * It can be simplified to:
+	 * Low Bit(0) : 2 * Time_(H_LB) < Time_(L_LB)
+	 * High Bit(1) : 2 * Time_(L_HB) < Time_(H_HB)
+	 * HIGH  ___           ____    _..     _________    ___
+	 *          |_________|    |_..  |____|         |__|
+	 * LOW        <L_LB>  <H_LB>     <L_HB>  <H_HB>
+	 *          [  Low Bit (0) ]     [  High Bit(1) ]
+	 */
+	if (bit) {
+		gpiod_direction_output(led->ctrl_gpio, KTD2692_LOW);
+		udelay(KTD2692_TIME_SHORT_BITSET_US);
+		gpiod_direction_output(led->ctrl_gpio, KTD2692_HIGH);
+		udelay(KTD2692_TIME_LONG_BITSET_US);
+	} else {
+		gpiod_direction_output(led->ctrl_gpio, KTD2692_LOW);
+		udelay(KTD2692_TIME_LONG_BITSET_US);
+		gpiod_direction_output(led->ctrl_gpio, KTD2692_HIGH);
+		udelay(KTD2692_TIME_SHORT_BITSET_US);
+	}
+}
+
+static void ktd2692_expresswire_write(struct ktd2692_context *led, u8 value)
+{
+	int i;
+
+	ktd2692_expresswire_start(led);
+	for (i = 7; i >= 0; i--)
+		ktd2692_expresswire_set_bit(led, value & BIT(i));
+	ktd2692_expresswire_end(led);
+}
+
+static void ktd2692_brightness_set(struct ktd2692_context *led,
+				   enum led_brightness brightness)
+{
+	mutex_lock(&led->lock);
+
+	if (brightness == LED_OFF) {
+		led->mode = KTD2692_MODE_DISABLE;
+		gpiod_direction_output(led->aux_gpio, KTD2692_LOW);
+	} else {
+		ktd2692_expresswire_write(led, brightness |
+					KTD2692_REG_MOVIE_CURRENT_BASE);
+		led->mode = KTD2692_MODE_MOVIE;
+	}
+
+	ktd2692_expresswire_write(led, led->mode | KTD2692_REG_MODE_BASE);
+	mutex_unlock(&led->lock);
+}
+
+static void ktd2692_brightness_set_work(struct work_struct *work)
+{
+	struct ktd2692_context *led =
+		container_of(work, struct ktd2692_context, work_brightness_set);
+
+	ktd2692_brightness_set(led, led->torch_brightness);
+}
+
+static void ktd2692_led_brightness_set(struct led_classdev *led_cdev,
+				       enum led_brightness brightness)
+{
+	struct led_classdev_flash *fled_cdev = lcdev_to_flcdev(led_cdev);
+	struct ktd2692_context *led = fled_cdev_to_led(fled_cdev);
+
+	led->torch_brightness = brightness;
+	schedule_work(&led->work_brightness_set);
+}
+
+static int ktd2692_led_brightness_set_sync(struct led_classdev *led_cdev,
+					   enum led_brightness brightness)
+{
+	struct led_classdev_flash *fled_cdev = lcdev_to_flcdev(led_cdev);
+	struct ktd2692_context *led = fled_cdev_to_led(fled_cdev);
+
+	ktd2692_brightness_set(led, brightness);
+
+	return 0;
+}
+
+static int ktd2692_led_flash_strobe_set(struct led_classdev_flash *fled_cdev,
+					bool state)
+{
+	struct ktd2692_context *led = fled_cdev_to_led(fled_cdev);
+	struct led_flash_setting *timeout = &fled_cdev->timeout;
+	u32 flash_tm_reg;
+
+	mutex_lock(&led->lock);
+
+	if (state) {
+		flash_tm_reg = GET_TIMEOUT_OFFSET(timeout->val, timeout->step);
+		ktd2692_expresswire_write(led, flash_tm_reg
+				| KTD2692_REG_FLASH_TIMEOUT_BASE);
+
+		led->mode = KTD2692_MODE_FLASH;
+		gpiod_direction_output(led->aux_gpio, KTD2692_HIGH);
+	} else {
+		led->mode = KTD2692_MODE_DISABLE;
+		gpiod_direction_output(led->aux_gpio, KTD2692_LOW);
+	}
+
+	ktd2692_expresswire_write(led, led->mode | KTD2692_REG_MODE_BASE);
+
+	fled_cdev->led_cdev.brightness = LED_OFF;
+	led->mode = KTD2692_MODE_DISABLE;
+
+	mutex_unlock(&led->lock);
+
+	return 0;
+}
+
+static int ktd2692_led_flash_timeout_set(struct led_classdev_flash *fled_cdev,
+					 u32 timeout)
+{
+	return 0;
+}
+
+static void ktd2692_init_movie_current_max(struct ktd2692_led_config_data *cfg)
+{
+	u32 offset, step;
+	u32 movie_current_microamp;
+
+	offset = KTD2692_MOVIE_MODE_CURRENT_LEVELS;
+	step = KTD2692_MM_TO_FL_RATIO(cfg->flash_max_microamp)
+		/ KTD2692_MOVIE_MODE_CURRENT_LEVELS;
+
+	do {
+		movie_current_microamp = step * offset;
+		offset--;
+	} while ((movie_current_microamp > cfg->movie_max_microamp) &&
+		(offset > 0));
+
+	cfg->max_brightness = offset;
+}
+
+static void ktd2692_init_flash_timeout(struct led_classdev_flash *fled_cdev,
+				       struct ktd2692_led_config_data *cfg)
+{
+	struct led_flash_setting *setting;
+
+	setting = &fled_cdev->timeout;
+	setting->min = KTD2692_FLASH_MODE_TIMEOUT_DISABLE;
+	setting->max = cfg->flash_max_timeout;
+	setting->step = cfg->flash_max_timeout
+			/ (KTD2692_FLASH_MODE_TIMEOUT_LEVELS - 1);
+	setting->val = cfg->flash_max_timeout;
+}
+
+static void ktd2692_setup(struct ktd2692_context *led)
+{
+	led->mode = KTD2692_MODE_DISABLE;
+	ktd2692_expresswire_reset(led);
+	gpiod_direction_output(led->aux_gpio, KTD2692_LOW);
+
+	ktd2692_expresswire_write(led, (KTD2962_MM_MIN_CURR_THRESHOLD_SCALE - 1)
+				 | KTD2692_REG_MM_MIN_CURR_THRESHOLD_BASE);
+	ktd2692_expresswire_write(led, KTD2692_FLASH_MODE_CURR_PERCENT(45)
+				 | KTD2692_REG_FLASH_CURRENT_BASE);
+}
+
+static int ktd2692_parse_dt(struct ktd2692_context *led, struct device *dev,
+			    struct ktd2692_led_config_data *cfg)
+{
+	struct device_node *np = dev->of_node;
+	struct device_node *child_node;
+	int ret;
+
+	if (!dev->of_node)
+		return -ENXIO;
+
+	led->ctrl_gpio = devm_gpiod_get(dev, "ctrl", GPIOD_ASIS);
+	if (IS_ERR(led->ctrl_gpio)) {
+		ret = PTR_ERR(led->ctrl_gpio);
+		dev_err(dev, "cannot get ctrl-gpios %d\n", ret);
+		return ret;
+	}
+
+	led->aux_gpio = devm_gpiod_get(dev, "aux", GPIOD_ASIS);
+	if (IS_ERR(led->aux_gpio)) {
+		ret = PTR_ERR(led->aux_gpio);
+		dev_err(dev, "cannot get aux-gpios %d\n", ret);
+		return ret;
+	}
+
+	led->regulator = devm_regulator_get(dev, "vin");
+	if (IS_ERR(led->regulator))
+		led->regulator = NULL;
+
+	if (led->regulator) {
+		ret = regulator_enable(led->regulator);
+		if (ret)
+			dev_err(dev, "Failed to enable supply: %d\n", ret);
+	}
+
+	child_node = of_get_next_available_child(np, NULL);
+	if (!child_node) {
+		dev_err(dev, "No DT child node found for connected LED.\n");
+		return -EINVAL;
+	}
+
+	led->fled_cdev.led_cdev.name =
+		of_get_property(child_node, "label", NULL) ? : child_node->name;
+
+	ret = of_property_read_u32(child_node, "led-max-microamp",
+				   &cfg->movie_max_microamp);
+	if (ret) {
+		dev_err(dev, "failed to parse led-max-microamp\n");
+		return ret;
+	}
+
+	ret = of_property_read_u32(child_node, "flash-max-microamp",
+				   &cfg->flash_max_microamp);
+	if (ret) {
+		dev_err(dev, "failed to parse flash-max-microamp\n");
+		return ret;
+	}
+
+	ret = of_property_read_u32(child_node, "flash-max-timeout-us",
+				   &cfg->flash_max_timeout);
+	if (ret)
+		dev_err(dev, "failed to parse flash-max-timeout-us\n");
+
+	of_node_put(child_node);
+	return ret;
+}
+
+static const struct led_flash_ops flash_ops = {
+	.strobe_set = ktd2692_led_flash_strobe_set,
+	.timeout_set = ktd2692_led_flash_timeout_set,
+};
+
+static int ktd2692_probe(struct platform_device *pdev)
+{
+	struct ktd2692_context *led;
+	struct led_classdev *led_cdev;
+	struct led_classdev_flash *fled_cdev;
+	struct ktd2692_led_config_data led_cfg;
+	int ret;
+
+	led = devm_kzalloc(&pdev->dev, sizeof(*led), GFP_KERNEL);
+	if (!led)
+		return -ENOMEM;
+
+	fled_cdev = &led->fled_cdev;
+	led_cdev = &fled_cdev->led_cdev;
+
+	ret = ktd2692_parse_dt(led, &pdev->dev, &led_cfg);
+	if (ret)
+		return ret;
+
+	ktd2692_init_flash_timeout(fled_cdev, &led_cfg);
+	ktd2692_init_movie_current_max(&led_cfg);
+
+	fled_cdev->ops = &flash_ops;
+
+	led_cdev->max_brightness = led_cfg.max_brightness;
+	led_cdev->brightness_set = ktd2692_led_brightness_set;
+	led_cdev->brightness_set_sync = ktd2692_led_brightness_set_sync;
+	led_cdev->flags |= LED_CORE_SUSPENDRESUME | LED_DEV_CAP_FLASH;
+
+	mutex_init(&led->lock);
+	INIT_WORK(&led->work_brightness_set, ktd2692_brightness_set_work);
+
+	platform_set_drvdata(pdev, led);
+
+	ret = led_classdev_flash_register(&pdev->dev, fled_cdev);
+	if (ret) {
+		dev_err(&pdev->dev, "can't register LED %s\n", led_cdev->name);
+		mutex_destroy(&led->lock);
+		return ret;
+	}
+
+	ktd2692_setup(led);
+
+	return 0;
+}
+
+static int ktd2692_remove(struct platform_device *pdev)
+{
+	struct ktd2692_context *led = platform_get_drvdata(pdev);
+	int ret;
+
+	led_classdev_flash_unregister(&led->fled_cdev);
+	cancel_work_sync(&led->work_brightness_set);
+
+	if (led->regulator) {
+		ret = regulator_disable(led->regulator);
+		if (ret)
+			dev_err(&pdev->dev,
+				"Failed to disable supply: %d\n", ret);
+	}
+
+	mutex_destroy(&led->lock);
+
+	return 0;
+}
+
+static const struct of_device_id ktd2692_match[] = {
+	{ .compatible = "kinetic,ktd2692", },
+	{ /* sentinel */ },
+};
+
+static struct platform_driver ktd2692_driver = {
+	.driver = {
+		.name  = "ktd2692",
+		.of_match_table = ktd2692_match,
+	},
+	.probe  = ktd2692_probe,
+	.remove = ktd2692_remove,
+};
+
+module_platform_driver(ktd2692_driver);
+
+MODULE_AUTHOR("Ingi Kim <ingi2.kim@samsung.com>");
+MODULE_DESCRIPTION("Kinetic KTD2692 LED driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/leds-lp5523.c b/drivers/leds/leds-lp5523.c
index 9e1716f..584dbbc 100644
--- a/drivers/leds/leds-lp5523.c
+++ b/drivers/leds/leds-lp5523.c
@@ -50,6 +50,7 @@
 #define LP5523_REG_OP_MODE		0x01
 #define LP5523_REG_ENABLE_LEDS_MSB	0x04
 #define LP5523_REG_ENABLE_LEDS_LSB	0x05
+#define LP5523_REG_LED_CTRL_BASE	0x06
 #define LP5523_REG_LED_PWM_BASE		0x16
 #define LP5523_REG_LED_CURRENT_BASE	0x26
 #define LP5523_REG_CONFIG		0x36
@@ -57,6 +58,7 @@
 #define LP5523_REG_RESET		0x3D
 #define LP5523_REG_LED_TEST_CTRL	0x41
 #define LP5523_REG_LED_TEST_ADC		0x42
+#define LP5523_REG_MASTER_FADER_BASE	0x48
 #define LP5523_REG_CH1_PROG_START	0x4C
 #define LP5523_REG_CH2_PROG_START	0x4D
 #define LP5523_REG_CH3_PROG_START	0x4E
@@ -78,6 +80,9 @@
 #define LP5523_EXT_CLK_USED		0x08
 #define LP5523_ENG_STATUS_MASK		0x07
 
+#define LP5523_FADER_MAPPING_MASK	0xC0
+#define LP5523_FADER_MAPPING_SHIFT	6
+
 /* Memory Page Selection */
 #define LP5523_PAGE_ENG1		0
 #define LP5523_PAGE_ENG2		1
@@ -666,6 +671,137 @@
 	return pos;
 }
 
+#define show_fader(nr)						\
+static ssize_t show_master_fader##nr(struct device *dev,	\
+			    struct device_attribute *attr,	\
+			    char *buf)				\
+{								\
+	return show_master_fader(dev, attr, buf, nr);		\
+}
+
+#define store_fader(nr)						\
+static ssize_t store_master_fader##nr(struct device *dev,	\
+			     struct device_attribute *attr,	\
+			     const char *buf, size_t len)	\
+{								\
+	return store_master_fader(dev, attr, buf, len, nr);	\
+}
+
+static ssize_t show_master_fader(struct device *dev,
+				 struct device_attribute *attr,
+				 char *buf, int nr)
+{
+	struct lp55xx_led *led = i2c_get_clientdata(to_i2c_client(dev));
+	struct lp55xx_chip *chip = led->chip;
+	int ret;
+	u8 val;
+
+	mutex_lock(&chip->lock);
+	ret = lp55xx_read(chip, LP5523_REG_MASTER_FADER_BASE + nr - 1, &val);
+	mutex_unlock(&chip->lock);
+
+	if (ret == 0)
+		ret = sprintf(buf, "%u\n", val);
+
+	return ret;
+}
+show_fader(1)
+show_fader(2)
+show_fader(3)
+
+static ssize_t store_master_fader(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t len, int nr)
+{
+	struct lp55xx_led *led = i2c_get_clientdata(to_i2c_client(dev));
+	struct lp55xx_chip *chip = led->chip;
+	int ret;
+	unsigned long val;
+
+	if (kstrtoul(buf, 0, &val))
+		return -EINVAL;
+
+	if (val > 0xff)
+		return -EINVAL;
+
+	mutex_lock(&chip->lock);
+	ret = lp55xx_write(chip, LP5523_REG_MASTER_FADER_BASE + nr - 1,
+			   (u8)val);
+	mutex_unlock(&chip->lock);
+
+	if (ret == 0)
+		ret = len;
+
+	return ret;
+}
+store_fader(1)
+store_fader(2)
+store_fader(3)
+
+static ssize_t show_master_fader_leds(struct device *dev,
+				      struct device_attribute *attr,
+				      char *buf)
+{
+	struct lp55xx_led *led = i2c_get_clientdata(to_i2c_client(dev));
+	struct lp55xx_chip *chip = led->chip;
+	int i, ret, pos = 0;
+	u8 val;
+
+	mutex_lock(&chip->lock);
+
+	for (i = 0; i < LP5523_MAX_LEDS; i++) {
+		ret = lp55xx_read(chip, LP5523_REG_LED_CTRL_BASE + i, &val);
+		if (ret)
+			goto leave;
+
+		val = (val & LP5523_FADER_MAPPING_MASK)
+			>> LP5523_FADER_MAPPING_SHIFT;
+		if (val > 3) {
+			ret = -EINVAL;
+			goto leave;
+		}
+		buf[pos++] = val + '0';
+	}
+	buf[pos++] = '\n';
+	ret = pos;
+leave:
+	mutex_unlock(&chip->lock);
+	return ret;
+}
+
+static ssize_t store_master_fader_leds(struct device *dev,
+				       struct device_attribute *attr,
+				       const char *buf, size_t len)
+{
+	struct lp55xx_led *led = i2c_get_clientdata(to_i2c_client(dev));
+	struct lp55xx_chip *chip = led->chip;
+	int i, n, ret;
+	u8 val;
+
+	n = min_t(int, len, LP5523_MAX_LEDS);
+
+	mutex_lock(&chip->lock);
+
+	for (i = 0; i < n; i++) {
+		if (buf[i] >= '0' && buf[i] <= '3') {
+			val = (buf[i] - '0') << LP5523_FADER_MAPPING_SHIFT;
+			ret = lp55xx_update_bits(chip,
+						 LP5523_REG_LED_CTRL_BASE + i,
+						 LP5523_FADER_MAPPING_MASK,
+						 val);
+			if (ret)
+				goto leave;
+		} else {
+			ret = -EINVAL;
+			goto leave;
+		}
+	}
+	ret = len;
+leave:
+	mutex_unlock(&chip->lock);
+	return ret;
+}
+
 static void lp5523_led_brightness_work(struct work_struct *work)
 {
 	struct lp55xx_led *led = container_of(work, struct lp55xx_led,
@@ -688,6 +824,14 @@
 static LP55XX_DEV_ATTR_WO(engine2_load, store_engine2_load);
 static LP55XX_DEV_ATTR_WO(engine3_load, store_engine3_load);
 static LP55XX_DEV_ATTR_RO(selftest, lp5523_selftest);
+static LP55XX_DEV_ATTR_RW(master_fader1, show_master_fader1,
+			  store_master_fader1);
+static LP55XX_DEV_ATTR_RW(master_fader2, show_master_fader2,
+			  store_master_fader2);
+static LP55XX_DEV_ATTR_RW(master_fader3, show_master_fader3,
+			  store_master_fader3);
+static LP55XX_DEV_ATTR_RW(master_fader_leds, show_master_fader_leds,
+			  store_master_fader_leds);
 
 static struct attribute *lp5523_attributes[] = {
 	&dev_attr_engine1_mode.attr,
@@ -700,6 +844,10 @@
 	&dev_attr_engine2_leds.attr,
 	&dev_attr_engine3_leds.attr,
 	&dev_attr_selftest.attr,
+	&dev_attr_master_fader1.attr,
+	&dev_attr_master_fader2.attr,
+	&dev_attr_master_fader3.attr,
+	&dev_attr_master_fader_leds.attr,
 	NULL,
 };
 
diff --git a/drivers/leds/leds-lp55xx-common.c b/drivers/leds/leds-lp55xx-common.c
index 77c26bc..96d51e9 100644
--- a/drivers/leds/leds-lp55xx-common.c
+++ b/drivers/leds/leds-lp55xx-common.c
@@ -223,7 +223,7 @@
 	const char *name = chip->cl->name;
 	struct device *dev = &chip->cl->dev;
 
-	return request_firmware_nowait(THIS_MODULE, true, name, dev,
+	return request_firmware_nowait(THIS_MODULE, false, name, dev,
 				GFP_KERNEL, chip, lp55xx_firmware_loaded);
 }
 
diff --git a/drivers/leds/leds-max77693.c b/drivers/leds/leds-max77693.c
new file mode 100644
index 0000000..b8b0eec
--- /dev/null
+++ b/drivers/leds/leds-max77693.c
@@ -0,0 +1,1097 @@
+/*
+ * LED Flash class driver for the flash cell of max77693 mfd.
+ *
+ *	Copyright (C) 2015, Samsung Electronics Co., Ltd.
+ *
+ *	Authors: Jacek Anaszewski <j.anaszewski@samsung.com>
+ *		 Andrzej Hajda <a.hajda@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ */
+
+#include <linux/led-class-flash.h>
+#include <linux/mfd/max77693.h>
+#include <linux/mfd/max77693-private.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+#include <media/v4l2-flash-led-class.h>
+
+#define MODE_OFF		0
+#define MODE_FLASH(a)		(1 << (a))
+#define MODE_TORCH(a)		(1 << (2 + (a)))
+#define MODE_FLASH_EXTERNAL(a)	(1 << (4 + (a)))
+
+#define MODE_FLASH_MASK		(MODE_FLASH(FLED1) | MODE_FLASH(FLED2) | \
+				 MODE_FLASH_EXTERNAL(FLED1) | \
+				 MODE_FLASH_EXTERNAL(FLED2))
+#define MODE_TORCH_MASK		(MODE_TORCH(FLED1) | MODE_TORCH(FLED2))
+
+#define FLED1_IOUT		(1 << 0)
+#define FLED2_IOUT		(1 << 1)
+
+enum max77693_fled {
+	FLED1,
+	FLED2,
+};
+
+enum max77693_led_mode {
+	FLASH,
+	TORCH,
+};
+
+struct max77693_led_config_data {
+	const char *label[2];
+	u32 iout_torch_max[2];
+	u32 iout_flash_max[2];
+	u32 flash_timeout_max[2];
+	u32 num_leds;
+	u32 boost_mode;
+	u32 boost_vout;
+	u32 low_vsys;
+};
+
+struct max77693_sub_led {
+	/* corresponding FLED output identifier */
+	int fled_id;
+	/* corresponding LED Flash class device */
+	struct led_classdev_flash fled_cdev;
+	/* assures led-triggers compatibility */
+	struct work_struct work_brightness_set;
+	/* V4L2 Flash device */
+	struct v4l2_flash *v4l2_flash;
+
+	/* brightness cache */
+	unsigned int torch_brightness;
+	/* flash timeout cache */
+	unsigned int flash_timeout;
+	/* flash faults that may have occurred */
+	u32 flash_faults;
+};
+
+struct max77693_led_device {
+	/* parent mfd regmap */
+	struct regmap *regmap;
+	/* platform device data */
+	struct platform_device *pdev;
+	/* secures access to the device */
+	struct mutex lock;
+
+	/* sub led data */
+	struct max77693_sub_led sub_leds[2];
+
+	/* maximum torch current values for FLED outputs */
+	u32 iout_torch_max[2];
+	/* maximum flash current values for FLED outputs */
+	u32 iout_flash_max[2];
+
+	/* current flash timeout cache */
+	unsigned int current_flash_timeout;
+	/* ITORCH register cache */
+	u8 torch_iout_reg;
+	/* mode of fled outputs */
+	unsigned int mode_flags;
+	/* recently strobed fled */
+	int strobing_sub_led_id;
+	/* bitmask of FLED outputs use state (bit 0. - FLED1, bit 1. - FLED2) */
+	u8 fled_mask;
+	/* FLED modes that can be set */
+	u8 allowed_modes;
+
+	/* arrangement of current outputs */
+	bool iout_joint;
+};
+
+static u8 max77693_led_iout_to_reg(u32 ua)
+{
+	if (ua < FLASH_IOUT_MIN)
+		ua = FLASH_IOUT_MIN;
+	return (ua - FLASH_IOUT_MIN) / FLASH_IOUT_STEP;
+}
+
+static u8 max77693_flash_timeout_to_reg(u32 us)
+{
+	return (us - FLASH_TIMEOUT_MIN) / FLASH_TIMEOUT_STEP;
+}
+
+static inline struct max77693_sub_led *flcdev_to_sub_led(
+					struct led_classdev_flash *fled_cdev)
+{
+	return container_of(fled_cdev, struct max77693_sub_led, fled_cdev);
+}
+
+static inline struct max77693_led_device *sub_led_to_led(
+					struct max77693_sub_led *sub_led)
+{
+	return container_of(sub_led, struct max77693_led_device,
+				sub_leds[sub_led->fled_id]);
+}
+
+static inline u8 max77693_led_vsys_to_reg(u32 mv)
+{
+	return ((mv - MAX_FLASH1_VSYS_MIN) / MAX_FLASH1_VSYS_STEP) << 2;
+}
+
+static inline u8 max77693_led_vout_to_reg(u32 mv)
+{
+	return (mv - FLASH_VOUT_MIN) / FLASH_VOUT_STEP + FLASH_VOUT_RMIN;
+}
+
+static inline bool max77693_fled_used(struct max77693_led_device *led,
+					 int fled_id)
+{
+	u8 fled_bit = (fled_id == FLED1) ? FLED1_IOUT : FLED2_IOUT;
+
+	return led->fled_mask & fled_bit;
+}
+
+static int max77693_set_mode_reg(struct max77693_led_device *led, u8 mode)
+{
+	struct regmap *rmap = led->regmap;
+	int ret, v = 0, i;
+
+	for (i = FLED1; i <= FLED2; ++i) {
+		if (mode & MODE_TORCH(i))
+			v |= FLASH_EN_ON << TORCH_EN_SHIFT(i);
+
+		if (mode & MODE_FLASH(i)) {
+			v |= FLASH_EN_ON << FLASH_EN_SHIFT(i);
+		} else if (mode & MODE_FLASH_EXTERNAL(i)) {
+			v |= FLASH_EN_FLASH << FLASH_EN_SHIFT(i);
+			/*
+			 * Enable hw triggering also for torch mode, as some
+			 * camera sensors use torch led to fathom ambient light
+			 * conditions before strobing the flash.
+			 */
+			v |= FLASH_EN_TORCH << TORCH_EN_SHIFT(i);
+		}
+	}
+
+	/* Reset the register only prior setting flash modes */
+	if (mode & ~(MODE_TORCH(FLED1) | MODE_TORCH(FLED2))) {
+		ret = regmap_write(rmap, MAX77693_LED_REG_FLASH_EN, 0);
+		if (ret < 0)
+			return ret;
+	}
+
+	return regmap_write(rmap, MAX77693_LED_REG_FLASH_EN, v);
+}
+
+static int max77693_add_mode(struct max77693_led_device *led, u8 mode)
+{
+	u8 new_mode_flags;
+	int i, ret;
+
+	if (led->iout_joint)
+		/* Span the mode on FLED2 for joint iouts case */
+		mode |= (mode << 1);
+
+	/*
+	 * FLASH_EXTERNAL mode activates FLASHEN and TORCHEN pins in the device.
+	 * Corresponding register bit fields interfere with SW triggered modes,
+	 * thus clear them to ensure proper device configuration.
+	 */
+	for (i = FLED1; i <= FLED2; ++i)
+		if (mode & MODE_FLASH_EXTERNAL(i))
+			led->mode_flags &= (~MODE_TORCH(i) & ~MODE_FLASH(i));
+
+	new_mode_flags = mode | led->mode_flags;
+	new_mode_flags &= led->allowed_modes;
+
+	if (new_mode_flags ^ led->mode_flags)
+		led->mode_flags = new_mode_flags;
+	else
+		return 0;
+
+	ret = max77693_set_mode_reg(led, led->mode_flags);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Clear flash mode flag after setting the mode to avoid spurious flash
+	 * strobing on each subsequent torch mode setting.
+	 */
+	if (mode & MODE_FLASH_MASK)
+		led->mode_flags &= ~mode;
+
+	return ret;
+}
+
+static int max77693_clear_mode(struct max77693_led_device *led,
+				u8 mode)
+{
+	if (led->iout_joint)
+		/* Clear mode also on FLED2 for joint iouts case */
+		mode |= (mode << 1);
+
+	led->mode_flags &= ~mode;
+
+	return max77693_set_mode_reg(led, led->mode_flags);
+}
+
+static void max77693_add_allowed_modes(struct max77693_led_device *led,
+				int fled_id, enum max77693_led_mode mode)
+{
+	if (mode == FLASH)
+		led->allowed_modes |= (MODE_FLASH(fled_id) |
+				       MODE_FLASH_EXTERNAL(fled_id));
+	else
+		led->allowed_modes |= MODE_TORCH(fled_id);
+}
+
+static void max77693_distribute_currents(struct max77693_led_device *led,
+				int fled_id, enum max77693_led_mode mode,
+				u32 micro_amp, u32 iout_max[2], u32 iout[2])
+{
+	if (!led->iout_joint) {
+		iout[fled_id] = micro_amp;
+		max77693_add_allowed_modes(led, fled_id, mode);
+		return;
+	}
+
+	iout[FLED1] = min(micro_amp, iout_max[FLED1]);
+	iout[FLED2] = micro_amp - iout[FLED1];
+
+	if (mode == FLASH)
+		led->allowed_modes &= ~MODE_FLASH_MASK;
+	else
+		led->allowed_modes &= ~MODE_TORCH_MASK;
+
+	max77693_add_allowed_modes(led, FLED1, mode);
+
+	if (iout[FLED2])
+		max77693_add_allowed_modes(led, FLED2, mode);
+}
+
+static int max77693_set_torch_current(struct max77693_led_device *led,
+				int fled_id, u32 micro_amp)
+{
+	struct regmap *rmap = led->regmap;
+	u8 iout1_reg = 0, iout2_reg = 0;
+	u32 iout[2];
+
+	max77693_distribute_currents(led, fled_id, TORCH, micro_amp,
+					led->iout_torch_max, iout);
+
+	if (fled_id == FLED1 || led->iout_joint) {
+		iout1_reg = max77693_led_iout_to_reg(iout[FLED1]);
+		led->torch_iout_reg &= TORCH_IOUT_MASK(TORCH_IOUT2_SHIFT);
+	}
+	if (fled_id == FLED2 || led->iout_joint) {
+		iout2_reg = max77693_led_iout_to_reg(iout[FLED2]);
+		led->torch_iout_reg &= TORCH_IOUT_MASK(TORCH_IOUT1_SHIFT);
+	}
+
+	led->torch_iout_reg |= ((iout1_reg << TORCH_IOUT1_SHIFT) |
+				(iout2_reg << TORCH_IOUT2_SHIFT));
+
+	return regmap_write(rmap, MAX77693_LED_REG_ITORCH,
+						led->torch_iout_reg);
+}
+
+static int max77693_set_flash_current(struct max77693_led_device *led,
+					int fled_id,
+					u32 micro_amp)
+{
+	struct regmap *rmap = led->regmap;
+	u8 iout1_reg, iout2_reg;
+	u32 iout[2];
+	int ret = -EINVAL;
+
+	max77693_distribute_currents(led, fled_id, FLASH, micro_amp,
+					led->iout_flash_max, iout);
+
+	if (fled_id == FLED1 || led->iout_joint) {
+		iout1_reg = max77693_led_iout_to_reg(iout[FLED1]);
+		ret = regmap_write(rmap, MAX77693_LED_REG_IFLASH1,
+							iout1_reg);
+		if (ret < 0)
+			return ret;
+	}
+	if (fled_id == FLED2 || led->iout_joint) {
+		iout2_reg = max77693_led_iout_to_reg(iout[FLED2]);
+		ret = regmap_write(rmap, MAX77693_LED_REG_IFLASH2,
+							iout2_reg);
+	}
+
+	return ret;
+}
+
+static int max77693_set_timeout(struct max77693_led_device *led, u32 microsec)
+{
+	struct regmap *rmap = led->regmap;
+	u8 v;
+	int ret;
+
+	v = max77693_flash_timeout_to_reg(microsec) | FLASH_TMR_LEVEL;
+
+	ret = regmap_write(rmap, MAX77693_LED_REG_FLASH_TIMER, v);
+	if (ret < 0)
+		return ret;
+
+	led->current_flash_timeout = microsec;
+
+	return 0;
+}
+
+static int max77693_get_strobe_status(struct max77693_led_device *led,
+					bool *state)
+{
+	struct regmap *rmap = led->regmap;
+	unsigned int v;
+	int ret;
+
+	ret = regmap_read(rmap, MAX77693_LED_REG_FLASH_STATUS, &v);
+	if (ret < 0)
+		return ret;
+
+	*state = v & FLASH_STATUS_FLASH_ON;
+
+	return ret;
+}
+
+static int max77693_get_flash_faults(struct max77693_sub_led *sub_led)
+{
+	struct max77693_led_device *led = sub_led_to_led(sub_led);
+	struct regmap *rmap = led->regmap;
+	unsigned int v;
+	u8 fault_open_mask, fault_short_mask;
+	int ret;
+
+	sub_led->flash_faults = 0;
+
+	if (led->iout_joint) {
+		fault_open_mask = FLASH_INT_FLED1_OPEN | FLASH_INT_FLED2_OPEN;
+		fault_short_mask = FLASH_INT_FLED1_SHORT |
+							FLASH_INT_FLED2_SHORT;
+	} else {
+		fault_open_mask = (sub_led->fled_id == FLED1) ?
+						FLASH_INT_FLED1_OPEN :
+						FLASH_INT_FLED2_OPEN;
+		fault_short_mask = (sub_led->fled_id == FLED1) ?
+						FLASH_INT_FLED1_SHORT :
+						FLASH_INT_FLED2_SHORT;
+	}
+
+	ret = regmap_read(rmap, MAX77693_LED_REG_FLASH_INT, &v);
+	if (ret < 0)
+		return ret;
+
+	if (v & fault_open_mask)
+		sub_led->flash_faults |= LED_FAULT_OVER_VOLTAGE;
+	if (v & fault_short_mask)
+		sub_led->flash_faults |= LED_FAULT_SHORT_CIRCUIT;
+	if (v & FLASH_INT_OVER_CURRENT)
+		sub_led->flash_faults |= LED_FAULT_OVER_CURRENT;
+
+	return 0;
+}
+
+static int max77693_setup(struct max77693_led_device *led,
+			 struct max77693_led_config_data *led_cfg)
+{
+	struct regmap *rmap = led->regmap;
+	int i, first_led, last_led, ret;
+	u32 max_flash_curr[2];
+	u8 v;
+
+	/*
+	 * Initialize only flash current. Torch current doesn't
+	 * require initialization as ITORCH register is written with
+	 * new value each time brightness_set op is called.
+	 */
+	if (led->iout_joint) {
+		first_led = FLED1;
+		last_led = FLED1;
+		max_flash_curr[FLED1] = led_cfg->iout_flash_max[FLED1] +
+					led_cfg->iout_flash_max[FLED2];
+	} else {
+		first_led = max77693_fled_used(led, FLED1) ? FLED1 : FLED2;
+		last_led = max77693_fled_used(led, FLED2) ? FLED2 : FLED1;
+		max_flash_curr[FLED1] = led_cfg->iout_flash_max[FLED1];
+		max_flash_curr[FLED2] = led_cfg->iout_flash_max[FLED2];
+	}
+
+	for (i = first_led; i <= last_led; ++i) {
+		ret = max77693_set_flash_current(led, i,
+					max_flash_curr[i]);
+		if (ret < 0)
+			return ret;
+	}
+
+	v = TORCH_TMR_NO_TIMER | MAX77693_LED_TRIG_TYPE_LEVEL;
+	ret = regmap_write(rmap, MAX77693_LED_REG_ITORCHTIMER, v);
+	if (ret < 0)
+		return ret;
+
+	if (led_cfg->low_vsys > 0)
+		v = max77693_led_vsys_to_reg(led_cfg->low_vsys) |
+						MAX_FLASH1_MAX_FL_EN;
+	else
+		v = 0;
+
+	ret = regmap_write(rmap, MAX77693_LED_REG_MAX_FLASH1, v);
+	if (ret < 0)
+		return ret;
+	ret = regmap_write(rmap, MAX77693_LED_REG_MAX_FLASH2, 0);
+	if (ret < 0)
+		return ret;
+
+	if (led_cfg->boost_mode == MAX77693_LED_BOOST_FIXED)
+		v = FLASH_BOOST_FIXED;
+	else
+		v = led_cfg->boost_mode | led_cfg->boost_mode << 1;
+
+	if (max77693_fled_used(led, FLED1) && max77693_fled_used(led, FLED2))
+		v |= FLASH_BOOST_LEDNUM_2;
+
+	ret = regmap_write(rmap, MAX77693_LED_REG_VOUT_CNTL, v);
+	if (ret < 0)
+		return ret;
+
+	v = max77693_led_vout_to_reg(led_cfg->boost_vout);
+	ret = regmap_write(rmap, MAX77693_LED_REG_VOUT_FLASH1, v);
+	if (ret < 0)
+		return ret;
+
+	return max77693_set_mode_reg(led, MODE_OFF);
+}
+
+static int __max77693_led_brightness_set(struct max77693_led_device *led,
+					int fled_id, enum led_brightness value)
+{
+	int ret;
+
+	mutex_lock(&led->lock);
+
+	if (value == 0) {
+		ret = max77693_clear_mode(led, MODE_TORCH(fled_id));
+		if (ret < 0)
+			dev_dbg(&led->pdev->dev,
+				"Failed to clear torch mode (%d)\n",
+				ret);
+		goto unlock;
+	}
+
+	ret = max77693_set_torch_current(led, fled_id, value * TORCH_IOUT_STEP);
+	if (ret < 0) {
+		dev_dbg(&led->pdev->dev,
+			"Failed to set torch current (%d)\n",
+			ret);
+		goto unlock;
+	}
+
+	ret = max77693_add_mode(led, MODE_TORCH(fled_id));
+	if (ret < 0)
+		dev_dbg(&led->pdev->dev,
+			"Failed to set torch mode (%d)\n",
+			ret);
+unlock:
+	mutex_unlock(&led->lock);
+	return ret;
+}
+
+static void max77693_led_brightness_set_work(
+					struct work_struct *work)
+{
+	struct max77693_sub_led *sub_led =
+			container_of(work, struct max77693_sub_led,
+					work_brightness_set);
+	struct max77693_led_device *led = sub_led_to_led(sub_led);
+
+	__max77693_led_brightness_set(led, sub_led->fled_id,
+				sub_led->torch_brightness);
+}
+
+/* LED subsystem callbacks */
+
+static int max77693_led_brightness_set_sync(
+				struct led_classdev *led_cdev,
+				enum led_brightness value)
+{
+	struct led_classdev_flash *fled_cdev = lcdev_to_flcdev(led_cdev);
+	struct max77693_sub_led *sub_led = flcdev_to_sub_led(fled_cdev);
+	struct max77693_led_device *led = sub_led_to_led(sub_led);
+
+	return __max77693_led_brightness_set(led, sub_led->fled_id, value);
+}
+
+static void max77693_led_brightness_set(
+				struct led_classdev *led_cdev,
+				enum led_brightness value)
+{
+	struct led_classdev_flash *fled_cdev = lcdev_to_flcdev(led_cdev);
+	struct max77693_sub_led *sub_led = flcdev_to_sub_led(fled_cdev);
+
+	sub_led->torch_brightness = value;
+	schedule_work(&sub_led->work_brightness_set);
+}
+
+static int max77693_led_flash_brightness_set(
+				struct led_classdev_flash *fled_cdev,
+				u32 brightness)
+{
+	struct max77693_sub_led *sub_led = flcdev_to_sub_led(fled_cdev);
+	struct max77693_led_device *led = sub_led_to_led(sub_led);
+	int ret;
+
+	mutex_lock(&led->lock);
+	ret = max77693_set_flash_current(led, sub_led->fled_id, brightness);
+	mutex_unlock(&led->lock);
+
+	return ret;
+}
+
+static int max77693_led_flash_strobe_set(
+				struct led_classdev_flash *fled_cdev,
+				bool state)
+{
+	struct max77693_sub_led *sub_led = flcdev_to_sub_led(fled_cdev);
+	struct max77693_led_device *led = sub_led_to_led(sub_led);
+	int fled_id = sub_led->fled_id;
+	int ret;
+
+	mutex_lock(&led->lock);
+
+	if (!state) {
+		ret = max77693_clear_mode(led, MODE_FLASH(fled_id));
+		goto unlock;
+	}
+
+	if (sub_led->flash_timeout != led->current_flash_timeout) {
+		ret = max77693_set_timeout(led, sub_led->flash_timeout);
+		if (ret < 0)
+			goto unlock;
+	}
+
+	led->strobing_sub_led_id = fled_id;
+
+	ret = max77693_add_mode(led, MODE_FLASH(fled_id));
+	if (ret < 0)
+		goto unlock;
+
+	ret = max77693_get_flash_faults(sub_led);
+
+unlock:
+	mutex_unlock(&led->lock);
+	return ret;
+}
+
+static int max77693_led_flash_fault_get(
+				struct led_classdev_flash *fled_cdev,
+				u32 *fault)
+{
+	struct max77693_sub_led *sub_led = flcdev_to_sub_led(fled_cdev);
+
+	*fault = sub_led->flash_faults;
+
+	return 0;
+}
+
+static int max77693_led_flash_strobe_get(
+				struct led_classdev_flash *fled_cdev,
+				bool *state)
+{
+	struct max77693_sub_led *sub_led = flcdev_to_sub_led(fled_cdev);
+	struct max77693_led_device *led = sub_led_to_led(sub_led);
+	int ret;
+
+	if (!state)
+		return -EINVAL;
+
+	mutex_lock(&led->lock);
+
+	ret = max77693_get_strobe_status(led, state);
+
+	*state = !!(*state && (led->strobing_sub_led_id == sub_led->fled_id));
+
+	mutex_unlock(&led->lock);
+
+	return ret;
+}
+
+static int max77693_led_flash_timeout_set(
+				struct led_classdev_flash *fled_cdev,
+				u32 timeout)
+{
+	struct max77693_sub_led *sub_led = flcdev_to_sub_led(fled_cdev);
+	struct max77693_led_device *led = sub_led_to_led(sub_led);
+
+	mutex_lock(&led->lock);
+	sub_led->flash_timeout = timeout;
+	mutex_unlock(&led->lock);
+
+	return 0;
+}
+
+static int max77693_led_parse_dt(struct max77693_led_device *led,
+				struct max77693_led_config_data *cfg,
+				struct device_node **sub_nodes)
+{
+	struct device *dev = &led->pdev->dev;
+	struct max77693_sub_led *sub_leds = led->sub_leds;
+	struct device_node *node = dev->of_node, *child_node;
+	struct property *prop;
+	u32 led_sources[2];
+	int i, ret, fled_id;
+
+	of_property_read_u32(node, "maxim,boost-mode", &cfg->boost_mode);
+	of_property_read_u32(node, "maxim,boost-mvout", &cfg->boost_vout);
+	of_property_read_u32(node, "maxim,mvsys-min", &cfg->low_vsys);
+
+	for_each_available_child_of_node(node, child_node) {
+		prop = of_find_property(child_node, "led-sources", NULL);
+		if (prop) {
+			const __be32 *srcs = NULL;
+
+			for (i = 0; i < ARRAY_SIZE(led_sources); ++i) {
+				srcs = of_prop_next_u32(prop, srcs,
+							&led_sources[i]);
+				if (!srcs)
+					break;
+			}
+		} else {
+			dev_err(dev,
+				"led-sources DT property missing\n");
+			of_node_put(child_node);
+			return -EINVAL;
+		}
+
+		if (i == 2) {
+			fled_id = FLED1;
+			led->fled_mask = FLED1_IOUT | FLED2_IOUT;
+		} else if (led_sources[0] == FLED1) {
+			fled_id = FLED1;
+			led->fled_mask |= FLED1_IOUT;
+		} else if (led_sources[0] == FLED2) {
+			fled_id = FLED2;
+			led->fled_mask |= FLED2_IOUT;
+		} else {
+			dev_err(dev,
+				"Wrong led-sources DT property value.\n");
+			of_node_put(child_node);
+			return -EINVAL;
+		}
+
+		if (sub_nodes[fled_id]) {
+			dev_err(dev,
+				"Conflicting \"led-sources\" DT properties\n");
+			return -EINVAL;
+		}
+
+		sub_nodes[fled_id] = child_node;
+		sub_leds[fled_id].fled_id = fled_id;
+
+		cfg->label[fled_id] =
+			of_get_property(child_node, "label", NULL) ? :
+						child_node->name;
+
+		ret = of_property_read_u32(child_node, "led-max-microamp",
+					&cfg->iout_torch_max[fled_id]);
+		if (ret < 0) {
+			cfg->iout_torch_max[fled_id] = TORCH_IOUT_MIN;
+			dev_warn(dev, "led-max-microamp DT property missing\n");
+		}
+
+		ret = of_property_read_u32(child_node, "flash-max-microamp",
+					&cfg->iout_flash_max[fled_id]);
+		if (ret < 0) {
+			cfg->iout_flash_max[fled_id] = FLASH_IOUT_MIN;
+			dev_warn(dev,
+				 "flash-max-microamp DT property missing\n");
+		}
+
+		ret = of_property_read_u32(child_node, "flash-max-timeout-us",
+					&cfg->flash_timeout_max[fled_id]);
+		if (ret < 0) {
+			cfg->flash_timeout_max[fled_id] = FLASH_TIMEOUT_MIN;
+			dev_warn(dev,
+				 "flash-max-timeout-us DT property missing\n");
+		}
+
+		if (++cfg->num_leds == 2 ||
+		    (max77693_fled_used(led, FLED1) &&
+		     max77693_fled_used(led, FLED2))) {
+			of_node_put(child_node);
+			break;
+		}
+	}
+
+	if (cfg->num_leds == 0) {
+		dev_err(dev, "No DT child node found for connected LED(s).\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void clamp_align(u32 *v, u32 min, u32 max, u32 step)
+{
+	*v = clamp_val(*v, min, max);
+	if (step > 1)
+		*v = (*v - min) / step * step + min;
+}
+
+static void max77693_align_iout_current(struct max77693_led_device *led,
+					u32 *iout, u32 min, u32 max, u32 step)
+{
+	int i;
+
+	if (led->iout_joint) {
+		if (iout[FLED1] > min) {
+			iout[FLED1] /= 2;
+			iout[FLED2] = iout[FLED1];
+		} else {
+			iout[FLED1] = min;
+			iout[FLED2] = 0;
+			return;
+		}
+	}
+
+	for (i = FLED1; i <= FLED2; ++i)
+		if (max77693_fled_used(led, i))
+			clamp_align(&iout[i], min, max, step);
+		else
+			iout[i] = 0;
+}
+
+static void max77693_led_validate_configuration(struct max77693_led_device *led,
+					struct max77693_led_config_data *cfg)
+{
+	u32 flash_iout_max = cfg->boost_mode ? FLASH_IOUT_MAX_2LEDS :
+					       FLASH_IOUT_MAX_1LED;
+	int i;
+
+	if (cfg->num_leds == 1 &&
+	    max77693_fled_used(led, FLED1) && max77693_fled_used(led, FLED2))
+		led->iout_joint = true;
+
+	cfg->boost_mode = clamp_val(cfg->boost_mode, MAX77693_LED_BOOST_NONE,
+			    MAX77693_LED_BOOST_FIXED);
+
+	/* Boost must be enabled if both current outputs are used */
+	if ((cfg->boost_mode == MAX77693_LED_BOOST_NONE) && led->iout_joint)
+		cfg->boost_mode = MAX77693_LED_BOOST_FIXED;
+
+	max77693_align_iout_current(led, cfg->iout_torch_max,
+			TORCH_IOUT_MIN, TORCH_IOUT_MAX, TORCH_IOUT_STEP);
+
+	max77693_align_iout_current(led, cfg->iout_flash_max,
+			FLASH_IOUT_MIN, flash_iout_max, FLASH_IOUT_STEP);
+
+	for (i = 0; i < ARRAY_SIZE(cfg->flash_timeout_max); ++i)
+		clamp_align(&cfg->flash_timeout_max[i], FLASH_TIMEOUT_MIN,
+				FLASH_TIMEOUT_MAX, FLASH_TIMEOUT_STEP);
+
+	clamp_align(&cfg->boost_vout, FLASH_VOUT_MIN, FLASH_VOUT_MAX,
+							FLASH_VOUT_STEP);
+
+	if (cfg->low_vsys)
+		clamp_align(&cfg->low_vsys, MAX_FLASH1_VSYS_MIN,
+				MAX_FLASH1_VSYS_MAX, MAX_FLASH1_VSYS_STEP);
+}
+
+static int max77693_led_get_configuration(struct max77693_led_device *led,
+				struct max77693_led_config_data *cfg,
+				struct device_node **sub_nodes)
+{
+	int ret;
+
+	ret = max77693_led_parse_dt(led, cfg, sub_nodes);
+	if (ret < 0)
+		return ret;
+
+	max77693_led_validate_configuration(led, cfg);
+
+	memcpy(led->iout_torch_max, cfg->iout_torch_max,
+				sizeof(led->iout_torch_max));
+	memcpy(led->iout_flash_max, cfg->iout_flash_max,
+				sizeof(led->iout_flash_max));
+
+	return 0;
+}
+
+static const struct led_flash_ops flash_ops = {
+	.flash_brightness_set	= max77693_led_flash_brightness_set,
+	.strobe_set		= max77693_led_flash_strobe_set,
+	.strobe_get		= max77693_led_flash_strobe_get,
+	.timeout_set		= max77693_led_flash_timeout_set,
+	.fault_get		= max77693_led_flash_fault_get,
+};
+
+static void max77693_init_flash_settings(struct max77693_sub_led *sub_led,
+				 struct max77693_led_config_data *led_cfg)
+{
+	struct led_classdev_flash *fled_cdev = &sub_led->fled_cdev;
+	struct max77693_led_device *led = sub_led_to_led(sub_led);
+	int fled_id = sub_led->fled_id;
+	struct led_flash_setting *setting;
+
+	/* Init flash intensity setting */
+	setting = &fled_cdev->brightness;
+	setting->min = FLASH_IOUT_MIN;
+	setting->max = led->iout_joint ?
+		led_cfg->iout_flash_max[FLED1] +
+		led_cfg->iout_flash_max[FLED2] :
+		led_cfg->iout_flash_max[fled_id];
+	setting->step = FLASH_IOUT_STEP;
+	setting->val = setting->max;
+
+	/* Init flash timeout setting */
+	setting = &fled_cdev->timeout;
+	setting->min = FLASH_TIMEOUT_MIN;
+	setting->max = led_cfg->flash_timeout_max[fled_id];
+	setting->step = FLASH_TIMEOUT_STEP;
+	setting->val = setting->max;
+}
+
+#if IS_ENABLED(CONFIG_V4L2_FLASH_LED_CLASS)
+
+static int max77693_led_external_strobe_set(
+				struct v4l2_flash *v4l2_flash,
+				bool enable)
+{
+	struct max77693_sub_led *sub_led =
+				flcdev_to_sub_led(v4l2_flash->fled_cdev);
+	struct max77693_led_device *led = sub_led_to_led(sub_led);
+	int fled_id = sub_led->fled_id;
+	int ret;
+
+	mutex_lock(&led->lock);
+
+	if (enable)
+		ret = max77693_add_mode(led, MODE_FLASH_EXTERNAL(fled_id));
+	else
+		ret = max77693_clear_mode(led, MODE_FLASH_EXTERNAL(fled_id));
+
+	mutex_unlock(&led->lock);
+
+	return ret;
+}
+
+static void max77693_init_v4l2_flash_config(struct max77693_sub_led *sub_led,
+				struct max77693_led_config_data *led_cfg,
+				struct v4l2_flash_config *v4l2_sd_cfg)
+{
+	struct max77693_led_device *led = sub_led_to_led(sub_led);
+	struct device *dev = &led->pdev->dev;
+	struct max77693_dev *iodev = dev_get_drvdata(dev->parent);
+	struct i2c_client *i2c = iodev->i2c;
+	struct led_flash_setting *s;
+
+	snprintf(v4l2_sd_cfg->dev_name, sizeof(v4l2_sd_cfg->dev_name),
+		 "%s %d-%04x", sub_led->fled_cdev.led_cdev.name,
+		 i2c_adapter_id(i2c->adapter), i2c->addr);
+
+	s = &v4l2_sd_cfg->torch_intensity;
+	s->min = TORCH_IOUT_MIN;
+	s->max = sub_led->fled_cdev.led_cdev.max_brightness * TORCH_IOUT_STEP;
+	s->step = TORCH_IOUT_STEP;
+	s->val = s->max;
+
+	/* Init flash faults config */
+	v4l2_sd_cfg->flash_faults = LED_FAULT_OVER_VOLTAGE |
+				LED_FAULT_SHORT_CIRCUIT |
+				LED_FAULT_OVER_CURRENT;
+
+	v4l2_sd_cfg->has_external_strobe = true;
+}
+
+static const struct v4l2_flash_ops v4l2_flash_ops = {
+	.external_strobe_set = max77693_led_external_strobe_set,
+};
+#else
+static inline void max77693_init_v4l2_flash_config(
+				struct max77693_sub_led *sub_led,
+				struct max77693_led_config_data *led_cfg,
+				struct v4l2_flash_config *v4l2_sd_cfg)
+{
+}
+static const struct v4l2_flash_ops v4l2_flash_ops;
+#endif
+
+static void max77693_init_fled_cdev(struct max77693_sub_led *sub_led,
+				struct max77693_led_config_data *led_cfg)
+{
+	struct max77693_led_device *led = sub_led_to_led(sub_led);
+	int fled_id = sub_led->fled_id;
+	struct led_classdev_flash *fled_cdev;
+	struct led_classdev *led_cdev;
+
+	/* Initialize LED Flash class device */
+	fled_cdev = &sub_led->fled_cdev;
+	fled_cdev->ops = &flash_ops;
+	led_cdev = &fled_cdev->led_cdev;
+
+	led_cdev->name = led_cfg->label[fled_id];
+
+	led_cdev->brightness_set = max77693_led_brightness_set;
+	led_cdev->brightness_set_sync = max77693_led_brightness_set_sync;
+	led_cdev->max_brightness = (led->iout_joint ?
+					led_cfg->iout_torch_max[FLED1] +
+					led_cfg->iout_torch_max[FLED2] :
+					led_cfg->iout_torch_max[fled_id]) /
+				   TORCH_IOUT_STEP;
+	led_cdev->flags |= LED_DEV_CAP_FLASH;
+	INIT_WORK(&sub_led->work_brightness_set,
+			max77693_led_brightness_set_work);
+
+	max77693_init_flash_settings(sub_led, led_cfg);
+
+	/* Init flash timeout cache */
+	sub_led->flash_timeout = fled_cdev->timeout.val;
+}
+
+static int max77693_register_led(struct max77693_sub_led *sub_led,
+				 struct max77693_led_config_data *led_cfg,
+				 struct device_node *sub_node)
+{
+	struct max77693_led_device *led = sub_led_to_led(sub_led);
+	struct led_classdev_flash *fled_cdev = &sub_led->fled_cdev;
+	struct device *dev = &led->pdev->dev;
+	struct v4l2_flash_config v4l2_sd_cfg = {};
+	int ret;
+
+	/* Register in the LED subsystem */
+	ret = led_classdev_flash_register(dev, fled_cdev);
+	if (ret < 0)
+		return ret;
+
+	max77693_init_v4l2_flash_config(sub_led, led_cfg, &v4l2_sd_cfg);
+
+	/* Register in the V4L2 subsystem. */
+	sub_led->v4l2_flash = v4l2_flash_init(dev, sub_node, fled_cdev, NULL,
+					      &v4l2_flash_ops, &v4l2_sd_cfg);
+	if (IS_ERR(sub_led->v4l2_flash)) {
+		ret = PTR_ERR(sub_led->v4l2_flash);
+		goto err_v4l2_flash_init;
+	}
+
+	return 0;
+
+err_v4l2_flash_init:
+	led_classdev_flash_unregister(fled_cdev);
+	return ret;
+}
+
+static int max77693_led_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct max77693_dev *iodev = dev_get_drvdata(dev->parent);
+	struct max77693_led_device *led;
+	struct max77693_sub_led *sub_leds;
+	struct device_node *sub_nodes[2] = {};
+	struct max77693_led_config_data led_cfg = {};
+	int init_fled_cdev[2], i, ret;
+
+	led = devm_kzalloc(dev, sizeof(*led), GFP_KERNEL);
+	if (!led)
+		return -ENOMEM;
+
+	led->pdev = pdev;
+	led->regmap = iodev->regmap;
+	led->allowed_modes = MODE_FLASH_MASK;
+	sub_leds = led->sub_leds;
+
+	platform_set_drvdata(pdev, led);
+	ret = max77693_led_get_configuration(led, &led_cfg, sub_nodes);
+	if (ret < 0)
+		return ret;
+
+	ret = max77693_setup(led, &led_cfg);
+	if (ret < 0)
+		return ret;
+
+	mutex_init(&led->lock);
+
+	init_fled_cdev[FLED1] =
+			led->iout_joint || max77693_fled_used(led, FLED1);
+	init_fled_cdev[FLED2] =
+			!led->iout_joint && max77693_fled_used(led, FLED2);
+
+	for (i = FLED1; i <= FLED2; ++i) {
+		if (!init_fled_cdev[i])
+			continue;
+
+		/* Initialize LED Flash class device */
+		max77693_init_fled_cdev(&sub_leds[i], &led_cfg);
+
+		/*
+		 * Register LED Flash class device and corresponding
+		 * V4L2 Flash device.
+		 */
+		ret = max77693_register_led(&sub_leds[i], &led_cfg,
+						sub_nodes[i]);
+		if (ret < 0) {
+			/*
+			 * At this moment FLED1 might have been already
+			 * registered and it needs to be released.
+			 */
+			if (i == FLED2)
+				goto err_register_led2;
+			else
+				goto err_register_led1;
+		}
+	}
+
+	return 0;
+
+err_register_led2:
+	/* It is possible than only FLED2 was to be registered */
+	if (!init_fled_cdev[FLED1])
+		goto err_register_led1;
+	v4l2_flash_release(sub_leds[FLED1].v4l2_flash);
+	led_classdev_flash_unregister(&sub_leds[FLED1].fled_cdev);
+err_register_led1:
+	mutex_destroy(&led->lock);
+
+	return ret;
+}
+
+static int max77693_led_remove(struct platform_device *pdev)
+{
+	struct max77693_led_device *led = platform_get_drvdata(pdev);
+	struct max77693_sub_led *sub_leds = led->sub_leds;
+
+	if (led->iout_joint || max77693_fled_used(led, FLED1)) {
+		v4l2_flash_release(sub_leds[FLED1].v4l2_flash);
+		led_classdev_flash_unregister(&sub_leds[FLED1].fled_cdev);
+		cancel_work_sync(&sub_leds[FLED1].work_brightness_set);
+	}
+
+	if (!led->iout_joint && max77693_fled_used(led, FLED2)) {
+		v4l2_flash_release(sub_leds[FLED2].v4l2_flash);
+		led_classdev_flash_unregister(&sub_leds[FLED2].fled_cdev);
+		cancel_work_sync(&sub_leds[FLED2].work_brightness_set);
+	}
+
+	mutex_destroy(&led->lock);
+
+	return 0;
+}
+
+static const struct of_device_id max77693_led_dt_match[] = {
+	{ .compatible = "maxim,max77693-led" },
+	{},
+};
+
+static struct platform_driver max77693_led_driver = {
+	.probe		= max77693_led_probe,
+	.remove		= max77693_led_remove,
+	.driver		= {
+		.name	= "max77693-led",
+		.of_match_table = max77693_led_dt_match,
+	},
+};
+
+module_platform_driver(max77693_led_driver);
+
+MODULE_AUTHOR("Jacek Anaszewski <j.anaszewski@samsung.com>");
+MODULE_AUTHOR("Andrzej Hajda <a.hajda@samsung.com>");
+MODULE_DESCRIPTION("Maxim MAX77693 led flash driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/leds-tlc591xx.c b/drivers/leds/leds-tlc591xx.c
new file mode 100644
index 0000000..de16c29
--- /dev/null
+++ b/drivers/leds/leds-tlc591xx.c
@@ -0,0 +1,300 @@
+/*
+ * Copyright 2014 Belkin Inc.
+ * Copyright 2015 Andrew Lunn <andrew@lunn.ch>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ */
+
+#include <linux/i2c.h>
+#include <linux/leds.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+
+#define TLC591XX_MAX_LEDS	16
+
+#define TLC591XX_REG_MODE1	0x00
+#define MODE1_RESPON_ADDR_MASK	0xF0
+#define MODE1_NORMAL_MODE	(0 << 4)
+#define MODE1_SPEED_MODE	(1 << 4)
+
+#define TLC591XX_REG_MODE2	0x01
+#define MODE2_DIM		(0 << 5)
+#define MODE2_BLINK		(1 << 5)
+#define MODE2_OCH_STOP		(0 << 3)
+#define MODE2_OCH_ACK		(1 << 3)
+
+#define TLC591XX_REG_PWM(x)	(0x02 + (x))
+
+#define TLC591XX_REG_GRPPWM	0x12
+#define TLC591XX_REG_GRPFREQ	0x13
+
+/* LED Driver Output State, determine the source that drives LED outputs */
+#define LEDOUT_OFF		0x0	/* Output LOW */
+#define LEDOUT_ON		0x1	/* Output HI-Z */
+#define LEDOUT_DIM		0x2	/* Dimming */
+#define LEDOUT_BLINK		0x3	/* Blinking */
+#define LEDOUT_MASK		0x3
+
+#define ldev_to_led(c)		container_of(c, struct tlc591xx_led, ldev)
+#define work_to_led(work)	container_of(work, struct tlc591xx_led, work)
+
+struct tlc591xx_led {
+	bool active;
+	unsigned int led_no;
+	struct led_classdev ldev;
+	struct work_struct work;
+	struct tlc591xx_priv *priv;
+};
+
+struct tlc591xx_priv {
+	struct tlc591xx_led leds[TLC591XX_MAX_LEDS];
+	struct regmap *regmap;
+	unsigned int reg_ledout_offset;
+};
+
+struct tlc591xx {
+	unsigned int max_leds;
+	unsigned int reg_ledout_offset;
+};
+
+static const struct tlc591xx tlc59116 = {
+	.max_leds = 16,
+	.reg_ledout_offset = 0x14,
+};
+
+static const struct tlc591xx tlc59108 = {
+	.max_leds = 8,
+	.reg_ledout_offset = 0x0c,
+};
+
+static int
+tlc591xx_set_mode(struct regmap *regmap, u8 mode)
+{
+	int err;
+	u8 val;
+
+	err = regmap_write(regmap, TLC591XX_REG_MODE1, MODE1_NORMAL_MODE);
+	if (err)
+		return err;
+
+	val = MODE2_OCH_STOP | mode;
+
+	return regmap_write(regmap, TLC591XX_REG_MODE2, val);
+}
+
+static int
+tlc591xx_set_ledout(struct tlc591xx_priv *priv, struct tlc591xx_led *led,
+		    u8 val)
+{
+	unsigned int i = (led->led_no % 4) * 2;
+	unsigned int mask = LEDOUT_MASK << i;
+	unsigned int addr = priv->reg_ledout_offset + (led->led_no >> 2);
+
+	val = val << i;
+
+	return regmap_update_bits(priv->regmap, addr, mask, val);
+}
+
+static int
+tlc591xx_set_pwm(struct tlc591xx_priv *priv, struct tlc591xx_led *led,
+		 u8 brightness)
+{
+	u8 pwm = TLC591XX_REG_PWM(led->led_no);
+
+	return regmap_write(priv->regmap, pwm, brightness);
+}
+
+static void
+tlc591xx_led_work(struct work_struct *work)
+{
+	struct tlc591xx_led *led = work_to_led(work);
+	struct tlc591xx_priv *priv = led->priv;
+	enum led_brightness brightness = led->ldev.brightness;
+	int err;
+
+	switch (brightness) {
+	case 0:
+		err = tlc591xx_set_ledout(priv, led, LEDOUT_OFF);
+		break;
+	case LED_FULL:
+		err = tlc591xx_set_ledout(priv, led, LEDOUT_ON);
+		break;
+	default:
+		err = tlc591xx_set_ledout(priv, led, LEDOUT_DIM);
+		if (!err)
+			err = tlc591xx_set_pwm(priv, led, brightness);
+	}
+
+	if (err)
+		dev_err(led->ldev.dev, "Failed setting brightness\n");
+}
+
+static void
+tlc591xx_brightness_set(struct led_classdev *led_cdev,
+			enum led_brightness brightness)
+{
+	struct tlc591xx_led *led = ldev_to_led(led_cdev);
+
+	led->ldev.brightness = brightness;
+	schedule_work(&led->work);
+}
+
+static void
+tlc591xx_destroy_devices(struct tlc591xx_priv *priv, unsigned int j)
+{
+	int i = j;
+
+	while (--i >= 0) {
+		if (priv->leds[i].active) {
+			led_classdev_unregister(&priv->leds[i].ldev);
+			cancel_work_sync(&priv->leds[i].work);
+		}
+	}
+}
+
+static int
+tlc591xx_configure(struct device *dev,
+		   struct tlc591xx_priv *priv,
+		   const struct tlc591xx *tlc591xx)
+{
+	unsigned int i;
+	int err = 0;
+
+	tlc591xx_set_mode(priv->regmap, MODE2_DIM);
+	for (i = 0; i < TLC591XX_MAX_LEDS; i++) {
+		struct tlc591xx_led *led = &priv->leds[i];
+
+		if (!led->active)
+			continue;
+
+		led->priv = priv;
+		led->led_no = i;
+		led->ldev.brightness_set = tlc591xx_brightness_set;
+		led->ldev.max_brightness = LED_FULL;
+		INIT_WORK(&led->work, tlc591xx_led_work);
+		err = led_classdev_register(dev, &led->ldev);
+		if (err < 0) {
+			dev_err(dev, "couldn't register LED %s\n",
+				led->ldev.name);
+			goto exit;
+		}
+	}
+
+	return 0;
+
+exit:
+	tlc591xx_destroy_devices(priv, i);
+	return err;
+}
+
+static const struct regmap_config tlc591xx_regmap = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = 0x1e,
+};
+
+static const struct of_device_id of_tlc591xx_leds_match[] = {
+	{ .compatible = "ti,tlc59116",
+	  .data = &tlc59116 },
+	{ .compatible = "ti,tlc59108",
+	  .data = &tlc59108 },
+	{},
+};
+MODULE_DEVICE_TABLE(of, of_tlc591xx_leds_match);
+
+static int
+tlc591xx_probe(struct i2c_client *client,
+	       const struct i2c_device_id *id)
+{
+	struct device_node *np = client->dev.of_node, *child;
+	struct device *dev = &client->dev;
+	const struct of_device_id *match;
+	const struct tlc591xx *tlc591xx;
+	struct tlc591xx_priv *priv;
+	int err, count, reg;
+
+	match = of_match_device(of_tlc591xx_leds_match, dev);
+	if (!match)
+		return -ENODEV;
+
+	tlc591xx = match->data;
+	if (!np)
+		return -ENODEV;
+
+	count = of_get_child_count(np);
+	if (!count || count > tlc591xx->max_leds)
+		return -EINVAL;
+
+	if (!i2c_check_functionality(client->adapter,
+				     I2C_FUNC_SMBUS_BYTE_DATA))
+		return -EIO;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->regmap = devm_regmap_init_i2c(client, &tlc591xx_regmap);
+	if (IS_ERR(priv->regmap)) {
+		err = PTR_ERR(priv->regmap);
+		dev_err(dev, "Failed to allocate register map: %d\n", err);
+		return err;
+	}
+	priv->reg_ledout_offset = tlc591xx->reg_ledout_offset;
+
+	i2c_set_clientdata(client, priv);
+
+	for_each_child_of_node(np, child) {
+		err = of_property_read_u32(child, "reg", &reg);
+		if (err)
+			return err;
+		if (reg < 0 || reg >= tlc591xx->max_leds)
+			return -EINVAL;
+		if (priv->leds[reg].active)
+			return -EINVAL;
+		priv->leds[reg].active = true;
+		priv->leds[reg].ldev.name =
+			of_get_property(child, "label", NULL) ? : child->name;
+		priv->leds[reg].ldev.default_trigger =
+			of_get_property(child, "linux,default-trigger", NULL);
+	}
+	return tlc591xx_configure(dev, priv, tlc591xx);
+}
+
+static int
+tlc591xx_remove(struct i2c_client *client)
+{
+	struct tlc591xx_priv *priv = i2c_get_clientdata(client);
+
+	tlc591xx_destroy_devices(priv, TLC591XX_MAX_LEDS);
+
+	return 0;
+}
+
+static const struct i2c_device_id tlc591xx_id[] = {
+	{ "tlc59116" },
+	{ "tlc59108" },
+	{},
+};
+MODULE_DEVICE_TABLE(i2c, tlc591xx_id);
+
+static struct i2c_driver tlc591xx_driver = {
+	.driver = {
+		.name = "tlc591xx",
+		.of_match_table = of_match_ptr(of_tlc591xx_leds_match),
+	},
+	.probe = tlc591xx_probe,
+	.remove = tlc591xx_remove,
+	.id_table = tlc591xx_id,
+};
+
+module_i2c_driver(tlc591xx_driver);
+
+MODULE_AUTHOR("Andrew Lunn <andrew@lunn.ch>");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("TLC591XX LED driver");
diff --git a/drivers/leds/leds.h b/drivers/leds/leds.h
index 79efe57..bc89d7a 100644
--- a/drivers/leds/leds.h
+++ b/drivers/leds/leds.h
@@ -13,7 +13,6 @@
 #ifndef __LEDS_H_INCLUDED
 #define __LEDS_H_INCLUDED
 
-#include <linux/device.h>
 #include <linux/rwsem.h>
 #include <linux/leds.h>
 
@@ -50,27 +49,4 @@
 extern struct rw_semaphore leds_list_lock;
 extern struct list_head leds_list;
 
-#ifdef CONFIG_LEDS_TRIGGERS
-void led_trigger_set_default(struct led_classdev *led_cdev);
-void led_trigger_set(struct led_classdev *led_cdev,
-			struct led_trigger *trigger);
-void led_trigger_remove(struct led_classdev *led_cdev);
-
-static inline void *led_get_trigger_data(struct led_classdev *led_cdev)
-{
-	return led_cdev->trigger_data;
-}
-
-#else
-#define led_trigger_set_default(x) do {} while (0)
-#define led_trigger_set(x, y) do {} while (0)
-#define led_trigger_remove(x) do {} while (0)
-#define led_get_trigger_data(x) (NULL)
-#endif
-
-ssize_t led_trigger_store(struct device *dev, struct device_attribute *attr,
-			const char *buf, size_t count);
-ssize_t led_trigger_show(struct device *dev, struct device_attribute *attr,
-			char *buf);
-
 #endif	/* __LEDS_H_INCLUDED */
diff --git a/drivers/mailbox/pl320-ipc.c b/drivers/mailbox/pl320-ipc.c
index f3755e0..f80acb3 100644
--- a/drivers/mailbox/pl320-ipc.c
+++ b/drivers/mailbox/pl320-ipc.c
@@ -195,4 +195,4 @@
 {
 	return amba_driver_register(&pl320_driver);
 }
-module_init(ipc_init);
+subsys_initcall(ipc_init);
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index fe080ad..ce64fc8 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -157,7 +157,7 @@
 
 	for_each_cache(ca, c, iter) {
 		struct journal_device *ja = &ca->journal;
-		unsigned long bitmap[SB_JOURNAL_BUCKETS / BITS_PER_LONG];
+		DECLARE_BITMAP(bitmap, SB_JOURNAL_BUCKETS);
 		unsigned i, l, r, m;
 		uint64_t seq;
 
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 4dd2bb7..94980bf 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -760,14 +760,8 @@
 	bio_split_pool_free(&d->bio_split_hook);
 	if (d->bio_split)
 		bioset_free(d->bio_split);
-	if (is_vmalloc_addr(d->full_dirty_stripes))
-		vfree(d->full_dirty_stripes);
-	else
-		kfree(d->full_dirty_stripes);
-	if (is_vmalloc_addr(d->stripe_sectors_dirty))
-		vfree(d->stripe_sectors_dirty);
-	else
-		kfree(d->stripe_sectors_dirty);
+	kvfree(d->full_dirty_stripes);
+	kvfree(d->stripe_sectors_dirty);
 
 	closure_debug_destroy(&d->cl);
 }
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index 98df757..1d04c48 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -52,10 +52,7 @@
 
 #define free_heap(heap)							\
 do {									\
-	if (is_vmalloc_addr((heap)->data))				\
-		vfree((heap)->data);					\
-	else								\
-		kfree((heap)->data);					\
+	kvfree((heap)->data);						\
 	(heap)->data = NULL;						\
 } while (0)
 
@@ -163,10 +160,7 @@
 
 #define free_fifo(fifo)							\
 do {									\
-	if (is_vmalloc_addr((fifo)->data))				\
-		vfree((fifo)->data);					\
-	else								\
-		kfree((fifo)->data);					\
+	kvfree((fifo)->data);						\
 	(fifo)->data = NULL;						\
 } while (0)
 
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 135a090..ed2346d 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -839,7 +839,7 @@
 		if (bitmap->storage.file) {
 			path = kmalloc(PAGE_SIZE, GFP_KERNEL);
 			if (path)
-				ptr = d_path(&bitmap->storage.file->f_path,
+				ptr = file_path(bitmap->storage.file,
 					     path, PAGE_SIZE);
 
 			printk(KERN_ALERT
@@ -1927,7 +1927,7 @@
 		   chunk_kb ? "KB" : "B");
 	if (bitmap->storage.file) {
 		seq_printf(seq, ", file: ");
-		seq_path(seq, &bitmap->storage.file->f_path, " \t\n");
+		seq_file_path(seq, bitmap->storage.file, " \t\n");
 	}
 
 	seq_printf(seq, "\n");
diff --git a/drivers/md/md.c b/drivers/md/md.c
index df92d30..d429c30 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5766,7 +5766,7 @@
 	/* bitmap disabled, zero the first byte and copy out */
 	if (!mddev->bitmap_info.file)
 		file->pathname[0] = '\0';
-	else if ((ptr = d_path(&mddev->bitmap_info.file->f_path,
+	else if ((ptr = file_path(mddev->bitmap_info.file,
 			       file->pathname, sizeof(file->pathname))),
 		 IS_ERR(ptr))
 		err = PTR_ERR(ptr);
diff --git a/drivers/media/platform/coda/coda-common.c b/drivers/media/platform/coda/coda-common.c
index 6d6e0ca..58f6548 100644
--- a/drivers/media/platform/coda/coda-common.c
+++ b/drivers/media/platform/coda/coda-common.c
@@ -2155,9 +2155,9 @@
 	}
 
 	/* Get IRAM pool from device tree or platform data */
-	pool = of_get_named_gen_pool(np, "iram", 0);
+	pool = of_gen_pool_get(np, "iram", 0);
 	if (!pool && pdata)
-		pool = dev_get_gen_pool(pdata->iram_dev);
+		pool = gen_pool_get(pdata->iram_dev);
 	if (!pool) {
 		dev_err(&pdev->dev, "iram pool not available\n");
 		return -ENOMEM;
diff --git a/drivers/media/v4l2-core/Kconfig b/drivers/media/v4l2-core/Kconfig
index f7a01a7..b4b0229 100644
--- a/drivers/media/v4l2-core/Kconfig
+++ b/drivers/media/v4l2-core/Kconfig
@@ -44,6 +44,17 @@
         tristate
         depends on VIDEOBUF2_CORE
 
+# Used by LED subsystem flash drivers
+config V4L2_FLASH_LED_CLASS
+	tristate "V4L2 flash API for LED flash class devices"
+	depends on VIDEO_V4L2_SUBDEV_API
+	depends on LEDS_CLASS_FLASH
+	---help---
+	  Say Y here to enable V4L2 flash API support for LED flash
+	  class drivers.
+
+	  When in doubt, say N.
+
 # Used by drivers that need Videobuf modules
 config VIDEOBUF_GEN
 	tristate
diff --git a/drivers/media/v4l2-core/Makefile b/drivers/media/v4l2-core/Makefile
index 63d29f2..dc3de00 100644
--- a/drivers/media/v4l2-core/Makefile
+++ b/drivers/media/v4l2-core/Makefile
@@ -22,6 +22,8 @@
 
 obj-$(CONFIG_V4L2_MEM2MEM_DEV) += v4l2-mem2mem.o
 
+obj-$(CONFIG_V4L2_FLASH_LED_CLASS) += v4l2-flash-led-class.o
+
 obj-$(CONFIG_VIDEOBUF_GEN) += videobuf-core.o
 obj-$(CONFIG_VIDEOBUF_DMA_SG) += videobuf-dma-sg.o
 obj-$(CONFIG_VIDEOBUF_DMA_CONTIG) += videobuf-dma-contig.o
diff --git a/drivers/media/v4l2-core/v4l2-async.c b/drivers/media/v4l2-core/v4l2-async.c
index 85a6a34..5bada20 100644
--- a/drivers/media/v4l2-core/v4l2-async.c
+++ b/drivers/media/v4l2-core/v4l2-async.c
@@ -22,10 +22,10 @@
 #include <media/v4l2-device.h>
 #include <media/v4l2-subdev.h>
 
-static bool match_i2c(struct device *dev, struct v4l2_async_subdev *asd)
+static bool match_i2c(struct v4l2_subdev *sd, struct v4l2_async_subdev *asd)
 {
 #if IS_ENABLED(CONFIG_I2C)
-	struct i2c_client *client = i2c_verify_client(dev);
+	struct i2c_client *client = i2c_verify_client(sd->dev);
 	return client &&
 		asd->match.i2c.adapter_id == client->adapter->nr &&
 		asd->match.i2c.address == client->addr;
@@ -34,14 +34,24 @@
 #endif
 }
 
-static bool match_devname(struct device *dev, struct v4l2_async_subdev *asd)
+static bool match_devname(struct v4l2_subdev *sd,
+			  struct v4l2_async_subdev *asd)
 {
-	return !strcmp(asd->match.device_name.name, dev_name(dev));
+	return !strcmp(asd->match.device_name.name, dev_name(sd->dev));
 }
 
-static bool match_of(struct device *dev, struct v4l2_async_subdev *asd)
+static bool match_of(struct v4l2_subdev *sd, struct v4l2_async_subdev *asd)
 {
-	return dev->of_node == asd->match.of.node;
+	return sd->of_node == asd->match.of.node;
+}
+
+static bool match_custom(struct v4l2_subdev *sd, struct v4l2_async_subdev *asd)
+{
+	if (!asd->match.custom.match)
+		/* Match always */
+		return true;
+
+	return asd->match.custom.match(sd->dev, asd);
 }
 
 static LIST_HEAD(subdev_list);
@@ -51,17 +61,14 @@
 static struct v4l2_async_subdev *v4l2_async_belongs(struct v4l2_async_notifier *notifier,
 						    struct v4l2_subdev *sd)
 {
+	bool (*match)(struct v4l2_subdev *, struct v4l2_async_subdev *);
 	struct v4l2_async_subdev *asd;
-	bool (*match)(struct device *, struct v4l2_async_subdev *);
 
 	list_for_each_entry(asd, &notifier->waiting, list) {
 		/* bus_type has been verified valid before */
 		switch (asd->match_type) {
 		case V4L2_ASYNC_MATCH_CUSTOM:
-			match = asd->match.custom.match;
-			if (!match)
-				/* Match always */
-				return asd;
+			match = match_custom;
 			break;
 		case V4L2_ASYNC_MATCH_DEVNAME:
 			match = match_devname;
@@ -79,7 +86,7 @@
 		}
 
 		/* match cannot be NULL here */
-		if (match(sd->dev, asd))
+		if (match(sd, asd))
 			return asd;
 	}
 
@@ -266,6 +273,14 @@
 {
 	struct v4l2_async_notifier *notifier;
 
+	/*
+	 * No reference taken. The reference is held by the device
+	 * (struct v4l2_subdev.dev), and async sub-device does not
+	 * exist independently of the device at any point of time.
+	 */
+	if (!sd->of_node && sd->dev)
+		sd->of_node = sd->dev->of_node;
+
 	mutex_lock(&list_lock);
 
 	INIT_LIST_HEAD(&sd->async_list);
diff --git a/drivers/media/v4l2-core/v4l2-flash-led-class.c b/drivers/media/v4l2-core/v4l2-flash-led-class.c
new file mode 100644
index 0000000..5bdfb8d
--- /dev/null
+++ b/drivers/media/v4l2-core/v4l2-flash-led-class.c
@@ -0,0 +1,710 @@
+/*
+ * V4L2 flash LED sub-device registration helpers.
+ *
+ *	Copyright (C) 2015 Samsung Electronics Co., Ltd
+ *	Author: Jacek Anaszewski <j.anaszewski@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/led-class-flash.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <media/v4l2-flash-led-class.h>
+
+#define has_flash_op(v4l2_flash, op)				\
+	(v4l2_flash && v4l2_flash->ops->op)
+
+#define call_flash_op(v4l2_flash, op, arg)			\
+		(has_flash_op(v4l2_flash, op) ?			\
+			v4l2_flash->ops->op(v4l2_flash, arg) :	\
+			-EINVAL)
+
+enum ctrl_init_data_id {
+	LED_MODE,
+	TORCH_INTENSITY,
+	FLASH_INTENSITY,
+	INDICATOR_INTENSITY,
+	FLASH_TIMEOUT,
+	STROBE_SOURCE,
+	/*
+	 * Only above values are applicable to
+	 * the 'ctrls' array in the struct v4l2_flash.
+	 */
+	FLASH_STROBE,
+	STROBE_STOP,
+	STROBE_STATUS,
+	FLASH_FAULT,
+	NUM_FLASH_CTRLS,
+};
+
+static enum led_brightness __intensity_to_led_brightness(
+					struct v4l2_ctrl *ctrl, s32 intensity)
+{
+	intensity -= ctrl->minimum;
+	intensity /= (u32) ctrl->step;
+
+	/*
+	 * Indicator LEDs, unlike torch LEDs, are turned on/off basing on
+	 * the state of V4L2_CID_FLASH_INDICATOR_INTENSITY control only.
+	 * Therefore it must be possible to set it to 0 level which in
+	 * the LED subsystem reflects LED_OFF state.
+	 */
+	if (ctrl->minimum)
+		++intensity;
+
+	return intensity;
+}
+
+static s32 __led_brightness_to_intensity(struct v4l2_ctrl *ctrl,
+					 enum led_brightness brightness)
+{
+	/*
+	 * Indicator LEDs, unlike torch LEDs, are turned on/off basing on
+	 * the state of V4L2_CID_FLASH_INDICATOR_INTENSITY control only.
+	 * Do not decrement brightness read from the LED subsystem for
+	 * indicator LED as it may equal 0. For torch LEDs this function
+	 * is called only when V4L2_FLASH_LED_MODE_TORCH is set and the
+	 * brightness read is guaranteed to be greater than 0. In the mode
+	 * V4L2_FLASH_LED_MODE_NONE the cached torch intensity value is used.
+	 */
+	if (ctrl->id != V4L2_CID_FLASH_INDICATOR_INTENSITY)
+		--brightness;
+
+	return (brightness * ctrl->step) + ctrl->minimum;
+}
+
+static void v4l2_flash_set_led_brightness(struct v4l2_flash *v4l2_flash,
+					struct v4l2_ctrl *ctrl)
+{
+	struct v4l2_ctrl **ctrls = v4l2_flash->ctrls;
+	enum led_brightness brightness;
+
+	if (has_flash_op(v4l2_flash, intensity_to_led_brightness))
+		brightness = call_flash_op(v4l2_flash,
+					intensity_to_led_brightness,
+					ctrl->val);
+	else
+		brightness = __intensity_to_led_brightness(ctrl, ctrl->val);
+	/*
+	 * In case a LED Flash class driver provides ops for custom
+	 * brightness <-> intensity conversion, it also must have defined
+	 * related v4l2 control step == 1. In such a case a backward conversion
+	 * from led brightness to v4l2 intensity is required to find out the
+	 * the aligned intensity value.
+	 */
+	if (has_flash_op(v4l2_flash, led_brightness_to_intensity))
+		ctrl->val = call_flash_op(v4l2_flash,
+					led_brightness_to_intensity,
+					brightness);
+
+	if (ctrl == ctrls[TORCH_INTENSITY]) {
+		if (ctrls[LED_MODE]->val != V4L2_FLASH_LED_MODE_TORCH)
+			return;
+
+		led_set_brightness(&v4l2_flash->fled_cdev->led_cdev,
+					brightness);
+	} else {
+		led_set_brightness(&v4l2_flash->iled_cdev->led_cdev,
+					brightness);
+	}
+}
+
+static int v4l2_flash_update_led_brightness(struct v4l2_flash *v4l2_flash,
+					struct v4l2_ctrl *ctrl)
+{
+	struct v4l2_ctrl **ctrls = v4l2_flash->ctrls;
+	struct led_classdev *led_cdev;
+	int ret;
+
+	if (ctrl == ctrls[TORCH_INTENSITY]) {
+		/*
+		 * Update torch brightness only if in TORCH_MODE. In other modes
+		 * torch led is turned off, which would spuriously inform the
+		 * user space that V4L2_CID_FLASH_TORCH_INTENSITY control value
+		 * has changed to 0.
+		 */
+		if (ctrls[LED_MODE]->val != V4L2_FLASH_LED_MODE_TORCH)
+			return 0;
+		led_cdev = &v4l2_flash->fled_cdev->led_cdev;
+	} else {
+		led_cdev = &v4l2_flash->iled_cdev->led_cdev;
+	}
+
+	ret = led_update_brightness(led_cdev);
+	if (ret < 0)
+		return ret;
+
+	if (has_flash_op(v4l2_flash, led_brightness_to_intensity))
+		ctrl->val = call_flash_op(v4l2_flash,
+						led_brightness_to_intensity,
+						led_cdev->brightness);
+	else
+		ctrl->val = __led_brightness_to_intensity(ctrl,
+						led_cdev->brightness);
+
+	return 0;
+}
+
+static int v4l2_flash_g_volatile_ctrl(struct v4l2_ctrl *c)
+{
+	struct v4l2_flash *v4l2_flash = v4l2_ctrl_to_v4l2_flash(c);
+	struct led_classdev_flash *fled_cdev = v4l2_flash->fled_cdev;
+	bool is_strobing;
+	int ret;
+
+	switch (c->id) {
+	case V4L2_CID_FLASH_TORCH_INTENSITY:
+	case V4L2_CID_FLASH_INDICATOR_INTENSITY:
+		return v4l2_flash_update_led_brightness(v4l2_flash, c);
+	case V4L2_CID_FLASH_INTENSITY:
+		ret = led_update_flash_brightness(fled_cdev);
+		if (ret < 0)
+			return ret;
+		/*
+		 * No conversion is needed as LED Flash class also uses
+		 * microamperes for flash intensity units.
+		 */
+		c->val = fled_cdev->brightness.val;
+		return 0;
+	case V4L2_CID_FLASH_STROBE_STATUS:
+		ret = led_get_flash_strobe(fled_cdev, &is_strobing);
+		if (ret < 0)
+			return ret;
+		c->val = is_strobing;
+		return 0;
+	case V4L2_CID_FLASH_FAULT:
+		/* LED faults map directly to V4L2 flash faults */
+		return led_get_flash_fault(fled_cdev, &c->val);
+	default:
+		return -EINVAL;
+	}
+}
+
+static bool __software_strobe_mode_inactive(struct v4l2_ctrl **ctrls)
+{
+	return ((ctrls[LED_MODE]->val != V4L2_FLASH_LED_MODE_FLASH) ||
+		(ctrls[STROBE_SOURCE] && (ctrls[STROBE_SOURCE]->val !=
+				V4L2_FLASH_STROBE_SOURCE_SOFTWARE)));
+}
+
+static int v4l2_flash_s_ctrl(struct v4l2_ctrl *c)
+{
+	struct v4l2_flash *v4l2_flash = v4l2_ctrl_to_v4l2_flash(c);
+	struct led_classdev_flash *fled_cdev = v4l2_flash->fled_cdev;
+	struct led_classdev *led_cdev = &fled_cdev->led_cdev;
+	struct v4l2_ctrl **ctrls = v4l2_flash->ctrls;
+	bool external_strobe;
+	int ret = 0;
+
+	switch (c->id) {
+	case V4L2_CID_FLASH_LED_MODE:
+		switch (c->val) {
+		case V4L2_FLASH_LED_MODE_NONE:
+			led_set_brightness(led_cdev, LED_OFF);
+			return led_set_flash_strobe(fled_cdev, false);
+		case V4L2_FLASH_LED_MODE_FLASH:
+			/* Turn the torch LED off */
+			led_set_brightness(led_cdev, LED_OFF);
+			if (ctrls[STROBE_SOURCE]) {
+				external_strobe = (ctrls[STROBE_SOURCE]->val ==
+					V4L2_FLASH_STROBE_SOURCE_EXTERNAL);
+
+				ret = call_flash_op(v4l2_flash,
+						external_strobe_set,
+						external_strobe);
+			}
+			return ret;
+		case V4L2_FLASH_LED_MODE_TORCH:
+			if (ctrls[STROBE_SOURCE]) {
+				ret = call_flash_op(v4l2_flash,
+						external_strobe_set,
+						false);
+				if (ret < 0)
+					return ret;
+			}
+			/* Stop flash strobing */
+			ret = led_set_flash_strobe(fled_cdev, false);
+			if (ret < 0)
+				return ret;
+
+			v4l2_flash_set_led_brightness(v4l2_flash,
+							ctrls[TORCH_INTENSITY]);
+			return 0;
+		}
+		break;
+	case V4L2_CID_FLASH_STROBE_SOURCE:
+		external_strobe = (c->val == V4L2_FLASH_STROBE_SOURCE_EXTERNAL);
+		/*
+		 * For some hardware arrangements setting strobe source may
+		 * affect torch mode. Therefore, if not in the flash mode,
+		 * cache only this setting. It will be applied upon switching
+		 * to flash mode.
+		 */
+		if (ctrls[LED_MODE]->val != V4L2_FLASH_LED_MODE_FLASH)
+			return 0;
+
+		return call_flash_op(v4l2_flash, external_strobe_set,
+					external_strobe);
+	case V4L2_CID_FLASH_STROBE:
+		if (__software_strobe_mode_inactive(ctrls))
+			return -EBUSY;
+		return led_set_flash_strobe(fled_cdev, true);
+	case V4L2_CID_FLASH_STROBE_STOP:
+		if (__software_strobe_mode_inactive(ctrls))
+			return -EBUSY;
+		return led_set_flash_strobe(fled_cdev, false);
+	case V4L2_CID_FLASH_TIMEOUT:
+		/*
+		 * No conversion is needed as LED Flash class also uses
+		 * microseconds for flash timeout units.
+		 */
+		return led_set_flash_timeout(fled_cdev, c->val);
+	case V4L2_CID_FLASH_INTENSITY:
+		/*
+		 * No conversion is needed as LED Flash class also uses
+		 * microamperes for flash intensity units.
+		 */
+		return led_set_flash_brightness(fled_cdev, c->val);
+	case V4L2_CID_FLASH_TORCH_INTENSITY:
+	case V4L2_CID_FLASH_INDICATOR_INTENSITY:
+		v4l2_flash_set_led_brightness(v4l2_flash, c);
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static const struct v4l2_ctrl_ops v4l2_flash_ctrl_ops = {
+	.g_volatile_ctrl = v4l2_flash_g_volatile_ctrl,
+	.s_ctrl = v4l2_flash_s_ctrl,
+};
+
+static void __lfs_to_v4l2_ctrl_config(struct led_flash_setting *s,
+				struct v4l2_ctrl_config *c)
+{
+	c->min = s->min;
+	c->max = s->max;
+	c->step = s->step;
+	c->def = s->val;
+}
+
+static void __fill_ctrl_init_data(struct v4l2_flash *v4l2_flash,
+			  struct v4l2_flash_config *flash_cfg,
+			  struct v4l2_flash_ctrl_data *ctrl_init_data)
+{
+	struct led_classdev_flash *fled_cdev = v4l2_flash->fled_cdev;
+	const struct led_flash_ops *fled_cdev_ops = fled_cdev->ops;
+	struct led_classdev *led_cdev = &fled_cdev->led_cdev;
+	struct v4l2_ctrl_config *ctrl_cfg;
+	u32 mask;
+
+	/* Init FLASH_FAULT ctrl data */
+	if (flash_cfg->flash_faults) {
+		ctrl_init_data[FLASH_FAULT].cid = V4L2_CID_FLASH_FAULT;
+		ctrl_cfg = &ctrl_init_data[FLASH_FAULT].config;
+		ctrl_cfg->id = V4L2_CID_FLASH_FAULT;
+		ctrl_cfg->max = flash_cfg->flash_faults;
+		ctrl_cfg->flags = V4L2_CTRL_FLAG_VOLATILE |
+				  V4L2_CTRL_FLAG_READ_ONLY;
+	}
+
+	/* Init FLASH_LED_MODE ctrl data */
+	mask = 1 << V4L2_FLASH_LED_MODE_NONE |
+	       1 << V4L2_FLASH_LED_MODE_TORCH;
+	if (led_cdev->flags & LED_DEV_CAP_FLASH)
+		mask |= 1 << V4L2_FLASH_LED_MODE_FLASH;
+
+	ctrl_init_data[LED_MODE].cid = V4L2_CID_FLASH_LED_MODE;
+	ctrl_cfg = &ctrl_init_data[LED_MODE].config;
+	ctrl_cfg->id = V4L2_CID_FLASH_LED_MODE;
+	ctrl_cfg->max = V4L2_FLASH_LED_MODE_TORCH;
+	ctrl_cfg->menu_skip_mask = ~mask;
+	ctrl_cfg->def = V4L2_FLASH_LED_MODE_NONE;
+	ctrl_cfg->flags = 0;
+
+	/* Init TORCH_INTENSITY ctrl data */
+	ctrl_init_data[TORCH_INTENSITY].cid = V4L2_CID_FLASH_TORCH_INTENSITY;
+	ctrl_cfg = &ctrl_init_data[TORCH_INTENSITY].config;
+	__lfs_to_v4l2_ctrl_config(&flash_cfg->torch_intensity, ctrl_cfg);
+	ctrl_cfg->id = V4L2_CID_FLASH_TORCH_INTENSITY;
+	ctrl_cfg->flags = V4L2_CTRL_FLAG_VOLATILE |
+			  V4L2_CTRL_FLAG_EXECUTE_ON_WRITE;
+
+	/* Init INDICATOR_INTENSITY ctrl data */
+	if (v4l2_flash->iled_cdev) {
+		ctrl_init_data[INDICATOR_INTENSITY].cid =
+					V4L2_CID_FLASH_INDICATOR_INTENSITY;
+		ctrl_cfg = &ctrl_init_data[INDICATOR_INTENSITY].config;
+		__lfs_to_v4l2_ctrl_config(&flash_cfg->indicator_intensity,
+					  ctrl_cfg);
+		ctrl_cfg->id = V4L2_CID_FLASH_INDICATOR_INTENSITY;
+		ctrl_cfg->min = 0;
+		ctrl_cfg->flags = V4L2_CTRL_FLAG_VOLATILE |
+				  V4L2_CTRL_FLAG_EXECUTE_ON_WRITE;
+	}
+
+	if (!(led_cdev->flags & LED_DEV_CAP_FLASH))
+		return;
+
+	/* Init FLASH_STROBE ctrl data */
+	ctrl_init_data[FLASH_STROBE].cid = V4L2_CID_FLASH_STROBE;
+	ctrl_cfg = &ctrl_init_data[FLASH_STROBE].config;
+	ctrl_cfg->id = V4L2_CID_FLASH_STROBE;
+
+	/* Init STROBE_STOP ctrl data */
+	ctrl_init_data[STROBE_STOP].cid = V4L2_CID_FLASH_STROBE_STOP;
+	ctrl_cfg = &ctrl_init_data[STROBE_STOP].config;
+	ctrl_cfg->id = V4L2_CID_FLASH_STROBE_STOP;
+
+	/* Init FLASH_STROBE_SOURCE ctrl data */
+	if (flash_cfg->has_external_strobe) {
+		mask = (1 << V4L2_FLASH_STROBE_SOURCE_SOFTWARE) |
+		       (1 << V4L2_FLASH_STROBE_SOURCE_EXTERNAL);
+		ctrl_init_data[STROBE_SOURCE].cid =
+					V4L2_CID_FLASH_STROBE_SOURCE;
+		ctrl_cfg = &ctrl_init_data[STROBE_SOURCE].config;
+		ctrl_cfg->id = V4L2_CID_FLASH_STROBE_SOURCE;
+		ctrl_cfg->max = V4L2_FLASH_STROBE_SOURCE_EXTERNAL;
+		ctrl_cfg->menu_skip_mask = ~mask;
+		ctrl_cfg->def = V4L2_FLASH_STROBE_SOURCE_SOFTWARE;
+	}
+
+	/* Init STROBE_STATUS ctrl data */
+	if (fled_cdev_ops->strobe_get) {
+		ctrl_init_data[STROBE_STATUS].cid =
+					V4L2_CID_FLASH_STROBE_STATUS;
+		ctrl_cfg = &ctrl_init_data[STROBE_STATUS].config;
+		ctrl_cfg->id = V4L2_CID_FLASH_STROBE_STATUS;
+		ctrl_cfg->flags = V4L2_CTRL_FLAG_VOLATILE |
+				  V4L2_CTRL_FLAG_READ_ONLY;
+	}
+
+	/* Init FLASH_TIMEOUT ctrl data */
+	if (fled_cdev_ops->timeout_set) {
+		ctrl_init_data[FLASH_TIMEOUT].cid = V4L2_CID_FLASH_TIMEOUT;
+		ctrl_cfg = &ctrl_init_data[FLASH_TIMEOUT].config;
+		__lfs_to_v4l2_ctrl_config(&fled_cdev->timeout, ctrl_cfg);
+		ctrl_cfg->id = V4L2_CID_FLASH_TIMEOUT;
+	}
+
+	/* Init FLASH_INTENSITY ctrl data */
+	if (fled_cdev_ops->flash_brightness_set) {
+		ctrl_init_data[FLASH_INTENSITY].cid = V4L2_CID_FLASH_INTENSITY;
+		ctrl_cfg = &ctrl_init_data[FLASH_INTENSITY].config;
+		__lfs_to_v4l2_ctrl_config(&fled_cdev->brightness, ctrl_cfg);
+		ctrl_cfg->id = V4L2_CID_FLASH_INTENSITY;
+		ctrl_cfg->flags = V4L2_CTRL_FLAG_VOLATILE |
+				  V4L2_CTRL_FLAG_EXECUTE_ON_WRITE;
+	}
+}
+
+static int v4l2_flash_init_controls(struct v4l2_flash *v4l2_flash,
+				struct v4l2_flash_config *flash_cfg)
+
+{
+	struct v4l2_flash_ctrl_data *ctrl_init_data;
+	struct v4l2_ctrl *ctrl;
+	struct v4l2_ctrl_config *ctrl_cfg;
+	int i, ret, num_ctrls = 0;
+
+	v4l2_flash->ctrls = devm_kzalloc(v4l2_flash->sd.dev,
+					sizeof(*v4l2_flash->ctrls) *
+					(STROBE_SOURCE + 1), GFP_KERNEL);
+	if (!v4l2_flash->ctrls)
+		return -ENOMEM;
+
+	/* allocate memory dynamically so as not to exceed stack frame size */
+	ctrl_init_data = kcalloc(NUM_FLASH_CTRLS, sizeof(*ctrl_init_data),
+					GFP_KERNEL);
+	if (!ctrl_init_data)
+		return -ENOMEM;
+
+	__fill_ctrl_init_data(v4l2_flash, flash_cfg, ctrl_init_data);
+
+	for (i = 0; i < NUM_FLASH_CTRLS; ++i)
+		if (ctrl_init_data[i].cid)
+			++num_ctrls;
+
+	v4l2_ctrl_handler_init(&v4l2_flash->hdl, num_ctrls);
+
+	for (i = 0; i < NUM_FLASH_CTRLS; ++i) {
+		ctrl_cfg = &ctrl_init_data[i].config;
+		if (!ctrl_init_data[i].cid)
+			continue;
+
+		if (ctrl_cfg->id == V4L2_CID_FLASH_LED_MODE ||
+		    ctrl_cfg->id == V4L2_CID_FLASH_STROBE_SOURCE)
+			ctrl = v4l2_ctrl_new_std_menu(&v4l2_flash->hdl,
+						&v4l2_flash_ctrl_ops,
+						ctrl_cfg->id,
+						ctrl_cfg->max,
+						ctrl_cfg->menu_skip_mask,
+						ctrl_cfg->def);
+		else
+			ctrl = v4l2_ctrl_new_std(&v4l2_flash->hdl,
+						&v4l2_flash_ctrl_ops,
+						ctrl_cfg->id,
+						ctrl_cfg->min,
+						ctrl_cfg->max,
+						ctrl_cfg->step,
+						ctrl_cfg->def);
+
+		if (ctrl)
+			ctrl->flags |= ctrl_cfg->flags;
+
+		if (i <= STROBE_SOURCE)
+			v4l2_flash->ctrls[i] = ctrl;
+	}
+
+	kfree(ctrl_init_data);
+
+	if (v4l2_flash->hdl.error) {
+		ret = v4l2_flash->hdl.error;
+		goto error_free_handler;
+	}
+
+	v4l2_ctrl_handler_setup(&v4l2_flash->hdl);
+
+	v4l2_flash->sd.ctrl_handler = &v4l2_flash->hdl;
+
+	return 0;
+
+error_free_handler:
+	v4l2_ctrl_handler_free(&v4l2_flash->hdl);
+	return ret;
+}
+
+static int __sync_device_with_v4l2_controls(struct v4l2_flash *v4l2_flash)
+{
+	struct led_classdev_flash *fled_cdev = v4l2_flash->fled_cdev;
+	struct v4l2_ctrl **ctrls = v4l2_flash->ctrls;
+	int ret = 0;
+
+	v4l2_flash_set_led_brightness(v4l2_flash, ctrls[TORCH_INTENSITY]);
+
+	if (ctrls[INDICATOR_INTENSITY])
+		v4l2_flash_set_led_brightness(v4l2_flash,
+						ctrls[INDICATOR_INTENSITY]);
+
+	if (ctrls[FLASH_TIMEOUT]) {
+		ret = led_set_flash_timeout(fled_cdev,
+					ctrls[FLASH_TIMEOUT]->val);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (ctrls[FLASH_INTENSITY]) {
+		ret = led_set_flash_brightness(fled_cdev,
+					ctrls[FLASH_INTENSITY]->val);
+		if (ret < 0)
+			return ret;
+	}
+
+	/*
+	 * For some hardware arrangements setting strobe source may affect
+	 * torch mode. Synchronize strobe source setting only if not in torch
+	 * mode. For torch mode case it will get synchronized upon switching
+	 * to flash mode.
+	 */
+	if (ctrls[STROBE_SOURCE] &&
+	    ctrls[LED_MODE]->val != V4L2_FLASH_LED_MODE_TORCH)
+		ret = call_flash_op(v4l2_flash, external_strobe_set,
+					ctrls[STROBE_SOURCE]->val);
+
+	return ret;
+}
+
+/*
+ * V4L2 subdev internal operations
+ */
+
+static int v4l2_flash_open(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
+{
+	struct v4l2_flash *v4l2_flash = v4l2_subdev_to_v4l2_flash(sd);
+	struct led_classdev_flash *fled_cdev = v4l2_flash->fled_cdev;
+	struct led_classdev *led_cdev = &fled_cdev->led_cdev;
+	struct led_classdev_flash *iled_cdev = v4l2_flash->iled_cdev;
+	struct led_classdev *led_cdev_ind = NULL;
+	int ret = 0;
+
+	if (!v4l2_fh_is_singular(&fh->vfh))
+		return 0;
+
+	mutex_lock(&led_cdev->led_access);
+
+	led_sysfs_disable(led_cdev);
+	led_trigger_remove(led_cdev);
+
+	mutex_unlock(&led_cdev->led_access);
+
+	if (iled_cdev) {
+		led_cdev_ind = &iled_cdev->led_cdev;
+
+		mutex_lock(&led_cdev_ind->led_access);
+
+		led_sysfs_disable(led_cdev_ind);
+		led_trigger_remove(led_cdev_ind);
+
+		mutex_unlock(&led_cdev_ind->led_access);
+	}
+
+	ret = __sync_device_with_v4l2_controls(v4l2_flash);
+	if (ret < 0)
+		goto out_sync_device;
+
+	return 0;
+out_sync_device:
+	mutex_lock(&led_cdev->led_access);
+	led_sysfs_enable(led_cdev);
+	mutex_unlock(&led_cdev->led_access);
+
+	if (led_cdev_ind) {
+		mutex_lock(&led_cdev_ind->led_access);
+		led_sysfs_enable(led_cdev_ind);
+		mutex_unlock(&led_cdev_ind->led_access);
+	}
+
+	return ret;
+}
+
+static int v4l2_flash_close(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
+{
+	struct v4l2_flash *v4l2_flash = v4l2_subdev_to_v4l2_flash(sd);
+	struct led_classdev_flash *fled_cdev = v4l2_flash->fled_cdev;
+	struct led_classdev *led_cdev = &fled_cdev->led_cdev;
+	struct led_classdev_flash *iled_cdev = v4l2_flash->iled_cdev;
+	int ret = 0;
+
+	if (!v4l2_fh_is_singular(&fh->vfh))
+		return 0;
+
+	mutex_lock(&led_cdev->led_access);
+
+	if (v4l2_flash->ctrls[STROBE_SOURCE])
+		ret = v4l2_ctrl_s_ctrl(v4l2_flash->ctrls[STROBE_SOURCE],
+				V4L2_FLASH_STROBE_SOURCE_SOFTWARE);
+	led_sysfs_enable(led_cdev);
+
+	mutex_unlock(&led_cdev->led_access);
+
+	if (iled_cdev) {
+		struct led_classdev *led_cdev_ind = &iled_cdev->led_cdev;
+
+		mutex_lock(&led_cdev_ind->led_access);
+		led_sysfs_enable(led_cdev_ind);
+		mutex_unlock(&led_cdev_ind->led_access);
+	}
+
+	return ret;
+}
+
+static const struct v4l2_subdev_internal_ops v4l2_flash_subdev_internal_ops = {
+	.open = v4l2_flash_open,
+	.close = v4l2_flash_close,
+};
+
+static const struct v4l2_subdev_core_ops v4l2_flash_core_ops = {
+	.queryctrl = v4l2_subdev_queryctrl,
+	.querymenu = v4l2_subdev_querymenu,
+};
+
+static const struct v4l2_subdev_ops v4l2_flash_subdev_ops = {
+	.core = &v4l2_flash_core_ops,
+};
+
+struct v4l2_flash *v4l2_flash_init(
+	struct device *dev, struct device_node *of_node,
+	struct led_classdev_flash *fled_cdev,
+	struct led_classdev_flash *iled_cdev,
+	const struct v4l2_flash_ops *ops,
+	struct v4l2_flash_config *config)
+{
+	struct v4l2_flash *v4l2_flash;
+	struct led_classdev *led_cdev;
+	struct v4l2_subdev *sd;
+	int ret;
+
+	if (!fled_cdev || !ops || !config)
+		return ERR_PTR(-EINVAL);
+
+	led_cdev = &fled_cdev->led_cdev;
+
+	v4l2_flash = devm_kzalloc(led_cdev->dev, sizeof(*v4l2_flash),
+					GFP_KERNEL);
+	if (!v4l2_flash)
+		return ERR_PTR(-ENOMEM);
+
+	sd = &v4l2_flash->sd;
+	v4l2_flash->fled_cdev = fled_cdev;
+	v4l2_flash->iled_cdev = iled_cdev;
+	v4l2_flash->ops = ops;
+	sd->dev = dev;
+	sd->of_node = of_node;
+	v4l2_subdev_init(sd, &v4l2_flash_subdev_ops);
+	sd->internal_ops = &v4l2_flash_subdev_internal_ops;
+	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
+	strlcpy(sd->name, config->dev_name, sizeof(sd->name));
+
+	ret = media_entity_init(&sd->entity, 0, NULL, 0);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	sd->entity.type = MEDIA_ENT_T_V4L2_SUBDEV_FLASH;
+
+	ret = v4l2_flash_init_controls(v4l2_flash, config);
+	if (ret < 0)
+		goto err_init_controls;
+
+	if (sd->of_node)
+		of_node_get(sd->of_node);
+	else
+		of_node_get(led_cdev->dev->of_node);
+
+	ret = v4l2_async_register_subdev(sd);
+	if (ret < 0)
+		goto err_async_register_sd;
+
+	return v4l2_flash;
+
+err_async_register_sd:
+	of_node_put(led_cdev->dev->of_node);
+	v4l2_ctrl_handler_free(sd->ctrl_handler);
+err_init_controls:
+	media_entity_cleanup(&sd->entity);
+
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(v4l2_flash_init);
+
+void v4l2_flash_release(struct v4l2_flash *v4l2_flash)
+{
+	struct v4l2_subdev *sd;
+	struct led_classdev *led_cdev;
+
+	if (IS_ERR_OR_NULL(v4l2_flash))
+		return;
+
+	sd = &v4l2_flash->sd;
+	led_cdev = &v4l2_flash->fled_cdev->led_cdev;
+
+	v4l2_async_unregister_subdev(sd);
+
+	if (sd->of_node)
+		of_node_put(sd->of_node);
+	else
+		of_node_put(led_cdev->dev->of_node);
+
+	v4l2_ctrl_handler_free(sd->ctrl_handler);
+	media_entity_cleanup(&sd->entity);
+}
+EXPORT_SYMBOL_GPL(v4l2_flash_release);
+
+MODULE_AUTHOR("Jacek Anaszewski <j.anaszewski@samsung.com>");
+MODULE_DESCRIPTION("V4L2 Flash sub-device helpers");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/memstick/host/jmb38x_ms.c b/drivers/memstick/host/jmb38x_ms.c
index aeabaa5..48db922 100644
--- a/drivers/memstick/host/jmb38x_ms.c
+++ b/drivers/memstick/host/jmb38x_ms.c
@@ -419,10 +419,10 @@
 	}
 
 	if (host->cmd_flags & DMA_DATA) {
-		if (1 != pci_map_sg(host->chip->pdev, &host->req->sg, 1,
+		if (1 != dma_map_sg(&host->chip->pdev->dev, &host->req->sg, 1,
 				    host->req->data_dir == READ
-				    ? PCI_DMA_FROMDEVICE
-				    : PCI_DMA_TODEVICE)) {
+				    ? DMA_FROM_DEVICE
+				    : DMA_TO_DEVICE)) {
 			host->req->error = -ENOMEM;
 			return host->req->error;
 		}
@@ -487,9 +487,9 @@
 	writel(0, host->addr + DMA_CONTROL);
 
 	if (host->cmd_flags & DMA_DATA) {
-		pci_unmap_sg(host->chip->pdev, &host->req->sg, 1,
+		dma_unmap_sg(&host->chip->pdev->dev, &host->req->sg, 1,
 			     host->req->data_dir == READ
-			     ? PCI_DMA_FROMDEVICE : PCI_DMA_TODEVICE);
+			     ? DMA_FROM_DEVICE : DMA_TO_DEVICE);
 	} else {
 		t_val = readl(host->addr + INT_STATUS_ENABLE);
 		if (host->req->data_dir == READ)
@@ -925,7 +925,7 @@
 	int pci_dev_busy = 0;
 	int rc, cnt;
 
-	rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+	rc = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
 	if (rc)
 		return rc;
 
diff --git a/drivers/memstick/host/r592.c b/drivers/memstick/host/r592.c
index e2a4f5f..ef09ba0 100644
--- a/drivers/memstick/host/r592.c
+++ b/drivers/memstick/host/r592.c
@@ -754,7 +754,7 @@
 		goto error2;
 
 	pci_set_master(pdev);
-	error = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+	error = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
 	if (error)
 		goto error3;
 
@@ -787,8 +787,8 @@
 	}
 
 	/* This is just a precation, so don't fail */
-	dev->dummy_dma_page = pci_alloc_consistent(pdev, PAGE_SIZE,
-		&dev->dummy_dma_page_physical_address);
+	dev->dummy_dma_page = dma_alloc_coherent(&pdev->dev, PAGE_SIZE,
+		&dev->dummy_dma_page_physical_address, GFP_KERNEL);
 	r592_stop_dma(dev , 0);
 
 	if (request_irq(dev->irq, &r592_irq, IRQF_SHARED,
@@ -805,7 +805,7 @@
 	free_irq(dev->irq, dev);
 error6:
 	if (dev->dummy_dma_page)
-		pci_free_consistent(pdev, PAGE_SIZE, dev->dummy_dma_page,
+		dma_free_coherent(&pdev->dev, PAGE_SIZE, dev->dummy_dma_page,
 			dev->dummy_dma_page_physical_address);
 
 	kthread_stop(dev->io_thread);
@@ -845,7 +845,7 @@
 	memstick_free_host(dev->host);
 
 	if (dev->dummy_dma_page)
-		pci_free_consistent(pdev, PAGE_SIZE, dev->dummy_dma_page,
+		dma_free_coherent(&pdev->dev, PAGE_SIZE, dev->dummy_dma_page,
 			dev->dummy_dma_page_physical_address);
 }
 
diff --git a/drivers/mfd/asic3.c b/drivers/mfd/asic3.c
index 977bd3a..120df5c 100644
--- a/drivers/mfd/asic3.c
+++ b/drivers/mfd/asic3.c
@@ -417,9 +417,8 @@
 	asic3_write_register(asic, ASIC3_OFFSET(INTR, INT_MASK),
 			     ASIC3_INTMASK_GINTMASK);
 
-	irq_set_chained_handler(asic->irq_nr, asic3_irq_demux);
+	irq_set_chained_handler_and_data(asic->irq_nr, asic3_irq_demux, asic);
 	irq_set_irq_type(asic->irq_nr, IRQ_TYPE_EDGE_RISING);
-	irq_set_handler_data(asic->irq_nr, asic);
 
 	return 0;
 }
diff --git a/drivers/misc/lis3lv02d/lis3lv02d.c b/drivers/misc/lis3lv02d/lis3lv02d.c
index 4739689..fb8705f 100644
--- a/drivers/misc/lis3lv02d/lis3lv02d.c
+++ b/drivers/misc/lis3lv02d/lis3lv02d.c
@@ -115,7 +115,7 @@
 	return ret;
 }
 
-static struct kernel_param_ops param_ops_axis = {
+static const struct kernel_param_ops param_ops_axis = {
 	.set = param_set_axis,
 	.get = param_get_int,
 };
diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c
index 357b6ae..458aa5a 100644
--- a/drivers/misc/mei/bus.c
+++ b/drivers/misc/mei/bus.c
@@ -552,22 +552,6 @@
 	schedule_work(&device->event_work);
 }
 
-void mei_cl_bus_remove_devices(struct mei_device *dev)
-{
-	struct mei_cl *cl, *next;
-
-	mutex_lock(&dev->device_lock);
-	list_for_each_entry_safe(cl, next, &dev->device_list, device_link) {
-		if (cl->device)
-			mei_cl_remove_device(cl->device);
-
-		list_del(&cl->device_link);
-		mei_cl_unlink(cl);
-		kfree(cl);
-	}
-	mutex_unlock(&dev->device_lock);
-}
-
 int __init mei_cl_bus_init(void)
 {
 	return bus_register(&mei_cl_bus_type);
diff --git a/drivers/misc/mei/init.c b/drivers/misc/mei/init.c
index 94514b2..00c3865 100644
--- a/drivers/misc/mei/init.c
+++ b/drivers/misc/mei/init.c
@@ -333,8 +333,6 @@
 
 	mei_nfc_host_exit(dev);
 
-	mei_cl_bus_remove_devices(dev);
-
 	mutex_lock(&dev->device_lock);
 
 	mei_wd_stop(dev);
diff --git a/drivers/misc/mei/nfc.c b/drivers/misc/mei/nfc.c
index b983c4e..290ef30 100644
--- a/drivers/misc/mei/nfc.c
+++ b/drivers/misc/mei/nfc.c
@@ -402,11 +402,12 @@
 
 	cldev->priv_data = NULL;
 
-	mutex_lock(&dev->device_lock);
 	/* Need to remove the device here
 	 * since mei_nfc_free will unlink the clients
 	 */
 	mei_cl_remove_device(cldev);
+
+	mutex_lock(&dev->device_lock);
 	mei_nfc_free(ndev);
 	mutex_unlock(&dev->device_lock);
 }
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index 9df2b68..b2b411d 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -43,6 +43,7 @@
 #include <linux/regulator/consumer.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/pm_runtime.h>
+#include <linux/pm_wakeirq.h>
 #include <linux/platform_data/hsmmc-omap.h>
 
 /* OMAP HSMMC Host Controller Registers */
@@ -218,7 +219,6 @@
 	unsigned int		flags;
 #define AUTO_CMD23		(1 << 0)        /* Auto CMD23 support */
 #define HSMMC_SDIO_IRQ_ENABLED	(1 << 1)        /* SDIO irq enabled */
-#define HSMMC_WAKE_IRQ_ENABLED	(1 << 2)
 	struct omap_hsmmc_next	next_data;
 	struct	omap_hsmmc_platform_data	*pdata;
 
@@ -1117,22 +1117,6 @@
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t omap_hsmmc_wake_irq(int irq, void *dev_id)
-{
-	struct omap_hsmmc_host *host = dev_id;
-
-	/* cirq is level triggered, disable to avoid infinite loop */
-	spin_lock(&host->irq_lock);
-	if (host->flags & HSMMC_WAKE_IRQ_ENABLED) {
-		disable_irq_nosync(host->wake_irq);
-		host->flags &= ~HSMMC_WAKE_IRQ_ENABLED;
-	}
-	spin_unlock(&host->irq_lock);
-	pm_request_resume(host->dev); /* no use counter */
-
-	return IRQ_HANDLED;
-}
-
 static void set_sd_bus_power(struct omap_hsmmc_host *host)
 {
 	unsigned long i;
@@ -1665,7 +1649,6 @@
 
 static int omap_hsmmc_configure_wake_irq(struct omap_hsmmc_host *host)
 {
-	struct mmc_host *mmc = host->mmc;
 	int ret;
 
 	/*
@@ -1677,11 +1660,7 @@
 	if (!host->dev->of_node || !host->wake_irq)
 		return -ENODEV;
 
-	/* Prevent auto-enabling of IRQ */
-	irq_set_status_flags(host->wake_irq, IRQ_NOAUTOEN);
-	ret = devm_request_irq(host->dev, host->wake_irq, omap_hsmmc_wake_irq,
-			       IRQF_TRIGGER_LOW | IRQF_ONESHOT,
-			       mmc_hostname(mmc), host);
+	ret = dev_pm_set_dedicated_wake_irq(host->dev, host->wake_irq);
 	if (ret) {
 		dev_err(mmc_dev(host->mmc), "Unable to request wake IRQ\n");
 		goto err;
@@ -1718,7 +1697,7 @@
 	return 0;
 
 err_free_irq:
-	devm_free_irq(host->dev, host->wake_irq, host);
+	dev_pm_clear_wake_irq(host->dev);
 err:
 	dev_warn(host->dev, "no SDIO IRQ support, falling back to polling\n");
 	host->wake_irq = 0;
@@ -2007,6 +1986,7 @@
 		omap_hsmmc_ops.multi_io_quirk = omap_hsmmc_multi_io_quirk;
 	}
 
+	device_init_wakeup(&pdev->dev, true);
 	pm_runtime_enable(host->dev);
 	pm_runtime_get_sync(host->dev);
 	pm_runtime_set_autosuspend_delay(host->dev, MMC_AUTOSUSPEND_DELAY);
@@ -2147,6 +2127,7 @@
 	if (host->use_reg)
 		omap_hsmmc_reg_put(host);
 err_irq:
+	device_init_wakeup(&pdev->dev, false);
 	if (host->tx_chan)
 		dma_release_channel(host->tx_chan);
 	if (host->rx_chan)
@@ -2178,6 +2159,7 @@
 
 	pm_runtime_put_sync(host->dev);
 	pm_runtime_disable(host->dev);
+	device_init_wakeup(&pdev->dev, false);
 	if (host->dbclk)
 		clk_disable_unprepare(host->dbclk);
 
@@ -2204,11 +2186,6 @@
 				OMAP_HSMMC_READ(host->base, HCTL) & ~SDBP);
 	}
 
-	/* do not wake up due to sdio irq */
-	if ((host->mmc->caps & MMC_CAP_SDIO_IRQ) &&
-	    !(host->mmc->pm_flags & MMC_PM_WAKE_SDIO_IRQ))
-		disable_irq(host->wake_irq);
-
 	if (host->dbclk)
 		clk_disable_unprepare(host->dbclk);
 
@@ -2233,11 +2210,6 @@
 		omap_hsmmc_conf_bus_power(host);
 
 	omap_hsmmc_protect_card(host);
-
-	if ((host->mmc->caps & MMC_CAP_SDIO_IRQ) &&
-	    !(host->mmc->pm_flags & MMC_PM_WAKE_SDIO_IRQ))
-		enable_irq(host->wake_irq);
-
 	pm_runtime_mark_last_busy(host->dev);
 	pm_runtime_put_autosuspend(host->dev);
 	return 0;
@@ -2277,10 +2249,6 @@
 		}
 
 		pinctrl_pm_select_idle_state(dev);
-
-		WARN_ON(host->flags & HSMMC_WAKE_IRQ_ENABLED);
-		enable_irq(host->wake_irq);
-		host->flags |= HSMMC_WAKE_IRQ_ENABLED;
 	} else {
 		pinctrl_pm_select_idle_state(dev);
 	}
@@ -2302,11 +2270,6 @@
 	spin_lock_irqsave(&host->irq_lock, flags);
 	if ((host->mmc->caps & MMC_CAP_SDIO_IRQ) &&
 	    (host->flags & HSMMC_SDIO_IRQ_ENABLED)) {
-		/* sdio irq flag can't change while in runtime suspend */
-		if (host->flags & HSMMC_WAKE_IRQ_ENABLED) {
-			disable_irq_nosync(host->wake_irq);
-			host->flags &= ~HSMMC_WAKE_IRQ_ENABLED;
-		}
 
 		pinctrl_pm_select_default_state(host->dev);
 
diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c
index 1a92d30..ebf46ad 100644
--- a/drivers/mtd/ubi/block.c
+++ b/drivers/mtd/ubi/block.c
@@ -162,7 +162,7 @@
 	return 0;
 }
 
-static struct kernel_param_ops ubiblock_param_ops = {
+static const struct kernel_param_ops ubiblock_param_ops = {
 	.set    = ubiblock_set_param,
 };
 module_param_cb(block, &ubiblock_param_ops, NULL, 0);
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 019fcef..c18f9e6 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -217,8 +217,8 @@
 	def_bool NETPOLL
 
 config NTB_NETDEV
-	tristate "Virtual Ethernet over NTB"
-	depends on NTB
+	tristate "Virtual Ethernet over NTB Transport"
+	depends on NTB_TRANSPORT
 
 config RIONET
 	tristate "RapidIO Ethernet over messaging driver support"
@@ -258,6 +258,20 @@
 
 	  If you don't know what to use this for, you don't need it.
 
+config TUN_VNET_CROSS_LE
+	bool "Support for cross-endian vnet headers on little-endian kernels"
+	default n
+	---help---
+	  This option allows TUN/TAP and MACVTAP device drivers in a
+	  little-endian kernel to parse vnet headers that come from a
+	  big-endian legacy virtio device.
+
+	  Userspace programs can control the feature using the TUNSETVNETBE
+	  and TUNGETVNETBE ioctls.
+
+	  Unless you have a little-endian system hosting a big-endian virtual
+	  machine with a legacy virtio NIC, you should say N.
+
 config VETH
 	tristate "Virtual ethernet pair device"
 	---help---
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
index dd03ad8..661cdaa 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
@@ -268,7 +268,7 @@
 	int ret;
 
 	/* Try to obtain pages, decreasing order if necessary */
-	gfp |= __GFP_COLD | __GFP_COMP;
+	gfp |= __GFP_COLD | __GFP_COMP | __GFP_NOWARN;
 	while (order >= 0) {
 		pages = alloc_pages(gfp, order);
 		if (pages)
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
index 95153b2..299eb43 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
@@ -948,7 +948,7 @@
 	struct resource *res;
 	void __iomem *base_addr;
 	u32 offset;
-	int ret;
+	int ret = 0;
 
 	pdev = pdata->pdev;
 	dev = &pdev->dev;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 7a4aaa3..cd4ae76 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -530,7 +530,6 @@
 
 struct bnx2x_alloc_pool {
 	struct page	*page;
-	dma_addr_t	dma;
 	unsigned int	offset;
 };
 
@@ -2418,10 +2417,13 @@
 				 AEU_INPUTS_ATTN_BITS_IGU_PARITY_ERROR | \
 				 AEU_INPUTS_ATTN_BITS_MISC_PARITY_ERROR)
 
-#define HW_PRTY_ASSERT_SET_3 (AEU_INPUTS_ATTN_BITS_MCP_LATCHED_ROM_PARITY | \
-		AEU_INPUTS_ATTN_BITS_MCP_LATCHED_UMP_RX_PARITY | \
-		AEU_INPUTS_ATTN_BITS_MCP_LATCHED_UMP_TX_PARITY | \
-		AEU_INPUTS_ATTN_BITS_MCP_LATCHED_SCPAD_PARITY)
+#define HW_PRTY_ASSERT_SET_3_WITHOUT_SCPAD \
+		(AEU_INPUTS_ATTN_BITS_MCP_LATCHED_ROM_PARITY | \
+		 AEU_INPUTS_ATTN_BITS_MCP_LATCHED_UMP_RX_PARITY | \
+		 AEU_INPUTS_ATTN_BITS_MCP_LATCHED_UMP_TX_PARITY)
+
+#define HW_PRTY_ASSERT_SET_3 (HW_PRTY_ASSERT_SET_3_WITHOUT_SCPAD | \
+			      AEU_INPUTS_ATTN_BITS_MCP_LATCHED_SCPAD_PARITY)
 
 #define HW_PRTY_ASSERT_SET_4 (AEU_INPUTS_ATTN_BITS_PGLUE_PARITY_ERROR | \
 			      AEU_INPUTS_ATTN_BITS_ATC_PARITY_ERROR)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index e2a6533..a90d736 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -563,23 +563,20 @@
 			return -ENOMEM;
 		}
 
-		pool->dma = dma_map_page(&bp->pdev->dev, pool->page, 0,
-					 PAGE_SIZE, DMA_FROM_DEVICE);
-		if (unlikely(dma_mapping_error(&bp->pdev->dev,
-					       pool->dma))) {
-			__free_pages(pool->page, PAGES_PER_SGE_SHIFT);
-			pool->page = NULL;
-			BNX2X_ERR("Can't map sge\n");
-			return -ENOMEM;
-		}
 		pool->offset = 0;
 	}
 
+	mapping = dma_map_page(&bp->pdev->dev, pool->page,
+			       pool->offset, SGE_PAGE_SIZE, DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(&bp->pdev->dev, mapping))) {
+		BNX2X_ERR("Can't map sge\n");
+		return -ENOMEM;
+	}
+
 	get_page(pool->page);
 	sw_buf->page = pool->page;
 	sw_buf->offset = pool->offset;
 
-	mapping = pool->dma + sw_buf->offset;
 	dma_unmap_addr_set(sw_buf, mapping, mapping);
 
 	sge->addr_hi = cpu_to_le32(U64_HI(mapping));
@@ -648,9 +645,9 @@
 			return err;
 		}
 
-		dma_unmap_single(&bp->pdev->dev,
-				 dma_unmap_addr(&old_rx_pg, mapping),
-				 SGE_PAGE_SIZE, DMA_FROM_DEVICE);
+		dma_unmap_page(&bp->pdev->dev,
+			       dma_unmap_addr(&old_rx_pg, mapping),
+			       SGE_PAGE_SIZE, DMA_FROM_DEVICE);
 		/* Add one frag and update the appropriate fields in the skb */
 		if (fp->mode == TPA_MODE_LRO)
 			skb_fill_page_desc(skb, j, old_rx_pg.page,
@@ -3421,8 +3418,13 @@
 			u32 wnd_sum = 0;
 
 			/* Headers length */
-			hlen = (int)(skb_transport_header(skb) - skb->data) +
-				tcp_hdrlen(skb);
+			if (xmit_type & XMIT_GSO_ENC)
+				hlen = (int)(skb_inner_transport_header(skb) -
+					     skb->data) +
+					     inner_tcp_hdrlen(skb);
+			else
+				hlen = (int)(skb_transport_header(skb) -
+					     skb->data) + tcp_hdrlen(skb);
 
 			/* Amount of data (w/o headers) on linear part of SKB*/
 			first_bd_sz = skb_headlen(skb) - hlen;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index 2b30081..03b7404 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -807,8 +807,8 @@
 	/* Since many fragments can share the same page, make sure to
 	 * only unmap and free the page once.
 	 */
-	dma_unmap_single(&bp->pdev->dev, dma_unmap_addr(sw_buf, mapping),
-			 SGE_PAGE_SIZE, DMA_FROM_DEVICE);
+	dma_unmap_page(&bp->pdev->dev, dma_unmap_addr(sw_buf, mapping),
+		       SGE_PAGE_SIZE, DMA_FROM_DEVICE);
 
 	put_page(page);
 
@@ -974,14 +974,6 @@
 	if (!pool->page)
 		return;
 
-	/* Page was not fully fragmented.  Unmap unused space */
-	if (pool->offset < PAGE_SIZE) {
-		dma_addr_t dma = pool->dma + pool->offset;
-		int size = PAGE_SIZE - pool->offset;
-
-		dma_unmap_single(&bp->pdev->dev, dma, size, DMA_FROM_DEVICE);
-	}
-
 	put_page(pool->page);
 
 	pool->page = NULL;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index 48ed005..76b9052 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -257,14 +257,15 @@
 {
 	struct bnx2x *bp = netdev_priv(dev);
 	int cfg_idx = bnx2x_get_link_cfg_idx(bp);
+	u32 media_type;
 
 	/* Dual Media boards present all available port types */
 	cmd->supported = bp->port.supported[cfg_idx] |
 		(bp->port.supported[cfg_idx ^ 1] &
 		 (SUPPORTED_TP | SUPPORTED_FIBRE));
 	cmd->advertising = bp->port.advertising[cfg_idx];
-	if (bp->link_params.phy[bnx2x_get_cur_phy_idx(bp)].media_type ==
-	    ETH_PHY_SFP_1G_FIBER) {
+	media_type = bp->link_params.phy[bnx2x_get_cur_phy_idx(bp)].media_type;
+	if (media_type == ETH_PHY_SFP_1G_FIBER) {
 		cmd->supported &= ~(SUPPORTED_10000baseT_Full);
 		cmd->advertising &= ~(ADVERTISED_10000baseT_Full);
 	}
@@ -312,12 +313,26 @@
 			cmd->lp_advertising |= ADVERTISED_100baseT_Full;
 		if (status & LINK_STATUS_LINK_PARTNER_1000THD_CAPABLE)
 			cmd->lp_advertising |= ADVERTISED_1000baseT_Half;
-		if (status & LINK_STATUS_LINK_PARTNER_1000TFD_CAPABLE)
-			cmd->lp_advertising |= ADVERTISED_1000baseT_Full;
+		if (status & LINK_STATUS_LINK_PARTNER_1000TFD_CAPABLE) {
+			if (media_type == ETH_PHY_KR) {
+				cmd->lp_advertising |=
+					ADVERTISED_1000baseKX_Full;
+			} else {
+				cmd->lp_advertising |=
+					ADVERTISED_1000baseT_Full;
+			}
+		}
 		if (status & LINK_STATUS_LINK_PARTNER_2500XFD_CAPABLE)
 			cmd->lp_advertising |= ADVERTISED_2500baseX_Full;
-		if (status & LINK_STATUS_LINK_PARTNER_10GXFD_CAPABLE)
-			cmd->lp_advertising |= ADVERTISED_10000baseT_Full;
+		if (status & LINK_STATUS_LINK_PARTNER_10GXFD_CAPABLE) {
+			if (media_type == ETH_PHY_KR) {
+				cmd->lp_advertising |=
+					ADVERTISED_10000baseKR_Full;
+			} else {
+				cmd->lp_advertising |=
+					ADVERTISED_10000baseT_Full;
+			}
+		}
 		if (status & LINK_STATUS_LINK_PARTNER_20GXFD_CAPABLE)
 			cmd->lp_advertising |= ADVERTISED_20000baseKR2_Full;
 	}
@@ -564,15 +579,20 @@
 				return -EINVAL;
 			}
 
-			if (!(bp->port.supported[cfg_idx] &
-			      SUPPORTED_1000baseT_Full)) {
+			if (bp->port.supported[cfg_idx] &
+			     SUPPORTED_1000baseT_Full) {
+				advertising = (ADVERTISED_1000baseT_Full |
+					       ADVERTISED_TP);
+
+			} else if (bp->port.supported[cfg_idx] &
+				   SUPPORTED_1000baseKX_Full) {
+				advertising = ADVERTISED_1000baseKX_Full;
+			} else {
 				DP(BNX2X_MSG_ETHTOOL,
 				   "1G full not supported\n");
 				return -EINVAL;
 			}
 
-			advertising = (ADVERTISED_1000baseT_Full |
-				       ADVERTISED_TP);
 			break;
 
 		case SPEED_2500:
@@ -600,17 +620,22 @@
 				return -EINVAL;
 			}
 			phy_idx = bnx2x_get_cur_phy_idx(bp);
-			if (!(bp->port.supported[cfg_idx]
-			      & SUPPORTED_10000baseT_Full) ||
-			    (bp->link_params.phy[phy_idx].media_type ==
+			if ((bp->port.supported[cfg_idx] &
+			     SUPPORTED_10000baseT_Full) &&
+			    (bp->link_params.phy[phy_idx].media_type !=
 			     ETH_PHY_SFP_1G_FIBER)) {
+				advertising = (ADVERTISED_10000baseT_Full |
+					       ADVERTISED_FIBRE);
+			} else if (bp->port.supported[cfg_idx] &
+			       SUPPORTED_10000baseKR_Full) {
+				advertising = (ADVERTISED_10000baseKR_Full |
+					       ADVERTISED_FIBRE);
+			} else {
 				DP(BNX2X_MSG_ETHTOOL,
 				   "10G full not supported\n");
 				return -EINVAL;
 			}
 
-			advertising = (ADVERTISED_10000baseT_Full |
-				       ADVERTISED_FIBRE);
 			break;
 
 		default:
@@ -633,6 +658,7 @@
 	bp->link_params.multi_phy_config = new_multi_phy_config;
 	if (netif_running(dev)) {
 		bnx2x_stats_handle(bp, STATS_EVENT_STOP);
+		bnx2x_force_link_reset(bp);
 		bnx2x_link_set(bp);
 	}
 
@@ -1204,6 +1230,7 @@
 	if (!(val & (MCPR_NVM_SW_ARB_ARB_ARB1 << port))) {
 		DP(BNX2X_MSG_ETHTOOL | BNX2X_MSG_NVM,
 		   "cannot get access to nvram interface\n");
+		bnx2x_release_hw_lock(bp, HW_LOCK_RESOURCE_NVRAM);
 		return -EBUSY;
 	}
 
@@ -1944,6 +1971,7 @@
 
 	if (netif_running(dev)) {
 		bnx2x_stats_handle(bp, STATS_EVENT_STOP);
+		bnx2x_force_link_reset(bp);
 		bnx2x_link_set(bp);
 	}
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 21a0d6a..a0b03c2 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -3392,9 +3392,9 @@
 	case BNX2X_FLOW_CTRL_AUTO:
 		switch (params->req_fc_auto_adv) {
 		case BNX2X_FLOW_CTRL_BOTH:
+		case BNX2X_FLOW_CTRL_RX:
 			*ieee_fc |= MDIO_COMBO_IEEE0_AUTO_NEG_ADV_PAUSE_BOTH;
 			break;
-		case BNX2X_FLOW_CTRL_RX:
 		case BNX2X_FLOW_CTRL_TX:
 			*ieee_fc |=
 				MDIO_COMBO_IEEE0_AUTO_NEG_ADV_PAUSE_ASYMMETRIC;
@@ -3488,14 +3488,21 @@
 	bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD, MDIO_AN_REG_ADV_PAUSE, val);
 }
 
-static void bnx2x_pause_resolve(struct link_vars *vars, u32 pause_result)
-{						/*  LD	    LP	 */
+static void bnx2x_pause_resolve(struct bnx2x_phy *phy,
+				struct link_params *params,
+				struct link_vars *vars,
+				u32 pause_result)
+{
+	struct bnx2x *bp = params->bp;
+						/*  LD	    LP	 */
 	switch (pause_result) {			/* ASYM P ASYM P */
 	case 0xb:				/*   1  0   1  1 */
+		DP(NETIF_MSG_LINK, "Flow Control: TX only\n");
 		vars->flow_ctrl = BNX2X_FLOW_CTRL_TX;
 		break;
 
 	case 0xe:				/*   1  1   1  0 */
+		DP(NETIF_MSG_LINK, "Flow Control: RX only\n");
 		vars->flow_ctrl = BNX2X_FLOW_CTRL_RX;
 		break;
 
@@ -3503,10 +3510,22 @@
 	case 0x7:				/*   0  1   1  1 */
 	case 0xd:				/*   1  1   0  1 */
 	case 0xf:				/*   1  1   1  1 */
-		vars->flow_ctrl = BNX2X_FLOW_CTRL_BOTH;
+		/* If the user selected to advertise RX ONLY,
+		 * although we advertised both, need to enable
+		 * RX only.
+		 */
+		if (params->req_fc_auto_adv == BNX2X_FLOW_CTRL_BOTH) {
+			DP(NETIF_MSG_LINK, "Flow Control: RX & TX\n");
+			vars->flow_ctrl = BNX2X_FLOW_CTRL_BOTH;
+		} else {
+			DP(NETIF_MSG_LINK, "Flow Control: RX only\n");
+			vars->flow_ctrl = BNX2X_FLOW_CTRL_RX;
+		}
 		break;
 
 	default:
+		DP(NETIF_MSG_LINK, "Flow Control: None\n");
+		vars->flow_ctrl = BNX2X_FLOW_CTRL_NONE;
 		break;
 	}
 	if (pause_result & (1<<0))
@@ -3567,7 +3586,7 @@
 	pause_result |= (lp_pause &
 			 MDIO_AN_REG_ADV_PAUSE_MASK) >> 10;
 	DP(NETIF_MSG_LINK, "Ext PHY pause result 0x%x\n", pause_result);
-	bnx2x_pause_resolve(vars, pause_result);
+	bnx2x_pause_resolve(phy, params, vars, pause_result);
 
 }
 
@@ -5396,7 +5415,7 @@
 				 MDIO_COMBO_IEEE0_AUTO_NEG_ADV_PAUSE_MASK)>>7;
 		DP(NETIF_MSG_LINK, "pause_result CL37 0x%x\n", pause_result);
 	}
-	bnx2x_pause_resolve(vars, pause_result);
+	bnx2x_pause_resolve(phy, params, vars, pause_result);
 
 }
 
@@ -7129,7 +7148,7 @@
 		pause_result |= (lp_pause &
 				 MDIO_COMBO_IEEE0_AUTO_NEG_ADV_PAUSE_BOTH) >> 7;
 
-		bnx2x_pause_resolve(vars, pause_result);
+		bnx2x_pause_resolve(phy, params, vars, pause_result);
 		DP(NETIF_MSG_LINK, "Ext PHY CL37 pause result 0x%x\n",
 			   pause_result);
 	}
@@ -11474,7 +11493,9 @@
 			   SUPPORTED_100baseT_Half |
 			   SUPPORTED_100baseT_Full |
 			   SUPPORTED_1000baseT_Full |
+			   SUPPORTED_1000baseKX_Full |
 			   SUPPORTED_10000baseT_Full |
+			   SUPPORTED_10000baseKR_Full |
 			   SUPPORTED_20000baseKR2_Full |
 			   SUPPORTED_20000baseMLD2_Full |
 			   SUPPORTED_FIBRE |
@@ -11980,8 +12001,8 @@
 			break;
 		case PORT_HW_CFG_NET_SERDES_IF_KR:
 			phy->media_type = ETH_PHY_KR;
-			phy->supported &= (SUPPORTED_1000baseT_Full |
-					   SUPPORTED_10000baseT_Full |
+			phy->supported &= (SUPPORTED_1000baseKX_Full |
+					   SUPPORTED_10000baseKR_Full |
 					   SUPPORTED_FIBRE |
 					   SUPPORTED_Autoneg |
 					   SUPPORTED_Pause |
@@ -11999,8 +12020,8 @@
 			phy->media_type = ETH_PHY_KR;
 			phy->flags |= FLAGS_WC_DUAL_MODE;
 			phy->supported &= (SUPPORTED_20000baseKR2_Full |
-					   SUPPORTED_10000baseT_Full |
-					   SUPPORTED_1000baseT_Full |
+					   SUPPORTED_10000baseKR_Full |
+					   SUPPORTED_1000baseKX_Full |
 					   SUPPORTED_Autoneg |
 					   SUPPORTED_FIBRE |
 					   SUPPORTED_Pause |
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 33501bc..c27af12 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -2287,13 +2287,11 @@
 void bnx2x_calc_fc_adv(struct bnx2x *bp)
 {
 	u8 cfg_idx = bnx2x_get_link_cfg_idx(bp);
+
+	bp->port.advertising[cfg_idx] &= ~(ADVERTISED_Asym_Pause |
+					   ADVERTISED_Pause);
 	switch (bp->link_vars.ieee_fc &
 		MDIO_COMBO_IEEE0_AUTO_NEG_ADV_PAUSE_MASK) {
-	case MDIO_COMBO_IEEE0_AUTO_NEG_ADV_PAUSE_NONE:
-		bp->port.advertising[cfg_idx] &= ~(ADVERTISED_Asym_Pause |
-						   ADVERTISED_Pause);
-		break;
-
 	case MDIO_COMBO_IEEE0_AUTO_NEG_ADV_PAUSE_BOTH:
 		bp->port.advertising[cfg_idx] |= (ADVERTISED_Asym_Pause |
 						  ADVERTISED_Pause);
@@ -2304,8 +2302,6 @@
 		break;
 
 	default:
-		bp->port.advertising[cfg_idx] &= ~(ADVERTISED_Asym_Pause |
-						   ADVERTISED_Pause);
 		break;
 	}
 }
@@ -2351,12 +2347,16 @@
 		if (load_mode == LOAD_DIAG) {
 			struct link_params *lp = &bp->link_params;
 			lp->loopback_mode = LOOPBACK_XGXS;
-			/* do PHY loopback at 10G speed, if possible */
-			if (lp->req_line_speed[cfx_idx] < SPEED_10000) {
+			/* Prefer doing PHY loopback at highest speed */
+			if (lp->req_line_speed[cfx_idx] < SPEED_20000) {
 				if (lp->speed_cap_mask[cfx_idx] &
-				    PORT_HW_CFG_SPEED_CAPABILITY_D0_10G)
+				    PORT_HW_CFG_SPEED_CAPABILITY_D0_20G)
 					lp->req_line_speed[cfx_idx] =
-					SPEED_10000;
+					SPEED_20000;
+				else if (lp->speed_cap_mask[cfx_idx] &
+					    PORT_HW_CFG_SPEED_CAPABILITY_D0_10G)
+						lp->req_line_speed[cfx_idx] =
+						SPEED_10000;
 				else
 					lp->req_line_speed[cfx_idx] =
 					SPEED_1000;
@@ -4867,9 +4867,7 @@
 				res = true;
 				break;
 			case AEU_INPUTS_ATTN_BITS_MCP_LATCHED_SCPAD_PARITY:
-				if (print)
-					_print_next_block((*par_num)++,
-							  "MCP SCPAD");
+				(*par_num)++;
 				/* clear latched SCPAD PATIRY from MCP */
 				REG_WR(bp, MISC_REG_AEU_CLR_LATCH_SIGNAL,
 				       1UL << 10);
@@ -4931,6 +4929,7 @@
 	    (sig[3] & HW_PRTY_ASSERT_SET_3) ||
 	    (sig[4] & HW_PRTY_ASSERT_SET_4)) {
 		int par_num = 0;
+
 		DP(NETIF_MSG_HW, "Was parity error: HW block parity attention:\n"
 				 "[0]:0x%08x [1]:0x%08x [2]:0x%08x [3]:0x%08x [4]:0x%08x\n",
 			  sig[0] & HW_PRTY_ASSERT_SET_0,
@@ -4938,9 +4937,18 @@
 			  sig[2] & HW_PRTY_ASSERT_SET_2,
 			  sig[3] & HW_PRTY_ASSERT_SET_3,
 			  sig[4] & HW_PRTY_ASSERT_SET_4);
-		if (print)
-			netdev_err(bp->dev,
-				   "Parity errors detected in blocks: ");
+		if (print) {
+			if (((sig[0] & HW_PRTY_ASSERT_SET_0) ||
+			     (sig[1] & HW_PRTY_ASSERT_SET_1) ||
+			     (sig[2] & HW_PRTY_ASSERT_SET_2) ||
+			     (sig[4] & HW_PRTY_ASSERT_SET_4)) ||
+			     (sig[3] & HW_PRTY_ASSERT_SET_3_WITHOUT_SCPAD)) {
+				netdev_err(bp->dev,
+					   "Parity errors detected in blocks: ");
+			} else {
+				print = false;
+			}
+		}
 		res |= bnx2x_check_blocks_with_parity0(bp,
 			sig[0] & HW_PRTY_ASSERT_SET_0, &par_num, print);
 		res |= bnx2x_check_blocks_with_parity1(bp,
@@ -8431,7 +8439,7 @@
 					 BNX2X_ETH_MAC, &ramrod_flags);
 	} else { /* vf */
 		return bnx2x_vfpf_config_mac(bp, bp->dev->dev_addr,
-					     bp->fp->index, true);
+					     bp->fp->index, set);
 	}
 }
 
@@ -9323,7 +9331,8 @@
 	 * function stop ramrod is sent, since as part of this ramrod FW access
 	 * PTP registers.
 	 */
-	bnx2x_stop_ptp(bp);
+	if (bp->flags & PTP_SUPPORTED)
+		bnx2x_stop_ptp(bp);
 
 	/* Disable HW interrupts, NAPI */
 	bnx2x_netif_stop(bp, 1);
@@ -11147,6 +11156,12 @@
 				bp->port.advertising[idx] |=
 					(ADVERTISED_1000baseT_Full |
 					 ADVERTISED_TP);
+			} else if (bp->port.supported[idx] &
+				   SUPPORTED_1000baseKX_Full) {
+				bp->link_params.req_line_speed[idx] =
+					SPEED_1000;
+				bp->port.advertising[idx] |=
+					ADVERTISED_1000baseKX_Full;
 			} else {
 				BNX2X_ERR("NVRAM config error. Invalid link_config 0x%x  speed_cap_mask 0x%x\n",
 				    link_config,
@@ -11179,6 +11194,13 @@
 				bp->port.advertising[idx] |=
 					(ADVERTISED_10000baseT_Full |
 						ADVERTISED_FIBRE);
+			} else if (bp->port.supported[idx] &
+				   SUPPORTED_10000baseKR_Full) {
+				bp->link_params.req_line_speed[idx] =
+					SPEED_10000;
+				bp->port.advertising[idx] |=
+					(ADVERTISED_10000baseKR_Full |
+						ADVERTISED_FIBRE);
 			} else {
 				BNX2X_ERR("NVRAM config error. Invalid link_config 0x%x  speed_cap_mask 0x%x\n",
 				    link_config,
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index 07cdf9b..4ad415a 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -424,7 +424,7 @@
 	o->head_exe_request = false;
 	o->saved_ramrod_flags = 0;
 	rc = bnx2x_exe_queue_step(bp, &o->exe_queue, &ramrod_flags);
-	if (rc != 0) {
+	if ((rc != 0) && (rc != 1)) {
 		BNX2X_ERR("execution of pending commands failed with rc %d\n",
 			  rc);
 #ifdef BNX2X_STOP_ON_ERROR
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 6f2887a..6159dea 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -594,6 +594,7 @@
 	wait_queue_head_t wq;
 	struct phy_device *phydev;
 	struct device_node *phy_dn;
+	struct device_node *mdio_dn;
 	struct mii_bus *mii_bus;
 	u16 gphy_rev;
 	struct clk *clk_eee;
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 6bef04e..adf23d2 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -408,6 +408,52 @@
 	return 0;
 }
 
+/* Workaround for integrated BCM7xxx Gigabit PHYs which have a problem with
+ * their internal MDIO management controller making them fail to successfully
+ * be read from or written to for the first transaction.  We insert a dummy
+ * BMSR read here to make sure that phy_get_device() and get_phy_id() can
+ * correctly read the PHY MII_PHYSID1/2 registers and successfully register a
+ * PHY device for this peripheral.
+ *
+ * Once the PHY driver is registered, we can workaround subsequent reads from
+ * there (e.g: during system-wide power management).
+ *
+ * bus->reset is invoked before mdiobus_scan during mdiobus_register and is
+ * therefore the right location to stick that workaround. Since we do not want
+ * to read from non-existing PHYs, we either use bus->phy_mask or do a manual
+ * Device Tree scan to limit the search area.
+ */
+static int bcmgenet_mii_bus_reset(struct mii_bus *bus)
+{
+	struct net_device *dev = bus->priv;
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct device_node *np = priv->mdio_dn;
+	struct device_node *child = NULL;
+	u32 read_mask = 0;
+	int addr = 0;
+
+	if (!np) {
+		read_mask = 1 << priv->phy_addr;
+	} else {
+		for_each_available_child_of_node(np, child) {
+			addr = of_mdio_parse_addr(&dev->dev, child);
+			if (addr < 0)
+				continue;
+
+			read_mask |= 1 << addr;
+		}
+	}
+
+	for (addr = 0; addr < PHY_MAX_ADDR; addr++) {
+		if (read_mask & 1 << addr) {
+			dev_dbg(&dev->dev, "Workaround for PHY @ %d\n", addr);
+			mdiobus_read(bus, addr, MII_BMSR);
+		}
+	}
+
+	return 0;
+}
+
 static int bcmgenet_mii_alloc(struct bcmgenet_priv *priv)
 {
 	struct mii_bus *bus;
@@ -427,6 +473,7 @@
 	bus->parent = &priv->pdev->dev;
 	bus->read = bcmgenet_mii_read;
 	bus->write = bcmgenet_mii_write;
+	bus->reset = bcmgenet_mii_bus_reset;
 	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-%d",
 		 priv->pdev->name, priv->pdev->id);
 
@@ -443,7 +490,6 @@
 {
 	struct device_node *dn = priv->pdev->dev.of_node;
 	struct device *kdev = &priv->pdev->dev;
-	struct device_node *mdio_dn;
 	char *compat;
 	int ret;
 
@@ -451,14 +497,14 @@
 	if (!compat)
 		return -ENOMEM;
 
-	mdio_dn = of_find_compatible_node(dn, NULL, compat);
+	priv->mdio_dn = of_find_compatible_node(dn, NULL, compat);
 	kfree(compat);
-	if (!mdio_dn) {
+	if (!priv->mdio_dn) {
 		dev_err(kdev, "unable to find MDIO bus node\n");
 		return -ENODEV;
 	}
 
-	ret = of_mdiobus_register(priv->mii_bus, mdio_dn);
+	ret = of_mdiobus_register(priv->mii_bus, priv->mdio_dn);
 	if (ret) {
 		dev_err(kdev, "failed to register MDIO bus\n");
 		return ret;
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
index 160f807..29f3308 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
@@ -434,8 +434,9 @@
 			if (ret)
 				return ret;
 
-			octnet_mdio45_access(lio, 1, LIO68XX_LED_BEACON_ADDR,
-					     &lio->phy_beacon_val);
+			ret = octnet_mdio45_access(lio, 1,
+						   LIO68XX_LED_BEACON_ADDR,
+						   &lio->phy_beacon_val);
 			if (ret)
 				return ret;
 
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
index 0d3106b..f67641a 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
@@ -650,14 +650,12 @@
 
 	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES; i++) {
 		/* could check  mask as well */
-		if (oct->droq[i])
-			vfree(oct->droq[i]);
+		vfree(oct->droq[i]);
 	}
 
 	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES; i++) {
 		/* could check mask as well */
-		if (oct->instr_queue[i])
-			vfree(oct->instr_queue[i]);
+		vfree(oct->instr_queue[i]);
 	}
 
 	i = oct->octeon_id;
@@ -1078,10 +1076,7 @@
 		oct->dispatch.count--;
 
 	spin_unlock_bh(&oct->dispatch.lock);
-
-	if (dfree)
-		vfree(dfree);
-
+	vfree(dfree);
 	return retval;
 }
 
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
index 94b502a..4dba86e 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
@@ -216,9 +216,7 @@
 	dev_dbg(&oct->pci_dev->dev, "%s[%d]\n", __func__, q_no);
 
 	octeon_droq_destroy_ring_buffers(oct, droq);
-
-	if (droq->recv_buf_list)
-		vfree(droq->recv_buf_list);
+	vfree(droq->recv_buf_list);
 
 	if (droq->info_base_addr)
 		cnnic_free_aligned_dma(oct->pci_dev, droq->info_list,
diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c
index 356796b..a2a2465 100644
--- a/drivers/net/ethernet/cavium/liquidio/request_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c
@@ -175,8 +175,7 @@
 		desc_size =
 		    CFG_GET_IQ_INSTR_TYPE(CHIP_FIELD(oct, cn6xxx, conf));
 
-	if (iq->request_list)
-		vfree(iq->request_list);
+	vfree(iq->request_list);
 
 	if (iq->base_addr) {
 		q_size = iq->max_count * desc_size;
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c
index b0cbb2b..76684dc 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c
@@ -1169,10 +1169,7 @@
  */
 void cxgb_free_mem(void *addr)
 {
-	if (is_vmalloc_addr(addr))
-		vfree(addr);
-	else
-		kfree(addr);
+	kvfree(addr);
 }
 
 /*
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index c64b5a9..351f3b1 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -1150,10 +1150,7 @@
  */
 void t4_free_mem(void *addr)
 {
-	if (is_vmalloc_addr(addr))
-		vfree(addr);
-	else
-		kfree(addr);
+	kvfree(addr);
 }
 
 /* Send a Work Request to write the filter at a specified index.  We construct
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index eadae1b..da2004e 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -1208,7 +1208,7 @@
 		napi_complete(napi);
 		vnic_intr_unmask(&enic->intr[intr]);
 	}
-	enic_poll_unlock_napi(&enic->rq[cq_rq]);
+	enic_poll_unlock_napi(&enic->rq[cq_rq], napi);
 
 	return rq_work_done;
 }
@@ -1414,7 +1414,7 @@
 		 */
 		enic_calc_int_moderation(enic, &enic->rq[rq]);
 
-	enic_poll_unlock_napi(&enic->rq[rq]);
+	enic_poll_unlock_napi(&enic->rq[rq], napi);
 	if (work_done < work_to_do) {
 
 		/* Some work done, but not enough to stay in polling,
diff --git a/drivers/net/ethernet/cisco/enic/vnic_rq.h b/drivers/net/ethernet/cisco/enic/vnic_rq.h
index 8111d52..b9c82f1 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_rq.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_rq.h
@@ -21,6 +21,7 @@
 #define _VNIC_RQ_H_
 
 #include <linux/pci.h>
+#include <linux/netdevice.h>
 
 #include "vnic_dev.h"
 #include "vnic_cq.h"
@@ -75,6 +76,12 @@
 	uint64_t wr_id;
 };
 
+enum enic_poll_state {
+	ENIC_POLL_STATE_IDLE,
+	ENIC_POLL_STATE_NAPI,
+	ENIC_POLL_STATE_POLL
+};
+
 struct vnic_rq {
 	unsigned int index;
 	struct vnic_dev *vdev;
@@ -86,19 +93,7 @@
 	void *os_buf_head;
 	unsigned int pkts_outstanding;
 #ifdef CONFIG_NET_RX_BUSY_POLL
-#define ENIC_POLL_STATE_IDLE		0
-#define ENIC_POLL_STATE_NAPI		(1 << 0) /* NAPI owns this poll */
-#define ENIC_POLL_STATE_POLL		(1 << 1) /* poll owns this poll */
-#define ENIC_POLL_STATE_NAPI_YIELD	(1 << 2) /* NAPI yielded this poll */
-#define ENIC_POLL_STATE_POLL_YIELD	(1 << 3) /* poll yielded this poll */
-#define ENIC_POLL_YIELD			(ENIC_POLL_STATE_NAPI_YIELD |	\
-					 ENIC_POLL_STATE_POLL_YIELD)
-#define ENIC_POLL_LOCKED		(ENIC_POLL_STATE_NAPI |		\
-					 ENIC_POLL_STATE_POLL)
-#define ENIC_POLL_USER_PEND		(ENIC_POLL_STATE_POLL |		\
-					 ENIC_POLL_STATE_POLL_YIELD)
-	unsigned int bpoll_state;
-	spinlock_t bpoll_lock;
+	atomic_t bpoll_state;
 #endif /* CONFIG_NET_RX_BUSY_POLL */
 };
 
@@ -215,76 +210,43 @@
 #ifdef CONFIG_NET_RX_BUSY_POLL
 static inline void enic_busy_poll_init_lock(struct vnic_rq *rq)
 {
-	spin_lock_init(&rq->bpoll_lock);
-	rq->bpoll_state = ENIC_POLL_STATE_IDLE;
+	atomic_set(&rq->bpoll_state, ENIC_POLL_STATE_IDLE);
 }
 
 static inline bool enic_poll_lock_napi(struct vnic_rq *rq)
 {
-	bool rc = true;
+	int rc = atomic_cmpxchg(&rq->bpoll_state, ENIC_POLL_STATE_IDLE,
+				ENIC_POLL_STATE_NAPI);
 
-	spin_lock(&rq->bpoll_lock);
-	if (rq->bpoll_state & ENIC_POLL_LOCKED) {
-		WARN_ON(rq->bpoll_state & ENIC_POLL_STATE_NAPI);
-		rq->bpoll_state |= ENIC_POLL_STATE_NAPI_YIELD;
-		rc = false;
-	} else {
-		rq->bpoll_state = ENIC_POLL_STATE_NAPI;
-	}
-	spin_unlock(&rq->bpoll_lock);
-
-	return rc;
+	return (rc == ENIC_POLL_STATE_IDLE);
 }
 
-static inline bool enic_poll_unlock_napi(struct vnic_rq *rq)
+static inline void enic_poll_unlock_napi(struct vnic_rq *rq,
+					 struct napi_struct *napi)
 {
-	bool rc = false;
-
-	spin_lock(&rq->bpoll_lock);
-	WARN_ON(rq->bpoll_state &
-		(ENIC_POLL_STATE_POLL | ENIC_POLL_STATE_NAPI_YIELD));
-	if (rq->bpoll_state & ENIC_POLL_STATE_POLL_YIELD)
-		rc = true;
-	rq->bpoll_state = ENIC_POLL_STATE_IDLE;
-	spin_unlock(&rq->bpoll_lock);
-
-	return rc;
+	WARN_ON(atomic_read(&rq->bpoll_state) != ENIC_POLL_STATE_NAPI);
+	napi_gro_flush(napi, false);
+	atomic_set(&rq->bpoll_state, ENIC_POLL_STATE_IDLE);
 }
 
 static inline bool enic_poll_lock_poll(struct vnic_rq *rq)
 {
-	bool rc = true;
+	int rc = atomic_cmpxchg(&rq->bpoll_state, ENIC_POLL_STATE_IDLE,
+				ENIC_POLL_STATE_POLL);
 
-	spin_lock_bh(&rq->bpoll_lock);
-	if (rq->bpoll_state & ENIC_POLL_LOCKED) {
-		rq->bpoll_state |= ENIC_POLL_STATE_POLL_YIELD;
-		rc = false;
-	} else {
-		rq->bpoll_state |= ENIC_POLL_STATE_POLL;
-	}
-	spin_unlock_bh(&rq->bpoll_lock);
-
-	return rc;
+	return (rc == ENIC_POLL_STATE_IDLE);
 }
 
-static inline bool enic_poll_unlock_poll(struct vnic_rq *rq)
+
+static inline void enic_poll_unlock_poll(struct vnic_rq *rq)
 {
-	bool rc = false;
-
-	spin_lock_bh(&rq->bpoll_lock);
-	WARN_ON(rq->bpoll_state & ENIC_POLL_STATE_NAPI);
-	if (rq->bpoll_state & ENIC_POLL_STATE_POLL_YIELD)
-		rc = true;
-	rq->bpoll_state = ENIC_POLL_STATE_IDLE;
-	spin_unlock_bh(&rq->bpoll_lock);
-
-	return rc;
+	WARN_ON(atomic_read(&rq->bpoll_state) != ENIC_POLL_STATE_POLL);
+	atomic_set(&rq->bpoll_state, ENIC_POLL_STATE_IDLE);
 }
 
 static inline bool enic_poll_busy_polling(struct vnic_rq *rq)
 {
-	WARN_ON(!(rq->bpoll_state & ENIC_POLL_LOCKED));
-	return rq->bpoll_state & ENIC_POLL_USER_PEND;
+	return atomic_read(&rq->bpoll_state) & ENIC_POLL_STATE_POLL;
 }
 
 #else
@@ -298,7 +260,8 @@
 	return true;
 }
 
-static inline bool enic_poll_unlock_napi(struct vnic_rq *rq)
+static inline bool enic_poll_unlock_napi(struct vnic_rq *rq,
+					 struct napi_struct *napi)
 {
 	return false;
 }
diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig
index b8de87b..ff76d4e 100644
--- a/drivers/net/ethernet/freescale/Kconfig
+++ b/drivers/net/ethernet/freescale/Kconfig
@@ -83,12 +83,12 @@
 
 config GIANFAR
 	tristate "Gianfar Ethernet"
-	depends on FSL_SOC
 	select FSL_PQ_MDIO
 	select PHYLIB
 	select CRC32
 	---help---
 	  This driver supports the Gigabit TSEC on the MPC83xx, MPC85xx,
-	  and MPC86xx family of chips, and the FEC on the 8540.
+	  and MPC86xx family of chips, the eTSEC on LS1021A and the FEC
+	  on the 8540.
 
 endif # NET_VENDOR_FREESCALE
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index a86af8a..1eee73c 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -428,6 +428,8 @@
 #define FEC_QUIRK_BUG_CAPTURE		(1 << 10)
 /* Controller has only one MDIO bus */
 #define FEC_QUIRK_SINGLE_MDIO		(1 << 11)
+/* Controller supports RACC register */
+#define FEC_QUIRK_HAS_RACC		(1 << 12)
 
 struct fec_enet_priv_tx_q {
 	int index;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index e464aea..1f89c59 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -85,28 +85,30 @@
 		.driver_data = 0,
 	}, {
 		.name = "imx25-fec",
-		.driver_data = FEC_QUIRK_USE_GASKET,
+		.driver_data = FEC_QUIRK_USE_GASKET | FEC_QUIRK_HAS_RACC,
 	}, {
 		.name = "imx27-fec",
-		.driver_data = 0,
+		.driver_data = FEC_QUIRK_HAS_RACC,
 	}, {
 		.name = "imx28-fec",
 		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME |
-				FEC_QUIRK_SINGLE_MDIO,
+				FEC_QUIRK_SINGLE_MDIO | FEC_QUIRK_HAS_RACC,
 	}, {
 		.name = "imx6q-fec",
 		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
 				FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
-				FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR006358,
+				FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR006358 |
+				FEC_QUIRK_HAS_RACC,
 	}, {
 		.name = "mvf600-fec",
-		.driver_data = FEC_QUIRK_ENET_MAC,
+		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_RACC,
 	}, {
 		.name = "imx6sx-fec",
 		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
 				FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
 				FEC_QUIRK_HAS_VLAN | FEC_QUIRK_HAS_AVB |
-				FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE,
+				FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE |
+				FEC_QUIRK_HAS_RACC,
 	}, {
 		/* sentinel */
 	}
@@ -970,13 +972,15 @@
 	writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
 
 #if !defined(CONFIG_M5272)
-	/* set RX checksum */
-	val = readl(fep->hwp + FEC_RACC);
-	if (fep->csum_flags & FLAG_RX_CSUM_ENABLED)
-		val |= FEC_RACC_OPTIONS;
-	else
-		val &= ~FEC_RACC_OPTIONS;
-	writel(val, fep->hwp + FEC_RACC);
+	if (fep->quirks & FEC_QUIRK_HAS_RACC) {
+		/* set RX checksum */
+		val = readl(fep->hwp + FEC_RACC);
+		if (fep->csum_flags & FLAG_RX_CSUM_ENABLED)
+			val |= FEC_RACC_OPTIONS;
+		else
+			val &= ~FEC_RACC_OPTIONS;
+		writel(val, fep->hwp + FEC_RACC);
+	}
 #endif
 
 	/*
diff --git a/drivers/net/ethernet/icplus/ipg.c b/drivers/net/ethernet/icplus/ipg.c
index ff29036..c3b6af8 100644
--- a/drivers/net/ethernet/icplus/ipg.c
+++ b/drivers/net/ethernet/icplus/ipg.c
@@ -1028,7 +1028,7 @@
 
 	/* detailed rx_errors */
 	sp->stats.rx_length_errors += ipg_r16(IPG_INRANGELENGTHERRORS) +
-		ipg_r16(IPG_FRAMETOOLONGERRRORS);
+		ipg_r16(IPG_FRAMETOOLONGERRORS);
 	sp->stats.rx_crc_errors += ipg_r16(IPG_FRAMECHECKSEQERRORS);
 
 	/* Unutilized IPG statistic registers. */
diff --git a/drivers/net/ethernet/icplus/ipg.h b/drivers/net/ethernet/icplus/ipg.h
index a21e4f5..de60628 100644
--- a/drivers/net/ethernet/icplus/ipg.h
+++ b/drivers/net/ethernet/icplus/ipg.h
@@ -102,7 +102,7 @@
 #define	IPG_MCSTFRAMESRCVDOK		0xB8
 #define	IPG_BCSTFRAMESRCVDOK		0xBE
 #define	IPG_MACCONTROLFRAMESRCVD	0xC6
-#define	IPG_FRAMETOOLONGERRRORS		0xC8
+#define	IPG_FRAMETOOLONGERRORS		0xC8
 #define	IPG_INRANGELENGTHERRORS		0xCA
 #define	IPG_FRAMECHECKSEQERRORS		0xCC
 #define	IPG_FRAMESLOSTRXERRORS		0xCE
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index b074b9a..91a5a0a 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -237,17 +237,19 @@
 	if (ret_val)
 		return false;
 out:
-	if ((hw->mac.type == e1000_pch_lpt) ||
-	    (hw->mac.type == e1000_pch_spt)) {
-		/* Unforce SMBus mode in PHY */
-		e1e_rphy_locked(hw, CV_SMB_CTRL, &phy_reg);
-		phy_reg &= ~CV_SMB_CTRL_FORCE_SMBUS;
-		e1e_wphy_locked(hw, CV_SMB_CTRL, phy_reg);
+	if ((hw->mac.type == e1000_pch_lpt) || (hw->mac.type == e1000_pch_spt)) {
+		/* Only unforce SMBus if ME is not active */
+		if (!(er32(FWSM) & E1000_ICH_FWSM_FW_VALID)) {
+			/* Unforce SMBus mode in PHY */
+			e1e_rphy_locked(hw, CV_SMB_CTRL, &phy_reg);
+			phy_reg &= ~CV_SMB_CTRL_FORCE_SMBUS;
+			e1e_wphy_locked(hw, CV_SMB_CTRL, phy_reg);
 
-		/* Unforce SMBus mode in MAC */
-		mac_reg = er32(CTRL_EXT);
-		mac_reg &= ~E1000_CTRL_EXT_FORCE_SMBUS;
-		ew32(CTRL_EXT, mac_reg);
+			/* Unforce SMBus mode in MAC */
+			mac_reg = er32(CTRL_EXT);
+			mac_reg &= ~E1000_CTRL_EXT_FORCE_SMBUS;
+			ew32(CTRL_EXT, mac_reg);
+		}
 	}
 
 	return true;
@@ -1087,6 +1089,7 @@
 	u32 mac_reg;
 	s32 ret_val = 0;
 	u16 phy_reg;
+	u16 oem_reg = 0;
 
 	if ((hw->mac.type < e1000_pch_lpt) ||
 	    (hw->adapter->pdev->device == E1000_DEV_ID_PCH_LPT_I217_LM) ||
@@ -1128,21 +1131,6 @@
 	if (ret_val)
 		goto out;
 
-	/* Si workaround for ULP entry flow on i127/rev6 h/w.  Enable
-	 * LPLU and disable Gig speed when entering ULP
-	 */
-	if ((hw->phy.type == e1000_phy_i217) && (hw->phy.revision == 6)) {
-		ret_val = e1000_read_phy_reg_hv_locked(hw, HV_OEM_BITS,
-						       &phy_reg);
-		if (ret_val)
-			goto release;
-		phy_reg |= HV_OEM_BITS_LPLU | HV_OEM_BITS_GBE_DIS;
-		ret_val = e1000_write_phy_reg_hv_locked(hw, HV_OEM_BITS,
-							phy_reg);
-		if (ret_val)
-			goto release;
-	}
-
 	/* Force SMBus mode in PHY */
 	ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &phy_reg);
 	if (ret_val)
@@ -1155,6 +1143,25 @@
 	mac_reg |= E1000_CTRL_EXT_FORCE_SMBUS;
 	ew32(CTRL_EXT, mac_reg);
 
+	/* Si workaround for ULP entry flow on i127/rev6 h/w.  Enable
+	 * LPLU and disable Gig speed when entering ULP
+	 */
+	if ((hw->phy.type == e1000_phy_i217) && (hw->phy.revision == 6)) {
+		ret_val = e1000_read_phy_reg_hv_locked(hw, HV_OEM_BITS,
+						       &oem_reg);
+		if (ret_val)
+			goto release;
+
+		phy_reg = oem_reg;
+		phy_reg |= HV_OEM_BITS_LPLU | HV_OEM_BITS_GBE_DIS;
+
+		ret_val = e1000_write_phy_reg_hv_locked(hw, HV_OEM_BITS,
+							phy_reg);
+
+		if (ret_val)
+			goto release;
+	}
+
 	/* Set Inband ULP Exit, Reset to SMBus mode and
 	 * Disable SMBus Release on PERST# in PHY
 	 */
@@ -1166,10 +1173,15 @@
 	if (to_sx) {
 		if (er32(WUFC) & E1000_WUFC_LNKC)
 			phy_reg |= I218_ULP_CONFIG1_WOL_HOST;
+		else
+			phy_reg &= ~I218_ULP_CONFIG1_WOL_HOST;
 
 		phy_reg |= I218_ULP_CONFIG1_STICKY_ULP;
+		phy_reg &= ~I218_ULP_CONFIG1_INBAND_EXIT;
 	} else {
 		phy_reg |= I218_ULP_CONFIG1_INBAND_EXIT;
+		phy_reg &= ~I218_ULP_CONFIG1_STICKY_ULP;
+		phy_reg &= ~I218_ULP_CONFIG1_WOL_HOST;
 	}
 	e1000_write_phy_reg_hv_locked(hw, I218_ULP_CONFIG1, phy_reg);
 
@@ -1181,6 +1193,15 @@
 	/* Commit ULP changes in PHY by starting auto ULP configuration */
 	phy_reg |= I218_ULP_CONFIG1_START;
 	e1000_write_phy_reg_hv_locked(hw, I218_ULP_CONFIG1, phy_reg);
+
+	if ((hw->phy.type == e1000_phy_i217) && (hw->phy.revision == 6) &&
+	    to_sx && (er32(STATUS) & E1000_STATUS_LU)) {
+		ret_val = e1000_write_phy_reg_hv_locked(hw, HV_OEM_BITS,
+							oem_reg);
+		if (ret_val)
+			goto release;
+	}
+
 release:
 	hw->phy.ops.release(hw);
 out:
@@ -1379,16 +1400,20 @@
 	if (((hw->mac.type == e1000_pch2lan) ||
 	     (hw->mac.type == e1000_pch_lpt) ||
 	     (hw->mac.type == e1000_pch_spt)) && link) {
-		u32 reg;
+		u16 speed, duplex;
 
-		reg = er32(STATUS);
+		e1000e_get_speed_and_duplex_copper(hw, &speed, &duplex);
 		tipg_reg = er32(TIPG);
 		tipg_reg &= ~E1000_TIPG_IPGT_MASK;
 
-		if (!(reg & (E1000_STATUS_FD | E1000_STATUS_SPEED_MASK))) {
+		if (duplex == HALF_DUPLEX && speed == SPEED_10) {
 			tipg_reg |= 0xFF;
 			/* Reduce Rx latency in analog PHY */
 			emi_val = 0;
+		} else if (hw->mac.type == e1000_pch_spt &&
+			   duplex == FULL_DUPLEX && speed != SPEED_1000) {
+			tipg_reg |= 0xC;
+			emi_val = 1;
 		} else {
 
 			/* Roll back the default values */
@@ -1412,14 +1437,59 @@
 
 		if (ret_val)
 			return ret_val;
+
+		if (hw->mac.type == e1000_pch_spt) {
+			u16 data;
+			u16 ptr_gap;
+
+			if (speed == SPEED_1000) {
+				ret_val = hw->phy.ops.acquire(hw);
+				if (ret_val)
+					return ret_val;
+
+				ret_val = e1e_rphy_locked(hw,
+							  PHY_REG(776, 20),
+							  &data);
+				if (ret_val) {
+					hw->phy.ops.release(hw);
+					return ret_val;
+				}
+
+				ptr_gap = (data & (0x3FF << 2)) >> 2;
+				if (ptr_gap < 0x18) {
+					data &= ~(0x3FF << 2);
+					data |= (0x18 << 2);
+					ret_val =
+					    e1e_wphy_locked(hw,
+							    PHY_REG(776, 20),
+							    data);
+				}
+				hw->phy.ops.release(hw);
+				if (ret_val)
+					return ret_val;
+			}
+		}
+	}
+
+	/* I217 Packet Loss issue:
+	 * ensure that FEXTNVM4 Beacon Duration is set correctly
+	 * on power up.
+	 * Set the Beacon Duration for I217 to 8 usec
+	 */
+	if ((hw->mac.type == e1000_pch_lpt) || (hw->mac.type == e1000_pch_spt)) {
+		u32 mac_reg;
+
+		mac_reg = er32(FEXTNVM4);
+		mac_reg &= ~E1000_FEXTNVM4_BEACON_DURATION_MASK;
+		mac_reg |= E1000_FEXTNVM4_BEACON_DURATION_8USEC;
+		ew32(FEXTNVM4, mac_reg);
 	}
 
 	/* Work-around I218 hang issue */
 	if ((hw->adapter->pdev->device == E1000_DEV_ID_PCH_LPTLP_I218_LM) ||
 	    (hw->adapter->pdev->device == E1000_DEV_ID_PCH_LPTLP_I218_V) ||
 	    (hw->adapter->pdev->device == E1000_DEV_ID_PCH_I218_LM3) ||
-	    (hw->adapter->pdev->device == E1000_DEV_ID_PCH_I218_V3) ||
-	    (hw->mac.type == e1000_pch_spt)) {
+	    (hw->adapter->pdev->device == E1000_DEV_ID_PCH_I218_V3)) {
 		ret_val = e1000_k1_workaround_lpt_lp(hw, link);
 		if (ret_val)
 			return ret_val;
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index e62b9dc..89d788d 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -6354,13 +6354,14 @@
 }
 
 /**
- * e1000e_disable_aspm - Disable ASPM states
+ * __e1000e_disable_aspm - Disable ASPM states
  * @pdev: pointer to PCI device struct
  * @state: bit-mask of ASPM states to disable
+ * @locked: indication if this context holds pci_bus_sem locked.
  *
  * Some devices *must* have certain ASPM states disabled per hardware errata.
  **/
-static void e1000e_disable_aspm(struct pci_dev *pdev, u16 state)
+static void __e1000e_disable_aspm(struct pci_dev *pdev, u16 state, int locked)
 {
 	struct pci_dev *parent = pdev->bus->self;
 	u16 aspm_dis_mask = 0;
@@ -6399,7 +6400,10 @@
 		 "L1" : "");
 
 #ifdef CONFIG_PCIEASPM
-	pci_disable_link_state_locked(pdev, state);
+	if (locked)
+		pci_disable_link_state_locked(pdev, state);
+	else
+		pci_disable_link_state(pdev, state);
 
 	/* Double-check ASPM control.  If not disabled by the above, the
 	 * BIOS is preventing that from happening (or CONFIG_PCIEASPM is
@@ -6422,6 +6426,32 @@
 					   aspm_dis_mask);
 }
 
+/**
+ * e1000e_disable_aspm - Disable ASPM states.
+ * @pdev: pointer to PCI device struct
+ * @state: bit-mask of ASPM states to disable
+ *
+ * This function acquires the pci_bus_sem!
+ * Some devices *must* have certain ASPM states disabled per hardware errata.
+ **/
+static void e1000e_disable_aspm(struct pci_dev *pdev, u16 state)
+{
+	__e1000e_disable_aspm(pdev, state, 0);
+}
+
+/**
+ * e1000e_disable_aspm_locked   Disable ASPM states.
+ * @pdev: pointer to PCI device struct
+ * @state: bit-mask of ASPM states to disable
+ *
+ * This function must be called with pci_bus_sem acquired!
+ * Some devices *must* have certain ASPM states disabled per hardware errata.
+ **/
+static void e1000e_disable_aspm_locked(struct pci_dev *pdev, u16 state)
+{
+	__e1000e_disable_aspm(pdev, state, 1);
+}
+
 #ifdef CONFIG_PM
 static int __e1000_resume(struct pci_dev *pdev)
 {
@@ -6435,7 +6465,7 @@
 	if (adapter->flags2 & FLAG2_DISABLE_ASPM_L1)
 		aspm_disable_flag |= PCIE_LINK_STATE_L1;
 	if (aspm_disable_flag)
-		e1000e_disable_aspm(pdev, aspm_disable_flag);
+		e1000e_disable_aspm_locked(pdev, aspm_disable_flag);
 
 	pci_set_master(pdev);
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index f54996f1..395f32f 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -484,6 +484,8 @@
 	if (!dev)
 		return -ENOMEM;
 
+	/* warn if we are about to overwrite the pointer */
+	WARN_ON(tx_ring->tx_bi);
 	bi_size = sizeof(struct i40e_tx_buffer) * tx_ring->count;
 	tx_ring->tx_bi = kzalloc(bi_size, GFP_KERNEL);
 	if (!tx_ring->tx_bi)
@@ -644,6 +646,8 @@
 	struct device *dev = rx_ring->dev;
 	int bi_size;
 
+	/* warn if we are about to overwrite the pointer */
+	WARN_ON(rx_ring->rx_bi);
 	bi_size = sizeof(struct i40e_rx_buffer) * rx_ring->count;
 	rx_ring->rx_bi = kzalloc(bi_size, GFP_KERNEL);
 	if (!rx_ring->rx_bi)
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h
index 1b98c25..fea3b75 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf.h
+++ b/drivers/net/ethernet/intel/i40evf/i40evf.h
@@ -264,7 +264,6 @@
 
 int i40evf_up(struct i40evf_adapter *adapter);
 void i40evf_down(struct i40evf_adapter *adapter);
-void i40evf_reinit_locked(struct i40evf_adapter *adapter);
 void i40evf_reset(struct i40evf_adapter *adapter);
 void i40evf_set_ethtool_ops(struct net_device *netdev);
 void i40evf_update_stats(struct i40evf_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
index f4e7766..2b53c87 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
@@ -267,8 +267,10 @@
 	adapter->tx_desc_count = new_tx_count;
 	adapter->rx_desc_count = new_rx_count;
 
-	if (netif_running(netdev))
-		i40evf_reinit_locked(adapter);
+	if (netif_running(netdev)) {
+		adapter->flags |= I40EVF_FLAG_RESET_NEEDED;
+		schedule_work(&adapter->reset_task);
+	}
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index 7c53aca..4ab4ebb 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -170,7 +170,8 @@
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
 
 	adapter->tx_timeout_count++;
-	if (!(adapter->flags & I40EVF_FLAG_RESET_PENDING)) {
+	if (!(adapter->flags & (I40EVF_FLAG_RESET_PENDING |
+				I40EVF_FLAG_RESET_NEEDED))) {
 		adapter->flags |= I40EVF_FLAG_RESET_NEEDED;
 		schedule_work(&adapter->reset_task);
 	}
@@ -1460,7 +1461,7 @@
 	for (i = 0; i <= I40E_VFQF_HLUT_MAX_INDEX; i++) {
 		lut = 0;
 		for (j = 0; j < 4; j++) {
-			if (cqueue == adapter->vsi_res->num_queue_pairs)
+			if (cqueue == adapter->num_active_queues)
 				cqueue = 0;
 			lut |= ((cqueue) << (8 * j));
 			cqueue++;
@@ -1470,8 +1471,8 @@
 	i40e_flush(hw);
 }
 
-#define I40EVF_RESET_WAIT_MS 100
-#define I40EVF_RESET_WAIT_COUNT 200
+#define I40EVF_RESET_WAIT_MS 10
+#define I40EVF_RESET_WAIT_COUNT 500
 /**
  * i40evf_reset_task - Call-back task to handle hardware reset
  * @work: pointer to work_struct
@@ -1495,10 +1496,17 @@
 				&adapter->crit_section))
 		usleep_range(500, 1000);
 
+	i40evf_misc_irq_disable(adapter);
 	if (adapter->flags & I40EVF_FLAG_RESET_NEEDED) {
-		dev_info(&adapter->pdev->dev, "Requesting reset from PF\n");
+		adapter->flags &= ~I40EVF_FLAG_RESET_NEEDED;
+		/* Restart the AQ here. If we have been reset but didn't
+		 * detect it, or if the PF had to reinit, our AQ will be hosed.
+		 */
+		i40evf_shutdown_adminq(hw);
+		i40evf_init_adminq(hw);
 		i40evf_request_reset(adapter);
 	}
+	adapter->flags |= I40EVF_FLAG_RESET_PENDING;
 
 	/* poll until we see the reset actually happen */
 	for (i = 0; i < I40EVF_RESET_WAIT_COUNT; i++) {
@@ -1507,10 +1515,10 @@
 		if ((rstat_val != I40E_VFR_VFACTIVE) &&
 		    (rstat_val != I40E_VFR_COMPLETED))
 			break;
-		msleep(I40EVF_RESET_WAIT_MS);
+		usleep_range(500, 1000);
 	}
 	if (i == I40EVF_RESET_WAIT_COUNT) {
-		adapter->flags &= ~I40EVF_FLAG_RESET_PENDING;
+		dev_info(&adapter->pdev->dev, "Never saw reset\n");
 		goto continue_reset; /* act like the reset happened */
 	}
 
@@ -1518,11 +1526,12 @@
 	for (i = 0; i < I40EVF_RESET_WAIT_COUNT; i++) {
 		rstat_val = rd32(hw, I40E_VFGEN_RSTAT) &
 			    I40E_VFGEN_RSTAT_VFR_STATE_MASK;
-		if ((rstat_val == I40E_VFR_VFACTIVE) ||
-		    (rstat_val == I40E_VFR_COMPLETED))
+		if (rstat_val == I40E_VFR_VFACTIVE)
 			break;
 		msleep(I40EVF_RESET_WAIT_MS);
 	}
+	/* extra wait to make sure minimum wait is met */
+	msleep(I40EVF_RESET_WAIT_MS);
 	if (i == I40EVF_RESET_WAIT_COUNT) {
 		struct i40evf_mac_filter *f, *ftmp;
 		struct i40evf_vlan_filter *fv, *fvtmp;
@@ -1534,11 +1543,10 @@
 
 		if (netif_running(adapter->netdev)) {
 			set_bit(__I40E_DOWN, &adapter->vsi.state);
-			i40evf_irq_disable(adapter);
-			i40evf_napi_disable_all(adapter);
-			netif_tx_disable(netdev);
-			netif_tx_stop_all_queues(netdev);
 			netif_carrier_off(netdev);
+			netif_tx_disable(netdev);
+			i40evf_napi_disable_all(adapter);
+			i40evf_irq_disable(adapter);
 			i40evf_free_traffic_irqs(adapter);
 			i40evf_free_all_tx_resources(adapter);
 			i40evf_free_all_rx_resources(adapter);
@@ -1550,6 +1558,7 @@
 			list_del(&f->list);
 			kfree(f);
 		}
+
 		list_for_each_entry_safe(fv, fvtmp, &adapter->vlan_filter_list,
 					 list) {
 			list_del(&fv->list);
@@ -1564,22 +1573,27 @@
 		i40evf_shutdown_adminq(hw);
 		adapter->netdev->flags &= ~IFF_UP;
 		clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
+		adapter->flags &= ~I40EVF_FLAG_RESET_PENDING;
+		dev_info(&adapter->pdev->dev, "Reset task did not complete, VF disabled\n");
 		return; /* Do not attempt to reinit. It's dead, Jim. */
 	}
 
 continue_reset:
-	adapter->flags &= ~I40EVF_FLAG_RESET_PENDING;
-
+	if (netif_running(adapter->netdev)) {
+		netif_carrier_off(netdev);
+		netif_tx_stop_all_queues(netdev);
+		i40evf_napi_disable_all(adapter);
+	}
 	i40evf_irq_disable(adapter);
 
-	if (netif_running(adapter->netdev)) {
-		i40evf_napi_disable_all(adapter);
-		netif_tx_disable(netdev);
-		netif_tx_stop_all_queues(netdev);
-		netif_carrier_off(netdev);
-	}
-
 	adapter->state = __I40EVF_RESETTING;
+	adapter->flags &= ~I40EVF_FLAG_RESET_PENDING;
+
+	/* free the Tx/Rx rings and descriptors, might be better to just
+	 * re-use them sometime in the future
+	 */
+	i40evf_free_all_rx_resources(adapter);
+	i40evf_free_all_tx_resources(adapter);
 
 	/* kill and reinit the admin queue */
 	if (i40evf_shutdown_adminq(hw))
@@ -1603,6 +1617,7 @@
 	adapter->aq_required = I40EVF_FLAG_AQ_ADD_MAC_FILTER;
 	adapter->aq_required |= I40EVF_FLAG_AQ_ADD_VLAN_FILTER;
 	clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
+	i40evf_misc_irq_enable(adapter);
 
 	mod_timer(&adapter->watchdog_timer, jiffies + 2);
 
@@ -1624,7 +1639,10 @@
 			goto reset_err;
 
 		i40evf_irq_enable(adapter, true);
+	} else {
+		adapter->state = __I40EVF_DOWN;
 	}
+
 	return;
 reset_err:
 	dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n");
@@ -1667,6 +1685,11 @@
 			memset(event.msg_buf, 0, I40EVF_MAX_AQ_BUF_SIZE);
 	} while (pending);
 
+	if ((adapter->flags &
+	     (I40EVF_FLAG_RESET_PENDING | I40EVF_FLAG_RESET_NEEDED)) ||
+	    adapter->state == __I40EVF_RESETTING)
+		goto freedom;
+
 	/* check for error indications */
 	val = rd32(hw, hw->aq.arq.len);
 	oldval = val;
@@ -1702,6 +1725,7 @@
 	if (oldval != val)
 		wr32(hw, hw->aq.asq.len, val);
 
+freedom:
 	kfree(event.msg_buf);
 out:
 	/* re-enable Admin queue interrupt cause */
@@ -1897,47 +1921,6 @@
 }
 
 /**
- * i40evf_reinit_locked - Software reinit
- * @adapter: board private structure
- *
- * Reinititalizes the ring structures in response to a software configuration
- * change. Roughly the same as close followed by open, but skips releasing
- * and reallocating the interrupts.
- **/
-void i40evf_reinit_locked(struct i40evf_adapter *adapter)
-{
-	struct net_device *netdev = adapter->netdev;
-	int err;
-
-	WARN_ON(in_interrupt());
-
-	i40evf_down(adapter);
-
-	/* allocate transmit descriptors */
-	err = i40evf_setup_all_tx_resources(adapter);
-	if (err)
-		goto err_reinit;
-
-	/* allocate receive descriptors */
-	err = i40evf_setup_all_rx_resources(adapter);
-	if (err)
-		goto err_reinit;
-
-	i40evf_configure(adapter);
-
-	err = i40evf_up_complete(adapter);
-	if (err)
-		goto err_reinit;
-
-	i40evf_irq_enable(adapter, true);
-	return;
-
-err_reinit:
-	dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n");
-	i40evf_close(netdev);
-}
-
-/**
  * i40evf_change_mtu - Change the Maximum Transfer Unit
  * @netdev: network interface device structure
  * @new_mtu: new value for maximum frame size
@@ -1952,9 +1935,10 @@
 	if ((new_mtu < 68) || (max_frame > I40E_MAX_RXBUFFER))
 		return -EINVAL;
 
-	/* must set new MTU before calling down or up */
 	netdev->mtu = new_mtu;
-	i40evf_reinit_locked(adapter);
+	adapter->flags |= I40EVF_FLAG_RESET_NEEDED;
+	schedule_work(&adapter->reset_task);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index 0f69ef8..b0182dd 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -1,5 +1,5 @@
 /* Intel(R) Gigabit Ethernet Linux driver
- * Copyright(c) 2007-2014 Intel Corporation.
+ * Copyright(c) 2007-2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -1900,8 +1900,8 @@
  *  igb_rx_fifo_flush_82575 - Clean rx fifo after RX enable
  *  @hw: pointer to the HW structure
  *
- *  After rx enable if managability is enabled then there is likely some
- *  bad data at the start of the fifo and possibly in the DMA fifo.  This
+ *  After rx enable if manageability is enabled then there is likely some
+ *  bad data at the start of the fifo and possibly in the DMA fifo. This
  *  function clears the fifos and flushes any packets that came in as rx was
  *  being enabled.
  **/
@@ -1910,6 +1910,11 @@
 	u32 rctl, rlpml, rxdctl[4], rfctl, temp_rctl, rx_enabled;
 	int i, ms_wait;
 
+	/* disable IPv6 options as per hardware errata */
+	rfctl = rd32(E1000_RFCTL);
+	rfctl |= E1000_RFCTL_IPV6_EX_DIS;
+	wr32(E1000_RFCTL, rfctl);
+
 	if (hw->mac.type != e1000_82575 ||
 	    !(rd32(E1000_MANC) & E1000_MANC_RCV_TCO_EN))
 		return;
@@ -1937,7 +1942,6 @@
 	 * incoming packets are rejected.  Set enable and wait 2ms so that
 	 * any packet that was coming in as RCTL.EN was set is flushed
 	 */
-	rfctl = rd32(E1000_RFCTL);
 	wr32(E1000_RFCTL, rfctl & ~E1000_RFCTL_LEF);
 
 	rlpml = rd32(E1000_RLPML);
diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h
index 217f813..f8684aa 100644
--- a/drivers/net/ethernet/intel/igb/e1000_defines.h
+++ b/drivers/net/ethernet/intel/igb/e1000_defines.h
@@ -344,7 +344,8 @@
 #define E1000_RXCSUM_PCSD      0x00002000   /* packet checksum disabled */
 
 /* Header split receive */
-#define E1000_RFCTL_LEF        0x00040000
+#define E1000_RFCTL_IPV6_EX_DIS         0x00010000
+#define E1000_RFCTL_LEF                 0x00040000
 
 /* Collision related configuration parameters */
 #define E1000_COLLISION_THRESHOLD       15
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index f287186..2f70a9b 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -58,7 +58,7 @@
 
 #define MAJ 5
 #define MIN 2
-#define BUILD 15
+#define BUILD 18
 #define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \
 __stringify(BUILD) "-k"
 char igb_driver_name[] = "igb";
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 5bdf782..370e20ed 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -310,6 +310,7 @@
 	unsigned int link;
 	unsigned int duplex;
 	unsigned int speed;
+	unsigned int tx_csum_limit;
 	int use_inband_status:1;
 };
 
@@ -2508,8 +2509,10 @@
 
 	dev->mtu = mtu;
 
-	if (!netif_running(dev))
+	if (!netif_running(dev)) {
+		netdev_update_features(dev);
 		return 0;
+	}
 
 	/* The interface is running, so we have to force a
 	 * reallocation of the queues
@@ -2538,9 +2541,26 @@
 	mvneta_start_dev(pp);
 	mvneta_port_up(pp);
 
+	netdev_update_features(dev);
+
 	return 0;
 }
 
+static netdev_features_t mvneta_fix_features(struct net_device *dev,
+					     netdev_features_t features)
+{
+	struct mvneta_port *pp = netdev_priv(dev);
+
+	if (pp->tx_csum_limit && dev->mtu > pp->tx_csum_limit) {
+		features &= ~(NETIF_F_IP_CSUM | NETIF_F_TSO);
+		netdev_info(dev,
+			    "Disable IP checksum for MTU greater than %dB\n",
+			    pp->tx_csum_limit);
+	}
+
+	return features;
+}
+
 /* Get mac address */
 static void mvneta_get_mac_addr(struct mvneta_port *pp, unsigned char *addr)
 {
@@ -2862,6 +2882,7 @@
 	.ndo_set_rx_mode     = mvneta_set_rx_mode,
 	.ndo_set_mac_address = mvneta_set_mac_addr,
 	.ndo_change_mtu      = mvneta_change_mtu,
+	.ndo_fix_features    = mvneta_fix_features,
 	.ndo_get_stats64     = mvneta_get_stats64,
 	.ndo_do_ioctl        = mvneta_ioctl,
 };
@@ -3107,6 +3128,9 @@
 		}
 	}
 
+	if (of_device_is_compatible(dn, "marvell,armada-370-neta"))
+		pp->tx_csum_limit = 1600;
+
 	pp->tx_ring_size = MVNETA_MAX_TXD;
 	pp->rx_ring_size = MVNETA_MAX_RXD;
 
@@ -3185,6 +3209,7 @@
 
 static const struct of_device_id mvneta_match[] = {
 	{ .compatible = "marvell,armada-370-neta" },
+	{ .compatible = "marvell,armada-xp-neta" },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, mvneta_match);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 77179d7..e0de2fd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1977,10 +1977,6 @@
 			mlx4_en_destroy_cq(priv, &priv->rx_cq[i]);
 	}
 
-	if (priv->base_tx_qpn) {
-		mlx4_qp_release_range(priv->mdev->dev, priv->base_tx_qpn, priv->tx_ring_num);
-		priv->base_tx_qpn = 0;
-	}
 }
 
 int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 35f726c..7a4f20b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -718,7 +718,7 @@
 }
 #endif
 static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va,
-		      int hwtstamp_rx_filter)
+		      netdev_features_t dev_features)
 {
 	__wsum hw_checksum = 0;
 
@@ -726,14 +726,8 @@
 
 	hw_checksum = csum_unfold((__force __sum16)cqe->checksum);
 
-	if (((struct ethhdr *)va)->h_proto == htons(ETH_P_8021Q) &&
-	    hwtstamp_rx_filter != HWTSTAMP_FILTER_NONE) {
-		/* next protocol non IPv4 or IPv6 */
-		if (((struct vlan_hdr *)hdr)->h_vlan_encapsulated_proto
-		    != htons(ETH_P_IP) &&
-		    ((struct vlan_hdr *)hdr)->h_vlan_encapsulated_proto
-		    != htons(ETH_P_IPV6))
-			return -1;
+	if (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_VLAN_PRESENT_MASK) &&
+	    !(dev_features & NETIF_F_HW_VLAN_CTAG_RX)) {
 		hw_checksum = get_fixed_vlan_csum(hw_checksum, hdr);
 		hdr += sizeof(struct vlan_hdr);
 	}
@@ -896,7 +890,8 @@
 
 			if (ip_summed == CHECKSUM_COMPLETE) {
 				void *va = skb_frag_address(skb_shinfo(gro_skb)->frags);
-				if (check_csum(cqe, gro_skb, va, ring->hwtstamp_rx_filter)) {
+				if (check_csum(cqe, gro_skb, va,
+					       dev->features)) {
 					ip_summed = CHECKSUM_NONE;
 					ring->csum_none++;
 					ring->csum_complete--;
@@ -951,7 +946,7 @@
 		}
 
 		if (ip_summed == CHECKSUM_COMPLETE) {
-			if (check_csum(cqe, skb, skb->data, ring->hwtstamp_rx_filter)) {
+			if (check_csum(cqe, skb, skb->data, dev->features)) {
 				ip_summed = CHECKSUM_NONE;
 				ring->csum_complete--;
 				ring->csum_none++;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 7bed3a8..c10d98f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -66,6 +66,7 @@
 	ring->size = size;
 	ring->size_mask = size - 1;
 	ring->stride = stride;
+	ring->full_size = ring->size - HEADROOM - MAX_DESC_TXBBS;
 
 	tmp = size * sizeof(struct mlx4_en_tx_info);
 	ring->tx_info = kmalloc_node(tmp, GFP_KERNEL | __GFP_NOWARN, node);
@@ -180,6 +181,7 @@
 		mlx4_bf_free(mdev->dev, &ring->bf);
 	mlx4_qp_remove(mdev->dev, &ring->qp);
 	mlx4_qp_free(mdev->dev, &ring->qp);
+	mlx4_qp_release_range(priv->mdev->dev, ring->qpn, 1);
 	mlx4_en_unmap_buffer(&ring->wqres.buf);
 	mlx4_free_hwq_res(mdev->dev, &ring->wqres, ring->buf_size);
 	kfree(ring->bounce_buf);
@@ -231,6 +233,11 @@
 		       MLX4_QP_STATE_RST, NULL, 0, 0, &ring->qp);
 }
 
+static inline bool mlx4_en_is_tx_ring_full(struct mlx4_en_tx_ring *ring)
+{
+	return ring->prod - ring->cons > ring->full_size;
+}
+
 static void mlx4_en_stamp_wqe(struct mlx4_en_priv *priv,
 			      struct mlx4_en_tx_ring *ring, int index,
 			      u8 owner)
@@ -473,11 +480,10 @@
 
 	netdev_tx_completed_queue(ring->tx_queue, packets, bytes);
 
-	/*
-	 * Wakeup Tx queue if this stopped, and at least 1 packet
-	 * was completed
+	/* Wakeup Tx queue if this stopped, and ring is not full.
 	 */
-	if (netif_tx_queue_stopped(ring->tx_queue) && txbbs_skipped > 0) {
+	if (netif_tx_queue_stopped(ring->tx_queue) &&
+	    !mlx4_en_is_tx_ring_full(ring)) {
 		netif_tx_wake_queue(ring->tx_queue);
 		ring->wake_queue++;
 	}
@@ -921,8 +927,7 @@
 	skb_tx_timestamp(skb);
 
 	/* Check available TXBBs And 2K spare for prefetch */
-	stop_queue = (int)(ring->prod - ring_cons) >
-		      ring->size - HEADROOM - MAX_DESC_TXBBS;
+	stop_queue = mlx4_en_is_tx_ring_full(ring);
 	if (unlikely(stop_queue)) {
 		netif_tx_stop_queue(ring->tx_queue);
 		ring->queue_stopped++;
@@ -991,8 +996,7 @@
 		smp_rmb();
 
 		ring_cons = ACCESS_ONCE(ring->cons);
-		if (unlikely(((int)(ring->prod - ring_cons)) <=
-			     ring->size - HEADROOM - MAX_DESC_TXBBS)) {
+		if (unlikely(!mlx4_en_is_tx_ring_full(ring))) {
 			netif_tx_wake_queue(ring->tx_queue);
 			ring->wake_queue++;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index 6fce587..0d80aed 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -93,8 +93,14 @@
 	mutex_lock(&intf_mutex);
 
 	list_add_tail(&intf->list, &intf_list);
-	list_for_each_entry(priv, &dev_list, dev_list)
+	list_for_each_entry(priv, &dev_list, dev_list) {
+		if (mlx4_is_mfunc(&priv->dev) && (intf->flags & MLX4_INTFF_BONDING)) {
+			mlx4_dbg(&priv->dev,
+				 "SRIOV, disabling HA mode for intf proto %d\n", intf->protocol);
+			intf->flags &= ~MLX4_INTFF_BONDING;
+		}
 		mlx4_add_device(intf, priv);
+	}
 
 	mutex_unlock(&intf_mutex);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index d5f9adb..666d166 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -279,6 +279,7 @@
 	u32			size; /* number of TXBBs */
 	u32			size_mask;
 	u16			stride;
+	u32			full_size;
 	u16			cqn;	/* index of port CQ associated with this ring */
 	u32			buf_size;
 	__be32			doorbell_qpn;
@@ -580,7 +581,6 @@
 	int vids[128];
 	bool wol;
 	struct device *ddev;
-	int base_tx_qpn;
 	struct hlist_head mac_hash[MLX4_EN_MAC_HASH_SIZE];
 	struct hwtstamp_config hwtstamp_config;
 	u32 counter_index;
diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index 2bae502..83651ac 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -279,7 +279,7 @@
 MODULE_FIRMWARE("myri10ge_rss_ethp_z8e.dat");
 MODULE_FIRMWARE("myri10ge_rss_eth_z8e.dat");
 
-/* Careful: must be accessed under kparam_block_sysfs_write */
+/* Careful: must be accessed under kernel_param_lock() */
 static char *myri10ge_fw_name = NULL;
 module_param(myri10ge_fw_name, charp, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(myri10ge_fw_name, "Firmware image name");
@@ -3427,7 +3427,7 @@
 		}
 	}
 
-	kparam_block_sysfs_write(myri10ge_fw_name);
+	kernel_param_lock(THIS_MODULE);
 	if (myri10ge_fw_name != NULL) {
 		char *fw_name = kstrdup(myri10ge_fw_name, GFP_KERNEL);
 		if (fw_name) {
@@ -3435,7 +3435,7 @@
 			set_fw_name(mgp, fw_name, true);
 		}
 	}
-	kparam_unblock_sysfs_write(myri10ge_fw_name);
+	kernel_param_unlock(THIS_MODULE);
 
 	if (mgp->board_number < MYRI10GE_MAX_BOARDS &&
 	    myri10ge_fw_names[mgp->board_number] != NULL &&
diff --git a/drivers/net/ethernet/renesas/ravb_ptp.c b/drivers/net/ethernet/renesas/ravb_ptp.c
index 42656da..7a8ce92 100644
--- a/drivers/net/ethernet/renesas/ravb_ptp.c
+++ b/drivers/net/ethernet/renesas/ravb_ptp.c
@@ -116,8 +116,10 @@
 	priv->ptp.current_addend = addend;
 
 	gccr = ravb_read(ndev, GCCR);
-	if (gccr & GCCR_LTI)
+	if (gccr & GCCR_LTI) {
+		spin_unlock_irqrestore(&priv->lock, flags);
 		return -EBUSY;
+	}
 	ravb_write(ndev, addend & GTI_TIV, GTI);
 	ravb_write(ndev, gccr | GCCR_LTI, GCCR);
 
diff --git a/drivers/net/ethernet/sis/sis900.h b/drivers/net/ethernet/sis/sis900.h
index 1341f33..7d430d3 100644
--- a/drivers/net/ethernet/sis/sis900.h
+++ b/drivers/net/ethernet/sis/sis900.h
@@ -56,7 +56,7 @@
 	EDB_MASTER_EN = 0x00002000
 };
 
-enum sis900_eeprom_access_reigster_bits {
+enum sis900_eeprom_access_register_bits {
 	MDC  = 0x00000040, MDDIR = 0x00000020, MDIO = 0x00000010, /* 7016 specific */
 	EECS = 0x00000008, EECLK = 0x00000004, EEDO = 0x00000002,
 	EEDI = 0x00000001
@@ -73,7 +73,7 @@
 	RxERR  = 0x00000004, RxDESC = 0x00000002, RxOK  = 0x00000001
 };
 
-enum sis900_interrupt_enable_reigster_bits {
+enum sis900_interrupt_enable_register_bits {
 	IE = 0x00000001
 };
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
index 08c483b..3f20bb1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
@@ -73,7 +73,7 @@
 #define MMC_RX_OCTETCOUNT_G		0x00000188
 #define MMC_RX_BROADCASTFRAME_G		0x0000018c
 #define MMC_RX_MULTICASTFRAME_G		0x00000190
-#define MMC_RX_CRC_ERRROR		0x00000194
+#define MMC_RX_CRC_ERROR		0x00000194
 #define MMC_RX_ALIGN_ERROR		0x00000198
 #define MMC_RX_RUN_ERROR		0x0000019C
 #define MMC_RX_JABBER_ERROR		0x000001A0
@@ -196,7 +196,7 @@
 	mmc->mmc_rx_octetcount_g += readl(ioaddr + MMC_RX_OCTETCOUNT_G);
 	mmc->mmc_rx_broadcastframe_g += readl(ioaddr + MMC_RX_BROADCASTFRAME_G);
 	mmc->mmc_rx_multicastframe_g += readl(ioaddr + MMC_RX_MULTICASTFRAME_G);
-	mmc->mmc_rx_crc_error += readl(ioaddr + MMC_RX_CRC_ERRROR);
+	mmc->mmc_rx_crc_error += readl(ioaddr + MMC_RX_CRC_ERROR);
 	mmc->mmc_rx_align_error += readl(ioaddr + MMC_RX_ALIGN_ERROR);
 	mmc->mmc_rx_run_error += readl(ioaddr + MMC_RX_RUN_ERROR);
 	mmc->mmc_rx_jabber_error += readl(ioaddr + MMC_RX_JABBER_ERROR);
diff --git a/drivers/net/ethernet/via/Kconfig b/drivers/net/ethernet/via/Kconfig
index 8b0b1d6..2f1264b 100644
--- a/drivers/net/ethernet/via/Kconfig
+++ b/drivers/net/ethernet/via/Kconfig
@@ -18,6 +18,7 @@
 config VIA_RHINE
 	tristate "VIA Rhine support"
 	depends on (PCI || OF_IRQ)
+	depends on HAS_DMA
 	select CRC32
 	select MII
 	---help---
@@ -42,6 +43,7 @@
 config VIA_VELOCITY
 	tristate "VIA Velocity support"
 	depends on (PCI || (OF_ADDRESS && OF_IRQ))
+	depends on HAS_DMA
 	select CRC32
 	select CRC_CCITT
 	select MII
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 6a64197f..f837080 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -48,15 +48,70 @@
 #define MACVTAP_FEATURES (IFF_VNET_HDR | IFF_MULTI_QUEUE)
 
 #define MACVTAP_VNET_LE 0x80000000
+#define MACVTAP_VNET_BE 0x40000000
+
+#ifdef CONFIG_TUN_VNET_CROSS_LE
+static inline bool macvtap_legacy_is_little_endian(struct macvtap_queue *q)
+{
+	return q->flags & MACVTAP_VNET_BE ? false :
+		virtio_legacy_is_little_endian();
+}
+
+static long macvtap_get_vnet_be(struct macvtap_queue *q, int __user *sp)
+{
+	int s = !!(q->flags & MACVTAP_VNET_BE);
+
+	if (put_user(s, sp))
+		return -EFAULT;
+
+	return 0;
+}
+
+static long macvtap_set_vnet_be(struct macvtap_queue *q, int __user *sp)
+{
+	int s;
+
+	if (get_user(s, sp))
+		return -EFAULT;
+
+	if (s)
+		q->flags |= MACVTAP_VNET_BE;
+	else
+		q->flags &= ~MACVTAP_VNET_BE;
+
+	return 0;
+}
+#else
+static inline bool macvtap_legacy_is_little_endian(struct macvtap_queue *q)
+{
+	return virtio_legacy_is_little_endian();
+}
+
+static long macvtap_get_vnet_be(struct macvtap_queue *q, int __user *argp)
+{
+	return -EINVAL;
+}
+
+static long macvtap_set_vnet_be(struct macvtap_queue *q, int __user *argp)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_TUN_VNET_CROSS_LE */
+
+static inline bool macvtap_is_little_endian(struct macvtap_queue *q)
+{
+	return q->flags & MACVTAP_VNET_LE ||
+		macvtap_legacy_is_little_endian(q);
+}
 
 static inline u16 macvtap16_to_cpu(struct macvtap_queue *q, __virtio16 val)
 {
-	return __virtio16_to_cpu(q->flags & MACVTAP_VNET_LE, val);
+	return __virtio16_to_cpu(macvtap_is_little_endian(q), val);
 }
 
 static inline __virtio16 cpu_to_macvtap16(struct macvtap_queue *q, u16 val)
 {
-	return __cpu_to_virtio16(q->flags & MACVTAP_VNET_LE, val);
+	return __cpu_to_virtio16(macvtap_is_little_endian(q), val);
 }
 
 static struct proto macvtap_proto = {
@@ -1085,6 +1140,12 @@
 			q->flags &= ~MACVTAP_VNET_LE;
 		return 0;
 
+	case TUNGETVNETBE:
+		return macvtap_get_vnet_be(q, sp);
+
+	case TUNSETVNETBE:
+		return macvtap_set_vnet_be(q, sp);
+
 	case TUNSETOFFLOAD:
 		/* let the user check for future flags */
 		if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 |
diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c
index 5a7e639..3cc316cb 100644
--- a/drivers/net/ntb_netdev.c
+++ b/drivers/net/ntb_netdev.c
@@ -5,6 +5,7 @@
  *   GPL LICENSE SUMMARY
  *
  *   Copyright(c) 2012 Intel Corporation. All rights reserved.
+ *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
  *
  *   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
@@ -13,6 +14,7 @@
  *   BSD LICENSE
  *
  *   Copyright(c) 2012 Intel Corporation. All rights reserved.
+ *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
  *
  *   Redistribution and use in source and binary forms, with or without
  *   modification, are permitted provided that the following conditions
@@ -40,7 +42,7 @@
  *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
  *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
- * Intel PCIe NTB Network Linux driver
+ * PCIe NTB Network Linux driver
  *
  * Contact Information:
  * Jon Mason <jon.mason@intel.com>
@@ -50,6 +52,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/ntb.h>
+#include <linux/ntb_transport.h>
 
 #define NTB_NETDEV_VER	"0.7"
 
@@ -70,26 +73,19 @@
 
 static LIST_HEAD(dev_list);
 
-static void ntb_netdev_event_handler(void *data, int status)
+static void ntb_netdev_event_handler(void *data, int link_is_up)
 {
 	struct net_device *ndev = data;
 	struct ntb_netdev *dev = netdev_priv(ndev);
 
-	netdev_dbg(ndev, "Event %x, Link %x\n", status,
+	netdev_dbg(ndev, "Event %x, Link %x\n", link_is_up,
 		   ntb_transport_link_query(dev->qp));
 
-	switch (status) {
-	case NTB_LINK_DOWN:
+	if (link_is_up) {
+		if (ntb_transport_link_query(dev->qp))
+			netif_carrier_on(ndev);
+	} else {
 		netif_carrier_off(ndev);
-		break;
-	case NTB_LINK_UP:
-		if (!ntb_transport_link_query(dev->qp))
-			return;
-
-		netif_carrier_on(ndev);
-		break;
-	default:
-		netdev_warn(ndev, "Unsupported event type %d\n", status);
 	}
 }
 
@@ -160,8 +156,6 @@
 	struct ntb_netdev *dev = netdev_priv(ndev);
 	int rc;
 
-	netdev_dbg(ndev, "%s: skb len %d\n", __func__, skb->len);
-
 	rc = ntb_transport_tx_enqueue(dev->qp, skb, skb->data, skb->len);
 	if (rc)
 		goto err;
@@ -322,20 +316,26 @@
 	.event_handler = ntb_netdev_event_handler,
 };
 
-static int ntb_netdev_probe(struct pci_dev *pdev)
+static int ntb_netdev_probe(struct device *client_dev)
 {
+	struct ntb_dev *ntb;
 	struct net_device *ndev;
+	struct pci_dev *pdev;
 	struct ntb_netdev *dev;
 	int rc;
 
-	ndev = alloc_etherdev(sizeof(struct ntb_netdev));
+	ntb = dev_ntb(client_dev->parent);
+	pdev = ntb->pdev;
+	if (!pdev)
+		return -ENODEV;
+
+	ndev = alloc_etherdev(sizeof(*dev));
 	if (!ndev)
 		return -ENOMEM;
 
 	dev = netdev_priv(ndev);
 	dev->ndev = ndev;
 	dev->pdev = pdev;
-	BUG_ON(!dev->pdev);
 	ndev->features = NETIF_F_HIGHDMA;
 
 	ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
@@ -349,7 +349,8 @@
 	ndev->netdev_ops = &ntb_netdev_ops;
 	ndev->ethtool_ops = &ntb_ethtool_ops;
 
-	dev->qp = ntb_transport_create_queue(ndev, pdev, &ntb_netdev_handlers);
+	dev->qp = ntb_transport_create_queue(ndev, client_dev,
+					     &ntb_netdev_handlers);
 	if (!dev->qp) {
 		rc = -EIO;
 		goto err;
@@ -372,12 +373,17 @@
 	return rc;
 }
 
-static void ntb_netdev_remove(struct pci_dev *pdev)
+static void ntb_netdev_remove(struct device *client_dev)
 {
+	struct ntb_dev *ntb;
 	struct net_device *ndev;
+	struct pci_dev *pdev;
 	struct ntb_netdev *dev;
 	bool found = false;
 
+	ntb = dev_ntb(client_dev->parent);
+	pdev = ntb->pdev;
+
 	list_for_each_entry(dev, &dev_list, list) {
 		if (dev->pdev == pdev) {
 			found = true;
@@ -396,7 +402,7 @@
 	free_netdev(ndev);
 }
 
-static struct ntb_client ntb_netdev_client = {
+static struct ntb_transport_client ntb_netdev_client = {
 	.driver.name = KBUILD_MODNAME,
 	.driver.owner = THIS_MODULE,
 	.probe = ntb_netdev_probe,
@@ -407,16 +413,16 @@
 {
 	int rc;
 
-	rc = ntb_register_client_dev(KBUILD_MODNAME);
+	rc = ntb_transport_register_client_dev(KBUILD_MODNAME);
 	if (rc)
 		return rc;
-	return ntb_register_client(&ntb_netdev_client);
+	return ntb_transport_register_client(&ntb_netdev_client);
 }
 module_init(ntb_netdev_init_module);
 
 static void __exit ntb_netdev_exit_module(void)
 {
-	ntb_unregister_client(&ntb_netdev_client);
-	ntb_unregister_client_dev(KBUILD_MODNAME);
+	ntb_transport_unregister_client(&ntb_netdev_client);
+	ntb_transport_unregister_client_dev(KBUILD_MODNAME);
 }
 module_exit(ntb_netdev_exit_module);
diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index 4dea85b..6b701b3 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -246,6 +246,13 @@
 	pr_info_once("%s: %s PHY revision: 0x%02x, patch: %d\n",
 		     dev_name(&phydev->dev), phydev->drv->name, rev, patch);
 
+	/* Dummy read to a register to workaround an issue upon reset where the
+	 * internal inverter may not allow the first MDIO transaction to pass
+	 * the MDIO management controller and make us return 0xffff for such
+	 * reads.
+	 */
+	phy_read(phydev, MII_BMSR);
+
 	switch (rev) {
 	case 0xb0:
 		ret = bcm7xxx_28nm_b0_afe_config_init(phydev);
diff --git a/drivers/net/phy/mdio-bcm-unimac.c b/drivers/net/phy/mdio-bcm-unimac.c
index fc7abc5..6a52a7f 100644
--- a/drivers/net/phy/mdio-bcm-unimac.c
+++ b/drivers/net/phy/mdio-bcm-unimac.c
@@ -120,6 +120,48 @@
 	return 0;
 }
 
+/* Workaround for integrated BCM7xxx Gigabit PHYs which have a problem with
+ * their internal MDIO management controller making them fail to successfully
+ * be read from or written to for the first transaction.  We insert a dummy
+ * BMSR read here to make sure that phy_get_device() and get_phy_id() can
+ * correctly read the PHY MII_PHYSID1/2 registers and successfully register a
+ * PHY device for this peripheral.
+ *
+ * Once the PHY driver is registered, we can workaround subsequent reads from
+ * there (e.g: during system-wide power management).
+ *
+ * bus->reset is invoked before mdiobus_scan during mdiobus_register and is
+ * therefore the right location to stick that workaround. Since we do not want
+ * to read from non-existing PHYs, we either use bus->phy_mask or do a manual
+ * Device Tree scan to limit the search area.
+ */
+static int unimac_mdio_reset(struct mii_bus *bus)
+{
+	struct device_node *np = bus->dev.of_node;
+	struct device_node *child;
+	u32 read_mask = 0;
+	int addr;
+
+	if (!np) {
+		read_mask = ~bus->phy_mask;
+	} else {
+		for_each_available_child_of_node(np, child) {
+			addr = of_mdio_parse_addr(&bus->dev, child);
+			if (addr < 0)
+				continue;
+
+			read_mask |= 1 << addr;
+		}
+	}
+
+	for (addr = 0; addr < PHY_MAX_ADDR; addr++) {
+		if (read_mask & 1 << addr)
+			mdiobus_read(bus, addr, MII_BMSR);
+	}
+
+	return 0;
+}
+
 static int unimac_mdio_probe(struct platform_device *pdev)
 {
 	struct unimac_mdio_priv *priv;
@@ -155,6 +197,7 @@
 	bus->parent = &pdev->dev;
 	bus->read = unimac_mdio_read;
 	bus->write = unimac_mdio_write;
+	bus->reset = unimac_mdio_reset;
 	snprintf(bus->id, MII_BUS_ID_SIZE, "%s", pdev->name);
 
 	bus->irq = kcalloc(PHY_MAX_ADDR, sizeof(int), GFP_KERNEL);
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index bdfe51f..0302483 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -230,7 +230,7 @@
 	for (i = 1;
 	     i < num_ids && c45_ids->devices_in_package == 0;
 	     i++) {
-		reg_addr = MII_ADDR_C45 | i << 16 | MDIO_DEVS2;
+retry:		reg_addr = MII_ADDR_C45 | i << 16 | MDIO_DEVS2;
 		phy_reg = mdiobus_read(bus, addr, reg_addr);
 		if (phy_reg < 0)
 			return -EIO;
@@ -242,12 +242,20 @@
 			return -EIO;
 		c45_ids->devices_in_package |= (phy_reg & 0xffff);
 
-		/* If mostly Fs, there is no device there,
-		 * let's get out of here.
-		 */
 		if ((c45_ids->devices_in_package & 0x1fffffff) == 0x1fffffff) {
-			*phy_id = 0xffffffff;
-			return 0;
+			if (i) {
+				/*  If mostly Fs, there is no device there,
+				 *  then let's continue to probe more, as some
+				 *  10G PHYs have zero Devices In package,
+				 *  e.g. Cortina CS4315/CS4340 PHY.
+				 */
+				i = 0;
+				goto retry;
+			} else {
+				/* no device there, let's get out of here */
+				*phy_id = 0xffffffff;
+				return 0;
+			}
 		}
 	}
 
@@ -796,10 +804,11 @@
 	if (phydev->supported & (SUPPORTED_1000baseT_Half |
 				 SUPPORTED_1000baseT_Full)) {
 		adv |= ethtool_adv_to_mii_ctrl1000_t(advertise);
-		if (adv != oldadv)
-			changed = 1;
 	}
 
+	if (adv != oldadv)
+		changed = 1;
+
 	err = phy_write(phydev, MII_CTRL1000, adv);
 	if (err < 0)
 		return err;
diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c
index 76cad71..17cad18 100644
--- a/drivers/net/phy/vitesse.c
+++ b/drivers/net/phy/vitesse.c
@@ -66,6 +66,7 @@
 #define PHY_ID_VSC8244			0x000fc6c0
 #define PHY_ID_VSC8514			0x00070670
 #define PHY_ID_VSC8574			0x000704a0
+#define PHY_ID_VSC8641			0x00070431
 #define PHY_ID_VSC8662			0x00070660
 #define PHY_ID_VSC8221			0x000fc550
 #define PHY_ID_VSC8211			0x000fc4b0
@@ -272,6 +273,18 @@
 	.config_intr    = &vsc82xx_config_intr,
 	.driver         = { .owner = THIS_MODULE,},
 }, {
+	.phy_id         = PHY_ID_VSC8641,
+	.name           = "Vitesse VSC8641",
+	.phy_id_mask    = 0x000ffff0,
+	.features       = PHY_GBIT_FEATURES,
+	.flags          = PHY_HAS_INTERRUPT,
+	.config_init    = &vsc824x_config_init,
+	.config_aneg    = &vsc82x4_config_aneg,
+	.read_status    = &genphy_read_status,
+	.ack_interrupt  = &vsc824x_ack_interrupt,
+	.config_intr    = &vsc82xx_config_intr,
+	.driver         = { .owner = THIS_MODULE,},
+}, {
 	.phy_id         = PHY_ID_VSC8662,
 	.name           = "Vitesse VSC8662",
 	.phy_id_mask    = 0x000ffff0,
@@ -318,6 +331,7 @@
 	{ PHY_ID_VSC8244, 0x000fffc0 },
 	{ PHY_ID_VSC8514, 0x000ffff0 },
 	{ PHY_ID_VSC8574, 0x000ffff0 },
+	{ PHY_ID_VSC8641, 0x000ffff0 },
 	{ PHY_ID_VSC8662, 0x000ffff0 },
 	{ PHY_ID_VSC8221, 0x000ffff0 },
 	{ PHY_ID_VSC8211, 0x000ffff0 },
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 1a1c4f7..06a0394 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -111,6 +111,7 @@
 #define TUN_FASYNC	IFF_ATTACH_QUEUE
 /* High bits in flags field are unused. */
 #define TUN_VNET_LE     0x80000000
+#define TUN_VNET_BE     0x40000000
 
 #define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \
 		      IFF_MULTI_QUEUE)
@@ -205,14 +206,68 @@
 	u32 flow_count;
 };
 
+#ifdef CONFIG_TUN_VNET_CROSS_LE
+static inline bool tun_legacy_is_little_endian(struct tun_struct *tun)
+{
+	return tun->flags & TUN_VNET_BE ? false :
+		virtio_legacy_is_little_endian();
+}
+
+static long tun_get_vnet_be(struct tun_struct *tun, int __user *argp)
+{
+	int be = !!(tun->flags & TUN_VNET_BE);
+
+	if (put_user(be, argp))
+		return -EFAULT;
+
+	return 0;
+}
+
+static long tun_set_vnet_be(struct tun_struct *tun, int __user *argp)
+{
+	int be;
+
+	if (get_user(be, argp))
+		return -EFAULT;
+
+	if (be)
+		tun->flags |= TUN_VNET_BE;
+	else
+		tun->flags &= ~TUN_VNET_BE;
+
+	return 0;
+}
+#else
+static inline bool tun_legacy_is_little_endian(struct tun_struct *tun)
+{
+	return virtio_legacy_is_little_endian();
+}
+
+static long tun_get_vnet_be(struct tun_struct *tun, int __user *argp)
+{
+	return -EINVAL;
+}
+
+static long tun_set_vnet_be(struct tun_struct *tun, int __user *argp)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_TUN_VNET_CROSS_LE */
+
+static inline bool tun_is_little_endian(struct tun_struct *tun)
+{
+	return tun->flags & TUN_VNET_LE ||
+		tun_legacy_is_little_endian(tun);
+}
+
 static inline u16 tun16_to_cpu(struct tun_struct *tun, __virtio16 val)
 {
-	return __virtio16_to_cpu(tun->flags & TUN_VNET_LE, val);
+	return __virtio16_to_cpu(tun_is_little_endian(tun), val);
 }
 
 static inline __virtio16 cpu_to_tun16(struct tun_struct *tun, u16 val)
 {
-	return __cpu_to_virtio16(tun->flags & TUN_VNET_LE, val);
+	return __cpu_to_virtio16(tun_is_little_endian(tun), val);
 }
 
 static inline u32 tun_hashfn(u32 rxhash)
@@ -2044,6 +2099,14 @@
 			tun->flags &= ~TUN_VNET_LE;
 		break;
 
+	case TUNGETVNETBE:
+		ret = tun_get_vnet_be(tun, argp);
+		break;
+
+	case TUNSETVNETBE:
+		ret = tun_set_vnet_be(tun, argp);
+		break;
+
 	case TUNATTACHFILTER:
 		/* Can be set only for TAPs */
 		ret = -EINVAL;
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index e9f1075..2652245 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -69,10 +69,10 @@
 /*
  * Version numbers
  */
-#define VMXNET3_DRIVER_VERSION_STRING   "1.3.5.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING   "1.4.2.0-k"
 
 /* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */
-#define VMXNET3_DRIVER_VERSION_NUM      0x01030500
+#define VMXNET3_DRIVER_VERSION_NUM      0x01040200
 
 #if defined(CONFIG_PCI_MSI)
 	/* RSS only makes sense if MSI-X is supported. */
diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index b9febab..6ca6193 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -62,7 +62,7 @@
 	return ret;
 }
 
-static struct kernel_param_ops mtu_max_ops = {
+static const struct kernel_param_ops mtu_max_ops = {
 	.set = mtu_max_set,
 	.get = param_get_uint,
 };
@@ -91,7 +91,7 @@
 	return 0;
 }
 
-static struct kernel_param_ops ring_order_ops = {
+static const struct kernel_param_ops ring_order_ops = {
 	.set = ring_order_set,
 	.get = param_get_uint,
 };
diff --git a/drivers/net/wireless/libertas_tf/if_usb.c b/drivers/net/wireless/libertas_tf/if_usb.c
index 1a20cee..799a2ef 100644
--- a/drivers/net/wireless/libertas_tf/if_usb.c
+++ b/drivers/net/wireless/libertas_tf/if_usb.c
@@ -821,15 +821,15 @@
 
 	lbtf_deb_enter(LBTF_DEB_USB);
 
-	kparam_block_sysfs_write(fw_name);
+	kernel_param_lock(THIS_MODULE);
 	ret = request_firmware(&cardp->fw, lbtf_fw_name, &cardp->udev->dev);
 	if (ret < 0) {
 		pr_err("request_firmware() failed with %#x\n", ret);
 		pr_err("firmware %s not found\n", lbtf_fw_name);
-		kparam_unblock_sysfs_write(fw_name);
+		kernel_param_unlock(THIS_MODULE);
 		goto done;
 	}
-	kparam_unblock_sysfs_write(fw_name);
+	kernel_param_unlock(THIS_MODULE);
 
 	if (check_fwfile_format(cardp->fw->data, cardp->fw->size))
 		goto release_fw;
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 5485f91..880d0d6 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -44,9 +44,9 @@
 #include <xen/xen.h>
 #include <xen/events.h>
 #include <xen/interface/memory.h>
+#include <xen/page.h>
 
 #include <asm/xen/hypercall.h>
-#include <asm/xen/page.h>
 
 /* Provide an option to disable split event channels at load time as
  * event channels are limited resource. Split event channels are
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 56d8afd..f948c46 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -45,7 +45,6 @@
 #include <linux/slab.h>
 #include <net/ip.h>
 
-#include <asm/xen/page.h>
 #include <xen/xen.h>
 #include <xen/xenbus.h>
 #include <xen/events.h>
@@ -1245,10 +1244,6 @@
 	np                   = netdev_priv(netdev);
 	np->xbdev            = dev;
 
-	/* No need to use rtnl_lock() before the call below as it
-	 * happens before register_netdev().
-	 */
-	netif_set_real_num_tx_queues(netdev, 0);
 	np->queues = NULL;
 
 	err = -ENOMEM;
@@ -1900,9 +1895,6 @@
 	xennet_disconnect_backend(info);
 	kfree(info->queues);
 	info->queues = NULL;
-	rtnl_lock();
-	netif_set_real_num_tx_queues(info->netdev, 0);
-	rtnl_unlock();
  out:
 	return err;
 }
diff --git a/drivers/ntb/Kconfig b/drivers/ntb/Kconfig
index f69df793..95944e5 100644
--- a/drivers/ntb/Kconfig
+++ b/drivers/ntb/Kconfig
@@ -1,13 +1,28 @@
-config NTB
-       tristate "Intel Non-Transparent Bridge support"
-       depends on PCI
-       depends on X86
-       help
-        The PCI-E Non-transparent bridge hardware is a point-to-point PCI-E bus
-        connecting 2 systems.  When configured, writes to the device's PCI
-        mapped memory will be mirrored to a buffer on the remote system.  The
-        ntb Linux driver uses this point-to-point communication as a method to
-        transfer data from one system to the other.
+menuconfig NTB
+	tristate "Non-Transparent Bridge support"
+	depends on PCI
+	help
+	 The PCI-E Non-transparent bridge hardware is a point-to-point PCI-E bus
+	 connecting 2 systems.  When configured, writes to the device's PCI
+	 mapped memory will be mirrored to a buffer on the remote system.  The
+	 ntb Linux driver uses this point-to-point communication as a method to
+	 transfer data from one system to the other.
 
-        If unsure, say N.
+	 If unsure, say N.
 
+if NTB
+
+source "drivers/ntb/hw/Kconfig"
+
+source "drivers/ntb/test/Kconfig"
+
+config NTB_TRANSPORT
+	tristate "NTB Transport Client"
+	help
+	 This is a transport driver that enables connected systems to exchange
+	 messages over the ntb hardware.  The transport exposes a queue pair api
+	 to client drivers.
+
+	 If unsure, say N.
+
+endif # NTB
diff --git a/drivers/ntb/Makefile b/drivers/ntb/Makefile
index 15cb59f..1921dec 100644
--- a/drivers/ntb/Makefile
+++ b/drivers/ntb/Makefile
@@ -1,3 +1,2 @@
-obj-$(CONFIG_NTB) += ntb.o
-
-ntb-objs := ntb_hw.o ntb_transport.o
+obj-$(CONFIG_NTB) += ntb.o hw/ test/
+obj-$(CONFIG_NTB_TRANSPORT) += ntb_transport.o
diff --git a/drivers/ntb/hw/Kconfig b/drivers/ntb/hw/Kconfig
new file mode 100644
index 0000000..4d5535c
--- /dev/null
+++ b/drivers/ntb/hw/Kconfig
@@ -0,0 +1 @@
+source "drivers/ntb/hw/intel/Kconfig"
diff --git a/drivers/ntb/hw/Makefile b/drivers/ntb/hw/Makefile
new file mode 100644
index 0000000..175d7c9
--- /dev/null
+++ b/drivers/ntb/hw/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_NTB_INTEL)	+= intel/
diff --git a/drivers/ntb/hw/intel/Kconfig b/drivers/ntb/hw/intel/Kconfig
new file mode 100644
index 0000000..91f995e
--- /dev/null
+++ b/drivers/ntb/hw/intel/Kconfig
@@ -0,0 +1,7 @@
+config NTB_INTEL
+	tristate "Intel Non-Transparent Bridge support"
+	depends on X86_64
+	help
+	 This driver supports Intel NTB on capable Xeon and Atom hardware.
+
+	 If unsure, say N.
diff --git a/drivers/ntb/hw/intel/Makefile b/drivers/ntb/hw/intel/Makefile
new file mode 100644
index 0000000..1b43456
--- /dev/null
+++ b/drivers/ntb/hw/intel/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_NTB_INTEL) += ntb_hw_intel.o
diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.c b/drivers/ntb/hw/intel/ntb_hw_intel.c
new file mode 100644
index 0000000..87751cf
--- /dev/null
+++ b/drivers/ntb/hw/intel/ntb_hw_intel.c
@@ -0,0 +1,2274 @@
+/*
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ *   redistributing this file, you may do so under either license.
+ *
+ *   GPL LICENSE SUMMARY
+ *
+ *   Copyright(c) 2012 Intel Corporation. All rights reserved.
+ *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of version 2 of the GNU General Public License as
+ *   published by the Free Software Foundation.
+ *
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2012 Intel Corporation. All rights reserved.
+ *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copy
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of Intel Corporation nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * Intel PCIe NTB Linux driver
+ *
+ * Contact Information:
+ * Jon Mason <jon.mason@intel.com>
+ */
+
+#include <linux/debugfs.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/random.h>
+#include <linux/slab.h>
+#include <linux/ntb.h>
+
+#include "ntb_hw_intel.h"
+
+#define NTB_NAME	"ntb_hw_intel"
+#define NTB_DESC	"Intel(R) PCI-E Non-Transparent Bridge Driver"
+#define NTB_VER		"2.0"
+
+MODULE_DESCRIPTION(NTB_DESC);
+MODULE_VERSION(NTB_VER);
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Intel Corporation");
+
+#define bar0_off(base, bar) ((base) + ((bar) << 2))
+#define bar2_off(base, bar) bar0_off(base, (bar) - 2)
+
+static const struct intel_ntb_reg atom_reg;
+static const struct intel_ntb_alt_reg atom_pri_reg;
+static const struct intel_ntb_alt_reg atom_sec_reg;
+static const struct intel_ntb_alt_reg atom_b2b_reg;
+static const struct intel_ntb_xlat_reg atom_pri_xlat;
+static const struct intel_ntb_xlat_reg atom_sec_xlat;
+static const struct intel_ntb_reg xeon_reg;
+static const struct intel_ntb_alt_reg xeon_pri_reg;
+static const struct intel_ntb_alt_reg xeon_sec_reg;
+static const struct intel_ntb_alt_reg xeon_b2b_reg;
+static const struct intel_ntb_xlat_reg xeon_pri_xlat;
+static const struct intel_ntb_xlat_reg xeon_sec_xlat;
+static struct intel_b2b_addr xeon_b2b_usd_addr;
+static struct intel_b2b_addr xeon_b2b_dsd_addr;
+static const struct ntb_dev_ops intel_ntb_ops;
+
+static const struct file_operations intel_ntb_debugfs_info;
+static struct dentry *debugfs_dir;
+
+static int b2b_mw_idx = -1;
+module_param(b2b_mw_idx, int, 0644);
+MODULE_PARM_DESC(b2b_mw_idx, "Use this mw idx to access the peer ntb.  A "
+		 "value of zero or positive starts from first mw idx, and a "
+		 "negative value starts from last mw idx.  Both sides MUST "
+		 "set the same value here!");
+
+static unsigned int b2b_mw_share;
+module_param(b2b_mw_share, uint, 0644);
+MODULE_PARM_DESC(b2b_mw_share, "If the b2b mw is large enough, configure the "
+		 "ntb so that the peer ntb only occupies the first half of "
+		 "the mw, so the second half can still be used as a mw.  Both "
+		 "sides MUST set the same value here!");
+
+module_param_named(xeon_b2b_usd_bar2_addr64,
+		   xeon_b2b_usd_addr.bar2_addr64, ullong, 0644);
+MODULE_PARM_DESC(xeon_b2b_usd_bar2_addr64,
+		 "XEON B2B USD BAR 2 64-bit address");
+
+module_param_named(xeon_b2b_usd_bar4_addr64,
+		   xeon_b2b_usd_addr.bar4_addr64, ullong, 0644);
+MODULE_PARM_DESC(xeon_b2b_usd_bar2_addr64,
+		 "XEON B2B USD BAR 4 64-bit address");
+
+module_param_named(xeon_b2b_usd_bar4_addr32,
+		   xeon_b2b_usd_addr.bar4_addr32, ullong, 0644);
+MODULE_PARM_DESC(xeon_b2b_usd_bar2_addr64,
+		 "XEON B2B USD split-BAR 4 32-bit address");
+
+module_param_named(xeon_b2b_usd_bar5_addr32,
+		   xeon_b2b_usd_addr.bar5_addr32, ullong, 0644);
+MODULE_PARM_DESC(xeon_b2b_usd_bar2_addr64,
+		 "XEON B2B USD split-BAR 5 32-bit address");
+
+module_param_named(xeon_b2b_dsd_bar2_addr64,
+		   xeon_b2b_dsd_addr.bar2_addr64, ullong, 0644);
+MODULE_PARM_DESC(xeon_b2b_dsd_bar2_addr64,
+		 "XEON B2B DSD BAR 2 64-bit address");
+
+module_param_named(xeon_b2b_dsd_bar4_addr64,
+		   xeon_b2b_dsd_addr.bar4_addr64, ullong, 0644);
+MODULE_PARM_DESC(xeon_b2b_dsd_bar2_addr64,
+		 "XEON B2B DSD BAR 4 64-bit address");
+
+module_param_named(xeon_b2b_dsd_bar4_addr32,
+		   xeon_b2b_dsd_addr.bar4_addr32, ullong, 0644);
+MODULE_PARM_DESC(xeon_b2b_dsd_bar2_addr64,
+		 "XEON B2B DSD split-BAR 4 32-bit address");
+
+module_param_named(xeon_b2b_dsd_bar5_addr32,
+		   xeon_b2b_dsd_addr.bar5_addr32, ullong, 0644);
+MODULE_PARM_DESC(xeon_b2b_dsd_bar2_addr64,
+		 "XEON B2B DSD split-BAR 5 32-bit address");
+
+#ifndef ioread64
+#ifdef readq
+#define ioread64 readq
+#else
+#define ioread64 _ioread64
+static inline u64 _ioread64(void __iomem *mmio)
+{
+	u64 low, high;
+
+	low = ioread32(mmio);
+	high = ioread32(mmio + sizeof(u32));
+	return low | (high << 32);
+}
+#endif
+#endif
+
+#ifndef iowrite64
+#ifdef writeq
+#define iowrite64 writeq
+#else
+#define iowrite64 _iowrite64
+static inline void _iowrite64(u64 val, void __iomem *mmio)
+{
+	iowrite32(val, mmio);
+	iowrite32(val >> 32, mmio + sizeof(u32));
+}
+#endif
+#endif
+
+static inline int pdev_is_atom(struct pci_dev *pdev)
+{
+	switch (pdev->device) {
+	case PCI_DEVICE_ID_INTEL_NTB_B2B_BWD:
+		return 1;
+	}
+	return 0;
+}
+
+static inline int pdev_is_xeon(struct pci_dev *pdev)
+{
+	switch (pdev->device) {
+	case PCI_DEVICE_ID_INTEL_NTB_SS_JSF:
+	case PCI_DEVICE_ID_INTEL_NTB_SS_SNB:
+	case PCI_DEVICE_ID_INTEL_NTB_SS_IVT:
+	case PCI_DEVICE_ID_INTEL_NTB_SS_HSX:
+	case PCI_DEVICE_ID_INTEL_NTB_PS_JSF:
+	case PCI_DEVICE_ID_INTEL_NTB_PS_SNB:
+	case PCI_DEVICE_ID_INTEL_NTB_PS_IVT:
+	case PCI_DEVICE_ID_INTEL_NTB_PS_HSX:
+	case PCI_DEVICE_ID_INTEL_NTB_B2B_JSF:
+	case PCI_DEVICE_ID_INTEL_NTB_B2B_SNB:
+	case PCI_DEVICE_ID_INTEL_NTB_B2B_IVT:
+	case PCI_DEVICE_ID_INTEL_NTB_B2B_HSX:
+		return 1;
+	}
+	return 0;
+}
+
+static inline void ndev_reset_unsafe_flags(struct intel_ntb_dev *ndev)
+{
+	ndev->unsafe_flags = 0;
+	ndev->unsafe_flags_ignore = 0;
+
+	/* Only B2B has a workaround to avoid SDOORBELL */
+	if (ndev->hwerr_flags & NTB_HWERR_SDOORBELL_LOCKUP)
+		if (!ntb_topo_is_b2b(ndev->ntb.topo))
+			ndev->unsafe_flags |= NTB_UNSAFE_DB;
+
+	/* No low level workaround to avoid SB01BASE */
+	if (ndev->hwerr_flags & NTB_HWERR_SB01BASE_LOCKUP) {
+		ndev->unsafe_flags |= NTB_UNSAFE_DB;
+		ndev->unsafe_flags |= NTB_UNSAFE_SPAD;
+	}
+}
+
+static inline int ndev_is_unsafe(struct intel_ntb_dev *ndev,
+				 unsigned long flag)
+{
+	return !!(flag & ndev->unsafe_flags & ~ndev->unsafe_flags_ignore);
+}
+
+static inline int ndev_ignore_unsafe(struct intel_ntb_dev *ndev,
+				     unsigned long flag)
+{
+	flag &= ndev->unsafe_flags;
+	ndev->unsafe_flags_ignore |= flag;
+
+	return !!flag;
+}
+
+static int ndev_mw_to_bar(struct intel_ntb_dev *ndev, int idx)
+{
+	if (idx < 0 || idx > ndev->mw_count)
+		return -EINVAL;
+	return ndev->reg->mw_bar[idx];
+}
+
+static inline int ndev_db_addr(struct intel_ntb_dev *ndev,
+			       phys_addr_t *db_addr, resource_size_t *db_size,
+			       phys_addr_t reg_addr, unsigned long reg)
+{
+	if (ndev_is_unsafe(ndev, NTB_UNSAFE_DB))
+		pr_warn_once("%s: NTB unsafe doorbell access", __func__);
+
+	if (db_addr) {
+		*db_addr = reg_addr + reg;
+		dev_dbg(ndev_dev(ndev), "Peer db addr %llx\n", *db_addr);
+	}
+
+	if (db_size) {
+		*db_size = ndev->reg->db_size;
+		dev_dbg(ndev_dev(ndev), "Peer db size %llx\n", *db_size);
+	}
+
+	return 0;
+}
+
+static inline u64 ndev_db_read(struct intel_ntb_dev *ndev,
+			       void __iomem *mmio)
+{
+	if (ndev_is_unsafe(ndev, NTB_UNSAFE_DB))
+		pr_warn_once("%s: NTB unsafe doorbell access", __func__);
+
+	return ndev->reg->db_ioread(mmio);
+}
+
+static inline int ndev_db_write(struct intel_ntb_dev *ndev, u64 db_bits,
+				void __iomem *mmio)
+{
+	if (ndev_is_unsafe(ndev, NTB_UNSAFE_DB))
+		pr_warn_once("%s: NTB unsafe doorbell access", __func__);
+
+	if (db_bits & ~ndev->db_valid_mask)
+		return -EINVAL;
+
+	ndev->reg->db_iowrite(db_bits, mmio);
+
+	return 0;
+}
+
+static inline int ndev_db_set_mask(struct intel_ntb_dev *ndev, u64 db_bits,
+				   void __iomem *mmio)
+{
+	unsigned long irqflags;
+
+	if (ndev_is_unsafe(ndev, NTB_UNSAFE_DB))
+		pr_warn_once("%s: NTB unsafe doorbell access", __func__);
+
+	if (db_bits & ~ndev->db_valid_mask)
+		return -EINVAL;
+
+	spin_lock_irqsave(&ndev->db_mask_lock, irqflags);
+	{
+		ndev->db_mask |= db_bits;
+		ndev->reg->db_iowrite(ndev->db_mask, mmio);
+	}
+	spin_unlock_irqrestore(&ndev->db_mask_lock, irqflags);
+
+	return 0;
+}
+
+static inline int ndev_db_clear_mask(struct intel_ntb_dev *ndev, u64 db_bits,
+				     void __iomem *mmio)
+{
+	unsigned long irqflags;
+
+	if (ndev_is_unsafe(ndev, NTB_UNSAFE_DB))
+		pr_warn_once("%s: NTB unsafe doorbell access", __func__);
+
+	if (db_bits & ~ndev->db_valid_mask)
+		return -EINVAL;
+
+	spin_lock_irqsave(&ndev->db_mask_lock, irqflags);
+	{
+		ndev->db_mask &= ~db_bits;
+		ndev->reg->db_iowrite(ndev->db_mask, mmio);
+	}
+	spin_unlock_irqrestore(&ndev->db_mask_lock, irqflags);
+
+	return 0;
+}
+
+static inline int ndev_vec_mask(struct intel_ntb_dev *ndev, int db_vector)
+{
+	u64 shift, mask;
+
+	shift = ndev->db_vec_shift;
+	mask = BIT_ULL(shift) - 1;
+
+	return mask << (shift * db_vector);
+}
+
+static inline int ndev_spad_addr(struct intel_ntb_dev *ndev, int idx,
+				 phys_addr_t *spad_addr, phys_addr_t reg_addr,
+				 unsigned long reg)
+{
+	if (ndev_is_unsafe(ndev, NTB_UNSAFE_SPAD))
+		pr_warn_once("%s: NTB unsafe scratchpad access", __func__);
+
+	if (idx < 0 || idx >= ndev->spad_count)
+		return -EINVAL;
+
+	if (spad_addr) {
+		*spad_addr = reg_addr + reg + (idx << 2);
+		dev_dbg(ndev_dev(ndev), "Peer spad addr %llx\n", *spad_addr);
+	}
+
+	return 0;
+}
+
+static inline u32 ndev_spad_read(struct intel_ntb_dev *ndev, int idx,
+				 void __iomem *mmio)
+{
+	if (ndev_is_unsafe(ndev, NTB_UNSAFE_SPAD))
+		pr_warn_once("%s: NTB unsafe scratchpad access", __func__);
+
+	if (idx < 0 || idx >= ndev->spad_count)
+		return 0;
+
+	return ioread32(mmio + (idx << 2));
+}
+
+static inline int ndev_spad_write(struct intel_ntb_dev *ndev, int idx, u32 val,
+				  void __iomem *mmio)
+{
+	if (ndev_is_unsafe(ndev, NTB_UNSAFE_SPAD))
+		pr_warn_once("%s: NTB unsafe scratchpad access", __func__);
+
+	if (idx < 0 || idx >= ndev->spad_count)
+		return -EINVAL;
+
+	iowrite32(val, mmio + (idx << 2));
+
+	return 0;
+}
+
+static irqreturn_t ndev_interrupt(struct intel_ntb_dev *ndev, int vec)
+{
+	u64 vec_mask;
+
+	vec_mask = ndev_vec_mask(ndev, vec);
+
+	dev_dbg(ndev_dev(ndev), "vec %d vec_mask %llx\n", vec, vec_mask);
+
+	ndev->last_ts = jiffies;
+
+	if (vec_mask & ndev->db_link_mask) {
+		if (ndev->reg->poll_link(ndev))
+			ntb_link_event(&ndev->ntb);
+	}
+
+	if (vec_mask & ndev->db_valid_mask)
+		ntb_db_event(&ndev->ntb, vec);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t ndev_vec_isr(int irq, void *dev)
+{
+	struct intel_ntb_vec *nvec = dev;
+
+	return ndev_interrupt(nvec->ndev, nvec->num);
+}
+
+static irqreturn_t ndev_irq_isr(int irq, void *dev)
+{
+	struct intel_ntb_dev *ndev = dev;
+
+	return ndev_interrupt(ndev, irq - ndev_pdev(ndev)->irq);
+}
+
+static int ndev_init_isr(struct intel_ntb_dev *ndev,
+			 int msix_min, int msix_max,
+			 int msix_shift, int total_shift)
+{
+	struct pci_dev *pdev;
+	int rc, i, msix_count, node;
+
+	pdev = ndev_pdev(ndev);
+
+	node = dev_to_node(&pdev->dev);
+
+	/* Mask all doorbell interrupts */
+	ndev->db_mask = ndev->db_valid_mask;
+	ndev->reg->db_iowrite(ndev->db_mask,
+			      ndev->self_mmio +
+			      ndev->self_reg->db_mask);
+
+	/* Try to set up msix irq */
+
+	ndev->vec = kzalloc_node(msix_max * sizeof(*ndev->vec),
+				 GFP_KERNEL, node);
+	if (!ndev->vec)
+		goto err_msix_vec_alloc;
+
+	ndev->msix = kzalloc_node(msix_max * sizeof(*ndev->msix),
+				  GFP_KERNEL, node);
+	if (!ndev->msix)
+		goto err_msix_alloc;
+
+	for (i = 0; i < msix_max; ++i)
+		ndev->msix[i].entry = i;
+
+	msix_count = pci_enable_msix_range(pdev, ndev->msix,
+					   msix_min, msix_max);
+	if (msix_count < 0)
+		goto err_msix_enable;
+
+	for (i = 0; i < msix_count; ++i) {
+		ndev->vec[i].ndev = ndev;
+		ndev->vec[i].num = i;
+		rc = request_irq(ndev->msix[i].vector, ndev_vec_isr, 0,
+				 "ndev_vec_isr", &ndev->vec[i]);
+		if (rc)
+			goto err_msix_request;
+	}
+
+	dev_dbg(ndev_dev(ndev), "Using msix interrupts\n");
+	ndev->db_vec_count = msix_count;
+	ndev->db_vec_shift = msix_shift;
+	return 0;
+
+err_msix_request:
+	while (i-- > 0)
+		free_irq(ndev->msix[i].vector, ndev);
+	pci_disable_msix(pdev);
+err_msix_enable:
+	kfree(ndev->msix);
+err_msix_alloc:
+	kfree(ndev->vec);
+err_msix_vec_alloc:
+	ndev->msix = NULL;
+	ndev->vec = NULL;
+
+	/* Try to set up msi irq */
+
+	rc = pci_enable_msi(pdev);
+	if (rc)
+		goto err_msi_enable;
+
+	rc = request_irq(pdev->irq, ndev_irq_isr, 0,
+			 "ndev_irq_isr", ndev);
+	if (rc)
+		goto err_msi_request;
+
+	dev_dbg(ndev_dev(ndev), "Using msi interrupts\n");
+	ndev->db_vec_count = 1;
+	ndev->db_vec_shift = total_shift;
+	return 0;
+
+err_msi_request:
+	pci_disable_msi(pdev);
+err_msi_enable:
+
+	/* Try to set up intx irq */
+
+	pci_intx(pdev, 1);
+
+	rc = request_irq(pdev->irq, ndev_irq_isr, IRQF_SHARED,
+			 "ndev_irq_isr", ndev);
+	if (rc)
+		goto err_intx_request;
+
+	dev_dbg(ndev_dev(ndev), "Using intx interrupts\n");
+	ndev->db_vec_count = 1;
+	ndev->db_vec_shift = total_shift;
+	return 0;
+
+err_intx_request:
+	return rc;
+}
+
+static void ndev_deinit_isr(struct intel_ntb_dev *ndev)
+{
+	struct pci_dev *pdev;
+	int i;
+
+	pdev = ndev_pdev(ndev);
+
+	/* Mask all doorbell interrupts */
+	ndev->db_mask = ndev->db_valid_mask;
+	ndev->reg->db_iowrite(ndev->db_mask,
+			      ndev->self_mmio +
+			      ndev->self_reg->db_mask);
+
+	if (ndev->msix) {
+		i = ndev->db_vec_count;
+		while (i--)
+			free_irq(ndev->msix[i].vector, &ndev->vec[i]);
+		pci_disable_msix(pdev);
+		kfree(ndev->msix);
+		kfree(ndev->vec);
+	} else {
+		free_irq(pdev->irq, ndev);
+		if (pci_dev_msi_enabled(pdev))
+			pci_disable_msi(pdev);
+	}
+}
+
+static ssize_t ndev_debugfs_read(struct file *filp, char __user *ubuf,
+				 size_t count, loff_t *offp)
+{
+	struct intel_ntb_dev *ndev;
+	void __iomem *mmio;
+	char *buf;
+	size_t buf_size;
+	ssize_t ret, off;
+	union { u64 v64; u32 v32; u16 v16; } u;
+
+	ndev = filp->private_data;
+	mmio = ndev->self_mmio;
+
+	buf_size = min(count, 0x800ul);
+
+	buf = kmalloc(buf_size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	off = 0;
+
+	off += scnprintf(buf + off, buf_size - off,
+			 "NTB Device Information:\n");
+
+	off += scnprintf(buf + off, buf_size - off,
+			 "Connection Topology -\t%s\n",
+			 ntb_topo_string(ndev->ntb.topo));
+
+	off += scnprintf(buf + off, buf_size - off,
+			 "B2B Offset -\t\t%#lx\n", ndev->b2b_off);
+	off += scnprintf(buf + off, buf_size - off,
+			 "B2B MW Idx -\t\t%d\n", ndev->b2b_idx);
+	off += scnprintf(buf + off, buf_size - off,
+			 "BAR4 Split -\t\t%s\n",
+			 ndev->bar4_split ? "yes" : "no");
+
+	off += scnprintf(buf + off, buf_size - off,
+			 "NTB CTL -\t\t%#06x\n", ndev->ntb_ctl);
+	off += scnprintf(buf + off, buf_size - off,
+			 "LNK STA -\t\t%#06x\n", ndev->lnk_sta);
+
+	if (!ndev->reg->link_is_up(ndev)) {
+		off += scnprintf(buf + off, buf_size - off,
+				 "Link Status -\t\tDown\n");
+	} else {
+		off += scnprintf(buf + off, buf_size - off,
+				 "Link Status -\t\tUp\n");
+		off += scnprintf(buf + off, buf_size - off,
+				 "Link Speed -\t\tPCI-E Gen %u\n",
+				 NTB_LNK_STA_SPEED(ndev->lnk_sta));
+		off += scnprintf(buf + off, buf_size - off,
+				 "Link Width -\t\tx%u\n",
+				 NTB_LNK_STA_WIDTH(ndev->lnk_sta));
+	}
+
+	off += scnprintf(buf + off, buf_size - off,
+			 "Memory Window Count -\t%u\n", ndev->mw_count);
+	off += scnprintf(buf + off, buf_size - off,
+			 "Scratchpad Count -\t%u\n", ndev->spad_count);
+	off += scnprintf(buf + off, buf_size - off,
+			 "Doorbell Count -\t%u\n", ndev->db_count);
+	off += scnprintf(buf + off, buf_size - off,
+			 "Doorbell Vector Count -\t%u\n", ndev->db_vec_count);
+	off += scnprintf(buf + off, buf_size - off,
+			 "Doorbell Vector Shift -\t%u\n", ndev->db_vec_shift);
+
+	off += scnprintf(buf + off, buf_size - off,
+			 "Doorbell Valid Mask -\t%#llx\n", ndev->db_valid_mask);
+	off += scnprintf(buf + off, buf_size - off,
+			 "Doorbell Link Mask -\t%#llx\n", ndev->db_link_mask);
+	off += scnprintf(buf + off, buf_size - off,
+			 "Doorbell Mask Cached -\t%#llx\n", ndev->db_mask);
+
+	u.v64 = ndev_db_read(ndev, mmio + ndev->self_reg->db_mask);
+	off += scnprintf(buf + off, buf_size - off,
+			 "Doorbell Mask -\t\t%#llx\n", u.v64);
+
+	u.v64 = ndev_db_read(ndev, mmio + ndev->self_reg->db_bell);
+	off += scnprintf(buf + off, buf_size - off,
+			 "Doorbell Bell -\t\t%#llx\n", u.v64);
+
+	off += scnprintf(buf + off, buf_size - off,
+			 "\nNTB Incoming XLAT:\n");
+
+	u.v64 = ioread64(mmio + bar2_off(ndev->xlat_reg->bar2_xlat, 2));
+	off += scnprintf(buf + off, buf_size - off,
+			 "XLAT23 -\t\t%#018llx\n", u.v64);
+
+	if (ndev->bar4_split) {
+		u.v32 = ioread32(mmio + bar2_off(ndev->xlat_reg->bar2_xlat, 4));
+		off += scnprintf(buf + off, buf_size - off,
+				 "XLAT4 -\t\t\t%#06x\n", u.v32);
+
+		u.v32 = ioread32(mmio + bar2_off(ndev->xlat_reg->bar2_xlat, 5));
+		off += scnprintf(buf + off, buf_size - off,
+				 "XLAT5 -\t\t\t%#06x\n", u.v32);
+	} else {
+		u.v64 = ioread64(mmio + bar2_off(ndev->xlat_reg->bar2_xlat, 4));
+		off += scnprintf(buf + off, buf_size - off,
+				 "XLAT45 -\t\t%#018llx\n", u.v64);
+	}
+
+	u.v64 = ioread64(mmio + bar2_off(ndev->xlat_reg->bar2_limit, 2));
+	off += scnprintf(buf + off, buf_size - off,
+			 "LMT23 -\t\t\t%#018llx\n", u.v64);
+
+	if (ndev->bar4_split) {
+		u.v32 = ioread32(mmio + bar2_off(ndev->xlat_reg->bar2_limit, 4));
+		off += scnprintf(buf + off, buf_size - off,
+				 "LMT4 -\t\t\t%#06x\n", u.v32);
+		u.v32 = ioread32(mmio + bar2_off(ndev->xlat_reg->bar2_limit, 5));
+		off += scnprintf(buf + off, buf_size - off,
+				 "LMT5 -\t\t\t%#06x\n", u.v32);
+	} else {
+		u.v64 = ioread64(mmio + bar2_off(ndev->xlat_reg->bar2_limit, 4));
+		off += scnprintf(buf + off, buf_size - off,
+				 "LMT45 -\t\t\t%#018llx\n", u.v64);
+	}
+
+	if (pdev_is_xeon(ndev->ntb.pdev)) {
+		if (ntb_topo_is_b2b(ndev->ntb.topo)) {
+			off += scnprintf(buf + off, buf_size - off,
+					 "\nNTB Outgoing B2B XLAT:\n");
+
+			u.v64 = ioread64(mmio + XEON_PBAR23XLAT_OFFSET);
+			off += scnprintf(buf + off, buf_size - off,
+					 "B2B XLAT23 -\t\t%#018llx\n", u.v64);
+
+			if (ndev->bar4_split) {
+				u.v32 = ioread32(mmio + XEON_PBAR4XLAT_OFFSET);
+				off += scnprintf(buf + off, buf_size - off,
+						 "B2B XLAT4 -\t\t%#06x\n",
+						 u.v32);
+				u.v32 = ioread32(mmio + XEON_PBAR5XLAT_OFFSET);
+				off += scnprintf(buf + off, buf_size - off,
+						 "B2B XLAT5 -\t\t%#06x\n",
+						 u.v32);
+			} else {
+				u.v64 = ioread64(mmio + XEON_PBAR45XLAT_OFFSET);
+				off += scnprintf(buf + off, buf_size - off,
+						 "B2B XLAT45 -\t\t%#018llx\n",
+						 u.v64);
+			}
+
+			u.v64 = ioread64(mmio + XEON_PBAR23LMT_OFFSET);
+			off += scnprintf(buf + off, buf_size - off,
+					 "B2B LMT23 -\t\t%#018llx\n", u.v64);
+
+			if (ndev->bar4_split) {
+				u.v32 = ioread32(mmio + XEON_PBAR4LMT_OFFSET);
+				off += scnprintf(buf + off, buf_size - off,
+						 "B2B LMT4 -\t\t%#06x\n",
+						 u.v32);
+				u.v32 = ioread32(mmio + XEON_PBAR5LMT_OFFSET);
+				off += scnprintf(buf + off, buf_size - off,
+						 "B2B LMT5 -\t\t%#06x\n",
+						 u.v32);
+			} else {
+				u.v64 = ioread64(mmio + XEON_PBAR45LMT_OFFSET);
+				off += scnprintf(buf + off, buf_size - off,
+						 "B2B LMT45 -\t\t%#018llx\n",
+						 u.v64);
+			}
+
+			off += scnprintf(buf + off, buf_size - off,
+					 "\nNTB Secondary BAR:\n");
+
+			u.v64 = ioread64(mmio + XEON_SBAR0BASE_OFFSET);
+			off += scnprintf(buf + off, buf_size - off,
+					 "SBAR01 -\t\t%#018llx\n", u.v64);
+
+			u.v64 = ioread64(mmio + XEON_SBAR23BASE_OFFSET);
+			off += scnprintf(buf + off, buf_size - off,
+					 "SBAR23 -\t\t%#018llx\n", u.v64);
+
+			if (ndev->bar4_split) {
+				u.v32 = ioread32(mmio + XEON_SBAR4BASE_OFFSET);
+				off += scnprintf(buf + off, buf_size - off,
+						 "SBAR4 -\t\t\t%#06x\n", u.v32);
+				u.v32 = ioread32(mmio + XEON_SBAR5BASE_OFFSET);
+				off += scnprintf(buf + off, buf_size - off,
+						 "SBAR5 -\t\t\t%#06x\n", u.v32);
+			} else {
+				u.v64 = ioread64(mmio + XEON_SBAR45BASE_OFFSET);
+				off += scnprintf(buf + off, buf_size - off,
+						 "SBAR45 -\t\t%#018llx\n",
+						 u.v64);
+			}
+		}
+
+		off += scnprintf(buf + off, buf_size - off,
+				 "\nXEON NTB Statistics:\n");
+
+		u.v16 = ioread16(mmio + XEON_USMEMMISS_OFFSET);
+		off += scnprintf(buf + off, buf_size - off,
+				 "Upstream Memory Miss -\t%u\n", u.v16);
+
+		off += scnprintf(buf + off, buf_size - off,
+				 "\nXEON NTB Hardware Errors:\n");
+
+		if (!pci_read_config_word(ndev->ntb.pdev,
+					  XEON_DEVSTS_OFFSET, &u.v16))
+			off += scnprintf(buf + off, buf_size - off,
+					 "DEVSTS -\t\t%#06x\n", u.v16);
+
+		if (!pci_read_config_word(ndev->ntb.pdev,
+					  XEON_LINK_STATUS_OFFSET, &u.v16))
+			off += scnprintf(buf + off, buf_size - off,
+					 "LNKSTS -\t\t%#06x\n", u.v16);
+
+		if (!pci_read_config_dword(ndev->ntb.pdev,
+					   XEON_UNCERRSTS_OFFSET, &u.v32))
+			off += scnprintf(buf + off, buf_size - off,
+					 "UNCERRSTS -\t\t%#06x\n", u.v32);
+
+		if (!pci_read_config_dword(ndev->ntb.pdev,
+					   XEON_CORERRSTS_OFFSET, &u.v32))
+			off += scnprintf(buf + off, buf_size - off,
+					 "CORERRSTS -\t\t%#06x\n", u.v32);
+	}
+
+	ret = simple_read_from_buffer(ubuf, count, offp, buf, off);
+	kfree(buf);
+	return ret;
+}
+
+static void ndev_init_debugfs(struct intel_ntb_dev *ndev)
+{
+	if (!debugfs_dir) {
+		ndev->debugfs_dir = NULL;
+		ndev->debugfs_info = NULL;
+	} else {
+		ndev->debugfs_dir =
+			debugfs_create_dir(ndev_name(ndev), debugfs_dir);
+		if (!ndev->debugfs_dir)
+			ndev->debugfs_info = NULL;
+		else
+			ndev->debugfs_info =
+				debugfs_create_file("info", S_IRUSR,
+						    ndev->debugfs_dir, ndev,
+						    &intel_ntb_debugfs_info);
+	}
+}
+
+static void ndev_deinit_debugfs(struct intel_ntb_dev *ndev)
+{
+	debugfs_remove_recursive(ndev->debugfs_dir);
+}
+
+static int intel_ntb_mw_count(struct ntb_dev *ntb)
+{
+	return ntb_ndev(ntb)->mw_count;
+}
+
+static int intel_ntb_mw_get_range(struct ntb_dev *ntb, int idx,
+				  phys_addr_t *base,
+				  resource_size_t *size,
+				  resource_size_t *align,
+				  resource_size_t *align_size)
+{
+	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
+	int bar;
+
+	if (idx >= ndev->b2b_idx && !ndev->b2b_off)
+		idx += 1;
+
+	bar = ndev_mw_to_bar(ndev, idx);
+	if (bar < 0)
+		return bar;
+
+	if (base)
+		*base = pci_resource_start(ndev->ntb.pdev, bar) +
+			(idx == ndev->b2b_idx ? ndev->b2b_off : 0);
+
+	if (size)
+		*size = pci_resource_len(ndev->ntb.pdev, bar) -
+			(idx == ndev->b2b_idx ? ndev->b2b_off : 0);
+
+	if (align)
+		*align = pci_resource_len(ndev->ntb.pdev, bar);
+
+	if (align_size)
+		*align_size = 1;
+
+	return 0;
+}
+
+static int intel_ntb_mw_set_trans(struct ntb_dev *ntb, int idx,
+				  dma_addr_t addr, resource_size_t size)
+{
+	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
+	unsigned long base_reg, xlat_reg, limit_reg;
+	resource_size_t bar_size, mw_size;
+	void __iomem *mmio;
+	u64 base, limit, reg_val;
+	int bar;
+
+	if (idx >= ndev->b2b_idx && !ndev->b2b_off)
+		idx += 1;
+
+	bar = ndev_mw_to_bar(ndev, idx);
+	if (bar < 0)
+		return bar;
+
+	bar_size = pci_resource_len(ndev->ntb.pdev, bar);
+
+	if (idx == ndev->b2b_idx)
+		mw_size = bar_size - ndev->b2b_off;
+	else
+		mw_size = bar_size;
+
+	/* hardware requires that addr is aligned to bar size */
+	if (addr & (bar_size - 1))
+		return -EINVAL;
+
+	/* make sure the range fits in the usable mw size */
+	if (size > mw_size)
+		return -EINVAL;
+
+	mmio = ndev->self_mmio;
+	base_reg = bar0_off(ndev->xlat_reg->bar0_base, bar);
+	xlat_reg = bar2_off(ndev->xlat_reg->bar2_xlat, bar);
+	limit_reg = bar2_off(ndev->xlat_reg->bar2_limit, bar);
+
+	if (bar < 4 || !ndev->bar4_split) {
+		base = ioread64(mmio + base_reg);
+
+		/* Set the limit if supported, if size is not mw_size */
+		if (limit_reg && size != mw_size)
+			limit = base + size;
+		else
+			limit = 0;
+
+		/* set and verify setting the translation address */
+		iowrite64(addr, mmio + xlat_reg);
+		reg_val = ioread64(mmio + xlat_reg);
+		if (reg_val != addr) {
+			iowrite64(0, mmio + xlat_reg);
+			return -EIO;
+		}
+
+		/* set and verify setting the limit */
+		iowrite64(limit, mmio + limit_reg);
+		reg_val = ioread64(mmio + limit_reg);
+		if (reg_val != limit) {
+			iowrite64(base, mmio + limit_reg);
+			iowrite64(0, mmio + xlat_reg);
+			return -EIO;
+		}
+	} else {
+		/* split bar addr range must all be 32 bit */
+		if (addr & (~0ull << 32))
+			return -EINVAL;
+		if ((addr + size) & (~0ull << 32))
+			return -EINVAL;
+
+		base = ioread32(mmio + base_reg);
+
+		/* Set the limit if supported, if size is not mw_size */
+		if (limit_reg && size != mw_size)
+			limit = base + size;
+		else
+			limit = 0;
+
+		/* set and verify setting the translation address */
+		iowrite32(addr, mmio + xlat_reg);
+		reg_val = ioread32(mmio + xlat_reg);
+		if (reg_val != addr) {
+			iowrite32(0, mmio + xlat_reg);
+			return -EIO;
+		}
+
+		/* set and verify setting the limit */
+		iowrite32(limit, mmio + limit_reg);
+		reg_val = ioread32(mmio + limit_reg);
+		if (reg_val != limit) {
+			iowrite32(base, mmio + limit_reg);
+			iowrite32(0, mmio + xlat_reg);
+			return -EIO;
+		}
+	}
+
+	return 0;
+}
+
+static int intel_ntb_link_is_up(struct ntb_dev *ntb,
+				enum ntb_speed *speed,
+				enum ntb_width *width)
+{
+	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
+
+	if (ndev->reg->link_is_up(ndev)) {
+		if (speed)
+			*speed = NTB_LNK_STA_SPEED(ndev->lnk_sta);
+		if (width)
+			*width = NTB_LNK_STA_WIDTH(ndev->lnk_sta);
+		return 1;
+	} else {
+		/* TODO MAYBE: is it possible to observe the link speed and
+		 * width while link is training? */
+		if (speed)
+			*speed = NTB_SPEED_NONE;
+		if (width)
+			*width = NTB_WIDTH_NONE;
+		return 0;
+	}
+}
+
+static int intel_ntb_link_enable(struct ntb_dev *ntb,
+				 enum ntb_speed max_speed,
+				 enum ntb_width max_width)
+{
+	struct intel_ntb_dev *ndev;
+	u32 ntb_ctl;
+
+	ndev = container_of(ntb, struct intel_ntb_dev, ntb);
+
+	if (ndev->ntb.topo == NTB_TOPO_SEC)
+		return -EINVAL;
+
+	dev_dbg(ndev_dev(ndev),
+		"Enabling link with max_speed %d max_width %d\n",
+		max_speed, max_width);
+	if (max_speed != NTB_SPEED_AUTO)
+		dev_dbg(ndev_dev(ndev), "ignoring max_speed %d\n", max_speed);
+	if (max_width != NTB_WIDTH_AUTO)
+		dev_dbg(ndev_dev(ndev), "ignoring max_width %d\n", max_width);
+
+	ntb_ctl = ioread32(ndev->self_mmio + ndev->reg->ntb_ctl);
+	ntb_ctl &= ~(NTB_CTL_DISABLE | NTB_CTL_CFG_LOCK);
+	ntb_ctl |= NTB_CTL_P2S_BAR2_SNOOP | NTB_CTL_S2P_BAR2_SNOOP;
+	ntb_ctl |= NTB_CTL_P2S_BAR4_SNOOP | NTB_CTL_S2P_BAR4_SNOOP;
+	if (ndev->bar4_split)
+		ntb_ctl |= NTB_CTL_P2S_BAR5_SNOOP | NTB_CTL_S2P_BAR5_SNOOP;
+	iowrite32(ntb_ctl, ndev->self_mmio + ndev->reg->ntb_ctl);
+
+	return 0;
+}
+
+static int intel_ntb_link_disable(struct ntb_dev *ntb)
+{
+	struct intel_ntb_dev *ndev;
+	u32 ntb_cntl;
+
+	ndev = container_of(ntb, struct intel_ntb_dev, ntb);
+
+	if (ndev->ntb.topo == NTB_TOPO_SEC)
+		return -EINVAL;
+
+	dev_dbg(ndev_dev(ndev), "Disabling link\n");
+
+	/* Bring NTB link down */
+	ntb_cntl = ioread32(ndev->self_mmio + ndev->reg->ntb_ctl);
+	ntb_cntl &= ~(NTB_CTL_P2S_BAR2_SNOOP | NTB_CTL_S2P_BAR2_SNOOP);
+	ntb_cntl &= ~(NTB_CTL_P2S_BAR4_SNOOP | NTB_CTL_S2P_BAR4_SNOOP);
+	if (ndev->bar4_split)
+		ntb_cntl &= ~(NTB_CTL_P2S_BAR5_SNOOP | NTB_CTL_S2P_BAR5_SNOOP);
+	ntb_cntl |= NTB_CTL_DISABLE | NTB_CTL_CFG_LOCK;
+	iowrite32(ntb_cntl, ndev->self_mmio + ndev->reg->ntb_ctl);
+
+	return 0;
+}
+
+static int intel_ntb_db_is_unsafe(struct ntb_dev *ntb)
+{
+	return ndev_ignore_unsafe(ntb_ndev(ntb), NTB_UNSAFE_DB);
+}
+
+static u64 intel_ntb_db_valid_mask(struct ntb_dev *ntb)
+{
+	return ntb_ndev(ntb)->db_valid_mask;
+}
+
+static int intel_ntb_db_vector_count(struct ntb_dev *ntb)
+{
+	struct intel_ntb_dev *ndev;
+
+	ndev = container_of(ntb, struct intel_ntb_dev, ntb);
+
+	return ndev->db_vec_count;
+}
+
+static u64 intel_ntb_db_vector_mask(struct ntb_dev *ntb, int db_vector)
+{
+	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
+
+	if (db_vector < 0 || db_vector > ndev->db_vec_count)
+		return 0;
+
+	return ndev->db_valid_mask & ndev_vec_mask(ndev, db_vector);
+}
+
+static u64 intel_ntb_db_read(struct ntb_dev *ntb)
+{
+	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
+
+	return ndev_db_read(ndev,
+			    ndev->self_mmio +
+			    ndev->self_reg->db_bell);
+}
+
+static int intel_ntb_db_clear(struct ntb_dev *ntb, u64 db_bits)
+{
+	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
+
+	return ndev_db_write(ndev, db_bits,
+			     ndev->self_mmio +
+			     ndev->self_reg->db_bell);
+}
+
+static int intel_ntb_db_set_mask(struct ntb_dev *ntb, u64 db_bits)
+{
+	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
+
+	return ndev_db_set_mask(ndev, db_bits,
+				ndev->self_mmio +
+				ndev->self_reg->db_mask);
+}
+
+static int intel_ntb_db_clear_mask(struct ntb_dev *ntb, u64 db_bits)
+{
+	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
+
+	return ndev_db_clear_mask(ndev, db_bits,
+				  ndev->self_mmio +
+				  ndev->self_reg->db_mask);
+}
+
+static int intel_ntb_peer_db_addr(struct ntb_dev *ntb,
+				  phys_addr_t *db_addr,
+				  resource_size_t *db_size)
+{
+	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
+
+	return ndev_db_addr(ndev, db_addr, db_size, ndev->peer_addr,
+			    ndev->peer_reg->db_bell);
+}
+
+static int intel_ntb_peer_db_set(struct ntb_dev *ntb, u64 db_bits)
+{
+	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
+
+	return ndev_db_write(ndev, db_bits,
+			     ndev->peer_mmio +
+			     ndev->peer_reg->db_bell);
+}
+
+static int intel_ntb_spad_is_unsafe(struct ntb_dev *ntb)
+{
+	return ndev_ignore_unsafe(ntb_ndev(ntb), NTB_UNSAFE_SPAD);
+}
+
+static int intel_ntb_spad_count(struct ntb_dev *ntb)
+{
+	struct intel_ntb_dev *ndev;
+
+	ndev = container_of(ntb, struct intel_ntb_dev, ntb);
+
+	return ndev->spad_count;
+}
+
+static u32 intel_ntb_spad_read(struct ntb_dev *ntb, int idx)
+{
+	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
+
+	return ndev_spad_read(ndev, idx,
+			      ndev->self_mmio +
+			      ndev->self_reg->spad);
+}
+
+static int intel_ntb_spad_write(struct ntb_dev *ntb,
+				int idx, u32 val)
+{
+	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
+
+	return ndev_spad_write(ndev, idx, val,
+			       ndev->self_mmio +
+			       ndev->self_reg->spad);
+}
+
+static int intel_ntb_peer_spad_addr(struct ntb_dev *ntb, int idx,
+				    phys_addr_t *spad_addr)
+{
+	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
+
+	return ndev_spad_addr(ndev, idx, spad_addr, ndev->peer_addr,
+			      ndev->peer_reg->spad);
+}
+
+static u32 intel_ntb_peer_spad_read(struct ntb_dev *ntb, int idx)
+{
+	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
+
+	return ndev_spad_read(ndev, idx,
+			      ndev->peer_mmio +
+			      ndev->peer_reg->spad);
+}
+
+static int intel_ntb_peer_spad_write(struct ntb_dev *ntb,
+				     int idx, u32 val)
+{
+	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
+
+	return ndev_spad_write(ndev, idx, val,
+			       ndev->peer_mmio +
+			       ndev->peer_reg->spad);
+}
+
+/* ATOM */
+
+static u64 atom_db_ioread(void __iomem *mmio)
+{
+	return ioread64(mmio);
+}
+
+static void atom_db_iowrite(u64 bits, void __iomem *mmio)
+{
+	iowrite64(bits, mmio);
+}
+
+static int atom_poll_link(struct intel_ntb_dev *ndev)
+{
+	u32 ntb_ctl;
+
+	ntb_ctl = ioread32(ndev->self_mmio + ATOM_NTBCNTL_OFFSET);
+
+	if (ntb_ctl == ndev->ntb_ctl)
+		return 0;
+
+	ndev->ntb_ctl = ntb_ctl;
+
+	ndev->lnk_sta = ioread32(ndev->self_mmio + ATOM_LINK_STATUS_OFFSET);
+
+	return 1;
+}
+
+static int atom_link_is_up(struct intel_ntb_dev *ndev)
+{
+	return ATOM_NTB_CTL_ACTIVE(ndev->ntb_ctl);
+}
+
+static int atom_link_is_err(struct intel_ntb_dev *ndev)
+{
+	if (ioread32(ndev->self_mmio + ATOM_LTSSMSTATEJMP_OFFSET)
+	    & ATOM_LTSSMSTATEJMP_FORCEDETECT)
+		return 1;
+
+	if (ioread32(ndev->self_mmio + ATOM_IBSTERRRCRVSTS0_OFFSET)
+	    & ATOM_IBIST_ERR_OFLOW)
+		return 1;
+
+	return 0;
+}
+
+static inline enum ntb_topo atom_ppd_topo(struct intel_ntb_dev *ndev, u32 ppd)
+{
+	switch (ppd & ATOM_PPD_TOPO_MASK) {
+	case ATOM_PPD_TOPO_B2B_USD:
+		dev_dbg(ndev_dev(ndev), "PPD %d B2B USD\n", ppd);
+		return NTB_TOPO_B2B_USD;
+
+	case ATOM_PPD_TOPO_B2B_DSD:
+		dev_dbg(ndev_dev(ndev), "PPD %d B2B DSD\n", ppd);
+		return NTB_TOPO_B2B_DSD;
+
+	case ATOM_PPD_TOPO_PRI_USD:
+	case ATOM_PPD_TOPO_PRI_DSD: /* accept bogus PRI_DSD */
+	case ATOM_PPD_TOPO_SEC_USD:
+	case ATOM_PPD_TOPO_SEC_DSD: /* accept bogus SEC_DSD */
+		dev_dbg(ndev_dev(ndev), "PPD %d non B2B disabled\n", ppd);
+		return NTB_TOPO_NONE;
+	}
+
+	dev_dbg(ndev_dev(ndev), "PPD %d invalid\n", ppd);
+	return NTB_TOPO_NONE;
+}
+
+static void atom_link_hb(struct work_struct *work)
+{
+	struct intel_ntb_dev *ndev = hb_ndev(work);
+	unsigned long poll_ts;
+	void __iomem *mmio;
+	u32 status32;
+
+	poll_ts = ndev->last_ts + ATOM_LINK_HB_TIMEOUT;
+
+	/* Delay polling the link status if an interrupt was received,
+	 * unless the cached link status says the link is down.
+	 */
+	if (time_after(poll_ts, jiffies) && atom_link_is_up(ndev)) {
+		schedule_delayed_work(&ndev->hb_timer, poll_ts - jiffies);
+		return;
+	}
+
+	if (atom_poll_link(ndev))
+		ntb_link_event(&ndev->ntb);
+
+	if (atom_link_is_up(ndev) || !atom_link_is_err(ndev)) {
+		schedule_delayed_work(&ndev->hb_timer, ATOM_LINK_HB_TIMEOUT);
+		return;
+	}
+
+	/* Link is down with error: recover the link! */
+
+	mmio = ndev->self_mmio;
+
+	/* Driver resets the NTB ModPhy lanes - magic! */
+	iowrite8(0xe0, mmio + ATOM_MODPHY_PCSREG6);
+	iowrite8(0x40, mmio + ATOM_MODPHY_PCSREG4);
+	iowrite8(0x60, mmio + ATOM_MODPHY_PCSREG4);
+	iowrite8(0x60, mmio + ATOM_MODPHY_PCSREG6);
+
+	/* Driver waits 100ms to allow the NTB ModPhy to settle */
+	msleep(100);
+
+	/* Clear AER Errors, write to clear */
+	status32 = ioread32(mmio + ATOM_ERRCORSTS_OFFSET);
+	dev_dbg(ndev_dev(ndev), "ERRCORSTS = %x\n", status32);
+	status32 &= PCI_ERR_COR_REP_ROLL;
+	iowrite32(status32, mmio + ATOM_ERRCORSTS_OFFSET);
+
+	/* Clear unexpected electrical idle event in LTSSM, write to clear */
+	status32 = ioread32(mmio + ATOM_LTSSMERRSTS0_OFFSET);
+	dev_dbg(ndev_dev(ndev), "LTSSMERRSTS0 = %x\n", status32);
+	status32 |= ATOM_LTSSMERRSTS0_UNEXPECTEDEI;
+	iowrite32(status32, mmio + ATOM_LTSSMERRSTS0_OFFSET);
+
+	/* Clear DeSkew Buffer error, write to clear */
+	status32 = ioread32(mmio + ATOM_DESKEWSTS_OFFSET);
+	dev_dbg(ndev_dev(ndev), "DESKEWSTS = %x\n", status32);
+	status32 |= ATOM_DESKEWSTS_DBERR;
+	iowrite32(status32, mmio + ATOM_DESKEWSTS_OFFSET);
+
+	status32 = ioread32(mmio + ATOM_IBSTERRRCRVSTS0_OFFSET);
+	dev_dbg(ndev_dev(ndev), "IBSTERRRCRVSTS0 = %x\n", status32);
+	status32 &= ATOM_IBIST_ERR_OFLOW;
+	iowrite32(status32, mmio + ATOM_IBSTERRRCRVSTS0_OFFSET);
+
+	/* Releases the NTB state machine to allow the link to retrain */
+	status32 = ioread32(mmio + ATOM_LTSSMSTATEJMP_OFFSET);
+	dev_dbg(ndev_dev(ndev), "LTSSMSTATEJMP = %x\n", status32);
+	status32 &= ~ATOM_LTSSMSTATEJMP_FORCEDETECT;
+	iowrite32(status32, mmio + ATOM_LTSSMSTATEJMP_OFFSET);
+
+	/* There is a potential race between the 2 NTB devices recovering at the
+	 * same time.  If the times are the same, the link will not recover and
+	 * the driver will be stuck in this loop forever.  Add a random interval
+	 * to the recovery time to prevent this race.
+	 */
+	schedule_delayed_work(&ndev->hb_timer, ATOM_LINK_RECOVERY_TIME
+			      + prandom_u32() % ATOM_LINK_RECOVERY_TIME);
+}
+
+static int atom_init_isr(struct intel_ntb_dev *ndev)
+{
+	int rc;
+
+	rc = ndev_init_isr(ndev, 1, ATOM_DB_MSIX_VECTOR_COUNT,
+			   ATOM_DB_MSIX_VECTOR_SHIFT, ATOM_DB_TOTAL_SHIFT);
+	if (rc)
+		return rc;
+
+	/* ATOM doesn't have link status interrupt, poll on that platform */
+	ndev->last_ts = jiffies;
+	INIT_DELAYED_WORK(&ndev->hb_timer, atom_link_hb);
+	schedule_delayed_work(&ndev->hb_timer, ATOM_LINK_HB_TIMEOUT);
+
+	return 0;
+}
+
+static void atom_deinit_isr(struct intel_ntb_dev *ndev)
+{
+	cancel_delayed_work_sync(&ndev->hb_timer);
+	ndev_deinit_isr(ndev);
+}
+
+static int atom_init_ntb(struct intel_ntb_dev *ndev)
+{
+	ndev->mw_count = ATOM_MW_COUNT;
+	ndev->spad_count = ATOM_SPAD_COUNT;
+	ndev->db_count = ATOM_DB_COUNT;
+
+	switch (ndev->ntb.topo) {
+	case NTB_TOPO_B2B_USD:
+	case NTB_TOPO_B2B_DSD:
+		ndev->self_reg = &atom_pri_reg;
+		ndev->peer_reg = &atom_b2b_reg;
+		ndev->xlat_reg = &atom_sec_xlat;
+
+		/* Enable Bus Master and Memory Space on the secondary side */
+		iowrite16(PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER,
+			  ndev->self_mmio + ATOM_SPCICMD_OFFSET);
+
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	ndev->db_valid_mask = BIT_ULL(ndev->db_count) - 1;
+
+	return 0;
+}
+
+static int atom_init_dev(struct intel_ntb_dev *ndev)
+{
+	u32 ppd;
+	int rc;
+
+	rc = pci_read_config_dword(ndev->ntb.pdev, ATOM_PPD_OFFSET, &ppd);
+	if (rc)
+		return -EIO;
+
+	ndev->ntb.topo = atom_ppd_topo(ndev, ppd);
+	if (ndev->ntb.topo == NTB_TOPO_NONE)
+		return -EINVAL;
+
+	rc = atom_init_ntb(ndev);
+	if (rc)
+		return rc;
+
+	rc = atom_init_isr(ndev);
+	if (rc)
+		return rc;
+
+	if (ndev->ntb.topo != NTB_TOPO_SEC) {
+		/* Initiate PCI-E link training */
+		rc = pci_write_config_dword(ndev->ntb.pdev, ATOM_PPD_OFFSET,
+					    ppd | ATOM_PPD_INIT_LINK);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+static void atom_deinit_dev(struct intel_ntb_dev *ndev)
+{
+	atom_deinit_isr(ndev);
+}
+
+/* XEON */
+
+static u64 xeon_db_ioread(void __iomem *mmio)
+{
+	return (u64)ioread16(mmio);
+}
+
+static void xeon_db_iowrite(u64 bits, void __iomem *mmio)
+{
+	iowrite16((u16)bits, mmio);
+}
+
+static int xeon_poll_link(struct intel_ntb_dev *ndev)
+{
+	u16 reg_val;
+	int rc;
+
+	ndev->reg->db_iowrite(ndev->db_link_mask,
+			      ndev->self_mmio +
+			      ndev->self_reg->db_bell);
+
+	rc = pci_read_config_word(ndev->ntb.pdev,
+				  XEON_LINK_STATUS_OFFSET, &reg_val);
+	if (rc)
+		return 0;
+
+	if (reg_val == ndev->lnk_sta)
+		return 0;
+
+	ndev->lnk_sta = reg_val;
+
+	return 1;
+}
+
+static int xeon_link_is_up(struct intel_ntb_dev *ndev)
+{
+	if (ndev->ntb.topo == NTB_TOPO_SEC)
+		return 1;
+
+	return NTB_LNK_STA_ACTIVE(ndev->lnk_sta);
+}
+
+static inline enum ntb_topo xeon_ppd_topo(struct intel_ntb_dev *ndev, u8 ppd)
+{
+	switch (ppd & XEON_PPD_TOPO_MASK) {
+	case XEON_PPD_TOPO_B2B_USD:
+		return NTB_TOPO_B2B_USD;
+
+	case XEON_PPD_TOPO_B2B_DSD:
+		return NTB_TOPO_B2B_DSD;
+
+	case XEON_PPD_TOPO_PRI_USD:
+	case XEON_PPD_TOPO_PRI_DSD: /* accept bogus PRI_DSD */
+		return NTB_TOPO_PRI;
+
+	case XEON_PPD_TOPO_SEC_USD:
+	case XEON_PPD_TOPO_SEC_DSD: /* accept bogus SEC_DSD */
+		return NTB_TOPO_SEC;
+	}
+
+	return NTB_TOPO_NONE;
+}
+
+static inline int xeon_ppd_bar4_split(struct intel_ntb_dev *ndev, u8 ppd)
+{
+	if (ppd & XEON_PPD_SPLIT_BAR_MASK) {
+		dev_dbg(ndev_dev(ndev), "PPD %d split bar\n", ppd);
+		return 1;
+	}
+	return 0;
+}
+
+static int xeon_init_isr(struct intel_ntb_dev *ndev)
+{
+	return ndev_init_isr(ndev, XEON_DB_MSIX_VECTOR_COUNT,
+			     XEON_DB_MSIX_VECTOR_COUNT,
+			     XEON_DB_MSIX_VECTOR_SHIFT,
+			     XEON_DB_TOTAL_SHIFT);
+}
+
+static void xeon_deinit_isr(struct intel_ntb_dev *ndev)
+{
+	ndev_deinit_isr(ndev);
+}
+
+static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev,
+			     const struct intel_b2b_addr *addr,
+			     const struct intel_b2b_addr *peer_addr)
+{
+	struct pci_dev *pdev;
+	void __iomem *mmio;
+	resource_size_t bar_size;
+	phys_addr_t bar_addr;
+	int b2b_bar;
+	u8 bar_sz;
+
+	pdev = ndev_pdev(ndev);
+	mmio = ndev->self_mmio;
+
+	if (ndev->b2b_idx >= ndev->mw_count) {
+		dev_dbg(ndev_dev(ndev), "not using b2b mw\n");
+		b2b_bar = 0;
+		ndev->b2b_off = 0;
+	} else {
+		b2b_bar = ndev_mw_to_bar(ndev, ndev->b2b_idx);
+		if (b2b_bar < 0)
+			return -EIO;
+
+		dev_dbg(ndev_dev(ndev), "using b2b mw bar %d\n", b2b_bar);
+
+		bar_size = pci_resource_len(ndev->ntb.pdev, b2b_bar);
+
+		dev_dbg(ndev_dev(ndev), "b2b bar size %#llx\n", bar_size);
+
+		if (b2b_mw_share && XEON_B2B_MIN_SIZE <= bar_size >> 1) {
+			dev_dbg(ndev_dev(ndev),
+				"b2b using first half of bar\n");
+			ndev->b2b_off = bar_size >> 1;
+		} else if (XEON_B2B_MIN_SIZE <= bar_size) {
+			dev_dbg(ndev_dev(ndev),
+				"b2b using whole bar\n");
+			ndev->b2b_off = 0;
+			--ndev->mw_count;
+		} else {
+			dev_dbg(ndev_dev(ndev),
+				"b2b bar size is too small\n");
+			return -EIO;
+		}
+	}
+
+	/* Reset the secondary bar sizes to match the primary bar sizes,
+	 * except disable or halve the size of the b2b secondary bar.
+	 *
+	 * Note: code for each specific bar size register, because the register
+	 * offsets are not in a consistent order (bar5sz comes after ppd, odd).
+	 */
+	pci_read_config_byte(pdev, XEON_PBAR23SZ_OFFSET, &bar_sz);
+	dev_dbg(ndev_dev(ndev), "PBAR23SZ %#x\n", bar_sz);
+	if (b2b_bar == 2) {
+		if (ndev->b2b_off)
+			bar_sz -= 1;
+		else
+			bar_sz = 0;
+	}
+	pci_write_config_byte(pdev, XEON_SBAR23SZ_OFFSET, bar_sz);
+	pci_read_config_byte(pdev, XEON_SBAR23SZ_OFFSET, &bar_sz);
+	dev_dbg(ndev_dev(ndev), "SBAR23SZ %#x\n", bar_sz);
+
+	if (!ndev->bar4_split) {
+		pci_read_config_byte(pdev, XEON_PBAR45SZ_OFFSET, &bar_sz);
+		dev_dbg(ndev_dev(ndev), "PBAR45SZ %#x\n", bar_sz);
+		if (b2b_bar == 4) {
+			if (ndev->b2b_off)
+				bar_sz -= 1;
+			else
+				bar_sz = 0;
+		}
+		pci_write_config_byte(pdev, XEON_SBAR45SZ_OFFSET, bar_sz);
+		pci_read_config_byte(pdev, XEON_SBAR45SZ_OFFSET, &bar_sz);
+		dev_dbg(ndev_dev(ndev), "SBAR45SZ %#x\n", bar_sz);
+	} else {
+		pci_read_config_byte(pdev, XEON_PBAR4SZ_OFFSET, &bar_sz);
+		dev_dbg(ndev_dev(ndev), "PBAR4SZ %#x\n", bar_sz);
+		if (b2b_bar == 4) {
+			if (ndev->b2b_off)
+				bar_sz -= 1;
+			else
+				bar_sz = 0;
+		}
+		pci_write_config_byte(pdev, XEON_SBAR4SZ_OFFSET, bar_sz);
+		pci_read_config_byte(pdev, XEON_SBAR4SZ_OFFSET, &bar_sz);
+		dev_dbg(ndev_dev(ndev), "SBAR4SZ %#x\n", bar_sz);
+
+		pci_read_config_byte(pdev, XEON_PBAR5SZ_OFFSET, &bar_sz);
+		dev_dbg(ndev_dev(ndev), "PBAR5SZ %#x\n", bar_sz);
+		if (b2b_bar == 5) {
+			if (ndev->b2b_off)
+				bar_sz -= 1;
+			else
+				bar_sz = 0;
+		}
+		pci_write_config_byte(pdev, XEON_SBAR5SZ_OFFSET, bar_sz);
+		pci_read_config_byte(pdev, XEON_SBAR5SZ_OFFSET, &bar_sz);
+		dev_dbg(ndev_dev(ndev), "SBAR5SZ %#x\n", bar_sz);
+	}
+
+	/* SBAR01 hit by first part of the b2b bar */
+	if (b2b_bar == 0)
+		bar_addr = addr->bar0_addr;
+	else if (b2b_bar == 2)
+		bar_addr = addr->bar2_addr64;
+	else if (b2b_bar == 4 && !ndev->bar4_split)
+		bar_addr = addr->bar4_addr64;
+	else if (b2b_bar == 4)
+		bar_addr = addr->bar4_addr32;
+	else if (b2b_bar == 5)
+		bar_addr = addr->bar5_addr32;
+	else
+		return -EIO;
+
+	dev_dbg(ndev_dev(ndev), "SBAR01 %#018llx\n", bar_addr);
+	iowrite64(bar_addr, mmio + XEON_SBAR0BASE_OFFSET);
+
+	/* Other SBAR are normally hit by the PBAR xlat, except for b2b bar.
+	 * The b2b bar is either disabled above, or configured half-size, and
+	 * it starts at the PBAR xlat + offset.
+	 */
+
+	bar_addr = addr->bar2_addr64 + (b2b_bar == 2 ? ndev->b2b_off : 0);
+	iowrite64(bar_addr, mmio + XEON_SBAR23BASE_OFFSET);
+	bar_addr = ioread64(mmio + XEON_SBAR23BASE_OFFSET);
+	dev_dbg(ndev_dev(ndev), "SBAR23 %#018llx\n", bar_addr);
+
+	if (!ndev->bar4_split) {
+		bar_addr = addr->bar4_addr64 +
+			(b2b_bar == 4 ? ndev->b2b_off : 0);
+		iowrite64(bar_addr, mmio + XEON_SBAR45BASE_OFFSET);
+		bar_addr = ioread64(mmio + XEON_SBAR45BASE_OFFSET);
+		dev_dbg(ndev_dev(ndev), "SBAR45 %#018llx\n", bar_addr);
+	} else {
+		bar_addr = addr->bar4_addr32 +
+			(b2b_bar == 4 ? ndev->b2b_off : 0);
+		iowrite32(bar_addr, mmio + XEON_SBAR4BASE_OFFSET);
+		bar_addr = ioread32(mmio + XEON_SBAR4BASE_OFFSET);
+		dev_dbg(ndev_dev(ndev), "SBAR4 %#010llx\n", bar_addr);
+
+		bar_addr = addr->bar5_addr32 +
+			(b2b_bar == 5 ? ndev->b2b_off : 0);
+		iowrite32(bar_addr, mmio + XEON_SBAR5BASE_OFFSET);
+		bar_addr = ioread32(mmio + XEON_SBAR5BASE_OFFSET);
+		dev_dbg(ndev_dev(ndev), "SBAR5 %#010llx\n", bar_addr);
+	}
+
+	/* setup incoming bar limits == base addrs (zero length windows) */
+
+	bar_addr = addr->bar2_addr64 + (b2b_bar == 2 ? ndev->b2b_off : 0);
+	iowrite64(bar_addr, mmio + XEON_SBAR23LMT_OFFSET);
+	bar_addr = ioread64(mmio + XEON_SBAR23LMT_OFFSET);
+	dev_dbg(ndev_dev(ndev), "SBAR23LMT %#018llx\n", bar_addr);
+
+	if (!ndev->bar4_split) {
+		bar_addr = addr->bar4_addr64 +
+			(b2b_bar == 4 ? ndev->b2b_off : 0);
+		iowrite64(bar_addr, mmio + XEON_SBAR45LMT_OFFSET);
+		bar_addr = ioread64(mmio + XEON_SBAR45LMT_OFFSET);
+		dev_dbg(ndev_dev(ndev), "SBAR45LMT %#018llx\n", bar_addr);
+	} else {
+		bar_addr = addr->bar4_addr32 +
+			(b2b_bar == 4 ? ndev->b2b_off : 0);
+		iowrite32(bar_addr, mmio + XEON_SBAR4LMT_OFFSET);
+		bar_addr = ioread32(mmio + XEON_SBAR4LMT_OFFSET);
+		dev_dbg(ndev_dev(ndev), "SBAR4LMT %#010llx\n", bar_addr);
+
+		bar_addr = addr->bar5_addr32 +
+			(b2b_bar == 5 ? ndev->b2b_off : 0);
+		iowrite32(bar_addr, mmio + XEON_SBAR5LMT_OFFSET);
+		bar_addr = ioread32(mmio + XEON_SBAR5LMT_OFFSET);
+		dev_dbg(ndev_dev(ndev), "SBAR5LMT %#05llx\n", bar_addr);
+	}
+
+	/* zero incoming translation addrs */
+	iowrite64(0, mmio + XEON_SBAR23XLAT_OFFSET);
+
+	if (!ndev->bar4_split) {
+		iowrite64(0, mmio + XEON_SBAR45XLAT_OFFSET);
+	} else {
+		iowrite32(0, mmio + XEON_SBAR4XLAT_OFFSET);
+		iowrite32(0, mmio + XEON_SBAR5XLAT_OFFSET);
+	}
+
+	/* zero outgoing translation limits (whole bar size windows) */
+	iowrite64(0, mmio + XEON_PBAR23LMT_OFFSET);
+	if (!ndev->bar4_split) {
+		iowrite64(0, mmio + XEON_PBAR45LMT_OFFSET);
+	} else {
+		iowrite32(0, mmio + XEON_PBAR4LMT_OFFSET);
+		iowrite32(0, mmio + XEON_PBAR5LMT_OFFSET);
+	}
+
+	/* set outgoing translation offsets */
+	bar_addr = peer_addr->bar2_addr64;
+	iowrite64(bar_addr, mmio + XEON_PBAR23XLAT_OFFSET);
+	bar_addr = ioread64(mmio + XEON_PBAR23XLAT_OFFSET);
+	dev_dbg(ndev_dev(ndev), "PBAR23XLAT %#018llx\n", bar_addr);
+
+	if (!ndev->bar4_split) {
+		bar_addr = peer_addr->bar4_addr64;
+		iowrite64(bar_addr, mmio + XEON_PBAR45XLAT_OFFSET);
+		bar_addr = ioread64(mmio + XEON_PBAR45XLAT_OFFSET);
+		dev_dbg(ndev_dev(ndev), "PBAR45XLAT %#018llx\n", bar_addr);
+	} else {
+		bar_addr = peer_addr->bar4_addr32;
+		iowrite32(bar_addr, mmio + XEON_PBAR4XLAT_OFFSET);
+		bar_addr = ioread32(mmio + XEON_PBAR4XLAT_OFFSET);
+		dev_dbg(ndev_dev(ndev), "PBAR4XLAT %#010llx\n", bar_addr);
+
+		bar_addr = peer_addr->bar5_addr32;
+		iowrite32(bar_addr, mmio + XEON_PBAR5XLAT_OFFSET);
+		bar_addr = ioread32(mmio + XEON_PBAR5XLAT_OFFSET);
+		dev_dbg(ndev_dev(ndev), "PBAR5XLAT %#010llx\n", bar_addr);
+	}
+
+	/* set the translation offset for b2b registers */
+	if (b2b_bar == 0)
+		bar_addr = peer_addr->bar0_addr;
+	else if (b2b_bar == 2)
+		bar_addr = peer_addr->bar2_addr64;
+	else if (b2b_bar == 4 && !ndev->bar4_split)
+		bar_addr = peer_addr->bar4_addr64;
+	else if (b2b_bar == 4)
+		bar_addr = peer_addr->bar4_addr32;
+	else if (b2b_bar == 5)
+		bar_addr = peer_addr->bar5_addr32;
+	else
+		return -EIO;
+
+	/* B2B_XLAT_OFFSET is 64bit, but can only take 32bit writes */
+	dev_dbg(ndev_dev(ndev), "B2BXLAT %#018llx\n", bar_addr);
+	iowrite32(bar_addr, mmio + XEON_B2B_XLAT_OFFSETL);
+	iowrite32(bar_addr >> 32, mmio + XEON_B2B_XLAT_OFFSETU);
+
+	if (b2b_bar) {
+		/* map peer ntb mmio config space registers */
+		ndev->peer_mmio = pci_iomap(pdev, b2b_bar,
+					    XEON_B2B_MIN_SIZE);
+		if (!ndev->peer_mmio)
+			return -EIO;
+	}
+
+	return 0;
+}
+
+static int xeon_init_ntb(struct intel_ntb_dev *ndev)
+{
+	int rc;
+	u32 ntb_ctl;
+
+	if (ndev->bar4_split)
+		ndev->mw_count = HSX_SPLIT_BAR_MW_COUNT;
+	else
+		ndev->mw_count = XEON_MW_COUNT;
+
+	ndev->spad_count = XEON_SPAD_COUNT;
+	ndev->db_count = XEON_DB_COUNT;
+	ndev->db_link_mask = XEON_DB_LINK_BIT;
+
+	switch (ndev->ntb.topo) {
+	case NTB_TOPO_PRI:
+		if (ndev->hwerr_flags & NTB_HWERR_SDOORBELL_LOCKUP) {
+			dev_err(ndev_dev(ndev), "NTB Primary config disabled\n");
+			return -EINVAL;
+		}
+
+		/* enable link to allow secondary side device to appear */
+		ntb_ctl = ioread32(ndev->self_mmio + ndev->reg->ntb_ctl);
+		ntb_ctl &= ~NTB_CTL_DISABLE;
+		iowrite32(ntb_ctl, ndev->self_mmio + ndev->reg->ntb_ctl);
+
+		/* use half the spads for the peer */
+		ndev->spad_count >>= 1;
+		ndev->self_reg = &xeon_pri_reg;
+		ndev->peer_reg = &xeon_sec_reg;
+		ndev->xlat_reg = &xeon_sec_xlat;
+		break;
+
+	case NTB_TOPO_SEC:
+		if (ndev->hwerr_flags & NTB_HWERR_SDOORBELL_LOCKUP) {
+			dev_err(ndev_dev(ndev), "NTB Secondary config disabled\n");
+			return -EINVAL;
+		}
+		/* use half the spads for the peer */
+		ndev->spad_count >>= 1;
+		ndev->self_reg = &xeon_sec_reg;
+		ndev->peer_reg = &xeon_pri_reg;
+		ndev->xlat_reg = &xeon_pri_xlat;
+		break;
+
+	case NTB_TOPO_B2B_USD:
+	case NTB_TOPO_B2B_DSD:
+		ndev->self_reg = &xeon_pri_reg;
+		ndev->peer_reg = &xeon_b2b_reg;
+		ndev->xlat_reg = &xeon_sec_xlat;
+
+		if (ndev->hwerr_flags & NTB_HWERR_SDOORBELL_LOCKUP) {
+			ndev->peer_reg = &xeon_pri_reg;
+
+			if (b2b_mw_idx < 0)
+				ndev->b2b_idx = b2b_mw_idx + ndev->mw_count;
+			else
+				ndev->b2b_idx = b2b_mw_idx;
+
+			dev_dbg(ndev_dev(ndev),
+				"setting up b2b mw idx %d means %d\n",
+				b2b_mw_idx, ndev->b2b_idx);
+
+		} else if (ndev->hwerr_flags & NTB_HWERR_B2BDOORBELL_BIT14) {
+			dev_warn(ndev_dev(ndev), "Reduce doorbell count by 1\n");
+			ndev->db_count -= 1;
+		}
+
+		if (ndev->ntb.topo == NTB_TOPO_B2B_USD) {
+			rc = xeon_setup_b2b_mw(ndev,
+					       &xeon_b2b_dsd_addr,
+					       &xeon_b2b_usd_addr);
+		} else {
+			rc = xeon_setup_b2b_mw(ndev,
+					       &xeon_b2b_usd_addr,
+					       &xeon_b2b_dsd_addr);
+		}
+		if (rc)
+			return rc;
+
+		/* Enable Bus Master and Memory Space on the secondary side */
+		iowrite16(PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER,
+			  ndev->self_mmio + XEON_SPCICMD_OFFSET);
+
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	ndev->db_valid_mask = BIT_ULL(ndev->db_count) - 1;
+
+	ndev->reg->db_iowrite(ndev->db_valid_mask,
+			      ndev->self_mmio +
+			      ndev->self_reg->db_mask);
+
+	return 0;
+}
+
+static int xeon_init_dev(struct intel_ntb_dev *ndev)
+{
+	struct pci_dev *pdev;
+	u8 ppd;
+	int rc, mem;
+
+	pdev = ndev_pdev(ndev);
+
+	switch (pdev->device) {
+	/* There is a Xeon hardware errata related to writes to SDOORBELL or
+	 * B2BDOORBELL in conjunction with inbound access to NTB MMIO Space,
+	 * which may hang the system.  To workaround this use the second memory
+	 * window to access the interrupt and scratch pad registers on the
+	 * remote system.
+	 */
+	case PCI_DEVICE_ID_INTEL_NTB_SS_JSF:
+	case PCI_DEVICE_ID_INTEL_NTB_PS_JSF:
+	case PCI_DEVICE_ID_INTEL_NTB_B2B_JSF:
+	case PCI_DEVICE_ID_INTEL_NTB_SS_SNB:
+	case PCI_DEVICE_ID_INTEL_NTB_PS_SNB:
+	case PCI_DEVICE_ID_INTEL_NTB_B2B_SNB:
+	case PCI_DEVICE_ID_INTEL_NTB_SS_IVT:
+	case PCI_DEVICE_ID_INTEL_NTB_PS_IVT:
+	case PCI_DEVICE_ID_INTEL_NTB_B2B_IVT:
+	case PCI_DEVICE_ID_INTEL_NTB_SS_HSX:
+	case PCI_DEVICE_ID_INTEL_NTB_PS_HSX:
+	case PCI_DEVICE_ID_INTEL_NTB_B2B_HSX:
+		ndev->hwerr_flags |= NTB_HWERR_SDOORBELL_LOCKUP;
+		break;
+	}
+
+	switch (pdev->device) {
+	/* There is a hardware errata related to accessing any register in
+	 * SB01BASE in the presence of bidirectional traffic crossing the NTB.
+	 */
+	case PCI_DEVICE_ID_INTEL_NTB_SS_IVT:
+	case PCI_DEVICE_ID_INTEL_NTB_PS_IVT:
+	case PCI_DEVICE_ID_INTEL_NTB_B2B_IVT:
+	case PCI_DEVICE_ID_INTEL_NTB_SS_HSX:
+	case PCI_DEVICE_ID_INTEL_NTB_PS_HSX:
+	case PCI_DEVICE_ID_INTEL_NTB_B2B_HSX:
+		ndev->hwerr_flags |= NTB_HWERR_SB01BASE_LOCKUP;
+		break;
+	}
+
+	switch (pdev->device) {
+	/* HW Errata on bit 14 of b2bdoorbell register.  Writes will not be
+	 * mirrored to the remote system.  Shrink the number of bits by one,
+	 * since bit 14 is the last bit.
+	 */
+	case PCI_DEVICE_ID_INTEL_NTB_SS_JSF:
+	case PCI_DEVICE_ID_INTEL_NTB_PS_JSF:
+	case PCI_DEVICE_ID_INTEL_NTB_B2B_JSF:
+	case PCI_DEVICE_ID_INTEL_NTB_SS_SNB:
+	case PCI_DEVICE_ID_INTEL_NTB_PS_SNB:
+	case PCI_DEVICE_ID_INTEL_NTB_B2B_SNB:
+	case PCI_DEVICE_ID_INTEL_NTB_SS_IVT:
+	case PCI_DEVICE_ID_INTEL_NTB_PS_IVT:
+	case PCI_DEVICE_ID_INTEL_NTB_B2B_IVT:
+	case PCI_DEVICE_ID_INTEL_NTB_SS_HSX:
+	case PCI_DEVICE_ID_INTEL_NTB_PS_HSX:
+	case PCI_DEVICE_ID_INTEL_NTB_B2B_HSX:
+		ndev->hwerr_flags |= NTB_HWERR_B2BDOORBELL_BIT14;
+		break;
+	}
+
+	ndev->reg = &xeon_reg;
+
+	rc = pci_read_config_byte(pdev, XEON_PPD_OFFSET, &ppd);
+	if (rc)
+		return -EIO;
+
+	ndev->ntb.topo = xeon_ppd_topo(ndev, ppd);
+	dev_dbg(ndev_dev(ndev), "ppd %#x topo %s\n", ppd,
+		ntb_topo_string(ndev->ntb.topo));
+	if (ndev->ntb.topo == NTB_TOPO_NONE)
+		return -EINVAL;
+
+	if (ndev->ntb.topo != NTB_TOPO_SEC) {
+		ndev->bar4_split = xeon_ppd_bar4_split(ndev, ppd);
+		dev_dbg(ndev_dev(ndev), "ppd %#x bar4_split %d\n",
+			ppd, ndev->bar4_split);
+	} else {
+		/* This is a way for transparent BAR to figure out if we are
+		 * doing split BAR or not. There is no way for the hw on the
+		 * transparent side to know and set the PPD.
+		 */
+		mem = pci_select_bars(pdev, IORESOURCE_MEM);
+		ndev->bar4_split = hweight32(mem) ==
+			HSX_SPLIT_BAR_MW_COUNT + 1;
+		dev_dbg(ndev_dev(ndev), "mem %#x bar4_split %d\n",
+			mem, ndev->bar4_split);
+	}
+
+	rc = xeon_init_ntb(ndev);
+	if (rc)
+		return rc;
+
+	return xeon_init_isr(ndev);
+}
+
+static void xeon_deinit_dev(struct intel_ntb_dev *ndev)
+{
+	xeon_deinit_isr(ndev);
+}
+
+static int intel_ntb_init_pci(struct intel_ntb_dev *ndev, struct pci_dev *pdev)
+{
+	int rc;
+
+	pci_set_drvdata(pdev, ndev);
+
+	rc = pci_enable_device(pdev);
+	if (rc)
+		goto err_pci_enable;
+
+	rc = pci_request_regions(pdev, NTB_NAME);
+	if (rc)
+		goto err_pci_regions;
+
+	pci_set_master(pdev);
+
+	rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+	if (rc) {
+		rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+		if (rc)
+			goto err_dma_mask;
+		dev_warn(ndev_dev(ndev), "Cannot DMA highmem\n");
+	}
+
+	rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+	if (rc) {
+		rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+		if (rc)
+			goto err_dma_mask;
+		dev_warn(ndev_dev(ndev), "Cannot DMA consistent highmem\n");
+	}
+
+	ndev->self_mmio = pci_iomap(pdev, 0, 0);
+	if (!ndev->self_mmio) {
+		rc = -EIO;
+		goto err_mmio;
+	}
+	ndev->peer_mmio = ndev->self_mmio;
+
+	return 0;
+
+err_mmio:
+err_dma_mask:
+	pci_clear_master(pdev);
+	pci_release_regions(pdev);
+err_pci_regions:
+	pci_disable_device(pdev);
+err_pci_enable:
+	pci_set_drvdata(pdev, NULL);
+	return rc;
+}
+
+static void intel_ntb_deinit_pci(struct intel_ntb_dev *ndev)
+{
+	struct pci_dev *pdev = ndev_pdev(ndev);
+
+	if (ndev->peer_mmio && ndev->peer_mmio != ndev->self_mmio)
+		pci_iounmap(pdev, ndev->peer_mmio);
+	pci_iounmap(pdev, ndev->self_mmio);
+
+	pci_clear_master(pdev);
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+	pci_set_drvdata(pdev, NULL);
+}
+
+static inline void ndev_init_struct(struct intel_ntb_dev *ndev,
+				    struct pci_dev *pdev)
+{
+	ndev->ntb.pdev = pdev;
+	ndev->ntb.topo = NTB_TOPO_NONE;
+	ndev->ntb.ops = &intel_ntb_ops;
+
+	ndev->b2b_off = 0;
+	ndev->b2b_idx = INT_MAX;
+
+	ndev->bar4_split = 0;
+
+	ndev->mw_count = 0;
+	ndev->spad_count = 0;
+	ndev->db_count = 0;
+	ndev->db_vec_count = 0;
+	ndev->db_vec_shift = 0;
+
+	ndev->ntb_ctl = 0;
+	ndev->lnk_sta = 0;
+
+	ndev->db_valid_mask = 0;
+	ndev->db_link_mask = 0;
+	ndev->db_mask = 0;
+
+	spin_lock_init(&ndev->db_mask_lock);
+}
+
+static int intel_ntb_pci_probe(struct pci_dev *pdev,
+			       const struct pci_device_id *id)
+{
+	struct intel_ntb_dev *ndev;
+	int rc, node;
+
+	node = dev_to_node(&pdev->dev);
+
+	if (pdev_is_atom(pdev)) {
+		ndev = kzalloc_node(sizeof(*ndev), GFP_KERNEL, node);
+		if (!ndev) {
+			rc = -ENOMEM;
+			goto err_ndev;
+		}
+
+		ndev_init_struct(ndev, pdev);
+
+		rc = intel_ntb_init_pci(ndev, pdev);
+		if (rc)
+			goto err_init_pci;
+
+		rc = atom_init_dev(ndev);
+		if (rc)
+			goto err_init_dev;
+
+	} else if (pdev_is_xeon(pdev)) {
+		ndev = kzalloc_node(sizeof(*ndev), GFP_KERNEL, node);
+		if (!ndev) {
+			rc = -ENOMEM;
+			goto err_ndev;
+		}
+
+		ndev_init_struct(ndev, pdev);
+
+		rc = intel_ntb_init_pci(ndev, pdev);
+		if (rc)
+			goto err_init_pci;
+
+		rc = xeon_init_dev(ndev);
+		if (rc)
+			goto err_init_dev;
+
+	} else {
+		rc = -EINVAL;
+		goto err_ndev;
+	}
+
+	ndev_reset_unsafe_flags(ndev);
+
+	ndev->reg->poll_link(ndev);
+
+	ndev_init_debugfs(ndev);
+
+	rc = ntb_register_device(&ndev->ntb);
+	if (rc)
+		goto err_register;
+
+	dev_info(&pdev->dev, "NTB device registered.\n");
+
+	return 0;
+
+err_register:
+	ndev_deinit_debugfs(ndev);
+	if (pdev_is_atom(pdev))
+		atom_deinit_dev(ndev);
+	else if (pdev_is_xeon(pdev))
+		xeon_deinit_dev(ndev);
+err_init_dev:
+	intel_ntb_deinit_pci(ndev);
+err_init_pci:
+	kfree(ndev);
+err_ndev:
+	return rc;
+}
+
+static void intel_ntb_pci_remove(struct pci_dev *pdev)
+{
+	struct intel_ntb_dev *ndev = pci_get_drvdata(pdev);
+
+	ntb_unregister_device(&ndev->ntb);
+	ndev_deinit_debugfs(ndev);
+	if (pdev_is_atom(pdev))
+		atom_deinit_dev(ndev);
+	else if (pdev_is_xeon(pdev))
+		xeon_deinit_dev(ndev);
+	intel_ntb_deinit_pci(ndev);
+	kfree(ndev);
+}
+
+static const struct intel_ntb_reg atom_reg = {
+	.poll_link		= atom_poll_link,
+	.link_is_up		= atom_link_is_up,
+	.db_ioread		= atom_db_ioread,
+	.db_iowrite		= atom_db_iowrite,
+	.db_size		= sizeof(u64),
+	.ntb_ctl		= ATOM_NTBCNTL_OFFSET,
+	.mw_bar			= {2, 4},
+};
+
+static const struct intel_ntb_alt_reg atom_pri_reg = {
+	.db_bell		= ATOM_PDOORBELL_OFFSET,
+	.db_mask		= ATOM_PDBMSK_OFFSET,
+	.spad			= ATOM_SPAD_OFFSET,
+};
+
+static const struct intel_ntb_alt_reg atom_b2b_reg = {
+	.db_bell		= ATOM_B2B_DOORBELL_OFFSET,
+	.spad			= ATOM_B2B_SPAD_OFFSET,
+};
+
+static const struct intel_ntb_xlat_reg atom_sec_xlat = {
+	/* FIXME : .bar0_base	= ATOM_SBAR0BASE_OFFSET, */
+	/* FIXME : .bar2_limit	= ATOM_SBAR2LMT_OFFSET, */
+	.bar2_xlat		= ATOM_SBAR2XLAT_OFFSET,
+};
+
+static const struct intel_ntb_reg xeon_reg = {
+	.poll_link		= xeon_poll_link,
+	.link_is_up		= xeon_link_is_up,
+	.db_ioread		= xeon_db_ioread,
+	.db_iowrite		= xeon_db_iowrite,
+	.db_size		= sizeof(u32),
+	.ntb_ctl		= XEON_NTBCNTL_OFFSET,
+	.mw_bar			= {2, 4, 5},
+};
+
+static const struct intel_ntb_alt_reg xeon_pri_reg = {
+	.db_bell		= XEON_PDOORBELL_OFFSET,
+	.db_mask		= XEON_PDBMSK_OFFSET,
+	.spad			= XEON_SPAD_OFFSET,
+};
+
+static const struct intel_ntb_alt_reg xeon_sec_reg = {
+	.db_bell		= XEON_SDOORBELL_OFFSET,
+	.db_mask		= XEON_SDBMSK_OFFSET,
+	/* second half of the scratchpads */
+	.spad			= XEON_SPAD_OFFSET + (XEON_SPAD_COUNT << 1),
+};
+
+static const struct intel_ntb_alt_reg xeon_b2b_reg = {
+	.db_bell		= XEON_B2B_DOORBELL_OFFSET,
+	.spad			= XEON_B2B_SPAD_OFFSET,
+};
+
+static const struct intel_ntb_xlat_reg xeon_pri_xlat = {
+	/* Note: no primary .bar0_base visible to the secondary side.
+	 *
+	 * The secondary side cannot get the base address stored in primary
+	 * bars.  The base address is necessary to set the limit register to
+	 * any value other than zero, or unlimited.
+	 *
+	 * WITHOUT THE BASE ADDRESS, THE SECONDARY SIDE CANNOT DISABLE the
+	 * window by setting the limit equal to base, nor can it limit the size
+	 * of the memory window by setting the limit to base + size.
+	 */
+	.bar2_limit		= XEON_PBAR23LMT_OFFSET,
+	.bar2_xlat		= XEON_PBAR23XLAT_OFFSET,
+};
+
+static const struct intel_ntb_xlat_reg xeon_sec_xlat = {
+	.bar0_base		= XEON_SBAR0BASE_OFFSET,
+	.bar2_limit		= XEON_SBAR23LMT_OFFSET,
+	.bar2_xlat		= XEON_SBAR23XLAT_OFFSET,
+};
+
+static struct intel_b2b_addr xeon_b2b_usd_addr = {
+	.bar2_addr64		= XEON_B2B_BAR2_USD_ADDR64,
+	.bar4_addr64		= XEON_B2B_BAR4_USD_ADDR64,
+	.bar4_addr32		= XEON_B2B_BAR4_USD_ADDR32,
+	.bar5_addr32		= XEON_B2B_BAR5_USD_ADDR32,
+};
+
+static struct intel_b2b_addr xeon_b2b_dsd_addr = {
+	.bar2_addr64		= XEON_B2B_BAR2_DSD_ADDR64,
+	.bar4_addr64		= XEON_B2B_BAR4_DSD_ADDR64,
+	.bar4_addr32		= XEON_B2B_BAR4_DSD_ADDR32,
+	.bar5_addr32		= XEON_B2B_BAR5_DSD_ADDR32,
+};
+
+/* operations for primary side of local ntb */
+static const struct ntb_dev_ops intel_ntb_ops = {
+	.mw_count		= intel_ntb_mw_count,
+	.mw_get_range		= intel_ntb_mw_get_range,
+	.mw_set_trans		= intel_ntb_mw_set_trans,
+	.link_is_up		= intel_ntb_link_is_up,
+	.link_enable		= intel_ntb_link_enable,
+	.link_disable		= intel_ntb_link_disable,
+	.db_is_unsafe		= intel_ntb_db_is_unsafe,
+	.db_valid_mask		= intel_ntb_db_valid_mask,
+	.db_vector_count	= intel_ntb_db_vector_count,
+	.db_vector_mask		= intel_ntb_db_vector_mask,
+	.db_read		= intel_ntb_db_read,
+	.db_clear		= intel_ntb_db_clear,
+	.db_set_mask		= intel_ntb_db_set_mask,
+	.db_clear_mask		= intel_ntb_db_clear_mask,
+	.peer_db_addr		= intel_ntb_peer_db_addr,
+	.peer_db_set		= intel_ntb_peer_db_set,
+	.spad_is_unsafe		= intel_ntb_spad_is_unsafe,
+	.spad_count		= intel_ntb_spad_count,
+	.spad_read		= intel_ntb_spad_read,
+	.spad_write		= intel_ntb_spad_write,
+	.peer_spad_addr		= intel_ntb_peer_spad_addr,
+	.peer_spad_read		= intel_ntb_peer_spad_read,
+	.peer_spad_write	= intel_ntb_peer_spad_write,
+};
+
+static const struct file_operations intel_ntb_debugfs_info = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.read = ndev_debugfs_read,
+};
+
+static const struct pci_device_id intel_ntb_pci_tbl[] = {
+	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_B2B_BWD)},
+	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_B2B_JSF)},
+	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_B2B_SNB)},
+	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_B2B_IVT)},
+	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_B2B_HSX)},
+	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_PS_JSF)},
+	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_PS_SNB)},
+	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_PS_IVT)},
+	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_PS_HSX)},
+	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_SS_JSF)},
+	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_SS_SNB)},
+	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_SS_IVT)},
+	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_SS_HSX)},
+	{0}
+};
+MODULE_DEVICE_TABLE(pci, intel_ntb_pci_tbl);
+
+static struct pci_driver intel_ntb_pci_driver = {
+	.name = KBUILD_MODNAME,
+	.id_table = intel_ntb_pci_tbl,
+	.probe = intel_ntb_pci_probe,
+	.remove = intel_ntb_pci_remove,
+};
+
+static int __init intel_ntb_pci_driver_init(void)
+{
+	pr_info("%s %s\n", NTB_DESC, NTB_VER);
+
+	if (debugfs_initialized())
+		debugfs_dir = debugfs_create_dir(KBUILD_MODNAME, NULL);
+
+	return pci_register_driver(&intel_ntb_pci_driver);
+}
+module_init(intel_ntb_pci_driver_init);
+
+static void __exit intel_ntb_pci_driver_exit(void)
+{
+	pci_unregister_driver(&intel_ntb_pci_driver);
+
+	debugfs_remove_recursive(debugfs_dir);
+}
+module_exit(intel_ntb_pci_driver_exit);
+
diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.h b/drivers/ntb/hw/intel/ntb_hw_intel.h
new file mode 100644
index 0000000..7ddaf38
--- /dev/null
+++ b/drivers/ntb/hw/intel/ntb_hw_intel.h
@@ -0,0 +1,342 @@
+/*
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ *   redistributing this file, you may do so under either license.
+ *
+ *   GPL LICENSE SUMMARY
+ *
+ *   Copyright(c) 2012 Intel Corporation. All rights reserved.
+ *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of version 2 of the GNU General Public License as
+ *   published by the Free Software Foundation.
+ *
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2012 Intel Corporation. All rights reserved.
+ *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copy
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of Intel Corporation nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * Intel PCIe NTB Linux driver
+ *
+ * Contact Information:
+ * Jon Mason <jon.mason@intel.com>
+ */
+
+#ifndef NTB_HW_INTEL_H
+#define NTB_HW_INTEL_H
+
+#include <linux/ntb.h>
+#include <linux/pci.h>
+
+#define PCI_DEVICE_ID_INTEL_NTB_B2B_JSF	0x3725
+#define PCI_DEVICE_ID_INTEL_NTB_PS_JSF	0x3726
+#define PCI_DEVICE_ID_INTEL_NTB_SS_JSF	0x3727
+#define PCI_DEVICE_ID_INTEL_NTB_B2B_SNB	0x3C0D
+#define PCI_DEVICE_ID_INTEL_NTB_PS_SNB	0x3C0E
+#define PCI_DEVICE_ID_INTEL_NTB_SS_SNB	0x3C0F
+#define PCI_DEVICE_ID_INTEL_NTB_B2B_IVT	0x0E0D
+#define PCI_DEVICE_ID_INTEL_NTB_PS_IVT	0x0E0E
+#define PCI_DEVICE_ID_INTEL_NTB_SS_IVT	0x0E0F
+#define PCI_DEVICE_ID_INTEL_NTB_B2B_HSX	0x2F0D
+#define PCI_DEVICE_ID_INTEL_NTB_PS_HSX	0x2F0E
+#define PCI_DEVICE_ID_INTEL_NTB_SS_HSX	0x2F0F
+#define PCI_DEVICE_ID_INTEL_NTB_B2B_BWD	0x0C4E
+
+/* Intel Xeon hardware */
+
+#define XEON_PBAR23LMT_OFFSET		0x0000
+#define XEON_PBAR45LMT_OFFSET		0x0008
+#define XEON_PBAR4LMT_OFFSET		0x0008
+#define XEON_PBAR5LMT_OFFSET		0x000c
+#define XEON_PBAR23XLAT_OFFSET		0x0010
+#define XEON_PBAR45XLAT_OFFSET		0x0018
+#define XEON_PBAR4XLAT_OFFSET		0x0018
+#define XEON_PBAR5XLAT_OFFSET		0x001c
+#define XEON_SBAR23LMT_OFFSET		0x0020
+#define XEON_SBAR45LMT_OFFSET		0x0028
+#define XEON_SBAR4LMT_OFFSET		0x0028
+#define XEON_SBAR5LMT_OFFSET		0x002c
+#define XEON_SBAR23XLAT_OFFSET		0x0030
+#define XEON_SBAR45XLAT_OFFSET		0x0038
+#define XEON_SBAR4XLAT_OFFSET		0x0038
+#define XEON_SBAR5XLAT_OFFSET		0x003c
+#define XEON_SBAR0BASE_OFFSET		0x0040
+#define XEON_SBAR23BASE_OFFSET		0x0048
+#define XEON_SBAR45BASE_OFFSET		0x0050
+#define XEON_SBAR4BASE_OFFSET		0x0050
+#define XEON_SBAR5BASE_OFFSET		0x0054
+#define XEON_SBDF_OFFSET		0x005c
+#define XEON_NTBCNTL_OFFSET		0x0058
+#define XEON_PDOORBELL_OFFSET		0x0060
+#define XEON_PDBMSK_OFFSET		0x0062
+#define XEON_SDOORBELL_OFFSET		0x0064
+#define XEON_SDBMSK_OFFSET		0x0066
+#define XEON_USMEMMISS_OFFSET		0x0070
+#define XEON_SPAD_OFFSET		0x0080
+#define XEON_PBAR23SZ_OFFSET		0x00d0
+#define XEON_PBAR45SZ_OFFSET		0x00d1
+#define XEON_PBAR4SZ_OFFSET		0x00d1
+#define XEON_SBAR23SZ_OFFSET		0x00d2
+#define XEON_SBAR45SZ_OFFSET		0x00d3
+#define XEON_SBAR4SZ_OFFSET		0x00d3
+#define XEON_PPD_OFFSET			0x00d4
+#define XEON_PBAR5SZ_OFFSET		0x00d5
+#define XEON_SBAR5SZ_OFFSET		0x00d6
+#define XEON_WCCNTRL_OFFSET		0x00e0
+#define XEON_UNCERRSTS_OFFSET		0x014c
+#define XEON_CORERRSTS_OFFSET		0x0158
+#define XEON_LINK_STATUS_OFFSET		0x01a2
+#define XEON_SPCICMD_OFFSET		0x0504
+#define XEON_DEVCTRL_OFFSET		0x0598
+#define XEON_DEVSTS_OFFSET		0x059a
+#define XEON_SLINK_STATUS_OFFSET	0x05a2
+#define XEON_B2B_SPAD_OFFSET		0x0100
+#define XEON_B2B_DOORBELL_OFFSET	0x0140
+#define XEON_B2B_XLAT_OFFSETL		0x0144
+#define XEON_B2B_XLAT_OFFSETU		0x0148
+#define XEON_PPD_CONN_MASK		0x03
+#define XEON_PPD_CONN_TRANSPARENT	0x00
+#define XEON_PPD_CONN_B2B		0x01
+#define XEON_PPD_CONN_RP		0x02
+#define XEON_PPD_DEV_MASK		0x10
+#define XEON_PPD_DEV_USD		0x00
+#define XEON_PPD_DEV_DSD		0x10
+#define XEON_PPD_SPLIT_BAR_MASK		0x40
+
+#define XEON_PPD_TOPO_MASK	(XEON_PPD_CONN_MASK | XEON_PPD_DEV_MASK)
+#define XEON_PPD_TOPO_PRI_USD	(XEON_PPD_CONN_RP | XEON_PPD_DEV_USD)
+#define XEON_PPD_TOPO_PRI_DSD	(XEON_PPD_CONN_RP | XEON_PPD_DEV_DSD)
+#define XEON_PPD_TOPO_SEC_USD	(XEON_PPD_CONN_TRANSPARENT | XEON_PPD_DEV_USD)
+#define XEON_PPD_TOPO_SEC_DSD	(XEON_PPD_CONN_TRANSPARENT | XEON_PPD_DEV_DSD)
+#define XEON_PPD_TOPO_B2B_USD	(XEON_PPD_CONN_B2B | XEON_PPD_DEV_USD)
+#define XEON_PPD_TOPO_B2B_DSD	(XEON_PPD_CONN_B2B | XEON_PPD_DEV_DSD)
+
+#define XEON_MW_COUNT			2
+#define HSX_SPLIT_BAR_MW_COUNT		3
+#define XEON_DB_COUNT			15
+#define XEON_DB_LINK			15
+#define XEON_DB_LINK_BIT			BIT_ULL(XEON_DB_LINK)
+#define XEON_DB_MSIX_VECTOR_COUNT	4
+#define XEON_DB_MSIX_VECTOR_SHIFT	5
+#define XEON_DB_TOTAL_SHIFT		16
+#define XEON_SPAD_COUNT			16
+
+/* Intel Atom hardware */
+
+#define ATOM_SBAR2XLAT_OFFSET		0x0008
+#define ATOM_PDOORBELL_OFFSET		0x0020
+#define ATOM_PDBMSK_OFFSET		0x0028
+#define ATOM_NTBCNTL_OFFSET		0x0060
+#define ATOM_SPAD_OFFSET			0x0080
+#define ATOM_PPD_OFFSET			0x00d4
+#define ATOM_PBAR2XLAT_OFFSET		0x8008
+#define ATOM_B2B_DOORBELL_OFFSET		0x8020
+#define ATOM_B2B_SPAD_OFFSET		0x8080
+#define ATOM_SPCICMD_OFFSET		0xb004
+#define ATOM_LINK_STATUS_OFFSET		0xb052
+#define ATOM_ERRCORSTS_OFFSET		0xb110
+#define ATOM_IP_BASE			0xc000
+#define ATOM_DESKEWSTS_OFFSET		(ATOM_IP_BASE + 0x3024)
+#define ATOM_LTSSMERRSTS0_OFFSET		(ATOM_IP_BASE + 0x3180)
+#define ATOM_LTSSMSTATEJMP_OFFSET	(ATOM_IP_BASE + 0x3040)
+#define ATOM_IBSTERRRCRVSTS0_OFFSET	(ATOM_IP_BASE + 0x3324)
+#define ATOM_MODPHY_PCSREG4		0x1c004
+#define ATOM_MODPHY_PCSREG6		0x1c006
+
+#define ATOM_PPD_INIT_LINK		0x0008
+#define ATOM_PPD_CONN_MASK		0x0300
+#define ATOM_PPD_CONN_TRANSPARENT	0x0000
+#define ATOM_PPD_CONN_B2B		0x0100
+#define ATOM_PPD_CONN_RP			0x0200
+#define ATOM_PPD_DEV_MASK		0x1000
+#define ATOM_PPD_DEV_USD			0x0000
+#define ATOM_PPD_DEV_DSD			0x1000
+#define ATOM_PPD_TOPO_MASK	(ATOM_PPD_CONN_MASK | ATOM_PPD_DEV_MASK)
+#define ATOM_PPD_TOPO_PRI_USD	(ATOM_PPD_CONN_TRANSPARENT | ATOM_PPD_DEV_USD)
+#define ATOM_PPD_TOPO_PRI_DSD	(ATOM_PPD_CONN_TRANSPARENT | ATOM_PPD_DEV_DSD)
+#define ATOM_PPD_TOPO_SEC_USD	(ATOM_PPD_CONN_RP | ATOM_PPD_DEV_USD)
+#define ATOM_PPD_TOPO_SEC_DSD	(ATOM_PPD_CONN_RP | ATOM_PPD_DEV_DSD)
+#define ATOM_PPD_TOPO_B2B_USD	(ATOM_PPD_CONN_B2B | ATOM_PPD_DEV_USD)
+#define ATOM_PPD_TOPO_B2B_DSD	(ATOM_PPD_CONN_B2B | ATOM_PPD_DEV_DSD)
+
+#define ATOM_MW_COUNT			2
+#define ATOM_DB_COUNT			34
+#define ATOM_DB_VALID_MASK		(BIT_ULL(ATOM_DB_COUNT) - 1)
+#define ATOM_DB_MSIX_VECTOR_COUNT	34
+#define ATOM_DB_MSIX_VECTOR_SHIFT	1
+#define ATOM_DB_TOTAL_SHIFT		34
+#define ATOM_SPAD_COUNT			16
+
+#define ATOM_NTB_CTL_DOWN_BIT		BIT(16)
+#define ATOM_NTB_CTL_ACTIVE(x)		!(x & ATOM_NTB_CTL_DOWN_BIT)
+
+#define ATOM_DESKEWSTS_DBERR		BIT(15)
+#define ATOM_LTSSMERRSTS0_UNEXPECTEDEI	BIT(20)
+#define ATOM_LTSSMSTATEJMP_FORCEDETECT	BIT(2)
+#define ATOM_IBIST_ERR_OFLOW		0x7FFF7FFF
+
+#define ATOM_LINK_HB_TIMEOUT		msecs_to_jiffies(1000)
+#define ATOM_LINK_RECOVERY_TIME		msecs_to_jiffies(500)
+
+/* Ntb control and link status */
+
+#define NTB_CTL_CFG_LOCK		BIT(0)
+#define NTB_CTL_DISABLE			BIT(1)
+#define NTB_CTL_S2P_BAR2_SNOOP		BIT(2)
+#define NTB_CTL_P2S_BAR2_SNOOP		BIT(4)
+#define NTB_CTL_S2P_BAR4_SNOOP		BIT(6)
+#define NTB_CTL_P2S_BAR4_SNOOP		BIT(8)
+#define NTB_CTL_S2P_BAR5_SNOOP		BIT(12)
+#define NTB_CTL_P2S_BAR5_SNOOP		BIT(14)
+
+#define NTB_LNK_STA_ACTIVE_BIT		0x2000
+#define NTB_LNK_STA_SPEED_MASK		0x000f
+#define NTB_LNK_STA_WIDTH_MASK		0x03f0
+#define NTB_LNK_STA_ACTIVE(x)		(!!((x) & NTB_LNK_STA_ACTIVE_BIT))
+#define NTB_LNK_STA_SPEED(x)		((x) & NTB_LNK_STA_SPEED_MASK)
+#define NTB_LNK_STA_WIDTH(x)		(((x) & NTB_LNK_STA_WIDTH_MASK) >> 4)
+
+/* Use the following addresses for translation between b2b ntb devices in case
+ * the hardware default values are not reliable. */
+#define XEON_B2B_BAR0_USD_ADDR		0x1000000000000000ull
+#define XEON_B2B_BAR2_USD_ADDR64	0x2000000000000000ull
+#define XEON_B2B_BAR4_USD_ADDR64	0x4000000000000000ull
+#define XEON_B2B_BAR4_USD_ADDR32	0x20000000u
+#define XEON_B2B_BAR5_USD_ADDR32	0x40000000u
+#define XEON_B2B_BAR0_DSD_ADDR		0x9000000000000000ull
+#define XEON_B2B_BAR2_DSD_ADDR64	0xa000000000000000ull
+#define XEON_B2B_BAR4_DSD_ADDR64	0xc000000000000000ull
+#define XEON_B2B_BAR4_DSD_ADDR32	0xa0000000u
+#define XEON_B2B_BAR5_DSD_ADDR32	0xc0000000u
+
+/* The peer ntb secondary config space is 32KB fixed size */
+#define XEON_B2B_MIN_SIZE		0x8000
+
+/* flags to indicate hardware errata */
+#define NTB_HWERR_SDOORBELL_LOCKUP	BIT_ULL(0)
+#define NTB_HWERR_SB01BASE_LOCKUP	BIT_ULL(1)
+#define NTB_HWERR_B2BDOORBELL_BIT14	BIT_ULL(2)
+
+/* flags to indicate unsafe api */
+#define NTB_UNSAFE_DB			BIT_ULL(0)
+#define NTB_UNSAFE_SPAD			BIT_ULL(1)
+
+struct intel_ntb_dev;
+
+struct intel_ntb_reg {
+	int (*poll_link)(struct intel_ntb_dev *ndev);
+	int (*link_is_up)(struct intel_ntb_dev *ndev);
+	u64 (*db_ioread)(void __iomem *mmio);
+	void (*db_iowrite)(u64 db_bits, void __iomem *mmio);
+	unsigned long			ntb_ctl;
+	resource_size_t			db_size;
+	int				mw_bar[];
+};
+
+struct intel_ntb_alt_reg {
+	unsigned long			db_bell;
+	unsigned long			db_mask;
+	unsigned long			spad;
+};
+
+struct intel_ntb_xlat_reg {
+	unsigned long			bar0_base;
+	unsigned long			bar2_xlat;
+	unsigned long			bar2_limit;
+};
+
+struct intel_b2b_addr {
+	phys_addr_t			bar0_addr;
+	phys_addr_t			bar2_addr64;
+	phys_addr_t			bar4_addr64;
+	phys_addr_t			bar4_addr32;
+	phys_addr_t			bar5_addr32;
+};
+
+struct intel_ntb_vec {
+	struct intel_ntb_dev		*ndev;
+	int				num;
+};
+
+struct intel_ntb_dev {
+	struct ntb_dev			ntb;
+
+	/* offset of peer bar0 in b2b bar */
+	unsigned long			b2b_off;
+	/* mw idx used to access peer bar0 */
+	unsigned int			b2b_idx;
+
+	/* BAR45 is split into BAR4 and BAR5 */
+	bool				bar4_split;
+
+	u32				ntb_ctl;
+	u32				lnk_sta;
+
+	unsigned char			mw_count;
+	unsigned char			spad_count;
+	unsigned char			db_count;
+	unsigned char			db_vec_count;
+	unsigned char			db_vec_shift;
+
+	u64				db_valid_mask;
+	u64				db_link_mask;
+	u64				db_mask;
+
+	/* synchronize rmw access of db_mask and hw reg */
+	spinlock_t			db_mask_lock;
+
+	struct msix_entry		*msix;
+	struct intel_ntb_vec		*vec;
+
+	const struct intel_ntb_reg	*reg;
+	const struct intel_ntb_alt_reg	*self_reg;
+	const struct intel_ntb_alt_reg	*peer_reg;
+	const struct intel_ntb_xlat_reg	*xlat_reg;
+	void				__iomem *self_mmio;
+	void				__iomem *peer_mmio;
+	phys_addr_t			peer_addr;
+
+	unsigned long			last_ts;
+	struct delayed_work		hb_timer;
+
+	unsigned long			hwerr_flags;
+	unsigned long			unsafe_flags;
+	unsigned long			unsafe_flags_ignore;
+
+	struct dentry			*debugfs_dir;
+	struct dentry			*debugfs_info;
+};
+
+#define ndev_pdev(ndev) ((ndev)->ntb.pdev)
+#define ndev_name(ndev) pci_name(ndev_pdev(ndev))
+#define ndev_dev(ndev) (&ndev_pdev(ndev)->dev)
+#define ntb_ndev(ntb) container_of(ntb, struct intel_ntb_dev, ntb)
+#define hb_ndev(work) container_of(work, struct intel_ntb_dev, hb_timer.work)
+
+#endif
diff --git a/drivers/ntb/ntb.c b/drivers/ntb/ntb.c
new file mode 100644
index 0000000..23435f2
--- /dev/null
+++ b/drivers/ntb/ntb.c
@@ -0,0 +1,251 @@
+/*
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ *   redistributing this file, you may do so under either license.
+ *
+ *   GPL LICENSE SUMMARY
+ *
+ *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of version 2 of the GNU General Public License as
+ *   published by the Free Software Foundation.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *   General Public License for more details.
+ *
+ *   BSD LICENSE
+ *
+ *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copy
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of Intel Corporation nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * PCIe NTB Linux driver
+ *
+ * Contact Information:
+ * Allen Hubbe <Allen.Hubbe@emc.com>
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <linux/ntb.h>
+#include <linux/pci.h>
+
+#define DRIVER_NAME			"ntb"
+#define DRIVER_DESCRIPTION		"PCIe NTB Driver Framework"
+
+#define DRIVER_LICENSE			"Dual BSD/GPL"
+#define DRIVER_VERSION			"1.0"
+#define DRIVER_RELDATE			"24 March 2015"
+#define DRIVER_AUTHOR			"Allen Hubbe <Allen.Hubbe@emc.com>"
+
+MODULE_LICENSE(DRIVER_LICENSE);
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESCRIPTION);
+
+static struct bus_type ntb_bus;
+static void ntb_dev_release(struct device *dev);
+
+int __ntb_register_client(struct ntb_client *client, struct module *mod,
+			  const char *mod_name)
+{
+	if (!client)
+		return -EINVAL;
+	if (!ntb_client_ops_is_valid(&client->ops))
+		return -EINVAL;
+
+	memset(&client->drv, 0, sizeof(client->drv));
+	client->drv.bus = &ntb_bus;
+	client->drv.name = mod_name;
+	client->drv.owner = mod;
+
+	return driver_register(&client->drv);
+}
+EXPORT_SYMBOL(__ntb_register_client);
+
+void ntb_unregister_client(struct ntb_client *client)
+{
+	driver_unregister(&client->drv);
+}
+EXPORT_SYMBOL(ntb_unregister_client);
+
+int ntb_register_device(struct ntb_dev *ntb)
+{
+	if (!ntb)
+		return -EINVAL;
+	if (!ntb->pdev)
+		return -EINVAL;
+	if (!ntb->ops)
+		return -EINVAL;
+	if (!ntb_dev_ops_is_valid(ntb->ops))
+		return -EINVAL;
+
+	init_completion(&ntb->released);
+
+	memset(&ntb->dev, 0, sizeof(ntb->dev));
+	ntb->dev.bus = &ntb_bus;
+	ntb->dev.parent = &ntb->pdev->dev;
+	ntb->dev.release = ntb_dev_release;
+	dev_set_name(&ntb->dev, pci_name(ntb->pdev));
+
+	ntb->ctx = NULL;
+	ntb->ctx_ops = NULL;
+	spin_lock_init(&ntb->ctx_lock);
+
+	return device_register(&ntb->dev);
+}
+EXPORT_SYMBOL(ntb_register_device);
+
+void ntb_unregister_device(struct ntb_dev *ntb)
+{
+	device_unregister(&ntb->dev);
+	wait_for_completion(&ntb->released);
+}
+EXPORT_SYMBOL(ntb_unregister_device);
+
+int ntb_set_ctx(struct ntb_dev *ntb, void *ctx,
+		const struct ntb_ctx_ops *ctx_ops)
+{
+	unsigned long irqflags;
+
+	if (!ntb_ctx_ops_is_valid(ctx_ops))
+		return -EINVAL;
+	if (ntb->ctx_ops)
+		return -EINVAL;
+
+	spin_lock_irqsave(&ntb->ctx_lock, irqflags);
+	{
+		ntb->ctx = ctx;
+		ntb->ctx_ops = ctx_ops;
+	}
+	spin_unlock_irqrestore(&ntb->ctx_lock, irqflags);
+
+	return 0;
+}
+EXPORT_SYMBOL(ntb_set_ctx);
+
+void ntb_clear_ctx(struct ntb_dev *ntb)
+{
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&ntb->ctx_lock, irqflags);
+	{
+		ntb->ctx_ops = NULL;
+		ntb->ctx = NULL;
+	}
+	spin_unlock_irqrestore(&ntb->ctx_lock, irqflags);
+}
+EXPORT_SYMBOL(ntb_clear_ctx);
+
+void ntb_link_event(struct ntb_dev *ntb)
+{
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&ntb->ctx_lock, irqflags);
+	{
+		if (ntb->ctx_ops && ntb->ctx_ops->link_event)
+			ntb->ctx_ops->link_event(ntb->ctx);
+	}
+	spin_unlock_irqrestore(&ntb->ctx_lock, irqflags);
+}
+EXPORT_SYMBOL(ntb_link_event);
+
+void ntb_db_event(struct ntb_dev *ntb, int vector)
+{
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&ntb->ctx_lock, irqflags);
+	{
+		if (ntb->ctx_ops && ntb->ctx_ops->db_event)
+			ntb->ctx_ops->db_event(ntb->ctx, vector);
+	}
+	spin_unlock_irqrestore(&ntb->ctx_lock, irqflags);
+}
+EXPORT_SYMBOL(ntb_db_event);
+
+static int ntb_probe(struct device *dev)
+{
+	struct ntb_dev *ntb;
+	struct ntb_client *client;
+	int rc;
+
+	get_device(dev);
+	ntb = dev_ntb(dev);
+	client = drv_ntb_client(dev->driver);
+
+	rc = client->ops.probe(client, ntb);
+	if (rc)
+		put_device(dev);
+
+	return rc;
+}
+
+static int ntb_remove(struct device *dev)
+{
+	struct ntb_dev *ntb;
+	struct ntb_client *client;
+
+	if (dev->driver) {
+		ntb = dev_ntb(dev);
+		client = drv_ntb_client(dev->driver);
+
+		client->ops.remove(client, ntb);
+		put_device(dev);
+	}
+
+	return 0;
+}
+
+static void ntb_dev_release(struct device *dev)
+{
+	struct ntb_dev *ntb = dev_ntb(dev);
+
+	complete(&ntb->released);
+}
+
+static struct bus_type ntb_bus = {
+	.name = "ntb",
+	.probe = ntb_probe,
+	.remove = ntb_remove,
+};
+
+static int __init ntb_driver_init(void)
+{
+	return bus_register(&ntb_bus);
+}
+module_init(ntb_driver_init);
+
+static void __exit ntb_driver_exit(void)
+{
+	bus_unregister(&ntb_bus);
+}
+module_exit(ntb_driver_exit);
+
diff --git a/drivers/ntb/ntb_hw.c b/drivers/ntb/ntb_hw.c
deleted file mode 100644
index 3f67386..0000000
--- a/drivers/ntb/ntb_hw.c
+++ /dev/null
@@ -1,1895 +0,0 @@
-/*
- * This file is provided under a dual BSD/GPLv2 license.  When using or
- *   redistributing this file, you may do so under either license.
- *
- *   GPL LICENSE SUMMARY
- *
- *   Copyright(c) 2012 Intel Corporation. All rights reserved.
- *
- *   This program is free software; you can redistribute it and/or modify
- *   it under the terms of version 2 of the GNU General Public License as
- *   published by the Free Software Foundation.
- *
- *   BSD LICENSE
- *
- *   Copyright(c) 2012 Intel Corporation. All rights reserved.
- *
- *   Redistribution and use in source and binary forms, with or without
- *   modification, are permitted provided that the following conditions
- *   are met:
- *
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copy
- *       notice, this list of conditions and the following disclaimer in
- *       the documentation and/or other materials provided with the
- *       distribution.
- *     * Neither the name of Intel Corporation nor the names of its
- *       contributors may be used to endorse or promote products derived
- *       from this software without specific prior written permission.
- *
- *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * Intel PCIe NTB Linux driver
- *
- * Contact Information:
- * Jon Mason <jon.mason@intel.com>
- */
-#include <linux/debugfs.h>
-#include <linux/delay.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/random.h>
-#include <linux/slab.h>
-#include "ntb_hw.h"
-#include "ntb_regs.h"
-
-#define NTB_NAME	"Intel(R) PCI-E Non-Transparent Bridge Driver"
-#define NTB_VER		"1.0"
-
-MODULE_DESCRIPTION(NTB_NAME);
-MODULE_VERSION(NTB_VER);
-MODULE_LICENSE("Dual BSD/GPL");
-MODULE_AUTHOR("Intel Corporation");
-
-enum {
-	NTB_CONN_TRANSPARENT = 0,
-	NTB_CONN_B2B,
-	NTB_CONN_RP,
-};
-
-enum {
-	NTB_DEV_USD = 0,
-	NTB_DEV_DSD,
-};
-
-enum {
-	SNB_HW = 0,
-	BWD_HW,
-};
-
-static struct dentry *debugfs_dir;
-
-#define BWD_LINK_RECOVERY_TIME	500
-
-/* Translate memory window 0,1,2 to BAR 2,4,5 */
-#define MW_TO_BAR(mw)	(mw == 0 ? 2 : (mw == 1 ? 4 : 5))
-
-static const struct pci_device_id ntb_pci_tbl[] = {
-	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_B2B_BWD)},
-	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_B2B_JSF)},
-	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_B2B_SNB)},
-	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_B2B_IVT)},
-	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_B2B_HSX)},
-	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_PS_JSF)},
-	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_PS_SNB)},
-	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_PS_IVT)},
-	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_PS_HSX)},
-	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_SS_JSF)},
-	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_SS_SNB)},
-	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_SS_IVT)},
-	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_SS_HSX)},
-	{0}
-};
-MODULE_DEVICE_TABLE(pci, ntb_pci_tbl);
-
-static int is_ntb_xeon(struct ntb_device *ndev)
-{
-	switch (ndev->pdev->device) {
-	case PCI_DEVICE_ID_INTEL_NTB_SS_JSF:
-	case PCI_DEVICE_ID_INTEL_NTB_SS_SNB:
-	case PCI_DEVICE_ID_INTEL_NTB_SS_IVT:
-	case PCI_DEVICE_ID_INTEL_NTB_SS_HSX:
-	case PCI_DEVICE_ID_INTEL_NTB_PS_JSF:
-	case PCI_DEVICE_ID_INTEL_NTB_PS_SNB:
-	case PCI_DEVICE_ID_INTEL_NTB_PS_IVT:
-	case PCI_DEVICE_ID_INTEL_NTB_PS_HSX:
-	case PCI_DEVICE_ID_INTEL_NTB_B2B_JSF:
-	case PCI_DEVICE_ID_INTEL_NTB_B2B_SNB:
-	case PCI_DEVICE_ID_INTEL_NTB_B2B_IVT:
-	case PCI_DEVICE_ID_INTEL_NTB_B2B_HSX:
-		return 1;
-	default:
-		return 0;
-	}
-
-	return 0;
-}
-
-static int is_ntb_atom(struct ntb_device *ndev)
-{
-	switch (ndev->pdev->device) {
-	case PCI_DEVICE_ID_INTEL_NTB_B2B_BWD:
-		return 1;
-	default:
-		return 0;
-	}
-
-	return 0;
-}
-
-static void ntb_set_errata_flags(struct ntb_device *ndev)
-{
-	switch (ndev->pdev->device) {
-	/*
-	 * this workaround applies to all platform up to IvyBridge
-	 * Haswell has splitbar support and use a different workaround
-	 */
-	case PCI_DEVICE_ID_INTEL_NTB_SS_JSF:
-	case PCI_DEVICE_ID_INTEL_NTB_SS_SNB:
-	case PCI_DEVICE_ID_INTEL_NTB_SS_IVT:
-	case PCI_DEVICE_ID_INTEL_NTB_SS_HSX:
-	case PCI_DEVICE_ID_INTEL_NTB_PS_JSF:
-	case PCI_DEVICE_ID_INTEL_NTB_PS_SNB:
-	case PCI_DEVICE_ID_INTEL_NTB_PS_IVT:
-	case PCI_DEVICE_ID_INTEL_NTB_PS_HSX:
-	case PCI_DEVICE_ID_INTEL_NTB_B2B_JSF:
-	case PCI_DEVICE_ID_INTEL_NTB_B2B_SNB:
-	case PCI_DEVICE_ID_INTEL_NTB_B2B_IVT:
-	case PCI_DEVICE_ID_INTEL_NTB_B2B_HSX:
-		ndev->wa_flags |= WA_SNB_ERR;
-		break;
-	}
-}
-
-/**
- * ntb_register_event_callback() - register event callback
- * @ndev: pointer to ntb_device instance
- * @func: callback function to register
- *
- * This function registers a callback for any HW driver events such as link
- * up/down, power management notices and etc.
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-int ntb_register_event_callback(struct ntb_device *ndev,
-				void (*func)(void *handle,
-					     enum ntb_hw_event event))
-{
-	if (ndev->event_cb)
-		return -EINVAL;
-
-	ndev->event_cb = func;
-
-	return 0;
-}
-
-/**
- * ntb_unregister_event_callback() - unregisters the event callback
- * @ndev: pointer to ntb_device instance
- *
- * This function unregisters the existing callback from transport
- */
-void ntb_unregister_event_callback(struct ntb_device *ndev)
-{
-	ndev->event_cb = NULL;
-}
-
-static void ntb_irq_work(unsigned long data)
-{
-	struct ntb_db_cb *db_cb = (struct ntb_db_cb *)data;
-	int rc;
-
-	rc = db_cb->callback(db_cb->data, db_cb->db_num);
-	if (rc)
-		tasklet_schedule(&db_cb->irq_work);
-	else {
-		struct ntb_device *ndev = db_cb->ndev;
-		unsigned long mask;
-
-		mask = readw(ndev->reg_ofs.ldb_mask);
-		clear_bit(db_cb->db_num * ndev->bits_per_vector, &mask);
-		writew(mask, ndev->reg_ofs.ldb_mask);
-	}
-}
-
-/**
- * ntb_register_db_callback() - register a callback for doorbell interrupt
- * @ndev: pointer to ntb_device instance
- * @idx: doorbell index to register callback, zero based
- * @data: pointer to be returned to caller with every callback
- * @func: callback function to register
- *
- * This function registers a callback function for the doorbell interrupt
- * on the primary side. The function will unmask the doorbell as well to
- * allow interrupt.
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-int ntb_register_db_callback(struct ntb_device *ndev, unsigned int idx,
-			     void *data, int (*func)(void *data, int db_num))
-{
-	unsigned long mask;
-
-	if (idx >= ndev->max_cbs || ndev->db_cb[idx].callback) {
-		dev_warn(&ndev->pdev->dev, "Invalid Index.\n");
-		return -EINVAL;
-	}
-
-	ndev->db_cb[idx].callback = func;
-	ndev->db_cb[idx].data = data;
-	ndev->db_cb[idx].ndev = ndev;
-
-	tasklet_init(&ndev->db_cb[idx].irq_work, ntb_irq_work,
-		     (unsigned long) &ndev->db_cb[idx]);
-
-	/* unmask interrupt */
-	mask = readw(ndev->reg_ofs.ldb_mask);
-	clear_bit(idx * ndev->bits_per_vector, &mask);
-	writew(mask, ndev->reg_ofs.ldb_mask);
-
-	return 0;
-}
-
-/**
- * ntb_unregister_db_callback() - unregister a callback for doorbell interrupt
- * @ndev: pointer to ntb_device instance
- * @idx: doorbell index to register callback, zero based
- *
- * This function unregisters a callback function for the doorbell interrupt
- * on the primary side. The function will also mask the said doorbell.
- */
-void ntb_unregister_db_callback(struct ntb_device *ndev, unsigned int idx)
-{
-	unsigned long mask;
-
-	if (idx >= ndev->max_cbs || !ndev->db_cb[idx].callback)
-		return;
-
-	mask = readw(ndev->reg_ofs.ldb_mask);
-	set_bit(idx * ndev->bits_per_vector, &mask);
-	writew(mask, ndev->reg_ofs.ldb_mask);
-
-	tasklet_disable(&ndev->db_cb[idx].irq_work);
-
-	ndev->db_cb[idx].callback = NULL;
-}
-
-/**
- * ntb_find_transport() - find the transport pointer
- * @transport: pointer to pci device
- *
- * Given the pci device pointer, return the transport pointer passed in when
- * the transport attached when it was inited.
- *
- * RETURNS: pointer to transport.
- */
-void *ntb_find_transport(struct pci_dev *pdev)
-{
-	struct ntb_device *ndev = pci_get_drvdata(pdev);
-	return ndev->ntb_transport;
-}
-
-/**
- * ntb_register_transport() - Register NTB transport with NTB HW driver
- * @transport: transport identifier
- *
- * This function allows a transport to reserve the hardware driver for
- * NTB usage.
- *
- * RETURNS: pointer to ntb_device, NULL on error.
- */
-struct ntb_device *ntb_register_transport(struct pci_dev *pdev, void *transport)
-{
-	struct ntb_device *ndev = pci_get_drvdata(pdev);
-
-	if (ndev->ntb_transport)
-		return NULL;
-
-	ndev->ntb_transport = transport;
-	return ndev;
-}
-
-/**
- * ntb_unregister_transport() - Unregister the transport with the NTB HW driver
- * @ndev - ntb_device of the transport to be freed
- *
- * This function unregisters the transport from the HW driver and performs any
- * necessary cleanups.
- */
-void ntb_unregister_transport(struct ntb_device *ndev)
-{
-	int i;
-
-	if (!ndev->ntb_transport)
-		return;
-
-	for (i = 0; i < ndev->max_cbs; i++)
-		ntb_unregister_db_callback(ndev, i);
-
-	ntb_unregister_event_callback(ndev);
-	ndev->ntb_transport = NULL;
-}
-
-/**
- * ntb_write_local_spad() - write to the secondary scratchpad register
- * @ndev: pointer to ntb_device instance
- * @idx: index to the scratchpad register, 0 based
- * @val: the data value to put into the register
- *
- * This function allows writing of a 32bit value to the indexed scratchpad
- * register. This writes over the data mirrored to the local scratchpad register
- * by the remote system.
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-int ntb_write_local_spad(struct ntb_device *ndev, unsigned int idx, u32 val)
-{
-	if (idx >= ndev->limits.max_spads)
-		return -EINVAL;
-
-	dev_dbg(&ndev->pdev->dev, "Writing %x to local scratch pad index %d\n",
-		val, idx);
-	writel(val, ndev->reg_ofs.spad_read + idx * 4);
-
-	return 0;
-}
-
-/**
- * ntb_read_local_spad() - read from the primary scratchpad register
- * @ndev: pointer to ntb_device instance
- * @idx: index to scratchpad register, 0 based
- * @val: pointer to 32bit integer for storing the register value
- *
- * This function allows reading of the 32bit scratchpad register on
- * the primary (internal) side.  This allows the local system to read data
- * written and mirrored to the scratchpad register by the remote system.
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-int ntb_read_local_spad(struct ntb_device *ndev, unsigned int idx, u32 *val)
-{
-	if (idx >= ndev->limits.max_spads)
-		return -EINVAL;
-
-	*val = readl(ndev->reg_ofs.spad_write + idx * 4);
-	dev_dbg(&ndev->pdev->dev,
-		"Reading %x from local scratch pad index %d\n", *val, idx);
-
-	return 0;
-}
-
-/**
- * ntb_write_remote_spad() - write to the secondary scratchpad register
- * @ndev: pointer to ntb_device instance
- * @idx: index to the scratchpad register, 0 based
- * @val: the data value to put into the register
- *
- * This function allows writing of a 32bit value to the indexed scratchpad
- * register. The register resides on the secondary (external) side.  This allows
- * the local system to write data to be mirrored to the remote systems
- * scratchpad register.
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-int ntb_write_remote_spad(struct ntb_device *ndev, unsigned int idx, u32 val)
-{
-	if (idx >= ndev->limits.max_spads)
-		return -EINVAL;
-
-	dev_dbg(&ndev->pdev->dev, "Writing %x to remote scratch pad index %d\n",
-		val, idx);
-	writel(val, ndev->reg_ofs.spad_write + idx * 4);
-
-	return 0;
-}
-
-/**
- * ntb_read_remote_spad() - read from the primary scratchpad register
- * @ndev: pointer to ntb_device instance
- * @idx: index to scratchpad register, 0 based
- * @val: pointer to 32bit integer for storing the register value
- *
- * This function allows reading of the 32bit scratchpad register on
- * the primary (internal) side.  This alloows the local system to read the data
- * it wrote to be mirrored on the remote system.
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-int ntb_read_remote_spad(struct ntb_device *ndev, unsigned int idx, u32 *val)
-{
-	if (idx >= ndev->limits.max_spads)
-		return -EINVAL;
-
-	*val = readl(ndev->reg_ofs.spad_read + idx * 4);
-	dev_dbg(&ndev->pdev->dev,
-		"Reading %x from remote scratch pad index %d\n", *val, idx);
-
-	return 0;
-}
-
-/**
- * ntb_get_mw_base() - get addr for the NTB memory window
- * @ndev: pointer to ntb_device instance
- * @mw: memory window number
- *
- * This function provides the base address of the memory window specified.
- *
- * RETURNS: address, or NULL on error.
- */
-resource_size_t ntb_get_mw_base(struct ntb_device *ndev, unsigned int mw)
-{
-	if (mw >= ntb_max_mw(ndev))
-		return 0;
-
-	return pci_resource_start(ndev->pdev, MW_TO_BAR(mw));
-}
-
-/**
- * ntb_get_mw_vbase() - get virtual addr for the NTB memory window
- * @ndev: pointer to ntb_device instance
- * @mw: memory window number
- *
- * This function provides the base virtual address of the memory window
- * specified.
- *
- * RETURNS: pointer to virtual address, or NULL on error.
- */
-void __iomem *ntb_get_mw_vbase(struct ntb_device *ndev, unsigned int mw)
-{
-	if (mw >= ntb_max_mw(ndev))
-		return NULL;
-
-	return ndev->mw[mw].vbase;
-}
-
-/**
- * ntb_get_mw_size() - return size of NTB memory window
- * @ndev: pointer to ntb_device instance
- * @mw: memory window number
- *
- * This function provides the physical size of the memory window specified
- *
- * RETURNS: the size of the memory window or zero on error
- */
-u64 ntb_get_mw_size(struct ntb_device *ndev, unsigned int mw)
-{
-	if (mw >= ntb_max_mw(ndev))
-		return 0;
-
-	return ndev->mw[mw].bar_sz;
-}
-
-/**
- * ntb_set_mw_addr - set the memory window address
- * @ndev: pointer to ntb_device instance
- * @mw: memory window number
- * @addr: base address for data
- *
- * This function sets the base physical address of the memory window.  This
- * memory address is where data from the remote system will be transfered into
- * or out of depending on how the transport is configured.
- */
-void ntb_set_mw_addr(struct ntb_device *ndev, unsigned int mw, u64 addr)
-{
-	if (mw >= ntb_max_mw(ndev))
-		return;
-
-	dev_dbg(&ndev->pdev->dev, "Writing addr %Lx to BAR %d\n", addr,
-		MW_TO_BAR(mw));
-
-	ndev->mw[mw].phys_addr = addr;
-
-	switch (MW_TO_BAR(mw)) {
-	case NTB_BAR_23:
-		writeq(addr, ndev->reg_ofs.bar2_xlat);
-		break;
-	case NTB_BAR_4:
-		if (ndev->split_bar)
-			writel(addr, ndev->reg_ofs.bar4_xlat);
-		else
-			writeq(addr, ndev->reg_ofs.bar4_xlat);
-		break;
-	case NTB_BAR_5:
-		writel(addr, ndev->reg_ofs.bar5_xlat);
-		break;
-	}
-}
-
-/**
- * ntb_ring_doorbell() - Set the doorbell on the secondary/external side
- * @ndev: pointer to ntb_device instance
- * @db: doorbell to ring
- *
- * This function allows triggering of a doorbell on the secondary/external
- * side that will initiate an interrupt on the remote host
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-void ntb_ring_doorbell(struct ntb_device *ndev, unsigned int db)
-{
-	dev_dbg(&ndev->pdev->dev, "%s: ringing doorbell %d\n", __func__, db);
-
-	if (ndev->hw_type == BWD_HW)
-		writeq((u64) 1 << db, ndev->reg_ofs.rdb);
-	else
-		writew(((1 << ndev->bits_per_vector) - 1) <<
-		       (db * ndev->bits_per_vector), ndev->reg_ofs.rdb);
-}
-
-static void bwd_recover_link(struct ntb_device *ndev)
-{
-	u32 status;
-
-	/* Driver resets the NTB ModPhy lanes - magic! */
-	writeb(0xe0, ndev->reg_base + BWD_MODPHY_PCSREG6);
-	writeb(0x40, ndev->reg_base + BWD_MODPHY_PCSREG4);
-	writeb(0x60, ndev->reg_base + BWD_MODPHY_PCSREG4);
-	writeb(0x60, ndev->reg_base + BWD_MODPHY_PCSREG6);
-
-	/* Driver waits 100ms to allow the NTB ModPhy to settle */
-	msleep(100);
-
-	/* Clear AER Errors, write to clear */
-	status = readl(ndev->reg_base + BWD_ERRCORSTS_OFFSET);
-	dev_dbg(&ndev->pdev->dev, "ERRCORSTS = %x\n", status);
-	status &= PCI_ERR_COR_REP_ROLL;
-	writel(status, ndev->reg_base + BWD_ERRCORSTS_OFFSET);
-
-	/* Clear unexpected electrical idle event in LTSSM, write to clear */
-	status = readl(ndev->reg_base + BWD_LTSSMERRSTS0_OFFSET);
-	dev_dbg(&ndev->pdev->dev, "LTSSMERRSTS0 = %x\n", status);
-	status |= BWD_LTSSMERRSTS0_UNEXPECTEDEI;
-	writel(status, ndev->reg_base + BWD_LTSSMERRSTS0_OFFSET);
-
-	/* Clear DeSkew Buffer error, write to clear */
-	status = readl(ndev->reg_base + BWD_DESKEWSTS_OFFSET);
-	dev_dbg(&ndev->pdev->dev, "DESKEWSTS = %x\n", status);
-	status |= BWD_DESKEWSTS_DBERR;
-	writel(status, ndev->reg_base + BWD_DESKEWSTS_OFFSET);
-
-	status = readl(ndev->reg_base + BWD_IBSTERRRCRVSTS0_OFFSET);
-	dev_dbg(&ndev->pdev->dev, "IBSTERRRCRVSTS0 = %x\n", status);
-	status &= BWD_IBIST_ERR_OFLOW;
-	writel(status, ndev->reg_base + BWD_IBSTERRRCRVSTS0_OFFSET);
-
-	/* Releases the NTB state machine to allow the link to retrain */
-	status = readl(ndev->reg_base + BWD_LTSSMSTATEJMP_OFFSET);
-	dev_dbg(&ndev->pdev->dev, "LTSSMSTATEJMP = %x\n", status);
-	status &= ~BWD_LTSSMSTATEJMP_FORCEDETECT;
-	writel(status, ndev->reg_base + BWD_LTSSMSTATEJMP_OFFSET);
-}
-
-static void ntb_link_event(struct ntb_device *ndev, int link_state)
-{
-	unsigned int event;
-
-	if (ndev->link_status == link_state)
-		return;
-
-	if (link_state == NTB_LINK_UP) {
-		u16 status;
-
-		dev_info(&ndev->pdev->dev, "Link Up\n");
-		ndev->link_status = NTB_LINK_UP;
-		event = NTB_EVENT_HW_LINK_UP;
-
-		if (is_ntb_atom(ndev) ||
-		    ndev->conn_type == NTB_CONN_TRANSPARENT)
-			status = readw(ndev->reg_ofs.lnk_stat);
-		else {
-			int rc = pci_read_config_word(ndev->pdev,
-						      SNB_LINK_STATUS_OFFSET,
-						      &status);
-			if (rc)
-				return;
-		}
-
-		ndev->link_width = (status & NTB_LINK_WIDTH_MASK) >> 4;
-		ndev->link_speed = (status & NTB_LINK_SPEED_MASK);
-		dev_info(&ndev->pdev->dev, "Link Width %d, Link Speed %d\n",
-			 ndev->link_width, ndev->link_speed);
-	} else {
-		dev_info(&ndev->pdev->dev, "Link Down\n");
-		ndev->link_status = NTB_LINK_DOWN;
-		event = NTB_EVENT_HW_LINK_DOWN;
-		/* Don't modify link width/speed, we need it in link recovery */
-	}
-
-	/* notify the upper layer if we have an event change */
-	if (ndev->event_cb)
-		ndev->event_cb(ndev->ntb_transport, event);
-}
-
-static int ntb_link_status(struct ntb_device *ndev)
-{
-	int link_state;
-
-	if (is_ntb_atom(ndev)) {
-		u32 ntb_cntl;
-
-		ntb_cntl = readl(ndev->reg_ofs.lnk_cntl);
-		if (ntb_cntl & BWD_CNTL_LINK_DOWN)
-			link_state = NTB_LINK_DOWN;
-		else
-			link_state = NTB_LINK_UP;
-	} else {
-		u16 status;
-		int rc;
-
-		rc = pci_read_config_word(ndev->pdev, SNB_LINK_STATUS_OFFSET,
-					  &status);
-		if (rc)
-			return rc;
-
-		if (status & NTB_LINK_STATUS_ACTIVE)
-			link_state = NTB_LINK_UP;
-		else
-			link_state = NTB_LINK_DOWN;
-	}
-
-	ntb_link_event(ndev, link_state);
-
-	return 0;
-}
-
-static void bwd_link_recovery(struct work_struct *work)
-{
-	struct ntb_device *ndev = container_of(work, struct ntb_device,
-					       lr_timer.work);
-	u32 status32;
-
-	bwd_recover_link(ndev);
-	/* There is a potential race between the 2 NTB devices recovering at the
-	 * same time.  If the times are the same, the link will not recover and
-	 * the driver will be stuck in this loop forever.  Add a random interval
-	 * to the recovery time to prevent this race.
-	 */
-	msleep(BWD_LINK_RECOVERY_TIME + prandom_u32() % BWD_LINK_RECOVERY_TIME);
-
-	status32 = readl(ndev->reg_base + BWD_LTSSMSTATEJMP_OFFSET);
-	if (status32 & BWD_LTSSMSTATEJMP_FORCEDETECT)
-		goto retry;
-
-	status32 = readl(ndev->reg_base + BWD_IBSTERRRCRVSTS0_OFFSET);
-	if (status32 & BWD_IBIST_ERR_OFLOW)
-		goto retry;
-
-	status32 = readl(ndev->reg_ofs.lnk_cntl);
-	if (!(status32 & BWD_CNTL_LINK_DOWN)) {
-		unsigned char speed, width;
-		u16 status16;
-
-		status16 = readw(ndev->reg_ofs.lnk_stat);
-		width = (status16 & NTB_LINK_WIDTH_MASK) >> 4;
-		speed = (status16 & NTB_LINK_SPEED_MASK);
-		if (ndev->link_width != width || ndev->link_speed != speed)
-			goto retry;
-	}
-
-	schedule_delayed_work(&ndev->hb_timer, NTB_HB_TIMEOUT);
-	return;
-
-retry:
-	schedule_delayed_work(&ndev->lr_timer, NTB_HB_TIMEOUT);
-}
-
-/* BWD doesn't have link status interrupt, poll on that platform */
-static void bwd_link_poll(struct work_struct *work)
-{
-	struct ntb_device *ndev = container_of(work, struct ntb_device,
-					       hb_timer.work);
-	unsigned long ts = jiffies;
-
-	/* If we haven't gotten an interrupt in a while, check the BWD link
-	 * status bit
-	 */
-	if (ts > ndev->last_ts + NTB_HB_TIMEOUT) {
-		int rc = ntb_link_status(ndev);
-		if (rc)
-			dev_err(&ndev->pdev->dev,
-				"Error determining link status\n");
-
-		/* Check to see if a link error is the cause of the link down */
-		if (ndev->link_status == NTB_LINK_DOWN) {
-			u32 status32 = readl(ndev->reg_base +
-					     BWD_LTSSMSTATEJMP_OFFSET);
-			if (status32 & BWD_LTSSMSTATEJMP_FORCEDETECT) {
-				schedule_delayed_work(&ndev->lr_timer, 0);
-				return;
-			}
-		}
-	}
-
-	schedule_delayed_work(&ndev->hb_timer, NTB_HB_TIMEOUT);
-}
-
-static int ntb_xeon_setup(struct ntb_device *ndev)
-{
-	switch (ndev->conn_type) {
-	case NTB_CONN_B2B:
-		ndev->reg_ofs.ldb = ndev->reg_base + SNB_PDOORBELL_OFFSET;
-		ndev->reg_ofs.ldb_mask = ndev->reg_base + SNB_PDBMSK_OFFSET;
-		ndev->reg_ofs.spad_read = ndev->reg_base + SNB_SPAD_OFFSET;
-		ndev->reg_ofs.bar2_xlat = ndev->reg_base + SNB_SBAR2XLAT_OFFSET;
-		ndev->reg_ofs.bar4_xlat = ndev->reg_base + SNB_SBAR4XLAT_OFFSET;
-		if (ndev->split_bar)
-			ndev->reg_ofs.bar5_xlat =
-				ndev->reg_base + SNB_SBAR5XLAT_OFFSET;
-		ndev->limits.max_spads = SNB_MAX_B2B_SPADS;
-
-		/* There is a Xeon hardware errata related to writes to
-		 * SDOORBELL or B2BDOORBELL in conjunction with inbound access
-		 * to NTB MMIO Space, which may hang the system.  To workaround
-		 * this use the second memory window to access the interrupt and
-		 * scratch pad registers on the remote system.
-		 */
-		if (ndev->wa_flags & WA_SNB_ERR) {
-			if (!ndev->mw[ndev->limits.max_mw - 1].bar_sz)
-				return -EINVAL;
-
-			ndev->limits.max_db_bits = SNB_MAX_DB_BITS;
-			ndev->reg_ofs.spad_write =
-				ndev->mw[ndev->limits.max_mw - 1].vbase +
-				SNB_SPAD_OFFSET;
-			ndev->reg_ofs.rdb =
-				ndev->mw[ndev->limits.max_mw - 1].vbase +
-				SNB_PDOORBELL_OFFSET;
-
-			/* Set the Limit register to 4k, the minimum size, to
-			 * prevent an illegal access
-			 */
-			writeq(ndev->mw[1].bar_sz + 0x1000, ndev->reg_base +
-			       SNB_PBAR4LMT_OFFSET);
-			/* HW errata on the Limit registers.  They can only be
-			 * written when the base register is 4GB aligned and
-			 * < 32bit.  This should already be the case based on
-			 * the driver defaults, but write the Limit registers
-			 * first just in case.
-			 */
-
-			ndev->limits.max_mw = SNB_ERRATA_MAX_MW;
-		} else {
-			/* HW Errata on bit 14 of b2bdoorbell register.  Writes
-			 * will not be mirrored to the remote system.  Shrink
-			 * the number of bits by one, since bit 14 is the last
-			 * bit.
-			 */
-			ndev->limits.max_db_bits = SNB_MAX_DB_BITS - 1;
-			ndev->reg_ofs.spad_write = ndev->reg_base +
-						   SNB_B2B_SPAD_OFFSET;
-			ndev->reg_ofs.rdb = ndev->reg_base +
-					    SNB_B2B_DOORBELL_OFFSET;
-
-			/* Disable the Limit register, just incase it is set to
-			 * something silly. A 64bit write should handle it
-			 * regardless of whether it has a split BAR or not.
-			 */
-			writeq(0, ndev->reg_base + SNB_PBAR4LMT_OFFSET);
-			/* HW errata on the Limit registers.  They can only be
-			 * written when the base register is 4GB aligned and
-			 * < 32bit.  This should already be the case based on
-			 * the driver defaults, but write the Limit registers
-			 * first just in case.
-			 */
-			if (ndev->split_bar)
-				ndev->limits.max_mw = HSX_SPLITBAR_MAX_MW;
-			else
-				ndev->limits.max_mw = SNB_MAX_MW;
-		}
-
-		/* The Xeon errata workaround requires setting SBAR Base
-		 * addresses to known values, so that the PBAR XLAT can be
-		 * pointed at SBAR0 of the remote system.
-		 */
-		if (ndev->dev_type == NTB_DEV_USD) {
-			writeq(SNB_MBAR23_DSD_ADDR, ndev->reg_base +
-			       SNB_PBAR2XLAT_OFFSET);
-			if (ndev->wa_flags & WA_SNB_ERR)
-				writeq(SNB_MBAR01_DSD_ADDR, ndev->reg_base +
-				       SNB_PBAR4XLAT_OFFSET);
-			else {
-				if (ndev->split_bar) {
-					writel(SNB_MBAR4_DSD_ADDR,
-					       ndev->reg_base +
-					       SNB_PBAR4XLAT_OFFSET);
-					writel(SNB_MBAR5_DSD_ADDR,
-					       ndev->reg_base +
-					       SNB_PBAR5XLAT_OFFSET);
-				} else
-					writeq(SNB_MBAR4_DSD_ADDR,
-					       ndev->reg_base +
-					       SNB_PBAR4XLAT_OFFSET);
-
-				/* B2B_XLAT_OFFSET is a 64bit register, but can
-				 * only take 32bit writes
-				 */
-				writel(SNB_MBAR01_DSD_ADDR & 0xffffffff,
-				       ndev->reg_base + SNB_B2B_XLAT_OFFSETL);
-				writel(SNB_MBAR01_DSD_ADDR >> 32,
-				       ndev->reg_base + SNB_B2B_XLAT_OFFSETU);
-			}
-
-			writeq(SNB_MBAR01_USD_ADDR, ndev->reg_base +
-			       SNB_SBAR0BASE_OFFSET);
-			writeq(SNB_MBAR23_USD_ADDR, ndev->reg_base +
-			       SNB_SBAR2BASE_OFFSET);
-			if (ndev->split_bar) {
-				writel(SNB_MBAR4_USD_ADDR, ndev->reg_base +
-				       SNB_SBAR4BASE_OFFSET);
-				writel(SNB_MBAR5_USD_ADDR, ndev->reg_base +
-				       SNB_SBAR5BASE_OFFSET);
-			} else
-				writeq(SNB_MBAR4_USD_ADDR, ndev->reg_base +
-				       SNB_SBAR4BASE_OFFSET);
-		} else {
-			writeq(SNB_MBAR23_USD_ADDR, ndev->reg_base +
-			       SNB_PBAR2XLAT_OFFSET);
-			if (ndev->wa_flags & WA_SNB_ERR)
-				writeq(SNB_MBAR01_USD_ADDR, ndev->reg_base +
-				       SNB_PBAR4XLAT_OFFSET);
-			else {
-				if (ndev->split_bar) {
-					writel(SNB_MBAR4_USD_ADDR,
-					       ndev->reg_base +
-					       SNB_PBAR4XLAT_OFFSET);
-					writel(SNB_MBAR5_USD_ADDR,
-					       ndev->reg_base +
-					       SNB_PBAR5XLAT_OFFSET);
-				} else
-					writeq(SNB_MBAR4_USD_ADDR,
-					       ndev->reg_base +
-					       SNB_PBAR4XLAT_OFFSET);
-
-				/*
-				 * B2B_XLAT_OFFSET is a 64bit register, but can
-				 * only take 32bit writes
-				 */
-				writel(SNB_MBAR01_USD_ADDR & 0xffffffff,
-				       ndev->reg_base + SNB_B2B_XLAT_OFFSETL);
-				writel(SNB_MBAR01_USD_ADDR >> 32,
-				       ndev->reg_base + SNB_B2B_XLAT_OFFSETU);
-			}
-			writeq(SNB_MBAR01_DSD_ADDR, ndev->reg_base +
-			       SNB_SBAR0BASE_OFFSET);
-			writeq(SNB_MBAR23_DSD_ADDR, ndev->reg_base +
-			       SNB_SBAR2BASE_OFFSET);
-			if (ndev->split_bar) {
-				writel(SNB_MBAR4_DSD_ADDR, ndev->reg_base +
-				       SNB_SBAR4BASE_OFFSET);
-				writel(SNB_MBAR5_DSD_ADDR, ndev->reg_base +
-				       SNB_SBAR5BASE_OFFSET);
-			} else
-				writeq(SNB_MBAR4_DSD_ADDR, ndev->reg_base +
-				       SNB_SBAR4BASE_OFFSET);
-
-		}
-		break;
-	case NTB_CONN_RP:
-		if (ndev->wa_flags & WA_SNB_ERR) {
-			dev_err(&ndev->pdev->dev,
-				"NTB-RP disabled due to hardware errata.\n");
-			return -EINVAL;
-		}
-
-		/* Scratch pads need to have exclusive access from the primary
-		 * or secondary side.  Halve the num spads so that each side can
-		 * have an equal amount.
-		 */
-		ndev->limits.max_spads = SNB_MAX_COMPAT_SPADS / 2;
-		ndev->limits.max_db_bits = SNB_MAX_DB_BITS;
-		/* Note: The SDOORBELL is the cause of the errata.  You REALLY
-		 * don't want to touch it.
-		 */
-		ndev->reg_ofs.rdb = ndev->reg_base + SNB_SDOORBELL_OFFSET;
-		ndev->reg_ofs.ldb = ndev->reg_base + SNB_PDOORBELL_OFFSET;
-		ndev->reg_ofs.ldb_mask = ndev->reg_base + SNB_PDBMSK_OFFSET;
-		/* Offset the start of the spads to correspond to whether it is
-		 * primary or secondary
-		 */
-		ndev->reg_ofs.spad_write = ndev->reg_base + SNB_SPAD_OFFSET +
-					   ndev->limits.max_spads * 4;
-		ndev->reg_ofs.spad_read = ndev->reg_base + SNB_SPAD_OFFSET;
-		ndev->reg_ofs.bar2_xlat = ndev->reg_base + SNB_SBAR2XLAT_OFFSET;
-		ndev->reg_ofs.bar4_xlat = ndev->reg_base + SNB_SBAR4XLAT_OFFSET;
-		if (ndev->split_bar) {
-			ndev->reg_ofs.bar5_xlat =
-				ndev->reg_base + SNB_SBAR5XLAT_OFFSET;
-			ndev->limits.max_mw = HSX_SPLITBAR_MAX_MW;
-		} else
-			ndev->limits.max_mw = SNB_MAX_MW;
-		break;
-	case NTB_CONN_TRANSPARENT:
-		if (ndev->wa_flags & WA_SNB_ERR) {
-			dev_err(&ndev->pdev->dev,
-				"NTB-TRANSPARENT disabled due to hardware errata.\n");
-			return -EINVAL;
-		}
-
-		/* Scratch pads need to have exclusive access from the primary
-		 * or secondary side.  Halve the num spads so that each side can
-		 * have an equal amount.
-		 */
-		ndev->limits.max_spads = SNB_MAX_COMPAT_SPADS / 2;
-		ndev->limits.max_db_bits = SNB_MAX_DB_BITS;
-		ndev->reg_ofs.rdb = ndev->reg_base + SNB_PDOORBELL_OFFSET;
-		ndev->reg_ofs.ldb = ndev->reg_base + SNB_SDOORBELL_OFFSET;
-		ndev->reg_ofs.ldb_mask = ndev->reg_base + SNB_SDBMSK_OFFSET;
-		ndev->reg_ofs.spad_write = ndev->reg_base + SNB_SPAD_OFFSET;
-		/* Offset the start of the spads to correspond to whether it is
-		 * primary or secondary
-		 */
-		ndev->reg_ofs.spad_read = ndev->reg_base + SNB_SPAD_OFFSET +
-					  ndev->limits.max_spads * 4;
-		ndev->reg_ofs.bar2_xlat = ndev->reg_base + SNB_PBAR2XLAT_OFFSET;
-		ndev->reg_ofs.bar4_xlat = ndev->reg_base + SNB_PBAR4XLAT_OFFSET;
-
-		if (ndev->split_bar) {
-			ndev->reg_ofs.bar5_xlat =
-				ndev->reg_base + SNB_PBAR5XLAT_OFFSET;
-			ndev->limits.max_mw = HSX_SPLITBAR_MAX_MW;
-		} else
-			ndev->limits.max_mw = SNB_MAX_MW;
-		break;
-	default:
-		/*
-		 * we should never hit this. the detect function should've
-		 * take cared of everything.
-		 */
-		return -EINVAL;
-	}
-
-	ndev->reg_ofs.lnk_cntl = ndev->reg_base + SNB_NTBCNTL_OFFSET;
-	ndev->reg_ofs.lnk_stat = ndev->reg_base + SNB_SLINK_STATUS_OFFSET;
-	ndev->reg_ofs.spci_cmd = ndev->reg_base + SNB_PCICMD_OFFSET;
-
-	ndev->limits.msix_cnt = SNB_MSIX_CNT;
-	ndev->bits_per_vector = SNB_DB_BITS_PER_VEC;
-
-	return 0;
-}
-
-static int ntb_bwd_setup(struct ntb_device *ndev)
-{
-	int rc;
-	u32 val;
-
-	ndev->hw_type = BWD_HW;
-
-	rc = pci_read_config_dword(ndev->pdev, NTB_PPD_OFFSET, &val);
-	if (rc)
-		return rc;
-
-	switch ((val & BWD_PPD_CONN_TYPE) >> 8) {
-	case NTB_CONN_B2B:
-		ndev->conn_type = NTB_CONN_B2B;
-		break;
-	case NTB_CONN_RP:
-	default:
-		dev_err(&ndev->pdev->dev, "Unsupported NTB configuration\n");
-		return -EINVAL;
-	}
-
-	if (val & BWD_PPD_DEV_TYPE)
-		ndev->dev_type = NTB_DEV_DSD;
-	else
-		ndev->dev_type = NTB_DEV_USD;
-
-	/* Initiate PCI-E link training */
-	rc = pci_write_config_dword(ndev->pdev, NTB_PPD_OFFSET,
-				    val | BWD_PPD_INIT_LINK);
-	if (rc)
-		return rc;
-
-	ndev->reg_ofs.ldb = ndev->reg_base + BWD_PDOORBELL_OFFSET;
-	ndev->reg_ofs.ldb_mask = ndev->reg_base + BWD_PDBMSK_OFFSET;
-	ndev->reg_ofs.rdb = ndev->reg_base + BWD_B2B_DOORBELL_OFFSET;
-	ndev->reg_ofs.bar2_xlat = ndev->reg_base + BWD_SBAR2XLAT_OFFSET;
-	ndev->reg_ofs.bar4_xlat = ndev->reg_base + BWD_SBAR4XLAT_OFFSET;
-	ndev->reg_ofs.lnk_cntl = ndev->reg_base + BWD_NTBCNTL_OFFSET;
-	ndev->reg_ofs.lnk_stat = ndev->reg_base + BWD_LINK_STATUS_OFFSET;
-	ndev->reg_ofs.spad_read = ndev->reg_base + BWD_SPAD_OFFSET;
-	ndev->reg_ofs.spad_write = ndev->reg_base + BWD_B2B_SPAD_OFFSET;
-	ndev->reg_ofs.spci_cmd = ndev->reg_base + BWD_PCICMD_OFFSET;
-	ndev->limits.max_mw = BWD_MAX_MW;
-	ndev->limits.max_spads = BWD_MAX_SPADS;
-	ndev->limits.max_db_bits = BWD_MAX_DB_BITS;
-	ndev->limits.msix_cnt = BWD_MSIX_CNT;
-	ndev->bits_per_vector = BWD_DB_BITS_PER_VEC;
-
-	/* Since bwd doesn't have a link interrupt, setup a poll timer */
-	INIT_DELAYED_WORK(&ndev->hb_timer, bwd_link_poll);
-	INIT_DELAYED_WORK(&ndev->lr_timer, bwd_link_recovery);
-	schedule_delayed_work(&ndev->hb_timer, NTB_HB_TIMEOUT);
-
-	return 0;
-}
-
-static int ntb_device_setup(struct ntb_device *ndev)
-{
-	int rc;
-
-	if (is_ntb_xeon(ndev))
-		rc = ntb_xeon_setup(ndev);
-	else if (is_ntb_atom(ndev))
-		rc = ntb_bwd_setup(ndev);
-	else
-		rc = -ENODEV;
-
-	if (rc)
-		return rc;
-
-	if (ndev->conn_type == NTB_CONN_B2B)
-		/* Enable Bus Master and Memory Space on the secondary side */
-		writew(PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER,
-		       ndev->reg_ofs.spci_cmd);
-
-	return 0;
-}
-
-static void ntb_device_free(struct ntb_device *ndev)
-{
-	if (is_ntb_atom(ndev)) {
-		cancel_delayed_work_sync(&ndev->hb_timer);
-		cancel_delayed_work_sync(&ndev->lr_timer);
-	}
-}
-
-static irqreturn_t bwd_callback_msix_irq(int irq, void *data)
-{
-	struct ntb_db_cb *db_cb = data;
-	struct ntb_device *ndev = db_cb->ndev;
-	unsigned long mask;
-
-	dev_dbg(&ndev->pdev->dev, "MSI-X irq %d received for DB %d\n", irq,
-		db_cb->db_num);
-
-	mask = readw(ndev->reg_ofs.ldb_mask);
-	set_bit(db_cb->db_num * ndev->bits_per_vector, &mask);
-	writew(mask, ndev->reg_ofs.ldb_mask);
-
-	tasklet_schedule(&db_cb->irq_work);
-
-	/* No need to check for the specific HB irq, any interrupt means
-	 * we're connected.
-	 */
-	ndev->last_ts = jiffies;
-
-	writeq((u64) 1 << db_cb->db_num, ndev->reg_ofs.ldb);
-
-	return IRQ_HANDLED;
-}
-
-static irqreturn_t xeon_callback_msix_irq(int irq, void *data)
-{
-	struct ntb_db_cb *db_cb = data;
-	struct ntb_device *ndev = db_cb->ndev;
-	unsigned long mask;
-
-	dev_dbg(&ndev->pdev->dev, "MSI-X irq %d received for DB %d\n", irq,
-		db_cb->db_num);
-
-	mask = readw(ndev->reg_ofs.ldb_mask);
-	set_bit(db_cb->db_num * ndev->bits_per_vector, &mask);
-	writew(mask, ndev->reg_ofs.ldb_mask);
-
-	tasklet_schedule(&db_cb->irq_work);
-
-	/* On Sandybridge, there are 16 bits in the interrupt register
-	 * but only 4 vectors.  So, 5 bits are assigned to the first 3
-	 * vectors, with the 4th having a single bit for link
-	 * interrupts.
-	 */
-	writew(((1 << ndev->bits_per_vector) - 1) <<
-	       (db_cb->db_num * ndev->bits_per_vector), ndev->reg_ofs.ldb);
-
-	return IRQ_HANDLED;
-}
-
-/* Since we do not have a HW doorbell in BWD, this is only used in JF/JT */
-static irqreturn_t xeon_event_msix_irq(int irq, void *dev)
-{
-	struct ntb_device *ndev = dev;
-	int rc;
-
-	dev_dbg(&ndev->pdev->dev, "MSI-X irq %d received for Events\n", irq);
-
-	rc = ntb_link_status(ndev);
-	if (rc)
-		dev_err(&ndev->pdev->dev, "Error determining link status\n");
-
-	/* bit 15 is always the link bit */
-	writew(1 << SNB_LINK_DB, ndev->reg_ofs.ldb);
-
-	return IRQ_HANDLED;
-}
-
-static irqreturn_t ntb_interrupt(int irq, void *dev)
-{
-	struct ntb_device *ndev = dev;
-	unsigned int i = 0;
-
-	if (is_ntb_atom(ndev)) {
-		u64 ldb = readq(ndev->reg_ofs.ldb);
-
-		dev_dbg(&ndev->pdev->dev, "irq %d - ldb = %Lx\n", irq, ldb);
-
-		while (ldb) {
-			i = __ffs(ldb);
-			ldb &= ldb - 1;
-			bwd_callback_msix_irq(irq, &ndev->db_cb[i]);
-		}
-	} else {
-		u16 ldb = readw(ndev->reg_ofs.ldb);
-
-		dev_dbg(&ndev->pdev->dev, "irq %d - ldb = %x\n", irq, ldb);
-
-		if (ldb & SNB_DB_HW_LINK) {
-			xeon_event_msix_irq(irq, dev);
-			ldb &= ~SNB_DB_HW_LINK;
-		}
-
-		while (ldb) {
-			i = __ffs(ldb);
-			ldb &= ldb - 1;
-			xeon_callback_msix_irq(irq, &ndev->db_cb[i]);
-		}
-	}
-
-	return IRQ_HANDLED;
-}
-
-static int ntb_setup_snb_msix(struct ntb_device *ndev, int msix_entries)
-{
-	struct pci_dev *pdev = ndev->pdev;
-	struct msix_entry *msix;
-	int rc, i;
-
-	if (msix_entries < ndev->limits.msix_cnt)
-		return -ENOSPC;
-
-	rc = pci_enable_msix_exact(pdev, ndev->msix_entries, msix_entries);
-	if (rc < 0)
-		return rc;
-
-	for (i = 0; i < msix_entries; i++) {
-		msix = &ndev->msix_entries[i];
-		WARN_ON(!msix->vector);
-
-		if (i == msix_entries - 1) {
-			rc = request_irq(msix->vector,
-					 xeon_event_msix_irq, 0,
-					 "ntb-event-msix", ndev);
-			if (rc)
-				goto err;
-		} else {
-			rc = request_irq(msix->vector,
-					 xeon_callback_msix_irq, 0,
-					 "ntb-callback-msix",
-					 &ndev->db_cb[i]);
-			if (rc)
-				goto err;
-		}
-	}
-
-	ndev->num_msix = msix_entries;
-	ndev->max_cbs = msix_entries - 1;
-
-	return 0;
-
-err:
-	while (--i >= 0) {
-		/* Code never reaches here for entry nr 'ndev->num_msix - 1' */
-		msix = &ndev->msix_entries[i];
-		free_irq(msix->vector, &ndev->db_cb[i]);
-	}
-
-	pci_disable_msix(pdev);
-	ndev->num_msix = 0;
-
-	return rc;
-}
-
-static int ntb_setup_bwd_msix(struct ntb_device *ndev, int msix_entries)
-{
-	struct pci_dev *pdev = ndev->pdev;
-	struct msix_entry *msix;
-	int rc, i;
-
-	msix_entries = pci_enable_msix_range(pdev, ndev->msix_entries,
-					     1, msix_entries);
-	if (msix_entries < 0)
-		return msix_entries;
-
-	for (i = 0; i < msix_entries; i++) {
-		msix = &ndev->msix_entries[i];
-		WARN_ON(!msix->vector);
-
-		rc = request_irq(msix->vector, bwd_callback_msix_irq, 0,
-				 "ntb-callback-msix", &ndev->db_cb[i]);
-		if (rc)
-			goto err;
-	}
-
-	ndev->num_msix = msix_entries;
-	ndev->max_cbs = msix_entries;
-
-	return 0;
-
-err:
-	while (--i >= 0)
-		free_irq(msix->vector, &ndev->db_cb[i]);
-
-	pci_disable_msix(pdev);
-	ndev->num_msix = 0;
-
-	return rc;
-}
-
-static int ntb_setup_msix(struct ntb_device *ndev)
-{
-	struct pci_dev *pdev = ndev->pdev;
-	int msix_entries;
-	int rc, i;
-
-	msix_entries = pci_msix_vec_count(pdev);
-	if (msix_entries < 0) {
-		rc = msix_entries;
-		goto err;
-	} else if (msix_entries > ndev->limits.msix_cnt) {
-		rc = -EINVAL;
-		goto err;
-	}
-
-	ndev->msix_entries = kmalloc(sizeof(struct msix_entry) * msix_entries,
-				     GFP_KERNEL);
-	if (!ndev->msix_entries) {
-		rc = -ENOMEM;
-		goto err;
-	}
-
-	for (i = 0; i < msix_entries; i++)
-		ndev->msix_entries[i].entry = i;
-
-	if (is_ntb_atom(ndev))
-		rc = ntb_setup_bwd_msix(ndev, msix_entries);
-	else
-		rc = ntb_setup_snb_msix(ndev, msix_entries);
-	if (rc)
-		goto err1;
-
-	return 0;
-
-err1:
-	kfree(ndev->msix_entries);
-err:
-	dev_err(&pdev->dev, "Error allocating MSI-X interrupt\n");
-	return rc;
-}
-
-static int ntb_setup_msi(struct ntb_device *ndev)
-{
-	struct pci_dev *pdev = ndev->pdev;
-	int rc;
-
-	rc = pci_enable_msi(pdev);
-	if (rc)
-		return rc;
-
-	rc = request_irq(pdev->irq, ntb_interrupt, 0, "ntb-msi", ndev);
-	if (rc) {
-		pci_disable_msi(pdev);
-		dev_err(&pdev->dev, "Error allocating MSI interrupt\n");
-		return rc;
-	}
-
-	return 0;
-}
-
-static int ntb_setup_intx(struct ntb_device *ndev)
-{
-	struct pci_dev *pdev = ndev->pdev;
-	int rc;
-
-	/* Verify intx is enabled */
-	pci_intx(pdev, 1);
-
-	rc = request_irq(pdev->irq, ntb_interrupt, IRQF_SHARED, "ntb-intx",
-			 ndev);
-	if (rc)
-		return rc;
-
-	return 0;
-}
-
-static int ntb_setup_interrupts(struct ntb_device *ndev)
-{
-	int rc;
-
-	/* On BWD, disable all interrupts.  On SNB, disable all but Link
-	 * Interrupt.  The rest will be unmasked as callbacks are registered.
-	 */
-	if (is_ntb_atom(ndev))
-		writeq(~0, ndev->reg_ofs.ldb_mask);
-	else {
-		u16 var = 1 << SNB_LINK_DB;
-		writew(~var, ndev->reg_ofs.ldb_mask);
-	}
-
-	rc = ntb_setup_msix(ndev);
-	if (!rc)
-		goto done;
-
-	ndev->bits_per_vector = 1;
-	ndev->max_cbs = ndev->limits.max_db_bits;
-
-	rc = ntb_setup_msi(ndev);
-	if (!rc)
-		goto done;
-
-	rc = ntb_setup_intx(ndev);
-	if (rc) {
-		dev_err(&ndev->pdev->dev, "no usable interrupts\n");
-		return rc;
-	}
-
-done:
-	return 0;
-}
-
-static void ntb_free_interrupts(struct ntb_device *ndev)
-{
-	struct pci_dev *pdev = ndev->pdev;
-
-	/* mask interrupts */
-	if (is_ntb_atom(ndev))
-		writeq(~0, ndev->reg_ofs.ldb_mask);
-	else
-		writew(~0, ndev->reg_ofs.ldb_mask);
-
-	if (ndev->num_msix) {
-		struct msix_entry *msix;
-		u32 i;
-
-		for (i = 0; i < ndev->num_msix; i++) {
-			msix = &ndev->msix_entries[i];
-			if (is_ntb_xeon(ndev) && i == ndev->num_msix - 1)
-				free_irq(msix->vector, ndev);
-			else
-				free_irq(msix->vector, &ndev->db_cb[i]);
-		}
-		pci_disable_msix(pdev);
-		kfree(ndev->msix_entries);
-	} else {
-		free_irq(pdev->irq, ndev);
-
-		if (pci_dev_msi_enabled(pdev))
-			pci_disable_msi(pdev);
-	}
-}
-
-static int ntb_create_callbacks(struct ntb_device *ndev)
-{
-	int i;
-
-	/* Chicken-egg issue.  We won't know how many callbacks are necessary
-	 * until we see how many MSI-X vectors we get, but these pointers need
-	 * to be passed into the MSI-X register function.  So, we allocate the
-	 * max, knowing that they might not all be used, to work around this.
-	 */
-	ndev->db_cb = kcalloc(ndev->limits.max_db_bits,
-			      sizeof(struct ntb_db_cb),
-			      GFP_KERNEL);
-	if (!ndev->db_cb)
-		return -ENOMEM;
-
-	for (i = 0; i < ndev->limits.max_db_bits; i++) {
-		ndev->db_cb[i].db_num = i;
-		ndev->db_cb[i].ndev = ndev;
-	}
-
-	return 0;
-}
-
-static void ntb_free_callbacks(struct ntb_device *ndev)
-{
-	int i;
-
-	for (i = 0; i < ndev->limits.max_db_bits; i++)
-		ntb_unregister_db_callback(ndev, i);
-
-	kfree(ndev->db_cb);
-}
-
-static ssize_t ntb_debugfs_read(struct file *filp, char __user *ubuf,
-				size_t count, loff_t *offp)
-{
-	struct ntb_device *ndev;
-	char *buf;
-	ssize_t ret, offset, out_count;
-
-	out_count = 500;
-
-	buf = kmalloc(out_count, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	ndev = filp->private_data;
-	offset = 0;
-	offset += snprintf(buf + offset, out_count - offset,
-			   "NTB Device Information:\n");
-	offset += snprintf(buf + offset, out_count - offset,
-			   "Connection Type - \t\t%s\n",
-			   ndev->conn_type == NTB_CONN_TRANSPARENT ?
-			   "Transparent" : (ndev->conn_type == NTB_CONN_B2B) ?
-			   "Back to back" : "Root Port");
-	offset += snprintf(buf + offset, out_count - offset,
-			   "Device Type - \t\t\t%s\n",
-			   ndev->dev_type == NTB_DEV_USD ?
-			   "DSD/USP" : "USD/DSP");
-	offset += snprintf(buf + offset, out_count - offset,
-			   "Max Number of Callbacks - \t%u\n",
-			   ntb_max_cbs(ndev));
-	offset += snprintf(buf + offset, out_count - offset,
-			   "Link Status - \t\t\t%s\n",
-			   ntb_hw_link_status(ndev) ? "Up" : "Down");
-	if (ntb_hw_link_status(ndev)) {
-		offset += snprintf(buf + offset, out_count - offset,
-				   "Link Speed - \t\t\tPCI-E Gen %u\n",
-				   ndev->link_speed);
-		offset += snprintf(buf + offset, out_count - offset,
-				   "Link Width - \t\t\tx%u\n",
-				   ndev->link_width);
-	}
-
-	if (is_ntb_xeon(ndev)) {
-		u32 status32;
-		u16 status16;
-		int rc;
-
-		offset += snprintf(buf + offset, out_count - offset,
-				   "\nNTB Device Statistics:\n");
-		offset += snprintf(buf + offset, out_count - offset,
-				   "Upstream Memory Miss - \t%u\n",
-				   readw(ndev->reg_base +
-					 SNB_USMEMMISS_OFFSET));
-
-		offset += snprintf(buf + offset, out_count - offset,
-				   "\nNTB Hardware Errors:\n");
-
-		rc = pci_read_config_word(ndev->pdev, SNB_DEVSTS_OFFSET,
-					  &status16);
-		if (!rc)
-			offset += snprintf(buf + offset, out_count - offset,
-					   "DEVSTS - \t%#06x\n", status16);
-
-		rc = pci_read_config_word(ndev->pdev, SNB_LINK_STATUS_OFFSET,
-					  &status16);
-		if (!rc)
-			offset += snprintf(buf + offset, out_count - offset,
-					   "LNKSTS - \t%#06x\n", status16);
-
-		rc = pci_read_config_dword(ndev->pdev, SNB_UNCERRSTS_OFFSET,
-					   &status32);
-		if (!rc)
-			offset += snprintf(buf + offset, out_count - offset,
-					   "UNCERRSTS - \t%#010x\n", status32);
-
-		rc = pci_read_config_dword(ndev->pdev, SNB_CORERRSTS_OFFSET,
-					   &status32);
-		if (!rc)
-			offset += snprintf(buf + offset, out_count - offset,
-					   "CORERRSTS - \t%#010x\n", status32);
-	}
-
-	if (offset > out_count)
-		offset = out_count;
-
-	ret = simple_read_from_buffer(ubuf, count, offp, buf, offset);
-	kfree(buf);
-	return ret;
-}
-
-static const struct file_operations ntb_debugfs_info = {
-	.owner = THIS_MODULE,
-	.open = simple_open,
-	.read = ntb_debugfs_read,
-};
-
-static void ntb_setup_debugfs(struct ntb_device *ndev)
-{
-	if (!debugfs_initialized())
-		return;
-
-	if (!debugfs_dir)
-		debugfs_dir = debugfs_create_dir(KBUILD_MODNAME, NULL);
-
-	ndev->debugfs_dir = debugfs_create_dir(pci_name(ndev->pdev),
-					       debugfs_dir);
-	if (ndev->debugfs_dir)
-		ndev->debugfs_info = debugfs_create_file("info", S_IRUSR,
-							 ndev->debugfs_dir,
-							 ndev,
-							 &ntb_debugfs_info);
-}
-
-static void ntb_free_debugfs(struct ntb_device *ndev)
-{
-	debugfs_remove_recursive(ndev->debugfs_dir);
-
-	if (debugfs_dir && simple_empty(debugfs_dir)) {
-		debugfs_remove_recursive(debugfs_dir);
-		debugfs_dir = NULL;
-	}
-}
-
-static void ntb_hw_link_up(struct ntb_device *ndev)
-{
-	if (ndev->conn_type == NTB_CONN_TRANSPARENT)
-		ntb_link_event(ndev, NTB_LINK_UP);
-	else {
-		u32 ntb_cntl;
-
-		/* Let's bring the NTB link up */
-		ntb_cntl = readl(ndev->reg_ofs.lnk_cntl);
-		ntb_cntl &= ~(NTB_CNTL_LINK_DISABLE | NTB_CNTL_CFG_LOCK);
-		ntb_cntl |= NTB_CNTL_P2S_BAR23_SNOOP | NTB_CNTL_S2P_BAR23_SNOOP;
-		ntb_cntl |= NTB_CNTL_P2S_BAR4_SNOOP | NTB_CNTL_S2P_BAR4_SNOOP;
-		if (ndev->split_bar)
-			ntb_cntl |= NTB_CNTL_P2S_BAR5_SNOOP |
-				    NTB_CNTL_S2P_BAR5_SNOOP;
-
-		writel(ntb_cntl, ndev->reg_ofs.lnk_cntl);
-	}
-}
-
-static void ntb_hw_link_down(struct ntb_device *ndev)
-{
-	u32 ntb_cntl;
-
-	if (ndev->conn_type == NTB_CONN_TRANSPARENT) {
-		ntb_link_event(ndev, NTB_LINK_DOWN);
-		return;
-	}
-
-	/* Bring NTB link down */
-	ntb_cntl = readl(ndev->reg_ofs.lnk_cntl);
-	ntb_cntl &= ~(NTB_CNTL_P2S_BAR23_SNOOP | NTB_CNTL_S2P_BAR23_SNOOP);
-	ntb_cntl &= ~(NTB_CNTL_P2S_BAR4_SNOOP | NTB_CNTL_S2P_BAR4_SNOOP);
-	if (ndev->split_bar)
-		ntb_cntl &= ~(NTB_CNTL_P2S_BAR5_SNOOP |
-			      NTB_CNTL_S2P_BAR5_SNOOP);
-	ntb_cntl |= NTB_CNTL_LINK_DISABLE | NTB_CNTL_CFG_LOCK;
-	writel(ntb_cntl, ndev->reg_ofs.lnk_cntl);
-}
-
-static void ntb_max_mw_detect(struct ntb_device *ndev)
-{
-	if (ndev->split_bar)
-		ndev->limits.max_mw = HSX_SPLITBAR_MAX_MW;
-	else
-		ndev->limits.max_mw = SNB_MAX_MW;
-}
-
-static int ntb_xeon_detect(struct ntb_device *ndev)
-{
-	int rc, bars_mask;
-	u32 bars;
-	u8 ppd;
-
-	ndev->hw_type = SNB_HW;
-
-	rc = pci_read_config_byte(ndev->pdev, NTB_PPD_OFFSET, &ppd);
-	if (rc)
-		return -EIO;
-
-	if (ppd & SNB_PPD_DEV_TYPE)
-		ndev->dev_type = NTB_DEV_USD;
-	else
-		ndev->dev_type = NTB_DEV_DSD;
-
-	ndev->split_bar = (ppd & SNB_PPD_SPLIT_BAR) ? 1 : 0;
-
-	switch (ppd & SNB_PPD_CONN_TYPE) {
-	case NTB_CONN_B2B:
-		dev_info(&ndev->pdev->dev, "Conn Type = B2B\n");
-		ndev->conn_type = NTB_CONN_B2B;
-		break;
-	case NTB_CONN_RP:
-		dev_info(&ndev->pdev->dev, "Conn Type = RP\n");
-		ndev->conn_type = NTB_CONN_RP;
-		break;
-	case NTB_CONN_TRANSPARENT:
-		dev_info(&ndev->pdev->dev, "Conn Type = TRANSPARENT\n");
-		ndev->conn_type = NTB_CONN_TRANSPARENT;
-		/*
-		 * This mode is default to USD/DSP. HW does not report
-		 * properly in transparent mode as it has no knowledge of
-		 * NTB. We will just force correct here.
-		 */
-		ndev->dev_type = NTB_DEV_USD;
-
-		/*
-		 * This is a way for transparent BAR to figure out if we
-		 * are doing split BAR or not. There is no way for the hw
-		 * on the transparent side to know and set the PPD.
-		 */
-		bars_mask = pci_select_bars(ndev->pdev, IORESOURCE_MEM);
-		bars = hweight32(bars_mask);
-		if (bars == (HSX_SPLITBAR_MAX_MW + 1))
-			ndev->split_bar = 1;
-
-		break;
-	default:
-		dev_err(&ndev->pdev->dev, "Unknown PPD %x\n", ppd);
-		return -ENODEV;
-	}
-
-	ntb_max_mw_detect(ndev);
-
-	return 0;
-}
-
-static int ntb_atom_detect(struct ntb_device *ndev)
-{
-	int rc;
-	u32 ppd;
-
-	ndev->hw_type = BWD_HW;
-	ndev->limits.max_mw = BWD_MAX_MW;
-
-	rc = pci_read_config_dword(ndev->pdev, NTB_PPD_OFFSET, &ppd);
-	if (rc)
-		return rc;
-
-	switch ((ppd & BWD_PPD_CONN_TYPE) >> 8) {
-	case NTB_CONN_B2B:
-		dev_info(&ndev->pdev->dev, "Conn Type = B2B\n");
-		ndev->conn_type = NTB_CONN_B2B;
-		break;
-	case NTB_CONN_RP:
-	default:
-		dev_err(&ndev->pdev->dev, "Unsupported NTB configuration\n");
-		return -EINVAL;
-	}
-
-	if (ppd & BWD_PPD_DEV_TYPE)
-		ndev->dev_type = NTB_DEV_DSD;
-	else
-		ndev->dev_type = NTB_DEV_USD;
-
-	return 0;
-}
-
-static int ntb_device_detect(struct ntb_device *ndev)
-{
-	int rc;
-
-	if (is_ntb_xeon(ndev))
-		rc = ntb_xeon_detect(ndev);
-	else if (is_ntb_atom(ndev))
-		rc = ntb_atom_detect(ndev);
-	else
-		rc = -ENODEV;
-
-	dev_info(&ndev->pdev->dev, "Device Type = %s\n",
-		 ndev->dev_type == NTB_DEV_USD ? "USD/DSP" : "DSD/USP");
-
-	return 0;
-}
-
-static int ntb_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
-{
-	struct ntb_device *ndev;
-	int rc, i;
-
-	ndev = kzalloc(sizeof(struct ntb_device), GFP_KERNEL);
-	if (!ndev)
-		return -ENOMEM;
-
-	ndev->pdev = pdev;
-
-	ntb_set_errata_flags(ndev);
-
-	ndev->link_status = NTB_LINK_DOWN;
-	pci_set_drvdata(pdev, ndev);
-	ntb_setup_debugfs(ndev);
-
-	rc = pci_enable_device(pdev);
-	if (rc)
-		goto err;
-
-	pci_set_master(ndev->pdev);
-
-	rc = ntb_device_detect(ndev);
-	if (rc)
-		goto err;
-
-	ndev->mw = kcalloc(ndev->limits.max_mw, sizeof(struct ntb_mw),
-			   GFP_KERNEL);
-	if (!ndev->mw) {
-		rc = -ENOMEM;
-		goto err1;
-	}
-
-	if (ndev->split_bar)
-		rc = pci_request_selected_regions(pdev, NTB_SPLITBAR_MASK,
-						  KBUILD_MODNAME);
-	else
-		rc = pci_request_selected_regions(pdev, NTB_BAR_MASK,
-						  KBUILD_MODNAME);
-
-	if (rc)
-		goto err2;
-
-	ndev->reg_base = pci_ioremap_bar(pdev, NTB_BAR_MMIO);
-	if (!ndev->reg_base) {
-		dev_warn(&pdev->dev, "Cannot remap BAR 0\n");
-		rc = -EIO;
-		goto err3;
-	}
-
-	for (i = 0; i < ndev->limits.max_mw; i++) {
-		ndev->mw[i].bar_sz = pci_resource_len(pdev, MW_TO_BAR(i));
-
-		/*
-		 * with the errata we need to steal last of the memory
-		 * windows for workarounds and they point to MMIO registers.
-		 */
-		if ((ndev->wa_flags & WA_SNB_ERR) &&
-		    (i == (ndev->limits.max_mw - 1))) {
-			ndev->mw[i].vbase =
-				ioremap_nocache(pci_resource_start(pdev,
-							MW_TO_BAR(i)),
-						ndev->mw[i].bar_sz);
-		} else {
-			ndev->mw[i].vbase =
-				ioremap_wc(pci_resource_start(pdev,
-							MW_TO_BAR(i)),
-					   ndev->mw[i].bar_sz);
-		}
-
-		dev_info(&pdev->dev, "MW %d size %llu\n", i,
-			 (unsigned long long) ndev->mw[i].bar_sz);
-		if (!ndev->mw[i].vbase) {
-			dev_warn(&pdev->dev, "Cannot remap BAR %d\n",
-				 MW_TO_BAR(i));
-			rc = -EIO;
-			goto err4;
-		}
-	}
-
-	rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
-	if (rc) {
-		rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
-		if (rc)
-			goto err4;
-
-		dev_warn(&pdev->dev, "Cannot DMA highmem\n");
-	}
-
-	rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
-	if (rc) {
-		rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
-		if (rc)
-			goto err4;
-
-		dev_warn(&pdev->dev, "Cannot DMA consistent highmem\n");
-	}
-
-	rc = ntb_device_setup(ndev);
-	if (rc)
-		goto err4;
-
-	rc = ntb_create_callbacks(ndev);
-	if (rc)
-		goto err5;
-
-	rc = ntb_setup_interrupts(ndev);
-	if (rc)
-		goto err6;
-
-	/* The scratchpad registers keep the values between rmmod/insmod,
-	 * blast them now
-	 */
-	for (i = 0; i < ndev->limits.max_spads; i++) {
-		ntb_write_local_spad(ndev, i, 0);
-		ntb_write_remote_spad(ndev, i, 0);
-	}
-
-	rc = ntb_transport_init(pdev);
-	if (rc)
-		goto err7;
-
-	ntb_hw_link_up(ndev);
-
-	return 0;
-
-err7:
-	ntb_free_interrupts(ndev);
-err6:
-	ntb_free_callbacks(ndev);
-err5:
-	ntb_device_free(ndev);
-err4:
-	for (i--; i >= 0; i--)
-		iounmap(ndev->mw[i].vbase);
-	iounmap(ndev->reg_base);
-err3:
-	if (ndev->split_bar)
-		pci_release_selected_regions(pdev, NTB_SPLITBAR_MASK);
-	else
-		pci_release_selected_regions(pdev, NTB_BAR_MASK);
-err2:
-	kfree(ndev->mw);
-err1:
-	pci_disable_device(pdev);
-err:
-	ntb_free_debugfs(ndev);
-	kfree(ndev);
-
-	dev_err(&pdev->dev, "Error loading %s module\n", KBUILD_MODNAME);
-	return rc;
-}
-
-static void ntb_pci_remove(struct pci_dev *pdev)
-{
-	struct ntb_device *ndev = pci_get_drvdata(pdev);
-	int i;
-
-	ntb_hw_link_down(ndev);
-
-	ntb_transport_free(ndev->ntb_transport);
-
-	ntb_free_interrupts(ndev);
-	ntb_free_callbacks(ndev);
-	ntb_device_free(ndev);
-
-	/* need to reset max_mw limits so we can unmap properly */
-	if (ndev->hw_type == SNB_HW)
-		ntb_max_mw_detect(ndev);
-
-	for (i = 0; i < ndev->limits.max_mw; i++)
-		iounmap(ndev->mw[i].vbase);
-
-	kfree(ndev->mw);
-	iounmap(ndev->reg_base);
-	if (ndev->split_bar)
-		pci_release_selected_regions(pdev, NTB_SPLITBAR_MASK);
-	else
-		pci_release_selected_regions(pdev, NTB_BAR_MASK);
-	pci_disable_device(pdev);
-	ntb_free_debugfs(ndev);
-	kfree(ndev);
-}
-
-static struct pci_driver ntb_pci_driver = {
-	.name = KBUILD_MODNAME,
-	.id_table = ntb_pci_tbl,
-	.probe = ntb_pci_probe,
-	.remove = ntb_pci_remove,
-};
-
-module_pci_driver(ntb_pci_driver);
diff --git a/drivers/ntb/ntb_hw.h b/drivers/ntb/ntb_hw.h
deleted file mode 100644
index 96de5fc..0000000
--- a/drivers/ntb/ntb_hw.h
+++ /dev/null
@@ -1,256 +0,0 @@
-/*
- * This file is provided under a dual BSD/GPLv2 license.  When using or
- *   redistributing this file, you may do so under either license.
- *
- *   GPL LICENSE SUMMARY
- *
- *   Copyright(c) 2012 Intel Corporation. All rights reserved.
- *
- *   This program is free software; you can redistribute it and/or modify
- *   it under the terms of version 2 of the GNU General Public License as
- *   published by the Free Software Foundation.
- *
- *   BSD LICENSE
- *
- *   Copyright(c) 2012 Intel Corporation. All rights reserved.
- *
- *   Redistribution and use in source and binary forms, with or without
- *   modification, are permitted provided that the following conditions
- *   are met:
- *
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copy
- *       notice, this list of conditions and the following disclaimer in
- *       the documentation and/or other materials provided with the
- *       distribution.
- *     * Neither the name of Intel Corporation nor the names of its
- *       contributors may be used to endorse or promote products derived
- *       from this software without specific prior written permission.
- *
- *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * Intel PCIe NTB Linux driver
- *
- * Contact Information:
- * Jon Mason <jon.mason@intel.com>
- */
-#include <linux/ntb.h>
-
-#define PCI_DEVICE_ID_INTEL_NTB_B2B_JSF		0x3725
-#define PCI_DEVICE_ID_INTEL_NTB_PS_JSF		0x3726
-#define PCI_DEVICE_ID_INTEL_NTB_SS_JSF		0x3727
-#define PCI_DEVICE_ID_INTEL_NTB_B2B_SNB		0x3C0D
-#define PCI_DEVICE_ID_INTEL_NTB_PS_SNB		0x3C0E
-#define PCI_DEVICE_ID_INTEL_NTB_SS_SNB		0x3C0F
-#define PCI_DEVICE_ID_INTEL_NTB_B2B_IVT		0x0E0D
-#define PCI_DEVICE_ID_INTEL_NTB_PS_IVT		0x0E0E
-#define PCI_DEVICE_ID_INTEL_NTB_SS_IVT		0x0E0F
-#define PCI_DEVICE_ID_INTEL_NTB_B2B_HSX		0x2F0D
-#define PCI_DEVICE_ID_INTEL_NTB_PS_HSX		0x2F0E
-#define PCI_DEVICE_ID_INTEL_NTB_SS_HSX		0x2F0F
-#define PCI_DEVICE_ID_INTEL_NTB_B2B_BWD		0x0C4E
-
-#ifndef readq
-static inline u64 readq(void __iomem *addr)
-{
-	return readl(addr) | (((u64) readl(addr + 4)) << 32LL);
-}
-#endif
-
-#ifndef writeq
-static inline void writeq(u64 val, void __iomem *addr)
-{
-	writel(val & 0xffffffff, addr);
-	writel(val >> 32, addr + 4);
-}
-#endif
-
-#define NTB_BAR_MMIO		0
-#define NTB_BAR_23		2
-#define NTB_BAR_4		4
-#define NTB_BAR_5		5
-
-#define NTB_BAR_MASK		((1 << NTB_BAR_MMIO) | (1 << NTB_BAR_23) |\
-				 (1 << NTB_BAR_4))
-#define NTB_SPLITBAR_MASK	((1 << NTB_BAR_MMIO) | (1 << NTB_BAR_23) |\
-				 (1 << NTB_BAR_4) | (1 << NTB_BAR_5))
-
-#define NTB_HB_TIMEOUT		msecs_to_jiffies(1000)
-
-enum ntb_hw_event {
-	NTB_EVENT_SW_EVENT0 = 0,
-	NTB_EVENT_SW_EVENT1,
-	NTB_EVENT_SW_EVENT2,
-	NTB_EVENT_HW_ERROR,
-	NTB_EVENT_HW_LINK_UP,
-	NTB_EVENT_HW_LINK_DOWN,
-};
-
-struct ntb_mw {
-	dma_addr_t phys_addr;
-	void __iomem *vbase;
-	resource_size_t bar_sz;
-};
-
-struct ntb_db_cb {
-	int (*callback)(void *data, int db_num);
-	unsigned int db_num;
-	void *data;
-	struct ntb_device *ndev;
-	struct tasklet_struct irq_work;
-};
-
-#define WA_SNB_ERR	0x00000001
-
-struct ntb_device {
-	struct pci_dev *pdev;
-	struct msix_entry *msix_entries;
-	void __iomem *reg_base;
-	struct ntb_mw *mw;
-	struct {
-		unsigned char max_mw;
-		unsigned char max_spads;
-		unsigned char max_db_bits;
-		unsigned char msix_cnt;
-	} limits;
-	struct {
-		void __iomem *ldb;
-		void __iomem *ldb_mask;
-		void __iomem *rdb;
-		void __iomem *bar2_xlat;
-		void __iomem *bar4_xlat;
-		void __iomem *bar5_xlat;
-		void __iomem *spad_write;
-		void __iomem *spad_read;
-		void __iomem *lnk_cntl;
-		void __iomem *lnk_stat;
-		void __iomem *spci_cmd;
-	} reg_ofs;
-	struct ntb_transport *ntb_transport;
-	void (*event_cb)(void *handle, enum ntb_hw_event event);
-
-	struct ntb_db_cb *db_cb;
-	unsigned char hw_type;
-	unsigned char conn_type;
-	unsigned char dev_type;
-	unsigned char num_msix;
-	unsigned char bits_per_vector;
-	unsigned char max_cbs;
-	unsigned char link_width;
-	unsigned char link_speed;
-	unsigned char link_status;
-	unsigned char split_bar;
-
-	struct delayed_work hb_timer;
-	unsigned long last_ts;
-
-	struct delayed_work lr_timer;
-
-	struct dentry *debugfs_dir;
-	struct dentry *debugfs_info;
-
-	unsigned int wa_flags;
-};
-
-/**
- * ntb_max_cbs() - return the max callbacks
- * @ndev: pointer to ntb_device instance
- *
- * Given the ntb pointer, return the maximum number of callbacks
- *
- * RETURNS: the maximum number of callbacks
- */
-static inline unsigned char ntb_max_cbs(struct ntb_device *ndev)
-{
-	return ndev->max_cbs;
-}
-
-/**
- * ntb_max_mw() - return the max number of memory windows
- * @ndev: pointer to ntb_device instance
- *
- * Given the ntb pointer, return the maximum number of memory windows
- *
- * RETURNS: the maximum number of memory windows
- */
-static inline unsigned char ntb_max_mw(struct ntb_device *ndev)
-{
-	return ndev->limits.max_mw;
-}
-
-/**
- * ntb_hw_link_status() - return the hardware link status
- * @ndev: pointer to ntb_device instance
- *
- * Returns true if the hardware is connected to the remote system
- *
- * RETURNS: true or false based on the hardware link state
- */
-static inline bool ntb_hw_link_status(struct ntb_device *ndev)
-{
-	return ndev->link_status == NTB_LINK_UP;
-}
-
-/**
- * ntb_query_pdev() - return the pci_dev pointer
- * @ndev: pointer to ntb_device instance
- *
- * Given the ntb pointer, return the pci_dev pointer for the NTB hardware device
- *
- * RETURNS: a pointer to the ntb pci_dev
- */
-static inline struct pci_dev *ntb_query_pdev(struct ntb_device *ndev)
-{
-	return ndev->pdev;
-}
-
-/**
- * ntb_query_debugfs() - return the debugfs pointer
- * @ndev: pointer to ntb_device instance
- *
- * Given the ntb pointer, return the debugfs directory pointer for the NTB
- * hardware device
- *
- * RETURNS: a pointer to the debugfs directory
- */
-static inline struct dentry *ntb_query_debugfs(struct ntb_device *ndev)
-{
-	return ndev->debugfs_dir;
-}
-
-struct ntb_device *ntb_register_transport(struct pci_dev *pdev,
-					  void *transport);
-void ntb_unregister_transport(struct ntb_device *ndev);
-void ntb_set_mw_addr(struct ntb_device *ndev, unsigned int mw, u64 addr);
-int ntb_register_db_callback(struct ntb_device *ndev, unsigned int idx,
-			     void *data, int (*db_cb_func)(void *data,
-							   int db_num));
-void ntb_unregister_db_callback(struct ntb_device *ndev, unsigned int idx);
-int ntb_register_event_callback(struct ntb_device *ndev,
-				void (*event_cb_func)(void *handle,
-						      enum ntb_hw_event event));
-void ntb_unregister_event_callback(struct ntb_device *ndev);
-int ntb_get_max_spads(struct ntb_device *ndev);
-int ntb_write_local_spad(struct ntb_device *ndev, unsigned int idx, u32 val);
-int ntb_read_local_spad(struct ntb_device *ndev, unsigned int idx, u32 *val);
-int ntb_write_remote_spad(struct ntb_device *ndev, unsigned int idx, u32 val);
-int ntb_read_remote_spad(struct ntb_device *ndev, unsigned int idx, u32 *val);
-resource_size_t ntb_get_mw_base(struct ntb_device *ndev, unsigned int mw);
-void __iomem *ntb_get_mw_vbase(struct ntb_device *ndev, unsigned int mw);
-u64 ntb_get_mw_size(struct ntb_device *ndev, unsigned int mw);
-void ntb_ring_doorbell(struct ntb_device *ndev, unsigned int idx);
-void *ntb_find_transport(struct pci_dev *pdev);
-
-int ntb_transport_init(struct pci_dev *pdev);
-void ntb_transport_free(void *transport);
diff --git a/drivers/ntb/ntb_regs.h b/drivers/ntb/ntb_regs.h
deleted file mode 100644
index f028ff8..0000000
--- a/drivers/ntb/ntb_regs.h
+++ /dev/null
@@ -1,177 +0,0 @@
-/*
- * This file is provided under a dual BSD/GPLv2 license.  When using or
- *   redistributing this file, you may do so under either license.
- *
- *   GPL LICENSE SUMMARY
- *
- *   Copyright(c) 2012 Intel Corporation. All rights reserved.
- *
- *   This program is free software; you can redistribute it and/or modify
- *   it under the terms of version 2 of the GNU General Public License as
- *   published by the Free Software Foundation.
- *
- *   BSD LICENSE
- *
- *   Copyright(c) 2012 Intel Corporation. All rights reserved.
- *
- *   Redistribution and use in source and binary forms, with or without
- *   modification, are permitted provided that the following conditions
- *   are met:
- *
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copy
- *       notice, this list of conditions and the following disclaimer in
- *       the documentation and/or other materials provided with the
- *       distribution.
- *     * Neither the name of Intel Corporation nor the names of its
- *       contributors may be used to endorse or promote products derived
- *       from this software without specific prior written permission.
- *
- *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * Intel PCIe NTB Linux driver
- *
- * Contact Information:
- * Jon Mason <jon.mason@intel.com>
- */
-
-#define NTB_LINK_STATUS_ACTIVE	0x2000
-#define NTB_LINK_SPEED_MASK	0x000f
-#define NTB_LINK_WIDTH_MASK	0x03f0
-
-#define SNB_MSIX_CNT		4
-#define SNB_MAX_B2B_SPADS	16
-#define SNB_MAX_COMPAT_SPADS	16
-/* Reserve the uppermost bit for link interrupt */
-#define SNB_MAX_DB_BITS		15
-#define SNB_LINK_DB		15
-#define SNB_DB_BITS_PER_VEC	5
-#define HSX_SPLITBAR_MAX_MW	3
-#define SNB_MAX_MW		2
-#define SNB_ERRATA_MAX_MW	1
-
-#define SNB_DB_HW_LINK		0x8000
-
-#define SNB_UNCERRSTS_OFFSET	0x014C
-#define SNB_CORERRSTS_OFFSET	0x0158
-#define SNB_LINK_STATUS_OFFSET	0x01A2
-#define SNB_PCICMD_OFFSET	0x0504
-#define SNB_DEVCTRL_OFFSET	0x0598
-#define SNB_DEVSTS_OFFSET	0x059A
-#define SNB_SLINK_STATUS_OFFSET	0x05A2
-
-#define SNB_PBAR2LMT_OFFSET	0x0000
-#define SNB_PBAR4LMT_OFFSET	0x0008
-#define SNB_PBAR5LMT_OFFSET	0x000C
-#define SNB_PBAR2XLAT_OFFSET	0x0010
-#define SNB_PBAR4XLAT_OFFSET	0x0018
-#define SNB_PBAR5XLAT_OFFSET	0x001C
-#define SNB_SBAR2LMT_OFFSET	0x0020
-#define SNB_SBAR4LMT_OFFSET	0x0028
-#define SNB_SBAR5LMT_OFFSET	0x002C
-#define SNB_SBAR2XLAT_OFFSET	0x0030
-#define SNB_SBAR4XLAT_OFFSET	0x0038
-#define SNB_SBAR5XLAT_OFFSET	0x003C
-#define SNB_SBAR0BASE_OFFSET	0x0040
-#define SNB_SBAR2BASE_OFFSET	0x0048
-#define SNB_SBAR4BASE_OFFSET	0x0050
-#define SNB_SBAR5BASE_OFFSET	0x0054
-#define SNB_NTBCNTL_OFFSET	0x0058
-#define SNB_SBDF_OFFSET		0x005C
-#define SNB_PDOORBELL_OFFSET	0x0060
-#define SNB_PDBMSK_OFFSET	0x0062
-#define SNB_SDOORBELL_OFFSET	0x0064
-#define SNB_SDBMSK_OFFSET	0x0066
-#define SNB_USMEMMISS_OFFSET	0x0070
-#define SNB_SPAD_OFFSET		0x0080
-#define SNB_SPADSEMA4_OFFSET	0x00c0
-#define SNB_WCCNTRL_OFFSET	0x00e0
-#define SNB_B2B_SPAD_OFFSET	0x0100
-#define SNB_B2B_DOORBELL_OFFSET	0x0140
-#define SNB_B2B_XLAT_OFFSETL	0x0144
-#define SNB_B2B_XLAT_OFFSETU	0x0148
-
-/*
- * The addresses are setup so the 32bit BARs can function. Thus
- * the addresses are all in 32bit space
- */
-#define SNB_MBAR01_USD_ADDR	0x000000002100000CULL
-#define SNB_MBAR23_USD_ADDR	0x000000004100000CULL
-#define SNB_MBAR4_USD_ADDR	0x000000008100000CULL
-#define SNB_MBAR5_USD_ADDR	0x00000000A100000CULL
-#define SNB_MBAR01_DSD_ADDR	0x000000002000000CULL
-#define SNB_MBAR23_DSD_ADDR	0x000000004000000CULL
-#define SNB_MBAR4_DSD_ADDR	0x000000008000000CULL
-#define SNB_MBAR5_DSD_ADDR	0x00000000A000000CULL
-
-#define BWD_MSIX_CNT		34
-#define BWD_MAX_SPADS		16
-#define BWD_MAX_DB_BITS		34
-#define BWD_DB_BITS_PER_VEC	1
-#define BWD_MAX_MW		2
-
-#define BWD_PCICMD_OFFSET	0xb004
-#define BWD_MBAR23_OFFSET	0xb018
-#define BWD_MBAR45_OFFSET	0xb020
-#define BWD_DEVCTRL_OFFSET	0xb048
-#define BWD_LINK_STATUS_OFFSET	0xb052
-#define BWD_ERRCORSTS_OFFSET	0xb110
-
-#define BWD_SBAR2XLAT_OFFSET	0x0008
-#define BWD_SBAR4XLAT_OFFSET	0x0010
-#define BWD_PDOORBELL_OFFSET	0x0020
-#define BWD_PDBMSK_OFFSET	0x0028
-#define BWD_NTBCNTL_OFFSET	0x0060
-#define BWD_EBDF_OFFSET		0x0064
-#define BWD_SPAD_OFFSET		0x0080
-#define BWD_SPADSEMA_OFFSET	0x00c0
-#define BWD_STKYSPAD_OFFSET	0x00c4
-#define BWD_PBAR2XLAT_OFFSET	0x8008
-#define BWD_PBAR4XLAT_OFFSET	0x8010
-#define BWD_B2B_DOORBELL_OFFSET	0x8020
-#define BWD_B2B_SPAD_OFFSET	0x8080
-#define BWD_B2B_SPADSEMA_OFFSET	0x80c0
-#define BWD_B2B_STKYSPAD_OFFSET	0x80c4
-
-#define BWD_MODPHY_PCSREG4	0x1c004
-#define BWD_MODPHY_PCSREG6	0x1c006
-
-#define BWD_IP_BASE		0xC000
-#define BWD_DESKEWSTS_OFFSET	(BWD_IP_BASE + 0x3024)
-#define BWD_LTSSMERRSTS0_OFFSET (BWD_IP_BASE + 0x3180)
-#define BWD_LTSSMSTATEJMP_OFFSET	(BWD_IP_BASE + 0x3040)
-#define BWD_IBSTERRRCRVSTS0_OFFSET	(BWD_IP_BASE + 0x3324)
-
-#define BWD_DESKEWSTS_DBERR	(1 << 15)
-#define BWD_LTSSMERRSTS0_UNEXPECTEDEI	(1 << 20)
-#define BWD_LTSSMSTATEJMP_FORCEDETECT	(1 << 2)
-#define BWD_IBIST_ERR_OFLOW	0x7FFF7FFF
-
-#define NTB_CNTL_CFG_LOCK		(1 << 0)
-#define NTB_CNTL_LINK_DISABLE		(1 << 1)
-#define NTB_CNTL_S2P_BAR23_SNOOP	(1 << 2)
-#define NTB_CNTL_P2S_BAR23_SNOOP	(1 << 4)
-#define NTB_CNTL_S2P_BAR4_SNOOP	(1 << 6)
-#define NTB_CNTL_P2S_BAR4_SNOOP	(1 << 8)
-#define NTB_CNTL_S2P_BAR5_SNOOP	(1 << 12)
-#define NTB_CNTL_P2S_BAR5_SNOOP	(1 << 14)
-#define BWD_CNTL_LINK_DOWN		(1 << 16)
-
-#define NTB_PPD_OFFSET		0x00D4
-#define SNB_PPD_CONN_TYPE	0x0003
-#define SNB_PPD_DEV_TYPE	0x0010
-#define SNB_PPD_SPLIT_BAR	(1 << 6)
-#define BWD_PPD_INIT_LINK	0x0008
-#define BWD_PPD_CONN_TYPE	0x0300
-#define BWD_PPD_DEV_TYPE	0x1000
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index e9bf2f4..efe3ad4 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -5,6 +5,7 @@
  *   GPL LICENSE SUMMARY
  *
  *   Copyright(c) 2012 Intel Corporation. All rights reserved.
+ *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
  *
  *   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
@@ -13,6 +14,7 @@
  *   BSD LICENSE
  *
  *   Copyright(c) 2012 Intel Corporation. All rights reserved.
+ *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
  *
  *   Redistribution and use in source and binary forms, with or without
  *   modification, are permitted provided that the following conditions
@@ -40,7 +42,7 @@
  *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
  *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
- * Intel PCIe NTB Linux driver
+ * PCIe NTB Transport Linux driver
  *
  * Contact Information:
  * Jon Mason <jon.mason@intel.com>
@@ -56,11 +58,25 @@
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/types.h>
-#include "ntb_hw.h"
+#include <linux/uaccess.h>
+#include "linux/ntb.h"
+#include "linux/ntb_transport.h"
 
-#define NTB_TRANSPORT_VERSION	3
+#define NTB_TRANSPORT_VERSION	4
+#define NTB_TRANSPORT_VER	"4"
+#define NTB_TRANSPORT_NAME	"ntb_transport"
+#define NTB_TRANSPORT_DESC	"Software Queue-Pair Transport over NTB"
 
-static unsigned int transport_mtu = 0x401E;
+MODULE_DESCRIPTION(NTB_TRANSPORT_DESC);
+MODULE_VERSION(NTB_TRANSPORT_VER);
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Intel Corporation");
+
+static unsigned long max_mw_size;
+module_param(max_mw_size, ulong, 0644);
+MODULE_PARM_DESC(max_mw_size, "Limit size of large memory windows");
+
+static unsigned int transport_mtu = 0x10000;
 module_param(transport_mtu, uint, 0644);
 MODULE_PARM_DESC(transport_mtu, "Maximum size of NTB transport packets");
 
@@ -72,10 +88,16 @@
 module_param(copy_bytes, uint, 0644);
 MODULE_PARM_DESC(copy_bytes, "Threshold under which NTB will use the CPU to copy instead of DMA");
 
+static bool use_dma;
+module_param(use_dma, bool, 0644);
+MODULE_PARM_DESC(use_dma, "Use DMA engine to perform large data copy");
+
+static struct dentry *nt_debugfs_dir;
+
 struct ntb_queue_entry {
 	/* ntb_queue list reference */
 	struct list_head entry;
-	/* pointers to data to be transfered */
+	/* pointers to data to be transferred */
 	void *cb_data;
 	void *buf;
 	unsigned int len;
@@ -94,14 +116,16 @@
 };
 
 struct ntb_transport_qp {
-	struct ntb_transport *transport;
-	struct ntb_device *ndev;
+	struct ntb_transport_ctx *transport;
+	struct ntb_dev *ndev;
 	void *cb_data;
 	struct dma_chan *dma_chan;
 
 	bool client_ready;
-	bool qp_link;
+	bool link_is_up;
+
 	u8 qp_num;	/* Only 64 QP's are allowed.  0-63 */
+	u64 qp_bit;
 
 	struct ntb_rx_info __iomem *rx_info;
 	struct ntb_rx_info *remote_rx_info;
@@ -127,6 +151,7 @@
 	unsigned int rx_max_entry;
 	unsigned int rx_max_frame;
 	dma_cookie_t last_cookie;
+	struct tasklet_struct rxc_db_work;
 
 	void (*event_handler)(void *data, int status);
 	struct delayed_work link_work;
@@ -153,33 +178,44 @@
 };
 
 struct ntb_transport_mw {
-	size_t size;
+	phys_addr_t phys_addr;
+	resource_size_t phys_size;
+	resource_size_t xlat_align;
+	resource_size_t xlat_align_size;
+	void __iomem *vbase;
+	size_t xlat_size;
+	size_t buff_size;
 	void *virt_addr;
 	dma_addr_t dma_addr;
 };
 
 struct ntb_transport_client_dev {
 	struct list_head entry;
+	struct ntb_transport_ctx *nt;
 	struct device dev;
 };
 
-struct ntb_transport {
+struct ntb_transport_ctx {
 	struct list_head entry;
 	struct list_head client_devs;
 
-	struct ntb_device *ndev;
-	struct ntb_transport_mw *mw;
-	struct ntb_transport_qp *qps;
-	unsigned int max_qps;
-	unsigned long qp_bitmap;
-	bool transport_link;
+	struct ntb_dev *ndev;
+
+	struct ntb_transport_mw *mw_vec;
+	struct ntb_transport_qp *qp_vec;
+	unsigned int mw_count;
+	unsigned int qp_count;
+	u64 qp_bitmap;
+	u64 qp_bitmap_free;
+
+	bool link_is_up;
 	struct delayed_work link_work;
 	struct work_struct link_cleanup;
 };
 
 enum {
-	DESC_DONE_FLAG = 1 << 0,
-	LINK_DOWN_FLAG = 1 << 1,
+	DESC_DONE_FLAG = BIT(0),
+	LINK_DOWN_FLAG = BIT(1),
 };
 
 struct ntb_payload_header {
@@ -200,68 +236,69 @@
 	MAX_SPAD,
 };
 
-#define QP_TO_MW(ndev, qp)	((qp) % ntb_max_mw(ndev))
+#define dev_client_dev(__dev) \
+	container_of((__dev), struct ntb_transport_client_dev, dev)
+
+#define drv_client(__drv) \
+	container_of((__drv), struct ntb_transport_client, driver)
+
+#define QP_TO_MW(nt, qp)	((qp) % nt->mw_count)
 #define NTB_QP_DEF_NUM_ENTRIES	100
 #define NTB_LINK_DOWN_TIMEOUT	10
 
-static int ntb_match_bus(struct device *dev, struct device_driver *drv)
+static void ntb_transport_rxc_db(unsigned long data);
+static const struct ntb_ctx_ops ntb_transport_ops;
+static struct ntb_client ntb_transport_client;
+
+static int ntb_transport_bus_match(struct device *dev,
+				   struct device_driver *drv)
 {
 	return !strncmp(dev_name(dev), drv->name, strlen(drv->name));
 }
 
-static int ntb_client_probe(struct device *dev)
+static int ntb_transport_bus_probe(struct device *dev)
 {
-	const struct ntb_client *drv = container_of(dev->driver,
-						    struct ntb_client, driver);
-	struct pci_dev *pdev = container_of(dev->parent, struct pci_dev, dev);
+	const struct ntb_transport_client *client;
 	int rc = -EINVAL;
 
 	get_device(dev);
-	if (drv && drv->probe)
-		rc = drv->probe(pdev);
+
+	client = drv_client(dev->driver);
+	rc = client->probe(dev);
 	if (rc)
 		put_device(dev);
 
 	return rc;
 }
 
-static int ntb_client_remove(struct device *dev)
+static int ntb_transport_bus_remove(struct device *dev)
 {
-	const struct ntb_client *drv = container_of(dev->driver,
-						    struct ntb_client, driver);
-	struct pci_dev *pdev = container_of(dev->parent, struct pci_dev, dev);
+	const struct ntb_transport_client *client;
 
-	if (drv && drv->remove)
-		drv->remove(pdev);
+	client = drv_client(dev->driver);
+	client->remove(dev);
 
 	put_device(dev);
 
 	return 0;
 }
 
-static struct bus_type ntb_bus_type = {
-	.name = "ntb_bus",
-	.match = ntb_match_bus,
-	.probe = ntb_client_probe,
-	.remove = ntb_client_remove,
+static struct bus_type ntb_transport_bus = {
+	.name = "ntb_transport",
+	.match = ntb_transport_bus_match,
+	.probe = ntb_transport_bus_probe,
+	.remove = ntb_transport_bus_remove,
 };
 
 static LIST_HEAD(ntb_transport_list);
 
-static int ntb_bus_init(struct ntb_transport *nt)
+static int ntb_bus_init(struct ntb_transport_ctx *nt)
 {
-	if (list_empty(&ntb_transport_list)) {
-		int rc = bus_register(&ntb_bus_type);
-		if (rc)
-			return rc;
-	}
-
 	list_add(&nt->entry, &ntb_transport_list);
-
 	return 0;
 }
 
-static void ntb_bus_remove(struct ntb_transport *nt)
+static void ntb_bus_remove(struct ntb_transport_ctx *nt)
 {
 	struct ntb_transport_client_dev *client_dev, *cd;
 
@@ -273,29 +310,26 @@
 	}
 
 	list_del(&nt->entry);
-
-	if (list_empty(&ntb_transport_list))
-		bus_unregister(&ntb_bus_type);
 }
 
-static void ntb_client_release(struct device *dev)
+static void ntb_transport_client_release(struct device *dev)
 {
 	struct ntb_transport_client_dev *client_dev;
-	client_dev = container_of(dev, struct ntb_transport_client_dev, dev);
 
+	client_dev = dev_client_dev(dev);
 	kfree(client_dev);
 }
 
 /**
- * ntb_unregister_client_dev - Unregister NTB client device
+ * ntb_transport_unregister_client_dev - Unregister NTB client device
  * @device_name: Name of NTB client device
  *
  * Unregister an NTB client device with the NTB transport layer
  */
-void ntb_unregister_client_dev(char *device_name)
+void ntb_transport_unregister_client_dev(char *device_name)
 {
 	struct ntb_transport_client_dev *client, *cd;
-	struct ntb_transport *nt;
+	struct ntb_transport_ctx *nt;
 
 	list_for_each_entry(nt, &ntb_transport_list, entry)
 		list_for_each_entry_safe(client, cd, &nt->client_devs, entry)
@@ -305,18 +339,19 @@
 				device_unregister(&client->dev);
 			}
 }
-EXPORT_SYMBOL_GPL(ntb_unregister_client_dev);
+EXPORT_SYMBOL_GPL(ntb_transport_unregister_client_dev);
 
 /**
- * ntb_register_client_dev - Register NTB client device
+ * ntb_transport_register_client_dev - Register NTB client device
  * @device_name: Name of NTB client device
  *
  * Register an NTB client device with the NTB transport layer
  */
-int ntb_register_client_dev(char *device_name)
+int ntb_transport_register_client_dev(char *device_name)
 {
 	struct ntb_transport_client_dev *client_dev;
-	struct ntb_transport *nt;
+	struct ntb_transport_ctx *nt;
+	int node;
 	int rc, i = 0;
 
 	if (list_empty(&ntb_transport_list))
@@ -325,8 +360,10 @@
 	list_for_each_entry(nt, &ntb_transport_list, entry) {
 		struct device *dev;
 
-		client_dev = kzalloc(sizeof(struct ntb_transport_client_dev),
-				     GFP_KERNEL);
+		node = dev_to_node(&nt->ndev->dev);
+
+		client_dev = kzalloc_node(sizeof(*client_dev),
+					  GFP_KERNEL, node);
 		if (!client_dev) {
 			rc = -ENOMEM;
 			goto err;
@@ -336,9 +373,9 @@
 
 		/* setup and register client devices */
 		dev_set_name(dev, "%s%d", device_name, i);
-		dev->bus = &ntb_bus_type;
-		dev->release = ntb_client_release;
-		dev->parent = &ntb_query_pdev(nt->ndev)->dev;
+		dev->bus = &ntb_transport_bus;
+		dev->release = ntb_transport_client_release;
+		dev->parent = &nt->ndev->dev;
 
 		rc = device_register(dev);
 		if (rc) {
@@ -353,44 +390,44 @@
 	return 0;
 
 err:
-	ntb_unregister_client_dev(device_name);
+	ntb_transport_unregister_client_dev(device_name);
 
 	return rc;
 }
-EXPORT_SYMBOL_GPL(ntb_register_client_dev);
+EXPORT_SYMBOL_GPL(ntb_transport_register_client_dev);
 
 /**
- * ntb_register_client - Register NTB client driver
+ * ntb_transport_register_client - Register NTB client driver
  * @drv: NTB client driver to be registered
  *
  * Register an NTB client driver with the NTB transport layer
  *
  * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
  */
-int ntb_register_client(struct ntb_client *drv)
+int ntb_transport_register_client(struct ntb_transport_client *drv)
 {
-	drv->driver.bus = &ntb_bus_type;
+	drv->driver.bus = &ntb_transport_bus;
 
 	if (list_empty(&ntb_transport_list))
 		return -ENODEV;
 
 	return driver_register(&drv->driver);
 }
-EXPORT_SYMBOL_GPL(ntb_register_client);
+EXPORT_SYMBOL_GPL(ntb_transport_register_client);
 
 /**
- * ntb_unregister_client - Unregister NTB client driver
+ * ntb_transport_unregister_client - Unregister NTB client driver
  * @drv: NTB client driver to be unregistered
  *
  * Unregister an NTB client driver with the NTB transport layer
  *
  * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
  */
-void ntb_unregister_client(struct ntb_client *drv)
+void ntb_transport_unregister_client(struct ntb_transport_client *drv)
 {
 	driver_unregister(&drv->driver);
 }
-EXPORT_SYMBOL_GPL(ntb_unregister_client);
+EXPORT_SYMBOL_GPL(ntb_transport_unregister_client);
 
 static ssize_t debugfs_read(struct file *filp, char __user *ubuf, size_t count,
 			    loff_t *offp)
@@ -452,8 +489,8 @@
 			       "tx_max_entry - \t%u\n", qp->tx_max_entry);
 
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
-			       "\nQP Link %s\n", (qp->qp_link == NTB_LINK_UP) ?
-			       "Up" : "Down");
+			       "\nQP Link %s\n",
+			       qp->link_is_up ? "Up" : "Down");
 	if (out_offset > out_count)
 		out_offset = out_count;
 
@@ -497,26 +534,31 @@
 	return entry;
 }
 
-static void ntb_transport_setup_qp_mw(struct ntb_transport *nt,
-				      unsigned int qp_num)
+static int ntb_transport_setup_qp_mw(struct ntb_transport_ctx *nt,
+				     unsigned int qp_num)
 {
-	struct ntb_transport_qp *qp = &nt->qps[qp_num];
+	struct ntb_transport_qp *qp = &nt->qp_vec[qp_num];
+	struct ntb_transport_mw *mw;
 	unsigned int rx_size, num_qps_mw;
-	u8 mw_num, mw_max;
+	unsigned int mw_num, mw_count, qp_count;
 	unsigned int i;
 
-	mw_max = ntb_max_mw(nt->ndev);
-	mw_num = QP_TO_MW(nt->ndev, qp_num);
+	mw_count = nt->mw_count;
+	qp_count = nt->qp_count;
 
-	WARN_ON(nt->mw[mw_num].virt_addr == NULL);
+	mw_num = QP_TO_MW(nt, qp_num);
+	mw = &nt->mw_vec[mw_num];
 
-	if (nt->max_qps % mw_max && mw_num + 1 < nt->max_qps / mw_max)
-		num_qps_mw = nt->max_qps / mw_max + 1;
+	if (!mw->virt_addr)
+		return -ENOMEM;
+
+	if (qp_count % mw_count && mw_num + 1 < qp_count / mw_count)
+		num_qps_mw = qp_count / mw_count + 1;
 	else
-		num_qps_mw = nt->max_qps / mw_max;
+		num_qps_mw = qp_count / mw_count;
 
-	rx_size = (unsigned int) nt->mw[mw_num].size / num_qps_mw;
-	qp->rx_buff = nt->mw[mw_num].virt_addr + qp_num / mw_max * rx_size;
+	rx_size = (unsigned int)mw->xlat_size / num_qps_mw;
+	qp->rx_buff = mw->virt_addr + rx_size * qp_num / mw_count;
 	rx_size -= sizeof(struct ntb_rx_info);
 
 	qp->remote_rx_info = qp->rx_buff + rx_size;
@@ -530,49 +572,63 @@
 
 	/* setup the hdr offsets with 0's */
 	for (i = 0; i < qp->rx_max_entry; i++) {
-		void *offset = qp->rx_buff + qp->rx_max_frame * (i + 1) -
-			       sizeof(struct ntb_payload_header);
+		void *offset = (qp->rx_buff + qp->rx_max_frame * (i + 1) -
+				sizeof(struct ntb_payload_header));
 		memset(offset, 0, sizeof(struct ntb_payload_header));
 	}
 
 	qp->rx_pkts = 0;
 	qp->tx_pkts = 0;
 	qp->tx_index = 0;
+
+	return 0;
 }
 
-static void ntb_free_mw(struct ntb_transport *nt, int num_mw)
+static void ntb_free_mw(struct ntb_transport_ctx *nt, int num_mw)
 {
-	struct ntb_transport_mw *mw = &nt->mw[num_mw];
-	struct pci_dev *pdev = ntb_query_pdev(nt->ndev);
+	struct ntb_transport_mw *mw = &nt->mw_vec[num_mw];
+	struct pci_dev *pdev = nt->ndev->pdev;
 
 	if (!mw->virt_addr)
 		return;
 
-	dma_free_coherent(&pdev->dev, mw->size, mw->virt_addr, mw->dma_addr);
+	ntb_mw_clear_trans(nt->ndev, num_mw);
+	dma_free_coherent(&pdev->dev, mw->buff_size,
+			  mw->virt_addr, mw->dma_addr);
+	mw->xlat_size = 0;
+	mw->buff_size = 0;
 	mw->virt_addr = NULL;
 }
 
-static int ntb_set_mw(struct ntb_transport *nt, int num_mw, unsigned int size)
+static int ntb_set_mw(struct ntb_transport_ctx *nt, int num_mw,
+		      unsigned int size)
 {
-	struct ntb_transport_mw *mw = &nt->mw[num_mw];
-	struct pci_dev *pdev = ntb_query_pdev(nt->ndev);
+	struct ntb_transport_mw *mw = &nt->mw_vec[num_mw];
+	struct pci_dev *pdev = nt->ndev->pdev;
+	unsigned int xlat_size, buff_size;
+	int rc;
+
+	xlat_size = round_up(size, mw->xlat_align_size);
+	buff_size = round_up(size, mw->xlat_align);
 
 	/* No need to re-setup */
-	if (mw->size == ALIGN(size, 4096))
+	if (mw->xlat_size == xlat_size)
 		return 0;
 
-	if (mw->size != 0)
+	if (mw->buff_size)
 		ntb_free_mw(nt, num_mw);
 
-	/* Alloc memory for receiving data.  Must be 4k aligned */
-	mw->size = ALIGN(size, 4096);
+	/* Alloc memory for receiving data.  Must be aligned */
+	mw->xlat_size = xlat_size;
+	mw->buff_size = buff_size;
 
-	mw->virt_addr = dma_alloc_coherent(&pdev->dev, mw->size, &mw->dma_addr,
-					   GFP_KERNEL);
+	mw->virt_addr = dma_alloc_coherent(&pdev->dev, buff_size,
+					   &mw->dma_addr, GFP_KERNEL);
 	if (!mw->virt_addr) {
-		mw->size = 0;
-		dev_err(&pdev->dev, "Unable to allocate MW buffer of size %d\n",
-		       (int) mw->size);
+		mw->xlat_size = 0;
+		mw->buff_size = 0;
+		dev_err(&pdev->dev, "Unable to alloc MW buff of size %d\n",
+			buff_size);
 		return -ENOMEM;
 	}
 
@@ -582,34 +638,58 @@
 	 * is a requirement of the hardware. It is recommended to setup CMA
 	 * for BAR sizes equal or greater than 4MB.
 	 */
-	if (!IS_ALIGNED(mw->dma_addr, mw->size)) {
-		dev_err(&pdev->dev, "DMA memory %pad not aligned to BAR size\n",
+	if (!IS_ALIGNED(mw->dma_addr, mw->xlat_align)) {
+		dev_err(&pdev->dev, "DMA memory %pad is not aligned\n",
 			&mw->dma_addr);
 		ntb_free_mw(nt, num_mw);
 		return -ENOMEM;
 	}
 
 	/* Notify HW the memory location of the receive buffer */
-	ntb_set_mw_addr(nt->ndev, num_mw, mw->dma_addr);
+	rc = ntb_mw_set_trans(nt->ndev, num_mw, mw->dma_addr, mw->xlat_size);
+	if (rc) {
+		dev_err(&pdev->dev, "Unable to set mw%d translation", num_mw);
+		ntb_free_mw(nt, num_mw);
+		return -EIO;
+	}
 
 	return 0;
 }
 
+static void ntb_qp_link_down_reset(struct ntb_transport_qp *qp)
+{
+	qp->link_is_up = false;
+
+	qp->tx_index = 0;
+	qp->rx_index = 0;
+	qp->rx_bytes = 0;
+	qp->rx_pkts = 0;
+	qp->rx_ring_empty = 0;
+	qp->rx_err_no_buf = 0;
+	qp->rx_err_oflow = 0;
+	qp->rx_err_ver = 0;
+	qp->rx_memcpy = 0;
+	qp->rx_async = 0;
+	qp->tx_bytes = 0;
+	qp->tx_pkts = 0;
+	qp->tx_ring_full = 0;
+	qp->tx_err_no_buf = 0;
+	qp->tx_memcpy = 0;
+	qp->tx_async = 0;
+}
+
 static void ntb_qp_link_cleanup(struct ntb_transport_qp *qp)
 {
-	struct ntb_transport *nt = qp->transport;
-	struct pci_dev *pdev = ntb_query_pdev(nt->ndev);
+	struct ntb_transport_ctx *nt = qp->transport;
+	struct pci_dev *pdev = nt->ndev->pdev;
 
-	if (qp->qp_link == NTB_LINK_DOWN) {
-		cancel_delayed_work_sync(&qp->link_work);
-		return;
-	}
+	dev_info(&pdev->dev, "qp %d: Link Cleanup\n", qp->qp_num);
+
+	cancel_delayed_work_sync(&qp->link_work);
+	ntb_qp_link_down_reset(qp);
 
 	if (qp->event_handler)
-		qp->event_handler(qp->cb_data, NTB_LINK_DOWN);
-
-	dev_info(&pdev->dev, "qp %d: Link Down\n", qp->qp_num);
-	qp->qp_link = NTB_LINK_DOWN;
+		qp->event_handler(qp->cb_data, qp->link_is_up);
 }
 
 static void ntb_qp_link_cleanup_work(struct work_struct *work)
@@ -617,11 +697,11 @@
 	struct ntb_transport_qp *qp = container_of(work,
 						   struct ntb_transport_qp,
 						   link_cleanup);
-	struct ntb_transport *nt = qp->transport;
+	struct ntb_transport_ctx *nt = qp->transport;
 
 	ntb_qp_link_cleanup(qp);
 
-	if (nt->transport_link == NTB_LINK_UP)
+	if (nt->link_is_up)
 		schedule_delayed_work(&qp->link_work,
 				      msecs_to_jiffies(NTB_LINK_DOWN_TIMEOUT));
 }
@@ -631,180 +711,132 @@
 	schedule_work(&qp->link_cleanup);
 }
 
-static void ntb_transport_link_cleanup(struct ntb_transport *nt)
+static void ntb_transport_link_cleanup(struct ntb_transport_ctx *nt)
 {
+	struct ntb_transport_qp *qp;
+	u64 qp_bitmap_alloc;
 	int i;
 
-	/* Pass along the info to any clients */
-	for (i = 0; i < nt->max_qps; i++)
-		if (!test_bit(i, &nt->qp_bitmap))
-			ntb_qp_link_cleanup(&nt->qps[i]);
+	qp_bitmap_alloc = nt->qp_bitmap & ~nt->qp_bitmap_free;
 
-	if (nt->transport_link == NTB_LINK_DOWN)
+	/* Pass along the info to any clients */
+	for (i = 0; i < nt->qp_count; i++)
+		if (qp_bitmap_alloc & BIT_ULL(i)) {
+			qp = &nt->qp_vec[i];
+			ntb_qp_link_cleanup(qp);
+			cancel_work_sync(&qp->link_cleanup);
+			cancel_delayed_work_sync(&qp->link_work);
+		}
+
+	if (!nt->link_is_up)
 		cancel_delayed_work_sync(&nt->link_work);
-	else
-		nt->transport_link = NTB_LINK_DOWN;
 
 	/* The scratchpad registers keep the values if the remote side
 	 * goes down, blast them now to give them a sane value the next
 	 * time they are accessed
 	 */
 	for (i = 0; i < MAX_SPAD; i++)
-		ntb_write_local_spad(nt->ndev, i, 0);
+		ntb_spad_write(nt->ndev, i, 0);
 }
 
 static void ntb_transport_link_cleanup_work(struct work_struct *work)
 {
-	struct ntb_transport *nt = container_of(work, struct ntb_transport,
-						link_cleanup);
+	struct ntb_transport_ctx *nt =
+		container_of(work, struct ntb_transport_ctx, link_cleanup);
 
 	ntb_transport_link_cleanup(nt);
 }
 
-static void ntb_transport_event_callback(void *data, enum ntb_hw_event event)
+static void ntb_transport_event_callback(void *data)
 {
-	struct ntb_transport *nt = data;
+	struct ntb_transport_ctx *nt = data;
 
-	switch (event) {
-	case NTB_EVENT_HW_LINK_UP:
+	if (ntb_link_is_up(nt->ndev, NULL, NULL) == 1)
 		schedule_delayed_work(&nt->link_work, 0);
-		break;
-	case NTB_EVENT_HW_LINK_DOWN:
+	else
 		schedule_work(&nt->link_cleanup);
-		break;
-	default:
-		BUG();
-	}
 }
 
 static void ntb_transport_link_work(struct work_struct *work)
 {
-	struct ntb_transport *nt = container_of(work, struct ntb_transport,
-						link_work.work);
-	struct ntb_device *ndev = nt->ndev;
-	struct pci_dev *pdev = ntb_query_pdev(ndev);
+	struct ntb_transport_ctx *nt =
+		container_of(work, struct ntb_transport_ctx, link_work.work);
+	struct ntb_dev *ndev = nt->ndev;
+	struct pci_dev *pdev = ndev->pdev;
+	resource_size_t size;
 	u32 val;
-	int rc, i;
+	int rc, i, spad;
 
 	/* send the local info, in the opposite order of the way we read it */
-	for (i = 0; i < ntb_max_mw(ndev); i++) {
-		rc = ntb_write_remote_spad(ndev, MW0_SZ_HIGH + (i * 2),
-					   ntb_get_mw_size(ndev, i) >> 32);
-		if (rc) {
-			dev_err(&pdev->dev, "Error writing %u to remote spad %d\n",
-				(u32)(ntb_get_mw_size(ndev, i) >> 32),
-				MW0_SZ_HIGH + (i * 2));
-			goto out;
-		}
+	for (i = 0; i < nt->mw_count; i++) {
+		size = nt->mw_vec[i].phys_size;
 
-		rc = ntb_write_remote_spad(ndev, MW0_SZ_LOW + (i * 2),
-					   (u32) ntb_get_mw_size(ndev, i));
-		if (rc) {
-			dev_err(&pdev->dev, "Error writing %u to remote spad %d\n",
-				(u32) ntb_get_mw_size(ndev, i),
-				MW0_SZ_LOW + (i * 2));
-			goto out;
-		}
+		if (max_mw_size && size > max_mw_size)
+			size = max_mw_size;
+
+		spad = MW0_SZ_HIGH + (i * 2);
+		ntb_peer_spad_write(ndev, spad, (u32)(size >> 32));
+
+		spad = MW0_SZ_LOW + (i * 2);
+		ntb_peer_spad_write(ndev, spad, (u32)size);
 	}
 
-	rc = ntb_write_remote_spad(ndev, NUM_MWS, ntb_max_mw(ndev));
-	if (rc) {
-		dev_err(&pdev->dev, "Error writing %x to remote spad %d\n",
-			ntb_max_mw(ndev), NUM_MWS);
-		goto out;
-	}
+	ntb_peer_spad_write(ndev, NUM_MWS, nt->mw_count);
 
-	rc = ntb_write_remote_spad(ndev, NUM_QPS, nt->max_qps);
-	if (rc) {
-		dev_err(&pdev->dev, "Error writing %x to remote spad %d\n",
-			nt->max_qps, NUM_QPS);
-		goto out;
-	}
+	ntb_peer_spad_write(ndev, NUM_QPS, nt->qp_count);
 
-	rc = ntb_write_remote_spad(ndev, VERSION, NTB_TRANSPORT_VERSION);
-	if (rc) {
-		dev_err(&pdev->dev, "Error writing %x to remote spad %d\n",
-			NTB_TRANSPORT_VERSION, VERSION);
-		goto out;
-	}
+	ntb_peer_spad_write(ndev, VERSION, NTB_TRANSPORT_VERSION);
 
 	/* Query the remote side for its info */
-	rc = ntb_read_remote_spad(ndev, VERSION, &val);
-	if (rc) {
-		dev_err(&pdev->dev, "Error reading remote spad %d\n", VERSION);
-		goto out;
-	}
-
+	val = ntb_spad_read(ndev, VERSION);
+	dev_dbg(&pdev->dev, "Remote version = %d\n", val);
 	if (val != NTB_TRANSPORT_VERSION)
 		goto out;
-	dev_dbg(&pdev->dev, "Remote version = %d\n", val);
 
-	rc = ntb_read_remote_spad(ndev, NUM_QPS, &val);
-	if (rc) {
-		dev_err(&pdev->dev, "Error reading remote spad %d\n", NUM_QPS);
-		goto out;
-	}
-
-	if (val != nt->max_qps)
-		goto out;
+	val = ntb_spad_read(ndev, NUM_QPS);
 	dev_dbg(&pdev->dev, "Remote max number of qps = %d\n", val);
-
-	rc = ntb_read_remote_spad(ndev, NUM_MWS, &val);
-	if (rc) {
-		dev_err(&pdev->dev, "Error reading remote spad %d\n", NUM_MWS);
+	if (val != nt->qp_count)
 		goto out;
-	}
 
-	if (val != ntb_max_mw(ndev))
-		goto out;
+	val = ntb_spad_read(ndev, NUM_MWS);
 	dev_dbg(&pdev->dev, "Remote number of mws = %d\n", val);
+	if (val != nt->mw_count)
+		goto out;
 
-	for (i = 0; i < ntb_max_mw(ndev); i++) {
+	for (i = 0; i < nt->mw_count; i++) {
 		u64 val64;
 
-		rc = ntb_read_remote_spad(ndev, MW0_SZ_HIGH + (i * 2), &val);
-		if (rc) {
-			dev_err(&pdev->dev, "Error reading remote spad %d\n",
-				MW0_SZ_HIGH + (i * 2));
-			goto out1;
-		}
+		val = ntb_spad_read(ndev, MW0_SZ_HIGH + (i * 2));
+		val64 = (u64)val << 32;
 
-		val64 = (u64) val << 32;
-
-		rc = ntb_read_remote_spad(ndev, MW0_SZ_LOW + (i * 2), &val);
-		if (rc) {
-			dev_err(&pdev->dev, "Error reading remote spad %d\n",
-				MW0_SZ_LOW + (i * 2));
-			goto out1;
-		}
-
+		val = ntb_spad_read(ndev, MW0_SZ_LOW + (i * 2));
 		val64 |= val;
 
-		dev_dbg(&pdev->dev, "Remote MW%d size = %llu\n", i, val64);
+		dev_dbg(&pdev->dev, "Remote MW%d size = %#llx\n", i, val64);
 
 		rc = ntb_set_mw(nt, i, val64);
 		if (rc)
 			goto out1;
 	}
 
-	nt->transport_link = NTB_LINK_UP;
+	nt->link_is_up = true;
 
-	for (i = 0; i < nt->max_qps; i++) {
-		struct ntb_transport_qp *qp = &nt->qps[i];
+	for (i = 0; i < nt->qp_count; i++) {
+		struct ntb_transport_qp *qp = &nt->qp_vec[i];
 
 		ntb_transport_setup_qp_mw(nt, i);
 
-		if (qp->client_ready == NTB_LINK_UP)
+		if (qp->client_ready)
 			schedule_delayed_work(&qp->link_work, 0);
 	}
 
 	return;
 
 out1:
-	for (i = 0; i < ntb_max_mw(ndev); i++)
+	for (i = 0; i < nt->mw_count; i++)
 		ntb_free_mw(nt, i);
 out:
-	if (ntb_hw_link_status(ndev))
+	if (ntb_link_is_up(ndev, NULL, NULL) == 1)
 		schedule_delayed_work(&nt->link_work,
 				      msecs_to_jiffies(NTB_LINK_DOWN_TIMEOUT));
 }
@@ -814,73 +846,73 @@
 	struct ntb_transport_qp *qp = container_of(work,
 						   struct ntb_transport_qp,
 						   link_work.work);
-	struct pci_dev *pdev = ntb_query_pdev(qp->ndev);
-	struct ntb_transport *nt = qp->transport;
-	int rc, val;
+	struct pci_dev *pdev = qp->ndev->pdev;
+	struct ntb_transport_ctx *nt = qp->transport;
+	int val;
 
-	WARN_ON(nt->transport_link != NTB_LINK_UP);
+	WARN_ON(!nt->link_is_up);
 
-	rc = ntb_read_local_spad(nt->ndev, QP_LINKS, &val);
-	if (rc) {
-		dev_err(&pdev->dev, "Error reading spad %d\n", QP_LINKS);
-		return;
-	}
+	val = ntb_spad_read(nt->ndev, QP_LINKS);
 
-	rc = ntb_write_remote_spad(nt->ndev, QP_LINKS, val | 1 << qp->qp_num);
-	if (rc)
-		dev_err(&pdev->dev, "Error writing %x to remote spad %d\n",
-			val | 1 << qp->qp_num, QP_LINKS);
+	ntb_peer_spad_write(nt->ndev, QP_LINKS, val | BIT(qp->qp_num));
 
 	/* query remote spad for qp ready bits */
-	rc = ntb_read_remote_spad(nt->ndev, QP_LINKS, &val);
-	if (rc)
-		dev_err(&pdev->dev, "Error reading remote spad %d\n", QP_LINKS);
-
-	dev_dbg(&pdev->dev, "Remote QP link status = %x\n", val);
+	ntb_peer_spad_read(nt->ndev, QP_LINKS);
+	dev_dbg_ratelimited(&pdev->dev, "Remote QP link status = %x\n", val);
 
 	/* See if the remote side is up */
-	if (1 << qp->qp_num & val) {
-		qp->qp_link = NTB_LINK_UP;
-
+	if (val & BIT(qp->qp_num)) {
 		dev_info(&pdev->dev, "qp %d: Link Up\n", qp->qp_num);
+		qp->link_is_up = true;
+
 		if (qp->event_handler)
-			qp->event_handler(qp->cb_data, NTB_LINK_UP);
-	} else if (nt->transport_link == NTB_LINK_UP)
+			qp->event_handler(qp->cb_data, qp->link_is_up);
+	} else if (nt->link_is_up)
 		schedule_delayed_work(&qp->link_work,
 				      msecs_to_jiffies(NTB_LINK_DOWN_TIMEOUT));
 }
 
-static int ntb_transport_init_queue(struct ntb_transport *nt,
+static int ntb_transport_init_queue(struct ntb_transport_ctx *nt,
 				    unsigned int qp_num)
 {
 	struct ntb_transport_qp *qp;
+	struct ntb_transport_mw *mw;
+	phys_addr_t mw_base;
+	resource_size_t mw_size;
 	unsigned int num_qps_mw, tx_size;
-	u8 mw_num, mw_max;
+	unsigned int mw_num, mw_count, qp_count;
 	u64 qp_offset;
 
-	mw_max = ntb_max_mw(nt->ndev);
-	mw_num = QP_TO_MW(nt->ndev, qp_num);
+	mw_count = nt->mw_count;
+	qp_count = nt->qp_count;
 
-	qp = &nt->qps[qp_num];
+	mw_num = QP_TO_MW(nt, qp_num);
+	mw = &nt->mw_vec[mw_num];
+
+	qp = &nt->qp_vec[qp_num];
 	qp->qp_num = qp_num;
 	qp->transport = nt;
 	qp->ndev = nt->ndev;
-	qp->qp_link = NTB_LINK_DOWN;
-	qp->client_ready = NTB_LINK_DOWN;
+	qp->client_ready = false;
 	qp->event_handler = NULL;
+	ntb_qp_link_down_reset(qp);
 
-	if (nt->max_qps % mw_max && mw_num + 1 < nt->max_qps / mw_max)
-		num_qps_mw = nt->max_qps / mw_max + 1;
+	if (qp_count % mw_count && mw_num + 1 < qp_count / mw_count)
+		num_qps_mw = qp_count / mw_count + 1;
 	else
-		num_qps_mw = nt->max_qps / mw_max;
+		num_qps_mw = qp_count / mw_count;
 
-	tx_size = (unsigned int) ntb_get_mw_size(qp->ndev, mw_num) / num_qps_mw;
-	qp_offset = qp_num / mw_max * tx_size;
-	qp->tx_mw = ntb_get_mw_vbase(nt->ndev, mw_num) + qp_offset;
+	mw_base = nt->mw_vec[mw_num].phys_addr;
+	mw_size = nt->mw_vec[mw_num].phys_size;
+
+	tx_size = (unsigned int)mw_size / num_qps_mw;
+	qp_offset = tx_size * qp_num / mw_count;
+
+	qp->tx_mw = nt->mw_vec[mw_num].vbase + qp_offset;
 	if (!qp->tx_mw)
 		return -EINVAL;
 
-	qp->tx_mw_phys = ntb_get_mw_base(qp->ndev, mw_num) + qp_offset;
+	qp->tx_mw_phys = mw_base + qp_offset;
 	if (!qp->tx_mw_phys)
 		return -EINVAL;
 
@@ -891,16 +923,19 @@
 	qp->tx_max_frame = min(transport_mtu, tx_size / 2);
 	qp->tx_max_entry = tx_size / qp->tx_max_frame;
 
-	if (ntb_query_debugfs(nt->ndev)) {
+	if (nt_debugfs_dir) {
 		char debugfs_name[4];
 
 		snprintf(debugfs_name, 4, "qp%d", qp_num);
 		qp->debugfs_dir = debugfs_create_dir(debugfs_name,
-						 ntb_query_debugfs(nt->ndev));
+						     nt_debugfs_dir);
 
 		qp->debugfs_stats = debugfs_create_file("stats", S_IRUSR,
 							qp->debugfs_dir, qp,
 							&ntb_qp_debugfs_stats);
+	} else {
+		qp->debugfs_dir = NULL;
+		qp->debugfs_stats = NULL;
 	}
 
 	INIT_DELAYED_WORK(&qp->link_work, ntb_qp_link_work);
@@ -914,46 +949,89 @@
 	INIT_LIST_HEAD(&qp->rx_free_q);
 	INIT_LIST_HEAD(&qp->tx_free_q);
 
+	tasklet_init(&qp->rxc_db_work, ntb_transport_rxc_db,
+		     (unsigned long)qp);
+
 	return 0;
 }
 
-int ntb_transport_init(struct pci_dev *pdev)
+static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev)
 {
-	struct ntb_transport *nt;
+	struct ntb_transport_ctx *nt;
+	struct ntb_transport_mw *mw;
+	unsigned int mw_count, qp_count;
+	u64 qp_bitmap;
+	int node;
 	int rc, i;
 
-	nt = kzalloc(sizeof(struct ntb_transport), GFP_KERNEL);
+	if (ntb_db_is_unsafe(ndev))
+		dev_dbg(&ndev->dev,
+			"doorbell is unsafe, proceed anyway...\n");
+	if (ntb_spad_is_unsafe(ndev))
+		dev_dbg(&ndev->dev,
+			"scratchpad is unsafe, proceed anyway...\n");
+
+	node = dev_to_node(&ndev->dev);
+
+	nt = kzalloc_node(sizeof(*nt), GFP_KERNEL, node);
 	if (!nt)
 		return -ENOMEM;
 
-	nt->ndev = ntb_register_transport(pdev, nt);
-	if (!nt->ndev) {
-		rc = -EIO;
+	nt->ndev = ndev;
+
+	mw_count = ntb_mw_count(ndev);
+
+	nt->mw_count = mw_count;
+
+	nt->mw_vec = kzalloc_node(mw_count * sizeof(*nt->mw_vec),
+				  GFP_KERNEL, node);
+	if (!nt->mw_vec) {
+		rc = -ENOMEM;
 		goto err;
 	}
 
-	nt->mw = kcalloc(ntb_max_mw(nt->ndev), sizeof(struct ntb_transport_mw),
-			 GFP_KERNEL);
-	if (!nt->mw) {
-		rc = -ENOMEM;
-		goto err1;
+	for (i = 0; i < mw_count; i++) {
+		mw = &nt->mw_vec[i];
+
+		rc = ntb_mw_get_range(ndev, i, &mw->phys_addr, &mw->phys_size,
+				      &mw->xlat_align, &mw->xlat_align_size);
+		if (rc)
+			goto err1;
+
+		mw->vbase = ioremap_wc(mw->phys_addr, mw->phys_size);
+		if (!mw->vbase) {
+			rc = -ENOMEM;
+			goto err1;
+		}
+
+		mw->buff_size = 0;
+		mw->xlat_size = 0;
+		mw->virt_addr = NULL;
+		mw->dma_addr = 0;
 	}
 
-	if (max_num_clients)
-		nt->max_qps = min(ntb_max_cbs(nt->ndev), max_num_clients);
-	else
-		nt->max_qps = min(ntb_max_cbs(nt->ndev), ntb_max_mw(nt->ndev));
+	qp_bitmap = ntb_db_valid_mask(ndev);
 
-	nt->qps = kcalloc(nt->max_qps, sizeof(struct ntb_transport_qp),
-			  GFP_KERNEL);
-	if (!nt->qps) {
+	qp_count = ilog2(qp_bitmap);
+	if (max_num_clients && max_num_clients < qp_count)
+		qp_count = max_num_clients;
+	else if (mw_count < qp_count)
+		qp_count = mw_count;
+
+	qp_bitmap &= BIT_ULL(qp_count) - 1;
+
+	nt->qp_count = qp_count;
+	nt->qp_bitmap = qp_bitmap;
+	nt->qp_bitmap_free = qp_bitmap;
+
+	nt->qp_vec = kzalloc_node(qp_count * sizeof(*nt->qp_vec),
+				  GFP_KERNEL, node);
+	if (!nt->qp_vec) {
 		rc = -ENOMEM;
 		goto err2;
 	}
 
-	nt->qp_bitmap = ((u64) 1 << nt->max_qps) - 1;
-
-	for (i = 0; i < nt->max_qps; i++) {
+	for (i = 0; i < qp_count; i++) {
 		rc = ntb_transport_init_queue(nt, i);
 		if (rc)
 			goto err3;
@@ -962,8 +1040,7 @@
 	INIT_DELAYED_WORK(&nt->link_work, ntb_transport_link_work);
 	INIT_WORK(&nt->link_cleanup, ntb_transport_link_cleanup_work);
 
-	rc = ntb_register_event_callback(nt->ndev,
-					 ntb_transport_event_callback);
+	rc = ntb_set_ctx(ndev, nt, &ntb_transport_ops);
 	if (rc)
 		goto err3;
 
@@ -972,51 +1049,61 @@
 	if (rc)
 		goto err4;
 
-	if (ntb_hw_link_status(nt->ndev))
-		schedule_delayed_work(&nt->link_work, 0);
+	nt->link_is_up = false;
+	ntb_link_enable(ndev, NTB_SPEED_AUTO, NTB_WIDTH_AUTO);
+	ntb_link_event(ndev);
 
 	return 0;
 
 err4:
-	ntb_unregister_event_callback(nt->ndev);
+	ntb_clear_ctx(ndev);
 err3:
-	kfree(nt->qps);
+	kfree(nt->qp_vec);
 err2:
-	kfree(nt->mw);
+	kfree(nt->mw_vec);
 err1:
-	ntb_unregister_transport(nt->ndev);
+	while (i--) {
+		mw = &nt->mw_vec[i];
+		iounmap(mw->vbase);
+	}
 err:
 	kfree(nt);
 	return rc;
 }
 
-void ntb_transport_free(void *transport)
+static void ntb_transport_free(struct ntb_client *self, struct ntb_dev *ndev)
 {
-	struct ntb_transport *nt = transport;
-	struct ntb_device *ndev = nt->ndev;
+	struct ntb_transport_ctx *nt = ndev->ctx;
+	struct ntb_transport_qp *qp;
+	u64 qp_bitmap_alloc;
 	int i;
 
 	ntb_transport_link_cleanup(nt);
+	cancel_work_sync(&nt->link_cleanup);
+	cancel_delayed_work_sync(&nt->link_work);
+
+	qp_bitmap_alloc = nt->qp_bitmap & ~nt->qp_bitmap_free;
 
 	/* verify that all the qp's are freed */
-	for (i = 0; i < nt->max_qps; i++) {
-		if (!test_bit(i, &nt->qp_bitmap))
-			ntb_transport_free_queue(&nt->qps[i]);
-		debugfs_remove_recursive(nt->qps[i].debugfs_dir);
+	for (i = 0; i < nt->qp_count; i++) {
+		qp = &nt->qp_vec[i];
+		if (qp_bitmap_alloc & BIT_ULL(i))
+			ntb_transport_free_queue(qp);
+		debugfs_remove_recursive(qp->debugfs_dir);
 	}
 
+	ntb_link_disable(ndev);
+	ntb_clear_ctx(ndev);
+
 	ntb_bus_remove(nt);
 
-	cancel_delayed_work_sync(&nt->link_work);
-
-	ntb_unregister_event_callback(ndev);
-
-	for (i = 0; i < ntb_max_mw(ndev); i++)
+	for (i = nt->mw_count; i--; ) {
 		ntb_free_mw(nt, i);
+		iounmap(nt->mw_vec[i].vbase);
+	}
 
-	kfree(nt->qps);
-	kfree(nt->mw);
-	ntb_unregister_transport(ndev);
+	kfree(nt->qp_vec);
+	kfree(nt->mw_vec);
 	kfree(nt);
 }
 
@@ -1028,15 +1115,13 @@
 	unsigned int len = entry->len;
 	struct ntb_payload_header *hdr = entry->rx_hdr;
 
-	/* Ensure that the data is fully copied out before clearing the flag */
-	wmb();
 	hdr->flags = 0;
 
 	iowrite32(entry->index, &qp->rx_info->entry);
 
 	ntb_list_add(&qp->ntb_rx_free_q_lock, &entry->entry, &qp->rx_free_q);
 
-	if (qp->rx_handler && qp->client_ready == NTB_LINK_UP)
+	if (qp->rx_handler && qp->client_ready)
 		qp->rx_handler(qp, qp->cb_data, cb_data, len);
 }
 
@@ -1047,6 +1132,9 @@
 
 	memcpy(buf, offset, len);
 
+	/* Ensure that the data is fully copied out before clearing the flag */
+	wmb();
+
 	ntb_rx_copy_callback(entry);
 }
 
@@ -1071,8 +1159,8 @@
 		goto err_wait;
 
 	device = chan->device;
-	pay_off = (size_t) offset & ~PAGE_MASK;
-	buff_off = (size_t) buf & ~PAGE_MASK;
+	pay_off = (size_t)offset & ~PAGE_MASK;
+	buff_off = (size_t)buf & ~PAGE_MASK;
 
 	if (!is_dma_copy_aligned(device, pay_off, buff_off, len))
 		goto err_wait;
@@ -1138,86 +1226,103 @@
 	struct ntb_payload_header *hdr;
 	struct ntb_queue_entry *entry;
 	void *offset;
+	int rc;
 
 	offset = qp->rx_buff + qp->rx_max_frame * qp->rx_index;
 	hdr = offset + qp->rx_max_frame - sizeof(struct ntb_payload_header);
 
-	entry = ntb_list_rm(&qp->ntb_rx_pend_q_lock, &qp->rx_pend_q);
-	if (!entry) {
-		dev_dbg(&ntb_query_pdev(qp->ndev)->dev,
-			"no buffer - HDR ver %u, len %d, flags %x\n",
-			hdr->ver, hdr->len, hdr->flags);
-		qp->rx_err_no_buf++;
-		return -ENOMEM;
-	}
+	dev_dbg(&qp->ndev->pdev->dev, "qp %d: RX ver %u len %d flags %x\n",
+		qp->qp_num, hdr->ver, hdr->len, hdr->flags);
 
 	if (!(hdr->flags & DESC_DONE_FLAG)) {
-		ntb_list_add(&qp->ntb_rx_pend_q_lock, &entry->entry,
-			     &qp->rx_pend_q);
+		dev_dbg(&qp->ndev->pdev->dev, "done flag not set\n");
 		qp->rx_ring_empty++;
 		return -EAGAIN;
 	}
 
-	if (hdr->ver != (u32) qp->rx_pkts) {
-		dev_dbg(&ntb_query_pdev(qp->ndev)->dev,
-			"qp %d: version mismatch, expected %llu - got %u\n",
-			qp->qp_num, qp->rx_pkts, hdr->ver);
-		ntb_list_add(&qp->ntb_rx_pend_q_lock, &entry->entry,
-			     &qp->rx_pend_q);
+	if (hdr->flags & LINK_DOWN_FLAG) {
+		dev_dbg(&qp->ndev->pdev->dev, "link down flag set\n");
+		ntb_qp_link_down(qp);
+		hdr->flags = 0;
+		return -EAGAIN;
+	}
+
+	if (hdr->ver != (u32)qp->rx_pkts) {
+		dev_dbg(&qp->ndev->pdev->dev,
+			"version mismatch, expected %llu - got %u\n",
+			qp->rx_pkts, hdr->ver);
 		qp->rx_err_ver++;
 		return -EIO;
 	}
 
-	if (hdr->flags & LINK_DOWN_FLAG) {
-		ntb_qp_link_down(qp);
+	entry = ntb_list_rm(&qp->ntb_rx_pend_q_lock, &qp->rx_pend_q);
+	if (!entry) {
+		dev_dbg(&qp->ndev->pdev->dev, "no receive buffer\n");
+		qp->rx_err_no_buf++;
 
+		rc = -ENOMEM;
 		goto err;
 	}
 
-	dev_dbg(&ntb_query_pdev(qp->ndev)->dev,
-		"rx offset %u, ver %u - %d payload received, buf size %d\n",
+	if (hdr->len > entry->len) {
+		dev_dbg(&qp->ndev->pdev->dev,
+			"receive buffer overflow! Wanted %d got %d\n",
+			hdr->len, entry->len);
+		qp->rx_err_oflow++;
+
+		rc = -EIO;
+		goto err;
+	}
+
+	dev_dbg(&qp->ndev->pdev->dev,
+		"RX OK index %u ver %u size %d into buf size %d\n",
 		qp->rx_index, hdr->ver, hdr->len, entry->len);
 
 	qp->rx_bytes += hdr->len;
 	qp->rx_pkts++;
 
-	if (hdr->len > entry->len) {
-		qp->rx_err_oflow++;
-		dev_dbg(&ntb_query_pdev(qp->ndev)->dev,
-			"RX overflow! Wanted %d got %d\n",
-			hdr->len, entry->len);
-
-		goto err;
-	}
-
 	entry->index = qp->rx_index;
 	entry->rx_hdr = hdr;
 
 	ntb_async_rx(entry, offset, hdr->len);
 
-out:
 	qp->rx_index++;
 	qp->rx_index %= qp->rx_max_entry;
 
 	return 0;
 
 err:
-	ntb_list_add(&qp->ntb_rx_pend_q_lock, &entry->entry, &qp->rx_pend_q);
-	/* Ensure that the data is fully copied out before clearing the flag */
-	wmb();
+	/* FIXME: if this syncrhonous update of the rx_index gets ahead of
+	 * asyncrhonous ntb_rx_copy_callback of previous entry, there are three
+	 * scenarios:
+	 *
+	 * 1) The peer might miss this update, but observe the update
+	 * from the memcpy completion callback.  In this case, the buffer will
+	 * not be freed on the peer to be reused for a different packet.  The
+	 * successful rx of a later packet would clear the condition, but the
+	 * condition could persist if several rx fail in a row.
+	 *
+	 * 2) The peer may observe this update before the asyncrhonous copy of
+	 * prior packets is completed.  The peer may overwrite the buffers of
+	 * the prior packets before they are copied.
+	 *
+	 * 3) Both: the peer may observe the update, and then observe the index
+	 * decrement by the asynchronous completion callback.  Who knows what
+	 * badness that will cause.
+	 */
 	hdr->flags = 0;
 	iowrite32(qp->rx_index, &qp->rx_info->entry);
 
-	goto out;
+	return rc;
 }
 
-static int ntb_transport_rxc_db(void *data, int db_num)
+static void ntb_transport_rxc_db(unsigned long data)
 {
-	struct ntb_transport_qp *qp = data;
+	struct ntb_transport_qp *qp = (void *)data;
 	int rc, i;
 
-	dev_dbg(&ntb_query_pdev(qp->ndev)->dev, "%s: doorbell %d received\n",
-		__func__, db_num);
+	dev_dbg(&qp->ndev->pdev->dev, "%s: doorbell %d received\n",
+		__func__, qp->qp_num);
 
 	/* Limit the number of packets processed in a single interrupt to
 	 * provide fairness to others
@@ -1231,7 +1336,21 @@
 	if (qp->dma_chan)
 		dma_async_issue_pending(qp->dma_chan);
 
-	return i;
+	if (i == qp->rx_max_entry) {
+		/* there is more work to do */
+		tasklet_schedule(&qp->rxc_db_work);
+	} else if (ntb_db_read(qp->ndev) & BIT_ULL(qp->qp_num)) {
+		/* the doorbell bit is set: clear it */
+		ntb_db_clear(qp->ndev, BIT_ULL(qp->qp_num));
+		/* ntb_db_read ensures ntb_db_clear write is committed */
+		ntb_db_read(qp->ndev);
+
+		/* an interrupt may have arrived between finishing
+		 * ntb_process_rxc and clearing the doorbell bit:
+		 * there might be some more work to do.
+		 */
+		tasklet_schedule(&qp->rxc_db_work);
+	}
 }
 
 static void ntb_tx_copy_callback(void *data)
@@ -1240,11 +1359,9 @@
 	struct ntb_transport_qp *qp = entry->qp;
 	struct ntb_payload_header __iomem *hdr = entry->tx_hdr;
 
-	/* Ensure that the data is fully copied out before setting the flags */
-	wmb();
 	iowrite32(entry->flags | DESC_DONE_FLAG, &hdr->flags);
 
-	ntb_ring_doorbell(qp->ndev, qp->qp_num);
+	ntb_peer_db_set(qp->ndev, BIT_ULL(qp->qp_num));
 
 	/* The entry length can only be zero if the packet is intended to be a
 	 * "link down" or similar.  Since no payload is being sent in these
@@ -1263,7 +1380,18 @@
 
 static void ntb_memcpy_tx(struct ntb_queue_entry *entry, void __iomem *offset)
 {
+#ifdef ARCH_HAS_NOCACHE_UACCESS
+	/*
+	 * Using non-temporal mov to improve performance on non-cached
+	 * writes, even though we aren't actually copying from user space.
+	 */
+	__copy_from_user_inatomic_nocache(offset, entry->buf, entry->len);
+#else
 	memcpy_toio(offset, entry->buf, entry->len);
+#endif
+
+	/* Ensure that the data is fully copied out before setting the flags */
+	wmb();
 
 	ntb_tx_copy_callback(entry);
 }
@@ -1288,7 +1416,7 @@
 	entry->tx_hdr = hdr;
 
 	iowrite32(entry->len, &hdr->len);
-	iowrite32((u32) qp->tx_pkts, &hdr->ver);
+	iowrite32((u32)qp->tx_pkts, &hdr->ver);
 
 	if (!chan)
 		goto err;
@@ -1298,8 +1426,8 @@
 
 	device = chan->device;
 	dest = qp->tx_mw_phys + qp->tx_max_frame * qp->tx_index;
-	buff_off = (size_t) buf & ~PAGE_MASK;
-	dest_off = (size_t) dest & ~PAGE_MASK;
+	buff_off = (size_t)buf & ~PAGE_MASK;
+	dest_off = (size_t)dest & ~PAGE_MASK;
 
 	if (!is_dma_copy_aligned(device, buff_off, dest_off, len))
 		goto err;
@@ -1347,9 +1475,6 @@
 static int ntb_process_tx(struct ntb_transport_qp *qp,
 			  struct ntb_queue_entry *entry)
 {
-	dev_dbg(&ntb_query_pdev(qp->ndev)->dev, "%lld - tx %u, entry len %d flags %x buff %p\n",
-		qp->tx_pkts, qp->tx_index, entry->len, entry->flags,
-		entry->buf);
 	if (qp->tx_index == qp->remote_rx_info->entry) {
 		qp->tx_ring_full++;
 		return -EAGAIN;
@@ -1376,15 +1501,14 @@
 
 static void ntb_send_link_down(struct ntb_transport_qp *qp)
 {
-	struct pci_dev *pdev = ntb_query_pdev(qp->ndev);
+	struct pci_dev *pdev = qp->ndev->pdev;
 	struct ntb_queue_entry *entry;
 	int i, rc;
 
-	if (qp->qp_link == NTB_LINK_DOWN)
+	if (!qp->link_is_up)
 		return;
 
-	qp->qp_link = NTB_LINK_DOWN;
-	dev_info(&pdev->dev, "qp %d: Link Down\n", qp->qp_num);
+	dev_info(&pdev->dev, "qp %d: Send Link Down\n", qp->qp_num);
 
 	for (i = 0; i < NTB_LINK_DOWN_TIMEOUT; i++) {
 		entry = ntb_list_rm(&qp->ntb_tx_free_q_lock, &qp->tx_free_q);
@@ -1405,6 +1529,13 @@
 	if (rc)
 		dev_err(&pdev->dev, "ntb: QP%d unable to send linkdown msg\n",
 			qp->qp_num);
+
+	ntb_qp_link_down_reset(qp);
+}
+
+static bool ntb_dma_filter_fn(struct dma_chan *chan, void *node)
+{
+	return dev_to_node(&chan->dev->device) == (int)(unsigned long)node;
 }
 
 /**
@@ -1422,18 +1553,25 @@
  * RETURNS: pointer to newly created ntb_queue, NULL on error.
  */
 struct ntb_transport_qp *
-ntb_transport_create_queue(void *data, struct pci_dev *pdev,
+ntb_transport_create_queue(void *data, struct device *client_dev,
 			   const struct ntb_queue_handlers *handlers)
 {
+	struct ntb_dev *ndev;
+	struct pci_dev *pdev;
+	struct ntb_transport_ctx *nt;
 	struct ntb_queue_entry *entry;
 	struct ntb_transport_qp *qp;
-	struct ntb_transport *nt;
+	u64 qp_bit;
 	unsigned int free_queue;
-	int rc, i;
+	dma_cap_mask_t dma_mask;
+	int node;
+	int i;
 
-	nt = ntb_find_transport(pdev);
-	if (!nt)
-		goto err;
+	ndev = dev_ntb(client_dev->parent);
+	pdev = ndev->pdev;
+	nt = ndev->ctx;
+
+	node = dev_to_node(&ndev->dev);
 
 	free_queue = ffs(nt->qp_bitmap);
 	if (!free_queue)
@@ -1442,23 +1580,31 @@
 	/* decrement free_queue to make it zero based */
 	free_queue--;
 
-	clear_bit(free_queue, &nt->qp_bitmap);
+	qp = &nt->qp_vec[free_queue];
+	qp_bit = BIT_ULL(qp->qp_num);
 
-	qp = &nt->qps[free_queue];
+	nt->qp_bitmap_free &= ~qp_bit;
+
 	qp->cb_data = data;
 	qp->rx_handler = handlers->rx_handler;
 	qp->tx_handler = handlers->tx_handler;
 	qp->event_handler = handlers->event_handler;
 
-	dmaengine_get();
-	qp->dma_chan = dma_find_channel(DMA_MEMCPY);
-	if (!qp->dma_chan) {
-		dmaengine_put();
-		dev_info(&pdev->dev, "Unable to allocate DMA channel, using CPU instead\n");
+	dma_cap_zero(dma_mask);
+	dma_cap_set(DMA_MEMCPY, dma_mask);
+
+	if (use_dma) {
+		qp->dma_chan = dma_request_channel(dma_mask, ntb_dma_filter_fn,
+						   (void *)(unsigned long)node);
+		if (!qp->dma_chan)
+			dev_info(&pdev->dev, "Unable to allocate DMA channel\n");
+	} else {
+		qp->dma_chan = NULL;
 	}
+	dev_dbg(&pdev->dev, "Using %s memcpy\n", qp->dma_chan ? "DMA" : "CPU");
 
 	for (i = 0; i < NTB_QP_DEF_NUM_ENTRIES; i++) {
-		entry = kzalloc(sizeof(struct ntb_queue_entry), GFP_ATOMIC);
+		entry = kzalloc_node(sizeof(*entry), GFP_ATOMIC, node);
 		if (!entry)
 			goto err1;
 
@@ -1468,7 +1614,7 @@
 	}
 
 	for (i = 0; i < NTB_QP_DEF_NUM_ENTRIES; i++) {
-		entry = kzalloc(sizeof(struct ntb_queue_entry), GFP_ATOMIC);
+		entry = kzalloc_node(sizeof(*entry), GFP_ATOMIC, node);
 		if (!entry)
 			goto err2;
 
@@ -1477,10 +1623,8 @@
 			     &qp->tx_free_q);
 	}
 
-	rc = ntb_register_db_callback(qp->ndev, free_queue, qp,
-				      ntb_transport_rxc_db);
-	if (rc)
-		goto err2;
+	ntb_db_clear(qp->ndev, qp_bit);
+	ntb_db_clear_mask(qp->ndev, qp_bit);
 
 	dev_info(&pdev->dev, "NTB Transport QP %d created\n", qp->qp_num);
 
@@ -1493,8 +1637,8 @@
 	while ((entry = ntb_list_rm(&qp->ntb_rx_free_q_lock, &qp->rx_free_q)))
 		kfree(entry);
 	if (qp->dma_chan)
-		dmaengine_put();
-	set_bit(free_queue, &nt->qp_bitmap);
+		dma_release_channel(qp->dma_chan);
+	nt->qp_bitmap_free |= qp_bit;
 err:
 	return NULL;
 }
@@ -1508,13 +1652,15 @@
  */
 void ntb_transport_free_queue(struct ntb_transport_qp *qp)
 {
+	struct ntb_transport_ctx *nt = qp->transport;
 	struct pci_dev *pdev;
 	struct ntb_queue_entry *entry;
+	u64 qp_bit;
 
 	if (!qp)
 		return;
 
-	pdev = ntb_query_pdev(qp->ndev);
+	pdev = qp->ndev->pdev;
 
 	if (qp->dma_chan) {
 		struct dma_chan *chan = qp->dma_chan;
@@ -1528,13 +1674,21 @@
 		 */
 		dma_sync_wait(chan, qp->last_cookie);
 		dmaengine_terminate_all(chan);
-		dmaengine_put();
+		dma_release_channel(chan);
 	}
 
-	ntb_unregister_db_callback(qp->ndev, qp->qp_num);
+	qp_bit = BIT_ULL(qp->qp_num);
+
+	ntb_db_set_mask(qp->ndev, qp_bit);
+	tasklet_disable(&qp->rxc_db_work);
 
 	cancel_delayed_work_sync(&qp->link_work);
 
+	qp->cb_data = NULL;
+	qp->rx_handler = NULL;
+	qp->tx_handler = NULL;
+	qp->event_handler = NULL;
+
 	while ((entry = ntb_list_rm(&qp->ntb_rx_free_q_lock, &qp->rx_free_q)))
 		kfree(entry);
 
@@ -1546,7 +1700,7 @@
 	while ((entry = ntb_list_rm(&qp->ntb_tx_free_q_lock, &qp->tx_free_q)))
 		kfree(entry);
 
-	set_bit(qp->qp_num, &qp->transport->qp_bitmap);
+	nt->qp_bitmap_free |= qp_bit;
 
 	dev_info(&pdev->dev, "NTB Transport QP %d freed\n", qp->qp_num);
 }
@@ -1567,7 +1721,7 @@
 	struct ntb_queue_entry *entry;
 	void *buf;
 
-	if (!qp || qp->client_ready == NTB_LINK_UP)
+	if (!qp || qp->client_ready)
 		return NULL;
 
 	entry = ntb_list_rm(&qp->ntb_rx_pend_q_lock, &qp->rx_pend_q);
@@ -1636,7 +1790,7 @@
 	struct ntb_queue_entry *entry;
 	int rc;
 
-	if (!qp || qp->qp_link != NTB_LINK_UP || !len)
+	if (!qp || !qp->link_is_up || !len)
 		return -EINVAL;
 
 	entry = ntb_list_rm(&qp->ntb_tx_free_q_lock, &qp->tx_free_q);
@@ -1670,9 +1824,9 @@
 	if (!qp)
 		return;
 
-	qp->client_ready = NTB_LINK_UP;
+	qp->client_ready = true;
 
-	if (qp->transport->transport_link == NTB_LINK_UP)
+	if (qp->transport->link_is_up)
 		schedule_delayed_work(&qp->link_work, 0);
 }
 EXPORT_SYMBOL_GPL(ntb_transport_link_up);
@@ -1688,27 +1842,20 @@
 void ntb_transport_link_down(struct ntb_transport_qp *qp)
 {
 	struct pci_dev *pdev;
-	int rc, val;
+	int val;
 
 	if (!qp)
 		return;
 
-	pdev = ntb_query_pdev(qp->ndev);
-	qp->client_ready = NTB_LINK_DOWN;
+	pdev = qp->ndev->pdev;
+	qp->client_ready = false;
 
-	rc = ntb_read_local_spad(qp->ndev, QP_LINKS, &val);
-	if (rc) {
-		dev_err(&pdev->dev, "Error reading spad %d\n", QP_LINKS);
-		return;
-	}
+	val = ntb_spad_read(qp->ndev, QP_LINKS);
 
-	rc = ntb_write_remote_spad(qp->ndev, QP_LINKS,
-				   val & ~(1 << qp->qp_num));
-	if (rc)
-		dev_err(&pdev->dev, "Error writing %x to remote spad %d\n",
-			val & ~(1 << qp->qp_num), QP_LINKS);
+	ntb_peer_spad_write(qp->ndev, QP_LINKS,
+			    val & ~BIT(qp->qp_num));
 
-	if (qp->qp_link == NTB_LINK_UP)
+	if (qp->link_is_up)
 		ntb_send_link_down(qp);
 	else
 		cancel_delayed_work_sync(&qp->link_work);
@@ -1728,7 +1875,7 @@
 	if (!qp)
 		return false;
 
-	return qp->qp_link == NTB_LINK_UP;
+	return qp->link_is_up;
 }
 EXPORT_SYMBOL_GPL(ntb_transport_link_query);
 
@@ -1774,3 +1921,71 @@
 	return max;
 }
 EXPORT_SYMBOL_GPL(ntb_transport_max_size);
+
+static void ntb_transport_doorbell_callback(void *data, int vector)
+{
+	struct ntb_transport_ctx *nt = data;
+	struct ntb_transport_qp *qp;
+	u64 db_bits;
+	unsigned int qp_num;
+
+	db_bits = (nt->qp_bitmap & ~nt->qp_bitmap_free &
+		   ntb_db_vector_mask(nt->ndev, vector));
+
+	while (db_bits) {
+		qp_num = __ffs(db_bits);
+		qp = &nt->qp_vec[qp_num];
+
+		tasklet_schedule(&qp->rxc_db_work);
+
+		db_bits &= ~BIT_ULL(qp_num);
+	}
+}
+
+static const struct ntb_ctx_ops ntb_transport_ops = {
+	.link_event = ntb_transport_event_callback,
+	.db_event = ntb_transport_doorbell_callback,
+};
+
+static struct ntb_client ntb_transport_client = {
+	.ops = {
+		.probe = ntb_transport_probe,
+		.remove = ntb_transport_free,
+	},
+};
+
+static int __init ntb_transport_init(void)
+{
+	int rc;
+
+	pr_info("%s, version %s\n", NTB_TRANSPORT_DESC, NTB_TRANSPORT_VER);
+
+	if (debugfs_initialized())
+		nt_debugfs_dir = debugfs_create_dir(KBUILD_MODNAME, NULL);
+
+	rc = bus_register(&ntb_transport_bus);
+	if (rc)
+		goto err_bus;
+
+	rc = ntb_register_client(&ntb_transport_client);
+	if (rc)
+		goto err_client;
+
+	return 0;
+
+err_client:
+	bus_unregister(&ntb_transport_bus);
+err_bus:
+	debugfs_remove_recursive(nt_debugfs_dir);
+	return rc;
+}
+module_init(ntb_transport_init);
+
+static void __exit ntb_transport_exit(void)
+{
+	debugfs_remove_recursive(nt_debugfs_dir);
+
+	ntb_unregister_client(&ntb_transport_client);
+	bus_unregister(&ntb_transport_bus);
+}
+module_exit(ntb_transport_exit);
diff --git a/drivers/ntb/test/Kconfig b/drivers/ntb/test/Kconfig
new file mode 100644
index 0000000..01852f9
--- /dev/null
+++ b/drivers/ntb/test/Kconfig
@@ -0,0 +1,19 @@
+config NTB_PINGPONG
+	tristate "NTB Ping Pong Test Client"
+	help
+	 This is a simple ping pong driver that exercises the scratchpads and
+	 doorbells of the ntb hardware.  This driver may be used to test that
+	 your ntb hardware and drivers are functioning at a basic level.
+
+	 If unsure, say N.
+
+config NTB_TOOL
+	tristate "NTB Debugging Tool Test Client"
+	help
+	 This is a simple debugging driver that enables the doorbell and
+	 scratchpad registers to be read and written from the debugfs.  This
+	 enables more complicated debugging to be scripted from user space.
+	 This driver may be used to test that your ntb hardware and drivers are
+	 functioning at a basic level.
+
+	 If unsure, say N.
diff --git a/drivers/ntb/test/Makefile b/drivers/ntb/test/Makefile
new file mode 100644
index 0000000..0ea32a3
--- /dev/null
+++ b/drivers/ntb/test/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_NTB_PINGPONG) += ntb_pingpong.o
+obj-$(CONFIG_NTB_TOOL) += ntb_tool.o
diff --git a/drivers/ntb/test/ntb_pingpong.c b/drivers/ntb/test/ntb_pingpong.c
new file mode 100644
index 0000000..fe16005
--- /dev/null
+++ b/drivers/ntb/test/ntb_pingpong.c
@@ -0,0 +1,250 @@
+/*
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ *   redistributing this file, you may do so under either license.
+ *
+ *   GPL LICENSE SUMMARY
+ *
+ *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of version 2 of the GNU General Public License as
+ *   published by the Free Software Foundation.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *   General Public License for more details.
+ *
+ *   BSD LICENSE
+ *
+ *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copy
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of Intel Corporation nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * PCIe NTB Pingpong Linux driver
+ *
+ * Contact Information:
+ * Allen Hubbe <Allen.Hubbe@emc.com>
+ */
+
+/* Note: load this module with option 'dyndbg=+p' */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <linux/dma-mapping.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include <linux/ntb.h>
+
+#define DRIVER_NAME			"ntb_pingpong"
+#define DRIVER_DESCRIPTION		"PCIe NTB Simple Pingpong Client"
+
+#define DRIVER_LICENSE			"Dual BSD/GPL"
+#define DRIVER_VERSION			"1.0"
+#define DRIVER_RELDATE			"24 March 2015"
+#define DRIVER_AUTHOR			"Allen Hubbe <Allen.Hubbe@emc.com>"
+
+MODULE_LICENSE(DRIVER_LICENSE);
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESCRIPTION);
+
+static unsigned int unsafe;
+module_param(unsafe, uint, 0644);
+MODULE_PARM_DESC(unsafe, "Run even though ntb operations may be unsafe");
+
+static unsigned int delay_ms = 1000;
+module_param(delay_ms, uint, 0644);
+MODULE_PARM_DESC(delay_ms, "Milliseconds to delay the response to peer");
+
+static unsigned long db_init = 0x7;
+module_param(db_init, ulong, 0644);
+MODULE_PARM_DESC(delay_ms, "Initial doorbell bits to ring on the peer");
+
+struct pp_ctx {
+	struct ntb_dev			*ntb;
+	u64				db_bits;
+	/* synchronize access to db_bits by ping and pong */
+	spinlock_t			db_lock;
+	struct timer_list		db_timer;
+	unsigned long			db_delay;
+};
+
+static void pp_ping(unsigned long ctx)
+{
+	struct pp_ctx *pp = (void *)ctx;
+	unsigned long irqflags;
+	u64 db_bits, db_mask;
+	u32 spad_rd, spad_wr;
+
+	spin_lock_irqsave(&pp->db_lock, irqflags);
+	{
+		db_mask = ntb_db_valid_mask(pp->ntb);
+		db_bits = ntb_db_read(pp->ntb);
+
+		if (db_bits) {
+			dev_dbg(&pp->ntb->dev,
+				"Masked pongs %#llx\n",
+				db_bits);
+			ntb_db_clear(pp->ntb, db_bits);
+		}
+
+		db_bits = ((pp->db_bits | db_bits) << 1) & db_mask;
+
+		if (!db_bits)
+			db_bits = db_init;
+
+		spad_rd = ntb_spad_read(pp->ntb, 0);
+		spad_wr = spad_rd + 1;
+
+		dev_dbg(&pp->ntb->dev,
+			"Ping bits %#llx read %#x write %#x\n",
+			db_bits, spad_rd, spad_wr);
+
+		ntb_peer_spad_write(pp->ntb, 0, spad_wr);
+		ntb_peer_db_set(pp->ntb, db_bits);
+		ntb_db_clear_mask(pp->ntb, db_mask);
+
+		pp->db_bits = 0;
+	}
+	spin_unlock_irqrestore(&pp->db_lock, irqflags);
+}
+
+static void pp_link_event(void *ctx)
+{
+	struct pp_ctx *pp = ctx;
+
+	if (ntb_link_is_up(pp->ntb, NULL, NULL) == 1) {
+		dev_dbg(&pp->ntb->dev, "link is up\n");
+		pp_ping((unsigned long)pp);
+	} else {
+		dev_dbg(&pp->ntb->dev, "link is down\n");
+		del_timer(&pp->db_timer);
+	}
+}
+
+static void pp_db_event(void *ctx, int vec)
+{
+	struct pp_ctx *pp = ctx;
+	u64 db_bits, db_mask;
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&pp->db_lock, irqflags);
+	{
+		db_mask = ntb_db_vector_mask(pp->ntb, vec);
+		db_bits = db_mask & ntb_db_read(pp->ntb);
+		ntb_db_set_mask(pp->ntb, db_mask);
+		ntb_db_clear(pp->ntb, db_bits);
+
+		pp->db_bits |= db_bits;
+
+		mod_timer(&pp->db_timer, jiffies + pp->db_delay);
+
+		dev_dbg(&pp->ntb->dev,
+			"Pong vec %d bits %#llx\n",
+			vec, db_bits);
+	}
+	spin_unlock_irqrestore(&pp->db_lock, irqflags);
+}
+
+static const struct ntb_ctx_ops pp_ops = {
+	.link_event = pp_link_event,
+	.db_event = pp_db_event,
+};
+
+static int pp_probe(struct ntb_client *client,
+		    struct ntb_dev *ntb)
+{
+	struct pp_ctx *pp;
+	int rc;
+
+	if (ntb_db_is_unsafe(ntb)) {
+		dev_dbg(&ntb->dev, "doorbell is unsafe\n");
+		if (!unsafe) {
+			rc = -EINVAL;
+			goto err_pp;
+		}
+	}
+
+	if (ntb_spad_is_unsafe(ntb)) {
+		dev_dbg(&ntb->dev, "scratchpad is unsafe\n");
+		if (!unsafe) {
+			rc = -EINVAL;
+			goto err_pp;
+		}
+	}
+
+	pp = kmalloc(sizeof(*pp), GFP_KERNEL);
+	if (!pp) {
+		rc = -ENOMEM;
+		goto err_pp;
+	}
+
+	pp->ntb = ntb;
+	pp->db_bits = 0;
+	spin_lock_init(&pp->db_lock);
+	setup_timer(&pp->db_timer, pp_ping, (unsigned long)pp);
+	pp->db_delay = msecs_to_jiffies(delay_ms);
+
+	rc = ntb_set_ctx(ntb, pp, &pp_ops);
+	if (rc)
+		goto err_ctx;
+
+	ntb_link_enable(ntb, NTB_SPEED_AUTO, NTB_WIDTH_AUTO);
+	ntb_link_event(ntb);
+
+	return 0;
+
+err_ctx:
+	kfree(pp);
+err_pp:
+	return rc;
+}
+
+static void pp_remove(struct ntb_client *client,
+		      struct ntb_dev *ntb)
+{
+	struct pp_ctx *pp = ntb->ctx;
+
+	ntb_clear_ctx(ntb);
+	del_timer_sync(&pp->db_timer);
+	ntb_link_disable(ntb);
+
+	kfree(pp);
+}
+
+static struct ntb_client pp_client = {
+	.ops = {
+		.probe = pp_probe,
+		.remove = pp_remove,
+	},
+};
+module_ntb_client(pp_client);
diff --git a/drivers/ntb/test/ntb_tool.c b/drivers/ntb/test/ntb_tool.c
new file mode 100644
index 0000000..6f5dc6c
--- /dev/null
+++ b/drivers/ntb/test/ntb_tool.c
@@ -0,0 +1,556 @@
+/*
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ *   redistributing this file, you may do so under either license.
+ *
+ *   GPL LICENSE SUMMARY
+ *
+ *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of version 2 of the GNU General Public License as
+ *   published by the Free Software Foundation.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *   General Public License for more details.
+ *
+ *   BSD LICENSE
+ *
+ *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copy
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of Intel Corporation nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * PCIe NTB Debugging Tool Linux driver
+ *
+ * Contact Information:
+ * Allen Hubbe <Allen.Hubbe@emc.com>
+ */
+
+/*
+ * How to use this tool, by example.
+ *
+ * Assuming $DBG_DIR is something like:
+ * '/sys/kernel/debug/ntb_tool/0000:00:03.0'
+ *
+ * Eg: check if clearing the doorbell mask generates an interrupt.
+ *
+ * # Set the doorbell mask
+ * root@self# echo 's 1' > $DBG_DIR/mask
+ *
+ * # Ring the doorbell from the peer
+ * root@peer# echo 's 1' > $DBG_DIR/peer_db
+ *
+ * # Clear the doorbell mask
+ * root@self# echo 'c 1' > $DBG_DIR/mask
+ *
+ * Observe debugging output in dmesg or your console.  You should see a
+ * doorbell event triggered by clearing the mask.  If not, this may indicate an
+ * issue with the hardware that needs to be worked around in the driver.
+ *
+ * Eg: read and write scratchpad registers
+ *
+ * root@peer# echo '0 0x01010101 1 0x7f7f7f7f' > $DBG_DIR/peer_spad
+ *
+ * root@self# cat $DBG_DIR/spad
+ *
+ * Observe that spad 0 and 1 have the values set by the peer.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <linux/debugfs.h>
+#include <linux/dma-mapping.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+
+#include <linux/ntb.h>
+
+#define DRIVER_NAME			"ntb_tool"
+#define DRIVER_DESCRIPTION		"PCIe NTB Debugging Tool"
+
+#define DRIVER_LICENSE			"Dual BSD/GPL"
+#define DRIVER_VERSION			"1.0"
+#define DRIVER_RELDATE			"22 April 2015"
+#define DRIVER_AUTHOR			"Allen Hubbe <Allen.Hubbe@emc.com>"
+
+MODULE_LICENSE(DRIVER_LICENSE);
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESCRIPTION);
+
+static struct dentry *tool_dbgfs;
+
+struct tool_ctx {
+	struct ntb_dev *ntb;
+	struct dentry *dbgfs;
+};
+
+#define SPAD_FNAME_SIZE 0x10
+#define INT_PTR(x) ((void *)(unsigned long)x)
+#define PTR_INT(x) ((int)(unsigned long)x)
+
+#define TOOL_FOPS_RDWR(__name, __read, __write) \
+	const struct file_operations __name = {	\
+		.owner = THIS_MODULE,		\
+		.open = simple_open,		\
+		.read = __read,			\
+		.write = __write,		\
+	}
+
+static void tool_link_event(void *ctx)
+{
+	struct tool_ctx *tc = ctx;
+	enum ntb_speed speed;
+	enum ntb_width width;
+	int up;
+
+	up = ntb_link_is_up(tc->ntb, &speed, &width);
+
+	dev_dbg(&tc->ntb->dev, "link is %s speed %d width %d\n",
+		up ? "up" : "down", speed, width);
+}
+
+static void tool_db_event(void *ctx, int vec)
+{
+	struct tool_ctx *tc = ctx;
+	u64 db_bits, db_mask;
+
+	db_mask = ntb_db_vector_mask(tc->ntb, vec);
+	db_bits = ntb_db_read(tc->ntb);
+
+	dev_dbg(&tc->ntb->dev, "doorbell vec %d mask %#llx bits %#llx\n",
+		vec, db_mask, db_bits);
+}
+
+static const struct ntb_ctx_ops tool_ops = {
+	.link_event = tool_link_event,
+	.db_event = tool_db_event,
+};
+
+static ssize_t tool_dbfn_read(struct tool_ctx *tc, char __user *ubuf,
+			      size_t size, loff_t *offp,
+			      u64 (*db_read_fn)(struct ntb_dev *))
+{
+	size_t buf_size;
+	char *buf;
+	ssize_t pos, rc;
+
+	if (!db_read_fn)
+		return -EINVAL;
+
+	buf_size = min_t(size_t, size, 0x20);
+
+	buf = kmalloc(buf_size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	pos = scnprintf(buf, buf_size, "%#llx\n",
+			db_read_fn(tc->ntb));
+
+	rc = simple_read_from_buffer(ubuf, size, offp, buf, pos);
+
+	kfree(buf);
+
+	return rc;
+}
+
+static ssize_t tool_dbfn_write(struct tool_ctx *tc,
+			       const char __user *ubuf,
+			       size_t size, loff_t *offp,
+			       int (*db_set_fn)(struct ntb_dev *, u64),
+			       int (*db_clear_fn)(struct ntb_dev *, u64))
+{
+	u64 db_bits;
+	char *buf, cmd;
+	ssize_t rc;
+	int n;
+
+	buf = kmalloc(size + 1, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	rc = simple_write_to_buffer(buf, size, offp, ubuf, size);
+	if (rc < 0) {
+		kfree(buf);
+		return rc;
+	}
+
+	buf[size] = 0;
+
+	n = sscanf(buf, "%c %lli", &cmd, &db_bits);
+
+	kfree(buf);
+
+	if (n != 2) {
+		rc = -EINVAL;
+	} else if (cmd == 's') {
+		if (!db_set_fn)
+			rc = -EINVAL;
+		else
+			rc = db_set_fn(tc->ntb, db_bits);
+	} else if (cmd == 'c') {
+		if (!db_clear_fn)
+			rc = -EINVAL;
+		else
+			rc = db_clear_fn(tc->ntb, db_bits);
+	} else {
+		rc = -EINVAL;
+	}
+
+	return rc ? : size;
+}
+
+static ssize_t tool_spadfn_read(struct tool_ctx *tc, char __user *ubuf,
+				size_t size, loff_t *offp,
+				u32 (*spad_read_fn)(struct ntb_dev *, int))
+{
+	size_t buf_size;
+	char *buf;
+	ssize_t pos, rc;
+	int i, spad_count;
+
+	if (!spad_read_fn)
+		return -EINVAL;
+
+	buf_size = min_t(size_t, size, 0x100);
+
+	buf = kmalloc(buf_size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	pos = 0;
+
+	spad_count = ntb_spad_count(tc->ntb);
+	for (i = 0; i < spad_count; ++i) {
+		pos += scnprintf(buf + pos, buf_size - pos, "%d\t%#x\n",
+				 i, spad_read_fn(tc->ntb, i));
+	}
+
+	rc = simple_read_from_buffer(ubuf, size, offp, buf, pos);
+
+	kfree(buf);
+
+	return rc;
+}
+
+static ssize_t tool_spadfn_write(struct tool_ctx *tc,
+				 const char __user *ubuf,
+				 size_t size, loff_t *offp,
+				 int (*spad_write_fn)(struct ntb_dev *,
+						      int, u32))
+{
+	int spad_idx;
+	u32 spad_val;
+	char *buf;
+	int pos, n;
+	ssize_t rc;
+
+	if (!spad_write_fn) {
+		dev_dbg(&tc->ntb->dev, "no spad write fn\n");
+		return -EINVAL;
+	}
+
+	buf = kmalloc(size + 1, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	rc = simple_write_to_buffer(buf, size, offp, ubuf, size);
+	if (rc < 0) {
+		kfree(buf);
+		return rc;
+	}
+
+	buf[size] = 0;
+
+	n = sscanf(buf, "%d %i%n", &spad_idx, &spad_val, &pos);
+	while (n == 2) {
+		rc = spad_write_fn(tc->ntb, spad_idx, spad_val);
+		if (rc)
+			break;
+
+		n = sscanf(buf + pos, "%d %i%n", &spad_idx, &spad_val, &pos);
+	}
+
+	if (n < 0)
+		rc = n;
+
+	kfree(buf);
+
+	return rc ? : size;
+}
+
+static ssize_t tool_db_read(struct file *filep, char __user *ubuf,
+			    size_t size, loff_t *offp)
+{
+	struct tool_ctx *tc = filep->private_data;
+
+	return tool_dbfn_read(tc, ubuf, size, offp,
+			      tc->ntb->ops->db_read);
+}
+
+static ssize_t tool_db_write(struct file *filep, const char __user *ubuf,
+			     size_t size, loff_t *offp)
+{
+	struct tool_ctx *tc = filep->private_data;
+
+	return tool_dbfn_write(tc, ubuf, size, offp,
+			       tc->ntb->ops->db_set,
+			       tc->ntb->ops->db_clear);
+}
+
+static TOOL_FOPS_RDWR(tool_db_fops,
+		      tool_db_read,
+		      tool_db_write);
+
+static ssize_t tool_mask_read(struct file *filep, char __user *ubuf,
+			      size_t size, loff_t *offp)
+{
+	struct tool_ctx *tc = filep->private_data;
+
+	return tool_dbfn_read(tc, ubuf, size, offp,
+			      tc->ntb->ops->db_read_mask);
+}
+
+static ssize_t tool_mask_write(struct file *filep, const char __user *ubuf,
+			       size_t size, loff_t *offp)
+{
+	struct tool_ctx *tc = filep->private_data;
+
+	return tool_dbfn_write(tc, ubuf, size, offp,
+			       tc->ntb->ops->db_set_mask,
+			       tc->ntb->ops->db_clear_mask);
+}
+
+static TOOL_FOPS_RDWR(tool_mask_fops,
+		      tool_mask_read,
+		      tool_mask_write);
+
+static ssize_t tool_peer_db_read(struct file *filep, char __user *ubuf,
+				 size_t size, loff_t *offp)
+{
+	struct tool_ctx *tc = filep->private_data;
+
+	return tool_dbfn_read(tc, ubuf, size, offp,
+			      tc->ntb->ops->peer_db_read);
+}
+
+static ssize_t tool_peer_db_write(struct file *filep, const char __user *ubuf,
+				  size_t size, loff_t *offp)
+{
+	struct tool_ctx *tc = filep->private_data;
+
+	return tool_dbfn_write(tc, ubuf, size, offp,
+			       tc->ntb->ops->peer_db_set,
+			       tc->ntb->ops->peer_db_clear);
+}
+
+static TOOL_FOPS_RDWR(tool_peer_db_fops,
+		      tool_peer_db_read,
+		      tool_peer_db_write);
+
+static ssize_t tool_peer_mask_read(struct file *filep, char __user *ubuf,
+				   size_t size, loff_t *offp)
+{
+	struct tool_ctx *tc = filep->private_data;
+
+	return tool_dbfn_read(tc, ubuf, size, offp,
+			      tc->ntb->ops->peer_db_read_mask);
+}
+
+static ssize_t tool_peer_mask_write(struct file *filep, const char __user *ubuf,
+				    size_t size, loff_t *offp)
+{
+	struct tool_ctx *tc = filep->private_data;
+
+	return tool_dbfn_write(tc, ubuf, size, offp,
+			       tc->ntb->ops->peer_db_set_mask,
+			       tc->ntb->ops->peer_db_clear_mask);
+}
+
+static TOOL_FOPS_RDWR(tool_peer_mask_fops,
+		      tool_peer_mask_read,
+		      tool_peer_mask_write);
+
+static ssize_t tool_spad_read(struct file *filep, char __user *ubuf,
+			      size_t size, loff_t *offp)
+{
+	struct tool_ctx *tc = filep->private_data;
+
+	return tool_spadfn_read(tc, ubuf, size, offp,
+				tc->ntb->ops->spad_read);
+}
+
+static ssize_t tool_spad_write(struct file *filep, const char __user *ubuf,
+			       size_t size, loff_t *offp)
+{
+	struct tool_ctx *tc = filep->private_data;
+
+	return tool_spadfn_write(tc, ubuf, size, offp,
+				 tc->ntb->ops->spad_write);
+}
+
+static TOOL_FOPS_RDWR(tool_spad_fops,
+		      tool_spad_read,
+		      tool_spad_write);
+
+static ssize_t tool_peer_spad_read(struct file *filep, char __user *ubuf,
+				   size_t size, loff_t *offp)
+{
+	struct tool_ctx *tc = filep->private_data;
+
+	return tool_spadfn_read(tc, ubuf, size, offp,
+				tc->ntb->ops->peer_spad_read);
+}
+
+static ssize_t tool_peer_spad_write(struct file *filep, const char __user *ubuf,
+				    size_t size, loff_t *offp)
+{
+	struct tool_ctx *tc = filep->private_data;
+
+	return tool_spadfn_write(tc, ubuf, size, offp,
+				 tc->ntb->ops->peer_spad_write);
+}
+
+static TOOL_FOPS_RDWR(tool_peer_spad_fops,
+		      tool_peer_spad_read,
+		      tool_peer_spad_write);
+
+static void tool_setup_dbgfs(struct tool_ctx *tc)
+{
+	/* This modules is useless without dbgfs... */
+	if (!tool_dbgfs) {
+		tc->dbgfs = NULL;
+		return;
+	}
+
+	tc->dbgfs = debugfs_create_dir(dev_name(&tc->ntb->dev),
+				       tool_dbgfs);
+	if (!tc->dbgfs)
+		return;
+
+	debugfs_create_file("db", S_IRUSR | S_IWUSR, tc->dbgfs,
+			    tc, &tool_db_fops);
+
+	debugfs_create_file("mask", S_IRUSR | S_IWUSR, tc->dbgfs,
+			    tc, &tool_mask_fops);
+
+	debugfs_create_file("peer_db", S_IRUSR | S_IWUSR, tc->dbgfs,
+			    tc, &tool_peer_db_fops);
+
+	debugfs_create_file("peer_mask", S_IRUSR | S_IWUSR, tc->dbgfs,
+			    tc, &tool_peer_mask_fops);
+
+	debugfs_create_file("spad", S_IRUSR | S_IWUSR, tc->dbgfs,
+			    tc, &tool_spad_fops);
+
+	debugfs_create_file("peer_spad", S_IRUSR | S_IWUSR, tc->dbgfs,
+			    tc, &tool_peer_spad_fops);
+}
+
+static int tool_probe(struct ntb_client *self, struct ntb_dev *ntb)
+{
+	struct tool_ctx *tc;
+	int rc;
+
+	if (ntb_db_is_unsafe(ntb))
+		dev_dbg(&ntb->dev, "doorbell is unsafe\n");
+
+	if (ntb_spad_is_unsafe(ntb))
+		dev_dbg(&ntb->dev, "scratchpad is unsafe\n");
+
+	tc = kmalloc(sizeof(*tc), GFP_KERNEL);
+	if (!tc) {
+		rc = -ENOMEM;
+		goto err_tc;
+	}
+
+	tc->ntb = ntb;
+
+	tool_setup_dbgfs(tc);
+
+	rc = ntb_set_ctx(ntb, tc, &tool_ops);
+	if (rc)
+		goto err_ctx;
+
+	ntb_link_enable(ntb, NTB_SPEED_AUTO, NTB_WIDTH_AUTO);
+	ntb_link_event(ntb);
+
+	return 0;
+
+err_ctx:
+	debugfs_remove_recursive(tc->dbgfs);
+	kfree(tc);
+err_tc:
+	return rc;
+}
+
+static void tool_remove(struct ntb_client *self, struct ntb_dev *ntb)
+{
+	struct tool_ctx *tc = ntb->ctx;
+
+	ntb_clear_ctx(ntb);
+	ntb_link_disable(ntb);
+
+	debugfs_remove_recursive(tc->dbgfs);
+	kfree(tc);
+}
+
+static struct ntb_client tool_client = {
+	.ops = {
+		.probe = tool_probe,
+		.remove = tool_remove,
+	},
+};
+
+static int __init tool_init(void)
+{
+	int rc;
+
+	if (debugfs_initialized())
+		tool_dbgfs = debugfs_create_dir(KBUILD_MODNAME, NULL);
+
+	rc = ntb_register_client(&tool_client);
+	if (rc)
+		goto err_client;
+
+	return 0;
+
+err_client:
+	debugfs_remove_recursive(tool_dbgfs);
+	return rc;
+}
+module_init(tool_init);
+
+static void __exit tool_exit(void)
+{
+	ntb_unregister_client(&tool_client);
+	debugfs_remove_recursive(tool_dbgfs);
+}
+module_exit(tool_exit);
diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index 07bb3c8..8df1b17 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -1,15 +1,20 @@
 config DTC
 	bool
 
-config OF
-	bool
+menuconfig OF
+	bool "Device Tree and Open Firmware support"
+	help
+	  This option enables the device tree infrastructure.
+	  It is automatically selected by platforms that need it or can
+	  be enabled manually for unittests, overlays or
+	  compile-coverage.
 
-menu "Device Tree and Open Firmware support"
-	depends on OF
+if OF
 
 config OF_UNITTEST
 	bool "Device Tree runtime unit tests"
-	depends on OF_IRQ && OF_EARLY_FLATTREE
+	depends on OF_IRQ
+	select OF_EARLY_FLATTREE
 	select OF_RESOLVE
 	help
 	  This option builds in test cases for the device tree infrastructure
@@ -97,4 +102,4 @@
 	  While this option is selected automatically when needed, you can
 	  enable it manually to improve device tree unit test coverage.
 
-endmenu # OF
+endif # OF
diff --git a/drivers/of/Makefile b/drivers/of/Makefile
index fcacb18..156c072 100644
--- a/drivers/of/Makefile
+++ b/drivers/of/Makefile
@@ -16,6 +16,3 @@
 obj-$(CONFIG_OF_OVERLAY) += overlay.o
 
 obj-$(CONFIG_OF_UNITTEST) += unittest-data/
-
-CFLAGS_fdt.o = -I$(src)/../../scripts/dtc/libfdt
-CFLAGS_fdt_address.o = -I$(src)/../../scripts/dtc/libfdt
diff --git a/drivers/of/address.c b/drivers/of/address.c
index 6906a3f..8bfda6a 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -712,7 +712,7 @@
 	}
 
 	/* add the range to the list */
-	range = kzalloc(sizeof(*range), GFP_KERNEL);
+	range = kzalloc(sizeof(*range), GFP_ATOMIC);
 	if (!range) {
 		err = -ENOMEM;
 		goto end_register;
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 6f85ff7..8b5a187 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -89,7 +89,7 @@
 #ifdef CONFIG_NUMA
 int __weak of_node_to_nid(struct device_node *np)
 {
-	return numa_node_id();
+	return NUMA_NO_NODE;
 }
 #endif
 
diff --git a/drivers/of/device.c b/drivers/of/device.c
index 20c1332..8b91ea2 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -163,6 +163,18 @@
 }
 EXPORT_SYMBOL(of_device_unregister);
 
+const void *of_device_get_match_data(const struct device *dev)
+{
+	const struct of_device_id *match;
+
+	match = of_match_device(dev->driver->of_match_table, dev);
+	if (!match)
+		return NULL;
+
+	return match->data;
+}
+EXPORT_SYMBOL(of_device_get_match_data);
+
 ssize_t of_device_get_modalias(struct device *dev, char *str, ssize_t len)
 {
 	const char *compat;
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index f2dd23a..0749656 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -164,11 +164,14 @@
  * unflatten_dt_node - Alloc and populate a device_node from the flat tree
  * @blob: The parent device tree blob
  * @mem: Memory chunk to use for allocating device nodes and properties
- * @p: pointer to node in flat tree
+ * @poffset: pointer to node in flat tree
  * @dad: Parent struct device_node
+ * @nodepp: The device_node tree created by the call
  * @fpsize: Size of the node path up at the current depth.
+ * @dryrun: If true, do not allocate device nodes but still calculate needed
+ * memory size
  */
-static void * unflatten_dt_node(void *blob,
+static void * unflatten_dt_node(const void *blob,
 				void *mem,
 				int *poffset,
 				struct device_node *dad,
@@ -378,7 +381,7 @@
  * @dt_alloc: An allocator that provides a virtual address to memory
  * for the resulting tree
  */
-static void __unflatten_device_tree(void *blob,
+static void __unflatten_device_tree(const void *blob,
 			     struct device_node **mynodes,
 			     void * (*dt_alloc)(u64 size, u64 align))
 {
@@ -441,7 +444,7 @@
  * pointers of the nodes so the normal device-tree walking functions
  * can be used.
  */
-void of_fdt_unflatten_tree(unsigned long *blob,
+void of_fdt_unflatten_tree(const unsigned long *blob,
 			struct device_node **mynodes)
 {
 	__unflatten_device_tree(blob, mynodes, &kernel_tree_alloc);
@@ -1024,6 +1027,11 @@
 	return __va(memblock_alloc(size, align));
 }
 #else
+void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size)
+{
+	WARN_ON(1);
+}
+
 int __init __weak early_init_dt_reserve_memory_arch(phys_addr_t base,
 					phys_addr_t size, bool nomap)
 {
@@ -1031,6 +1039,12 @@
 		  &base, &size, nomap ? " (nomap)" : "");
 	return -ENOSYS;
 }
+
+void * __init __weak early_init_dt_alloc_memory_arch(u64 size, u64 align)
+{
+	WARN_ON(1);
+	return NULL;
+}
 #endif
 
 bool __init early_init_dt_verify(void *params)
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 1a79806..3cf7a01 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -252,8 +252,6 @@
 		 * Successfully parsed an interrrupt-map translation; copy new
 		 * interrupt specifier into the out_irq structure
 		 */
-		out_irq->np = newpar;
-
 		match_array = imap - newaddrsize - newintsize;
 		for (i = 0; i < newintsize; i++)
 			out_irq->args[i] = be32_to_cpup(imap - newintsize + i);
@@ -262,6 +260,7 @@
 
 	skiplevel:
 		/* Iterate again with new parent */
+		out_irq->np = newpar;
 		pr_debug(" -> new parent: %s\n", of_node_full_name(newpar));
 		of_node_put(ipar);
 		ipar = newpar;
@@ -469,7 +468,7 @@
 }
 EXPORT_SYMBOL_GPL(of_irq_to_resource_table);
 
-struct intc_desc {
+struct of_intc_desc {
 	struct list_head	list;
 	struct device_node	*dev;
 	struct device_node	*interrupt_parent;
@@ -485,7 +484,7 @@
 void __init of_irq_init(const struct of_device_id *matches)
 {
 	struct device_node *np, *parent = NULL;
-	struct intc_desc *desc, *temp_desc;
+	struct of_intc_desc *desc, *temp_desc;
 	struct list_head intc_desc_list, intc_parent_list;
 
 	INIT_LIST_HEAD(&intc_desc_list);
@@ -496,7 +495,7 @@
 				!of_device_is_available(np))
 			continue;
 		/*
-		 * Here, we allocate and populate an intc_desc with the node
+		 * Here, we allocate and populate an of_intc_desc with the node
 		 * pointer, interrupt-parent device_node etc.
 		 */
 		desc = kzalloc(sizeof(*desc), GFP_KERNEL);
diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
index dee9270..24e025f 100644
--- a/drivers/of/overlay.c
+++ b/drivers/of/overlay.c
@@ -333,7 +333,7 @@
  * of the overlay in a list. This list can be used to prevent
  * illegal overlay removals.
  *
- * Returns the id of the created overlay, or an negative error number
+ * Returns the id of the created overlay, or a negative error number
  */
 int of_overlay_create(struct device_node *tree)
 {
@@ -481,7 +481,7 @@
  *
  * Removes an overlay if it is permissible.
  *
- * Returns 0 on success, or an negative error number
+ * Returns 0 on success, or a negative error number
  */
 int of_overlay_destroy(int id)
 {
@@ -528,7 +528,7 @@
  *
  * Removes all overlays from the system in the correct order.
  *
- * Returns 0 on success, or an negative error number
+ * Returns 0 on success, or a negative error number
  */
 int of_overlay_destroy_all(void)
 {
diff --git a/drivers/pci/host/pci-keystone.c b/drivers/pci/host/pci-keystone.c
index b75d684..734da58 100644
--- a/drivers/pci/host/pci-keystone.c
+++ b/drivers/pci/host/pci-keystone.c
@@ -221,10 +221,9 @@
 	/* MSI IRQ */
 	if (IS_ENABLED(CONFIG_PCI_MSI)) {
 		for (i = 0; i < ks_pcie->num_msi_host_irqs; i++) {
-			irq_set_chained_handler(ks_pcie->msi_host_irqs[i],
-						ks_pcie_msi_irq_handler);
-			irq_set_handler_data(ks_pcie->msi_host_irqs[i],
-					     ks_pcie);
+			irq_set_chained_handler_and_data(ks_pcie->msi_host_irqs[i],
+							 ks_pcie_msi_irq_handler,
+							 ks_pcie);
 		}
 	}
 }
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index 240f388..8b7a900 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -20,6 +20,7 @@
 #include <linux/workqueue.h>
 #include <linux/bitops.h>
 #include <linux/time.h>
+#include <linux/ktime.h>
 #include <xen/platform_pci.h>
 
 #include <asm/xen/swiotlb-xen.h>
@@ -115,7 +116,6 @@
 	evtchn_port_t port = pdev->evtchn;
 	unsigned irq = pdev->irq;
 	s64 ns, ns_timeout;
-	struct timeval tv;
 
 	spin_lock_irqsave(&pdev->sh_info_lock, irq_flags);
 
@@ -132,8 +132,7 @@
 	 * (in the latter case we end up continually re-executing poll() with a
 	 * timeout in the past). 1s difference gives plenty of slack for error.
 	 */
-	do_gettimeofday(&tv);
-	ns_timeout = timeval_to_ns(&tv) + 2 * (s64)NSEC_PER_SEC;
+	ns_timeout = ktime_get_ns() + 2 * (s64)NSEC_PER_SEC;
 
 	xen_clear_irq_pending(irq);
 
@@ -141,8 +140,7 @@
 			(unsigned long *)&pdev->sh_info->flags)) {
 		xen_poll_irq_timeout(irq, jiffies + 3*HZ);
 		xen_clear_irq_pending(irq);
-		do_gettimeofday(&tv);
-		ns = timeval_to_ns(&tv);
+		ns = ktime_get_ns();
 		if (ns > ns_timeout) {
 			dev_err(&pdev->xdev->dev,
 				"pciback not responding!!!\n");
diff --git a/drivers/pcmcia/xxs1500_ss.c b/drivers/pcmcia/xxs1500_ss.c
index 4c04360..b2a1895 100644
--- a/drivers/pcmcia/xxs1500_ss.c
+++ b/drivers/pcmcia/xxs1500_ss.c
@@ -11,6 +11,7 @@
 #include <linux/io.h>
 #include <linux/ioport.h>
 #include <linux/mm.h>
+#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/pm.h>
 #include <linux/resource.h>
diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
index c4fc77a..ad1ea16 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
@@ -1351,8 +1351,7 @@
 		set_irq_flags(virq, IRQF_VALID);
 	};
 
-	irq_set_chained_handler(irq, mtk_eint_irq_handler);
-	irq_set_handler_data(irq, pctl);
+	irq_set_chained_handler_and_data(irq, mtk_eint_irq_handler, pctl);
 	set_irq_flags(irq, IRQF_VALID);
 	return 0;
 
diff --git a/drivers/pinctrl/pinctrl-adi2.c b/drivers/pinctrl/pinctrl-adi2.c
index 873433d..c3c3d23 100644
--- a/drivers/pinctrl/pinctrl-adi2.c
+++ b/drivers/pinctrl/pinctrl-adi2.c
@@ -865,8 +865,8 @@
 	pint->pint_map_port = adi_pint_map_port;
 	platform_set_drvdata(pdev, pint);
 
-	irq_set_chained_handler(pint->irq, adi_gpio_handle_pint_irq);
-	irq_set_handler_data(pint->irq, pint);
+	irq_set_chained_handler_and_data(pint->irq, adi_gpio_handle_pint_irq,
+					 pint);
 
 	list_add_tail(&pint->node, &adi_pint_list);
 
diff --git a/drivers/pinctrl/pinctrl-st.c b/drivers/pinctrl/pinctrl-st.c
index d34ac87..c262e5f 100644
--- a/drivers/pinctrl/pinctrl-st.c
+++ b/drivers/pinctrl/pinctrl-st.c
@@ -1661,8 +1661,8 @@
 		if (IS_ERR(info->irqmux_base))
 			return PTR_ERR(info->irqmux_base);
 
-		irq_set_chained_handler(irq, st_gpio_irqmux_handler);
-		irq_set_handler_data(irq, info);
+		irq_set_chained_handler_and_data(irq, st_gpio_irqmux_handler,
+						 info);
 
 	}
 
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c
index 0b7afa5..b18dabb 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.c
@@ -563,8 +563,8 @@
 		return -ENOMEM;
 	}
 
-	irq_set_chained_handler(irq, exynos_irq_demux_eint16_31);
-	irq_set_handler_data(irq, muxed_data);
+	irq_set_chained_handler_and_data(irq, exynos_irq_demux_eint16_31,
+					 muxed_data);
 
 	bank = d->pin_banks;
 	idx = 0;
diff --git a/drivers/pinctrl/samsung/pinctrl-s3c24xx.c b/drivers/pinctrl/samsung/pinctrl-s3c24xx.c
index f1993f42..01b43db 100644
--- a/drivers/pinctrl/samsung/pinctrl-s3c24xx.c
+++ b/drivers/pinctrl/samsung/pinctrl-s3c24xx.c
@@ -514,8 +514,7 @@
 		}
 
 		eint_data->parents[i] = irq;
-		irq_set_chained_handler(irq, handlers[i]);
-		irq_set_handler_data(irq, eint_data);
+		irq_set_chained_handler_and_data(irq, handlers[i], eint_data);
 	}
 
 	bank = d->pin_banks;
diff --git a/drivers/pinctrl/samsung/pinctrl-s3c64xx.c b/drivers/pinctrl/samsung/pinctrl-s3c64xx.c
index 7756c1e..ec8cc3b 100644
--- a/drivers/pinctrl/samsung/pinctrl-s3c64xx.c
+++ b/drivers/pinctrl/samsung/pinctrl-s3c64xx.c
@@ -506,8 +506,7 @@
 		data->domains[nr_domains++] = bank->irq_domain;
 	}
 
-	irq_set_chained_handler(d->irq, s3c64xx_eint_gpio_irq);
-	irq_set_handler_data(d->irq, data);
+	irq_set_chained_handler_and_data(d->irq, s3c64xx_eint_gpio_irq, data);
 
 	return 0;
 }
@@ -731,8 +730,9 @@
 			return -ENXIO;
 		}
 
-		irq_set_chained_handler(irq, s3c64xx_eint0_handlers[i]);
-		irq_set_handler_data(irq, data);
+		irq_set_chained_handler_and_data(irq,
+						 s3c64xx_eint0_handlers[i],
+						 data);
 	}
 
 	bank = d->pin_banks;
diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
index d7857c7..f09573e 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
@@ -1005,9 +1005,9 @@
 		writel(0xffffffff,
 			pctl->membase + sunxi_irq_status_reg_from_bank(i));
 
-		irq_set_chained_handler(pctl->irq[i],
-					sunxi_pinctrl_irq_handler);
-		irq_set_handler_data(pctl->irq[i], pctl);
+		irq_set_chained_handler_and_data(pctl->irq[i],
+						 sunxi_pinctrl_irq_handler,
+						 pctl);
 	}
 
 	dev_info(&pdev->dev, "initialized sunXi PIO driver\n");
diff --git a/drivers/platform/goldfish/pdev_bus.c b/drivers/platform/goldfish/pdev_bus.c
index 8c43589..1f52462 100644
--- a/drivers/platform/goldfish/pdev_bus.c
+++ b/drivers/platform/goldfish/pdev_bus.c
@@ -220,20 +220,10 @@
 	return ret;
 }
 
-static int goldfish_pdev_bus_remove(struct platform_device *pdev)
-{
-	iounmap(pdev_bus_base);
-	free_irq(pdev_bus_irq, pdev);
-	release_mem_region(pdev_bus_addr, pdev_bus_len);
-	return 0;
-}
-
 static struct platform_driver goldfish_pdev_bus_driver = {
 	.probe = goldfish_pdev_bus_probe,
-	.remove = goldfish_pdev_bus_remove,
 	.driver = {
 		.name = "goldfish_pdev_bus"
 	}
 };
-
-module_platform_driver(goldfish_pdev_bus_driver);
+builtin_platform_driver(goldfish_pdev_bus_driver);
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 7137a07..6dc13e4 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -141,6 +141,22 @@
 	  To compile this driver as a module, choose M here: the module will
 	  be called dell-smo8800.
 
+config DELL_RBTN
+	tristate "Dell Airplane Mode Switch driver"
+	depends on ACPI
+	depends on INPUT
+	depends on RFKILL
+	---help---
+	  Say Y here if you want to support Dell Airplane Mode Switch ACPI
+	  device on Dell laptops. Sometimes it has names: DELLABCE or DELRBTN.
+	  This driver register rfkill device or input hotkey device depending
+	  on hardware type (hw switch slider or keyboard toggle button). For
+	  rfkill devices it receive HW switch events and set correct hard
+	  rfkill state.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called dell-rbtn.
+
 
 config FUJITSU_LAPTOP
 	tristate "Fujitsu Laptop Extras"
@@ -622,7 +638,6 @@
 	select NEW_LEDS
 	depends on BACKLIGHT_CLASS_DEVICE
 	depends on INPUT
-	depends on RFKILL || RFKILL = n
 	depends on SERIO_I8042 || SERIO_I8042 = n
 	depends on ACPI_VIDEO || ACPI_VIDEO = n
 	select INPUT_POLLDEV
@@ -653,6 +668,7 @@
 config TOSHIBA_BT_RFKILL
 	tristate "Toshiba Bluetooth RFKill switch support"
 	depends on ACPI
+	depends on RFKILL || RFKILL = n
 	---help---
 	  This driver adds support for Bluetooth events for the RFKill
 	  switch on modern Toshiba laptops with full ACPI support and
@@ -896,4 +912,11 @@
 	  a paravirtualized device provided by QEMU; it lets a virtual machine
 	  (guest) communicate panic events to the host.
 
+config INTEL_PMC_IPC
+	tristate "Intel PMC IPC Driver"
+	---help---
+	This driver provides support for PMC control on some Intel platforms.
+	The PMC is an ARC processor which defines IPC commands for communication
+	with other entities in the CPU.
+
 endif # X86_PLATFORM_DEVICES
diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile
index f82232b..dda95a9 100644
--- a/drivers/platform/x86/Makefile
+++ b/drivers/platform/x86/Makefile
@@ -14,6 +14,7 @@
 obj-$(CONFIG_DELL_WMI)		+= dell-wmi.o
 obj-$(CONFIG_DELL_WMI_AIO)	+= dell-wmi-aio.o
 obj-$(CONFIG_DELL_SMO8800)	+= dell-smo8800.o
+obj-$(CONFIG_DELL_RBTN)		+= dell-rbtn.o
 obj-$(CONFIG_ACER_WMI)		+= acer-wmi.o
 obj-$(CONFIG_ACERHDF)		+= acerhdf.o
 obj-$(CONFIG_HP_ACCEL)		+= hp_accel.o
@@ -58,3 +59,4 @@
 
 obj-$(CONFIG_PVPANIC)           += pvpanic.o
 obj-$(CONFIG_ALIENWARE_WMI)	+= alienware-wmi.o
+obj-$(CONFIG_INTEL_PMC_IPC)	+= intel_pmc_ipc.o
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 6f8558f..efbc3f0 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -78,6 +78,7 @@
 #define ASUS_WMI_METHODID_GPID		0x44495047 /* Get Panel ID?? (Resol) */
 #define ASUS_WMI_METHODID_QMOD		0x444F4D51 /* Quiet MODe */
 #define ASUS_WMI_METHODID_SPLV		0x4C425053 /* Set Panel Light Value */
+#define ASUS_WMI_METHODID_AGFN		0x4E464741 /* FaN? */
 #define ASUS_WMI_METHODID_SFUN		0x4E554653 /* FUNCtionalities */
 #define ASUS_WMI_METHODID_SDSP		0x50534453 /* Set DiSPlay output */
 #define ASUS_WMI_METHODID_GDSP		0x50534447 /* Get DiSPlay output */
@@ -150,12 +151,38 @@
 #define ASUS_WMI_DSTS_BRIGHTNESS_MASK	0x000000FF
 #define ASUS_WMI_DSTS_MAX_BRIGTH_MASK	0x0000FF00
 
+#define ASUS_FAN_DESC			"cpu_fan"
+#define ASUS_FAN_MFUN			0x13
+#define ASUS_FAN_SFUN_READ		0x06
+#define ASUS_FAN_SFUN_WRITE		0x07
+#define ASUS_FAN_CTRL_MANUAL		1
+#define ASUS_FAN_CTRL_AUTO		2
+
 struct bios_args {
 	u32 arg0;
 	u32 arg1;
 } __packed;
 
 /*
+ * Struct that's used for all methods called via AGFN. Naming is
+ * identically to the AML code.
+ */
+struct agfn_args {
+	u16 mfun; /* probably "Multi-function" to be called */
+	u16 sfun; /* probably "Sub-function" to be called */
+	u16 len;  /* size of the hole struct, including subfunction fields */
+	u8 stas;  /* not used by now */
+	u8 err;   /* zero on success */
+} __packed;
+
+/* struct used for calling fan read and write methods */
+struct fan_args {
+	struct agfn_args agfn;	/* common fields */
+	u8 fan;			/* fan number: 0: set auto mode 1: 1st fan */
+	u32 speed;		/* read: RPM/100 - write: 0-255 */
+} __packed;
+
+/*
  * <platform>/    - debugfs root directory
  *   dev_id      - current dev_id
  *   ctrl_param  - current ctrl_param
@@ -204,6 +231,10 @@
 	struct asus_rfkill gps;
 	struct asus_rfkill uwb;
 
+	bool asus_hwmon_fan_manual_mode;
+	int asus_hwmon_num_fans;
+	int asus_hwmon_pwm;
+
 	struct hotplug_slot *hotplug_slot;
 	struct mutex hotplug_lock;
 	struct mutex wmi_lock;
@@ -294,6 +325,36 @@
 	return 0;
 }
 
+static int asus_wmi_evaluate_method_agfn(const struct acpi_buffer args)
+{
+	struct acpi_buffer input;
+	u64 phys_addr;
+	u32 retval;
+	u32 status = -1;
+
+	/*
+	 * Copy to dma capable address otherwise memory corruption occurs as
+	 * bios has to be able to access it.
+	 */
+	input.pointer = kzalloc(args.length, GFP_DMA | GFP_KERNEL);
+	input.length = args.length;
+	if (!input.pointer)
+		return -ENOMEM;
+	phys_addr = virt_to_phys(input.pointer);
+	memcpy(input.pointer, args.pointer, args.length);
+
+	status = asus_wmi_evaluate_method(ASUS_WMI_METHODID_AGFN,
+					phys_addr, 0, &retval);
+	if (!status)
+		memcpy(args.pointer, input.pointer, args.length);
+
+	kfree(input.pointer);
+	if (status)
+		return -ENXIO;
+
+	return retval;
+}
+
 static int asus_wmi_get_devstate(struct asus_wmi *asus, u32 dev_id, u32 *retval)
 {
 	return asus_wmi_evaluate_method(asus->dsts_id, dev_id, 0, retval);
@@ -1022,35 +1083,228 @@
 /*
  * Hwmon device
  */
-static ssize_t asus_hwmon_pwm1(struct device *dev,
+static int asus_hwmon_agfn_fan_speed_read(struct asus_wmi *asus, int fan,
+					  int *speed)
+{
+	struct fan_args args = {
+		.agfn.len = sizeof(args),
+		.agfn.mfun = ASUS_FAN_MFUN,
+		.agfn.sfun = ASUS_FAN_SFUN_READ,
+		.fan = fan,
+		.speed = 0,
+	};
+	struct acpi_buffer input = { (acpi_size) sizeof(args), &args };
+	int status;
+
+	if (fan != 1)
+		return -EINVAL;
+
+	status = asus_wmi_evaluate_method_agfn(input);
+
+	if (status || args.agfn.err)
+		return -ENXIO;
+
+	if (speed)
+		*speed = args.speed;
+
+	return 0;
+}
+
+static int asus_hwmon_agfn_fan_speed_write(struct asus_wmi *asus, int fan,
+				     int *speed)
+{
+	struct fan_args args = {
+		.agfn.len = sizeof(args),
+		.agfn.mfun = ASUS_FAN_MFUN,
+		.agfn.sfun = ASUS_FAN_SFUN_WRITE,
+		.fan = fan,
+		.speed = speed ?  *speed : 0,
+	};
+	struct acpi_buffer input = { (acpi_size) sizeof(args), &args };
+	int status;
+
+	/* 1: for setting 1st fan's speed 0: setting auto mode */
+	if (fan != 1 && fan != 0)
+		return -EINVAL;
+
+	status = asus_wmi_evaluate_method_agfn(input);
+
+	if (status || args.agfn.err)
+		return -ENXIO;
+
+	if (speed && fan == 1)
+		asus->asus_hwmon_pwm = *speed;
+
+	return 0;
+}
+
+/*
+ * Check if we can read the speed of one fan. If true we assume we can also
+ * control it.
+ */
+static int asus_hwmon_get_fan_number(struct asus_wmi *asus, int *num_fans)
+{
+	int status;
+	int speed = 0;
+
+	*num_fans = 0;
+
+	status = asus_hwmon_agfn_fan_speed_read(asus, 1, &speed);
+	if (!status)
+		*num_fans = 1;
+
+	return 0;
+}
+
+static int asus_hwmon_fan_set_auto(struct asus_wmi *asus)
+{
+	int status;
+
+	status = asus_hwmon_agfn_fan_speed_write(asus, 0, NULL);
+	if (status)
+		return -ENXIO;
+
+	asus->asus_hwmon_fan_manual_mode = false;
+
+	return 0;
+}
+
+static int asus_hwmon_fan_rpm_show(struct device *dev, int fan)
+{
+	struct asus_wmi *asus = dev_get_drvdata(dev);
+	int value;
+	int ret;
+
+	/* no speed readable on manual mode */
+	if (asus->asus_hwmon_fan_manual_mode)
+		return -ENXIO;
+
+	ret = asus_hwmon_agfn_fan_speed_read(asus, fan+1, &value);
+	if (ret) {
+		pr_warn("reading fan speed failed: %d\n", ret);
+		return -ENXIO;
+	}
+
+	return value;
+}
+
+static void asus_hwmon_pwm_show(struct asus_wmi *asus, int fan, int *value)
+{
+	int err;
+
+	if (asus->asus_hwmon_pwm >= 0) {
+		*value = asus->asus_hwmon_pwm;
+		return;
+	}
+
+	err = asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_FAN_CTRL, value);
+	if (err < 0)
+		return;
+
+	*value &= 0xFF;
+
+	if (*value == 1) /* Low Speed */
+		*value = 85;
+	else if (*value == 2)
+		*value = 170;
+	else if (*value == 3)
+		*value = 255;
+	else if (*value) {
+		pr_err("Unknown fan speed %#x\n", *value);
+		*value = -1;
+	}
+}
+
+static ssize_t pwm1_show(struct device *dev,
 			       struct device_attribute *attr,
 			       char *buf)
 {
 	struct asus_wmi *asus = dev_get_drvdata(dev);
-	u32 value;
-	int err;
+	int value;
 
-	err = asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_FAN_CTRL, &value);
-
-	if (err < 0)
-		return err;
-
-	value &= 0xFF;
-
-	if (value == 1) /* Low Speed */
-		value = 85;
-	else if (value == 2)
-		value = 170;
-	else if (value == 3)
-		value = 255;
-	else if (value != 0) {
-		pr_err("Unknown fan speed %#x\n", value);
-		value = -1;
-	}
+	asus_hwmon_pwm_show(asus, 0, &value);
 
 	return sprintf(buf, "%d\n", value);
 }
 
+static ssize_t pwm1_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count) {
+	struct asus_wmi *asus = dev_get_drvdata(dev);
+	int value;
+	int state;
+	int ret;
+
+	ret = kstrtouint(buf, 10, &value);
+
+	if (ret)
+		return ret;
+
+	value = clamp(value, 0, 255);
+
+	state = asus_hwmon_agfn_fan_speed_write(asus, 1, &value);
+	if (state)
+		pr_warn("Setting fan speed failed: %d\n", state);
+	else
+		asus->asus_hwmon_fan_manual_mode = true;
+
+	return count;
+}
+
+static ssize_t fan1_input_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	int value = asus_hwmon_fan_rpm_show(dev, 0);
+
+	return sprintf(buf, "%d\n", value < 0 ? -1 : value*100);
+
+}
+
+static ssize_t pwm1_enable_show(struct device *dev,
+						 struct device_attribute *attr,
+						 char *buf)
+{
+	struct asus_wmi *asus = dev_get_drvdata(dev);
+
+	if (asus->asus_hwmon_fan_manual_mode)
+		return sprintf(buf, "%d\n", ASUS_FAN_CTRL_MANUAL);
+
+	return sprintf(buf, "%d\n", ASUS_FAN_CTRL_AUTO);
+}
+
+static ssize_t pwm1_enable_store(struct device *dev,
+						  struct device_attribute *attr,
+						  const char *buf, size_t count)
+{
+	struct asus_wmi *asus = dev_get_drvdata(dev);
+	int status = 0;
+	int state;
+	int ret;
+
+	ret = kstrtouint(buf, 10, &state);
+
+	if (ret)
+		return ret;
+
+	if (state == ASUS_FAN_CTRL_MANUAL)
+		asus->asus_hwmon_fan_manual_mode = true;
+	else
+		status = asus_hwmon_fan_set_auto(asus);
+
+	if (status)
+		return status;
+
+	return count;
+}
+
+static ssize_t fan1_label_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
+{
+	return sprintf(buf, "%s\n", ASUS_FAN_DESC);
+}
+
 static ssize_t asus_hwmon_temp1(struct device *dev,
 				struct device_attribute *attr,
 				char *buf)
@@ -1069,11 +1323,21 @@
 	return sprintf(buf, "%d\n", value);
 }
 
-static DEVICE_ATTR(pwm1, S_IRUGO, asus_hwmon_pwm1, NULL);
+/* Fan1 */
+static DEVICE_ATTR_RW(pwm1);
+static DEVICE_ATTR_RW(pwm1_enable);
+static DEVICE_ATTR_RO(fan1_input);
+static DEVICE_ATTR_RO(fan1_label);
+
+/* Temperature */
 static DEVICE_ATTR(temp1_input, S_IRUGO, asus_hwmon_temp1, NULL);
 
 static struct attribute *hwmon_attributes[] = {
 	&dev_attr_pwm1.attr,
+	&dev_attr_pwm1_enable.attr,
+	&dev_attr_fan1_input.attr,
+	&dev_attr_fan1_label.attr,
+
 	&dev_attr_temp1_input.attr,
 	NULL
 };
@@ -1084,19 +1348,28 @@
 	struct device *dev = container_of(kobj, struct device, kobj);
 	struct platform_device *pdev = to_platform_device(dev->parent);
 	struct asus_wmi *asus = platform_get_drvdata(pdev);
-	bool ok = true;
 	int dev_id = -1;
+	int fan_attr = -1;
 	u32 value = ASUS_WMI_UNSUPPORTED_METHOD;
+	bool ok = true;
 
 	if (attr == &dev_attr_pwm1.attr)
 		dev_id = ASUS_WMI_DEVID_FAN_CTRL;
 	else if (attr == &dev_attr_temp1_input.attr)
 		dev_id = ASUS_WMI_DEVID_THERMAL_CTRL;
 
+
+	if (attr == &dev_attr_fan1_input.attr
+	    || attr == &dev_attr_fan1_label.attr
+	    || attr == &dev_attr_pwm1.attr
+	    || attr == &dev_attr_pwm1_enable.attr) {
+		fan_attr = 1;
+	}
+
 	if (dev_id != -1) {
 		int err = asus_wmi_get_devstate(asus, dev_id, &value);
 
-		if (err < 0)
+		if (err < 0 && fan_attr == -1)
 			return 0; /* can't return negative here */
 	}
 
@@ -1112,10 +1385,16 @@
 		if (value == ASUS_WMI_UNSUPPORTED_METHOD || value & 0xFFF80000
 		    || (!asus->sfun && !(value & ASUS_WMI_DSTS_PRESENCE_BIT)))
 			ok = false;
+		else
+			ok = fan_attr <= asus->asus_hwmon_num_fans;
 	} else if (dev_id == ASUS_WMI_DEVID_THERMAL_CTRL) {
 		/* If value is zero, something is clearly wrong */
-		if (value == 0)
+		if (!value)
 			ok = false;
+	} else if (fan_attr <= asus->asus_hwmon_num_fans && fan_attr != -1) {
+		ok = true;
+	} else {
+		ok = false;
 	}
 
 	return ok ? attr->mode : 0;
@@ -1723,6 +2002,25 @@
 	return -ENOMEM;
 }
 
+static int asus_wmi_fan_init(struct asus_wmi *asus)
+{
+	int status;
+
+	asus->asus_hwmon_pwm = -1;
+	asus->asus_hwmon_num_fans = -1;
+	asus->asus_hwmon_fan_manual_mode = false;
+
+	status = asus_hwmon_get_fan_number(asus, &asus->asus_hwmon_num_fans);
+	if (status) {
+		asus->asus_hwmon_num_fans = 0;
+		pr_warn("Could not determine number of fans: %d\n", status);
+		return -ENXIO;
+	}
+
+	pr_info("Number of fans: %d\n", asus->asus_hwmon_num_fans);
+	return 0;
+}
+
 /*
  * WMI Driver
  */
@@ -1756,6 +2054,9 @@
 	if (err)
 		goto fail_input;
 
+	err = asus_wmi_fan_init(asus); /* probably no problems on error */
+	asus_hwmon_fan_set_auto(asus);
+
 	err = asus_wmi_hwmon_init(asus);
 	if (err)
 		goto fail_hwmon;
@@ -1831,6 +2132,7 @@
 	asus_wmi_rfkill_exit(asus);
 	asus_wmi_debugfs_exit(asus);
 	asus_wmi_platform_exit(asus);
+	asus_hwmon_fan_set_auto(asus);
 
 	kfree(asus);
 	return 0;
diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c
index 01d0810..ed317cc 100644
--- a/drivers/platform/x86/dell-laptop.c
+++ b/drivers/platform/x86/dell-laptop.c
@@ -33,6 +33,7 @@
 #include <linux/seq_file.h>
 #include <acpi/video.h>
 #include "../../firmware/dcdbas.h"
+#include "dell-rbtn.h"
 
 #define BRIGHTNESS_TOKEN 0x7d
 #define KBD_LED_OFF_TOKEN 0x01E1
@@ -306,7 +307,6 @@
 };
 
 static struct calling_interface_buffer *buffer;
-static struct page *bufferpage;
 static DEFINE_MUTEX(buffer_mutex);
 
 static int hwswitch_state;
@@ -423,45 +423,125 @@
 	}
 }
 
-/* Derived from information in DellWirelessCtl.cpp:
-   Class 17, select 11 is radio control. It returns an array of 32-bit values.
-
-   Input byte 0 = 0: Wireless information
-
-   result[0]: return code
-   result[1]:
-     Bit 0:      Hardware switch supported
-     Bit 1:      Wifi locator supported
-     Bit 2:      Wifi is supported
-     Bit 3:      Bluetooth is supported
-     Bit 4:      WWAN is supported
-     Bit 5:      Wireless keyboard supported
-     Bits 6-7:   Reserved
-     Bit 8:      Wifi is installed
-     Bit 9:      Bluetooth is installed
-     Bit 10:     WWAN is installed
-     Bits 11-15: Reserved
-     Bit 16:     Hardware switch is on
-     Bit 17:     Wifi is blocked
-     Bit 18:     Bluetooth is blocked
-     Bit 19:     WWAN is blocked
-     Bits 20-31: Reserved
-   result[2]: NVRAM size in bytes
-   result[3]: NVRAM format version number
-
-   Input byte 0 = 2: Wireless switch configuration
-   result[0]: return code
-   result[1]:
-     Bit 0:      Wifi controlled by switch
-     Bit 1:      Bluetooth controlled by switch
-     Bit 2:      WWAN controlled by switch
-     Bits 3-6:   Reserved
-     Bit 7:      Wireless switch config locked
-     Bit 8:      Wifi locator enabled
-     Bits 9-14:  Reserved
-     Bit 15:     Wifi locator setting locked
-     Bits 16-31: Reserved
-*/
+/*
+ * Derived from information in smbios-wireless-ctl:
+ *
+ * cbSelect 17, Value 11
+ *
+ * Return Wireless Info
+ * cbArg1, byte0 = 0x00
+ *
+ *     cbRes1 Standard return codes (0, -1, -2)
+ *     cbRes2 Info bit flags:
+ *
+ *     0 Hardware switch supported (1)
+ *     1 WiFi locator supported (1)
+ *     2 WLAN supported (1)
+ *     3 Bluetooth (BT) supported (1)
+ *     4 WWAN supported (1)
+ *     5 Wireless KBD supported (1)
+ *     6 Uw b supported (1)
+ *     7 WiGig supported (1)
+ *     8 WLAN installed (1)
+ *     9 BT installed (1)
+ *     10 WWAN installed (1)
+ *     11 Uw b installed (1)
+ *     12 WiGig installed (1)
+ *     13-15 Reserved (0)
+ *     16 Hardware (HW) switch is On (1)
+ *     17 WLAN disabled (1)
+ *     18 BT disabled (1)
+ *     19 WWAN disabled (1)
+ *     20 Uw b disabled (1)
+ *     21 WiGig disabled (1)
+ *     20-31 Reserved (0)
+ *
+ *     cbRes3 NVRAM size in bytes
+ *     cbRes4, byte 0 NVRAM format version number
+ *
+ *
+ * Set QuickSet Radio Disable Flag
+ *     cbArg1, byte0 = 0x01
+ *     cbArg1, byte1
+ *     Radio ID     value:
+ *     0        Radio Status
+ *     1        WLAN ID
+ *     2        BT ID
+ *     3        WWAN ID
+ *     4        UWB ID
+ *     5        WIGIG ID
+ *     cbArg1, byte2    Flag bits:
+ *             0 QuickSet disables radio (1)
+ *             1-7 Reserved (0)
+ *
+ *     cbRes1    Standard return codes (0, -1, -2)
+ *     cbRes2    QuickSet (QS) radio disable bit map:
+ *     0 QS disables WLAN
+ *     1 QS disables BT
+ *     2 QS disables WWAN
+ *     3 QS disables UWB
+ *     4 QS disables WIGIG
+ *     5-31 Reserved (0)
+ *
+ * Wireless Switch Configuration
+ *     cbArg1, byte0 = 0x02
+ *
+ *     cbArg1, byte1
+ *     Subcommand:
+ *     0 Get config
+ *     1 Set config
+ *     2 Set WiFi locator enable/disable
+ *     cbArg1,byte2
+ *     Switch settings (if byte 1==1):
+ *     0 WLAN sw itch control (1)
+ *     1 BT sw itch control (1)
+ *     2 WWAN sw itch control (1)
+ *     3 UWB sw itch control (1)
+ *     4 WiGig sw itch control (1)
+ *     5-7 Reserved (0)
+ *    cbArg1, byte2 Enable bits (if byte 1==2):
+ *     0 Enable WiFi locator (1)
+ *
+ *    cbRes1     Standard return codes (0, -1, -2)
+ *    cbRes2 QuickSet radio disable bit map:
+ *     0 WLAN controlled by sw itch (1)
+ *     1 BT controlled by sw itch (1)
+ *     2 WWAN controlled by sw itch (1)
+ *     3 UWB controlled by sw itch (1)
+ *     4 WiGig controlled by sw itch (1)
+ *     5-6 Reserved (0)
+ *     7 Wireless sw itch config locked (1)
+ *     8 WiFi locator enabled (1)
+ *     9-14 Reserved (0)
+ *     15 WiFi locator setting locked (1)
+ *     16-31 Reserved (0)
+ *
+ * Read Local Config Data (LCD)
+ *     cbArg1, byte0 = 0x10
+ *     cbArg1, byte1 NVRAM index low byte
+ *     cbArg1, byte2 NVRAM index high byte
+ *     cbRes1 Standard return codes (0, -1, -2)
+ *     cbRes2 4 bytes read from LCD[index]
+ *     cbRes3 4 bytes read from LCD[index+4]
+ *     cbRes4 4 bytes read from LCD[index+8]
+ *
+ * Write Local Config Data (LCD)
+ *     cbArg1, byte0 = 0x11
+ *     cbArg1, byte1 NVRAM index low byte
+ *     cbArg1, byte2 NVRAM index high byte
+ *     cbArg2 4 bytes to w rite at LCD[index]
+ *     cbArg3 4 bytes to w rite at LCD[index+4]
+ *     cbArg4 4 bytes to w rite at LCD[index+8]
+ *     cbRes1 Standard return codes (0, -1, -2)
+ *
+ * Populate Local Config Data from NVRAM
+ *     cbArg1, byte0 = 0x12
+ *     cbRes1 Standard return codes (0, -1, -2)
+ *
+ * Commit Local Config Data to NVRAM
+ *     cbArg1, byte0 = 0x13
+ *     cbRes1 Standard return codes (0, -1, -2)
+ */
 
 static int dell_rfkill_set(void *data, bool blocked)
 {
@@ -549,12 +629,21 @@
 		  (status & BIT(4)) >> 4);
 	seq_printf(s, "Bit 5 : Wireless keyboard supported: %lu\n",
 		  (status & BIT(5)) >> 5);
+	seq_printf(s, "Bit 6 : UWB supported:               %lu\n",
+		  (status & BIT(6)) >> 6);
+	seq_printf(s, "Bit 7 : WiGig supported:             %lu\n",
+		  (status & BIT(7)) >> 7);
 	seq_printf(s, "Bit 8 : Wifi is installed:           %lu\n",
 		  (status & BIT(8)) >> 8);
 	seq_printf(s, "Bit 9 : Bluetooth is installed:      %lu\n",
 		  (status & BIT(9)) >> 9);
 	seq_printf(s, "Bit 10: WWAN is installed:           %lu\n",
 		  (status & BIT(10)) >> 10);
+	seq_printf(s, "Bit 11: UWB installed:               %lu\n",
+		  (status & BIT(11)) >> 11);
+	seq_printf(s, "Bit 12: WiGig installed:             %lu\n",
+		  (status & BIT(12)) >> 12);
+
 	seq_printf(s, "Bit 16: Hardware switch is on:       %lu\n",
 		  (status & BIT(16)) >> 16);
 	seq_printf(s, "Bit 17: Wifi is blocked:             %lu\n",
@@ -563,6 +652,10 @@
 		  (status & BIT(18)) >> 18);
 	seq_printf(s, "Bit 19: WWAN is blocked:             %lu\n",
 		  (status & BIT(19)) >> 19);
+	seq_printf(s, "Bit 20: UWB is blocked:              %lu\n",
+		  (status & BIT(20)) >> 20);
+	seq_printf(s, "Bit 21: WiGig is blocked:            %lu\n",
+		  (status & BIT(21)) >> 21);
 
 	seq_printf(s, "\nhwswitch_state:\t0x%X\n", hwswitch_state);
 	seq_printf(s, "Bit 0 : Wifi controlled by switch:      %lu\n",
@@ -571,6 +664,10 @@
 		   (hwswitch_state & BIT(1)) >> 1);
 	seq_printf(s, "Bit 2 : WWAN controlled by switch:      %lu\n",
 		   (hwswitch_state & BIT(2)) >> 2);
+	seq_printf(s, "Bit 3 : UWB controlled by switch:       %lu\n",
+		   (hwswitch_state & BIT(3)) >> 3);
+	seq_printf(s, "Bit 4 : WiGig controlled by switch:     %lu\n",
+		   (hwswitch_state & BIT(4)) >> 4);
 	seq_printf(s, "Bit 7 : Wireless switch config locked:  %lu\n",
 		   (hwswitch_state & BIT(7)) >> 7);
 	seq_printf(s, "Bit 8 : Wifi locator enabled:           %lu\n",
@@ -643,6 +740,20 @@
 	return false;
 }
 
+static int (*dell_rbtn_notifier_register_func)(struct notifier_block *);
+static int (*dell_rbtn_notifier_unregister_func)(struct notifier_block *);
+
+static int dell_laptop_rbtn_notifier_call(struct notifier_block *nb,
+					  unsigned long action, void *data)
+{
+	schedule_delayed_work(&dell_rfkill_work, 0);
+	return NOTIFY_OK;
+}
+
+static struct notifier_block dell_laptop_rbtn_notifier = {
+	.notifier_call = dell_laptop_rbtn_notifier_call,
+};
+
 static int __init dell_setup_rfkill(void)
 {
 	int status, ret, whitelisted;
@@ -719,10 +830,62 @@
 			goto err_wwan;
 	}
 
-	ret = i8042_install_filter(dell_laptop_i8042_filter);
-	if (ret) {
-		pr_warn("Unable to install key filter\n");
+	/*
+	 * Dell Airplane Mode Switch driver (dell-rbtn) supports ACPI devices
+	 * which can receive events from HW slider switch.
+	 *
+	 * Dell SMBIOS on whitelisted models supports controlling radio devices
+	 * but does not support receiving HW button switch events. We can use
+	 * i8042 filter hook function to receive keyboard data and handle
+	 * keycode for HW button.
+	 *
+	 * So if it is possible we will use Dell Airplane Mode Switch ACPI
+	 * driver for receiving HW events and Dell SMBIOS for setting rfkill
+	 * states. If ACPI driver or device is not available we will fallback to
+	 * i8042 filter hook function.
+	 *
+	 * To prevent duplicate rfkill devices which control and do same thing,
+	 * dell-rbtn driver will automatically remove its own rfkill devices
+	 * once function dell_rbtn_notifier_register() is called.
+	 */
+
+	dell_rbtn_notifier_register_func =
+		symbol_request(dell_rbtn_notifier_register);
+	if (dell_rbtn_notifier_register_func) {
+		dell_rbtn_notifier_unregister_func =
+			symbol_request(dell_rbtn_notifier_unregister);
+		if (!dell_rbtn_notifier_unregister_func) {
+			symbol_put(dell_rbtn_notifier_register);
+			dell_rbtn_notifier_register_func = NULL;
+		}
+	}
+
+	if (dell_rbtn_notifier_register_func) {
+		ret = dell_rbtn_notifier_register_func(
+			&dell_laptop_rbtn_notifier);
+		symbol_put(dell_rbtn_notifier_register);
+		dell_rbtn_notifier_register_func = NULL;
+		if (ret != 0) {
+			symbol_put(dell_rbtn_notifier_unregister);
+			dell_rbtn_notifier_unregister_func = NULL;
+		}
+	} else {
+		pr_info("Symbols from dell-rbtn acpi driver are not available\n");
+		ret = -ENODEV;
+	}
+
+	if (ret == 0) {
+		pr_info("Using dell-rbtn acpi driver for receiving events\n");
+	} else if (ret != -ENODEV) {
+		pr_warn("Unable to register dell rbtn notifier\n");
 		goto err_filter;
+	} else {
+		ret = i8042_install_filter(dell_laptop_i8042_filter);
+		if (ret) {
+			pr_warn("Unable to install key filter\n");
+			goto err_filter;
+		}
+		pr_info("Using i8042 filter function for receiving events\n");
 	}
 
 	return 0;
@@ -745,6 +908,14 @@
 
 static void dell_cleanup_rfkill(void)
 {
+	if (dell_rbtn_notifier_unregister_func) {
+		dell_rbtn_notifier_unregister_func(&dell_laptop_rbtn_notifier);
+		symbol_put(dell_rbtn_notifier_unregister);
+		dell_rbtn_notifier_unregister_func = NULL;
+	} else {
+		i8042_remove_filter(dell_laptop_i8042_filter);
+	}
+	cancel_delayed_work_sync(&dell_rfkill_work);
 	if (wifi_rfkill) {
 		rfkill_unregister(wifi_rfkill);
 		rfkill_destroy(wifi_rfkill);
@@ -1897,12 +2068,11 @@
 	 * Allocate buffer below 4GB for SMI data--only 32-bit physical addr
 	 * is passed to SMI handler.
 	 */
-	bufferpage = alloc_page(GFP_KERNEL | GFP_DMA32);
-	if (!bufferpage) {
+	buffer = (void *)__get_free_page(GFP_KERNEL | GFP_DMA32);
+	if (!buffer) {
 		ret = -ENOMEM;
 		goto fail_buffer;
 	}
-	buffer = page_address(bufferpage);
 
 	ret = dell_setup_rfkill();
 
@@ -1957,11 +2127,9 @@
 	return 0;
 
 fail_backlight:
-	i8042_remove_filter(dell_laptop_i8042_filter);
-	cancel_delayed_work_sync(&dell_rfkill_work);
 	dell_cleanup_rfkill();
 fail_rfkill:
-	free_page((unsigned long)bufferpage);
+	free_page((unsigned long)buffer);
 fail_buffer:
 	platform_device_del(platform_device);
 fail_platform_device2:
@@ -1979,8 +2147,6 @@
 	if (quirks && quirks->touchpad_led)
 		touchpad_led_exit();
 	kbd_led_exit();
-	i8042_remove_filter(dell_laptop_i8042_filter);
-	cancel_delayed_work_sync(&dell_rfkill_work);
 	backlight_device_unregister(dell_backlight_device);
 	dell_cleanup_rfkill();
 	if (platform_device) {
@@ -1991,7 +2157,14 @@
 	free_page((unsigned long)buffer);
 }
 
-module_init(dell_init);
+/* dell-rbtn.c driver export functions which will not work correctly (and could
+ * cause kernel crash) if they are called before dell-rbtn.c init code. This is
+ * not problem when dell-rbtn.c is compiled as external module. When both files
+ * (dell-rbtn.c and dell-laptop.c) are compiled statically into kernel, then we
+ * need to ensure that dell_init() will be called after initializing dell-rbtn.
+ * This can be achieved by late_initcall() instead module_init().
+ */
+late_initcall(dell_init);
 module_exit(dell_exit);
 
 MODULE_AUTHOR("Matthew Garrett <mjg@redhat.com>");
diff --git a/drivers/platform/x86/dell-rbtn.c b/drivers/platform/x86/dell-rbtn.c
new file mode 100644
index 0000000..cd410e3
--- /dev/null
+++ b/drivers/platform/x86/dell-rbtn.c
@@ -0,0 +1,423 @@
+/*
+    Dell Airplane Mode Switch driver
+    Copyright (C) 2014-2015  Pali Rohár <pali.rohar@gmail.com>
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+*/
+
+#include <linux/module.h>
+#include <linux/acpi.h>
+#include <linux/rfkill.h>
+#include <linux/input.h>
+
+enum rbtn_type {
+	RBTN_UNKNOWN,
+	RBTN_TOGGLE,
+	RBTN_SLIDER,
+};
+
+struct rbtn_data {
+	enum rbtn_type type;
+	struct rfkill *rfkill;
+	struct input_dev *input_dev;
+};
+
+
+/*
+ * acpi functions
+ */
+
+static enum rbtn_type rbtn_check(struct acpi_device *device)
+{
+	unsigned long long output;
+	acpi_status status;
+
+	status = acpi_evaluate_integer(device->handle, "CRBT", NULL, &output);
+	if (ACPI_FAILURE(status))
+		return RBTN_UNKNOWN;
+
+	switch (output) {
+	case 0:
+	case 1:
+		return RBTN_TOGGLE;
+	case 2:
+	case 3:
+		return RBTN_SLIDER;
+	default:
+		return RBTN_UNKNOWN;
+	}
+}
+
+static int rbtn_get(struct acpi_device *device)
+{
+	unsigned long long output;
+	acpi_status status;
+
+	status = acpi_evaluate_integer(device->handle, "GRBT", NULL, &output);
+	if (ACPI_FAILURE(status))
+		return -EINVAL;
+
+	return !output;
+}
+
+static int rbtn_acquire(struct acpi_device *device, bool enable)
+{
+	struct acpi_object_list input;
+	union acpi_object param;
+	acpi_status status;
+
+	param.type = ACPI_TYPE_INTEGER;
+	param.integer.value = enable;
+	input.count = 1;
+	input.pointer = &param;
+
+	status = acpi_evaluate_object(device->handle, "ARBT", &input, NULL);
+	if (ACPI_FAILURE(status))
+		return -EINVAL;
+
+	return 0;
+}
+
+
+/*
+ * rfkill device
+ */
+
+static void rbtn_rfkill_query(struct rfkill *rfkill, void *data)
+{
+	struct acpi_device *device = data;
+	int state;
+
+	state = rbtn_get(device);
+	if (state < 0)
+		return;
+
+	rfkill_set_states(rfkill, state, state);
+}
+
+static int rbtn_rfkill_set_block(void *data, bool blocked)
+{
+	/* NOTE: setting soft rfkill state is not supported */
+	return -EINVAL;
+}
+
+static struct rfkill_ops rbtn_ops = {
+	.query = rbtn_rfkill_query,
+	.set_block = rbtn_rfkill_set_block,
+};
+
+static int rbtn_rfkill_init(struct acpi_device *device)
+{
+	struct rbtn_data *rbtn_data = device->driver_data;
+	int ret;
+
+	if (rbtn_data->rfkill)
+		return 0;
+
+	/*
+	 * NOTE: rbtn controls all radio devices, not only WLAN
+	 *       but rfkill interface does not support "ANY" type
+	 *       so "WLAN" type is used
+	 */
+	rbtn_data->rfkill = rfkill_alloc("dell-rbtn", &device->dev,
+					 RFKILL_TYPE_WLAN, &rbtn_ops, device);
+	if (!rbtn_data->rfkill)
+		return -ENOMEM;
+
+	ret = rfkill_register(rbtn_data->rfkill);
+	if (ret) {
+		rfkill_destroy(rbtn_data->rfkill);
+		rbtn_data->rfkill = NULL;
+		return ret;
+	}
+
+	return 0;
+}
+
+static void rbtn_rfkill_exit(struct acpi_device *device)
+{
+	struct rbtn_data *rbtn_data = device->driver_data;
+
+	if (!rbtn_data->rfkill)
+		return;
+
+	rfkill_unregister(rbtn_data->rfkill);
+	rfkill_destroy(rbtn_data->rfkill);
+	rbtn_data->rfkill = NULL;
+}
+
+static void rbtn_rfkill_event(struct acpi_device *device)
+{
+	struct rbtn_data *rbtn_data = device->driver_data;
+
+	if (rbtn_data->rfkill)
+		rbtn_rfkill_query(rbtn_data->rfkill, device);
+}
+
+
+/*
+ * input device
+ */
+
+static int rbtn_input_init(struct rbtn_data *rbtn_data)
+{
+	int ret;
+
+	rbtn_data->input_dev = input_allocate_device();
+	if (!rbtn_data->input_dev)
+		return -ENOMEM;
+
+	rbtn_data->input_dev->name = "DELL Wireless hotkeys";
+	rbtn_data->input_dev->phys = "dellabce/input0";
+	rbtn_data->input_dev->id.bustype = BUS_HOST;
+	rbtn_data->input_dev->evbit[0] = BIT(EV_KEY);
+	set_bit(KEY_RFKILL, rbtn_data->input_dev->keybit);
+
+	ret = input_register_device(rbtn_data->input_dev);
+	if (ret) {
+		input_free_device(rbtn_data->input_dev);
+		rbtn_data->input_dev = NULL;
+		return ret;
+	}
+
+	return 0;
+}
+
+static void rbtn_input_exit(struct rbtn_data *rbtn_data)
+{
+	input_unregister_device(rbtn_data->input_dev);
+	rbtn_data->input_dev = NULL;
+}
+
+static void rbtn_input_event(struct rbtn_data *rbtn_data)
+{
+	input_report_key(rbtn_data->input_dev, KEY_RFKILL, 1);
+	input_sync(rbtn_data->input_dev);
+	input_report_key(rbtn_data->input_dev, KEY_RFKILL, 0);
+	input_sync(rbtn_data->input_dev);
+}
+
+
+/*
+ * acpi driver
+ */
+
+static int rbtn_add(struct acpi_device *device);
+static int rbtn_remove(struct acpi_device *device);
+static void rbtn_notify(struct acpi_device *device, u32 event);
+
+static const struct acpi_device_id rbtn_ids[] = {
+	{ "DELRBTN", 0 },
+	{ "DELLABCE", 0 },
+	{ "", 0 },
+};
+
+static struct acpi_driver rbtn_driver = {
+	.name = "dell-rbtn",
+	.ids = rbtn_ids,
+	.ops = {
+		.add = rbtn_add,
+		.remove = rbtn_remove,
+		.notify = rbtn_notify,
+	},
+	.owner = THIS_MODULE,
+};
+
+
+/*
+ * notifier export functions
+ */
+
+static bool auto_remove_rfkill = true;
+
+static ATOMIC_NOTIFIER_HEAD(rbtn_chain_head);
+
+static int rbtn_inc_count(struct device *dev, void *data)
+{
+	struct acpi_device *device = to_acpi_device(dev);
+	struct rbtn_data *rbtn_data = device->driver_data;
+	int *count = data;
+
+	if (rbtn_data->type == RBTN_SLIDER)
+		(*count)++;
+
+	return 0;
+}
+
+static int rbtn_switch_dev(struct device *dev, void *data)
+{
+	struct acpi_device *device = to_acpi_device(dev);
+	struct rbtn_data *rbtn_data = device->driver_data;
+	bool enable = data;
+
+	if (rbtn_data->type != RBTN_SLIDER)
+		return 0;
+
+	if (enable)
+		rbtn_rfkill_init(device);
+	else
+		rbtn_rfkill_exit(device);
+
+	return 0;
+}
+
+int dell_rbtn_notifier_register(struct notifier_block *nb)
+{
+	bool first;
+	int count;
+	int ret;
+
+	count = 0;
+	ret = driver_for_each_device(&rbtn_driver.drv, NULL, &count,
+				     rbtn_inc_count);
+	if (ret || count == 0)
+		return -ENODEV;
+
+	first = !rbtn_chain_head.head;
+
+	ret = atomic_notifier_chain_register(&rbtn_chain_head, nb);
+	if (ret != 0)
+		return ret;
+
+	if (auto_remove_rfkill && first)
+		ret = driver_for_each_device(&rbtn_driver.drv, NULL,
+					     (void *)false, rbtn_switch_dev);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dell_rbtn_notifier_register);
+
+int dell_rbtn_notifier_unregister(struct notifier_block *nb)
+{
+	int ret;
+
+	ret = atomic_notifier_chain_unregister(&rbtn_chain_head, nb);
+	if (ret != 0)
+		return ret;
+
+	if (auto_remove_rfkill && !rbtn_chain_head.head)
+		ret = driver_for_each_device(&rbtn_driver.drv, NULL,
+					     (void *)true, rbtn_switch_dev);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dell_rbtn_notifier_unregister);
+
+
+/*
+ * acpi driver functions
+ */
+
+static int rbtn_add(struct acpi_device *device)
+{
+	struct rbtn_data *rbtn_data;
+	enum rbtn_type type;
+	int ret = 0;
+
+	type = rbtn_check(device);
+	if (type == RBTN_UNKNOWN) {
+		dev_info(&device->dev, "Unknown device type\n");
+		return -EINVAL;
+	}
+
+	ret = rbtn_acquire(device, true);
+	if (ret < 0) {
+		dev_err(&device->dev, "Cannot enable device\n");
+		return ret;
+	}
+
+	rbtn_data = devm_kzalloc(&device->dev, sizeof(*rbtn_data), GFP_KERNEL);
+	if (!rbtn_data)
+		return -ENOMEM;
+
+	rbtn_data->type = type;
+	device->driver_data = rbtn_data;
+
+	switch (rbtn_data->type) {
+	case RBTN_TOGGLE:
+		ret = rbtn_input_init(rbtn_data);
+		break;
+	case RBTN_SLIDER:
+		if (auto_remove_rfkill && rbtn_chain_head.head)
+			ret = 0;
+		else
+			ret = rbtn_rfkill_init(device);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+
+}
+
+static int rbtn_remove(struct acpi_device *device)
+{
+	struct rbtn_data *rbtn_data = device->driver_data;
+
+	switch (rbtn_data->type) {
+	case RBTN_TOGGLE:
+		rbtn_input_exit(rbtn_data);
+		break;
+	case RBTN_SLIDER:
+		rbtn_rfkill_exit(device);
+		break;
+	default:
+		break;
+	}
+
+	rbtn_acquire(device, false);
+	device->driver_data = NULL;
+
+	return 0;
+}
+
+static void rbtn_notify(struct acpi_device *device, u32 event)
+{
+	struct rbtn_data *rbtn_data = device->driver_data;
+
+	if (event != 0x80) {
+		dev_info(&device->dev, "Received unknown event (0x%x)\n",
+			 event);
+		return;
+	}
+
+	switch (rbtn_data->type) {
+	case RBTN_TOGGLE:
+		rbtn_input_event(rbtn_data);
+		break;
+	case RBTN_SLIDER:
+		rbtn_rfkill_event(device);
+		atomic_notifier_call_chain(&rbtn_chain_head, event, device);
+		break;
+	default:
+		break;
+	}
+}
+
+
+/*
+ * module functions
+ */
+
+module_acpi_driver(rbtn_driver);
+
+module_param(auto_remove_rfkill, bool, 0444);
+
+MODULE_PARM_DESC(auto_remove_rfkill, "Automatically remove rfkill devices when "
+				     "other modules start receiving events "
+				     "from this module and re-add them when "
+				     "the last module stops receiving events "
+				     "(default true)");
+MODULE_DEVICE_TABLE(acpi, rbtn_ids);
+MODULE_DESCRIPTION("Dell Airplane Mode Switch driver");
+MODULE_AUTHOR("Pali Rohár <pali.rohar@gmail.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/platform/x86/dell-rbtn.h b/drivers/platform/x86/dell-rbtn.h
new file mode 100644
index 0000000..c59cc6b
--- /dev/null
+++ b/drivers/platform/x86/dell-rbtn.h
@@ -0,0 +1,24 @@
+/*
+    Dell Airplane Mode Switch driver
+    Copyright (C) 2014-2015  Pali Rohár <pali.rohar@gmail.com>
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+*/
+
+#ifndef _DELL_RBTN_H_
+#define _DELL_RBTN_H_
+
+struct notifier_block;
+
+int dell_rbtn_notifier_register(struct notifier_block *nb);
+int dell_rbtn_notifier_unregister(struct notifier_block *nb);
+
+#endif
diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index bea0228..76b5738 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -465,8 +465,9 @@
 static int ideapad_rfk_set(void *data, bool blocked)
 {
 	struct ideapad_rfk_priv *priv = data;
+	int opcode = ideapad_rfk_data[priv->dev].opcode;
 
-	return write_ec_cmd(priv->priv->adev->handle, priv->dev, !blocked);
+	return write_ec_cmd(priv->priv->adev->handle, opcode, !blocked);
 }
 
 static struct rfkill_ops ideapad_rfk_ops = {
@@ -838,6 +839,13 @@
 		},
 	},
 	{
+		.ident = "Lenovo G50-30",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo G50-30"),
+		},
+	},
+	{
 		.ident = "Lenovo Yoga 2 11 / 13 / Pro",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
diff --git a/drivers/platform/x86/intel_pmc_ipc.c b/drivers/platform/x86/intel_pmc_ipc.c
new file mode 100644
index 0000000..d734763
--- /dev/null
+++ b/drivers/platform/x86/intel_pmc_ipc.c
@@ -0,0 +1,767 @@
+/*
+ * intel_pmc_ipc.c: Driver for the Intel PMC IPC mechanism
+ *
+ * (C) Copyright 2014-2015 Intel Corporation
+ *
+ * This driver is based on Intel SCU IPC driver(intel_scu_opc.c) by
+ *     Sreedhara DS <sreedhara.ds@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ *
+ * PMC running in ARC processor communicates with other entity running in IA
+ * core through IPC mechanism which in turn messaging between IA core ad PMC.
+ */
+
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/pm.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/interrupt.h>
+#include <linux/pm_qos.h>
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/sched.h>
+#include <linux/atomic.h>
+#include <linux/notifier.h>
+#include <linux/suspend.h>
+#include <linux/acpi.h>
+#include <asm/intel_pmc_ipc.h>
+#include <linux/mfd/lpc_ich.h>
+
+/*
+ * IPC registers
+ * The IA write to IPC_CMD command register triggers an interrupt to the ARC,
+ * The ARC handles the interrupt and services it, writing optional data to
+ * the IPC1 registers, updates the IPC_STS response register with the status.
+ */
+#define IPC_CMD			0x0
+#define		IPC_CMD_MSI		0x100
+#define		IPC_CMD_SIZE		16
+#define		IPC_CMD_SUBCMD		12
+#define IPC_STATUS		0x04
+#define		IPC_STATUS_IRQ		0x4
+#define		IPC_STATUS_ERR		0x2
+#define		IPC_STATUS_BUSY		0x1
+#define IPC_SPTR		0x08
+#define IPC_DPTR		0x0C
+#define IPC_WRITE_BUFFER	0x80
+#define IPC_READ_BUFFER		0x90
+
+/*
+ * 16-byte buffer for sending data associated with IPC command.
+ */
+#define IPC_DATA_BUFFER_SIZE	16
+
+#define IPC_LOOP_CNT		3000000
+#define IPC_MAX_SEC		3
+
+#define IPC_TRIGGER_MODE_IRQ		true
+
+/* exported resources from IFWI */
+#define PLAT_RESOURCE_IPC_INDEX		0
+#define PLAT_RESOURCE_IPC_SIZE		0x1000
+#define PLAT_RESOURCE_GCR_SIZE		0x1000
+#define PLAT_RESOURCE_PUNIT_DATA_INDEX	1
+#define PLAT_RESOURCE_PUNIT_INTER_INDEX	2
+#define PLAT_RESOURCE_ACPI_IO_INDEX	0
+
+/*
+ * BIOS does not create an ACPI device for each PMC function,
+ * but exports multiple resources from one ACPI device(IPC) for
+ * multiple functions. This driver is responsible to create a
+ * platform device and to export resources for those functions.
+ */
+#define TCO_DEVICE_NAME			"iTCO_wdt"
+#define SMI_EN_OFFSET			0x30
+#define SMI_EN_SIZE			4
+#define TCO_BASE_OFFSET			0x60
+#define TCO_REGS_SIZE			16
+#define PUNIT_DEVICE_NAME		"intel_punit_ipc"
+
+static const int iTCO_version = 3;
+
+static struct intel_pmc_ipc_dev {
+	struct device *dev;
+	void __iomem *ipc_base;
+	bool irq_mode;
+	int irq;
+	int cmd;
+	struct completion cmd_complete;
+
+	/* The following PMC BARs share the same ACPI device with the IPC */
+	void *acpi_io_base;
+	int acpi_io_size;
+	struct platform_device *tco_dev;
+
+	/* gcr */
+	void *gcr_base;
+	int gcr_size;
+
+	/* punit */
+	void *punit_base;
+	int punit_size;
+	void *punit_base2;
+	int punit_size2;
+	struct platform_device *punit_dev;
+} ipcdev;
+
+static char *ipc_err_sources[] = {
+	[IPC_ERR_NONE] =
+		"no error",
+	[IPC_ERR_CMD_NOT_SUPPORTED] =
+		"command not supported",
+	[IPC_ERR_CMD_NOT_SERVICED] =
+		"command not serviced",
+	[IPC_ERR_UNABLE_TO_SERVICE] =
+		"unable to service",
+	[IPC_ERR_CMD_INVALID] =
+		"command invalid",
+	[IPC_ERR_CMD_FAILED] =
+		"command failed",
+	[IPC_ERR_EMSECURITY] =
+		"Invalid Battery",
+	[IPC_ERR_UNSIGNEDKERNEL] =
+		"Unsigned kernel",
+};
+
+/* Prevent concurrent calls to the PMC */
+static DEFINE_MUTEX(ipclock);
+
+static inline void ipc_send_command(u32 cmd)
+{
+	ipcdev.cmd = cmd;
+	if (ipcdev.irq_mode) {
+		reinit_completion(&ipcdev.cmd_complete);
+		cmd |= IPC_CMD_MSI;
+	}
+	writel(cmd, ipcdev.ipc_base + IPC_CMD);
+}
+
+static inline u32 ipc_read_status(void)
+{
+	return readl(ipcdev.ipc_base + IPC_STATUS);
+}
+
+static inline void ipc_data_writel(u32 data, u32 offset)
+{
+	writel(data, ipcdev.ipc_base + IPC_WRITE_BUFFER + offset);
+}
+
+static inline u8 ipc_data_readb(u32 offset)
+{
+	return readb(ipcdev.ipc_base + IPC_READ_BUFFER + offset);
+}
+
+static inline u32 ipc_data_readl(u32 offset)
+{
+	return readl(ipcdev.ipc_base + IPC_READ_BUFFER + offset);
+}
+
+static int intel_pmc_ipc_check_status(void)
+{
+	int status;
+	int ret = 0;
+
+	if (ipcdev.irq_mode) {
+		if (0 == wait_for_completion_timeout(
+				&ipcdev.cmd_complete, IPC_MAX_SEC * HZ))
+			ret = -ETIMEDOUT;
+	} else {
+		int loop_count = IPC_LOOP_CNT;
+
+		while ((ipc_read_status() & IPC_STATUS_BUSY) && --loop_count)
+			udelay(1);
+		if (loop_count == 0)
+			ret = -ETIMEDOUT;
+	}
+
+	status = ipc_read_status();
+	if (ret == -ETIMEDOUT) {
+		dev_err(ipcdev.dev,
+			"IPC timed out, TS=0x%x, CMD=0x%x\n",
+			status, ipcdev.cmd);
+		return ret;
+	}
+
+	if (status & IPC_STATUS_ERR) {
+		int i;
+
+		ret = -EIO;
+		i = (status >> IPC_CMD_SIZE) & 0xFF;
+		if (i < ARRAY_SIZE(ipc_err_sources))
+			dev_err(ipcdev.dev,
+				"IPC failed: %s, STS=0x%x, CMD=0x%x\n",
+				ipc_err_sources[i], status, ipcdev.cmd);
+		else
+			dev_err(ipcdev.dev,
+				"IPC failed: unknown, STS=0x%x, CMD=0x%x\n",
+				status, ipcdev.cmd);
+		if ((i == IPC_ERR_UNSIGNEDKERNEL) || (i == IPC_ERR_EMSECURITY))
+			ret = -EACCES;
+	}
+
+	return ret;
+}
+
+/*
+ * intel_pmc_ipc_simple_command
+ * @cmd: command
+ * @sub: sub type
+ */
+int intel_pmc_ipc_simple_command(int cmd, int sub)
+{
+	int ret;
+
+	mutex_lock(&ipclock);
+	if (ipcdev.dev == NULL) {
+		mutex_unlock(&ipclock);
+		return -ENODEV;
+	}
+	ipc_send_command(sub << IPC_CMD_SUBCMD | cmd);
+	ret = intel_pmc_ipc_check_status();
+	mutex_unlock(&ipclock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(intel_pmc_ipc_simple_command);
+
+/*
+ * intel_pmc_ipc_raw_cmd
+ * @cmd: command
+ * @sub: sub type
+ * @in: input data
+ * @inlen: input length in bytes
+ * @out: output data
+ * @outlen: output length in dwords
+ * @sptr: data writing to SPTR register
+ * @dptr: data writing to DPTR register
+ */
+int intel_pmc_ipc_raw_cmd(u32 cmd, u32 sub, u8 *in, u32 inlen, u32 *out,
+			  u32 outlen, u32 dptr, u32 sptr)
+{
+	u32 wbuf[4] = { 0 };
+	int ret;
+	int i;
+
+	if (inlen > IPC_DATA_BUFFER_SIZE || outlen > IPC_DATA_BUFFER_SIZE / 4)
+		return -EINVAL;
+
+	mutex_lock(&ipclock);
+	if (ipcdev.dev == NULL) {
+		mutex_unlock(&ipclock);
+		return -ENODEV;
+	}
+	memcpy(wbuf, in, inlen);
+	writel(dptr, ipcdev.ipc_base + IPC_DPTR);
+	writel(sptr, ipcdev.ipc_base + IPC_SPTR);
+	/* The input data register is 32bit register and inlen is in Byte */
+	for (i = 0; i < ((inlen + 3) / 4); i++)
+		ipc_data_writel(wbuf[i], 4 * i);
+	ipc_send_command((inlen << IPC_CMD_SIZE) |
+			(sub << IPC_CMD_SUBCMD) | cmd);
+	ret = intel_pmc_ipc_check_status();
+	if (!ret) {
+		/* out is read from 32bit register and outlen is in 32bit */
+		for (i = 0; i < outlen; i++)
+			*out++ = ipc_data_readl(4 * i);
+	}
+	mutex_unlock(&ipclock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(intel_pmc_ipc_raw_cmd);
+
+/*
+ * intel_pmc_ipc_command
+ * @cmd: command
+ * @sub: sub type
+ * @in: input data
+ * @inlen: input length in bytes
+ * @out: output data
+ * @outlen: output length in dwords
+ */
+int intel_pmc_ipc_command(u32 cmd, u32 sub, u8 *in, u32 inlen,
+			  u32 *out, u32 outlen)
+{
+	return intel_pmc_ipc_raw_cmd(cmd, sub, in, inlen, out, outlen, 0, 0);
+}
+EXPORT_SYMBOL_GPL(intel_pmc_ipc_command);
+
+static irqreturn_t ioc(int irq, void *dev_id)
+{
+	int status;
+
+	if (ipcdev.irq_mode) {
+		status = ipc_read_status();
+		writel(status | IPC_STATUS_IRQ, ipcdev.ipc_base + IPC_STATUS);
+	}
+	complete(&ipcdev.cmd_complete);
+
+	return IRQ_HANDLED;
+}
+
+static int ipc_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	resource_size_t pci_resource;
+	int ret;
+	int len;
+
+	ipcdev.dev = &pci_dev_get(pdev)->dev;
+	ipcdev.irq_mode = IPC_TRIGGER_MODE_IRQ;
+
+	ret = pci_enable_device(pdev);
+	if (ret)
+		return ret;
+
+	ret = pci_request_regions(pdev, "intel_pmc_ipc");
+	if (ret)
+		return ret;
+
+	pci_resource = pci_resource_start(pdev, 0);
+	len = pci_resource_len(pdev, 0);
+	if (!pci_resource || !len) {
+		dev_err(&pdev->dev, "Failed to get resource\n");
+		return -ENOMEM;
+	}
+
+	init_completion(&ipcdev.cmd_complete);
+
+	if (request_irq(pdev->irq, ioc, 0, "intel_pmc_ipc", &ipcdev)) {
+		dev_err(&pdev->dev, "Failed to request irq\n");
+		return -EBUSY;
+	}
+
+	ipcdev.ipc_base = ioremap_nocache(pci_resource, len);
+	if (!ipcdev.ipc_base) {
+		dev_err(&pdev->dev, "Failed to ioremap ipc base\n");
+		free_irq(pdev->irq, &ipcdev);
+		ret = -ENOMEM;
+	}
+
+	return ret;
+}
+
+static void ipc_pci_remove(struct pci_dev *pdev)
+{
+	free_irq(pdev->irq, &ipcdev);
+	pci_release_regions(pdev);
+	pci_dev_put(pdev);
+	iounmap(ipcdev.ipc_base);
+	ipcdev.dev = NULL;
+}
+
+static const struct pci_device_id ipc_pci_ids[] = {
+	{PCI_VDEVICE(INTEL, 0x0a94), 0},
+	{PCI_VDEVICE(INTEL, 0x1a94), 0},
+	{ 0,}
+};
+MODULE_DEVICE_TABLE(pci, ipc_pci_ids);
+
+static struct pci_driver ipc_pci_driver = {
+	.name = "intel_pmc_ipc",
+	.id_table = ipc_pci_ids,
+	.probe = ipc_pci_probe,
+	.remove = ipc_pci_remove,
+};
+
+static ssize_t intel_pmc_ipc_simple_cmd_store(struct device *dev,
+					      struct device_attribute *attr,
+					      const char *buf, size_t count)
+{
+	int subcmd;
+	int cmd;
+	int ret;
+
+	ret = sscanf(buf, "%d %d", &cmd, &subcmd);
+	if (ret != 2) {
+		dev_err(dev, "Error args\n");
+		return -EINVAL;
+	}
+
+	ret = intel_pmc_ipc_simple_command(cmd, subcmd);
+	if (ret) {
+		dev_err(dev, "command %d error with %d\n", cmd, ret);
+		return ret;
+	}
+	return (ssize_t)count;
+}
+
+static ssize_t intel_pmc_ipc_northpeak_store(struct device *dev,
+					     struct device_attribute *attr,
+					     const char *buf, size_t count)
+{
+	unsigned long val;
+	int subcmd;
+	int ret;
+
+	if (kstrtoul(buf, 0, &val))
+		return -EINVAL;
+
+	if (val)
+		subcmd = 1;
+	else
+		subcmd = 0;
+	ret = intel_pmc_ipc_simple_command(PMC_IPC_NORTHPEAK_CTRL, subcmd);
+	if (ret) {
+		dev_err(dev, "command north %d error with %d\n", subcmd, ret);
+		return ret;
+	}
+	return (ssize_t)count;
+}
+
+static DEVICE_ATTR(simplecmd, S_IWUSR,
+		   NULL, intel_pmc_ipc_simple_cmd_store);
+static DEVICE_ATTR(northpeak, S_IWUSR,
+		   NULL, intel_pmc_ipc_northpeak_store);
+
+static struct attribute *intel_ipc_attrs[] = {
+	&dev_attr_northpeak.attr,
+	&dev_attr_simplecmd.attr,
+	NULL
+};
+
+static const struct attribute_group intel_ipc_group = {
+	.attrs = intel_ipc_attrs,
+};
+
+#define PUNIT_RESOURCE_INTER		1
+static struct resource punit_res[] = {
+	/* Punit */
+	{
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.flags = IORESOURCE_MEM,
+	},
+};
+
+#define TCO_RESOURCE_ACPI_IO		0
+#define TCO_RESOURCE_SMI_EN_IO		1
+#define TCO_RESOURCE_GCR_MEM		2
+static struct resource tco_res[] = {
+	/* ACPI - TCO */
+	{
+		.flags = IORESOURCE_IO,
+	},
+	/* ACPI - SMI */
+	{
+		.flags = IORESOURCE_IO,
+	},
+	/* GCS */
+	{
+		.flags = IORESOURCE_MEM,
+	},
+};
+
+static struct lpc_ich_info tco_info = {
+	.name = "Apollo Lake SoC",
+	.iTCO_version = 3,
+};
+
+static int ipc_create_punit_device(void)
+{
+	struct platform_device *pdev;
+	struct resource *res;
+	int ret;
+
+	pdev = platform_device_alloc(PUNIT_DEVICE_NAME, -1);
+	if (!pdev) {
+		dev_err(ipcdev.dev, "Failed to alloc punit platform device\n");
+		return -ENOMEM;
+	}
+
+	pdev->dev.parent = ipcdev.dev;
+
+	res = punit_res;
+	res->start = (resource_size_t)ipcdev.punit_base;
+	res->end = res->start + ipcdev.punit_size - 1;
+
+	res = punit_res + PUNIT_RESOURCE_INTER;
+	res->start = (resource_size_t)ipcdev.punit_base2;
+	res->end = res->start + ipcdev.punit_size2 - 1;
+
+	ret = platform_device_add_resources(pdev, punit_res,
+					    ARRAY_SIZE(punit_res));
+	if (ret) {
+		dev_err(ipcdev.dev, "Failed to add platform punit resources\n");
+		goto err;
+	}
+
+	ret = platform_device_add(pdev);
+	if (ret) {
+		dev_err(ipcdev.dev, "Failed to add punit platform device\n");
+		goto err;
+	}
+	ipcdev.punit_dev = pdev;
+
+	return 0;
+err:
+	platform_device_put(pdev);
+	return ret;
+}
+
+static int ipc_create_tco_device(void)
+{
+	struct platform_device *pdev;
+	struct resource *res;
+	int ret;
+
+	pdev = platform_device_alloc(TCO_DEVICE_NAME, -1);
+	if (!pdev) {
+		dev_err(ipcdev.dev, "Failed to alloc tco platform device\n");
+		return -ENOMEM;
+	}
+
+	pdev->dev.parent = ipcdev.dev;
+
+	res = tco_res + TCO_RESOURCE_ACPI_IO;
+	res->start = (resource_size_t)ipcdev.acpi_io_base + TCO_BASE_OFFSET;
+	res->end = res->start + TCO_REGS_SIZE - 1;
+
+	res = tco_res + TCO_RESOURCE_SMI_EN_IO;
+	res->start = (resource_size_t)ipcdev.acpi_io_base + SMI_EN_OFFSET;
+	res->end = res->start + SMI_EN_SIZE - 1;
+
+	res = tco_res + TCO_RESOURCE_GCR_MEM;
+	res->start = (resource_size_t)ipcdev.gcr_base;
+	res->end = res->start + ipcdev.gcr_size - 1;
+
+	ret = platform_device_add_resources(pdev, tco_res, ARRAY_SIZE(tco_res));
+	if (ret) {
+		dev_err(ipcdev.dev, "Failed to add tco platform resources\n");
+		goto err;
+	}
+
+	ret = platform_device_add_data(pdev, &tco_info,
+				       sizeof(struct lpc_ich_info));
+	if (ret) {
+		dev_err(ipcdev.dev, "Failed to add tco platform data\n");
+		goto err;
+	}
+
+	ret = platform_device_add(pdev);
+	if (ret) {
+		dev_err(ipcdev.dev, "Failed to add tco platform device\n");
+		goto err;
+	}
+	ipcdev.tco_dev = pdev;
+
+	return 0;
+err:
+	platform_device_put(pdev);
+	return ret;
+}
+
+static int ipc_create_pmc_devices(void)
+{
+	int ret;
+
+	ret = ipc_create_tco_device();
+	if (ret) {
+		dev_err(ipcdev.dev, "Failed to add tco platform device\n");
+		return ret;
+	}
+	ret = ipc_create_punit_device();
+	if (ret) {
+		dev_err(ipcdev.dev, "Failed to add punit platform device\n");
+		platform_device_unregister(ipcdev.tco_dev);
+	}
+	return ret;
+}
+
+static int ipc_plat_get_res(struct platform_device *pdev)
+{
+	struct resource *res;
+	void __iomem *addr;
+	int size;
+
+	res = platform_get_resource(pdev, IORESOURCE_IO,
+				    PLAT_RESOURCE_ACPI_IO_INDEX);
+	if (!res) {
+		dev_err(&pdev->dev, "Failed to get io resource\n");
+		return -ENXIO;
+	}
+	size = resource_size(res);
+	ipcdev.acpi_io_base = (void *)res->start;
+	ipcdev.acpi_io_size = size;
+	dev_info(&pdev->dev, "io res: %llx %x\n",
+		 (long long)res->start, (int)resource_size(res));
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM,
+				    PLAT_RESOURCE_PUNIT_DATA_INDEX);
+	if (!res) {
+		dev_err(&pdev->dev, "Failed to get punit resource\n");
+		return -ENXIO;
+	}
+	size = resource_size(res);
+	ipcdev.punit_base = (void *)res->start;
+	ipcdev.punit_size = size;
+	dev_info(&pdev->dev, "punit data res: %llx %x\n",
+		 (long long)res->start, (int)resource_size(res));
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM,
+				    PLAT_RESOURCE_PUNIT_INTER_INDEX);
+	if (!res) {
+		dev_err(&pdev->dev, "Failed to get punit inter resource\n");
+		return -ENXIO;
+	}
+	size = resource_size(res);
+	ipcdev.punit_base2 = (void *)res->start;
+	ipcdev.punit_size2 = size;
+	dev_info(&pdev->dev, "punit interface res: %llx %x\n",
+		 (long long)res->start, (int)resource_size(res));
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM,
+				    PLAT_RESOURCE_IPC_INDEX);
+	if (!res) {
+		dev_err(&pdev->dev, "Failed to get ipc resource\n");
+		return -ENXIO;
+	}
+	size = PLAT_RESOURCE_IPC_SIZE;
+	if (!request_mem_region(res->start, size, pdev->name)) {
+		dev_err(&pdev->dev, "Failed to request ipc resource\n");
+		return -EBUSY;
+	}
+	addr = ioremap_nocache(res->start, size);
+	if (!addr) {
+		dev_err(&pdev->dev, "I/O memory remapping failed\n");
+		release_mem_region(res->start, size);
+		return -ENOMEM;
+	}
+	ipcdev.ipc_base = addr;
+
+	ipcdev.gcr_base = (void *)(res->start + size);
+	ipcdev.gcr_size = PLAT_RESOURCE_GCR_SIZE;
+	dev_info(&pdev->dev, "ipc res: %llx %x\n",
+		 (long long)res->start, (int)resource_size(res));
+
+	return 0;
+}
+
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id ipc_acpi_ids[] = {
+	{ "INT34D2", 0},
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, ipc_acpi_ids);
+#endif
+
+static int ipc_plat_probe(struct platform_device *pdev)
+{
+	struct resource *res;
+	int ret;
+
+	ipcdev.dev = &pdev->dev;
+	ipcdev.irq_mode = IPC_TRIGGER_MODE_IRQ;
+	init_completion(&ipcdev.cmd_complete);
+
+	ipcdev.irq = platform_get_irq(pdev, 0);
+	if (ipcdev.irq < 0) {
+		dev_err(&pdev->dev, "Failed to get irq\n");
+		return -EINVAL;
+	}
+
+	ret = ipc_plat_get_res(pdev);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to request resource\n");
+		return ret;
+	}
+
+	ret = ipc_create_pmc_devices();
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to create pmc devices\n");
+		goto err_device;
+	}
+
+	if (request_irq(ipcdev.irq, ioc, 0, "intel_pmc_ipc", &ipcdev)) {
+		dev_err(&pdev->dev, "Failed to request irq\n");
+		ret = -EBUSY;
+		goto err_irq;
+	}
+
+	ret = sysfs_create_group(&pdev->dev.kobj, &intel_ipc_group);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to create sysfs group %d\n",
+			ret);
+		goto err_sys;
+	}
+
+	return 0;
+err_sys:
+	free_irq(ipcdev.irq, &ipcdev);
+err_irq:
+	platform_device_unregister(ipcdev.tco_dev);
+	platform_device_unregister(ipcdev.punit_dev);
+err_device:
+	iounmap(ipcdev.ipc_base);
+	res = platform_get_resource(pdev, IORESOURCE_MEM,
+				    PLAT_RESOURCE_IPC_INDEX);
+	if (res)
+		release_mem_region(res->start, PLAT_RESOURCE_IPC_SIZE);
+	return ret;
+}
+
+static int ipc_plat_remove(struct platform_device *pdev)
+{
+	struct resource *res;
+
+	sysfs_remove_group(&pdev->dev.kobj, &intel_ipc_group);
+	free_irq(ipcdev.irq, &ipcdev);
+	platform_device_unregister(ipcdev.tco_dev);
+	platform_device_unregister(ipcdev.punit_dev);
+	iounmap(ipcdev.ipc_base);
+	res = platform_get_resource(pdev, IORESOURCE_MEM,
+				    PLAT_RESOURCE_IPC_INDEX);
+	if (res)
+		release_mem_region(res->start, PLAT_RESOURCE_IPC_SIZE);
+	ipcdev.dev = NULL;
+	return 0;
+}
+
+static struct platform_driver ipc_plat_driver = {
+	.remove = ipc_plat_remove,
+	.probe = ipc_plat_probe,
+	.driver = {
+		.name = "pmc-ipc-plat",
+		.acpi_match_table = ACPI_PTR(ipc_acpi_ids),
+	},
+};
+
+static int __init intel_pmc_ipc_init(void)
+{
+	int ret;
+
+	ret = platform_driver_register(&ipc_plat_driver);
+	if (ret) {
+		pr_err("Failed to register PMC ipc platform driver\n");
+		return ret;
+	}
+	ret = pci_register_driver(&ipc_pci_driver);
+	if (ret) {
+		pr_err("Failed to register PMC ipc pci driver\n");
+		platform_driver_unregister(&ipc_plat_driver);
+		return ret;
+	}
+	return ret;
+}
+
+static void __exit intel_pmc_ipc_exit(void)
+{
+	pci_unregister_driver(&ipc_pci_driver);
+	platform_driver_unregister(&ipc_plat_driver);
+}
+
+MODULE_AUTHOR("Zha Qipeng <qipeng.zha@intel.com>");
+MODULE_DESCRIPTION("Intel PMC IPC driver");
+MODULE_LICENSE("GPL");
+
+/* Some modules are dependent on this, so init earlier */
+fs_initcall(intel_pmc_ipc_init);
+module_exit(intel_pmc_ipc_exit);
diff --git a/drivers/platform/x86/pvpanic.c b/drivers/platform/x86/pvpanic.c
index 073a90a..fd86dab 100644
--- a/drivers/platform/x86/pvpanic.c
+++ b/drivers/platform/x86/pvpanic.c
@@ -92,13 +92,13 @@
 
 static int pvpanic_add(struct acpi_device *device)
 {
-	acpi_status status;
-	u64 ret;
+	int ret;
 
-	status = acpi_evaluate_integer(device->handle, "_STA", NULL,
-				       &ret);
+	ret = acpi_bus_get_status(device);
+	if (ret < 0)
+		return ret;
 
-	if (ACPI_FAILURE(status) || (ret & 0x0B) != 0x0B)
+	if (!device->status.enabled || !device->status.functional)
 		return -ENODEV;
 
 	acpi_walk_resources(device->handle, METHOD_NAME__CRS,
diff --git a/drivers/platform/x86/tc1100-wmi.c b/drivers/platform/x86/tc1100-wmi.c
index e365425..89aa976 100644
--- a/drivers/platform/x86/tc1100-wmi.c
+++ b/drivers/platform/x86/tc1100-wmi.c
@@ -82,7 +82,7 @@
 		tmp = 0;
 	}
 
-	if (result.length > 0 && result.pointer)
+	if (result.length > 0)
 		kfree(result.pointer);
 
 	switch (instance) {
diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c
index 59bf27e..3ad7b1f 100644
--- a/drivers/platform/x86/toshiba_acpi.c
+++ b/drivers/platform/x86/toshiba_acpi.c
@@ -31,7 +31,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#define TOSHIBA_ACPI_VERSION	"0.21"
+#define TOSHIBA_ACPI_VERSION	"0.22"
 #define PROC_INTERFACE_VERSION	1
 
 #include <linux/kernel.h>
@@ -41,7 +41,6 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/backlight.h>
-#include <linux/rfkill.h>
 #include <linux/input.h>
 #include <linux/input/sparse-keymap.h>
 #include <linux/leds.h>
@@ -82,7 +81,7 @@
 
 #define TCI_WORDS			6
 
-/* operations */
+/* Operations */
 #define HCI_SET				0xff00
 #define HCI_GET				0xfe00
 #define SCI_OPEN			0xf100
@@ -90,7 +89,7 @@
 #define SCI_GET				0xf300
 #define SCI_SET				0xf400
 
-/* return codes */
+/* Return codes */
 #define TOS_SUCCESS			0x0000
 #define TOS_OPEN_CLOSE_OK		0x0044
 #define TOS_FAILURE			0x1000
@@ -105,7 +104,7 @@
 #define TOS_NOT_INITIALIZED		0x8d50
 #define TOS_NOT_INSTALLED		0x8e00
 
-/* registers */
+/* Registers */
 #define HCI_FAN				0x0004
 #define HCI_TR_BACKLIGHT		0x0005
 #define HCI_SYSTEM_EVENT		0x0016
@@ -127,7 +126,7 @@
 #define SCI_TOUCHPAD			0x050e
 #define SCI_KBD_FUNCTION_KEYS		0x0522
 
-/* field definitions */
+/* Field definitions */
 #define HCI_ACCEL_MASK			0x7fff
 #define HCI_HOTKEY_DISABLE		0x0b
 #define HCI_HOTKEY_ENABLE		0x09
@@ -165,7 +164,6 @@
 struct toshiba_acpi_dev {
 	struct acpi_device *acpi_dev;
 	const char *method_hci;
-	struct rfkill *bt_rfk;
 	struct input_dev *hotkey_dev;
 	struct work_struct hotkey_work;
 	struct backlight_device *backlight_dev;
@@ -202,8 +200,6 @@
 	unsigned int panel_power_on_supported:1;
 	unsigned int usb_three_supported:1;
 	unsigned int sysfs_created:1;
-
-	struct mutex mutex;
 };
 
 static struct toshiba_acpi_dev *toshiba_acpi;
@@ -330,13 +326,13 @@
 }
 
 /*
- * Common hci tasks (get or set one or two value)
+ * Common hci tasks
  *
  * In addition to the ACPI status, the HCI system returns a result which
  * may be useful (such as "not supported").
  */
 
-static u32 hci_write1(struct toshiba_acpi_dev *dev, u32 reg, u32 in1)
+static u32 hci_write(struct toshiba_acpi_dev *dev, u32 reg, u32 in1)
 {
 	u32 in[TCI_WORDS] = { HCI_SET, reg, in1, 0, 0, 0 };
 	u32 out[TCI_WORDS];
@@ -345,7 +341,7 @@
 	return ACPI_SUCCESS(status) ? out[0] : TOS_FAILURE;
 }
 
-static u32 hci_read1(struct toshiba_acpi_dev *dev, u32 reg, u32 *out1)
+static u32 hci_read(struct toshiba_acpi_dev *dev, u32 reg, u32 *out1)
 {
 	u32 in[TCI_WORDS] = { HCI_GET, reg, 0, 0, 0, 0 };
 	u32 out[TCI_WORDS];
@@ -359,31 +355,6 @@
 	return out[0];
 }
 
-static u32 hci_write2(struct toshiba_acpi_dev *dev, u32 reg, u32 in1, u32 in2)
-{
-	u32 in[TCI_WORDS] = { HCI_SET, reg, in1, in2, 0, 0 };
-	u32 out[TCI_WORDS];
-	acpi_status status = tci_raw(dev, in, out);
-
-	return ACPI_SUCCESS(status) ? out[0] : TOS_FAILURE;
-}
-
-static u32 hci_read2(struct toshiba_acpi_dev *dev,
-		     u32 reg, u32 *out1, u32 *out2)
-{
-	u32 in[TCI_WORDS] = { HCI_GET, reg, *out1, *out2, 0, 0 };
-	u32 out[TCI_WORDS];
-	acpi_status status = tci_raw(dev, in, out);
-
-	if (ACPI_FAILURE(status))
-		return TOS_FAILURE;
-
-	*out1 = out[2];
-	*out2 = out[3];
-
-	return out[0];
-}
-
 /*
  * Common sci tasks
  */
@@ -395,7 +366,7 @@
 	acpi_status status;
 
 	status = tci_raw(dev, in, out);
-	if  (ACPI_FAILURE(status) || out[0] == TOS_FAILURE) {
+	if  (ACPI_FAILURE(status)) {
 		pr_err("ACPI call to open SCI failed\n");
 		return 0;
 	}
@@ -433,7 +404,7 @@
 	acpi_status status;
 
 	status = tci_raw(dev, in, out);
-	if (ACPI_FAILURE(status) || out[0] == TOS_FAILURE) {
+	if (ACPI_FAILURE(status)) {
 		pr_err("ACPI call to close SCI failed\n");
 		return;
 	}
@@ -481,7 +452,7 @@
 
 	status = tci_raw(dev, in, out);
 	sci_close(dev);
-	if (ACPI_FAILURE(status) || out[0] == TOS_FAILURE) {
+	if (ACPI_FAILURE(status)) {
 		pr_err("ACPI call to query Illumination support failed\n");
 		return 0;
 	} else if (out[0] == TOS_NOT_SUPPORTED) {
@@ -522,7 +493,7 @@
 			struct toshiba_acpi_dev, led_dev);
 	u32 state, result;
 
-	/* First request : initialize communication. */
+	/* First request : initialize communication. */
 	if (!sci_open(dev))
 		return LED_OFF;
 
@@ -625,7 +596,7 @@
 	u32 state, result;
 
 	/* Check the keyboard backlight state */
-	result = hci_read1(dev, HCI_KBD_ILLUMINATION, &state);
+	result = hci_read(dev, HCI_KBD_ILLUMINATION, &state);
 	if (result == TOS_FAILURE || result == TOS_INPUT_DATA_ERROR) {
 		pr_err("ACPI call to get the keyboard backlight failed\n");
 		return LED_OFF;
@@ -646,7 +617,7 @@
 
 	/* Set the keyboard backlight state */
 	state = brightness ? 1 : 0;
-	result = hci_write1(dev, HCI_KBD_ILLUMINATION, state);
+	result = hci_write(dev, HCI_KBD_ILLUMINATION, state);
 	if (result == TOS_FAILURE || result == TOS_INPUT_DATA_ERROR) {
 		pr_err("ACPI call to set KBD Illumination mode failed\n");
 		return;
@@ -703,7 +674,7 @@
 	u32 out[TCI_WORDS];
 
 	status = tci_raw(dev, in, out);
-	if (ACPI_FAILURE(status) || out[0] == TOS_FAILURE) {
+	if (ACPI_FAILURE(status)) {
 		pr_err("ACPI call to get ECO led failed\n");
 	} else if (out[0] == TOS_NOT_INSTALLED) {
 		pr_info("ECO led not installed");
@@ -825,7 +796,7 @@
 		return;
 
 	status = tci_raw(dev, in, out);
-	if (ACPI_FAILURE(status) || out[0] == TOS_FAILURE) {
+	if (ACPI_FAILURE(status)) {
 		pr_err("ACPI call to get USB Sleep and Charge mode failed\n");
 		sci_close(dev);
 		return;
@@ -839,7 +810,7 @@
 
 	in[5] = SCI_USB_CHARGE_BAT_LVL;
 	status = tci_raw(dev, in, out);
-	if (ACPI_FAILURE(status) || out[0] == TOS_FAILURE) {
+	if (ACPI_FAILURE(status)) {
 		pr_err("ACPI call to get USB Sleep and Charge mode failed\n");
 		sci_close(dev);
 		return;
@@ -919,7 +890,7 @@
 	in[5] = SCI_USB_CHARGE_BAT_LVL;
 	status = tci_raw(dev, in, out);
 	sci_close(dev);
-	if (ACPI_FAILURE(status) || out[0] == TOS_FAILURE) {
+	if (ACPI_FAILURE(status)) {
 		pr_err("ACPI call to get USB S&C battery level failed\n");
 		return -EIO;
 	} else if (out[0] == TOS_NOT_SUPPORTED) {
@@ -948,7 +919,7 @@
 	in[5] = SCI_USB_CHARGE_BAT_LVL;
 	status = tci_raw(dev, in, out);
 	sci_close(dev);
-	if (ACPI_FAILURE(status) || out[0] == TOS_FAILURE) {
+	if (ACPI_FAILURE(status)) {
 		pr_err("ACPI call to set USB S&C battery level failed\n");
 		return -EIO;
 	} else if (out[0] == TOS_NOT_SUPPORTED) {
@@ -974,7 +945,7 @@
 	in[5] = SCI_USB_CHARGE_RAPID_DSP;
 	status = tci_raw(dev, in, out);
 	sci_close(dev);
-	if (ACPI_FAILURE(status) || out[0] == TOS_FAILURE) {
+	if (ACPI_FAILURE(status)) {
 		pr_err("ACPI call to get USB Rapid Charge failed\n");
 		return -EIO;
 	} else if (out[0] == TOS_NOT_SUPPORTED ||
@@ -1002,7 +973,7 @@
 	in[5] = SCI_USB_CHARGE_RAPID_DSP;
 	status = tci_raw(dev, in, out);
 	sci_close(dev);
-	if (ACPI_FAILURE(status) || out[0] == TOS_FAILURE) {
+	if (ACPI_FAILURE(status)) {
 		pr_err("ACPI call to set USB Rapid Charge failed\n");
 		return -EIO;
 	} else if (out[0] == TOS_NOT_SUPPORTED) {
@@ -1194,121 +1165,31 @@
 static int toshiba_hotkey_event_type_get(struct toshiba_acpi_dev *dev,
 					 u32 *type)
 {
-	u32 val1 = 0x03;
-	u32 val2 = 0;
-	u32 result;
+	u32 in[TCI_WORDS] = { HCI_GET, HCI_SYSTEM_INFO, 0x03, 0, 0, 0 };
+	u32 out[TCI_WORDS];
+	acpi_status status;
 
-	result = hci_read2(dev, HCI_SYSTEM_INFO, &val1, &val2);
-	if (result == TOS_FAILURE) {
+	status = tci_raw(dev, in, out);
+	if (ACPI_FAILURE(status)) {
 		pr_err("ACPI call to get System type failed\n");
 		return -EIO;
-	} else if (result == TOS_NOT_SUPPORTED) {
+	} else if (out[0] == TOS_NOT_SUPPORTED) {
 		pr_info("System type not supported\n");
 		return -ENODEV;
 	}
 
-	*type = val2;
+	*type = out[3];
 
 	return 0;
 }
 
-/* Bluetooth rfkill handlers */
-
-static u32 hci_get_bt_present(struct toshiba_acpi_dev *dev, bool *present)
-{
-	u32 hci_result;
-	u32 value, value2;
-
-	value = 0;
-	value2 = 0;
-	hci_result = hci_read2(dev, HCI_WIRELESS, &value, &value2);
-	if (hci_result == TOS_SUCCESS)
-		*present = (value & HCI_WIRELESS_BT_PRESENT) ? true : false;
-
-	return hci_result;
-}
-
-static u32 hci_get_radio_state(struct toshiba_acpi_dev *dev, bool *radio_state)
-{
-	u32 hci_result;
-	u32 value, value2;
-
-	value = 0;
-	value2 = 0x0001;
-	hci_result = hci_read2(dev, HCI_WIRELESS, &value, &value2);
-
-	*radio_state = value & HCI_WIRELESS_KILL_SWITCH;
-	return hci_result;
-}
-
-static int bt_rfkill_set_block(void *data, bool blocked)
-{
-	struct toshiba_acpi_dev *dev = data;
-	u32 result1, result2;
-	u32 value;
-	int err;
-	bool radio_state;
-
-	value = (blocked == false);
-
-	mutex_lock(&dev->mutex);
-	if (hci_get_radio_state(dev, &radio_state) != TOS_SUCCESS) {
-		err = -EIO;
-		goto out;
-	}
-
-	if (!radio_state) {
-		err = 0;
-		goto out;
-	}
-
-	result1 = hci_write2(dev, HCI_WIRELESS, value, HCI_WIRELESS_BT_POWER);
-	result2 = hci_write2(dev, HCI_WIRELESS, value, HCI_WIRELESS_BT_ATTACH);
-
-	if (result1 != TOS_SUCCESS || result2 != TOS_SUCCESS)
-		err = -EIO;
-	else
-		err = 0;
- out:
-	mutex_unlock(&dev->mutex);
-	return err;
-}
-
-static void bt_rfkill_poll(struct rfkill *rfkill, void *data)
-{
-	bool new_rfk_state;
-	bool value;
-	u32 hci_result;
-	struct toshiba_acpi_dev *dev = data;
-
-	mutex_lock(&dev->mutex);
-
-	hci_result = hci_get_radio_state(dev, &value);
-	if (hci_result != TOS_SUCCESS) {
-		/* Can't do anything useful */
-		mutex_unlock(&dev->mutex);
-		return;
-	}
-
-	new_rfk_state = value;
-
-	mutex_unlock(&dev->mutex);
-
-	if (rfkill_set_hw_state(rfkill, !new_rfk_state))
-		bt_rfkill_set_block(data, true);
-}
-
-static const struct rfkill_ops toshiba_rfk_ops = {
-	.set_block = bt_rfkill_set_block,
-	.poll = bt_rfkill_poll,
-};
-
+/* Transflective Backlight */
 static int get_tr_backlight_status(struct toshiba_acpi_dev *dev, bool *enabled)
 {
 	u32 hci_result;
 	u32 status;
 
-	hci_result = hci_read1(dev, HCI_TR_BACKLIGHT, &status);
+	hci_result = hci_read(dev, HCI_TR_BACKLIGHT, &status);
 	*enabled = !status;
 	return hci_result == TOS_SUCCESS ? 0 : -EIO;
 }
@@ -1318,12 +1199,13 @@
 	u32 hci_result;
 	u32 value = !enable;
 
-	hci_result = hci_write1(dev, HCI_TR_BACKLIGHT, value);
+	hci_result = hci_write(dev, HCI_TR_BACKLIGHT, value);
 	return hci_result == TOS_SUCCESS ? 0 : -EIO;
 }
 
-static struct proc_dir_entry *toshiba_proc_dir /*= 0*/;
+static struct proc_dir_entry *toshiba_proc_dir;
 
+/* LCD Brightness */
 static int __get_lcd_brightness(struct toshiba_acpi_dev *dev)
 {
 	u32 hci_result;
@@ -1341,7 +1223,7 @@
 		brightness++;
 	}
 
-	hci_result = hci_read1(dev, HCI_LCD_BRIGHTNESS, &value);
+	hci_result = hci_read(dev, HCI_LCD_BRIGHTNESS, &value);
 	if (hci_result == TOS_SUCCESS)
 		return brightness + (value >> HCI_LCD_BRIGHTNESS_SHIFT);
 
@@ -1396,7 +1278,7 @@
 	}
 
 	value = value << HCI_LCD_BRIGHTNESS_SHIFT;
-	hci_result = hci_write1(dev, HCI_LCD_BRIGHTNESS, value);
+	hci_result = hci_write(dev, HCI_LCD_BRIGHTNESS, value);
 	return hci_result == TOS_SUCCESS ? 0 : -EIO;
 }
 
@@ -1446,7 +1328,7 @@
 {
 	u32 hci_result;
 
-	hci_result = hci_read1(dev, HCI_VIDEO_OUT, status);
+	hci_result = hci_read(dev, HCI_VIDEO_OUT, status);
 	return hci_result == TOS_SUCCESS ? 0 : -EIO;
 }
 
@@ -1531,7 +1413,8 @@
 			_set_bit(&new_video_out, HCI_VIDEO_OUT_TV, tv_out);
 		/*
 		 * To avoid unnecessary video disruption, only write the new
-		 * video setting if something changed. */
+		 * video setting if something changed.
+		 */
 		if (new_video_out != video_out)
 			ret = write_acpi_int(METHOD_VIDEO_OUT, new_video_out);
 	}
@@ -1552,7 +1435,7 @@
 {
 	u32 hci_result;
 
-	hci_result = hci_read1(dev, HCI_FAN, status);
+	hci_result = hci_read(dev, HCI_FAN, status);
 	return hci_result == TOS_SUCCESS ? 0 : -EIO;
 }
 
@@ -1592,7 +1475,7 @@
 
 	if (sscanf(cmd, " force_on : %i", &value) == 1 &&
 	    value >= 0 && value <= 1) {
-		hci_result = hci_write1(dev, HCI_FAN, value);
+		hci_result = hci_write(dev, HCI_FAN, value);
 		if (hci_result == TOS_SUCCESS)
 			dev->force_fan = value;
 		else
@@ -1620,7 +1503,7 @@
 	u32 value;
 
 	if (!dev->key_event_valid && dev->system_event_supported) {
-		hci_result = hci_read1(dev, HCI_SYSTEM_EVENT, &value);
+		hci_result = hci_read(dev, HCI_SYSTEM_EVENT, &value);
 		if (hci_result == TOS_SUCCESS) {
 			dev->key_event_valid = 1;
 			dev->last_key_event = value;
@@ -1632,7 +1515,7 @@
 			 * some machines where system events sporadically
 			 * become disabled.
 			 */
-			hci_result = hci_write1(dev, HCI_SYSTEM_EVENT, 1);
+			hci_result = hci_write(dev, HCI_SYSTEM_EVENT, 1);
 			pr_notice("Re-enabled hotkeys\n");
 		} else {
 			pr_err("Error reading hotkey status\n");
@@ -1769,7 +1652,7 @@
 	if (state != 0 && state != 1)
 		return -EINVAL;
 
-	result = hci_write1(toshiba, HCI_FAN, state);
+	result = hci_write(toshiba, HCI_FAN, state);
 	if (result == TOS_FAILURE)
 		return -EIO;
 	else if (result == TOS_NOT_SUPPORTED)
@@ -2391,7 +2274,7 @@
 	if (ACPI_FAILURE(status))
 		return -ENODEV;
 
-	result = hci_write1(dev, HCI_HOTKEY_EVENT, HCI_HOTKEY_ENABLE);
+	result = hci_write(dev, HCI_HOTKEY_EVENT, HCI_HOTKEY_ENABLE);
 	if (result == TOS_FAILURE)
 		return -EIO;
 	else if (result == TOS_NOT_SUPPORTED)
@@ -2408,8 +2291,8 @@
 	 * Re-activate the hotkeys, but this time, we are using the
 	 * "Special Functions" mode.
 	 */
-	result = hci_write1(dev, HCI_HOTKEY_EVENT,
-			    HCI_HOTKEY_SPECIAL_FUNCTIONS);
+	result = hci_write(dev, HCI_HOTKEY_EVENT,
+			   HCI_HOTKEY_SPECIAL_FUNCTIONS);
 	if (result != TOS_SUCCESS)
 		pr_err("Could not enable the Special Function mode\n");
 }
@@ -2490,7 +2373,7 @@
 			toshiba_acpi_report_hotkey(dev, scancode);
 	} else if (dev->system_event_supported) {
 		do {
-			hci_result = hci_read1(dev, HCI_SYSTEM_EVENT, &value);
+			hci_result = hci_read(dev, HCI_SYSTEM_EVENT, &value);
 			switch (hci_result) {
 			case TOS_SUCCESS:
 				toshiba_acpi_report_hotkey(dev, (int)value);
@@ -2502,7 +2385,7 @@
 				 * sporadically become disabled.
 				 */
 				hci_result =
-					hci_write1(dev, HCI_SYSTEM_EVENT, 1);
+					hci_write(dev, HCI_SYSTEM_EVENT, 1);
 				pr_notice("Re-enabled hotkeys\n");
 				/* Fall through */
 			default:
@@ -2579,7 +2462,7 @@
 	if (acpi_has_method(dev->acpi_dev->handle, "INFO"))
 		dev->info_supported = 1;
 	else {
-		hci_result = hci_write1(dev, HCI_SYSTEM_EVENT, 1);
+		hci_result = hci_write(dev, HCI_SYSTEM_EVENT, 1);
 		if (hci_result == TOS_SUCCESS)
 			dev->system_event_supported = 1;
 	}
@@ -2689,11 +2572,6 @@
 		sparse_keymap_free(dev->hotkey_dev);
 	}
 
-	if (dev->bt_rfk) {
-		rfkill_unregister(dev->bt_rfk);
-		rfkill_destroy(dev->bt_rfk);
-	}
-
 	backlight_device_unregister(dev->backlight_dev);
 
 	if (dev->illumination_supported)
@@ -2730,7 +2608,6 @@
 	const char *hci_method;
 	u32 special_functions;
 	u32 dummy;
-	bool bt_present;
 	int ret = 0;
 
 	if (toshiba_acpi)
@@ -2766,33 +2643,10 @@
 	if (toshiba_acpi_setup_keyboard(dev))
 		pr_info("Unable to activate hotkeys\n");
 
-	mutex_init(&dev->mutex);
-
 	ret = toshiba_acpi_setup_backlight(dev);
 	if (ret)
 		goto error;
 
-	/* Register rfkill switch for Bluetooth */
-	if (hci_get_bt_present(dev, &bt_present) == TOS_SUCCESS && bt_present) {
-		dev->bt_rfk = rfkill_alloc("Toshiba Bluetooth",
-					   &acpi_dev->dev,
-					   RFKILL_TYPE_BLUETOOTH,
-					   &toshiba_rfk_ops,
-					   dev);
-		if (!dev->bt_rfk) {
-			pr_err("unable to allocate rfkill device\n");
-			ret = -ENOMEM;
-			goto error;
-		}
-
-		ret = rfkill_register(dev->bt_rfk);
-		if (ret) {
-			pr_err("unable to register rfkill device\n");
-			rfkill_destroy(dev->bt_rfk);
-			goto error;
-		}
-	}
-
 	if (toshiba_illumination_available(dev)) {
 		dev->led_dev.name = "toshiba::illumination";
 		dev->led_dev.max_brightness = 1;
@@ -2930,7 +2784,7 @@
 	u32 result;
 
 	if (dev->hotkey_dev)
-		result = hci_write1(dev, HCI_HOTKEY_EVENT, HCI_HOTKEY_DISABLE);
+		result = hci_write(dev, HCI_HOTKEY_EVENT, HCI_HOTKEY_DISABLE);
 
 	return 0;
 }
diff --git a/drivers/platform/x86/toshiba_bluetooth.c b/drivers/platform/x86/toshiba_bluetooth.c
index 2498007..c5e4508 100644
--- a/drivers/platform/x86/toshiba_bluetooth.c
+++ b/drivers/platform/x86/toshiba_bluetooth.c
@@ -10,12 +10,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * Note the Toshiba Bluetooth RFKill switch seems to be a strange
- * fish. It only provides a BT event when the switch is flipped to
- * the 'on' position. When flipping it to 'off', the USB device is
- * simply pulled away underneath us, without any BT event being
- * delivered.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -25,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/acpi.h>
+#include <linux/rfkill.h>
 
 #define BT_KILLSWITCH_MASK	0x01
 #define BT_PLUGGED_MASK		0x40
@@ -34,6 +29,15 @@
 MODULE_DESCRIPTION("Toshiba Laptop ACPI Bluetooth Enable Driver");
 MODULE_LICENSE("GPL");
 
+struct toshiba_bluetooth_dev {
+	struct acpi_device *acpi_dev;
+	struct rfkill *rfk;
+
+	bool killswitch;
+	bool plugged;
+	bool powered;
+};
+
 static int toshiba_bt_rfkill_add(struct acpi_device *device);
 static int toshiba_bt_rfkill_remove(struct acpi_device *device);
 static void toshiba_bt_rfkill_notify(struct acpi_device *device, u32 event);
@@ -95,41 +99,12 @@
 		return -ENXIO;
 	}
 
-	pr_info("Bluetooth status %llu\n", status);
-
 	return status;
 }
 
 static int toshiba_bluetooth_enable(acpi_handle handle)
 {
 	acpi_status result;
-	bool killswitch;
-	bool powered;
-	bool plugged;
-	int status;
-
-	/*
-	 * Query ACPI to verify RFKill switch is set to 'on'.
-	 * If not, we return silently, no need to report it as
-	 * an error.
-	 */
-	status = toshiba_bluetooth_status(handle);
-	if (status < 0)
-		return status;
-
-	killswitch = (status & BT_KILLSWITCH_MASK) ? true : false;
-	powered = (status & BT_POWER_MASK) ? true : false;
-	plugged = (status & BT_PLUGGED_MASK) ? true : false;
-
-	if (!killswitch)
-		return 0;
-	/*
-	 * This check ensures to only enable the device if it is powered
-	 * off or detached, as some recent devices somehow pass the killswitch
-	 * test, causing a loop enabling/disabling the device, see bug 93911.
-	 */
-	if (powered || plugged)
-		return 0;
 
 	result = acpi_evaluate_object(handle, "AUSB", NULL, NULL);
 	if (ACPI_FAILURE(result)) {
@@ -165,20 +140,102 @@
 	return 0;
 }
 
+/* Helper function */
+static int toshiba_bluetooth_sync_status(struct toshiba_bluetooth_dev *bt_dev)
+{
+	int status;
+
+	status = toshiba_bluetooth_status(bt_dev->acpi_dev->handle);
+	if (status < 0) {
+		pr_err("Could not sync bluetooth device status\n");
+		return status;
+	}
+
+	bt_dev->killswitch = (status & BT_KILLSWITCH_MASK) ? true : false;
+	bt_dev->plugged = (status & BT_PLUGGED_MASK) ? true : false;
+	bt_dev->powered = (status & BT_POWER_MASK) ? true : false;
+
+	pr_debug("Bluetooth status %d killswitch %d plugged %d powered %d\n",
+		 status, bt_dev->killswitch, bt_dev->plugged, bt_dev->powered);
+
+	return 0;
+}
+
+/* RFKill handlers */
+static int bt_rfkill_set_block(void *data, bool blocked)
+{
+	struct toshiba_bluetooth_dev *bt_dev = data;
+	int ret;
+
+	ret = toshiba_bluetooth_sync_status(bt_dev);
+	if (ret)
+		return ret;
+
+	if (!bt_dev->killswitch)
+		return 0;
+
+	if (blocked)
+		ret = toshiba_bluetooth_disable(bt_dev->acpi_dev->handle);
+	else
+		ret = toshiba_bluetooth_enable(bt_dev->acpi_dev->handle);
+
+	return ret;
+}
+
+static void bt_rfkill_poll(struct rfkill *rfkill, void *data)
+{
+	struct toshiba_bluetooth_dev *bt_dev = data;
+
+	if (toshiba_bluetooth_sync_status(bt_dev))
+		return;
+
+	/*
+	 * Note the Toshiba Bluetooth RFKill switch seems to be a strange
+	 * fish. It only provides a BT event when the switch is flipped to
+	 * the 'on' position. When flipping it to 'off', the USB device is
+	 * simply pulled away underneath us, without any BT event being
+	 * delivered.
+	 */
+	rfkill_set_hw_state(bt_dev->rfk, !bt_dev->killswitch);
+}
+
+static const struct rfkill_ops rfk_ops = {
+	.set_block = bt_rfkill_set_block,
+	.poll = bt_rfkill_poll,
+};
+
+/* ACPI driver functions */
 static void toshiba_bt_rfkill_notify(struct acpi_device *device, u32 event)
 {
-	toshiba_bluetooth_enable(device->handle);
+	struct toshiba_bluetooth_dev *bt_dev = acpi_driver_data(device);
+
+	if (toshiba_bluetooth_sync_status(bt_dev))
+		return;
+
+	rfkill_set_hw_state(bt_dev->rfk, !bt_dev->killswitch);
 }
 
 #ifdef CONFIG_PM_SLEEP
 static int toshiba_bt_resume(struct device *dev)
 {
-	return toshiba_bluetooth_enable(to_acpi_device(dev)->handle);
+	struct toshiba_bluetooth_dev *bt_dev;
+	int ret;
+
+	bt_dev = acpi_driver_data(to_acpi_device(dev));
+
+	ret = toshiba_bluetooth_sync_status(bt_dev);
+	if (ret)
+		return ret;
+
+	rfkill_set_hw_state(bt_dev->rfk, !bt_dev->killswitch);
+
+	return 0;
 }
 #endif
 
 static int toshiba_bt_rfkill_add(struct acpi_device *device)
 {
+	struct toshiba_bluetooth_dev *bt_dev;
 	int result;
 
 	result = toshiba_bluetooth_present(device->handle);
@@ -187,17 +244,54 @@
 
 	pr_info("Toshiba ACPI Bluetooth device driver\n");
 
-	/* Enable the BT device */
-	result = toshiba_bluetooth_enable(device->handle);
-	if (result)
+	bt_dev = kzalloc(sizeof(*bt_dev), GFP_KERNEL);
+	if (!bt_dev)
+		return -ENOMEM;
+	bt_dev->acpi_dev = device;
+	device->driver_data = bt_dev;
+	dev_set_drvdata(&device->dev, bt_dev);
+
+	result = toshiba_bluetooth_sync_status(bt_dev);
+	if (result) {
+		kfree(bt_dev);
 		return result;
+	}
+
+	bt_dev->rfk = rfkill_alloc("Toshiba Bluetooth",
+				   &device->dev,
+				   RFKILL_TYPE_BLUETOOTH,
+				   &rfk_ops,
+				   bt_dev);
+	if (!bt_dev->rfk) {
+		pr_err("Unable to allocate rfkill device\n");
+		kfree(bt_dev);
+		return -ENOMEM;
+	}
+
+	rfkill_set_hw_state(bt_dev->rfk, !bt_dev->killswitch);
+
+	result = rfkill_register(bt_dev->rfk);
+	if (result) {
+		pr_err("Unable to register rfkill device\n");
+		rfkill_destroy(bt_dev->rfk);
+		kfree(bt_dev);
+	}
 
 	return result;
 }
 
 static int toshiba_bt_rfkill_remove(struct acpi_device *device)
 {
+	struct toshiba_bluetooth_dev *bt_dev = acpi_driver_data(device);
+
 	/* clean up */
+	if (bt_dev->rfk) {
+		rfkill_unregister(bt_dev->rfk);
+		rfkill_destroy(bt_dev->rfk);
+	}
+
+	kfree(bt_dev);
+
 	return toshiba_bluetooth_disable(device->handle);
 }
 
diff --git a/drivers/platform/x86/toshiba_haps.c b/drivers/platform/x86/toshiba_haps.c
index 65300b6..7f2afc6 100644
--- a/drivers/platform/x86/toshiba_haps.c
+++ b/drivers/platform/x86/toshiba_haps.c
@@ -78,15 +78,20 @@
 				      const char *buf, size_t count)
 {
 	struct toshiba_haps_dev *haps = dev_get_drvdata(dev);
-	int level, ret;
+	int level;
+	int ret;
 
-	if (sscanf(buf, "%d", &level) != 1 || level < 0 || level > 3)
-		return -EINVAL;
-
-	/* Set the sensor level.
-	 * Acceptable levels are:
+	ret = kstrtoint(buf, 0, &level);
+	if (ret)
+		return ret;
+	/*
+	 * Check for supported levels, which can be:
 	 * 0 - Disabled | 1 - Low | 2 - Medium | 3 - High
 	 */
+	if (level < 0 || level > 3)
+		return -EINVAL;
+
+	/* Set the sensor level */
 	ret = toshiba_haps_protection_level(haps->acpi_dev->handle, level);
 	if (ret != 0)
 		return ret;
@@ -95,15 +100,21 @@
 
 	return count;
 }
+static DEVICE_ATTR_RW(protection_level);
 
 static ssize_t reset_protection_store(struct device *dev,
 				      struct device_attribute *attr,
 				      const char *buf, size_t count)
 {
 	struct toshiba_haps_dev *haps = dev_get_drvdata(dev);
-	int reset, ret;
+	int reset;
+	int ret;
 
-	if (sscanf(buf, "%d", &reset) != 1 || reset != 1)
+	ret = kstrtoint(buf, 0, &reset);
+	if (ret)
+		return ret;
+	/* The only accepted value is 1 */
+	if (reset != 1)
 		return -EINVAL;
 
 	/* Reset the protection interface */
@@ -113,10 +124,7 @@
 
 	return count;
 }
-
-static DEVICE_ATTR(protection_level, S_IRUGO | S_IWUSR,
-		   protection_level_show, protection_level_store);
-static DEVICE_ATTR(reset_protection, S_IWUSR, NULL, reset_protection_store);
+static DEVICE_ATTR_WO(reset_protection);
 
 static struct attribute *haps_attributes[] = {
 	&dev_attr_protection_level.attr,
diff --git a/drivers/power/reset/syscon-reboot.c b/drivers/power/reset/syscon-reboot.c
index d3c7d24..7d0d269 100644
--- a/drivers/power/reset/syscon-reboot.c
+++ b/drivers/power/reset/syscon-reboot.c
@@ -88,4 +88,4 @@
 		.of_match_table = syscon_reboot_of_match,
 	},
 };
-module_platform_driver(syscon_reboot_driver);
+builtin_platform_driver(syscon_reboot_driver);
diff --git a/drivers/power/test_power.c b/drivers/power/test_power.c
index f986e0c..83c42ea 100644
--- a/drivers/power/test_power.c
+++ b/drivers/power/test_power.c
@@ -448,42 +448,42 @@
 
 #define param_get_battery_voltage param_get_int
 
-static struct kernel_param_ops param_ops_ac_online = {
+static const struct kernel_param_ops param_ops_ac_online = {
 	.set = param_set_ac_online,
 	.get = param_get_ac_online,
 };
 
-static struct kernel_param_ops param_ops_usb_online = {
+static const struct kernel_param_ops param_ops_usb_online = {
 	.set = param_set_usb_online,
 	.get = param_get_usb_online,
 };
 
-static struct kernel_param_ops param_ops_battery_status = {
+static const struct kernel_param_ops param_ops_battery_status = {
 	.set = param_set_battery_status,
 	.get = param_get_battery_status,
 };
 
-static struct kernel_param_ops param_ops_battery_present = {
+static const struct kernel_param_ops param_ops_battery_present = {
 	.set = param_set_battery_present,
 	.get = param_get_battery_present,
 };
 
-static struct kernel_param_ops param_ops_battery_technology = {
+static const struct kernel_param_ops param_ops_battery_technology = {
 	.set = param_set_battery_technology,
 	.get = param_get_battery_technology,
 };
 
-static struct kernel_param_ops param_ops_battery_health = {
+static const struct kernel_param_ops param_ops_battery_health = {
 	.set = param_set_battery_health,
 	.get = param_get_battery_health,
 };
 
-static struct kernel_param_ops param_ops_battery_capacity = {
+static const struct kernel_param_ops param_ops_battery_capacity = {
 	.set = param_set_battery_capacity,
 	.get = param_get_battery_capacity,
 };
 
-static struct kernel_param_ops param_ops_battery_voltage = {
+static const struct kernel_param_ops param_ops_battery_voltage = {
 	.set = param_set_battery_voltage,
 	.get = param_get_battery_voltage,
 };
diff --git a/drivers/regulator/max77802.c b/drivers/regulator/max77802.c
index 6af41ab..c07ee13 100644
--- a/drivers/regulator/max77802.c
+++ b/drivers/regulator/max77802.c
@@ -27,6 +27,7 @@
 #include <linux/gpio.h>
 #include <linux/slab.h>
 #include <linux/gpio/consumer.h>
+#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/driver.h>
 #include <linux/regulator/machine.h>
diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig
index 5e343ba..28c711f 100644
--- a/drivers/remoteproc/Kconfig
+++ b/drivers/remoteproc/Kconfig
@@ -41,6 +41,19 @@
 	  This can be either built-in or a loadable module.
 	  If unsure say N.
 
+config WKUP_M3_RPROC
+	tristate "AMx3xx Wakeup M3 remoteproc support"
+	depends on SOC_AM33XX || SOC_AM43XX
+	select REMOTEPROC
+	help
+	  Say y here to support Wakeup M3 remote processor on TI AM33xx
+	  and AM43xx family of SoCs.
+
+	  Required for Suspend-to-RAM on AM33xx and AM43xx SoCs. Also needed
+	  for deep CPUIdle states on AM33xx SoCs. Allows for loading of the
+	  firmware onto these remote processors.
+	  If unsure say N.
+
 config DA8XX_REMOTEPROC
 	tristate "DA8xx/OMAP-L13x remoteproc support"
 	depends on ARCH_DAVINCI_DA8XX
diff --git a/drivers/remoteproc/Makefile b/drivers/remoteproc/Makefile
index ac2ff75..81b04d1 100644
--- a/drivers/remoteproc/Makefile
+++ b/drivers/remoteproc/Makefile
@@ -9,4 +9,5 @@
 remoteproc-y				+= remoteproc_elf_loader.o
 obj-$(CONFIG_OMAP_REMOTEPROC)		+= omap_remoteproc.o
 obj-$(CONFIG_STE_MODEM_RPROC)	 	+= ste_modem_rproc.o
+obj-$(CONFIG_WKUP_M3_RPROC)		+= wkup_m3_rproc.o
 obj-$(CONFIG_DA8XX_REMOTEPROC)		+= da8xx_remoteproc.o
diff --git a/drivers/remoteproc/da8xx_remoteproc.c b/drivers/remoteproc/da8xx_remoteproc.c
index f8d6a06..009e56f 100644
--- a/drivers/remoteproc/da8xx_remoteproc.c
+++ b/drivers/remoteproc/da8xx_remoteproc.c
@@ -26,8 +26,7 @@
 static char *da8xx_fw_name;
 module_param(da8xx_fw_name, charp, S_IRUGO);
 MODULE_PARM_DESC(da8xx_fw_name,
-		 "\n\t\tName of DSP firmware file in /lib/firmware"
-		 " (if not specified defaults to 'rproc-dsp-fw')");
+		 "Name of DSP firmware file in /lib/firmware (if not specified defaults to 'rproc-dsp-fw')");
 
 /*
  * OMAP-L138 Technical References:
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 11cdb11..8b3130f 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -44,6 +44,9 @@
 
 #include "remoteproc_internal.h"
 
+static DEFINE_MUTEX(rproc_list_mutex);
+static LIST_HEAD(rproc_list);
+
 typedef int (*rproc_handle_resources_t)(struct rproc *rproc,
 				struct resource_table *table, int len);
 typedef int (*rproc_handle_resource_t)(struct rproc *rproc,
@@ -132,32 +135,48 @@
 
 	iommu_detach_device(domain, dev);
 	iommu_domain_free(domain);
-
-	return;
 }
 
-/*
+/**
+ * rproc_da_to_va() - lookup the kernel virtual address for a remoteproc address
+ * @rproc: handle of a remote processor
+ * @da: remoteproc device address to translate
+ * @len: length of the memory region @da is pointing to
+ *
  * Some remote processors will ask us to allocate them physically contiguous
  * memory regions (which we call "carveouts"), and map them to specific
- * device addresses (which are hardcoded in the firmware).
+ * device addresses (which are hardcoded in the firmware). They may also have
+ * dedicated memory regions internal to the processors, and use them either
+ * exclusively or alongside carveouts.
  *
  * They may then ask us to copy objects into specific device addresses (e.g.
  * code/data sections) or expose us certain symbols in other device address
  * (e.g. their trace buffer).
  *
- * This function is an internal helper with which we can go over the allocated
- * carveouts and translate specific device address to kernel virtual addresses
- * so we can access the referenced memory.
+ * This function is a helper function with which we can go over the allocated
+ * carveouts and translate specific device addresses to kernel virtual addresses
+ * so we can access the referenced memory. This function also allows to perform
+ * translations on the internal remoteproc memory regions through a platform
+ * implementation specific da_to_va ops, if present.
+ *
+ * The function returns a valid kernel address on success or NULL on failure.
  *
  * Note: phys_to_virt(iommu_iova_to_phys(rproc->domain, da)) will work too,
  * but only on kernel direct mapped RAM memory. Instead, we're just using
- * here the output of the DMA API, which should be more correct.
+ * here the output of the DMA API for the carveouts, which should be more
+ * correct.
  */
 void *rproc_da_to_va(struct rproc *rproc, u64 da, int len)
 {
 	struct rproc_mem_entry *carveout;
 	void *ptr = NULL;
 
+	if (rproc->ops->da_to_va) {
+		ptr = rproc->ops->da_to_va(rproc, da, len);
+		if (ptr)
+			goto out;
+	}
+
 	list_for_each_entry(carveout, &rproc->carveouts, node) {
 		int offset = da - carveout->da;
 
@@ -174,6 +193,7 @@
 		break;
 	}
 
+out:
 	return ptr;
 }
 EXPORT_SYMBOL(rproc_da_to_va);
@@ -411,10 +431,8 @@
 	}
 
 	trace = kzalloc(sizeof(*trace), GFP_KERNEL);
-	if (!trace) {
-		dev_err(dev, "kzalloc trace failed\n");
+	if (!trace)
 		return -ENOMEM;
-	}
 
 	/* set the trace buffer dma properties */
 	trace->len = rsc->len;
@@ -489,10 +507,8 @@
 	}
 
 	mapping = kzalloc(sizeof(*mapping), GFP_KERNEL);
-	if (!mapping) {
-		dev_err(dev, "kzalloc mapping failed\n");
+	if (!mapping)
 		return -ENOMEM;
-	}
 
 	ret = iommu_map(rproc->domain, rsc->da, rsc->pa, rsc->len, rsc->flags);
 	if (ret) {
@@ -565,10 +581,8 @@
 			rsc->da, rsc->pa, rsc->len, rsc->flags);
 
 	carveout = kzalloc(sizeof(*carveout), GFP_KERNEL);
-	if (!carveout) {
-		dev_err(dev, "kzalloc carveout failed\n");
+	if (!carveout)
 		return -ENOMEM;
-	}
 
 	va = dma_alloc_coherent(dev->parent, rsc->len, &dma, GFP_KERNEL);
 	if (!va) {
@@ -768,7 +782,8 @@
 
 	/* clean up carveout allocations */
 	list_for_each_entry_safe(entry, tmp, &rproc->carveouts, node) {
-		dma_free_coherent(dev->parent, entry->len, entry->va, entry->dma);
+		dma_free_coherent(dev->parent, entry->len, entry->va,
+				  entry->dma);
 		list_del(&entry->node);
 		kfree(entry);
 	}
@@ -808,9 +823,8 @@
 
 	/* look for the resource table */
 	table = rproc_find_rsc_table(rproc, fw, &tablesz);
-	if (!table) {
+	if (!table)
 		goto clean_up;
-	}
 
 	/* Verify that resource table in loaded fw is unchanged */
 	if (rproc->table_csum != crc32(0, table, tablesz)) {
@@ -911,7 +925,8 @@
 
 	/* count the number of notify-ids */
 	rproc->max_notifyid = -1;
-	ret = rproc_handle_resources(rproc, tablesz, rproc_count_vrings_handler);
+	ret = rproc_handle_resources(rproc, tablesz,
+				     rproc_count_vrings_handler);
 	if (ret)
 		goto out;
 
@@ -1152,6 +1167,50 @@
 EXPORT_SYMBOL(rproc_shutdown);
 
 /**
+ * rproc_get_by_phandle() - find a remote processor by phandle
+ * @phandle: phandle to the rproc
+ *
+ * Finds an rproc handle using the remote processor's phandle, and then
+ * return a handle to the rproc.
+ *
+ * This function increments the remote processor's refcount, so always
+ * use rproc_put() to decrement it back once rproc isn't needed anymore.
+ *
+ * Returns the rproc handle on success, and NULL on failure.
+ */
+#ifdef CONFIG_OF
+struct rproc *rproc_get_by_phandle(phandle phandle)
+{
+	struct rproc *rproc = NULL, *r;
+	struct device_node *np;
+
+	np = of_find_node_by_phandle(phandle);
+	if (!np)
+		return NULL;
+
+	mutex_lock(&rproc_list_mutex);
+	list_for_each_entry(r, &rproc_list, node) {
+		if (r->dev.parent && r->dev.parent->of_node == np) {
+			rproc = r;
+			get_device(&rproc->dev);
+			break;
+		}
+	}
+	mutex_unlock(&rproc_list_mutex);
+
+	of_node_put(np);
+
+	return rproc;
+}
+#else
+struct rproc *rproc_get_by_phandle(phandle phandle)
+{
+	return NULL;
+}
+#endif
+EXPORT_SYMBOL(rproc_get_by_phandle);
+
+/**
  * rproc_add() - register a remote processor
  * @rproc: the remote processor handle to register
  *
@@ -1180,6 +1239,11 @@
 	if (ret < 0)
 		return ret;
 
+	/* expose to rproc_get_by_phandle users */
+	mutex_lock(&rproc_list_mutex);
+	list_add(&rproc->node, &rproc_list);
+	mutex_unlock(&rproc_list_mutex);
+
 	dev_info(dev, "%s is available\n", rproc->name);
 
 	dev_info(dev, "Note: remoteproc is still under development and considered experimental.\n");
@@ -1268,10 +1332,8 @@
 		name_len = strlen(name) + strlen(template) - 2 + 1;
 
 	rproc = kzalloc(sizeof(struct rproc) + len + name_len, GFP_KERNEL);
-	if (!rproc) {
-		dev_err(dev, "%s: kzalloc failed\n", __func__);
+	if (!rproc)
 		return NULL;
-	}
 
 	if (!firmware) {
 		p = (char *)rproc + sizeof(struct rproc) + len;
@@ -1369,6 +1431,11 @@
 	/* Free the copy of the resource table */
 	kfree(rproc->cached_table);
 
+	/* the rproc is downref'ed as soon as it's removed from the klist */
+	mutex_lock(&rproc_list_mutex);
+	list_del(&rproc->node);
+	mutex_unlock(&rproc_list_mutex);
+
 	device_del(&rproc->dev);
 
 	return 0;
diff --git a/drivers/remoteproc/remoteproc_internal.h b/drivers/remoteproc/remoteproc_internal.h
index 70701a5..8041b95 100644
--- a/drivers/remoteproc/remoteproc_internal.h
+++ b/drivers/remoteproc/remoteproc_internal.h
@@ -35,7 +35,7 @@
  * @get_boot_addr:	get boot address to entry point specified in firmware
  */
 struct rproc_fw_ops {
-	struct resource_table *(*find_rsc_table) (struct rproc *rproc,
+	struct resource_table *(*find_rsc_table)(struct rproc *rproc,
 						const struct firmware *fw,
 						int *tablesz);
 	struct resource_table *(*find_loaded_rsc_table)(struct rproc *rproc,
diff --git a/drivers/remoteproc/ste_modem_rproc.c b/drivers/remoteproc/ste_modem_rproc.c
index dd193f3..53dc17b 100644
--- a/drivers/remoteproc/ste_modem_rproc.c
+++ b/drivers/remoteproc/ste_modem_rproc.c
@@ -67,8 +67,7 @@
 static const struct ste_toc_entry *sproc_find_rsc_entry(const void *data)
 {
 	int i;
-	const struct ste_toc *toc;
-	toc = data;
+	const struct ste_toc *toc = data;
 
 	/* Search the table for the resource table */
 	for (i = 0; i < SPROC_MAX_TOC_ENTRIES &&
@@ -230,6 +229,7 @@
 static int sproc_stop(struct rproc *rproc)
 {
 	struct sproc *sproc = rproc->priv;
+
 	sproc_dbg(sproc, "stop ste-modem\n");
 
 	return sproc->mdev->ops.power(sproc->mdev, false);
diff --git a/drivers/remoteproc/wkup_m3_rproc.c b/drivers/remoteproc/wkup_m3_rproc.c
new file mode 100644
index 0000000..edf8181
--- /dev/null
+++ b/drivers/remoteproc/wkup_m3_rproc.c
@@ -0,0 +1,257 @@
+/*
+ * TI AMx3 Wakeup M3 Remote Processor driver
+ *
+ * Copyright (C) 2014-2015 Texas Instruments, Inc.
+ *
+ * Dave Gerlach <d-gerlach@ti.com>
+ * Suman Anna <s-anna@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/remoteproc.h>
+
+#include <linux/platform_data/wkup_m3.h>
+
+#include "remoteproc_internal.h"
+
+#define WKUPM3_MEM_MAX	2
+
+/**
+ * struct wkup_m3_mem - WkupM3 internal memory structure
+ * @cpu_addr: MPU virtual address of the memory region
+ * @bus_addr: Bus address used to access the memory region
+ * @dev_addr: Device address from Wakeup M3 view
+ * @size: Size of the memory region
+ */
+struct wkup_m3_mem {
+	void __iomem *cpu_addr;
+	phys_addr_t bus_addr;
+	u32 dev_addr;
+	size_t size;
+};
+
+/**
+ * struct wkup_m3_rproc - WkupM3 remote processor state
+ * @rproc: rproc handle
+ * @pdev: pointer to platform device
+ * @mem: WkupM3 memory information
+ */
+struct wkup_m3_rproc {
+	struct rproc *rproc;
+	struct platform_device *pdev;
+	struct wkup_m3_mem mem[WKUPM3_MEM_MAX];
+};
+
+static int wkup_m3_rproc_start(struct rproc *rproc)
+{
+	struct wkup_m3_rproc *wkupm3 = rproc->priv;
+	struct platform_device *pdev = wkupm3->pdev;
+	struct device *dev = &pdev->dev;
+	struct wkup_m3_platform_data *pdata = dev_get_platdata(dev);
+
+	if (pdata->deassert_reset(pdev, pdata->reset_name)) {
+		dev_err(dev, "Unable to reset wkup_m3!\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static int wkup_m3_rproc_stop(struct rproc *rproc)
+{
+	struct wkup_m3_rproc *wkupm3 = rproc->priv;
+	struct platform_device *pdev = wkupm3->pdev;
+	struct device *dev = &pdev->dev;
+	struct wkup_m3_platform_data *pdata = dev_get_platdata(dev);
+
+	if (pdata->assert_reset(pdev, pdata->reset_name)) {
+		dev_err(dev, "Unable to assert reset of wkup_m3!\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static void *wkup_m3_rproc_da_to_va(struct rproc *rproc, u64 da, int len)
+{
+	struct wkup_m3_rproc *wkupm3 = rproc->priv;
+	void *va = NULL;
+	int i;
+	u32 offset;
+
+	if (len <= 0)
+		return NULL;
+
+	for (i = 0; i < WKUPM3_MEM_MAX; i++) {
+		if (da >= wkupm3->mem[i].dev_addr && da + len <=
+		    wkupm3->mem[i].dev_addr +  wkupm3->mem[i].size) {
+			offset = da -  wkupm3->mem[i].dev_addr;
+			/* __force to make sparse happy with type conversion */
+			va = (__force void *)(wkupm3->mem[i].cpu_addr + offset);
+			break;
+		}
+	}
+
+	return va;
+}
+
+static struct rproc_ops wkup_m3_rproc_ops = {
+	.start		= wkup_m3_rproc_start,
+	.stop		= wkup_m3_rproc_stop,
+	.da_to_va	= wkup_m3_rproc_da_to_va,
+};
+
+static const struct of_device_id wkup_m3_rproc_of_match[] = {
+	{ .compatible = "ti,am3352-wkup-m3", },
+	{ .compatible = "ti,am4372-wkup-m3", },
+	{},
+};
+
+static int wkup_m3_rproc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct wkup_m3_platform_data *pdata = dev->platform_data;
+	/* umem always needs to be processed first */
+	const char *mem_names[WKUPM3_MEM_MAX] = { "umem", "dmem" };
+	struct wkup_m3_rproc *wkupm3;
+	const char *fw_name;
+	struct rproc *rproc;
+	struct resource *res;
+	const __be32 *addrp;
+	u32 l4_offset = 0;
+	u64 size;
+	int ret;
+	int i;
+
+	if (!(pdata && pdata->deassert_reset && pdata->assert_reset &&
+	      pdata->reset_name)) {
+		dev_err(dev, "Platform data missing!\n");
+		return -ENODEV;
+	}
+
+	ret = of_property_read_string(dev->of_node, "ti,pm-firmware",
+				      &fw_name);
+	if (ret) {
+		dev_err(dev, "No firmware filename given\n");
+		return -ENODEV;
+	}
+
+	pm_runtime_enable(&pdev->dev);
+	ret = pm_runtime_get_sync(&pdev->dev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "pm_runtime_get_sync() failed\n");
+		goto err;
+	}
+
+	rproc = rproc_alloc(dev, "wkup_m3", &wkup_m3_rproc_ops,
+			    fw_name, sizeof(*wkupm3));
+	if (!rproc) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	wkupm3 = rproc->priv;
+	wkupm3->rproc = rproc;
+	wkupm3->pdev = pdev;
+
+	for (i = 0; i < ARRAY_SIZE(mem_names); i++) {
+		res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						   mem_names[i]);
+		wkupm3->mem[i].cpu_addr = devm_ioremap_resource(dev, res);
+		if (IS_ERR(wkupm3->mem[i].cpu_addr)) {
+			dev_err(&pdev->dev, "devm_ioremap_resource failed for resource %d\n",
+				i);
+			ret = PTR_ERR(wkupm3->mem[i].cpu_addr);
+			goto err;
+		}
+		wkupm3->mem[i].bus_addr = res->start;
+		wkupm3->mem[i].size = resource_size(res);
+		addrp = of_get_address(dev->of_node, i, &size, NULL);
+		/*
+		 * The wkupm3 has umem at address 0 in its view, so the device
+		 * addresses for each memory region is computed as a relative
+		 * offset of the bus address for umem, and therefore needs to be
+		 * processed first.
+		 */
+		if (!strcmp(mem_names[i], "umem"))
+			l4_offset = be32_to_cpu(*addrp);
+		wkupm3->mem[i].dev_addr = be32_to_cpu(*addrp) - l4_offset;
+	}
+
+	dev_set_drvdata(dev, rproc);
+
+	ret = rproc_add(rproc);
+	if (ret) {
+		dev_err(dev, "rproc_add failed\n");
+		goto err_put_rproc;
+	}
+
+	return 0;
+
+err_put_rproc:
+	rproc_put(rproc);
+err:
+	pm_runtime_put_noidle(dev);
+	pm_runtime_disable(dev);
+	return ret;
+}
+
+static int wkup_m3_rproc_remove(struct platform_device *pdev)
+{
+	struct rproc *rproc = platform_get_drvdata(pdev);
+
+	rproc_del(rproc);
+	rproc_put(rproc);
+	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int wkup_m3_rpm_suspend(struct device *dev)
+{
+	return -EBUSY;
+}
+
+static int wkup_m3_rpm_resume(struct device *dev)
+{
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops wkup_m3_rproc_pm_ops = {
+	SET_RUNTIME_PM_OPS(wkup_m3_rpm_suspend, wkup_m3_rpm_resume, NULL)
+};
+
+static struct platform_driver wkup_m3_rproc_driver = {
+	.probe = wkup_m3_rproc_probe,
+	.remove = wkup_m3_rproc_remove,
+	.driver = {
+		.name = "wkup_m3_rproc",
+		.of_match_table = wkup_m3_rproc_of_match,
+		.pm = &wkup_m3_rproc_pm_ops,
+	},
+};
+
+module_platform_driver(wkup_m3_rproc_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("TI Wakeup M3 remote processor control driver");
+MODULE_AUTHOR("Dave Gerlach <d-gerlach@ti.com>");
diff --git a/drivers/s390/kvm/virtio_ccw.c b/drivers/s390/kvm/virtio_ccw.c
index 6f1fa177..f8d8fdb 100644
--- a/drivers/s390/kvm/virtio_ccw.c
+++ b/drivers/s390/kvm/virtio_ccw.c
@@ -65,6 +65,7 @@
 	bool is_thinint;
 	bool going_away;
 	bool device_lost;
+	unsigned int config_ready;
 	void *airq_info;
 };
 
@@ -833,8 +834,11 @@
 	if (ret)
 		goto out_free;
 
-	memcpy(vcdev->config, config_area, sizeof(vcdev->config));
-	memcpy(buf, &vcdev->config[offset], len);
+	memcpy(vcdev->config, config_area, offset + len);
+	if (buf)
+		memcpy(buf, &vcdev->config[offset], len);
+	if (vcdev->config_ready < offset + len)
+		vcdev->config_ready = offset + len;
 
 out_free:
 	kfree(config_area);
@@ -857,6 +861,9 @@
 	if (!config_area)
 		goto out_free;
 
+	/* Make sure we don't overwrite fields. */
+	if (vcdev->config_ready < offset)
+		virtio_ccw_get_config(vdev, 0, NULL, offset);
 	memcpy(&vcdev->config[offset], buf, len);
 	/* Write the config area to the host. */
 	memcpy(config_area, vcdev->config, sizeof(vcdev->config));
diff --git a/drivers/scsi/cxgbi/libcxgbi.h b/drivers/scsi/cxgbi/libcxgbi.h
index b3e5bd1..9842301 100644
--- a/drivers/scsi/cxgbi/libcxgbi.h
+++ b/drivers/scsi/cxgbi/libcxgbi.h
@@ -685,10 +685,7 @@
 
 static inline void cxgbi_free_big_mem(void *addr)
 {
-	if (is_vmalloc_addr(addr))
-		vfree(addr);
-	else
-		kfree(addr);
+	kvfree(addr);
 }
 
 static inline void cxgbi_set_iscsi_ipv4(struct cxgbi_hba *chba, __be32 ipaddr)
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 4a484d6..b749026 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -1191,7 +1191,7 @@
 	list_for_each_entry(se_cmd, &se_sess->sess_cmd_list, se_cmd_list) {
 		struct qla_tgt_cmd *cmd =
 			container_of(se_cmd, struct qla_tgt_cmd, se_cmd);
-		if (cmd->tag == abts->exchange_addr_to_abort) {
+		if (se_cmd->tag == abts->exchange_addr_to_abort) {
 			lun = cmd->unpacked_lun;
 			found_lun = true;
 			break;
@@ -1728,9 +1728,8 @@
 
 	if (unlikely(cmd->aborted)) {
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf014,
-		    "qla_target(%d): terminating exchange "
-		    "for aborted cmd=%p (se_cmd=%p, tag=%d)", vha->vp_idx, cmd,
-		    se_cmd, cmd->tag);
+		       "qla_target(%d): terminating exchange for aborted cmd=%p (se_cmd=%p, tag=%lld)",
+		       vha->vp_idx, cmd, se_cmd, se_cmd->tag);
 
 		cmd->state = QLA_TGT_STATE_ABORTED;
 		cmd->cmd_flags |= BIT_6;
@@ -1765,18 +1764,17 @@
 	if (se_cmd->se_cmd_flags & SCF_UNDERFLOW_BIT) {
 		prm->residual = se_cmd->residual_count;
 		ql_dbg(ql_dbg_io + ql_dbg_verbose, vha, 0x305c,
-		    "Residual underflow: %d (tag %d, "
-		    "op %x, bufflen %d, rq_result %x)\n", prm->residual,
-		    cmd->tag, se_cmd->t_task_cdb ? se_cmd->t_task_cdb[0] : 0,
-		    cmd->bufflen, prm->rq_result);
+		    "Residual underflow: %d (tag %lld, op %x, bufflen %d, rq_result %x)\n",
+		       prm->residual, se_cmd->tag,
+		       se_cmd->t_task_cdb ? se_cmd->t_task_cdb[0] : 0,
+		       cmd->bufflen, prm->rq_result);
 		prm->rq_result |= SS_RESIDUAL_UNDER;
 	} else if (se_cmd->se_cmd_flags & SCF_OVERFLOW_BIT) {
 		prm->residual = se_cmd->residual_count;
 		ql_dbg(ql_dbg_io, vha, 0x305d,
-		    "Residual overflow: %d (tag %d, "
-		    "op %x, bufflen %d, rq_result %x)\n", prm->residual,
-		    cmd->tag, se_cmd->t_task_cdb ? se_cmd->t_task_cdb[0] : 0,
-		    cmd->bufflen, prm->rq_result);
+		    "Residual overflow: %d (tag %lld, op %x, bufflen %d, rq_result %x)\n",
+		       prm->residual, se_cmd->tag, se_cmd->t_task_cdb ?
+		       se_cmd->t_task_cdb[0] : 0, cmd->bufflen, prm->rq_result);
 		prm->rq_result |= SS_RESIDUAL_OVER;
 	}
 
@@ -1849,7 +1847,7 @@
 	    == 50) {
 		*xmit_type &= ~QLA_TGT_XMIT_STATUS;
 		ql_dbg(ql_dbg_tgt_mgt, cmd->vha, 0xf015,
-		    "Dropping cmd %p (tag %d) status", cmd, cmd->tag);
+		    "Dropping cmd %p (tag %d) status", cmd, se_cmd->tag);
 	}
 #endif
 	/*
@@ -1873,7 +1871,7 @@
 		ql_dbg(ql_dbg_tgt_mgt, cmd->vha, 0xf016,
 		    "Cutting cmd %p (tag %d) buffer"
 		    " tail to len %d, sg_cnt %d (cmd->bufflen %d,"
-		    " cmd->sg_cnt %d)", cmd, cmd->tag, tot_len, leave,
+		    " cmd->sg_cnt %d)", cmd, se_cmd->tag, tot_len, leave,
 		    cmd->bufflen, cmd->sg_cnt);
 
 		cmd->bufflen = tot_len;
@@ -1885,13 +1883,13 @@
 
 		ql_dbg(ql_dbg_tgt_mgt, cmd->vha, 0xf017,
 		    "Cutting cmd %p (tag %d) buffer head "
-		    "to offset %d (cmd->bufflen %d)", cmd, cmd->tag, offset,
+		    "to offset %d (cmd->bufflen %d)", cmd, se_cmd->tag, offset,
 		    cmd->bufflen);
 		if (offset == 0)
 			*xmit_type &= ~QLA_TGT_XMIT_DATA;
 		else if (qlt_set_data_offset(cmd, offset)) {
 			ql_dbg(ql_dbg_tgt_mgt, cmd->vha, 0xf018,
-			    "qlt_set_data_offset() failed (tag %d)", cmd->tag);
+			    "qlt_set_data_offset() failed (tag %d)", se_cmd->tag);
 		}
 	}
 }
@@ -3194,7 +3192,7 @@
 		return;
 	} else if (cmd->state == QLA_TGT_STATE_ABORTED) {
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf01e,
-		    "Aborted command %p (tag %d) finished\n", cmd, cmd->tag);
+		  "Aborted command %p (tag %lld) finished\n", cmd, se_cmd->tag);
 	} else {
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf05c,
 		    "qla_target(%d): A command in state (%d) should "
@@ -3266,7 +3264,7 @@
 		goto out_term;
 
 	cdb = &atio->u.isp24.fcp_cmnd.cdb[0];
-	cmd->tag = atio->u.isp24.exchange_addr;
+	cmd->se_cmd.tag = atio->u.isp24.exchange_addr;
 	cmd->unpacked_lun = scsilun_to_int(
 	    (struct scsi_lun *)&atio->u.isp24.fcp_cmnd.lun);
 
@@ -3893,9 +3891,8 @@
 			resp = 1;
 		} else {
 			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf064,
-			    "qla_target(%d): SRR for in data for cmd "
-			    "without them (tag %d, SCSI status %d), "
-			    "reject", vha->vp_idx, cmd->tag,
+			       "qla_target(%d): SRR for in data for cmd without them (tag %lld, SCSI status %d), reject",
+			       vha->vp_idx, se_cmd->tag,
 			    cmd->se_cmd.scsi_status);
 			goto out_reject;
 		}
@@ -3929,10 +3926,8 @@
 			}
 		} else {
 			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf066,
-			    "qla_target(%d): SRR for out data for cmd "
-			    "without them (tag %d, SCSI status %d), "
-			    "reject", vha->vp_idx, cmd->tag,
-			    cmd->se_cmd.scsi_status);
+			    "qla_target(%d): SRR for out data for cmd without them (tag %lld, SCSI status %d), reject",
+			       vha->vp_idx, se_cmd->tag, cmd->se_cmd.scsi_status);
 			goto out_reject;
 		}
 		break;
@@ -4053,10 +4048,9 @@
 		cmd->sg = se_cmd->t_data_sg;
 
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf02c,
-		    "SRR cmd %p (se_cmd %p, tag %d, op %x), "
-		    "sg_cnt=%d, offset=%d", cmd, &cmd->se_cmd, cmd->tag,
-		    se_cmd->t_task_cdb ? se_cmd->t_task_cdb[0] : 0,
-		    cmd->sg_cnt, cmd->offset);
+		       "SRR cmd %p (se_cmd %p, tag %lld, op %x), sg_cnt=%d, offset=%d",
+		       cmd, &cmd->se_cmd, se_cmd->tag, se_cmd->t_task_cdb ?
+		       se_cmd->t_task_cdb[0] : 0, cmd->sg_cnt, cmd->offset);
 
 		qlt_handle_srr(vha, sctio, imm);
 
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index 3320867..985d76d 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -924,7 +924,6 @@
 	int sg_cnt;		/* SG segments count */
 	int bufflen;		/* cmd buffer length */
 	int offset;
-	uint32_t tag;
 	uint32_t unpacked_lun;
 	enum dma_data_direction dma_data_direction;
 	uint32_t reset_count;
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index e32d24e..d9a8c60 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -44,7 +44,6 @@
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
 #include <target/target_core_fabric_configfs.h>
-#include <target/target_core_configfs.h>
 #include <target/configfs_macros.h>
 
 #include "qla_def.h"
@@ -54,9 +53,6 @@
 static struct workqueue_struct *tcm_qla2xxx_free_wq;
 static struct workqueue_struct *tcm_qla2xxx_cmd_wq;
 
-static const struct target_core_fabric_ops tcm_qla2xxx_ops;
-static const struct target_core_fabric_ops tcm_qla2xxx_npiv_ops;
-
 /*
  * Parse WWN.
  * If strict, we require lower-case hex and colon separators to be sure
@@ -191,23 +187,6 @@
 	return "qla2xxx_npiv";
 }
 
-static u8 tcm_qla2xxx_get_fabric_proto_ident(struct se_portal_group *se_tpg)
-{
-	struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
-				struct tcm_qla2xxx_tpg, se_tpg);
-	struct tcm_qla2xxx_lport *lport = tpg->lport;
-	u8 proto_id;
-
-	switch (lport->lport_proto_id) {
-	case SCSI_PROTOCOL_FCP:
-	default:
-		proto_id = fc_get_fabric_proto_ident(se_tpg);
-		break;
-	}
-
-	return proto_id;
-}
-
 static char *tcm_qla2xxx_get_fabric_wwn(struct se_portal_group *se_tpg)
 {
 	struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
@@ -224,78 +203,6 @@
 	return tpg->lport_tpgt;
 }
 
-static u32 tcm_qla2xxx_get_default_depth(struct se_portal_group *se_tpg)
-{
-	return 1;
-}
-
-static u32 tcm_qla2xxx_get_pr_transport_id(
-	struct se_portal_group *se_tpg,
-	struct se_node_acl *se_nacl,
-	struct t10_pr_registration *pr_reg,
-	int *format_code,
-	unsigned char *buf)
-{
-	struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
-				struct tcm_qla2xxx_tpg, se_tpg);
-	struct tcm_qla2xxx_lport *lport = tpg->lport;
-	int ret = 0;
-
-	switch (lport->lport_proto_id) {
-	case SCSI_PROTOCOL_FCP:
-	default:
-		ret = fc_get_pr_transport_id(se_tpg, se_nacl, pr_reg,
-					format_code, buf);
-		break;
-	}
-
-	return ret;
-}
-
-static u32 tcm_qla2xxx_get_pr_transport_id_len(
-	struct se_portal_group *se_tpg,
-	struct se_node_acl *se_nacl,
-	struct t10_pr_registration *pr_reg,
-	int *format_code)
-{
-	struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
-				struct tcm_qla2xxx_tpg, se_tpg);
-	struct tcm_qla2xxx_lport *lport = tpg->lport;
-	int ret = 0;
-
-	switch (lport->lport_proto_id) {
-	case SCSI_PROTOCOL_FCP:
-	default:
-		ret = fc_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,
-					format_code);
-		break;
-	}
-
-	return ret;
-}
-
-static char *tcm_qla2xxx_parse_pr_out_transport_id(
-	struct se_portal_group *se_tpg,
-	const char *buf,
-	u32 *out_tid_len,
-	char **port_nexus_ptr)
-{
-	struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
-				struct tcm_qla2xxx_tpg, se_tpg);
-	struct tcm_qla2xxx_lport *lport = tpg->lport;
-	char *tid = NULL;
-
-	switch (lport->lport_proto_id) {
-	case SCSI_PROTOCOL_FCP:
-	default:
-		tid = fc_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,
-					port_nexus_ptr);
-		break;
-	}
-
-	return tid;
-}
-
 static int tcm_qla2xxx_check_demo_mode(struct se_portal_group *se_tpg)
 {
 	struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
@@ -344,29 +251,6 @@
 	return tpg->tpg_attrib.fabric_prot_type;
 }
 
-static struct se_node_acl *tcm_qla2xxx_alloc_fabric_acl(
-	struct se_portal_group *se_tpg)
-{
-	struct tcm_qla2xxx_nacl *nacl;
-
-	nacl = kzalloc(sizeof(struct tcm_qla2xxx_nacl), GFP_KERNEL);
-	if (!nacl) {
-		pr_err("Unable to allocate struct tcm_qla2xxx_nacl\n");
-		return NULL;
-	}
-
-	return &nacl->se_node_acl;
-}
-
-static void tcm_qla2xxx_release_fabric_acl(
-	struct se_portal_group *se_tpg,
-	struct se_node_acl *se_nacl)
-{
-	struct tcm_qla2xxx_nacl *nacl = container_of(se_nacl,
-			struct tcm_qla2xxx_nacl, se_node_acl);
-	kfree(nacl);
-}
-
 static u32 tcm_qla2xxx_tpg_get_inst_index(struct se_portal_group *se_tpg)
 {
 	struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
@@ -430,7 +314,7 @@
 		cmd->cmd_flags |= BIT_14;
 	}
 
-	return target_put_sess_cmd(se_cmd->se_sess, se_cmd);
+	return target_put_sess_cmd(se_cmd);
 }
 
 /* tcm_qla2xxx_release_cmd - Callback from TCM Core to release underlying
@@ -534,19 +418,6 @@
 	return;
 }
 
-static u32 tcm_qla2xxx_get_task_tag(struct se_cmd *se_cmd)
-{
-	struct qla_tgt_cmd *cmd;
-
-	/* check for task mgmt cmd */
-	if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)
-		return 0xffffffff;
-
-	cmd = container_of(se_cmd, struct qla_tgt_cmd, se_cmd);
-
-	return cmd->tag;
-}
-
 static int tcm_qla2xxx_get_cmd_state(struct se_cmd *se_cmd)
 {
 	return 0;
@@ -827,17 +698,6 @@
 	qlt_unreg_sess(se_sess->fabric_sess_ptr);
 }
 
-static void tcm_qla2xxx_put_session(struct se_session *se_sess)
-{
-	struct qla_tgt_sess *sess = se_sess->fabric_sess_ptr;
-	struct qla_hw_data *ha = sess->vha->hw;
-	unsigned long flags;
-
-	spin_lock_irqsave(&ha->hardware_lock, flags);
-	kref_put(&se_sess->sess_kref, tcm_qla2xxx_release_session);
-	spin_unlock_irqrestore(&ha->hardware_lock, flags);
-}
-
 static void tcm_qla2xxx_put_sess(struct qla_tgt_sess *sess)
 {
 	if (!sess)
@@ -853,53 +713,20 @@
 	target_sess_cmd_list_set_waiting(sess->se_sess);
 }
 
-static struct se_node_acl *tcm_qla2xxx_make_nodeacl(
-	struct se_portal_group *se_tpg,
-	struct config_group *group,
-	const char *name)
+static int tcm_qla2xxx_init_nodeacl(struct se_node_acl *se_nacl,
+		const char *name)
 {
-	struct se_node_acl *se_nacl, *se_nacl_new;
-	struct tcm_qla2xxx_nacl *nacl;
+	struct tcm_qla2xxx_nacl *nacl =
+		container_of(se_nacl, struct tcm_qla2xxx_nacl, se_node_acl);
 	u64 wwnn;
-	u32 qla2xxx_nexus_depth;
 
 	if (tcm_qla2xxx_parse_wwn(name, &wwnn, 1) < 0)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
-	se_nacl_new = tcm_qla2xxx_alloc_fabric_acl(se_tpg);
-	if (!se_nacl_new)
-		return ERR_PTR(-ENOMEM);
-/* #warning FIXME: Hardcoded qla2xxx_nexus depth in tcm_qla2xxx_make_nodeacl */
-	qla2xxx_nexus_depth = 1;
-
-	/*
-	 * se_nacl_new may be released by core_tpg_add_initiator_node_acl()
-	 * when converting a NodeACL from demo mode -> explict
-	 */
-	se_nacl = core_tpg_add_initiator_node_acl(se_tpg, se_nacl_new,
-				name, qla2xxx_nexus_depth);
-	if (IS_ERR(se_nacl)) {
-		tcm_qla2xxx_release_fabric_acl(se_tpg, se_nacl_new);
-		return se_nacl;
-	}
-	/*
-	 * Locate our struct tcm_qla2xxx_nacl and set the FC Nport WWPN
-	 */
-	nacl = container_of(se_nacl, struct tcm_qla2xxx_nacl, se_node_acl);
 	nacl->nport_wwnn = wwnn;
 	tcm_qla2xxx_format_wwn(&nacl->nport_name[0], TCM_QLA2XXX_NAMELEN, wwnn);
 
-	return se_nacl;
-}
-
-static void tcm_qla2xxx_drop_nodeacl(struct se_node_acl *se_acl)
-{
-	struct se_portal_group *se_tpg = se_acl->se_tpg;
-	struct tcm_qla2xxx_nacl *nacl = container_of(se_acl,
-				struct tcm_qla2xxx_nacl, se_node_acl);
-
-	core_tpg_del_initiator_node_acl(se_tpg, se_acl, 1);
-	kfree(nacl);
+	return 0;
 }
 
 /* Start items for tcm_qla2xxx_tpg_attrib_cit */
@@ -1175,8 +1002,7 @@
 	tpg->tpg_attrib.cache_dynamic_acls = 1;
 	tpg->tpg_attrib.demo_mode_login_only = 1;
 
-	ret = core_tpg_register(&tcm_qla2xxx_ops, wwn,
-				&tpg->se_tpg, tpg, TRANSPORT_TPG_TYPE_NORMAL);
+	ret = core_tpg_register(wwn, &tpg->se_tpg, SCSI_PROTOCOL_FCP);
 	if (ret < 0) {
 		kfree(tpg);
 		return NULL;
@@ -1295,8 +1121,7 @@
 	tpg->tpg_attrib.cache_dynamic_acls = 1;
 	tpg->tpg_attrib.demo_mode_login_only = 1;
 
-	ret = core_tpg_register(&tcm_qla2xxx_npiv_ops, wwn,
-				&tpg->se_tpg, tpg, TRANSPORT_TPG_TYPE_NORMAL);
+	ret = core_tpg_register(wwn, &tpg->se_tpg, SCSI_PROTOCOL_FCP);
 	if (ret < 0) {
 		kfree(tpg);
 		return NULL;
@@ -1988,14 +1813,10 @@
 static const struct target_core_fabric_ops tcm_qla2xxx_ops = {
 	.module				= THIS_MODULE,
 	.name				= "qla2xxx",
+	.node_acl_size			= sizeof(struct tcm_qla2xxx_nacl),
 	.get_fabric_name		= tcm_qla2xxx_get_fabric_name,
-	.get_fabric_proto_ident		= tcm_qla2xxx_get_fabric_proto_ident,
 	.tpg_get_wwn			= tcm_qla2xxx_get_fabric_wwn,
 	.tpg_get_tag			= tcm_qla2xxx_get_tag,
-	.tpg_get_default_depth		= tcm_qla2xxx_get_default_depth,
-	.tpg_get_pr_transport_id	= tcm_qla2xxx_get_pr_transport_id,
-	.tpg_get_pr_transport_id_len	= tcm_qla2xxx_get_pr_transport_id_len,
-	.tpg_parse_pr_out_transport_id	= tcm_qla2xxx_parse_pr_out_transport_id,
 	.tpg_check_demo_mode		= tcm_qla2xxx_check_demo_mode,
 	.tpg_check_demo_mode_cache	= tcm_qla2xxx_check_demo_mode_cache,
 	.tpg_check_demo_mode_write_protect =
@@ -2004,12 +1825,9 @@
 					tcm_qla2xxx_check_prod_write_protect,
 	.tpg_check_prot_fabric_only	= tcm_qla2xxx_check_prot_fabric_only,
 	.tpg_check_demo_mode_login_only = tcm_qla2xxx_check_demo_mode_login_only,
-	.tpg_alloc_fabric_acl		= tcm_qla2xxx_alloc_fabric_acl,
-	.tpg_release_fabric_acl		= tcm_qla2xxx_release_fabric_acl,
 	.tpg_get_inst_index		= tcm_qla2xxx_tpg_get_inst_index,
 	.check_stop_free		= tcm_qla2xxx_check_stop_free,
 	.release_cmd			= tcm_qla2xxx_release_cmd,
-	.put_session			= tcm_qla2xxx_put_session,
 	.shutdown_session		= tcm_qla2xxx_shutdown_session,
 	.close_session			= tcm_qla2xxx_close_session,
 	.sess_get_index			= tcm_qla2xxx_sess_get_index,
@@ -2017,7 +1835,6 @@
 	.write_pending			= tcm_qla2xxx_write_pending,
 	.write_pending_status		= tcm_qla2xxx_write_pending_status,
 	.set_default_node_attributes	= tcm_qla2xxx_set_default_node_attrs,
-	.get_task_tag			= tcm_qla2xxx_get_task_tag,
 	.get_cmd_state			= tcm_qla2xxx_get_cmd_state,
 	.queue_data_in			= tcm_qla2xxx_queue_data_in,
 	.queue_status			= tcm_qla2xxx_queue_status,
@@ -2031,12 +1848,7 @@
 	.fabric_drop_wwn		= tcm_qla2xxx_drop_lport,
 	.fabric_make_tpg		= tcm_qla2xxx_make_tpg,
 	.fabric_drop_tpg		= tcm_qla2xxx_drop_tpg,
-	.fabric_post_link		= NULL,
-	.fabric_pre_unlink		= NULL,
-	.fabric_make_np			= NULL,
-	.fabric_drop_np			= NULL,
-	.fabric_make_nodeacl		= tcm_qla2xxx_make_nodeacl,
-	.fabric_drop_nodeacl		= tcm_qla2xxx_drop_nodeacl,
+	.fabric_init_nodeacl		= tcm_qla2xxx_init_nodeacl,
 
 	.tfc_wwn_attrs			= tcm_qla2xxx_wwn_attrs,
 	.tfc_tpg_base_attrs		= tcm_qla2xxx_tpg_attrs,
@@ -2046,26 +1858,19 @@
 static const struct target_core_fabric_ops tcm_qla2xxx_npiv_ops = {
 	.module				= THIS_MODULE,
 	.name				= "qla2xxx_npiv",
+	.node_acl_size			= sizeof(struct tcm_qla2xxx_nacl),
 	.get_fabric_name		= tcm_qla2xxx_npiv_get_fabric_name,
-	.get_fabric_proto_ident		= tcm_qla2xxx_get_fabric_proto_ident,
 	.tpg_get_wwn			= tcm_qla2xxx_get_fabric_wwn,
 	.tpg_get_tag			= tcm_qla2xxx_get_tag,
-	.tpg_get_default_depth		= tcm_qla2xxx_get_default_depth,
-	.tpg_get_pr_transport_id	= tcm_qla2xxx_get_pr_transport_id,
-	.tpg_get_pr_transport_id_len	= tcm_qla2xxx_get_pr_transport_id_len,
-	.tpg_parse_pr_out_transport_id	= tcm_qla2xxx_parse_pr_out_transport_id,
 	.tpg_check_demo_mode		= tcm_qla2xxx_check_demo_mode,
 	.tpg_check_demo_mode_cache	= tcm_qla2xxx_check_demo_mode_cache,
 	.tpg_check_demo_mode_write_protect = tcm_qla2xxx_check_demo_mode,
 	.tpg_check_prod_mode_write_protect =
 	    tcm_qla2xxx_check_prod_write_protect,
 	.tpg_check_demo_mode_login_only	= tcm_qla2xxx_check_demo_mode_login_only,
-	.tpg_alloc_fabric_acl		= tcm_qla2xxx_alloc_fabric_acl,
-	.tpg_release_fabric_acl		= tcm_qla2xxx_release_fabric_acl,
 	.tpg_get_inst_index		= tcm_qla2xxx_tpg_get_inst_index,
 	.check_stop_free                = tcm_qla2xxx_check_stop_free,
 	.release_cmd			= tcm_qla2xxx_release_cmd,
-	.put_session			= tcm_qla2xxx_put_session,
 	.shutdown_session		= tcm_qla2xxx_shutdown_session,
 	.close_session			= tcm_qla2xxx_close_session,
 	.sess_get_index			= tcm_qla2xxx_sess_get_index,
@@ -2073,7 +1878,6 @@
 	.write_pending			= tcm_qla2xxx_write_pending,
 	.write_pending_status		= tcm_qla2xxx_write_pending_status,
 	.set_default_node_attributes	= tcm_qla2xxx_set_default_node_attrs,
-	.get_task_tag			= tcm_qla2xxx_get_task_tag,
 	.get_cmd_state			= tcm_qla2xxx_get_cmd_state,
 	.queue_data_in			= tcm_qla2xxx_queue_data_in,
 	.queue_status			= tcm_qla2xxx_queue_status,
@@ -2087,12 +1891,7 @@
 	.fabric_drop_wwn		= tcm_qla2xxx_npiv_drop_lport,
 	.fabric_make_tpg		= tcm_qla2xxx_npiv_make_tpg,
 	.fabric_drop_tpg		= tcm_qla2xxx_drop_tpg,
-	.fabric_post_link		= NULL,
-	.fabric_pre_unlink		= NULL,
-	.fabric_make_np			= NULL,
-	.fabric_drop_np			= NULL,
-	.fabric_make_nodeacl		= tcm_qla2xxx_make_nodeacl,
-	.fabric_drop_nodeacl		= tcm_qla2xxx_drop_nodeacl,
+	.fabric_init_nodeacl		= tcm_qla2xxx_init_nodeacl,
 
 	.tfc_wwn_attrs			= tcm_qla2xxx_wwn_attrs,
 	.tfc_tpg_base_attrs		= tcm_qla2xxx_npiv_tpg_attrs,
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.h b/drivers/scsi/qla2xxx/tcm_qla2xxx.h
index 2329511..3bbf4cb 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.h
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.h
@@ -13,6 +13,8 @@
 #include "qla_target.h"
 
 struct tcm_qla2xxx_nacl {
+	struct se_node_acl se_node_acl;
+
 	/* From libfc struct fc_rport->port_id */
 	u32 nport_id;
 	/* Binary World Wide unique Node Name for remote FC Initiator Nport */
@@ -23,8 +25,6 @@
 	struct qla_tgt_sess *qla_tgt_sess;
 	/* Pointer to TCM FC nexus */
 	struct se_session *nport_nexus;
-	/* Returned by tcm_qla2xxx_make_nodeacl() */
-	struct se_node_acl se_node_acl;
 };
 
 struct tcm_qla2xxx_tpg_attrib {
@@ -57,8 +57,6 @@
 };
 
 struct tcm_qla2xxx_lport {
-	/* SCSI protocol the lport is providing */
-	u8 lport_proto_id;
 	/* Binary World Wide unique Port Name for FC Target Lport */
 	u64 lport_wwpn;
 	/* Binary World Wide unique Port Name for FC NPIV Target Lport */
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 1f8e2dc..30268bb 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -2363,17 +2363,13 @@
 	u64 block, rest = 0;
 	struct scsi_data_buffer *sdb;
 	enum dma_data_direction dir;
-	size_t (*func)(struct scatterlist *, unsigned int, void *, size_t,
-		       off_t);
 
 	if (do_write) {
 		sdb = scsi_out(scmd);
 		dir = DMA_TO_DEVICE;
-		func = sg_pcopy_to_buffer;
 	} else {
 		sdb = scsi_in(scmd);
 		dir = DMA_FROM_DEVICE;
-		func = sg_pcopy_from_buffer;
 	}
 
 	if (!sdb->length)
@@ -2385,16 +2381,16 @@
 	if (block + num > sdebug_store_sectors)
 		rest = block + num - sdebug_store_sectors;
 
-	ret = func(sdb->table.sgl, sdb->table.nents,
+	ret = sg_copy_buffer(sdb->table.sgl, sdb->table.nents,
 		   fake_storep + (block * scsi_debug_sector_size),
-		   (num - rest) * scsi_debug_sector_size, 0);
+		   (num - rest) * scsi_debug_sector_size, 0, do_write);
 	if (ret != (num - rest) * scsi_debug_sector_size)
 		return ret;
 
 	if (rest) {
-		ret += func(sdb->table.sgl, sdb->table.nents,
+		ret += sg_copy_buffer(sdb->table.sgl, sdb->table.nents,
 			    fake_storep, rest * scsi_debug_sector_size,
-			    (num - rest) * scsi_debug_sector_size);
+			    (num - rest) * scsi_debug_sector_size, do_write);
 	}
 
 	return ret;
diff --git a/drivers/sh/intc/core.c b/drivers/sh/intc/core.c
index 81f2298..156b790 100644
--- a/drivers/sh/intc/core.c
+++ b/drivers/sh/intc/core.c
@@ -366,8 +366,9 @@
 
 			/* redirect this interrupts to the first one */
 			irq_set_chip(irq2, &dummy_irq_chip);
-			irq_set_chained_handler(irq2, intc_redirect_irq);
-			irq_set_handler_data(irq2, (void *)irq);
+			irq_set_chained_handler_and_data(irq2,
+							 intc_redirect_irq,
+							 (void *)irq);
 		}
 	}
 
diff --git a/drivers/sh/intc/virq.c b/drivers/sh/intc/virq.c
index f30ac93..f5f1b82 100644
--- a/drivers/sh/intc/virq.c
+++ b/drivers/sh/intc/virq.c
@@ -243,8 +243,9 @@
 		 */
 		irq_set_nothread(irq);
 
-		irq_set_chained_handler(entry->pirq, intc_virq_handler);
+		/* Set handler data before installing the handler */
 		add_virq_to_pirq(entry->pirq, irq);
+		irq_set_chained_handler(entry->pirq, intc_virq_handler);
 
 		radix_tree_tag_clear(&d->tree, entry->enum_id,
 				     INTC_TAG_VIRQ_NEEDS_ALLOC);
diff --git a/drivers/soc/qcom/spm.c b/drivers/soc/qcom/spm.c
index b562af8..b04b05a 100644
--- a/drivers/soc/qcom/spm.c
+++ b/drivers/soc/qcom/spm.c
@@ -260,7 +260,7 @@
 		/* We have atleast one power down mode */
 		cpumask_clear(&mask);
 		cpumask_set_cpu(cpu, &mask);
-		qcom_scm_set_warm_boot_addr(cpu_resume, &mask);
+		qcom_scm_set_warm_boot_addr(cpu_resume_arm, &mask);
 	}
 
 	per_cpu(qcom_idle_ops, cpu) = fns;
diff --git a/drivers/soc/tegra/pmc.c b/drivers/soc/tegra/pmc.c
index cc119d1..75d0457 100644
--- a/drivers/soc/tegra/pmc.c
+++ b/drivers/soc/tegra/pmc.c
@@ -1021,7 +1021,7 @@
 	},
 	.probe = tegra_pmc_probe,
 };
-module_platform_driver(tegra_pmc_driver);
+builtin_platform_driver(tegra_pmc_driver);
 
 /*
  * Early initialization to allow access to registers in the very early boot
diff --git a/drivers/soc/versatile/soc-realview.c b/drivers/soc/versatile/soc-realview.c
index 1a07bf5..e642c45 100644
--- a/drivers/soc/versatile/soc-realview.c
+++ b/drivers/soc/versatile/soc-realview.c
@@ -142,4 +142,4 @@
 		.of_match_table = realview_soc_of_match,
 	},
 };
-module_platform_driver(realview_soc_driver);
+builtin_platform_driver(realview_soc_driver);
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index a3fba36..4e68b62 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -29,7 +29,6 @@
 #include <scsi/scsi_tcq.h>
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
-#include <target/target_core_configfs.h>
 
 #include <target/iscsi/iscsi_target_core.h>
 #include "iscsi_target_parameters.h"
@@ -716,7 +715,7 @@
 	 */
 	if (cmd->se_cmd.se_tfo != NULL) {
 		pr_debug("iscsi reject: calling target_put_sess_cmd >>>>>>\n");
-		target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd);
+		target_put_sess_cmd(&cmd->se_cmd);
 	}
 	return -1;
 }
@@ -1002,13 +1001,15 @@
 		hdr->cmdsn, be32_to_cpu(hdr->data_length), payload_length,
 		conn->cid);
 
-	target_get_sess_cmd(conn->sess->se_sess, &cmd->se_cmd, true);
+	target_get_sess_cmd(&cmd->se_cmd, true);
 
 	cmd->sense_reason = transport_lookup_cmd_lun(&cmd->se_cmd,
 						     scsilun_to_int(&hdr->lun));
 	if (cmd->sense_reason)
 		goto attach_cmd;
 
+	/* only used for printks or comparing with ->ref_task_tag */
+	cmd->se_cmd.tag = (__force u32)cmd->init_task_tag;
 	cmd->sense_reason = target_setup_cmd_from_cdb(&cmd->se_cmd, hdr->cdb);
 	if (cmd->sense_reason) {
 		if (cmd->sense_reason == TCM_OUT_OF_RESOURCES) {
@@ -1068,7 +1069,7 @@
 		if (cmdsn_ret == CMDSN_ERROR_CANNOT_RECOVER)
 			return -1;
 		else if (cmdsn_ret == CMDSN_LOWER_THAN_EXP) {
-			target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd);
+			target_put_sess_cmd(&cmd->se_cmd);
 			return 0;
 		}
 	}
@@ -1084,7 +1085,7 @@
 		if (!cmd->sense_reason)
 			return 0;
 
-		target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd);
+		target_put_sess_cmd(&cmd->se_cmd);
 		return 0;
 	}
 
@@ -1115,7 +1116,6 @@
 iscsit_get_immediate_data(struct iscsi_cmd *cmd, struct iscsi_scsi_req *hdr,
 			  bool dump_payload)
 {
-	struct iscsi_conn *conn = cmd->conn;
 	int cmdsn_ret = 0, immed_ret = IMMEDIATE_DATA_NORMAL_OPERATION;
 	/*
 	 * Special case for Unsupported SAM WRITE Opcodes and ImmediateData=Yes.
@@ -1142,7 +1142,7 @@
 
 			rc = iscsit_dump_data_payload(cmd->conn,
 						      cmd->first_burst_len, 1);
-			target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd);
+			target_put_sess_cmd(&cmd->se_cmd);
 			return rc;
 		} else if (cmd->unsolicited_data)
 			iscsit_set_unsoliticed_dataout(cmd);
@@ -1811,7 +1811,7 @@
 				      conn->sess->se_sess, 0, DMA_NONE,
 				      TCM_SIMPLE_TAG, cmd->sense_buffer + 2);
 
-		target_get_sess_cmd(conn->sess->se_sess, &cmd->se_cmd, true);
+		target_get_sess_cmd(&cmd->se_cmd, true);
 		sess_ref = true;
 
 		switch (function) {
@@ -1953,7 +1953,7 @@
 	 */
 	if (sess_ref) {
 		pr_debug("Handle TMR, using sess_ref=true check\n");
-		target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd);
+		target_put_sess_cmd(&cmd->se_cmd);
 	}
 
 	iscsit_add_cmd_to_response_queue(cmd, conn, cmd->i_state);
@@ -2737,11 +2737,7 @@
 	cmd->iov_data_count = iov_count;
 	cmd->tx_size = tx_size;
 
-	/* sendpage is preferred but can't insert markers */
-	if (!conn->conn_ops->IFMarker)
-		ret = iscsit_fe_sendpage_sg(cmd, conn);
-	else
-		ret = iscsit_send_tx_data(cmd, conn, 0);
+	ret = iscsit_fe_sendpage_sg(cmd, conn);
 
 	iscsit_unmap_iovec(cmd);
 
@@ -4073,17 +4069,9 @@
 			" opcode while ERL=0, closing iSCSI connection.\n");
 			return -1;
 		}
-		if (!conn->conn_ops->OFMarker) {
-			pr_err("Unable to recover from unknown"
-			" opcode while OFMarker=No, closing iSCSI"
-				" connection.\n");
-			return -1;
-		}
-		if (iscsit_recover_from_unknown_opcode(conn) < 0) {
-			pr_err("Unable to recover from unknown"
-				" opcode, closing iSCSI connection.\n");
-			return -1;
-		}
+		pr_err("Unable to recover from unknown opcode while OFMarker=No,"
+		       " closing iSCSI connection.\n");
+		ret = -1;
 		break;
 	}
 
diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c
index 469fce4..c1898c8 100644
--- a/drivers/target/iscsi/iscsi_target_configfs.c
+++ b/drivers/target/iscsi/iscsi_target_configfs.c
@@ -24,7 +24,6 @@
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
 #include <target/target_core_fabric_configfs.h>
-#include <target/target_core_configfs.h>
 #include <target/configfs_macros.h>
 #include <target/iscsi/iscsi_transport.h>
 
@@ -860,57 +859,19 @@
 	NULL,
 };
 
-static struct se_node_acl *lio_tpg_alloc_fabric_acl(
-	struct se_portal_group *se_tpg)
+static int lio_target_init_nodeacl(struct se_node_acl *se_nacl,
+		const char *name)
 {
-	struct iscsi_node_acl *acl;
-
-	acl = kzalloc(sizeof(struct iscsi_node_acl), GFP_KERNEL);
-	if (!acl) {
-		pr_err("Unable to allocate memory for struct iscsi_node_acl\n");
-		return NULL;
-	}
-
-	return &acl->se_node_acl;
-}
-
-static struct se_node_acl *lio_target_make_nodeacl(
-	struct se_portal_group *se_tpg,
-	struct config_group *group,
-	const char *name)
-{
-	struct config_group *stats_cg;
-	struct iscsi_node_acl *acl;
-	struct se_node_acl *se_nacl_new, *se_nacl;
-	struct iscsi_portal_group *tpg = container_of(se_tpg,
-			struct iscsi_portal_group, tpg_se_tpg);
-	u32 cmdsn_depth;
-
-	se_nacl_new = lio_tpg_alloc_fabric_acl(se_tpg);
-	if (!se_nacl_new)
-		return ERR_PTR(-ENOMEM);
-
-	cmdsn_depth = tpg->tpg_attrib.default_cmdsn_depth;
-	/*
-	 * se_nacl_new may be released by core_tpg_add_initiator_node_acl()
-	 * when converting a NdoeACL from demo mode -> explict
-	 */
-	se_nacl = core_tpg_add_initiator_node_acl(se_tpg, se_nacl_new,
-				name, cmdsn_depth);
-	if (IS_ERR(se_nacl))
-		return se_nacl;
-
-	acl = container_of(se_nacl, struct iscsi_node_acl, se_node_acl);
-	stats_cg = &se_nacl->acl_fabric_stat_group;
+	struct iscsi_node_acl *acl =
+		container_of(se_nacl, struct iscsi_node_acl, se_node_acl);
+	struct config_group *stats_cg = &se_nacl->acl_fabric_stat_group;
 
 	stats_cg->default_groups = kmalloc(sizeof(struct config_group *) * 2,
 				GFP_KERNEL);
 	if (!stats_cg->default_groups) {
 		pr_err("Unable to allocate memory for"
 				" stats_cg->default_groups\n");
-		core_tpg_del_initiator_node_acl(se_tpg, se_nacl, 1);
-		kfree(acl);
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 	}
 
 	stats_cg->default_groups[0] = &acl->node_stat_grps.iscsi_sess_stats_group;
@@ -918,13 +879,11 @@
 	config_group_init_type_name(&acl->node_stat_grps.iscsi_sess_stats_group,
 			"iscsi_sess_stats", &iscsi_stat_sess_cit);
 
-	return se_nacl;
+	return 0;
 }
 
-static void lio_target_drop_nodeacl(
-	struct se_node_acl *se_nacl)
+static void lio_target_cleanup_nodeacl( struct se_node_acl *se_nacl)
 {
-	struct se_portal_group *se_tpg = se_nacl->se_tpg;
 	struct iscsi_node_acl *acl = container_of(se_nacl,
 			struct iscsi_node_acl, se_node_acl);
 	struct config_item *df_item;
@@ -938,9 +897,6 @@
 		config_item_put(df_item);
 	}
 	kfree(stats_cg->default_groups);
-
-	core_tpg_del_initiator_node_acl(se_tpg, se_nacl, 1);
-	kfree(acl);
 }
 
 /* End items for lio_target_acl_cit */
@@ -1463,8 +1419,7 @@
 	if (!tpg)
 		return NULL;
 
-	ret = core_tpg_register(&iscsi_ops, wwn, &tpg->tpg_se_tpg,
-				tpg, TRANSPORT_TPG_TYPE_NORMAL);
+	ret = core_tpg_register(wwn, &tpg->tpg_se_tpg, SCSI_PROTOCOL_ISCSI);
 	if (ret < 0)
 		return NULL;
 
@@ -1735,14 +1690,6 @@
 	return "iSCSI";
 }
 
-static u32 iscsi_get_task_tag(struct se_cmd *se_cmd)
-{
-	struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd);
-
-	/* only used for printks or comparism with ->ref_task_tag */
-	return (__force u32)cmd->init_task_tag;
-}
-
 static int iscsi_get_cmd_state(struct se_cmd *se_cmd)
 {
 	struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd);
@@ -1832,78 +1779,58 @@
 	cmd->conn->conn_transport->iscsit_aborted_task(cmd->conn, cmd);
 }
 
+static inline struct iscsi_portal_group *iscsi_tpg(struct se_portal_group *se_tpg)
+{
+	return container_of(se_tpg, struct iscsi_portal_group, tpg_se_tpg);
+}
+
 static char *lio_tpg_get_endpoint_wwn(struct se_portal_group *se_tpg)
 {
-	struct iscsi_portal_group *tpg = se_tpg->se_tpg_fabric_ptr;
-
-	return &tpg->tpg_tiqn->tiqn[0];
+	return iscsi_tpg(se_tpg)->tpg_tiqn->tiqn;
 }
 
 static u16 lio_tpg_get_tag(struct se_portal_group *se_tpg)
 {
-	struct iscsi_portal_group *tpg = se_tpg->se_tpg_fabric_ptr;
-
-	return tpg->tpgt;
+	return iscsi_tpg(se_tpg)->tpgt;
 }
 
 static u32 lio_tpg_get_default_depth(struct se_portal_group *se_tpg)
 {
-	struct iscsi_portal_group *tpg = se_tpg->se_tpg_fabric_ptr;
-
-	return tpg->tpg_attrib.default_cmdsn_depth;
+	return iscsi_tpg(se_tpg)->tpg_attrib.default_cmdsn_depth;
 }
 
 static int lio_tpg_check_demo_mode(struct se_portal_group *se_tpg)
 {
-	struct iscsi_portal_group *tpg = se_tpg->se_tpg_fabric_ptr;
-
-	return tpg->tpg_attrib.generate_node_acls;
+	return iscsi_tpg(se_tpg)->tpg_attrib.generate_node_acls;
 }
 
 static int lio_tpg_check_demo_mode_cache(struct se_portal_group *se_tpg)
 {
-	struct iscsi_portal_group *tpg = se_tpg->se_tpg_fabric_ptr;
-
-	return tpg->tpg_attrib.cache_dynamic_acls;
+	return iscsi_tpg(se_tpg)->tpg_attrib.cache_dynamic_acls;
 }
 
 static int lio_tpg_check_demo_mode_write_protect(
 	struct se_portal_group *se_tpg)
 {
-	struct iscsi_portal_group *tpg = se_tpg->se_tpg_fabric_ptr;
-
-	return tpg->tpg_attrib.demo_mode_write_protect;
+	return iscsi_tpg(se_tpg)->tpg_attrib.demo_mode_write_protect;
 }
 
 static int lio_tpg_check_prod_mode_write_protect(
 	struct se_portal_group *se_tpg)
 {
-	struct iscsi_portal_group *tpg = se_tpg->se_tpg_fabric_ptr;
-
-	return tpg->tpg_attrib.prod_mode_write_protect;
+	return iscsi_tpg(se_tpg)->tpg_attrib.prod_mode_write_protect;
 }
 
 static int lio_tpg_check_prot_fabric_only(
 	struct se_portal_group *se_tpg)
 {
-	struct iscsi_portal_group *tpg = se_tpg->se_tpg_fabric_ptr;
 	/*
 	 * Only report fabric_prot_type if t10_pi has also been enabled
 	 * for incoming ib_isert sessions.
 	 */
-	if (!tpg->tpg_attrib.t10_pi)
+	if (!iscsi_tpg(se_tpg)->tpg_attrib.t10_pi)
 		return 0;
-
-	return tpg->tpg_attrib.fabric_prot_type;
-}
-
-static void lio_tpg_release_fabric_acl(
-	struct se_portal_group *se_tpg,
-	struct se_node_acl *se_acl)
-{
-	struct iscsi_node_acl *acl = container_of(se_acl,
-				struct iscsi_node_acl, se_node_acl);
-	kfree(acl);
+	return iscsi_tpg(se_tpg)->tpg_attrib.fabric_prot_type;
 }
 
 /*
@@ -1948,9 +1875,7 @@
 
 static u32 lio_tpg_get_inst_index(struct se_portal_group *se_tpg)
 {
-	struct iscsi_portal_group *tpg = se_tpg->se_tpg_fabric_ptr;
-
-	return tpg->tpg_tiqn->tiqn_index;
+	return iscsi_tpg(se_tpg)->tpg_tiqn->tiqn_index;
 }
 
 static void lio_set_default_node_attributes(struct se_node_acl *se_acl)
@@ -1967,7 +1892,7 @@
 
 static int lio_check_stop_free(struct se_cmd *se_cmd)
 {
-	return target_put_sess_cmd(se_cmd->se_sess, se_cmd);
+	return target_put_sess_cmd(se_cmd);
 }
 
 static void lio_release_cmd(struct se_cmd *se_cmd)
@@ -1981,14 +1906,11 @@
 const struct target_core_fabric_ops iscsi_ops = {
 	.module				= THIS_MODULE,
 	.name				= "iscsi",
+	.node_acl_size			= sizeof(struct iscsi_node_acl),
 	.get_fabric_name		= iscsi_get_fabric_name,
-	.get_fabric_proto_ident		= iscsi_get_fabric_proto_ident,
 	.tpg_get_wwn			= lio_tpg_get_endpoint_wwn,
 	.tpg_get_tag			= lio_tpg_get_tag,
 	.tpg_get_default_depth		= lio_tpg_get_default_depth,
-	.tpg_get_pr_transport_id	= iscsi_get_pr_transport_id,
-	.tpg_get_pr_transport_id_len	= iscsi_get_pr_transport_id_len,
-	.tpg_parse_pr_out_transport_id	= iscsi_parse_pr_out_transport_id,
 	.tpg_check_demo_mode		= lio_tpg_check_demo_mode,
 	.tpg_check_demo_mode_cache	= lio_tpg_check_demo_mode_cache,
 	.tpg_check_demo_mode_write_protect =
@@ -1996,8 +1918,6 @@
 	.tpg_check_prod_mode_write_protect =
 			lio_tpg_check_prod_mode_write_protect,
 	.tpg_check_prot_fabric_only	= &lio_tpg_check_prot_fabric_only,
-	.tpg_alloc_fabric_acl		= lio_tpg_alloc_fabric_acl,
-	.tpg_release_fabric_acl		= lio_tpg_release_fabric_acl,
 	.tpg_get_inst_index		= lio_tpg_get_inst_index,
 	.check_stop_free		= lio_check_stop_free,
 	.release_cmd			= lio_release_cmd,
@@ -2008,7 +1928,6 @@
 	.write_pending			= lio_write_pending,
 	.write_pending_status		= lio_write_pending_status,
 	.set_default_node_attributes	= lio_set_default_node_attributes,
-	.get_task_tag			= iscsi_get_task_tag,
 	.get_cmd_state			= iscsi_get_cmd_state,
 	.queue_data_in			= lio_queue_data_in,
 	.queue_status			= lio_queue_status,
@@ -2020,8 +1939,8 @@
 	.fabric_drop_tpg		= lio_target_tiqn_deltpg,
 	.fabric_make_np			= lio_target_call_addnptotpg,
 	.fabric_drop_np			= lio_target_call_delnpfromtpg,
-	.fabric_make_nodeacl		= lio_target_make_nodeacl,
-	.fabric_drop_nodeacl		= lio_target_drop_nodeacl,
+	.fabric_init_nodeacl		= lio_target_init_nodeacl,
+	.fabric_cleanup_nodeacl		= lio_target_cleanup_nodeacl,
 
 	.tfc_discovery_attrs		= lio_target_discovery_auth_attrs,
 	.tfc_wwn_attrs			= lio_target_wwn_attrs,
diff --git a/drivers/target/iscsi/iscsi_target_erl0.c b/drivers/target/iscsi/iscsi_target_erl0.c
index 959a14c..210f6e4 100644
--- a/drivers/target/iscsi/iscsi_target_erl0.c
+++ b/drivers/target/iscsi/iscsi_target_erl0.c
@@ -956,56 +956,3 @@
 
 	iscsit_handle_connection_cleanup(conn);
 }
-
-/*
- *	This is the simple function that makes the magic of
- *	sync and steering happen in the follow paradoxical order:
- *
- *	0) Receive conn->of_marker (bytes left until next OFMarker)
- *	   bytes into an offload buffer.  When we pass the exact number
- *	   of bytes in conn->of_marker, iscsit_dump_data_payload() and hence
- *	   rx_data() will automatically receive the identical u32 marker
- *	   values and store it in conn->of_marker_offset;
- *	1) Now conn->of_marker_offset will contain the offset to the start
- *	   of the next iSCSI PDU.  Dump these remaining bytes into another
- *	   offload buffer.
- *	2) We are done!
- *	   Next byte in the TCP stream will contain the next iSCSI PDU!
- *	   Cool Huh?!
- */
-int iscsit_recover_from_unknown_opcode(struct iscsi_conn *conn)
-{
-	/*
-	 * Make sure the remaining bytes to next maker is a sane value.
-	 */
-	if (conn->of_marker > (conn->conn_ops->OFMarkInt * 4)) {
-		pr_err("Remaining bytes to OFMarker: %u exceeds"
-			" OFMarkInt bytes: %u.\n", conn->of_marker,
-				conn->conn_ops->OFMarkInt * 4);
-		return -1;
-	}
-
-	pr_debug("Advancing %u bytes in TCP stream to get to the"
-			" next OFMarker.\n", conn->of_marker);
-
-	if (iscsit_dump_data_payload(conn, conn->of_marker, 0) < 0)
-		return -1;
-
-	/*
-	 * Make sure the offset marker we retrived is a valid value.
-	 */
-	if (conn->of_marker_offset > (ISCSI_HDR_LEN + (ISCSI_CRC_LEN * 2) +
-	    conn->conn_ops->MaxRecvDataSegmentLength)) {
-		pr_err("OfMarker offset value: %u exceeds limit.\n",
-			conn->of_marker_offset);
-		return -1;
-	}
-
-	pr_debug("Discarding %u bytes of TCP stream to get to the"
-			" next iSCSI Opcode.\n", conn->of_marker_offset);
-
-	if (iscsit_dump_data_payload(conn, conn->of_marker_offset, 0) < 0)
-		return -1;
-
-	return 0;
-}
diff --git a/drivers/target/iscsi/iscsi_target_erl0.h b/drivers/target/iscsi/iscsi_target_erl0.h
index 21acc9a..a9e2f94 100644
--- a/drivers/target/iscsi/iscsi_target_erl0.h
+++ b/drivers/target/iscsi/iscsi_target_erl0.h
@@ -10,6 +10,5 @@
 extern void iscsit_cause_connection_reinstatement(struct iscsi_conn *, int);
 extern void iscsit_fall_back_to_erl0(struct iscsi_session *);
 extern void iscsit_take_action_for_connection_exit(struct iscsi_conn *);
-extern int iscsit_recover_from_unknown_opcode(struct iscsi_conn *);
 
 #endif   /*** ISCSI_TARGET_ERL0_H ***/
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 70d799d..3d0fe4f 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -410,8 +410,6 @@
 	if (iscsi_change_param_sprintf(conn, "ErrorRecoveryLevel=%d", na->default_erl))
 		return -1;
 
-	if (iscsi_login_disable_FIM_keys(conn->param_list, conn) < 0)
-		return -1;
 	/*
 	 * Set RDMAExtensions=Yes by default for iSER enabled network portals
 	 */
@@ -477,59 +475,6 @@
 	return 0;
 }
 
-/*
- * Remove PSTATE_NEGOTIATE for the four FIM related keys.
- * The Initiator node will be able to enable FIM by proposing them itself.
- */
-int iscsi_login_disable_FIM_keys(
-	struct iscsi_param_list *param_list,
-	struct iscsi_conn *conn)
-{
-	struct iscsi_param *param;
-
-	param = iscsi_find_param_from_key("OFMarker", param_list);
-	if (!param) {
-		pr_err("iscsi_find_param_from_key() for"
-				" OFMarker failed\n");
-		iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
-				ISCSI_LOGIN_STATUS_NO_RESOURCES);
-		return -1;
-	}
-	param->state &= ~PSTATE_NEGOTIATE;
-
-	param = iscsi_find_param_from_key("OFMarkInt", param_list);
-	if (!param) {
-		pr_err("iscsi_find_param_from_key() for"
-				" IFMarker failed\n");
-		iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
-				ISCSI_LOGIN_STATUS_NO_RESOURCES);
-		return -1;
-	}
-	param->state &= ~PSTATE_NEGOTIATE;
-
-	param = iscsi_find_param_from_key("IFMarker", param_list);
-	if (!param) {
-		pr_err("iscsi_find_param_from_key() for"
-				" IFMarker failed\n");
-		iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
-				ISCSI_LOGIN_STATUS_NO_RESOURCES);
-		return -1;
-	}
-	param->state &= ~PSTATE_NEGOTIATE;
-
-	param = iscsi_find_param_from_key("IFMarkInt", param_list);
-	if (!param) {
-		pr_err("iscsi_find_param_from_key() for"
-				" IFMarker failed\n");
-		iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
-				ISCSI_LOGIN_STATUS_NO_RESOURCES);
-		return -1;
-	}
-	param->state &= ~PSTATE_NEGOTIATE;
-
-	return 0;
-}
-
 static int iscsi_login_non_zero_tsih_s1(
 	struct iscsi_conn *conn,
 	unsigned char *buf)
@@ -616,7 +561,7 @@
 	if (iscsi_change_param_sprintf(conn, "TargetPortalGroupTag=%hu", sess->tpg->tpgt))
 		return -1;
 
-	return iscsi_login_disable_FIM_keys(conn->param_list, conn);
+	return 0;
 }
 
 int iscsi_login_post_auth_non_zero_tsih(
@@ -765,7 +710,6 @@
 	conn->conn_state = TARG_CONN_STATE_LOGGED_IN;
 
 	iscsi_set_connection_parameters(conn->conn_ops, conn->param_list);
-	iscsit_set_sync_and_steering_values(conn);
 	/*
 	 * SCSI Initiator -> SCSI Target Port Mapping
 	 */
diff --git a/drivers/target/iscsi/iscsi_target_login.h b/drivers/target/iscsi/iscsi_target_login.h
index 29d0983..1c73580 100644
--- a/drivers/target/iscsi/iscsi_target_login.h
+++ b/drivers/target/iscsi/iscsi_target_login.h
@@ -16,6 +16,5 @@
 extern void iscsi_target_login_sess_out(struct iscsi_conn *, struct iscsi_np *,
 				bool, bool);
 extern int iscsi_target_login_thread(void *);
-extern int iscsi_login_disable_FIM_keys(struct iscsi_param_list *, struct iscsi_conn *);
 
 #endif   /*** ISCSI_TARGET_LOGIN_H ***/
diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c
index d4f9e96..e8a52f7 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.c
+++ b/drivers/target/iscsi/iscsi_target_parameters.c
@@ -34,13 +34,6 @@
 	iov.iov_len	= length;
 	iov.iov_base	= buf;
 
-	/*
-	 * Initial Marker-less Interval.
-	 * Add the values regardless of IFMarker/OFMarker, considering
-	 * it may not be negoitated yet.
-	 */
-	conn->of_marker += length;
-
 	rx_got = rx_data(conn, &iov, 1, length);
 	if (rx_got != length) {
 		pr_err("rx_data returned %d, expecting %d.\n",
@@ -72,13 +65,6 @@
 		iov_cnt++;
 	}
 
-	/*
-	 * Initial Marker-less Interval.
-	 * Add the values regardless of IFMarker/OFMarker, considering
-	 * it may not be negoitated yet.
-	 */
-	conn->if_marker += length;
-
 	tx_sent = tx_data(conn, &iov[0], iov_cnt, length);
 	if (tx_sent != length) {
 		pr_err("tx_data returned %d, expecting %d.\n",
@@ -97,12 +83,6 @@
 				"CRC32C" : "None");
 	pr_debug("MaxRecvDataSegmentLength: %u\n",
 				conn_ops->MaxRecvDataSegmentLength);
-	pr_debug("OFMarker: %s\n", (conn_ops->OFMarker) ? "Yes" : "No");
-	pr_debug("IFMarker: %s\n", (conn_ops->IFMarker) ? "Yes" : "No");
-	if (conn_ops->OFMarker)
-		pr_debug("OFMarkInt: %u\n", conn_ops->OFMarkInt);
-	if (conn_ops->IFMarker)
-		pr_debug("IFMarkInt: %u\n", conn_ops->IFMarkInt);
 }
 
 void iscsi_dump_sess_ops(struct iscsi_sess_ops *sess_ops)
@@ -194,10 +174,6 @@
 	case TYPERANGE_DIGEST:
 		param->type = TYPE_VALUE_LIST | TYPE_STRING;
 		break;
-	case TYPERANGE_MARKINT:
-		param->type = TYPE_NUMBER_RANGE;
-		param->type_range |= TYPERANGE_1_TO_65535;
-		break;
 	case TYPERANGE_ISCSINAME:
 	case TYPERANGE_SESSIONTYPE:
 	case TYPERANGE_TARGETADDRESS:
@@ -422,13 +398,13 @@
 
 	param = iscsi_set_default_param(pl, IFMARKINT, INITIAL_IFMARKINT,
 			PHASE_OPERATIONAL, SCOPE_CONNECTION_ONLY, SENDER_BOTH,
-			TYPERANGE_MARKINT, USE_INITIAL_ONLY);
+			TYPERANGE_UTF8, USE_INITIAL_ONLY);
 	if (!param)
 		goto out;
 
 	param = iscsi_set_default_param(pl, OFMARKINT, INITIAL_OFMARKINT,
 			PHASE_OPERATIONAL, SCOPE_CONNECTION_ONLY, SENDER_BOTH,
-			TYPERANGE_MARKINT, USE_INITIAL_ONLY);
+			TYPERANGE_UTF8, USE_INITIAL_ONLY);
 	if (!param)
 		goto out;
 	/*
@@ -524,9 +500,9 @@
 		} else if (!strcmp(param->name, OFMARKER)) {
 			SET_PSTATE_NEGOTIATE(param);
 		} else if (!strcmp(param->name, IFMARKINT)) {
-			SET_PSTATE_NEGOTIATE(param);
+			SET_PSTATE_REJECT(param);
 		} else if (!strcmp(param->name, OFMARKINT)) {
-			SET_PSTATE_NEGOTIATE(param);
+			SET_PSTATE_REJECT(param);
 		} else if (!strcmp(param->name, RDMAEXTENSIONS)) {
 			if (iser)
 				SET_PSTATE_NEGOTIATE(param);
@@ -906,91 +882,6 @@
 	return 0;
 }
 
-static int iscsi_check_numerical_range_value(struct iscsi_param *param, char *value)
-{
-	char *left_val_ptr = NULL, *right_val_ptr = NULL;
-	char *tilde_ptr = NULL;
-	u32 left_val, right_val, local_left_val;
-
-	if (strcmp(param->name, IFMARKINT) &&
-	    strcmp(param->name, OFMARKINT)) {
-		pr_err("Only parameters \"%s\" or \"%s\" may contain a"
-		       " numerical range value.\n", IFMARKINT, OFMARKINT);
-		return -1;
-	}
-
-	if (IS_PSTATE_PROPOSER(param))
-		return 0;
-
-	tilde_ptr = strchr(value, '~');
-	if (!tilde_ptr) {
-		pr_err("Unable to locate numerical range indicator"
-			" \"~\" for \"%s\".\n", param->name);
-		return -1;
-	}
-	*tilde_ptr = '\0';
-
-	left_val_ptr = value;
-	right_val_ptr = value + strlen(left_val_ptr) + 1;
-
-	if (iscsi_check_numerical_value(param, left_val_ptr) < 0)
-		return -1;
-	if (iscsi_check_numerical_value(param, right_val_ptr) < 0)
-		return -1;
-
-	left_val = simple_strtoul(left_val_ptr, NULL, 0);
-	right_val = simple_strtoul(right_val_ptr, NULL, 0);
-	*tilde_ptr = '~';
-
-	if (right_val < left_val) {
-		pr_err("Numerical range for parameter \"%s\" contains"
-			" a right value which is less than the left.\n",
-				param->name);
-		return -1;
-	}
-
-	/*
-	 * For now,  enforce reasonable defaults for [I,O]FMarkInt.
-	 */
-	tilde_ptr = strchr(param->value, '~');
-	if (!tilde_ptr) {
-		pr_err("Unable to locate numerical range indicator"
-			" \"~\" for \"%s\".\n", param->name);
-		return -1;
-	}
-	*tilde_ptr = '\0';
-
-	left_val_ptr = param->value;
-	right_val_ptr = param->value + strlen(left_val_ptr) + 1;
-
-	local_left_val = simple_strtoul(left_val_ptr, NULL, 0);
-	*tilde_ptr = '~';
-
-	if (param->set_param) {
-		if ((left_val < local_left_val) ||
-		    (right_val < local_left_val)) {
-			pr_err("Passed value range \"%u~%u\" is below"
-				" minimum left value \"%u\" for key \"%s\","
-				" rejecting.\n", left_val, right_val,
-				local_left_val, param->name);
-			return -1;
-		}
-	} else {
-		if ((left_val < local_left_val) &&
-		    (right_val < local_left_val)) {
-			pr_err("Received value range \"%u~%u\" is"
-				" below minimum left value \"%u\" for key"
-				" \"%s\", rejecting.\n", left_val, right_val,
-				local_left_val, param->name);
-			SET_PSTATE_REJECT(param);
-			if (iscsi_update_param_value(param, REJECT) < 0)
-				return -1;
-		}
-	}
-
-	return 0;
-}
-
 static int iscsi_check_string_or_list_value(struct iscsi_param *param, char *value)
 {
 	if (IS_PSTATE_PROPOSER(param))
@@ -1027,33 +918,6 @@
 	return 0;
 }
 
-/*
- *	This function is used to pick a value range number,  currently just
- *	returns the lesser of both right values.
- */
-static char *iscsi_get_value_from_number_range(
-	struct iscsi_param *param,
-	char *value)
-{
-	char *end_ptr, *tilde_ptr1 = NULL, *tilde_ptr2 = NULL;
-	u32 acceptor_right_value, proposer_right_value;
-
-	tilde_ptr1 = strchr(value, '~');
-	if (!tilde_ptr1)
-		return NULL;
-	*tilde_ptr1++ = '\0';
-	proposer_right_value = simple_strtoul(tilde_ptr1, &end_ptr, 0);
-
-	tilde_ptr2 = strchr(param->value, '~');
-	if (!tilde_ptr2)
-		return NULL;
-	*tilde_ptr2++ = '\0';
-	acceptor_right_value = simple_strtoul(tilde_ptr2, &end_ptr, 0);
-
-	return (acceptor_right_value >= proposer_right_value) ?
-		tilde_ptr1 : tilde_ptr2;
-}
-
 static char *iscsi_check_valuelist_for_support(
 	struct iscsi_param *param,
 	char *value)
@@ -1103,7 +967,7 @@
 				struct iscsi_conn *conn)
 {
 	u8 acceptor_boolean_value = 0, proposer_boolean_value = 0;
-	char *negoitated_value = NULL;
+	char *negotiated_value = NULL;
 
 	if (IS_PSTATE_ACCEPTOR(param)) {
 		pr_err("Received key \"%s\" twice, protocol error.\n",
@@ -1203,24 +1067,16 @@
 			pr_debug("Updated %s to target MXDSL value: %s\n",
 					param->name, param->value);
 		}
-
-	} else if (IS_TYPE_NUMBER_RANGE(param)) {
-		negoitated_value = iscsi_get_value_from_number_range(
-					param, value);
-		if (!negoitated_value)
-			return -1;
-		if (iscsi_update_param_value(param, negoitated_value) < 0)
-			return -1;
 	} else if (IS_TYPE_VALUE_LIST(param)) {
-		negoitated_value = iscsi_check_valuelist_for_support(
+		negotiated_value = iscsi_check_valuelist_for_support(
 					param, value);
-		if (!negoitated_value) {
+		if (!negotiated_value) {
 			pr_err("Proposer's value list \"%s\" contains"
 				" no valid values from Acceptor's value list"
 				" \"%s\".\n", value, param->value);
 			return -1;
 		}
-		if (iscsi_update_param_value(param, negoitated_value) < 0)
+		if (iscsi_update_param_value(param, negotiated_value) < 0)
 			return -1;
 	} else if (IS_PHASE_DECLARATIVE(param)) {
 		if (iscsi_update_param_value(param, value) < 0)
@@ -1239,47 +1095,7 @@
 		return -1;
 	}
 
-	if (IS_TYPE_NUMBER_RANGE(param)) {
-		u32 left_val = 0, right_val = 0, recieved_value = 0;
-		char *left_val_ptr = NULL, *right_val_ptr = NULL;
-		char *tilde_ptr = NULL;
-
-		if (!strcmp(value, IRRELEVANT) || !strcmp(value, REJECT)) {
-			if (iscsi_update_param_value(param, value) < 0)
-				return -1;
-			return 0;
-		}
-
-		tilde_ptr = strchr(value, '~');
-		if (tilde_ptr) {
-			pr_err("Illegal \"~\" in response for \"%s\".\n",
-					param->name);
-			return -1;
-		}
-		tilde_ptr = strchr(param->value, '~');
-		if (!tilde_ptr) {
-			pr_err("Unable to locate numerical range"
-				" indicator \"~\" for \"%s\".\n", param->name);
-			return -1;
-		}
-		*tilde_ptr = '\0';
-
-		left_val_ptr = param->value;
-		right_val_ptr = param->value + strlen(left_val_ptr) + 1;
-		left_val = simple_strtoul(left_val_ptr, NULL, 0);
-		right_val = simple_strtoul(right_val_ptr, NULL, 0);
-		recieved_value = simple_strtoul(value, NULL, 0);
-
-		*tilde_ptr = '~';
-
-		if ((recieved_value < left_val) ||
-		    (recieved_value > right_val)) {
-			pr_err("Illegal response \"%s=%u\", value must"
-				" be between %u and %u.\n", param->name,
-				recieved_value, left_val, right_val);
-			return -1;
-		}
-	} else if (IS_TYPE_VALUE_LIST(param)) {
+	if (IS_TYPE_VALUE_LIST(param)) {
 		char *comma_ptr = NULL, *tmp_ptr = NULL;
 
 		comma_ptr = strchr(value, ',');
@@ -1361,9 +1177,6 @@
 		} else if (IS_TYPE_NUMBER(param)) {
 			if (iscsi_check_numerical_value(param, value) < 0)
 				return -1;
-		} else if (IS_TYPE_NUMBER_RANGE(param)) {
-			if (iscsi_check_numerical_range_value(param, value) < 0)
-				return -1;
 		} else if (IS_TYPE_STRING(param) || IS_TYPE_VALUE_LIST(param)) {
 			if (iscsi_check_string_or_list_value(param, value) < 0)
 				return -1;
@@ -1483,8 +1296,6 @@
 	char *tmpptr;
 	u8 DataSequenceInOrder = 0;
 	u8 ErrorRecoveryLevel = 0, SessionType = 0;
-	u8 IFMarker = 0, OFMarker = 0;
-	u8 IFMarkInt_Reject = 1, OFMarkInt_Reject = 1;
 	u32 FirstBurstLength = 0, MaxBurstLength = 0;
 	struct iscsi_param *param = NULL;
 
@@ -1503,28 +1314,12 @@
 		if (!strcmp(param->name, MAXBURSTLENGTH))
 			MaxBurstLength = simple_strtoul(param->value,
 					&tmpptr, 0);
-		if (!strcmp(param->name, IFMARKER))
-			if (!strcmp(param->value, YES))
-				IFMarker = 1;
-		if (!strcmp(param->name, OFMARKER))
-			if (!strcmp(param->value, YES))
-				OFMarker = 1;
-		if (!strcmp(param->name, IFMARKINT))
-			if (!strcmp(param->value, REJECT))
-				IFMarkInt_Reject = 1;
-		if (!strcmp(param->name, OFMARKINT))
-			if (!strcmp(param->value, REJECT))
-				OFMarkInt_Reject = 1;
 	}
 
 	list_for_each_entry(param, &param_list->param_list, p_list) {
 		if (!(param->phase & phase))
 			continue;
-		if (!SessionType && (!IS_PSTATE_ACCEPTOR(param) &&
-		     (strcmp(param->name, IFMARKER) &&
-		      strcmp(param->name, OFMARKER) &&
-		      strcmp(param->name, IFMARKINT) &&
-		      strcmp(param->name, OFMARKINT))))
+		if (!SessionType && !IS_PSTATE_ACCEPTOR(param))
 			continue;
 		if (!strcmp(param->name, MAXOUTSTANDINGR2T) &&
 		    DataSequenceInOrder && (ErrorRecoveryLevel > 0)) {
@@ -1556,38 +1351,6 @@
 					param->name, param->value);
 			}
 		}
-		if (!strcmp(param->name, IFMARKER) && IFMarkInt_Reject) {
-			if (iscsi_update_param_value(param, NO) < 0)
-				return -1;
-			IFMarker = 0;
-			pr_debug("Reset \"%s\" to \"%s\".\n",
-					param->name, param->value);
-		}
-		if (!strcmp(param->name, OFMARKER) && OFMarkInt_Reject) {
-			if (iscsi_update_param_value(param, NO) < 0)
-				return -1;
-			OFMarker = 0;
-			pr_debug("Reset \"%s\" to \"%s\".\n",
-					 param->name, param->value);
-		}
-		if (!strcmp(param->name, IFMARKINT) && !IFMarker) {
-			if (!strcmp(param->value, REJECT))
-				continue;
-			param->state &= ~PSTATE_NEGOTIATE;
-			if (iscsi_update_param_value(param, IRRELEVANT) < 0)
-				return -1;
-			pr_debug("Reset \"%s\" to \"%s\".\n",
-					param->name, param->value);
-		}
-		if (!strcmp(param->name, OFMARKINT) && !OFMarker) {
-			if (!strcmp(param->value, REJECT))
-				continue;
-			param->state &= ~PSTATE_NEGOTIATE;
-			if (iscsi_update_param_value(param, IRRELEVANT) < 0)
-				return -1;
-			pr_debug("Reset \"%s\" to \"%s\".\n",
-					param->name, param->value);
-		}
 	}
 
 	return 0;
@@ -1824,24 +1587,6 @@
 			 */
 			pr_debug("MaxRecvDataSegmentLength:     %u\n",
 				ops->MaxRecvDataSegmentLength);
-		} else if (!strcmp(param->name, OFMARKER)) {
-			ops->OFMarker = !strcmp(param->value, YES);
-			pr_debug("OFMarker:                     %s\n",
-				param->value);
-		} else if (!strcmp(param->name, IFMARKER)) {
-			ops->IFMarker = !strcmp(param->value, YES);
-			pr_debug("IFMarker:                     %s\n",
-				param->value);
-		} else if (!strcmp(param->name, OFMARKINT)) {
-			ops->OFMarkInt =
-				simple_strtoul(param->value, &tmpptr, 0);
-			pr_debug("OFMarkInt:                    %s\n",
-				param->value);
-		} else if (!strcmp(param->name, IFMARKINT)) {
-			ops->IFMarkInt =
-				simple_strtoul(param->value, &tmpptr, 0);
-			pr_debug("IFMarkInt:                    %s\n",
-				param->value);
 		} else if (!strcmp(param->name, INITIATORRECVDATASEGMENTLENGTH)) {
 			ops->InitiatorRecvDataSegmentLength =
 				simple_strtoul(param->value, &tmpptr, 0);
diff --git a/drivers/target/iscsi/iscsi_target_parameters.h b/drivers/target/iscsi/iscsi_target_parameters.h
index a47046a..a0751e3 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.h
+++ b/drivers/target/iscsi/iscsi_target_parameters.h
@@ -138,8 +138,8 @@
 #define INITIAL_SESSIONTYPE			NORMAL
 #define INITIAL_IFMARKER			NO
 #define INITIAL_OFMARKER			NO
-#define INITIAL_IFMARKINT			"2048~65535"
-#define INITIAL_OFMARKINT			"2048~65535"
+#define INITIAL_IFMARKINT			REJECT
+#define INITIAL_OFMARKINT			REJECT
 
 /*
  * Initial values for iSER parameters following RFC-5046 Section 6
@@ -239,10 +239,9 @@
 #define TYPERANGE_AUTH			0x0200
 #define TYPERANGE_DIGEST		0x0400
 #define TYPERANGE_ISCSINAME		0x0800
-#define TYPERANGE_MARKINT		0x1000
-#define TYPERANGE_SESSIONTYPE		0x2000
-#define TYPERANGE_TARGETADDRESS		0x4000
-#define TYPERANGE_UTF8			0x8000
+#define TYPERANGE_SESSIONTYPE		0x1000
+#define TYPERANGE_TARGETADDRESS		0x2000
+#define TYPERANGE_UTF8			0x4000
 
 #define IS_TYPERANGE_0_TO_2(p)		((p)->type_range & TYPERANGE_0_TO_2)
 #define IS_TYPERANGE_0_TO_3600(p)	((p)->type_range & TYPERANGE_0_TO_3600)
diff --git a/drivers/target/iscsi/iscsi_target_tmr.c b/drivers/target/iscsi/iscsi_target_tmr.c
index fe9a582..cf59c39 100644
--- a/drivers/target/iscsi/iscsi_target_tmr.c
+++ b/drivers/target/iscsi/iscsi_target_tmr.c
@@ -120,7 +120,7 @@
 	struct iscsi_tmr_req *tmr_req = cmd->tmr_req;
 	struct se_tmr_req *se_tmr = cmd->se_cmd.se_tmr_req;
 	struct iscsi_tm *hdr = (struct iscsi_tm *) buf;
-	int ret, ref_lun;
+	u64 ret, ref_lun;
 
 	pr_debug("Got TASK_REASSIGN TMR ITT: 0x%08x,"
 		" RefTaskTag: 0x%08x, ExpDataSN: 0x%08x, CID: %hu\n",
@@ -164,7 +164,7 @@
 	ref_lun = scsilun_to_int(&hdr->lun);
 	if (ref_lun != ref_cmd->se_cmd.orig_fe_lun) {
 		pr_err("Unable to perform connection recovery for"
-			" differing ref_lun: %d ref_cmd orig_fe_lun: %u\n",
+			" differing ref_lun: %llu ref_cmd orig_fe_lun: %llu\n",
 			ref_lun, ref_cmd->se_cmd.orig_fe_lun);
 		return ISCSI_TMF_RSP_REJECTED;
 	}
diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c
index 5e3295f..968068f 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.c
+++ b/drivers/target/iscsi/iscsi_target_tpg.c
@@ -18,7 +18,6 @@
 
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
-#include <target/target_core_configfs.h>
 
 #include <target/iscsi/iscsi_target_core.h>
 #include "iscsi_target_erl0.h"
@@ -67,9 +66,12 @@
 		pr_err("Unable to allocate struct iscsi_portal_group\n");
 		return -1;
 	}
-
-	ret = core_tpg_register(&iscsi_ops, NULL, &tpg->tpg_se_tpg,
-				tpg, TRANSPORT_TPG_TYPE_DISCOVERY);
+	/*
+	 * Save iscsi_ops pointer for special case discovery TPG that
+	 * doesn't exist as se_wwn->wwn_group within configfs.
+	 */
+	tpg->tpg_se_tpg.se_tpg_tfo = &iscsi_ops;
+	ret = core_tpg_register(NULL, &tpg->tpg_se_tpg, -1);
 	if (ret < 0) {
 		kfree(tpg);
 		return -1;
@@ -280,8 +282,6 @@
 		return -EPERM;
 	}
 
-	core_tpg_clear_object_luns(&tpg->tpg_se_tpg);
-
 	if (tpg->param_list) {
 		iscsi_release_param_list(tpg->param_list);
 		tpg->param_list = NULL;
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index b18edda..a2bff07 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -22,7 +22,6 @@
 #include <scsi/iscsi_proto.h>
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
-#include <target/target_core_configfs.h>
 #include <target/iscsi/iscsi_transport.h>
 
 #include <target/iscsi/iscsi_target_core.h>
@@ -746,7 +745,7 @@
 		rc = transport_generic_free_cmd(&cmd->se_cmd, shutdown);
 		if (!rc && shutdown && se_cmd && se_cmd->se_sess) {
 			__iscsit_free_cmd(cmd, true, shutdown);
-			target_put_sess_cmd(se_cmd->se_sess, se_cmd);
+			target_put_sess_cmd(se_cmd);
 		}
 		break;
 	case ISCSI_OP_REJECT:
@@ -762,7 +761,7 @@
 			rc = transport_generic_free_cmd(&cmd->se_cmd, shutdown);
 			if (!rc && shutdown && se_cmd->se_sess) {
 				__iscsit_free_cmd(cmd, true, shutdown);
-				target_put_sess_cmd(se_cmd->se_sess, se_cmd);
+				target_put_sess_cmd(se_cmd);
 			}
 			break;
 		}
@@ -809,54 +808,6 @@
 	spin_unlock_bh(&sess->session_usage_lock);
 }
 
-/*
- *	Setup conn->if_marker and conn->of_marker values based upon
- *	the initial marker-less interval. (see iSCSI v19 A.2)
- */
-int iscsit_set_sync_and_steering_values(struct iscsi_conn *conn)
-{
-	int login_ifmarker_count = 0, login_ofmarker_count = 0, next_marker = 0;
-	/*
-	 * IFMarkInt and OFMarkInt are negotiated as 32-bit words.
-	 */
-	u32 IFMarkInt = (conn->conn_ops->IFMarkInt * 4);
-	u32 OFMarkInt = (conn->conn_ops->OFMarkInt * 4);
-
-	if (conn->conn_ops->OFMarker) {
-		/*
-		 * Account for the first Login Command received not
-		 * via iscsi_recv_msg().
-		 */
-		conn->of_marker += ISCSI_HDR_LEN;
-		if (conn->of_marker <= OFMarkInt) {
-			conn->of_marker = (OFMarkInt - conn->of_marker);
-		} else {
-			login_ofmarker_count = (conn->of_marker / OFMarkInt);
-			next_marker = (OFMarkInt * (login_ofmarker_count + 1)) +
-					(login_ofmarker_count * MARKER_SIZE);
-			conn->of_marker = (next_marker - conn->of_marker);
-		}
-		conn->of_marker_offset = 0;
-		pr_debug("Setting OFMarker value to %u based on Initial"
-			" Markerless Interval.\n", conn->of_marker);
-	}
-
-	if (conn->conn_ops->IFMarker) {
-		if (conn->if_marker <= IFMarkInt) {
-			conn->if_marker = (IFMarkInt - conn->if_marker);
-		} else {
-			login_ifmarker_count = (conn->if_marker / IFMarkInt);
-			next_marker = (IFMarkInt * (login_ifmarker_count + 1)) +
-					(login_ifmarker_count * MARKER_SIZE);
-			conn->if_marker = (next_marker - conn->if_marker);
-		}
-		pr_debug("Setting IFMarker value to %u based on Initial"
-			" Markerless Interval.\n", conn->if_marker);
-	}
-
-	return 0;
-}
-
 struct iscsi_conn *iscsit_get_conn_from_cid(struct iscsi_session *sess, u16 cid)
 {
 	struct iscsi_conn *conn;
diff --git a/drivers/target/iscsi/iscsi_target_util.h b/drivers/target/iscsi/iscsi_target_util.h
index 1ab754a..995f1cb 100644
--- a/drivers/target/iscsi/iscsi_target_util.h
+++ b/drivers/target/iscsi/iscsi_target_util.h
@@ -34,7 +34,6 @@
 extern int iscsit_check_session_usage_count(struct iscsi_session *);
 extern void iscsit_dec_session_usage_count(struct iscsi_session *);
 extern void iscsit_inc_session_usage_count(struct iscsi_session *);
-extern int iscsit_set_sync_and_steering_values(struct iscsi_conn *);
 extern struct iscsi_conn *iscsit_get_conn_from_cid(struct iscsi_session *, u16);
 extern struct iscsi_conn *iscsit_get_conn_from_cid_rcfr(struct iscsi_session *, u16);
 extern void iscsit_check_conn_usage_count(struct iscsi_conn *);
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index 51f0c89..a556bde 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -35,14 +35,11 @@
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
 #include <target/target_core_fabric_configfs.h>
-#include <target/target_core_configfs.h>
 
 #include "tcm_loop.h"
 
 #define to_tcm_loop_hba(hba)	container_of(hba, struct tcm_loop_hba, dev)
 
-static const struct target_core_fabric_ops loop_ops;
-
 static struct workqueue_struct *tcm_loop_workqueue;
 static struct kmem_cache *tcm_loop_cmd_cache;
 
@@ -165,6 +162,7 @@
 		transfer_length = scsi_bufflen(sc);
 	}
 
+	se_cmd->tag = tl_cmd->sc_cmd_tag;
 	rc = target_submit_cmd_map_sgls(se_cmd, tl_nexus->se_sess, sc->cmnd,
 			&tl_cmd->tl_sense_buf[0], tl_cmd->sc->device->lun,
 			transfer_length, TCM_SIMPLE_TAG,
@@ -217,7 +215,7 @@
  * to struct scsi_device
  */
 static int tcm_loop_issue_tmr(struct tcm_loop_tpg *tl_tpg,
-			      int lun, int task, enum tcm_tmreq_table tmr)
+			      u64 lun, int task, enum tcm_tmreq_table tmr)
 {
 	struct se_cmd *se_cmd = NULL;
 	struct se_session *se_sess;
@@ -409,7 +407,7 @@
 	sh->max_id = 2;
 	sh->max_lun = 0;
 	sh->max_channel = 0;
-	sh->max_cmd_len = TL_SCSI_MAX_CMD_LEN;
+	sh->max_cmd_len = SCSI_MAX_VARLEN_CDB_SIZE;
 
 	host_prot = SHOST_DIF_TYPE1_PROTECTION | SHOST_DIF_TYPE2_PROTECTION |
 		    SHOST_DIF_TYPE3_PROTECTION | SHOST_DIX_TYPE1_PROTECTION |
@@ -520,147 +518,26 @@
 	return "loopback";
 }
 
-static u8 tcm_loop_get_fabric_proto_ident(struct se_portal_group *se_tpg)
+static inline struct tcm_loop_tpg *tl_tpg(struct se_portal_group *se_tpg)
 {
-	struct tcm_loop_tpg *tl_tpg = se_tpg->se_tpg_fabric_ptr;
-	struct tcm_loop_hba *tl_hba = tl_tpg->tl_hba;
-	/*
-	 * tl_proto_id is set at tcm_loop_configfs.c:tcm_loop_make_scsi_hba()
-	 * time based on the protocol dependent prefix of the passed configfs group.
-	 *
-	 * Based upon tl_proto_id, TCM_Loop emulates the requested fabric
-	 * ProtocolID using target_core_fabric_lib.c symbols.
-	 */
-	switch (tl_hba->tl_proto_id) {
-	case SCSI_PROTOCOL_SAS:
-		return sas_get_fabric_proto_ident(se_tpg);
-	case SCSI_PROTOCOL_FCP:
-		return fc_get_fabric_proto_ident(se_tpg);
-	case SCSI_PROTOCOL_ISCSI:
-		return iscsi_get_fabric_proto_ident(se_tpg);
-	default:
-		pr_err("Unknown tl_proto_id: 0x%02x, using"
-			" SAS emulation\n", tl_hba->tl_proto_id);
-		break;
-	}
-
-	return sas_get_fabric_proto_ident(se_tpg);
+	return container_of(se_tpg, struct tcm_loop_tpg, tl_se_tpg);
 }
 
 static char *tcm_loop_get_endpoint_wwn(struct se_portal_group *se_tpg)
 {
-	struct tcm_loop_tpg *tl_tpg = se_tpg->se_tpg_fabric_ptr;
 	/*
 	 * Return the passed NAA identifier for the SAS Target Port
 	 */
-	return &tl_tpg->tl_hba->tl_wwn_address[0];
+	return &tl_tpg(se_tpg)->tl_hba->tl_wwn_address[0];
 }
 
 static u16 tcm_loop_get_tag(struct se_portal_group *se_tpg)
 {
-	struct tcm_loop_tpg *tl_tpg = se_tpg->se_tpg_fabric_ptr;
 	/*
 	 * This Tag is used when forming SCSI Name identifier in EVPD=1 0x83
 	 * to represent the SCSI Target Port.
 	 */
-	return tl_tpg->tl_tpgt;
-}
-
-static u32 tcm_loop_get_default_depth(struct se_portal_group *se_tpg)
-{
-	return 1;
-}
-
-static u32 tcm_loop_get_pr_transport_id(
-	struct se_portal_group *se_tpg,
-	struct se_node_acl *se_nacl,
-	struct t10_pr_registration *pr_reg,
-	int *format_code,
-	unsigned char *buf)
-{
-	struct tcm_loop_tpg *tl_tpg = se_tpg->se_tpg_fabric_ptr;
-	struct tcm_loop_hba *tl_hba = tl_tpg->tl_hba;
-
-	switch (tl_hba->tl_proto_id) {
-	case SCSI_PROTOCOL_SAS:
-		return sas_get_pr_transport_id(se_tpg, se_nacl, pr_reg,
-					format_code, buf);
-	case SCSI_PROTOCOL_FCP:
-		return fc_get_pr_transport_id(se_tpg, se_nacl, pr_reg,
-					format_code, buf);
-	case SCSI_PROTOCOL_ISCSI:
-		return iscsi_get_pr_transport_id(se_tpg, se_nacl, pr_reg,
-					format_code, buf);
-	default:
-		pr_err("Unknown tl_proto_id: 0x%02x, using"
-			" SAS emulation\n", tl_hba->tl_proto_id);
-		break;
-	}
-
-	return sas_get_pr_transport_id(se_tpg, se_nacl, pr_reg,
-			format_code, buf);
-}
-
-static u32 tcm_loop_get_pr_transport_id_len(
-	struct se_portal_group *se_tpg,
-	struct se_node_acl *se_nacl,
-	struct t10_pr_registration *pr_reg,
-	int *format_code)
-{
-	struct tcm_loop_tpg *tl_tpg = se_tpg->se_tpg_fabric_ptr;
-	struct tcm_loop_hba *tl_hba = tl_tpg->tl_hba;
-
-	switch (tl_hba->tl_proto_id) {
-	case SCSI_PROTOCOL_SAS:
-		return sas_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,
-					format_code);
-	case SCSI_PROTOCOL_FCP:
-		return fc_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,
-					format_code);
-	case SCSI_PROTOCOL_ISCSI:
-		return iscsi_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,
-					format_code);
-	default:
-		pr_err("Unknown tl_proto_id: 0x%02x, using"
-			" SAS emulation\n", tl_hba->tl_proto_id);
-		break;
-	}
-
-	return sas_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,
-			format_code);
-}
-
-/*
- * Used for handling SCSI fabric dependent TransportIDs in SPC-3 and above
- * Persistent Reservation SPEC_I_PT=1 and PROUT REGISTER_AND_MOVE operations.
- */
-static char *tcm_loop_parse_pr_out_transport_id(
-	struct se_portal_group *se_tpg,
-	const char *buf,
-	u32 *out_tid_len,
-	char **port_nexus_ptr)
-{
-	struct tcm_loop_tpg *tl_tpg = se_tpg->se_tpg_fabric_ptr;
-	struct tcm_loop_hba *tl_hba = tl_tpg->tl_hba;
-
-	switch (tl_hba->tl_proto_id) {
-	case SCSI_PROTOCOL_SAS:
-		return sas_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,
-					port_nexus_ptr);
-	case SCSI_PROTOCOL_FCP:
-		return fc_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,
-					port_nexus_ptr);
-	case SCSI_PROTOCOL_ISCSI:
-		return iscsi_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,
-					port_nexus_ptr);
-	default:
-		pr_err("Unknown tl_proto_id: 0x%02x, using"
-			" SAS emulation\n", tl_hba->tl_proto_id);
-		break;
-	}
-
-	return sas_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,
-			port_nexus_ptr);
+	return tl_tpg(se_tpg)->tl_tpgt;
 }
 
 /*
@@ -703,30 +580,6 @@
 	return tl_tpg->tl_fabric_prot_type;
 }
 
-static struct se_node_acl *tcm_loop_tpg_alloc_fabric_acl(
-	struct se_portal_group *se_tpg)
-{
-	struct tcm_loop_nacl *tl_nacl;
-
-	tl_nacl = kzalloc(sizeof(struct tcm_loop_nacl), GFP_KERNEL);
-	if (!tl_nacl) {
-		pr_err("Unable to allocate struct tcm_loop_nacl\n");
-		return NULL;
-	}
-
-	return &tl_nacl->se_node_acl;
-}
-
-static void tcm_loop_tpg_release_fabric_acl(
-	struct se_portal_group *se_tpg,
-	struct se_node_acl *se_nacl)
-{
-	struct tcm_loop_nacl *tl_nacl = container_of(se_nacl,
-				struct tcm_loop_nacl, se_node_acl);
-
-	kfree(tl_nacl);
-}
-
 static u32 tcm_loop_get_inst_index(struct se_portal_group *se_tpg)
 {
 	return 1;
@@ -742,14 +595,6 @@
 	return;
 }
 
-static u32 tcm_loop_get_task_tag(struct se_cmd *se_cmd)
-{
-	struct tcm_loop_cmd *tl_cmd = container_of(se_cmd,
-			struct tcm_loop_cmd, tl_se_cmd);
-
-	return tl_cmd->sc_cmd_tag;
-}
-
 static int tcm_loop_get_cmd_state(struct se_cmd *se_cmd)
 {
 	struct tcm_loop_cmd *tl_cmd = container_of(se_cmd,
@@ -902,7 +747,7 @@
 				se_lun->unpacked_lun);
 	if (!sd) {
 		pr_err("Unable to locate struct scsi_device for %d:%d:"
-			"%d\n", 0, tl_tpg->tl_tpgt, se_lun->unpacked_lun);
+			"%llu\n", 0, tl_tpg->tl_tpgt, se_lun->unpacked_lun);
 		return;
 	}
 	/*
@@ -1234,8 +1079,7 @@
 	/*
 	 * Register the tl_tpg as a emulated SAS TCM Target Endpoint
 	 */
-	ret = core_tpg_register(&loop_ops, wwn, &tl_tpg->tl_se_tpg, tl_tpg,
-			TRANSPORT_TPG_TYPE_NORMAL);
+	ret = core_tpg_register(wwn, &tl_tpg->tl_se_tpg, tl_hba->tl_proto_id);
 	if (ret < 0)
 		return ERR_PTR(-ENOMEM);
 
@@ -1386,13 +1230,8 @@
 	.module				= THIS_MODULE,
 	.name				= "loopback",
 	.get_fabric_name		= tcm_loop_get_fabric_name,
-	.get_fabric_proto_ident		= tcm_loop_get_fabric_proto_ident,
 	.tpg_get_wwn			= tcm_loop_get_endpoint_wwn,
 	.tpg_get_tag			= tcm_loop_get_tag,
-	.tpg_get_default_depth		= tcm_loop_get_default_depth,
-	.tpg_get_pr_transport_id	= tcm_loop_get_pr_transport_id,
-	.tpg_get_pr_transport_id_len	= tcm_loop_get_pr_transport_id_len,
-	.tpg_parse_pr_out_transport_id	= tcm_loop_parse_pr_out_transport_id,
 	.tpg_check_demo_mode		= tcm_loop_check_demo_mode,
 	.tpg_check_demo_mode_cache	= tcm_loop_check_demo_mode_cache,
 	.tpg_check_demo_mode_write_protect =
@@ -1400,8 +1239,6 @@
 	.tpg_check_prod_mode_write_protect =
 				tcm_loop_check_prod_mode_write_protect,
 	.tpg_check_prot_fabric_only	= tcm_loop_check_prot_fabric_only,
-	.tpg_alloc_fabric_acl		= tcm_loop_tpg_alloc_fabric_acl,
-	.tpg_release_fabric_acl		= tcm_loop_tpg_release_fabric_acl,
 	.tpg_get_inst_index		= tcm_loop_get_inst_index,
 	.check_stop_free		= tcm_loop_check_stop_free,
 	.release_cmd			= tcm_loop_release_cmd,
@@ -1411,7 +1248,6 @@
 	.write_pending			= tcm_loop_write_pending,
 	.write_pending_status		= tcm_loop_write_pending_status,
 	.set_default_node_attributes	= tcm_loop_set_default_node_attributes,
-	.get_task_tag			= tcm_loop_get_task_tag,
 	.get_cmd_state			= tcm_loop_get_cmd_state,
 	.queue_data_in			= tcm_loop_queue_data_in,
 	.queue_status			= tcm_loop_queue_status,
diff --git a/drivers/target/loopback/tcm_loop.h b/drivers/target/loopback/tcm_loop.h
index 1e72ff7..4346462 100644
--- a/drivers/target/loopback/tcm_loop.h
+++ b/drivers/target/loopback/tcm_loop.h
@@ -2,11 +2,6 @@
 #define TL_WWN_ADDR_LEN			256
 #define TL_TPGS_PER_HBA			32
 
-/*
- * Used in tcm_loop_driver_probe() for struct Scsi_Host->max_cmd_len
- */
-#define TL_SCSI_MAX_CMD_LEN		32
-
 struct tcm_loop_cmd {
 	/* State of Linux/SCSI CDB+Data descriptor */
 	u32 sc_cmd_state;
@@ -33,10 +28,6 @@
 	struct se_session *se_sess;
 };
 
-struct tcm_loop_nacl {
-	struct se_node_acl se_node_acl;
-};
-
 #define TCM_TRANSPORT_ONLINE 0
 #define TCM_TRANSPORT_OFFLINE 1
 
diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c
index ce81f17..0edf320 100644
--- a/drivers/target/sbp/sbp_target.c
+++ b/drivers/target/sbp/sbp_target.c
@@ -36,7 +36,6 @@
 #include <target/target_core_backend.h>
 #include <target/target_core_fabric.h>
 #include <target/target_core_fabric_configfs.h>
-#include <target/target_core_configfs.h>
 #include <target/configfs_macros.h>
 #include <asm/unaligned.h>
 
@@ -109,13 +108,13 @@
 }
 
 static struct sbp_login_descriptor *sbp_login_find_by_lun(
-		struct sbp_session *session, struct se_lun *lun)
+		struct sbp_session *session, u32 unpacked_lun)
 {
 	struct sbp_login_descriptor *login, *found = NULL;
 
 	spin_lock_bh(&session->lock);
 	list_for_each_entry(login, &session->login_list, link) {
-		if (login->lun == lun)
+		if (login->login_lun == unpacked_lun)
 			found = login;
 	}
 	spin_unlock_bh(&session->lock);
@@ -125,7 +124,7 @@
 
 static int sbp_login_count_all_by_lun(
 		struct sbp_tpg *tpg,
-		struct se_lun *lun,
+		u32 unpacked_lun,
 		int exclusive)
 {
 	struct se_session *se_sess;
@@ -139,7 +138,7 @@
 
 		spin_lock_bh(&sess->lock);
 		list_for_each_entry(login, &sess->login_list, link) {
-			if (login->lun != lun)
+			if (login->login_lun != unpacked_lun)
 				continue;
 
 			if (!exclusive || login->exclusive)
@@ -175,23 +174,23 @@
 	return found;
 }
 
-static struct se_lun *sbp_get_lun_from_tpg(struct sbp_tpg *tpg, int lun)
+static u32 sbp_get_lun_from_tpg(struct sbp_tpg *tpg, u32 login_lun, int *err)
 {
 	struct se_portal_group *se_tpg = &tpg->se_tpg;
 	struct se_lun *se_lun;
 
-	if (lun >= TRANSPORT_MAX_LUNS_PER_TPG)
-		return ERR_PTR(-EINVAL);
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(se_lun, &se_tpg->tpg_lun_hlist, link) {
+		if (se_lun->unpacked_lun == login_lun) {
+			rcu_read_unlock();
+			*err = 0;
+			return login_lun;
+		}
+	}
+	rcu_read_unlock();
 
-	spin_lock(&se_tpg->tpg_lun_lock);
-	se_lun = se_tpg->tpg_lun_list[lun];
-
-	if (se_lun->lun_status != TRANSPORT_LUN_STATUS_ACTIVE)
-		se_lun = ERR_PTR(-ENODEV);
-
-	spin_unlock(&se_tpg->tpg_lun_lock);
-
-	return se_lun;
+	*err = -ENODEV;
+	return login_lun;
 }
 
 static struct sbp_session *sbp_session_create(
@@ -295,17 +294,16 @@
 {
 	struct sbp_tport *tport = agent->tport;
 	struct sbp_tpg *tpg = tport->tpg;
-	struct se_lun *se_lun;
-	int ret;
-	u64 guid;
 	struct sbp_session *sess;
 	struct sbp_login_descriptor *login;
 	struct sbp_login_response_block *response;
-	int login_response_len;
+	u64 guid;
+	u32 unpacked_lun;
+	int login_response_len, ret;
 
-	se_lun = sbp_get_lun_from_tpg(tpg,
-			LOGIN_ORB_LUN(be32_to_cpu(req->orb.misc)));
-	if (IS_ERR(se_lun)) {
+	unpacked_lun = sbp_get_lun_from_tpg(tpg,
+			LOGIN_ORB_LUN(be32_to_cpu(req->orb.misc)), &ret);
+	if (ret) {
 		pr_notice("login to unknown LUN: %d\n",
 			LOGIN_ORB_LUN(be32_to_cpu(req->orb.misc)));
 
@@ -326,11 +324,11 @@
 	}
 
 	pr_notice("mgt_agent LOGIN to LUN %d from %016llx\n",
-		se_lun->unpacked_lun, guid);
+		unpacked_lun, guid);
 
 	sess = sbp_session_find_by_guid(tpg, guid);
 	if (sess) {
-		login = sbp_login_find_by_lun(sess, se_lun);
+		login = sbp_login_find_by_lun(sess, unpacked_lun);
 		if (login) {
 			pr_notice("initiator already logged-in\n");
 
@@ -358,7 +356,7 @@
 	 * reject with access_denied if any logins present
 	 */
 	if (LOGIN_ORB_EXCLUSIVE(be32_to_cpu(req->orb.misc)) &&
-			sbp_login_count_all_by_lun(tpg, se_lun, 0)) {
+			sbp_login_count_all_by_lun(tpg, unpacked_lun, 0)) {
 		pr_warn("refusing exclusive login with other active logins\n");
 
 		req->status.status = cpu_to_be32(
@@ -371,7 +369,7 @@
 	 * check exclusive bit in any existing login descriptor
 	 * reject with access_denied if any exclusive logins present
 	 */
-	if (sbp_login_count_all_by_lun(tpg, se_lun, 1)) {
+	if (sbp_login_count_all_by_lun(tpg, unpacked_lun, 1)) {
 		pr_warn("refusing login while another exclusive login present\n");
 
 		req->status.status = cpu_to_be32(
@@ -384,7 +382,7 @@
 	 * check we haven't exceeded the number of allowed logins
 	 * reject with resources_unavailable if we have
 	 */
-	if (sbp_login_count_all_by_lun(tpg, se_lun, 0) >=
+	if (sbp_login_count_all_by_lun(tpg, unpacked_lun, 0) >=
 			tport->max_logins_per_lun) {
 		pr_warn("max number of logins reached\n");
 
@@ -440,7 +438,7 @@
 	}
 
 	login->sess = sess;
-	login->lun = se_lun;
+	login->login_lun = unpacked_lun;
 	login->status_fifo_addr = sbp2_pointer_to_addr(&req->orb.status_fifo);
 	login->exclusive = LOGIN_ORB_EXCLUSIVE(be32_to_cpu(req->orb.misc));
 	login->login_id = atomic_inc_return(&login_id);
@@ -602,7 +600,7 @@
 	}
 
 	pr_info("mgt_agent LOGOUT from LUN %d session %d\n",
-		login->lun->unpacked_lun, login->login_id);
+		login->login_lun, login->login_id);
 
 	if (req->node_addr != login->sess->node_id) {
 		pr_warn("logout from different node ID\n");
@@ -1228,12 +1226,14 @@
 		goto err;
 	}
 
-	unpacked_lun = req->login->lun->unpacked_lun;
+	unpacked_lun = req->login->login_lun;
 	sbp_calc_data_length_direction(req, &data_length, &data_dir);
 
 	pr_debug("sbp_handle_command ORB:0x%llx unpacked_lun:%d data_len:%d data_dir:%d\n",
 			req->orb_pointer, unpacked_lun, data_length, data_dir);
 
+	/* only used for printk until we do TMRs */
+	req->se_cmd.tag = req->orb_pointer;
 	if (target_submit_cmd(&req->se_cmd, sess->se_sess, req->cmd_buf,
 			      req->sense_buf, unpacked_lun, data_length,
 			      TCM_SIMPLE_TAG, data_dir, 0))
@@ -1707,33 +1707,6 @@
 	return tpg->tport_tpgt;
 }
 
-static u32 sbp_get_default_depth(struct se_portal_group *se_tpg)
-{
-	return 1;
-}
-
-static struct se_node_acl *sbp_alloc_fabric_acl(struct se_portal_group *se_tpg)
-{
-	struct sbp_nacl *nacl;
-
-	nacl = kzalloc(sizeof(struct sbp_nacl), GFP_KERNEL);
-	if (!nacl) {
-		pr_err("Unable to allocate struct sbp_nacl\n");
-		return NULL;
-	}
-
-	return &nacl->se_node_acl;
-}
-
-static void sbp_release_fabric_acl(
-	struct se_portal_group *se_tpg,
-	struct se_node_acl *se_nacl)
-{
-	struct sbp_nacl *nacl =
-		container_of(se_nacl, struct sbp_nacl, se_node_acl);
-	kfree(nacl);
-}
-
 static u32 sbp_tpg_get_inst_index(struct se_portal_group *se_tpg)
 {
 	return 1;
@@ -1795,15 +1768,6 @@
 	return;
 }
 
-static u32 sbp_get_task_tag(struct se_cmd *se_cmd)
-{
-	struct sbp_target_request *req = container_of(se_cmd,
-			struct sbp_target_request, se_cmd);
-
-	/* only used for printk until we do TMRs */
-	return (u32)req->orb_pointer;
-}
-
 static int sbp_get_cmd_state(struct se_cmd *se_cmd)
 {
 	return 0;
@@ -1859,106 +1823,23 @@
 	return 1;
 }
 
-/*
- * Handlers for Serial Bus Protocol 2/3 (SBP-2 / SBP-3)
- */
-static u8 sbp_get_fabric_proto_ident(struct se_portal_group *se_tpg)
-{
-	/*
-	 * Return a IEEE 1394 SCSI Protocol identifier for loopback operations
-	 * This is defined in section 7.5.1 Table 362 in spc4r17
-	 */
-	return SCSI_PROTOCOL_SBP;
-}
-
-static u32 sbp_get_pr_transport_id(
-	struct se_portal_group *se_tpg,
-	struct se_node_acl *se_nacl,
-	struct t10_pr_registration *pr_reg,
-	int *format_code,
-	unsigned char *buf)
-{
-	int ret;
-
-	/*
-	 * Set PROTOCOL IDENTIFIER to 3h for SBP
-	 */
-	buf[0] = SCSI_PROTOCOL_SBP;
-	/*
-	 * From spc4r17, 7.5.4.4 TransportID for initiator ports using SCSI
-	 * over IEEE 1394
-	 */
-	ret = hex2bin(&buf[8], se_nacl->initiatorname, 8);
-	if (ret < 0)
-		pr_debug("sbp transport_id: invalid hex string\n");
-
-	/*
-	 * The IEEE 1394 Transport ID is a hardcoded 24-byte length
-	 */
-	return 24;
-}
-
-static u32 sbp_get_pr_transport_id_len(
-	struct se_portal_group *se_tpg,
-	struct se_node_acl *se_nacl,
-	struct t10_pr_registration *pr_reg,
-	int *format_code)
-{
-	*format_code = 0;
-	/*
-	 * From spc4r17, 7.5.4.4 TransportID for initiator ports using SCSI
-	 * over IEEE 1394
-	 *
-	 * The SBP Transport ID is a hardcoded 24-byte length
-	 */
-	return 24;
-}
-
-/*
- * Used for handling SCSI fabric dependent TransportIDs in SPC-3 and above
- * Persistent Reservation SPEC_I_PT=1 and PROUT REGISTER_AND_MOVE operations.
- */
-static char *sbp_parse_pr_out_transport_id(
-	struct se_portal_group *se_tpg,
-	const char *buf,
-	u32 *out_tid_len,
-	char **port_nexus_ptr)
-{
-	/*
-	 * Assume the FORMAT CODE 00b from spc4r17, 7.5.4.4 TransportID
-	 * for initiator ports using SCSI over SBP Serial SCSI Protocol
-	 *
-	 * The TransportID for a IEEE 1394 Initiator Port is of fixed size of
-	 * 24 bytes, and IEEE 1394 does not contain a I_T nexus identifier,
-	 * so we return the **port_nexus_ptr set to NULL.
-	 */
-	*port_nexus_ptr = NULL;
-	*out_tid_len = 24;
-
-	return (char *)&buf[8];
-}
-
 static int sbp_count_se_tpg_luns(struct se_portal_group *tpg)
 {
-	int i, count = 0;
+	struct se_lun *lun;
+	int count = 0;
 
-	spin_lock(&tpg->tpg_lun_lock);
-	for (i = 0; i < TRANSPORT_MAX_LUNS_PER_TPG; i++) {
-		struct se_lun *se_lun = tpg->tpg_lun_list[i];
-
-		if (se_lun->lun_status == TRANSPORT_LUN_STATUS_FREE)
-			continue;
-
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(lun, &tpg->tpg_lun_hlist, link)
 		count++;
-	}
-	spin_unlock(&tpg->tpg_lun_lock);
+	rcu_read_unlock();
 
 	return count;
 }
 
 static int sbp_update_unit_directory(struct sbp_tport *tport)
 {
-	int num_luns, num_entries, idx = 0, mgt_agt_addr, ret, i;
+	struct se_lun *lun;
+	int num_luns, num_entries, idx = 0, mgt_agt_addr, ret;
 	u32 *data;
 
 	if (tport->unit_directory.data) {
@@ -2020,28 +1901,23 @@
 	/* unit unique ID (leaf is just after LUNs) */
 	data[idx++] = 0x8d000000 | (num_luns + 1);
 
-	spin_lock(&tport->tpg->se_tpg.tpg_lun_lock);
-	for (i = 0; i < TRANSPORT_MAX_LUNS_PER_TPG; i++) {
-		struct se_lun *se_lun = tport->tpg->se_tpg.tpg_lun_list[i];
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(lun, &tport->tpg->se_tpg.tpg_lun_hlist, link) {
 		struct se_device *dev;
 		int type;
-
-		if (se_lun->lun_status == TRANSPORT_LUN_STATUS_FREE)
-			continue;
-
-		spin_unlock(&tport->tpg->se_tpg.tpg_lun_lock);
-
-		dev = se_lun->lun_se_dev;
+		/*
+		 * rcu_dereference_raw protected by se_lun->lun_group symlink
+		 * reference to se_device->dev_group.
+		 */
+		dev = rcu_dereference_raw(lun->lun_se_dev);
 		type = dev->transport->get_device_type(dev);
 
 		/* logical_unit_number */
 		data[idx++] = 0x14000000 |
 			((type << 16) & 0x1f0000) |
-			(se_lun->unpacked_lun & 0xffff);
-
-		spin_lock(&tport->tpg->se_tpg.tpg_lun_lock);
+			(lun->unpacked_lun & 0xffff);
 	}
-	spin_unlock(&tport->tpg->se_tpg.tpg_lun_lock);
+	rcu_read_unlock();
 
 	/* unit unique ID leaf */
 	data[idx++] = 2 << 16;
@@ -2100,48 +1976,13 @@
 	return snprintf(buf, len, "%016llx", wwn);
 }
 
-static struct se_node_acl *sbp_make_nodeacl(
-		struct se_portal_group *se_tpg,
-		struct config_group *group,
-		const char *name)
+static int sbp_init_nodeacl(struct se_node_acl *se_nacl, const char *name)
 {
-	struct se_node_acl *se_nacl, *se_nacl_new;
-	struct sbp_nacl *nacl;
 	u64 guid = 0;
-	u32 nexus_depth = 1;
 
 	if (sbp_parse_wwn(name, &guid) < 0)
-		return ERR_PTR(-EINVAL);
-
-	se_nacl_new = sbp_alloc_fabric_acl(se_tpg);
-	if (!se_nacl_new)
-		return ERR_PTR(-ENOMEM);
-
-	/*
-	 * se_nacl_new may be released by core_tpg_add_initiator_node_acl()
-	 * when converting a NodeACL from demo mode -> explict
-	 */
-	se_nacl = core_tpg_add_initiator_node_acl(se_tpg, se_nacl_new,
-			name, nexus_depth);
-	if (IS_ERR(se_nacl)) {
-		sbp_release_fabric_acl(se_tpg, se_nacl_new);
-		return se_nacl;
-	}
-
-	nacl = container_of(se_nacl, struct sbp_nacl, se_node_acl);
-	nacl->guid = guid;
-	sbp_format_wwn(nacl->iport_name, SBP_NAMELEN, guid);
-
-	return se_nacl;
-}
-
-static void sbp_drop_nodeacl(struct se_node_acl *se_acl)
-{
-	struct sbp_nacl *nacl =
-		container_of(se_acl, struct sbp_nacl, se_node_acl);
-
-	core_tpg_del_initiator_node_acl(se_acl->se_tpg, se_acl, 1);
-	kfree(nacl);
+		return -EINVAL;
+	return 0;
 }
 
 static int sbp_post_link_lun(
@@ -2214,8 +2055,7 @@
 		goto out_free_tpg;
 	}
 
-	ret = core_tpg_register(&sbp_ops, wwn, &tpg->se_tpg, tpg,
-			TRANSPORT_TPG_TYPE_NORMAL);
+	ret = core_tpg_register(wwn, &tpg->se_tpg, SCSI_PROTOCOL_SBP);
 	if (ret < 0)
 		goto out_unreg_mgt_agt;
 
@@ -2505,19 +2345,12 @@
 	.module				= THIS_MODULE,
 	.name				= "sbp",
 	.get_fabric_name		= sbp_get_fabric_name,
-	.get_fabric_proto_ident		= sbp_get_fabric_proto_ident,
 	.tpg_get_wwn			= sbp_get_fabric_wwn,
 	.tpg_get_tag			= sbp_get_tag,
-	.tpg_get_default_depth		= sbp_get_default_depth,
-	.tpg_get_pr_transport_id	= sbp_get_pr_transport_id,
-	.tpg_get_pr_transport_id_len	= sbp_get_pr_transport_id_len,
-	.tpg_parse_pr_out_transport_id	= sbp_parse_pr_out_transport_id,
 	.tpg_check_demo_mode		= sbp_check_true,
 	.tpg_check_demo_mode_cache	= sbp_check_true,
 	.tpg_check_demo_mode_write_protect = sbp_check_false,
 	.tpg_check_prod_mode_write_protect = sbp_check_false,
-	.tpg_alloc_fabric_acl		= sbp_alloc_fabric_acl,
-	.tpg_release_fabric_acl		= sbp_release_fabric_acl,
 	.tpg_get_inst_index		= sbp_tpg_get_inst_index,
 	.release_cmd			= sbp_release_cmd,
 	.shutdown_session		= sbp_shutdown_session,
@@ -2526,7 +2359,6 @@
 	.write_pending			= sbp_write_pending,
 	.write_pending_status		= sbp_write_pending_status,
 	.set_default_node_attributes	= sbp_set_default_node_attrs,
-	.get_task_tag			= sbp_get_task_tag,
 	.get_cmd_state			= sbp_get_cmd_state,
 	.queue_data_in			= sbp_queue_data_in,
 	.queue_status			= sbp_queue_status,
@@ -2542,8 +2374,7 @@
 	.fabric_pre_unlink		= sbp_pre_unlink_lun,
 	.fabric_make_np			= NULL,
 	.fabric_drop_np			= NULL,
-	.fabric_make_nodeacl		= sbp_make_nodeacl,
-	.fabric_drop_nodeacl		= sbp_drop_nodeacl,
+	.fabric_init_nodeacl		= sbp_init_nodeacl,
 
 	.tfc_wwn_attrs			= sbp_wwn_attrs,
 	.tfc_tpg_base_attrs		= sbp_tpg_base_attrs,
diff --git a/drivers/target/sbp/sbp_target.h b/drivers/target/sbp/sbp_target.h
index 6d0d74a..73bcb12 100644
--- a/drivers/target/sbp/sbp_target.h
+++ b/drivers/target/sbp/sbp_target.h
@@ -125,7 +125,7 @@
 	struct sbp_session *sess;
 	struct list_head link;
 
-	struct se_lun *lun;
+	u32 login_lun;
 
 	u64 status_fifo_addr;
 	int exclusive;
@@ -151,15 +151,6 @@
 	u64 reconnect_expires;
 };
 
-struct sbp_nacl {
-	/* Initiator EUI-64 */
-	u64 guid;
-	/* ASCII formatted GUID for SBP Initiator port */
-	char iport_name[SBP_NAMELEN];
-	/* Returned by sbp_make_nodeacl() */
-	struct se_node_acl se_node_acl;
-};
-
 struct sbp_tpg {
 	/* Target portal group tag for TCM */
 	u16 tport_tpgt;
diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index 8ca3737..49aba4a 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -34,7 +34,6 @@
 #include <target/target_core_base.h>
 #include <target/target_core_backend.h>
 #include <target/target_core_fabric.h>
-#include <target/target_core_configfs.h>
 
 #include "target_core_internal.h"
 #include "target_core_alua.h"
@@ -43,11 +42,13 @@
 static sense_reason_t core_alua_check_transition(int state, int valid,
 						 int *primary);
 static int core_alua_set_tg_pt_secondary_state(
-		struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem,
-		struct se_port *port, int explicit, int offline);
+		struct se_lun *lun, int explicit, int offline);
 
 static char *core_alua_dump_state(int state);
 
+static void __target_attach_tg_pt_gp(struct se_lun *lun,
+		struct t10_alua_tg_pt_gp *tg_pt_gp);
+
 static u16 alua_lu_gps_counter;
 static u32 alua_lu_gps_count;
 
@@ -145,9 +146,8 @@
 target_emulate_report_target_port_groups(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
-	struct se_port *port;
 	struct t10_alua_tg_pt_gp *tg_pt_gp;
-	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem;
+	struct se_lun *lun;
 	unsigned char *buf;
 	u32 rd_len = 0, off;
 	int ext_hdr = (cmd->t_task_cdb[1] & 0x20);
@@ -222,9 +222,8 @@
 		rd_len += 8;
 
 		spin_lock(&tg_pt_gp->tg_pt_gp_lock);
-		list_for_each_entry(tg_pt_gp_mem, &tg_pt_gp->tg_pt_gp_mem_list,
-				tg_pt_gp_mem_list) {
-			port = tg_pt_gp_mem->tg_pt;
+		list_for_each_entry(lun, &tg_pt_gp->tg_pt_gp_lun_list,
+				lun_tg_pt_gp_link) {
 			/*
 			 * Start Target Port descriptor format
 			 *
@@ -234,8 +233,8 @@
 			/*
 			 * Set RELATIVE TARGET PORT IDENTIFIER
 			 */
-			buf[off++] = ((port->sep_rtpi >> 8) & 0xff);
-			buf[off++] = (port->sep_rtpi & 0xff);
+			buf[off++] = ((lun->lun_rtpi >> 8) & 0xff);
+			buf[off++] = (lun->lun_rtpi & 0xff);
 			rd_len += 4;
 		}
 		spin_unlock(&tg_pt_gp->tg_pt_gp_lock);
@@ -259,15 +258,11 @@
 		 * this CDB was received upon to determine this value individually
 		 * for ALUA target port group.
 		 */
-		port = cmd->se_lun->lun_sep;
-		tg_pt_gp_mem = port->sep_alua_tg_pt_gp_mem;
-		if (tg_pt_gp_mem) {
-			spin_lock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
-			tg_pt_gp = tg_pt_gp_mem->tg_pt_gp;
-			if (tg_pt_gp)
-				buf[5] = tg_pt_gp->tg_pt_gp_implicit_trans_secs;
-			spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
-		}
+		spin_lock(&cmd->se_lun->lun_tg_pt_gp_lock);
+		tg_pt_gp = cmd->se_lun->lun_tg_pt_gp;
+		if (tg_pt_gp)
+			buf[5] = tg_pt_gp->tg_pt_gp_implicit_trans_secs;
+		spin_unlock(&cmd->se_lun->lun_tg_pt_gp_lock);
 	}
 	transport_kunmap_data_sg(cmd);
 
@@ -284,10 +279,9 @@
 target_emulate_set_target_port_groups(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
-	struct se_port *port, *l_port = cmd->se_lun->lun_sep;
+	struct se_lun *l_lun = cmd->se_lun;
 	struct se_node_acl *nacl = cmd->se_sess->se_node_acl;
 	struct t10_alua_tg_pt_gp *tg_pt_gp = NULL, *l_tg_pt_gp;
-	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem, *l_tg_pt_gp_mem;
 	unsigned char *buf;
 	unsigned char *ptr;
 	sense_reason_t rc = TCM_NO_SENSE;
@@ -295,9 +289,6 @@
 	int alua_access_state, primary = 0, valid_states;
 	u16 tg_pt_id, rtpi;
 
-	if (!l_port)
-		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-
 	if (cmd->data_length < 4) {
 		pr_warn("SET TARGET PORT GROUPS parameter list length %u too"
 			" small\n", cmd->data_length);
@@ -312,29 +303,24 @@
 	 * Determine if explicit ALUA via SET_TARGET_PORT_GROUPS is allowed
 	 * for the local tg_pt_gp.
 	 */
-	l_tg_pt_gp_mem = l_port->sep_alua_tg_pt_gp_mem;
-	if (!l_tg_pt_gp_mem) {
-		pr_err("Unable to access l_port->sep_alua_tg_pt_gp_mem\n");
-		rc = TCM_UNSUPPORTED_SCSI_OPCODE;
-		goto out;
-	}
-	spin_lock(&l_tg_pt_gp_mem->tg_pt_gp_mem_lock);
-	l_tg_pt_gp = l_tg_pt_gp_mem->tg_pt_gp;
+	spin_lock(&l_lun->lun_tg_pt_gp_lock);
+	l_tg_pt_gp = l_lun->lun_tg_pt_gp;
 	if (!l_tg_pt_gp) {
-		spin_unlock(&l_tg_pt_gp_mem->tg_pt_gp_mem_lock);
-		pr_err("Unable to access *l_tg_pt_gp_mem->tg_pt_gp\n");
+		spin_unlock(&l_lun->lun_tg_pt_gp_lock);
+		pr_err("Unable to access l_lun->tg_pt_gp\n");
 		rc = TCM_UNSUPPORTED_SCSI_OPCODE;
 		goto out;
 	}
-	spin_unlock(&l_tg_pt_gp_mem->tg_pt_gp_mem_lock);
 
 	if (!(l_tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_EXPLICIT_ALUA)) {
+		spin_unlock(&l_lun->lun_tg_pt_gp_lock);
 		pr_debug("Unable to process SET_TARGET_PORT_GROUPS"
 				" while TPGS_EXPLICIT_ALUA is disabled\n");
 		rc = TCM_UNSUPPORTED_SCSI_OPCODE;
 		goto out;
 	}
 	valid_states = l_tg_pt_gp->tg_pt_gp_alua_supported_states;
+	spin_unlock(&l_lun->lun_tg_pt_gp_lock);
 
 	ptr = &buf[4]; /* Skip over RESERVED area in header */
 
@@ -396,7 +382,7 @@
 				spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 
 				if (!core_alua_do_port_transition(tg_pt_gp,
-						dev, l_port, nacl,
+						dev, l_lun, nacl,
 						alua_access_state, 1))
 					found = true;
 
@@ -406,6 +392,8 @@
 			}
 			spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 		} else {
+			struct se_lun *lun;
+
 			/*
 			 * Extract the RELATIVE TARGET PORT IDENTIFIER to identify
 			 * the Target Port in question for the the incoming
@@ -417,17 +405,16 @@
 			 * for the struct se_device storage object.
 			 */
 			spin_lock(&dev->se_port_lock);
-			list_for_each_entry(port, &dev->dev_sep_list,
-							sep_list) {
-				if (port->sep_rtpi != rtpi)
+			list_for_each_entry(lun, &dev->dev_sep_list,
+							lun_dev_link) {
+				if (lun->lun_rtpi != rtpi)
 					continue;
 
-				tg_pt_gp_mem = port->sep_alua_tg_pt_gp_mem;
-
+				// XXX: racy unlock
 				spin_unlock(&dev->se_port_lock);
 
 				if (!core_alua_set_tg_pt_secondary_state(
-						tg_pt_gp_mem, port, 1, 1))
+						lun, 1, 1))
 					found = true;
 
 				spin_lock(&dev->se_port_lock);
@@ -696,9 +683,7 @@
 	struct se_device *dev = cmd->se_dev;
 	unsigned char *cdb = cmd->t_task_cdb;
 	struct se_lun *lun = cmd->se_lun;
-	struct se_port *port = lun->lun_sep;
 	struct t10_alua_tg_pt_gp *tg_pt_gp;
-	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem;
 	int out_alua_state, nonop_delay_msecs;
 
 	if (dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)
@@ -706,33 +691,27 @@
 	if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
 		return 0;
 
-	if (!port)
-		return 0;
 	/*
 	 * First, check for a struct se_port specific secondary ALUA target port
 	 * access state: OFFLINE
 	 */
-	if (atomic_read(&port->sep_tg_pt_secondary_offline)) {
+	if (atomic_read(&lun->lun_tg_pt_secondary_offline)) {
 		pr_debug("ALUA: Got secondary offline status for local"
 				" target port\n");
 		set_ascq(cmd, ASCQ_04H_ALUA_OFFLINE);
 		return TCM_CHECK_CONDITION_NOT_READY;
 	}
-	 /*
-	 * Second, obtain the struct t10_alua_tg_pt_gp_member pointer to the
-	 * ALUA target port group, to obtain current ALUA access state.
-	 * Otherwise look for the underlying struct se_device association with
-	 * a ALUA logical unit group.
-	 */
-	tg_pt_gp_mem = port->sep_alua_tg_pt_gp_mem;
-	if (!tg_pt_gp_mem)
+
+	if (!lun->lun_tg_pt_gp)
 		return 0;
 
-	spin_lock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
-	tg_pt_gp = tg_pt_gp_mem->tg_pt_gp;
+	spin_lock(&lun->lun_tg_pt_gp_lock);
+	tg_pt_gp = lun->lun_tg_pt_gp;
 	out_alua_state = atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state);
 	nonop_delay_msecs = tg_pt_gp->tg_pt_gp_nonop_delay_msecs;
-	spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
+
+	// XXX: keeps using tg_pt_gp witout reference after unlock
+	spin_unlock(&lun->lun_tg_pt_gp_lock);
 	/*
 	 * Process ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED in a separate conditional
 	 * statement so the compiler knows explicitly to check this case first.
@@ -764,7 +743,7 @@
 		break;
 	/*
 	 * OFFLINE is a secondary ALUA target port group access state, that is
-	 * handled above with struct se_port->sep_tg_pt_secondary_offline=1
+	 * handled above with struct se_lun->lun_tg_pt_secondary_offline=1
 	 */
 	case ALUA_ACCESS_STATE_OFFLINE:
 	default:
@@ -906,10 +885,6 @@
 }
 EXPORT_SYMBOL(core_alua_check_nonop_delay);
 
-/*
- * Called with tg_pt_gp->tg_pt_gp_md_mutex or tg_pt_gp_mem->sep_tg_pt_md_mutex
- *
- */
 static int core_alua_write_tpg_metadata(
 	const char *path,
 	unsigned char *md_buf,
@@ -965,22 +940,15 @@
 	return rc;
 }
 
-static void core_alua_do_transition_tg_pt_work(struct work_struct *work)
+static void core_alua_queue_state_change_ua(struct t10_alua_tg_pt_gp *tg_pt_gp)
 {
-	struct t10_alua_tg_pt_gp *tg_pt_gp = container_of(work,
-		struct t10_alua_tg_pt_gp, tg_pt_gp_transition_work.work);
-	struct se_device *dev = tg_pt_gp->tg_pt_gp_dev;
 	struct se_dev_entry *se_deve;
+	struct se_lun *lun;
 	struct se_lun_acl *lacl;
-	struct se_port *port;
-	struct t10_alua_tg_pt_gp_member *mem;
-	bool explicit = (tg_pt_gp->tg_pt_gp_alua_access_status ==
-			 ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG);
 
 	spin_lock(&tg_pt_gp->tg_pt_gp_lock);
-	list_for_each_entry(mem, &tg_pt_gp->tg_pt_gp_mem_list,
-				tg_pt_gp_mem_list) {
-		port = mem->tg_pt;
+	list_for_each_entry(lun, &tg_pt_gp->tg_pt_gp_lun_list,
+				lun_tg_pt_gp_link) {
 		/*
 		 * After an implicit target port asymmetric access state
 		 * change, a device server shall establish a unit attention
@@ -995,38 +963,58 @@
 		 * every I_T nexus other than the I_T nexus on which the SET
 		 * TARGET PORT GROUPS command
 		 */
-		atomic_inc_mb(&mem->tg_pt_gp_mem_ref_cnt);
+		if (!percpu_ref_tryget_live(&lun->lun_ref))
+			continue;
 		spin_unlock(&tg_pt_gp->tg_pt_gp_lock);
 
-		spin_lock_bh(&port->sep_alua_lock);
-		list_for_each_entry(se_deve, &port->sep_alua_list,
-					alua_port_list) {
-			lacl = se_deve->se_lun_acl;
+		spin_lock(&lun->lun_deve_lock);
+		list_for_each_entry(se_deve, &lun->lun_deve_list, lun_link) {
+			lacl = rcu_dereference_check(se_deve->se_lun_acl,
+					lockdep_is_held(&lun->lun_deve_lock));
+
+			/*
+			 * spc4r37 p.242:
+			 * After an explicit target port asymmetric access
+			 * state change, a device server shall establish a
+			 * unit attention condition with the additional sense
+			 * code set to ASYMMETRIC ACCESS STATE CHANGED for
+			 * the initiator port associated with every I_T nexus
+			 * other than the I_T nexus on which the SET TARGET
+			 * PORT GROUPS command was received.
+			 */
+			if ((tg_pt_gp->tg_pt_gp_alua_access_status ==
+			     ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG) &&
+			   (tg_pt_gp->tg_pt_gp_alua_lun != NULL) &&
+			    (tg_pt_gp->tg_pt_gp_alua_lun == lun))
+				continue;
+
 			/*
 			 * se_deve->se_lun_acl pointer may be NULL for a
 			 * entry created without explicit Node+MappedLUN ACLs
 			 */
-			if (!lacl)
+			if (lacl && (tg_pt_gp->tg_pt_gp_alua_nacl != NULL) &&
+			    (tg_pt_gp->tg_pt_gp_alua_nacl == lacl->se_lun_nacl))
 				continue;
 
-			if ((tg_pt_gp->tg_pt_gp_alua_access_status ==
-			     ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG) &&
-			   (tg_pt_gp->tg_pt_gp_alua_nacl != NULL) &&
-			    (tg_pt_gp->tg_pt_gp_alua_nacl == lacl->se_lun_nacl) &&
-			   (tg_pt_gp->tg_pt_gp_alua_port != NULL) &&
-			    (tg_pt_gp->tg_pt_gp_alua_port == port))
-				continue;
-
-			core_scsi3_ua_allocate(lacl->se_lun_nacl,
-				se_deve->mapped_lun, 0x2A,
+			core_scsi3_ua_allocate(se_deve, 0x2A,
 				ASCQ_2AH_ASYMMETRIC_ACCESS_STATE_CHANGED);
 		}
-		spin_unlock_bh(&port->sep_alua_lock);
+		spin_unlock(&lun->lun_deve_lock);
 
 		spin_lock(&tg_pt_gp->tg_pt_gp_lock);
-		atomic_dec_mb(&mem->tg_pt_gp_mem_ref_cnt);
+		percpu_ref_put(&lun->lun_ref);
 	}
 	spin_unlock(&tg_pt_gp->tg_pt_gp_lock);
+}
+
+static void core_alua_do_transition_tg_pt_work(struct work_struct *work)
+{
+	struct t10_alua_tg_pt_gp *tg_pt_gp = container_of(work,
+		struct t10_alua_tg_pt_gp, tg_pt_gp_transition_work.work);
+	struct se_device *dev = tg_pt_gp->tg_pt_gp_dev;
+	bool explicit = (tg_pt_gp->tg_pt_gp_alua_access_status ==
+			 ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG);
+
 	/*
 	 * Update the ALUA metadata buf that has been allocated in
 	 * core_alua_do_port_transition(), this metadata will be written
@@ -1056,6 +1044,9 @@
 		tg_pt_gp->tg_pt_gp_id,
 		core_alua_dump_state(tg_pt_gp->tg_pt_gp_alua_previous_state),
 		core_alua_dump_state(tg_pt_gp->tg_pt_gp_alua_pending_state));
+
+	core_alua_queue_state_change_ua(tg_pt_gp);
+
 	spin_lock(&dev->t10_alua.tg_pt_gps_lock);
 	atomic_dec(&tg_pt_gp->tg_pt_gp_ref_cnt);
 	spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
@@ -1108,6 +1099,8 @@
 				ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG :
 				ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA;
 
+	core_alua_queue_state_change_ua(tg_pt_gp);
+
 	/*
 	 * Check for the optional ALUA primary state transition delay
 	 */
@@ -1142,7 +1135,7 @@
 int core_alua_do_port_transition(
 	struct t10_alua_tg_pt_gp *l_tg_pt_gp,
 	struct se_device *l_dev,
-	struct se_port *l_port,
+	struct se_lun *l_lun,
 	struct se_node_acl *l_nacl,
 	int new_state,
 	int explicit)
@@ -1172,7 +1165,7 @@
 		 * core_alua_do_transition_tg_pt() will always return
 		 * success.
 		 */
-		l_tg_pt_gp->tg_pt_gp_alua_port = l_port;
+		l_tg_pt_gp->tg_pt_gp_alua_lun = l_lun;
 		l_tg_pt_gp->tg_pt_gp_alua_nacl = l_nacl;
 		rc = core_alua_do_transition_tg_pt(l_tg_pt_gp,
 						   new_state, explicit);
@@ -1211,10 +1204,10 @@
 				continue;
 
 			if (l_tg_pt_gp == tg_pt_gp) {
-				tg_pt_gp->tg_pt_gp_alua_port = l_port;
+				tg_pt_gp->tg_pt_gp_alua_lun = l_lun;
 				tg_pt_gp->tg_pt_gp_alua_nacl = l_nacl;
 			} else {
-				tg_pt_gp->tg_pt_gp_alua_port = NULL;
+				tg_pt_gp->tg_pt_gp_alua_lun = NULL;
 				tg_pt_gp->tg_pt_gp_alua_nacl = NULL;
 			}
 			atomic_inc_mb(&tg_pt_gp->tg_pt_gp_ref_cnt);
@@ -1251,22 +1244,20 @@
 	return rc;
 }
 
-/*
- * Called with tg_pt_gp_mem->sep_tg_pt_md_mutex held
- */
-static int core_alua_update_tpg_secondary_metadata(
-	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem,
-	struct se_port *port)
+static int core_alua_update_tpg_secondary_metadata(struct se_lun *lun)
 {
+	struct se_portal_group *se_tpg = lun->lun_tpg;
 	unsigned char *md_buf;
-	struct se_portal_group *se_tpg = port->sep_tpg;
 	char path[ALUA_METADATA_PATH_LEN], wwn[ALUA_SECONDARY_METADATA_WWN_LEN];
 	int len, rc;
 
+	mutex_lock(&lun->lun_tg_pt_md_mutex);
+
 	md_buf = kzalloc(ALUA_MD_BUF_LEN, GFP_KERNEL);
 	if (!md_buf) {
 		pr_err("Unable to allocate buf for ALUA metadata\n");
-		return -ENOMEM;
+		rc = -ENOMEM;
+		goto out_unlock;
 	}
 
 	memset(path, 0, ALUA_METADATA_PATH_LEN);
@@ -1281,32 +1272,33 @@
 
 	len = snprintf(md_buf, ALUA_MD_BUF_LEN, "alua_tg_pt_offline=%d\n"
 			"alua_tg_pt_status=0x%02x\n",
-			atomic_read(&port->sep_tg_pt_secondary_offline),
-			port->sep_tg_pt_secondary_stat);
+			atomic_read(&lun->lun_tg_pt_secondary_offline),
+			lun->lun_tg_pt_secondary_stat);
 
-	snprintf(path, ALUA_METADATA_PATH_LEN, "/var/target/alua/%s/%s/lun_%u",
+	snprintf(path, ALUA_METADATA_PATH_LEN, "/var/target/alua/%s/%s/lun_%llu",
 			se_tpg->se_tpg_tfo->get_fabric_name(), wwn,
-			port->sep_lun->unpacked_lun);
+			lun->unpacked_lun);
 
 	rc = core_alua_write_tpg_metadata(path, md_buf, len);
 	kfree(md_buf);
 
+out_unlock:
+	mutex_unlock(&lun->lun_tg_pt_md_mutex);
 	return rc;
 }
 
 static int core_alua_set_tg_pt_secondary_state(
-	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem,
-	struct se_port *port,
+	struct se_lun *lun,
 	int explicit,
 	int offline)
 {
 	struct t10_alua_tg_pt_gp *tg_pt_gp;
 	int trans_delay_msecs;
 
-	spin_lock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
-	tg_pt_gp = tg_pt_gp_mem->tg_pt_gp;
+	spin_lock(&lun->lun_tg_pt_gp_lock);
+	tg_pt_gp = lun->lun_tg_pt_gp;
 	if (!tg_pt_gp) {
-		spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
+		spin_unlock(&lun->lun_tg_pt_gp_lock);
 		pr_err("Unable to complete secondary state"
 				" transition\n");
 		return -EINVAL;
@@ -1314,14 +1306,14 @@
 	trans_delay_msecs = tg_pt_gp->tg_pt_gp_trans_delay_msecs;
 	/*
 	 * Set the secondary ALUA target port access state to OFFLINE
-	 * or release the previously secondary state for struct se_port
+	 * or release the previously secondary state for struct se_lun
 	 */
 	if (offline)
-		atomic_set(&port->sep_tg_pt_secondary_offline, 1);
+		atomic_set(&lun->lun_tg_pt_secondary_offline, 1);
 	else
-		atomic_set(&port->sep_tg_pt_secondary_offline, 0);
+		atomic_set(&lun->lun_tg_pt_secondary_offline, 0);
 
-	port->sep_tg_pt_secondary_stat = (explicit) ?
+	lun->lun_tg_pt_secondary_stat = (explicit) ?
 			ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG :
 			ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA;
 
@@ -1330,7 +1322,7 @@
 		"implicit", config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item),
 		tg_pt_gp->tg_pt_gp_id, (offline) ? "OFFLINE" : "ONLINE");
 
-	spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
+	spin_unlock(&lun->lun_tg_pt_gp_lock);
 	/*
 	 * Do the optional transition delay after we set the secondary
 	 * ALUA access state.
@@ -1341,11 +1333,8 @@
 	 * See if we need to update the ALUA fabric port metadata for
 	 * secondary state and status
 	 */
-	if (port->sep_tg_pt_secondary_write_md) {
-		mutex_lock(&port->sep_tg_pt_md_mutex);
-		core_alua_update_tpg_secondary_metadata(tg_pt_gp_mem, port);
-		mutex_unlock(&port->sep_tg_pt_md_mutex);
-	}
+	if (lun->lun_tg_pt_secondary_write_md)
+		core_alua_update_tpg_secondary_metadata(lun);
 
 	return 0;
 }
@@ -1699,7 +1688,7 @@
 		return NULL;
 	}
 	INIT_LIST_HEAD(&tg_pt_gp->tg_pt_gp_list);
-	INIT_LIST_HEAD(&tg_pt_gp->tg_pt_gp_mem_list);
+	INIT_LIST_HEAD(&tg_pt_gp->tg_pt_gp_lun_list);
 	mutex_init(&tg_pt_gp->tg_pt_gp_md_mutex);
 	spin_lock_init(&tg_pt_gp->tg_pt_gp_lock);
 	atomic_set(&tg_pt_gp->tg_pt_gp_ref_cnt, 0);
@@ -1793,32 +1782,11 @@
 	return 0;
 }
 
-struct t10_alua_tg_pt_gp_member *core_alua_allocate_tg_pt_gp_mem(
-	struct se_port *port)
-{
-	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem;
-
-	tg_pt_gp_mem = kmem_cache_zalloc(t10_alua_tg_pt_gp_mem_cache,
-				GFP_KERNEL);
-	if (!tg_pt_gp_mem) {
-		pr_err("Unable to allocate struct t10_alua_tg_pt_gp_member\n");
-		return ERR_PTR(-ENOMEM);
-	}
-	INIT_LIST_HEAD(&tg_pt_gp_mem->tg_pt_gp_mem_list);
-	spin_lock_init(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
-	atomic_set(&tg_pt_gp_mem->tg_pt_gp_mem_ref_cnt, 0);
-
-	tg_pt_gp_mem->tg_pt = port;
-	port->sep_alua_tg_pt_gp_mem = tg_pt_gp_mem;
-
-	return tg_pt_gp_mem;
-}
-
 void core_alua_free_tg_pt_gp(
 	struct t10_alua_tg_pt_gp *tg_pt_gp)
 {
 	struct se_device *dev = tg_pt_gp->tg_pt_gp_dev;
-	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem, *tg_pt_gp_mem_tmp;
+	struct se_lun *lun, *next;
 
 	/*
 	 * Once we have reached this point, config_item_put() has already
@@ -1849,30 +1817,24 @@
 	 * struct se_port.
 	 */
 	spin_lock(&tg_pt_gp->tg_pt_gp_lock);
-	list_for_each_entry_safe(tg_pt_gp_mem, tg_pt_gp_mem_tmp,
-			&tg_pt_gp->tg_pt_gp_mem_list, tg_pt_gp_mem_list) {
-		if (tg_pt_gp_mem->tg_pt_gp_assoc) {
-			list_del(&tg_pt_gp_mem->tg_pt_gp_mem_list);
-			tg_pt_gp->tg_pt_gp_members--;
-			tg_pt_gp_mem->tg_pt_gp_assoc = 0;
-		}
+	list_for_each_entry_safe(lun, next,
+			&tg_pt_gp->tg_pt_gp_lun_list, lun_tg_pt_gp_link) {
+		list_del_init(&lun->lun_tg_pt_gp_link);
+		tg_pt_gp->tg_pt_gp_members--;
+
 		spin_unlock(&tg_pt_gp->tg_pt_gp_lock);
 		/*
-		 * tg_pt_gp_mem is associated with a single
-		 * se_port->sep_alua_tg_pt_gp_mem, and is released via
-		 * core_alua_free_tg_pt_gp_mem().
-		 *
 		 * If the passed tg_pt_gp does NOT match the default_tg_pt_gp,
 		 * assume we want to re-associate a given tg_pt_gp_mem with
 		 * default_tg_pt_gp.
 		 */
-		spin_lock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
+		spin_lock(&lun->lun_tg_pt_gp_lock);
 		if (tg_pt_gp != dev->t10_alua.default_tg_pt_gp) {
-			__core_alua_attach_tg_pt_gp_mem(tg_pt_gp_mem,
+			__target_attach_tg_pt_gp(lun,
 					dev->t10_alua.default_tg_pt_gp);
 		} else
-			tg_pt_gp_mem->tg_pt_gp = NULL;
-		spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
+			lun->lun_tg_pt_gp = NULL;
+		spin_unlock(&lun->lun_tg_pt_gp_lock);
 
 		spin_lock(&tg_pt_gp->tg_pt_gp_lock);
 	}
@@ -1881,35 +1843,6 @@
 	kmem_cache_free(t10_alua_tg_pt_gp_cache, tg_pt_gp);
 }
 
-void core_alua_free_tg_pt_gp_mem(struct se_port *port)
-{
-	struct t10_alua_tg_pt_gp *tg_pt_gp;
-	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem;
-
-	tg_pt_gp_mem = port->sep_alua_tg_pt_gp_mem;
-	if (!tg_pt_gp_mem)
-		return;
-
-	while (atomic_read(&tg_pt_gp_mem->tg_pt_gp_mem_ref_cnt))
-		cpu_relax();
-
-	spin_lock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
-	tg_pt_gp = tg_pt_gp_mem->tg_pt_gp;
-	if (tg_pt_gp) {
-		spin_lock(&tg_pt_gp->tg_pt_gp_lock);
-		if (tg_pt_gp_mem->tg_pt_gp_assoc) {
-			list_del(&tg_pt_gp_mem->tg_pt_gp_mem_list);
-			tg_pt_gp->tg_pt_gp_members--;
-			tg_pt_gp_mem->tg_pt_gp_assoc = 0;
-		}
-		spin_unlock(&tg_pt_gp->tg_pt_gp_lock);
-		tg_pt_gp_mem->tg_pt_gp = NULL;
-	}
-	spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
-
-	kmem_cache_free(t10_alua_tg_pt_gp_mem_cache, tg_pt_gp_mem);
-}
-
 static struct t10_alua_tg_pt_gp *core_alua_get_tg_pt_gp_by_name(
 		struct se_device *dev, const char *name)
 {
@@ -1943,50 +1876,65 @@
 	spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 }
 
-/*
- * Called with struct t10_alua_tg_pt_gp_member->tg_pt_gp_mem_lock held
- */
-void __core_alua_attach_tg_pt_gp_mem(
-	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem,
-	struct t10_alua_tg_pt_gp *tg_pt_gp)
+static void __target_attach_tg_pt_gp(struct se_lun *lun,
+		struct t10_alua_tg_pt_gp *tg_pt_gp)
 {
+	struct se_dev_entry *se_deve;
+
+	assert_spin_locked(&lun->lun_tg_pt_gp_lock);
+
 	spin_lock(&tg_pt_gp->tg_pt_gp_lock);
-	tg_pt_gp_mem->tg_pt_gp = tg_pt_gp;
-	tg_pt_gp_mem->tg_pt_gp_assoc = 1;
-	list_add_tail(&tg_pt_gp_mem->tg_pt_gp_mem_list,
-			&tg_pt_gp->tg_pt_gp_mem_list);
+	lun->lun_tg_pt_gp = tg_pt_gp;
+	list_add_tail(&lun->lun_tg_pt_gp_link, &tg_pt_gp->tg_pt_gp_lun_list);
 	tg_pt_gp->tg_pt_gp_members++;
+	spin_lock(&lun->lun_deve_lock);
+	list_for_each_entry(se_deve, &lun->lun_deve_list, lun_link)
+		core_scsi3_ua_allocate(se_deve, 0x3f,
+				       ASCQ_3FH_INQUIRY_DATA_HAS_CHANGED);
+	spin_unlock(&lun->lun_deve_lock);
 	spin_unlock(&tg_pt_gp->tg_pt_gp_lock);
 }
 
-/*
- * Called with struct t10_alua_tg_pt_gp_member->tg_pt_gp_mem_lock held
- */
-static void __core_alua_drop_tg_pt_gp_mem(
-	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem,
-	struct t10_alua_tg_pt_gp *tg_pt_gp)
+void target_attach_tg_pt_gp(struct se_lun *lun,
+		struct t10_alua_tg_pt_gp *tg_pt_gp)
 {
+	spin_lock(&lun->lun_tg_pt_gp_lock);
+	__target_attach_tg_pt_gp(lun, tg_pt_gp);
+	spin_unlock(&lun->lun_tg_pt_gp_lock);
+}
+
+static void __target_detach_tg_pt_gp(struct se_lun *lun,
+		struct t10_alua_tg_pt_gp *tg_pt_gp)
+{
+	assert_spin_locked(&lun->lun_tg_pt_gp_lock);
+
 	spin_lock(&tg_pt_gp->tg_pt_gp_lock);
-	list_del(&tg_pt_gp_mem->tg_pt_gp_mem_list);
-	tg_pt_gp_mem->tg_pt_gp = NULL;
-	tg_pt_gp_mem->tg_pt_gp_assoc = 0;
+	list_del_init(&lun->lun_tg_pt_gp_link);
 	tg_pt_gp->tg_pt_gp_members--;
 	spin_unlock(&tg_pt_gp->tg_pt_gp_lock);
+
+	lun->lun_tg_pt_gp = NULL;
 }
 
-ssize_t core_alua_show_tg_pt_gp_info(struct se_port *port, char *page)
+void target_detach_tg_pt_gp(struct se_lun *lun)
+{
+	struct t10_alua_tg_pt_gp *tg_pt_gp;
+
+	spin_lock(&lun->lun_tg_pt_gp_lock);
+	tg_pt_gp = lun->lun_tg_pt_gp;
+	if (tg_pt_gp)
+		__target_detach_tg_pt_gp(lun, tg_pt_gp);
+	spin_unlock(&lun->lun_tg_pt_gp_lock);
+}
+
+ssize_t core_alua_show_tg_pt_gp_info(struct se_lun *lun, char *page)
 {
 	struct config_item *tg_pt_ci;
 	struct t10_alua_tg_pt_gp *tg_pt_gp;
-	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem;
 	ssize_t len = 0;
 
-	tg_pt_gp_mem = port->sep_alua_tg_pt_gp_mem;
-	if (!tg_pt_gp_mem)
-		return len;
-
-	spin_lock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
-	tg_pt_gp = tg_pt_gp_mem->tg_pt_gp;
+	spin_lock(&lun->lun_tg_pt_gp_lock);
+	tg_pt_gp = lun->lun_tg_pt_gp;
 	if (tg_pt_gp) {
 		tg_pt_ci = &tg_pt_gp->tg_pt_gp_group.cg_item;
 		len += sprintf(page, "TG Port Alias: %s\nTG Port Group ID:"
@@ -1998,34 +1946,33 @@
 					&tg_pt_gp->tg_pt_gp_alua_access_state)),
 			core_alua_dump_status(
 				tg_pt_gp->tg_pt_gp_alua_access_status),
-			(atomic_read(&port->sep_tg_pt_secondary_offline)) ?
+			atomic_read(&lun->lun_tg_pt_secondary_offline) ?
 			"Offline" : "None",
-			core_alua_dump_status(port->sep_tg_pt_secondary_stat));
+			core_alua_dump_status(lun->lun_tg_pt_secondary_stat));
 	}
-	spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
+	spin_unlock(&lun->lun_tg_pt_gp_lock);
 
 	return len;
 }
 
 ssize_t core_alua_store_tg_pt_gp_info(
-	struct se_port *port,
+	struct se_lun *lun,
 	const char *page,
 	size_t count)
 {
-	struct se_portal_group *tpg;
-	struct se_lun *lun;
-	struct se_device *dev = port->sep_lun->lun_se_dev;
+	struct se_portal_group *tpg = lun->lun_tpg;
+	/*
+	 * rcu_dereference_raw protected by se_lun->lun_group symlink
+	 * reference to se_device->dev_group.
+	 */
+	struct se_device *dev = rcu_dereference_raw(lun->lun_se_dev);
 	struct t10_alua_tg_pt_gp *tg_pt_gp = NULL, *tg_pt_gp_new = NULL;
-	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem;
 	unsigned char buf[TG_PT_GROUP_NAME_BUF];
 	int move = 0;
 
-	tpg = port->sep_tpg;
-	lun = port->sep_lun;
-
-	tg_pt_gp_mem = port->sep_alua_tg_pt_gp_mem;
-	if (!tg_pt_gp_mem)
-		return 0;
+	if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH ||
+	    (dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE))
+		return -ENODEV;
 
 	if (count > TG_PT_GROUP_NAME_BUF) {
 		pr_err("ALUA Target Port Group alias too large!\n");
@@ -2049,8 +1996,8 @@
 			return -ENODEV;
 	}
 
-	spin_lock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
-	tg_pt_gp = tg_pt_gp_mem->tg_pt_gp;
+	spin_lock(&lun->lun_tg_pt_gp_lock);
+	tg_pt_gp = lun->lun_tg_pt_gp;
 	if (tg_pt_gp) {
 		/*
 		 * Clearing an existing tg_pt_gp association, and replacing
@@ -2068,24 +2015,19 @@
 					&tg_pt_gp->tg_pt_gp_group.cg_item),
 				tg_pt_gp->tg_pt_gp_id);
 
-			__core_alua_drop_tg_pt_gp_mem(tg_pt_gp_mem, tg_pt_gp);
-			__core_alua_attach_tg_pt_gp_mem(tg_pt_gp_mem,
+			__target_detach_tg_pt_gp(lun, tg_pt_gp);
+			__target_attach_tg_pt_gp(lun,
 					dev->t10_alua.default_tg_pt_gp);
-			spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
+			spin_unlock(&lun->lun_tg_pt_gp_lock);
 
 			return count;
 		}
-		/*
-		 * Removing existing association of tg_pt_gp_mem with tg_pt_gp
-		 */
-		__core_alua_drop_tg_pt_gp_mem(tg_pt_gp_mem, tg_pt_gp);
+		__target_detach_tg_pt_gp(lun, tg_pt_gp);
 		move = 1;
 	}
-	/*
-	 * Associate tg_pt_gp_mem with tg_pt_gp_new.
-	 */
-	__core_alua_attach_tg_pt_gp_mem(tg_pt_gp_mem, tg_pt_gp_new);
-	spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
+
+	__target_attach_tg_pt_gp(lun, tg_pt_gp_new);
+	spin_unlock(&lun->lun_tg_pt_gp_lock);
 	pr_debug("Target_Core_ConfigFS: %s %s/tpgt_%hu/%s to ALUA"
 		" Target Port Group: alua/%s, ID: %hu\n", (move) ?
 		"Moving" : "Adding", tpg->se_tpg_tfo->tpg_get_wwn(tpg),
@@ -2268,11 +2210,8 @@
 
 ssize_t core_alua_show_offline_bit(struct se_lun *lun, char *page)
 {
-	if (!lun->lun_sep)
-		return -ENODEV;
-
 	return sprintf(page, "%d\n",
-		atomic_read(&lun->lun_sep->sep_tg_pt_secondary_offline));
+		atomic_read(&lun->lun_tg_pt_secondary_offline));
 }
 
 ssize_t core_alua_store_offline_bit(
@@ -2280,11 +2219,16 @@
 	const char *page,
 	size_t count)
 {
-	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem;
+	/*
+	 * rcu_dereference_raw protected by se_lun->lun_group symlink
+	 * reference to se_device->dev_group.
+	 */
+	struct se_device *dev = rcu_dereference_raw(lun->lun_se_dev);
 	unsigned long tmp;
 	int ret;
 
-	if (!lun->lun_sep)
+	if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH ||
+	    (dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE))
 		return -ENODEV;
 
 	ret = kstrtoul(page, 0, &tmp);
@@ -2297,14 +2241,8 @@
 				tmp);
 		return -EINVAL;
 	}
-	tg_pt_gp_mem = lun->lun_sep->sep_alua_tg_pt_gp_mem;
-	if (!tg_pt_gp_mem) {
-		pr_err("Unable to locate *tg_pt_gp_mem\n");
-		return -EINVAL;
-	}
 
-	ret = core_alua_set_tg_pt_secondary_state(tg_pt_gp_mem,
-			lun->lun_sep, 0, (int)tmp);
+	ret = core_alua_set_tg_pt_secondary_state(lun, 0, (int)tmp);
 	if (ret < 0)
 		return -EINVAL;
 
@@ -2315,7 +2253,7 @@
 	struct se_lun *lun,
 	char *page)
 {
-	return sprintf(page, "%d\n", lun->lun_sep->sep_tg_pt_secondary_stat);
+	return sprintf(page, "%d\n", lun->lun_tg_pt_secondary_stat);
 }
 
 ssize_t core_alua_store_secondary_status(
@@ -2338,7 +2276,7 @@
 				tmp);
 		return -EINVAL;
 	}
-	lun->lun_sep->sep_tg_pt_secondary_stat = (int)tmp;
+	lun->lun_tg_pt_secondary_stat = (int)tmp;
 
 	return count;
 }
@@ -2347,8 +2285,7 @@
 	struct se_lun *lun,
 	char *page)
 {
-	return sprintf(page, "%d\n",
-			lun->lun_sep->sep_tg_pt_secondary_write_md);
+	return sprintf(page, "%d\n", lun->lun_tg_pt_secondary_write_md);
 }
 
 ssize_t core_alua_store_secondary_write_metadata(
@@ -2369,7 +2306,7 @@
 				" %lu\n", tmp);
 		return -EINVAL;
 	}
-	lun->lun_sep->sep_tg_pt_secondary_write_md = (int)tmp;
+	lun->lun_tg_pt_secondary_write_md = (int)tmp;
 
 	return count;
 }
diff --git a/drivers/target/target_core_alua.h b/drivers/target/target_core_alua.h
index 0a7d65e..9b250f9 100644
--- a/drivers/target/target_core_alua.h
+++ b/drivers/target/target_core_alua.h
@@ -85,7 +85,6 @@
 extern struct kmem_cache *t10_alua_lu_gp_cache;
 extern struct kmem_cache *t10_alua_lu_gp_mem_cache;
 extern struct kmem_cache *t10_alua_tg_pt_gp_cache;
-extern struct kmem_cache *t10_alua_tg_pt_gp_mem_cache;
 extern struct kmem_cache *t10_alua_lba_map_cache;
 extern struct kmem_cache *t10_alua_lba_map_mem_cache;
 
@@ -94,7 +93,7 @@
 extern sense_reason_t target_emulate_report_referrals(struct se_cmd *);
 extern int core_alua_check_nonop_delay(struct se_cmd *);
 extern int core_alua_do_port_transition(struct t10_alua_tg_pt_gp *,
-				struct se_device *, struct se_port *,
+				struct se_device *, struct se_lun *,
 				struct se_node_acl *, int, int);
 extern char *core_alua_dump_status(int);
 extern struct t10_alua_lba_map *core_alua_allocate_lba_map(
@@ -117,14 +116,11 @@
 extern struct t10_alua_tg_pt_gp *core_alua_allocate_tg_pt_gp(
 			struct se_device *, const char *, int);
 extern int core_alua_set_tg_pt_gp_id(struct t10_alua_tg_pt_gp *, u16);
-extern struct t10_alua_tg_pt_gp_member *core_alua_allocate_tg_pt_gp_mem(
-					struct se_port *);
 extern void core_alua_free_tg_pt_gp(struct t10_alua_tg_pt_gp *);
-extern void core_alua_free_tg_pt_gp_mem(struct se_port *);
-extern void __core_alua_attach_tg_pt_gp_mem(struct t10_alua_tg_pt_gp_member *,
-					struct t10_alua_tg_pt_gp *);
-extern ssize_t core_alua_show_tg_pt_gp_info(struct se_port *, char *);
-extern ssize_t core_alua_store_tg_pt_gp_info(struct se_port *, const char *,
+extern void target_detach_tg_pt_gp(struct se_lun *);
+extern void target_attach_tg_pt_gp(struct se_lun *, struct t10_alua_tg_pt_gp *);
+extern ssize_t core_alua_show_tg_pt_gp_info(struct se_lun *, char *);
+extern ssize_t core_alua_store_tg_pt_gp_info(struct se_lun *, const char *,
 						size_t);
 extern ssize_t core_alua_show_access_type(struct t10_alua_tg_pt_gp *, char *);
 extern ssize_t core_alua_store_access_type(struct t10_alua_tg_pt_gp *,
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index e7b0430..0b0de36 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -41,7 +41,6 @@
 #include <target/target_core_backend.h>
 #include <target/target_core_fabric.h>
 #include <target/target_core_fabric_configfs.h>
-#include <target/target_core_configfs.h>
 #include <target/configfs_macros.h>
 
 #include "target_core_internal.h"
@@ -51,15 +50,26 @@
 #include "target_core_xcopy.h"
 
 #define TB_CIT_SETUP(_name, _item_ops, _group_ops, _attrs)		\
-static void target_core_setup_##_name##_cit(struct se_subsystem_api *sa) \
+static void target_core_setup_##_name##_cit(struct target_backend *tb)	\
 {									\
-	struct target_backend_cits *tbc = &sa->tb_cits;			\
-	struct config_item_type *cit = &tbc->tb_##_name##_cit;		\
+	struct config_item_type *cit = &tb->tb_##_name##_cit;		\
 									\
 	cit->ct_item_ops = _item_ops;					\
 	cit->ct_group_ops = _group_ops;					\
 	cit->ct_attrs = _attrs;						\
-	cit->ct_owner = sa->owner;					\
+	cit->ct_owner = tb->ops->owner;					\
+	pr_debug("Setup generic %s\n", __stringify(_name));		\
+}
+
+#define TB_CIT_SETUP_DRV(_name, _item_ops, _group_ops)			\
+static void target_core_setup_##_name##_cit(struct target_backend *tb)	\
+{									\
+	struct config_item_type *cit = &tb->tb_##_name##_cit;		\
+									\
+	cit->ct_item_ops = _item_ops;					\
+	cit->ct_group_ops = _group_ops;					\
+	cit->ct_attrs = tb->ops->tb_##_name##_attrs;			\
+	cit->ct_owner = tb->ops->owner;					\
 	pr_debug("Setup generic %s\n", __stringify(_name));		\
 }
 
@@ -92,7 +102,7 @@
 				      char *page)
 {
 	return sprintf(page, "Target Engine Core ConfigFS Infrastructure %s"
-		" on %s/%s on "UTS_RELEASE"\n", TARGET_CORE_CONFIGFS_VERSION,
+		" on %s/%s on "UTS_RELEASE"\n", TARGET_CORE_VERSION,
 		utsname()->sysname, utsname()->machine);
 }
 
@@ -116,7 +126,7 @@
 
 	mutex_lock(&g_tf_lock);
 	list_for_each_entry(tf, &g_tf_list, tf_list) {
-		if (!strcmp(tf->tf_name, name)) {
+		if (!strcmp(tf->tf_ops->name, name)) {
 			atomic_inc(&tf->tf_access_cnt);
 			mutex_unlock(&g_tf_lock);
 			return tf;
@@ -193,29 +203,24 @@
 		return ERR_PTR(-EINVAL);
 	}
 	pr_debug("Target_Core_ConfigFS: REGISTER -> Located fabric:"
-			" %s\n", tf->tf_name);
+			" %s\n", tf->tf_ops->name);
 	/*
 	 * On a successful target_core_get_fabric() look, the returned
 	 * struct target_fabric_configfs *tf will contain a usage reference.
 	 */
 	pr_debug("Target_Core_ConfigFS: REGISTER tfc_wwn_cit -> %p\n",
-			&tf->tf_cit_tmpl.tfc_wwn_cit);
+			&tf->tf_wwn_cit);
 
 	tf->tf_group.default_groups = tf->tf_default_groups;
 	tf->tf_group.default_groups[0] = &tf->tf_disc_group;
 	tf->tf_group.default_groups[1] = NULL;
 
-	config_group_init_type_name(&tf->tf_group, name,
-			&tf->tf_cit_tmpl.tfc_wwn_cit);
+	config_group_init_type_name(&tf->tf_group, name, &tf->tf_wwn_cit);
 	config_group_init_type_name(&tf->tf_disc_group, "discovery_auth",
-			&tf->tf_cit_tmpl.tfc_discovery_cit);
+			&tf->tf_discovery_cit);
 
 	pr_debug("Target_Core_ConfigFS: REGISTER -> Allocated Fabric:"
 			" %s\n", tf->tf_group.cg_item.ci_name);
-	tf->tf_fabric = &tf->tf_group.cg_item;
-	pr_debug("Target_Core_ConfigFS: REGISTER -> Set tf->tf_fabric"
-			" for %s\n", name);
-
 	return &tf->tf_group;
 }
 
@@ -236,13 +241,9 @@
 		" tf list\n", config_item_name(item));
 
 	pr_debug("Target_Core_ConfigFS: DEREGISTER -> located fabric:"
-			" %s\n", tf->tf_name);
+			" %s\n", tf->tf_ops->name);
 	atomic_dec(&tf->tf_access_cnt);
 
-	pr_debug("Target_Core_ConfigFS: DEREGISTER -> Releasing"
-			" tf->tf_fabric for %s\n", tf->tf_name);
-	tf->tf_fabric = NULL;
-
 	pr_debug("Target_Core_ConfigFS: DEREGISTER -> Releasing ci"
 			" %s\n", config_item_name(item));
 
@@ -318,10 +319,6 @@
 		pr_err("Missing tfo->get_fabric_name()\n");
 		return -EINVAL;
 	}
-	if (!tfo->get_fabric_proto_ident) {
-		pr_err("Missing tfo->get_fabric_proto_ident()\n");
-		return -EINVAL;
-	}
 	if (!tfo->tpg_get_wwn) {
 		pr_err("Missing tfo->tpg_get_wwn()\n");
 		return -EINVAL;
@@ -330,18 +327,6 @@
 		pr_err("Missing tfo->tpg_get_tag()\n");
 		return -EINVAL;
 	}
-	if (!tfo->tpg_get_default_depth) {
-		pr_err("Missing tfo->tpg_get_default_depth()\n");
-		return -EINVAL;
-	}
-	if (!tfo->tpg_get_pr_transport_id) {
-		pr_err("Missing tfo->tpg_get_pr_transport_id()\n");
-		return -EINVAL;
-	}
-	if (!tfo->tpg_get_pr_transport_id_len) {
-		pr_err("Missing tfo->tpg_get_pr_transport_id_len()\n");
-		return -EINVAL;
-	}
 	if (!tfo->tpg_check_demo_mode) {
 		pr_err("Missing tfo->tpg_check_demo_mode()\n");
 		return -EINVAL;
@@ -358,14 +343,6 @@
 		pr_err("Missing tfo->tpg_check_prod_mode_write_protect()\n");
 		return -EINVAL;
 	}
-	if (!tfo->tpg_alloc_fabric_acl) {
-		pr_err("Missing tfo->tpg_alloc_fabric_acl()\n");
-		return -EINVAL;
-	}
-	if (!tfo->tpg_release_fabric_acl) {
-		pr_err("Missing tfo->tpg_release_fabric_acl()\n");
-		return -EINVAL;
-	}
 	if (!tfo->tpg_get_inst_index) {
 		pr_err("Missing tfo->tpg_get_inst_index()\n");
 		return -EINVAL;
@@ -398,10 +375,6 @@
 		pr_err("Missing tfo->set_default_node_attributes()\n");
 		return -EINVAL;
 	}
-	if (!tfo->get_task_tag) {
-		pr_err("Missing tfo->get_task_tag()\n");
-		return -EINVAL;
-	}
 	if (!tfo->get_cmd_state) {
 		pr_err("Missing tfo->get_cmd_state()\n");
 		return -EINVAL;
@@ -464,15 +437,7 @@
 
 	INIT_LIST_HEAD(&tf->tf_list);
 	atomic_set(&tf->tf_access_cnt, 0);
-
-	/*
-	 * Setup the default generic struct config_item_type's (cits) in
-	 * struct target_fabric_configfs->tf_cit_tmpl
-	 */
-	tf->tf_module = fo->module;
-	snprintf(tf->tf_name, TARGET_FABRIC_NAME_SIZE, "%s", fo->name);
-
-	tf->tf_ops = *fo;
+	tf->tf_ops = fo;
 	target_fabric_setup_cits(tf);
 
 	mutex_lock(&g_tf_lock);
@@ -489,7 +454,7 @@
 
 	mutex_lock(&g_tf_lock);
 	list_for_each_entry(t, &g_tf_list, tf_list) {
-		if (!strcmp(t->tf_name, fo->name)) {
+		if (!strcmp(t->tf_ops->name, fo->name)) {
 			BUG_ON(atomic_read(&t->tf_access_cnt));
 			list_del(&t->tf_list);
 			kfree(t);
@@ -505,16 +470,605 @@
 //############################################################################*/
 
 /* Start functions for struct config_item_type tb_dev_attrib_cit */
+#define DEF_TB_DEV_ATTRIB_SHOW(_name)					\
+static ssize_t show_##_name(struct se_dev_attrib *da, char *page)	\
+{									\
+	return snprintf(page, PAGE_SIZE, "%u\n", da->_name);		\
+}
+
+DEF_TB_DEV_ATTRIB_SHOW(emulate_model_alias);
+DEF_TB_DEV_ATTRIB_SHOW(emulate_dpo);
+DEF_TB_DEV_ATTRIB_SHOW(emulate_fua_write);
+DEF_TB_DEV_ATTRIB_SHOW(emulate_fua_read);
+DEF_TB_DEV_ATTRIB_SHOW(emulate_write_cache);
+DEF_TB_DEV_ATTRIB_SHOW(emulate_ua_intlck_ctrl);
+DEF_TB_DEV_ATTRIB_SHOW(emulate_tas);
+DEF_TB_DEV_ATTRIB_SHOW(emulate_tpu);
+DEF_TB_DEV_ATTRIB_SHOW(emulate_tpws);
+DEF_TB_DEV_ATTRIB_SHOW(emulate_caw);
+DEF_TB_DEV_ATTRIB_SHOW(emulate_3pc);
+DEF_TB_DEV_ATTRIB_SHOW(pi_prot_type);
+DEF_TB_DEV_ATTRIB_SHOW(hw_pi_prot_type);
+DEF_TB_DEV_ATTRIB_SHOW(pi_prot_format);
+DEF_TB_DEV_ATTRIB_SHOW(enforce_pr_isids);
+DEF_TB_DEV_ATTRIB_SHOW(is_nonrot);
+DEF_TB_DEV_ATTRIB_SHOW(emulate_rest_reord);
+DEF_TB_DEV_ATTRIB_SHOW(force_pr_aptpl);
+DEF_TB_DEV_ATTRIB_SHOW(hw_block_size);
+DEF_TB_DEV_ATTRIB_SHOW(block_size);
+DEF_TB_DEV_ATTRIB_SHOW(hw_max_sectors);
+DEF_TB_DEV_ATTRIB_SHOW(optimal_sectors);
+DEF_TB_DEV_ATTRIB_SHOW(hw_queue_depth);
+DEF_TB_DEV_ATTRIB_SHOW(queue_depth);
+DEF_TB_DEV_ATTRIB_SHOW(max_unmap_lba_count);
+DEF_TB_DEV_ATTRIB_SHOW(max_unmap_block_desc_count);
+DEF_TB_DEV_ATTRIB_SHOW(unmap_granularity);
+DEF_TB_DEV_ATTRIB_SHOW(unmap_granularity_alignment);
+DEF_TB_DEV_ATTRIB_SHOW(max_write_same_len);
+
+#define DEF_TB_DEV_ATTRIB_STORE_U32(_name)				\
+static ssize_t store_##_name(struct se_dev_attrib *da, const char *page,\
+		size_t count)						\
+{									\
+	u32 val;							\
+	int ret;							\
+									\
+	ret = kstrtou32(page, 0, &val);					\
+	if (ret < 0)							\
+		return ret;						\
+	da->_name = val;						\
+	return count;							\
+}
+
+DEF_TB_DEV_ATTRIB_STORE_U32(max_unmap_lba_count);
+DEF_TB_DEV_ATTRIB_STORE_U32(max_unmap_block_desc_count);
+DEF_TB_DEV_ATTRIB_STORE_U32(unmap_granularity);
+DEF_TB_DEV_ATTRIB_STORE_U32(unmap_granularity_alignment);
+DEF_TB_DEV_ATTRIB_STORE_U32(max_write_same_len);
+
+#define DEF_TB_DEV_ATTRIB_STORE_BOOL(_name)				\
+static ssize_t store_##_name(struct se_dev_attrib *da, const char *page,\
+		size_t count)						\
+{									\
+	bool flag;							\
+	int ret;							\
+									\
+	ret = strtobool(page, &flag);					\
+	if (ret < 0)							\
+		return ret;						\
+	da->_name = flag;						\
+	return count;							\
+}
+
+DEF_TB_DEV_ATTRIB_STORE_BOOL(emulate_fua_write);
+DEF_TB_DEV_ATTRIB_STORE_BOOL(emulate_caw);
+DEF_TB_DEV_ATTRIB_STORE_BOOL(emulate_3pc);
+DEF_TB_DEV_ATTRIB_STORE_BOOL(enforce_pr_isids);
+DEF_TB_DEV_ATTRIB_STORE_BOOL(is_nonrot);
+
+#define DEF_TB_DEV_ATTRIB_STORE_STUB(_name)				\
+static ssize_t store_##_name(struct se_dev_attrib *da, const char *page,\
+		size_t count)						\
+{									\
+	printk_once(KERN_WARNING					\
+		"ignoring deprecated ##_name## attribute\n");	\
+	return count;							\
+}
+
+DEF_TB_DEV_ATTRIB_STORE_STUB(emulate_dpo);
+DEF_TB_DEV_ATTRIB_STORE_STUB(emulate_fua_read);
+
+static void dev_set_t10_wwn_model_alias(struct se_device *dev)
+{
+	const char *configname;
+
+	configname = config_item_name(&dev->dev_group.cg_item);
+	if (strlen(configname) >= 16) {
+		pr_warn("dev[%p]: Backstore name '%s' is too long for "
+			"INQUIRY_MODEL, truncating to 16 bytes\n", dev,
+			configname);
+	}
+	snprintf(&dev->t10_wwn.model[0], 16, "%s", configname);
+}
+
+static ssize_t store_emulate_model_alias(struct se_dev_attrib *da,
+		const char *page, size_t count)
+{
+	struct se_device *dev = da->da_dev;
+	bool flag;
+	int ret;
+
+	if (dev->export_count) {
+		pr_err("dev[%p]: Unable to change model alias"
+			" while export_count is %d\n",
+			dev, dev->export_count);
+		return -EINVAL;
+	}
+
+	ret = strtobool(page, &flag);
+	if (ret < 0)
+		return ret;
+
+	if (flag) {
+		dev_set_t10_wwn_model_alias(dev);
+	} else {
+		strncpy(&dev->t10_wwn.model[0],
+			dev->transport->inquiry_prod, 16);
+	}
+	da->emulate_model_alias = flag;
+	return count;
+}
+
+static ssize_t store_emulate_write_cache(struct se_dev_attrib *da,
+		const char *page, size_t count)
+{
+	bool flag;
+	int ret;
+
+	ret = strtobool(page, &flag);
+	if (ret < 0)
+		return ret;
+
+	if (flag && da->da_dev->transport->get_write_cache) {
+		pr_err("emulate_write_cache not supported for this device\n");
+		return -EINVAL;
+	}
+
+	da->emulate_write_cache = flag;
+	pr_debug("dev[%p]: SE Device WRITE_CACHE_EMULATION flag: %d\n",
+			da->da_dev, flag);
+	return count;
+}
+
+static ssize_t store_emulate_ua_intlck_ctrl(struct se_dev_attrib *da,
+		const char *page, size_t count)
+{
+	u32 val;
+	int ret;
+
+	ret = kstrtou32(page, 0, &val);
+	if (ret < 0)
+		return ret;
+
+	if (val != 0 && val != 1 && val != 2) {
+		pr_err("Illegal value %d\n", val);
+		return -EINVAL;
+	}
+
+	if (da->da_dev->export_count) {
+		pr_err("dev[%p]: Unable to change SE Device"
+			" UA_INTRLCK_CTRL while export_count is %d\n",
+			da->da_dev, da->da_dev->export_count);
+		return -EINVAL;
+	}
+	da->emulate_ua_intlck_ctrl = val;
+	pr_debug("dev[%p]: SE Device UA_INTRLCK_CTRL flag: %d\n",
+		da->da_dev, val);
+	return count;
+}
+
+static ssize_t store_emulate_tas(struct se_dev_attrib *da,
+		const char *page, size_t count)
+{
+	bool flag;
+	int ret;
+
+	ret = strtobool(page, &flag);
+	if (ret < 0)
+		return ret;
+
+	if (da->da_dev->export_count) {
+		pr_err("dev[%p]: Unable to change SE Device TAS while"
+			" export_count is %d\n",
+			da->da_dev, da->da_dev->export_count);
+		return -EINVAL;
+	}
+	da->emulate_tas = flag;
+	pr_debug("dev[%p]: SE Device TASK_ABORTED status bit: %s\n",
+		da->da_dev, flag ? "Enabled" : "Disabled");
+
+	return count;
+}
+
+static ssize_t store_emulate_tpu(struct se_dev_attrib *da,
+		const char *page, size_t count)
+{
+	bool flag;
+	int ret;
+
+	ret = strtobool(page, &flag);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * We expect this value to be non-zero when generic Block Layer
+	 * Discard supported is detected iblock_create_virtdevice().
+	 */
+	if (flag && !da->max_unmap_block_desc_count) {
+		pr_err("Generic Block Discard not supported\n");
+		return -ENOSYS;
+	}
+
+	da->emulate_tpu = flag;
+	pr_debug("dev[%p]: SE Device Thin Provisioning UNMAP bit: %d\n",
+		da->da_dev, flag);
+	return count;
+}
+
+static ssize_t store_emulate_tpws(struct se_dev_attrib *da,
+		const char *page, size_t count)
+{
+	bool flag;
+	int ret;
+
+	ret = strtobool(page, &flag);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * We expect this value to be non-zero when generic Block Layer
+	 * Discard supported is detected iblock_create_virtdevice().
+	 */
+	if (flag && !da->max_unmap_block_desc_count) {
+		pr_err("Generic Block Discard not supported\n");
+		return -ENOSYS;
+	}
+
+	da->emulate_tpws = flag;
+	pr_debug("dev[%p]: SE Device Thin Provisioning WRITE_SAME: %d\n",
+				da->da_dev, flag);
+	return count;
+}
+
+static ssize_t store_pi_prot_type(struct se_dev_attrib *da,
+		const char *page, size_t count)
+{
+	int old_prot = da->pi_prot_type, ret;
+	struct se_device *dev = da->da_dev;
+	u32 flag;
+
+	ret = kstrtou32(page, 0, &flag);
+	if (ret < 0)
+		return ret;
+
+	if (flag != 0 && flag != 1 && flag != 2 && flag != 3) {
+		pr_err("Illegal value %d for pi_prot_type\n", flag);
+		return -EINVAL;
+	}
+	if (flag == 2) {
+		pr_err("DIF TYPE2 protection currently not supported\n");
+		return -ENOSYS;
+	}
+	if (da->hw_pi_prot_type) {
+		pr_warn("DIF protection enabled on underlying hardware,"
+			" ignoring\n");
+		return count;
+	}
+	if (!dev->transport->init_prot || !dev->transport->free_prot) {
+		/* 0 is only allowed value for non-supporting backends */
+		if (flag == 0)
+			return 0;
+
+		pr_err("DIF protection not supported by backend: %s\n",
+		       dev->transport->name);
+		return -ENOSYS;
+	}
+	if (!(dev->dev_flags & DF_CONFIGURED)) {
+		pr_err("DIF protection requires device to be configured\n");
+		return -ENODEV;
+	}
+	if (dev->export_count) {
+		pr_err("dev[%p]: Unable to change SE Device PROT type while"
+		       " export_count is %d\n", dev, dev->export_count);
+		return -EINVAL;
+	}
+
+	da->pi_prot_type = flag;
+
+	if (flag && !old_prot) {
+		ret = dev->transport->init_prot(dev);
+		if (ret) {
+			da->pi_prot_type = old_prot;
+			return ret;
+		}
+
+	} else if (!flag && old_prot) {
+		dev->transport->free_prot(dev);
+	}
+
+	pr_debug("dev[%p]: SE Device Protection Type: %d\n", dev, flag);
+	return count;
+}
+
+static ssize_t store_pi_prot_format(struct se_dev_attrib *da,
+		const char *page, size_t count)
+{
+	struct se_device *dev = da->da_dev;
+	bool flag;
+	int ret;
+
+	ret = strtobool(page, &flag);
+	if (ret < 0)
+		return ret;
+
+	if (!flag)
+		return count;
+
+	if (!dev->transport->format_prot) {
+		pr_err("DIF protection format not supported by backend %s\n",
+		       dev->transport->name);
+		return -ENOSYS;
+	}
+	if (!(dev->dev_flags & DF_CONFIGURED)) {
+		pr_err("DIF protection format requires device to be configured\n");
+		return -ENODEV;
+	}
+	if (dev->export_count) {
+		pr_err("dev[%p]: Unable to format SE Device PROT type while"
+		       " export_count is %d\n", dev, dev->export_count);
+		return -EINVAL;
+	}
+
+	ret = dev->transport->format_prot(dev);
+	if (ret)
+		return ret;
+
+	pr_debug("dev[%p]: SE Device Protection Format complete\n", dev);
+	return count;
+}
+
+static ssize_t store_force_pr_aptpl(struct se_dev_attrib *da,
+		const char *page, size_t count)
+{
+	bool flag;
+	int ret;
+
+	ret = strtobool(page, &flag);
+	if (ret < 0)
+		return ret;
+	if (da->da_dev->export_count) {
+		pr_err("dev[%p]: Unable to set force_pr_aptpl while"
+		       " export_count is %d\n",
+		       da->da_dev, da->da_dev->export_count);
+		return -EINVAL;
+	}
+
+	da->force_pr_aptpl = flag;
+	pr_debug("dev[%p]: SE Device force_pr_aptpl: %d\n", da->da_dev, flag);
+	return count;
+}
+
+static ssize_t store_emulate_rest_reord(struct se_dev_attrib *da,
+		const char *page, size_t count)
+{
+	bool flag;
+	int ret;
+
+	ret = strtobool(page, &flag);
+	if (ret < 0)
+		return ret;
+
+	if (flag != 0) {
+		printk(KERN_ERR "dev[%p]: SE Device emulation of restricted"
+			" reordering not implemented\n", da->da_dev);
+		return -ENOSYS;
+	}
+	da->emulate_rest_reord = flag;
+	pr_debug("dev[%p]: SE Device emulate_rest_reord: %d\n",
+		da->da_dev, flag);
+	return count;
+}
+
+/*
+ * Note, this can only be called on unexported SE Device Object.
+ */
+static ssize_t store_queue_depth(struct se_dev_attrib *da,
+		const char *page, size_t count)
+{
+	struct se_device *dev = da->da_dev;
+	u32 val;
+	int ret;
+
+	ret = kstrtou32(page, 0, &val);
+	if (ret < 0)
+		return ret;
+
+	if (dev->export_count) {
+		pr_err("dev[%p]: Unable to change SE Device TCQ while"
+			" export_count is %d\n",
+			dev, dev->export_count);
+		return -EINVAL;
+	}
+	if (!val) {
+		pr_err("dev[%p]: Illegal ZERO value for queue_depth\n", dev);
+		return -EINVAL;
+	}
+
+	if (val > dev->dev_attrib.queue_depth) {
+		if (val > dev->dev_attrib.hw_queue_depth) {
+			pr_err("dev[%p]: Passed queue_depth:"
+				" %u exceeds TCM/SE_Device MAX"
+				" TCQ: %u\n", dev, val,
+				dev->dev_attrib.hw_queue_depth);
+			return -EINVAL;
+		}
+	}
+	da->queue_depth = dev->queue_depth = val;
+	pr_debug("dev[%p]: SE Device TCQ Depth changed to: %u\n", dev, val);
+	return count;
+}
+
+static ssize_t store_optimal_sectors(struct se_dev_attrib *da,
+		const char *page, size_t count)
+{
+	u32 val;
+	int ret;
+
+	ret = kstrtou32(page, 0, &val);
+	if (ret < 0)
+		return ret;
+
+	if (da->da_dev->export_count) {
+		pr_err("dev[%p]: Unable to change SE Device"
+			" optimal_sectors while export_count is %d\n",
+			da->da_dev, da->da_dev->export_count);
+		return -EINVAL;
+	}
+	if (val > da->hw_max_sectors) {
+		pr_err("dev[%p]: Passed optimal_sectors %u cannot be"
+			" greater than hw_max_sectors: %u\n",
+			da->da_dev, val, da->hw_max_sectors);
+		return -EINVAL;
+	}
+
+	da->optimal_sectors = val;
+	pr_debug("dev[%p]: SE Device optimal_sectors changed to %u\n",
+			da->da_dev, val);
+	return count;
+}
+
+static ssize_t store_block_size(struct se_dev_attrib *da,
+		const char *page, size_t count)
+{
+	u32 val;
+	int ret;
+
+	ret = kstrtou32(page, 0, &val);
+	if (ret < 0)
+		return ret;
+
+	if (da->da_dev->export_count) {
+		pr_err("dev[%p]: Unable to change SE Device block_size"
+			" while export_count is %d\n",
+			da->da_dev, da->da_dev->export_count);
+		return -EINVAL;
+	}
+
+	if (val != 512 && val != 1024 && val != 2048 && val != 4096) {
+		pr_err("dev[%p]: Illegal value for block_device: %u"
+			" for SE device, must be 512, 1024, 2048 or 4096\n",
+			da->da_dev, val);
+		return -EINVAL;
+	}
+
+	da->block_size = val;
+	if (da->max_bytes_per_io)
+		da->hw_max_sectors = da->max_bytes_per_io / val;
+
+	pr_debug("dev[%p]: SE Device block_size changed to %u\n",
+			da->da_dev, val);
+	return count;
+}
+
+CONFIGFS_EATTR_STRUCT(target_backend_dev_attrib, se_dev_attrib);
+#define TB_DEV_ATTR(_backend, _name, _mode)				\
+static struct target_backend_dev_attrib_attribute _backend##_dev_attrib_##_name = \
+	__CONFIGFS_EATTR(_name, _mode,					\
+	show_##_name,							\
+	store_##_name);
+
+#define TB_DEV_ATTR_RO(_backend, _name)					\
+static struct target_backend_dev_attrib_attribute _backend##_dev_attrib_##_name = \
+	__CONFIGFS_EATTR_RO(_name,					\
+	show_##_name);
+
+TB_DEV_ATTR(target_core, emulate_model_alias, S_IRUGO | S_IWUSR);
+TB_DEV_ATTR(target_core, emulate_dpo, S_IRUGO | S_IWUSR);
+TB_DEV_ATTR(target_core, emulate_fua_write, S_IRUGO | S_IWUSR);
+TB_DEV_ATTR(target_core, emulate_fua_read, S_IRUGO | S_IWUSR);
+TB_DEV_ATTR(target_core, emulate_write_cache, S_IRUGO | S_IWUSR);
+TB_DEV_ATTR(target_core, emulate_ua_intlck_ctrl, S_IRUGO | S_IWUSR);
+TB_DEV_ATTR(target_core, emulate_tas, S_IRUGO | S_IWUSR);
+TB_DEV_ATTR(target_core, emulate_tpu, S_IRUGO | S_IWUSR);
+TB_DEV_ATTR(target_core, emulate_tpws, S_IRUGO | S_IWUSR);
+TB_DEV_ATTR(target_core, emulate_caw, S_IRUGO | S_IWUSR);
+TB_DEV_ATTR(target_core, emulate_3pc, S_IRUGO | S_IWUSR);
+TB_DEV_ATTR(target_core, pi_prot_type, S_IRUGO | S_IWUSR);
+TB_DEV_ATTR_RO(target_core, hw_pi_prot_type);
+TB_DEV_ATTR(target_core, pi_prot_format, S_IRUGO | S_IWUSR);
+TB_DEV_ATTR(target_core, enforce_pr_isids, S_IRUGO | S_IWUSR);
+TB_DEV_ATTR(target_core, is_nonrot, S_IRUGO | S_IWUSR);
+TB_DEV_ATTR(target_core, emulate_rest_reord, S_IRUGO | S_IWUSR);
+TB_DEV_ATTR(target_core, force_pr_aptpl, S_IRUGO | S_IWUSR)
+TB_DEV_ATTR_RO(target_core, hw_block_size);
+TB_DEV_ATTR(target_core, block_size, S_IRUGO | S_IWUSR)
+TB_DEV_ATTR_RO(target_core, hw_max_sectors);
+TB_DEV_ATTR(target_core, optimal_sectors, S_IRUGO | S_IWUSR);
+TB_DEV_ATTR_RO(target_core, hw_queue_depth);
+TB_DEV_ATTR(target_core, queue_depth, S_IRUGO | S_IWUSR);
+TB_DEV_ATTR(target_core, max_unmap_lba_count, S_IRUGO | S_IWUSR);
+TB_DEV_ATTR(target_core, max_unmap_block_desc_count, S_IRUGO | S_IWUSR);
+TB_DEV_ATTR(target_core, unmap_granularity, S_IRUGO | S_IWUSR);
+TB_DEV_ATTR(target_core, unmap_granularity_alignment, S_IRUGO | S_IWUSR);
+TB_DEV_ATTR(target_core, max_write_same_len, S_IRUGO | S_IWUSR);
 
 CONFIGFS_EATTR_STRUCT(target_core_dev_attrib, se_dev_attrib);
 CONFIGFS_EATTR_OPS(target_core_dev_attrib, se_dev_attrib, da_group);
 
+/*
+ * dev_attrib attributes for devices using the target core SBC/SPC
+ * interpreter.  Any backend using spc_parse_cdb should be using
+ * these.
+ */
+struct configfs_attribute *sbc_attrib_attrs[] = {
+	&target_core_dev_attrib_emulate_model_alias.attr,
+	&target_core_dev_attrib_emulate_dpo.attr,
+	&target_core_dev_attrib_emulate_fua_write.attr,
+	&target_core_dev_attrib_emulate_fua_read.attr,
+	&target_core_dev_attrib_emulate_write_cache.attr,
+	&target_core_dev_attrib_emulate_ua_intlck_ctrl.attr,
+	&target_core_dev_attrib_emulate_tas.attr,
+	&target_core_dev_attrib_emulate_tpu.attr,
+	&target_core_dev_attrib_emulate_tpws.attr,
+	&target_core_dev_attrib_emulate_caw.attr,
+	&target_core_dev_attrib_emulate_3pc.attr,
+	&target_core_dev_attrib_pi_prot_type.attr,
+	&target_core_dev_attrib_hw_pi_prot_type.attr,
+	&target_core_dev_attrib_pi_prot_format.attr,
+	&target_core_dev_attrib_enforce_pr_isids.attr,
+	&target_core_dev_attrib_is_nonrot.attr,
+	&target_core_dev_attrib_emulate_rest_reord.attr,
+	&target_core_dev_attrib_force_pr_aptpl.attr,
+	&target_core_dev_attrib_hw_block_size.attr,
+	&target_core_dev_attrib_block_size.attr,
+	&target_core_dev_attrib_hw_max_sectors.attr,
+	&target_core_dev_attrib_optimal_sectors.attr,
+	&target_core_dev_attrib_hw_queue_depth.attr,
+	&target_core_dev_attrib_queue_depth.attr,
+	&target_core_dev_attrib_max_unmap_lba_count.attr,
+	&target_core_dev_attrib_max_unmap_block_desc_count.attr,
+	&target_core_dev_attrib_unmap_granularity.attr,
+	&target_core_dev_attrib_unmap_granularity_alignment.attr,
+	&target_core_dev_attrib_max_write_same_len.attr,
+	NULL,
+};
+EXPORT_SYMBOL(sbc_attrib_attrs);
+
+TB_DEV_ATTR_RO(target_pt, hw_pi_prot_type);
+TB_DEV_ATTR_RO(target_pt, hw_block_size);
+TB_DEV_ATTR_RO(target_pt, hw_max_sectors);
+TB_DEV_ATTR_RO(target_pt, hw_queue_depth);
+
+/*
+ * Minimal dev_attrib attributes for devices passing through CDBs.
+ * In this case we only provide a few read-only attributes for
+ * backwards compatibility.
+ */
+struct configfs_attribute *passthrough_attrib_attrs[] = {
+	&target_pt_dev_attrib_hw_pi_prot_type.attr,
+	&target_pt_dev_attrib_hw_block_size.attr,
+	&target_pt_dev_attrib_hw_max_sectors.attr,
+	&target_pt_dev_attrib_hw_queue_depth.attr,
+	NULL,
+};
+EXPORT_SYMBOL(passthrough_attrib_attrs);
+
 static struct configfs_item_operations target_core_dev_attrib_ops = {
 	.show_attribute		= target_core_dev_attrib_attr_show,
 	.store_attribute	= target_core_dev_attrib_attr_store,
 };
 
-TB_CIT_SETUP(dev_attrib, &target_core_dev_attrib_ops, NULL, NULL);
+TB_CIT_SETUP_DRV(dev_attrib, &target_core_dev_attrib_ops, NULL);
 
 /* End functions for struct config_item_type tb_dev_attrib_cit */
 
@@ -862,7 +1416,6 @@
 		struct se_device *dev, char *page)
 {
 	struct se_node_acl *se_nacl;
-	struct se_lun *lun;
 	struct se_portal_group *se_tpg;
 	struct t10_pr_registration *pr_reg;
 	const struct target_core_fabric_ops *tfo;
@@ -877,7 +1430,6 @@
 
 	se_nacl = pr_reg->pr_reg_nacl;
 	se_tpg = se_nacl->se_tpg;
-	lun = pr_reg->pr_reg_tg_pt_lun;
 	tfo = se_tpg->se_tpg_tfo;
 
 	len += sprintf(page+len, "SPC-3 Reservation: %s"
@@ -885,9 +1437,9 @@
 		tfo->tpg_get_wwn(se_tpg));
 	len += sprintf(page+len, "SPC-3 Reservation: Relative Port"
 		" Identifier Tag: %hu %s Portal Group Tag: %hu"
-		" %s Logical Unit: %u\n", lun->lun_sep->sep_rtpi,
+		" %s Logical Unit: %llu\n", pr_reg->tg_pt_sep_rtpi,
 		tfo->get_fabric_name(), tfo->tpg_get_tag(se_tpg),
-		tfo->get_fabric_name(), lun->unpacked_lun);
+		tfo->get_fabric_name(), pr_reg->pr_aptpl_target_lun);
 
 out_unlock:
 	spin_unlock(&dev->dev_reservation_lock);
@@ -1012,12 +1564,12 @@
 	{Opt_res_type, "res_type=%d"},
 	{Opt_res_scope, "res_scope=%d"},
 	{Opt_res_all_tg_pt, "res_all_tg_pt=%d"},
-	{Opt_mapped_lun, "mapped_lun=%d"},
+	{Opt_mapped_lun, "mapped_lun=%lld"},
 	{Opt_target_fabric, "target_fabric=%s"},
 	{Opt_target_node, "target_node=%s"},
 	{Opt_tpgt, "tpgt=%d"},
 	{Opt_port_rtpi, "port_rtpi=%d"},
-	{Opt_target_lun, "target_lun=%d"},
+	{Opt_target_lun, "target_lun=%lld"},
 	{Opt_err, NULL}
 };
 
@@ -1032,10 +1584,10 @@
 	substring_t args[MAX_OPT_ARGS];
 	unsigned long long tmp_ll;
 	u64 sa_res_key = 0;
-	u32 mapped_lun = 0, target_lun = 0;
+	u64 mapped_lun = 0, target_lun = 0;
 	int ret = -1, res_holder = 0, all_tg_pt = 0, arg, token;
-	u16 port_rpti = 0, tpgt = 0;
-	u8 type = 0, scope;
+	u16 tpgt = 0;
+	u8 type = 0;
 
 	if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
 		return 0;
@@ -1115,7 +1667,6 @@
 			break;
 		case Opt_res_scope:
 			match_int(args, &arg);
-			scope = (u8)arg;
 			break;
 		case Opt_res_all_tg_pt:
 			match_int(args, &arg);
@@ -1123,7 +1674,7 @@
 			break;
 		case Opt_mapped_lun:
 			match_int(args, &arg);
-			mapped_lun = (u32)arg;
+			mapped_lun = (u64)arg;
 			break;
 		/*
 		 * PR APTPL Metadata for Target Port
@@ -1155,11 +1706,10 @@
 			break;
 		case Opt_port_rtpi:
 			match_int(args, &arg);
-			port_rpti = (u16)arg;
 			break;
 		case Opt_target_lun:
 			match_int(args, &arg);
-			target_lun = (u32)arg;
+			target_lun = (u64)arg;
 			break;
 		default:
 			break;
@@ -1223,13 +1773,13 @@
 static ssize_t target_core_show_dev_info(void *p, char *page)
 {
 	struct se_device *dev = p;
-	struct se_subsystem_api *t = dev->transport;
 	int bl = 0;
 	ssize_t read_bytes = 0;
 
 	transport_dump_dev_state(dev, page, &bl);
 	read_bytes += bl;
-	read_bytes += t->show_configfs_dev_params(dev, page+read_bytes);
+	read_bytes += dev->transport->show_configfs_dev_params(dev,
+			page+read_bytes);
 	return read_bytes;
 }
 
@@ -1247,9 +1797,8 @@
 	size_t count)
 {
 	struct se_device *dev = p;
-	struct se_subsystem_api *t = dev->transport;
 
-	return t->set_configfs_dev_params(dev, page, count);
+	return dev->transport->set_configfs_dev_params(dev, page, count);
 }
 
 static struct target_core_configfs_attribute target_core_attr_dev_control = {
@@ -2339,21 +2888,16 @@
 	struct t10_alua_tg_pt_gp *tg_pt_gp,
 	char *page)
 {
-	struct se_port *port;
-	struct se_portal_group *tpg;
 	struct se_lun *lun;
-	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem;
 	ssize_t len = 0, cur_len;
 	unsigned char buf[TG_PT_GROUP_NAME_BUF];
 
 	memset(buf, 0, TG_PT_GROUP_NAME_BUF);
 
 	spin_lock(&tg_pt_gp->tg_pt_gp_lock);
-	list_for_each_entry(tg_pt_gp_mem, &tg_pt_gp->tg_pt_gp_mem_list,
-			tg_pt_gp_mem_list) {
-		port = tg_pt_gp_mem->tg_pt;
-		tpg = port->sep_tpg;
-		lun = port->sep_lun;
+	list_for_each_entry(lun, &tg_pt_gp->tg_pt_gp_lun_list,
+			lun_tg_pt_gp_link) {
+		struct se_portal_group *tpg = lun->lun_tpg;
 
 		cur_len = snprintf(buf, TG_PT_GROUP_NAME_BUF, "%s/%s/tpgt_%hu"
 			"/%s\n", tpg->se_tpg_tfo->get_fabric_name(),
@@ -2526,9 +3070,9 @@
 	const char *name)
 {
 	struct t10_alua_tg_pt_gp *tg_pt_gp;
-	struct se_subsystem_api *t;
 	struct config_item *hba_ci = &group->cg_item;
 	struct se_hba *hba = item_to_hba(hba_ci);
+	struct target_backend *tb = hba->backend;
 	struct se_device *dev;
 	struct config_group *dev_cg = NULL, *tg_pt_gp_cg = NULL;
 	struct config_group *dev_stat_grp = NULL;
@@ -2537,10 +3081,6 @@
 	ret = mutex_lock_interruptible(&hba->hba_access_mutex);
 	if (ret)
 		return ERR_PTR(ret);
-	/*
-	 * Locate the struct se_subsystem_api from parent's struct se_hba.
-	 */
-	t = hba->transport;
 
 	dev = target_alloc_device(hba, name);
 	if (!dev)
@@ -2553,17 +3093,17 @@
 	if (!dev_cg->default_groups)
 		goto out_free_device;
 
-	config_group_init_type_name(dev_cg, name, &t->tb_cits.tb_dev_cit);
+	config_group_init_type_name(dev_cg, name, &tb->tb_dev_cit);
 	config_group_init_type_name(&dev->dev_attrib.da_group, "attrib",
-			&t->tb_cits.tb_dev_attrib_cit);
+			&tb->tb_dev_attrib_cit);
 	config_group_init_type_name(&dev->dev_pr_group, "pr",
-			&t->tb_cits.tb_dev_pr_cit);
+			&tb->tb_dev_pr_cit);
 	config_group_init_type_name(&dev->t10_wwn.t10_wwn_group, "wwn",
-			&t->tb_cits.tb_dev_wwn_cit);
+			&tb->tb_dev_wwn_cit);
 	config_group_init_type_name(&dev->t10_alua.alua_tg_pt_gps_group,
-			"alua", &t->tb_cits.tb_dev_alua_tg_pt_gps_cit);
+			"alua", &tb->tb_dev_alua_tg_pt_gps_cit);
 	config_group_init_type_name(&dev->dev_stat_grps.stat_group,
-			"statistics", &t->tb_cits.tb_dev_stat_cit);
+			"statistics", &tb->tb_dev_stat_cit);
 
 	dev_cg->default_groups[0] = &dev->dev_attrib.da_group;
 	dev_cg->default_groups[1] = &dev->dev_pr_group;
@@ -2693,8 +3233,8 @@
 	char *page)
 {
 	return sprintf(page, "HBA Index: %d plugin: %s version: %s\n",
-			hba->hba_id, hba->transport->name,
-			TARGET_CORE_CONFIGFS_VERSION);
+			hba->hba_id, hba->backend->ops->name,
+			TARGET_CORE_VERSION);
 }
 
 SE_HBA_ATTR_RO(hba_info);
@@ -2713,11 +3253,10 @@
 static ssize_t target_core_hba_store_attr_hba_mode(struct se_hba *hba,
 				const char *page, size_t count)
 {
-	struct se_subsystem_api *transport = hba->transport;
 	unsigned long mode_flag;
 	int ret;
 
-	if (transport->pmode_enable_hba == NULL)
+	if (hba->backend->ops->pmode_enable_hba == NULL)
 		return -EINVAL;
 
 	ret = kstrtoul(page, 0, &mode_flag);
@@ -2731,7 +3270,7 @@
 		return -EINVAL;
 	}
 
-	ret = transport->pmode_enable_hba(hba, mode_flag);
+	ret = hba->backend->ops->pmode_enable_hba(hba, mode_flag);
 	if (ret < 0)
 		return -EINVAL;
 	if (ret > 0)
@@ -2857,16 +3396,15 @@
 
 /* Stop functions for struct config_item_type target_core_hba_cit */
 
-void target_core_setup_sub_cits(struct se_subsystem_api *sa)
+void target_setup_backend_cits(struct target_backend *tb)
 {
-	target_core_setup_dev_cit(sa);
-	target_core_setup_dev_attrib_cit(sa);
-	target_core_setup_dev_pr_cit(sa);
-	target_core_setup_dev_wwn_cit(sa);
-	target_core_setup_dev_alua_tg_pt_gps_cit(sa);
-	target_core_setup_dev_stat_cit(sa);
+	target_core_setup_dev_cit(tb);
+	target_core_setup_dev_attrib_cit(tb);
+	target_core_setup_dev_pr_cit(tb);
+	target_core_setup_dev_wwn_cit(tb);
+	target_core_setup_dev_alua_tg_pt_gps_cit(tb);
+	target_core_setup_dev_stat_cit(tb);
 }
-EXPORT_SYMBOL(target_core_setup_sub_cits);
 
 static int __init target_core_init_configfs(void)
 {
@@ -2968,7 +3506,7 @@
 		goto out_global;
 	}
 	pr_debug("TARGET_CORE[0]: Initialized ConfigFS Fabric"
-		" Infrastructure: "TARGET_CORE_CONFIGFS_VERSION" on %s/%s"
+		" Infrastructure: "TARGET_CORE_VERSION" on %s/%s"
 		" on "UTS_RELEASE"\n", utsname()->sysname, utsname()->machine);
 	/*
 	 * Register built-in RAMDISK subsystem logic for virtual LUN 0
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 417f88b..09e682b 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -56,40 +56,37 @@
 struct se_device *g_lun0_dev;
 
 sense_reason_t
-transport_lookup_cmd_lun(struct se_cmd *se_cmd, u32 unpacked_lun)
+transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 {
 	struct se_lun *se_lun = NULL;
 	struct se_session *se_sess = se_cmd->se_sess;
-	struct se_device *dev;
-	unsigned long flags;
+	struct se_node_acl *nacl = se_sess->se_node_acl;
+	struct se_dev_entry *deve;
 
-	if (unpacked_lun >= TRANSPORT_MAX_LUNS_PER_TPG)
-		return TCM_NON_EXISTENT_LUN;
-
-	spin_lock_irqsave(&se_sess->se_node_acl->device_list_lock, flags);
-	se_cmd->se_deve = se_sess->se_node_acl->device_list[unpacked_lun];
-	if (se_cmd->se_deve->lun_flags & TRANSPORT_LUNFLAGS_INITIATOR_ACCESS) {
-		struct se_dev_entry *deve = se_cmd->se_deve;
-
-		deve->total_cmds++;
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, unpacked_lun);
+	if (deve) {
+		atomic_long_inc(&deve->total_cmds);
 
 		if ((se_cmd->data_direction == DMA_TO_DEVICE) &&
 		    (deve->lun_flags & TRANSPORT_LUNFLAGS_READ_ONLY)) {
 			pr_err("TARGET_CORE[%s]: Detected WRITE_PROTECTED LUN"
-				" Access for 0x%08x\n",
+				" Access for 0x%08llx\n",
 				se_cmd->se_tfo->get_fabric_name(),
 				unpacked_lun);
-			spin_unlock_irqrestore(&se_sess->se_node_acl->device_list_lock, flags);
+			rcu_read_unlock();
 			return TCM_WRITE_PROTECTED;
 		}
 
 		if (se_cmd->data_direction == DMA_TO_DEVICE)
-			deve->write_bytes += se_cmd->data_length;
+			atomic_long_add(se_cmd->data_length,
+					&deve->write_bytes);
 		else if (se_cmd->data_direction == DMA_FROM_DEVICE)
-			deve->read_bytes += se_cmd->data_length;
+			atomic_long_add(se_cmd->data_length,
+					&deve->read_bytes);
 
-		se_lun = deve->se_lun;
-		se_cmd->se_lun = deve->se_lun;
+		se_lun = rcu_dereference(deve->se_lun);
+		se_cmd->se_lun = rcu_dereference(deve->se_lun);
 		se_cmd->pr_res_key = deve->pr_res_key;
 		se_cmd->orig_fe_lun = unpacked_lun;
 		se_cmd->se_cmd_flags |= SCF_SE_LUN_CMD;
@@ -97,7 +94,7 @@
 		percpu_ref_get(&se_lun->lun_ref);
 		se_cmd->lun_ref_active = true;
 	}
-	spin_unlock_irqrestore(&se_sess->se_node_acl->device_list_lock, flags);
+	rcu_read_unlock();
 
 	if (!se_lun) {
 		/*
@@ -107,7 +104,7 @@
 		 */
 		if (unpacked_lun != 0) {
 			pr_err("TARGET_CORE[%s]: Detected NON_EXISTENT_LUN"
-				" Access for 0x%08x\n",
+				" Access for 0x%08llx\n",
 				se_cmd->se_tfo->get_fabric_name(),
 				unpacked_lun);
 			return TCM_NON_EXISTENT_LUN;
@@ -119,64 +116,66 @@
 		    (se_cmd->data_direction != DMA_NONE))
 			return TCM_WRITE_PROTECTED;
 
-		se_lun = &se_sess->se_tpg->tpg_virt_lun0;
-		se_cmd->se_lun = &se_sess->se_tpg->tpg_virt_lun0;
+		se_lun = se_sess->se_tpg->tpg_virt_lun0;
+		se_cmd->se_lun = se_sess->se_tpg->tpg_virt_lun0;
 		se_cmd->orig_fe_lun = 0;
 		se_cmd->se_cmd_flags |= SCF_SE_LUN_CMD;
 
 		percpu_ref_get(&se_lun->lun_ref);
 		se_cmd->lun_ref_active = true;
 	}
+	/*
+	 * RCU reference protected by percpu se_lun->lun_ref taken above that
+	 * must drop to zero (including initial reference) before this se_lun
+	 * pointer can be kfree_rcu() by the final se_lun->lun_group put via
+	 * target_core_fabric_configfs.c:target_fabric_port_release
+	 */
+	se_cmd->se_dev = rcu_dereference_raw(se_lun->lun_se_dev);
+	atomic_long_inc(&se_cmd->se_dev->num_cmds);
 
-	/* Directly associate cmd with se_dev */
-	se_cmd->se_dev = se_lun->lun_se_dev;
-
-	dev = se_lun->lun_se_dev;
-	atomic_long_inc(&dev->num_cmds);
 	if (se_cmd->data_direction == DMA_TO_DEVICE)
-		atomic_long_add(se_cmd->data_length, &dev->write_bytes);
+		atomic_long_add(se_cmd->data_length,
+				&se_cmd->se_dev->write_bytes);
 	else if (se_cmd->data_direction == DMA_FROM_DEVICE)
-		atomic_long_add(se_cmd->data_length, &dev->read_bytes);
+		atomic_long_add(se_cmd->data_length,
+				&se_cmd->se_dev->read_bytes);
 
 	return 0;
 }
 EXPORT_SYMBOL(transport_lookup_cmd_lun);
 
-int transport_lookup_tmr_lun(struct se_cmd *se_cmd, u32 unpacked_lun)
+int transport_lookup_tmr_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 {
 	struct se_dev_entry *deve;
 	struct se_lun *se_lun = NULL;
 	struct se_session *se_sess = se_cmd->se_sess;
+	struct se_node_acl *nacl = se_sess->se_node_acl;
 	struct se_tmr_req *se_tmr = se_cmd->se_tmr_req;
 	unsigned long flags;
 
-	if (unpacked_lun >= TRANSPORT_MAX_LUNS_PER_TPG)
-		return -ENODEV;
-
-	spin_lock_irqsave(&se_sess->se_node_acl->device_list_lock, flags);
-	se_cmd->se_deve = se_sess->se_node_acl->device_list[unpacked_lun];
-	deve = se_cmd->se_deve;
-
-	if (deve->lun_flags & TRANSPORT_LUNFLAGS_INITIATOR_ACCESS) {
-		se_tmr->tmr_lun = deve->se_lun;
-		se_cmd->se_lun = deve->se_lun;
-		se_lun = deve->se_lun;
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, unpacked_lun);
+	if (deve) {
+		se_tmr->tmr_lun = rcu_dereference(deve->se_lun);
+		se_cmd->se_lun = rcu_dereference(deve->se_lun);
+		se_lun = rcu_dereference(deve->se_lun);
 		se_cmd->pr_res_key = deve->pr_res_key;
 		se_cmd->orig_fe_lun = unpacked_lun;
 	}
-	spin_unlock_irqrestore(&se_sess->se_node_acl->device_list_lock, flags);
+	rcu_read_unlock();
 
 	if (!se_lun) {
 		pr_debug("TARGET_CORE[%s]: Detected NON_EXISTENT_LUN"
-			" Access for 0x%08x\n",
+			" Access for 0x%08llx\n",
 			se_cmd->se_tfo->get_fabric_name(),
 			unpacked_lun);
 		return -ENODEV;
 	}
-
-	/* Directly associate cmd with se_dev */
-	se_cmd->se_dev = se_lun->lun_se_dev;
-	se_tmr->tmr_dev = se_lun->lun_se_dev;
+	/*
+	 * XXX: Add percpu se_lun->lun_ref reference count for TMR
+	 */
+	se_cmd->se_dev = rcu_dereference_raw(se_lun->lun_se_dev);
+	se_tmr->tmr_dev = rcu_dereference_raw(se_lun->lun_se_dev);
 
 	spin_lock_irqsave(&se_tmr->tmr_dev->se_tmr_lock, flags);
 	list_add_tail(&se_tmr->tmr_list, &se_tmr->tmr_dev->dev_tmr_list);
@@ -186,9 +185,24 @@
 }
 EXPORT_SYMBOL(transport_lookup_tmr_lun);
 
+bool target_lun_is_rdonly(struct se_cmd *cmd)
+{
+	struct se_session *se_sess = cmd->se_sess;
+	struct se_dev_entry *deve;
+	bool ret;
+
+	rcu_read_lock();
+	deve = target_nacl_find_deve(se_sess->se_node_acl, cmd->orig_fe_lun);
+	ret = (deve && deve->lun_flags & TRANSPORT_LUNFLAGS_READ_ONLY);
+	rcu_read_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL(target_lun_is_rdonly);
+
 /*
  * This function is called from core_scsi3_emulate_pro_register_and_move()
- * and core_scsi3_decode_spec_i_port(), and will increment &deve->pr_ref_count
+ * and core_scsi3_decode_spec_i_port(), and will increment &deve->pr_kref
  * when a matching rtpi is found.
  */
 struct se_dev_entry *core_get_se_deve_from_rtpi(
@@ -197,143 +211,55 @@
 {
 	struct se_dev_entry *deve;
 	struct se_lun *lun;
-	struct se_port *port;
 	struct se_portal_group *tpg = nacl->se_tpg;
-	u32 i;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	for (i = 0; i < TRANSPORT_MAX_LUNS_PER_TPG; i++) {
-		deve = nacl->device_list[i];
-
-		if (!(deve->lun_flags & TRANSPORT_LUNFLAGS_INITIATOR_ACCESS))
-			continue;
-
-		lun = deve->se_lun;
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(deve, &nacl->lun_entry_hlist, link) {
+		lun = rcu_dereference(deve->se_lun);
 		if (!lun) {
 			pr_err("%s device entries device pointer is"
 				" NULL, but Initiator has access.\n",
 				tpg->se_tpg_tfo->get_fabric_name());
 			continue;
 		}
-		port = lun->lun_sep;
-		if (!port) {
-			pr_err("%s device entries device pointer is"
-				" NULL, but Initiator has access.\n",
-				tpg->se_tpg_tfo->get_fabric_name());
-			continue;
-		}
-		if (port->sep_rtpi != rtpi)
+		if (lun->lun_rtpi != rtpi)
 			continue;
 
-		atomic_inc_mb(&deve->pr_ref_count);
-		spin_unlock_irq(&nacl->device_list_lock);
+		kref_get(&deve->pr_kref);
+		rcu_read_unlock();
 
 		return deve;
 	}
-	spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_unlock();
 
 	return NULL;
 }
 
-int core_free_device_list_for_node(
+void core_free_device_list_for_node(
 	struct se_node_acl *nacl,
 	struct se_portal_group *tpg)
 {
 	struct se_dev_entry *deve;
-	struct se_lun *lun;
-	u32 i;
 
-	if (!nacl->device_list)
-		return 0;
-
-	spin_lock_irq(&nacl->device_list_lock);
-	for (i = 0; i < TRANSPORT_MAX_LUNS_PER_TPG; i++) {
-		deve = nacl->device_list[i];
-
-		if (!(deve->lun_flags & TRANSPORT_LUNFLAGS_INITIATOR_ACCESS))
-			continue;
-
-		if (!deve->se_lun) {
-			pr_err("%s device entries device pointer is"
-				" NULL, but Initiator has access.\n",
-				tpg->se_tpg_tfo->get_fabric_name());
-			continue;
-		}
-		lun = deve->se_lun;
-
-		spin_unlock_irq(&nacl->device_list_lock);
-		core_disable_device_list_for_node(lun, NULL, deve->mapped_lun,
-			TRANSPORT_LUNFLAGS_NO_ACCESS, nacl, tpg);
-		spin_lock_irq(&nacl->device_list_lock);
+	mutex_lock(&nacl->lun_entry_mutex);
+	hlist_for_each_entry_rcu(deve, &nacl->lun_entry_hlist, link) {
+		struct se_lun *lun = rcu_dereference_check(deve->se_lun,
+					lockdep_is_held(&nacl->lun_entry_mutex));
+		core_disable_device_list_for_node(lun, deve, nacl, tpg);
 	}
-	spin_unlock_irq(&nacl->device_list_lock);
-
-	array_free(nacl->device_list, TRANSPORT_MAX_LUNS_PER_TPG);
-	nacl->device_list = NULL;
-
-	return 0;
+	mutex_unlock(&nacl->lun_entry_mutex);
 }
 
 void core_update_device_list_access(
-	u32 mapped_lun,
+	u64 mapped_lun,
 	u32 lun_access,
 	struct se_node_acl *nacl)
 {
 	struct se_dev_entry *deve;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	deve = nacl->device_list[mapped_lun];
-	if (lun_access & TRANSPORT_LUNFLAGS_READ_WRITE) {
-		deve->lun_flags &= ~TRANSPORT_LUNFLAGS_READ_ONLY;
-		deve->lun_flags |= TRANSPORT_LUNFLAGS_READ_WRITE;
-	} else {
-		deve->lun_flags &= ~TRANSPORT_LUNFLAGS_READ_WRITE;
-		deve->lun_flags |= TRANSPORT_LUNFLAGS_READ_ONLY;
-	}
-	spin_unlock_irq(&nacl->device_list_lock);
-}
-
-/*      core_enable_device_list_for_node():
- *
- *
- */
-int core_enable_device_list_for_node(
-	struct se_lun *lun,
-	struct se_lun_acl *lun_acl,
-	u32 mapped_lun,
-	u32 lun_access,
-	struct se_node_acl *nacl,
-	struct se_portal_group *tpg)
-{
-	struct se_port *port = lun->lun_sep;
-	struct se_dev_entry *deve;
-
-	spin_lock_irq(&nacl->device_list_lock);
-
-	deve = nacl->device_list[mapped_lun];
-
-	/*
-	 * Check if the call is handling demo mode -> explicit LUN ACL
-	 * transition.  This transition must be for the same struct se_lun
-	 * + mapped_lun that was setup in demo mode..
-	 */
-	if (deve->lun_flags & TRANSPORT_LUNFLAGS_INITIATOR_ACCESS) {
-		if (deve->se_lun_acl != NULL) {
-			pr_err("struct se_dev_entry->se_lun_acl"
-			       " already set for demo mode -> explicit"
-			       " LUN ACL transition\n");
-			spin_unlock_irq(&nacl->device_list_lock);
-			return -EINVAL;
-		}
-		if (deve->se_lun != lun) {
-			pr_err("struct se_dev_entry->se_lun does"
-			       " match passed struct se_lun for demo mode"
-			       " -> explicit LUN ACL transition\n");
-			spin_unlock_irq(&nacl->device_list_lock);
-			return -EINVAL;
-		}
-		deve->se_lun_acl = lun_acl;
-
+	mutex_lock(&nacl->lun_entry_mutex);
+	deve = target_nacl_find_deve(nacl, mapped_lun);
+	if (deve) {
 		if (lun_access & TRANSPORT_LUNFLAGS_READ_WRITE) {
 			deve->lun_flags &= ~TRANSPORT_LUNFLAGS_READ_ONLY;
 			deve->lun_flags |= TRANSPORT_LUNFLAGS_READ_WRITE;
@@ -341,87 +267,182 @@
 			deve->lun_flags &= ~TRANSPORT_LUNFLAGS_READ_WRITE;
 			deve->lun_flags |= TRANSPORT_LUNFLAGS_READ_ONLY;
 		}
-
-		spin_unlock_irq(&nacl->device_list_lock);
-		return 0;
 	}
-
-	deve->se_lun = lun;
-	deve->se_lun_acl = lun_acl;
-	deve->mapped_lun = mapped_lun;
-	deve->lun_flags |= TRANSPORT_LUNFLAGS_INITIATOR_ACCESS;
-
-	if (lun_access & TRANSPORT_LUNFLAGS_READ_WRITE) {
-		deve->lun_flags &= ~TRANSPORT_LUNFLAGS_READ_ONLY;
-		deve->lun_flags |= TRANSPORT_LUNFLAGS_READ_WRITE;
-	} else {
-		deve->lun_flags &= ~TRANSPORT_LUNFLAGS_READ_WRITE;
-		deve->lun_flags |= TRANSPORT_LUNFLAGS_READ_ONLY;
-	}
-
-	deve->creation_time = get_jiffies_64();
-	deve->attach_count++;
-	spin_unlock_irq(&nacl->device_list_lock);
-
-	spin_lock_bh(&port->sep_alua_lock);
-	list_add_tail(&deve->alua_port_list, &port->sep_alua_list);
-	spin_unlock_bh(&port->sep_alua_lock);
-
-	return 0;
+	mutex_unlock(&nacl->lun_entry_mutex);
 }
 
-/*      core_disable_device_list_for_node():
- *
- *
+/*
+ * Called with rcu_read_lock or nacl->device_list_lock held.
  */
-int core_disable_device_list_for_node(
+struct se_dev_entry *target_nacl_find_deve(struct se_node_acl *nacl, u64 mapped_lun)
+{
+	struct se_dev_entry *deve;
+
+	hlist_for_each_entry_rcu(deve, &nacl->lun_entry_hlist, link)
+		if (deve->mapped_lun == mapped_lun)
+			return deve;
+
+	return NULL;
+}
+EXPORT_SYMBOL(target_nacl_find_deve);
+
+void target_pr_kref_release(struct kref *kref)
+{
+	struct se_dev_entry *deve = container_of(kref, struct se_dev_entry,
+						 pr_kref);
+	complete(&deve->pr_comp);
+}
+
+static void
+target_luns_data_has_changed(struct se_node_acl *nacl, struct se_dev_entry *new,
+			     bool skip_new)
+{
+	struct se_dev_entry *tmp;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(tmp, &nacl->lun_entry_hlist, link) {
+		if (skip_new && tmp == new)
+			continue;
+		core_scsi3_ua_allocate(tmp, 0x3F,
+				       ASCQ_3FH_REPORTED_LUNS_DATA_HAS_CHANGED);
+	}
+	rcu_read_unlock();
+}
+
+int core_enable_device_list_for_node(
 	struct se_lun *lun,
 	struct se_lun_acl *lun_acl,
-	u32 mapped_lun,
+	u64 mapped_lun,
 	u32 lun_access,
 	struct se_node_acl *nacl,
 	struct se_portal_group *tpg)
 {
-	struct se_port *port = lun->lun_sep;
-	struct se_dev_entry *deve = nacl->device_list[mapped_lun];
+	struct se_dev_entry *orig, *new;
 
+	new = kzalloc(sizeof(*new), GFP_KERNEL);
+	if (!new) {
+		pr_err("Unable to allocate se_dev_entry memory\n");
+		return -ENOMEM;
+	}
+
+	atomic_set(&new->ua_count, 0);
+	spin_lock_init(&new->ua_lock);
+	INIT_LIST_HEAD(&new->ua_list);
+	INIT_LIST_HEAD(&new->lun_link);
+
+	new->mapped_lun = mapped_lun;
+	kref_init(&new->pr_kref);
+	init_completion(&new->pr_comp);
+
+	if (lun_access & TRANSPORT_LUNFLAGS_READ_WRITE)
+		new->lun_flags |= TRANSPORT_LUNFLAGS_READ_WRITE;
+	else
+		new->lun_flags |= TRANSPORT_LUNFLAGS_READ_ONLY;
+
+	new->creation_time = get_jiffies_64();
+	new->attach_count++;
+
+	mutex_lock(&nacl->lun_entry_mutex);
+	orig = target_nacl_find_deve(nacl, mapped_lun);
+	if (orig && orig->se_lun) {
+		struct se_lun *orig_lun = rcu_dereference_check(orig->se_lun,
+					lockdep_is_held(&nacl->lun_entry_mutex));
+
+		if (orig_lun != lun) {
+			pr_err("Existing orig->se_lun doesn't match new lun"
+			       " for dynamic -> explicit NodeACL conversion:"
+				" %s\n", nacl->initiatorname);
+			mutex_unlock(&nacl->lun_entry_mutex);
+			kfree(new);
+			return -EINVAL;
+		}
+		BUG_ON(orig->se_lun_acl != NULL);
+
+		rcu_assign_pointer(new->se_lun, lun);
+		rcu_assign_pointer(new->se_lun_acl, lun_acl);
+		hlist_del_rcu(&orig->link);
+		hlist_add_head_rcu(&new->link, &nacl->lun_entry_hlist);
+		mutex_unlock(&nacl->lun_entry_mutex);
+
+		spin_lock(&lun->lun_deve_lock);
+		list_del(&orig->lun_link);
+		list_add_tail(&new->lun_link, &lun->lun_deve_list);
+		spin_unlock(&lun->lun_deve_lock);
+
+		kref_put(&orig->pr_kref, target_pr_kref_release);
+		wait_for_completion(&orig->pr_comp);
+
+		target_luns_data_has_changed(nacl, new, true);
+		kfree_rcu(orig, rcu_head);
+		return 0;
+	}
+
+	rcu_assign_pointer(new->se_lun, lun);
+	rcu_assign_pointer(new->se_lun_acl, lun_acl);
+	hlist_add_head_rcu(&new->link, &nacl->lun_entry_hlist);
+	mutex_unlock(&nacl->lun_entry_mutex);
+
+	spin_lock(&lun->lun_deve_lock);
+	list_add_tail(&new->lun_link, &lun->lun_deve_list);
+	spin_unlock(&lun->lun_deve_lock);
+
+	target_luns_data_has_changed(nacl, new, true);
+	return 0;
+}
+
+/*
+ *	Called with se_node_acl->lun_entry_mutex held.
+ */
+void core_disable_device_list_for_node(
+	struct se_lun *lun,
+	struct se_dev_entry *orig,
+	struct se_node_acl *nacl,
+	struct se_portal_group *tpg)
+{
+	/*
+	 * rcu_dereference_raw protected by se_lun->lun_group symlink
+	 * reference to se_device->dev_group.
+	 */
+	struct se_device *dev = rcu_dereference_raw(lun->lun_se_dev);
 	/*
 	 * If the MappedLUN entry is being disabled, the entry in
-	 * port->sep_alua_list must be removed now before clearing the
+	 * lun->lun_deve_list must be removed now before clearing the
 	 * struct se_dev_entry pointers below as logic in
 	 * core_alua_do_transition_tg_pt() depends on these being present.
 	 *
 	 * deve->se_lun_acl will be NULL for demo-mode created LUNs
 	 * that have not been explicitly converted to MappedLUNs ->
-	 * struct se_lun_acl, but we remove deve->alua_port_list from
-	 * port->sep_alua_list. This also means that active UAs and
+	 * struct se_lun_acl, but we remove deve->lun_link from
+	 * lun->lun_deve_list. This also means that active UAs and
 	 * NodeACL context specific PR metadata for demo-mode
 	 * MappedLUN *deve will be released below..
 	 */
-	spin_lock_bh(&port->sep_alua_lock);
-	list_del(&deve->alua_port_list);
-	spin_unlock_bh(&port->sep_alua_lock);
-	/*
-	 * Wait for any in process SPEC_I_PT=1 or REGISTER_AND_MOVE
-	 * PR operation to complete.
-	 */
-	while (atomic_read(&deve->pr_ref_count) != 0)
-		cpu_relax();
-
-	spin_lock_irq(&nacl->device_list_lock);
+	spin_lock(&lun->lun_deve_lock);
+	list_del(&orig->lun_link);
+	spin_unlock(&lun->lun_deve_lock);
 	/*
 	 * Disable struct se_dev_entry LUN ACL mapping
 	 */
-	core_scsi3_ua_release_all(deve);
-	deve->se_lun = NULL;
-	deve->se_lun_acl = NULL;
-	deve->lun_flags = 0;
-	deve->creation_time = 0;
-	deve->attach_count--;
-	spin_unlock_irq(&nacl->device_list_lock);
+	core_scsi3_ua_release_all(orig);
 
-	core_scsi3_free_pr_reg_from_nacl(lun->lun_se_dev, nacl);
-	return 0;
+	hlist_del_rcu(&orig->link);
+	clear_bit(DEF_PR_REG_ACTIVE, &orig->deve_flags);
+	rcu_assign_pointer(orig->se_lun, NULL);
+	rcu_assign_pointer(orig->se_lun_acl, NULL);
+	orig->lun_flags = 0;
+	orig->creation_time = 0;
+	orig->attach_count--;
+	/*
+	 * Before firing off RCU callback, wait for any in process SPEC_I_PT=1
+	 * or REGISTER_AND_MOVE PR operation to complete.
+	 */
+	kref_put(&orig->pr_kref, target_pr_kref_release);
+	wait_for_completion(&orig->pr_comp);
+
+	kfree_rcu(orig, rcu_head);
+
+	core_scsi3_free_pr_reg_from_nacl(dev, nacl);
+	target_luns_data_has_changed(nacl, NULL, false);
 }
 
 /*      core_clear_lun_from_tpg():
@@ -432,53 +453,35 @@
 {
 	struct se_node_acl *nacl;
 	struct se_dev_entry *deve;
-	u32 i;
 
-	spin_lock_irq(&tpg->acl_node_lock);
+	mutex_lock(&tpg->acl_node_mutex);
 	list_for_each_entry(nacl, &tpg->acl_node_list, acl_list) {
-		spin_unlock_irq(&tpg->acl_node_lock);
 
-		spin_lock_irq(&nacl->device_list_lock);
-		for (i = 0; i < TRANSPORT_MAX_LUNS_PER_TPG; i++) {
-			deve = nacl->device_list[i];
-			if (lun != deve->se_lun)
+		mutex_lock(&nacl->lun_entry_mutex);
+		hlist_for_each_entry_rcu(deve, &nacl->lun_entry_hlist, link) {
+			struct se_lun *tmp_lun = rcu_dereference_check(deve->se_lun,
+					lockdep_is_held(&nacl->lun_entry_mutex));
+
+			if (lun != tmp_lun)
 				continue;
-			spin_unlock_irq(&nacl->device_list_lock);
 
-			core_disable_device_list_for_node(lun, NULL,
-				deve->mapped_lun, TRANSPORT_LUNFLAGS_NO_ACCESS,
-				nacl, tpg);
-
-			spin_lock_irq(&nacl->device_list_lock);
+			core_disable_device_list_for_node(lun, deve, nacl, tpg);
 		}
-		spin_unlock_irq(&nacl->device_list_lock);
-
-		spin_lock_irq(&tpg->acl_node_lock);
+		mutex_unlock(&nacl->lun_entry_mutex);
 	}
-	spin_unlock_irq(&tpg->acl_node_lock);
+	mutex_unlock(&tpg->acl_node_mutex);
 }
 
-static struct se_port *core_alloc_port(struct se_device *dev)
+int core_alloc_rtpi(struct se_lun *lun, struct se_device *dev)
 {
-	struct se_port *port, *port_tmp;
-
-	port = kzalloc(sizeof(struct se_port), GFP_KERNEL);
-	if (!port) {
-		pr_err("Unable to allocate struct se_port\n");
-		return ERR_PTR(-ENOMEM);
-	}
-	INIT_LIST_HEAD(&port->sep_alua_list);
-	INIT_LIST_HEAD(&port->sep_list);
-	atomic_set(&port->sep_tg_pt_secondary_offline, 0);
-	spin_lock_init(&port->sep_alua_lock);
-	mutex_init(&port->sep_tg_pt_md_mutex);
+	struct se_lun *tmp;
 
 	spin_lock(&dev->se_port_lock);
-	if (dev->dev_port_count == 0x0000ffff) {
+	if (dev->export_count == 0x0000ffff) {
 		pr_warn("Reached dev->dev_port_count =="
 				" 0x0000ffff\n");
 		spin_unlock(&dev->se_port_lock);
-		return ERR_PTR(-ENOSPC);
+		return -ENOSPC;
 	}
 again:
 	/*
@@ -493,133 +496,23 @@
 	 * 2h        Relative port 2, historically known as port B
 	 * 3h to FFFFh    Relative port 3 through 65 535
 	 */
-	port->sep_rtpi = dev->dev_rpti_counter++;
-	if (!port->sep_rtpi)
+	lun->lun_rtpi = dev->dev_rpti_counter++;
+	if (!lun->lun_rtpi)
 		goto again;
 
-	list_for_each_entry(port_tmp, &dev->dev_sep_list, sep_list) {
+	list_for_each_entry(tmp, &dev->dev_sep_list, lun_dev_link) {
 		/*
 		 * Make sure RELATIVE TARGET PORT IDENTIFIER is unique
 		 * for 16-bit wrap..
 		 */
-		if (port->sep_rtpi == port_tmp->sep_rtpi)
+		if (lun->lun_rtpi == tmp->lun_rtpi)
 			goto again;
 	}
 	spin_unlock(&dev->se_port_lock);
 
-	return port;
-}
-
-static void core_export_port(
-	struct se_device *dev,
-	struct se_portal_group *tpg,
-	struct se_port *port,
-	struct se_lun *lun)
-{
-	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem = NULL;
-
-	spin_lock(&dev->se_port_lock);
-	spin_lock(&lun->lun_sep_lock);
-	port->sep_tpg = tpg;
-	port->sep_lun = lun;
-	lun->lun_sep = port;
-	spin_unlock(&lun->lun_sep_lock);
-
-	list_add_tail(&port->sep_list, &dev->dev_sep_list);
-	spin_unlock(&dev->se_port_lock);
-
-	if (!(dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) &&
-	    !(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)) {
-		tg_pt_gp_mem = core_alua_allocate_tg_pt_gp_mem(port);
-		if (IS_ERR(tg_pt_gp_mem) || !tg_pt_gp_mem) {
-			pr_err("Unable to allocate t10_alua_tg_pt"
-					"_gp_member_t\n");
-			return;
-		}
-		spin_lock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
-		__core_alua_attach_tg_pt_gp_mem(tg_pt_gp_mem,
-			dev->t10_alua.default_tg_pt_gp);
-		spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
-		pr_debug("%s/%s: Adding to default ALUA Target Port"
-			" Group: alua/default_tg_pt_gp\n",
-			dev->transport->name, tpg->se_tpg_tfo->get_fabric_name());
-	}
-
-	dev->dev_port_count++;
-	port->sep_index = port->sep_rtpi; /* RELATIVE TARGET PORT IDENTIFIER */
-}
-
-/*
- *	Called with struct se_device->se_port_lock spinlock held.
- */
-static void core_release_port(struct se_device *dev, struct se_port *port)
-	__releases(&dev->se_port_lock) __acquires(&dev->se_port_lock)
-{
-	/*
-	 * Wait for any port reference for PR ALL_TG_PT=1 operation
-	 * to complete in __core_scsi3_alloc_registration()
-	 */
-	spin_unlock(&dev->se_port_lock);
-	if (atomic_read(&port->sep_tg_pt_ref_cnt))
-		cpu_relax();
-	spin_lock(&dev->se_port_lock);
-
-	core_alua_free_tg_pt_gp_mem(port);
-
-	list_del(&port->sep_list);
-	dev->dev_port_count--;
-	kfree(port);
-}
-
-int core_dev_export(
-	struct se_device *dev,
-	struct se_portal_group *tpg,
-	struct se_lun *lun)
-{
-	struct se_hba *hba = dev->se_hba;
-	struct se_port *port;
-
-	port = core_alloc_port(dev);
-	if (IS_ERR(port))
-		return PTR_ERR(port);
-
-	lun->lun_se_dev = dev;
-
-	spin_lock(&hba->device_lock);
-	dev->export_count++;
-	spin_unlock(&hba->device_lock);
-
-	core_export_port(dev, tpg, port, lun);
 	return 0;
 }
 
-void core_dev_unexport(
-	struct se_device *dev,
-	struct se_portal_group *tpg,
-	struct se_lun *lun)
-{
-	struct se_hba *hba = dev->se_hba;
-	struct se_port *port = lun->lun_sep;
-
-	spin_lock(&lun->lun_sep_lock);
-	if (lun->lun_se_dev == NULL) {
-		spin_unlock(&lun->lun_sep_lock);
-		return;
-	}
-	spin_unlock(&lun->lun_sep_lock);
-
-	spin_lock(&dev->se_port_lock);
-	core_release_port(dev, port);
-	spin_unlock(&dev->se_port_lock);
-
-	spin_lock(&hba->device_lock);
-	dev->export_count--;
-	spin_unlock(&hba->device_lock);
-
-	lun->lun_sep = NULL;
-	lun->lun_se_dev = NULL;
-}
-
 static void se_release_vpd_for_dev(struct se_device *dev)
 {
 	struct t10_vpd *vpd, *vpd_tmp;
@@ -651,556 +544,19 @@
 	return aligned_max_sectors;
 }
 
-bool se_dev_check_wce(struct se_device *dev)
-{
-	bool wce = false;
-
-	if (dev->transport->get_write_cache)
-		wce = dev->transport->get_write_cache(dev);
-	else if (dev->dev_attrib.emulate_write_cache > 0)
-		wce = true;
-
-	return wce;
-}
-
-int se_dev_set_max_unmap_lba_count(
-	struct se_device *dev,
-	u32 max_unmap_lba_count)
-{
-	dev->dev_attrib.max_unmap_lba_count = max_unmap_lba_count;
-	pr_debug("dev[%p]: Set max_unmap_lba_count: %u\n",
-			dev, dev->dev_attrib.max_unmap_lba_count);
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_max_unmap_lba_count);
-
-int se_dev_set_max_unmap_block_desc_count(
-	struct se_device *dev,
-	u32 max_unmap_block_desc_count)
-{
-	dev->dev_attrib.max_unmap_block_desc_count =
-		max_unmap_block_desc_count;
-	pr_debug("dev[%p]: Set max_unmap_block_desc_count: %u\n",
-			dev, dev->dev_attrib.max_unmap_block_desc_count);
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_max_unmap_block_desc_count);
-
-int se_dev_set_unmap_granularity(
-	struct se_device *dev,
-	u32 unmap_granularity)
-{
-	dev->dev_attrib.unmap_granularity = unmap_granularity;
-	pr_debug("dev[%p]: Set unmap_granularity: %u\n",
-			dev, dev->dev_attrib.unmap_granularity);
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_unmap_granularity);
-
-int se_dev_set_unmap_granularity_alignment(
-	struct se_device *dev,
-	u32 unmap_granularity_alignment)
-{
-	dev->dev_attrib.unmap_granularity_alignment = unmap_granularity_alignment;
-	pr_debug("dev[%p]: Set unmap_granularity_alignment: %u\n",
-			dev, dev->dev_attrib.unmap_granularity_alignment);
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_unmap_granularity_alignment);
-
-int se_dev_set_max_write_same_len(
-	struct se_device *dev,
-	u32 max_write_same_len)
-{
-	dev->dev_attrib.max_write_same_len = max_write_same_len;
-	pr_debug("dev[%p]: Set max_write_same_len: %u\n",
-			dev, dev->dev_attrib.max_write_same_len);
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_max_write_same_len);
-
-static void dev_set_t10_wwn_model_alias(struct se_device *dev)
-{
-	const char *configname;
-
-	configname = config_item_name(&dev->dev_group.cg_item);
-	if (strlen(configname) >= 16) {
-		pr_warn("dev[%p]: Backstore name '%s' is too long for "
-			"INQUIRY_MODEL, truncating to 16 bytes\n", dev,
-			configname);
-	}
-	snprintf(&dev->t10_wwn.model[0], 16, "%s", configname);
-}
-
-int se_dev_set_emulate_model_alias(struct se_device *dev, int flag)
-{
-	if (dev->export_count) {
-		pr_err("dev[%p]: Unable to change model alias"
-			" while export_count is %d\n",
-			dev, dev->export_count);
-			return -EINVAL;
-	}
-
-	if (flag != 0 && flag != 1) {
-		pr_err("Illegal value %d\n", flag);
-		return -EINVAL;
-	}
-
-	if (flag) {
-		dev_set_t10_wwn_model_alias(dev);
-	} else {
-		strncpy(&dev->t10_wwn.model[0],
-			dev->transport->inquiry_prod, 16);
-	}
-	dev->dev_attrib.emulate_model_alias = flag;
-
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_emulate_model_alias);
-
-int se_dev_set_emulate_dpo(struct se_device *dev, int flag)
-{
-	if (flag != 0 && flag != 1) {
-		pr_err("Illegal value %d\n", flag);
-		return -EINVAL;
-	}
-
-	if (flag) {
-		pr_err("dpo_emulated not supported\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_emulate_dpo);
-
-int se_dev_set_emulate_fua_write(struct se_device *dev, int flag)
-{
-	if (flag != 0 && flag != 1) {
-		pr_err("Illegal value %d\n", flag);
-		return -EINVAL;
-	}
-	if (flag &&
-	    dev->transport->get_write_cache) {
-		pr_warn("emulate_fua_write not supported for this device, ignoring\n");
-		return 0;
-	}
-	if (dev->export_count) {
-		pr_err("emulate_fua_write cannot be changed with active"
-		       " exports: %d\n", dev->export_count);
-		return -EINVAL;
-	}
-	dev->dev_attrib.emulate_fua_write = flag;
-	pr_debug("dev[%p]: SE Device Forced Unit Access WRITEs: %d\n",
-			dev, dev->dev_attrib.emulate_fua_write);
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_emulate_fua_write);
-
-int se_dev_set_emulate_fua_read(struct se_device *dev, int flag)
-{
-	if (flag != 0 && flag != 1) {
-		pr_err("Illegal value %d\n", flag);
-		return -EINVAL;
-	}
-
-	if (flag) {
-		pr_err("ua read emulated not supported\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_emulate_fua_read);
-
-int se_dev_set_emulate_write_cache(struct se_device *dev, int flag)
-{
-	if (flag != 0 && flag != 1) {
-		pr_err("Illegal value %d\n", flag);
-		return -EINVAL;
-	}
-	if (flag &&
-	    dev->transport->get_write_cache) {
-		pr_err("emulate_write_cache not supported for this device\n");
-		return -EINVAL;
-	}
-	if (dev->export_count) {
-		pr_err("emulate_write_cache cannot be changed with active"
-		       " exports: %d\n", dev->export_count);
-		return -EINVAL;
-	}
-	dev->dev_attrib.emulate_write_cache = flag;
-	pr_debug("dev[%p]: SE Device WRITE_CACHE_EMULATION flag: %d\n",
-			dev, dev->dev_attrib.emulate_write_cache);
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_emulate_write_cache);
-
-int se_dev_set_emulate_ua_intlck_ctrl(struct se_device *dev, int flag)
-{
-	if ((flag != 0) && (flag != 1) && (flag != 2)) {
-		pr_err("Illegal value %d\n", flag);
-		return -EINVAL;
-	}
-
-	if (dev->export_count) {
-		pr_err("dev[%p]: Unable to change SE Device"
-			" UA_INTRLCK_CTRL while export_count is %d\n",
-			dev, dev->export_count);
-		return -EINVAL;
-	}
-	dev->dev_attrib.emulate_ua_intlck_ctrl = flag;
-	pr_debug("dev[%p]: SE Device UA_INTRLCK_CTRL flag: %d\n",
-		dev, dev->dev_attrib.emulate_ua_intlck_ctrl);
-
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_emulate_ua_intlck_ctrl);
-
-int se_dev_set_emulate_tas(struct se_device *dev, int flag)
-{
-	if ((flag != 0) && (flag != 1)) {
-		pr_err("Illegal value %d\n", flag);
-		return -EINVAL;
-	}
-
-	if (dev->export_count) {
-		pr_err("dev[%p]: Unable to change SE Device TAS while"
-			" export_count is %d\n",
-			dev, dev->export_count);
-		return -EINVAL;
-	}
-	dev->dev_attrib.emulate_tas = flag;
-	pr_debug("dev[%p]: SE Device TASK_ABORTED status bit: %s\n",
-		dev, (dev->dev_attrib.emulate_tas) ? "Enabled" : "Disabled");
-
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_emulate_tas);
-
-int se_dev_set_emulate_tpu(struct se_device *dev, int flag)
-{
-	if ((flag != 0) && (flag != 1)) {
-		pr_err("Illegal value %d\n", flag);
-		return -EINVAL;
-	}
-	/*
-	 * We expect this value to be non-zero when generic Block Layer
-	 * Discard supported is detected iblock_create_virtdevice().
-	 */
-	if (flag && !dev->dev_attrib.max_unmap_block_desc_count) {
-		pr_err("Generic Block Discard not supported\n");
-		return -ENOSYS;
-	}
-
-	dev->dev_attrib.emulate_tpu = flag;
-	pr_debug("dev[%p]: SE Device Thin Provisioning UNMAP bit: %d\n",
-				dev, flag);
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_emulate_tpu);
-
-int se_dev_set_emulate_tpws(struct se_device *dev, int flag)
-{
-	if ((flag != 0) && (flag != 1)) {
-		pr_err("Illegal value %d\n", flag);
-		return -EINVAL;
-	}
-	/*
-	 * We expect this value to be non-zero when generic Block Layer
-	 * Discard supported is detected iblock_create_virtdevice().
-	 */
-	if (flag && !dev->dev_attrib.max_unmap_block_desc_count) {
-		pr_err("Generic Block Discard not supported\n");
-		return -ENOSYS;
-	}
-
-	dev->dev_attrib.emulate_tpws = flag;
-	pr_debug("dev[%p]: SE Device Thin Provisioning WRITE_SAME: %d\n",
-				dev, flag);
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_emulate_tpws);
-
-int se_dev_set_emulate_caw(struct se_device *dev, int flag)
-{
-	if (flag != 0 && flag != 1) {
-		pr_err("Illegal value %d\n", flag);
-		return -EINVAL;
-	}
-	dev->dev_attrib.emulate_caw = flag;
-	pr_debug("dev[%p]: SE Device CompareAndWrite (AtomicTestandSet): %d\n",
-		 dev, flag);
-
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_emulate_caw);
-
-int se_dev_set_emulate_3pc(struct se_device *dev, int flag)
-{
-	if (flag != 0 && flag != 1) {
-		pr_err("Illegal value %d\n", flag);
-		return -EINVAL;
-	}
-	dev->dev_attrib.emulate_3pc = flag;
-	pr_debug("dev[%p]: SE Device 3rd Party Copy (EXTENDED_COPY): %d\n",
-		dev, flag);
-
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_emulate_3pc);
-
-int se_dev_set_pi_prot_type(struct se_device *dev, int flag)
-{
-	int rc, old_prot = dev->dev_attrib.pi_prot_type;
-
-	if (flag != 0 && flag != 1 && flag != 2 && flag != 3) {
-		pr_err("Illegal value %d for pi_prot_type\n", flag);
-		return -EINVAL;
-	}
-	if (flag == 2) {
-		pr_err("DIF TYPE2 protection currently not supported\n");
-		return -ENOSYS;
-	}
-	if (dev->dev_attrib.hw_pi_prot_type) {
-		pr_warn("DIF protection enabled on underlying hardware,"
-			" ignoring\n");
-		return 0;
-	}
-	if (!dev->transport->init_prot || !dev->transport->free_prot) {
-		/* 0 is only allowed value for non-supporting backends */
-		if (flag == 0)
-			return 0;
-
-		pr_err("DIF protection not supported by backend: %s\n",
-		       dev->transport->name);
-		return -ENOSYS;
-	}
-	if (!(dev->dev_flags & DF_CONFIGURED)) {
-		pr_err("DIF protection requires device to be configured\n");
-		return -ENODEV;
-	}
-	if (dev->export_count) {
-		pr_err("dev[%p]: Unable to change SE Device PROT type while"
-		       " export_count is %d\n", dev, dev->export_count);
-		return -EINVAL;
-	}
-
-	dev->dev_attrib.pi_prot_type = flag;
-
-	if (flag && !old_prot) {
-		rc = dev->transport->init_prot(dev);
-		if (rc) {
-			dev->dev_attrib.pi_prot_type = old_prot;
-			return rc;
-		}
-
-	} else if (!flag && old_prot) {
-		dev->transport->free_prot(dev);
-	}
-	pr_debug("dev[%p]: SE Device Protection Type: %d\n", dev, flag);
-
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_pi_prot_type);
-
-int se_dev_set_pi_prot_format(struct se_device *dev, int flag)
-{
-	int rc;
-
-	if (!flag)
-		return 0;
-
-	if (flag != 1) {
-		pr_err("Illegal value %d for pi_prot_format\n", flag);
-		return -EINVAL;
-	}
-	if (!dev->transport->format_prot) {
-		pr_err("DIF protection format not supported by backend %s\n",
-		       dev->transport->name);
-		return -ENOSYS;
-	}
-	if (!(dev->dev_flags & DF_CONFIGURED)) {
-		pr_err("DIF protection format requires device to be configured\n");
-		return -ENODEV;
-	}
-	if (dev->export_count) {
-		pr_err("dev[%p]: Unable to format SE Device PROT type while"
-		       " export_count is %d\n", dev, dev->export_count);
-		return -EINVAL;
-	}
-
-	rc = dev->transport->format_prot(dev);
-	if (rc)
-		return rc;
-
-	pr_debug("dev[%p]: SE Device Protection Format complete\n", dev);
-
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_pi_prot_format);
-
-int se_dev_set_enforce_pr_isids(struct se_device *dev, int flag)
-{
-	if ((flag != 0) && (flag != 1)) {
-		pr_err("Illegal value %d\n", flag);
-		return -EINVAL;
-	}
-	dev->dev_attrib.enforce_pr_isids = flag;
-	pr_debug("dev[%p]: SE Device enforce_pr_isids bit: %s\n", dev,
-		(dev->dev_attrib.enforce_pr_isids) ? "Enabled" : "Disabled");
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_enforce_pr_isids);
-
-int se_dev_set_force_pr_aptpl(struct se_device *dev, int flag)
-{
-	if ((flag != 0) && (flag != 1)) {
-		printk(KERN_ERR "Illegal value %d\n", flag);
-		return -EINVAL;
-	}
-	if (dev->export_count) {
-		pr_err("dev[%p]: Unable to set force_pr_aptpl while"
-		       " export_count is %d\n", dev, dev->export_count);
-		return -EINVAL;
-	}
-
-	dev->dev_attrib.force_pr_aptpl = flag;
-	pr_debug("dev[%p]: SE Device force_pr_aptpl: %d\n", dev, flag);
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_force_pr_aptpl);
-
-int se_dev_set_is_nonrot(struct se_device *dev, int flag)
-{
-	if ((flag != 0) && (flag != 1)) {
-		printk(KERN_ERR "Illegal value %d\n", flag);
-		return -EINVAL;
-	}
-	dev->dev_attrib.is_nonrot = flag;
-	pr_debug("dev[%p]: SE Device is_nonrot bit: %d\n",
-	       dev, flag);
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_is_nonrot);
-
-int se_dev_set_emulate_rest_reord(struct se_device *dev, int flag)
-{
-	if (flag != 0) {
-		printk(KERN_ERR "dev[%p]: SE Device emulatation of restricted"
-			" reordering not implemented\n", dev);
-		return -ENOSYS;
-	}
-	dev->dev_attrib.emulate_rest_reord = flag;
-	pr_debug("dev[%p]: SE Device emulate_rest_reord: %d\n", dev, flag);
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_emulate_rest_reord);
-
-/*
- * Note, this can only be called on unexported SE Device Object.
- */
-int se_dev_set_queue_depth(struct se_device *dev, u32 queue_depth)
-{
-	if (dev->export_count) {
-		pr_err("dev[%p]: Unable to change SE Device TCQ while"
-			" export_count is %d\n",
-			dev, dev->export_count);
-		return -EINVAL;
-	}
-	if (!queue_depth) {
-		pr_err("dev[%p]: Illegal ZERO value for queue"
-			"_depth\n", dev);
-		return -EINVAL;
-	}
-
-	if (queue_depth > dev->dev_attrib.queue_depth) {
-		if (queue_depth > dev->dev_attrib.hw_queue_depth) {
-			pr_err("dev[%p]: Passed queue_depth:"
-				" %u exceeds TCM/SE_Device MAX"
-				" TCQ: %u\n", dev, queue_depth,
-				dev->dev_attrib.hw_queue_depth);
-			return -EINVAL;
-		}
-	}
-	dev->dev_attrib.queue_depth = dev->queue_depth = queue_depth;
-	pr_debug("dev[%p]: SE Device TCQ Depth changed to: %u\n",
-			dev, queue_depth);
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_queue_depth);
-
-int se_dev_set_optimal_sectors(struct se_device *dev, u32 optimal_sectors)
-{
-	if (dev->export_count) {
-		pr_err("dev[%p]: Unable to change SE Device"
-			" optimal_sectors while export_count is %d\n",
-			dev, dev->export_count);
-		return -EINVAL;
-	}
-	if (optimal_sectors > dev->dev_attrib.hw_max_sectors) {
-		pr_err("dev[%p]: Passed optimal_sectors %u cannot be"
-			" greater than hw_max_sectors: %u\n", dev,
-			optimal_sectors, dev->dev_attrib.hw_max_sectors);
-		return -EINVAL;
-	}
-
-	dev->dev_attrib.optimal_sectors = optimal_sectors;
-	pr_debug("dev[%p]: SE Device optimal_sectors changed to %u\n",
-			dev, optimal_sectors);
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_optimal_sectors);
-
-int se_dev_set_block_size(struct se_device *dev, u32 block_size)
-{
-	if (dev->export_count) {
-		pr_err("dev[%p]: Unable to change SE Device block_size"
-			" while export_count is %d\n",
-			dev, dev->export_count);
-		return -EINVAL;
-	}
-
-	if ((block_size != 512) &&
-	    (block_size != 1024) &&
-	    (block_size != 2048) &&
-	    (block_size != 4096)) {
-		pr_err("dev[%p]: Illegal value for block_device: %u"
-			" for SE device, must be 512, 1024, 2048 or 4096\n",
-			dev, block_size);
-		return -EINVAL;
-	}
-
-	dev->dev_attrib.block_size = block_size;
-	pr_debug("dev[%p]: SE Device block_size changed to %u\n",
-			dev, block_size);
-
-	if (dev->dev_attrib.max_bytes_per_io)
-		dev->dev_attrib.hw_max_sectors =
-			dev->dev_attrib.max_bytes_per_io / block_size;
-
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_block_size);
-
-struct se_lun *core_dev_add_lun(
+int core_dev_add_lun(
 	struct se_portal_group *tpg,
 	struct se_device *dev,
-	u32 unpacked_lun)
+	struct se_lun *lun)
 {
-	struct se_lun *lun;
 	int rc;
 
-	lun = core_tpg_alloc_lun(tpg, unpacked_lun);
-	if (IS_ERR(lun))
-		return lun;
-
 	rc = core_tpg_add_lun(tpg, lun,
 				TRANSPORT_LUNFLAGS_READ_WRITE, dev);
 	if (rc < 0)
-		return ERR_PTR(rc);
+		return rc;
 
-	pr_debug("%s_TPG[%u]_LUN[%u] - Activated %s Logical Unit from"
+	pr_debug("%s_TPG[%u]_LUN[%llu] - Activated %s Logical Unit from"
 		" CORE HBA: %u\n", tpg->se_tpg_tfo->get_fabric_name(),
 		tpg->se_tpg_tfo->tpg_get_tag(tpg), lun->unpacked_lun,
 		tpg->se_tpg_tfo->get_fabric_name(), dev->se_hba->hba_id);
@@ -1210,20 +566,19 @@
 	 */
 	if (tpg->se_tpg_tfo->tpg_check_demo_mode(tpg)) {
 		struct se_node_acl *acl;
-		spin_lock_irq(&tpg->acl_node_lock);
+
+		mutex_lock(&tpg->acl_node_mutex);
 		list_for_each_entry(acl, &tpg->acl_node_list, acl_list) {
 			if (acl->dynamic_node_acl &&
 			    (!tpg->se_tpg_tfo->tpg_check_demo_mode_login_only ||
 			     !tpg->se_tpg_tfo->tpg_check_demo_mode_login_only(tpg))) {
-				spin_unlock_irq(&tpg->acl_node_lock);
-				core_tpg_add_node_to_devs(acl, tpg);
-				spin_lock_irq(&tpg->acl_node_lock);
+				core_tpg_add_node_to_devs(acl, tpg, lun);
 			}
 		}
-		spin_unlock_irq(&tpg->acl_node_lock);
+		mutex_unlock(&tpg->acl_node_mutex);
 	}
 
-	return lun;
+	return 0;
 }
 
 /*      core_dev_del_lun():
@@ -1234,7 +589,7 @@
 	struct se_portal_group *tpg,
 	struct se_lun *lun)
 {
-	pr_debug("%s_TPG[%u]_LUN[%u] - Deactivating %s Logical Unit from"
+	pr_debug("%s_TPG[%u]_LUN[%llu] - Deactivating %s Logical Unit from"
 		" device object\n", tpg->se_tpg_tfo->get_fabric_name(),
 		tpg->se_tpg_tfo->tpg_get_tag(tpg), lun->unpacked_lun,
 		tpg->se_tpg_tfo->get_fabric_name());
@@ -1242,72 +597,10 @@
 	core_tpg_remove_lun(tpg, lun);
 }
 
-struct se_lun *core_get_lun_from_tpg(struct se_portal_group *tpg, u32 unpacked_lun)
-{
-	struct se_lun *lun;
-
-	spin_lock(&tpg->tpg_lun_lock);
-	if (unpacked_lun > (TRANSPORT_MAX_LUNS_PER_TPG-1)) {
-		pr_err("%s LUN: %u exceeds TRANSPORT_MAX_LUNS"
-			"_PER_TPG-1: %u for Target Portal Group: %hu\n",
-			tpg->se_tpg_tfo->get_fabric_name(), unpacked_lun,
-			TRANSPORT_MAX_LUNS_PER_TPG-1,
-			tpg->se_tpg_tfo->tpg_get_tag(tpg));
-		spin_unlock(&tpg->tpg_lun_lock);
-		return NULL;
-	}
-	lun = tpg->tpg_lun_list[unpacked_lun];
-
-	if (lun->lun_status != TRANSPORT_LUN_STATUS_FREE) {
-		pr_err("%s Logical Unit Number: %u is not free on"
-			" Target Portal Group: %hu, ignoring request.\n",
-			tpg->se_tpg_tfo->get_fabric_name(), unpacked_lun,
-			tpg->se_tpg_tfo->tpg_get_tag(tpg));
-		spin_unlock(&tpg->tpg_lun_lock);
-		return NULL;
-	}
-	spin_unlock(&tpg->tpg_lun_lock);
-
-	return lun;
-}
-
-/*      core_dev_get_lun():
- *
- *
- */
-static struct se_lun *core_dev_get_lun(struct se_portal_group *tpg, u32 unpacked_lun)
-{
-	struct se_lun *lun;
-
-	spin_lock(&tpg->tpg_lun_lock);
-	if (unpacked_lun > (TRANSPORT_MAX_LUNS_PER_TPG-1)) {
-		pr_err("%s LUN: %u exceeds TRANSPORT_MAX_LUNS_PER"
-			"_TPG-1: %u for Target Portal Group: %hu\n",
-			tpg->se_tpg_tfo->get_fabric_name(), unpacked_lun,
-			TRANSPORT_MAX_LUNS_PER_TPG-1,
-			tpg->se_tpg_tfo->tpg_get_tag(tpg));
-		spin_unlock(&tpg->tpg_lun_lock);
-		return NULL;
-	}
-	lun = tpg->tpg_lun_list[unpacked_lun];
-
-	if (lun->lun_status != TRANSPORT_LUN_STATUS_ACTIVE) {
-		pr_err("%s Logical Unit Number: %u is not active on"
-			" Target Portal Group: %hu, ignoring request.\n",
-			tpg->se_tpg_tfo->get_fabric_name(), unpacked_lun,
-			tpg->se_tpg_tfo->tpg_get_tag(tpg));
-		spin_unlock(&tpg->tpg_lun_lock);
-		return NULL;
-	}
-	spin_unlock(&tpg->tpg_lun_lock);
-
-	return lun;
-}
-
 struct se_lun_acl *core_dev_init_initiator_node_lun_acl(
 	struct se_portal_group *tpg,
 	struct se_node_acl *nacl,
-	u32 mapped_lun,
+	u64 mapped_lun,
 	int *ret)
 {
 	struct se_lun_acl *lacl;
@@ -1325,7 +618,6 @@
 		return NULL;
 	}
 
-	INIT_LIST_HEAD(&lacl->lacl_list);
 	lacl->mapped_lun = mapped_lun;
 	lacl->se_lun_nacl = nacl;
 	snprintf(lacl->initiatorname, TRANSPORT_IQN_LEN, "%s",
@@ -1337,22 +629,16 @@
 int core_dev_add_initiator_node_lun_acl(
 	struct se_portal_group *tpg,
 	struct se_lun_acl *lacl,
-	u32 unpacked_lun,
+	struct se_lun *lun,
 	u32 lun_access)
 {
-	struct se_lun *lun;
-	struct se_node_acl *nacl;
+	struct se_node_acl *nacl = lacl->se_lun_nacl;
+	/*
+	 * rcu_dereference_raw protected by se_lun->lun_group symlink
+	 * reference to se_device->dev_group.
+	 */
+	struct se_device *dev = rcu_dereference_raw(lun->lun_se_dev);
 
-	lun = core_dev_get_lun(tpg, unpacked_lun);
-	if (!lun) {
-		pr_err("%s Logical Unit Number: %u is not active on"
-			" Target Portal Group: %hu, ignoring request.\n",
-			tpg->se_tpg_tfo->get_fabric_name(), unpacked_lun,
-			tpg->se_tpg_tfo->tpg_get_tag(tpg));
-		return -EINVAL;
-	}
-
-	nacl = lacl->se_lun_nacl;
 	if (!nacl)
 		return -EINVAL;
 
@@ -1366,52 +652,40 @@
 			lun_access, nacl, tpg) < 0)
 		return -EINVAL;
 
-	spin_lock(&lun->lun_acl_lock);
-	list_add_tail(&lacl->lacl_list, &lun->lun_acl_list);
-	atomic_inc_mb(&lun->lun_acl_count);
-	spin_unlock(&lun->lun_acl_lock);
-
-	pr_debug("%s_TPG[%hu]_LUN[%u->%u] - Added %s ACL for "
+	pr_debug("%s_TPG[%hu]_LUN[%llu->%llu] - Added %s ACL for "
 		" InitiatorNode: %s\n", tpg->se_tpg_tfo->get_fabric_name(),
-		tpg->se_tpg_tfo->tpg_get_tag(tpg), unpacked_lun, lacl->mapped_lun,
+		tpg->se_tpg_tfo->tpg_get_tag(tpg), lun->unpacked_lun, lacl->mapped_lun,
 		(lun_access & TRANSPORT_LUNFLAGS_READ_WRITE) ? "RW" : "RO",
 		lacl->initiatorname);
 	/*
 	 * Check to see if there are any existing persistent reservation APTPL
 	 * pre-registrations that need to be enabled for this LUN ACL..
 	 */
-	core_scsi3_check_aptpl_registration(lun->lun_se_dev, tpg, lun, nacl,
+	core_scsi3_check_aptpl_registration(dev, tpg, lun, nacl,
 					    lacl->mapped_lun);
 	return 0;
 }
 
-/*      core_dev_del_initiator_node_lun_acl():
- *
- *
- */
 int core_dev_del_initiator_node_lun_acl(
-	struct se_portal_group *tpg,
 	struct se_lun *lun,
 	struct se_lun_acl *lacl)
 {
+	struct se_portal_group *tpg = lun->lun_tpg;
 	struct se_node_acl *nacl;
+	struct se_dev_entry *deve;
 
 	nacl = lacl->se_lun_nacl;
 	if (!nacl)
 		return -EINVAL;
 
-	spin_lock(&lun->lun_acl_lock);
-	list_del(&lacl->lacl_list);
-	atomic_dec_mb(&lun->lun_acl_count);
-	spin_unlock(&lun->lun_acl_lock);
+	mutex_lock(&nacl->lun_entry_mutex);
+	deve = target_nacl_find_deve(nacl, lacl->mapped_lun);
+	if (deve)
+		core_disable_device_list_for_node(lun, deve, nacl, tpg);
+	mutex_unlock(&nacl->lun_entry_mutex);
 
-	core_disable_device_list_for_node(lun, NULL, lacl->mapped_lun,
-		TRANSPORT_LUNFLAGS_NO_ACCESS, nacl, tpg);
-
-	lacl->se_lun = NULL;
-
-	pr_debug("%s_TPG[%hu]_LUN[%u] - Removed ACL for"
-		" InitiatorNode: %s Mapped LUN: %u\n",
+	pr_debug("%s_TPG[%hu]_LUN[%llu] - Removed ACL for"
+		" InitiatorNode: %s Mapped LUN: %llu\n",
 		tpg->se_tpg_tfo->get_fabric_name(),
 		tpg->se_tpg_tfo->tpg_get_tag(tpg), lun->unpacked_lun,
 		lacl->initiatorname, lacl->mapped_lun);
@@ -1424,7 +698,7 @@
 	struct se_lun_acl *lacl)
 {
 	pr_debug("%s_TPG[%hu] - Freeing ACL for %s InitiatorNode: %s"
-		" Mapped LUN: %u\n", tpg->se_tpg_tfo->get_fabric_name(),
+		" Mapped LUN: %llu\n", tpg->se_tpg_tfo->get_fabric_name(),
 		tpg->se_tpg_tfo->tpg_get_tag(tpg),
 		tpg->se_tpg_tfo->get_fabric_name(),
 		lacl->initiatorname, lacl->mapped_lun);
@@ -1473,14 +747,15 @@
 	struct se_device *dev;
 	struct se_lun *xcopy_lun;
 
-	dev = hba->transport->alloc_device(hba, name);
+	dev = hba->backend->ops->alloc_device(hba, name);
 	if (!dev)
 		return NULL;
 
 	dev->dev_link_magic = SE_DEV_LINK_MAGIC;
 	dev->se_hba = hba;
-	dev->transport = hba->transport;
+	dev->transport = hba->backend->ops;
 	dev->prot_length = sizeof(struct se_dif_v1_tuple);
+	dev->hba_index = hba->hba_index;
 
 	INIT_LIST_HEAD(&dev->dev_list);
 	INIT_LIST_HEAD(&dev->dev_sep_list);
@@ -1513,9 +788,9 @@
 
 	dev->dev_attrib.da_dev = dev;
 	dev->dev_attrib.emulate_model_alias = DA_EMULATE_MODEL_ALIAS;
-	dev->dev_attrib.emulate_dpo = DA_EMULATE_DPO;
-	dev->dev_attrib.emulate_fua_write = DA_EMULATE_FUA_WRITE;
-	dev->dev_attrib.emulate_fua_read = DA_EMULATE_FUA_READ;
+	dev->dev_attrib.emulate_dpo = 1;
+	dev->dev_attrib.emulate_fua_write = 1;
+	dev->dev_attrib.emulate_fua_read = 1;
 	dev->dev_attrib.emulate_write_cache = DA_EMULATE_WRITE_CACHE;
 	dev->dev_attrib.emulate_ua_intlck_ctrl = DA_EMULATE_UA_INTLLCK_CTRL;
 	dev->dev_attrib.emulate_tas = DA_EMULATE_TAS;
@@ -1537,12 +812,12 @@
 	dev->dev_attrib.max_write_same_len = DA_MAX_WRITE_SAME_LEN;
 
 	xcopy_lun = &dev->xcopy_lun;
-	xcopy_lun->lun_se_dev = dev;
-	init_completion(&xcopy_lun->lun_shutdown_comp);
-	INIT_LIST_HEAD(&xcopy_lun->lun_acl_list);
-	spin_lock_init(&xcopy_lun->lun_acl_lock);
-	spin_lock_init(&xcopy_lun->lun_sep_lock);
+	rcu_assign_pointer(xcopy_lun->lun_se_dev, dev);
 	init_completion(&xcopy_lun->lun_ref_comp);
+	INIT_LIST_HEAD(&xcopy_lun->lun_deve_list);
+	INIT_LIST_HEAD(&xcopy_lun->lun_dev_link);
+	mutex_init(&xcopy_lun->lun_tg_pt_md_mutex);
+	xcopy_lun->lun_tpg = &xcopy_pt_tpg;
 
 	return dev;
 }
@@ -1679,7 +954,7 @@
 		goto out_free_hba;
 	}
 
-	hba->transport->set_configfs_dev_params(dev, buf, sizeof(buf));
+	hba->backend->ops->set_configfs_dev_params(dev, buf, sizeof(buf));
 
 	ret = target_configure_device(dev);
 	if (ret)
diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c
index 1f7886b..48a3698 100644
--- a/drivers/target/target_core_fabric_configfs.c
+++ b/drivers/target/target_core_fabric_configfs.c
@@ -36,7 +36,6 @@
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
 #include <target/target_core_fabric_configfs.h>
-#include <target/target_core_configfs.h>
 #include <target/configfs_macros.h>
 
 #include "target_core_internal.h"
@@ -46,27 +45,25 @@
 #define TF_CIT_SETUP(_name, _item_ops, _group_ops, _attrs)		\
 static void target_fabric_setup_##_name##_cit(struct target_fabric_configfs *tf) \
 {									\
-	struct target_fabric_configfs_template *tfc = &tf->tf_cit_tmpl;	\
-	struct config_item_type *cit = &tfc->tfc_##_name##_cit;		\
+	struct config_item_type *cit = &tf->tf_##_name##_cit;		\
 									\
 	cit->ct_item_ops = _item_ops;					\
 	cit->ct_group_ops = _group_ops;					\
 	cit->ct_attrs = _attrs;						\
-	cit->ct_owner = tf->tf_module;					\
+	cit->ct_owner = tf->tf_ops->module;				\
 	pr_debug("Setup generic %s\n", __stringify(_name));		\
 }
 
 #define TF_CIT_SETUP_DRV(_name, _item_ops, _group_ops)		\
 static void target_fabric_setup_##_name##_cit(struct target_fabric_configfs *tf) \
 {									\
-	struct target_fabric_configfs_template *tfc = &tf->tf_cit_tmpl;	\
-	struct config_item_type *cit = &tfc->tfc_##_name##_cit;		\
-	struct configfs_attribute **attrs = tf->tf_ops.tfc_##_name##_attrs; \
+	struct config_item_type *cit = &tf->tf_##_name##_cit;		\
+	struct configfs_attribute **attrs = tf->tf_ops->tfc_##_name##_attrs; \
 									\
 	cit->ct_item_ops = _item_ops;					\
 	cit->ct_group_ops = _group_ops;					\
 	cit->ct_attrs = attrs;						\
-	cit->ct_owner = tf->tf_module;					\
+	cit->ct_owner = tf->tf_ops->module;				\
 	pr_debug("Setup generic %s\n", __stringify(_name));		\
 }
 
@@ -83,7 +80,7 @@
 			struct se_lun_acl, se_lun_group);
 	struct se_portal_group *se_tpg;
 	struct config_item *nacl_ci, *tpg_ci, *tpg_ci_s, *wwn_ci, *wwn_ci_s;
-	int ret = 0, lun_access;
+	int lun_access;
 
 	if (lun->lun_link_magic != SE_LUN_LINK_MAGIC) {
 		pr_err("Bad lun->lun_link_magic, not a valid lun_ci pointer:"
@@ -93,12 +90,11 @@
 	/*
 	 * Ensure that the source port exists
 	 */
-	if (!lun->lun_sep || !lun->lun_sep->sep_tpg) {
-		pr_err("Source se_lun->lun_sep or lun->lun_sep->sep"
-				"_tpg does not exist\n");
+	if (!lun->lun_se_dev) {
+		pr_err("Source se_lun->lun_se_dev does not exist\n");
 		return -EINVAL;
 	}
-	se_tpg = lun->lun_sep->sep_tpg;
+	se_tpg = lun->lun_tpg;
 
 	nacl_ci = &lun_acl_ci->ci_parent->ci_group->cg_item;
 	tpg_ci = &nacl_ci->ci_group->cg_item;
@@ -125,49 +121,35 @@
 	 * which be will write protected (READ-ONLY) when
 	 * tpg_1/attrib/demo_mode_write_protect=1
 	 */
-	spin_lock_irq(&lacl->se_lun_nacl->device_list_lock);
-	deve = lacl->se_lun_nacl->device_list[lacl->mapped_lun];
-	if (deve->lun_flags & TRANSPORT_LUNFLAGS_INITIATOR_ACCESS)
+	rcu_read_lock();
+	deve = target_nacl_find_deve(lacl->se_lun_nacl, lacl->mapped_lun);
+	if (deve)
 		lun_access = deve->lun_flags;
 	else
 		lun_access =
 			(se_tpg->se_tpg_tfo->tpg_check_prod_mode_write_protect(
 				se_tpg)) ? TRANSPORT_LUNFLAGS_READ_ONLY :
 					   TRANSPORT_LUNFLAGS_READ_WRITE;
-	spin_unlock_irq(&lacl->se_lun_nacl->device_list_lock);
+	rcu_read_unlock();
 	/*
 	 * Determine the actual mapped LUN value user wants..
 	 *
 	 * This value is what the SCSI Initiator actually sees the
-	 * iscsi/$IQN/$TPGT/lun/lun_* as on their SCSI Initiator Ports.
+	 * $FABRIC/$WWPN/$TPGT/lun/lun_* as on their SCSI Initiator Ports.
 	 */
-	ret = core_dev_add_initiator_node_lun_acl(se_tpg, lacl,
-			lun->unpacked_lun, lun_access);
-
-	return (ret < 0) ? -EINVAL : 0;
+	return core_dev_add_initiator_node_lun_acl(se_tpg, lacl, lun, lun_access);
 }
 
 static int target_fabric_mappedlun_unlink(
 	struct config_item *lun_acl_ci,
 	struct config_item *lun_ci)
 {
-	struct se_lun *lun;
 	struct se_lun_acl *lacl = container_of(to_config_group(lun_acl_ci),
 			struct se_lun_acl, se_lun_group);
-	struct se_node_acl *nacl = lacl->se_lun_nacl;
-	struct se_dev_entry *deve = nacl->device_list[lacl->mapped_lun];
-	struct se_portal_group *se_tpg;
-	/*
-	 * Determine if the underlying MappedLUN has already been released..
-	 */
-	if (!deve->se_lun)
-		return 0;
+	struct se_lun *lun = container_of(to_config_group(lun_ci),
+			struct se_lun, lun_group);
 
-	lun = container_of(to_config_group(lun_ci), struct se_lun, lun_group);
-	se_tpg = lun->lun_sep->sep_tpg;
-
-	core_dev_del_initiator_node_lun_acl(se_tpg, lun, lacl);
-	return 0;
+	return core_dev_del_initiator_node_lun_acl(lun, lacl);
 }
 
 CONFIGFS_EATTR_STRUCT(target_fabric_mappedlun, se_lun_acl);
@@ -183,14 +165,15 @@
 {
 	struct se_node_acl *se_nacl = lacl->se_lun_nacl;
 	struct se_dev_entry *deve;
-	ssize_t len;
+	ssize_t len = 0;
 
-	spin_lock_irq(&se_nacl->device_list_lock);
-	deve = se_nacl->device_list[lacl->mapped_lun];
-	len = sprintf(page, "%d\n",
-			(deve->lun_flags & TRANSPORT_LUNFLAGS_READ_ONLY) ?
-			1 : 0);
-	spin_unlock_irq(&se_nacl->device_list_lock);
+	rcu_read_lock();
+	deve = target_nacl_find_deve(se_nacl, lacl->mapped_lun);
+	if (deve) {
+		len = sprintf(page, "%d\n",
+			(deve->lun_flags & TRANSPORT_LUNFLAGS_READ_ONLY) ? 1 : 0);
+	}
+	rcu_read_unlock();
 
 	return len;
 }
@@ -218,7 +201,7 @@
 			lacl->se_lun_nacl);
 
 	pr_debug("%s_ConfigFS: Changed Initiator ACL: %s"
-		" Mapped LUN: %u Write Protect bit to %s\n",
+		" Mapped LUN: %llu Write Protect bit to %s\n",
 		se_tpg->se_tpg_tfo->get_fabric_name(),
 		lacl->initiatorname, lacl->mapped_lun, (op) ? "ON" : "OFF");
 
@@ -338,7 +321,7 @@
 	struct config_item *acl_ci;
 	struct config_group *lacl_cg = NULL, *ml_stat_grp = NULL;
 	char *buf;
-	unsigned long mapped_lun;
+	unsigned long long mapped_lun;
 	int ret = 0;
 
 	acl_ci = &group->cg_item;
@@ -366,21 +349,9 @@
 	 * Determine the Mapped LUN value.  This is what the SCSI Initiator
 	 * Port will actually see.
 	 */
-	ret = kstrtoul(buf + 4, 0, &mapped_lun);
+	ret = kstrtoull(buf + 4, 0, &mapped_lun);
 	if (ret)
 		goto out;
-	if (mapped_lun > UINT_MAX) {
-		ret = -EINVAL;
-		goto out;
-	}
-	if (mapped_lun > (TRANSPORT_MAX_LUNS_PER_TPG-1)) {
-		pr_err("Mapped LUN: %lu exceeds TRANSPORT_MAX_LUNS_PER_TPG"
-			"-1: %u for Target Portal Group: %u\n", mapped_lun,
-			TRANSPORT_MAX_LUNS_PER_TPG-1,
-			se_tpg->se_tpg_tfo->tpg_get_tag(se_tpg));
-		ret = -EINVAL;
-		goto out;
-	}
 
 	lacl = core_dev_init_initiator_node_lun_acl(se_tpg, se_nacl,
 			mapped_lun, &ret);
@@ -399,9 +370,9 @@
 	}
 
 	config_group_init_type_name(&lacl->se_lun_group, name,
-			&tf->tf_cit_tmpl.tfc_tpg_mappedlun_cit);
+			&tf->tf_tpg_mappedlun_cit);
 	config_group_init_type_name(&lacl->ml_stat_grps.stat_group,
-			"statistics", &tf->tf_cit_tmpl.tfc_tpg_mappedlun_stat_cit);
+			"statistics", &tf->tf_tpg_mappedlun_stat_cit);
 	lacl_cg->default_groups[0] = &lacl->ml_stat_grps.stat_group;
 	lacl_cg->default_groups[1] = NULL;
 
@@ -458,10 +429,11 @@
 {
 	struct se_node_acl *se_nacl = container_of(to_config_group(item),
 			struct se_node_acl, acl_group);
-	struct se_portal_group *se_tpg = se_nacl->se_tpg;
-	struct target_fabric_configfs *tf = se_tpg->se_tpg_wwn->wwn_tf;
+	struct target_fabric_configfs *tf = se_nacl->se_tpg->se_tpg_wwn->wwn_tf;
 
-	tf->tf_ops.fabric_drop_nodeacl(se_nacl);
+	if (tf->tf_ops->fabric_cleanup_nodeacl)
+		tf->tf_ops->fabric_cleanup_nodeacl(se_nacl);
+	core_tpg_del_initiator_node_acl(se_nacl);
 }
 
 static struct configfs_item_operations target_fabric_nacl_base_item_ops = {
@@ -501,15 +473,18 @@
 	struct se_node_acl *se_nacl;
 	struct config_group *nacl_cg;
 
-	if (!tf->tf_ops.fabric_make_nodeacl) {
-		pr_err("tf->tf_ops.fabric_make_nodeacl is NULL\n");
-		return ERR_PTR(-ENOSYS);
-	}
-
-	se_nacl = tf->tf_ops.fabric_make_nodeacl(se_tpg, group, name);
+	se_nacl = core_tpg_add_initiator_node_acl(se_tpg, name);
 	if (IS_ERR(se_nacl))
 		return ERR_CAST(se_nacl);
 
+	if (tf->tf_ops->fabric_init_nodeacl) {
+		int ret = tf->tf_ops->fabric_init_nodeacl(se_nacl, name);
+		if (ret) {
+			core_tpg_del_initiator_node_acl(se_nacl);
+			return ERR_PTR(ret);
+		}
+	}
+
 	nacl_cg = &se_nacl->acl_group;
 	nacl_cg->default_groups = se_nacl->acl_default_groups;
 	nacl_cg->default_groups[0] = &se_nacl->acl_attrib_group;
@@ -519,16 +494,15 @@
 	nacl_cg->default_groups[4] = NULL;
 
 	config_group_init_type_name(&se_nacl->acl_group, name,
-			&tf->tf_cit_tmpl.tfc_tpg_nacl_base_cit);
+			&tf->tf_tpg_nacl_base_cit);
 	config_group_init_type_name(&se_nacl->acl_attrib_group, "attrib",
-			&tf->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit);
+			&tf->tf_tpg_nacl_attrib_cit);
 	config_group_init_type_name(&se_nacl->acl_auth_group, "auth",
-			&tf->tf_cit_tmpl.tfc_tpg_nacl_auth_cit);
+			&tf->tf_tpg_nacl_auth_cit);
 	config_group_init_type_name(&se_nacl->acl_param_group, "param",
-			&tf->tf_cit_tmpl.tfc_tpg_nacl_param_cit);
+			&tf->tf_tpg_nacl_param_cit);
 	config_group_init_type_name(&se_nacl->acl_fabric_stat_group,
-			"fabric_statistics",
-			&tf->tf_cit_tmpl.tfc_tpg_nacl_stat_cit);
+			"fabric_statistics", &tf->tf_tpg_nacl_stat_cit);
 
 	return &se_nacl->acl_group;
 }
@@ -575,7 +549,7 @@
 	struct se_portal_group *se_tpg = se_tpg_np->tpg_np_parent;
 	struct target_fabric_configfs *tf = se_tpg->se_tpg_wwn->wwn_tf;
 
-	tf->tf_ops.fabric_drop_np(se_tpg_np);
+	tf->tf_ops->fabric_drop_np(se_tpg_np);
 }
 
 static struct configfs_item_operations target_fabric_np_base_item_ops = {
@@ -599,18 +573,18 @@
 	struct target_fabric_configfs *tf = se_tpg->se_tpg_wwn->wwn_tf;
 	struct se_tpg_np *se_tpg_np;
 
-	if (!tf->tf_ops.fabric_make_np) {
+	if (!tf->tf_ops->fabric_make_np) {
 		pr_err("tf->tf_ops.fabric_make_np is NULL\n");
 		return ERR_PTR(-ENOSYS);
 	}
 
-	se_tpg_np = tf->tf_ops.fabric_make_np(se_tpg, group, name);
+	se_tpg_np = tf->tf_ops->fabric_make_np(se_tpg, group, name);
 	if (!se_tpg_np || IS_ERR(se_tpg_np))
 		return ERR_PTR(-EINVAL);
 
 	se_tpg_np->tpg_np_parent = se_tpg;
 	config_group_init_type_name(&se_tpg_np->tpg_np_group, name,
-			&tf->tf_cit_tmpl.tfc_tpg_np_base_cit);
+			&tf->tf_tpg_np_base_cit);
 
 	return &se_tpg_np->tpg_np_group;
 }
@@ -654,10 +628,10 @@
 	struct se_lun *lun,
 	char *page)
 {
-	if (!lun || !lun->lun_sep)
+	if (!lun || !lun->lun_se_dev)
 		return -ENODEV;
 
-	return core_alua_show_tg_pt_gp_info(lun->lun_sep, page);
+	return core_alua_show_tg_pt_gp_info(lun, page);
 }
 
 static ssize_t target_fabric_port_store_attr_alua_tg_pt_gp(
@@ -665,10 +639,10 @@
 	const char *page,
 	size_t count)
 {
-	if (!lun || !lun->lun_sep)
+	if (!lun || !lun->lun_se_dev)
 		return -ENODEV;
 
-	return core_alua_store_tg_pt_gp_info(lun->lun_sep, page, count);
+	return core_alua_store_tg_pt_gp_info(lun, page, count);
 }
 
 TCM_PORT_ATTR(alua_tg_pt_gp, S_IRUGO | S_IWUSR);
@@ -680,7 +654,7 @@
 	struct se_lun *lun,
 	char *page)
 {
-	if (!lun || !lun->lun_sep)
+	if (!lun || !lun->lun_se_dev)
 		return -ENODEV;
 
 	return core_alua_show_offline_bit(lun, page);
@@ -691,7 +665,7 @@
 	const char *page,
 	size_t count)
 {
-	if (!lun || !lun->lun_sep)
+	if (!lun || !lun->lun_se_dev)
 		return -ENODEV;
 
 	return core_alua_store_offline_bit(lun, page, count);
@@ -706,7 +680,7 @@
 	struct se_lun *lun,
 	char *page)
 {
-	if (!lun || !lun->lun_sep)
+	if (!lun || !lun->lun_se_dev)
 		return -ENODEV;
 
 	return core_alua_show_secondary_status(lun, page);
@@ -717,7 +691,7 @@
 	const char *page,
 	size_t count)
 {
-	if (!lun || !lun->lun_sep)
+	if (!lun || !lun->lun_se_dev)
 		return -ENODEV;
 
 	return core_alua_store_secondary_status(lun, page, count);
@@ -732,7 +706,7 @@
 	struct se_lun *lun,
 	char *page)
 {
-	if (!lun || !lun->lun_sep)
+	if (!lun || !lun->lun_se_dev)
 		return -ENODEV;
 
 	return core_alua_show_secondary_write_metadata(lun, page);
@@ -743,7 +717,7 @@
 	const char *page,
 	size_t count)
 {
-	if (!lun || !lun->lun_sep)
+	if (!lun || !lun->lun_se_dev)
 		return -ENODEV;
 
 	return core_alua_store_secondary_write_metadata(lun, page, count);
@@ -769,7 +743,6 @@
 	struct config_item *tpg_ci;
 	struct se_lun *lun = container_of(to_config_group(lun_ci),
 				struct se_lun, lun_group);
-	struct se_lun *lun_p;
 	struct se_portal_group *se_tpg;
 	struct se_device *dev =
 		container_of(to_config_group(se_dev_ci), struct se_device, dev_group);
@@ -797,20 +770,19 @@
 		return -EEXIST;
 	}
 
-	lun_p = core_dev_add_lun(se_tpg, dev, lun->unpacked_lun);
-	if (IS_ERR(lun_p)) {
-		pr_err("core_dev_add_lun() failed\n");
-		ret = PTR_ERR(lun_p);
+	ret = core_dev_add_lun(se_tpg, dev, lun);
+	if (ret) {
+		pr_err("core_dev_add_lun() failed: %d\n", ret);
 		goto out;
 	}
 
-	if (tf->tf_ops.fabric_post_link) {
+	if (tf->tf_ops->fabric_post_link) {
 		/*
 		 * Call the optional fabric_post_link() to allow a
 		 * fabric module to setup any additional state once
 		 * core_dev_add_lun() has been called..
 		 */
-		tf->tf_ops.fabric_post_link(se_tpg, lun);
+		tf->tf_ops->fabric_post_link(se_tpg, lun);
 	}
 
 	return 0;
@@ -824,25 +796,34 @@
 {
 	struct se_lun *lun = container_of(to_config_group(lun_ci),
 				struct se_lun, lun_group);
-	struct se_portal_group *se_tpg = lun->lun_sep->sep_tpg;
+	struct se_portal_group *se_tpg = lun->lun_tpg;
 	struct target_fabric_configfs *tf = se_tpg->se_tpg_wwn->wwn_tf;
 
-	if (tf->tf_ops.fabric_pre_unlink) {
+	if (tf->tf_ops->fabric_pre_unlink) {
 		/*
 		 * Call the optional fabric_pre_unlink() to allow a
 		 * fabric module to release any additional stat before
 		 * core_dev_del_lun() is called.
 		*/
-		tf->tf_ops.fabric_pre_unlink(se_tpg, lun);
+		tf->tf_ops->fabric_pre_unlink(se_tpg, lun);
 	}
 
 	core_dev_del_lun(se_tpg, lun);
 	return 0;
 }
 
+static void target_fabric_port_release(struct config_item *item)
+{
+	struct se_lun *lun = container_of(to_config_group(item),
+					  struct se_lun, lun_group);
+
+	kfree_rcu(lun, rcu_head);
+}
+
 static struct configfs_item_operations target_fabric_port_item_ops = {
 	.show_attribute		= target_fabric_port_attr_show,
 	.store_attribute	= target_fabric_port_attr_store,
+	.release		= target_fabric_port_release,
 	.allow_link		= target_fabric_port_link,
 	.drop_link		= target_fabric_port_unlink,
 };
@@ -887,7 +868,7 @@
 			struct se_portal_group, tpg_lun_group);
 	struct target_fabric_configfs *tf = se_tpg->se_tpg_wwn->wwn_tf;
 	struct config_group *lun_cg = NULL, *port_stat_grp = NULL;
-	unsigned long unpacked_lun;
+	unsigned long long unpacked_lun;
 	int errno;
 
 	if (strstr(name, "lun_") != name) {
@@ -895,28 +876,27 @@
 				" \"lun_$LUN_NUMBER\"\n");
 		return ERR_PTR(-EINVAL);
 	}
-	errno = kstrtoul(name + 4, 0, &unpacked_lun);
+	errno = kstrtoull(name + 4, 0, &unpacked_lun);
 	if (errno)
 		return ERR_PTR(errno);
-	if (unpacked_lun > UINT_MAX)
-		return ERR_PTR(-EINVAL);
 
-	lun = core_get_lun_from_tpg(se_tpg, unpacked_lun);
-	if (!lun)
-		return ERR_PTR(-EINVAL);
+	lun = core_tpg_alloc_lun(se_tpg, unpacked_lun);
+	if (IS_ERR(lun))
+		return ERR_CAST(lun);
 
 	lun_cg = &lun->lun_group;
 	lun_cg->default_groups = kmalloc(sizeof(struct config_group *) * 2,
 				GFP_KERNEL);
 	if (!lun_cg->default_groups) {
 		pr_err("Unable to allocate lun_cg->default_groups\n");
+		kfree(lun);
 		return ERR_PTR(-ENOMEM);
 	}
 
 	config_group_init_type_name(&lun->lun_group, name,
-			&tf->tf_cit_tmpl.tfc_tpg_port_cit);
+			&tf->tf_tpg_port_cit);
 	config_group_init_type_name(&lun->port_stat_grps.stat_group,
-			"statistics", &tf->tf_cit_tmpl.tfc_tpg_port_stat_cit);
+			"statistics", &tf->tf_tpg_port_stat_cit);
 	lun_cg->default_groups[0] = &lun->port_stat_grps.stat_group;
 	lun_cg->default_groups[1] = NULL;
 
@@ -926,6 +906,7 @@
 	if (!port_stat_grp->default_groups) {
 		pr_err("Unable to allocate port_stat_grp->default_groups\n");
 		kfree(lun_cg->default_groups);
+		kfree(lun);
 		return ERR_PTR(-ENOMEM);
 	}
 	target_stat_setup_port_default_groups(lun);
@@ -1023,7 +1004,7 @@
 	struct se_wwn *wwn = se_tpg->se_tpg_wwn;
 	struct target_fabric_configfs *tf = wwn->wwn_tf;
 
-	tf->tf_ops.fabric_drop_tpg(se_tpg);
+	tf->tf_ops->fabric_drop_tpg(se_tpg);
 }
 
 static struct configfs_item_operations target_fabric_tpg_base_item_ops = {
@@ -1046,12 +1027,12 @@
 	struct target_fabric_configfs *tf = wwn->wwn_tf;
 	struct se_portal_group *se_tpg;
 
-	if (!tf->tf_ops.fabric_make_tpg) {
-		pr_err("tf->tf_ops.fabric_make_tpg is NULL\n");
+	if (!tf->tf_ops->fabric_make_tpg) {
+		pr_err("tf->tf_ops->fabric_make_tpg is NULL\n");
 		return ERR_PTR(-ENOSYS);
 	}
 
-	se_tpg = tf->tf_ops.fabric_make_tpg(wwn, group, name);
+	se_tpg = tf->tf_ops->fabric_make_tpg(wwn, group, name);
 	if (!se_tpg || IS_ERR(se_tpg))
 		return ERR_PTR(-EINVAL);
 	/*
@@ -1067,19 +1048,19 @@
 	se_tpg->tpg_group.default_groups[6] = NULL;
 
 	config_group_init_type_name(&se_tpg->tpg_group, name,
-			&tf->tf_cit_tmpl.tfc_tpg_base_cit);
+			&tf->tf_tpg_base_cit);
 	config_group_init_type_name(&se_tpg->tpg_lun_group, "lun",
-			&tf->tf_cit_tmpl.tfc_tpg_lun_cit);
+			&tf->tf_tpg_lun_cit);
 	config_group_init_type_name(&se_tpg->tpg_np_group, "np",
-			&tf->tf_cit_tmpl.tfc_tpg_np_cit);
+			&tf->tf_tpg_np_cit);
 	config_group_init_type_name(&se_tpg->tpg_acl_group, "acls",
-			&tf->tf_cit_tmpl.tfc_tpg_nacl_cit);
+			&tf->tf_tpg_nacl_cit);
 	config_group_init_type_name(&se_tpg->tpg_attrib_group, "attrib",
-			&tf->tf_cit_tmpl.tfc_tpg_attrib_cit);
+			&tf->tf_tpg_attrib_cit);
 	config_group_init_type_name(&se_tpg->tpg_auth_group, "auth",
-			&tf->tf_cit_tmpl.tfc_tpg_auth_cit);
+			&tf->tf_tpg_auth_cit);
 	config_group_init_type_name(&se_tpg->tpg_param_group, "param",
-			&tf->tf_cit_tmpl.tfc_tpg_param_cit);
+			&tf->tf_tpg_param_cit);
 
 	return &se_tpg->tpg_group;
 }
@@ -1112,7 +1093,7 @@
 				struct se_wwn, wwn_group);
 	struct target_fabric_configfs *tf = wwn->wwn_tf;
 
-	tf->tf_ops.fabric_drop_wwn(wwn);
+	tf->tf_ops->fabric_drop_wwn(wwn);
 }
 
 static struct configfs_item_operations target_fabric_tpg_item_ops = {
@@ -1148,12 +1129,12 @@
 				struct target_fabric_configfs, tf_group);
 	struct se_wwn *wwn;
 
-	if (!tf->tf_ops.fabric_make_wwn) {
+	if (!tf->tf_ops->fabric_make_wwn) {
 		pr_err("tf->tf_ops.fabric_make_wwn is NULL\n");
 		return ERR_PTR(-ENOSYS);
 	}
 
-	wwn = tf->tf_ops.fabric_make_wwn(tf, group, name);
+	wwn = tf->tf_ops->fabric_make_wwn(tf, group, name);
 	if (!wwn || IS_ERR(wwn))
 		return ERR_PTR(-EINVAL);
 
@@ -1165,10 +1146,9 @@
 	wwn->wwn_group.default_groups[0] = &wwn->fabric_stat_group;
 	wwn->wwn_group.default_groups[1] = NULL;
 
-	config_group_init_type_name(&wwn->wwn_group, name,
-			&tf->tf_cit_tmpl.tfc_tpg_cit);
+	config_group_init_type_name(&wwn->wwn_group, name, &tf->tf_tpg_cit);
 	config_group_init_type_name(&wwn->fabric_stat_group, "fabric_statistics",
-			&tf->tf_cit_tmpl.tfc_wwn_fabric_stats_cit);
+			&tf->tf_wwn_fabric_stats_cit);
 
 	return &wwn->wwn_group;
 }
diff --git a/drivers/target/target_core_fabric_lib.c b/drivers/target/target_core_fabric_lib.c
index 41f4f27..cb6497c 100644
--- a/drivers/target/target_core_fabric_lib.c
+++ b/drivers/target/target_core_fabric_lib.c
@@ -24,6 +24,11 @@
  *
  ******************************************************************************/
 
+/*
+ * See SPC4, section 7.5 "Protocol specific parameters" for details
+ * on the formats implemented in this file.
+ */
+
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/ctype.h>
@@ -34,124 +39,30 @@
 
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
-#include <target/target_core_configfs.h>
 
 #include "target_core_internal.h"
 #include "target_core_pr.h"
 
-/*
- * Handlers for Serial Attached SCSI (SAS)
- */
-u8 sas_get_fabric_proto_ident(struct se_portal_group *se_tpg)
-{
-	/*
-	 * Return a SAS Serial SCSI Protocol identifier for loopback operations
-	 * This is defined in  section 7.5.1 Table 362 in spc4r17
-	 */
-	return 0x6;
-}
-EXPORT_SYMBOL(sas_get_fabric_proto_ident);
 
-u32 sas_get_pr_transport_id(
-	struct se_portal_group *se_tpg,
-	struct se_node_acl *se_nacl,
-	struct t10_pr_registration *pr_reg,
+static int sas_get_pr_transport_id(
+	struct se_node_acl *nacl,
 	int *format_code,
 	unsigned char *buf)
 {
-	unsigned char *ptr;
 	int ret;
 
-	/*
-	 * Set PROTOCOL IDENTIFIER to 6h for SAS
-	 */
-	buf[0] = 0x06;
-	/*
-	 * From spc4r17, 7.5.4.7 TransportID for initiator ports using SCSI
-	 * over SAS Serial SCSI Protocol
-	 */
-	ptr = &se_nacl->initiatorname[4]; /* Skip over 'naa. prefix */
+	/* Skip over 'naa. prefix */
+	ret = hex2bin(&buf[4], &nacl->initiatorname[4], 8);
+	if (ret) {
+		pr_debug("%s: invalid hex string\n", __func__);
+		return ret;
+	}
 
-	ret = hex2bin(&buf[4], ptr, 8);
-	if (ret < 0)
-		pr_debug("sas transport_id: invalid hex string\n");
-
-	/*
-	 * The SAS Transport ID is a hardcoded 24-byte length
-	 */
 	return 24;
 }
-EXPORT_SYMBOL(sas_get_pr_transport_id);
 
-u32 sas_get_pr_transport_id_len(
-	struct se_portal_group *se_tpg,
+static int fc_get_pr_transport_id(
 	struct se_node_acl *se_nacl,
-	struct t10_pr_registration *pr_reg,
-	int *format_code)
-{
-	*format_code = 0;
-	/*
-	 * From spc4r17, 7.5.4.7 TransportID for initiator ports using SCSI
-	 * over SAS Serial SCSI Protocol
-	 *
-	 * The SAS Transport ID is a hardcoded 24-byte length
-	 */
-	return 24;
-}
-EXPORT_SYMBOL(sas_get_pr_transport_id_len);
-
-/*
- * Used for handling SCSI fabric dependent TransportIDs in SPC-3 and above
- * Persistent Reservation SPEC_I_PT=1 and PROUT REGISTER_AND_MOVE operations.
- */
-char *sas_parse_pr_out_transport_id(
-	struct se_portal_group *se_tpg,
-	const char *buf,
-	u32 *out_tid_len,
-	char **port_nexus_ptr)
-{
-	/*
-	 * Assume the FORMAT CODE 00b from spc4r17, 7.5.4.7 TransportID
-	 * for initiator ports using SCSI over SAS Serial SCSI Protocol
-	 *
-	 * The TransportID for a SAS Initiator Port is of fixed size of
-	 * 24 bytes, and SAS does not contain a I_T nexus identifier,
-	 * so we return the **port_nexus_ptr set to NULL.
-	 */
-	*port_nexus_ptr = NULL;
-	*out_tid_len = 24;
-
-	return (char *)&buf[4];
-}
-EXPORT_SYMBOL(sas_parse_pr_out_transport_id);
-
-/*
- * Handlers for Fibre Channel Protocol (FCP)
- */
-u8 fc_get_fabric_proto_ident(struct se_portal_group *se_tpg)
-{
-	return 0x0;	/* 0 = fcp-2 per SPC4 section 7.5.1 */
-}
-EXPORT_SYMBOL(fc_get_fabric_proto_ident);
-
-u32 fc_get_pr_transport_id_len(
-	struct se_portal_group *se_tpg,
-	struct se_node_acl *se_nacl,
-	struct t10_pr_registration *pr_reg,
-	int *format_code)
-{
-	*format_code = 0;
-	/*
-	 * The FC Transport ID is a hardcoded 24-byte length
-	 */
-	return 24;
-}
-EXPORT_SYMBOL(fc_get_pr_transport_id_len);
-
-u32 fc_get_pr_transport_id(
-	struct se_portal_group *se_tpg,
-	struct se_node_acl *se_nacl,
-	struct t10_pr_registration *pr_reg,
 	int *format_code,
 	unsigned char *buf)
 {
@@ -160,24 +71,20 @@
 	u32 off = 8;
 
 	/*
-	 * PROTOCOL IDENTIFIER is 0h for FCP-2
-	 *
-	 * From spc4r17, 7.5.4.2 TransportID for initiator ports using
-	 * SCSI over Fibre Channel
-	 *
 	 * We convert the ASCII formatted N Port name into a binary
 	 * encoded TransportID.
 	 */
 	ptr = &se_nacl->initiatorname[0];
-
 	for (i = 0; i < 24; ) {
 		if (!strncmp(&ptr[i], ":", 1)) {
 			i++;
 			continue;
 		}
 		ret = hex2bin(&buf[off++], &ptr[i], 1);
-		if (ret < 0)
-			pr_debug("fc transport_id: invalid hex string\n");
+		if (ret < 0) {
+			pr_debug("%s: invalid hex string\n", __func__);
+			return ret;
+		}
 		i += 2;
 	}
 	/*
@@ -185,42 +92,52 @@
 	 */
 	return 24;
 }
-EXPORT_SYMBOL(fc_get_pr_transport_id);
 
-char *fc_parse_pr_out_transport_id(
-	struct se_portal_group *se_tpg,
-	const char *buf,
-	u32 *out_tid_len,
-	char **port_nexus_ptr)
+static int sbp_get_pr_transport_id(
+	struct se_node_acl *nacl,
+	int *format_code,
+	unsigned char *buf)
 {
-	/*
-	 * The TransportID for a FC N Port is of fixed size of
-	 * 24 bytes, and FC does not contain a I_T nexus identifier,
-	 * so we return the **port_nexus_ptr set to NULL.
-	 */
-	*port_nexus_ptr = NULL;
-	*out_tid_len = 24;
+	int ret;
 
-	 return (char *)&buf[8];
+	ret = hex2bin(&buf[8], nacl->initiatorname, 8);
+	if (ret) {
+		pr_debug("%s: invalid hex string\n", __func__);
+		return ret;
+	}
+
+	return 24;
 }
-EXPORT_SYMBOL(fc_parse_pr_out_transport_id);
 
-/*
- * Handlers for Internet Small Computer Systems Interface (iSCSI)
- */
-
-u8 iscsi_get_fabric_proto_ident(struct se_portal_group *se_tpg)
+static int srp_get_pr_transport_id(
+	struct se_node_acl *nacl,
+	int *format_code,
+	unsigned char *buf)
 {
-	/*
-	 * This value is defined for "Internet SCSI (iSCSI)"
-	 * in spc4r17 section 7.5.1 Table 362
-	 */
-	return 0x5;
-}
-EXPORT_SYMBOL(iscsi_get_fabric_proto_ident);
+	const char *p;
+	unsigned len, count, leading_zero_bytes;
+	int rc;
 
-u32 iscsi_get_pr_transport_id(
-	struct se_portal_group *se_tpg,
+	p = nacl->initiatorname;
+	if (strncasecmp(p, "0x", 2) == 0)
+		p += 2;
+	len = strlen(p);
+	if (len % 2)
+		return -EINVAL;
+
+	count = min(len / 2, 16U);
+	leading_zero_bytes = 16 - count;
+	memset(buf + 8, 0, leading_zero_bytes);
+	rc = hex2bin(buf + 8 + leading_zero_bytes, p, count);
+	if (rc < 0) {
+		pr_debug("hex2bin failed for %s: %d\n", __func__, rc);
+		return rc;
+	}
+
+	return 24;
+}
+
+static int iscsi_get_pr_transport_id(
 	struct se_node_acl *se_nacl,
 	struct t10_pr_registration *pr_reg,
 	int *format_code,
@@ -231,10 +148,6 @@
 
 	spin_lock_irq(&se_nacl->nacl_sess_lock);
 	/*
-	 * Set PROTOCOL IDENTIFIER to 5h for iSCSI
-	*/
-	buf[0] = 0x05;
-	/*
 	 * From spc4r17 Section 7.5.4.6: TransportID for initiator
 	 * ports using SCSI over iSCSI.
 	 *
@@ -313,10 +226,8 @@
 
 	return len;
 }
-EXPORT_SYMBOL(iscsi_get_pr_transport_id);
 
-u32 iscsi_get_pr_transport_id_len(
-	struct se_portal_group *se_tpg,
+static int iscsi_get_pr_transport_id_len(
 	struct se_node_acl *se_nacl,
 	struct t10_pr_registration *pr_reg,
 	int *format_code)
@@ -359,9 +270,8 @@
 
 	return len;
 }
-EXPORT_SYMBOL(iscsi_get_pr_transport_id_len);
 
-char *iscsi_parse_pr_out_transport_id(
+static char *iscsi_parse_pr_out_transport_id(
 	struct se_portal_group *se_tpg,
 	const char *buf,
 	u32 *out_tid_len,
@@ -448,4 +358,79 @@
 
 	return (char *)&buf[4];
 }
-EXPORT_SYMBOL(iscsi_parse_pr_out_transport_id);
+
+int target_get_pr_transport_id_len(struct se_node_acl *nacl,
+		struct t10_pr_registration *pr_reg, int *format_code)
+{
+	switch (nacl->se_tpg->proto_id) {
+	case SCSI_PROTOCOL_FCP:
+	case SCSI_PROTOCOL_SBP:
+	case SCSI_PROTOCOL_SRP:
+	case SCSI_PROTOCOL_SAS:
+		break;
+	case SCSI_PROTOCOL_ISCSI:
+		return iscsi_get_pr_transport_id_len(nacl, pr_reg, format_code);
+	default:
+		pr_err("Unknown proto_id: 0x%02x\n", nacl->se_tpg->proto_id);
+		return -EINVAL;
+	}
+
+	/*
+	 * Most transports use a fixed length 24 byte identifier.
+	 */
+	*format_code = 0;
+	return 24;
+}
+
+int target_get_pr_transport_id(struct se_node_acl *nacl,
+		struct t10_pr_registration *pr_reg, int *format_code,
+		unsigned char *buf)
+{
+	switch (nacl->se_tpg->proto_id) {
+	case SCSI_PROTOCOL_SAS:
+		return sas_get_pr_transport_id(nacl, format_code, buf);
+	case SCSI_PROTOCOL_SBP:
+		return sbp_get_pr_transport_id(nacl, format_code, buf);
+	case SCSI_PROTOCOL_SRP:
+		return srp_get_pr_transport_id(nacl, format_code, buf);
+	case SCSI_PROTOCOL_FCP:
+		return fc_get_pr_transport_id(nacl, format_code, buf);
+	case SCSI_PROTOCOL_ISCSI:
+		return iscsi_get_pr_transport_id(nacl, pr_reg, format_code,
+				buf);
+	default:
+		pr_err("Unknown proto_id: 0x%02x\n", nacl->se_tpg->proto_id);
+		return -EINVAL;
+	}
+}
+
+const char *target_parse_pr_out_transport_id(struct se_portal_group *tpg,
+		const char *buf, u32 *out_tid_len, char **port_nexus_ptr)
+{
+	u32 offset;
+
+	switch (tpg->proto_id) {
+	case SCSI_PROTOCOL_SAS:
+		/*
+		 * Assume the FORMAT CODE 00b from spc4r17, 7.5.4.7 TransportID
+		 * for initiator ports using SCSI over SAS Serial SCSI Protocol.
+		 */
+		offset = 4;
+		break;
+	case SCSI_PROTOCOL_SBP:
+	case SCSI_PROTOCOL_SRP:
+	case SCSI_PROTOCOL_FCP:
+		offset = 8;
+		break;
+	case SCSI_PROTOCOL_ISCSI:
+		return iscsi_parse_pr_out_transport_id(tpg, buf, out_tid_len,
+					port_nexus_ptr);
+	default:
+		pr_err("Unknown proto_id: 0x%02x\n", tpg->proto_id);
+		return NULL;
+	}
+
+	*port_nexus_ptr = NULL;
+	*out_tid_len = 24;
+	return buf + offset;
+}
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index 6641713..e319570 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -37,7 +37,6 @@
 
 #include <target/target_core_base.h>
 #include <target/target_core_backend.h>
-#include <target/target_core_backend_configfs.h>
 
 #include "target_core_file.h"
 
@@ -46,10 +45,6 @@
 	return container_of(dev, struct fd_dev, dev);
 }
 
-/*	fd_attach_hba(): (Part of se_subsystem_api_t template)
- *
- *
- */
 static int fd_attach_hba(struct se_hba *hba, u32 host_id)
 {
 	struct fd_host *fd_host;
@@ -66,7 +61,7 @@
 
 	pr_debug("CORE_HBA[%d] - TCM FILEIO HBA Driver %s on Generic"
 		" Target Core Stack %s\n", hba->hba_id, FD_VERSION,
-		TARGET_CORE_MOD_VERSION);
+		TARGET_CORE_VERSION);
 	pr_debug("CORE_HBA[%d] - Attached FILEIO HBA: %u to Generic\n",
 		hba->hba_id, fd_host->fd_host_id);
 
@@ -246,6 +241,14 @@
 	return ret;
 }
 
+static void fd_dev_call_rcu(struct rcu_head *p)
+{
+	struct se_device *dev = container_of(p, struct se_device, rcu_head);
+	struct fd_dev *fd_dev = FD_DEV(dev);
+
+	kfree(fd_dev);
+}
+
 static void fd_free_device(struct se_device *dev)
 {
 	struct fd_dev *fd_dev = FD_DEV(dev);
@@ -254,79 +257,18 @@
 		filp_close(fd_dev->fd_file, NULL);
 		fd_dev->fd_file = NULL;
 	}
-
-	kfree(fd_dev);
+	call_rcu(&dev->rcu_head, fd_dev_call_rcu);
 }
 
-static int fd_do_prot_rw(struct se_cmd *cmd, struct fd_prot *fd_prot,
-			 int is_write)
+static int fd_do_rw(struct se_cmd *cmd, struct file *fd,
+		    u32 block_size, struct scatterlist *sgl,
+		    u32 sgl_nents, u32 data_length, int is_write)
 {
-	struct se_device *se_dev = cmd->se_dev;
-	struct fd_dev *dev = FD_DEV(se_dev);
-	struct file *prot_fd = dev->fd_prot_file;
-	loff_t pos = (cmd->t_task_lba * se_dev->prot_length);
-	unsigned char *buf;
-	u32 prot_size;
-	int rc, ret = 1;
-
-	prot_size = (cmd->data_length / se_dev->dev_attrib.block_size) *
-		     se_dev->prot_length;
-
-	if (!is_write) {
-		fd_prot->prot_buf = kzalloc(prot_size, GFP_KERNEL);
-		if (!fd_prot->prot_buf) {
-			pr_err("Unable to allocate fd_prot->prot_buf\n");
-			return -ENOMEM;
-		}
-		buf = fd_prot->prot_buf;
-
-		fd_prot->prot_sg_nents = 1;
-		fd_prot->prot_sg = kzalloc(sizeof(struct scatterlist),
-					   GFP_KERNEL);
-		if (!fd_prot->prot_sg) {
-			pr_err("Unable to allocate fd_prot->prot_sg\n");
-			kfree(fd_prot->prot_buf);
-			return -ENOMEM;
-		}
-		sg_init_table(fd_prot->prot_sg, fd_prot->prot_sg_nents);
-		sg_set_buf(fd_prot->prot_sg, buf, prot_size);
-	}
-
-	if (is_write) {
-		rc = kernel_write(prot_fd, fd_prot->prot_buf, prot_size, pos);
-		if (rc < 0 || prot_size != rc) {
-			pr_err("kernel_write() for fd_do_prot_rw failed:"
-			       " %d\n", rc);
-			ret = -EINVAL;
-		}
-	} else {
-		rc = kernel_read(prot_fd, pos, fd_prot->prot_buf, prot_size);
-		if (rc < 0) {
-			pr_err("kernel_read() for fd_do_prot_rw failed:"
-			       " %d\n", rc);
-			ret = -EINVAL;
-		}
-	}
-
-	if (is_write || ret < 0) {
-		kfree(fd_prot->prot_sg);
-		kfree(fd_prot->prot_buf);
-	}
-
-	return ret;
-}
-
-static int fd_do_rw(struct se_cmd *cmd, struct scatterlist *sgl,
-		u32 sgl_nents, int is_write)
-{
-	struct se_device *se_dev = cmd->se_dev;
-	struct fd_dev *dev = FD_DEV(se_dev);
-	struct file *fd = dev->fd_file;
 	struct scatterlist *sg;
 	struct iov_iter iter;
 	struct bio_vec *bvec;
 	ssize_t len = 0;
-	loff_t pos = (cmd->t_task_lba * se_dev->dev_attrib.block_size);
+	loff_t pos = (cmd->t_task_lba * block_size);
 	int ret = 0, i;
 
 	bvec = kcalloc(sgl_nents, sizeof(struct bio_vec), GFP_KERNEL);
@@ -352,7 +294,7 @@
 	kfree(bvec);
 
 	if (is_write) {
-		if (ret < 0 || ret != cmd->data_length) {
+		if (ret < 0 || ret != data_length) {
 			pr_err("%s() write returned %d\n", __func__, ret);
 			return (ret < 0 ? ret : -EINVAL);
 		}
@@ -363,10 +305,10 @@
 		 * block_device.
 		 */
 		if (S_ISBLK(file_inode(fd)->i_mode)) {
-			if (ret < 0 || ret != cmd->data_length) {
+			if (ret < 0 || ret != data_length) {
 				pr_err("%s() returned %d, expecting %u for "
 						"S_ISBLK\n", __func__, ret,
-						cmd->data_length);
+						data_length);
 				return (ret < 0 ? ret : -EINVAL);
 			}
 		} else {
@@ -533,9 +475,9 @@
 }
 
 static sense_reason_t
-fd_do_unmap(struct se_cmd *cmd, void *priv, sector_t lba, sector_t nolb)
+fd_execute_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb)
 {
-	struct file *file = priv;
+	struct file *file = FD_DEV(cmd->se_dev)->fd_file;
 	struct inode *inode = file->f_mapping->host;
 	int ret;
 
@@ -577,42 +519,13 @@
 }
 
 static sense_reason_t
-fd_execute_write_same_unmap(struct se_cmd *cmd)
-{
-	struct se_device *se_dev = cmd->se_dev;
-	struct fd_dev *fd_dev = FD_DEV(se_dev);
-	struct file *file = fd_dev->fd_file;
-	sector_t lba = cmd->t_task_lba;
-	sector_t nolb = sbc_get_write_same_sectors(cmd);
-	sense_reason_t ret;
-
-	if (!nolb) {
-		target_complete_cmd(cmd, SAM_STAT_GOOD);
-		return 0;
-	}
-
-	ret = fd_do_unmap(cmd, file, lba, nolb);
-	if (ret)
-		return ret;
-
-	target_complete_cmd(cmd, GOOD);
-	return 0;
-}
-
-static sense_reason_t
-fd_execute_unmap(struct se_cmd *cmd)
-{
-	struct file *file = FD_DEV(cmd->se_dev)->fd_file;
-
-	return sbc_execute_unmap(cmd, fd_do_unmap, file);
-}
-
-static sense_reason_t
 fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 	      enum dma_data_direction data_direction)
 {
 	struct se_device *dev = cmd->se_dev;
-	struct fd_prot fd_prot;
+	struct fd_dev *fd_dev = FD_DEV(dev);
+	struct file *file = fd_dev->fd_file;
+	struct file *pfile = fd_dev->fd_prot_file;
 	sense_reason_t rc;
 	int ret = 0;
 	/*
@@ -630,58 +543,45 @@
 	 * physical memory addresses to struct iovec virtual memory.
 	 */
 	if (data_direction == DMA_FROM_DEVICE) {
-		memset(&fd_prot, 0, sizeof(struct fd_prot));
-
 		if (cmd->prot_type && dev->dev_attrib.pi_prot_type) {
-			ret = fd_do_prot_rw(cmd, &fd_prot, false);
+			ret = fd_do_rw(cmd, pfile, dev->prot_length,
+				       cmd->t_prot_sg, cmd->t_prot_nents,
+				       cmd->prot_length, 0);
 			if (ret < 0)
 				return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 		}
 
-		ret = fd_do_rw(cmd, sgl, sgl_nents, 0);
+		ret = fd_do_rw(cmd, file, dev->dev_attrib.block_size,
+			       sgl, sgl_nents, cmd->data_length, 0);
 
 		if (ret > 0 && cmd->prot_type && dev->dev_attrib.pi_prot_type) {
-			u32 sectors = cmd->data_length / dev->dev_attrib.block_size;
+			u32 sectors = cmd->data_length >>
+					ilog2(dev->dev_attrib.block_size);
 
-			rc = sbc_dif_verify_read(cmd, cmd->t_task_lba, sectors,
-						 0, fd_prot.prot_sg, 0);
-			if (rc) {
-				kfree(fd_prot.prot_sg);
-				kfree(fd_prot.prot_buf);
+			rc = sbc_dif_verify(cmd, cmd->t_task_lba, sectors,
+					    0, cmd->t_prot_sg, 0);
+			if (rc)
 				return rc;
-			}
-			kfree(fd_prot.prot_sg);
-			kfree(fd_prot.prot_buf);
 		}
 	} else {
-		memset(&fd_prot, 0, sizeof(struct fd_prot));
-
 		if (cmd->prot_type && dev->dev_attrib.pi_prot_type) {
-			u32 sectors = cmd->data_length / dev->dev_attrib.block_size;
+			u32 sectors = cmd->data_length >>
+					ilog2(dev->dev_attrib.block_size);
 
-			ret = fd_do_prot_rw(cmd, &fd_prot, false);
-			if (ret < 0)
-				return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-
-			rc = sbc_dif_verify_write(cmd, cmd->t_task_lba, sectors,
-						  0, fd_prot.prot_sg, 0);
-			if (rc) {
-				kfree(fd_prot.prot_sg);
-				kfree(fd_prot.prot_buf);
+			rc = sbc_dif_verify(cmd, cmd->t_task_lba, sectors,
+					    0, cmd->t_prot_sg, 0);
+			if (rc)
 				return rc;
-			}
 		}
 
-		ret = fd_do_rw(cmd, sgl, sgl_nents, 1);
+		ret = fd_do_rw(cmd, file, dev->dev_attrib.block_size,
+			       sgl, sgl_nents, cmd->data_length, 1);
 		/*
 		 * Perform implicit vfs_fsync_range() for fd_do_writev() ops
 		 * for SCSI WRITEs with Forced Unit Access (FUA) set.
 		 * Allow this to happen independent of WCE=0 setting.
 		 */
-		if (ret > 0 &&
-		    dev->dev_attrib.emulate_fua_write > 0 &&
-		    (cmd->se_cmd_flags & SCF_FUA)) {
-			struct fd_dev *fd_dev = FD_DEV(dev);
+		if (ret > 0 && (cmd->se_cmd_flags & SCF_FUA)) {
 			loff_t start = cmd->t_task_lba *
 				dev->dev_attrib.block_size;
 			loff_t end;
@@ -695,17 +595,16 @@
 		}
 
 		if (ret > 0 && cmd->prot_type && dev->dev_attrib.pi_prot_type) {
-			ret = fd_do_prot_rw(cmd, &fd_prot, true);
+			ret = fd_do_rw(cmd, pfile, dev->prot_length,
+				       cmd->t_prot_sg, cmd->t_prot_nents,
+				       cmd->prot_length, 1);
 			if (ret < 0)
 				return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 		}
 	}
 
-	if (ret < 0) {
-		kfree(fd_prot.prot_sg);
-		kfree(fd_prot.prot_buf);
+	if (ret < 0)
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-	}
 
 	if (ret)
 		target_complete_cmd(cmd, SAM_STAT_GOOD);
@@ -908,7 +807,6 @@
 	.execute_rw		= fd_execute_rw,
 	.execute_sync_cache	= fd_execute_sync_cache,
 	.execute_write_same	= fd_execute_write_same,
-	.execute_write_same_unmap = fd_execute_write_same_unmap,
 	.execute_unmap		= fd_execute_unmap,
 };
 
@@ -918,42 +816,7 @@
 	return sbc_parse_cdb(cmd, &fd_sbc_ops);
 }
 
-DEF_TB_DEFAULT_ATTRIBS(fileio);
-
-static struct configfs_attribute *fileio_backend_dev_attrs[] = {
-	&fileio_dev_attrib_emulate_model_alias.attr,
-	&fileio_dev_attrib_emulate_dpo.attr,
-	&fileio_dev_attrib_emulate_fua_write.attr,
-	&fileio_dev_attrib_emulate_fua_read.attr,
-	&fileio_dev_attrib_emulate_write_cache.attr,
-	&fileio_dev_attrib_emulate_ua_intlck_ctrl.attr,
-	&fileio_dev_attrib_emulate_tas.attr,
-	&fileio_dev_attrib_emulate_tpu.attr,
-	&fileio_dev_attrib_emulate_tpws.attr,
-	&fileio_dev_attrib_emulate_caw.attr,
-	&fileio_dev_attrib_emulate_3pc.attr,
-	&fileio_dev_attrib_pi_prot_type.attr,
-	&fileio_dev_attrib_hw_pi_prot_type.attr,
-	&fileio_dev_attrib_pi_prot_format.attr,
-	&fileio_dev_attrib_enforce_pr_isids.attr,
-	&fileio_dev_attrib_is_nonrot.attr,
-	&fileio_dev_attrib_emulate_rest_reord.attr,
-	&fileio_dev_attrib_force_pr_aptpl.attr,
-	&fileio_dev_attrib_hw_block_size.attr,
-	&fileio_dev_attrib_block_size.attr,
-	&fileio_dev_attrib_hw_max_sectors.attr,
-	&fileio_dev_attrib_optimal_sectors.attr,
-	&fileio_dev_attrib_hw_queue_depth.attr,
-	&fileio_dev_attrib_queue_depth.attr,
-	&fileio_dev_attrib_max_unmap_lba_count.attr,
-	&fileio_dev_attrib_max_unmap_block_desc_count.attr,
-	&fileio_dev_attrib_unmap_granularity.attr,
-	&fileio_dev_attrib_unmap_granularity_alignment.attr,
-	&fileio_dev_attrib_max_write_same_len.attr,
-	NULL,
-};
-
-static struct se_subsystem_api fileio_template = {
+static const struct target_backend_ops fileio_ops = {
 	.name			= "fileio",
 	.inquiry_prod		= "FILEIO",
 	.inquiry_rev		= FD_VERSION,
@@ -971,21 +834,17 @@
 	.init_prot		= fd_init_prot,
 	.format_prot		= fd_format_prot,
 	.free_prot		= fd_free_prot,
+	.tb_dev_attrib_attrs	= sbc_attrib_attrs,
 };
 
 static int __init fileio_module_init(void)
 {
-	struct target_backend_cits *tbc = &fileio_template.tb_cits;
-
-	target_core_setup_sub_cits(&fileio_template);
-	tbc->tb_dev_attrib_cit.ct_attrs = fileio_backend_dev_attrs;
-
-	return transport_subsystem_register(&fileio_template);
+	return transport_backend_register(&fileio_ops);
 }
 
 static void __exit fileio_module_exit(void)
 {
-	transport_subsystem_release(&fileio_template);
+	target_backend_unregister(&fileio_ops);
 }
 
 MODULE_DESCRIPTION("TCM FILEIO subsystem plugin");
diff --git a/drivers/target/target_core_file.h b/drivers/target/target_core_file.h
index 182cbb2..068966f 100644
--- a/drivers/target/target_core_file.h
+++ b/drivers/target/target_core_file.h
@@ -21,12 +21,6 @@
 #define FDBD_HAS_BUFFERED_IO_WCE 0x04
 #define FDBD_FORMAT_UNIT_SIZE	2048
 
-struct fd_prot {
-	unsigned char	*prot_buf;
-	struct scatterlist *prot_sg;
-	u32 prot_sg_nents;
-};
-
 struct fd_dev {
 	struct se_device dev;
 
diff --git a/drivers/target/target_core_hba.c b/drivers/target/target_core_hba.c
index ff95f95..62ea4e8 100644
--- a/drivers/target/target_core_hba.c
+++ b/drivers/target/target_core_hba.c
@@ -36,67 +36,78 @@
 #include <target/target_core_base.h>
 #include <target/target_core_backend.h>
 #include <target/target_core_fabric.h>
-#include <target/target_core_configfs.h>
 
 #include "target_core_internal.h"
 
-static LIST_HEAD(subsystem_list);
-static DEFINE_MUTEX(subsystem_mutex);
+static LIST_HEAD(backend_list);
+static DEFINE_MUTEX(backend_mutex);
 
 static u32 hba_id_counter;
 
 static DEFINE_SPINLOCK(hba_lock);
 static LIST_HEAD(hba_list);
 
-int transport_subsystem_register(struct se_subsystem_api *sub_api)
+
+int transport_backend_register(const struct target_backend_ops *ops)
 {
-	struct se_subsystem_api *s;
+	struct target_backend *tb, *old;
 
-	INIT_LIST_HEAD(&sub_api->sub_api_list);
+	tb = kzalloc(sizeof(*tb), GFP_KERNEL);
+	if (!tb)
+		return -ENOMEM;
+	tb->ops = ops;
 
-	mutex_lock(&subsystem_mutex);
-	list_for_each_entry(s, &subsystem_list, sub_api_list) {
-		if (!strcmp(s->name, sub_api->name)) {
-			pr_err("%p is already registered with"
-				" duplicate name %s, unable to process"
-				" request\n", s, s->name);
-			mutex_unlock(&subsystem_mutex);
+	mutex_lock(&backend_mutex);
+	list_for_each_entry(old, &backend_list, list) {
+		if (!strcmp(old->ops->name, ops->name)) {
+			pr_err("backend %s already registered.\n", ops->name);
+			mutex_unlock(&backend_mutex);
+			kfree(tb);
 			return -EEXIST;
 		}
 	}
-	list_add_tail(&sub_api->sub_api_list, &subsystem_list);
-	mutex_unlock(&subsystem_mutex);
+	target_setup_backend_cits(tb);
+	list_add_tail(&tb->list, &backend_list);
+	mutex_unlock(&backend_mutex);
 
-	pr_debug("TCM: Registered subsystem plugin: %s struct module:"
-			" %p\n", sub_api->name, sub_api->owner);
+	pr_debug("TCM: Registered subsystem plugin: %s struct module: %p\n",
+			ops->name, ops->owner);
 	return 0;
 }
-EXPORT_SYMBOL(transport_subsystem_register);
+EXPORT_SYMBOL(transport_backend_register);
 
-void transport_subsystem_release(struct se_subsystem_api *sub_api)
+void target_backend_unregister(const struct target_backend_ops *ops)
 {
-	mutex_lock(&subsystem_mutex);
-	list_del(&sub_api->sub_api_list);
-	mutex_unlock(&subsystem_mutex);
+	struct target_backend *tb;
+
+	mutex_lock(&backend_mutex);
+	list_for_each_entry(tb, &backend_list, list) {
+		if (tb->ops == ops) {
+			list_del(&tb->list);
+			kfree(tb);
+			break;
+		}
+	}
+	mutex_unlock(&backend_mutex);
 }
-EXPORT_SYMBOL(transport_subsystem_release);
+EXPORT_SYMBOL(target_backend_unregister);
 
-static struct se_subsystem_api *core_get_backend(const char *sub_name)
+static struct target_backend *core_get_backend(const char *name)
 {
-	struct se_subsystem_api *s;
+	struct target_backend *tb;
 
-	mutex_lock(&subsystem_mutex);
-	list_for_each_entry(s, &subsystem_list, sub_api_list) {
-		if (!strcmp(s->name, sub_name))
+	mutex_lock(&backend_mutex);
+	list_for_each_entry(tb, &backend_list, list) {
+		if (!strcmp(tb->ops->name, name))
 			goto found;
 	}
-	mutex_unlock(&subsystem_mutex);
+	mutex_unlock(&backend_mutex);
 	return NULL;
 found:
-	if (s->owner && !try_module_get(s->owner))
-		s = NULL;
-	mutex_unlock(&subsystem_mutex);
-	return s;
+	if (tb->ops->owner && !try_module_get(tb->ops->owner))
+		tb = NULL;
+	mutex_unlock(&backend_mutex);
+	return tb;
 }
 
 struct se_hba *
@@ -117,13 +128,13 @@
 	hba->hba_index = scsi_get_new_index(SCSI_INST_INDEX);
 	hba->hba_flags |= hba_flags;
 
-	hba->transport = core_get_backend(plugin_name);
-	if (!hba->transport) {
+	hba->backend = core_get_backend(plugin_name);
+	if (!hba->backend) {
 		ret = -EINVAL;
 		goto out_free_hba;
 	}
 
-	ret = hba->transport->attach_hba(hba, plugin_dep_id);
+	ret = hba->backend->ops->attach_hba(hba, plugin_dep_id);
 	if (ret < 0)
 		goto out_module_put;
 
@@ -138,8 +149,8 @@
 	return hba;
 
 out_module_put:
-	module_put(hba->transport->owner);
-	hba->transport = NULL;
+	module_put(hba->backend->ops->owner);
+	hba->backend = NULL;
 out_free_hba:
 	kfree(hba);
 	return ERR_PTR(ret);
@@ -150,7 +161,7 @@
 {
 	WARN_ON(hba->dev_count);
 
-	hba->transport->detach_hba(hba);
+	hba->backend->ops->detach_hba(hba);
 
 	spin_lock(&hba_lock);
 	list_del(&hba->hba_node);
@@ -159,9 +170,9 @@
 	pr_debug("CORE_HBA[%d] - Detached HBA from Generic Target"
 			" Core\n", hba->hba_id);
 
-	module_put(hba->transport->owner);
+	module_put(hba->backend->ops->owner);
 
-	hba->transport = NULL;
+	hba->backend = NULL;
 	kfree(hba);
 	return 0;
 }
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 972ed17..6d88d24 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -40,7 +40,6 @@
 
 #include <target/target_core_base.h>
 #include <target/target_core_backend.h>
-#include <target/target_core_backend_configfs.h>
 
 #include "target_core_iblock.h"
 
@@ -53,17 +52,11 @@
 }
 
 
-static struct se_subsystem_api iblock_template;
-
-/*	iblock_attach_hba(): (Part of se_subsystem_api_t template)
- *
- *
- */
 static int iblock_attach_hba(struct se_hba *hba, u32 host_id)
 {
 	pr_debug("CORE_HBA[%d] - TCM iBlock HBA Driver %s on"
 		" Generic Target Core Stack %s\n", hba->hba_id,
-		IBLOCK_VERSION, TARGET_CORE_MOD_VERSION);
+		IBLOCK_VERSION, TARGET_CORE_VERSION);
 	return 0;
 }
 
@@ -197,6 +190,14 @@
 	return ret;
 }
 
+static void iblock_dev_call_rcu(struct rcu_head *p)
+{
+	struct se_device *dev = container_of(p, struct se_device, rcu_head);
+	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
+
+	kfree(ib_dev);
+}
+
 static void iblock_free_device(struct se_device *dev)
 {
 	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
@@ -206,7 +207,7 @@
 	if (ib_dev->ibd_bio_set != NULL)
 		bioset_free(ib_dev->ibd_bio_set);
 
-	kfree(ib_dev);
+	call_rcu(&dev->rcu_head, iblock_dev_call_rcu);
 }
 
 static unsigned long long iblock_emulate_read_cap_with_block_size(
@@ -414,10 +415,9 @@
 }
 
 static sense_reason_t
-iblock_do_unmap(struct se_cmd *cmd, void *priv,
-		sector_t lba, sector_t nolb)
+iblock_execute_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb)
 {
-	struct block_device *bdev = priv;
+	struct block_device *bdev = IBLOCK_DEV(cmd->se_dev)->ibd_bd;
 	int ret;
 
 	ret = blkdev_issue_discard(bdev, lba, nolb, GFP_KERNEL, 0);
@@ -430,30 +430,6 @@
 }
 
 static sense_reason_t
-iblock_execute_unmap(struct se_cmd *cmd)
-{
-	struct block_device *bdev = IBLOCK_DEV(cmd->se_dev)->ibd_bd;
-
-	return sbc_execute_unmap(cmd, iblock_do_unmap, bdev);
-}
-
-static sense_reason_t
-iblock_execute_write_same_unmap(struct se_cmd *cmd)
-{
-	struct block_device *bdev = IBLOCK_DEV(cmd->se_dev)->ibd_bd;
-	sector_t lba = cmd->t_task_lba;
-	sector_t nolb = sbc_get_write_same_sectors(cmd);
-	sense_reason_t ret;
-
-	ret = iblock_do_unmap(cmd, bdev, lba, nolb);
-	if (ret)
-		return ret;
-
-	target_complete_cmd(cmd, GOOD);
-	return 0;
-}
-
-static sense_reason_t
 iblock_execute_write_same(struct se_cmd *cmd)
 {
 	struct iblock_req *ibr;
@@ -844,7 +820,6 @@
 	.execute_rw		= iblock_execute_rw,
 	.execute_sync_cache	= iblock_execute_sync_cache,
 	.execute_write_same	= iblock_execute_write_same,
-	.execute_write_same_unmap = iblock_execute_write_same_unmap,
 	.execute_unmap		= iblock_execute_unmap,
 };
 
@@ -863,42 +838,7 @@
 	return q->flush_flags & REQ_FLUSH;
 }
 
-DEF_TB_DEFAULT_ATTRIBS(iblock);
-
-static struct configfs_attribute *iblock_backend_dev_attrs[] = {
-	&iblock_dev_attrib_emulate_model_alias.attr,
-	&iblock_dev_attrib_emulate_dpo.attr,
-	&iblock_dev_attrib_emulate_fua_write.attr,
-	&iblock_dev_attrib_emulate_fua_read.attr,
-	&iblock_dev_attrib_emulate_write_cache.attr,
-	&iblock_dev_attrib_emulate_ua_intlck_ctrl.attr,
-	&iblock_dev_attrib_emulate_tas.attr,
-	&iblock_dev_attrib_emulate_tpu.attr,
-	&iblock_dev_attrib_emulate_tpws.attr,
-	&iblock_dev_attrib_emulate_caw.attr,
-	&iblock_dev_attrib_emulate_3pc.attr,
-	&iblock_dev_attrib_pi_prot_type.attr,
-	&iblock_dev_attrib_hw_pi_prot_type.attr,
-	&iblock_dev_attrib_pi_prot_format.attr,
-	&iblock_dev_attrib_enforce_pr_isids.attr,
-	&iblock_dev_attrib_is_nonrot.attr,
-	&iblock_dev_attrib_emulate_rest_reord.attr,
-	&iblock_dev_attrib_force_pr_aptpl.attr,
-	&iblock_dev_attrib_hw_block_size.attr,
-	&iblock_dev_attrib_block_size.attr,
-	&iblock_dev_attrib_hw_max_sectors.attr,
-	&iblock_dev_attrib_optimal_sectors.attr,
-	&iblock_dev_attrib_hw_queue_depth.attr,
-	&iblock_dev_attrib_queue_depth.attr,
-	&iblock_dev_attrib_max_unmap_lba_count.attr,
-	&iblock_dev_attrib_max_unmap_block_desc_count.attr,
-	&iblock_dev_attrib_unmap_granularity.attr,
-	&iblock_dev_attrib_unmap_granularity_alignment.attr,
-	&iblock_dev_attrib_max_write_same_len.attr,
-	NULL,
-};
-
-static struct se_subsystem_api iblock_template = {
+static const struct target_backend_ops iblock_ops = {
 	.name			= "iblock",
 	.inquiry_prod		= "IBLOCK",
 	.inquiry_rev		= IBLOCK_VERSION,
@@ -918,21 +858,17 @@
 	.get_io_min		= iblock_get_io_min,
 	.get_io_opt		= iblock_get_io_opt,
 	.get_write_cache	= iblock_get_write_cache,
+	.tb_dev_attrib_attrs	= sbc_attrib_attrs,
 };
 
 static int __init iblock_module_init(void)
 {
-	struct target_backend_cits *tbc = &iblock_template.tb_cits;
-
-	target_core_setup_sub_cits(&iblock_template);
-	tbc->tb_dev_attrib_cit.ct_attrs = iblock_backend_dev_attrs;
-
-	return transport_subsystem_register(&iblock_template);
+	return transport_backend_register(&iblock_ops);
 }
 
 static void __exit iblock_module_exit(void)
 {
-	transport_subsystem_release(&iblock_template);
+	target_backend_unregister(&iblock_ops);
 }
 
 MODULE_DESCRIPTION("TCM IBLOCK subsystem plugin");
diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index 68bd7f5..99c24ac 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -1,6 +1,53 @@
 #ifndef TARGET_CORE_INTERNAL_H
 #define TARGET_CORE_INTERNAL_H
 
+#define TARGET_CORE_NAME_MAX_LEN	64
+#define TARGET_FABRIC_NAME_SIZE		32
+
+struct target_backend {
+	struct list_head list;
+
+	const struct target_backend_ops *ops;
+
+	struct config_item_type tb_dev_cit;
+	struct config_item_type tb_dev_attrib_cit;
+	struct config_item_type tb_dev_pr_cit;
+	struct config_item_type tb_dev_wwn_cit;
+	struct config_item_type tb_dev_alua_tg_pt_gps_cit;
+	struct config_item_type tb_dev_stat_cit;
+};
+
+struct target_fabric_configfs {
+	atomic_t		tf_access_cnt;
+	struct list_head	tf_list;
+	struct config_group	tf_group;
+	struct config_group	tf_disc_group;
+	struct config_group	*tf_default_groups[2];
+	const struct target_core_fabric_ops *tf_ops;
+
+	struct config_item_type tf_discovery_cit;
+	struct config_item_type	tf_wwn_cit;
+	struct config_item_type tf_wwn_fabric_stats_cit;
+	struct config_item_type tf_tpg_cit;
+	struct config_item_type tf_tpg_base_cit;
+	struct config_item_type tf_tpg_lun_cit;
+	struct config_item_type tf_tpg_port_cit;
+	struct config_item_type tf_tpg_port_stat_cit;
+	struct config_item_type tf_tpg_np_cit;
+	struct config_item_type tf_tpg_np_base_cit;
+	struct config_item_type tf_tpg_attrib_cit;
+	struct config_item_type tf_tpg_auth_cit;
+	struct config_item_type tf_tpg_param_cit;
+	struct config_item_type tf_tpg_nacl_cit;
+	struct config_item_type tf_tpg_nacl_base_cit;
+	struct config_item_type tf_tpg_nacl_attrib_cit;
+	struct config_item_type tf_tpg_nacl_auth_cit;
+	struct config_item_type tf_tpg_nacl_param_cit;
+	struct config_item_type tf_tpg_nacl_stat_cit;
+	struct config_item_type tf_tpg_mappedlun_cit;
+	struct config_item_type tf_tpg_mappedlun_stat_cit;
+};
+
 /* target_core_alua.c */
 extern struct t10_alua_lu_gp *default_lu_gp;
 
@@ -8,28 +55,27 @@
 extern struct mutex g_device_mutex;
 extern struct list_head g_device_list;
 
+int	core_alloc_rtpi(struct se_lun *lun, struct se_device *dev);
 struct se_dev_entry *core_get_se_deve_from_rtpi(struct se_node_acl *, u16);
-int	core_free_device_list_for_node(struct se_node_acl *,
+void	target_pr_kref_release(struct kref *);
+void	core_free_device_list_for_node(struct se_node_acl *,
 		struct se_portal_group *);
-void	core_update_device_list_access(u32, u32, struct se_node_acl *);
+void	core_update_device_list_access(u64, u32, struct se_node_acl *);
+struct se_dev_entry *target_nacl_find_deve(struct se_node_acl *, u64);
 int	core_enable_device_list_for_node(struct se_lun *, struct se_lun_acl *,
-		u32, u32, struct se_node_acl *, struct se_portal_group *);
-int	core_disable_device_list_for_node(struct se_lun *, struct se_lun_acl *,
-		u32, u32, struct se_node_acl *, struct se_portal_group *);
+		u64, u32, struct se_node_acl *, struct se_portal_group *);
+void	core_disable_device_list_for_node(struct se_lun *, struct se_dev_entry *,
+		struct se_node_acl *, struct se_portal_group *);
 void	core_clear_lun_from_tpg(struct se_lun *, struct se_portal_group *);
-int	core_dev_export(struct se_device *, struct se_portal_group *,
-		struct se_lun *);
-void	core_dev_unexport(struct se_device *, struct se_portal_group *,
-		struct se_lun *);
-struct se_lun *core_dev_add_lun(struct se_portal_group *, struct se_device *, u32);
+int	core_dev_add_lun(struct se_portal_group *, struct se_device *,
+		struct se_lun *lun);
 void	core_dev_del_lun(struct se_portal_group *, struct se_lun *);
-struct se_lun *core_get_lun_from_tpg(struct se_portal_group *, u32);
 struct se_lun_acl *core_dev_init_initiator_node_lun_acl(struct se_portal_group *,
-		struct se_node_acl *, u32, int *);
+		struct se_node_acl *, u64, int *);
 int	core_dev_add_initiator_node_lun_acl(struct se_portal_group *,
-		struct se_lun_acl *, u32, u32);
-int	core_dev_del_initiator_node_lun_acl(struct se_portal_group *,
-		struct se_lun *, struct se_lun_acl *);
+		struct se_lun_acl *, struct se_lun *lun, u32);
+int	core_dev_del_initiator_node_lun_acl(struct se_lun *,
+		struct se_lun_acl *);
 void	core_dev_free_initiator_node_lun_acl(struct se_portal_group *,
 		struct se_lun_acl *lacl);
 int	core_dev_setup_virtual_lun0(void);
@@ -38,6 +84,18 @@
 int	target_configure_device(struct se_device *dev);
 void	target_free_device(struct se_device *);
 
+/* target_core_configfs.c */
+void	target_setup_backend_cits(struct target_backend *);
+
+/* target_core_fabric_lib.c */
+int	target_get_pr_transport_id_len(struct se_node_acl *nacl,
+		struct t10_pr_registration *pr_reg, int *format_code);
+int	target_get_pr_transport_id(struct se_node_acl *nacl,
+		struct t10_pr_registration *pr_reg, int *format_code,
+		unsigned char *buf);
+const char *target_parse_pr_out_transport_id(struct se_portal_group *tpg,
+		const char *buf, u32 *out_tid_len, char **port_nexus_ptr);
+
 /* target_core_hba.c */
 struct se_hba *core_alloc_hba(const char *, u32, u32);
 int	core_delete_hba(struct se_hba *);
@@ -53,12 +111,16 @@
 
 struct se_node_acl *__core_tpg_get_initiator_node_acl(struct se_portal_group *tpg,
 		const char *);
-void	core_tpg_add_node_to_devs(struct se_node_acl *, struct se_portal_group *);
+void	core_tpg_add_node_to_devs(struct se_node_acl *, struct se_portal_group *,
+				  struct se_lun *);
 void	core_tpg_wait_for_nacl_pr_ref(struct se_node_acl *);
-struct se_lun *core_tpg_alloc_lun(struct se_portal_group *, u32);
+struct se_lun *core_tpg_alloc_lun(struct se_portal_group *, u64);
 int	core_tpg_add_lun(struct se_portal_group *, struct se_lun *,
 		u32, struct se_device *);
 void core_tpg_remove_lun(struct se_portal_group *, struct se_lun *);
+struct se_node_acl *core_tpg_add_initiator_node_acl(struct se_portal_group *tpg,
+		const char *initiatorname);
+void core_tpg_del_initiator_node_acl(struct se_node_acl *acl);
 
 /* target_core_transport.c */
 extern struct kmem_cache *se_tmr_req_cache;
@@ -77,14 +139,19 @@
 int	transport_dump_vpd_ident_type(struct t10_vpd *, unsigned char *, int);
 int	transport_dump_vpd_ident(struct t10_vpd *, unsigned char *, int);
 bool	target_stop_cmd(struct se_cmd *cmd, unsigned long *flags);
-int	transport_clear_lun_ref(struct se_lun *);
+void	transport_clear_lun_ref(struct se_lun *);
 void	transport_send_task_abort(struct se_cmd *);
 sense_reason_t	target_cmd_size_check(struct se_cmd *cmd, unsigned int size);
 void	target_qf_do_work(struct work_struct *work);
+bool	target_check_wce(struct se_device *dev);
+bool	target_check_fua(struct se_device *dev);
 
 /* target_core_stat.c */
 void	target_stat_setup_dev_default_groups(struct se_device *);
 void	target_stat_setup_port_default_groups(struct se_lun *);
 void	target_stat_setup_mappedlun_default_groups(struct se_lun_acl *);
 
+/* target_core_xcopy.c */
+extern struct se_portal_group xcopy_pt_tpg;
+
 #endif /* TARGET_CORE_INTERNAL_H */
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 8e5fa29..0fdbe43 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -35,7 +35,6 @@
 #include <target/target_core_base.h>
 #include <target/target_core_backend.h>
 #include <target/target_core_fabric.h>
-#include <target/target_core_configfs.h>
 
 #include "target_core_internal.h"
 #include "target_core_pr.h"
@@ -45,7 +44,6 @@
  * Used for Specify Initiator Ports Capable Bit (SPEC_I_PT)
  */
 struct pr_transport_id_holder {
-	int dest_local_nexus;
 	struct t10_pr_registration *dest_pr_reg;
 	struct se_portal_group *dest_tpg;
 	struct se_node_acl *dest_node_acl;
@@ -231,9 +229,10 @@
 		dev->dev_reservation_flags &= ~DRF_SPC2_RESERVATIONS_WITH_ISID;
 	}
 	tpg = sess->se_tpg;
-	pr_debug("SCSI-2 Released reservation for %s LUN: %u ->"
-		" MAPPED LUN: %u for %s\n", tpg->se_tpg_tfo->get_fabric_name(),
-		cmd->se_lun->unpacked_lun, cmd->se_deve->mapped_lun,
+	pr_debug("SCSI-2 Released reservation for %s LUN: %llu ->"
+		" MAPPED LUN: %llu for %s\n",
+		tpg->se_tpg_tfo->get_fabric_name(),
+		cmd->se_lun->unpacked_lun, cmd->orig_fe_lun,
 		sess->se_node_acl->initiatorname);
 
 out_unlock:
@@ -277,12 +276,12 @@
 	   (dev->dev_reserved_node_acl != sess->se_node_acl)) {
 		pr_err("SCSI-2 RESERVATION CONFLIFT for %s fabric\n",
 			tpg->se_tpg_tfo->get_fabric_name());
-		pr_err("Original reserver LUN: %u %s\n",
+		pr_err("Original reserver LUN: %llu %s\n",
 			cmd->se_lun->unpacked_lun,
 			dev->dev_reserved_node_acl->initiatorname);
-		pr_err("Current attempt - LUN: %u -> MAPPED LUN: %u"
+		pr_err("Current attempt - LUN: %llu -> MAPPED LUN: %llu"
 			" from %s \n", cmd->se_lun->unpacked_lun,
-			cmd->se_deve->mapped_lun,
+			cmd->orig_fe_lun,
 			sess->se_node_acl->initiatorname);
 		ret = TCM_RESERVATION_CONFLICT;
 		goto out_unlock;
@@ -294,9 +293,9 @@
 		dev->dev_res_bin_isid = sess->sess_bin_isid;
 		dev->dev_reservation_flags |= DRF_SPC2_RESERVATIONS_WITH_ISID;
 	}
-	pr_debug("SCSI-2 Reserved %s LUN: %u -> MAPPED LUN: %u"
+	pr_debug("SCSI-2 Reserved %s LUN: %llu -> MAPPED LUN: %llu"
 		" for %s\n", tpg->se_tpg_tfo->get_fabric_name(),
-		cmd->se_lun->unpacked_lun, cmd->se_deve->mapped_lun,
+		cmd->se_lun->unpacked_lun, cmd->orig_fe_lun,
 		sess->se_node_acl->initiatorname);
 
 out_unlock:
@@ -314,28 +313,31 @@
  * This function is called by those initiator ports who are *NOT*
  * the active PR reservation holder when a reservation is present.
  */
-static int core_scsi3_pr_seq_non_holder(
-	struct se_cmd *cmd,
-	u32 pr_reg_type)
+static int core_scsi3_pr_seq_non_holder(struct se_cmd *cmd, u32 pr_reg_type,
+					bool isid_mismatch)
 {
 	unsigned char *cdb = cmd->t_task_cdb;
-	struct se_dev_entry *se_deve;
 	struct se_session *se_sess = cmd->se_sess;
-	int other_cdb = 0, ignore_reg;
+	struct se_node_acl *nacl = se_sess->se_node_acl;
+	int other_cdb = 0;
 	int registered_nexus = 0, ret = 1; /* Conflict by default */
 	int all_reg = 0, reg_only = 0; /* ALL_REG, REG_ONLY */
 	int we = 0; /* Write Exclusive */
 	int legacy = 0; /* Act like a legacy device and return
 			 * RESERVATION CONFLICT on some CDBs */
 
-	se_deve = se_sess->se_node_acl->device_list[cmd->orig_fe_lun];
-	/*
-	 * Determine if the registration should be ignored due to
-	 * non-matching ISIDs in target_scsi3_pr_reservation_check().
-	 */
-	ignore_reg = (pr_reg_type & 0x80000000);
-	if (ignore_reg)
-		pr_reg_type &= ~0x80000000;
+	if (isid_mismatch) {
+		registered_nexus = 0;
+	} else {
+		struct se_dev_entry *se_deve;
+
+		rcu_read_lock();
+		se_deve = target_nacl_find_deve(nacl, cmd->orig_fe_lun);
+		if (se_deve)
+			registered_nexus = test_bit(DEF_PR_REG_ACTIVE,
+						    &se_deve->deve_flags);
+		rcu_read_unlock();
+	}
 
 	switch (pr_reg_type) {
 	case PR_TYPE_WRITE_EXCLUSIVE:
@@ -345,8 +347,6 @@
 		 * Some commands are only allowed for the persistent reservation
 		 * holder.
 		 */
-		if ((se_deve->def_pr_registered) && !(ignore_reg))
-			registered_nexus = 1;
 		break;
 	case PR_TYPE_WRITE_EXCLUSIVE_REGONLY:
 		we = 1;
@@ -355,8 +355,6 @@
 		 * Some commands are only allowed for registered I_T Nexuses.
 		 */
 		reg_only = 1;
-		if ((se_deve->def_pr_registered) && !(ignore_reg))
-			registered_nexus = 1;
 		break;
 	case PR_TYPE_WRITE_EXCLUSIVE_ALLREG:
 		we = 1;
@@ -365,8 +363,6 @@
 		 * Each registered I_T Nexus is a reservation holder.
 		 */
 		all_reg = 1;
-		if ((se_deve->def_pr_registered) && !(ignore_reg))
-			registered_nexus = 1;
 		break;
 	default:
 		return -EINVAL;
@@ -572,6 +568,7 @@
 	struct se_device *dev = cmd->se_dev;
 	struct se_session *sess = cmd->se_sess;
 	u32 pr_reg_type;
+	bool isid_mismatch = false;
 
 	if (!dev->dev_pr_res_holder)
 		return 0;
@@ -584,7 +581,7 @@
 	if (dev->dev_pr_res_holder->isid_present_at_reg) {
 		if (dev->dev_pr_res_holder->pr_reg_bin_isid !=
 		    sess->sess_bin_isid) {
-			pr_reg_type |= 0x80000000;
+			isid_mismatch = true;
 			goto check_nonholder;
 		}
 	}
@@ -592,7 +589,7 @@
 	return 0;
 
 check_nonholder:
-	if (core_scsi3_pr_seq_non_holder(cmd, pr_reg_type))
+	if (core_scsi3_pr_seq_non_holder(cmd, pr_reg_type, isid_mismatch))
 		return TCM_RESERVATION_CONFLICT;
 	return 0;
 }
@@ -620,7 +617,9 @@
 static struct t10_pr_registration *__core_scsi3_do_alloc_registration(
 	struct se_device *dev,
 	struct se_node_acl *nacl,
+	struct se_lun *lun,
 	struct se_dev_entry *deve,
+	u64 mapped_lun,
 	unsigned char *isid,
 	u64 sa_res_key,
 	int all_tg_pt,
@@ -642,12 +641,12 @@
 	atomic_set(&pr_reg->pr_res_holders, 0);
 	pr_reg->pr_reg_nacl = nacl;
 	pr_reg->pr_reg_deve = deve;
-	pr_reg->pr_res_mapped_lun = deve->mapped_lun;
-	pr_reg->pr_aptpl_target_lun = deve->se_lun->unpacked_lun;
+	pr_reg->pr_res_mapped_lun = mapped_lun;
+	pr_reg->pr_aptpl_target_lun = lun->unpacked_lun;
+	pr_reg->tg_pt_sep_rtpi = lun->lun_rtpi;
 	pr_reg->pr_res_key = sa_res_key;
 	pr_reg->pr_reg_all_tg_pt = all_tg_pt;
 	pr_reg->pr_reg_aptpl = aptpl;
-	pr_reg->pr_reg_tg_pt_lun = deve->se_lun;
 	/*
 	 * If an ISID value for this SCSI Initiator Port exists,
 	 * save it to the registration now.
@@ -671,7 +670,9 @@
 static struct t10_pr_registration *__core_scsi3_alloc_registration(
 	struct se_device *dev,
 	struct se_node_acl *nacl,
+	struct se_lun *lun,
 	struct se_dev_entry *deve,
+	u64 mapped_lun,
 	unsigned char *isid,
 	u64 sa_res_key,
 	int all_tg_pt,
@@ -679,7 +680,8 @@
 {
 	struct se_dev_entry *deve_tmp;
 	struct se_node_acl *nacl_tmp;
-	struct se_port *port, *port_tmp;
+	struct se_lun_acl *lacl_tmp;
+	struct se_lun *lun_tmp, *next, *dest_lun;
 	const struct target_core_fabric_ops *tfo = nacl->se_tpg->se_tpg_tfo;
 	struct t10_pr_registration *pr_reg, *pr_reg_atp, *pr_reg_tmp, *pr_reg_tmp_safe;
 	int ret;
@@ -687,8 +689,9 @@
 	 * Create a registration for the I_T Nexus upon which the
 	 * PROUT REGISTER was received.
 	 */
-	pr_reg = __core_scsi3_do_alloc_registration(dev, nacl, deve, isid,
-			sa_res_key, all_tg_pt, aptpl);
+	pr_reg = __core_scsi3_do_alloc_registration(dev, nacl, lun, deve, mapped_lun,
+						    isid, sa_res_key, all_tg_pt,
+						    aptpl);
 	if (!pr_reg)
 		return NULL;
 	/*
@@ -701,13 +704,13 @@
 	 * for ALL_TG_PT=1
 	 */
 	spin_lock(&dev->se_port_lock);
-	list_for_each_entry_safe(port, port_tmp, &dev->dev_sep_list, sep_list) {
-		atomic_inc_mb(&port->sep_tg_pt_ref_cnt);
+	list_for_each_entry_safe(lun_tmp, next, &dev->dev_sep_list, lun_dev_link) {
+		if (!percpu_ref_tryget_live(&lun_tmp->lun_ref))
+			continue;
 		spin_unlock(&dev->se_port_lock);
 
-		spin_lock_bh(&port->sep_alua_lock);
-		list_for_each_entry(deve_tmp, &port->sep_alua_list,
-					alua_port_list) {
+		spin_lock(&lun_tmp->lun_deve_lock);
+		list_for_each_entry(deve_tmp, &lun_tmp->lun_deve_list, lun_link) {
 			/*
 			 * This pointer will be NULL for demo mode MappedLUNs
 			 * that have not been make explicit via a ConfigFS
@@ -716,7 +719,9 @@
 			if (!deve_tmp->se_lun_acl)
 				continue;
 
-			nacl_tmp = deve_tmp->se_lun_acl->se_lun_nacl;
+			lacl_tmp = rcu_dereference_check(deve_tmp->se_lun_acl,
+						lockdep_is_held(&lun_tmp->lun_deve_lock));
+			nacl_tmp = lacl_tmp->se_lun_nacl;
 			/*
 			 * Skip the matching struct se_node_acl that is allocated
 			 * above..
@@ -736,8 +741,8 @@
 			if (strcmp(nacl->initiatorname, nacl_tmp->initiatorname))
 				continue;
 
-			atomic_inc_mb(&deve_tmp->pr_ref_count);
-			spin_unlock_bh(&port->sep_alua_lock);
+			kref_get(&deve_tmp->pr_kref);
+			spin_unlock(&lun_tmp->lun_deve_lock);
 			/*
 			 * Grab a configfs group dependency that is released
 			 * for the exception path at label out: below, or upon
@@ -748,8 +753,8 @@
 			if (ret < 0) {
 				pr_err("core_scsi3_lunacl_depend"
 						"_item() failed\n");
-				atomic_dec_mb(&port->sep_tg_pt_ref_cnt);
-				atomic_dec_mb(&deve_tmp->pr_ref_count);
+				percpu_ref_put(&lun_tmp->lun_ref);
+				kref_put(&deve_tmp->pr_kref, target_pr_kref_release);
 				goto out;
 			}
 			/*
@@ -759,24 +764,27 @@
 			 * the original *pr_reg is processed in
 			 * __core_scsi3_add_registration()
 			 */
+			dest_lun = rcu_dereference_check(deve_tmp->se_lun,
+				atomic_read(&deve_tmp->pr_kref.refcount) != 0);
+
 			pr_reg_atp = __core_scsi3_do_alloc_registration(dev,
-						nacl_tmp, deve_tmp, NULL,
+						nacl_tmp, dest_lun, deve_tmp,
+						deve_tmp->mapped_lun, NULL,
 						sa_res_key, all_tg_pt, aptpl);
 			if (!pr_reg_atp) {
-				atomic_dec_mb(&port->sep_tg_pt_ref_cnt);
-				atomic_dec_mb(&deve_tmp->pr_ref_count);
+				percpu_ref_put(&lun_tmp->lun_ref);
 				core_scsi3_lunacl_undepend_item(deve_tmp);
 				goto out;
 			}
 
 			list_add_tail(&pr_reg_atp->pr_reg_atp_mem_list,
 				      &pr_reg->pr_reg_atp_list);
-			spin_lock_bh(&port->sep_alua_lock);
+			spin_lock(&lun_tmp->lun_deve_lock);
 		}
-		spin_unlock_bh(&port->sep_alua_lock);
+		spin_unlock(&lun_tmp->lun_deve_lock);
 
 		spin_lock(&dev->se_port_lock);
-		atomic_dec_mb(&port->sep_tg_pt_ref_cnt);
+		percpu_ref_put(&lun_tmp->lun_ref);
 	}
 	spin_unlock(&dev->se_port_lock);
 
@@ -797,10 +805,10 @@
 	u64 sa_res_key,
 	unsigned char *i_port,
 	unsigned char *isid,
-	u32 mapped_lun,
+	u64 mapped_lun,
 	unsigned char *t_port,
 	u16 tpgt,
-	u32 target_lun,
+	u64 target_lun,
 	int res_holder,
 	int all_tg_pt,
 	u8 type)
@@ -831,7 +839,6 @@
 	pr_reg->pr_res_key = sa_res_key;
 	pr_reg->pr_reg_all_tg_pt = all_tg_pt;
 	pr_reg->pr_reg_aptpl = 1;
-	pr_reg->pr_reg_tg_pt_lun = NULL;
 	pr_reg->pr_res_scope = 0; /* Always LUN_SCOPE */
 	pr_reg->pr_res_type = type;
 	/*
@@ -895,9 +902,9 @@
 	struct se_device *dev,
 	struct se_portal_group *tpg,
 	struct se_lun *lun,
-	u32 target_lun,
+	u64 target_lun,
 	struct se_node_acl *nacl,
-	struct se_dev_entry *deve)
+	u64 mapped_lun)
 {
 	struct t10_pr_registration *pr_reg, *pr_reg_tmp;
 	struct t10_reservation *pr_tmpl = &dev->t10_pr;
@@ -925,14 +932,13 @@
 				pr_reg_aptpl_list) {
 
 		if (!strcmp(pr_reg->pr_iport, i_port) &&
-		     (pr_reg->pr_res_mapped_lun == deve->mapped_lun) &&
+		     (pr_reg->pr_res_mapped_lun == mapped_lun) &&
 		    !(strcmp(pr_reg->pr_tport, t_port)) &&
 		     (pr_reg->pr_reg_tpgt == tpgt) &&
 		     (pr_reg->pr_aptpl_target_lun == target_lun)) {
 
 			pr_reg->pr_reg_nacl = nacl;
-			pr_reg->pr_reg_deve = deve;
-			pr_reg->pr_reg_tg_pt_lun = lun;
+			pr_reg->tg_pt_sep_rtpi = lun->lun_rtpi;
 
 			list_del(&pr_reg->pr_reg_aptpl_list);
 			spin_unlock(&pr_tmpl->aptpl_reg_lock);
@@ -967,15 +973,14 @@
 	struct se_portal_group *tpg,
 	struct se_lun *lun,
 	struct se_node_acl *nacl,
-	u32 mapped_lun)
+	u64 mapped_lun)
 {
-	struct se_dev_entry *deve = nacl->device_list[mapped_lun];
-
 	if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)
 		return 0;
 
 	return __core_scsi3_check_aptpl_registration(dev, tpg, lun,
-				lun->unpacked_lun, nacl, deve);
+						     lun->unpacked_lun, nacl,
+						     mapped_lun);
 }
 
 static void __core_scsi3_dump_registration(
@@ -1009,10 +1014,6 @@
 		pr_reg->pr_reg_aptpl);
 }
 
-/*
- * this function can be called with struct se_device->dev_reservation_lock
- * when register_move = 1
- */
 static void __core_scsi3_add_registration(
 	struct se_device *dev,
 	struct se_node_acl *nacl,
@@ -1023,6 +1024,7 @@
 	const struct target_core_fabric_ops *tfo = nacl->se_tpg->se_tpg_tfo;
 	struct t10_pr_registration *pr_reg_tmp, *pr_reg_tmp_safe;
 	struct t10_reservation *pr_tmpl = &dev->t10_pr;
+	struct se_dev_entry *deve;
 
 	/*
 	 * Increment PRgeneration counter for struct se_device upon a successful
@@ -1039,10 +1041,16 @@
 
 	spin_lock(&pr_tmpl->registration_lock);
 	list_add_tail(&pr_reg->pr_reg_list, &pr_tmpl->registration_list);
-	pr_reg->pr_reg_deve->def_pr_registered = 1;
 
 	__core_scsi3_dump_registration(tfo, dev, nacl, pr_reg, register_type);
 	spin_unlock(&pr_tmpl->registration_lock);
+
+	rcu_read_lock();
+	deve = pr_reg->pr_reg_deve;
+	if (deve)
+		set_bit(DEF_PR_REG_ACTIVE, &deve->deve_flags);
+	rcu_read_unlock();
+
 	/*
 	 * Skip extra processing for ALL_TG_PT=0 or REGISTER_AND_MOVE.
 	 */
@@ -1054,6 +1062,8 @@
 	 */
 	list_for_each_entry_safe(pr_reg_tmp, pr_reg_tmp_safe,
 			&pr_reg->pr_reg_atp_list, pr_reg_atp_mem_list) {
+		struct se_node_acl *nacl_tmp = pr_reg_tmp->pr_reg_nacl;
+
 		list_del(&pr_reg_tmp->pr_reg_atp_mem_list);
 
 		pr_reg_tmp->pr_res_generation = core_scsi3_pr_generation(dev);
@@ -1061,12 +1071,17 @@
 		spin_lock(&pr_tmpl->registration_lock);
 		list_add_tail(&pr_reg_tmp->pr_reg_list,
 			      &pr_tmpl->registration_list);
-		pr_reg_tmp->pr_reg_deve->def_pr_registered = 1;
 
-		__core_scsi3_dump_registration(tfo, dev,
-				pr_reg_tmp->pr_reg_nacl, pr_reg_tmp,
-				register_type);
+		__core_scsi3_dump_registration(tfo, dev, nacl_tmp, pr_reg_tmp,
+					       register_type);
 		spin_unlock(&pr_tmpl->registration_lock);
+
+		rcu_read_lock();
+		deve = pr_reg_tmp->pr_reg_deve;
+		if (deve)
+			set_bit(DEF_PR_REG_ACTIVE, &deve->deve_flags);
+		rcu_read_unlock();
+
 		/*
 		 * Drop configfs group dependency reference from
 		 * __core_scsi3_alloc_registration()
@@ -1078,7 +1093,9 @@
 static int core_scsi3_alloc_registration(
 	struct se_device *dev,
 	struct se_node_acl *nacl,
+	struct se_lun *lun,
 	struct se_dev_entry *deve,
+	u64 mapped_lun,
 	unsigned char *isid,
 	u64 sa_res_key,
 	int all_tg_pt,
@@ -1088,8 +1105,9 @@
 {
 	struct t10_pr_registration *pr_reg;
 
-	pr_reg = __core_scsi3_alloc_registration(dev, nacl, deve, isid,
-			sa_res_key, all_tg_pt, aptpl);
+	pr_reg = __core_scsi3_alloc_registration(dev, nacl, lun, deve, mapped_lun,
+						 isid, sa_res_key, all_tg_pt,
+						 aptpl);
 	if (!pr_reg)
 		return -EPERM;
 
@@ -1242,13 +1260,13 @@
 	const struct target_core_fabric_ops *tfo =
 			pr_reg->pr_reg_nacl->se_tpg->se_tpg_tfo;
 	struct t10_reservation *pr_tmpl = &dev->t10_pr;
+	struct se_node_acl *nacl = pr_reg->pr_reg_nacl;
+	struct se_dev_entry *deve;
 	char i_buf[PR_REG_ISID_ID_LEN];
 
 	memset(i_buf, 0, PR_REG_ISID_ID_LEN);
 	core_pr_dump_initiator_port(pr_reg, i_buf, PR_REG_ISID_ID_LEN);
 
-	pr_reg->pr_reg_deve->def_pr_registered = 0;
-	pr_reg->pr_reg_deve->pr_res_key = 0;
 	if (!list_empty(&pr_reg->pr_reg_list))
 		list_del(&pr_reg->pr_reg_list);
 	/*
@@ -1257,6 +1275,8 @@
 	 */
 	if (dec_holders)
 		core_scsi3_put_pr_reg(pr_reg);
+
+	spin_unlock(&pr_tmpl->registration_lock);
 	/*
 	 * Wait until all reference from any other I_T nexuses for this
 	 * *pr_reg have been released.  Because list_del() is called above,
@@ -1264,13 +1284,18 @@
 	 * count back to zero, and we release *pr_reg.
 	 */
 	while (atomic_read(&pr_reg->pr_res_holders) != 0) {
-		spin_unlock(&pr_tmpl->registration_lock);
 		pr_debug("SPC-3 PR [%s] waiting for pr_res_holders\n",
 				tfo->get_fabric_name());
 		cpu_relax();
-		spin_lock(&pr_tmpl->registration_lock);
 	}
 
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, pr_reg->pr_res_mapped_lun);
+	if (deve)
+		clear_bit(DEF_PR_REG_ACTIVE, &deve->deve_flags);
+	rcu_read_unlock();
+
+	spin_lock(&pr_tmpl->registration_lock);
 	pr_debug("SPC-3 PR [%s] Service Action: UNREGISTER Initiator"
 		" Node: %s%s\n", tfo->get_fabric_name(),
 		pr_reg->pr_reg_nacl->initiatorname,
@@ -1392,12 +1417,14 @@
 
 static int core_scsi3_lunacl_depend_item(struct se_dev_entry *se_deve)
 {
-	struct se_lun_acl *lun_acl = se_deve->se_lun_acl;
+	struct se_lun_acl *lun_acl;
 	struct se_node_acl *nacl;
 	struct se_portal_group *tpg;
 	/*
 	 * For nacl->dynamic_node_acl=1
 	 */
+	lun_acl = rcu_dereference_check(se_deve->se_lun_acl,
+				atomic_read(&se_deve->pr_kref.refcount) != 0);
 	if (!lun_acl)
 		return 0;
 
@@ -1409,21 +1436,23 @@
 
 static void core_scsi3_lunacl_undepend_item(struct se_dev_entry *se_deve)
 {
-	struct se_lun_acl *lun_acl = se_deve->se_lun_acl;
+	struct se_lun_acl *lun_acl;
 	struct se_node_acl *nacl;
 	struct se_portal_group *tpg;
 	/*
 	 * For nacl->dynamic_node_acl=1
 	 */
+	lun_acl = rcu_dereference_check(se_deve->se_lun_acl,
+				atomic_read(&se_deve->pr_kref.refcount) != 0);
 	if (!lun_acl) {
-		atomic_dec_mb(&se_deve->pr_ref_count);
+		kref_put(&se_deve->pr_kref, target_pr_kref_release);
 		return;
 	}
 	nacl = lun_acl->se_lun_nacl;
 	tpg = nacl->se_tpg;
 
 	target_undepend_item(&lun_acl->se_lun_group.cg_item);
-	atomic_dec_mb(&se_deve->pr_ref_count);
+	kref_put(&se_deve->pr_kref, target_pr_kref_release);
 }
 
 static sense_reason_t
@@ -1436,30 +1465,25 @@
 	int aptpl)
 {
 	struct se_device *dev = cmd->se_dev;
-	struct se_port *tmp_port;
 	struct se_portal_group *dest_tpg = NULL, *tmp_tpg;
 	struct se_session *se_sess = cmd->se_sess;
 	struct se_node_acl *dest_node_acl = NULL;
-	struct se_dev_entry *dest_se_deve = NULL, *local_se_deve;
+	struct se_dev_entry *dest_se_deve = NULL;
 	struct t10_pr_registration *dest_pr_reg, *local_pr_reg, *pr_reg_e;
 	struct t10_pr_registration *pr_reg_tmp, *pr_reg_tmp_safe;
 	LIST_HEAD(tid_dest_list);
 	struct pr_transport_id_holder *tidh_new, *tidh, *tidh_tmp;
-	const struct target_core_fabric_ops *tmp_tf_ops;
-	unsigned char *buf;
-	unsigned char *ptr, *i_str = NULL, proto_ident, tmp_proto_ident;
+	unsigned char *buf, *ptr, proto_ident;
+	const unsigned char *i_str;
 	char *iport_ptr = NULL, i_buf[PR_REG_ISID_ID_LEN];
 	sense_reason_t ret;
 	u32 tpdl, tid_len = 0;
-	int dest_local_nexus;
 	u32 dest_rtpi = 0;
 
-	local_se_deve = se_sess->se_node_acl->device_list[cmd->orig_fe_lun];
 	/*
 	 * Allocate a struct pr_transport_id_holder and setup the
-	 * local_node_acl and local_se_deve pointers and add to
-	 * struct list_head tid_dest_list for add registration
-	 * processing in the loop of tid_dest_list below.
+	 * local_node_acl pointer and add to struct list_head tid_dest_list
+	 * for add registration processing in the loop of tid_dest_list below.
 	 */
 	tidh_new = kzalloc(sizeof(struct pr_transport_id_holder), GFP_KERNEL);
 	if (!tidh_new) {
@@ -1469,10 +1493,10 @@
 	INIT_LIST_HEAD(&tidh_new->dest_list);
 	tidh_new->dest_tpg = tpg;
 	tidh_new->dest_node_acl = se_sess->se_node_acl;
-	tidh_new->dest_se_deve = local_se_deve;
 
 	local_pr_reg = __core_scsi3_alloc_registration(cmd->se_dev,
-				se_sess->se_node_acl, local_se_deve, l_isid,
+				se_sess->se_node_acl, cmd->se_lun,
+				NULL, cmd->orig_fe_lun, l_isid,
 				sa_res_key, all_tg_pt, aptpl);
 	if (!local_pr_reg) {
 		kfree(tidh_new);
@@ -1481,10 +1505,10 @@
 	tidh_new->dest_pr_reg = local_pr_reg;
 	/*
 	 * The local I_T nexus does not hold any configfs dependances,
-	 * so we set tid_h->dest_local_nexus=1 to prevent the
+	 * so we set tidh_new->dest_se_deve to NULL to prevent the
 	 * configfs_undepend_item() calls in the tid_dest_list loops below.
 	 */
-	tidh_new->dest_local_nexus = 1;
+	tidh_new->dest_se_deve = NULL;
 	list_add_tail(&tidh_new->dest_list, &tid_dest_list);
 
 	if (cmd->data_length < 28) {
@@ -1525,32 +1549,25 @@
 	ptr = &buf[28];
 
 	while (tpdl > 0) {
+		struct se_lun *dest_lun, *tmp_lun;
+
 		proto_ident = (ptr[0] & 0x0f);
 		dest_tpg = NULL;
 
 		spin_lock(&dev->se_port_lock);
-		list_for_each_entry(tmp_port, &dev->dev_sep_list, sep_list) {
-			tmp_tpg = tmp_port->sep_tpg;
-			if (!tmp_tpg)
-				continue;
-			tmp_tf_ops = tmp_tpg->se_tpg_tfo;
-			if (!tmp_tf_ops)
-				continue;
-			if (!tmp_tf_ops->get_fabric_proto_ident ||
-			    !tmp_tf_ops->tpg_parse_pr_out_transport_id)
-				continue;
+		list_for_each_entry(tmp_lun, &dev->dev_sep_list, lun_dev_link) {
+			tmp_tpg = tmp_lun->lun_tpg;
+
 			/*
 			 * Look for the matching proto_ident provided by
 			 * the received TransportID
 			 */
-			tmp_proto_ident = tmp_tf_ops->get_fabric_proto_ident(tmp_tpg);
-			if (tmp_proto_ident != proto_ident)
+			if (tmp_tpg->proto_id != proto_ident)
 				continue;
-			dest_rtpi = tmp_port->sep_rtpi;
+			dest_rtpi = tmp_lun->lun_rtpi;
 
-			i_str = tmp_tf_ops->tpg_parse_pr_out_transport_id(
-					tmp_tpg, (const char *)ptr, &tid_len,
-					&iport_ptr);
+			i_str = target_parse_pr_out_transport_id(tmp_tpg,
+					(const char *)ptr, &tid_len, &iport_ptr);
 			if (!i_str)
 				continue;
 
@@ -1569,12 +1586,12 @@
 			 * from the decoded fabric module specific TransportID
 			 * at *i_str.
 			 */
-			spin_lock_irq(&tmp_tpg->acl_node_lock);
+			mutex_lock(&tmp_tpg->acl_node_mutex);
 			dest_node_acl = __core_tpg_get_initiator_node_acl(
 						tmp_tpg, i_str);
 			if (dest_node_acl)
 				atomic_inc_mb(&dest_node_acl->acl_pr_ref_count);
-			spin_unlock_irq(&tmp_tpg->acl_node_lock);
+			mutex_unlock(&tmp_tpg->acl_node_mutex);
 
 			if (!dest_node_acl) {
 				core_scsi3_tpg_undepend_item(tmp_tpg);
@@ -1644,7 +1661,7 @@
 		if (core_scsi3_lunacl_depend_item(dest_se_deve)) {
 			pr_err("core_scsi3_lunacl_depend_item()"
 					" failed\n");
-			atomic_dec_mb(&dest_se_deve->pr_ref_count);
+			kref_put(&dest_se_deve->pr_kref, target_pr_kref_release);
 			core_scsi3_nodeacl_undepend_item(dest_node_acl);
 			core_scsi3_tpg_undepend_item(dest_tpg);
 			ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
@@ -1652,7 +1669,7 @@
 		}
 
 		pr_debug("SPC-3 PR SPEC_I_PT: Located %s Node: %s"
-			" dest_se_deve mapped_lun: %u\n",
+			" dest_se_deve mapped_lun: %llu\n",
 			dest_tpg->se_tpg_tfo->get_fabric_name(),
 			dest_node_acl->initiatorname, dest_se_deve->mapped_lun);
 
@@ -1708,9 +1725,13 @@
 		 * and then call __core_scsi3_add_registration() in the
 		 * 2nd loop which will never fail.
 		 */
+		dest_lun = rcu_dereference_check(dest_se_deve->se_lun,
+				atomic_read(&dest_se_deve->pr_kref.refcount) != 0);
+
 		dest_pr_reg = __core_scsi3_alloc_registration(cmd->se_dev,
-				dest_node_acl, dest_se_deve, iport_ptr,
-				sa_res_key, all_tg_pt, aptpl);
+					dest_node_acl, dest_lun, dest_se_deve,
+					dest_se_deve->mapped_lun, iport_ptr,
+					sa_res_key, all_tg_pt, aptpl);
 		if (!dest_pr_reg) {
 			core_scsi3_lunacl_undepend_item(dest_se_deve);
 			core_scsi3_nodeacl_undepend_item(dest_node_acl);
@@ -1748,7 +1769,6 @@
 		dest_node_acl = tidh->dest_node_acl;
 		dest_se_deve = tidh->dest_se_deve;
 		dest_pr_reg = tidh->dest_pr_reg;
-		dest_local_nexus = tidh->dest_local_nexus;
 
 		list_del(&tidh->dest_list);
 		kfree(tidh);
@@ -1761,10 +1781,11 @@
 
 		pr_debug("SPC-3 PR [%s] SPEC_I_PT: Successfully"
 			" registered Transport ID for Node: %s%s Mapped LUN:"
-			" %u\n", dest_tpg->se_tpg_tfo->get_fabric_name(),
-			dest_node_acl->initiatorname, i_buf, dest_se_deve->mapped_lun);
+			" %llu\n", dest_tpg->se_tpg_tfo->get_fabric_name(),
+			dest_node_acl->initiatorname, i_buf, (dest_se_deve) ?
+			dest_se_deve->mapped_lun : 0);
 
-		if (dest_local_nexus)
+		if (!dest_se_deve)
 			continue;
 
 		core_scsi3_lunacl_undepend_item(dest_se_deve);
@@ -1785,7 +1806,6 @@
 		dest_node_acl = tidh->dest_node_acl;
 		dest_se_deve = tidh->dest_se_deve;
 		dest_pr_reg = tidh->dest_pr_reg;
-		dest_local_nexus = tidh->dest_local_nexus;
 
 		list_del(&tidh->dest_list);
 		kfree(tidh);
@@ -1803,7 +1823,7 @@
 
 		kmem_cache_free(t10_pr_reg_cache, dest_pr_reg);
 
-		if (dest_local_nexus)
+		if (!dest_se_deve)
 			continue;
 
 		core_scsi3_lunacl_undepend_item(dest_se_deve);
@@ -1818,7 +1838,6 @@
 	unsigned char *buf,
 	u32 pr_aptpl_buf_len)
 {
-	struct se_lun *lun;
 	struct se_portal_group *tpg;
 	struct t10_pr_registration *pr_reg;
 	unsigned char tmp[512], isid_buf[32];
@@ -1837,7 +1856,6 @@
 		tmp[0] = '\0';
 		isid_buf[0] = '\0';
 		tpg = pr_reg->pr_reg_nacl->se_tpg;
-		lun = pr_reg->pr_reg_tg_pt_lun;
 		/*
 		 * Write out any ISID value to APTPL metadata that was included
 		 * in the original registration.
@@ -1856,7 +1874,7 @@
 				"sa_res_key=%llu\n"
 				"res_holder=1\nres_type=%02x\n"
 				"res_scope=%02x\nres_all_tg_pt=%d\n"
-				"mapped_lun=%u\n", reg_count,
+				"mapped_lun=%llu\n", reg_count,
 				tpg->se_tpg_tfo->get_fabric_name(),
 				pr_reg->pr_reg_nacl->initiatorname, isid_buf,
 				pr_reg->pr_res_key, pr_reg->pr_res_type,
@@ -1866,7 +1884,7 @@
 			snprintf(tmp, 512, "PR_REG_START: %d\n"
 				"initiator_fabric=%s\ninitiator_node=%s\n%s"
 				"sa_res_key=%llu\nres_holder=0\n"
-				"res_all_tg_pt=%d\nmapped_lun=%u\n",
+				"res_all_tg_pt=%d\nmapped_lun=%llu\n",
 				reg_count, tpg->se_tpg_tfo->get_fabric_name(),
 				pr_reg->pr_reg_nacl->initiatorname, isid_buf,
 				pr_reg->pr_res_key, pr_reg->pr_reg_all_tg_pt,
@@ -1885,11 +1903,12 @@
 		 * Include information about the associated SCSI target port.
 		 */
 		snprintf(tmp, 512, "target_fabric=%s\ntarget_node=%s\n"
-			"tpgt=%hu\nport_rtpi=%hu\ntarget_lun=%u\nPR_REG_END:"
+			"tpgt=%hu\nport_rtpi=%hu\ntarget_lun=%llu\nPR_REG_END:"
 			" %d\n", tpg->se_tpg_tfo->get_fabric_name(),
 			tpg->se_tpg_tfo->tpg_get_wwn(tpg),
 			tpg->se_tpg_tfo->tpg_get_tag(tpg),
-			lun->lun_sep->sep_rtpi, lun->unpacked_lun, reg_count);
+			pr_reg->tg_pt_sep_rtpi, pr_reg->pr_aptpl_target_lun,
+			reg_count);
 
 		if ((len + strlen(tmp) >= pr_aptpl_buf_len)) {
 			pr_err("Unable to update renaming APTPL metadata,"
@@ -2000,7 +2019,6 @@
 {
 	struct se_session *se_sess = cmd->se_sess;
 	struct se_device *dev = cmd->se_dev;
-	struct se_dev_entry *se_deve;
 	struct se_lun *se_lun = cmd->se_lun;
 	struct se_portal_group *se_tpg;
 	struct t10_pr_registration *pr_reg, *pr_reg_p, *pr_reg_tmp;
@@ -2014,7 +2032,6 @@
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 	se_tpg = se_sess->se_tpg;
-	se_deve = se_sess->se_node_acl->device_list[cmd->orig_fe_lun];
 
 	if (se_tpg->se_tpg_tfo->sess_get_initiator_sid) {
 		memset(&isid_buf[0], 0, PR_REG_ISID_LEN);
@@ -2045,7 +2062,8 @@
 			 * Logical Unit of the SCSI device server.
 			 */
 			if (core_scsi3_alloc_registration(cmd->se_dev,
-					se_sess->se_node_acl, se_deve, isid_ptr,
+					se_sess->se_node_acl, cmd->se_lun,
+					NULL, cmd->orig_fe_lun, isid_ptr,
 					sa_res_key, all_tg_pt, aptpl,
 					register_type, 0)) {
 				pr_err("Unable to allocate"
@@ -2066,7 +2084,6 @@
 			if (ret != 0)
 				return ret;
 		}
-
 		return core_scsi3_update_and_write_aptpl(dev, aptpl);
 	}
 
@@ -2180,7 +2197,7 @@
 					&pr_tmpl->registration_list,
 					pr_reg_list) {
 
-				core_scsi3_ua_allocate(
+				target_ua_allocate_lun(
 					pr_reg_p->pr_reg_nacl,
 					pr_reg_p->pr_res_mapped_lun,
 					0x2A,
@@ -2607,7 +2624,7 @@
 		if (pr_reg_p == pr_reg)
 			continue;
 
-		core_scsi3_ua_allocate(pr_reg_p->pr_reg_nacl,
+		target_ua_allocate_lun(pr_reg_p->pr_reg_nacl,
 				pr_reg_p->pr_res_mapped_lun,
 				0x2A, ASCQ_2AH_RESERVATIONS_RELEASED);
 	}
@@ -2630,7 +2647,7 @@
 	struct se_session *se_sess = cmd->se_sess;
 	struct t10_reservation *pr_tmpl = &dev->t10_pr;
 	struct t10_pr_registration *pr_reg, *pr_reg_tmp, *pr_reg_n, *pr_res_holder;
-	u32 pr_res_mapped_lun = 0;
+	u64 pr_res_mapped_lun = 0;
 	int calling_it_nexus = 0;
 	/*
 	 * Locate the existing *pr_reg via struct se_node_acl pointers
@@ -2692,7 +2709,7 @@
 		 *    additional sense code set to RESERVATIONS PREEMPTED.
 		 */
 		if (!calling_it_nexus)
-			core_scsi3_ua_allocate(pr_reg_nacl, pr_res_mapped_lun,
+			target_ua_allocate_lun(pr_reg_nacl, pr_res_mapped_lun,
 				0x2A, ASCQ_2AH_RESERVATIONS_PREEMPTED);
 	}
 	spin_unlock(&pr_tmpl->registration_lock);
@@ -2786,7 +2803,7 @@
 	LIST_HEAD(preempt_and_abort_list);
 	struct t10_pr_registration *pr_reg, *pr_reg_tmp, *pr_reg_n, *pr_res_holder;
 	struct t10_reservation *pr_tmpl = &dev->t10_pr;
-	u32 pr_res_mapped_lun = 0;
+	u64 pr_res_mapped_lun = 0;
 	int all_reg = 0, calling_it_nexus = 0;
 	bool sa_res_key_unmatched = sa_res_key != 0;
 	int prh_type = 0, prh_scope = 0;
@@ -2901,7 +2918,7 @@
 						NULL, 0);
 			}
 			if (!calling_it_nexus)
-				core_scsi3_ua_allocate(pr_reg_nacl,
+				target_ua_allocate_lun(pr_reg_nacl,
 					pr_res_mapped_lun, 0x2A,
 					ASCQ_2AH_REGISTRATIONS_PREEMPTED);
 		}
@@ -3007,7 +3024,7 @@
 		 *    persistent reservation and/or registration, with the
 		 *    additional sense code set to REGISTRATIONS PREEMPTED;
 		 */
-		core_scsi3_ua_allocate(pr_reg_nacl, pr_res_mapped_lun, 0x2A,
+		target_ua_allocate_lun(pr_reg_nacl, pr_res_mapped_lun, 0x2A,
 				ASCQ_2AH_REGISTRATIONS_PREEMPTED);
 	}
 	spin_unlock(&pr_tmpl->registration_lock);
@@ -3040,7 +3057,7 @@
 			if (calling_it_nexus)
 				continue;
 
-			core_scsi3_ua_allocate(pr_reg->pr_reg_nacl,
+			target_ua_allocate_lun(pr_reg->pr_reg_nacl,
 					pr_reg->pr_res_mapped_lun, 0x2A,
 					ASCQ_2AH_RESERVATIONS_RELEASED);
 		}
@@ -3099,15 +3116,14 @@
 	struct se_session *se_sess = cmd->se_sess;
 	struct se_device *dev = cmd->se_dev;
 	struct se_dev_entry *dest_se_deve = NULL;
-	struct se_lun *se_lun = cmd->se_lun;
+	struct se_lun *se_lun = cmd->se_lun, *tmp_lun;
 	struct se_node_acl *pr_res_nacl, *pr_reg_nacl, *dest_node_acl = NULL;
-	struct se_port *se_port;
 	struct se_portal_group *se_tpg, *dest_se_tpg = NULL;
 	const struct target_core_fabric_ops *dest_tf_ops = NULL, *tf_ops;
 	struct t10_pr_registration *pr_reg, *pr_res_holder, *dest_pr_reg;
 	struct t10_reservation *pr_tmpl = &dev->t10_pr;
 	unsigned char *buf;
-	unsigned char *initiator_str;
+	const unsigned char *initiator_str;
 	char *iport_ptr = NULL, i_buf[PR_REG_ISID_ID_LEN];
 	u32 tid_len, tmp_tid_len;
 	int new_reg = 0, type, scope, matching_iname;
@@ -3186,12 +3202,10 @@
 	}
 
 	spin_lock(&dev->se_port_lock);
-	list_for_each_entry(se_port, &dev->dev_sep_list, sep_list) {
-		if (se_port->sep_rtpi != rtpi)
+	list_for_each_entry(tmp_lun, &dev->dev_sep_list, lun_dev_link) {
+		if (tmp_lun->lun_rtpi != rtpi)
 			continue;
-		dest_se_tpg = se_port->sep_tpg;
-		if (!dest_se_tpg)
-			continue;
+		dest_se_tpg = tmp_lun->lun_tpg;
 		dest_tf_ops = dest_se_tpg->se_tpg_tfo;
 		if (!dest_tf_ops)
 			continue;
@@ -3230,23 +3244,16 @@
 	pr_debug("SPC-3 PR REGISTER_AND_MOVE: Extracted Protocol Identifier:"
 			" 0x%02x\n", proto_ident);
 
-	if (proto_ident != dest_tf_ops->get_fabric_proto_ident(dest_se_tpg)) {
+	if (proto_ident != dest_se_tpg->proto_id) {
 		pr_err("SPC-3 PR REGISTER_AND_MOVE: Received"
 			" proto_ident: 0x%02x does not match ident: 0x%02x"
 			" from fabric: %s\n", proto_ident,
-			dest_tf_ops->get_fabric_proto_ident(dest_se_tpg),
+			dest_se_tpg->proto_id,
 			dest_tf_ops->get_fabric_name());
 		ret = TCM_INVALID_PARAMETER_LIST;
 		goto out;
 	}
-	if (dest_tf_ops->tpg_parse_pr_out_transport_id == NULL) {
-		pr_err("SPC-3 PR REGISTER_AND_MOVE: Fabric does not"
-			" containg a valid tpg_parse_pr_out_transport_id"
-			" function pointer\n");
-		ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-		goto out;
-	}
-	initiator_str = dest_tf_ops->tpg_parse_pr_out_transport_id(dest_se_tpg,
+	initiator_str = target_parse_pr_out_transport_id(dest_se_tpg,
 			(const char *)&buf[24], &tmp_tid_len, &iport_ptr);
 	if (!initiator_str) {
 		pr_err("SPC-3 PR REGISTER_AND_MOVE: Unable to locate"
@@ -3295,12 +3302,12 @@
 	/*
 	 * Locate the destination struct se_node_acl from the received Transport ID
 	 */
-	spin_lock_irq(&dest_se_tpg->acl_node_lock);
+	mutex_lock(&dest_se_tpg->acl_node_mutex);
 	dest_node_acl = __core_tpg_get_initiator_node_acl(dest_se_tpg,
 				initiator_str);
 	if (dest_node_acl)
 		atomic_inc_mb(&dest_node_acl->acl_pr_ref_count);
-	spin_unlock_irq(&dest_se_tpg->acl_node_lock);
+	mutex_unlock(&dest_se_tpg->acl_node_mutex);
 
 	if (!dest_node_acl) {
 		pr_err("Unable to locate %s dest_node_acl for"
@@ -3337,14 +3344,14 @@
 
 	if (core_scsi3_lunacl_depend_item(dest_se_deve)) {
 		pr_err("core_scsi3_lunacl_depend_item() failed\n");
-		atomic_dec_mb(&dest_se_deve->pr_ref_count);
+		kref_put(&dest_se_deve->pr_kref, target_pr_kref_release);
 		dest_se_deve = NULL;
 		ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 		goto out;
 	}
 
 	pr_debug("SPC-3 PR REGISTER_AND_MOVE: Located %s node %s LUN"
-		" ACL for dest_se_deve->mapped_lun: %u\n",
+		" ACL for dest_se_deve->mapped_lun: %llu\n",
 		dest_tf_ops->get_fabric_name(), dest_node_acl->initiatorname,
 		dest_se_deve->mapped_lun);
 
@@ -3421,13 +3428,17 @@
 	dest_pr_reg = __core_scsi3_locate_pr_reg(dev, dest_node_acl,
 					iport_ptr);
 	if (!dest_pr_reg) {
-		if (core_scsi3_alloc_registration(cmd->se_dev,
-				dest_node_acl, dest_se_deve, iport_ptr,
-				sa_res_key, 0, aptpl, 2, 1)) {
-			spin_unlock(&dev->dev_reservation_lock);
+		struct se_lun *dest_lun = rcu_dereference_check(dest_se_deve->se_lun,
+				atomic_read(&dest_se_deve->pr_kref.refcount) != 0);
+
+		spin_unlock(&dev->dev_reservation_lock);
+		if (core_scsi3_alloc_registration(cmd->se_dev, dest_node_acl,
+					dest_lun, dest_se_deve, dest_se_deve->mapped_lun,
+					iport_ptr, sa_res_key, 0, aptpl, 2, 1)) {
 			ret = TCM_INVALID_PARAMETER_LIST;
 			goto out;
 		}
+		spin_lock(&dev->dev_reservation_lock);
 		dest_pr_reg = __core_scsi3_locate_pr_reg(dev, dest_node_acl,
 						iport_ptr);
 		new_reg = 1;
@@ -3883,9 +3894,10 @@
 	struct t10_pr_registration *pr_reg, *pr_reg_tmp;
 	struct t10_reservation *pr_tmpl = &dev->t10_pr;
 	unsigned char *buf;
-	u32 add_desc_len = 0, add_len = 0, desc_len, exp_desc_len;
+	u32 add_desc_len = 0, add_len = 0;
 	u32 off = 8; /* off into first Full Status descriptor */
 	int format_code = 0, pr_res_type = 0, pr_res_scope = 0;
+	int exp_desc_len, desc_len;
 	bool all_reg = false;
 
 	if (cmd->data_length < 8) {
@@ -3930,10 +3942,10 @@
 		 * Determine expected length of $FABRIC_MOD specific
 		 * TransportID full status descriptor..
 		 */
-		exp_desc_len = se_tpg->se_tpg_tfo->tpg_get_pr_transport_id_len(
-				se_tpg, se_nacl, pr_reg, &format_code);
-
-		if ((exp_desc_len + add_len) > cmd->data_length) {
+		exp_desc_len = target_get_pr_transport_id_len(se_nacl, pr_reg,
+					&format_code);
+		if (exp_desc_len < 0 ||
+		    exp_desc_len + add_len > cmd->data_length) {
 			pr_warn("SPC-3 PRIN READ_FULL_STATUS ran"
 				" out of buffer: %d\n", cmd->data_length);
 			spin_lock(&pr_tmpl->registration_lock);
@@ -3990,21 +4002,26 @@
 		 * IDENTIFIER field are not defined by this standard.
 		 */
 		if (!pr_reg->pr_reg_all_tg_pt) {
-			struct se_port *port = pr_reg->pr_reg_tg_pt_lun->lun_sep;
+			u16 sep_rtpi = pr_reg->tg_pt_sep_rtpi;
 
-			buf[off++] = ((port->sep_rtpi >> 8) & 0xff);
-			buf[off++] = (port->sep_rtpi & 0xff);
+			buf[off++] = ((sep_rtpi >> 8) & 0xff);
+			buf[off++] = (sep_rtpi & 0xff);
 		} else
 			off += 2; /* Skip over RELATIVE TARGET PORT IDENTIFIER */
 
+		buf[off+4] = se_tpg->proto_id;
+
 		/*
-		 * Now, have the $FABRIC_MOD fill in the protocol identifier
+		 * Now, have the $FABRIC_MOD fill in the transport ID.
 		 */
-		desc_len = se_tpg->se_tpg_tfo->tpg_get_pr_transport_id(se_tpg,
-				se_nacl, pr_reg, &format_code, &buf[off+4]);
+		desc_len = target_get_pr_transport_id(se_nacl, pr_reg,
+				&format_code, &buf[off+4]);
 
 		spin_lock(&pr_tmpl->registration_lock);
 		atomic_dec_mb(&pr_reg->pr_res_holders);
+
+		if (desc_len < 0)
+			break;
 		/*
 		 * Set the ADDITIONAL DESCRIPTOR LENGTH
 		 */
diff --git a/drivers/target/target_core_pr.h b/drivers/target/target_core_pr.h
index 749fd7b..e3d26e9 100644
--- a/drivers/target/target_core_pr.h
+++ b/drivers/target/target_core_pr.h
@@ -56,11 +56,11 @@
 extern sense_reason_t target_scsi2_reservation_reserve(struct se_cmd *);
 extern int core_scsi3_alloc_aptpl_registration(
 			struct t10_reservation *, u64,
-			unsigned char *, unsigned char *, u32,
-			unsigned char *, u16, u32, int, int, u8);
+			unsigned char *, unsigned char *, u64,
+			unsigned char *, u16, u64, int, int, u8);
 extern int core_scsi3_check_aptpl_registration(struct se_device *,
 			struct se_portal_group *, struct se_lun *,
-			struct se_node_acl *, u32);
+			struct se_node_acl *, u64);
 extern void core_scsi3_free_pr_reg_from_nacl(struct se_device *,
 					     struct se_node_acl *);
 extern void core_scsi3_free_all_registrations(struct se_device *);
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 26581e2..08e9084 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -42,9 +42,9 @@
 
 #include <target/target_core_base.h>
 #include <target/target_core_backend.h>
-#include <target/target_core_backend_configfs.h>
 
 #include "target_core_alua.h"
+#include "target_core_internal.h"
 #include "target_core_pscsi.h"
 
 #define ISPRINT(a)  ((a >= ' ') && (a <= '~'))
@@ -54,8 +54,6 @@
 	return container_of(dev, struct pscsi_dev_virt, dev);
 }
 
-static struct se_subsystem_api pscsi_template;
-
 static sense_reason_t pscsi_execute_cmd(struct se_cmd *cmd);
 static void pscsi_req_done(struct request *, int);
 
@@ -80,7 +78,7 @@
 
 	pr_debug("CORE_HBA[%d] - TCM SCSI HBA Driver %s on"
 		" Generic Target Core Stack %s\n", hba->hba_id,
-		PSCSI_VERSION, TARGET_CORE_MOD_VERSION);
+		PSCSI_VERSION, TARGET_CORE_VERSION);
 	pr_debug("CORE_HBA[%d] - Attached SCSI HBA to Generic\n",
 	       hba->hba_id);
 
@@ -579,6 +577,14 @@
 	return -ENODEV;
 }
 
+static void pscsi_dev_call_rcu(struct rcu_head *p)
+{
+	struct se_device *dev = container_of(p, struct se_device, rcu_head);
+	struct pscsi_dev_virt *pdv = PSCSI_DEV(dev);
+
+	kfree(pdv);
+}
+
 static void pscsi_free_device(struct se_device *dev)
 {
 	struct pscsi_dev_virt *pdv = PSCSI_DEV(dev);
@@ -610,8 +616,7 @@
 
 		pdv->pdv_sd = NULL;
 	}
-
-	kfree(pdv);
+	call_rcu(&dev->rcu_head, pscsi_dev_call_rcu);
 }
 
 static void pscsi_transport_complete(struct se_cmd *cmd, struct scatterlist *sg,
@@ -635,12 +640,14 @@
 	 * Hack to make sure that Write-Protect modepage is set if R/O mode is
 	 * forced.
 	 */
-	if (!cmd->se_deve || !cmd->data_length)
+	if (!cmd->data_length)
 		goto after_mode_sense;
 
 	if (((cdb[0] == MODE_SENSE) || (cdb[0] == MODE_SENSE_10)) &&
 	     (status_byte(result) << 1) == SAM_STAT_GOOD) {
-		if (cmd->se_deve->lun_flags & TRANSPORT_LUNFLAGS_READ_ONLY) {
+		bool read_only = target_lun_is_rdonly(cmd);
+
+		if (read_only) {
 			unsigned char *buf;
 
 			buf = transport_kmap_data_sg(cmd);
@@ -1116,27 +1123,7 @@
 	kfree(pt);
 }
 
-DEF_TB_DEV_ATTRIB_RO(pscsi, hw_pi_prot_type);
-TB_DEV_ATTR_RO(pscsi, hw_pi_prot_type);
-
-DEF_TB_DEV_ATTRIB_RO(pscsi, hw_block_size);
-TB_DEV_ATTR_RO(pscsi, hw_block_size);
-
-DEF_TB_DEV_ATTRIB_RO(pscsi, hw_max_sectors);
-TB_DEV_ATTR_RO(pscsi, hw_max_sectors);
-
-DEF_TB_DEV_ATTRIB_RO(pscsi, hw_queue_depth);
-TB_DEV_ATTR_RO(pscsi, hw_queue_depth);
-
-static struct configfs_attribute *pscsi_backend_dev_attrs[] = {
-	&pscsi_dev_attrib_hw_pi_prot_type.attr,
-	&pscsi_dev_attrib_hw_block_size.attr,
-	&pscsi_dev_attrib_hw_max_sectors.attr,
-	&pscsi_dev_attrib_hw_queue_depth.attr,
-	NULL,
-};
-
-static struct se_subsystem_api pscsi_template = {
+static const struct target_backend_ops pscsi_ops = {
 	.name			= "pscsi",
 	.owner			= THIS_MODULE,
 	.transport_flags	= TRANSPORT_FLAG_PASSTHROUGH,
@@ -1152,21 +1139,17 @@
 	.show_configfs_dev_params = pscsi_show_configfs_dev_params,
 	.get_device_type	= pscsi_get_device_type,
 	.get_blocks		= pscsi_get_blocks,
+	.tb_dev_attrib_attrs	= passthrough_attrib_attrs,
 };
 
 static int __init pscsi_module_init(void)
 {
-	struct target_backend_cits *tbc = &pscsi_template.tb_cits;
-
-	target_core_setup_sub_cits(&pscsi_template);
-	tbc->tb_dev_attrib_cit.ct_attrs = pscsi_backend_dev_attrs;
-
-	return transport_subsystem_register(&pscsi_template);
+	return transport_backend_register(&pscsi_ops);
 }
 
 static void __exit pscsi_module_exit(void)
 {
-	transport_subsystem_release(&pscsi_template);
+	target_backend_unregister(&pscsi_ops);
 }
 
 MODULE_DESCRIPTION("TCM PSCSI subsystem plugin");
diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c
index b2d8f6f..4703f40 100644
--- a/drivers/target/target_core_rd.c
+++ b/drivers/target/target_core_rd.c
@@ -33,7 +33,6 @@
 
 #include <target/target_core_base.h>
 #include <target/target_core_backend.h>
-#include <target/target_core_backend_configfs.h>
 
 #include "target_core_rd.h"
 
@@ -42,10 +41,6 @@
 	return container_of(dev, struct rd_dev, dev);
 }
 
-/*	rd_attach_hba(): (Part of se_subsystem_api_t template)
- *
- *
- */
 static int rd_attach_hba(struct se_hba *hba, u32 host_id)
 {
 	struct rd_host *rd_host;
@@ -62,7 +57,7 @@
 
 	pr_debug("CORE_HBA[%d] - TCM Ramdisk HBA Driver %s on"
 		" Generic Target Core Stack %s\n", hba->hba_id,
-		RD_HBA_VERSION, TARGET_CORE_MOD_VERSION);
+		RD_HBA_VERSION, TARGET_CORE_VERSION);
 
 	return 0;
 }
@@ -354,12 +349,20 @@
 	return ret;
 }
 
+static void rd_dev_call_rcu(struct rcu_head *p)
+{
+	struct se_device *dev = container_of(p, struct se_device, rcu_head);
+	struct rd_dev *rd_dev = RD_DEV(dev);
+
+	kfree(rd_dev);
+}
+
 static void rd_free_device(struct se_device *dev)
 {
 	struct rd_dev *rd_dev = RD_DEV(dev);
 
 	rd_release_device_space(rd_dev);
-	kfree(rd_dev);
+	call_rcu(&dev->rcu_head, rd_dev_call_rcu);
 }
 
 static struct rd_dev_sg_table *rd_get_sg_table(struct rd_dev *rd_dev, u32 page)
@@ -402,10 +405,7 @@
 	return NULL;
 }
 
-typedef sense_reason_t (*dif_verify)(struct se_cmd *, sector_t, unsigned int,
-				     unsigned int, struct scatterlist *, int);
-
-static sense_reason_t rd_do_prot_rw(struct se_cmd *cmd, dif_verify dif_verify)
+static sense_reason_t rd_do_prot_rw(struct se_cmd *cmd, bool is_read)
 {
 	struct se_device *se_dev = cmd->se_dev;
 	struct rd_dev *dev = RD_DEV(se_dev);
@@ -465,7 +465,16 @@
 
 #endif /* !CONFIG_ARCH_HAS_SG_CHAIN */
 
-	rc = dif_verify(cmd, cmd->t_task_lba, sectors, 0, prot_sg, prot_offset);
+	if (is_read)
+		rc = sbc_dif_verify(cmd, cmd->t_task_lba, sectors, 0,
+				    prot_sg, prot_offset);
+	else
+		rc = sbc_dif_verify(cmd, cmd->t_task_lba, sectors, 0,
+				    cmd->t_prot_sg, 0);
+
+	if (!rc)
+		sbc_dif_copy_prot(cmd, sectors, is_read, prot_sg, prot_offset);
+
 	if (need_to_release)
 		kfree(prot_sg);
 
@@ -511,7 +520,7 @@
 
 	if (cmd->prot_type && se_dev->dev_attrib.pi_prot_type &&
 	    data_direction == DMA_TO_DEVICE) {
-		rc = rd_do_prot_rw(cmd, sbc_dif_verify_write);
+		rc = rd_do_prot_rw(cmd, false);
 		if (rc)
 			return rc;
 	}
@@ -579,7 +588,7 @@
 
 	if (cmd->prot_type && se_dev->dev_attrib.pi_prot_type &&
 	    data_direction == DMA_FROM_DEVICE) {
-		rc = rd_do_prot_rw(cmd, sbc_dif_verify_read);
+		rc = rd_do_prot_rw(cmd, true);
 		if (rc)
 			return rc;
 	}
@@ -693,42 +702,7 @@
 	return sbc_parse_cdb(cmd, &rd_sbc_ops);
 }
 
-DEF_TB_DEFAULT_ATTRIBS(rd_mcp);
-
-static struct configfs_attribute *rd_mcp_backend_dev_attrs[] = {
-	&rd_mcp_dev_attrib_emulate_model_alias.attr,
-	&rd_mcp_dev_attrib_emulate_dpo.attr,
-	&rd_mcp_dev_attrib_emulate_fua_write.attr,
-	&rd_mcp_dev_attrib_emulate_fua_read.attr,
-	&rd_mcp_dev_attrib_emulate_write_cache.attr,
-	&rd_mcp_dev_attrib_emulate_ua_intlck_ctrl.attr,
-	&rd_mcp_dev_attrib_emulate_tas.attr,
-	&rd_mcp_dev_attrib_emulate_tpu.attr,
-	&rd_mcp_dev_attrib_emulate_tpws.attr,
-	&rd_mcp_dev_attrib_emulate_caw.attr,
-	&rd_mcp_dev_attrib_emulate_3pc.attr,
-	&rd_mcp_dev_attrib_pi_prot_type.attr,
-	&rd_mcp_dev_attrib_hw_pi_prot_type.attr,
-	&rd_mcp_dev_attrib_pi_prot_format.attr,
-	&rd_mcp_dev_attrib_enforce_pr_isids.attr,
-	&rd_mcp_dev_attrib_is_nonrot.attr,
-	&rd_mcp_dev_attrib_emulate_rest_reord.attr,
-	&rd_mcp_dev_attrib_force_pr_aptpl.attr,
-	&rd_mcp_dev_attrib_hw_block_size.attr,
-	&rd_mcp_dev_attrib_block_size.attr,
-	&rd_mcp_dev_attrib_hw_max_sectors.attr,
-	&rd_mcp_dev_attrib_optimal_sectors.attr,
-	&rd_mcp_dev_attrib_hw_queue_depth.attr,
-	&rd_mcp_dev_attrib_queue_depth.attr,
-	&rd_mcp_dev_attrib_max_unmap_lba_count.attr,
-	&rd_mcp_dev_attrib_max_unmap_block_desc_count.attr,
-	&rd_mcp_dev_attrib_unmap_granularity.attr,
-	&rd_mcp_dev_attrib_unmap_granularity_alignment.attr,
-	&rd_mcp_dev_attrib_max_write_same_len.attr,
-	NULL,
-};
-
-static struct se_subsystem_api rd_mcp_template = {
+static const struct target_backend_ops rd_mcp_ops = {
 	.name			= "rd_mcp",
 	.inquiry_prod		= "RAMDISK-MCP",
 	.inquiry_rev		= RD_MCP_VERSION,
@@ -744,25 +718,15 @@
 	.get_blocks		= rd_get_blocks,
 	.init_prot		= rd_init_prot,
 	.free_prot		= rd_free_prot,
+	.tb_dev_attrib_attrs	= sbc_attrib_attrs,
 };
 
 int __init rd_module_init(void)
 {
-	struct target_backend_cits *tbc = &rd_mcp_template.tb_cits;
-	int ret;
-
-	target_core_setup_sub_cits(&rd_mcp_template);
-	tbc->tb_dev_attrib_cit.ct_attrs = rd_mcp_backend_dev_attrs;
-
-	ret = transport_subsystem_register(&rd_mcp_template);
-	if (ret < 0) {
-		return ret;
-	}
-
-	return 0;
+	return transport_backend_register(&rd_mcp_ops);
 }
 
 void rd_module_exit(void)
 {
-	transport_subsystem_release(&rd_mcp_template);
+	target_backend_unregister(&rd_mcp_ops);
 }
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 43719b3..e318ddb 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -38,6 +38,7 @@
 
 static sense_reason_t
 sbc_check_prot(struct se_device *, struct se_cmd *, unsigned char *, u32, bool);
+static sense_reason_t sbc_execute_unmap(struct se_cmd *cmd);
 
 static sense_reason_t
 sbc_emulate_readcapacity(struct se_cmd *cmd)
@@ -177,6 +178,23 @@
 EXPORT_SYMBOL(sbc_get_write_same_sectors);
 
 static sense_reason_t
+sbc_execute_write_same_unmap(struct se_cmd *cmd)
+{
+	struct sbc_ops *ops = cmd->protocol_data;
+	sector_t nolb = sbc_get_write_same_sectors(cmd);
+	sense_reason_t ret;
+
+	if (nolb) {
+		ret = ops->execute_unmap(cmd, cmd->t_task_lba, nolb);
+		if (ret)
+			return ret;
+	}
+
+	target_complete_cmd(cmd, GOOD);
+	return 0;
+}
+
+static sense_reason_t
 sbc_emulate_noop(struct se_cmd *cmd)
 {
 	target_complete_cmd(cmd, GOOD);
@@ -299,7 +317,7 @@
 	 * translated into block discard requests within backend code.
 	 */
 	if (flags[0] & 0x08) {
-		if (!ops->execute_write_same_unmap)
+		if (!ops->execute_unmap)
 			return TCM_UNSUPPORTED_SCSI_OPCODE;
 
 		if (!dev->dev_attrib.emulate_tpws) {
@@ -307,7 +325,7 @@
 			       " has emulate_tpws disabled\n");
 			return TCM_UNSUPPORTED_SCSI_OPCODE;
 		}
-		cmd->execute_cmd = ops->execute_write_same_unmap;
+		cmd->execute_cmd = sbc_execute_write_same_unmap;
 		return 0;
 	}
 	if (!ops->execute_write_same)
@@ -381,7 +399,9 @@
 static sense_reason_t
 sbc_execute_rw(struct se_cmd *cmd)
 {
-	return cmd->execute_rw(cmd, cmd->t_data_sg, cmd->t_data_nents,
+	struct sbc_ops *ops = cmd->protocol_data;
+
+	return ops->execute_rw(cmd, cmd->t_data_sg, cmd->t_data_nents,
 			       cmd->data_direction);
 }
 
@@ -560,6 +580,7 @@
 static sense_reason_t
 sbc_compare_and_write(struct se_cmd *cmd)
 {
+	struct sbc_ops *ops = cmd->protocol_data;
 	struct se_device *dev = cmd->se_dev;
 	sense_reason_t ret;
 	int rc;
@@ -579,7 +600,7 @@
 	 */
 	cmd->data_length = cmd->t_task_nolb * dev->dev_attrib.block_size;
 
-	ret = cmd->execute_rw(cmd, cmd->t_bidi_data_sg, cmd->t_bidi_data_nents,
+	ret = ops->execute_rw(cmd, cmd->t_bidi_data_sg, cmd->t_bidi_data_nents,
 			      DMA_FROM_DEVICE);
 	if (ret) {
 		cmd->transport_complete_callback = NULL;
@@ -738,14 +759,15 @@
 sbc_check_dpofua(struct se_device *dev, struct se_cmd *cmd, unsigned char *cdb)
 {
 	if (cdb[1] & 0x10) {
-		if (!dev->dev_attrib.emulate_dpo) {
+		/* see explanation in spc_emulate_modesense */
+		if (!target_check_fua(dev)) {
 			pr_err("Got CDB: 0x%02x with DPO bit set, but device"
 			       " does not advertise support for DPO\n", cdb[0]);
 			return -EINVAL;
 		}
 	}
 	if (cdb[1] & 0x8) {
-		if (!dev->dev_attrib.emulate_fua_write || !se_dev_check_wce(dev)) {
+		if (!target_check_fua(dev)) {
 			pr_err("Got CDB: 0x%02x with FUA bit set, but device"
 			       " does not advertise support for FUA write\n",
 			       cdb[0]);
@@ -765,12 +787,13 @@
 	u32 sectors = 0;
 	sense_reason_t ret;
 
+	cmd->protocol_data = ops;
+
 	switch (cdb[0]) {
 	case READ_6:
 		sectors = transport_get_sectors_6(cdb);
 		cmd->t_task_lba = transport_lba_21(cdb);
 		cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
-		cmd->execute_rw = ops->execute_rw;
 		cmd->execute_cmd = sbc_execute_rw;
 		break;
 	case READ_10:
@@ -785,7 +808,6 @@
 			return ret;
 
 		cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
-		cmd->execute_rw = ops->execute_rw;
 		cmd->execute_cmd = sbc_execute_rw;
 		break;
 	case READ_12:
@@ -800,7 +822,6 @@
 			return ret;
 
 		cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
-		cmd->execute_rw = ops->execute_rw;
 		cmd->execute_cmd = sbc_execute_rw;
 		break;
 	case READ_16:
@@ -815,14 +836,12 @@
 			return ret;
 
 		cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
-		cmd->execute_rw = ops->execute_rw;
 		cmd->execute_cmd = sbc_execute_rw;
 		break;
 	case WRITE_6:
 		sectors = transport_get_sectors_6(cdb);
 		cmd->t_task_lba = transport_lba_21(cdb);
 		cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
-		cmd->execute_rw = ops->execute_rw;
 		cmd->execute_cmd = sbc_execute_rw;
 		break;
 	case WRITE_10:
@@ -838,7 +857,6 @@
 			return ret;
 
 		cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
-		cmd->execute_rw = ops->execute_rw;
 		cmd->execute_cmd = sbc_execute_rw;
 		break;
 	case WRITE_12:
@@ -853,7 +871,6 @@
 			return ret;
 
 		cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
-		cmd->execute_rw = ops->execute_rw;
 		cmd->execute_cmd = sbc_execute_rw;
 		break;
 	case WRITE_16:
@@ -868,7 +885,6 @@
 			return ret;
 
 		cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
-		cmd->execute_rw = ops->execute_rw;
 		cmd->execute_cmd = sbc_execute_rw;
 		break;
 	case XDWRITEREAD_10:
@@ -886,7 +902,6 @@
 		/*
 		 * Setup BIDI XOR callback to be run after I/O completion.
 		 */
-		cmd->execute_rw = ops->execute_rw;
 		cmd->execute_cmd = sbc_execute_rw;
 		cmd->transport_complete_callback = &xdreadwrite_callback;
 		break;
@@ -910,7 +925,6 @@
 			 * Setup BIDI XOR callback to be run during after I/O
 			 * completion.
 			 */
-			cmd->execute_rw = ops->execute_rw;
 			cmd->execute_cmd = sbc_execute_rw;
 			cmd->transport_complete_callback = &xdreadwrite_callback;
 			break;
@@ -954,7 +968,6 @@
 		cmd->t_task_lba = get_unaligned_be64(&cdb[2]);
 		cmd->t_task_nolb = sectors;
 		cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB | SCF_COMPARE_AND_WRITE;
-		cmd->execute_rw = ops->execute_rw;
 		cmd->execute_cmd = sbc_compare_and_write;
 		cmd->transport_complete_callback = compare_and_write_callback;
 		break;
@@ -1004,7 +1017,7 @@
 			return TCM_UNSUPPORTED_SCSI_OPCODE;
 		}
 		size = get_unaligned_be16(&cdb[7]);
-		cmd->execute_cmd = ops->execute_unmap;
+		cmd->execute_cmd = sbc_execute_unmap;
 		break;
 	case WRITE_SAME_16:
 		sectors = transport_get_sectors_16(cdb);
@@ -1092,12 +1105,10 @@
 }
 EXPORT_SYMBOL(sbc_get_device_type);
 
-sense_reason_t
-sbc_execute_unmap(struct se_cmd *cmd,
-	sense_reason_t (*do_unmap_fn)(struct se_cmd *, void *,
-				      sector_t, sector_t),
-	void *priv)
+static sense_reason_t
+sbc_execute_unmap(struct se_cmd *cmd)
 {
+	struct sbc_ops *ops = cmd->protocol_data;
 	struct se_device *dev = cmd->se_dev;
 	unsigned char *buf, *ptr = NULL;
 	sector_t lba;
@@ -1161,7 +1172,7 @@
 			goto err;
 		}
 
-		ret = do_unmap_fn(cmd, priv, lba, range);
+		ret = ops->execute_unmap(cmd, lba, range);
 		if (ret)
 			goto err;
 
@@ -1175,34 +1186,56 @@
 		target_complete_cmd(cmd, GOOD);
 	return ret;
 }
-EXPORT_SYMBOL(sbc_execute_unmap);
 
 void
 sbc_dif_generate(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct se_dif_v1_tuple *sdt;
-	struct scatterlist *dsg, *psg = cmd->t_prot_sg;
+	struct scatterlist *dsg = cmd->t_data_sg, *psg;
 	sector_t sector = cmd->t_task_lba;
 	void *daddr, *paddr;
 	int i, j, offset = 0;
+	unsigned int block_size = dev->dev_attrib.block_size;
 
-	for_each_sg(cmd->t_data_sg, dsg, cmd->t_data_nents, i) {
-		daddr = kmap_atomic(sg_page(dsg)) + dsg->offset;
+	for_each_sg(cmd->t_prot_sg, psg, cmd->t_prot_nents, i) {
 		paddr = kmap_atomic(sg_page(psg)) + psg->offset;
+		daddr = kmap_atomic(sg_page(dsg)) + dsg->offset;
 
-		for (j = 0; j < dsg->length; j += dev->dev_attrib.block_size) {
+		for (j = 0; j < psg->length;
+				j += sizeof(struct se_dif_v1_tuple)) {
+			__u16 crc;
+			unsigned int avail;
 
-			if (offset >= psg->length) {
-				kunmap_atomic(paddr);
-				psg = sg_next(psg);
-				paddr = kmap_atomic(sg_page(psg)) + psg->offset;
-				offset = 0;
+			if (offset >= dsg->length) {
+				offset -= dsg->length;
+				kunmap_atomic(daddr - dsg->offset);
+				dsg = sg_next(dsg);
+				if (!dsg) {
+					kunmap_atomic(paddr - psg->offset);
+					return;
+				}
+				daddr = kmap_atomic(sg_page(dsg)) + dsg->offset;
 			}
 
-			sdt = paddr + offset;
-			sdt->guard_tag = cpu_to_be16(crc_t10dif(daddr + j,
-						dev->dev_attrib.block_size));
+			sdt = paddr + j;
+			avail = min(block_size, dsg->length - offset);
+			crc = crc_t10dif(daddr + offset, avail);
+			if (avail < block_size) {
+				kunmap_atomic(daddr - dsg->offset);
+				dsg = sg_next(dsg);
+				if (!dsg) {
+					kunmap_atomic(paddr - psg->offset);
+					return;
+				}
+				daddr = kmap_atomic(sg_page(dsg)) + dsg->offset;
+				offset = block_size - avail;
+				crc = crc_t10dif_update(crc, daddr, offset);
+			} else {
+				offset += block_size;
+			}
+
+			sdt->guard_tag = cpu_to_be16(crc);
 			if (cmd->prot_type == TARGET_DIF_TYPE1_PROT)
 				sdt->ref_tag = cpu_to_be32(sector & 0xffffffff);
 			sdt->app_tag = 0;
@@ -1215,26 +1248,23 @@
 				 be32_to_cpu(sdt->ref_tag));
 
 			sector++;
-			offset += sizeof(struct se_dif_v1_tuple);
 		}
 
-		kunmap_atomic(paddr);
-		kunmap_atomic(daddr);
+		kunmap_atomic(daddr - dsg->offset);
+		kunmap_atomic(paddr - psg->offset);
 	}
 }
 
 static sense_reason_t
 sbc_dif_v1_verify(struct se_cmd *cmd, struct se_dif_v1_tuple *sdt,
-		  const void *p, sector_t sector, unsigned int ei_lba)
+		  __u16 crc, sector_t sector, unsigned int ei_lba)
 {
-	struct se_device *dev = cmd->se_dev;
-	int block_size = dev->dev_attrib.block_size;
 	__be16 csum;
 
 	if (!(cmd->prot_checks & TARGET_DIF_CHECK_GUARD))
 		goto check_ref;
 
-	csum = cpu_to_be16(crc_t10dif(p, block_size));
+	csum = cpu_to_be16(crc);
 
 	if (sdt->guard_tag != csum) {
 		pr_err("DIFv1 checksum failed on sector %llu guard tag 0x%04x"
@@ -1266,9 +1296,8 @@
 	return 0;
 }
 
-static void
-sbc_dif_copy_prot(struct se_cmd *cmd, unsigned int sectors, bool read,
-		  struct scatterlist *sg, int sg_off)
+void sbc_dif_copy_prot(struct se_cmd *cmd, unsigned int sectors, bool read,
+		       struct scatterlist *sg, int sg_off)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct scatterlist *psg;
@@ -1300,100 +1329,54 @@
 			copied += len;
 			psg_len -= len;
 
+			kunmap_atomic(addr - sg->offset - offset);
+
 			if (offset >= sg->length) {
 				sg = sg_next(sg);
 				offset = 0;
 			}
-			kunmap_atomic(addr);
 		}
-		kunmap_atomic(paddr);
+		kunmap_atomic(paddr - psg->offset);
 	}
 }
+EXPORT_SYMBOL(sbc_dif_copy_prot);
 
 sense_reason_t
-sbc_dif_verify_write(struct se_cmd *cmd, sector_t start, unsigned int sectors,
-		     unsigned int ei_lba, struct scatterlist *sg, int sg_off)
+sbc_dif_verify(struct se_cmd *cmd, sector_t start, unsigned int sectors,
+	       unsigned int ei_lba, struct scatterlist *psg, int psg_off)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct se_dif_v1_tuple *sdt;
-	struct scatterlist *dsg, *psg = cmd->t_prot_sg;
+	struct scatterlist *dsg = cmd->t_data_sg;
 	sector_t sector = start;
 	void *daddr, *paddr;
-	int i, j, offset = 0;
+	int i;
 	sense_reason_t rc;
+	int dsg_off = 0;
+	unsigned int block_size = dev->dev_attrib.block_size;
 
-	for_each_sg(cmd->t_data_sg, dsg, cmd->t_data_nents, i) {
-		daddr = kmap_atomic(sg_page(dsg)) + dsg->offset;
+	for (; psg && sector < start + sectors; psg = sg_next(psg)) {
 		paddr = kmap_atomic(sg_page(psg)) + psg->offset;
-
-		for (j = 0; j < dsg->length; j += dev->dev_attrib.block_size) {
-
-			if (offset >= psg->length) {
-				kunmap_atomic(paddr);
-				psg = sg_next(psg);
-				paddr = kmap_atomic(sg_page(psg)) + psg->offset;
-				offset = 0;
-			}
-
-			sdt = paddr + offset;
-
-			pr_debug("DIF WRITE sector: %llu guard_tag: 0x%04x"
-				 " app_tag: 0x%04x ref_tag: %u\n",
-				 (unsigned long long)sector, sdt->guard_tag,
-				 sdt->app_tag, be32_to_cpu(sdt->ref_tag));
-
-			rc = sbc_dif_v1_verify(cmd, sdt, daddr + j, sector,
-					       ei_lba);
-			if (rc) {
-				kunmap_atomic(paddr);
-				kunmap_atomic(daddr);
-				cmd->bad_sector = sector;
-				return rc;
-			}
-
-			sector++;
-			ei_lba++;
-			offset += sizeof(struct se_dif_v1_tuple);
-		}
-
-		kunmap_atomic(paddr);
-		kunmap_atomic(daddr);
-	}
-	if (!sg)
-		return 0;
-
-	sbc_dif_copy_prot(cmd, sectors, false, sg, sg_off);
-
-	return 0;
-}
-EXPORT_SYMBOL(sbc_dif_verify_write);
-
-static sense_reason_t
-__sbc_dif_verify_read(struct se_cmd *cmd, sector_t start, unsigned int sectors,
-		      unsigned int ei_lba, struct scatterlist *sg, int sg_off)
-{
-	struct se_device *dev = cmd->se_dev;
-	struct se_dif_v1_tuple *sdt;
-	struct scatterlist *dsg, *psg = sg;
-	sector_t sector = start;
-	void *daddr, *paddr;
-	int i, j, offset = sg_off;
-	sense_reason_t rc;
-
-	for_each_sg(cmd->t_data_sg, dsg, cmd->t_data_nents, i) {
 		daddr = kmap_atomic(sg_page(dsg)) + dsg->offset;
-		paddr = kmap_atomic(sg_page(psg)) + sg->offset;
 
-		for (j = 0; j < dsg->length; j += dev->dev_attrib.block_size) {
+		for (i = psg_off; i < psg->length &&
+				sector < start + sectors;
+				i += sizeof(struct se_dif_v1_tuple)) {
+			__u16 crc;
+			unsigned int avail;
 
-			if (offset >= psg->length) {
-				kunmap_atomic(paddr);
-				psg = sg_next(psg);
-				paddr = kmap_atomic(sg_page(psg)) + psg->offset;
-				offset = 0;
+			if (dsg_off >= dsg->length) {
+				dsg_off -= dsg->length;
+				kunmap_atomic(daddr - dsg->offset);
+				dsg = sg_next(dsg);
+				if (!dsg) {
+					kunmap_atomic(paddr - psg->offset);
+					return 0;
+				}
+				daddr = kmap_atomic(sg_page(dsg)) + dsg->offset;
 			}
 
-			sdt = paddr + offset;
+			sdt = paddr + i;
 
 			pr_debug("DIF READ sector: %llu guard_tag: 0x%04x"
 				 " app_tag: 0x%04x ref_tag: %u\n",
@@ -1401,53 +1384,43 @@
 				 sdt->app_tag, be32_to_cpu(sdt->ref_tag));
 
 			if (sdt->app_tag == cpu_to_be16(0xffff)) {
-				sector++;
-				offset += sizeof(struct se_dif_v1_tuple);
-				continue;
+				dsg_off += block_size;
+				goto next;
 			}
 
-			rc = sbc_dif_v1_verify(cmd, sdt, daddr + j, sector,
-					       ei_lba);
+			avail = min(block_size, dsg->length - dsg_off);
+			crc = crc_t10dif(daddr + dsg_off, avail);
+			if (avail < block_size) {
+				kunmap_atomic(daddr - dsg->offset);
+				dsg = sg_next(dsg);
+				if (!dsg) {
+					kunmap_atomic(paddr - psg->offset);
+					return 0;
+				}
+				daddr = kmap_atomic(sg_page(dsg)) + dsg->offset;
+				dsg_off = block_size - avail;
+				crc = crc_t10dif_update(crc, daddr, dsg_off);
+			} else {
+				dsg_off += block_size;
+			}
+
+			rc = sbc_dif_v1_verify(cmd, sdt, crc, sector, ei_lba);
 			if (rc) {
-				kunmap_atomic(paddr);
-				kunmap_atomic(daddr);
+				kunmap_atomic(daddr - dsg->offset);
+				kunmap_atomic(paddr - psg->offset);
 				cmd->bad_sector = sector;
 				return rc;
 			}
-
+next:
 			sector++;
 			ei_lba++;
-			offset += sizeof(struct se_dif_v1_tuple);
 		}
 
-		kunmap_atomic(paddr);
-		kunmap_atomic(daddr);
+		psg_off = 0;
+		kunmap_atomic(daddr - dsg->offset);
+		kunmap_atomic(paddr - psg->offset);
 	}
 
 	return 0;
 }
-
-sense_reason_t
-sbc_dif_read_strip(struct se_cmd *cmd)
-{
-	struct se_device *dev = cmd->se_dev;
-	u32 sectors = cmd->prot_length / dev->prot_length;
-
-	return __sbc_dif_verify_read(cmd, cmd->t_task_lba, sectors, 0,
-				     cmd->t_prot_sg, 0);
-}
-
-sense_reason_t
-sbc_dif_verify_read(struct se_cmd *cmd, sector_t start, unsigned int sectors,
-		    unsigned int ei_lba, struct scatterlist *sg, int sg_off)
-{
-	sense_reason_t rc;
-
-	rc = __sbc_dif_verify_read(cmd, start, sectors, ei_lba, sg, sg_off);
-	if (rc)
-		return rc;
-
-	sbc_dif_copy_prot(cmd, sectors, true, sg, sg_off);
-	return 0;
-}
-EXPORT_SYMBOL(sbc_dif_verify_read);
+EXPORT_SYMBOL(sbc_dif_verify);
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 52ea640..b074443 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -38,10 +38,9 @@
 #include "target_core_ua.h"
 #include "target_core_xcopy.h"
 
-static void spc_fill_alua_data(struct se_port *port, unsigned char *buf)
+static void spc_fill_alua_data(struct se_lun *lun, unsigned char *buf)
 {
 	struct t10_alua_tg_pt_gp *tg_pt_gp;
-	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem;
 
 	/*
 	 * Set SCCS for MAINTENANCE_IN + REPORT_TARGET_PORT_GROUPS.
@@ -54,17 +53,11 @@
 	 *
 	 * See spc4r17 section 6.4.2 Table 135
 	 */
-	if (!port)
-		return;
-	tg_pt_gp_mem = port->sep_alua_tg_pt_gp_mem;
-	if (!tg_pt_gp_mem)
-		return;
-
-	spin_lock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
-	tg_pt_gp = tg_pt_gp_mem->tg_pt_gp;
+	spin_lock(&lun->lun_tg_pt_gp_lock);
+	tg_pt_gp = lun->lun_tg_pt_gp;
 	if (tg_pt_gp)
 		buf[5] |= tg_pt_gp->tg_pt_gp_alua_access_type;
-	spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
+	spin_unlock(&lun->lun_tg_pt_gp_lock);
 }
 
 sense_reason_t
@@ -95,7 +88,7 @@
 	/*
 	 * Enable SCCS and TPGS fields for Emulated ALUA
 	 */
-	spc_fill_alua_data(lun->lun_sep, buf);
+	spc_fill_alua_data(lun, buf);
 
 	/*
 	 * Set Third-Party Copy (3PC) bit to indicate support for EXTENDED_COPY
@@ -182,11 +175,9 @@
 {
 	struct se_device *dev = cmd->se_dev;
 	struct se_lun *lun = cmd->se_lun;
-	struct se_port *port = NULL;
 	struct se_portal_group *tpg = NULL;
 	struct t10_alua_lu_gp_member *lu_gp_mem;
 	struct t10_alua_tg_pt_gp *tg_pt_gp;
-	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem;
 	unsigned char *prod = &dev->t10_wwn.model[0];
 	u32 prod_len;
 	u32 unit_serial_len, off = 0;
@@ -268,18 +259,15 @@
 	/* Header size for Designation descriptor */
 	len += (id_len + 4);
 	off += (id_len + 4);
-	/*
-	 * struct se_port is only set for INQUIRY VPD=1 through $FABRIC_MOD
-	 */
-	port = lun->lun_sep;
-	if (port) {
+
+	if (1) {
 		struct t10_alua_lu_gp *lu_gp;
 		u32 padding, scsi_name_len, scsi_target_len;
 		u16 lu_gp_id = 0;
 		u16 tg_pt_gp_id = 0;
 		u16 tpgt;
 
-		tpg = port->sep_tpg;
+		tpg = lun->lun_tpg;
 		/*
 		 * Relative target port identifer, see spc4r17
 		 * section 7.7.3.7
@@ -287,8 +275,7 @@
 		 * Get the PROTOCOL IDENTIFIER as defined by spc4r17
 		 * section 7.5.1 Table 362
 		 */
-		buf[off] =
-			(tpg->se_tpg_tfo->get_fabric_proto_ident(tpg) << 4);
+		buf[off] = tpg->proto_id << 4;
 		buf[off++] |= 0x1; /* CODE SET == Binary */
 		buf[off] = 0x80; /* Set PIV=1 */
 		/* Set ASSOCIATION == target port: 01b */
@@ -300,8 +287,8 @@
 		/* Skip over Obsolete field in RTPI payload
 		 * in Table 472 */
 		off += 2;
-		buf[off++] = ((port->sep_rtpi >> 8) & 0xff);
-		buf[off++] = (port->sep_rtpi & 0xff);
+		buf[off++] = ((lun->lun_rtpi >> 8) & 0xff);
+		buf[off++] = (lun->lun_rtpi & 0xff);
 		len += 8; /* Header size + Designation descriptor */
 		/*
 		 * Target port group identifier, see spc4r17
@@ -310,21 +297,16 @@
 		 * Get the PROTOCOL IDENTIFIER as defined by spc4r17
 		 * section 7.5.1 Table 362
 		 */
-		tg_pt_gp_mem = port->sep_alua_tg_pt_gp_mem;
-		if (!tg_pt_gp_mem)
-			goto check_lu_gp;
-
-		spin_lock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
-		tg_pt_gp = tg_pt_gp_mem->tg_pt_gp;
+		spin_lock(&lun->lun_tg_pt_gp_lock);
+		tg_pt_gp = lun->lun_tg_pt_gp;
 		if (!tg_pt_gp) {
-			spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
+			spin_unlock(&lun->lun_tg_pt_gp_lock);
 			goto check_lu_gp;
 		}
 		tg_pt_gp_id = tg_pt_gp->tg_pt_gp_id;
-		spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
+		spin_unlock(&lun->lun_tg_pt_gp_lock);
 
-		buf[off] =
-			(tpg->se_tpg_tfo->get_fabric_proto_ident(tpg) << 4);
+		buf[off] = tpg->proto_id << 4;
 		buf[off++] |= 0x1; /* CODE SET == Binary */
 		buf[off] = 0x80; /* Set PIV=1 */
 		/* Set ASSOCIATION == target port: 01b */
@@ -372,8 +354,7 @@
 		 * section 7.5.1 Table 362
 		 */
 check_scsi_name:
-		buf[off] =
-			(tpg->se_tpg_tfo->get_fabric_proto_ident(tpg) << 4);
+		buf[off] = tpg->proto_id << 4;
 		buf[off++] |= 0x3; /* CODE SET == UTF-8 */
 		buf[off] = 0x80; /* Set PIV=1 */
 		/* Set ASSOCIATION == target port: 01b */
@@ -413,8 +394,7 @@
 		/*
 		 * Target device designator
 		 */
-		buf[off] =
-			(tpg->se_tpg_tfo->get_fabric_proto_ident(tpg) << 4);
+		buf[off] = tpg->proto_id << 4;
 		buf[off++] |= 0x3; /* CODE SET == UTF-8 */
 		buf[off] = 0x80; /* Set PIV=1 */
 		/* Set ASSOCIATION == target device: 10b */
@@ -482,7 +462,7 @@
 	buf[5] = 0x07;
 
 	/* If WriteCache emulation is enabled, set V_SUP */
-	if (se_dev_check_wce(dev))
+	if (target_check_wce(dev))
 		buf[6] = 0x01;
 	/* If an LBA map is present set R_SUP */
 	spin_lock(&cmd->se_dev->t10_alua.lba_map_lock);
@@ -699,7 +679,7 @@
 spc_emulate_inquiry(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
-	struct se_portal_group *tpg = cmd->se_lun->lun_sep->sep_tpg;
+	struct se_portal_group *tpg = cmd->se_lun->lun_tpg;
 	unsigned char *rbuf;
 	unsigned char *cdb = cmd->t_task_cdb;
 	unsigned char *buf;
@@ -713,7 +693,7 @@
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 
-	if (dev == tpg->tpg_virt_lun0.lun_se_dev)
+	if (dev == rcu_access_pointer(tpg->tpg_virt_lun0->lun_se_dev))
 		buf[0] = 0x3f; /* Not connected */
 	else
 		buf[0] = dev->transport->get_device_type(dev);
@@ -889,7 +869,7 @@
 	if (pc == 1)
 		goto out;
 
-	if (se_dev_check_wce(dev))
+	if (target_check_wce(dev))
 		p[2] = 0x04; /* Write Cache Enable */
 	p[12] = 0x20; /* Disabled Read Ahead */
 
@@ -986,6 +966,7 @@
 	int length = 0;
 	int ret;
 	int i;
+	bool read_only = target_lun_is_rdonly(cmd);;
 
 	memset(buf, 0, SE_MODE_PAGE_BUF);
 
@@ -996,13 +977,15 @@
 	length = ten ? 3 : 2;
 
 	/* DEVICE-SPECIFIC PARAMETER */
-	if ((cmd->se_lun->lun_access & TRANSPORT_LUNFLAGS_READ_ONLY) ||
-	    (cmd->se_deve &&
-	     (cmd->se_deve->lun_flags & TRANSPORT_LUNFLAGS_READ_ONLY)))
+	if ((cmd->se_lun->lun_access & TRANSPORT_LUNFLAGS_READ_ONLY) || read_only)
 		spc_modesense_write_protect(&buf[length], type);
 
-	if ((se_dev_check_wce(dev)) &&
-	    (dev->dev_attrib.emulate_fua_write > 0))
+	/*
+	 * SBC only allows us to enable FUA and DPO together.  Fortunately
+	 * DPO is explicitly specified as a hint, so a noop is a perfectly
+	 * valid implementation.
+	 */
+	if (target_check_fua(dev))
 		spc_modesense_dpofua(&buf[length], type);
 
 	++length;
@@ -1212,8 +1195,9 @@
 {
 	struct se_dev_entry *deve;
 	struct se_session *sess = cmd->se_sess;
+	struct se_node_acl *nacl;
 	unsigned char *buf;
-	u32 lun_count = 0, offset = 8, i;
+	u32 lun_count = 0, offset = 8;
 
 	if (cmd->data_length < 16) {
 		pr_warn("REPORT LUNS allocation length %u too small\n",
@@ -1235,12 +1219,10 @@
 		lun_count = 1;
 		goto done;
 	}
+	nacl = sess->se_node_acl;
 
-	spin_lock_irq(&sess->se_node_acl->device_list_lock);
-	for (i = 0; i < TRANSPORT_MAX_LUNS_PER_TPG; i++) {
-		deve = sess->se_node_acl->device_list[i];
-		if (!(deve->lun_flags & TRANSPORT_LUNFLAGS_INITIATOR_ACCESS))
-			continue;
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(deve, &nacl->lun_entry_hlist, link) {
 		/*
 		 * We determine the correct LUN LIST LENGTH even once we
 		 * have reached the initial allocation length.
@@ -1253,7 +1235,7 @@
 		int_to_scsilun(deve->mapped_lun, (struct scsi_lun *)&buf[offset]);
 		offset += 8;
 	}
-	spin_unlock_irq(&sess->se_node_acl->device_list_lock);
+	rcu_read_unlock();
 
 	/*
 	 * See SPC3 r07, page 159.
diff --git a/drivers/target/target_core_stat.c b/drivers/target/target_core_stat.c
index 40f6c13..20ed5d2 100644
--- a/drivers/target/target_core_stat.c
+++ b/drivers/target/target_core_stat.c
@@ -37,7 +37,6 @@
 #include <target/target_core_base.h>
 #include <target/target_core_backend.h>
 #include <target/target_core_fabric.h>
-#include <target/target_core_configfs.h>
 #include <target/configfs_macros.h>
 
 #include "target_core_internal.h"
@@ -104,7 +103,7 @@
 	struct se_device *dev =
 		container_of(sgrps, struct se_device, dev_stat_grps);
 
-	return snprintf(page, PAGE_SIZE, "%u\n", dev->dev_port_count);
+	return snprintf(page, PAGE_SIZE, "%u\n", dev->export_count);
 }
 DEV_STAT_SCSI_DEV_ATTR_RO(ports);
 
@@ -540,20 +539,14 @@
 	struct se_port_stat_grps *pgrps, char *page)
 {
 	struct se_lun *lun = container_of(pgrps, struct se_lun, port_stat_grps);
-	struct se_port *sep;
-	struct se_device *dev = lun->lun_se_dev;
-	struct se_hba *hba;
-	ssize_t ret;
+	struct se_device *dev;
+	ssize_t ret = -ENODEV;
 
-	spin_lock(&lun->lun_sep_lock);
-	sep = lun->lun_sep;
-	if (!sep) {
-		spin_unlock(&lun->lun_sep_lock);
-		return -ENODEV;
-	}
-	hba = dev->se_hba;
-	ret = snprintf(page, PAGE_SIZE, "%u\n", hba->hba_index);
-	spin_unlock(&lun->lun_sep_lock);
+	rcu_read_lock();
+	dev = rcu_dereference(lun->lun_se_dev);
+	if (dev)
+		ret = snprintf(page, PAGE_SIZE, "%u\n", dev->hba_index);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_PORT_ATTR_RO(inst);
@@ -562,18 +555,14 @@
 	struct se_port_stat_grps *pgrps, char *page)
 {
 	struct se_lun *lun = container_of(pgrps, struct se_lun, port_stat_grps);
-	struct se_port *sep;
-	struct se_device *dev = lun->lun_se_dev;
-	ssize_t ret;
+	struct se_device *dev;
+	ssize_t ret = -ENODEV;
 
-	spin_lock(&lun->lun_sep_lock);
-	sep = lun->lun_sep;
-	if (!sep) {
-		spin_unlock(&lun->lun_sep_lock);
-		return -ENODEV;
-	}
-	ret = snprintf(page, PAGE_SIZE, "%u\n", dev->dev_index);
-	spin_unlock(&lun->lun_sep_lock);
+	rcu_read_lock();
+	dev = rcu_dereference(lun->lun_se_dev);
+	if (dev)
+		ret = snprintf(page, PAGE_SIZE, "%u\n", dev->dev_index);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_PORT_ATTR_RO(dev);
@@ -582,17 +571,14 @@
 	struct se_port_stat_grps *pgrps, char *page)
 {
 	struct se_lun *lun = container_of(pgrps, struct se_lun, port_stat_grps);
-	struct se_port *sep;
-	ssize_t ret;
+	struct se_device *dev;
+	ssize_t ret = -ENODEV;
 
-	spin_lock(&lun->lun_sep_lock);
-	sep = lun->lun_sep;
-	if (!sep) {
-		spin_unlock(&lun->lun_sep_lock);
-		return -ENODEV;
-	}
-	ret = snprintf(page, PAGE_SIZE, "%u\n", sep->sep_index);
-	spin_unlock(&lun->lun_sep_lock);
+	rcu_read_lock();
+	dev = rcu_dereference(lun->lun_se_dev);
+	if (dev)
+		ret = snprintf(page, PAGE_SIZE, "%u\n", lun->lun_rtpi);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_PORT_ATTR_RO(indx);
@@ -601,21 +587,14 @@
 	struct se_port_stat_grps *pgrps, char *page)
 {
 	struct se_lun *lun = container_of(pgrps, struct se_lun, port_stat_grps);
-	struct se_device *dev = lun->lun_se_dev;
-	struct se_port *sep;
-	ssize_t ret;
+	struct se_device *dev;
+	ssize_t ret = -ENODEV;
 
-	if (!dev)
-		return -ENODEV;
-
-	spin_lock(&lun->lun_sep_lock);
-	sep = lun->lun_sep;
-	if (!sep) {
-		spin_unlock(&lun->lun_sep_lock);
-		return -ENODEV;
-	}
-	ret = snprintf(page, PAGE_SIZE, "%s%u\n", "Device", dev->dev_index);
-	spin_unlock(&lun->lun_sep_lock);
+	rcu_read_lock();
+	dev = rcu_dereference(lun->lun_se_dev);
+	if (dev)
+		ret = snprintf(page, PAGE_SIZE, "%s%u\n", "Device", dev->dev_index);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_PORT_ATTR_RO(role);
@@ -624,18 +603,16 @@
 	struct se_port_stat_grps *pgrps, char *page)
 {
 	struct se_lun *lun = container_of(pgrps, struct se_lun, port_stat_grps);
-	struct se_port *sep;
-	ssize_t ret;
+	struct se_device *dev;
+	ssize_t ret = -ENODEV;
 
-	spin_lock(&lun->lun_sep_lock);
-	sep = lun->lun_sep;
-	if (!sep) {
-		spin_unlock(&lun->lun_sep_lock);
-		return -ENODEV;
+	rcu_read_lock();
+	dev = rcu_dereference(lun->lun_se_dev);
+	if (dev) {
+		/* FIXME: scsiPortBusyStatuses  */
+		ret = snprintf(page, PAGE_SIZE, "%u\n", 0);
 	}
-	/* FIXME: scsiPortBusyStatuses  */
-	ret = snprintf(page, PAGE_SIZE, "%u\n", 0);
-	spin_unlock(&lun->lun_sep_lock);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_PORT_ATTR_RO(busy_count);
@@ -683,20 +660,14 @@
 	struct se_port_stat_grps *pgrps, char *page)
 {
 	struct se_lun *lun = container_of(pgrps, struct se_lun, port_stat_grps);
-	struct se_device *dev = lun->lun_se_dev;
-	struct se_port *sep;
-	struct se_hba *hba;
-	ssize_t ret;
+	struct se_device *dev;
+	ssize_t ret = -ENODEV;
 
-	spin_lock(&lun->lun_sep_lock);
-	sep = lun->lun_sep;
-	if (!sep) {
-		spin_unlock(&lun->lun_sep_lock);
-		return -ENODEV;
-	}
-	hba = dev->se_hba;
-	ret = snprintf(page, PAGE_SIZE, "%u\n", hba->hba_index);
-	spin_unlock(&lun->lun_sep_lock);
+	rcu_read_lock();
+	dev = rcu_dereference(lun->lun_se_dev);
+	if (dev)
+		ret = snprintf(page, PAGE_SIZE, "%u\n", dev->hba_index);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_TGT_PORT_ATTR_RO(inst);
@@ -705,18 +676,14 @@
 	struct se_port_stat_grps *pgrps, char *page)
 {
 	struct se_lun *lun = container_of(pgrps, struct se_lun, port_stat_grps);
-	struct se_device *dev = lun->lun_se_dev;
-	struct se_port *sep;
-	ssize_t ret;
+	struct se_device *dev;
+	ssize_t ret = -ENODEV;
 
-	spin_lock(&lun->lun_sep_lock);
-	sep = lun->lun_sep;
-	if (!sep) {
-		spin_unlock(&lun->lun_sep_lock);
-		return -ENODEV;
-	}
-	ret = snprintf(page, PAGE_SIZE, "%u\n", dev->dev_index);
-	spin_unlock(&lun->lun_sep_lock);
+	rcu_read_lock();
+	dev = rcu_dereference(lun->lun_se_dev);
+	if (dev)
+		ret = snprintf(page, PAGE_SIZE, "%u\n", dev->dev_index);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_TGT_PORT_ATTR_RO(dev);
@@ -725,17 +692,14 @@
 	struct se_port_stat_grps *pgrps, char *page)
 {
 	struct se_lun *lun = container_of(pgrps, struct se_lun, port_stat_grps);
-	struct se_port *sep;
-	ssize_t ret;
+	struct se_device *dev;
+	ssize_t ret = -ENODEV;
 
-	spin_lock(&lun->lun_sep_lock);
-	sep = lun->lun_sep;
-	if (!sep) {
-		spin_unlock(&lun->lun_sep_lock);
-		return -ENODEV;
-	}
-	ret = snprintf(page, PAGE_SIZE, "%u\n", sep->sep_index);
-	spin_unlock(&lun->lun_sep_lock);
+	rcu_read_lock();
+	dev = rcu_dereference(lun->lun_se_dev);
+	if (dev)
+		ret = snprintf(page, PAGE_SIZE, "%u\n", lun->lun_rtpi);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_TGT_PORT_ATTR_RO(indx);
@@ -744,21 +708,17 @@
 	struct se_port_stat_grps *pgrps, char *page)
 {
 	struct se_lun *lun = container_of(pgrps, struct se_lun, port_stat_grps);
-	struct se_port *sep;
-	struct se_portal_group *tpg;
-	ssize_t ret;
+	struct se_portal_group *tpg = lun->lun_tpg;
+	struct se_device *dev;
+	ssize_t ret = -ENODEV;
 
-	spin_lock(&lun->lun_sep_lock);
-	sep = lun->lun_sep;
-	if (!sep) {
-		spin_unlock(&lun->lun_sep_lock);
-		return -ENODEV;
-	}
-	tpg = sep->sep_tpg;
-
-	ret = snprintf(page, PAGE_SIZE, "%sPort#%u\n",
-		tpg->se_tpg_tfo->get_fabric_name(), sep->sep_index);
-	spin_unlock(&lun->lun_sep_lock);
+	rcu_read_lock();
+	dev = rcu_dereference(lun->lun_se_dev);
+	if (dev)
+		ret = snprintf(page, PAGE_SIZE, "%sPort#%u\n",
+			tpg->se_tpg_tfo->get_fabric_name(),
+			lun->lun_rtpi);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_TGT_PORT_ATTR_RO(name);
@@ -767,22 +727,17 @@
 	struct se_port_stat_grps *pgrps, char *page)
 {
 	struct se_lun *lun = container_of(pgrps, struct se_lun, port_stat_grps);
-	struct se_port *sep;
-	struct se_portal_group *tpg;
-	ssize_t ret;
+	struct se_portal_group *tpg = lun->lun_tpg;
+	struct se_device *dev;
+	ssize_t ret = -ENODEV;
 
-	spin_lock(&lun->lun_sep_lock);
-	sep = lun->lun_sep;
-	if (!sep) {
-		spin_unlock(&lun->lun_sep_lock);
-		return -ENODEV;
-	}
-	tpg = sep->sep_tpg;
-
-	ret = snprintf(page, PAGE_SIZE, "%s%s%d\n",
-		tpg->se_tpg_tfo->tpg_get_wwn(tpg), "+t+",
-		tpg->se_tpg_tfo->tpg_get_tag(tpg));
-	spin_unlock(&lun->lun_sep_lock);
+	rcu_read_lock();
+	dev = rcu_dereference(lun->lun_se_dev);
+	if (dev)
+		ret = snprintf(page, PAGE_SIZE, "%s%s%d\n",
+			tpg->se_tpg_tfo->tpg_get_wwn(tpg), "+t+",
+			tpg->se_tpg_tfo->tpg_get_tag(tpg));
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_TGT_PORT_ATTR_RO(port_index);
@@ -791,18 +746,15 @@
 	struct se_port_stat_grps *pgrps, char *page)
 {
 	struct se_lun *lun = container_of(pgrps, struct se_lun, port_stat_grps);
-	struct se_port *sep;
-	ssize_t ret;
+	struct se_device *dev;
+	ssize_t ret = -ENODEV;
 
-	spin_lock(&lun->lun_sep_lock);
-	sep = lun->lun_sep;
-	if (!sep) {
-		spin_unlock(&lun->lun_sep_lock);
-		return -ENODEV;
-	}
-
-	ret = snprintf(page, PAGE_SIZE, "%llu\n", sep->sep_stats.cmd_pdus);
-	spin_unlock(&lun->lun_sep_lock);
+	rcu_read_lock();
+	dev = rcu_dereference(lun->lun_se_dev);
+	if (dev)
+		ret = snprintf(page, PAGE_SIZE, "%lu\n",
+			       atomic_long_read(&lun->lun_stats.cmd_pdus));
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_TGT_PORT_ATTR_RO(in_cmds);
@@ -811,19 +763,15 @@
 	struct se_port_stat_grps *pgrps, char *page)
 {
 	struct se_lun *lun = container_of(pgrps, struct se_lun, port_stat_grps);
-	struct se_port *sep;
-	ssize_t ret;
+	struct se_device *dev;
+	ssize_t ret = -ENODEV;
 
-	spin_lock(&lun->lun_sep_lock);
-	sep = lun->lun_sep;
-	if (!sep) {
-		spin_unlock(&lun->lun_sep_lock);
-		return -ENODEV;
-	}
-
-	ret = snprintf(page, PAGE_SIZE, "%u\n",
-			(u32)(sep->sep_stats.rx_data_octets >> 20));
-	spin_unlock(&lun->lun_sep_lock);
+	rcu_read_lock();
+	dev = rcu_dereference(lun->lun_se_dev);
+	if (dev)
+		ret = snprintf(page, PAGE_SIZE, "%u\n",
+			(u32)(atomic_long_read(&lun->lun_stats.rx_data_octets) >> 20));
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_TGT_PORT_ATTR_RO(write_mbytes);
@@ -832,19 +780,15 @@
 	struct se_port_stat_grps *pgrps, char *page)
 {
 	struct se_lun *lun = container_of(pgrps, struct se_lun, port_stat_grps);
-	struct se_port *sep;
-	ssize_t ret;
+	struct se_device *dev;
+	ssize_t ret = -ENODEV;
 
-	spin_lock(&lun->lun_sep_lock);
-	sep = lun->lun_sep;
-	if (!sep) {
-		spin_unlock(&lun->lun_sep_lock);
-		return -ENODEV;
-	}
-
-	ret = snprintf(page, PAGE_SIZE, "%u\n",
-			(u32)(sep->sep_stats.tx_data_octets >> 20));
-	spin_unlock(&lun->lun_sep_lock);
+	rcu_read_lock();
+	dev = rcu_dereference(lun->lun_se_dev);
+	if (dev)
+		ret = snprintf(page, PAGE_SIZE, "%u\n",
+				(u32)(atomic_long_read(&lun->lun_stats.tx_data_octets) >> 20));
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_TGT_PORT_ATTR_RO(read_mbytes);
@@ -853,19 +797,16 @@
 	struct se_port_stat_grps *pgrps, char *page)
 {
 	struct se_lun *lun = container_of(pgrps, struct se_lun, port_stat_grps);
-	struct se_port *sep;
-	ssize_t ret;
+	struct se_device *dev;
+	ssize_t ret = -ENODEV;
 
-	spin_lock(&lun->lun_sep_lock);
-	sep = lun->lun_sep;
-	if (!sep) {
-		spin_unlock(&lun->lun_sep_lock);
-		return -ENODEV;
+	rcu_read_lock();
+	dev = rcu_dereference(lun->lun_se_dev);
+	if (dev) {
+		/* FIXME: scsiTgtPortHsInCommands */
+		ret = snprintf(page, PAGE_SIZE, "%u\n", 0);
 	}
-
-	/* FIXME: scsiTgtPortHsInCommands */
-	ret = snprintf(page, PAGE_SIZE, "%u\n", 0);
-	spin_unlock(&lun->lun_sep_lock);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_TGT_PORT_ATTR_RO(hs_in_cmds);
@@ -919,21 +860,14 @@
 	struct se_port_stat_grps *pgrps, char *page)
 {
 	struct se_lun *lun = container_of(pgrps, struct se_lun, port_stat_grps);
-	struct se_device *dev = lun->lun_se_dev;
-	struct se_port *sep;
-	struct se_hba *hba;
-	ssize_t ret;
+	struct se_device *dev;
+	ssize_t ret = -ENODEV;
 
-	spin_lock(&lun->lun_sep_lock);
-	sep = lun->lun_sep;
-	if (!sep) {
-		spin_unlock(&lun->lun_sep_lock);
-		return -ENODEV;
-	}
-
-	hba = dev->se_hba;
-	ret = snprintf(page, PAGE_SIZE, "%u\n", hba->hba_index);
-	spin_unlock(&lun->lun_sep_lock);
+	rcu_read_lock();
+	dev = rcu_dereference(lun->lun_se_dev);
+	if (dev)
+		ret = snprintf(page, PAGE_SIZE, "%u\n", dev->hba_index);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_TRANSPORT_ATTR_RO(inst);
@@ -942,21 +876,18 @@
 	struct se_port_stat_grps *pgrps, char *page)
 {
 	struct se_lun *lun = container_of(pgrps, struct se_lun, port_stat_grps);
-	struct se_port *sep;
-	struct se_portal_group *tpg;
-	ssize_t ret;
+	struct se_device *dev;
+	struct se_portal_group *tpg = lun->lun_tpg;
+	ssize_t ret = -ENODEV;
 
-	spin_lock(&lun->lun_sep_lock);
-	sep = lun->lun_sep;
-	if (!sep) {
-		spin_unlock(&lun->lun_sep_lock);
-		return -ENODEV;
+	rcu_read_lock();
+	dev = rcu_dereference(lun->lun_se_dev);
+	if (dev) {
+		/* scsiTransportType */
+		ret = snprintf(page, PAGE_SIZE, "scsiTransport%s\n",
+			       tpg->se_tpg_tfo->get_fabric_name());
 	}
-	tpg = sep->sep_tpg;
-	/* scsiTransportType */
-	ret = snprintf(page, PAGE_SIZE, "scsiTransport%s\n",
-			tpg->se_tpg_tfo->get_fabric_name());
-	spin_unlock(&lun->lun_sep_lock);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_TRANSPORT_ATTR_RO(device);
@@ -965,20 +896,16 @@
 	struct se_port_stat_grps *pgrps, char *page)
 {
 	struct se_lun *lun = container_of(pgrps, struct se_lun, port_stat_grps);
-	struct se_port *sep;
-	struct se_portal_group *tpg;
-	ssize_t ret;
+	struct se_device *dev;
+	struct se_portal_group *tpg = lun->lun_tpg;
+	ssize_t ret = -ENODEV;
 
-	spin_lock(&lun->lun_sep_lock);
-	sep = lun->lun_sep;
-	if (!sep) {
-		spin_unlock(&lun->lun_sep_lock);
-		return -ENODEV;
-	}
-	tpg = sep->sep_tpg;
-	ret = snprintf(page, PAGE_SIZE, "%u\n",
-			tpg->se_tpg_tfo->tpg_get_inst_index(tpg));
-	spin_unlock(&lun->lun_sep_lock);
+	rcu_read_lock();
+	dev = rcu_dereference(lun->lun_se_dev);
+	if (dev)
+		ret = snprintf(page, PAGE_SIZE, "%u\n",
+			       tpg->se_tpg_tfo->tpg_get_inst_index(tpg));
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_TRANSPORT_ATTR_RO(indx);
@@ -987,26 +914,22 @@
 	struct se_port_stat_grps *pgrps, char *page)
 {
 	struct se_lun *lun = container_of(pgrps, struct se_lun, port_stat_grps);
-	struct se_device *dev = lun->lun_se_dev;
-	struct se_port *sep;
-	struct se_portal_group *tpg;
+	struct se_device *dev;
+	struct se_portal_group *tpg = lun->lun_tpg;
 	struct t10_wwn *wwn;
-	ssize_t ret;
+	ssize_t ret = -ENODEV;
 
-	spin_lock(&lun->lun_sep_lock);
-	sep = lun->lun_sep;
-	if (!sep) {
-		spin_unlock(&lun->lun_sep_lock);
-		return -ENODEV;
+	rcu_read_lock();
+	dev = rcu_dereference(lun->lun_se_dev);
+	if (dev) {
+		wwn = &dev->t10_wwn;
+		/* scsiTransportDevName */
+		ret = snprintf(page, PAGE_SIZE, "%s+%s\n",
+				tpg->se_tpg_tfo->tpg_get_wwn(tpg),
+				(strlen(wwn->unit_serial)) ? wwn->unit_serial :
+				wwn->vendor);
 	}
-	tpg = sep->sep_tpg;
-	wwn = &dev->t10_wwn;
-	/* scsiTransportDevName */
-	ret = snprintf(page, PAGE_SIZE, "%s+%s\n",
-			tpg->se_tpg_tfo->tpg_get_wwn(tpg),
-			(strlen(wwn->unit_serial)) ? wwn->unit_serial :
-			wwn->vendor);
-	spin_unlock(&lun->lun_sep_lock);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_TRANSPORT_ATTR_RO(dev_name);
@@ -1082,17 +1005,17 @@
 	struct se_portal_group *tpg;
 	ssize_t ret;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	deve = nacl->device_list[lacl->mapped_lun];
-	if (!deve->se_lun || !deve->se_lun_acl) {
-		spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, lacl->mapped_lun);
+	if (!deve) {
+		rcu_read_unlock();
 		return -ENODEV;
 	}
 	tpg = nacl->se_tpg;
 	/* scsiInstIndex */
 	ret = snprintf(page, PAGE_SIZE, "%u\n",
 			tpg->se_tpg_tfo->tpg_get_inst_index(tpg));
-	spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_AUTH_INTR_ATTR_RO(inst);
@@ -1107,16 +1030,16 @@
 	struct se_lun *lun;
 	ssize_t ret;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	deve = nacl->device_list[lacl->mapped_lun];
-	if (!deve->se_lun || !deve->se_lun_acl) {
-		spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, lacl->mapped_lun);
+	if (!deve) {
+		rcu_read_unlock();
 		return -ENODEV;
 	}
-	lun = deve->se_lun;
+	lun = rcu_dereference(deve->se_lun);
 	/* scsiDeviceIndex */
-	ret = snprintf(page, PAGE_SIZE, "%u\n", lun->lun_se_dev->dev_index);
-	spin_unlock_irq(&nacl->device_list_lock);
+	ret = snprintf(page, PAGE_SIZE, "%u\n", lun->lun_index);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_AUTH_INTR_ATTR_RO(dev);
@@ -1131,16 +1054,16 @@
 	struct se_portal_group *tpg;
 	ssize_t ret;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	deve = nacl->device_list[lacl->mapped_lun];
-	if (!deve->se_lun || !deve->se_lun_acl) {
-		spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, lacl->mapped_lun);
+	if (!deve) {
+		rcu_read_unlock();
 		return -ENODEV;
 	}
 	tpg = nacl->se_tpg;
 	/* scsiAuthIntrTgtPortIndex */
 	ret = snprintf(page, PAGE_SIZE, "%u\n", tpg->se_tpg_tfo->tpg_get_tag(tpg));
-	spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_AUTH_INTR_ATTR_RO(port);
@@ -1154,15 +1077,15 @@
 	struct se_dev_entry *deve;
 	ssize_t ret;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	deve = nacl->device_list[lacl->mapped_lun];
-	if (!deve->se_lun || !deve->se_lun_acl) {
-		spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, lacl->mapped_lun);
+	if (!deve) {
+		rcu_read_unlock();
 		return -ENODEV;
 	}
 	/* scsiAuthIntrIndex */
 	ret = snprintf(page, PAGE_SIZE, "%u\n", nacl->acl_index);
-	spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_AUTH_INTR_ATTR_RO(indx);
@@ -1176,15 +1099,15 @@
 	struct se_dev_entry *deve;
 	ssize_t ret;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	deve = nacl->device_list[lacl->mapped_lun];
-	if (!deve->se_lun || !deve->se_lun_acl) {
-		spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, lacl->mapped_lun);
+	if (!deve) {
+		rcu_read_unlock();
 		return -ENODEV;
 	}
 	/* scsiAuthIntrDevOrPort */
 	ret = snprintf(page, PAGE_SIZE, "%u\n", 1);
-	spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_AUTH_INTR_ATTR_RO(dev_or_port);
@@ -1198,15 +1121,15 @@
 	struct se_dev_entry *deve;
 	ssize_t ret;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	deve = nacl->device_list[lacl->mapped_lun];
-	if (!deve->se_lun || !deve->se_lun_acl) {
-		spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, lacl->mapped_lun);
+	if (!deve) {
+		rcu_read_unlock();
 		return -ENODEV;
 	}
 	/* scsiAuthIntrName */
 	ret = snprintf(page, PAGE_SIZE, "%s\n", nacl->initiatorname);
-	spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_AUTH_INTR_ATTR_RO(intr_name);
@@ -1220,15 +1143,15 @@
 	struct se_dev_entry *deve;
 	ssize_t ret;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	deve = nacl->device_list[lacl->mapped_lun];
-	if (!deve->se_lun || !deve->se_lun_acl) {
-		spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, lacl->mapped_lun);
+	if (!deve) {
+		rcu_read_unlock();
 		return -ENODEV;
 	}
 	/* FIXME: scsiAuthIntrLunMapIndex */
 	ret = snprintf(page, PAGE_SIZE, "%u\n", 0);
-	spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_AUTH_INTR_ATTR_RO(map_indx);
@@ -1242,15 +1165,15 @@
 	struct se_dev_entry *deve;
 	ssize_t ret;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	deve = nacl->device_list[lacl->mapped_lun];
-	if (!deve->se_lun || !deve->se_lun_acl) {
-		spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, lacl->mapped_lun);
+	if (!deve) {
+		rcu_read_unlock();
 		return -ENODEV;
 	}
 	/* scsiAuthIntrAttachedTimes */
 	ret = snprintf(page, PAGE_SIZE, "%u\n", deve->attach_count);
-	spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_AUTH_INTR_ATTR_RO(att_count);
@@ -1264,15 +1187,16 @@
 	struct se_dev_entry *deve;
 	ssize_t ret;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	deve = nacl->device_list[lacl->mapped_lun];
-	if (!deve->se_lun || !deve->se_lun_acl) {
-		spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, lacl->mapped_lun);
+	if (!deve) {
+		rcu_read_unlock();
 		return -ENODEV;
 	}
 	/* scsiAuthIntrOutCommands */
-	ret = snprintf(page, PAGE_SIZE, "%u\n", deve->total_cmds);
-	spin_unlock_irq(&nacl->device_list_lock);
+	ret = snprintf(page, PAGE_SIZE, "%lu\n",
+		       atomic_long_read(&deve->total_cmds));
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_AUTH_INTR_ATTR_RO(num_cmds);
@@ -1286,15 +1210,16 @@
 	struct se_dev_entry *deve;
 	ssize_t ret;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	deve = nacl->device_list[lacl->mapped_lun];
-	if (!deve->se_lun || !deve->se_lun_acl) {
-		spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, lacl->mapped_lun);
+	if (!deve) {
+		rcu_read_unlock();
 		return -ENODEV;
 	}
 	/* scsiAuthIntrReadMegaBytes */
-	ret = snprintf(page, PAGE_SIZE, "%u\n", (u32)(deve->read_bytes >> 20));
-	spin_unlock_irq(&nacl->device_list_lock);
+	ret = snprintf(page, PAGE_SIZE, "%u\n",
+		      (u32)(atomic_long_read(&deve->read_bytes) >> 20));
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_AUTH_INTR_ATTR_RO(read_mbytes);
@@ -1308,15 +1233,16 @@
 	struct se_dev_entry *deve;
 	ssize_t ret;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	deve = nacl->device_list[lacl->mapped_lun];
-	if (!deve->se_lun || !deve->se_lun_acl) {
-		spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, lacl->mapped_lun);
+	if (!deve) {
+		rcu_read_unlock();
 		return -ENODEV;
 	}
 	/* scsiAuthIntrWrittenMegaBytes */
-	ret = snprintf(page, PAGE_SIZE, "%u\n", (u32)(deve->write_bytes >> 20));
-	spin_unlock_irq(&nacl->device_list_lock);
+	ret = snprintf(page, PAGE_SIZE, "%u\n",
+		      (u32)(atomic_long_read(&deve->write_bytes) >> 20));
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_AUTH_INTR_ATTR_RO(write_mbytes);
@@ -1330,15 +1256,15 @@
 	struct se_dev_entry *deve;
 	ssize_t ret;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	deve = nacl->device_list[lacl->mapped_lun];
-	if (!deve->se_lun || !deve->se_lun_acl) {
-		spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, lacl->mapped_lun);
+	if (!deve) {
+		rcu_read_unlock();
 		return -ENODEV;
 	}
 	/* FIXME: scsiAuthIntrHSOutCommands */
 	ret = snprintf(page, PAGE_SIZE, "%u\n", 0);
-	spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_AUTH_INTR_ATTR_RO(hs_num_cmds);
@@ -1352,16 +1278,16 @@
 	struct se_dev_entry *deve;
 	ssize_t ret;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	deve = nacl->device_list[lacl->mapped_lun];
-	if (!deve->se_lun || !deve->se_lun_acl) {
-		spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, lacl->mapped_lun);
+	if (!deve) {
+		rcu_read_unlock();
 		return -ENODEV;
 	}
 	/* scsiAuthIntrLastCreation */
 	ret = snprintf(page, PAGE_SIZE, "%u\n", (u32)(((u32)deve->creation_time -
 				INITIAL_JIFFIES) * 100 / HZ));
-	spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_AUTH_INTR_ATTR_RO(creation_time);
@@ -1375,15 +1301,15 @@
 	struct se_dev_entry *deve;
 	ssize_t ret;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	deve = nacl->device_list[lacl->mapped_lun];
-	if (!deve->se_lun || !deve->se_lun_acl) {
-		spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, lacl->mapped_lun);
+	if (!deve) {
+		rcu_read_unlock();
 		return -ENODEV;
 	}
 	/* FIXME: scsiAuthIntrRowStatus */
 	ret = snprintf(page, PAGE_SIZE, "Ready\n");
-	spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_AUTH_INTR_ATTR_RO(row_status);
@@ -1448,17 +1374,17 @@
 	struct se_portal_group *tpg;
 	ssize_t ret;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	deve = nacl->device_list[lacl->mapped_lun];
-	if (!deve->se_lun || !deve->se_lun_acl) {
-		spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, lacl->mapped_lun);
+	if (!deve) {
+		rcu_read_unlock();
 		return -ENODEV;
 	}
 	tpg = nacl->se_tpg;
 	/* scsiInstIndex */
 	ret = snprintf(page, PAGE_SIZE, "%u\n",
 			tpg->se_tpg_tfo->tpg_get_inst_index(tpg));
-	spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_ATTR_INTR_PORT_ATTR_RO(inst);
@@ -1473,16 +1399,16 @@
 	struct se_lun *lun;
 	ssize_t ret;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	deve = nacl->device_list[lacl->mapped_lun];
-	if (!deve->se_lun || !deve->se_lun_acl) {
-		spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, lacl->mapped_lun);
+	if (!deve) {
+		rcu_read_unlock();
 		return -ENODEV;
 	}
-	lun = deve->se_lun;
+	lun = rcu_dereference(deve->se_lun);
 	/* scsiDeviceIndex */
-	ret = snprintf(page, PAGE_SIZE, "%u\n", lun->lun_se_dev->dev_index);
-	spin_unlock_irq(&nacl->device_list_lock);
+	ret = snprintf(page, PAGE_SIZE, "%u\n", lun->lun_index);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_ATTR_INTR_PORT_ATTR_RO(dev);
@@ -1497,16 +1423,16 @@
 	struct se_portal_group *tpg;
 	ssize_t ret;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	deve = nacl->device_list[lacl->mapped_lun];
-	if (!deve->se_lun || !deve->se_lun_acl) {
-		spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, lacl->mapped_lun);
+	if (!deve) {
+		rcu_read_unlock();
 		return -ENODEV;
 	}
 	tpg = nacl->se_tpg;
 	/* scsiPortIndex */
 	ret = snprintf(page, PAGE_SIZE, "%u\n", tpg->se_tpg_tfo->tpg_get_tag(tpg));
-	spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_ATTR_INTR_PORT_ATTR_RO(port);
@@ -1546,15 +1472,15 @@
 	struct se_dev_entry *deve;
 	ssize_t ret;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	deve = nacl->device_list[lacl->mapped_lun];
-	if (!deve->se_lun || !deve->se_lun_acl) {
-		spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, lacl->mapped_lun);
+	if (!deve) {
+		rcu_read_unlock();
 		return -ENODEV;
 	}
 	/* scsiAttIntrPortAuthIntrIdx */
 	ret = snprintf(page, PAGE_SIZE, "%u\n", nacl->acl_index);
-	spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_unlock();
 	return ret;
 }
 DEV_STAT_SCSI_ATTR_INTR_PORT_ATTR_RO(port_auth_indx);
diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index a5bb0c4..5b28203 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -31,7 +31,6 @@
 #include <target/target_core_base.h>
 #include <target/target_core_backend.h>
 #include <target/target_core_fabric.h>
-#include <target/target_core_configfs.h>
 
 #include "target_core_internal.h"
 #include "target_core_alua.h"
@@ -115,7 +114,7 @@
 {
 	struct se_cmd *se_cmd;
 	unsigned long flags;
-	int ref_tag;
+	u64 ref_tag;
 
 	spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
 	list_for_each_entry(se_cmd, &se_sess->sess_cmd_list, se_cmd_list) {
@@ -127,16 +126,17 @@
 		if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)
 			continue;
 
-		ref_tag = se_cmd->se_tfo->get_task_tag(se_cmd);
+		ref_tag = se_cmd->tag;
 		if (tmr->ref_task_tag != ref_tag)
 			continue;
 
-		printk("ABORT_TASK: Found referenced %s task_tag: %u\n",
+		printk("ABORT_TASK: Found referenced %s task_tag: %llu\n",
 			se_cmd->se_tfo->get_fabric_name(), ref_tag);
 
 		spin_lock(&se_cmd->t_state_lock);
 		if (se_cmd->transport_state & CMD_T_COMPLETE) {
-			printk("ABORT_TASK: ref_tag: %u already complete, skipping\n", ref_tag);
+			printk("ABORT_TASK: ref_tag: %llu already complete,"
+			       " skipping\n", ref_tag);
 			spin_unlock(&se_cmd->t_state_lock);
 			spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 			goto out;
@@ -151,18 +151,18 @@
 		cancel_work_sync(&se_cmd->work);
 		transport_wait_for_tasks(se_cmd);
 
-		target_put_sess_cmd(se_sess, se_cmd);
+		target_put_sess_cmd(se_cmd);
 		transport_cmd_finish_abort(se_cmd, true);
 
 		printk("ABORT_TASK: Sending TMR_FUNCTION_COMPLETE for"
-				" ref_tag: %d\n", ref_tag);
+				" ref_tag: %llu\n", ref_tag);
 		tmr->response = TMR_FUNCTION_COMPLETE;
 		return;
 	}
 	spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 
 out:
-	printk("ABORT_TASK: Sending TMR_TASK_DOES_NOT_EXIST for ref_tag: %d\n",
+	printk("ABORT_TASK: Sending TMR_TASK_DOES_NOT_EXIST for ref_tag: %lld\n",
 			tmr->ref_task_tag);
 	tmr->response = TMR_TASK_DOES_NOT_EXIST;
 }
@@ -287,16 +287,16 @@
 		list_del(&cmd->state_list);
 
 		pr_debug("LUN_RESET: %s cmd: %p"
-			" ITT/CmdSN: 0x%08x/0x%08x, i_state: %d, t_state: %d"
+			" ITT/CmdSN: 0x%08llx/0x%08x, i_state: %d, t_state: %d"
 			"cdb: 0x%02x\n",
 			(preempt_and_abort_list) ? "Preempt" : "", cmd,
-			cmd->se_tfo->get_task_tag(cmd), 0,
+			cmd->tag, 0,
 			cmd->se_tfo->get_cmd_state(cmd), cmd->t_state,
 			cmd->t_task_cdb[0]);
-		pr_debug("LUN_RESET: ITT[0x%08x] - pr_res_key: 0x%016Lx"
+		pr_debug("LUN_RESET: ITT[0x%08llx] - pr_res_key: 0x%016Lx"
 			" -- CMD_T_ACTIVE: %d"
 			" CMD_T_STOP: %d CMD_T_SENT: %d\n",
-			cmd->se_tfo->get_task_tag(cmd), cmd->pr_res_key,
+			cmd->tag, cmd->pr_res_key,
 			(cmd->transport_state & CMD_T_ACTIVE) != 0,
 			(cmd->transport_state & CMD_T_STOP) != 0,
 			(cmd->transport_state & CMD_T_SENT) != 0);
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index 84de757..babde4a 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -39,6 +39,7 @@
 #include <target/target_core_fabric.h>
 
 #include "target_core_internal.h"
+#include "target_core_alua.h"
 #include "target_core_pr.h"
 
 extern struct se_device *g_lun0_dev;
@@ -46,45 +47,9 @@
 static DEFINE_SPINLOCK(tpg_lock);
 static LIST_HEAD(tpg_list);
 
-/*	core_clear_initiator_node_from_tpg():
- *
- *
- */
-static void core_clear_initiator_node_from_tpg(
-	struct se_node_acl *nacl,
-	struct se_portal_group *tpg)
-{
-	int i;
-	struct se_dev_entry *deve;
-	struct se_lun *lun;
-
-	spin_lock_irq(&nacl->device_list_lock);
-	for (i = 0; i < TRANSPORT_MAX_LUNS_PER_TPG; i++) {
-		deve = nacl->device_list[i];
-
-		if (!(deve->lun_flags & TRANSPORT_LUNFLAGS_INITIATOR_ACCESS))
-			continue;
-
-		if (!deve->se_lun) {
-			pr_err("%s device entries device pointer is"
-				" NULL, but Initiator has access.\n",
-				tpg->se_tpg_tfo->get_fabric_name());
-			continue;
-		}
-
-		lun = deve->se_lun;
-		spin_unlock_irq(&nacl->device_list_lock);
-		core_disable_device_list_for_node(lun, NULL, deve->mapped_lun,
-			TRANSPORT_LUNFLAGS_NO_ACCESS, nacl, tpg);
-
-		spin_lock_irq(&nacl->device_list_lock);
-	}
-	spin_unlock_irq(&nacl->device_list_lock);
-}
-
 /*	__core_tpg_get_initiator_node_acl():
  *
- *	spin_lock_bh(&tpg->acl_node_lock); must be held when calling
+ *	mutex_lock(&tpg->acl_node_mutex); must be held when calling
  */
 struct se_node_acl *__core_tpg_get_initiator_node_acl(
 	struct se_portal_group *tpg,
@@ -110,9 +75,9 @@
 {
 	struct se_node_acl *acl;
 
-	spin_lock_irq(&tpg->acl_node_lock);
+	mutex_lock(&tpg->acl_node_mutex);
 	acl = __core_tpg_get_initiator_node_acl(tpg, initiatorname);
-	spin_unlock_irq(&tpg->acl_node_lock);
+	mutex_unlock(&tpg->acl_node_mutex);
 
 	return acl;
 }
@@ -124,22 +89,20 @@
  */
 void core_tpg_add_node_to_devs(
 	struct se_node_acl *acl,
-	struct se_portal_group *tpg)
+	struct se_portal_group *tpg,
+	struct se_lun *lun_orig)
 {
-	int i = 0;
 	u32 lun_access = 0;
 	struct se_lun *lun;
 	struct se_device *dev;
 
-	spin_lock(&tpg->tpg_lun_lock);
-	for (i = 0; i < TRANSPORT_MAX_LUNS_PER_TPG; i++) {
-		lun = tpg->tpg_lun_list[i];
-		if (lun->lun_status != TRANSPORT_LUN_STATUS_ACTIVE)
+	mutex_lock(&tpg->tpg_lun_mutex);
+	hlist_for_each_entry_rcu(lun, &tpg->tpg_lun_hlist, link) {
+		if (lun_orig && lun != lun_orig)
 			continue;
 
-		spin_unlock(&tpg->tpg_lun_lock);
-
-		dev = lun->lun_se_dev;
+		dev = rcu_dereference_check(lun->lun_se_dev,
+					    lockdep_is_held(&tpg->tpg_lun_mutex));
 		/*
 		 * By default in LIO-Target $FABRIC_MOD,
 		 * demo_mode_write_protect is ON, or READ_ONLY;
@@ -157,7 +120,7 @@
 				lun_access = TRANSPORT_LUNFLAGS_READ_WRITE;
 		}
 
-		pr_debug("TARGET_CORE[%s]->TPG[%u]_LUN[%u] - Adding %s"
+		pr_debug("TARGET_CORE[%s]->TPG[%u]_LUN[%llu] - Adding %s"
 			" access for LUN in Demo Mode\n",
 			tpg->se_tpg_tfo->get_fabric_name(),
 			tpg->se_tpg_tfo->tpg_get_tag(tpg), lun->unpacked_lun,
@@ -165,7 +128,7 @@
 			"READ-WRITE" : "READ-ONLY");
 
 		core_enable_device_list_for_node(lun, NULL, lun->unpacked_lun,
-				lun_access, acl, tpg);
+						 lun_access, acl, tpg);
 		/*
 		 * Check to see if there are any existing persistent reservation
 		 * APTPL pre-registrations that need to be enabled for this dynamic
@@ -173,9 +136,8 @@
 		 */
 		core_scsi3_check_aptpl_registration(dev, tpg, lun, acl,
 						    lun->unpacked_lun);
-		spin_lock(&tpg->tpg_lun_lock);
 	}
-	spin_unlock(&tpg->tpg_lun_lock);
+	mutex_unlock(&tpg->tpg_lun_mutex);
 }
 
 /*      core_set_queue_depth_for_node():
@@ -196,67 +158,63 @@
 	return 0;
 }
 
-void array_free(void *array, int n)
+static struct se_node_acl *target_alloc_node_acl(struct se_portal_group *tpg,
+		const unsigned char *initiatorname)
 {
-	void **a = array;
-	int i;
+	struct se_node_acl *acl;
 
-	for (i = 0; i < n; i++)
-		kfree(a[i]);
-	kfree(a);
-}
-
-static void *array_zalloc(int n, size_t size, gfp_t flags)
-{
-	void **a;
-	int i;
-
-	a = kzalloc(n * sizeof(void*), flags);
-	if (!a)
+	acl = kzalloc(max(sizeof(*acl), tpg->se_tpg_tfo->node_acl_size),
+			GFP_KERNEL);
+	if (!acl)
 		return NULL;
-	for (i = 0; i < n; i++) {
-		a[i] = kzalloc(size, flags);
-		if (!a[i]) {
-			array_free(a, n);
-			return NULL;
-		}
-	}
-	return a;
+
+	INIT_LIST_HEAD(&acl->acl_list);
+	INIT_LIST_HEAD(&acl->acl_sess_list);
+	INIT_HLIST_HEAD(&acl->lun_entry_hlist);
+	kref_init(&acl->acl_kref);
+	init_completion(&acl->acl_free_comp);
+	spin_lock_init(&acl->nacl_sess_lock);
+	mutex_init(&acl->lun_entry_mutex);
+	atomic_set(&acl->acl_pr_ref_count, 0);
+	if (tpg->se_tpg_tfo->tpg_get_default_depth)
+		acl->queue_depth = tpg->se_tpg_tfo->tpg_get_default_depth(tpg);
+	else
+		acl->queue_depth = 1;
+	snprintf(acl->initiatorname, TRANSPORT_IQN_LEN, "%s", initiatorname);
+	acl->se_tpg = tpg;
+	acl->acl_index = scsi_get_new_index(SCSI_AUTH_INTR_INDEX);
+
+	tpg->se_tpg_tfo->set_default_node_attributes(acl);
+
+	if (core_set_queue_depth_for_node(tpg, acl) < 0)
+		goto out_free_acl;
+
+	return acl;
+
+out_free_acl:
+	kfree(acl);
+	return NULL;
 }
 
-/*      core_create_device_list_for_node():
- *
- *
- */
-static int core_create_device_list_for_node(struct se_node_acl *nacl)
+static void target_add_node_acl(struct se_node_acl *acl)
 {
-	struct se_dev_entry *deve;
-	int i;
+	struct se_portal_group *tpg = acl->se_tpg;
 
-	nacl->device_list = array_zalloc(TRANSPORT_MAX_LUNS_PER_TPG,
-			sizeof(struct se_dev_entry), GFP_KERNEL);
-	if (!nacl->device_list) {
-		pr_err("Unable to allocate memory for"
-			" struct se_node_acl->device_list\n");
-		return -ENOMEM;
-	}
-	for (i = 0; i < TRANSPORT_MAX_LUNS_PER_TPG; i++) {
-		deve = nacl->device_list[i];
+	mutex_lock(&tpg->acl_node_mutex);
+	list_add_tail(&acl->acl_list, &tpg->acl_node_list);
+	tpg->num_node_acls++;
+	mutex_unlock(&tpg->acl_node_mutex);
 
-		atomic_set(&deve->ua_count, 0);
-		atomic_set(&deve->pr_ref_count, 0);
-		spin_lock_init(&deve->ua_lock);
-		INIT_LIST_HEAD(&deve->alua_port_list);
-		INIT_LIST_HEAD(&deve->ua_list);
-	}
-
-	return 0;
+	pr_debug("%s_TPG[%hu] - Added %s ACL with TCQ Depth: %d for %s"
+		" Initiator Node: %s\n",
+		tpg->se_tpg_tfo->get_fabric_name(),
+		tpg->se_tpg_tfo->tpg_get_tag(tpg),
+		acl->dynamic_node_acl ? "DYNAMIC" : "",
+		acl->queue_depth,
+		tpg->se_tpg_tfo->get_fabric_name(),
+		acl->initiatorname);
 }
 
-/*	core_tpg_check_initiator_node_acl()
- *
- *
- */
 struct se_node_acl *core_tpg_check_initiator_node_acl(
 	struct se_portal_group *tpg,
 	unsigned char *initiatorname)
@@ -270,35 +228,11 @@
 	if (!tpg->se_tpg_tfo->tpg_check_demo_mode(tpg))
 		return NULL;
 
-	acl =  tpg->se_tpg_tfo->tpg_alloc_fabric_acl(tpg);
+	acl = target_alloc_node_acl(tpg, initiatorname);
 	if (!acl)
 		return NULL;
-
-	INIT_LIST_HEAD(&acl->acl_list);
-	INIT_LIST_HEAD(&acl->acl_sess_list);
-	kref_init(&acl->acl_kref);
-	init_completion(&acl->acl_free_comp);
-	spin_lock_init(&acl->device_list_lock);
-	spin_lock_init(&acl->nacl_sess_lock);
-	atomic_set(&acl->acl_pr_ref_count, 0);
-	acl->queue_depth = tpg->se_tpg_tfo->tpg_get_default_depth(tpg);
-	snprintf(acl->initiatorname, TRANSPORT_IQN_LEN, "%s", initiatorname);
-	acl->se_tpg = tpg;
-	acl->acl_index = scsi_get_new_index(SCSI_AUTH_INTR_INDEX);
 	acl->dynamic_node_acl = 1;
 
-	tpg->se_tpg_tfo->set_default_node_attributes(acl);
-
-	if (core_create_device_list_for_node(acl) < 0) {
-		tpg->se_tpg_tfo->tpg_release_fabric_acl(tpg, acl);
-		return NULL;
-	}
-
-	if (core_set_queue_depth_for_node(tpg, acl) < 0) {
-		core_free_device_list_for_node(acl, tpg);
-		tpg->se_tpg_tfo->tpg_release_fabric_acl(tpg, acl);
-		return NULL;
-	}
 	/*
 	 * Here we only create demo-mode MappedLUNs from the active
 	 * TPG LUNs if the fabric is not explicitly asking for
@@ -306,18 +240,9 @@
 	 */
 	if ((tpg->se_tpg_tfo->tpg_check_demo_mode_login_only == NULL) ||
 	    (tpg->se_tpg_tfo->tpg_check_demo_mode_login_only(tpg) != 1))
-		core_tpg_add_node_to_devs(acl, tpg);
+		core_tpg_add_node_to_devs(acl, tpg, NULL);
 
-	spin_lock_irq(&tpg->acl_node_lock);
-	list_add_tail(&acl->acl_list, &tpg->acl_node_list);
-	tpg->num_node_acls++;
-	spin_unlock_irq(&tpg->acl_node_lock);
-
-	pr_debug("%s_TPG[%u] - Added DYNAMIC ACL with TCQ Depth: %d for %s"
-		" Initiator Node: %s\n", tpg->se_tpg_tfo->get_fabric_name(),
-		tpg->se_tpg_tfo->tpg_get_tag(tpg), acl->queue_depth,
-		tpg->se_tpg_tfo->get_fabric_name(), initiatorname);
-
+	target_add_node_acl(acl);
 	return acl;
 }
 EXPORT_SYMBOL(core_tpg_check_initiator_node_acl);
@@ -328,40 +253,13 @@
 		cpu_relax();
 }
 
-void core_tpg_clear_object_luns(struct se_portal_group *tpg)
-{
-	int i;
-	struct se_lun *lun;
-
-	spin_lock(&tpg->tpg_lun_lock);
-	for (i = 0; i < TRANSPORT_MAX_LUNS_PER_TPG; i++) {
-		lun = tpg->tpg_lun_list[i];
-
-		if ((lun->lun_status != TRANSPORT_LUN_STATUS_ACTIVE) ||
-		    (lun->lun_se_dev == NULL))
-			continue;
-
-		spin_unlock(&tpg->tpg_lun_lock);
-		core_dev_del_lun(tpg, lun);
-		spin_lock(&tpg->tpg_lun_lock);
-	}
-	spin_unlock(&tpg->tpg_lun_lock);
-}
-EXPORT_SYMBOL(core_tpg_clear_object_luns);
-
-/*	core_tpg_add_initiator_node_acl():
- *
- *
- */
 struct se_node_acl *core_tpg_add_initiator_node_acl(
 	struct se_portal_group *tpg,
-	struct se_node_acl *se_nacl,
-	const char *initiatorname,
-	u32 queue_depth)
+	const char *initiatorname)
 {
-	struct se_node_acl *acl = NULL;
+	struct se_node_acl *acl;
 
-	spin_lock_irq(&tpg->acl_node_lock);
+	mutex_lock(&tpg->acl_node_mutex);
 	acl = __core_tpg_get_initiator_node_acl(tpg, initiatorname);
 	if (acl) {
 		if (acl->dynamic_node_acl) {
@@ -369,99 +267,42 @@
 			pr_debug("%s_TPG[%u] - Replacing dynamic ACL"
 				" for %s\n", tpg->se_tpg_tfo->get_fabric_name(),
 				tpg->se_tpg_tfo->tpg_get_tag(tpg), initiatorname);
-			spin_unlock_irq(&tpg->acl_node_lock);
-			/*
-			 * Release the locally allocated struct se_node_acl
-			 * because * core_tpg_add_initiator_node_acl() returned
-			 * a pointer to an existing demo mode node ACL.
-			 */
-			if (se_nacl)
-				tpg->se_tpg_tfo->tpg_release_fabric_acl(tpg,
-							se_nacl);
-			goto done;
+			mutex_unlock(&tpg->acl_node_mutex);
+			return acl;
 		}
 
 		pr_err("ACL entry for %s Initiator"
 			" Node %s already exists for TPG %u, ignoring"
 			" request.\n",  tpg->se_tpg_tfo->get_fabric_name(),
 			initiatorname, tpg->se_tpg_tfo->tpg_get_tag(tpg));
-		spin_unlock_irq(&tpg->acl_node_lock);
+		mutex_unlock(&tpg->acl_node_mutex);
 		return ERR_PTR(-EEXIST);
 	}
-	spin_unlock_irq(&tpg->acl_node_lock);
+	mutex_unlock(&tpg->acl_node_mutex);
 
-	if (!se_nacl) {
-		pr_err("struct se_node_acl pointer is NULL\n");
-		return ERR_PTR(-EINVAL);
-	}
-	/*
-	 * For v4.x logic the se_node_acl_s is hanging off a fabric
-	 * dependent structure allocated via
-	 * struct target_core_fabric_ops->fabric_make_nodeacl()
-	 */
-	acl = se_nacl;
-
-	INIT_LIST_HEAD(&acl->acl_list);
-	INIT_LIST_HEAD(&acl->acl_sess_list);
-	kref_init(&acl->acl_kref);
-	init_completion(&acl->acl_free_comp);
-	spin_lock_init(&acl->device_list_lock);
-	spin_lock_init(&acl->nacl_sess_lock);
-	atomic_set(&acl->acl_pr_ref_count, 0);
-	acl->queue_depth = queue_depth;
-	snprintf(acl->initiatorname, TRANSPORT_IQN_LEN, "%s", initiatorname);
-	acl->se_tpg = tpg;
-	acl->acl_index = scsi_get_new_index(SCSI_AUTH_INTR_INDEX);
-
-	tpg->se_tpg_tfo->set_default_node_attributes(acl);
-
-	if (core_create_device_list_for_node(acl) < 0) {
-		tpg->se_tpg_tfo->tpg_release_fabric_acl(tpg, acl);
+	acl = target_alloc_node_acl(tpg, initiatorname);
+	if (!acl)
 		return ERR_PTR(-ENOMEM);
-	}
 
-	if (core_set_queue_depth_for_node(tpg, acl) < 0) {
-		core_free_device_list_for_node(acl, tpg);
-		tpg->se_tpg_tfo->tpg_release_fabric_acl(tpg, acl);
-		return ERR_PTR(-EINVAL);
-	}
-
-	spin_lock_irq(&tpg->acl_node_lock);
-	list_add_tail(&acl->acl_list, &tpg->acl_node_list);
-	tpg->num_node_acls++;
-	spin_unlock_irq(&tpg->acl_node_lock);
-
-done:
-	pr_debug("%s_TPG[%hu] - Added ACL with TCQ Depth: %d for %s"
-		" Initiator Node: %s\n", tpg->se_tpg_tfo->get_fabric_name(),
-		tpg->se_tpg_tfo->tpg_get_tag(tpg), acl->queue_depth,
-		tpg->se_tpg_tfo->get_fabric_name(), initiatorname);
-
+	target_add_node_acl(acl);
 	return acl;
 }
-EXPORT_SYMBOL(core_tpg_add_initiator_node_acl);
 
-/*	core_tpg_del_initiator_node_acl():
- *
- *
- */
-int core_tpg_del_initiator_node_acl(
-	struct se_portal_group *tpg,
-	struct se_node_acl *acl,
-	int force)
+void core_tpg_del_initiator_node_acl(struct se_node_acl *acl)
 {
+	struct se_portal_group *tpg = acl->se_tpg;
 	LIST_HEAD(sess_list);
 	struct se_session *sess, *sess_tmp;
 	unsigned long flags;
 	int rc;
 
-	spin_lock_irq(&tpg->acl_node_lock);
+	mutex_lock(&tpg->acl_node_mutex);
 	if (acl->dynamic_node_acl) {
 		acl->dynamic_node_acl = 0;
 	}
 	list_del(&acl->acl_list);
 	tpg->num_node_acls--;
-	spin_unlock_irq(&tpg->acl_node_lock);
+	mutex_unlock(&tpg->acl_node_mutex);
 
 	spin_lock_irqsave(&acl->nacl_sess_lock, flags);
 	acl->acl_stop = 1;
@@ -493,7 +334,6 @@
 	wait_for_completion(&acl->acl_free_comp);
 
 	core_tpg_wait_for_nacl_pr_ref(acl);
-	core_clear_initiator_node_from_tpg(acl, tpg);
 	core_free_device_list_for_node(acl, tpg);
 
 	pr_debug("%s_TPG[%hu] - Deleted ACL with TCQ Depth: %d for %s"
@@ -501,9 +341,8 @@
 		tpg->se_tpg_tfo->tpg_get_tag(tpg), acl->queue_depth,
 		tpg->se_tpg_tfo->get_fabric_name(), acl->initiatorname);
 
-	return 0;
+	kfree(acl);
 }
-EXPORT_SYMBOL(core_tpg_del_initiator_node_acl);
 
 /*	core_tpg_set_initiator_node_queue_depth():
  *
@@ -520,21 +359,21 @@
 	unsigned long flags;
 	int dynamic_acl = 0;
 
-	spin_lock_irq(&tpg->acl_node_lock);
+	mutex_lock(&tpg->acl_node_mutex);
 	acl = __core_tpg_get_initiator_node_acl(tpg, initiatorname);
 	if (!acl) {
 		pr_err("Access Control List entry for %s Initiator"
 			" Node %s does not exists for TPG %hu, ignoring"
 			" request.\n", tpg->se_tpg_tfo->get_fabric_name(),
 			initiatorname, tpg->se_tpg_tfo->tpg_get_tag(tpg));
-		spin_unlock_irq(&tpg->acl_node_lock);
+		mutex_unlock(&tpg->acl_node_mutex);
 		return -ENODEV;
 	}
 	if (acl->dynamic_node_acl) {
 		acl->dynamic_node_acl = 0;
 		dynamic_acl = 1;
 	}
-	spin_unlock_irq(&tpg->acl_node_lock);
+	mutex_unlock(&tpg->acl_node_mutex);
 
 	spin_lock_irqsave(&tpg->session_lock, flags);
 	list_for_each_entry(sess, &tpg->tpg_sess_list, sess_list) {
@@ -550,10 +389,10 @@
 				tpg->se_tpg_tfo->get_fabric_name(), initiatorname);
 			spin_unlock_irqrestore(&tpg->session_lock, flags);
 
-			spin_lock_irq(&tpg->acl_node_lock);
+			mutex_lock(&tpg->acl_node_mutex);
 			if (dynamic_acl)
 				acl->dynamic_node_acl = 1;
-			spin_unlock_irq(&tpg->acl_node_lock);
+			mutex_unlock(&tpg->acl_node_mutex);
 			return -EEXIST;
 		}
 		/*
@@ -588,10 +427,10 @@
 		if (init_sess)
 			tpg->se_tpg_tfo->close_session(init_sess);
 
-		spin_lock_irq(&tpg->acl_node_lock);
+		mutex_lock(&tpg->acl_node_mutex);
 		if (dynamic_acl)
 			acl->dynamic_node_acl = 1;
-		spin_unlock_irq(&tpg->acl_node_lock);
+		mutex_unlock(&tpg->acl_node_mutex);
 		return -EINVAL;
 	}
 	spin_unlock_irqrestore(&tpg->session_lock, flags);
@@ -607,10 +446,10 @@
 		initiatorname, tpg->se_tpg_tfo->get_fabric_name(),
 		tpg->se_tpg_tfo->tpg_get_tag(tpg));
 
-	spin_lock_irq(&tpg->acl_node_lock);
+	mutex_lock(&tpg->acl_node_mutex);
 	if (dynamic_acl)
 		acl->dynamic_node_acl = 1;
-	spin_unlock_irq(&tpg->acl_node_lock);
+	mutex_unlock(&tpg->acl_node_mutex);
 
 	return 0;
 }
@@ -646,78 +485,54 @@
 	complete(&lun->lun_ref_comp);
 }
 
-static int core_tpg_setup_virtual_lun0(struct se_portal_group *se_tpg)
-{
-	/* Set in core_dev_setup_virtual_lun0() */
-	struct se_device *dev = g_lun0_dev;
-	struct se_lun *lun = &se_tpg->tpg_virt_lun0;
-	u32 lun_access = TRANSPORT_LUNFLAGS_READ_ONLY;
-	int ret;
-
-	lun->unpacked_lun = 0;
-	lun->lun_status = TRANSPORT_LUN_STATUS_FREE;
-	atomic_set(&lun->lun_acl_count, 0);
-	init_completion(&lun->lun_shutdown_comp);
-	INIT_LIST_HEAD(&lun->lun_acl_list);
-	spin_lock_init(&lun->lun_acl_lock);
-	spin_lock_init(&lun->lun_sep_lock);
-	init_completion(&lun->lun_ref_comp);
-
-	ret = core_tpg_add_lun(se_tpg, lun, lun_access, dev);
-	if (ret < 0)
-		return ret;
-
-	return 0;
-}
-
 int core_tpg_register(
-	const struct target_core_fabric_ops *tfo,
 	struct se_wwn *se_wwn,
 	struct se_portal_group *se_tpg,
-	void *tpg_fabric_ptr,
-	int se_tpg_type)
+	int proto_id)
 {
-	struct se_lun *lun;
-	u32 i;
+	int ret;
 
-	se_tpg->tpg_lun_list = array_zalloc(TRANSPORT_MAX_LUNS_PER_TPG,
-			sizeof(struct se_lun), GFP_KERNEL);
-	if (!se_tpg->tpg_lun_list) {
-		pr_err("Unable to allocate struct se_portal_group->"
-				"tpg_lun_list\n");
-		return -ENOMEM;
+	if (!se_tpg)
+		return -EINVAL;
+	/*
+	 * For the typical case where core_tpg_register() is called by a
+	 * fabric driver from target_core_fabric_ops->fabric_make_tpg()
+	 * configfs context, use the original tf_ops pointer already saved
+	 * by target-core in target_fabric_make_wwn().
+	 *
+	 * Otherwise, for special cases like iscsi-target discovery TPGs
+	 * the caller is responsible for setting ->se_tpg_tfo ahead of
+	 * calling core_tpg_register().
+	 */
+	if (se_wwn)
+		se_tpg->se_tpg_tfo = se_wwn->wwn_tf->tf_ops;
+
+	if (!se_tpg->se_tpg_tfo) {
+		pr_err("Unable to locate se_tpg->se_tpg_tfo pointer\n");
+		return -EINVAL;
 	}
 
-	for (i = 0; i < TRANSPORT_MAX_LUNS_PER_TPG; i++) {
-		lun = se_tpg->tpg_lun_list[i];
-		lun->unpacked_lun = i;
-		lun->lun_link_magic = SE_LUN_LINK_MAGIC;
-		lun->lun_status = TRANSPORT_LUN_STATUS_FREE;
-		atomic_set(&lun->lun_acl_count, 0);
-		init_completion(&lun->lun_shutdown_comp);
-		INIT_LIST_HEAD(&lun->lun_acl_list);
-		spin_lock_init(&lun->lun_acl_lock);
-		spin_lock_init(&lun->lun_sep_lock);
-		init_completion(&lun->lun_ref_comp);
-	}
-
-	se_tpg->se_tpg_type = se_tpg_type;
-	se_tpg->se_tpg_fabric_ptr = tpg_fabric_ptr;
-	se_tpg->se_tpg_tfo = tfo;
+	INIT_HLIST_HEAD(&se_tpg->tpg_lun_hlist);
+	se_tpg->proto_id = proto_id;
 	se_tpg->se_tpg_wwn = se_wwn;
 	atomic_set(&se_tpg->tpg_pr_ref_count, 0);
 	INIT_LIST_HEAD(&se_tpg->acl_node_list);
 	INIT_LIST_HEAD(&se_tpg->se_tpg_node);
 	INIT_LIST_HEAD(&se_tpg->tpg_sess_list);
-	spin_lock_init(&se_tpg->acl_node_lock);
 	spin_lock_init(&se_tpg->session_lock);
-	spin_lock_init(&se_tpg->tpg_lun_lock);
+	mutex_init(&se_tpg->tpg_lun_mutex);
+	mutex_init(&se_tpg->acl_node_mutex);
 
-	if (se_tpg->se_tpg_type == TRANSPORT_TPG_TYPE_NORMAL) {
-		if (core_tpg_setup_virtual_lun0(se_tpg) < 0) {
-			array_free(se_tpg->tpg_lun_list,
-				   TRANSPORT_MAX_LUNS_PER_TPG);
-			return -ENOMEM;
+	if (se_tpg->proto_id >= 0) {
+		se_tpg->tpg_virt_lun0 = core_tpg_alloc_lun(se_tpg, 0);
+		if (IS_ERR(se_tpg->tpg_virt_lun0))
+			return PTR_ERR(se_tpg->tpg_virt_lun0);
+
+		ret = core_tpg_add_lun(se_tpg, se_tpg->tpg_virt_lun0,
+				TRANSPORT_LUNFLAGS_READ_ONLY, g_lun0_dev);
+		if (ret < 0) {
+			kfree(se_tpg->tpg_virt_lun0);
+			return ret;
 		}
 	}
 
@@ -725,11 +540,11 @@
 	list_add_tail(&se_tpg->se_tpg_node, &tpg_list);
 	spin_unlock_bh(&tpg_lock);
 
-	pr_debug("TARGET_CORE[%s]: Allocated %s struct se_portal_group for"
-		" endpoint: %s, Portal Tag: %u\n", tfo->get_fabric_name(),
-		(se_tpg->se_tpg_type == TRANSPORT_TPG_TYPE_NORMAL) ?
-		"Normal" : "Discovery", (tfo->tpg_get_wwn(se_tpg) == NULL) ?
-		"None" : tfo->tpg_get_wwn(se_tpg), tfo->tpg_get_tag(se_tpg));
+	pr_debug("TARGET_CORE[%s]: Allocated portal_group for endpoint: %s, "
+		 "Proto: %d, Portal Tag: %u\n", se_tpg->se_tpg_tfo->get_fabric_name(),
+		se_tpg->se_tpg_tfo->tpg_get_wwn(se_tpg) ?
+		se_tpg->se_tpg_tfo->tpg_get_wwn(se_tpg) : NULL,
+		se_tpg->proto_id, se_tpg->se_tpg_tfo->tpg_get_tag(se_tpg));
 
 	return 0;
 }
@@ -737,14 +552,14 @@
 
 int core_tpg_deregister(struct se_portal_group *se_tpg)
 {
+	const struct target_core_fabric_ops *tfo = se_tpg->se_tpg_tfo;
 	struct se_node_acl *nacl, *nacl_tmp;
+	LIST_HEAD(node_list);
 
-	pr_debug("TARGET_CORE[%s]: Deallocating %s struct se_portal_group"
-		" for endpoint: %s Portal Tag %u\n",
-		(se_tpg->se_tpg_type == TRANSPORT_TPG_TYPE_NORMAL) ?
-		"Normal" : "Discovery", se_tpg->se_tpg_tfo->get_fabric_name(),
-		se_tpg->se_tpg_tfo->tpg_get_wwn(se_tpg),
-		se_tpg->se_tpg_tfo->tpg_get_tag(se_tpg));
+	pr_debug("TARGET_CORE[%s]: Deallocating portal_group for endpoint: %s, "
+		 "Proto: %d, Portal Tag: %u\n", tfo->get_fabric_name(),
+		tfo->tpg_get_wwn(se_tpg) ? tfo->tpg_get_wwn(se_tpg) : NULL,
+		se_tpg->proto_id, tfo->tpg_get_tag(se_tpg));
 
 	spin_lock_bh(&tpg_lock);
 	list_del(&se_tpg->se_tpg_node);
@@ -752,61 +567,56 @@
 
 	while (atomic_read(&se_tpg->tpg_pr_ref_count) != 0)
 		cpu_relax();
+
+	mutex_lock(&se_tpg->acl_node_mutex);
+	list_splice_init(&se_tpg->acl_node_list, &node_list);
+	mutex_unlock(&se_tpg->acl_node_mutex);
 	/*
 	 * Release any remaining demo-mode generated se_node_acl that have
 	 * not been released because of TFO->tpg_check_demo_mode_cache() == 1
 	 * in transport_deregister_session().
 	 */
-	spin_lock_irq(&se_tpg->acl_node_lock);
-	list_for_each_entry_safe(nacl, nacl_tmp, &se_tpg->acl_node_list,
-			acl_list) {
+	list_for_each_entry_safe(nacl, nacl_tmp, &node_list, acl_list) {
 		list_del(&nacl->acl_list);
 		se_tpg->num_node_acls--;
-		spin_unlock_irq(&se_tpg->acl_node_lock);
 
 		core_tpg_wait_for_nacl_pr_ref(nacl);
 		core_free_device_list_for_node(nacl, se_tpg);
-		se_tpg->se_tpg_tfo->tpg_release_fabric_acl(se_tpg, nacl);
-
-		spin_lock_irq(&se_tpg->acl_node_lock);
+		kfree(nacl);
 	}
-	spin_unlock_irq(&se_tpg->acl_node_lock);
 
-	if (se_tpg->se_tpg_type == TRANSPORT_TPG_TYPE_NORMAL)
-		core_tpg_remove_lun(se_tpg, &se_tpg->tpg_virt_lun0);
+	if (se_tpg->proto_id >= 0) {
+		core_tpg_remove_lun(se_tpg, se_tpg->tpg_virt_lun0);
+		kfree_rcu(se_tpg->tpg_virt_lun0, rcu_head);
+	}
 
-	se_tpg->se_tpg_fabric_ptr = NULL;
-	array_free(se_tpg->tpg_lun_list, TRANSPORT_MAX_LUNS_PER_TPG);
 	return 0;
 }
 EXPORT_SYMBOL(core_tpg_deregister);
 
 struct se_lun *core_tpg_alloc_lun(
 	struct se_portal_group *tpg,
-	u32 unpacked_lun)
+	u64 unpacked_lun)
 {
 	struct se_lun *lun;
 
-	if (unpacked_lun > (TRANSPORT_MAX_LUNS_PER_TPG-1)) {
-		pr_err("%s LUN: %u exceeds TRANSPORT_MAX_LUNS_PER_TPG"
-			"-1: %u for Target Portal Group: %u\n",
-			tpg->se_tpg_tfo->get_fabric_name(),
-			unpacked_lun, TRANSPORT_MAX_LUNS_PER_TPG-1,
-			tpg->se_tpg_tfo->tpg_get_tag(tpg));
-		return ERR_PTR(-EOVERFLOW);
+	lun = kzalloc(sizeof(*lun), GFP_KERNEL);
+	if (!lun) {
+		pr_err("Unable to allocate se_lun memory\n");
+		return ERR_PTR(-ENOMEM);
 	}
-
-	spin_lock(&tpg->tpg_lun_lock);
-	lun = tpg->tpg_lun_list[unpacked_lun];
-	if (lun->lun_status == TRANSPORT_LUN_STATUS_ACTIVE) {
-		pr_err("TPG Logical Unit Number: %u is already active"
-			" on %s Target Portal Group: %u, ignoring request.\n",
-			unpacked_lun, tpg->se_tpg_tfo->get_fabric_name(),
-			tpg->se_tpg_tfo->tpg_get_tag(tpg));
-		spin_unlock(&tpg->tpg_lun_lock);
-		return ERR_PTR(-EINVAL);
-	}
-	spin_unlock(&tpg->tpg_lun_lock);
+	lun->unpacked_lun = unpacked_lun;
+	lun->lun_link_magic = SE_LUN_LINK_MAGIC;
+	atomic_set(&lun->lun_acl_count, 0);
+	init_completion(&lun->lun_ref_comp);
+	INIT_LIST_HEAD(&lun->lun_deve_list);
+	INIT_LIST_HEAD(&lun->lun_dev_link);
+	atomic_set(&lun->lun_tg_pt_secondary_offline, 0);
+	spin_lock_init(&lun->lun_deve_lock);
+	mutex_init(&lun->lun_tg_pt_md_mutex);
+	INIT_LIST_HEAD(&lun->lun_tg_pt_gp_link);
+	spin_lock_init(&lun->lun_tg_pt_gp_lock);
+	lun->lun_tpg = tpg;
 
 	return lun;
 }
@@ -822,34 +632,70 @@
 	ret = percpu_ref_init(&lun->lun_ref, core_tpg_lun_ref_release, 0,
 			      GFP_KERNEL);
 	if (ret < 0)
-		return ret;
+		goto out;
 
-	ret = core_dev_export(dev, tpg, lun);
-	if (ret < 0) {
-		percpu_ref_exit(&lun->lun_ref);
-		return ret;
-	}
+	ret = core_alloc_rtpi(lun, dev);
+	if (ret)
+		goto out_kill_ref;
 
-	spin_lock(&tpg->tpg_lun_lock);
+	if (!(dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) &&
+	    !(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE))
+		target_attach_tg_pt_gp(lun, dev->t10_alua.default_tg_pt_gp);
+
+	mutex_lock(&tpg->tpg_lun_mutex);
+
+	spin_lock(&dev->se_port_lock);
+	lun->lun_index = dev->dev_index;
+	rcu_assign_pointer(lun->lun_se_dev, dev);
+	dev->export_count++;
+	list_add_tail(&lun->lun_dev_link, &dev->dev_sep_list);
+	spin_unlock(&dev->se_port_lock);
+
 	lun->lun_access = lun_access;
-	lun->lun_status = TRANSPORT_LUN_STATUS_ACTIVE;
-	spin_unlock(&tpg->tpg_lun_lock);
+	if (!(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE))
+		hlist_add_head_rcu(&lun->link, &tpg->tpg_lun_hlist);
+	mutex_unlock(&tpg->tpg_lun_mutex);
 
 	return 0;
+
+out_kill_ref:
+	percpu_ref_exit(&lun->lun_ref);
+out:
+	return ret;
 }
 
 void core_tpg_remove_lun(
 	struct se_portal_group *tpg,
 	struct se_lun *lun)
 {
+	/*
+	 * rcu_dereference_raw protected by se_lun->lun_group symlink
+	 * reference to se_device->dev_group.
+	 */
+	struct se_device *dev = rcu_dereference_raw(lun->lun_se_dev);
+
 	core_clear_lun_from_tpg(lun, tpg);
+	/*
+	 * Wait for any active I/O references to percpu se_lun->lun_ref to
+	 * be released.  Also, se_lun->lun_ref is now used by PR and ALUA
+	 * logic when referencing a remote target port during ALL_TGT_PT=1
+	 * and generating UNIT_ATTENTIONs for ALUA access state transition.
+	 */
 	transport_clear_lun_ref(lun);
 
-	core_dev_unexport(lun->lun_se_dev, tpg, lun);
+	mutex_lock(&tpg->tpg_lun_mutex);
+	if (lun->lun_se_dev) {
+		target_detach_tg_pt_gp(lun);
 
-	spin_lock(&tpg->tpg_lun_lock);
-	lun->lun_status = TRANSPORT_LUN_STATUS_FREE;
-	spin_unlock(&tpg->tpg_lun_lock);
+		spin_lock(&dev->se_port_lock);
+		list_del(&lun->lun_dev_link);
+		dev->export_count--;
+		rcu_assign_pointer(lun->lun_se_dev, NULL);
+		spin_unlock(&dev->se_port_lock);
+	}
+	if (!(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE))
+		hlist_del_rcu(&lun->link);
+	mutex_unlock(&tpg->tpg_lun_mutex);
 
 	percpu_ref_exit(&lun->lun_ref);
 }
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 0b4e242..ce8574b 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -43,7 +43,6 @@
 #include <target/target_core_base.h>
 #include <target/target_core_backend.h>
 #include <target/target_core_fabric.h>
-#include <target/target_core_configfs.h>
 
 #include "target_core_internal.h"
 #include "target_core_alua.h"
@@ -60,7 +59,6 @@
 struct kmem_cache *t10_alua_lu_gp_cache;
 struct kmem_cache *t10_alua_lu_gp_mem_cache;
 struct kmem_cache *t10_alua_tg_pt_gp_cache;
-struct kmem_cache *t10_alua_tg_pt_gp_mem_cache;
 struct kmem_cache *t10_alua_lba_map_cache;
 struct kmem_cache *t10_alua_lba_map_mem_cache;
 
@@ -119,16 +117,6 @@
 				"cache failed\n");
 		goto out_free_lu_gp_mem_cache;
 	}
-	t10_alua_tg_pt_gp_mem_cache = kmem_cache_create(
-			"t10_alua_tg_pt_gp_mem_cache",
-			sizeof(struct t10_alua_tg_pt_gp_member),
-			__alignof__(struct t10_alua_tg_pt_gp_member),
-			0, NULL);
-	if (!t10_alua_tg_pt_gp_mem_cache) {
-		pr_err("kmem_cache_create() for t10_alua_tg_pt_gp_"
-				"mem_t failed\n");
-		goto out_free_tg_pt_gp_cache;
-	}
 	t10_alua_lba_map_cache = kmem_cache_create(
 			"t10_alua_lba_map_cache",
 			sizeof(struct t10_alua_lba_map),
@@ -136,7 +124,7 @@
 	if (!t10_alua_lba_map_cache) {
 		pr_err("kmem_cache_create() for t10_alua_lba_map_"
 				"cache failed\n");
-		goto out_free_tg_pt_gp_mem_cache;
+		goto out_free_tg_pt_gp_cache;
 	}
 	t10_alua_lba_map_mem_cache = kmem_cache_create(
 			"t10_alua_lba_map_mem_cache",
@@ -159,8 +147,6 @@
 	kmem_cache_destroy(t10_alua_lba_map_mem_cache);
 out_free_lba_map_cache:
 	kmem_cache_destroy(t10_alua_lba_map_cache);
-out_free_tg_pt_gp_mem_cache:
-	kmem_cache_destroy(t10_alua_tg_pt_gp_mem_cache);
 out_free_tg_pt_gp_cache:
 	kmem_cache_destroy(t10_alua_tg_pt_gp_cache);
 out_free_lu_gp_mem_cache:
@@ -186,7 +172,6 @@
 	kmem_cache_destroy(t10_alua_lu_gp_cache);
 	kmem_cache_destroy(t10_alua_lu_gp_mem_cache);
 	kmem_cache_destroy(t10_alua_tg_pt_gp_cache);
-	kmem_cache_destroy(t10_alua_tg_pt_gp_mem_cache);
 	kmem_cache_destroy(t10_alua_lba_map_cache);
 	kmem_cache_destroy(t10_alua_lba_map_mem_cache);
 }
@@ -279,10 +264,7 @@
 	if (rc < 0) {
 		pr_err("Unable to init se_sess->sess_tag_pool,"
 			" tag_num: %u\n", tag_num);
-		if (is_vmalloc_addr(se_sess->sess_cmd_map))
-			vfree(se_sess->sess_cmd_map);
-		else
-			kfree(se_sess->sess_cmd_map);
+		kvfree(se_sess->sess_cmd_map);
 		se_sess->sess_cmd_map = NULL;
 		return -ENOMEM;
 	}
@@ -409,12 +391,6 @@
 
 void target_put_session(struct se_session *se_sess)
 {
-	struct se_portal_group *tpg = se_sess->se_tpg;
-
-	if (tpg->se_tpg_tfo->put_session != NULL) {
-		tpg->se_tpg_tfo->put_session(se_sess);
-		return;
-	}
 	kref_put(&se_sess->sess_kref, target_release_session);
 }
 EXPORT_SYMBOL(target_put_session);
@@ -489,10 +465,7 @@
 {
 	if (se_sess->sess_cmd_map) {
 		percpu_ida_destroy(&se_sess->sess_tag_pool);
-		if (is_vmalloc_addr(se_sess->sess_cmd_map))
-			vfree(se_sess->sess_cmd_map);
-		else
-			kfree(se_sess->sess_cmd_map);
+		kvfree(se_sess->sess_cmd_map);
 	}
 	kmem_cache_free(se_sess_cache, se_sess);
 }
@@ -504,7 +477,7 @@
 	const struct target_core_fabric_ops *se_tfo;
 	struct se_node_acl *se_nacl;
 	unsigned long flags;
-	bool comp_nacl = true;
+	bool comp_nacl = true, drop_nacl = false;
 
 	if (!se_tpg) {
 		transport_free_session(se_sess);
@@ -524,22 +497,22 @@
 	 */
 	se_nacl = se_sess->se_node_acl;
 
-	spin_lock_irqsave(&se_tpg->acl_node_lock, flags);
+	mutex_lock(&se_tpg->acl_node_mutex);
 	if (se_nacl && se_nacl->dynamic_node_acl) {
 		if (!se_tfo->tpg_check_demo_mode_cache(se_tpg)) {
 			list_del(&se_nacl->acl_list);
 			se_tpg->num_node_acls--;
-			spin_unlock_irqrestore(&se_tpg->acl_node_lock, flags);
-			core_tpg_wait_for_nacl_pr_ref(se_nacl);
-			core_free_device_list_for_node(se_nacl, se_tpg);
-			se_tfo->tpg_release_fabric_acl(se_tpg, se_nacl);
-
-			comp_nacl = false;
-			spin_lock_irqsave(&se_tpg->acl_node_lock, flags);
+			drop_nacl = true;
 		}
 	}
-	spin_unlock_irqrestore(&se_tpg->acl_node_lock, flags);
+	mutex_unlock(&se_tpg->acl_node_mutex);
 
+	if (drop_nacl) {
+		core_tpg_wait_for_nacl_pr_ref(se_nacl);
+		core_free_device_list_for_node(se_nacl, se_tpg);
+		kfree(se_nacl);
+		comp_nacl = false;
+	}
 	pr_debug("TARGET_CORE[%s]: Deregistered fabric_sess\n",
 		se_tpg->se_tpg_tfo->get_fabric_name());
 	/*
@@ -599,9 +572,8 @@
 	 * this command for frontend exceptions.
 	 */
 	if (cmd->transport_state & CMD_T_STOP) {
-		pr_debug("%s:%d CMD_T_STOP for ITT: 0x%08x\n",
-			__func__, __LINE__,
-			cmd->se_tfo->get_task_tag(cmd));
+		pr_debug("%s:%d CMD_T_STOP for ITT: 0x%08llx\n",
+			__func__, __LINE__, cmd->tag);
 
 		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
@@ -1154,6 +1126,8 @@
 /*
  * Used by fabric modules containing a local struct se_cmd within their
  * fabric dependent per I/O descriptor.
+ *
+ * Preserves the value of @cmd->tag.
  */
 void transport_init_se_cmd(
 	struct se_cmd *cmd,
@@ -1280,11 +1254,7 @@
 		return ret;
 
 	cmd->se_cmd_flags |= SCF_SUPPORTED_SAM_OPCODE;
-
-	spin_lock(&cmd->se_lun->lun_sep_lock);
-	if (cmd->se_lun->lun_sep)
-		cmd->se_lun->lun_sep->sep_stats.cmd_pdus++;
-	spin_unlock(&cmd->se_lun->lun_sep_lock);
+	atomic_long_inc(&cmd->se_lun->lun_stats.cmd_pdus);
 	return 0;
 }
 EXPORT_SYMBOL(target_setup_cmd_from_cdb);
@@ -1352,11 +1322,9 @@
 
 	cmd->t_data_sg = sgl;
 	cmd->t_data_nents = sgl_count;
+	cmd->t_bidi_data_sg = sgl_bidi;
+	cmd->t_bidi_data_nents = sgl_bidi_count;
 
-	if (sgl_bidi && sgl_bidi_count) {
-		cmd->t_bidi_data_sg = sgl_bidi;
-		cmd->t_bidi_data_nents = sgl_bidi_count;
-	}
 	cmd->se_cmd_flags |= SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC;
 	return 0;
 }
@@ -1381,6 +1349,8 @@
  * @sgl_prot: struct scatterlist memory protection information
  * @sgl_prot_count: scatterlist count for protection information
  *
+ * Task tags are supported if the caller has set @se_cmd->tag.
+ *
  * Returns non zero to signal active I/O shutdown failure.  All other
  * setup exceptions will be returned as a SCSI CHECK_CONDITION response,
  * but still return zero here.
@@ -1389,7 +1359,7 @@
  * assumes internal allocation of fabric payload buffer by target-core.
  */
 int target_submit_cmd_map_sgls(struct se_cmd *se_cmd, struct se_session *se_sess,
-		unsigned char *cdb, unsigned char *sense, u32 unpacked_lun,
+		unsigned char *cdb, unsigned char *sense, u64 unpacked_lun,
 		u32 data_length, int task_attr, int data_dir, int flags,
 		struct scatterlist *sgl, u32 sgl_count,
 		struct scatterlist *sgl_bidi, u32 sgl_bidi_count,
@@ -1418,7 +1388,7 @@
 	 * for fabrics using TARGET_SCF_ACK_KREF that expect a second
 	 * kref_put() to happen during fabric packet acknowledgement.
 	 */
-	ret = target_get_sess_cmd(se_sess, se_cmd, (flags & TARGET_SCF_ACK_KREF));
+	ret = target_get_sess_cmd(se_cmd, flags & TARGET_SCF_ACK_KREF);
 	if (ret)
 		return ret;
 	/*
@@ -1432,7 +1402,7 @@
 	rc = transport_lookup_cmd_lun(se_cmd, unpacked_lun);
 	if (rc) {
 		transport_send_check_condition_and_sense(se_cmd, rc, 0);
-		target_put_sess_cmd(se_sess, se_cmd);
+		target_put_sess_cmd(se_cmd);
 		return 0;
 	}
 
@@ -1449,6 +1419,7 @@
 	if (sgl_prot_count) {
 		se_cmd->t_prot_sg = sgl_prot;
 		se_cmd->t_prot_nents = sgl_prot_count;
+		se_cmd->se_cmd_flags |= SCF_PASSTHROUGH_PROT_SG_TO_MEM_NOALLOC;
 	}
 
 	/*
@@ -1512,6 +1483,8 @@
  * @data_dir: DMA data direction
  * @flags: flags for command submission from target_sc_flags_tables
  *
+ * Task tags are supported if the caller has set @se_cmd->tag.
+ *
  * Returns non zero to signal active I/O shutdown failure.  All other
  * setup exceptions will be returned as a SCSI CHECK_CONDITION response,
  * but still return zero here.
@@ -1522,7 +1495,7 @@
  * It also assumes interal target core SGL memory allocation.
  */
 int target_submit_cmd(struct se_cmd *se_cmd, struct se_session *se_sess,
-		unsigned char *cdb, unsigned char *sense, u32 unpacked_lun,
+		unsigned char *cdb, unsigned char *sense, u64 unpacked_lun,
 		u32 data_length, int task_attr, int data_dir, int flags)
 {
 	return target_submit_cmd_map_sgls(se_cmd, se_sess, cdb, sense,
@@ -1559,7 +1532,7 @@
  **/
 
 int target_submit_tmr(struct se_cmd *se_cmd, struct se_session *se_sess,
-		unsigned char *sense, u32 unpacked_lun,
+		unsigned char *sense, u64 unpacked_lun,
 		void *fabric_tmr_ptr, unsigned char tm_type,
 		gfp_t gfp, unsigned int tag, int flags)
 {
@@ -1583,7 +1556,7 @@
 		se_cmd->se_tmr_req->ref_task_tag = tag;
 
 	/* See target_submit_cmd for commentary */
-	ret = target_get_sess_cmd(se_sess, se_cmd, (flags & TARGET_SCF_ACK_KREF));
+	ret = target_get_sess_cmd(se_cmd, flags & TARGET_SCF_ACK_KREF);
 	if (ret) {
 		core_tmr_release_req(se_cmd->se_tmr_req);
 		return ret;
@@ -1639,9 +1612,8 @@
 {
 	int ret = 0;
 
-	pr_debug("-----[ Storage Engine Exception for cmd: %p ITT: 0x%08x"
-		" CDB: 0x%02x\n", cmd, cmd->se_tfo->get_task_tag(cmd),
-		cmd->t_task_cdb[0]);
+	pr_debug("-----[ Storage Engine Exception for cmd: %p ITT: 0x%08llx"
+		" CDB: 0x%02x\n", cmd, cmd->tag, cmd->t_task_cdb[0]);
 	pr_debug("-----[ i_state: %d t_state: %d sense_reason: %d\n",
 		cmd->se_tfo->get_cmd_state(cmd),
 		cmd->t_state, sense_reason);
@@ -1698,13 +1670,13 @@
 		 * See spc4r17, section 7.4.6 Control Mode Page, Table 349
 		 */
 		if (cmd->se_sess &&
-		    cmd->se_dev->dev_attrib.emulate_ua_intlck_ctrl == 2)
-			core_scsi3_ua_allocate(cmd->se_sess->se_node_acl,
-				cmd->orig_fe_lun, 0x2C,
-				ASCQ_2CH_PREVIOUS_RESERVATION_CONFLICT_STATUS);
-
+		    cmd->se_dev->dev_attrib.emulate_ua_intlck_ctrl == 2) {
+			target_ua_allocate_lun(cmd->se_sess->se_node_acl,
+					       cmd->orig_fe_lun, 0x2C,
+					ASCQ_2CH_PREVIOUS_RESERVATION_CONFLICT_STATUS);
+		}
 		trace_target_cmd_complete(cmd);
-		ret = cmd->se_tfo-> queue_status(cmd);
+		ret = cmd->se_tfo->queue_status(cmd);
 		if (ret == -EAGAIN || ret == -ENOMEM)
 			goto queue_full;
 		goto check_stop;
@@ -1765,8 +1737,8 @@
 			break;
 
 		sectors = cmd->data_length >> ilog2(cmd->se_dev->dev_attrib.block_size);
-		cmd->pi_err = sbc_dif_verify_write(cmd, cmd->t_task_lba,
-						   sectors, 0, NULL, 0);
+		cmd->pi_err = sbc_dif_verify(cmd, cmd->t_task_lba,
+					     sectors, 0, cmd->t_prot_sg, 0);
 		if (unlikely(cmd->pi_err)) {
 			spin_lock_irq(&cmd->t_state_lock);
 			cmd->transport_state &= ~(CMD_T_BUSY|CMD_T_SENT);
@@ -1849,9 +1821,8 @@
 	 */
 	spin_lock_irq(&cmd->t_state_lock);
 	if (cmd->transport_state & CMD_T_STOP) {
-		pr_debug("%s:%d CMD_T_STOP for ITT: 0x%08x\n",
-			__func__, __LINE__,
-			cmd->se_tfo->get_task_tag(cmd));
+		pr_debug("%s:%d CMD_T_STOP for ITT: 0x%08llx\n",
+			__func__, __LINE__, cmd->tag);
 
 		spin_unlock_irq(&cmd->t_state_lock);
 		complete_all(&cmd->t_transport_stop_comp);
@@ -1990,16 +1961,17 @@
 
 static bool target_read_prot_action(struct se_cmd *cmd)
 {
-	sense_reason_t rc;
-
 	switch (cmd->prot_op) {
 	case TARGET_PROT_DIN_STRIP:
 		if (!(cmd->se_sess->sup_prot_ops & TARGET_PROT_DIN_STRIP)) {
-			rc = sbc_dif_read_strip(cmd);
-			if (rc) {
-				cmd->pi_err = rc;
+			u32 sectors = cmd->data_length >>
+				  ilog2(cmd->se_dev->dev_attrib.block_size);
+
+			cmd->pi_err = sbc_dif_verify(cmd, cmd->t_task_lba,
+						     sectors, 0, cmd->t_prot_sg,
+						     0);
+			if (cmd->pi_err)
 				return true;
-			}
 		}
 		break;
 	case TARGET_PROT_DIN_INSERT:
@@ -2078,12 +2050,8 @@
 queue_rsp:
 	switch (cmd->data_direction) {
 	case DMA_FROM_DEVICE:
-		spin_lock(&cmd->se_lun->lun_sep_lock);
-		if (cmd->se_lun->lun_sep) {
-			cmd->se_lun->lun_sep->sep_stats.tx_data_octets +=
-					cmd->data_length;
-		}
-		spin_unlock(&cmd->se_lun->lun_sep_lock);
+		atomic_long_add(cmd->data_length,
+				&cmd->se_lun->lun_stats.tx_data_octets);
 		/*
 		 * Perform READ_STRIP of PI using software emulation when
 		 * backend had PI enabled, if the transport will not be
@@ -2106,22 +2074,14 @@
 			goto queue_full;
 		break;
 	case DMA_TO_DEVICE:
-		spin_lock(&cmd->se_lun->lun_sep_lock);
-		if (cmd->se_lun->lun_sep) {
-			cmd->se_lun->lun_sep->sep_stats.rx_data_octets +=
-				cmd->data_length;
-		}
-		spin_unlock(&cmd->se_lun->lun_sep_lock);
+		atomic_long_add(cmd->data_length,
+				&cmd->se_lun->lun_stats.rx_data_octets);
 		/*
 		 * Check if we need to send READ payload for BIDI-COMMAND
 		 */
 		if (cmd->se_cmd_flags & SCF_BIDI) {
-			spin_lock(&cmd->se_lun->lun_sep_lock);
-			if (cmd->se_lun->lun_sep) {
-				cmd->se_lun->lun_sep->sep_stats.tx_data_octets +=
-					cmd->data_length;
-			}
-			spin_unlock(&cmd->se_lun->lun_sep_lock);
+			atomic_long_add(cmd->data_length,
+					&cmd->se_lun->lun_stats.tx_data_octets);
 			ret = cmd->se_tfo->queue_data_in(cmd);
 			if (ret == -EAGAIN || ret == -ENOMEM)
 				goto queue_full;
@@ -2178,6 +2138,12 @@
 
 static inline void transport_free_pages(struct se_cmd *cmd)
 {
+	if (!(cmd->se_cmd_flags & SCF_PASSTHROUGH_PROT_SG_TO_MEM_NOALLOC)) {
+		transport_free_sgl(cmd->t_prot_sg, cmd->t_prot_nents);
+		cmd->t_prot_sg = NULL;
+		cmd->t_prot_nents = 0;
+	}
+
 	if (cmd->se_cmd_flags & SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC) {
 		/*
 		 * Release special case READ buffer payload required for
@@ -2201,10 +2167,6 @@
 	transport_free_sgl(cmd->t_bidi_data_sg, cmd->t_bidi_data_nents);
 	cmd->t_bidi_data_sg = NULL;
 	cmd->t_bidi_data_nents = 0;
-
-	transport_free_sgl(cmd->t_prot_sg, cmd->t_prot_nents);
-	cmd->t_prot_sg = NULL;
-	cmd->t_prot_nents = 0;
 }
 
 /**
@@ -2226,7 +2188,7 @@
 	 * If this cmd has been setup with target_get_sess_cmd(), drop
 	 * the kref and call ->release_cmd() in kref callback.
 	 */
-	return target_put_sess_cmd(cmd->se_sess, cmd);
+	return target_put_sess_cmd(cmd);
 }
 
 /**
@@ -2343,6 +2305,14 @@
 	int ret = 0;
 	bool zero_flag = !(cmd->se_cmd_flags & SCF_SCSI_DATA_CDB);
 
+	if (cmd->prot_op != TARGET_PROT_NORMAL &&
+	    !(cmd->se_cmd_flags & SCF_PASSTHROUGH_PROT_SG_TO_MEM_NOALLOC)) {
+		ret = target_alloc_sgl(&cmd->t_prot_sg, &cmd->t_prot_nents,
+				       cmd->prot_length, true);
+		if (ret < 0)
+			return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+	}
+
 	/*
 	 * Determine is the TCM fabric module has already allocated physical
 	 * memory, and is directly calling transport_generic_map_mem_to_cmd()
@@ -2368,14 +2338,6 @@
 				return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 		}
 
-		if (cmd->prot_op != TARGET_PROT_NORMAL) {
-			ret = target_alloc_sgl(&cmd->t_prot_sg,
-					       &cmd->t_prot_nents,
-					       cmd->prot_length, true);
-			if (ret < 0)
-				return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-		}
-
 		ret = target_alloc_sgl(&cmd->t_data_sg, &cmd->t_data_nents,
 				       cmd->data_length, zero_flag);
 		if (ret < 0)
@@ -2470,13 +2432,12 @@
 EXPORT_SYMBOL(transport_generic_free_cmd);
 
 /* target_get_sess_cmd - Add command to active ->sess_cmd_list
- * @se_sess:	session to reference
  * @se_cmd:	command descriptor to add
  * @ack_kref:	Signal that fabric will perform an ack target_put_sess_cmd()
  */
-int target_get_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd,
-			       bool ack_kref)
+int target_get_sess_cmd(struct se_cmd *se_cmd, bool ack_kref)
 {
+	struct se_session *se_sess = se_cmd->se_sess;
 	unsigned long flags;
 	int ret = 0;
 
@@ -2498,7 +2459,7 @@
 	spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 
 	if (ret && ack_kref)
-		target_put_sess_cmd(se_sess, se_cmd);
+		target_put_sess_cmd(se_cmd);
 
 	return ret;
 }
@@ -2527,11 +2488,12 @@
 }
 
 /* target_put_sess_cmd - Check for active I/O shutdown via kref_put
- * @se_sess:	session to reference
  * @se_cmd:	command descriptor to drop
  */
-int target_put_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd)
+int target_put_sess_cmd(struct se_cmd *se_cmd)
 {
+	struct se_session *se_sess = se_cmd->se_sess;
+
 	if (!se_sess) {
 		se_cmd->se_tfo->release_cmd(se_cmd);
 		return 1;
@@ -2597,31 +2559,10 @@
 }
 EXPORT_SYMBOL(target_wait_for_sess_cmds);
 
-static int transport_clear_lun_ref_thread(void *p)
+void transport_clear_lun_ref(struct se_lun *lun)
 {
-	struct se_lun *lun = p;
-
 	percpu_ref_kill(&lun->lun_ref);
-
 	wait_for_completion(&lun->lun_ref_comp);
-	complete(&lun->lun_shutdown_comp);
-
-	return 0;
-}
-
-int transport_clear_lun_ref(struct se_lun *lun)
-{
-	struct task_struct *kt;
-
-	kt = kthread_run(transport_clear_lun_ref_thread, lun,
-			"tcm_cl_%u", lun->unpacked_lun);
-	if (IS_ERR(kt)) {
-		pr_err("Unable to start clear_lun thread\n");
-		return PTR_ERR(kt);
-	}
-	wait_for_completion(&lun->lun_shutdown_comp);
-
-	return 0;
 }
 
 /**
@@ -2655,10 +2596,8 @@
 
 	cmd->transport_state |= CMD_T_STOP;
 
-	pr_debug("wait_for_tasks: Stopping %p ITT: 0x%08x"
-		" i_state: %d, t_state: %d, CMD_T_STOP\n",
-		cmd, cmd->se_tfo->get_task_tag(cmd),
-		cmd->se_tfo->get_cmd_state(cmd), cmd->t_state);
+	pr_debug("wait_for_tasks: Stopping %p ITT: 0x%08llx i_state: %d, t_state: %d, CMD_T_STOP\n",
+		cmd, cmd->tag, cmd->se_tfo->get_cmd_state(cmd), cmd->t_state);
 
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
@@ -2667,9 +2606,8 @@
 	spin_lock_irqsave(&cmd->t_state_lock, flags);
 	cmd->transport_state &= ~(CMD_T_ACTIVE | CMD_T_STOP);
 
-	pr_debug("wait_for_tasks: Stopped wait_for_completion("
-		"&cmd->t_transport_stop_comp) for ITT: 0x%08x\n",
-		cmd->se_tfo->get_task_tag(cmd));
+	pr_debug("wait_for_tasks: Stopped wait_for_completion(&cmd->t_transport_stop_comp) for ITT: 0x%08llx\n",
+		cmd->tag);
 
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
@@ -2971,8 +2909,8 @@
 	if (!send_status || !(cmd->se_cmd_flags & SCF_SEND_DELAYED_TAS))
 		return 1;
 
-	pr_debug("Sending delayed SAM_STAT_TASK_ABORTED status for CDB: 0x%02x ITT: 0x%08x\n",
-		 cmd->t_task_cdb[0], cmd->se_tfo->get_task_tag(cmd));
+	pr_debug("Sending delayed SAM_STAT_TASK_ABORTED status for CDB: 0x%02x ITT: 0x%08llx\n",
+		 cmd->t_task_cdb[0], cmd->tag);
 
 	cmd->se_cmd_flags &= ~SCF_SEND_DELAYED_TAS;
 	cmd->scsi_status = SAM_STAT_TASK_ABORTED;
@@ -3011,9 +2949,8 @@
 
 	transport_lun_remove_cmd(cmd);
 
-	pr_debug("Setting SAM_STAT_TASK_ABORTED status for CDB: 0x%02x,"
-		" ITT: 0x%08x\n", cmd->t_task_cdb[0],
-		cmd->se_tfo->get_task_tag(cmd));
+	pr_debug("Setting SAM_STAT_TASK_ABORTED status for CDB: 0x%02x, ITT: 0x%08llx\n",
+		 cmd->t_task_cdb[0], cmd->tag);
 
 	trace_target_cmd_complete(cmd);
 	cmd->se_tfo->queue_status(cmd);
@@ -3039,6 +2976,11 @@
 		ret = core_tmr_lun_reset(dev, tmr, NULL, NULL);
 		tmr->response = (!ret) ? TMR_FUNCTION_COMPLETE :
 					 TMR_FUNCTION_REJECTED;
+		if (tmr->response == TMR_FUNCTION_COMPLETE) {
+			target_ua_allocate_lun(cmd->se_sess->se_node_acl,
+					       cmd->orig_fe_lun, 0x29,
+					       ASCQ_29H_BUS_DEVICE_RESET_FUNCTION_OCCURRED);
+		}
 		break;
 	case TMR_TARGET_WARM_RESET:
 		tmr->response = TMR_FUNCTION_REJECTED;
@@ -3073,3 +3015,22 @@
 	return 0;
 }
 EXPORT_SYMBOL(transport_generic_handle_tmr);
+
+bool
+target_check_wce(struct se_device *dev)
+{
+	bool wce = false;
+
+	if (dev->transport->get_write_cache)
+		wce = dev->transport->get_write_cache(dev);
+	else if (dev->dev_attrib.emulate_write_cache > 0)
+		wce = true;
+
+	return wce;
+}
+
+bool
+target_check_fua(struct se_device *dev)
+{
+	return target_check_wce(dev) && dev->dev_attrib.emulate_fua_write > 0;
+}
diff --git a/drivers/target/target_core_ua.c b/drivers/target/target_core_ua.c
index e44cc94..be25eb8 100644
--- a/drivers/target/target_core_ua.c
+++ b/drivers/target/target_core_ua.c
@@ -29,7 +29,6 @@
 
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
-#include <target/target_core_configfs.h>
 
 #include "target_core_internal.h"
 #include "target_core_alua.h"
@@ -50,9 +49,17 @@
 	if (!nacl)
 		return 0;
 
-	deve = nacl->device_list[cmd->orig_fe_lun];
-	if (!atomic_read(&deve->ua_count))
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, cmd->orig_fe_lun);
+	if (!deve) {
+		rcu_read_unlock();
 		return 0;
+	}
+	if (!atomic_read(&deve->ua_count)) {
+		rcu_read_unlock();
+		return 0;
+	}
+	rcu_read_unlock();
 	/*
 	 * From sam4r14, section 5.14 Unit attention condition:
 	 *
@@ -79,18 +86,11 @@
 }
 
 int core_scsi3_ua_allocate(
-	struct se_node_acl *nacl,
-	u32 unpacked_lun,
+	struct se_dev_entry *deve,
 	u8 asc,
 	u8 ascq)
 {
-	struct se_dev_entry *deve;
 	struct se_ua *ua, *ua_p, *ua_tmp;
-	/*
-	 * PASSTHROUGH OPS
-	 */
-	if (!nacl)
-		return -EINVAL;
 
 	ua = kmem_cache_zalloc(se_ua_cache, GFP_ATOMIC);
 	if (!ua) {
@@ -99,13 +99,9 @@
 	}
 	INIT_LIST_HEAD(&ua->ua_nacl_list);
 
-	ua->ua_nacl = nacl;
 	ua->ua_asc = asc;
 	ua->ua_ascq = ascq;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	deve = nacl->device_list[unpacked_lun];
-
 	spin_lock(&deve->ua_lock);
 	list_for_each_entry_safe(ua_p, ua_tmp, &deve->ua_list, ua_nacl_list) {
 		/*
@@ -113,7 +109,6 @@
 		 */
 		if ((ua_p->ua_asc == asc) && (ua_p->ua_ascq == ascq)) {
 			spin_unlock(&deve->ua_lock);
-			spin_unlock_irq(&nacl->device_list_lock);
 			kmem_cache_free(se_ua_cache, ua);
 			return 0;
 		}
@@ -158,24 +153,40 @@
 			list_add_tail(&ua->ua_nacl_list,
 				&deve->ua_list);
 		spin_unlock(&deve->ua_lock);
-		spin_unlock_irq(&nacl->device_list_lock);
 
 		atomic_inc_mb(&deve->ua_count);
 		return 0;
 	}
 	list_add_tail(&ua->ua_nacl_list, &deve->ua_list);
 	spin_unlock(&deve->ua_lock);
-	spin_unlock_irq(&nacl->device_list_lock);
 
-	pr_debug("[%s]: Allocated UNIT ATTENTION, mapped LUN: %u, ASC:"
-		" 0x%02x, ASCQ: 0x%02x\n",
-		nacl->se_tpg->se_tpg_tfo->get_fabric_name(), unpacked_lun,
+	pr_debug("Allocated UNIT ATTENTION, mapped LUN: %llu, ASC:"
+		" 0x%02x, ASCQ: 0x%02x\n", deve->mapped_lun,
 		asc, ascq);
 
 	atomic_inc_mb(&deve->ua_count);
 	return 0;
 }
 
+void target_ua_allocate_lun(struct se_node_acl *nacl,
+			    u32 unpacked_lun, u8 asc, u8 ascq)
+{
+	struct se_dev_entry *deve;
+
+	if (!nacl)
+		return;
+
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, unpacked_lun);
+	if (!deve) {
+		rcu_read_unlock();
+		return;
+	}
+
+	core_scsi3_ua_allocate(deve, asc, ascq);
+	rcu_read_unlock();
+}
+
 void core_scsi3_ua_release_all(
 	struct se_dev_entry *deve)
 {
@@ -210,10 +221,14 @@
 	if (!nacl)
 		return;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	deve = nacl->device_list[cmd->orig_fe_lun];
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, cmd->orig_fe_lun);
+	if (!deve) {
+		rcu_read_unlock();
+		return;
+	}
 	if (!atomic_read(&deve->ua_count)) {
-		spin_unlock_irq(&nacl->device_list_lock);
+		rcu_read_unlock();
 		return;
 	}
 	/*
@@ -249,10 +264,10 @@
 		atomic_dec_mb(&deve->ua_count);
 	}
 	spin_unlock(&deve->ua_lock);
-	spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_unlock();
 
 	pr_debug("[%s]: %s UNIT ATTENTION condition with"
-		" INTLCK_CTRL: %d, mapped LUN: %u, got CDB: 0x%02x"
+		" INTLCK_CTRL: %d, mapped LUN: %llu, got CDB: 0x%02x"
 		" reported ASC: 0x%02x, ASCQ: 0x%02x\n",
 		nacl->se_tpg->se_tpg_tfo->get_fabric_name(),
 		(dev->dev_attrib.emulate_ua_intlck_ctrl != 0) ? "Reporting" :
@@ -278,10 +293,14 @@
 	if (!nacl)
 		return -EINVAL;
 
-	spin_lock_irq(&nacl->device_list_lock);
-	deve = nacl->device_list[cmd->orig_fe_lun];
+	rcu_read_lock();
+	deve = target_nacl_find_deve(nacl, cmd->orig_fe_lun);
+	if (!deve) {
+		rcu_read_unlock();
+		return -EINVAL;
+	}
 	if (!atomic_read(&deve->ua_count)) {
-		spin_unlock_irq(&nacl->device_list_lock);
+		rcu_read_unlock();
 		return -EPERM;
 	}
 	/*
@@ -307,10 +326,10 @@
 		atomic_dec_mb(&deve->ua_count);
 	}
 	spin_unlock(&deve->ua_lock);
-	spin_unlock_irq(&nacl->device_list_lock);
+	rcu_read_unlock();
 
 	pr_debug("[%s]: Released UNIT ATTENTION condition, mapped"
-		" LUN: %u, got REQUEST_SENSE reported ASC: 0x%02x,"
+		" LUN: %llu, got REQUEST_SENSE reported ASC: 0x%02x,"
 		" ASCQ: 0x%02x\n", nacl->se_tpg->se_tpg_tfo->get_fabric_name(),
 		cmd->orig_fe_lun, *asc, *ascq);
 
diff --git a/drivers/target/target_core_ua.h b/drivers/target/target_core_ua.h
index a6b56b3..bd6e78b 100644
--- a/drivers/target/target_core_ua.h
+++ b/drivers/target/target_core_ua.h
@@ -25,10 +25,14 @@
 
 #define ASCQ_2CH_PREVIOUS_RESERVATION_CONFLICT_STATUS		0x09
 
+#define ASCQ_3FH_INQUIRY_DATA_HAS_CHANGED			0x03
+#define ASCQ_3FH_REPORTED_LUNS_DATA_HAS_CHANGED			0x0E
+
 extern struct kmem_cache *se_ua_cache;
 
 extern sense_reason_t target_scsi3_ua_check(struct se_cmd *);
-extern int core_scsi3_ua_allocate(struct se_node_acl *, u32, u8, u8);
+extern int core_scsi3_ua_allocate(struct se_dev_entry *, u8, u8);
+extern void target_ua_allocate_lun(struct se_node_acl *, u32, u8, u8);
 extern void core_scsi3_ua_release_all(struct se_dev_entry *);
 extern void core_scsi3_ua_for_check_condition(struct se_cmd *, u8 *, u8 *);
 extern int core_scsi3_ua_clear_for_request_sense(struct se_cmd *,
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 549af98..c448ef4 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -1,6 +1,7 @@
 /*
  * Copyright (C) 2013 Shaohua Li <shli@kernel.org>
  * Copyright (C) 2014 Red Hat, Inc.
+ * Copyright (C) 2015 Arrikto, Inc.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -30,7 +31,6 @@
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
 #include <target/target_core_backend.h>
-#include <target/target_core_backend_configfs.h>
 
 #include <linux/target_core_user.h>
 
@@ -168,6 +168,11 @@
 	tcmu_cmd->tcmu_dev = udev;
 	tcmu_cmd->data_length = se_cmd->data_length;
 
+	if (se_cmd->se_cmd_flags & SCF_BIDI) {
+		BUG_ON(!(se_cmd->t_bidi_data_sg && se_cmd->t_bidi_data_nents));
+		tcmu_cmd->data_length += se_cmd->t_bidi_data_sg->length;
+	}
+
 	tcmu_cmd->deadline = jiffies + msecs_to_jiffies(TCMU_TIME_OUT);
 
 	idr_preload(GFP_KERNEL);
@@ -226,9 +231,106 @@
 
 #define UPDATE_HEAD(head, used, size) smp_store_release(&head, ((head % size) + used) % size)
 
+static void alloc_and_scatter_data_area(struct tcmu_dev *udev,
+	struct scatterlist *data_sg, unsigned int data_nents,
+	struct iovec **iov, int *iov_cnt, bool copy_data)
+{
+	int i;
+	void *from, *to;
+	size_t copy_bytes;
+	struct scatterlist *sg;
+
+	for_each_sg(data_sg, sg, data_nents, i) {
+		copy_bytes = min_t(size_t, sg->length,
+				 head_to_end(udev->data_head, udev->data_size));
+		from = kmap_atomic(sg_page(sg)) + sg->offset;
+		to = (void *) udev->mb_addr + udev->data_off + udev->data_head;
+
+		if (copy_data) {
+			memcpy(to, from, copy_bytes);
+			tcmu_flush_dcache_range(to, copy_bytes);
+		}
+
+		/* Even iov_base is relative to mb_addr */
+		(*iov)->iov_len = copy_bytes;
+		(*iov)->iov_base = (void __user *) udev->data_off +
+						udev->data_head;
+		(*iov_cnt)++;
+		(*iov)++;
+
+		UPDATE_HEAD(udev->data_head, copy_bytes, udev->data_size);
+
+		/* Uh oh, we wrapped the buffer. Must split sg across 2 iovs. */
+		if (sg->length != copy_bytes) {
+			void *from_skip = from + copy_bytes;
+
+			copy_bytes = sg->length - copy_bytes;
+
+			(*iov)->iov_len = copy_bytes;
+			(*iov)->iov_base = (void __user *) udev->data_off +
+							udev->data_head;
+
+			if (copy_data) {
+				to = (void *) udev->mb_addr +
+					udev->data_off + udev->data_head;
+				memcpy(to, from_skip, copy_bytes);
+				tcmu_flush_dcache_range(to, copy_bytes);
+			}
+
+			(*iov_cnt)++;
+			(*iov)++;
+
+			UPDATE_HEAD(udev->data_head,
+				copy_bytes, udev->data_size);
+		}
+
+		kunmap_atomic(from - sg->offset);
+	}
+}
+
+static void gather_and_free_data_area(struct tcmu_dev *udev,
+	struct scatterlist *data_sg, unsigned int data_nents)
+{
+	int i;
+	void *from, *to;
+	size_t copy_bytes;
+	struct scatterlist *sg;
+
+	/* It'd be easier to look at entry's iovec again, but UAM */
+	for_each_sg(data_sg, sg, data_nents, i) {
+		copy_bytes = min_t(size_t, sg->length,
+				 head_to_end(udev->data_tail, udev->data_size));
+
+		to = kmap_atomic(sg_page(sg)) + sg->offset;
+		WARN_ON(sg->length + sg->offset > PAGE_SIZE);
+		from = (void *) udev->mb_addr +
+			udev->data_off + udev->data_tail;
+		tcmu_flush_dcache_range(from, copy_bytes);
+		memcpy(to, from, copy_bytes);
+
+		UPDATE_HEAD(udev->data_tail, copy_bytes, udev->data_size);
+
+		/* Uh oh, wrapped the data buffer for this sg's data */
+		if (sg->length != copy_bytes) {
+			void *to_skip = to + copy_bytes;
+
+			from = (void *) udev->mb_addr +
+				udev->data_off + udev->data_tail;
+			WARN_ON(udev->data_tail);
+			copy_bytes = sg->length - copy_bytes;
+			tcmu_flush_dcache_range(from, copy_bytes);
+			memcpy(to_skip, from, copy_bytes);
+
+			UPDATE_HEAD(udev->data_tail,
+				copy_bytes, udev->data_size);
+		}
+		kunmap_atomic(to - sg->offset);
+	}
+}
+
 /*
- * We can't queue a command until we have space available on the cmd ring *and* space
- * space avail on the data ring.
+ * We can't queue a command until we have space available on the cmd ring *and*
+ * space available on the data ring.
  *
  * Called with ring lock held.
  */
@@ -276,12 +378,11 @@
 	size_t base_command_size, command_size;
 	struct tcmu_mailbox *mb;
 	struct tcmu_cmd_entry *entry;
-	int i;
-	struct scatterlist *sg;
 	struct iovec *iov;
-	int iov_cnt = 0;
+	int iov_cnt;
 	uint32_t cmd_head;
 	uint64_t cdb_off;
+	bool copy_to_data_area;
 
 	if (test_bit(TCMU_DEV_BIT_BROKEN, &udev->flags))
 		return -EINVAL;
@@ -294,7 +395,8 @@
 	 * b/c size == offsetof one-past-element.
 	*/
 	base_command_size = max(offsetof(struct tcmu_cmd_entry,
-					 req.iov[se_cmd->t_data_nents + 2]),
+					 req.iov[se_cmd->t_bidi_data_nents +
+						 se_cmd->t_data_nents + 2]),
 				sizeof(struct tcmu_cmd_entry));
 	command_size = base_command_size
 		+ round_up(scsi_command_size(se_cmd->t_task_cdb), TCMU_OP_ALIGN_SIZE);
@@ -362,53 +464,20 @@
 	 * Fix up iovecs, and handle if allocation in data ring wrapped.
 	 */
 	iov = &entry->req.iov[0];
-	for_each_sg(se_cmd->t_data_sg, sg, se_cmd->t_data_nents, i) {
-		size_t copy_bytes = min((size_t)sg->length,
-				     head_to_end(udev->data_head, udev->data_size));
-		void *from = kmap_atomic(sg_page(sg)) + sg->offset;
-		void *to = (void *) mb + udev->data_off + udev->data_head;
-
-		if (tcmu_cmd->se_cmd->data_direction == DMA_TO_DEVICE) {
-			memcpy(to, from, copy_bytes);
-			tcmu_flush_dcache_range(to, copy_bytes);
-		}
-
-		/* Even iov_base is relative to mb_addr */
-		iov->iov_len = copy_bytes;
-		iov->iov_base = (void __user *) udev->data_off +
-						udev->data_head;
-		iov_cnt++;
-		iov++;
-
-		UPDATE_HEAD(udev->data_head, copy_bytes, udev->data_size);
-
-		/* Uh oh, we wrapped the buffer. Must split sg across 2 iovs. */
-		if (sg->length != copy_bytes) {
-			from += copy_bytes;
-			copy_bytes = sg->length - copy_bytes;
-
-			iov->iov_len = copy_bytes;
-			iov->iov_base = (void __user *) udev->data_off +
-							udev->data_head;
-
-			if (se_cmd->data_direction == DMA_TO_DEVICE) {
-				to = (void *) mb + udev->data_off + udev->data_head;
-				memcpy(to, from, copy_bytes);
-				tcmu_flush_dcache_range(to, copy_bytes);
-			}
-
-			iov_cnt++;
-			iov++;
-
-			UPDATE_HEAD(udev->data_head, copy_bytes, udev->data_size);
-		}
-
-		kunmap_atomic(from);
-	}
+	iov_cnt = 0;
+	copy_to_data_area = (se_cmd->data_direction == DMA_TO_DEVICE
+		|| se_cmd->se_cmd_flags & SCF_BIDI);
+	alloc_and_scatter_data_area(udev, se_cmd->t_data_sg,
+		se_cmd->t_data_nents, &iov, &iov_cnt, copy_to_data_area);
 	entry->req.iov_cnt = iov_cnt;
-	entry->req.iov_bidi_cnt = 0;
 	entry->req.iov_dif_cnt = 0;
 
+	/* Handle BIDI commands */
+	iov_cnt = 0;
+	alloc_and_scatter_data_area(udev, se_cmd->t_bidi_data_sg,
+		se_cmd->t_bidi_data_nents, &iov, &iov_cnt, false);
+	entry->req.iov_bidi_cnt = iov_cnt;
+
 	/* All offsets relative to mb_addr, not start of entry! */
 	cdb_off = CMDR_OFF + cmd_head + base_command_size;
 	memcpy((void *) mb + cdb_off, se_cmd->t_task_cdb, scsi_command_size(se_cmd->t_task_cdb));
@@ -481,47 +550,22 @@
 			       se_cmd->scsi_sense_length);
 
 		UPDATE_HEAD(udev->data_tail, cmd->data_length, udev->data_size);
-	}
-	else if (se_cmd->data_direction == DMA_FROM_DEVICE) {
-		struct scatterlist *sg;
-		int i;
+	} else if (se_cmd->se_cmd_flags & SCF_BIDI) {
+		/* Discard data_out buffer */
+		UPDATE_HEAD(udev->data_tail,
+			(size_t)se_cmd->t_data_sg->length, udev->data_size);
 
-		/* It'd be easier to look at entry's iovec again, but UAM */
-		for_each_sg(se_cmd->t_data_sg, sg, se_cmd->t_data_nents, i) {
-			size_t copy_bytes;
-			void *to;
-			void *from;
-
-			copy_bytes = min((size_t)sg->length,
-					 head_to_end(udev->data_tail, udev->data_size));
-
-			to = kmap_atomic(sg_page(sg)) + sg->offset;
-			WARN_ON(sg->length + sg->offset > PAGE_SIZE);
-			from = (void *) udev->mb_addr + udev->data_off + udev->data_tail;
-			tcmu_flush_dcache_range(from, copy_bytes);
-			memcpy(to, from, copy_bytes);
-
-			UPDATE_HEAD(udev->data_tail, copy_bytes, udev->data_size);
-
-			/* Uh oh, wrapped the data buffer for this sg's data */
-			if (sg->length != copy_bytes) {
-				from = (void *) udev->mb_addr + udev->data_off + udev->data_tail;
-				WARN_ON(udev->data_tail);
-				to += copy_bytes;
-				copy_bytes = sg->length - copy_bytes;
-				tcmu_flush_dcache_range(from, copy_bytes);
-				memcpy(to, from, copy_bytes);
-
-				UPDATE_HEAD(udev->data_tail, copy_bytes, udev->data_size);
-			}
-
-			kunmap_atomic(to);
-		}
-
+		/* Get Data-In buffer */
+		gather_and_free_data_area(udev,
+			se_cmd->t_bidi_data_sg, se_cmd->t_bidi_data_nents);
+	} else if (se_cmd->data_direction == DMA_FROM_DEVICE) {
+		gather_and_free_data_area(udev,
+			se_cmd->t_data_sg, se_cmd->t_data_nents);
 	} else if (se_cmd->data_direction == DMA_TO_DEVICE) {
 		UPDATE_HEAD(udev->data_tail, cmd->data_length, udev->data_size);
-	} else {
-		pr_warn("TCMU: data direction was %d!\n", se_cmd->data_direction);
+	} else if (se_cmd->data_direction != DMA_NONE) {
+		pr_warn("TCMU: data direction was %d!\n",
+			se_cmd->data_direction);
 	}
 
 	target_complete_cmd(cmd->se_cmd, entry->rsp.scsi_status);
@@ -910,6 +954,14 @@
 	return -EINVAL;
 }
 
+static void tcmu_dev_call_rcu(struct rcu_head *p)
+{
+	struct se_device *dev = container_of(p, struct se_device, rcu_head);
+	struct tcmu_dev *udev = TCMU_DEV(dev);
+
+	kfree(udev);
+}
+
 static void tcmu_free_device(struct se_device *dev)
 {
 	struct tcmu_dev *udev = TCMU_DEV(dev);
@@ -935,8 +987,7 @@
 		kfree(udev->uio_info.name);
 		kfree(udev->name);
 	}
-
-	kfree(udev);
+	call_rcu(&dev->rcu_head, tcmu_dev_call_rcu);
 }
 
 enum {
@@ -1054,27 +1105,7 @@
 	return passthrough_parse_cdb(cmd, tcmu_pass_op);
 }
 
-DEF_TB_DEV_ATTRIB_RO(tcmu, hw_pi_prot_type);
-TB_DEV_ATTR_RO(tcmu, hw_pi_prot_type);
-
-DEF_TB_DEV_ATTRIB_RO(tcmu, hw_block_size);
-TB_DEV_ATTR_RO(tcmu, hw_block_size);
-
-DEF_TB_DEV_ATTRIB_RO(tcmu, hw_max_sectors);
-TB_DEV_ATTR_RO(tcmu, hw_max_sectors);
-
-DEF_TB_DEV_ATTRIB_RO(tcmu, hw_queue_depth);
-TB_DEV_ATTR_RO(tcmu, hw_queue_depth);
-
-static struct configfs_attribute *tcmu_backend_dev_attrs[] = {
-	&tcmu_dev_attrib_hw_pi_prot_type.attr,
-	&tcmu_dev_attrib_hw_block_size.attr,
-	&tcmu_dev_attrib_hw_max_sectors.attr,
-	&tcmu_dev_attrib_hw_queue_depth.attr,
-	NULL,
-};
-
-static struct se_subsystem_api tcmu_template = {
+static const struct target_backend_ops tcmu_ops = {
 	.name			= "user",
 	.inquiry_prod		= "USER",
 	.inquiry_rev		= TCMU_VERSION,
@@ -1090,11 +1121,11 @@
 	.show_configfs_dev_params = tcmu_show_configfs_dev_params,
 	.get_device_type	= sbc_get_device_type,
 	.get_blocks		= tcmu_get_blocks,
+	.tb_dev_attrib_attrs	= passthrough_attrib_attrs,
 };
 
 static int __init tcmu_module_init(void)
 {
-	struct target_backend_cits *tbc = &tcmu_template.tb_cits;
 	int ret;
 
 	BUILD_BUG_ON((sizeof(struct tcmu_cmd_entry) % TCMU_OP_ALIGN_SIZE) != 0);
@@ -1117,10 +1148,7 @@
 		goto out_unreg_device;
 	}
 
-	target_core_setup_sub_cits(&tcmu_template);
-	tbc->tb_dev_attrib_cit.ct_attrs = tcmu_backend_dev_attrs;
-
-	ret = transport_subsystem_register(&tcmu_template);
+	ret = transport_backend_register(&tcmu_ops);
 	if (ret)
 		goto out_unreg_genl;
 
@@ -1138,7 +1166,7 @@
 
 static void __exit tcmu_module_exit(void)
 {
-	transport_subsystem_release(&tcmu_template);
+	target_backend_unregister(&tcmu_ops);
 	genl_unregister_family(&tcmu_genl_family);
 	root_device_unregister(tcmu_root_device);
 	kmem_cache_destroy(tcmu_cmd_cache);
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index 5ec0d00..4515f52 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -31,7 +31,6 @@
 #include <target/target_core_base.h>
 #include <target/target_core_backend.h>
 #include <target/target_core_fabric.h>
-#include <target/target_core_configfs.h>
 
 #include "target_core_internal.h"
 #include "target_core_pr.h"
@@ -348,8 +347,7 @@
 	unsigned char sense_buffer[TRANSPORT_SENSE_BUFFER];
 };
 
-static struct se_port xcopy_pt_port;
-static struct se_portal_group xcopy_pt_tpg;
+struct se_portal_group xcopy_pt_tpg;
 static struct se_session xcopy_pt_sess;
 static struct se_node_acl xcopy_pt_nacl;
 
@@ -358,11 +356,6 @@
         return "xcopy-pt";
 }
 
-static u32 xcopy_pt_get_tag(struct se_cmd *se_cmd)
-{
-        return 0;
-}
-
 static int xcopy_pt_get_cmd_state(struct se_cmd *se_cmd)
 {
         return 0;
@@ -423,7 +416,6 @@
 
 static const struct target_core_fabric_ops xcopy_pt_tfo = {
 	.get_fabric_name	= xcopy_pt_get_fabric_name,
-	.get_task_tag		= xcopy_pt_get_tag,
 	.get_cmd_state		= xcopy_pt_get_cmd_state,
 	.release_cmd		= xcopy_pt_release_cmd,
 	.check_stop_free	= xcopy_pt_check_stop_free,
@@ -445,17 +437,11 @@
 		return -ENOMEM;
 	}
 
-	memset(&xcopy_pt_port, 0, sizeof(struct se_port));
-	INIT_LIST_HEAD(&xcopy_pt_port.sep_alua_list);
-	INIT_LIST_HEAD(&xcopy_pt_port.sep_list);
-	mutex_init(&xcopy_pt_port.sep_tg_pt_md_mutex);
-
 	memset(&xcopy_pt_tpg, 0, sizeof(struct se_portal_group));
 	INIT_LIST_HEAD(&xcopy_pt_tpg.se_tpg_node);
 	INIT_LIST_HEAD(&xcopy_pt_tpg.acl_node_list);
 	INIT_LIST_HEAD(&xcopy_pt_tpg.tpg_sess_list);
 
-	xcopy_pt_port.sep_tpg = &xcopy_pt_tpg;
 	xcopy_pt_tpg.se_tpg_tfo = &xcopy_pt_tfo;
 
 	memset(&xcopy_pt_nacl, 0, sizeof(struct se_node_acl));
@@ -496,10 +482,6 @@
 		 */
 		if (remote_port) {
 			xpt_cmd->remote_port = remote_port;
-			pt_cmd->se_lun->lun_sep = &xcopy_pt_port;
-			pr_debug("Setup emulated remote DEST xcopy_pt_port: %p to"
-				" cmd->se_lun->lun_sep for X-COPY data PUSH\n",
-				pt_cmd->se_lun->lun_sep);
 		} else {
 			pt_cmd->se_lun = ec_cmd->se_lun;
 			pt_cmd->se_dev = ec_cmd->se_dev;
@@ -519,10 +501,6 @@
 		 */
 		if (remote_port) {
 			xpt_cmd->remote_port = remote_port;
-			pt_cmd->se_lun->lun_sep = &xcopy_pt_port;
-			pr_debug("Setup emulated remote SRC xcopy_pt_port: %p to"
-				" cmd->se_lun->lun_sep for X-COPY data PULL\n",
-				pt_cmd->se_lun->lun_sep);
 		} else {
 			pt_cmd->se_lun = ec_cmd->se_lun;
 			pt_cmd->se_dev = ec_cmd->se_dev;
@@ -574,6 +552,7 @@
 	xpt_cmd->xcopy_op = xop;
 	target_xcopy_setup_pt_port(xpt_cmd, xop, remote_port);
 
+	cmd->tag = 0;
 	sense_rc = target_setup_cmd_from_cdb(cmd, cdb);
 	if (sense_rc) {
 		ret = -EINVAL;
diff --git a/drivers/target/tcm_fc/tcm_fc.h b/drivers/target/tcm_fc/tcm_fc.h
index 881deb3..39909da 100644
--- a/drivers/target/tcm_fc/tcm_fc.h
+++ b/drivers/target/tcm_fc/tcm_fc.h
@@ -80,8 +80,8 @@
  * Node ACL for FC remote port session.
  */
 struct ft_node_acl {
-	struct ft_node_auth node_auth;
 	struct se_node_acl se_node_acl;
+	struct ft_node_auth node_auth;
 };
 
 struct ft_lun {
@@ -157,7 +157,6 @@
 int ft_queue_data_in(struct se_cmd *);
 int ft_write_pending(struct se_cmd *);
 int ft_write_pending_status(struct se_cmd *);
-u32 ft_get_task_tag(struct se_cmd *);
 int ft_get_cmd_state(struct se_cmd *);
 void ft_queue_tm_resp(struct se_cmd *);
 void ft_aborted_task(struct se_cmd *);
diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c
index 1bf78e7..6803172 100644
--- a/drivers/target/tcm_fc/tfc_cmd.c
+++ b/drivers/target/tcm_fc/tfc_cmd.c
@@ -36,7 +36,6 @@
 
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
-#include <target/target_core_configfs.h>
 #include <target/configfs_macros.h>
 
 #include "tcm_fc.h"
@@ -243,15 +242,6 @@
 	return 0;
 }
 
-u32 ft_get_task_tag(struct se_cmd *se_cmd)
-{
-	struct ft_cmd *cmd = container_of(se_cmd, struct ft_cmd, se_cmd);
-
-	if (cmd->aborted)
-		return ~0;
-	return fc_seq_exch(cmd->seq)->rxid;
-}
-
 int ft_get_cmd_state(struct se_cmd *se_cmd)
 {
 	return 0;
@@ -564,6 +554,7 @@
 	}
 
 	fc_seq_exch(cmd->seq)->lp->tt.seq_set_resp(cmd->seq, ft_recv_seq, cmd);
+	cmd->se_cmd.tag = fc_seq_exch(cmd->seq)->rxid;
 	/*
 	 * Use a single se_cmd->cmd_kref as we expect to release se_cmd
 	 * directly from ft_check_stop_free callback in response path.
diff --git a/drivers/target/tcm_fc/tfc_conf.c b/drivers/target/tcm_fc/tfc_conf.c
index 86b699b..1667093 100644
--- a/drivers/target/tcm_fc/tfc_conf.c
+++ b/drivers/target/tcm_fc/tfc_conf.c
@@ -39,13 +39,10 @@
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
 #include <target/target_core_fabric_configfs.h>
-#include <target/target_core_configfs.h>
 #include <target/configfs_macros.h>
 
 #include "tcm_fc.h"
 
-static const struct target_core_fabric_ops ft_fabric_ops;
-
 static LIST_HEAD(ft_wwn_list);
 DEFINE_MUTEX(ft_lport_lock);
 
@@ -194,48 +191,17 @@
  * Add ACL for an initiator.  The ACL is named arbitrarily.
  * The port_name and/or node_name are attributes.
  */
-static struct se_node_acl *ft_add_acl(
-	struct se_portal_group *se_tpg,
-	struct config_group *group,
-	const char *name)
+static int ft_init_nodeacl(struct se_node_acl *nacl, const char *name)
 {
-	struct ft_node_acl *acl;
-	struct ft_tpg *tpg;
+	struct ft_node_acl *acl =
+		container_of(nacl, struct ft_node_acl, se_node_acl);
 	u64 wwpn;
-	u32 q_depth;
-
-	pr_debug("add acl %s\n", name);
-	tpg = container_of(se_tpg, struct ft_tpg, se_tpg);
 
 	if (ft_parse_wwn(name, &wwpn, 1) < 0)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
-	acl = kzalloc(sizeof(struct ft_node_acl), GFP_KERNEL);
-	if (!acl)
-		return ERR_PTR(-ENOMEM);
 	acl->node_auth.port_name = wwpn;
-
-	q_depth = 32;		/* XXX bogus default - get from tpg? */
-	return core_tpg_add_initiator_node_acl(&tpg->se_tpg,
-				&acl->se_node_acl, name, q_depth);
-}
-
-static void ft_del_acl(struct se_node_acl *se_acl)
-{
-	struct se_portal_group *se_tpg = se_acl->se_tpg;
-	struct ft_tpg *tpg;
-	struct ft_node_acl *acl = container_of(se_acl,
-				struct ft_node_acl, se_node_acl);
-
-	pr_debug("del acl %s\n",
-		config_item_name(&se_acl->acl_group.cg_item));
-
-	tpg = container_of(se_tpg, struct ft_tpg, se_tpg);
-	pr_debug("del acl %p se_acl %p tpg %p se_tpg %p\n",
-		    acl, se_acl, tpg, &tpg->se_tpg);
-
-	core_tpg_del_initiator_node_acl(&tpg->se_tpg, se_acl, 1);
-	kfree(acl);
+	return 0;
 }
 
 struct ft_node_acl *ft_acl_get(struct ft_tpg *tpg, struct fc_rport_priv *rdata)
@@ -245,7 +211,7 @@
 	struct se_portal_group *se_tpg = &tpg->se_tpg;
 	struct se_node_acl *se_acl;
 
-	spin_lock_irq(&se_tpg->acl_node_lock);
+	mutex_lock(&se_tpg->acl_node_mutex);
 	list_for_each_entry(se_acl, &se_tpg->acl_node_list, acl_list) {
 		acl = container_of(se_acl, struct ft_node_acl, se_node_acl);
 		pr_debug("acl %p port_name %llx\n",
@@ -259,33 +225,10 @@
 			break;
 		}
 	}
-	spin_unlock_irq(&se_tpg->acl_node_lock);
+	mutex_unlock(&se_tpg->acl_node_mutex);
 	return found;
 }
 
-static struct se_node_acl *ft_tpg_alloc_fabric_acl(struct se_portal_group *se_tpg)
-{
-	struct ft_node_acl *acl;
-
-	acl = kzalloc(sizeof(*acl), GFP_KERNEL);
-	if (!acl) {
-		pr_err("Unable to allocate struct ft_node_acl\n");
-		return NULL;
-	}
-	pr_debug("acl %p\n", acl);
-	return &acl->se_node_acl;
-}
-
-static void ft_tpg_release_fabric_acl(struct se_portal_group *se_tpg,
-				      struct se_node_acl *se_acl)
-{
-	struct ft_node_acl *acl = container_of(se_acl,
-				struct ft_node_acl, se_node_acl);
-
-	pr_debug("acl %p\n", acl);
-	kfree(acl);
-}
-
 /*
  * local_port port_group (tpg) ops.
  */
@@ -333,8 +276,7 @@
 		return NULL;
 	}
 
-	ret = core_tpg_register(&ft_fabric_ops, wwn, &tpg->se_tpg,
-				tpg, TRANSPORT_TPG_TYPE_NORMAL);
+	ret = core_tpg_register(wwn, &tpg->se_tpg, SCSI_PROTOCOL_FCP);
 	if (ret < 0) {
 		destroy_workqueue(wq);
 		kfree(tpg);
@@ -459,6 +401,11 @@
 	NULL,
 };
 
+static inline struct ft_tpg *ft_tpg(struct se_portal_group *se_tpg)
+{
+	return container_of(se_tpg, struct ft_tpg, se_tpg);
+}
+
 static char *ft_get_fabric_name(void)
 {
 	return "fc";
@@ -466,25 +413,16 @@
 
 static char *ft_get_fabric_wwn(struct se_portal_group *se_tpg)
 {
-	struct ft_tpg *tpg = se_tpg->se_tpg_fabric_ptr;
-
-	return tpg->lport_wwn->name;
+	return ft_tpg(se_tpg)->lport_wwn->name;
 }
 
 static u16 ft_get_tag(struct se_portal_group *se_tpg)
 {
-	struct ft_tpg *tpg = se_tpg->se_tpg_fabric_ptr;
-
 	/*
 	 * This tag is used when forming SCSI Name identifier in EVPD=1 0x83
 	 * to represent the SCSI Target Port.
 	 */
-	return tpg->index;
-}
-
-static u32 ft_get_default_depth(struct se_portal_group *se_tpg)
-{
-	return 1;
+	return ft_tpg(se_tpg)->index;
 }
 
 static int ft_check_false(struct se_portal_group *se_tpg)
@@ -498,28 +436,20 @@
 
 static u32 ft_tpg_get_inst_index(struct se_portal_group *se_tpg)
 {
-	struct ft_tpg *tpg = se_tpg->se_tpg_fabric_ptr;
-
-	return tpg->index;
+	return ft_tpg(se_tpg)->index;
 }
 
 static const struct target_core_fabric_ops ft_fabric_ops = {
 	.module =			THIS_MODULE,
 	.name =				"fc",
+	.node_acl_size =		sizeof(struct ft_node_acl),
 	.get_fabric_name =		ft_get_fabric_name,
-	.get_fabric_proto_ident =	fc_get_fabric_proto_ident,
 	.tpg_get_wwn =			ft_get_fabric_wwn,
 	.tpg_get_tag =			ft_get_tag,
-	.tpg_get_default_depth =	ft_get_default_depth,
-	.tpg_get_pr_transport_id =	fc_get_pr_transport_id,
-	.tpg_get_pr_transport_id_len =	fc_get_pr_transport_id_len,
-	.tpg_parse_pr_out_transport_id = fc_parse_pr_out_transport_id,
 	.tpg_check_demo_mode =		ft_check_false,
 	.tpg_check_demo_mode_cache =	ft_check_false,
 	.tpg_check_demo_mode_write_protect = ft_check_false,
 	.tpg_check_prod_mode_write_protect = ft_check_false,
-	.tpg_alloc_fabric_acl =		ft_tpg_alloc_fabric_acl,
-	.tpg_release_fabric_acl =	ft_tpg_release_fabric_acl,
 	.tpg_get_inst_index =		ft_tpg_get_inst_index,
 	.check_stop_free =		ft_check_stop_free,
 	.release_cmd =			ft_release_cmd,
@@ -530,7 +460,6 @@
 	.write_pending =		ft_write_pending,
 	.write_pending_status =		ft_write_pending_status,
 	.set_default_node_attributes =	ft_set_default_node_attr,
-	.get_task_tag =			ft_get_task_tag,
 	.get_cmd_state =		ft_get_cmd_state,
 	.queue_data_in =		ft_queue_data_in,
 	.queue_status =			ft_queue_status,
@@ -544,12 +473,7 @@
 	.fabric_drop_wwn =		&ft_del_wwn,
 	.fabric_make_tpg =		&ft_add_tpg,
 	.fabric_drop_tpg =		&ft_del_tpg,
-	.fabric_post_link =		NULL,
-	.fabric_pre_unlink =		NULL,
-	.fabric_make_np =		NULL,
-	.fabric_drop_np =		NULL,
-	.fabric_make_nodeacl =		&ft_add_acl,
-	.fabric_drop_nodeacl =		&ft_del_acl,
+	.fabric_init_nodeacl =		&ft_init_nodeacl,
 
 	.tfc_wwn_attrs			= ft_wwn_attrs,
 	.tfc_tpg_nacl_base_attrs	= ft_nacl_base_attrs,
diff --git a/drivers/target/tcm_fc/tfc_io.c b/drivers/target/tcm_fc/tfc_io.c
index fe585d1..4b0fedd 100644
--- a/drivers/target/tcm_fc/tfc_io.c
+++ b/drivers/target/tcm_fc/tfc_io.c
@@ -44,7 +44,6 @@
 
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
-#include <target/target_core_configfs.h>
 #include <target/configfs_macros.h>
 
 #include "tcm_fc.h"
diff --git a/drivers/target/tcm_fc/tfc_sess.c b/drivers/target/tcm_fc/tfc_sess.c
index f2a616d..31a9e3f 100644
--- a/drivers/target/tcm_fc/tfc_sess.c
+++ b/drivers/target/tcm_fc/tfc_sess.c
@@ -36,7 +36,6 @@
 
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
-#include <target/target_core_configfs.h>
 #include <target/configfs_macros.h>
 
 #include "tcm_fc.h"
diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c
index 2e67161..5820e85 100644
--- a/drivers/thermal/intel_powerclamp.c
+++ b/drivers/thermal/intel_powerclamp.c
@@ -119,7 +119,7 @@
 	return ret;
 }
 
-static struct kernel_param_ops duration_ops = {
+static const struct kernel_param_ops duration_ops = {
 	.set = duration_set,
 	.get = param_get_int,
 };
@@ -167,7 +167,7 @@
 	return ret;
 }
 
-static struct kernel_param_ops window_size_ops = {
+static const struct kernel_param_ops window_size_ops = {
 	.set = window_size_set,
 	.get = param_get_int,
 };
diff --git a/drivers/tty/hvc/hvc_iucv.c b/drivers/tty/hvc/hvc_iucv.c
index f78a87b..bb809cf 100644
--- a/drivers/tty/hvc/hvc_iucv.c
+++ b/drivers/tty/hvc/hvc_iucv.c
@@ -1345,7 +1345,7 @@
 
 #define param_check_vmidfilter(name, p) __param_check(name, p, void)
 
-static struct kernel_param_ops param_ops_vmidfilter = {
+static const struct kernel_param_ops param_ops_vmidfilter = {
 	.set = param_set_vmidfilter,
 	.get = param_get_vmidfilter,
 };
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index 7a3d146..a9d837f 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -302,7 +302,7 @@
 static void xen_console_update_evtchn(struct xencons_info *info)
 {
 	if (xen_hvm_domain()) {
-		uint64_t v;
+		uint64_t v = 0;
 		int err;
 
 		err = hvm_get_parameter(HVM_PARAM_CONSOLE_EVTCHN, &v);
diff --git a/drivers/tty/metag_da.c b/drivers/tty/metag_da.c
index 3774600..9325262 100644
--- a/drivers/tty/metag_da.c
+++ b/drivers/tty/metag_da.c
@@ -640,25 +640,7 @@
 	put_tty_driver(channel_driver);
 	return ret;
 }
-
-static void dashtty_exit(void)
-{
-	int nport;
-	struct dashtty_port *dport;
-
-	del_timer_sync(&put_timer);
-	kthread_stop(dashtty_thread);
-	del_timer_sync(&poll_timer);
-	tty_unregister_driver(channel_driver);
-	for (nport = 0; nport < NUM_TTY_CHANNELS; nport++) {
-		dport = &dashtty_ports[nport];
-		tty_port_destroy(&dport->port);
-	}
-	put_tty_driver(channel_driver);
-}
-
-module_init(dashtty_init);
-module_exit(dashtty_exit);
+device_initcall(dashtty_init);
 
 #ifdef CONFIG_DA_CONSOLE
 
diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c
index 9782043..d75a66c 100644
--- a/drivers/tty/serial/8250/8250_omap.c
+++ b/drivers/tty/serial/8250/8250_omap.c
@@ -22,6 +22,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/console.h>
 #include <linux/pm_qos.h>
+#include <linux/pm_wakeirq.h>
 #include <linux/dma-mapping.h>
 
 #include "8250.h"
@@ -552,17 +553,6 @@
 	pm_qos_update_request(&priv->pm_qos_request, priv->latency);
 }
 
-static irqreturn_t omap_wake_irq(int irq, void *dev_id)
-{
-	struct uart_port *port = dev_id;
-	int ret;
-
-	ret = port->handle_irq(port);
-	if (ret)
-		return IRQ_HANDLED;
-	return IRQ_NONE;
-}
-
 #ifdef CONFIG_SERIAL_8250_DMA
 static int omap_8250_dma_handle_irq(struct uart_port *port);
 #endif
@@ -596,11 +586,9 @@
 	int ret;
 
 	if (priv->wakeirq) {
-		ret = request_irq(priv->wakeirq, omap_wake_irq,
-				  port->irqflags, "uart wakeup irq", port);
+		ret = dev_pm_set_dedicated_wake_irq(port->dev, priv->wakeirq);
 		if (ret)
 			return ret;
-		disable_irq(priv->wakeirq);
 	}
 
 	pm_runtime_get_sync(port->dev);
@@ -649,8 +637,7 @@
 err:
 	pm_runtime_mark_last_busy(port->dev);
 	pm_runtime_put_autosuspend(port->dev);
-	if (priv->wakeirq)
-		free_irq(priv->wakeirq, port);
+	dev_pm_clear_wake_irq(port->dev);
 	return ret;
 }
 
@@ -682,10 +669,8 @@
 
 	pm_runtime_mark_last_busy(port->dev);
 	pm_runtime_put_autosuspend(port->dev);
-
 	free_irq(port->irq, port);
-	if (priv->wakeirq)
-		free_irq(priv->wakeirq, port);
+	dev_pm_clear_wake_irq(port->dev);
 }
 
 static void omap_8250_throttle(struct uart_port *port)
@@ -1226,31 +1211,6 @@
 	return 0;
 }
 
-#ifdef CONFIG_PM
-
-static inline void omap8250_enable_wakeirq(struct omap8250_priv *priv,
-					   bool enable)
-{
-	if (!priv->wakeirq)
-		return;
-
-	if (enable)
-		enable_irq(priv->wakeirq);
-	else
-		disable_irq_nosync(priv->wakeirq);
-}
-
-static void omap8250_enable_wakeup(struct omap8250_priv *priv,
-				   bool enable)
-{
-	if (enable == priv->wakeups_enabled)
-		return;
-
-	omap8250_enable_wakeirq(priv, enable);
-	priv->wakeups_enabled = enable;
-}
-#endif
-
 #ifdef CONFIG_PM_SLEEP
 static int omap8250_prepare(struct device *dev)
 {
@@ -1277,11 +1237,6 @@
 
 	serial8250_suspend_port(priv->line);
 	flush_work(&priv->qos_work);
-
-	if (device_may_wakeup(dev))
-		omap8250_enable_wakeup(priv, true);
-	else
-		omap8250_enable_wakeup(priv, false);
 	return 0;
 }
 
@@ -1289,9 +1244,6 @@
 {
 	struct omap8250_priv *priv = dev_get_drvdata(dev);
 
-	if (device_may_wakeup(dev))
-		omap8250_enable_wakeup(priv, false);
-
 	serial8250_resume_port(priv->line);
 	return 0;
 }
@@ -1333,7 +1285,6 @@
 			return -EBUSY;
 	}
 
-	omap8250_enable_wakeup(priv, true);
 	if (up->dma)
 		omap_8250_rx_dma(up, UART_IIR_RX_TIMEOUT);
 
@@ -1354,7 +1305,6 @@
 		return 0;
 
 	up = serial8250_get_port(priv->line);
-	omap8250_enable_wakeup(priv, false);
 	loss_cntx = omap8250_lost_context(up);
 
 	if (loss_cntx)
diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c
index 7f49172..7a2172b 100644
--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -38,6 +38,7 @@
 #include <linux/serial_core.h>
 #include <linux/irq.h>
 #include <linux/pm_runtime.h>
+#include <linux/pm_wakeirq.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/gpio.h>
@@ -160,7 +161,6 @@
 	unsigned long		port_activity;
 	int			context_loss_cnt;
 	u32			errata;
-	u8			wakeups_enabled;
 	u32			features;
 
 	int			rts_gpio;
@@ -209,28 +209,11 @@
 	return pdata->get_context_loss_count(up->dev);
 }
 
-static inline void serial_omap_enable_wakeirq(struct uart_omap_port *up,
-				       bool enable)
-{
-	if (!up->wakeirq)
-		return;
-
-	if (enable)
-		enable_irq(up->wakeirq);
-	else
-		disable_irq_nosync(up->wakeirq);
-}
-
+/* REVISIT: Remove this when omap3 boots in device tree only mode */
 static void serial_omap_enable_wakeup(struct uart_omap_port *up, bool enable)
 {
 	struct omap_uart_port_info *pdata = dev_get_platdata(up->dev);
 
-	if (enable == up->wakeups_enabled)
-		return;
-
-	serial_omap_enable_wakeirq(up, enable);
-	up->wakeups_enabled = enable;
-
 	if (!pdata || !pdata->enable_wakeup)
 		return;
 
@@ -750,13 +733,11 @@
 
 	/* Optional wake-up IRQ */
 	if (up->wakeirq) {
-		retval = request_irq(up->wakeirq, serial_omap_irq,
-				     up->port.irqflags, up->name, up);
+		retval = dev_pm_set_dedicated_wake_irq(up->dev, up->wakeirq);
 		if (retval) {
 			free_irq(up->port.irq, up);
 			return retval;
 		}
-		disable_irq(up->wakeirq);
 	}
 
 	dev_dbg(up->port.dev, "serial_omap_startup+%d\n", up->port.line);
@@ -845,8 +826,7 @@
 	pm_runtime_mark_last_busy(up->dev);
 	pm_runtime_put_autosuspend(up->dev);
 	free_irq(up->port.irq, up);
-	if (up->wakeirq)
-		free_irq(up->wakeirq, up);
+	dev_pm_clear_wake_irq(up->dev);
 }
 
 static void serial_omap_uart_qos_work(struct work_struct *work)
@@ -1139,13 +1119,6 @@
 	serial_out(up, UART_EFR, efr);
 	serial_out(up, UART_LCR, 0);
 
-	if (!device_may_wakeup(up->dev)) {
-		if (!state)
-			pm_runtime_forbid(up->dev);
-		else
-			pm_runtime_allow(up->dev);
-	}
-
 	pm_runtime_mark_last_busy(up->dev);
 	pm_runtime_put_autosuspend(up->dev);
 }
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 2847108..b5b4278 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -988,7 +988,7 @@
 	return 0;
 }
 
-static struct kernel_param_ops param_ops_sysrq_reset_seq = {
+static const struct kernel_param_ops param_ops_sysrq_reset_seq = {
 	.get	= param_get_ushort,
 	.set	= sysrq_reset_seq_param_set,
 };
diff --git a/drivers/usb/atm/ueagle-atm.c b/drivers/usb/atm/ueagle-atm.c
index 888998a..a2ae88d 100644
--- a/drivers/usb/atm/ueagle-atm.c
+++ b/drivers/usb/atm/ueagle-atm.c
@@ -1599,7 +1599,7 @@
 	char file_arr[] = "CMVxy.bin";
 	char *file;
 
-	kparam_block_sysfs_write(cmv_file);
+	kernel_param_lock(THIS_MODULE);
 	/* set proper name corresponding modem version and line type */
 	if (cmv_file[sc->modem_index] == NULL) {
 		if (UEA_CHIP_VERSION(sc) == ADI930)
@@ -1618,7 +1618,7 @@
 	strlcat(cmv_name, file, UEA_FW_NAME_MAX);
 	if (ver == 2)
 		strlcat(cmv_name, ".v2", UEA_FW_NAME_MAX);
-	kparam_unblock_sysfs_write(cmv_file);
+	kernel_param_unlock(THIS_MODULE);
 }
 
 static int request_cmvs_old(struct uea_softc *sc,
diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c
index 3cc109f..d2259c6 100644
--- a/drivers/usb/gadget/function/f_mass_storage.c
+++ b/drivers/usb/gadget/function/f_mass_storage.c
@@ -2936,7 +2936,7 @@
 	if (fsg_lun_is_open(lun)) {
 		p = "(error)";
 		if (pathbuf) {
-			p = d_path(&lun->filp->f_path, pathbuf, PATH_MAX);
+			p = file_path(lun->filp, pathbuf, PATH_MAX);
 			if (IS_ERR(p))
 				p = "(error)";
 		}
diff --git a/drivers/usb/gadget/function/storage_common.c b/drivers/usb/gadget/function/storage_common.c
index 648f9e4..d626830 100644
--- a/drivers/usb/gadget/function/storage_common.c
+++ b/drivers/usb/gadget/function/storage_common.c
@@ -341,7 +341,7 @@
 
 	down_read(filesem);
 	if (fsg_lun_is_open(curlun)) {	/* Get the complete pathname */
-		p = d_path(&curlun->filp->f_path, buf, PAGE_SIZE - 1);
+		p = file_path(curlun->filp, buf, PAGE_SIZE - 1);
 		if (IS_ERR(p))
 			rc = PTR_ERR(p);
 		else {
diff --git a/drivers/usb/gadget/legacy/tcm_usb_gadget.c b/drivers/usb/gadget/legacy/tcm_usb_gadget.c
index 6ce932f..c3c4808 100644
--- a/drivers/usb/gadget/legacy/tcm_usb_gadget.c
+++ b/drivers/usb/gadget/legacy/tcm_usb_gadget.c
@@ -20,7 +20,6 @@
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
 #include <target/target_core_fabric_configfs.h>
-#include <target/target_core_configfs.h>
 #include <target/configfs_macros.h>
 #include <asm/unaligned.h>
 
@@ -28,8 +27,6 @@
 
 USB_GADGET_COMPOSITE_OPTIONS();
 
-static const struct target_core_fabric_ops usbg_ops;
-
 static inline struct f_uas *to_f_uas(struct usb_function *f)
 {
 	return container_of(f, struct f_uas, function);
@@ -1111,6 +1108,7 @@
 	memcpy(cmd->cmd_buf, cmd_iu->cdb, cmd_len);
 
 	cmd->tag = be16_to_cpup(&cmd_iu->tag);
+	cmd->se_cmd.tag = cmd->tag;
 	if (fu->flags & USBG_USE_STREAMS) {
 		if (cmd->tag > UASP_SS_EP_COMP_NUM_STREAMS)
 			goto err;
@@ -1244,6 +1242,7 @@
 	cmd->unpacked_lun = cbw->Lun;
 	cmd->is_read = cbw->Flags & US_BULK_FLAG_IN ? 1 : 0;
 	cmd->data_len = le32_to_cpu(cbw->DataTransferLength);
+	cmd->se_cmd.tag = le32_to_cpu(cmd->bot_tag);
 
 	INIT_WORK(&cmd->work, bot_cmd_work);
 	ret = queue_work(tpg->workqueue, &cmd->work);
@@ -1273,23 +1272,6 @@
 	return "usb_gadget";
 }
 
-static u8 usbg_get_fabric_proto_ident(struct se_portal_group *se_tpg)
-{
-	struct usbg_tpg *tpg = container_of(se_tpg,
-				struct usbg_tpg, se_tpg);
-	struct usbg_tport *tport = tpg->tport;
-	u8 proto_id;
-
-	switch (tport->tport_proto_id) {
-	case SCSI_PROTOCOL_SAS:
-	default:
-		proto_id = sas_get_fabric_proto_ident(se_tpg);
-		break;
-	}
-
-	return proto_id;
-}
-
 static char *usbg_get_fabric_wwn(struct se_portal_group *se_tpg)
 {
 	struct usbg_tpg *tpg = container_of(se_tpg,
@@ -1306,97 +1288,6 @@
 	return tpg->tport_tpgt;
 }
 
-static u32 usbg_get_default_depth(struct se_portal_group *se_tpg)
-{
-	return 1;
-}
-
-static u32 usbg_get_pr_transport_id(
-	struct se_portal_group *se_tpg,
-	struct se_node_acl *se_nacl,
-	struct t10_pr_registration *pr_reg,
-	int *format_code,
-	unsigned char *buf)
-{
-	struct usbg_tpg *tpg = container_of(se_tpg,
-				struct usbg_tpg, se_tpg);
-	struct usbg_tport *tport = tpg->tport;
-	int ret = 0;
-
-	switch (tport->tport_proto_id) {
-	case SCSI_PROTOCOL_SAS:
-	default:
-		ret = sas_get_pr_transport_id(se_tpg, se_nacl, pr_reg,
-					format_code, buf);
-		break;
-	}
-
-	return ret;
-}
-
-static u32 usbg_get_pr_transport_id_len(
-	struct se_portal_group *se_tpg,
-	struct se_node_acl *se_nacl,
-	struct t10_pr_registration *pr_reg,
-	int *format_code)
-{
-	struct usbg_tpg *tpg = container_of(se_tpg,
-				struct usbg_tpg, se_tpg);
-	struct usbg_tport *tport = tpg->tport;
-	int ret = 0;
-
-	switch (tport->tport_proto_id) {
-	case SCSI_PROTOCOL_SAS:
-	default:
-		ret = sas_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,
-					format_code);
-		break;
-	}
-
-	return ret;
-}
-
-static char *usbg_parse_pr_out_transport_id(
-	struct se_portal_group *se_tpg,
-	const char *buf,
-	u32 *out_tid_len,
-	char **port_nexus_ptr)
-{
-	struct usbg_tpg *tpg = container_of(se_tpg,
-				struct usbg_tpg, se_tpg);
-	struct usbg_tport *tport = tpg->tport;
-	char *tid = NULL;
-
-	switch (tport->tport_proto_id) {
-	case SCSI_PROTOCOL_SAS:
-	default:
-		tid = sas_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,
-					port_nexus_ptr);
-	}
-
-	return tid;
-}
-
-static struct se_node_acl *usbg_alloc_fabric_acl(struct se_portal_group *se_tpg)
-{
-	struct usbg_nacl *nacl;
-
-	nacl = kzalloc(sizeof(struct usbg_nacl), GFP_KERNEL);
-	if (!nacl)
-		return NULL;
-
-	return &nacl->se_node_acl;
-}
-
-static void usbg_release_fabric_acl(
-	struct se_portal_group *se_tpg,
-	struct se_node_acl *se_nacl)
-{
-	struct usbg_nacl *nacl = container_of(se_nacl,
-			struct usbg_nacl, se_node_acl);
-	kfree(nacl);
-}
-
 static u32 usbg_tpg_get_inst_index(struct se_portal_group *se_tpg)
 {
 	return 1;
@@ -1447,18 +1338,6 @@
 	return;
 }
 
-static u32 usbg_get_task_tag(struct se_cmd *se_cmd)
-{
-	struct usbg_cmd *cmd = container_of(se_cmd, struct usbg_cmd,
-			se_cmd);
-	struct f_uas *fu = cmd->fu;
-
-	if (fu->flags & USBG_IS_BOT)
-		return le32_to_cpu(cmd->bot_tag);
-	else
-		return cmd->tag;
-}
-
 static int usbg_get_cmd_state(struct se_cmd *se_cmd)
 {
 	return 0;
@@ -1488,50 +1367,11 @@
 	return n;
 }
 
-static struct se_node_acl *usbg_make_nodeacl(
-	struct se_portal_group *se_tpg,
-	struct config_group *group,
-	const char *name)
+static int usbg_init_nodeacl(struct se_node_acl *se_nacl, const char *name)
 {
-	struct se_node_acl *se_nacl, *se_nacl_new;
-	struct usbg_nacl *nacl;
-	u64 wwpn = 0;
-	u32 nexus_depth;
-	const char *wnn_name;
-
-	wnn_name = usbg_check_wwn(name);
-	if (!wnn_name)
-		return ERR_PTR(-EINVAL);
-	se_nacl_new = usbg_alloc_fabric_acl(se_tpg);
-	if (!(se_nacl_new))
-		return ERR_PTR(-ENOMEM);
-
-	nexus_depth = 1;
-	/*
-	 * se_nacl_new may be released by core_tpg_add_initiator_node_acl()
-	 * when converting a NodeACL from demo mode -> explict
-	 */
-	se_nacl = core_tpg_add_initiator_node_acl(se_tpg, se_nacl_new,
-				name, nexus_depth);
-	if (IS_ERR(se_nacl)) {
-		usbg_release_fabric_acl(se_tpg, se_nacl_new);
-		return se_nacl;
-	}
-	/*
-	 * Locate our struct usbg_nacl and set the FC Nport WWPN
-	 */
-	nacl = container_of(se_nacl, struct usbg_nacl, se_node_acl);
-	nacl->iport_wwpn = wwpn;
-	snprintf(nacl->iport_name, sizeof(nacl->iport_name), "%s", name);
-	return se_nacl;
-}
-
-static void usbg_drop_nodeacl(struct se_node_acl *se_acl)
-{
-	struct usbg_nacl *nacl = container_of(se_acl,
-				struct usbg_nacl, se_node_acl);
-	core_tpg_del_initiator_node_acl(se_acl->se_tpg, se_acl, 1);
-	kfree(nacl);
+	if (!usbg_check_wwn(name))
+		return -EINVAL;
+	return 0;
 }
 
 struct usbg_tpg *the_only_tpg_I_currently_have;
@@ -1571,8 +1411,11 @@
 	tpg->tport = tport;
 	tpg->tport_tpgt = tpgt;
 
-	ret = core_tpg_register(&usbg_ops, wwn, &tpg->se_tpg, tpg,
-				TRANSPORT_TPG_TYPE_NORMAL);
+	/*
+	 * SPC doesn't assign a protocol identifier for USB-SCSI, so we
+	 * pretend to be SAS..
+	 */
+	ret = core_tpg_register(wwn, &tpg->se_tpg, SCSI_PROTOCOL_SAS);
 	if (ret < 0) {
 		destroy_workqueue(tpg->workqueue);
 		kfree(tpg);
@@ -1866,19 +1709,12 @@
 	.module				= THIS_MODULE,
 	.name				= "usb_gadget",
 	.get_fabric_name		= usbg_get_fabric_name,
-	.get_fabric_proto_ident		= usbg_get_fabric_proto_ident,
 	.tpg_get_wwn			= usbg_get_fabric_wwn,
 	.tpg_get_tag			= usbg_get_tag,
-	.tpg_get_default_depth		= usbg_get_default_depth,
-	.tpg_get_pr_transport_id	= usbg_get_pr_transport_id,
-	.tpg_get_pr_transport_id_len	= usbg_get_pr_transport_id_len,
-	.tpg_parse_pr_out_transport_id	= usbg_parse_pr_out_transport_id,
 	.tpg_check_demo_mode		= usbg_check_true,
 	.tpg_check_demo_mode_cache	= usbg_check_false,
 	.tpg_check_demo_mode_write_protect = usbg_check_false,
 	.tpg_check_prod_mode_write_protect = usbg_check_false,
-	.tpg_alloc_fabric_acl		= usbg_alloc_fabric_acl,
-	.tpg_release_fabric_acl		= usbg_release_fabric_acl,
 	.tpg_get_inst_index		= usbg_tpg_get_inst_index,
 	.release_cmd			= usbg_release_cmd,
 	.shutdown_session		= usbg_shutdown_session,
@@ -1888,7 +1724,6 @@
 	.write_pending			= usbg_send_write_request,
 	.write_pending_status		= usbg_write_pending_status,
 	.set_default_node_attributes	= usbg_set_default_node_attrs,
-	.get_task_tag			= usbg_get_task_tag,
 	.get_cmd_state			= usbg_get_cmd_state,
 	.queue_data_in			= usbg_send_read_response,
 	.queue_status			= usbg_send_status_response,
@@ -1902,10 +1737,7 @@
 	.fabric_drop_tpg		= usbg_drop_tpg,
 	.fabric_post_link		= usbg_port_link,
 	.fabric_pre_unlink		= usbg_port_unlink,
-	.fabric_make_np			= NULL,
-	.fabric_drop_np			= NULL,
-	.fabric_make_nodeacl		= usbg_make_nodeacl,
-	.fabric_drop_nodeacl		= usbg_drop_nodeacl,
+	.fabric_init_nodeacl		= usbg_init_nodeacl,
 
 	.tfc_wwn_attrs			= usbg_wwn_attrs,
 	.tfc_tpg_base_attrs		= usbg_base_attrs,
diff --git a/drivers/usb/gadget/legacy/tcm_usb_gadget.h b/drivers/usb/gadget/legacy/tcm_usb_gadget.h
index 9fb3544..0b749e1 100644
--- a/drivers/usb/gadget/legacy/tcm_usb_gadget.h
+++ b/drivers/usb/gadget/legacy/tcm_usb_gadget.h
@@ -24,15 +24,6 @@
 #define USB_G_ALT_INT_BBB       0
 #define USB_G_ALT_INT_UAS       1
 
-struct usbg_nacl {
-	/* Binary World Wide unique Port Name for SAS Initiator port */
-	u64 iport_wwpn;
-	/* ASCII formatted WWPN for Sas Initiator port */
-	char iport_name[USBG_NAMELEN];
-	/* Returned by usbg_make_nodeacl() */
-	struct se_node_acl se_node_acl;
-};
-
 struct tcm_usbg_nexus {
 	struct se_session *tvn_se_sess;
 };
@@ -52,8 +43,6 @@
 };
 
 struct usbg_tport {
-	/* SCSI protocol the tport is providing */
-	u8 tport_proto_id;
 	/* Binary World Wide unique Port Name for SAS Target port */
 	u64 tport_wwpn;
 	/* ASCII formatted WWPN for SAS Target port */
diff --git a/drivers/vhost/Kconfig b/drivers/vhost/Kconfig
index 017a1e8..533eaf0 100644
--- a/drivers/vhost/Kconfig
+++ b/drivers/vhost/Kconfig
@@ -32,3 +32,18 @@
 	---help---
 	  This option is selected by any driver which needs to access
 	  the core of vhost.
+
+config VHOST_CROSS_ENDIAN_LEGACY
+	bool "Cross-endian support for vhost"
+	default n
+	---help---
+	  This option allows vhost to support guests with a different byte
+	  ordering from host while using legacy virtio.
+
+	  Userspace programs can control the feature using the
+	  VHOST_SET_VRING_ENDIAN and VHOST_GET_VRING_ENDIAN ioctls.
+
+	  This is only useful on a few platforms (ppc64 and arm64). Since it
+	  adds some overhead, it is disabled by default.
+
+	  If unsure, say "N".
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 55722fe..dfcc02c 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -43,7 +43,6 @@
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
 #include <target/target_core_fabric_configfs.h>
-#include <target/target_core_configfs.h>
 #include <target/configfs_macros.h>
 #include <linux/vhost.h>
 #include <linux/virtio_scsi.h>
@@ -117,15 +116,6 @@
 	struct se_session *tvn_se_sess;
 };
 
-struct vhost_scsi_nacl {
-	/* Binary World Wide unique Port Name for Vhost Initiator port */
-	u64 iport_wwpn;
-	/* ASCII formatted WWPN for Sas Initiator port */
-	char iport_name[VHOST_SCSI_NAMELEN];
-	/* Returned by vhost_scsi_make_nodeacl() */
-	struct se_node_acl se_node_acl;
-};
-
 struct vhost_scsi_tpg {
 	/* Vhost port target portal group tag for TCM */
 	u16 tport_tpgt;
@@ -218,7 +208,6 @@
 	int vs_events_nr; /* num of pending events, protected by vq->mutex */
 };
 
-static struct target_core_fabric_ops vhost_scsi_ops;
 static struct workqueue_struct *vhost_scsi_workqueue;
 
 /* Global spinlock to protect vhost_scsi TPG list for vhost IOCTL access */
@@ -299,28 +288,6 @@
 	return "vhost";
 }
 
-static u8 vhost_scsi_get_fabric_proto_ident(struct se_portal_group *se_tpg)
-{
-	struct vhost_scsi_tpg *tpg = container_of(se_tpg,
-				struct vhost_scsi_tpg, se_tpg);
-	struct vhost_scsi_tport *tport = tpg->tport;
-
-	switch (tport->tport_proto_id) {
-	case SCSI_PROTOCOL_SAS:
-		return sas_get_fabric_proto_ident(se_tpg);
-	case SCSI_PROTOCOL_FCP:
-		return fc_get_fabric_proto_ident(se_tpg);
-	case SCSI_PROTOCOL_ISCSI:
-		return iscsi_get_fabric_proto_ident(se_tpg);
-	default:
-		pr_err("Unknown tport_proto_id: 0x%02x, using"
-			" SAS emulation\n", tport->tport_proto_id);
-		break;
-	}
-
-	return sas_get_fabric_proto_ident(se_tpg);
-}
-
 static char *vhost_scsi_get_fabric_wwn(struct se_portal_group *se_tpg)
 {
 	struct vhost_scsi_tpg *tpg = container_of(se_tpg,
@@ -337,102 +304,6 @@
 	return tpg->tport_tpgt;
 }
 
-static u32 vhost_scsi_get_default_depth(struct se_portal_group *se_tpg)
-{
-	return 1;
-}
-
-static u32
-vhost_scsi_get_pr_transport_id(struct se_portal_group *se_tpg,
-			      struct se_node_acl *se_nacl,
-			      struct t10_pr_registration *pr_reg,
-			      int *format_code,
-			      unsigned char *buf)
-{
-	struct vhost_scsi_tpg *tpg = container_of(se_tpg,
-				struct vhost_scsi_tpg, se_tpg);
-	struct vhost_scsi_tport *tport = tpg->tport;
-
-	switch (tport->tport_proto_id) {
-	case SCSI_PROTOCOL_SAS:
-		return sas_get_pr_transport_id(se_tpg, se_nacl, pr_reg,
-					format_code, buf);
-	case SCSI_PROTOCOL_FCP:
-		return fc_get_pr_transport_id(se_tpg, se_nacl, pr_reg,
-					format_code, buf);
-	case SCSI_PROTOCOL_ISCSI:
-		return iscsi_get_pr_transport_id(se_tpg, se_nacl, pr_reg,
-					format_code, buf);
-	default:
-		pr_err("Unknown tport_proto_id: 0x%02x, using"
-			" SAS emulation\n", tport->tport_proto_id);
-		break;
-	}
-
-	return sas_get_pr_transport_id(se_tpg, se_nacl, pr_reg,
-			format_code, buf);
-}
-
-static u32
-vhost_scsi_get_pr_transport_id_len(struct se_portal_group *se_tpg,
-				  struct se_node_acl *se_nacl,
-				  struct t10_pr_registration *pr_reg,
-				  int *format_code)
-{
-	struct vhost_scsi_tpg *tpg = container_of(se_tpg,
-				struct vhost_scsi_tpg, se_tpg);
-	struct vhost_scsi_tport *tport = tpg->tport;
-
-	switch (tport->tport_proto_id) {
-	case SCSI_PROTOCOL_SAS:
-		return sas_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,
-					format_code);
-	case SCSI_PROTOCOL_FCP:
-		return fc_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,
-					format_code);
-	case SCSI_PROTOCOL_ISCSI:
-		return iscsi_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,
-					format_code);
-	default:
-		pr_err("Unknown tport_proto_id: 0x%02x, using"
-			" SAS emulation\n", tport->tport_proto_id);
-		break;
-	}
-
-	return sas_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,
-			format_code);
-}
-
-static char *
-vhost_scsi_parse_pr_out_transport_id(struct se_portal_group *se_tpg,
-				    const char *buf,
-				    u32 *out_tid_len,
-				    char **port_nexus_ptr)
-{
-	struct vhost_scsi_tpg *tpg = container_of(se_tpg,
-				struct vhost_scsi_tpg, se_tpg);
-	struct vhost_scsi_tport *tport = tpg->tport;
-
-	switch (tport->tport_proto_id) {
-	case SCSI_PROTOCOL_SAS:
-		return sas_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,
-					port_nexus_ptr);
-	case SCSI_PROTOCOL_FCP:
-		return fc_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,
-					port_nexus_ptr);
-	case SCSI_PROTOCOL_ISCSI:
-		return iscsi_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,
-					port_nexus_ptr);
-	default:
-		pr_err("Unknown tport_proto_id: 0x%02x, using"
-			" SAS emulation\n", tport->tport_proto_id);
-		break;
-	}
-
-	return sas_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,
-			port_nexus_ptr);
-}
-
 static int vhost_scsi_check_prot_fabric_only(struct se_portal_group *se_tpg)
 {
 	struct vhost_scsi_tpg *tpg = container_of(se_tpg,
@@ -441,29 +312,6 @@
 	return tpg->tv_fabric_prot_type;
 }
 
-static struct se_node_acl *
-vhost_scsi_alloc_fabric_acl(struct se_portal_group *se_tpg)
-{
-	struct vhost_scsi_nacl *nacl;
-
-	nacl = kzalloc(sizeof(struct vhost_scsi_nacl), GFP_KERNEL);
-	if (!nacl) {
-		pr_err("Unable to allocate struct vhost_scsi_nacl\n");
-		return NULL;
-	}
-
-	return &nacl->se_node_acl;
-}
-
-static void
-vhost_scsi_release_fabric_acl(struct se_portal_group *se_tpg,
-			     struct se_node_acl *se_nacl)
-{
-	struct vhost_scsi_nacl *nacl = container_of(se_nacl,
-			struct vhost_scsi_nacl, se_node_acl);
-	kfree(nacl);
-}
-
 static u32 vhost_scsi_tpg_get_inst_index(struct se_portal_group *se_tpg)
 {
 	return 1;
@@ -521,11 +369,6 @@
 	return;
 }
 
-static u32 vhost_scsi_get_task_tag(struct se_cmd *se_cmd)
-{
-	return 0;
-}
-
 static int vhost_scsi_get_cmd_state(struct se_cmd *se_cmd)
 {
 	return 0;
@@ -609,7 +452,7 @@
 
 static int vhost_scsi_check_stop_free(struct se_cmd *se_cmd)
 {
-	return target_put_sess_cmd(se_cmd->se_sess, se_cmd);
+	return target_put_sess_cmd(se_cmd);
 }
 
 static void
@@ -970,6 +813,7 @@
 	}
 	tv_nexus = cmd->tvc_nexus;
 
+	se_cmd->tag = 0;
 	rc = target_submit_cmd_map_sgls(se_cmd, tv_nexus->tvn_se_sess,
 			cmd->tvc_cdb, &cmd->tvc_sense_buf[0],
 			cmd->tvc_lun, cmd->tvc_exp_data_len,
@@ -1824,50 +1668,6 @@
 	mutex_unlock(&vhost_scsi_mutex);
 }
 
-static struct se_node_acl *
-vhost_scsi_make_nodeacl(struct se_portal_group *se_tpg,
-		       struct config_group *group,
-		       const char *name)
-{
-	struct se_node_acl *se_nacl, *se_nacl_new;
-	struct vhost_scsi_nacl *nacl;
-	u64 wwpn = 0;
-	u32 nexus_depth;
-
-	/* vhost_scsi_parse_wwn(name, &wwpn, 1) < 0)
-		return ERR_PTR(-EINVAL); */
-	se_nacl_new = vhost_scsi_alloc_fabric_acl(se_tpg);
-	if (!se_nacl_new)
-		return ERR_PTR(-ENOMEM);
-
-	nexus_depth = 1;
-	/*
-	 * se_nacl_new may be released by core_tpg_add_initiator_node_acl()
-	 * when converting a NodeACL from demo mode -> explict
-	 */
-	se_nacl = core_tpg_add_initiator_node_acl(se_tpg, se_nacl_new,
-				name, nexus_depth);
-	if (IS_ERR(se_nacl)) {
-		vhost_scsi_release_fabric_acl(se_tpg, se_nacl_new);
-		return se_nacl;
-	}
-	/*
-	 * Locate our struct vhost_scsi_nacl and set the FC Nport WWPN
-	 */
-	nacl = container_of(se_nacl, struct vhost_scsi_nacl, se_node_acl);
-	nacl->iport_wwpn = wwpn;
-
-	return se_nacl;
-}
-
-static void vhost_scsi_drop_nodeacl(struct se_node_acl *se_acl)
-{
-	struct vhost_scsi_nacl *nacl = container_of(se_acl,
-				struct vhost_scsi_nacl, se_node_acl);
-	core_tpg_del_initiator_node_acl(se_acl->se_tpg, se_acl, 1);
-	kfree(nacl);
-}
-
 static void vhost_scsi_free_cmd_map_res(struct vhost_scsi_nexus *nexus,
 				       struct se_session *se_sess)
 {
@@ -2202,8 +2002,7 @@
 	tpg->tport = tport;
 	tpg->tport_tpgt = tpgt;
 
-	ret = core_tpg_register(&vhost_scsi_ops, wwn,
-				&tpg->se_tpg, tpg, TRANSPORT_TPG_TYPE_NORMAL);
+	ret = core_tpg_register(wwn, &tpg->se_tpg, tport->tport_proto_id);
 	if (ret < 0) {
 		kfree(tpg);
 		return NULL;
@@ -2327,20 +2126,13 @@
 	.module				= THIS_MODULE,
 	.name				= "vhost",
 	.get_fabric_name		= vhost_scsi_get_fabric_name,
-	.get_fabric_proto_ident		= vhost_scsi_get_fabric_proto_ident,
 	.tpg_get_wwn			= vhost_scsi_get_fabric_wwn,
 	.tpg_get_tag			= vhost_scsi_get_tpgt,
-	.tpg_get_default_depth		= vhost_scsi_get_default_depth,
-	.tpg_get_pr_transport_id	= vhost_scsi_get_pr_transport_id,
-	.tpg_get_pr_transport_id_len	= vhost_scsi_get_pr_transport_id_len,
-	.tpg_parse_pr_out_transport_id	= vhost_scsi_parse_pr_out_transport_id,
 	.tpg_check_demo_mode		= vhost_scsi_check_true,
 	.tpg_check_demo_mode_cache	= vhost_scsi_check_true,
 	.tpg_check_demo_mode_write_protect = vhost_scsi_check_false,
 	.tpg_check_prod_mode_write_protect = vhost_scsi_check_false,
 	.tpg_check_prot_fabric_only	= vhost_scsi_check_prot_fabric_only,
-	.tpg_alloc_fabric_acl		= vhost_scsi_alloc_fabric_acl,
-	.tpg_release_fabric_acl		= vhost_scsi_release_fabric_acl,
 	.tpg_get_inst_index		= vhost_scsi_tpg_get_inst_index,
 	.release_cmd			= vhost_scsi_release_cmd,
 	.check_stop_free		= vhost_scsi_check_stop_free,
@@ -2351,7 +2143,6 @@
 	.write_pending			= vhost_scsi_write_pending,
 	.write_pending_status		= vhost_scsi_write_pending_status,
 	.set_default_node_attributes	= vhost_scsi_set_default_node_attrs,
-	.get_task_tag			= vhost_scsi_get_task_tag,
 	.get_cmd_state			= vhost_scsi_get_cmd_state,
 	.queue_data_in			= vhost_scsi_queue_data_in,
 	.queue_status			= vhost_scsi_queue_status,
@@ -2366,10 +2157,6 @@
 	.fabric_drop_tpg		= vhost_scsi_drop_tpg,
 	.fabric_post_link		= vhost_scsi_port_link,
 	.fabric_pre_unlink		= vhost_scsi_port_unlink,
-	.fabric_make_np			= NULL,
-	.fabric_drop_np			= NULL,
-	.fabric_make_nodeacl		= vhost_scsi_make_nodeacl,
-	.fabric_drop_nodeacl		= vhost_scsi_drop_nodeacl,
 
 	.tfc_wwn_attrs			= vhost_scsi_wwn_attrs,
 	.tfc_tpg_base_attrs		= vhost_scsi_tpg_attrs,
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 2ee2826..9e8e004 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -36,6 +36,77 @@
 #define vhost_used_event(vq) ((__virtio16 __user *)&vq->avail->ring[vq->num])
 #define vhost_avail_event(vq) ((__virtio16 __user *)&vq->used->ring[vq->num])
 
+#ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY
+static void vhost_vq_reset_user_be(struct vhost_virtqueue *vq)
+{
+	vq->user_be = !virtio_legacy_is_little_endian();
+}
+
+static long vhost_set_vring_endian(struct vhost_virtqueue *vq, int __user *argp)
+{
+	struct vhost_vring_state s;
+
+	if (vq->private_data)
+		return -EBUSY;
+
+	if (copy_from_user(&s, argp, sizeof(s)))
+		return -EFAULT;
+
+	if (s.num != VHOST_VRING_LITTLE_ENDIAN &&
+	    s.num != VHOST_VRING_BIG_ENDIAN)
+		return -EINVAL;
+
+	vq->user_be = s.num;
+
+	return 0;
+}
+
+static long vhost_get_vring_endian(struct vhost_virtqueue *vq, u32 idx,
+				   int __user *argp)
+{
+	struct vhost_vring_state s = {
+		.index = idx,
+		.num = vq->user_be
+	};
+
+	if (copy_to_user(argp, &s, sizeof(s)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static void vhost_init_is_le(struct vhost_virtqueue *vq)
+{
+	/* Note for legacy virtio: user_be is initialized at reset time
+	 * according to the host endianness. If userspace does not set an
+	 * explicit endianness, the default behavior is native endian, as
+	 * expected by legacy virtio.
+	 */
+	vq->is_le = vhost_has_feature(vq, VIRTIO_F_VERSION_1) || !vq->user_be;
+}
+#else
+static void vhost_vq_reset_user_be(struct vhost_virtqueue *vq)
+{
+}
+
+static long vhost_set_vring_endian(struct vhost_virtqueue *vq, int __user *argp)
+{
+	return -ENOIOCTLCMD;
+}
+
+static long vhost_get_vring_endian(struct vhost_virtqueue *vq, u32 idx,
+				   int __user *argp)
+{
+	return -ENOIOCTLCMD;
+}
+
+static void vhost_init_is_le(struct vhost_virtqueue *vq)
+{
+	if (vhost_has_feature(vq, VIRTIO_F_VERSION_1))
+		vq->is_le = true;
+}
+#endif /* CONFIG_VHOST_CROSS_ENDIAN_LEGACY */
+
 static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
 			    poll_table *pt)
 {
@@ -199,6 +270,8 @@
 	vq->call = NULL;
 	vq->log_ctx = NULL;
 	vq->memory = NULL;
+	vq->is_le = virtio_legacy_is_little_endian();
+	vhost_vq_reset_user_be(vq);
 }
 
 static int vhost_worker(void *data)
@@ -806,6 +879,12 @@
 		} else
 			filep = eventfp;
 		break;
+	case VHOST_SET_VRING_ENDIAN:
+		r = vhost_set_vring_endian(vq, argp);
+		break;
+	case VHOST_GET_VRING_ENDIAN:
+		r = vhost_get_vring_endian(vq, idx, argp);
+		break;
 	default:
 		r = -ENOIOCTLCMD;
 	}
@@ -1044,8 +1123,12 @@
 {
 	__virtio16 last_used_idx;
 	int r;
-	if (!vq->private_data)
+	if (!vq->private_data) {
+		vq->is_le = virtio_legacy_is_little_endian();
 		return 0;
+	}
+
+	vhost_init_is_le(vq);
 
 	r = vhost_update_used_flags(vq);
 	if (r)
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 8c1c792..ce6f6da 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -106,6 +106,14 @@
 	/* Log write descriptors */
 	void __user *log_base;
 	struct vhost_log *log;
+
+	/* Ring endianness. Defaults to legacy native endianness.
+	 * Set to true when starting a modern virtio device. */
+	bool is_le;
+#ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY
+	/* Ring endianness requested by userspace for cross-endian support. */
+	bool user_be;
+#endif
 };
 
 struct vhost_dev {
@@ -173,34 +181,39 @@
 	return vq->acked_features & (1ULL << bit);
 }
 
+static inline bool vhost_is_little_endian(struct vhost_virtqueue *vq)
+{
+	return vq->is_le;
+}
+
 /* Memory accessors */
 static inline u16 vhost16_to_cpu(struct vhost_virtqueue *vq, __virtio16 val)
 {
-	return __virtio16_to_cpu(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val);
+	return __virtio16_to_cpu(vhost_is_little_endian(vq), val);
 }
 
 static inline __virtio16 cpu_to_vhost16(struct vhost_virtqueue *vq, u16 val)
 {
-	return __cpu_to_virtio16(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val);
+	return __cpu_to_virtio16(vhost_is_little_endian(vq), val);
 }
 
 static inline u32 vhost32_to_cpu(struct vhost_virtqueue *vq, __virtio32 val)
 {
-	return __virtio32_to_cpu(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val);
+	return __virtio32_to_cpu(vhost_is_little_endian(vq), val);
 }
 
 static inline __virtio32 cpu_to_vhost32(struct vhost_virtqueue *vq, u32 val)
 {
-	return __cpu_to_virtio32(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val);
+	return __cpu_to_virtio32(vhost_is_little_endian(vq), val);
 }
 
 static inline u64 vhost64_to_cpu(struct vhost_virtqueue *vq, __virtio64 val)
 {
-	return __virtio64_to_cpu(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val);
+	return __virtio64_to_cpu(vhost_is_little_endian(vq), val);
 }
 
 static inline __virtio64 cpu_to_vhost64(struct vhost_virtqueue *vq, u64 val)
 {
-	return __cpu_to_virtio64(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val);
+	return __cpu_to_virtio64(vhost_is_little_endian(vq), val);
 }
 #endif
diff --git a/drivers/video/fbdev/omap2/dss/dss.c b/drivers/video/fbdev/omap2/dss/dss.c
index 612b093..9200a86 100644
--- a/drivers/video/fbdev/omap2/dss/dss.c
+++ b/drivers/video/fbdev/omap2/dss/dss.c
@@ -1225,6 +1225,15 @@
 {
 	struct component_match **match = data;
 
+	/*
+	 * HACK
+	 * We don't have a working driver for rfbi, so skip it here always.
+	 * Otherwise dss will never get probed successfully, as it will wait
+	 * for rfbi to get probed.
+	 */
+	if (strstr(dev_name(dev), "rfbi"))
+		return 0;
+
 	component_match_add(dev->parent, match, dss_component_compare, dev);
 
 	return 0;
diff --git a/drivers/video/fbdev/uvesafb.c b/drivers/video/fbdev/uvesafb.c
index d32d1c4..178ae93 100644
--- a/drivers/video/fbdev/uvesafb.c
+++ b/drivers/video/fbdev/uvesafb.c
@@ -1977,7 +1977,7 @@
 
 	return 0;
 }
-static struct kernel_param_ops param_ops_scroll = {
+static const struct kernel_param_ops param_ops_scroll = {
 	.set = param_set_scroll,
 };
 #define param_check_scroll(name, p) __param_check(name, p, void)
diff --git a/drivers/video/fbdev/vt8623fb.c b/drivers/video/fbdev/vt8623fb.c
index ea7f056..8bac309 100644
--- a/drivers/video/fbdev/vt8623fb.c
+++ b/drivers/video/fbdev/vt8623fb.c
@@ -754,9 +754,9 @@
 
 	/* Prepare startup mode */
 
-	kparam_block_sysfs_write(mode_option);
+	kernel_param_lock(THIS_MODULE);
 	rc = fb_find_mode(&(info->var), info, mode_option, NULL, 0, NULL, 8);
-	kparam_unblock_sysfs_write(mode_option);
+	kernel_param_unlock(THIS_MODULE);
 	if (! ((rc == 1) || (rc == 2))) {
 		rc = -EINVAL;
 		dev_err(info->device, "mode %s not found\n", mode_option);
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index 7a5e60d..10189b5 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -691,7 +691,7 @@
 	return strlen(buffer) + 1;
 }
 
-static struct kernel_param_ops vm_cmdline_param_ops = {
+static const struct kernel_param_ops vm_cmdline_param_ops = {
 	.set = vm_cmdline_set,
 	.get = vm_cmdline_get,
 };
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index 5447b81..78f804a 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -507,10 +507,6 @@
 	if (rc)
 		goto err_enable_device;
 
-	rc = pci_request_regions(pci_dev, "virtio-pci");
-	if (rc)
-		goto err_request_regions;
-
 	if (force_legacy) {
 		rc = virtio_pci_legacy_probe(vp_dev);
 		/* Also try modern mode if we can't map BAR0 (no IO space). */
@@ -540,8 +536,6 @@
 	else
 	     virtio_pci_modern_remove(vp_dev);
 err_probe:
-	pci_release_regions(pci_dev);
-err_request_regions:
 	pci_disable_device(pci_dev);
 err_enable_device:
 	kfree(vp_dev);
@@ -559,7 +553,6 @@
 	else
 		virtio_pci_modern_remove(vp_dev);
 
-	pci_release_regions(pci_dev);
 	pci_disable_device(pci_dev);
 }
 
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index 28ee4e5..b976d96 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -75,6 +75,8 @@
 	/* Multiply queue_notify_off by this value. (non-legacy mode). */
 	u32 notify_offset_multiplier;
 
+	int modern_bars;
+
 	/* Legacy only field */
 	/* the IO mapping for the PCI config space */
 	void __iomem *ioaddr;
diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c
index 256a527..48bc979 100644
--- a/drivers/virtio/virtio_pci_legacy.c
+++ b/drivers/virtio/virtio_pci_legacy.c
@@ -215,6 +215,7 @@
 int virtio_pci_legacy_probe(struct virtio_pci_device *vp_dev)
 {
 	struct pci_dev *pci_dev = vp_dev->pci_dev;
+	int rc;
 
 	/* We only own devices >= 0x1000 and <= 0x103f: leave the rest. */
 	if (pci_dev->device < 0x1000 || pci_dev->device > 0x103f)
@@ -226,9 +227,14 @@
 		return -ENODEV;
 	}
 
+	rc = pci_request_region(pci_dev, 0, "virtio-pci-legacy");
+	if (rc)
+		return rc;
+
+	rc = -ENOMEM;
 	vp_dev->ioaddr = pci_iomap(pci_dev, 0, 0);
 	if (!vp_dev->ioaddr)
-		return -ENOMEM;
+		goto err_iomap;
 
 	vp_dev->isr = vp_dev->ioaddr + VIRTIO_PCI_ISR;
 
@@ -246,6 +252,10 @@
 	vp_dev->del_vq = del_vq;
 
 	return 0;
+
+err_iomap:
+	pci_release_region(pci_dev, 0);
+	return rc;
 }
 
 void virtio_pci_legacy_remove(struct virtio_pci_device *vp_dev)
@@ -253,4 +263,5 @@
 	struct pci_dev *pci_dev = vp_dev->pci_dev;
 
 	pci_iounmap(pci_dev, vp_dev->ioaddr);
+	pci_release_region(pci_dev, 0);
 }
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index e88e099..8e5cf19 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -499,7 +499,7 @@
  * Returns offset of the capability, or 0.
  */
 static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type,
-					     u32 ioresource_types)
+					     u32 ioresource_types, int *bars)
 {
 	int pos;
 
@@ -520,8 +520,10 @@
 
 		if (type == cfg_type) {
 			if (pci_resource_len(dev, bar) &&
-			    pci_resource_flags(dev, bar) & ioresource_types)
+			    pci_resource_flags(dev, bar) & ioresource_types) {
+				*bars |= (1 << bar);
 				return pos;
+			}
 		}
 	}
 	return 0;
@@ -617,7 +619,8 @@
 
 	/* check for a common config: if not, use legacy mode (bar 0). */
 	common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG,
-					    IORESOURCE_IO | IORESOURCE_MEM);
+					    IORESOURCE_IO | IORESOURCE_MEM,
+					    &vp_dev->modern_bars);
 	if (!common) {
 		dev_info(&pci_dev->dev,
 			 "virtio_pci: leaving for legacy driver\n");
@@ -626,9 +629,11 @@
 
 	/* If common is there, these should be too... */
 	isr = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_ISR_CFG,
-					 IORESOURCE_IO | IORESOURCE_MEM);
+					 IORESOURCE_IO | IORESOURCE_MEM,
+					 &vp_dev->modern_bars);
 	notify = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_NOTIFY_CFG,
-					    IORESOURCE_IO | IORESOURCE_MEM);
+					    IORESOURCE_IO | IORESOURCE_MEM,
+					    &vp_dev->modern_bars);
 	if (!isr || !notify) {
 		dev_err(&pci_dev->dev,
 			"virtio_pci: missing capabilities %i/%i/%i\n",
@@ -640,7 +645,13 @@
 	 * device-specific configuration.
 	 */
 	device = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_DEVICE_CFG,
-					    IORESOURCE_IO | IORESOURCE_MEM);
+					    IORESOURCE_IO | IORESOURCE_MEM,
+					    &vp_dev->modern_bars);
+
+	err = pci_request_selected_regions(pci_dev, vp_dev->modern_bars,
+					   "virtio-pci-modern");
+	if (err)
+		return err;
 
 	err = -EINVAL;
 	vp_dev->common = map_capability(pci_dev, common,
@@ -727,4 +738,5 @@
 		pci_iounmap(pci_dev, vp_dev->notify_base);
 	pci_iounmap(pci_dev, vp_dev->isr);
 	pci_iounmap(pci_dev, vp_dev->common);
+	pci_release_selected_regions(pci_dev, vp_dev->modern_bars);
 }
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 262647b..241fafd 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -1,3 +1,4 @@
+
 #
 # Watchdog device configuration
 #
@@ -96,6 +97,15 @@
 
 	  This driver can be built as a module. The module name is da9063_wdt.
 
+config DA9062_WATCHDOG
+	tristate "Dialog DA9062 Watchdog"
+	depends on MFD_DA9062
+	select WATCHDOG_CORE
+	help
+	  Support for the watchdog in the DA9062 PMIC.
+
+	  This driver can be built as a module. The module name is da9062_wdt.
+
 config GPIO_WATCHDOG
 	tristate "Watchdog device controlled through GPIO-line"
 	depends on OF_GPIO
@@ -104,6 +114,17 @@
 	  If you say yes here you get support for watchdog device
 	  controlled through GPIO-line.
 
+config GPIO_WATCHDOG_ARCH_INITCALL
+	bool "Register the watchdog as early as possible"
+	depends on GPIO_WATCHDOG=y
+	help
+	  In some situations, the default initcall level (module_init)
+	  in not early enough in the boot process to avoid the watchdog
+	  to be triggered.
+	  If you say yes here, the initcall level would be raised to
+	  arch_initcall.
+	  If in doubt, say N.
+
 config MENF21BMC_WATCHDOG
 	tristate "MEN 14F021P00 BMC Watchdog"
 	depends on MFD_MENF21BMC
@@ -169,6 +190,7 @@
 
 config CADENCE_WATCHDOG
 	tristate "Cadence Watchdog Timer"
+	depends on HAS_IOMEM
 	select WATCHDOG_CORE
 	help
 	  Say Y here if you want to include support for the watchdog
@@ -408,7 +430,7 @@
 
 config MAX63XX_WATCHDOG
 	tristate "Max63xx watchdog"
-	depends on ARM && HAS_IOMEM
+	depends on HAS_IOMEM
 	select WATCHDOG_CORE
 	help
 	  Support for memory mapped max63{69,70,71,72,73,74} watchdog timer.
@@ -526,6 +548,16 @@
 	  To compile this driver as a module, choose M here: the
 	  module will be called mtk_wdt.
 
+config DIGICOLOR_WATCHDOG
+	tristate "Conexant Digicolor SoCs watchdog support"
+	depends on ARCH_DIGICOLOR
+	select WATCHDOG_CORE
+	help
+	  Say Y here to include support for the watchdog timer
+	  in Conexant Digicolor SoCs.
+	  To compile this driver as a module, choose M here: the
+	  module will be called digicolor_wdt.
+
 # AVR32 Architecture
 
 config AT32AP700X_WDT
@@ -1355,7 +1387,7 @@
 config MEN_A21_WDT
        tristate "MEN A21 VME CPU Carrier Board Watchdog Timer"
        select WATCHDOG_CORE
-       depends on GPIOLIB
+       depends on GPIOLIB || COMPILE_TEST
        help
         Watchdog driver for MEN A21 VMEbus CPU Carrier Boards.
 
diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile
index d98768c..59ea9a1 100644
--- a/drivers/watchdog/Makefile
+++ b/drivers/watchdog/Makefile
@@ -65,6 +65,7 @@
 obj-$(CONFIG_TEGRA_WATCHDOG) += tegra_wdt.o
 obj-$(CONFIG_MESON_WATCHDOG) += meson_wdt.o
 obj-$(CONFIG_MEDIATEK_WATCHDOG) += mtk_wdt.o
+obj-$(CONFIG_DIGICOLOR_WATCHDOG) += digicolor_wdt.o
 
 # AVR32 Architecture
 obj-$(CONFIG_AT32AP700X_WDT) += at32ap700x_wdt.o
@@ -180,6 +181,7 @@
 # Architecture Independent
 obj-$(CONFIG_DA9052_WATCHDOG) += da9052_wdt.o
 obj-$(CONFIG_DA9055_WATCHDOG) += da9055_wdt.o
+obj-$(CONFIG_DA9062_WATCHDOG) += da9062_wdt.o
 obj-$(CONFIG_DA9063_WATCHDOG) += da9063_wdt.o
 obj-$(CONFIG_GPIO_WATCHDOG)	+= gpio_wdt.o
 obj-$(CONFIG_WM831X_WATCHDOG) += wm831x_wdt.o
diff --git a/drivers/watchdog/at91sam9_wdt.c b/drivers/watchdog/at91sam9_wdt.c
index 1443b3c..e4698f7 100644
--- a/drivers/watchdog/at91sam9_wdt.c
+++ b/drivers/watchdog/at91sam9_wdt.c
@@ -40,9 +40,9 @@
 #define DRV_NAME "AT91SAM9 Watchdog"
 
 #define wdt_read(wdt, field) \
-	__raw_readl((wdt)->base + (field))
+	readl_relaxed((wdt)->base + (field))
 #define wdt_write(wtd, field, val) \
-	__raw_writel((val), (wdt)->base + (field))
+	writel_relaxed((val), (wdt)->base + (field))
 
 /* AT91SAM9 watchdog runs a 12bit counter @ 256Hz,
  * use this to convert a watchdog
diff --git a/drivers/watchdog/da9062_wdt.c b/drivers/watchdog/da9062_wdt.c
new file mode 100644
index 0000000..b3a870c
--- /dev/null
+++ b/drivers/watchdog/da9062_wdt.c
@@ -0,0 +1,253 @@
+/*
+ * da9062_wdt.c - WDT device driver for DA9062
+ * Copyright (C) 2015  Dialog Semiconductor Ltd.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/watchdog.h>
+#include <linux/platform_device.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/jiffies.h>
+#include <linux/mfd/da9062/registers.h>
+#include <linux/mfd/da9062/core.h>
+#include <linux/regmap.h>
+#include <linux/of.h>
+
+static const unsigned int wdt_timeout[] = { 0, 2, 4, 8, 16, 32, 65, 131 };
+#define DA9062_TWDSCALE_DISABLE		0
+#define DA9062_TWDSCALE_MIN		1
+#define DA9062_TWDSCALE_MAX		(ARRAY_SIZE(wdt_timeout) - 1)
+#define DA9062_WDT_MIN_TIMEOUT		wdt_timeout[DA9062_TWDSCALE_MIN]
+#define DA9062_WDT_MAX_TIMEOUT		wdt_timeout[DA9062_TWDSCALE_MAX]
+#define DA9062_WDG_DEFAULT_TIMEOUT	wdt_timeout[DA9062_TWDSCALE_MAX-1]
+#define DA9062_RESET_PROTECTION_MS	300
+
+struct da9062_watchdog {
+	struct da9062 *hw;
+	struct watchdog_device wdtdev;
+	unsigned long j_time_stamp;
+};
+
+static void da9062_set_window_start(struct da9062_watchdog *wdt)
+{
+	wdt->j_time_stamp = jiffies;
+}
+
+static void da9062_apply_window_protection(struct da9062_watchdog *wdt)
+{
+	unsigned long delay = msecs_to_jiffies(DA9062_RESET_PROTECTION_MS);
+	unsigned long timeout = wdt->j_time_stamp + delay;
+	unsigned long now = jiffies;
+	unsigned int diff_ms;
+
+	/* if time-limit has not elapsed then wait for remainder */
+	if (time_before(now, timeout)) {
+		diff_ms = jiffies_to_msecs(timeout-now);
+		dev_dbg(wdt->hw->dev,
+			"Kicked too quickly. Delaying %u msecs\n", diff_ms);
+		msleep(diff_ms);
+	}
+}
+
+static unsigned int da9062_wdt_timeout_to_sel(unsigned int secs)
+{
+	unsigned int i;
+
+	for (i = DA9062_TWDSCALE_MIN; i <= DA9062_TWDSCALE_MAX; i++) {
+		if (wdt_timeout[i] >= secs)
+			return i;
+	}
+
+	return DA9062_TWDSCALE_MAX;
+}
+
+static int da9062_reset_watchdog_timer(struct da9062_watchdog *wdt)
+{
+	int ret;
+
+	da9062_apply_window_protection(wdt);
+
+	ret = regmap_update_bits(wdt->hw->regmap,
+			   DA9062AA_CONTROL_F,
+			   DA9062AA_WATCHDOG_MASK,
+			   DA9062AA_WATCHDOG_MASK);
+
+	da9062_set_window_start(wdt);
+
+	return ret;
+}
+
+static int da9062_wdt_update_timeout_register(struct da9062_watchdog *wdt,
+					      unsigned int regval)
+{
+	struct da9062 *chip = wdt->hw;
+	int ret;
+
+	ret = da9062_reset_watchdog_timer(wdt);
+	if (ret)
+		return ret;
+
+	return regmap_update_bits(chip->regmap,
+				  DA9062AA_CONTROL_D,
+				  DA9062AA_TWDSCALE_MASK,
+				  regval);
+}
+
+static int da9062_wdt_start(struct watchdog_device *wdd)
+{
+	struct da9062_watchdog *wdt = watchdog_get_drvdata(wdd);
+	unsigned int selector;
+	int ret;
+
+	selector = da9062_wdt_timeout_to_sel(wdt->wdtdev.timeout);
+	ret = da9062_wdt_update_timeout_register(wdt, selector);
+	if (ret)
+		dev_err(wdt->hw->dev, "Watchdog failed to start (err = %d)\n",
+			ret);
+
+	return ret;
+}
+
+static int da9062_wdt_stop(struct watchdog_device *wdd)
+{
+	struct da9062_watchdog *wdt = watchdog_get_drvdata(wdd);
+	int ret;
+
+	ret = da9062_reset_watchdog_timer(wdt);
+	if (ret) {
+		dev_err(wdt->hw->dev, "Failed to ping the watchdog (err = %d)\n",
+			ret);
+		return ret;
+	}
+
+	ret = regmap_update_bits(wdt->hw->regmap,
+				 DA9062AA_CONTROL_D,
+				 DA9062AA_TWDSCALE_MASK,
+				 DA9062_TWDSCALE_DISABLE);
+	if (ret)
+		dev_err(wdt->hw->dev, "Watchdog failed to stop (err = %d)\n",
+			ret);
+
+	return ret;
+}
+
+static int da9062_wdt_ping(struct watchdog_device *wdd)
+{
+	struct da9062_watchdog *wdt = watchdog_get_drvdata(wdd);
+	int ret;
+
+	ret = da9062_reset_watchdog_timer(wdt);
+	if (ret)
+		dev_err(wdt->hw->dev, "Failed to ping the watchdog (err = %d)\n",
+			ret);
+
+	return ret;
+}
+
+static int da9062_wdt_set_timeout(struct watchdog_device *wdd,
+				  unsigned int timeout)
+{
+	struct da9062_watchdog *wdt = watchdog_get_drvdata(wdd);
+	unsigned int selector;
+	int ret;
+
+	selector = da9062_wdt_timeout_to_sel(timeout);
+	ret = da9062_wdt_update_timeout_register(wdt, selector);
+	if (ret)
+		dev_err(wdt->hw->dev, "Failed to set watchdog timeout (err = %d)\n",
+			ret);
+	else
+		wdd->timeout = wdt_timeout[selector];
+
+	return ret;
+}
+
+static const struct watchdog_info da9062_watchdog_info = {
+	.options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING,
+	.identity = "DA9062 WDT",
+};
+
+static const struct watchdog_ops da9062_watchdog_ops = {
+	.owner = THIS_MODULE,
+	.start = da9062_wdt_start,
+	.stop = da9062_wdt_stop,
+	.ping = da9062_wdt_ping,
+	.set_timeout = da9062_wdt_set_timeout,
+};
+
+static int da9062_wdt_probe(struct platform_device *pdev)
+{
+	int ret;
+	struct da9062 *chip;
+	struct da9062_watchdog *wdt;
+
+	chip = dev_get_drvdata(pdev->dev.parent);
+	if (!chip)
+		return -EINVAL;
+
+	wdt = devm_kzalloc(&pdev->dev, sizeof(*wdt), GFP_KERNEL);
+	if (!wdt)
+		return -ENOMEM;
+
+	wdt->hw = chip;
+
+	wdt->wdtdev.info = &da9062_watchdog_info;
+	wdt->wdtdev.ops = &da9062_watchdog_ops;
+	wdt->wdtdev.min_timeout = DA9062_WDT_MIN_TIMEOUT;
+	wdt->wdtdev.max_timeout = DA9062_WDT_MAX_TIMEOUT;
+	wdt->wdtdev.timeout = DA9062_WDG_DEFAULT_TIMEOUT;
+	wdt->wdtdev.status = WATCHDOG_NOWAYOUT_INIT_STATUS;
+
+	watchdog_set_drvdata(&wdt->wdtdev, wdt);
+	dev_set_drvdata(&pdev->dev, wdt);
+
+	ret = watchdog_register_device(&wdt->wdtdev);
+	if (ret < 0) {
+		dev_err(wdt->hw->dev,
+			"watchdog registration failed (%d)\n", ret);
+		return ret;
+	}
+
+	da9062_set_window_start(wdt);
+
+	ret = da9062_wdt_ping(&wdt->wdtdev);
+	if (ret < 0)
+		watchdog_unregister_device(&wdt->wdtdev);
+
+	return ret;
+}
+
+static int da9062_wdt_remove(struct platform_device *pdev)
+{
+	struct da9062_watchdog *wdt = dev_get_drvdata(&pdev->dev);
+
+	watchdog_unregister_device(&wdt->wdtdev);
+	return 0;
+}
+
+static struct platform_driver da9062_wdt_driver = {
+	.probe = da9062_wdt_probe,
+	.remove = da9062_wdt_remove,
+	.driver = {
+		.name = "da9062-watchdog",
+	},
+};
+module_platform_driver(da9062_wdt_driver);
+
+MODULE_AUTHOR("S Twiss <stwiss.opensource@diasemi.com>");
+MODULE_DESCRIPTION("WDT device driver for Dialog DA9062");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:da9062-watchdog");
diff --git a/drivers/watchdog/digicolor_wdt.c b/drivers/watchdog/digicolor_wdt.c
new file mode 100644
index 0000000..31d8e49
--- /dev/null
+++ b/drivers/watchdog/digicolor_wdt.c
@@ -0,0 +1,205 @@
+/*
+ * Watchdog driver for Conexant Digicolor
+ *
+ * Copyright (C) 2015 Paradox Innovation Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/delay.h>
+#include <linux/clk.h>
+#include <linux/watchdog.h>
+#include <linux/reboot.h>
+#include <linux/platform_device.h>
+#include <linux/of_address.h>
+
+#define TIMER_A_CONTROL		0
+#define TIMER_A_COUNT		4
+
+#define TIMER_A_ENABLE_COUNT	BIT(0)
+#define TIMER_A_ENABLE_WATCHDOG	BIT(1)
+
+struct dc_wdt {
+	void __iomem		*base;
+	struct clk		*clk;
+	struct notifier_block	restart_handler;
+	spinlock_t		lock;
+};
+
+static unsigned timeout;
+module_param(timeout, uint, 0);
+MODULE_PARM_DESC(timeout, "Watchdog timeout in seconds");
+
+static void dc_wdt_set(struct dc_wdt *wdt, u32 ticks)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&wdt->lock, flags);
+
+	writel_relaxed(0, wdt->base + TIMER_A_CONTROL);
+	writel_relaxed(ticks, wdt->base + TIMER_A_COUNT);
+	writel_relaxed(TIMER_A_ENABLE_COUNT | TIMER_A_ENABLE_WATCHDOG,
+		       wdt->base + TIMER_A_CONTROL);
+
+	spin_unlock_irqrestore(&wdt->lock, flags);
+}
+
+static int dc_restart_handler(struct notifier_block *this, unsigned long mode,
+			      void *cmd)
+{
+	struct dc_wdt *wdt = container_of(this, struct dc_wdt, restart_handler);
+
+	dc_wdt_set(wdt, 1);
+	/* wait for reset to assert... */
+	mdelay(500);
+
+	return NOTIFY_DONE;
+}
+
+static int dc_wdt_start(struct watchdog_device *wdog)
+{
+	struct dc_wdt *wdt = watchdog_get_drvdata(wdog);
+
+	dc_wdt_set(wdt, wdog->timeout * clk_get_rate(wdt->clk));
+
+	return 0;
+}
+
+static int dc_wdt_stop(struct watchdog_device *wdog)
+{
+	struct dc_wdt *wdt = watchdog_get_drvdata(wdog);
+
+	writel_relaxed(0, wdt->base + TIMER_A_CONTROL);
+
+	return 0;
+}
+
+static int dc_wdt_set_timeout(struct watchdog_device *wdog, unsigned int t)
+{
+	struct dc_wdt *wdt = watchdog_get_drvdata(wdog);
+
+	dc_wdt_set(wdt, t * clk_get_rate(wdt->clk));
+	wdog->timeout = t;
+
+	return 0;
+}
+
+static unsigned int dc_wdt_get_timeleft(struct watchdog_device *wdog)
+{
+	struct dc_wdt *wdt = watchdog_get_drvdata(wdog);
+	uint32_t count = readl_relaxed(wdt->base + TIMER_A_COUNT);
+
+	return count / clk_get_rate(wdt->clk);
+}
+
+static struct watchdog_ops dc_wdt_ops = {
+	.owner		= THIS_MODULE,
+	.start		= dc_wdt_start,
+	.stop		= dc_wdt_stop,
+	.set_timeout	= dc_wdt_set_timeout,
+	.get_timeleft	= dc_wdt_get_timeleft,
+};
+
+static struct watchdog_info dc_wdt_info = {
+	.options	= WDIOF_SETTIMEOUT | WDIOF_MAGICCLOSE
+			| WDIOF_KEEPALIVEPING,
+	.identity	= "Conexant Digicolor Watchdog",
+};
+
+static struct watchdog_device dc_wdt_wdd = {
+	.info		= &dc_wdt_info,
+	.ops		= &dc_wdt_ops,
+	.min_timeout	= 1,
+};
+
+static int dc_wdt_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct dc_wdt *wdt;
+	int ret;
+
+	wdt = devm_kzalloc(dev, sizeof(struct dc_wdt), GFP_KERNEL);
+	if (!wdt)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, wdt);
+
+	wdt->base = of_iomap(np, 0);
+	if (!wdt->base) {
+		dev_err(dev, "Failed to remap watchdog regs");
+		return -ENODEV;
+	}
+
+	wdt->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(wdt->clk)) {
+		ret = PTR_ERR(wdt->clk);
+		goto err_iounmap;
+	}
+	dc_wdt_wdd.max_timeout = U32_MAX / clk_get_rate(wdt->clk);
+	dc_wdt_wdd.timeout = dc_wdt_wdd.max_timeout;
+
+	spin_lock_init(&wdt->lock);
+
+	watchdog_set_drvdata(&dc_wdt_wdd, wdt);
+	watchdog_init_timeout(&dc_wdt_wdd, timeout, dev);
+	ret = watchdog_register_device(&dc_wdt_wdd);
+	if (ret) {
+		dev_err(dev, "Failed to register watchdog device");
+		goto err_iounmap;
+	}
+
+	wdt->restart_handler.notifier_call = dc_restart_handler;
+	wdt->restart_handler.priority = 128;
+	ret = register_restart_handler(&wdt->restart_handler);
+	if (ret)
+		dev_warn(&pdev->dev, "cannot register restart handler\n");
+
+	return 0;
+
+err_iounmap:
+	iounmap(wdt->base);
+	return ret;
+}
+
+static int dc_wdt_remove(struct platform_device *pdev)
+{
+	struct dc_wdt *wdt = platform_get_drvdata(pdev);
+
+	unregister_restart_handler(&wdt->restart_handler);
+	watchdog_unregister_device(&dc_wdt_wdd);
+	iounmap(wdt->base);
+
+	return 0;
+}
+
+static void dc_wdt_shutdown(struct platform_device *pdev)
+{
+	dc_wdt_stop(&dc_wdt_wdd);
+}
+
+static const struct of_device_id dc_wdt_of_match[] = {
+	{ .compatible = "cnxt,cx92755-wdt", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, dc_wdt_of_match);
+
+static struct platform_driver dc_wdt_driver = {
+	.probe		= dc_wdt_probe,
+	.remove		= dc_wdt_remove,
+	.shutdown	= dc_wdt_shutdown,
+	.driver = {
+		.name =		"digicolor-wdt",
+		.of_match_table = dc_wdt_of_match,
+	},
+};
+module_platform_driver(dc_wdt_driver);
+
+MODULE_AUTHOR("Baruch Siach <baruch@tkos.co.il>");
+MODULE_DESCRIPTION("Driver for Conexant Digicolor watchdog timer");
+MODULE_LICENSE("GPL");
diff --git a/drivers/watchdog/dw_wdt.c b/drivers/watchdog/dw_wdt.c
index d0bb949..6ea0634 100644
--- a/drivers/watchdog/dw_wdt.c
+++ b/drivers/watchdog/dw_wdt.c
@@ -35,7 +35,6 @@
 #include <linux/pm.h>
 #include <linux/platform_device.h>
 #include <linux/reboot.h>
-#include <linux/spinlock.h>
 #include <linux/timer.h>
 #include <linux/uaccess.h>
 #include <linux/watchdog.h>
@@ -61,7 +60,6 @@
 #define WDT_TIMEOUT		(HZ / 2)
 
 static struct {
-	spinlock_t		lock;
 	void __iomem		*regs;
 	struct clk		*clk;
 	unsigned long		in_use;
@@ -177,7 +175,6 @@
 	/* Make sure we don't get unloaded. */
 	__module_get(THIS_MODULE);
 
-	spin_lock(&dw_wdt.lock);
 	if (!dw_wdt_is_enabled()) {
 		/*
 		 * The watchdog is not currently enabled. Set the timeout to
@@ -190,8 +187,6 @@
 
 	dw_wdt_set_next_heartbeat();
 
-	spin_unlock(&dw_wdt.lock);
-
 	return nonseekable_open(inode, filp);
 }
 
@@ -220,6 +215,7 @@
 	}
 
 	dw_wdt_set_next_heartbeat();
+	dw_wdt_keepalive();
 	mod_timer(&dw_wdt.timer, jiffies + WDT_TIMEOUT);
 
 	return len;
@@ -348,8 +344,6 @@
 	if (ret)
 		return ret;
 
-	spin_lock_init(&dw_wdt.lock);
-
 	ret = misc_register(&dw_wdt_miscdev);
 	if (ret)
 		goto out_disable_clk;
diff --git a/drivers/watchdog/gpio_wdt.c b/drivers/watchdog/gpio_wdt.c
index cbc313d..1687cc2 100644
--- a/drivers/watchdog/gpio_wdt.c
+++ b/drivers/watchdog/gpio_wdt.c
@@ -267,7 +267,16 @@
 	.probe	= gpio_wdt_probe,
 	.remove	= gpio_wdt_remove,
 };
+
+#ifdef CONFIG_GPIO_WATCHDOG_ARCH_INITCALL
+static int __init gpio_wdt_init(void)
+{
+	return platform_driver_register(&gpio_wdt_driver);
+}
+arch_initcall(gpio_wdt_init);
+#else
 module_platform_driver(gpio_wdt_driver);
+#endif
 
 MODULE_AUTHOR("Alexander Shiyan <shc_work@mail.ru>");
 MODULE_DESCRIPTION("GPIO Watchdog");
diff --git a/drivers/watchdog/hpwdt.c b/drivers/watchdog/hpwdt.c
index ada3e44..286369d 100644
--- a/drivers/watchdog/hpwdt.c
+++ b/drivers/watchdog/hpwdt.c
@@ -588,7 +588,7 @@
 {
 	void __user *argp = (void __user *)arg;
 	int __user *p = argp;
-	int new_margin;
+	int new_margin, options;
 	int ret = -ENOTTY;
 
 	switch (cmd) {
@@ -608,6 +608,20 @@
 		ret = 0;
 		break;
 
+	case WDIOC_SETOPTIONS:
+		ret = get_user(options, p);
+		if (ret)
+			break;
+
+		if (options & WDIOS_DISABLECARD)
+			hpwdt_stop();
+
+		if (options & WDIOS_ENABLECARD) {
+			hpwdt_start();
+			hpwdt_ping();
+		}
+		break;
+
 	case WDIOC_SETTIMEOUT:
 		ret = get_user(new_margin, p);
 		if (ret)
diff --git a/drivers/watchdog/imgpdc_wdt.c b/drivers/watchdog/imgpdc_wdt.c
index 0deaa4f..0f73621 100644
--- a/drivers/watchdog/imgpdc_wdt.c
+++ b/drivers/watchdog/imgpdc_wdt.c
@@ -9,6 +9,35 @@
  *
  * Based on drivers/watchdog/sunxi_wdt.c Copyright (c) 2013 Carlo Caione
  *                                                     2012 Henrik Nordstrom
+ *
+ * Notes
+ * -----
+ * The timeout value is rounded to the next power of two clock cycles.
+ * This is configured using the PDC_WDT_CONFIG register, according to this
+ * formula:
+ *
+ *     timeout = 2^(delay + 1) clock cycles
+ *
+ * Where 'delay' is the value written in PDC_WDT_CONFIG register.
+ *
+ * Therefore, the hardware only allows to program watchdog timeouts, expressed
+ * as a power of two number of watchdog clock cycles. The current implementation
+ * guarantees that the actual watchdog timeout will be _at least_ the value
+ * programmed in the imgpdg_wdt driver.
+ *
+ * The following table shows how the user-configured timeout relates
+ * to the actual hardware timeout (watchdog clock @ 40000 Hz):
+ *
+ * input timeout | WD_DELAY | actual timeout
+ * -----------------------------------
+ *      10       |   18     |  13 seconds
+ *      20       |   19     |  26 seconds
+ *      30       |   20     |  52 seconds
+ *      60       |   21     |  104 seconds
+ *
+ * Albeit coarse, this granularity would suffice most watchdog uses.
+ * If the platform allows it, the user should be able to change the watchdog
+ * clock rate and achieve a finer timeout granularity.
  */
 
 #include <linux/clk.h>
@@ -16,6 +45,7 @@
 #include <linux/log2.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/reboot.h>
 #include <linux/slab.h>
 #include <linux/watchdog.h>
 
@@ -42,7 +72,7 @@
 #define PDC_WDT_MIN_TIMEOUT		1
 #define PDC_WDT_DEF_TIMEOUT		64
 
-static int heartbeat = PDC_WDT_DEF_TIMEOUT;
+static int heartbeat;
 module_param(heartbeat, int, 0);
 MODULE_PARM_DESC(heartbeat, "Watchdog heartbeats in seconds "
 	"(default=" __MODULE_STRING(PDC_WDT_DEF_TIMEOUT) ")");
@@ -57,6 +87,7 @@
 	struct clk *wdt_clk;
 	struct clk *sys_clk;
 	void __iomem *base;
+	struct notifier_block restart_handler;
 };
 
 static int pdc_wdt_keepalive(struct watchdog_device *wdt_dev)
@@ -84,18 +115,24 @@
 	return 0;
 }
 
+static void __pdc_wdt_set_timeout(struct pdc_wdt_dev *wdt)
+{
+	unsigned long clk_rate = clk_get_rate(wdt->wdt_clk);
+	unsigned int val;
+
+	val = readl(wdt->base + PDC_WDT_CONFIG) & ~PDC_WDT_CONFIG_DELAY_MASK;
+	val |= order_base_2(wdt->wdt_dev.timeout * clk_rate) - 1;
+	writel(val, wdt->base + PDC_WDT_CONFIG);
+}
+
 static int pdc_wdt_set_timeout(struct watchdog_device *wdt_dev,
 			       unsigned int new_timeout)
 {
-	unsigned int val;
 	struct pdc_wdt_dev *wdt = watchdog_get_drvdata(wdt_dev);
-	unsigned long clk_rate = clk_get_rate(wdt->wdt_clk);
 
 	wdt->wdt_dev.timeout = new_timeout;
 
-	val = readl(wdt->base + PDC_WDT_CONFIG) & ~PDC_WDT_CONFIG_DELAY_MASK;
-	val |= order_base_2(new_timeout * clk_rate) - 1;
-	writel(val, wdt->base + PDC_WDT_CONFIG);
+	__pdc_wdt_set_timeout(wdt);
 
 	return 0;
 }
@@ -106,6 +143,8 @@
 	unsigned int val;
 	struct pdc_wdt_dev *wdt = watchdog_get_drvdata(wdt_dev);
 
+	__pdc_wdt_set_timeout(wdt);
+
 	val = readl(wdt->base + PDC_WDT_CONFIG);
 	val |= PDC_WDT_CONFIG_ENABLE;
 	writel(val, wdt->base + PDC_WDT_CONFIG);
@@ -128,8 +167,21 @@
 	.set_timeout	= pdc_wdt_set_timeout,
 };
 
+static int pdc_wdt_restart(struct notifier_block *this, unsigned long mode,
+			   void *cmd)
+{
+	struct pdc_wdt_dev *wdt = container_of(this, struct pdc_wdt_dev,
+					       restart_handler);
+
+	/* Assert SOFT_RESET */
+	writel(0x1, wdt->base + PDC_WDT_SOFT_RESET);
+
+	return NOTIFY_OK;
+}
+
 static int pdc_wdt_probe(struct platform_device *pdev)
 {
+	u64 div;
 	int ret, val;
 	unsigned long clk_rate;
 	struct resource *res;
@@ -189,16 +241,15 @@
 
 	pdc_wdt->wdt_dev.info = &pdc_wdt_info;
 	pdc_wdt->wdt_dev.ops = &pdc_wdt_ops;
-	pdc_wdt->wdt_dev.max_timeout = 1 << PDC_WDT_CONFIG_DELAY_MASK;
+
+	div = 1ULL << (PDC_WDT_CONFIG_DELAY_MASK + 1);
+	do_div(div, clk_rate);
+	pdc_wdt->wdt_dev.max_timeout = div;
+	pdc_wdt->wdt_dev.timeout = PDC_WDT_DEF_TIMEOUT;
 	pdc_wdt->wdt_dev.parent = &pdev->dev;
 	watchdog_set_drvdata(&pdc_wdt->wdt_dev, pdc_wdt);
 
-	ret = watchdog_init_timeout(&pdc_wdt->wdt_dev, heartbeat, &pdev->dev);
-	if (ret < 0) {
-		pdc_wdt->wdt_dev.timeout = pdc_wdt->wdt_dev.max_timeout;
-		dev_warn(&pdev->dev,
-			 "Initial timeout out of range! setting max timeout\n");
-	}
+	watchdog_init_timeout(&pdc_wdt->wdt_dev, heartbeat, &pdev->dev);
 
 	pdc_wdt_stop(&pdc_wdt->wdt_dev);
 
@@ -238,6 +289,13 @@
 	if (ret)
 		goto disable_wdt_clk;
 
+	pdc_wdt->restart_handler.notifier_call = pdc_wdt_restart;
+	pdc_wdt->restart_handler.priority = 128;
+	ret = register_restart_handler(&pdc_wdt->restart_handler);
+	if (ret)
+		dev_warn(&pdev->dev, "failed to register restart handler: %d\n",
+			 ret);
+
 	return 0;
 
 disable_wdt_clk:
diff --git a/drivers/watchdog/imx2_wdt.c b/drivers/watchdog/imx2_wdt.c
index 5e6d808..0bb1a1d 100644
--- a/drivers/watchdog/imx2_wdt.c
+++ b/drivers/watchdog/imx2_wdt.c
@@ -166,6 +166,8 @@
 {
 	struct imx2_wdt_device *wdev = watchdog_get_drvdata(wdog);
 
+	wdog->timeout = new_timeout;
+
 	regmap_update_bits(wdev->regmap, IMX2_WDT_WCR, IMX2_WDT_WCR_WT,
 			   WDOG_SEC_TO_COUNT(new_timeout));
 	return 0;
@@ -256,8 +258,11 @@
 	wdog->ops		= &imx2_wdt_ops;
 	wdog->min_timeout	= 1;
 	wdog->max_timeout	= IMX2_WDT_MAX_TIME;
+	wdog->parent		= &pdev->dev;
 
-	clk_prepare_enable(wdev->clk);
+	ret = clk_prepare_enable(wdev->clk);
+	if (ret)
+		return ret;
 
 	regmap_read(wdev->regmap, IMX2_WDT_WRSR, &val);
 	wdog->bootstatus = val & IMX2_WDT_WRSR_TOUT ? WDIOF_CARDRESET : 0;
@@ -286,7 +291,7 @@
 	ret = watchdog_register_device(wdog);
 	if (ret) {
 		dev_err(&pdev->dev, "cannot register watchdog device\n");
-		return ret;
+		goto disable_clk;
 	}
 
 	wdev->restart_handler.notifier_call = imx2_restart_handler;
@@ -299,6 +304,10 @@
 		 wdog->timeout, nowayout);
 
 	return 0;
+
+disable_clk:
+	clk_disable_unprepare(wdev->clk);
+	return ret;
 }
 
 static int __exit imx2_wdt_remove(struct platform_device *pdev)
@@ -362,8 +371,11 @@
 {
 	struct watchdog_device *wdog = dev_get_drvdata(dev);
 	struct imx2_wdt_device *wdev = watchdog_get_drvdata(wdog);
+	int ret;
 
-	clk_prepare_enable(wdev->clk);
+	ret = clk_prepare_enable(wdev->clk);
+	if (ret)
+		return ret;
 
 	if (watchdog_active(wdog) && !imx2_wdt_is_running(wdev)) {
 		/*
diff --git a/drivers/watchdog/max63xx_wdt.c b/drivers/watchdog/max63xx_wdt.c
index 08da311..f36ca4b 100644
--- a/drivers/watchdog/max63xx_wdt.c
+++ b/drivers/watchdog/max63xx_wdt.c
@@ -39,10 +39,22 @@
 #define MAX6369_WDSET	(7 << 0)
 #define MAX6369_WDI	(1 << 3)
 
-static DEFINE_SPINLOCK(io_lock);
+#define MAX6369_WDSET_DISABLED	3
 
 static int nodelay;
-static void __iomem	*wdt_base;
+
+struct max63xx_wdt {
+	struct watchdog_device wdd;
+	const struct max63xx_timeout *timeout;
+
+	/* memory mapping */
+	void __iomem *base;
+	spinlock_t lock;
+
+	/* WDI and WSET bits write access routines */
+	void (*ping)(struct max63xx_wdt *wdt);
+	void (*set)(struct max63xx_wdt *wdt, u8 set);
+};
 
 /*
  * The timeout values used are actually the absolute minimum the chip
@@ -59,25 +71,25 @@
 
 /* Timeouts in second */
 struct max63xx_timeout {
-	u8 wdset;
-	u8 tdelay;
-	u8 twd;
+	const u8 wdset;
+	const u8 tdelay;
+	const u8 twd;
 };
 
-static struct max63xx_timeout max6369_table[] = {
+static const struct max63xx_timeout max6369_table[] = {
 	{ 5,  1,  1 },
 	{ 6, 10, 10 },
 	{ 7, 60, 60 },
 	{ },
 };
 
-static struct max63xx_timeout max6371_table[] = {
+static const struct max63xx_timeout max6371_table[] = {
 	{ 6, 60,  3 },
 	{ 7, 60, 60 },
 	{ },
 };
 
-static struct max63xx_timeout max6373_table[] = {
+static const struct max63xx_timeout max6373_table[] = {
 	{ 2, 60,  1 },
 	{ 5,  0,  1 },
 	{ 1,  3,  3 },
@@ -86,8 +98,6 @@
 	{ },
 };
 
-static struct max63xx_timeout *current_timeout;
-
 static struct max63xx_timeout *
 max63xx_select_timeout(struct max63xx_timeout *table, int value)
 {
@@ -108,59 +118,32 @@
 
 static int max63xx_wdt_ping(struct watchdog_device *wdd)
 {
-	u8 val;
+	struct max63xx_wdt *wdt = watchdog_get_drvdata(wdd);
 
-	spin_lock(&io_lock);
-
-	val = __raw_readb(wdt_base);
-
-	__raw_writeb(val | MAX6369_WDI, wdt_base);
-	__raw_writeb(val & ~MAX6369_WDI, wdt_base);
-
-	spin_unlock(&io_lock);
+	wdt->ping(wdt);
 	return 0;
 }
 
 static int max63xx_wdt_start(struct watchdog_device *wdd)
 {
-	struct max63xx_timeout *entry = watchdog_get_drvdata(wdd);
-	u8 val;
+	struct max63xx_wdt *wdt = watchdog_get_drvdata(wdd);
 
-	spin_lock(&io_lock);
-
-	val = __raw_readb(wdt_base);
-	val &= ~MAX6369_WDSET;
-	val |= entry->wdset;
-	__raw_writeb(val, wdt_base);
-
-	spin_unlock(&io_lock);
+	wdt->set(wdt, wdt->timeout->wdset);
 
 	/* check for a edge triggered startup */
-	if (entry->tdelay == 0)
-		max63xx_wdt_ping(wdd);
+	if (wdt->timeout->tdelay == 0)
+		wdt->ping(wdt);
 	return 0;
 }
 
 static int max63xx_wdt_stop(struct watchdog_device *wdd)
 {
-	u8 val;
+	struct max63xx_wdt *wdt = watchdog_get_drvdata(wdd);
 
-	spin_lock(&io_lock);
-
-	val = __raw_readb(wdt_base);
-	val &= ~MAX6369_WDSET;
-	val |= 3;
-	__raw_writeb(val, wdt_base);
-
-	spin_unlock(&io_lock);
+	wdt->set(wdt, MAX6369_WDSET_DISABLED);
 	return 0;
 }
 
-static const struct watchdog_info max63xx_wdt_info = {
-	.options = WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE,
-	.identity = "max63xx Watchdog",
-};
-
 static const struct watchdog_ops max63xx_wdt_ops = {
 	.owner = THIS_MODULE,
 	.start = max63xx_wdt_start,
@@ -168,53 +151,108 @@
 	.ping = max63xx_wdt_ping,
 };
 
-static struct watchdog_device max63xx_wdt_dev = {
-	.info = &max63xx_wdt_info,
-	.ops = &max63xx_wdt_ops,
+static const struct watchdog_info max63xx_wdt_info = {
+	.options = WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE,
+	.identity = "max63xx Watchdog",
 };
 
+static void max63xx_mmap_ping(struct max63xx_wdt *wdt)
+{
+	u8 val;
+
+	spin_lock(&wdt->lock);
+
+	val = __raw_readb(wdt->base);
+
+	__raw_writeb(val | MAX6369_WDI, wdt->base);
+	__raw_writeb(val & ~MAX6369_WDI, wdt->base);
+
+	spin_unlock(&wdt->lock);
+}
+
+static void max63xx_mmap_set(struct max63xx_wdt *wdt, u8 set)
+{
+	u8 val;
+
+	spin_lock(&wdt->lock);
+
+	val = __raw_readb(wdt->base);
+	val &= ~MAX6369_WDSET;
+	val |= set & MAX6369_WDSET;
+	__raw_writeb(val, wdt->base);
+
+	spin_unlock(&wdt->lock);
+}
+
+static int max63xx_mmap_init(struct platform_device *p, struct max63xx_wdt *wdt)
+{
+	struct resource *mem = platform_get_resource(p, IORESOURCE_MEM, 0);
+
+	wdt->base = devm_ioremap_resource(&p->dev, mem);
+	if (IS_ERR(wdt->base))
+		return PTR_ERR(wdt->base);
+
+	spin_lock_init(&wdt->lock);
+
+	wdt->ping = max63xx_mmap_ping;
+	wdt->set = max63xx_mmap_set;
+	return 0;
+}
+
 static int max63xx_wdt_probe(struct platform_device *pdev)
 {
-	struct resource	*wdt_mem;
+	struct max63xx_wdt *wdt;
 	struct max63xx_timeout *table;
+	int err;
+
+	wdt = devm_kzalloc(&pdev->dev, sizeof(*wdt), GFP_KERNEL);
+	if (!wdt)
+		return -ENOMEM;
 
 	table = (struct max63xx_timeout *)pdev->id_entry->driver_data;
 
 	if (heartbeat < 1 || heartbeat > MAX_HEARTBEAT)
 		heartbeat = DEFAULT_HEARTBEAT;
 
-	dev_info(&pdev->dev, "requesting %ds heartbeat\n", heartbeat);
-	current_timeout = max63xx_select_timeout(table, heartbeat);
-
-	if (!current_timeout) {
-		dev_err(&pdev->dev, "unable to satisfy heartbeat request\n");
+	wdt->timeout = max63xx_select_timeout(table, heartbeat);
+	if (!wdt->timeout) {
+		dev_err(&pdev->dev, "unable to satisfy %ds heartbeat request\n",
+			heartbeat);
 		return -EINVAL;
 	}
 
+	err = max63xx_mmap_init(pdev, wdt);
+	if (err)
+		return err;
+
+	platform_set_drvdata(pdev, &wdt->wdd);
+	watchdog_set_drvdata(&wdt->wdd, wdt);
+
+	wdt->wdd.parent = &pdev->dev;
+	wdt->wdd.timeout = wdt->timeout->twd;
+	wdt->wdd.info = &max63xx_wdt_info;
+	wdt->wdd.ops = &max63xx_wdt_ops;
+
+	watchdog_set_nowayout(&wdt->wdd, nowayout);
+
+	err = watchdog_register_device(&wdt->wdd);
+	if (err)
+		return err;
+
 	dev_info(&pdev->dev, "using %ds heartbeat with %ds initial delay\n",
-		 current_timeout->twd, current_timeout->tdelay);
-
-	heartbeat = current_timeout->twd;
-
-	wdt_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	wdt_base = devm_ioremap_resource(&pdev->dev, wdt_mem);
-	if (IS_ERR(wdt_base))
-		return PTR_ERR(wdt_base);
-
-	max63xx_wdt_dev.timeout = heartbeat;
-	watchdog_set_nowayout(&max63xx_wdt_dev, nowayout);
-	watchdog_set_drvdata(&max63xx_wdt_dev, current_timeout);
-
-	return watchdog_register_device(&max63xx_wdt_dev);
+		 wdt->timeout->twd, wdt->timeout->tdelay);
+	return 0;
 }
 
 static int max63xx_wdt_remove(struct platform_device *pdev)
 {
-	watchdog_unregister_device(&max63xx_wdt_dev);
+	struct watchdog_device *wdd = platform_get_drvdata(pdev);
+
+	watchdog_unregister_device(wdd);
 	return 0;
 }
 
-static struct platform_device_id max63xx_id_table[] = {
+static const struct platform_device_id max63xx_id_table[] = {
 	{ "max6369_wdt", (kernel_ulong_t)max6369_table, },
 	{ "max6370_wdt", (kernel_ulong_t)max6369_table, },
 	{ "max6371_wdt", (kernel_ulong_t)max6371_table, },
diff --git a/drivers/watchdog/mena21_wdt.c b/drivers/watchdog/mena21_wdt.c
index 96dbba9..d193a5e 100644
--- a/drivers/watchdog/mena21_wdt.c
+++ b/drivers/watchdog/mena21_wdt.c
@@ -208,14 +208,15 @@
 	else if (reset == 7)
 		a21_wdt.bootstatus |= WDIOF_EXTERN2;
 
+	drv->wdt = a21_wdt;
+	dev_set_drvdata(&pdev->dev, drv);
+
 	ret = watchdog_register_device(&a21_wdt);
 	if (ret) {
 		dev_err(&pdev->dev, "Cannot register watchdog device\n");
 		goto err_register_wd;
 	}
 
-	dev_set_drvdata(&pdev->dev, drv);
-
 	dev_info(&pdev->dev, "MEN A21 watchdog timer driver enabled\n");
 
 	return 0;
diff --git a/drivers/watchdog/omap_wdt.c b/drivers/watchdog/omap_wdt.c
index 1e6be9e..de911c7 100644
--- a/drivers/watchdog/omap_wdt.c
+++ b/drivers/watchdog/omap_wdt.c
@@ -53,7 +53,15 @@
 module_param(timer_margin, uint, 0);
 MODULE_PARM_DESC(timer_margin, "initial watchdog timeout (in seconds)");
 
+#define to_omap_wdt_dev(_wdog)	container_of(_wdog, struct omap_wdt_dev, wdog)
+
+static bool early_enable;
+module_param(early_enable, bool, 0);
+MODULE_PARM_DESC(early_enable,
+	"Watchdog is started on module insertion (default=0)");
+
 struct omap_wdt_dev {
+	struct watchdog_device wdog;
 	void __iomem    *base;          /* physical */
 	struct device   *dev;
 	bool		omap_wdt_users;
@@ -123,7 +131,7 @@
 
 static int omap_wdt_start(struct watchdog_device *wdog)
 {
-	struct omap_wdt_dev *wdev = watchdog_get_drvdata(wdog);
+	struct omap_wdt_dev *wdev = to_omap_wdt_dev(wdog);
 	void __iomem *base = wdev->base;
 
 	mutex_lock(&wdev->lock);
@@ -132,6 +140,13 @@
 
 	pm_runtime_get_sync(wdev->dev);
 
+	/*
+	 * Make sure the watchdog is disabled. This is unfortunately required
+	 * because writing to various registers with the watchdog running has no
+	 * effect.
+	 */
+	omap_wdt_disable(wdev);
+
 	/* initialize prescaler */
 	while (readl_relaxed(base + OMAP_WATCHDOG_WPS) & 0x01)
 		cpu_relax();
@@ -151,7 +166,7 @@
 
 static int omap_wdt_stop(struct watchdog_device *wdog)
 {
-	struct omap_wdt_dev *wdev = watchdog_get_drvdata(wdog);
+	struct omap_wdt_dev *wdev = to_omap_wdt_dev(wdog);
 
 	mutex_lock(&wdev->lock);
 	omap_wdt_disable(wdev);
@@ -163,7 +178,7 @@
 
 static int omap_wdt_ping(struct watchdog_device *wdog)
 {
-	struct omap_wdt_dev *wdev = watchdog_get_drvdata(wdog);
+	struct omap_wdt_dev *wdev = to_omap_wdt_dev(wdog);
 
 	mutex_lock(&wdev->lock);
 	omap_wdt_reload(wdev);
@@ -175,7 +190,7 @@
 static int omap_wdt_set_timeout(struct watchdog_device *wdog,
 				unsigned int timeout)
 {
-	struct omap_wdt_dev *wdev = watchdog_get_drvdata(wdog);
+	struct omap_wdt_dev *wdev = to_omap_wdt_dev(wdog);
 
 	mutex_lock(&wdev->lock);
 	omap_wdt_disable(wdev);
@@ -188,6 +203,16 @@
 	return 0;
 }
 
+static unsigned int omap_wdt_get_timeleft(struct watchdog_device *wdog)
+{
+	struct omap_wdt_dev *wdev = watchdog_get_drvdata(wdog);
+	void __iomem *base = wdev->base;
+	u32 value;
+
+	value = readl_relaxed(base + OMAP_WATCHDOG_CRR);
+	return GET_WCCR_SECS(value);
+}
+
 static const struct watchdog_info omap_wdt_info = {
 	.options = WDIOF_SETTIMEOUT | WDIOF_MAGICCLOSE | WDIOF_KEEPALIVEPING,
 	.identity = "OMAP Watchdog",
@@ -199,21 +224,16 @@
 	.stop		= omap_wdt_stop,
 	.ping		= omap_wdt_ping,
 	.set_timeout	= omap_wdt_set_timeout,
+	.get_timeleft	= omap_wdt_get_timeleft,
 };
 
 static int omap_wdt_probe(struct platform_device *pdev)
 {
 	struct omap_wd_timer_platform_data *pdata = dev_get_platdata(&pdev->dev);
-	struct watchdog_device *omap_wdt;
 	struct resource *res;
 	struct omap_wdt_dev *wdev;
-	u32 rs;
 	int ret;
 
-	omap_wdt = devm_kzalloc(&pdev->dev, sizeof(*omap_wdt), GFP_KERNEL);
-	if (!omap_wdt)
-		return -ENOMEM;
-
 	wdev = devm_kzalloc(&pdev->dev, sizeof(*wdev), GFP_KERNEL);
 	if (!wdev)
 		return -ENOMEM;
@@ -229,35 +249,30 @@
 	if (IS_ERR(wdev->base))
 		return PTR_ERR(wdev->base);
 
-	omap_wdt->info	      = &omap_wdt_info;
-	omap_wdt->ops	      = &omap_wdt_ops;
-	omap_wdt->min_timeout = TIMER_MARGIN_MIN;
-	omap_wdt->max_timeout = TIMER_MARGIN_MAX;
+	wdev->wdog.info = &omap_wdt_info;
+	wdev->wdog.ops = &omap_wdt_ops;
+	wdev->wdog.min_timeout = TIMER_MARGIN_MIN;
+	wdev->wdog.max_timeout = TIMER_MARGIN_MAX;
 
-	if (timer_margin >= TIMER_MARGIN_MIN &&
-	    timer_margin <= TIMER_MARGIN_MAX)
-		omap_wdt->timeout = timer_margin;
-	else
-		omap_wdt->timeout = TIMER_MARGIN_DEFAULT;
+	if (watchdog_init_timeout(&wdev->wdog, timer_margin, &pdev->dev) < 0)
+		wdev->wdog.timeout = TIMER_MARGIN_DEFAULT;
 
-	watchdog_set_drvdata(omap_wdt, wdev);
-	watchdog_set_nowayout(omap_wdt, nowayout);
+	watchdog_set_nowayout(&wdev->wdog, nowayout);
 
-	platform_set_drvdata(pdev, omap_wdt);
+	platform_set_drvdata(pdev, wdev);
 
 	pm_runtime_enable(wdev->dev);
 	pm_runtime_get_sync(wdev->dev);
 
-	if (pdata && pdata->read_reset_sources)
-		rs = pdata->read_reset_sources();
-	else
-		rs = 0;
-	omap_wdt->bootstatus = (rs & (1 << OMAP_MPU_WD_RST_SRC_ID_SHIFT)) ?
-				WDIOF_CARDRESET : 0;
+	if (pdata && pdata->read_reset_sources) {
+		u32 rs = pdata->read_reset_sources();
+		if (rs & (1 << OMAP_MPU_WD_RST_SRC_ID_SHIFT))
+			wdev->wdog.bootstatus = WDIOF_CARDRESET;
+	}
 
 	omap_wdt_disable(wdev);
 
-	ret = watchdog_register_device(omap_wdt);
+	ret = watchdog_register_device(&wdev->wdog);
 	if (ret) {
 		pm_runtime_disable(wdev->dev);
 		return ret;
@@ -265,17 +280,19 @@
 
 	pr_info("OMAP Watchdog Timer Rev 0x%02x: initial timeout %d sec\n",
 		readl_relaxed(wdev->base + OMAP_WATCHDOG_REV) & 0xFF,
-		omap_wdt->timeout);
+		wdev->wdog.timeout);
 
 	pm_runtime_put_sync(wdev->dev);
 
+	if (early_enable)
+		omap_wdt_start(&wdev->wdog);
+
 	return 0;
 }
 
 static void omap_wdt_shutdown(struct platform_device *pdev)
 {
-	struct watchdog_device *wdog = platform_get_drvdata(pdev);
-	struct omap_wdt_dev *wdev = watchdog_get_drvdata(wdog);
+	struct omap_wdt_dev *wdev = platform_get_drvdata(pdev);
 
 	mutex_lock(&wdev->lock);
 	if (wdev->omap_wdt_users) {
@@ -287,11 +304,10 @@
 
 static int omap_wdt_remove(struct platform_device *pdev)
 {
-	struct watchdog_device *wdog = platform_get_drvdata(pdev);
-	struct omap_wdt_dev *wdev = watchdog_get_drvdata(wdog);
+	struct omap_wdt_dev *wdev = platform_get_drvdata(pdev);
 
 	pm_runtime_disable(wdev->dev);
-	watchdog_unregister_device(wdog);
+	watchdog_unregister_device(&wdev->wdog);
 
 	return 0;
 }
@@ -306,8 +322,7 @@
 
 static int omap_wdt_suspend(struct platform_device *pdev, pm_message_t state)
 {
-	struct watchdog_device *wdog = platform_get_drvdata(pdev);
-	struct omap_wdt_dev *wdev = watchdog_get_drvdata(wdog);
+	struct omap_wdt_dev *wdev = platform_get_drvdata(pdev);
 
 	mutex_lock(&wdev->lock);
 	if (wdev->omap_wdt_users) {
@@ -321,8 +336,7 @@
 
 static int omap_wdt_resume(struct platform_device *pdev)
 {
-	struct watchdog_device *wdog = platform_get_drvdata(pdev);
-	struct omap_wdt_dev *wdev = watchdog_get_drvdata(wdog);
+	struct omap_wdt_dev *wdev = platform_get_drvdata(pdev);
 
 	mutex_lock(&wdev->lock);
 	if (wdev->omap_wdt_users) {
diff --git a/drivers/watchdog/omap_wdt.h b/drivers/watchdog/omap_wdt.h
index 09b774c..42f31ec 100644
--- a/drivers/watchdog/omap_wdt.h
+++ b/drivers/watchdog/omap_wdt.h
@@ -50,5 +50,6 @@
 
 #define PTV			0	/* prescale */
 #define GET_WLDR_VAL(secs)	(0xffffffff - ((secs) * (32768/(1<<PTV))) + 1)
+#define GET_WCCR_SECS(val)	((0xffffffff - (val) + 1) / (32768/(1<<PTV)))
 
 #endif				/* _OMAP_WATCHDOG_H */
diff --git a/drivers/watchdog/st_lpc_wdt.c b/drivers/watchdog/st_lpc_wdt.c
index f32be15..6785afd 100644
--- a/drivers/watchdog/st_lpc_wdt.c
+++ b/drivers/watchdog/st_lpc_wdt.c
@@ -197,7 +197,7 @@
 		return -EINVAL;
 	}
 
-	/* LPC can either run in RTC or WDT mode */
+	/* LPC can either run as a Clocksource or in RTC or WDT mode */
 	if (mode != ST_LPC_MODE_WDT)
 		return -ENODEV;
 
diff --git a/drivers/watchdog/watchdog_core.c b/drivers/watchdog/watchdog_core.c
index cec9b55..1a80594 100644
--- a/drivers/watchdog/watchdog_core.c
+++ b/drivers/watchdog/watchdog_core.c
@@ -43,6 +43,45 @@
 static DEFINE_IDA(watchdog_ida);
 static struct class *watchdog_class;
 
+/*
+ * Deferred Registration infrastructure.
+ *
+ * Sometimes watchdog drivers needs to be loaded as soon as possible,
+ * for example when it's impossible to disable it. To do so,
+ * raising the initcall level of the watchdog driver is a solution.
+ * But in such case, the miscdev is maybe not ready (subsys_initcall), and
+ * watchdog_core need miscdev to register the watchdog as a char device.
+ *
+ * The deferred registration infrastructure offer a way for the watchdog
+ * subsystem to register a watchdog properly, even before miscdev is ready.
+ */
+
+static DEFINE_MUTEX(wtd_deferred_reg_mutex);
+static LIST_HEAD(wtd_deferred_reg_list);
+static bool wtd_deferred_reg_done;
+
+static int watchdog_deferred_registration_add(struct watchdog_device *wdd)
+{
+	list_add_tail(&wdd->deferred,
+		      &wtd_deferred_reg_list);
+	return 0;
+}
+
+static void watchdog_deferred_registration_del(struct watchdog_device *wdd)
+{
+	struct list_head *p, *n;
+	struct watchdog_device *wdd_tmp;
+
+	list_for_each_safe(p, n, &wtd_deferred_reg_list) {
+		wdd_tmp = list_entry(p, struct watchdog_device,
+				     deferred);
+		if (wdd_tmp == wdd) {
+			list_del(&wdd_tmp->deferred);
+			break;
+		}
+	}
+}
+
 static void watchdog_check_min_max_timeout(struct watchdog_device *wdd)
 {
 	/*
@@ -98,17 +137,7 @@
 }
 EXPORT_SYMBOL_GPL(watchdog_init_timeout);
 
-/**
- * watchdog_register_device() - register a watchdog device
- * @wdd: watchdog device
- *
- * Register a watchdog device with the kernel so that the
- * watchdog timer can be accessed from userspace.
- *
- * A zero is returned on success and a negative errno code for
- * failure.
- */
-int watchdog_register_device(struct watchdog_device *wdd)
+static int __watchdog_register_device(struct watchdog_device *wdd)
 {
 	int ret, id, devno;
 
@@ -164,16 +193,33 @@
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(watchdog_register_device);
 
 /**
- * watchdog_unregister_device() - unregister a watchdog device
- * @wdd: watchdog device to unregister
+ * watchdog_register_device() - register a watchdog device
+ * @wdd: watchdog device
  *
- * Unregister a watchdog device that was previously successfully
- * registered with watchdog_register_device().
+ * Register a watchdog device with the kernel so that the
+ * watchdog timer can be accessed from userspace.
+ *
+ * A zero is returned on success and a negative errno code for
+ * failure.
  */
-void watchdog_unregister_device(struct watchdog_device *wdd)
+
+int watchdog_register_device(struct watchdog_device *wdd)
+{
+	int ret;
+
+	mutex_lock(&wtd_deferred_reg_mutex);
+	if (wtd_deferred_reg_done)
+		ret = __watchdog_register_device(wdd);
+	else
+		ret = watchdog_deferred_registration_add(wdd);
+	mutex_unlock(&wtd_deferred_reg_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(watchdog_register_device);
+
+static void __watchdog_unregister_device(struct watchdog_device *wdd)
 {
 	int ret;
 	int devno;
@@ -189,8 +235,43 @@
 	ida_simple_remove(&watchdog_ida, wdd->id);
 	wdd->dev = NULL;
 }
+
+/**
+ * watchdog_unregister_device() - unregister a watchdog device
+ * @wdd: watchdog device to unregister
+ *
+ * Unregister a watchdog device that was previously successfully
+ * registered with watchdog_register_device().
+ */
+
+void watchdog_unregister_device(struct watchdog_device *wdd)
+{
+	mutex_lock(&wtd_deferred_reg_mutex);
+	if (wtd_deferred_reg_done)
+		__watchdog_unregister_device(wdd);
+	else
+		watchdog_deferred_registration_del(wdd);
+	mutex_unlock(&wtd_deferred_reg_mutex);
+}
+
 EXPORT_SYMBOL_GPL(watchdog_unregister_device);
 
+static int __init watchdog_deferred_registration(void)
+{
+	mutex_lock(&wtd_deferred_reg_mutex);
+	wtd_deferred_reg_done = true;
+	while (!list_empty(&wtd_deferred_reg_list)) {
+		struct watchdog_device *wdd;
+
+		wdd = list_first_entry(&wtd_deferred_reg_list,
+				       struct watchdog_device, deferred);
+		list_del(&wdd->deferred);
+		__watchdog_register_device(wdd);
+	}
+	mutex_unlock(&wtd_deferred_reg_mutex);
+	return 0;
+}
+
 static int __init watchdog_init(void)
 {
 	int err;
@@ -207,6 +288,7 @@
 		return err;
 	}
 
+	watchdog_deferred_registration();
 	return 0;
 }
 
@@ -217,7 +299,7 @@
 	ida_destroy(&watchdog_ida);
 }
 
-subsys_initcall(watchdog_init);
+subsys_initcall_sync(watchdog_init);
 module_exit(watchdog_exit);
 
 MODULE_AUTHOR("Alan Cox <alan@lxorguk.ukuu.org.uk>");
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 3838795..96093ae 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -39,8 +39,8 @@
 #include <asm/irq.h>
 #include <asm/idle.h>
 #include <asm/io_apic.h>
-#include <asm/xen/page.h>
 #include <asm/xen/pci.h>
+#include <xen/page.h>
 #endif
 #include <asm/sync_bitops.h>
 #include <asm/xen/hypercall.h>
diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c
index 417415d..ed673e1 100644
--- a/drivers/xen/events/events_fifo.c
+++ b/drivers/xen/events/events_fifo.c
@@ -44,13 +44,13 @@
 #include <asm/sync_bitops.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
-#include <asm/xen/page.h>
 
 #include <xen/xen.h>
 #include <xen/xen-ops.h>
 #include <xen/events.h>
 #include <xen/interface/xen.h>
 #include <xen/interface/event_channel.h>
+#include <xen/page.h>
 
 #include "events_internal.h"
 
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 8927485..67b9163 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -41,9 +41,9 @@
 #include <xen/balloon.h>
 #include <xen/gntdev.h>
 #include <xen/events.h>
+#include <xen/page.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
-#include <asm/xen/page.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Derek G. Murray <Derek.Murray@cl.cam.ac.uk>, "
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index b1c7170..62f591f 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -138,7 +138,6 @@
 static int gnttab_expand(unsigned int req_entries);
 
 #define RPP (PAGE_SIZE / sizeof(grant_ref_t))
-#define SPP (PAGE_SIZE / sizeof(grant_status_t))
 
 static inline grant_ref_t *__gnttab_entry(grant_ref_t entry)
 {
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index 9e6a851..d10effe 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -19,10 +19,10 @@
 #include <xen/grant_table.h>
 #include <xen/events.h>
 #include <xen/hvc-console.h>
+#include <xen/page.h>
 #include <xen/xen-ops.h>
 
 #include <asm/xen/hypercall.h>
-#include <asm/xen/page.h>
 #include <asm/xen/hypervisor.h>
 
 enum shutdown_state {
diff --git a/drivers/xen/tmem.c b/drivers/xen/tmem.c
index d88f367..239738f 100644
--- a/drivers/xen/tmem.c
+++ b/drivers/xen/tmem.c
@@ -17,8 +17,8 @@
 
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
+#include <xen/page.h>
 #include <asm/xen/hypercall.h>
-#include <asm/xen/page.h>
 #include <asm/xen/hypervisor.h>
 #include <xen/tmem.h>
 
@@ -389,7 +389,7 @@
 	}
 #endif
 #ifdef CONFIG_CLEANCACHE
-	BUG_ON(sizeof(struct cleancache_filekey) != sizeof(struct tmem_oid));
+	BUILD_BUG_ON(sizeof(struct cleancache_filekey) != sizeof(struct tmem_oid));
 	if (tmem_enabled && cleancache) {
 		int err;
 
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index 39223c3..9eeefd7 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -53,7 +53,6 @@
 
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
-#include <target/target_core_configfs.h>
 #include <target/target_core_fabric_configfs.h>
 
 #include <asm/hypervisor.h>
@@ -201,8 +200,6 @@
 static DEFINE_MUTEX(scsiback_mutex);
 static LIST_HEAD(scsiback_list);
 
-static const struct target_core_fabric_ops scsiback_ops;
-
 static void scsiback_get(struct vscsibk_info *info)
 {
 	atomic_inc(&info->nr_unreplied_reqs);
@@ -397,6 +394,7 @@
 	memset(se_cmd, 0, sizeof(*se_cmd));
 
 	scsiback_get(pending_req->info);
+	se_cmd->tag = pending_req->rqid;
 	rc = target_submit_cmd_map_sgls(se_cmd, sess, pending_req->cmnd,
 			pending_req->sense_buffer, pending_req->v2p->lun,
 			pending_req->data_len, 0,
@@ -863,7 +861,8 @@
 	struct list_head *head = &(info->v2p_entry_lists);
 	unsigned long flags;
 	char *lunp;
-	unsigned int lun;
+	unsigned long long unpacked_lun;
+	struct se_lun *se_lun;
 	struct scsiback_tpg *tpg_entry, *tpg = NULL;
 	char *error = "doesn't exist";
 
@@ -874,24 +873,27 @@
 	}
 	*lunp = 0;
 	lunp++;
-	if (kstrtouint(lunp, 10, &lun) || lun >= TRANSPORT_MAX_LUNS_PER_TPG) {
+	err = kstrtoull(lunp, 10, &unpacked_lun);
+	if (err < 0) {
 		pr_err("lun number not valid: %s\n", lunp);
-		return -EINVAL;
+		return err;
 	}
 
 	mutex_lock(&scsiback_mutex);
 	list_for_each_entry(tpg_entry, &scsiback_list, tv_tpg_list) {
 		if (!strcmp(phy, tpg_entry->tport->tport_name) ||
 		    !strcmp(phy, tpg_entry->param_alias)) {
-			spin_lock(&tpg_entry->se_tpg.tpg_lun_lock);
-			if (tpg_entry->se_tpg.tpg_lun_list[lun]->lun_status ==
-			    TRANSPORT_LUN_STATUS_ACTIVE) {
-				if (!tpg_entry->tpg_nexus)
-					error = "nexus undefined";
-				else
-					tpg = tpg_entry;
+			mutex_lock(&tpg_entry->se_tpg.tpg_lun_mutex);
+			hlist_for_each_entry(se_lun, &tpg_entry->se_tpg.tpg_lun_hlist, link) {
+				if (se_lun->unpacked_lun == unpacked_lun) {
+					if (!tpg_entry->tpg_nexus)
+						error = "nexus undefined";
+					else
+						tpg = tpg_entry;
+					break;
+				}
 			}
-			spin_unlock(&tpg_entry->se_tpg.tpg_lun_lock);
+			mutex_unlock(&tpg_entry->se_tpg.tpg_lun_mutex);
 			break;
 		}
 	}
@@ -903,7 +905,7 @@
 	mutex_unlock(&scsiback_mutex);
 
 	if (!tpg) {
-		pr_err("%s:%d %s\n", phy, lun, error);
+		pr_err("%s:%llu %s\n", phy, unpacked_lun, error);
 		return -ENODEV;
 	}
 
@@ -931,7 +933,7 @@
 	kref_init(&new->kref);
 	new->v = *v;
 	new->tpg = tpg;
-	new->lun = lun;
+	new->lun = unpacked_lun;
 	list_add_tail(&new->l, head);
 
 out:
@@ -1251,28 +1253,6 @@
 	return "Unknown";
 }
 
-static u8 scsiback_get_fabric_proto_ident(struct se_portal_group *se_tpg)
-{
-	struct scsiback_tpg *tpg = container_of(se_tpg,
-				struct scsiback_tpg, se_tpg);
-	struct scsiback_tport *tport = tpg->tport;
-
-	switch (tport->tport_proto_id) {
-	case SCSI_PROTOCOL_SAS:
-		return sas_get_fabric_proto_ident(se_tpg);
-	case SCSI_PROTOCOL_FCP:
-		return fc_get_fabric_proto_ident(se_tpg);
-	case SCSI_PROTOCOL_ISCSI:
-		return iscsi_get_fabric_proto_ident(se_tpg);
-	default:
-		pr_err("Unknown tport_proto_id: 0x%02x, using SAS emulation\n",
-			tport->tport_proto_id);
-		break;
-	}
-
-	return sas_get_fabric_proto_ident(se_tpg);
-}
-
 static char *scsiback_get_fabric_wwn(struct se_portal_group *se_tpg)
 {
 	struct scsiback_tpg *tpg = container_of(se_tpg,
@@ -1289,102 +1269,6 @@
 	return tpg->tport_tpgt;
 }
 
-static u32 scsiback_get_default_depth(struct se_portal_group *se_tpg)
-{
-	return 1;
-}
-
-static u32
-scsiback_get_pr_transport_id(struct se_portal_group *se_tpg,
-			      struct se_node_acl *se_nacl,
-			      struct t10_pr_registration *pr_reg,
-			      int *format_code,
-			      unsigned char *buf)
-{
-	struct scsiback_tpg *tpg = container_of(se_tpg,
-				struct scsiback_tpg, se_tpg);
-	struct scsiback_tport *tport = tpg->tport;
-
-	switch (tport->tport_proto_id) {
-	case SCSI_PROTOCOL_SAS:
-		return sas_get_pr_transport_id(se_tpg, se_nacl, pr_reg,
-					format_code, buf);
-	case SCSI_PROTOCOL_FCP:
-		return fc_get_pr_transport_id(se_tpg, se_nacl, pr_reg,
-					format_code, buf);
-	case SCSI_PROTOCOL_ISCSI:
-		return iscsi_get_pr_transport_id(se_tpg, se_nacl, pr_reg,
-					format_code, buf);
-	default:
-		pr_err("Unknown tport_proto_id: 0x%02x, using SAS emulation\n",
-			tport->tport_proto_id);
-		break;
-	}
-
-	return sas_get_pr_transport_id(se_tpg, se_nacl, pr_reg,
-			format_code, buf);
-}
-
-static u32
-scsiback_get_pr_transport_id_len(struct se_portal_group *se_tpg,
-				  struct se_node_acl *se_nacl,
-				  struct t10_pr_registration *pr_reg,
-				  int *format_code)
-{
-	struct scsiback_tpg *tpg = container_of(se_tpg,
-				struct scsiback_tpg, se_tpg);
-	struct scsiback_tport *tport = tpg->tport;
-
-	switch (tport->tport_proto_id) {
-	case SCSI_PROTOCOL_SAS:
-		return sas_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,
-					format_code);
-	case SCSI_PROTOCOL_FCP:
-		return fc_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,
-					format_code);
-	case SCSI_PROTOCOL_ISCSI:
-		return iscsi_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,
-					format_code);
-	default:
-		pr_err("Unknown tport_proto_id: 0x%02x, using SAS emulation\n",
-			tport->tport_proto_id);
-		break;
-	}
-
-	return sas_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,
-			format_code);
-}
-
-static char *
-scsiback_parse_pr_out_transport_id(struct se_portal_group *se_tpg,
-				    const char *buf,
-				    u32 *out_tid_len,
-				    char **port_nexus_ptr)
-{
-	struct scsiback_tpg *tpg = container_of(se_tpg,
-				struct scsiback_tpg, se_tpg);
-	struct scsiback_tport *tport = tpg->tport;
-
-	switch (tport->tport_proto_id) {
-	case SCSI_PROTOCOL_SAS:
-		return sas_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,
-					port_nexus_ptr);
-	case SCSI_PROTOCOL_FCP:
-		return fc_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,
-					port_nexus_ptr);
-	case SCSI_PROTOCOL_ISCSI:
-		return iscsi_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,
-					port_nexus_ptr);
-	default:
-		pr_err("Unknown tport_proto_id: 0x%02x, using SAS emulation\n",
-			tport->tport_proto_id);
-		break;
-	}
-
-	return sas_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,
-			port_nexus_ptr);
-}
-
 static struct se_wwn *
 scsiback_make_tport(struct target_fabric_configfs *tf,
 		     struct config_group *group,
@@ -1451,19 +1335,6 @@
 	kfree(tport);
 }
 
-static struct se_node_acl *
-scsiback_alloc_fabric_acl(struct se_portal_group *se_tpg)
-{
-	return kzalloc(sizeof(struct se_node_acl), GFP_KERNEL);
-}
-
-static void
-scsiback_release_fabric_acl(struct se_portal_group *se_tpg,
-			     struct se_node_acl *se_nacl)
-{
-	kfree(se_nacl);
-}
-
 static u32 scsiback_tpg_get_inst_index(struct se_portal_group *se_tpg)
 {
 	return 1;
@@ -1522,14 +1393,6 @@
 {
 }
 
-static u32 scsiback_get_task_tag(struct se_cmd *se_cmd)
-{
-	struct vscsibk_pend *pending_req = container_of(se_cmd,
-				struct vscsibk_pend, se_cmd);
-
-	return pending_req->rqid;
-}
-
 static int scsiback_get_cmd_state(struct se_cmd *se_cmd)
 {
 	return 0;
@@ -1898,8 +1761,7 @@
 	tpg->tport = tport;
 	tpg->tport_tpgt = tpgt;
 
-	ret = core_tpg_register(&scsiback_ops, wwn,
-				&tpg->se_tpg, tpg, TRANSPORT_TPG_TYPE_NORMAL);
+	ret = core_tpg_register(wwn, &tpg->se_tpg, tport->tport_proto_id);
 	if (ret < 0) {
 		kfree(tpg);
 		return NULL;
@@ -1944,23 +1806,15 @@
 	.module				= THIS_MODULE,
 	.name				= "xen-pvscsi",
 	.get_fabric_name		= scsiback_get_fabric_name,
-	.get_fabric_proto_ident		= scsiback_get_fabric_proto_ident,
 	.tpg_get_wwn			= scsiback_get_fabric_wwn,
 	.tpg_get_tag			= scsiback_get_tag,
-	.tpg_get_default_depth		= scsiback_get_default_depth,
-	.tpg_get_pr_transport_id	= scsiback_get_pr_transport_id,
-	.tpg_get_pr_transport_id_len	= scsiback_get_pr_transport_id_len,
-	.tpg_parse_pr_out_transport_id	= scsiback_parse_pr_out_transport_id,
 	.tpg_check_demo_mode		= scsiback_check_true,
 	.tpg_check_demo_mode_cache	= scsiback_check_true,
 	.tpg_check_demo_mode_write_protect = scsiback_check_false,
 	.tpg_check_prod_mode_write_protect = scsiback_check_false,
-	.tpg_alloc_fabric_acl		= scsiback_alloc_fabric_acl,
-	.tpg_release_fabric_acl		= scsiback_release_fabric_acl,
 	.tpg_get_inst_index		= scsiback_tpg_get_inst_index,
 	.check_stop_free		= scsiback_check_stop_free,
 	.release_cmd			= scsiback_release_cmd,
-	.put_session			= NULL,
 	.shutdown_session		= scsiback_shutdown_session,
 	.close_session			= scsiback_close_session,
 	.sess_get_index			= scsiback_sess_get_index,
@@ -1968,7 +1822,6 @@
 	.write_pending			= scsiback_write_pending,
 	.write_pending_status		= scsiback_write_pending_status,
 	.set_default_node_attributes	= scsiback_set_default_node_attrs,
-	.get_task_tag			= scsiback_get_task_tag,
 	.get_cmd_state			= scsiback_get_cmd_state,
 	.queue_data_in			= scsiback_queue_data_in,
 	.queue_status			= scsiback_queue_status,
@@ -1983,12 +1836,6 @@
 	.fabric_drop_tpg		= scsiback_drop_tpg,
 	.fabric_post_link		= scsiback_port_link,
 	.fabric_pre_unlink		= scsiback_port_unlink,
-	.fabric_make_np			= NULL,
-	.fabric_drop_np			= NULL,
-#if 0
-	.fabric_make_nodeacl		= scsiback_make_nodeacl,
-	.fabric_drop_nodeacl		= scsiback_drop_nodeacl,
-#endif
 
 	.tfc_wwn_attrs			= scsiback_wwn_attrs,
 	.tfc_tpg_base_attrs		= scsiback_tpg_attrs,
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index 96b2011..9ad3272 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -37,7 +37,7 @@
 #include <linux/vmalloc.h>
 #include <linux/export.h>
 #include <asm/xen/hypervisor.h>
-#include <asm/xen/page.h>
+#include <xen/page.h>
 #include <xen/interface/xen.h>
 #include <xen/interface/event_channel.h>
 #include <xen/balloon.h>
@@ -379,16 +379,16 @@
 	int i, j;
 
 	for (i = 0; i < nr_pages; i++) {
-		unsigned long addr = (unsigned long)vaddr +
-			(PAGE_SIZE * i);
 		err = gnttab_grant_foreign_access(dev->otherend_id,
-						  virt_to_mfn(addr), 0);
+						  virt_to_mfn(vaddr), 0);
 		if (err < 0) {
 			xenbus_dev_fatal(dev, err,
 					 "granting access to ring page");
 			goto fail;
 		}
 		grefs[i] = err;
+
+		vaddr = vaddr + PAGE_SIZE;
 	}
 
 	return 0;
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 5390a67..4308fb3 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -742,7 +742,7 @@
 	int err = 0;
 
 	if (xen_hvm_domain()) {
-		uint64_t v;
+		uint64_t v = 0;
 
 		err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v);
 		if (!err && v)
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index a19c31d..4d4a0df 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -242,7 +242,7 @@
 static struct inode *adfs_alloc_inode(struct super_block *sb)
 {
 	struct adfs_inode_info *ei;
-	ei = (struct adfs_inode_info *)kmem_cache_alloc(adfs_inode_cachep, GFP_KERNEL);
+	ei = kmem_cache_alloc(adfs_inode_cachep, GFP_KERNEL);
 	if (!ei)
 		return NULL;
 	return &ei->vfs_inode;
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index cffe837..c69a87e 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -64,7 +64,7 @@
 /* short cut to get to the affs specific inode data */
 static inline struct affs_inode_info *AFFS_I(struct inode *inode)
 {
-	return list_entry(inode, struct affs_inode_info, vfs_inode);
+	return container_of(inode, struct affs_inode_info, vfs_inode);
 }
 
 /*
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index a8f463c..5fa92bc 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -140,7 +140,7 @@
 {
 	struct inode *dir, *inode = d_inode(dentry);
 	struct super_block *sb = inode->i_sb;
-	struct buffer_head *bh = NULL, *link_bh = NULL;
+	struct buffer_head *bh, *link_bh = NULL;
 	u32 link_ino, ino;
 	int retval;
 
diff --git a/fs/affs/inode.c b/fs/affs/inode.c
index a022f4a..1734950 100644
--- a/fs/affs/inode.c
+++ b/fs/affs/inode.c
@@ -346,7 +346,7 @@
 {
 	struct super_block *sb = dir->i_sb;
 	struct buffer_head *inode_bh = NULL;
-	struct buffer_head *bh = NULL;
+	struct buffer_head *bh;
 	u32 block = 0;
 	int retval;
 
diff --git a/fs/affs/symlink.c b/fs/affs/symlink.c
index f39b71c..ea5b69a 100644
--- a/fs/affs/symlink.c
+++ b/fs/affs/symlink.c
@@ -16,14 +16,12 @@
 	struct inode *inode = page->mapping->host;
 	char *link = kmap(page);
 	struct slink_front *lf;
-	int err;
 	int			 i, j;
 	char			 c;
 	char			 lc;
 
 	pr_debug("follow_link(ino=%lu)\n", inode->i_ino);
 
-	err = -EIO;
 	bh = affs_bread(inode->i_sb, inode->i_ino);
 	if (!bh)
 		goto fail;
@@ -66,7 +64,7 @@
 	SetPageError(page);
 	kunmap(page);
 	unlock_page(page);
-	return err;
+	return -EIO;
 }
 
 const struct address_space_operations affs_symlink_aops = {
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index 5b700ef..c37149b 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -238,11 +238,6 @@
 	return d_inode(sbi->sb->s_root)->i_ino;
 }
 
-static inline int simple_positive(struct dentry *dentry)
-{
-	return d_really_is_positive(dentry) && !d_unhashed(dentry);
-}
-
 static inline void __autofs4_add_expiring(struct dentry *dentry)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
diff --git a/fs/befs/befs.h b/fs/befs/befs.h
index 1fead8d..35d19e8 100644
--- a/fs/befs/befs.h
+++ b/fs/befs/befs.h
@@ -112,7 +112,7 @@
 static inline struct befs_inode_info *
 BEFS_I(const struct inode *inode)
 {
-	return list_entry(inode, struct befs_inode_info, vfs_inode);
+	return container_of(inode, struct befs_inode_info, vfs_inode);
 }
 
 static inline befs_blocknr_t
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index cd46e41..6b65996 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1530,7 +1530,7 @@
 		file = vma->vm_file;
 		if (!file)
 			continue;
-		filename = d_path(&file->f_path, name_curpos, remaining);
+		filename = file_path(file, name_curpos, remaining);
 		if (IS_ERR(filename)) {
 			if (PTR_ERR(filename) == -ENAMETOOLONG) {
 				vfree(data);
@@ -1540,7 +1540,7 @@
 			continue;
 		}
 
-		/* d_path() fills at the end, move name down */
+		/* file_path() fills at the end, move name down */
 		/* n = strlen(filename) + 1: */
 		n = (name_curpos + remaining) - filename;
 		remaining = filename - name_curpos;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 4fe10f9..1982437 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -152,6 +152,9 @@
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 
+	if (IS_DAX(inode))
+		return dax_do_io(iocb, inode, iter, offset, blkdev_get_block,
+				NULL, DIO_SKIP_DIO_COUNT);
 	return __blockdev_direct_IO(iocb, inode, I_BDEV(inode), iter, offset,
 				    blkdev_get_block, NULL, NULL,
 				    DIO_SKIP_DIO_COUNT);
@@ -443,6 +446,12 @@
 	long avail;
 	const struct block_device_operations *ops = bdev->bd_disk->fops;
 
+	/*
+	 * The device driver is allowed to sleep, in order to make the
+	 * memory directly accessible.
+	 */
+	might_sleep();
+
 	if (size < 0)
 		return size;
 	if (!ops->direct_access)
@@ -1170,6 +1179,7 @@
 		bdev->bd_disk = disk;
 		bdev->bd_queue = disk->queue;
 		bdev->bd_contains = bdev;
+		bdev->bd_inode->i_flags = disk->fops->direct_access ? S_DAX : 0;
 		if (!partno) {
 			ret = -ENXIO;
 			bdev->bd_part = disk_get_part(disk, partno);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 795d754..b823fac9 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1748,7 +1748,7 @@
 	}
 
 	current->backing_dev_info = inode_to_bdi(inode);
-	err = file_remove_suid(file);
+	err = file_remove_privs(file);
 	if (err) {
 		mutex_unlock(&inode->i_mutex);
 		goto out;
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index 8c52472..aecd085 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -43,7 +43,6 @@
 	loff_t				i_size;		/* object size */
 	unsigned long			flags;
 #define CACHEFILES_OBJECT_ACTIVE	0		/* T if marked active */
-#define CACHEFILES_OBJECT_BURIED	1		/* T if preemptively buried */
 	atomic_t			usage;		/* object usage count */
 	uint8_t				type;		/* object type */
 	uint8_t				new;		/* T if object new */
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index ab857ab..fc1056f 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -97,7 +97,8 @@
  *   call vfs_unlink(), vfs_rmdir() or vfs_rename()
  */
 static void cachefiles_mark_object_buried(struct cachefiles_cache *cache,
-					  struct dentry *dentry)
+					  struct dentry *dentry,
+					  enum fscache_why_object_killed why)
 {
 	struct cachefiles_object *object;
 	struct rb_node *p;
@@ -132,8 +133,9 @@
 		pr_err("\n");
 		pr_err("Error: Can't preemptively bury live object\n");
 		cachefiles_printk_object(object, NULL);
-	} else if (test_and_set_bit(CACHEFILES_OBJECT_BURIED, &object->flags)) {
-		pr_err("Error: Object already preemptively buried\n");
+	} else {
+		if (why != FSCACHE_OBJECT_IS_STALE)
+			fscache_object_mark_killed(&object->fscache, why);
 	}
 
 	write_unlock(&cache->active_lock);
@@ -265,7 +267,8 @@
 static int cachefiles_bury_object(struct cachefiles_cache *cache,
 				  struct dentry *dir,
 				  struct dentry *rep,
-				  bool preemptive)
+				  bool preemptive,
+				  enum fscache_why_object_killed why)
 {
 	struct dentry *grave, *trap;
 	struct path path, path_to_graveyard;
@@ -289,7 +292,7 @@
 			ret = vfs_unlink(d_inode(dir), rep, NULL);
 
 			if (preemptive)
-				cachefiles_mark_object_buried(cache, rep);
+				cachefiles_mark_object_buried(cache, rep, why);
 		}
 
 		mutex_unlock(&d_inode(dir)->i_mutex);
@@ -394,7 +397,7 @@
 					    "Rename failed with error %d", ret);
 
 		if (preemptive)
-			cachefiles_mark_object_buried(cache, rep);
+			cachefiles_mark_object_buried(cache, rep, why);
 	}
 
 	unlock_rename(cache->graveyard, dir);
@@ -422,7 +425,7 @@
 
 	mutex_lock_nested(&d_inode(dir)->i_mutex, I_MUTEX_PARENT);
 
-	if (test_bit(CACHEFILES_OBJECT_BURIED, &object->flags)) {
+	if (test_bit(FSCACHE_OBJECT_KILLED_BY_CACHE, &object->fscache.flags)) {
 		/* object allocation for the same key preemptively deleted this
 		 * object's file so that it could create its own file */
 		_debug("object preemptively buried");
@@ -433,7 +436,8 @@
 		 * may have been renamed */
 		if (dir == object->dentry->d_parent) {
 			ret = cachefiles_bury_object(cache, dir,
-						     object->dentry, false);
+						     object->dentry, false,
+						     FSCACHE_OBJECT_WAS_RETIRED);
 		} else {
 			/* it got moved, presumably by cachefilesd culling it,
 			 * so it's no longer in the key path and we can ignore
@@ -522,7 +526,7 @@
 		if (d_is_negative(next)) {
 			ret = cachefiles_has_space(cache, 1, 0);
 			if (ret < 0)
-				goto create_error;
+				goto no_space_error;
 
 			path.dentry = dir;
 			ret = security_path_mkdir(&path, next, 0);
@@ -551,7 +555,7 @@
 		if (d_is_negative(next)) {
 			ret = cachefiles_has_space(cache, 1, 0);
 			if (ret < 0)
-				goto create_error;
+				goto no_space_error;
 
 			path.dentry = dir;
 			ret = security_path_mknod(&path, next, S_IFREG, 0);
@@ -602,7 +606,8 @@
 			 * mutex) */
 			object->dentry = NULL;
 
-			ret = cachefiles_bury_object(cache, dir, next, true);
+			ret = cachefiles_bury_object(cache, dir, next, true,
+						     FSCACHE_OBJECT_IS_STALE);
 			dput(next);
 			next = NULL;
 
@@ -610,6 +615,7 @@
 				goto delete_error;
 
 			_debug("redo lookup");
+			fscache_object_retrying_stale(&object->fscache);
 			goto lookup_again;
 		}
 	}
@@ -662,6 +668,8 @@
 	_leave(" = 0 [%lu]", d_backing_inode(object->dentry)->i_ino);
 	return 0;
 
+no_space_error:
+	fscache_object_mark_killed(&object->fscache, FSCACHE_OBJECT_NO_SPACE);
 create_error:
 	_debug("create error %d", ret);
 	if (ret == -EIO)
@@ -927,7 +935,8 @@
 	/*  actually remove the victim (drops the dir mutex) */
 	_debug("bury");
 
-	ret = cachefiles_bury_object(cache, dir, victim, false);
+	ret = cachefiles_bury_object(cache, dir, victim, false,
+				     FSCACHE_OBJECT_WAS_CULLED);
 	if (ret < 0)
 		goto error;
 
diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index 64fa248..8f84646 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -187,10 +187,10 @@
 		val_size2 = posix_acl_xattr_size(default_acl->a_count);
 
 	err = -ENOMEM;
-	tmp_buf = kmalloc(max(val_size1, val_size2), GFP_NOFS);
+	tmp_buf = kmalloc(max(val_size1, val_size2), GFP_KERNEL);
 	if (!tmp_buf)
 		goto out_err;
-	pagelist = kmalloc(sizeof(struct ceph_pagelist), GFP_NOFS);
+	pagelist = kmalloc(sizeof(struct ceph_pagelist), GFP_KERNEL);
 	if (!pagelist)
 		goto out_err;
 	ceph_pagelist_init(pagelist);
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index e162bcd..890c509 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -87,17 +87,21 @@
 	inode = mapping->host;
 	ci = ceph_inode(inode);
 
-	/*
-	 * Note that we're grabbing a snapc ref here without holding
-	 * any locks!
-	 */
-	snapc = ceph_get_snap_context(ci->i_snap_realm->cached_context);
-
 	/* dirty the head */
 	spin_lock(&ci->i_ceph_lock);
-	if (ci->i_head_snapc == NULL)
-		ci->i_head_snapc = ceph_get_snap_context(snapc);
-	++ci->i_wrbuffer_ref_head;
+	BUG_ON(ci->i_wr_ref == 0); // caller should hold Fw reference
+	if (__ceph_have_pending_cap_snap(ci)) {
+		struct ceph_cap_snap *capsnap =
+				list_last_entry(&ci->i_cap_snaps,
+						struct ceph_cap_snap,
+						ci_item);
+		snapc = ceph_get_snap_context(capsnap->context);
+		capsnap->dirty_pages++;
+	} else {
+		BUG_ON(!ci->i_head_snapc);
+		snapc = ceph_get_snap_context(ci->i_head_snapc);
+		++ci->i_wrbuffer_ref_head;
+	}
 	if (ci->i_wrbuffer_ref == 0)
 		ihold(inode);
 	++ci->i_wrbuffer_ref;
@@ -346,7 +350,7 @@
 
 	/* build page vector */
 	nr_pages = calc_pages_for(0, len);
-	pages = kmalloc(sizeof(*pages) * nr_pages, GFP_NOFS);
+	pages = kmalloc(sizeof(*pages) * nr_pages, GFP_KERNEL);
 	ret = -ENOMEM;
 	if (!pages)
 		goto out;
@@ -358,7 +362,7 @@
  		dout("start_read %p adding %p idx %lu\n", inode, page,
 		     page->index);
 		if (add_to_page_cache_lru(page, &inode->i_data, page->index,
-					  GFP_NOFS)) {
+					  GFP_KERNEL)) {
 			ceph_fscache_uncache_page(inode, page);
 			page_cache_release(page);
 			dout("start_read %p add_to_page_cache failed %p\n",
@@ -436,7 +440,7 @@
  * only snap context we are allowed to write back.
  */
 static struct ceph_snap_context *get_oldest_context(struct inode *inode,
-						    u64 *snap_size)
+						    loff_t *snap_size)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_snap_context *snapc = NULL;
@@ -476,8 +480,9 @@
 	struct ceph_osd_client *osdc;
 	struct ceph_snap_context *snapc, *oldest;
 	loff_t page_off = page_offset(page);
+	loff_t snap_size = -1;
 	long writeback_stat;
-	u64 truncate_size, snap_size = 0;
+	u64 truncate_size;
 	u32 truncate_seq;
 	int err = 0, len = PAGE_CACHE_SIZE;
 
@@ -512,7 +517,7 @@
 	spin_lock(&ci->i_ceph_lock);
 	truncate_seq = ci->i_truncate_seq;
 	truncate_size = ci->i_truncate_size;
-	if (!snap_size)
+	if (snap_size == -1)
 		snap_size = i_size_read(inode);
 	spin_unlock(&ci->i_ceph_lock);
 
@@ -695,7 +700,8 @@
 	unsigned wsize = 1 << inode->i_blkbits;
 	struct ceph_osd_request *req = NULL;
 	int do_sync = 0;
-	u64 truncate_size, snap_size;
+	loff_t snap_size, i_size;
+	u64 truncate_size;
 	u32 truncate_seq;
 
 	/*
@@ -741,7 +747,7 @@
 retry:
 	/* find oldest snap context with dirty data */
 	ceph_put_snap_context(snapc);
-	snap_size = 0;
+	snap_size = -1;
 	snapc = get_oldest_context(inode, &snap_size);
 	if (!snapc) {
 		/* hmm, why does writepages get called when there
@@ -749,16 +755,13 @@
 		dout(" no snap context with dirty data?\n");
 		goto out;
 	}
-	if (snap_size == 0)
-		snap_size = i_size_read(inode);
 	dout(" oldest snapc is %p seq %lld (%d snaps)\n",
 	     snapc, snapc->seq, snapc->num_snaps);
 
 	spin_lock(&ci->i_ceph_lock);
 	truncate_seq = ci->i_truncate_seq;
 	truncate_size = ci->i_truncate_size;
-	if (!snap_size)
-		snap_size = i_size_read(inode);
+	i_size = i_size_read(inode);
 	spin_unlock(&ci->i_ceph_lock);
 
 	if (last_snapc && snapc != last_snapc) {
@@ -828,8 +831,10 @@
 				dout("waiting on writeback %p\n", page);
 				wait_on_page_writeback(page);
 			}
-			if (page_offset(page) >= snap_size) {
-				dout("%p page eof %llu\n", page, snap_size);
+			if (page_offset(page) >=
+			    (snap_size == -1 ? i_size : snap_size)) {
+				dout("%p page eof %llu\n", page,
+				     (snap_size == -1 ? i_size : snap_size));
 				done = 1;
 				unlock_page(page);
 				break;
@@ -884,7 +889,8 @@
 				}
 
 				if (do_sync)
-					osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC);
+					osd_req_op_init(req, 1,
+							CEPH_OSD_OP_STARTSYNC, 0);
 
 				req->r_callback = writepages_finish;
 				req->r_inode = inode;
@@ -944,10 +950,18 @@
 		}
 
 		/* Format the osd request message and submit the write */
-
 		offset = page_offset(pages[0]);
-		len = min(snap_size - offset,
-			  (u64)locked_pages << PAGE_CACHE_SHIFT);
+		len = (u64)locked_pages << PAGE_CACHE_SHIFT;
+		if (snap_size == -1) {
+			len = min(len, (u64)i_size_read(inode) - offset);
+			 /* writepages_finish() clears writeback pages
+			  * according to the data length, so make sure
+			  * data length covers all locked pages */
+			len = max(len, 1 +
+				((u64)(locked_pages - 1) << PAGE_CACHE_SHIFT));
+		} else {
+			len = min(len, snap_size - offset);
+		}
 		dout("writepages got %d pages at %llu~%llu\n",
 		     locked_pages, offset, len);
 
@@ -1032,7 +1046,6 @@
 {
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
 	loff_t page_off = pos & PAGE_CACHE_MASK;
 	int pos_in_page = pos & ~PAGE_CACHE_MASK;
 	int end_in_page = pos_in_page + len;
@@ -1044,10 +1057,6 @@
 	/* writepages currently holds page lock, but if we change that later, */
 	wait_on_page_writeback(page);
 
-	/* check snap context */
-	BUG_ON(!ci->i_snap_realm);
-	down_read(&mdsc->snap_rwsem);
-	BUG_ON(!ci->i_snap_realm->cached_context);
 	snapc = page_snap_context(page);
 	if (snapc && snapc != ci->i_head_snapc) {
 		/*
@@ -1055,7 +1064,6 @@
 		 * context!  is it writeable now?
 		 */
 		oldest = get_oldest_context(inode, NULL);
-		up_read(&mdsc->snap_rwsem);
 
 		if (snapc->seq > oldest->seq) {
 			ceph_put_snap_context(oldest);
@@ -1112,7 +1120,6 @@
 	}
 
 	/* we need to read it. */
-	up_read(&mdsc->snap_rwsem);
 	r = readpage_nounlock(file, page);
 	if (r < 0)
 		goto fail_nosnap;
@@ -1157,16 +1164,13 @@
 
 /*
  * we don't do anything in here that simple_write_end doesn't do
- * except adjust dirty page accounting and drop read lock on
- * mdsc->snap_rwsem.
+ * except adjust dirty page accounting
  */
 static int ceph_write_end(struct file *file, struct address_space *mapping,
 			  loff_t pos, unsigned len, unsigned copied,
 			  struct page *page, void *fsdata)
 {
 	struct inode *inode = file_inode(file);
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
-	struct ceph_mds_client *mdsc = fsc->mdsc;
 	unsigned from = pos & (PAGE_CACHE_SIZE - 1);
 	int check_cap = 0;
 
@@ -1188,7 +1192,6 @@
 	set_page_dirty(page);
 
 	unlock_page(page);
-	up_read(&mdsc->snap_rwsem);
 	page_cache_release(page);
 
 	if (check_cap)
@@ -1314,13 +1317,17 @@
 	struct inode *inode = file_inode(vma->vm_file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_file_info *fi = vma->vm_file->private_data;
-	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
+	struct ceph_cap_flush *prealloc_cf;
 	struct page *page = vmf->page;
 	loff_t off = page_offset(page);
 	loff_t size = i_size_read(inode);
 	size_t len;
 	int want, got, ret;
 
+	prealloc_cf = ceph_alloc_cap_flush();
+	if (!prealloc_cf)
+		return VM_FAULT_SIGBUS;
+
 	if (ci->i_inline_version != CEPH_INLINE_NONE) {
 		struct page *locked_page = NULL;
 		if (off == 0) {
@@ -1330,8 +1337,10 @@
 		ret = ceph_uninline_data(vma->vm_file, locked_page);
 		if (locked_page)
 			unlock_page(locked_page);
-		if (ret < 0)
-			return VM_FAULT_SIGBUS;
+		if (ret < 0) {
+			ret = VM_FAULT_SIGBUS;
+			goto out_free;
+		}
 	}
 
 	if (off + PAGE_CACHE_SIZE <= size)
@@ -1353,7 +1362,8 @@
 			break;
 		if (ret != -ERESTARTSYS) {
 			WARN_ON(1);
-			return VM_FAULT_SIGBUS;
+			ret = VM_FAULT_SIGBUS;
+			goto out_free;
 		}
 	}
 	dout("page_mkwrite %p %llu~%zd got cap refs on %s\n",
@@ -1373,7 +1383,6 @@
 	if (ret == 0) {
 		/* success.  we'll keep the page locked. */
 		set_page_dirty(page);
-		up_read(&mdsc->snap_rwsem);
 		ret = VM_FAULT_LOCKED;
 	} else {
 		if (ret == -ENOMEM)
@@ -1389,7 +1398,8 @@
 		int dirty;
 		spin_lock(&ci->i_ceph_lock);
 		ci->i_inline_version = CEPH_INLINE_NONE;
-		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR);
+		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR,
+					       &prealloc_cf);
 		spin_unlock(&ci->i_ceph_lock);
 		if (dirty)
 			__mark_inode_dirty(inode, dirty);
@@ -1398,6 +1408,8 @@
 	dout("page_mkwrite %p %llu~%zd dropping cap refs on %s ret %d\n",
 	     inode, off, len, ceph_cap_string(got), ret);
 	ceph_put_cap_refs(ci, got);
+out_free:
+	ceph_free_cap_flush(prealloc_cf);
 
 	return ret;
 }
@@ -1509,8 +1521,7 @@
 				    ceph_vino(inode), 0, &len, 0, 1,
 				    CEPH_OSD_OP_CREATE,
 				    CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE,
-				    ci->i_snap_realm->cached_context,
-				    0, 0, false);
+				    ceph_empty_snapc, 0, 0, false);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto out;
@@ -1528,7 +1539,7 @@
 				    ceph_vino(inode), 0, &len, 1, 3,
 				    CEPH_OSD_OP_WRITE,
 				    CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE,
-				    ci->i_snap_realm->cached_context,
+				    ceph_empty_snapc,
 				    ci->i_truncate_seq, ci->i_truncate_size,
 				    false);
 	if (IS_ERR(req)) {
@@ -1597,3 +1608,206 @@
 	vma->vm_ops = &ceph_vmops;
 	return 0;
 }
+
+enum {
+	POOL_READ	= 1,
+	POOL_WRITE	= 2,
+};
+
+static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool)
+{
+	struct ceph_fs_client *fsc = ceph_inode_to_client(&ci->vfs_inode);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
+	struct ceph_osd_request *rd_req = NULL, *wr_req = NULL;
+	struct rb_node **p, *parent;
+	struct ceph_pool_perm *perm;
+	struct page **pages;
+	int err = 0, err2 = 0, have = 0;
+
+	down_read(&mdsc->pool_perm_rwsem);
+	p = &mdsc->pool_perm_tree.rb_node;
+	while (*p) {
+		perm = rb_entry(*p, struct ceph_pool_perm, node);
+		if (pool < perm->pool)
+			p = &(*p)->rb_left;
+		else if (pool > perm->pool)
+			p = &(*p)->rb_right;
+		else {
+			have = perm->perm;
+			break;
+		}
+	}
+	up_read(&mdsc->pool_perm_rwsem);
+	if (*p)
+		goto out;
+
+	dout("__ceph_pool_perm_get pool %u no perm cached\n", pool);
+
+	down_write(&mdsc->pool_perm_rwsem);
+	parent = NULL;
+	while (*p) {
+		parent = *p;
+		perm = rb_entry(parent, struct ceph_pool_perm, node);
+		if (pool < perm->pool)
+			p = &(*p)->rb_left;
+		else if (pool > perm->pool)
+			p = &(*p)->rb_right;
+		else {
+			have = perm->perm;
+			break;
+		}
+	}
+	if (*p) {
+		up_write(&mdsc->pool_perm_rwsem);
+		goto out;
+	}
+
+	rd_req = ceph_osdc_alloc_request(&fsc->client->osdc,
+					 ceph_empty_snapc,
+					 1, false, GFP_NOFS);
+	if (!rd_req) {
+		err = -ENOMEM;
+		goto out_unlock;
+	}
+
+	rd_req->r_flags = CEPH_OSD_FLAG_READ;
+	osd_req_op_init(rd_req, 0, CEPH_OSD_OP_STAT, 0);
+	rd_req->r_base_oloc.pool = pool;
+	snprintf(rd_req->r_base_oid.name, sizeof(rd_req->r_base_oid.name),
+		 "%llx.00000000", ci->i_vino.ino);
+	rd_req->r_base_oid.name_len = strlen(rd_req->r_base_oid.name);
+
+	wr_req = ceph_osdc_alloc_request(&fsc->client->osdc,
+					 ceph_empty_snapc,
+					 1, false, GFP_NOFS);
+	if (!wr_req) {
+		err = -ENOMEM;
+		goto out_unlock;
+	}
+
+	wr_req->r_flags = CEPH_OSD_FLAG_WRITE |
+			  CEPH_OSD_FLAG_ACK | CEPH_OSD_FLAG_ONDISK;
+	osd_req_op_init(wr_req, 0, CEPH_OSD_OP_CREATE, CEPH_OSD_OP_FLAG_EXCL);
+	wr_req->r_base_oloc.pool = pool;
+	wr_req->r_base_oid = rd_req->r_base_oid;
+
+	/* one page should be large enough for STAT data */
+	pages = ceph_alloc_page_vector(1, GFP_KERNEL);
+	if (IS_ERR(pages)) {
+		err = PTR_ERR(pages);
+		goto out_unlock;
+	}
+
+	osd_req_op_raw_data_in_pages(rd_req, 0, pages, PAGE_SIZE,
+				     0, false, true);
+	ceph_osdc_build_request(rd_req, 0, NULL, CEPH_NOSNAP,
+				&ci->vfs_inode.i_mtime);
+	err = ceph_osdc_start_request(&fsc->client->osdc, rd_req, false);
+
+	ceph_osdc_build_request(wr_req, 0, NULL, CEPH_NOSNAP,
+				&ci->vfs_inode.i_mtime);
+	err2 = ceph_osdc_start_request(&fsc->client->osdc, wr_req, false);
+
+	if (!err)
+		err = ceph_osdc_wait_request(&fsc->client->osdc, rd_req);
+	if (!err2)
+		err2 = ceph_osdc_wait_request(&fsc->client->osdc, wr_req);
+
+	if (err >= 0 || err == -ENOENT)
+		have |= POOL_READ;
+	else if (err != -EPERM)
+		goto out_unlock;
+
+	if (err2 == 0 || err2 == -EEXIST)
+		have |= POOL_WRITE;
+	else if (err2 != -EPERM) {
+		err = err2;
+		goto out_unlock;
+	}
+
+	perm = kmalloc(sizeof(*perm), GFP_NOFS);
+	if (!perm) {
+		err = -ENOMEM;
+		goto out_unlock;
+	}
+
+	perm->pool = pool;
+	perm->perm = have;
+	rb_link_node(&perm->node, parent, p);
+	rb_insert_color(&perm->node, &mdsc->pool_perm_tree);
+	err = 0;
+out_unlock:
+	up_write(&mdsc->pool_perm_rwsem);
+
+	if (rd_req)
+		ceph_osdc_put_request(rd_req);
+	if (wr_req)
+		ceph_osdc_put_request(wr_req);
+out:
+	if (!err)
+		err = have;
+	dout("__ceph_pool_perm_get pool %u result = %d\n", pool, err);
+	return err;
+}
+
+int ceph_pool_perm_check(struct ceph_inode_info *ci, int need)
+{
+	u32 pool;
+	int ret, flags;
+
+	if (ceph_test_mount_opt(ceph_inode_to_client(&ci->vfs_inode),
+				NOPOOLPERM))
+		return 0;
+
+	spin_lock(&ci->i_ceph_lock);
+	flags = ci->i_ceph_flags;
+	pool = ceph_file_layout_pg_pool(ci->i_layout);
+	spin_unlock(&ci->i_ceph_lock);
+check:
+	if (flags & CEPH_I_POOL_PERM) {
+		if ((need & CEPH_CAP_FILE_RD) && !(flags & CEPH_I_POOL_RD)) {
+			dout("ceph_pool_perm_check pool %u no read perm\n",
+			     pool);
+			return -EPERM;
+		}
+		if ((need & CEPH_CAP_FILE_WR) && !(flags & CEPH_I_POOL_WR)) {
+			dout("ceph_pool_perm_check pool %u no write perm\n",
+			     pool);
+			return -EPERM;
+		}
+		return 0;
+	}
+
+	ret = __ceph_pool_perm_get(ci, pool);
+	if (ret < 0)
+		return ret;
+
+	flags = CEPH_I_POOL_PERM;
+	if (ret & POOL_READ)
+		flags |= CEPH_I_POOL_RD;
+	if (ret & POOL_WRITE)
+		flags |= CEPH_I_POOL_WR;
+
+	spin_lock(&ci->i_ceph_lock);
+	if (pool == ceph_file_layout_pg_pool(ci->i_layout)) {
+		ci->i_ceph_flags = flags;
+        } else {
+		pool = ceph_file_layout_pg_pool(ci->i_layout);
+		flags = ci->i_ceph_flags;
+	}
+	spin_unlock(&ci->i_ceph_lock);
+	goto check;
+}
+
+void ceph_pool_perm_destroy(struct ceph_mds_client *mdsc)
+{
+	struct ceph_pool_perm *perm;
+	struct rb_node *n;
+
+	while (!RB_EMPTY_ROOT(&mdsc->pool_perm_tree)) {
+		n = rb_first(&mdsc->pool_perm_tree);
+		perm = rb_entry(n, struct ceph_pool_perm, node);
+		rb_erase(n, &mdsc->pool_perm_tree);
+		kfree(perm);
+	}
+}
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index be5ea6a..dc10c9d 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -833,7 +833,9 @@
 		used |= CEPH_CAP_PIN;
 	if (ci->i_rd_ref)
 		used |= CEPH_CAP_FILE_RD;
-	if (ci->i_rdcache_ref || ci->vfs_inode.i_data.nrpages)
+	if (ci->i_rdcache_ref ||
+	    (!S_ISDIR(ci->vfs_inode.i_mode) && /* ignore readdir cache */
+	     ci->vfs_inode.i_data.nrpages))
 		used |= CEPH_CAP_FILE_CACHE;
 	if (ci->i_wr_ref)
 		used |= CEPH_CAP_FILE_WR;
@@ -926,16 +928,6 @@
 
 	/* remove from session list */
 	spin_lock(&session->s_cap_lock);
-	/*
-	 * s_cap_reconnect is protected by s_cap_lock. no one changes
-	 * s_cap_gen while session is in the reconnect state.
-	 */
-	if (queue_release &&
-	    (!session->s_cap_reconnect ||
-	     cap->cap_gen == session->s_cap_gen))
-		__queue_cap_release(session, ci->i_vino.ino, cap->cap_id,
-				    cap->mseq, cap->issue_seq);
-
 	if (session->s_cap_iterator == cap) {
 		/* not yet, we are iterating over this very cap */
 		dout("__ceph_remove_cap  delaying %p removal from session %p\n",
@@ -948,6 +940,25 @@
 	}
 	/* protect backpointer with s_cap_lock: see iterate_session_caps */
 	cap->ci = NULL;
+
+	/*
+	 * s_cap_reconnect is protected by s_cap_lock. no one changes
+	 * s_cap_gen while session is in the reconnect state.
+	 */
+	if (queue_release &&
+	    (!session->s_cap_reconnect || cap->cap_gen == session->s_cap_gen)) {
+		cap->queue_release = 1;
+		if (removed) {
+			list_add_tail(&cap->session_caps,
+				      &session->s_cap_releases);
+			session->s_num_cap_releases++;
+			removed = 0;
+		}
+	} else {
+		cap->queue_release = 0;
+	}
+	cap->cap_ino = ci->i_vino.ino;
+
 	spin_unlock(&session->s_cap_lock);
 
 	/* remove from inode list */
@@ -977,8 +988,8 @@
 static int send_cap_msg(struct ceph_mds_session *session,
 			u64 ino, u64 cid, int op,
 			int caps, int wanted, int dirty,
-			u32 seq, u64 flush_tid, u32 issue_seq, u32 mseq,
-			u64 size, u64 max_size,
+			u32 seq, u64 flush_tid, u64 oldest_flush_tid,
+			u32 issue_seq, u32 mseq, u64 size, u64 max_size,
 			struct timespec *mtime, struct timespec *atime,
 			u64 time_warp_seq,
 			kuid_t uid, kgid_t gid, umode_t mode,
@@ -992,20 +1003,23 @@
 	size_t extra_len;
 
 	dout("send_cap_msg %s %llx %llx caps %s wanted %s dirty %s"
-	     " seq %u/%u mseq %u follows %lld size %llu/%llu"
+	     " seq %u/%u tid %llu/%llu mseq %u follows %lld size %llu/%llu"
 	     " xattr_ver %llu xattr_len %d\n", ceph_cap_op_name(op),
 	     cid, ino, ceph_cap_string(caps), ceph_cap_string(wanted),
 	     ceph_cap_string(dirty),
-	     seq, issue_seq, mseq, follows, size, max_size,
+	     seq, issue_seq, flush_tid, oldest_flush_tid,
+	     mseq, follows, size, max_size,
 	     xattr_version, xattrs_buf ? (int)xattrs_buf->vec.iov_len : 0);
 
-	/* flock buffer size + inline version + inline data size */
-	extra_len = 4 + 8 + 4;
+	/* flock buffer size + inline version + inline data size +
+	 * osd_epoch_barrier + oldest_flush_tid */
+	extra_len = 4 + 8 + 4 + 4 + 8;
 	msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPS, sizeof(*fc) + extra_len,
 			   GFP_NOFS, false);
 	if (!msg)
 		return -ENOMEM;
 
+	msg->hdr.version = cpu_to_le16(6);
 	msg->hdr.tid = cpu_to_le64(flush_tid);
 
 	fc = msg->front.iov_base;
@@ -1041,6 +1055,10 @@
 	ceph_encode_64(&p, inline_data ? 0 : CEPH_INLINE_NONE);
 	/* inline data size */
 	ceph_encode_32(&p, 0);
+	/* osd_epoch_barrier */
+	ceph_encode_32(&p, 0);
+	/* oldest_flush_tid */
+	ceph_encode_64(&p, oldest_flush_tid);
 
 	fc->xattr_version = cpu_to_le64(xattr_version);
 	if (xattrs_buf) {
@@ -1053,44 +1071,6 @@
 	return 0;
 }
 
-void __queue_cap_release(struct ceph_mds_session *session,
-			 u64 ino, u64 cap_id, u32 migrate_seq,
-			 u32 issue_seq)
-{
-	struct ceph_msg *msg;
-	struct ceph_mds_cap_release *head;
-	struct ceph_mds_cap_item *item;
-
-	BUG_ON(!session->s_num_cap_releases);
-	msg = list_first_entry(&session->s_cap_releases,
-			       struct ceph_msg, list_head);
-
-	dout(" adding %llx release to mds%d msg %p (%d left)\n",
-	     ino, session->s_mds, msg, session->s_num_cap_releases);
-
-	BUG_ON(msg->front.iov_len + sizeof(*item) > PAGE_CACHE_SIZE);
-	head = msg->front.iov_base;
-	le32_add_cpu(&head->num, 1);
-	item = msg->front.iov_base + msg->front.iov_len;
-	item->ino = cpu_to_le64(ino);
-	item->cap_id = cpu_to_le64(cap_id);
-	item->migrate_seq = cpu_to_le32(migrate_seq);
-	item->seq = cpu_to_le32(issue_seq);
-
-	session->s_num_cap_releases--;
-
-	msg->front.iov_len += sizeof(*item);
-	if (le32_to_cpu(head->num) == CEPH_CAPS_PER_RELEASE) {
-		dout(" release msg %p full\n", msg);
-		list_move_tail(&msg->list_head, &session->s_cap_releases_done);
-	} else {
-		dout(" release msg %p at %d/%d (%d)\n", msg,
-		     (int)le32_to_cpu(head->num),
-		     (int)CEPH_CAPS_PER_RELEASE,
-		     (int)msg->front.iov_len);
-	}
-}
-
 /*
  * Queue cap releases when an inode is dropped from our cache.  Since
  * inode is about to be destroyed, there is no need for i_ceph_lock.
@@ -1127,7 +1107,7 @@
  */
 static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
 		      int op, int used, int want, int retain, int flushing,
-		      unsigned *pflush_tid)
+		      u64 flush_tid, u64 oldest_flush_tid)
 	__releases(cap->ci->i_ceph_lock)
 {
 	struct ceph_inode_info *ci = cap->ci;
@@ -1145,8 +1125,6 @@
 	u64 xattr_version = 0;
 	struct ceph_buffer *xattr_blob = NULL;
 	int delayed = 0;
-	u64 flush_tid = 0;
-	int i;
 	int ret;
 	bool inline_data;
 
@@ -1190,26 +1168,7 @@
 	cap->implemented &= cap->issued | used;
 	cap->mds_wanted = want;
 
-	if (flushing) {
-		/*
-		 * assign a tid for flush operations so we can avoid
-		 * flush1 -> dirty1 -> flush2 -> flushack1 -> mark
-		 * clean type races.  track latest tid for every bit
-		 * so we can handle flush AxFw, flush Fw, and have the
-		 * first ack clean Ax.
-		 */
-		flush_tid = ++ci->i_cap_flush_last_tid;
-		if (pflush_tid)
-			*pflush_tid = flush_tid;
-		dout(" cap_flush_tid %d\n", (int)flush_tid);
-		for (i = 0; i < CEPH_CAP_BITS; i++)
-			if (flushing & (1 << i))
-				ci->i_cap_flush_tid[i] = flush_tid;
-
-		follows = ci->i_head_snapc->seq;
-	} else {
-		follows = 0;
-	}
+	follows = flushing ? ci->i_head_snapc->seq : 0;
 
 	keep = cap->implemented;
 	seq = cap->seq;
@@ -1237,7 +1196,8 @@
 	spin_unlock(&ci->i_ceph_lock);
 
 	ret = send_cap_msg(session, ceph_vino(inode).ino, cap_id,
-		op, keep, want, flushing, seq, flush_tid, issue_seq, mseq,
+		op, keep, want, flushing, seq,
+		flush_tid, oldest_flush_tid, issue_seq, mseq,
 		size, max_size, &mtime, &atime, time_warp_seq,
 		uid, gid, mode, xattr_version, xattr_blob,
 		follows, inline_data);
@@ -1259,14 +1219,14 @@
  * asynchronously back to the MDS once sync writes complete and dirty
  * data is written out.
  *
- * Unless @again is true, skip cap_snaps that were already sent to
+ * Unless @kick is true, skip cap_snaps that were already sent to
  * the MDS (i.e., during this session).
  *
  * Called under i_ceph_lock.  Takes s_mutex as needed.
  */
 void __ceph_flush_snaps(struct ceph_inode_info *ci,
 			struct ceph_mds_session **psession,
-			int again)
+			int kick)
 		__releases(ci->i_ceph_lock)
 		__acquires(ci->i_ceph_lock)
 {
@@ -1297,11 +1257,8 @@
 		if (capsnap->dirty_pages || capsnap->writing)
 			break;
 
-		/*
-		 * if cap writeback already occurred, we should have dropped
-		 * the capsnap in ceph_put_wrbuffer_cap_refs.
-		 */
-		BUG_ON(capsnap->dirty == 0);
+		/* should be removed by ceph_try_drop_cap_snap() */
+		BUG_ON(!capsnap->need_flush);
 
 		/* pick mds, take s_mutex */
 		if (ci->i_auth_cap == NULL) {
@@ -1310,7 +1267,7 @@
 		}
 
 		/* only flush each capsnap once */
-		if (!again && !list_empty(&capsnap->flushing_item)) {
+		if (!kick && !list_empty(&capsnap->flushing_item)) {
 			dout("already flushed %p, skipping\n", capsnap);
 			continue;
 		}
@@ -1320,6 +1277,9 @@
 
 		if (session && session->s_mds != mds) {
 			dout("oops, wrong session %p mutex\n", session);
+			if (kick)
+				goto out;
+
 			mutex_unlock(&session->s_mutex);
 			ceph_put_mds_session(session);
 			session = NULL;
@@ -1343,20 +1303,22 @@
 			goto retry;
 		}
 
-		capsnap->flush_tid = ++ci->i_cap_flush_last_tid;
+		spin_lock(&mdsc->cap_dirty_lock);
+		capsnap->flush_tid = ++mdsc->last_cap_flush_tid;
+		spin_unlock(&mdsc->cap_dirty_lock);
+
 		atomic_inc(&capsnap->nref);
-		if (!list_empty(&capsnap->flushing_item))
-			list_del_init(&capsnap->flushing_item);
-		list_add_tail(&capsnap->flushing_item,
-			      &session->s_cap_snaps_flushing);
+		if (list_empty(&capsnap->flushing_item))
+			list_add_tail(&capsnap->flushing_item,
+				      &session->s_cap_snaps_flushing);
 		spin_unlock(&ci->i_ceph_lock);
 
 		dout("flush_snaps %p cap_snap %p follows %lld tid %llu\n",
 		     inode, capsnap, capsnap->follows, capsnap->flush_tid);
 		send_cap_msg(session, ceph_vino(inode).ino, 0,
 			     CEPH_CAP_OP_FLUSHSNAP, capsnap->issued, 0,
-			     capsnap->dirty, 0, capsnap->flush_tid, 0, mseq,
-			     capsnap->size, 0,
+			     capsnap->dirty, 0, capsnap->flush_tid, 0,
+			     0, mseq, capsnap->size, 0,
 			     &capsnap->mtime, &capsnap->atime,
 			     capsnap->time_warp_seq,
 			     capsnap->uid, capsnap->gid, capsnap->mode,
@@ -1396,7 +1358,8 @@
  * Caller is then responsible for calling __mark_inode_dirty with the
  * returned flags value.
  */
-int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask)
+int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask,
+			   struct ceph_cap_flush **pcf)
 {
 	struct ceph_mds_client *mdsc =
 		ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
@@ -1416,9 +1379,14 @@
 	     ceph_cap_string(was | mask));
 	ci->i_dirty_caps |= mask;
 	if (was == 0) {
-		if (!ci->i_head_snapc)
+		WARN_ON_ONCE(ci->i_prealloc_cap_flush);
+		swap(ci->i_prealloc_cap_flush, *pcf);
+
+		if (!ci->i_head_snapc) {
+			WARN_ON_ONCE(!rwsem_is_locked(&mdsc->snap_rwsem));
 			ci->i_head_snapc = ceph_get_snap_context(
 				ci->i_snap_realm->cached_context);
+		}
 		dout(" inode %p now dirty snapc %p auth cap %p\n",
 		     &ci->vfs_inode, ci->i_head_snapc, ci->i_auth_cap);
 		BUG_ON(!list_empty(&ci->i_dirty_item));
@@ -1429,6 +1397,8 @@
 			ihold(inode);
 			dirty |= I_DIRTY_SYNC;
 		}
+	} else {
+		WARN_ON_ONCE(!ci->i_prealloc_cap_flush);
 	}
 	BUG_ON(list_empty(&ci->i_dirty_item));
 	if (((was | ci->i_flushing_caps) & CEPH_CAP_FILE_BUFFER) &&
@@ -1438,6 +1408,74 @@
 	return dirty;
 }
 
+static void __add_cap_flushing_to_inode(struct ceph_inode_info *ci,
+					struct ceph_cap_flush *cf)
+{
+	struct rb_node **p = &ci->i_cap_flush_tree.rb_node;
+	struct rb_node *parent = NULL;
+	struct ceph_cap_flush *other = NULL;
+
+	while (*p) {
+		parent = *p;
+		other = rb_entry(parent, struct ceph_cap_flush, i_node);
+
+		if (cf->tid < other->tid)
+			p = &(*p)->rb_left;
+		else if (cf->tid > other->tid)
+			p = &(*p)->rb_right;
+		else
+			BUG();
+	}
+
+	rb_link_node(&cf->i_node, parent, p);
+	rb_insert_color(&cf->i_node, &ci->i_cap_flush_tree);
+}
+
+static void __add_cap_flushing_to_mdsc(struct ceph_mds_client *mdsc,
+				       struct ceph_cap_flush *cf)
+{
+	struct rb_node **p = &mdsc->cap_flush_tree.rb_node;
+	struct rb_node *parent = NULL;
+	struct ceph_cap_flush *other = NULL;
+
+	while (*p) {
+		parent = *p;
+		other = rb_entry(parent, struct ceph_cap_flush, g_node);
+
+		if (cf->tid < other->tid)
+			p = &(*p)->rb_left;
+		else if (cf->tid > other->tid)
+			p = &(*p)->rb_right;
+		else
+			BUG();
+	}
+
+	rb_link_node(&cf->g_node, parent, p);
+	rb_insert_color(&cf->g_node, &mdsc->cap_flush_tree);
+}
+
+struct ceph_cap_flush *ceph_alloc_cap_flush(void)
+{
+	return kmem_cache_alloc(ceph_cap_flush_cachep, GFP_KERNEL);
+}
+
+void ceph_free_cap_flush(struct ceph_cap_flush *cf)
+{
+	if (cf)
+		kmem_cache_free(ceph_cap_flush_cachep, cf);
+}
+
+static u64 __get_oldest_flush_tid(struct ceph_mds_client *mdsc)
+{
+	struct rb_node *n = rb_first(&mdsc->cap_flush_tree);
+	if (n) {
+		struct ceph_cap_flush *cf =
+			rb_entry(n, struct ceph_cap_flush, g_node);
+		return cf->tid;
+	}
+	return 0;
+}
+
 /*
  * Add dirty inode to the flushing list.  Assigned a seq number so we
  * can wait for caps to flush without starving.
@@ -1445,14 +1483,17 @@
  * Called under i_ceph_lock.
  */
 static int __mark_caps_flushing(struct inode *inode,
-				 struct ceph_mds_session *session)
+				struct ceph_mds_session *session,
+				u64 *flush_tid, u64 *oldest_flush_tid)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_cap_flush *cf = NULL;
 	int flushing;
 
 	BUG_ON(ci->i_dirty_caps == 0);
 	BUG_ON(list_empty(&ci->i_dirty_item));
+	BUG_ON(!ci->i_prealloc_cap_flush);
 
 	flushing = ci->i_dirty_caps;
 	dout("__mark_caps_flushing flushing %s, flushing_caps %s -> %s\n",
@@ -1463,22 +1504,31 @@
 	ci->i_dirty_caps = 0;
 	dout(" inode %p now !dirty\n", inode);
 
+	swap(cf, ci->i_prealloc_cap_flush);
+	cf->caps = flushing;
+	cf->kick = false;
+
 	spin_lock(&mdsc->cap_dirty_lock);
 	list_del_init(&ci->i_dirty_item);
 
+	cf->tid = ++mdsc->last_cap_flush_tid;
+	__add_cap_flushing_to_mdsc(mdsc, cf);
+	*oldest_flush_tid = __get_oldest_flush_tid(mdsc);
+
 	if (list_empty(&ci->i_flushing_item)) {
-		ci->i_cap_flush_seq = ++mdsc->cap_flush_seq;
 		list_add_tail(&ci->i_flushing_item, &session->s_cap_flushing);
 		mdsc->num_cap_flushing++;
-		dout(" inode %p now flushing seq %lld\n", inode,
-		     ci->i_cap_flush_seq);
+		dout(" inode %p now flushing tid %llu\n", inode, cf->tid);
 	} else {
 		list_move_tail(&ci->i_flushing_item, &session->s_cap_flushing);
-		dout(" inode %p now flushing (more) seq %lld\n", inode,
-		     ci->i_cap_flush_seq);
+		dout(" inode %p now flushing (more) tid %llu\n",
+		     inode, cf->tid);
 	}
 	spin_unlock(&mdsc->cap_dirty_lock);
 
+	__add_cap_flushing_to_inode(ci, cf);
+
+	*flush_tid = cf->tid;
 	return flushing;
 }
 
@@ -1524,6 +1574,7 @@
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct inode *inode = &ci->vfs_inode;
 	struct ceph_cap *cap;
+	u64 flush_tid, oldest_flush_tid;
 	int file_wanted, used, cap_used;
 	int took_snap_rwsem = 0;             /* true if mdsc->snap_rwsem held */
 	int issued, implemented, want, retain, revoking, flushing = 0;
@@ -1553,13 +1604,13 @@
 retry_locked:
 	file_wanted = __ceph_caps_file_wanted(ci);
 	used = __ceph_caps_used(ci);
-	want = file_wanted | used;
 	issued = __ceph_caps_issued(ci, &implemented);
 	revoking = implemented & ~issued;
 
-	retain = want | CEPH_CAP_PIN;
+	want = file_wanted;
+	retain = file_wanted | used | CEPH_CAP_PIN;
 	if (!mdsc->stopping && inode->i_nlink > 0) {
-		if (want) {
+		if (file_wanted) {
 			retain |= CEPH_CAP_ANY;       /* be greedy */
 		} else if (S_ISDIR(inode->i_mode) &&
 			   (issued & CEPH_CAP_FILE_SHARED) &&
@@ -1602,9 +1653,10 @@
 	 * If we fail, it's because pages are locked.... try again later.
 	 */
 	if ((!is_delayed || mdsc->stopping) &&
-	    ci->i_wrbuffer_ref == 0 &&               /* no dirty pages... */
-	    inode->i_data.nrpages &&                 /* have cached pages */
-	    (file_wanted == 0 ||                     /* no open files */
+	    !S_ISDIR(inode->i_mode) &&		/* ignore readdir cache */
+	    ci->i_wrbuffer_ref == 0 &&		/* no dirty pages... */
+	    inode->i_data.nrpages &&		/* have cached pages */
+	    (file_wanted == 0 ||		/* no open files */
 	     (revoking & (CEPH_CAP_FILE_CACHE|
 			  CEPH_CAP_FILE_LAZYIO))) && /*  or revoking cache */
 	    !tried_invalidate) {
@@ -1742,17 +1794,25 @@
 			took_snap_rwsem = 1;
 		}
 
-		if (cap == ci->i_auth_cap && ci->i_dirty_caps)
-			flushing = __mark_caps_flushing(inode, session);
-		else
+		if (cap == ci->i_auth_cap && ci->i_dirty_caps) {
+			flushing = __mark_caps_flushing(inode, session,
+							&flush_tid,
+							&oldest_flush_tid);
+		} else {
 			flushing = 0;
+			flush_tid = 0;
+			spin_lock(&mdsc->cap_dirty_lock);
+			oldest_flush_tid = __get_oldest_flush_tid(mdsc);
+			spin_unlock(&mdsc->cap_dirty_lock);
+		}
 
 		mds = cap->mds;  /* remember mds, so we don't repeat */
 		sent++;
 
 		/* __send_cap drops i_ceph_lock */
 		delayed += __send_cap(mdsc, cap, CEPH_CAP_OP_UPDATE, cap_used,
-				      want, retain, flushing, NULL);
+				      want, retain, flushing,
+				      flush_tid, oldest_flush_tid);
 		goto retry; /* retake i_ceph_lock and restart our cap scan. */
 	}
 
@@ -1781,12 +1841,13 @@
 /*
  * Try to flush dirty caps back to the auth mds.
  */
-static int try_flush_caps(struct inode *inode, unsigned *flush_tid)
+static int try_flush_caps(struct inode *inode, u64 *ptid)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	int flushing = 0;
 	struct ceph_mds_session *session = NULL;
+	int flushing = 0;
+	u64 flush_tid = 0, oldest_flush_tid = 0;
 
 retry:
 	spin_lock(&ci->i_ceph_lock);
@@ -1811,42 +1872,54 @@
 		if (cap->session->s_state < CEPH_MDS_SESSION_OPEN)
 			goto out;
 
-		flushing = __mark_caps_flushing(inode, session);
+		flushing = __mark_caps_flushing(inode, session, &flush_tid,
+						&oldest_flush_tid);
 
 		/* __send_cap drops i_ceph_lock */
 		delayed = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH, used, want,
-				     cap->issued | cap->implemented, flushing,
-				     flush_tid);
-		if (!delayed)
-			goto out_unlocked;
+				     (cap->issued | cap->implemented),
+				     flushing, flush_tid, oldest_flush_tid);
 
-		spin_lock(&ci->i_ceph_lock);
-		__cap_delay_requeue(mdsc, ci);
+		if (delayed) {
+			spin_lock(&ci->i_ceph_lock);
+			__cap_delay_requeue(mdsc, ci);
+			spin_unlock(&ci->i_ceph_lock);
+		}
+	} else {
+		struct rb_node *n = rb_last(&ci->i_cap_flush_tree);
+		if (n) {
+			struct ceph_cap_flush *cf =
+				rb_entry(n, struct ceph_cap_flush, i_node);
+			flush_tid = cf->tid;
+		}
+		flushing = ci->i_flushing_caps;
+		spin_unlock(&ci->i_ceph_lock);
 	}
 out:
-	spin_unlock(&ci->i_ceph_lock);
-out_unlocked:
 	if (session)
 		mutex_unlock(&session->s_mutex);
+
+	*ptid = flush_tid;
 	return flushing;
 }
 
 /*
  * Return true if we've flushed caps through the given flush_tid.
  */
-static int caps_are_flushed(struct inode *inode, unsigned tid)
+static int caps_are_flushed(struct inode *inode, u64 flush_tid)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	int i, ret = 1;
+	struct ceph_cap_flush *cf;
+	struct rb_node *n;
+	int ret = 1;
 
 	spin_lock(&ci->i_ceph_lock);
-	for (i = 0; i < CEPH_CAP_BITS; i++)
-		if ((ci->i_flushing_caps & (1 << i)) &&
-		    ci->i_cap_flush_tid[i] <= tid) {
-			/* still flushing this bit */
+	n = rb_first(&ci->i_cap_flush_tree);
+	if (n) {
+		cf = rb_entry(n, struct ceph_cap_flush, i_node);
+		if (cf->tid <= flush_tid)
 			ret = 0;
-			break;
-		}
+	}
 	spin_unlock(&ci->i_ceph_lock);
 	return ret;
 }
@@ -1864,13 +1937,16 @@
 	struct ceph_osd_request *req;
 	u64 last_tid;
 
+	if (!S_ISREG(inode->i_mode))
+		return;
+
 	spin_lock(&ci->i_unsafe_lock);
 	if (list_empty(head))
 		goto out;
 
 	/* set upper bound as _last_ entry in chain */
-	req = list_entry(head->prev, struct ceph_osd_request,
-			 r_unsafe_item);
+	req = list_last_entry(head, struct ceph_osd_request,
+			      r_unsafe_item);
 	last_tid = req->r_tid;
 
 	do {
@@ -1888,18 +1964,64 @@
 		 */
 		if (list_empty(head))
 			break;
-		req = list_entry(head->next, struct ceph_osd_request,
-				 r_unsafe_item);
+		req = list_first_entry(head, struct ceph_osd_request,
+				       r_unsafe_item);
 	} while (req->r_tid < last_tid);
 out:
 	spin_unlock(&ci->i_unsafe_lock);
 }
 
+/*
+ * wait for any uncommitted directory operations to commit.
+ */
+static int unsafe_dirop_wait(struct inode *inode)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct list_head *head = &ci->i_unsafe_dirops;
+	struct ceph_mds_request *req;
+	u64 last_tid;
+	int ret = 0;
+
+	if (!S_ISDIR(inode->i_mode))
+		return 0;
+
+	spin_lock(&ci->i_unsafe_lock);
+	if (list_empty(head))
+		goto out;
+
+	req = list_last_entry(head, struct ceph_mds_request,
+			      r_unsafe_dir_item);
+	last_tid = req->r_tid;
+
+	do {
+		ceph_mdsc_get_request(req);
+		spin_unlock(&ci->i_unsafe_lock);
+
+		dout("unsafe_dirop_wait %p wait on tid %llu (until %llu)\n",
+		     inode, req->r_tid, last_tid);
+		ret = !wait_for_completion_timeout(&req->r_safe_completion,
+					ceph_timeout_jiffies(req->r_timeout));
+		if (ret)
+			ret = -EIO;  /* timed out */
+
+		ceph_mdsc_put_request(req);
+
+		spin_lock(&ci->i_unsafe_lock);
+		if (ret || list_empty(head))
+			break;
+		req = list_first_entry(head, struct ceph_mds_request,
+				       r_unsafe_dir_item);
+	} while (req->r_tid < last_tid);
+out:
+	spin_unlock(&ci->i_unsafe_lock);
+	return ret;
+}
+
 int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	struct inode *inode = file->f_mapping->host;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	unsigned flush_tid;
+	u64 flush_tid;
 	int ret;
 	int dirty;
 
@@ -1908,25 +2030,30 @@
 
 	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
 	if (ret < 0)
-		return ret;
+		goto out;
+
+	if (datasync)
+		goto out;
+
 	mutex_lock(&inode->i_mutex);
 
 	dirty = try_flush_caps(inode, &flush_tid);
 	dout("fsync dirty caps are %s\n", ceph_cap_string(dirty));
 
+	ret = unsafe_dirop_wait(inode);
+
 	/*
 	 * only wait on non-file metadata writeback (the mds
 	 * can recover size and mtime, so we don't need to
 	 * wait for that)
 	 */
-	if (!datasync && (dirty & ~CEPH_CAP_ANY_FILE_WR)) {
-		dout("fsync waiting for flush_tid %u\n", flush_tid);
+	if (!ret && (dirty & ~CEPH_CAP_ANY_FILE_WR)) {
 		ret = wait_event_interruptible(ci->i_cap_wq,
-				       caps_are_flushed(inode, flush_tid));
+					caps_are_flushed(inode, flush_tid));
 	}
-
-	dout("fsync %p%s done\n", inode, datasync ? " datasync" : "");
 	mutex_unlock(&inode->i_mutex);
+out:
+	dout("fsync %p%s result=%d\n", inode, datasync ? " datasync" : "", ret);
 	return ret;
 }
 
@@ -1939,7 +2066,7 @@
 int ceph_write_inode(struct inode *inode, struct writeback_control *wbc)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	unsigned flush_tid;
+	u64 flush_tid;
 	int err = 0;
 	int dirty;
 	int wait = wbc->sync_mode == WB_SYNC_ALL;
@@ -1994,6 +2121,104 @@
 	}
 }
 
+static int __kick_flushing_caps(struct ceph_mds_client *mdsc,
+				struct ceph_mds_session *session,
+				struct ceph_inode_info *ci,
+				bool kick_all)
+{
+	struct inode *inode = &ci->vfs_inode;
+	struct ceph_cap *cap;
+	struct ceph_cap_flush *cf;
+	struct rb_node *n;
+	int delayed = 0;
+	u64 first_tid = 0;
+	u64 oldest_flush_tid;
+
+	spin_lock(&mdsc->cap_dirty_lock);
+	oldest_flush_tid = __get_oldest_flush_tid(mdsc);
+	spin_unlock(&mdsc->cap_dirty_lock);
+
+	while (true) {
+		spin_lock(&ci->i_ceph_lock);
+		cap = ci->i_auth_cap;
+		if (!(cap && cap->session == session)) {
+			pr_err("%p auth cap %p not mds%d ???\n", inode,
+					cap, session->s_mds);
+			spin_unlock(&ci->i_ceph_lock);
+			break;
+		}
+
+		for (n = rb_first(&ci->i_cap_flush_tree); n; n = rb_next(n)) {
+			cf = rb_entry(n, struct ceph_cap_flush, i_node);
+			if (cf->tid < first_tid)
+				continue;
+			if (kick_all || cf->kick)
+				break;
+		}
+		if (!n) {
+			spin_unlock(&ci->i_ceph_lock);
+			break;
+		}
+
+		cf = rb_entry(n, struct ceph_cap_flush, i_node);
+		cf->kick = false;
+
+		first_tid = cf->tid + 1;
+
+		dout("kick_flushing_caps %p cap %p tid %llu %s\n", inode,
+		     cap, cf->tid, ceph_cap_string(cf->caps));
+		delayed |= __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH,
+				      __ceph_caps_used(ci),
+				      __ceph_caps_wanted(ci),
+				      cap->issued | cap->implemented,
+				      cf->caps, cf->tid, oldest_flush_tid);
+	}
+	return delayed;
+}
+
+void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc,
+				   struct ceph_mds_session *session)
+{
+	struct ceph_inode_info *ci;
+	struct ceph_cap *cap;
+	struct ceph_cap_flush *cf;
+	struct rb_node *n;
+
+	dout("early_kick_flushing_caps mds%d\n", session->s_mds);
+	list_for_each_entry(ci, &session->s_cap_flushing, i_flushing_item) {
+		spin_lock(&ci->i_ceph_lock);
+		cap = ci->i_auth_cap;
+		if (!(cap && cap->session == session)) {
+			pr_err("%p auth cap %p not mds%d ???\n",
+				&ci->vfs_inode, cap, session->s_mds);
+			spin_unlock(&ci->i_ceph_lock);
+			continue;
+		}
+
+
+		/*
+		 * if flushing caps were revoked, we re-send the cap flush
+		 * in client reconnect stage. This guarantees MDS * processes
+		 * the cap flush message before issuing the flushing caps to
+		 * other client.
+		 */
+		if ((cap->issued & ci->i_flushing_caps) !=
+		    ci->i_flushing_caps) {
+			spin_unlock(&ci->i_ceph_lock);
+			if (!__kick_flushing_caps(mdsc, session, ci, true))
+				continue;
+			spin_lock(&ci->i_ceph_lock);
+		}
+
+		for (n = rb_first(&ci->i_cap_flush_tree); n; n = rb_next(n)) {
+			cf = rb_entry(n, struct ceph_cap_flush, i_node);
+			cf->kick = true;
+		}
+
+		spin_unlock(&ci->i_ceph_lock);
+	}
+}
+
 void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc,
 			     struct ceph_mds_session *session)
 {
@@ -2003,28 +2228,10 @@
 
 	dout("kick_flushing_caps mds%d\n", session->s_mds);
 	list_for_each_entry(ci, &session->s_cap_flushing, i_flushing_item) {
-		struct inode *inode = &ci->vfs_inode;
-		struct ceph_cap *cap;
-		int delayed = 0;
-
-		spin_lock(&ci->i_ceph_lock);
-		cap = ci->i_auth_cap;
-		if (cap && cap->session == session) {
-			dout("kick_flushing_caps %p cap %p %s\n", inode,
-			     cap, ceph_cap_string(ci->i_flushing_caps));
-			delayed = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH,
-					     __ceph_caps_used(ci),
-					     __ceph_caps_wanted(ci),
-					     cap->issued | cap->implemented,
-					     ci->i_flushing_caps, NULL);
-			if (delayed) {
-				spin_lock(&ci->i_ceph_lock);
-				__cap_delay_requeue(mdsc, ci);
-				spin_unlock(&ci->i_ceph_lock);
-			}
-		} else {
-			pr_err("%p auth cap %p not mds%d ???\n", inode,
-			       cap, session->s_mds);
+		int delayed = __kick_flushing_caps(mdsc, session, ci, false);
+		if (delayed) {
+			spin_lock(&ci->i_ceph_lock);
+			__cap_delay_requeue(mdsc, ci);
 			spin_unlock(&ci->i_ceph_lock);
 		}
 	}
@@ -2036,26 +2243,25 @@
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_cap *cap;
-	int delayed = 0;
 
 	spin_lock(&ci->i_ceph_lock);
 	cap = ci->i_auth_cap;
-	dout("kick_flushing_inode_caps %p flushing %s flush_seq %lld\n", inode,
-	     ceph_cap_string(ci->i_flushing_caps), ci->i_cap_flush_seq);
+	dout("kick_flushing_inode_caps %p flushing %s\n", inode,
+	     ceph_cap_string(ci->i_flushing_caps));
 
 	__ceph_flush_snaps(ci, &session, 1);
 
 	if (ci->i_flushing_caps) {
+		int delayed;
+
 		spin_lock(&mdsc->cap_dirty_lock);
 		list_move_tail(&ci->i_flushing_item,
 			       &cap->session->s_cap_flushing);
 		spin_unlock(&mdsc->cap_dirty_lock);
 
-		delayed = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH,
-				     __ceph_caps_used(ci),
-				     __ceph_caps_wanted(ci),
-				     cap->issued | cap->implemented,
-				     ci->i_flushing_caps, NULL);
+		spin_unlock(&ci->i_ceph_lock);
+
+		delayed = __kick_flushing_caps(mdsc, session, ci, true);
 		if (delayed) {
 			spin_lock(&ci->i_ceph_lock);
 			__cap_delay_requeue(mdsc, ci);
@@ -2073,7 +2279,8 @@
  *
  * Protected by i_ceph_lock.
  */
-static void __take_cap_refs(struct ceph_inode_info *ci, int got)
+static void __take_cap_refs(struct ceph_inode_info *ci, int got,
+			    bool snap_rwsem_locked)
 {
 	if (got & CEPH_CAP_PIN)
 		ci->i_pin_ref++;
@@ -2081,8 +2288,14 @@
 		ci->i_rd_ref++;
 	if (got & CEPH_CAP_FILE_CACHE)
 		ci->i_rdcache_ref++;
-	if (got & CEPH_CAP_FILE_WR)
+	if (got & CEPH_CAP_FILE_WR) {
+		if (ci->i_wr_ref == 0 && !ci->i_head_snapc) {
+			BUG_ON(!snap_rwsem_locked);
+			ci->i_head_snapc = ceph_get_snap_context(
+					ci->i_snap_realm->cached_context);
+		}
 		ci->i_wr_ref++;
+	}
 	if (got & CEPH_CAP_FILE_BUFFER) {
 		if (ci->i_wb_ref == 0)
 			ihold(&ci->vfs_inode);
@@ -2100,16 +2313,19 @@
  * requested from the MDS.
  */
 static int try_get_cap_refs(struct ceph_inode_info *ci, int need, int want,
-			    loff_t endoff, int *got, int *check_max, int *err)
+			    loff_t endoff, bool nonblock, int *got, int *err)
 {
 	struct inode *inode = &ci->vfs_inode;
+	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
 	int ret = 0;
 	int have, implemented;
 	int file_wanted;
+	bool snap_rwsem_locked = false;
 
 	dout("get_cap_refs %p need %s want %s\n", inode,
 	     ceph_cap_string(need), ceph_cap_string(want));
 
+again:
 	spin_lock(&ci->i_ceph_lock);
 
 	/* make sure file is actually open */
@@ -2125,6 +2341,10 @@
 	/* finish pending truncate */
 	while (ci->i_truncate_pending) {
 		spin_unlock(&ci->i_ceph_lock);
+		if (snap_rwsem_locked) {
+			up_read(&mdsc->snap_rwsem);
+			snap_rwsem_locked = false;
+		}
 		__ceph_do_pending_vmtruncate(inode);
 		spin_lock(&ci->i_ceph_lock);
 	}
@@ -2136,7 +2356,7 @@
 			dout("get_cap_refs %p endoff %llu > maxsize %llu\n",
 			     inode, endoff, ci->i_max_size);
 			if (endoff > ci->i_requested_max_size) {
-				*check_max = 1;
+				*err = -EAGAIN;
 				ret = 1;
 			}
 			goto out_unlock;
@@ -2164,8 +2384,29 @@
 		     inode, ceph_cap_string(have), ceph_cap_string(not),
 		     ceph_cap_string(revoking));
 		if ((revoking & not) == 0) {
+			if (!snap_rwsem_locked &&
+			    !ci->i_head_snapc &&
+			    (need & CEPH_CAP_FILE_WR)) {
+				if (!down_read_trylock(&mdsc->snap_rwsem)) {
+					/*
+					 * we can not call down_read() when
+					 * task isn't in TASK_RUNNING state
+					 */
+					if (nonblock) {
+						*err = -EAGAIN;
+						ret = 1;
+						goto out_unlock;
+					}
+
+					spin_unlock(&ci->i_ceph_lock);
+					down_read(&mdsc->snap_rwsem);
+					snap_rwsem_locked = true;
+					goto again;
+				}
+				snap_rwsem_locked = true;
+			}
 			*got = need | (have & want);
-			__take_cap_refs(ci, *got);
+			__take_cap_refs(ci, *got, true);
 			ret = 1;
 		}
 	} else {
@@ -2189,6 +2430,8 @@
 	}
 out_unlock:
 	spin_unlock(&ci->i_ceph_lock);
+	if (snap_rwsem_locked)
+		up_read(&mdsc->snap_rwsem);
 
 	dout("get_cap_refs %p ret %d got %s\n", inode,
 	     ret, ceph_cap_string(*got));
@@ -2231,50 +2474,70 @@
 int ceph_get_caps(struct ceph_inode_info *ci, int need, int want,
 		  loff_t endoff, int *got, struct page **pinned_page)
 {
-	int _got, check_max, ret, err = 0;
+	int _got, ret, err = 0;
 
-retry:
-	if (endoff > 0)
-		check_max_size(&ci->vfs_inode, endoff);
-	_got = 0;
-	check_max = 0;
-	ret = wait_event_interruptible(ci->i_cap_wq,
-				try_get_cap_refs(ci, need, want, endoff,
-						 &_got, &check_max, &err));
-	if (err)
-		ret = err;
+	ret = ceph_pool_perm_check(ci, need);
 	if (ret < 0)
 		return ret;
 
-	if (check_max)
-		goto retry;
+	while (true) {
+		if (endoff > 0)
+			check_max_size(&ci->vfs_inode, endoff);
 
-	if (ci->i_inline_version != CEPH_INLINE_NONE &&
-	    (_got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) &&
-	    i_size_read(&ci->vfs_inode) > 0) {
-		struct page *page = find_get_page(ci->vfs_inode.i_mapping, 0);
-		if (page) {
-			if (PageUptodate(page)) {
-				*pinned_page = page;
-				goto out;
-			}
-			page_cache_release(page);
-		}
-		/*
-		 * drop cap refs first because getattr while holding
-		 * caps refs can cause deadlock.
-		 */
-		ceph_put_cap_refs(ci, _got);
+		err = 0;
 		_got = 0;
+		ret = try_get_cap_refs(ci, need, want, endoff,
+				       false, &_got, &err);
+		if (ret) {
+			if (err == -EAGAIN)
+				continue;
+			if (err < 0)
+				return err;
+		} else {
+			ret = wait_event_interruptible(ci->i_cap_wq,
+					try_get_cap_refs(ci, need, want, endoff,
+							 true, &_got, &err));
+			if (err == -EAGAIN)
+				continue;
+			if (err < 0)
+				ret = err;
+			if (ret < 0)
+				return ret;
+		}
 
-		/* getattr request will bring inline data into page cache */
-		ret = __ceph_do_getattr(&ci->vfs_inode, NULL,
-					CEPH_STAT_CAP_INLINE_DATA, true);
-		if (ret < 0)
-			return ret;
-		goto retry;
+		if (ci->i_inline_version != CEPH_INLINE_NONE &&
+		    (_got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) &&
+		    i_size_read(&ci->vfs_inode) > 0) {
+			struct page *page =
+				find_get_page(ci->vfs_inode.i_mapping, 0);
+			if (page) {
+				if (PageUptodate(page)) {
+					*pinned_page = page;
+					break;
+				}
+				page_cache_release(page);
+			}
+			/*
+			 * drop cap refs first because getattr while
+			 * holding * caps refs can cause deadlock.
+			 */
+			ceph_put_cap_refs(ci, _got);
+			_got = 0;
+
+			/*
+			 * getattr request will bring inline data into
+			 * page cache
+			 */
+			ret = __ceph_do_getattr(&ci->vfs_inode, NULL,
+						CEPH_STAT_CAP_INLINE_DATA,
+						true);
+			if (ret < 0)
+				return ret;
+			continue;
+		}
+		break;
 	}
-out:
+
 	*got = _got;
 	return 0;
 }
@@ -2286,10 +2549,31 @@
 void ceph_get_cap_refs(struct ceph_inode_info *ci, int caps)
 {
 	spin_lock(&ci->i_ceph_lock);
-	__take_cap_refs(ci, caps);
+	__take_cap_refs(ci, caps, false);
 	spin_unlock(&ci->i_ceph_lock);
 }
 
+
+/*
+ * drop cap_snap that is not associated with any snapshot.
+ * we don't need to send FLUSHSNAP message for it.
+ */
+static int ceph_try_drop_cap_snap(struct ceph_cap_snap *capsnap)
+{
+	if (!capsnap->need_flush &&
+	    !capsnap->writing && !capsnap->dirty_pages) {
+
+		dout("dropping cap_snap %p follows %llu\n",
+		     capsnap, capsnap->follows);
+		ceph_put_snap_context(capsnap->context);
+		list_del(&capsnap->ci_item);
+		list_del(&capsnap->flushing_item);
+		ceph_put_cap_snap(capsnap);
+		return 1;
+	}
+	return 0;
+}
+
 /*
  * Release cap refs.
  *
@@ -2303,7 +2587,6 @@
 {
 	struct inode *inode = &ci->vfs_inode;
 	int last = 0, put = 0, flushsnaps = 0, wake = 0;
-	struct ceph_cap_snap *capsnap;
 
 	spin_lock(&ci->i_ceph_lock);
 	if (had & CEPH_CAP_PIN)
@@ -2325,17 +2608,24 @@
 	if (had & CEPH_CAP_FILE_WR)
 		if (--ci->i_wr_ref == 0) {
 			last++;
-			if (!list_empty(&ci->i_cap_snaps)) {
-				capsnap = list_first_entry(&ci->i_cap_snaps,
-						     struct ceph_cap_snap,
-						     ci_item);
-				if (capsnap->writing) {
-					capsnap->writing = 0;
-					flushsnaps =
-						__ceph_finish_cap_snap(ci,
-								       capsnap);
-					wake = 1;
-				}
+			if (__ceph_have_pending_cap_snap(ci)) {
+				struct ceph_cap_snap *capsnap =
+					list_last_entry(&ci->i_cap_snaps,
+							struct ceph_cap_snap,
+							ci_item);
+				capsnap->writing = 0;
+				if (ceph_try_drop_cap_snap(capsnap))
+					put++;
+				else if (__ceph_finish_cap_snap(ci, capsnap))
+					flushsnaps = 1;
+				wake = 1;
+			}
+			if (ci->i_wrbuffer_ref_head == 0 &&
+			    ci->i_dirty_caps == 0 &&
+			    ci->i_flushing_caps == 0) {
+				BUG_ON(!ci->i_head_snapc);
+				ceph_put_snap_context(ci->i_head_snapc);
+				ci->i_head_snapc = NULL;
 			}
 			/* see comment in __ceph_remove_cap() */
 			if (!__ceph_is_any_caps(ci) && ci->i_snap_realm)
@@ -2352,7 +2642,7 @@
 		ceph_flush_snaps(ci);
 	if (wake)
 		wake_up_all(&ci->i_cap_wq);
-	if (put)
+	while (put-- > 0)
 		iput(inode);
 }
 
@@ -2380,7 +2670,9 @@
 	if (ci->i_head_snapc == snapc) {
 		ci->i_wrbuffer_ref_head -= nr;
 		if (ci->i_wrbuffer_ref_head == 0 &&
-		    ci->i_dirty_caps == 0 && ci->i_flushing_caps == 0) {
+		    ci->i_wr_ref == 0 &&
+		    ci->i_dirty_caps == 0 &&
+		    ci->i_flushing_caps == 0) {
 			BUG_ON(!ci->i_head_snapc);
 			ceph_put_snap_context(ci->i_head_snapc);
 			ci->i_head_snapc = NULL;
@@ -2401,25 +2693,15 @@
 		capsnap->dirty_pages -= nr;
 		if (capsnap->dirty_pages == 0) {
 			complete_capsnap = 1;
-			if (capsnap->dirty == 0)
-				/* cap writeback completed before we created
-				 * the cap_snap; no FLUSHSNAP is needed */
-				drop_capsnap = 1;
+			drop_capsnap = ceph_try_drop_cap_snap(capsnap);
 		}
 		dout("put_wrbuffer_cap_refs on %p cap_snap %p "
-		     " snap %lld %d/%d -> %d/%d %s%s%s\n",
+		     " snap %lld %d/%d -> %d/%d %s%s\n",
 		     inode, capsnap, capsnap->context->seq,
 		     ci->i_wrbuffer_ref+nr, capsnap->dirty_pages + nr,
 		     ci->i_wrbuffer_ref, capsnap->dirty_pages,
 		     last ? " (wrbuffer last)" : "",
-		     complete_capsnap ? " (complete capsnap)" : "",
-		     drop_capsnap ? " (drop capsnap)" : "");
-		if (drop_capsnap) {
-			ceph_put_snap_context(capsnap->context);
-			list_del(&capsnap->ci_item);
-			list_del(&capsnap->flushing_item);
-			ceph_put_cap_snap(capsnap);
-		}
+		     complete_capsnap ? " (complete capsnap)" : "");
 	}
 
 	spin_unlock(&ci->i_ceph_lock);
@@ -2526,7 +2808,8 @@
 	 * try to invalidate (once).  (If there are dirty buffers, we
 	 * will invalidate _after_ writeback.)
 	 */
-	if (((cap->issued & ~newcaps) & CEPH_CAP_FILE_CACHE) &&
+	if (!S_ISDIR(inode->i_mode) && /* don't invalidate readdir cache */
+	    ((cap->issued & ~newcaps) & CEPH_CAP_FILE_CACHE) &&
 	    (newcaps & CEPH_CAP_FILE_LAZYIO) == 0 &&
 	    !ci->i_wrbuffer_ref) {
 		if (try_nonblocking_invalidate(inode)) {
@@ -2732,16 +3015,29 @@
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_cap_flush *cf;
+	struct rb_node *n;
+	LIST_HEAD(to_remove);
 	unsigned seq = le32_to_cpu(m->seq);
 	int dirty = le32_to_cpu(m->dirty);
 	int cleaned = 0;
 	int drop = 0;
-	int i;
 
-	for (i = 0; i < CEPH_CAP_BITS; i++)
-		if ((dirty & (1 << i)) &&
-		    (u16)flush_tid == ci->i_cap_flush_tid[i])
-			cleaned |= 1 << i;
+	n = rb_first(&ci->i_cap_flush_tree);
+	while (n) {
+		cf = rb_entry(n, struct ceph_cap_flush, i_node);
+		n = rb_next(&cf->i_node);
+		if (cf->tid == flush_tid)
+			cleaned = cf->caps;
+		if (cf->tid <= flush_tid) {
+			rb_erase(&cf->i_node, &ci->i_cap_flush_tree);
+			list_add_tail(&cf->list, &to_remove);
+		} else {
+			cleaned &= ~cf->caps;
+			if (!cleaned)
+				break;
+		}
+	}
 
 	dout("handle_cap_flush_ack inode %p mds%d seq %d on %s cleaned %s,"
 	     " flushing %s -> %s\n",
@@ -2749,12 +3045,23 @@
 	     ceph_cap_string(cleaned), ceph_cap_string(ci->i_flushing_caps),
 	     ceph_cap_string(ci->i_flushing_caps & ~cleaned));
 
-	if (ci->i_flushing_caps == (ci->i_flushing_caps & ~cleaned))
+	if (list_empty(&to_remove) && !cleaned)
 		goto out;
 
 	ci->i_flushing_caps &= ~cleaned;
 
 	spin_lock(&mdsc->cap_dirty_lock);
+
+	if (!list_empty(&to_remove)) {
+		list_for_each_entry(cf, &to_remove, list)
+			rb_erase(&cf->g_node, &mdsc->cap_flush_tree);
+
+		n = rb_first(&mdsc->cap_flush_tree);
+		cf = n ? rb_entry(n, struct ceph_cap_flush, g_node) : NULL;
+		if (!cf || cf->tid > flush_tid)
+			wake_up_all(&mdsc->cap_flushing_wq);
+	}
+
 	if (ci->i_flushing_caps == 0) {
 		list_del_init(&ci->i_flushing_item);
 		if (!list_empty(&session->s_cap_flushing))
@@ -2764,14 +3071,14 @@
 					 struct ceph_inode_info,
 					 i_flushing_item)->vfs_inode);
 		mdsc->num_cap_flushing--;
-		wake_up_all(&mdsc->cap_flushing_wq);
 		dout(" inode %p now !flushing\n", inode);
 
 		if (ci->i_dirty_caps == 0) {
 			dout(" inode %p now clean\n", inode);
 			BUG_ON(!list_empty(&ci->i_dirty_item));
 			drop = 1;
-			if (ci->i_wrbuffer_ref_head == 0) {
+			if (ci->i_wr_ref == 0 &&
+			    ci->i_wrbuffer_ref_head == 0) {
 				BUG_ON(!ci->i_head_snapc);
 				ceph_put_snap_context(ci->i_head_snapc);
 				ci->i_head_snapc = NULL;
@@ -2785,6 +3092,13 @@
 
 out:
 	spin_unlock(&ci->i_ceph_lock);
+
+	while (!list_empty(&to_remove)) {
+		cf = list_first_entry(&to_remove,
+				      struct ceph_cap_flush, list);
+		list_del(&cf->list);
+		ceph_free_cap_flush(cf);
+	}
 	if (drop)
 		iput(inode);
 }
@@ -2800,6 +3114,7 @@
 				     struct ceph_mds_session *session)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 	u64 follows = le64_to_cpu(m->snap_follows);
 	struct ceph_cap_snap *capsnap;
 	int drop = 0;
@@ -2823,6 +3138,7 @@
 			list_del(&capsnap->ci_item);
 			list_del(&capsnap->flushing_item);
 			ceph_put_cap_snap(capsnap);
+			wake_up_all(&mdsc->cap_flushing_wq);
 			drop = 1;
 			break;
 		} else {
@@ -2971,7 +3287,6 @@
 			mutex_lock_nested(&session->s_mutex,
 					  SINGLE_DEPTH_NESTING);
 		}
-		ceph_add_cap_releases(mdsc, tsession);
 		new_cap = ceph_get_cap(mdsc, NULL);
 	} else {
 		WARN_ON(1);
@@ -3167,16 +3482,20 @@
 	dout(" mds%d seq %lld cap seq %u\n", session->s_mds, session->s_seq,
 	     (unsigned)seq);
 
-	if (op == CEPH_CAP_OP_IMPORT)
-		ceph_add_cap_releases(mdsc, session);
-
 	if (!inode) {
 		dout(" i don't have ino %llx\n", vino.ino);
 
 		if (op == CEPH_CAP_OP_IMPORT) {
+			cap = ceph_get_cap(mdsc, NULL);
+			cap->cap_ino = vino.ino;
+			cap->queue_release = 1;
+			cap->cap_id = cap_id;
+			cap->mseq = mseq;
+			cap->seq = seq;
 			spin_lock(&session->s_cap_lock);
-			__queue_cap_release(session, vino.ino, cap_id,
-					    mseq, seq);
+			list_add_tail(&cap->session_caps,
+					&session->s_cap_releases);
+			session->s_num_cap_releases++;
 			spin_unlock(&session->s_cap_lock);
 		}
 		goto flush_cap_releases;
@@ -3252,11 +3571,10 @@
 
 flush_cap_releases:
 	/*
-	 * send any full release message to try to move things
+	 * send any cap release message to try to move things
 	 * along for the mds (who clearly thinks we still have this
 	 * cap).
 	 */
-	ceph_add_cap_releases(mdsc, session);
 	ceph_send_cap_releases(mdsc, session);
 
 done:
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 4248307..9314b4e 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -38,7 +38,7 @@
 	if (dentry->d_fsdata)
 		return 0;
 
-	di = kmem_cache_alloc(ceph_dentry_cachep, GFP_NOFS | __GFP_ZERO);
+	di = kmem_cache_alloc(ceph_dentry_cachep, GFP_KERNEL | __GFP_ZERO);
 	if (!di)
 		return -ENOMEM;          /* oh well */
 
@@ -107,6 +107,27 @@
 }
 
 /*
+ * make note of the last dentry we read, so we can
+ * continue at the same lexicographical point,
+ * regardless of what dir changes take place on the
+ * server.
+ */
+static int note_last_dentry(struct ceph_file_info *fi, const char *name,
+		            int len, unsigned next_offset)
+{
+	char *buf = kmalloc(len+1, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+	kfree(fi->last_name);
+	fi->last_name = buf;
+	memcpy(fi->last_name, name, len);
+	fi->last_name[len] = 0;
+	fi->next_offset = next_offset;
+	dout("note_last_dentry '%s'\n", fi->last_name);
+	return 0;
+}
+
+/*
  * When possible, we try to satisfy a readdir by peeking at the
  * dcache.  We make this work by carefully ordering dentries on
  * d_child when we initially get results back from the MDS, and
@@ -123,123 +144,113 @@
 	struct ceph_file_info *fi = file->private_data;
 	struct dentry *parent = file->f_path.dentry;
 	struct inode *dir = d_inode(parent);
-	struct list_head *p;
-	struct dentry *dentry, *last;
+	struct dentry *dentry, *last = NULL;
 	struct ceph_dentry_info *di;
+	unsigned nsize = PAGE_CACHE_SIZE / sizeof(struct dentry *);
 	int err = 0;
+	loff_t ptr_pos = 0;
+	struct ceph_readdir_cache_control cache_ctl = {};
 
-	/* claim ref on last dentry we returned */
-	last = fi->dentry;
-	fi->dentry = NULL;
+	dout("__dcache_readdir %p v%u at %llu\n", dir, shared_gen, ctx->pos);
 
-	dout("__dcache_readdir %p v%u at %llu (last %p)\n",
-	     dir, shared_gen, ctx->pos, last);
-
-	spin_lock(&parent->d_lock);
-
-	/* start at beginning? */
-	if (ctx->pos == 2 || last == NULL ||
-	    fpos_cmp(ctx->pos, ceph_dentry(last)->offset) < 0) {
-		if (list_empty(&parent->d_subdirs))
-			goto out_unlock;
-		p = parent->d_subdirs.prev;
-		dout(" initial p %p/%p\n", p->prev, p->next);
-	} else {
-		p = last->d_child.prev;
+	/* we can calculate cache index for the first dirfrag */
+	if (ceph_frag_is_leftmost(fpos_frag(ctx->pos))) {
+		cache_ctl.index = fpos_off(ctx->pos) - 2;
+		BUG_ON(cache_ctl.index < 0);
+		ptr_pos = cache_ctl.index * sizeof(struct dentry *);
 	}
 
-more:
-	dentry = list_entry(p, struct dentry, d_child);
-	di = ceph_dentry(dentry);
-	while (1) {
-		dout(" p %p/%p %s d_subdirs %p/%p\n", p->prev, p->next,
-		     d_unhashed(dentry) ? "!hashed" : "hashed",
-		     parent->d_subdirs.prev, parent->d_subdirs.next);
-		if (p == &parent->d_subdirs) {
+	while (true) {
+		pgoff_t pgoff;
+		bool emit_dentry;
+
+		if (ptr_pos >= i_size_read(dir)) {
 			fi->flags |= CEPH_F_ATEND;
-			goto out_unlock;
+			err = 0;
+			break;
 		}
-		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
+
+		err = -EAGAIN;
+		pgoff = ptr_pos >> PAGE_CACHE_SHIFT;
+		if (!cache_ctl.page || pgoff != page_index(cache_ctl.page)) {
+			ceph_readdir_cache_release(&cache_ctl);
+			cache_ctl.page = find_lock_page(&dir->i_data, pgoff);
+			if (!cache_ctl.page) {
+				dout(" page %lu not found\n", pgoff);
+				break;
+			}
+			/* reading/filling the cache are serialized by
+			 * i_mutex, no need to use page lock */
+			unlock_page(cache_ctl.page);
+			cache_ctl.dentries = kmap(cache_ctl.page);
+		}
+
+		rcu_read_lock();
+		spin_lock(&parent->d_lock);
+		/* check i_size again here, because empty directory can be
+		 * marked as complete while not holding the i_mutex. */
+		if (ceph_dir_is_complete_ordered(dir) &&
+		    ptr_pos < i_size_read(dir))
+			dentry = cache_ctl.dentries[cache_ctl.index % nsize];
+		else
+			dentry = NULL;
+		spin_unlock(&parent->d_lock);
+		if (dentry && !lockref_get_not_dead(&dentry->d_lockref))
+			dentry = NULL;
+		rcu_read_unlock();
+		if (!dentry)
+			break;
+
+		emit_dentry = false;
+		di = ceph_dentry(dentry);
+		spin_lock(&dentry->d_lock);
 		if (di->lease_shared_gen == shared_gen &&
-		    !d_unhashed(dentry) && d_really_is_positive(dentry) &&
+		    d_really_is_positive(dentry) &&
 		    ceph_snap(d_inode(dentry)) != CEPH_SNAPDIR &&
 		    ceph_ino(d_inode(dentry)) != CEPH_INO_CEPH &&
-		    fpos_cmp(ctx->pos, di->offset) <= 0)
-			break;
-		dout(" skipping %p %pd at %llu (%llu)%s%s\n", dentry,
-		     dentry, di->offset,
-		     ctx->pos, d_unhashed(dentry) ? " unhashed" : "",
-		     !d_inode(dentry) ? " null" : "");
-		spin_unlock(&dentry->d_lock);
-		p = p->prev;
-		dentry = list_entry(p, struct dentry, d_child);
-		di = ceph_dentry(dentry);
-	}
-
-	dget_dlock(dentry);
-	spin_unlock(&dentry->d_lock);
-	spin_unlock(&parent->d_lock);
-
-	/* make sure a dentry wasn't dropped while we didn't have parent lock */
-	if (!ceph_dir_is_complete_ordered(dir)) {
-		dout(" lost dir complete on %p; falling back to mds\n", dir);
-		dput(dentry);
-		err = -EAGAIN;
-		goto out;
-	}
-
-	dout(" %llu (%llu) dentry %p %pd %p\n", di->offset, ctx->pos,
-	     dentry, dentry, d_inode(dentry));
-	if (!dir_emit(ctx, dentry->d_name.name,
-		      dentry->d_name.len,
-		      ceph_translate_ino(dentry->d_sb, d_inode(dentry)->i_ino),
-		      d_inode(dentry)->i_mode >> 12)) {
-		if (last) {
-			/* remember our position */
-			fi->dentry = last;
-			fi->next_offset = fpos_off(di->offset);
+		    fpos_cmp(ctx->pos, di->offset) <= 0) {
+			emit_dentry = true;
 		}
-		dput(dentry);
-		return 0;
+		spin_unlock(&dentry->d_lock);
+
+		if (emit_dentry) {
+			dout(" %llu (%llu) dentry %p %pd %p\n", di->offset, ctx->pos,
+			     dentry, dentry, d_inode(dentry));
+			ctx->pos = di->offset;
+			if (!dir_emit(ctx, dentry->d_name.name,
+				      dentry->d_name.len,
+				      ceph_translate_ino(dentry->d_sb,
+							 d_inode(dentry)->i_ino),
+				      d_inode(dentry)->i_mode >> 12)) {
+				dput(dentry);
+				err = 0;
+				break;
+			}
+			ctx->pos++;
+
+			if (last)
+				dput(last);
+			last = dentry;
+		} else {
+			dput(dentry);
+		}
+
+		cache_ctl.index++;
+		ptr_pos += sizeof(struct dentry *);
 	}
-
-	ctx->pos = di->offset + 1;
-
-	if (last)
+	ceph_readdir_cache_release(&cache_ctl);
+	if (last) {
+		int ret;
+		di = ceph_dentry(last);
+		ret = note_last_dentry(fi, last->d_name.name, last->d_name.len,
+				       fpos_off(di->offset) + 1);
+		if (ret < 0)
+			err = ret;
 		dput(last);
-	last = dentry;
-
-	spin_lock(&parent->d_lock);
-	p = p->prev;	/* advance to next dentry */
-	goto more;
-
-out_unlock:
-	spin_unlock(&parent->d_lock);
-out:
-	if (last)
-		dput(last);
+	}
 	return err;
 }
 
-/*
- * make note of the last dentry we read, so we can
- * continue at the same lexicographical point,
- * regardless of what dir changes take place on the
- * server.
- */
-static int note_last_dentry(struct ceph_file_info *fi, const char *name,
-			    int len)
-{
-	kfree(fi->last_name);
-	fi->last_name = kmalloc(len+1, GFP_NOFS);
-	if (!fi->last_name)
-		return -ENOMEM;
-	memcpy(fi->last_name, name, len);
-	fi->last_name[len] = 0;
-	dout("note_last_dentry '%s'\n", fi->last_name);
-	return 0;
-}
-
 static int ceph_readdir(struct file *file, struct dir_context *ctx)
 {
 	struct ceph_file_info *fi = file->private_data;
@@ -280,8 +291,7 @@
 
 	/* can we use the dcache? */
 	spin_lock(&ci->i_ceph_lock);
-	if ((ctx->pos == 2 || fi->dentry) &&
-	    ceph_test_mount_opt(fsc, DCACHE) &&
+	if (ceph_test_mount_opt(fsc, DCACHE) &&
 	    !ceph_test_mount_opt(fsc, NOASYNCREADDIR) &&
 	    ceph_snap(inode) != CEPH_SNAPDIR &&
 	    __ceph_dir_is_complete_ordered(ci) &&
@@ -296,24 +306,8 @@
 	} else {
 		spin_unlock(&ci->i_ceph_lock);
 	}
-	if (fi->dentry) {
-		err = note_last_dentry(fi, fi->dentry->d_name.name,
-				       fi->dentry->d_name.len);
-		if (err)
-			return err;
-		dput(fi->dentry);
-		fi->dentry = NULL;
-	}
 
 	/* proceed with a normal readdir */
-
-	if (ctx->pos == 2) {
-		/* note dir version at start of readdir so we can tell
-		 * if any dentries get dropped */
-		fi->dir_release_count = atomic_read(&ci->i_release_count);
-		fi->dir_ordered_count = ci->i_ordered_count;
-	}
-
 more:
 	/* do we have the correct frag content buffered? */
 	if (fi->frag != frag || fi->last_readdir == NULL) {
@@ -342,12 +336,15 @@
 		req->r_direct_hash = ceph_frag_value(frag);
 		req->r_direct_is_hash = true;
 		if (fi->last_name) {
-			req->r_path2 = kstrdup(fi->last_name, GFP_NOFS);
+			req->r_path2 = kstrdup(fi->last_name, GFP_KERNEL);
 			if (!req->r_path2) {
 				ceph_mdsc_put_request(req);
 				return -ENOMEM;
 			}
 		}
+		req->r_dir_release_cnt = fi->dir_release_count;
+		req->r_dir_ordered_cnt = fi->dir_ordered_count;
+		req->r_readdir_cache_idx = fi->readdir_cache_idx;
 		req->r_readdir_offset = fi->next_offset;
 		req->r_args.readdir.frag = cpu_to_le32(frag);
 
@@ -364,26 +361,38 @@
 		     (int)req->r_reply_info.dir_end,
 		     (int)req->r_reply_info.dir_complete);
 
-		if (!req->r_did_prepopulate) {
-			dout("readdir !did_prepopulate");
-			/* preclude from marking dir complete */
-			fi->dir_release_count--;
-		}
 
 		/* note next offset and last dentry name */
 		rinfo = &req->r_reply_info;
 		if (le32_to_cpu(rinfo->dir_dir->frag) != frag) {
 			frag = le32_to_cpu(rinfo->dir_dir->frag);
-			if (ceph_frag_is_leftmost(frag))
-				fi->next_offset = 2;
-			else
-				fi->next_offset = 0;
-			off = fi->next_offset;
+			off = req->r_readdir_offset;
+			fi->next_offset = off;
 		}
+
 		fi->frag = frag;
 		fi->offset = fi->next_offset;
 		fi->last_readdir = req;
 
+		if (req->r_did_prepopulate) {
+			fi->readdir_cache_idx = req->r_readdir_cache_idx;
+			if (fi->readdir_cache_idx < 0) {
+				/* preclude from marking dir ordered */
+				fi->dir_ordered_count = 0;
+			} else if (ceph_frag_is_leftmost(frag) && off == 2) {
+				/* note dir version at start of readdir so
+				 * we can tell if any dentries get dropped */
+				fi->dir_release_count = req->r_dir_release_cnt;
+				fi->dir_ordered_count = req->r_dir_ordered_cnt;
+			}
+		} else {
+			dout("readdir !did_prepopulate");
+			/* disable readdir cache */
+			fi->readdir_cache_idx = -1;
+			/* preclude from marking dir complete */
+			fi->dir_release_count = 0;
+		}
+
 		if (req->r_reply_info.dir_end) {
 			kfree(fi->last_name);
 			fi->last_name = NULL;
@@ -394,10 +403,10 @@
 		} else {
 			err = note_last_dentry(fi,
 				       rinfo->dir_dname[rinfo->dir_nr-1],
-				       rinfo->dir_dname_len[rinfo->dir_nr-1]);
+				       rinfo->dir_dname_len[rinfo->dir_nr-1],
+				       fi->next_offset + rinfo->dir_nr);
 			if (err)
 				return err;
-			fi->next_offset += rinfo->dir_nr;
 		}
 	}
 
@@ -453,16 +462,22 @@
 	 * were released during the whole readdir, and we should have
 	 * the complete dir contents in our cache.
 	 */
-	spin_lock(&ci->i_ceph_lock);
-	if (atomic_read(&ci->i_release_count) == fi->dir_release_count) {
-		if (ci->i_ordered_count == fi->dir_ordered_count)
+	if (atomic64_read(&ci->i_release_count) == fi->dir_release_count) {
+		spin_lock(&ci->i_ceph_lock);
+		if (fi->dir_ordered_count == atomic64_read(&ci->i_ordered_count)) {
 			dout(" marking %p complete and ordered\n", inode);
-		else
+			/* use i_size to track number of entries in
+			 * readdir cache */
+			BUG_ON(fi->readdir_cache_idx < 0);
+			i_size_write(inode, fi->readdir_cache_idx *
+				     sizeof(struct dentry*));
+		} else {
 			dout(" marking %p complete\n", inode);
+		}
 		__ceph_dir_set_complete(ci, fi->dir_release_count,
 					fi->dir_ordered_count);
+		spin_unlock(&ci->i_ceph_lock);
 	}
-	spin_unlock(&ci->i_ceph_lock);
 
 	dout("readdir %p file %p done.\n", inode, file);
 	return 0;
@@ -476,14 +491,12 @@
 	}
 	kfree(fi->last_name);
 	fi->last_name = NULL;
+	fi->dir_release_count = 0;
+	fi->readdir_cache_idx = -1;
 	if (ceph_frag_is_leftmost(frag))
 		fi->next_offset = 2;  /* compensate for . and .. */
 	else
 		fi->next_offset = 0;
-	if (fi->dentry) {
-		dput(fi->dentry);
-		fi->dentry = NULL;
-	}
 	fi->flags &= ~CEPH_F_ATEND;
 }
 
@@ -497,13 +510,12 @@
 	mutex_lock(&inode->i_mutex);
 	retval = -EINVAL;
 	switch (whence) {
-	case SEEK_END:
-		offset += inode->i_size + 2;   /* FIXME */
-		break;
 	case SEEK_CUR:
 		offset += file->f_pos;
 	case SEEK_SET:
 		break;
+	case SEEK_END:
+		retval = -EOPNOTSUPP;
 	default:
 		goto out;
 	}
@@ -516,20 +528,18 @@
 		}
 		retval = offset;
 
-		/*
-		 * discard buffered readdir content on seekdir(0), or
-		 * seek to new frag, or seek prior to current chunk.
-		 */
 		if (offset == 0 ||
 		    fpos_frag(offset) != fi->frag ||
 		    fpos_off(offset) < fi->offset) {
+			/* discard buffered readdir content on seekdir(0), or
+			 * seek to new frag, or seek prior to current chunk */
 			dout("dir_llseek dropping %p content\n", file);
 			reset_readdir(fi, fpos_frag(offset));
+		} else if (fpos_cmp(offset, old_offset) > 0) {
+			/* reset dir_release_count if we did a forward seek */
+			fi->dir_release_count = 0;
+			fi->readdir_cache_idx = -1;
 		}
-
-		/* bump dir_release_count if we did a forward seek */
-		if (fpos_cmp(offset, old_offset) > 0)
-			fi->dir_release_count--;
 	}
 out:
 	mutex_unlock(&inode->i_mutex);
@@ -764,7 +774,7 @@
 		err = PTR_ERR(req);
 		goto out;
 	}
-	req->r_path2 = kstrdup(dest, GFP_NOFS);
+	req->r_path2 = kstrdup(dest, GFP_KERNEL);
 	if (!req->r_path2) {
 		err = -ENOMEM;
 		ceph_mdsc_put_request(req);
@@ -985,16 +995,15 @@
 		 * to do it here.
 		 */
 
+		/* d_move screws up sibling dentries' offsets */
+		ceph_dir_clear_complete(old_dir);
+		ceph_dir_clear_complete(new_dir);
+
 		d_move(old_dentry, new_dentry);
 
 		/* ensure target dentry is invalidated, despite
 		   rehashing bug in vfs_rename_dir */
 		ceph_invalidate_dentry_lease(new_dentry);
-
-		/* d_move screws up sibling dentries' offsets */
-		ceph_dir_clear_complete(old_dir);
-		ceph_dir_clear_complete(new_dir);
-
 	}
 	ceph_mdsc_put_request(req);
 	return err;
@@ -1189,7 +1198,7 @@
 		return -EISDIR;
 
 	if (!cf->dir_info) {
-		cf->dir_info = kmalloc(bufsize, GFP_NOFS);
+		cf->dir_info = kmalloc(bufsize, GFP_KERNEL);
 		if (!cf->dir_info)
 			return -ENOMEM;
 		cf->dir_info_len =
@@ -1224,66 +1233,6 @@
 }
 
 /*
- * an fsync() on a dir will wait for any uncommitted directory
- * operations to commit.
- */
-static int ceph_dir_fsync(struct file *file, loff_t start, loff_t end,
-			  int datasync)
-{
-	struct inode *inode = file_inode(file);
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct list_head *head = &ci->i_unsafe_dirops;
-	struct ceph_mds_request *req;
-	u64 last_tid;
-	int ret = 0;
-
-	dout("dir_fsync %p\n", inode);
-	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
-	if (ret)
-		return ret;
-	mutex_lock(&inode->i_mutex);
-
-	spin_lock(&ci->i_unsafe_lock);
-	if (list_empty(head))
-		goto out;
-
-	req = list_entry(head->prev,
-			 struct ceph_mds_request, r_unsafe_dir_item);
-	last_tid = req->r_tid;
-
-	do {
-		ceph_mdsc_get_request(req);
-		spin_unlock(&ci->i_unsafe_lock);
-
-		dout("dir_fsync %p wait on tid %llu (until %llu)\n",
-		     inode, req->r_tid, last_tid);
-		if (req->r_timeout) {
-			unsigned long time_left = wait_for_completion_timeout(
-							&req->r_safe_completion,
-							req->r_timeout);
-			if (time_left > 0)
-				ret = 0;
-			else
-				ret = -EIO;  /* timed out */
-		} else {
-			wait_for_completion(&req->r_safe_completion);
-		}
-		ceph_mdsc_put_request(req);
-
-		spin_lock(&ci->i_unsafe_lock);
-		if (ret || list_empty(head))
-			break;
-		req = list_entry(head->next,
-				 struct ceph_mds_request, r_unsafe_dir_item);
-	} while (req->r_tid < last_tid);
-out:
-	spin_unlock(&ci->i_unsafe_lock);
-	mutex_unlock(&inode->i_mutex);
-
-	return ret;
-}
-
-/*
  * We maintain a private dentry LRU.
  *
  * FIXME: this needs to be changed to a per-mds lru to be useful.
@@ -1353,7 +1302,7 @@
 	.open = ceph_open,
 	.release = ceph_release,
 	.unlocked_ioctl = ceph_ioctl,
-	.fsync = ceph_dir_fsync,
+	.fsync = ceph_fsync,
 };
 
 const struct file_operations ceph_snapdir_fops = {
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 3b6b522..8b79d87 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -89,13 +89,14 @@
 	case S_IFDIR:
 		dout("init_file %p %p 0%o (regular)\n", inode, file,
 		     inode->i_mode);
-		cf = kmem_cache_alloc(ceph_file_cachep, GFP_NOFS | __GFP_ZERO);
+		cf = kmem_cache_alloc(ceph_file_cachep, GFP_KERNEL | __GFP_ZERO);
 		if (cf == NULL) {
 			ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
 			return -ENOMEM;
 		}
 		cf->fmode = fmode;
 		cf->next_offset = 2;
+		cf->readdir_cache_idx = -1;
 		file->private_data = cf;
 		BUG_ON(inode->i_fop->release != ceph_release);
 		break;
@@ -324,7 +325,6 @@
 		ceph_mdsc_put_request(cf->last_readdir);
 	kfree(cf->last_name);
 	kfree(cf->dir_info);
-	dput(cf->dentry);
 	kmem_cache_free(ceph_file_cachep, cf);
 
 	/* wake up anyone waiting for caps on this inode */
@@ -483,7 +483,7 @@
 		}
 	} else {
 		num_pages = calc_pages_for(off, len);
-		pages = ceph_alloc_page_vector(num_pages, GFP_NOFS);
+		pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
 		if (IS_ERR(pages))
 			return PTR_ERR(pages);
 		ret = striped_read(inode, off, len, pages,
@@ -557,13 +557,13 @@
  * objects, rollback on failure, etc.)
  */
 static ssize_t
-ceph_sync_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos)
+ceph_sync_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
+		       struct ceph_snap_context *snapc)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
-	struct ceph_snap_context *snapc;
 	struct ceph_vino vino;
 	struct ceph_osd_request *req;
 	struct page **pages;
@@ -600,7 +600,6 @@
 		size_t start;
 		ssize_t n;
 
-		snapc = ci->i_snap_realm->cached_context;
 		vino = ceph_vino(inode);
 		req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
 					    vino, pos, &len, 0,
@@ -614,7 +613,7 @@
 			break;
 		}
 
-		osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC);
+		osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC, 0);
 
 		n = iov_iter_get_pages_alloc(from, &pages, len, &start);
 		if (unlikely(n < 0)) {
@@ -674,13 +673,13 @@
  * objects, rollback on failure, etc.)
  */
 static ssize_t
-ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos)
+ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
+		struct ceph_snap_context *snapc)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
-	struct ceph_snap_context *snapc;
 	struct ceph_vino vino;
 	struct ceph_osd_request *req;
 	struct page **pages;
@@ -717,7 +716,6 @@
 		size_t left;
 		int n;
 
-		snapc = ci->i_snap_realm->cached_context;
 		vino = ceph_vino(inode);
 		req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
 					    vino, pos, &len, 0, 1,
@@ -736,7 +734,7 @@
 		 */
 		num_pages = (len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 
-		pages = ceph_alloc_page_vector(num_pages, GFP_NOFS);
+		pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
 		if (IS_ERR(pages)) {
 			ret = PTR_ERR(pages);
 			goto out;
@@ -860,7 +858,7 @@
 		struct page *page = NULL;
 		loff_t i_size;
 		if (retry_op == READ_INLINE) {
-			page = __page_cache_alloc(GFP_NOFS);
+			page = __page_cache_alloc(GFP_KERNEL);
 			if (!page)
 				return -ENOMEM;
 		}
@@ -941,6 +939,7 @@
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_osd_client *osdc =
 		&ceph_sb_to_client(inode->i_sb)->client->osdc;
+	struct ceph_cap_flush *prealloc_cf;
 	ssize_t count, written = 0;
 	int err, want, got;
 	loff_t pos;
@@ -948,6 +947,10 @@
 	if (ceph_snap(inode) != CEPH_NOSNAP)
 		return -EROFS;
 
+	prealloc_cf = ceph_alloc_cap_flush();
+	if (!prealloc_cf)
+		return -ENOMEM;
+
 	mutex_lock(&inode->i_mutex);
 
 	/* We can write back this queue in page reclaim */
@@ -959,7 +962,7 @@
 
 	pos = iocb->ki_pos;
 	count = iov_iter_count(from);
-	err = file_remove_suid(file);
+	err = file_remove_privs(file);
 	if (err)
 		goto out;
 
@@ -996,14 +999,30 @@
 
 	if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 ||
 	    (iocb->ki_flags & IOCB_DIRECT) || (fi->flags & CEPH_F_SYNC)) {
+		struct ceph_snap_context *snapc;
 		struct iov_iter data;
 		mutex_unlock(&inode->i_mutex);
+
+		spin_lock(&ci->i_ceph_lock);
+		if (__ceph_have_pending_cap_snap(ci)) {
+			struct ceph_cap_snap *capsnap =
+					list_last_entry(&ci->i_cap_snaps,
+							struct ceph_cap_snap,
+							ci_item);
+			snapc = ceph_get_snap_context(capsnap->context);
+		} else {
+			BUG_ON(!ci->i_head_snapc);
+			snapc = ceph_get_snap_context(ci->i_head_snapc);
+		}
+		spin_unlock(&ci->i_ceph_lock);
+
 		/* we might need to revert back to that point */
 		data = *from;
 		if (iocb->ki_flags & IOCB_DIRECT)
-			written = ceph_sync_direct_write(iocb, &data, pos);
+			written = ceph_sync_direct_write(iocb, &data, pos,
+							 snapc);
 		else
-			written = ceph_sync_write(iocb, &data, pos);
+			written = ceph_sync_write(iocb, &data, pos, snapc);
 		if (written == -EOLDSNAPC) {
 			dout("aio_write %p %llx.%llx %llu~%u"
 				"got EOLDSNAPC, retrying\n",
@@ -1014,6 +1033,7 @@
 		}
 		if (written > 0)
 			iov_iter_advance(from, written);
+		ceph_put_snap_context(snapc);
 	} else {
 		loff_t old_size = inode->i_size;
 		/*
@@ -1035,7 +1055,8 @@
 		int dirty;
 		spin_lock(&ci->i_ceph_lock);
 		ci->i_inline_version = CEPH_INLINE_NONE;
-		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR);
+		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR,
+					       &prealloc_cf);
 		spin_unlock(&ci->i_ceph_lock);
 		if (dirty)
 			__mark_inode_dirty(inode, dirty);
@@ -1059,6 +1080,7 @@
 out:
 	mutex_unlock(&inode->i_mutex);
 out_unlocked:
+	ceph_free_cap_flush(prealloc_cf);
 	current->backing_dev_info = NULL;
 	return written ? written : err;
 }
@@ -1255,6 +1277,7 @@
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_osd_client *osdc =
 		&ceph_inode_to_client(inode)->client->osdc;
+	struct ceph_cap_flush *prealloc_cf;
 	int want, got = 0;
 	int dirty;
 	int ret = 0;
@@ -1267,6 +1290,10 @@
 	if (!S_ISREG(inode->i_mode))
 		return -EOPNOTSUPP;
 
+	prealloc_cf = ceph_alloc_cap_flush();
+	if (!prealloc_cf)
+		return -ENOMEM;
+
 	mutex_lock(&inode->i_mutex);
 
 	if (ceph_snap(inode) != CEPH_NOSNAP) {
@@ -1313,7 +1340,8 @@
 	if (!ret) {
 		spin_lock(&ci->i_ceph_lock);
 		ci->i_inline_version = CEPH_INLINE_NONE;
-		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR);
+		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR,
+					       &prealloc_cf);
 		spin_unlock(&ci->i_ceph_lock);
 		if (dirty)
 			__mark_inode_dirty(inode, dirty);
@@ -1322,6 +1350,7 @@
 	ceph_put_cap_refs(ci, got);
 unlock:
 	mutex_unlock(&inode->i_mutex);
+	ceph_free_cap_flush(prealloc_cf);
 	return ret;
 }
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 571acd8..96d2bd8 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -389,9 +389,10 @@
 	ci->i_inline_version = 0;
 	ci->i_time_warp_seq = 0;
 	ci->i_ceph_flags = 0;
-	ci->i_ordered_count = 0;
-	atomic_set(&ci->i_release_count, 1);
-	atomic_set(&ci->i_complete_count, 0);
+	atomic64_set(&ci->i_ordered_count, 1);
+	atomic64_set(&ci->i_release_count, 1);
+	atomic64_set(&ci->i_complete_seq[0], 0);
+	atomic64_set(&ci->i_complete_seq[1], 0);
 	ci->i_symlink = NULL;
 
 	memset(&ci->i_dir_layout, 0, sizeof(ci->i_dir_layout));
@@ -415,9 +416,8 @@
 	ci->i_flushing_caps = 0;
 	INIT_LIST_HEAD(&ci->i_dirty_item);
 	INIT_LIST_HEAD(&ci->i_flushing_item);
-	ci->i_cap_flush_seq = 0;
-	ci->i_cap_flush_last_tid = 0;
-	memset(&ci->i_cap_flush_tid, 0, sizeof(ci->i_cap_flush_tid));
+	ci->i_prealloc_cap_flush = NULL;
+	ci->i_cap_flush_tree = RB_ROOT;
 	init_waitqueue_head(&ci->i_cap_wq);
 	ci->i_hold_caps_min = 0;
 	ci->i_hold_caps_max = 0;
@@ -752,7 +752,10 @@
 
 	if (new_version ||
 	    (new_issued & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR))) {
+		if (ci->i_layout.fl_pg_pool != info->layout.fl_pg_pool)
+			ci->i_ceph_flags &= ~CEPH_I_POOL_PERM;
 		ci->i_layout = info->layout;
+
 		queue_trunc = ceph_fill_file_size(inode, issued,
 					le32_to_cpu(info->truncate_seq),
 					le64_to_cpu(info->truncate_size),
@@ -858,9 +861,10 @@
 			    (issued & CEPH_CAP_FILE_EXCL) == 0 &&
 			    !__ceph_dir_is_complete(ci)) {
 				dout(" marking %p complete (empty)\n", inode);
+				i_size_write(inode, 0);
 				__ceph_dir_set_complete(ci,
-					atomic_read(&ci->i_release_count),
-					ci->i_ordered_count);
+					atomic64_read(&ci->i_release_count),
+					atomic64_read(&ci->i_ordered_count));
 			}
 
 			wake = true;
@@ -1212,6 +1216,10 @@
 			dout("fill_trace doing d_move %p -> %p\n",
 			     req->r_old_dentry, dn);
 
+			/* d_move screws up sibling dentries' offsets */
+			ceph_dir_clear_ordered(dir);
+			ceph_dir_clear_ordered(olddir);
+
 			d_move(req->r_old_dentry, dn);
 			dout(" src %p '%pd' dst %p '%pd'\n",
 			     req->r_old_dentry,
@@ -1222,10 +1230,6 @@
 			   rehashing bug in vfs_rename_dir */
 			ceph_invalidate_dentry_lease(dn);
 
-			/* d_move screws up sibling dentries' offsets */
-			ceph_dir_clear_ordered(dir);
-			ceph_dir_clear_ordered(olddir);
-
 			dout("dn %p gets new offset %lld\n", req->r_old_dentry,
 			     ceph_dentry(req->r_old_dentry)->offset);
 
@@ -1333,6 +1337,49 @@
 	return err;
 }
 
+void ceph_readdir_cache_release(struct ceph_readdir_cache_control *ctl)
+{
+	if (ctl->page) {
+		kunmap(ctl->page);
+		page_cache_release(ctl->page);
+		ctl->page = NULL;
+	}
+}
+
+static int fill_readdir_cache(struct inode *dir, struct dentry *dn,
+			      struct ceph_readdir_cache_control *ctl,
+			      struct ceph_mds_request *req)
+{
+	struct ceph_inode_info *ci = ceph_inode(dir);
+	unsigned nsize = PAGE_CACHE_SIZE / sizeof(struct dentry*);
+	unsigned idx = ctl->index % nsize;
+	pgoff_t pgoff = ctl->index / nsize;
+
+	if (!ctl->page || pgoff != page_index(ctl->page)) {
+		ceph_readdir_cache_release(ctl);
+		ctl->page  = grab_cache_page(&dir->i_data, pgoff);
+		if (!ctl->page) {
+			ctl->index = -1;
+			return -ENOMEM;
+		}
+		/* reading/filling the cache are serialized by
+		 * i_mutex, no need to use page lock */
+		unlock_page(ctl->page);
+		ctl->dentries = kmap(ctl->page);
+	}
+
+	if (req->r_dir_release_cnt == atomic64_read(&ci->i_release_count) &&
+	    req->r_dir_ordered_cnt == atomic64_read(&ci->i_ordered_count)) {
+		dout("readdir cache dn %p idx %d\n", dn, ctl->index);
+		ctl->dentries[idx] = dn;
+		ctl->index++;
+	} else {
+		dout("disable readdir cache\n");
+		ctl->index = -1;
+	}
+	return 0;
+}
+
 int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 			     struct ceph_mds_session *session)
 {
@@ -1345,8 +1392,11 @@
 	struct inode *snapdir = NULL;
 	struct ceph_mds_request_head *rhead = req->r_request->front.iov_base;
 	struct ceph_dentry_info *di;
-	u64 r_readdir_offset = req->r_readdir_offset;
 	u32 frag = le32_to_cpu(rhead->args.readdir.frag);
+	struct ceph_readdir_cache_control cache_ctl = {};
+
+	if (req->r_aborted)
+		return readdir_prepopulate_inodes_only(req, session);
 
 	if (rinfo->dir_dir &&
 	    le32_to_cpu(rinfo->dir_dir->frag) != frag) {
@@ -1354,14 +1404,11 @@
 		     frag, le32_to_cpu(rinfo->dir_dir->frag));
 		frag = le32_to_cpu(rinfo->dir_dir->frag);
 		if (ceph_frag_is_leftmost(frag))
-			r_readdir_offset = 2;
+			req->r_readdir_offset = 2;
 		else
-			r_readdir_offset = 0;
+			req->r_readdir_offset = 0;
 	}
 
-	if (req->r_aborted)
-		return readdir_prepopulate_inodes_only(req, session);
-
 	if (le32_to_cpu(rinfo->head->op) == CEPH_MDS_OP_LSSNAP) {
 		snapdir = ceph_get_snapdir(d_inode(parent));
 		parent = d_find_alias(snapdir);
@@ -1374,6 +1421,17 @@
 			ceph_fill_dirfrag(d_inode(parent), rinfo->dir_dir);
 	}
 
+	if (ceph_frag_is_leftmost(frag) && req->r_readdir_offset == 2) {
+		/* note dir version at start of readdir so we can tell
+		 * if any dentries get dropped */
+		struct ceph_inode_info *ci = ceph_inode(d_inode(parent));
+		req->r_dir_release_cnt = atomic64_read(&ci->i_release_count);
+		req->r_dir_ordered_cnt = atomic64_read(&ci->i_ordered_count);
+		req->r_readdir_cache_idx = 0;
+	}
+
+	cache_ctl.index = req->r_readdir_cache_idx;
+
 	/* FIXME: release caps/leases if error occurs */
 	for (i = 0; i < rinfo->dir_nr; i++) {
 		struct ceph_vino vino;
@@ -1413,13 +1471,6 @@
 			d_delete(dn);
 			dput(dn);
 			goto retry_lookup;
-		} else {
-			/* reorder parent's d_subdirs */
-			spin_lock(&parent->d_lock);
-			spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED);
-			list_move(&dn->d_child, &parent->d_subdirs);
-			spin_unlock(&dn->d_lock);
-			spin_unlock(&parent->d_lock);
 		}
 
 		/* inode */
@@ -1436,13 +1487,15 @@
 			}
 		}
 
-		if (fill_inode(in, NULL, &rinfo->dir_in[i], NULL, session,
-			       req->r_request_started, -1,
-			       &req->r_caps_reservation) < 0) {
+		ret = fill_inode(in, NULL, &rinfo->dir_in[i], NULL, session,
+				 req->r_request_started, -1,
+				 &req->r_caps_reservation);
+		if (ret < 0) {
 			pr_err("fill_inode badness on %p\n", in);
 			if (d_really_is_negative(dn))
 				iput(in);
 			d_drop(dn);
+			err = ret;
 			goto next_item;
 		}
 
@@ -1458,19 +1511,28 @@
 		}
 
 		di = dn->d_fsdata;
-		di->offset = ceph_make_fpos(frag, i + r_readdir_offset);
+		di->offset = ceph_make_fpos(frag, i + req->r_readdir_offset);
 
 		update_dentry_lease(dn, rinfo->dir_dlease[i],
 				    req->r_session,
 				    req->r_request_started);
+
+		if (err == 0 && cache_ctl.index >= 0) {
+			ret = fill_readdir_cache(d_inode(parent), dn,
+						 &cache_ctl, req);
+			if (ret < 0)
+				err = ret;
+		}
 next_item:
 		if (dn)
 			dput(dn);
 	}
-	if (err == 0)
-		req->r_did_prepopulate = true;
-
 out:
+	if (err == 0) {
+		req->r_did_prepopulate = true;
+		req->r_readdir_cache_idx = cache_ctl.index;
+	}
+	ceph_readdir_cache_release(&cache_ctl);
 	if (snapdir) {
 		iput(snapdir);
 		dput(parent);
@@ -1712,11 +1774,13 @@
 	const unsigned int ia_valid = attr->ia_valid;
 	struct ceph_mds_request *req;
 	struct ceph_mds_client *mdsc = ceph_sb_to_client(dentry->d_sb)->mdsc;
+	struct ceph_cap_flush *prealloc_cf;
 	int issued;
 	int release = 0, dirtied = 0;
 	int mask = 0;
 	int err = 0;
 	int inode_dirty_flags = 0;
+	bool lock_snap_rwsem = false;
 
 	if (ceph_snap(inode) != CEPH_NOSNAP)
 		return -EROFS;
@@ -1725,13 +1789,31 @@
 	if (err != 0)
 		return err;
 
+	prealloc_cf = ceph_alloc_cap_flush();
+	if (!prealloc_cf)
+		return -ENOMEM;
+
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETATTR,
 				       USE_AUTH_MDS);
-	if (IS_ERR(req))
+	if (IS_ERR(req)) {
+		ceph_free_cap_flush(prealloc_cf);
 		return PTR_ERR(req);
+	}
 
 	spin_lock(&ci->i_ceph_lock);
 	issued = __ceph_caps_issued(ci, NULL);
+
+	if (!ci->i_head_snapc &&
+	    (issued & (CEPH_CAP_ANY_EXCL | CEPH_CAP_FILE_WR))) {
+		lock_snap_rwsem = true;
+		if (!down_read_trylock(&mdsc->snap_rwsem)) {
+			spin_unlock(&ci->i_ceph_lock);
+			down_read(&mdsc->snap_rwsem);
+			spin_lock(&ci->i_ceph_lock);
+			issued = __ceph_caps_issued(ci, NULL);
+		}
+	}
+
 	dout("setattr %p issued %s\n", inode, ceph_cap_string(issued));
 
 	if (ia_valid & ATTR_UID) {
@@ -1874,12 +1956,15 @@
 		dout("setattr %p ATTR_FILE ... hrm!\n", inode);
 
 	if (dirtied) {
-		inode_dirty_flags = __ceph_mark_dirty_caps(ci, dirtied);
+		inode_dirty_flags = __ceph_mark_dirty_caps(ci, dirtied,
+							   &prealloc_cf);
 		inode->i_ctime = CURRENT_TIME;
 	}
 
 	release &= issued;
 	spin_unlock(&ci->i_ceph_lock);
+	if (lock_snap_rwsem)
+		up_read(&mdsc->snap_rwsem);
 
 	if (inode_dirty_flags)
 		__mark_inode_dirty(inode, inode_dirty_flags);
@@ -1904,9 +1989,11 @@
 	ceph_mdsc_put_request(req);
 	if (mask & CEPH_SETATTR_SIZE)
 		__ceph_do_pending_vmtruncate(inode);
+	ceph_free_cap_flush(prealloc_cf);
 	return err;
 out_put:
 	ceph_mdsc_put_request(req);
+	ceph_free_cap_flush(prealloc_cf);
 	return err;
 }
 
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 84f37f3..6aa07af 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -8,6 +8,7 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/utsname.h>
+#include <linux/ratelimit.h>
 
 #include "super.h"
 #include "mds_client.h"
@@ -458,7 +459,6 @@
 	s->s_cap_reconnect = 0;
 	s->s_cap_iterator = NULL;
 	INIT_LIST_HEAD(&s->s_cap_releases);
-	INIT_LIST_HEAD(&s->s_cap_releases_done);
 	INIT_LIST_HEAD(&s->s_cap_flushing);
 	INIT_LIST_HEAD(&s->s_cap_snaps_flushing);
 
@@ -629,6 +629,9 @@
 	req->r_uid = current_fsuid();
 	req->r_gid = current_fsgid();
 
+	if (mdsc->oldest_tid == 0 && req->r_op != CEPH_MDS_OP_SETFILELOCK)
+		mdsc->oldest_tid = req->r_tid;
+
 	if (dir) {
 		struct ceph_inode_info *ci = ceph_inode(dir);
 
@@ -644,6 +647,21 @@
 				 struct ceph_mds_request *req)
 {
 	dout("__unregister_request %p tid %lld\n", req, req->r_tid);
+
+	if (req->r_tid == mdsc->oldest_tid) {
+		struct rb_node *p = rb_next(&req->r_node);
+		mdsc->oldest_tid = 0;
+		while (p) {
+			struct ceph_mds_request *next_req =
+				rb_entry(p, struct ceph_mds_request, r_node);
+			if (next_req->r_op != CEPH_MDS_OP_SETFILELOCK) {
+				mdsc->oldest_tid = next_req->r_tid;
+				break;
+			}
+			p = rb_next(p);
+		}
+	}
+
 	rb_erase(&req->r_node, &mdsc->request_tree);
 	RB_CLEAR_NODE(&req->r_node);
 
@@ -998,27 +1016,25 @@
  * session caps
  */
 
-/*
- * Free preallocated cap messages assigned to this session
- */
-static void cleanup_cap_releases(struct ceph_mds_session *session)
+/* caller holds s_cap_lock, we drop it */
+static void cleanup_cap_releases(struct ceph_mds_client *mdsc,
+				 struct ceph_mds_session *session)
+	__releases(session->s_cap_lock)
 {
-	struct ceph_msg *msg;
-
-	spin_lock(&session->s_cap_lock);
-	while (!list_empty(&session->s_cap_releases)) {
-		msg = list_first_entry(&session->s_cap_releases,
-				       struct ceph_msg, list_head);
-		list_del_init(&msg->list_head);
-		ceph_msg_put(msg);
-	}
-	while (!list_empty(&session->s_cap_releases_done)) {
-		msg = list_first_entry(&session->s_cap_releases_done,
-				       struct ceph_msg, list_head);
-		list_del_init(&msg->list_head);
-		ceph_msg_put(msg);
-	}
+	LIST_HEAD(tmp_list);
+	list_splice_init(&session->s_cap_releases, &tmp_list);
+	session->s_num_cap_releases = 0;
 	spin_unlock(&session->s_cap_lock);
+
+	dout("cleanup_cap_releases mds%d\n", session->s_mds);
+	while (!list_empty(&tmp_list)) {
+		struct ceph_cap *cap;
+		/* zero out the in-progress message */
+		cap = list_first_entry(&tmp_list,
+					struct ceph_cap, session_caps);
+		list_del(&cap->session_caps);
+		ceph_put_cap(mdsc, cap);
+	}
 }
 
 static void cleanup_session_requests(struct ceph_mds_client *mdsc,
@@ -1033,7 +1049,8 @@
 		req = list_first_entry(&session->s_unsafe,
 				       struct ceph_mds_request, r_unsafe_item);
 		list_del_init(&req->r_unsafe_item);
-		pr_info(" dropping unsafe request %llu\n", req->r_tid);
+		pr_warn_ratelimited(" dropping unsafe request %llu\n",
+				    req->r_tid);
 		__unregister_request(mdsc, req);
 	}
 	/* zero r_attempts, so kick_requests() will re-send requests */
@@ -1095,10 +1112,16 @@
 			dout("iterate_session_caps  finishing cap %p removal\n",
 			     cap);
 			BUG_ON(cap->session != session);
+			cap->session = NULL;
 			list_del_init(&cap->session_caps);
 			session->s_nr_caps--;
-			cap->session = NULL;
-			old_cap = cap;  /* put_cap it w/o locks held */
+			if (cap->queue_release) {
+				list_add_tail(&cap->session_caps,
+					      &session->s_cap_releases);
+				session->s_num_cap_releases++;
+			} else {
+				old_cap = cap;  /* put_cap it w/o locks held */
+			}
 		}
 		if (ret < 0)
 			goto out;
@@ -1119,6 +1142,7 @@
 				  void *arg)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	LIST_HEAD(to_remove);
 	int drop = 0;
 
 	dout("removing cap %p, ci is %p, inode is %p\n",
@@ -1126,12 +1150,27 @@
 	spin_lock(&ci->i_ceph_lock);
 	__ceph_remove_cap(cap, false);
 	if (!ci->i_auth_cap) {
+		struct ceph_cap_flush *cf;
 		struct ceph_mds_client *mdsc =
 			ceph_sb_to_client(inode->i_sb)->mdsc;
 
+		while (true) {
+			struct rb_node *n = rb_first(&ci->i_cap_flush_tree);
+			if (!n)
+				break;
+			cf = rb_entry(n, struct ceph_cap_flush, i_node);
+			rb_erase(&cf->i_node, &ci->i_cap_flush_tree);
+			list_add(&cf->list, &to_remove);
+		}
+
 		spin_lock(&mdsc->cap_dirty_lock);
+
+		list_for_each_entry(cf, &to_remove, list)
+			rb_erase(&cf->g_node, &mdsc->cap_flush_tree);
+
 		if (!list_empty(&ci->i_dirty_item)) {
-			pr_info(" dropping dirty %s state for %p %lld\n",
+			pr_warn_ratelimited(
+				" dropping dirty %s state for %p %lld\n",
 				ceph_cap_string(ci->i_dirty_caps),
 				inode, ceph_ino(inode));
 			ci->i_dirty_caps = 0;
@@ -1139,7 +1178,8 @@
 			drop = 1;
 		}
 		if (!list_empty(&ci->i_flushing_item)) {
-			pr_info(" dropping dirty+flushing %s state for %p %lld\n",
+			pr_warn_ratelimited(
+				" dropping dirty+flushing %s state for %p %lld\n",
 				ceph_cap_string(ci->i_flushing_caps),
 				inode, ceph_ino(inode));
 			ci->i_flushing_caps = 0;
@@ -1148,8 +1188,20 @@
 			drop = 1;
 		}
 		spin_unlock(&mdsc->cap_dirty_lock);
+
+		if (!ci->i_dirty_caps && ci->i_prealloc_cap_flush) {
+			list_add(&ci->i_prealloc_cap_flush->list, &to_remove);
+			ci->i_prealloc_cap_flush = NULL;
+		}
 	}
 	spin_unlock(&ci->i_ceph_lock);
+	while (!list_empty(&to_remove)) {
+		struct ceph_cap_flush *cf;
+		cf = list_first_entry(&to_remove,
+				      struct ceph_cap_flush, list);
+		list_del(&cf->list);
+		ceph_free_cap_flush(cf);
+	}
 	while (drop--)
 		iput(inode);
 	return 0;
@@ -1191,11 +1243,12 @@
 			spin_lock(&session->s_cap_lock);
 		}
 	}
-	spin_unlock(&session->s_cap_lock);
+
+	// drop cap expires and unlock s_cap_lock
+	cleanup_cap_releases(session->s_mdsc, session);
 
 	BUG_ON(session->s_nr_caps > 0);
 	BUG_ON(!list_empty(&session->s_cap_flushing));
-	cleanup_cap_releases(session);
 }
 
 /*
@@ -1371,7 +1424,8 @@
 	     inode, cap, ceph_cap_string(mine), ceph_cap_string(oissued),
 	     ceph_cap_string(used), ceph_cap_string(wanted));
 	if (cap == ci->i_auth_cap) {
-		if (ci->i_dirty_caps | ci->i_flushing_caps)
+		if (ci->i_dirty_caps || ci->i_flushing_caps ||
+		    !list_empty(&ci->i_cap_snaps))
 			goto out;
 		if ((used | wanted) & CEPH_CAP_ANY_WR)
 			goto out;
@@ -1417,121 +1471,80 @@
 		session->s_trim_caps = 0;
 	}
 
-	ceph_add_cap_releases(mdsc, session);
 	ceph_send_cap_releases(mdsc, session);
 	return 0;
 }
 
-/*
- * Allocate cap_release messages.  If there is a partially full message
- * in the queue, try to allocate enough to cover it's remainder, so that
- * we can send it immediately.
- *
- * Called under s_mutex.
- */
-int ceph_add_cap_releases(struct ceph_mds_client *mdsc,
-			  struct ceph_mds_session *session)
+static int check_capsnap_flush(struct ceph_inode_info *ci,
+			       u64 want_snap_seq)
 {
-	struct ceph_msg *msg, *partial = NULL;
-	struct ceph_mds_cap_release *head;
-	int err = -ENOMEM;
-	int extra = mdsc->fsc->mount_options->cap_release_safety;
-	int num;
-
-	dout("add_cap_releases %p mds%d extra %d\n", session, session->s_mds,
-	     extra);
-
-	spin_lock(&session->s_cap_lock);
-
-	if (!list_empty(&session->s_cap_releases)) {
-		msg = list_first_entry(&session->s_cap_releases,
-				       struct ceph_msg,
-				 list_head);
-		head = msg->front.iov_base;
-		num = le32_to_cpu(head->num);
-		if (num) {
-			dout(" partial %p with (%d/%d)\n", msg, num,
-			     (int)CEPH_CAPS_PER_RELEASE);
-			extra += CEPH_CAPS_PER_RELEASE - num;
-			partial = msg;
-		}
+	int ret = 1;
+	spin_lock(&ci->i_ceph_lock);
+	if (want_snap_seq > 0 && !list_empty(&ci->i_cap_snaps)) {
+		struct ceph_cap_snap *capsnap =
+			list_first_entry(&ci->i_cap_snaps,
+					 struct ceph_cap_snap, ci_item);
+		ret = capsnap->follows >= want_snap_seq;
 	}
-	while (session->s_num_cap_releases < session->s_nr_caps + extra) {
-		spin_unlock(&session->s_cap_lock);
-		msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPRELEASE, PAGE_CACHE_SIZE,
-				   GFP_NOFS, false);
-		if (!msg)
-			goto out_unlocked;
-		dout("add_cap_releases %p msg %p now %d\n", session, msg,
-		     (int)msg->front.iov_len);
-		head = msg->front.iov_base;
-		head->num = cpu_to_le32(0);
-		msg->front.iov_len = sizeof(*head);
-		spin_lock(&session->s_cap_lock);
-		list_add(&msg->list_head, &session->s_cap_releases);
-		session->s_num_cap_releases += CEPH_CAPS_PER_RELEASE;
-	}
-
-	if (partial) {
-		head = partial->front.iov_base;
-		num = le32_to_cpu(head->num);
-		dout(" queueing partial %p with %d/%d\n", partial, num,
-		     (int)CEPH_CAPS_PER_RELEASE);
-		list_move_tail(&partial->list_head,
-			       &session->s_cap_releases_done);
-		session->s_num_cap_releases -= CEPH_CAPS_PER_RELEASE - num;
-	}
-	err = 0;
-	spin_unlock(&session->s_cap_lock);
-out_unlocked:
-	return err;
+	spin_unlock(&ci->i_ceph_lock);
+	return ret;
 }
 
-static int check_cap_flush(struct inode *inode, u64 want_flush_seq)
+static int check_caps_flush(struct ceph_mds_client *mdsc,
+			    u64 want_flush_tid)
 {
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	int ret;
-	spin_lock(&ci->i_ceph_lock);
-	if (ci->i_flushing_caps)
-		ret = ci->i_cap_flush_seq >= want_flush_seq;
-	else
-		ret = 1;
-	spin_unlock(&ci->i_ceph_lock);
+	struct rb_node *n;
+	struct ceph_cap_flush *cf;
+	int ret = 1;
+
+	spin_lock(&mdsc->cap_dirty_lock);
+	n = rb_first(&mdsc->cap_flush_tree);
+	cf = n ? rb_entry(n, struct ceph_cap_flush, g_node) : NULL;
+	if (cf && cf->tid <= want_flush_tid) {
+		dout("check_caps_flush still flushing tid %llu <= %llu\n",
+		     cf->tid, want_flush_tid);
+		ret = 0;
+	}
+	spin_unlock(&mdsc->cap_dirty_lock);
 	return ret;
 }
 
 /*
  * flush all dirty inode data to disk.
  *
- * returns true if we've flushed through want_flush_seq
+ * returns true if we've flushed through want_flush_tid
  */
-static void wait_caps_flush(struct ceph_mds_client *mdsc, u64 want_flush_seq)
+static void wait_caps_flush(struct ceph_mds_client *mdsc,
+			    u64 want_flush_tid, u64 want_snap_seq)
 {
 	int mds;
 
-	dout("check_cap_flush want %lld\n", want_flush_seq);
+	dout("check_caps_flush want %llu snap want %llu\n",
+	     want_flush_tid, want_snap_seq);
 	mutex_lock(&mdsc->mutex);
-	for (mds = 0; mds < mdsc->max_sessions; mds++) {
+	for (mds = 0; mds < mdsc->max_sessions; ) {
 		struct ceph_mds_session *session = mdsc->sessions[mds];
 		struct inode *inode = NULL;
 
-		if (!session)
+		if (!session) {
+			mds++;
 			continue;
+		}
 		get_session(session);
 		mutex_unlock(&mdsc->mutex);
 
 		mutex_lock(&session->s_mutex);
-		if (!list_empty(&session->s_cap_flushing)) {
-			struct ceph_inode_info *ci =
-				list_entry(session->s_cap_flushing.next,
-					   struct ceph_inode_info,
-					   i_flushing_item);
-
-			if (!check_cap_flush(&ci->vfs_inode, want_flush_seq)) {
-				dout("check_cap_flush still flushing %p "
-				     "seq %lld <= %lld to mds%d\n",
-				     &ci->vfs_inode, ci->i_cap_flush_seq,
-				     want_flush_seq, session->s_mds);
+		if (!list_empty(&session->s_cap_snaps_flushing)) {
+			struct ceph_cap_snap *capsnap =
+				list_first_entry(&session->s_cap_snaps_flushing,
+						 struct ceph_cap_snap,
+						 flushing_item);
+			struct ceph_inode_info *ci = capsnap->ci;
+			if (!check_capsnap_flush(ci, want_snap_seq)) {
+				dout("check_cap_flush still flushing snap %p "
+				     "follows %lld <= %lld to mds%d\n",
+				     &ci->vfs_inode, capsnap->follows,
+				     want_snap_seq, mds);
 				inode = igrab(&ci->vfs_inode);
 			}
 		}
@@ -1540,15 +1553,21 @@
 
 		if (inode) {
 			wait_event(mdsc->cap_flushing_wq,
-				   check_cap_flush(inode, want_flush_seq));
+				   check_capsnap_flush(ceph_inode(inode),
+						       want_snap_seq));
 			iput(inode);
+		} else {
+			mds++;
 		}
 
 		mutex_lock(&mdsc->mutex);
 	}
-
 	mutex_unlock(&mdsc->mutex);
-	dout("check_cap_flush ok, flushed thru %lld\n", want_flush_seq);
+
+	wait_event(mdsc->cap_flushing_wq,
+		   check_caps_flush(mdsc, want_flush_tid));
+
+	dout("check_caps_flush ok, flushed thru %llu\n", want_flush_tid);
 }
 
 /*
@@ -1557,62 +1576,76 @@
 void ceph_send_cap_releases(struct ceph_mds_client *mdsc,
 			    struct ceph_mds_session *session)
 {
-	struct ceph_msg *msg;
+	struct ceph_msg *msg = NULL;
+	struct ceph_mds_cap_release *head;
+	struct ceph_mds_cap_item *item;
+	struct ceph_cap *cap;
+	LIST_HEAD(tmp_list);
+	int num_cap_releases;
 
-	dout("send_cap_releases mds%d\n", session->s_mds);
 	spin_lock(&session->s_cap_lock);
-	while (!list_empty(&session->s_cap_releases_done)) {
-		msg = list_first_entry(&session->s_cap_releases_done,
-				 struct ceph_msg, list_head);
-		list_del_init(&msg->list_head);
-		spin_unlock(&session->s_cap_lock);
+again:
+	list_splice_init(&session->s_cap_releases, &tmp_list);
+	num_cap_releases = session->s_num_cap_releases;
+	session->s_num_cap_releases = 0;
+	spin_unlock(&session->s_cap_lock);
+
+	while (!list_empty(&tmp_list)) {
+		if (!msg) {
+			msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPRELEASE,
+					PAGE_CACHE_SIZE, GFP_NOFS, false);
+			if (!msg)
+				goto out_err;
+			head = msg->front.iov_base;
+			head->num = cpu_to_le32(0);
+			msg->front.iov_len = sizeof(*head);
+		}
+		cap = list_first_entry(&tmp_list, struct ceph_cap,
+					session_caps);
+		list_del(&cap->session_caps);
+		num_cap_releases--;
+
+		head = msg->front.iov_base;
+		le32_add_cpu(&head->num, 1);
+		item = msg->front.iov_base + msg->front.iov_len;
+		item->ino = cpu_to_le64(cap->cap_ino);
+		item->cap_id = cpu_to_le64(cap->cap_id);
+		item->migrate_seq = cpu_to_le32(cap->mseq);
+		item->seq = cpu_to_le32(cap->issue_seq);
+		msg->front.iov_len += sizeof(*item);
+
+		ceph_put_cap(mdsc, cap);
+
+		if (le32_to_cpu(head->num) == CEPH_CAPS_PER_RELEASE) {
+			msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
+			dout("send_cap_releases mds%d %p\n", session->s_mds, msg);
+			ceph_con_send(&session->s_con, msg);
+			msg = NULL;
+		}
+	}
+
+	BUG_ON(num_cap_releases != 0);
+
+	spin_lock(&session->s_cap_lock);
+	if (!list_empty(&session->s_cap_releases))
+		goto again;
+	spin_unlock(&session->s_cap_lock);
+
+	if (msg) {
 		msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
 		dout("send_cap_releases mds%d %p\n", session->s_mds, msg);
 		ceph_con_send(&session->s_con, msg);
-		spin_lock(&session->s_cap_lock);
 	}
+	return;
+out_err:
+	pr_err("send_cap_releases mds%d, failed to allocate message\n",
+		session->s_mds);
+	spin_lock(&session->s_cap_lock);
+	list_splice(&tmp_list, &session->s_cap_releases);
+	session->s_num_cap_releases += num_cap_releases;
 	spin_unlock(&session->s_cap_lock);
 }
 
-static void discard_cap_releases(struct ceph_mds_client *mdsc,
-				 struct ceph_mds_session *session)
-{
-	struct ceph_msg *msg;
-	struct ceph_mds_cap_release *head;
-	unsigned num;
-
-	dout("discard_cap_releases mds%d\n", session->s_mds);
-
-	if (!list_empty(&session->s_cap_releases)) {
-		/* zero out the in-progress message */
-		msg = list_first_entry(&session->s_cap_releases,
-					struct ceph_msg, list_head);
-		head = msg->front.iov_base;
-		num = le32_to_cpu(head->num);
-		dout("discard_cap_releases mds%d %p %u\n",
-		     session->s_mds, msg, num);
-		head->num = cpu_to_le32(0);
-		msg->front.iov_len = sizeof(*head);
-		session->s_num_cap_releases += num;
-	}
-
-	/* requeue completed messages */
-	while (!list_empty(&session->s_cap_releases_done)) {
-		msg = list_first_entry(&session->s_cap_releases_done,
-				 struct ceph_msg, list_head);
-		list_del_init(&msg->list_head);
-
-		head = msg->front.iov_base;
-		num = le32_to_cpu(head->num);
-		dout("discard_cap_releases mds%d %p %u\n", session->s_mds, msg,
-		     num);
-		session->s_num_cap_releases += num;
-		head->num = cpu_to_le32(0);
-		msg->front.iov_len = sizeof(*head);
-		list_add(&msg->list_head, &session->s_cap_releases);
-	}
-}
-
 /*
  * requests
  */
@@ -1635,7 +1668,8 @@
 
 	order = get_order(size * num_entries);
 	while (order >= 0) {
-		rinfo->dir_in = (void*)__get_free_pages(GFP_NOFS | __GFP_NOWARN,
+		rinfo->dir_in = (void*)__get_free_pages(GFP_KERNEL |
+							__GFP_NOWARN,
 							order);
 		if (rinfo->dir_in)
 			break;
@@ -1697,13 +1731,9 @@
 			struct ceph_mds_request, r_node);
 }
 
-static u64 __get_oldest_tid(struct ceph_mds_client *mdsc)
+static inline  u64 __get_oldest_tid(struct ceph_mds_client *mdsc)
 {
-	struct ceph_mds_request *req = __get_oldest_req(mdsc);
-
-	if (req)
-		return req->r_tid;
-	return 0;
+	return mdsc->oldest_tid;
 }
 
 /*
@@ -2267,15 +2297,18 @@
 	/* wait */
 	mutex_unlock(&mdsc->mutex);
 	dout("do_request waiting\n");
-	if (req->r_timeout) {
-		err = (long)wait_for_completion_killable_timeout(
-			&req->r_completion, req->r_timeout);
-		if (err == 0)
-			err = -EIO;
-	} else if (req->r_wait_for_completion) {
+	if (!req->r_timeout && req->r_wait_for_completion) {
 		err = req->r_wait_for_completion(mdsc, req);
 	} else {
-		err = wait_for_completion_killable(&req->r_completion);
+		long timeleft = wait_for_completion_killable_timeout(
+					&req->r_completion,
+					ceph_timeout_jiffies(req->r_timeout));
+		if (timeleft > 0)
+			err = 0;
+		else if (!timeleft)
+			err = -EIO;  /* timed out */
+		else
+			err = timeleft;  /* killed */
 	}
 	dout("do_request waited, got %d\n", err);
 	mutex_lock(&mdsc->mutex);
@@ -2496,7 +2529,6 @@
 	}
 	mutex_unlock(&mdsc->mutex);
 
-	ceph_add_cap_releases(mdsc, req->r_session);
 	mutex_unlock(&session->s_mutex);
 
 	/* kick calling process */
@@ -2888,8 +2920,7 @@
 	 */
 	session->s_cap_reconnect = 1;
 	/* drop old cap expires; we're about to reestablish that state */
-	discard_cap_releases(mdsc, session);
-	spin_unlock(&session->s_cap_lock);
+	cleanup_cap_releases(mdsc, session);
 
 	/* trim unused caps to reduce MDS's cache rejoin time */
 	if (mdsc->fsc->sb->s_root)
@@ -2956,6 +2987,9 @@
 
 	reply->hdr.data_len = cpu_to_le32(pagelist->length);
 	ceph_msg_data_add_pagelist(reply, pagelist);
+
+	ceph_early_kick_flushing_caps(mdsc, session);
+
 	ceph_con_send(&session->s_con, reply);
 
 	mutex_unlock(&session->s_mutex);
@@ -3352,7 +3386,6 @@
 			send_renew_caps(mdsc, s);
 		else
 			ceph_con_keepalive(&s->s_con);
-		ceph_add_cap_releases(mdsc, s);
 		if (s->s_state == CEPH_MDS_SESSION_OPEN ||
 		    s->s_state == CEPH_MDS_SESSION_HUNG)
 			ceph_send_cap_releases(mdsc, s);
@@ -3390,11 +3423,13 @@
 	atomic_set(&mdsc->num_sessions, 0);
 	mdsc->max_sessions = 0;
 	mdsc->stopping = 0;
+	mdsc->last_snap_seq = 0;
 	init_rwsem(&mdsc->snap_rwsem);
 	mdsc->snap_realms = RB_ROOT;
 	INIT_LIST_HEAD(&mdsc->snap_empty);
 	spin_lock_init(&mdsc->snap_empty_lock);
 	mdsc->last_tid = 0;
+	mdsc->oldest_tid = 0;
 	mdsc->request_tree = RB_ROOT;
 	INIT_DELAYED_WORK(&mdsc->delayed_work, delayed_work);
 	mdsc->last_renew_caps = jiffies;
@@ -3402,7 +3437,8 @@
 	spin_lock_init(&mdsc->cap_delay_lock);
 	INIT_LIST_HEAD(&mdsc->snap_flush_list);
 	spin_lock_init(&mdsc->snap_flush_lock);
-	mdsc->cap_flush_seq = 0;
+	mdsc->last_cap_flush_tid = 1;
+	mdsc->cap_flush_tree = RB_ROOT;
 	INIT_LIST_HEAD(&mdsc->cap_dirty);
 	INIT_LIST_HEAD(&mdsc->cap_dirty_migrating);
 	mdsc->num_cap_flushing = 0;
@@ -3414,6 +3450,9 @@
 	ceph_caps_init(mdsc);
 	ceph_adjust_min_caps(mdsc, fsc->min_caps);
 
+	init_rwsem(&mdsc->pool_perm_rwsem);
+	mdsc->pool_perm_tree = RB_ROOT;
+
 	return 0;
 }
 
@@ -3423,8 +3462,8 @@
  */
 static void wait_requests(struct ceph_mds_client *mdsc)
 {
+	struct ceph_options *opts = mdsc->fsc->client->options;
 	struct ceph_mds_request *req;
-	struct ceph_fs_client *fsc = mdsc->fsc;
 
 	mutex_lock(&mdsc->mutex);
 	if (__get_oldest_req(mdsc)) {
@@ -3432,7 +3471,7 @@
 
 		dout("wait_requests waiting for requests\n");
 		wait_for_completion_timeout(&mdsc->safe_umount_waiters,
-				    fsc->client->options->mount_timeout * HZ);
+				    ceph_timeout_jiffies(opts->mount_timeout));
 
 		/* tear down remaining requests */
 		mutex_lock(&mdsc->mutex);
@@ -3485,7 +3524,8 @@
 			nextreq = rb_entry(n, struct ceph_mds_request, r_node);
 		else
 			nextreq = NULL;
-		if ((req->r_op & CEPH_MDS_OP_WRITE)) {
+		if (req->r_op != CEPH_MDS_OP_SETFILELOCK &&
+		    (req->r_op & CEPH_MDS_OP_WRITE)) {
 			/* write op */
 			ceph_mdsc_get_request(req);
 			if (nextreq)
@@ -3513,7 +3553,7 @@
 
 void ceph_mdsc_sync(struct ceph_mds_client *mdsc)
 {
-	u64 want_tid, want_flush;
+	u64 want_tid, want_flush, want_snap;
 
 	if (mdsc->fsc->mount_state == CEPH_MOUNT_SHUTDOWN)
 		return;
@@ -3525,13 +3565,18 @@
 
 	ceph_flush_dirty_caps(mdsc);
 	spin_lock(&mdsc->cap_dirty_lock);
-	want_flush = mdsc->cap_flush_seq;
+	want_flush = mdsc->last_cap_flush_tid;
 	spin_unlock(&mdsc->cap_dirty_lock);
 
-	dout("sync want tid %lld flush_seq %lld\n", want_tid, want_flush);
+	down_read(&mdsc->snap_rwsem);
+	want_snap = mdsc->last_snap_seq;
+	up_read(&mdsc->snap_rwsem);
+
+	dout("sync want tid %lld flush_seq %lld snap_seq %lld\n",
+	     want_tid, want_flush, want_snap);
 
 	wait_unsafe_requests(mdsc, want_tid);
-	wait_caps_flush(mdsc, want_flush);
+	wait_caps_flush(mdsc, want_flush, want_snap);
 }
 
 /*
@@ -3549,10 +3594,9 @@
  */
 void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc)
 {
+	struct ceph_options *opts = mdsc->fsc->client->options;
 	struct ceph_mds_session *session;
 	int i;
-	struct ceph_fs_client *fsc = mdsc->fsc;
-	unsigned long timeout = fsc->client->options->mount_timeout * HZ;
 
 	dout("close_sessions\n");
 
@@ -3573,7 +3617,7 @@
 
 	dout("waiting for sessions to close\n");
 	wait_event_timeout(mdsc->session_close_wq, done_closing_sessions(mdsc),
-			   timeout);
+			   ceph_timeout_jiffies(opts->mount_timeout));
 
 	/* tear down remaining sessions */
 	mutex_lock(&mdsc->mutex);
@@ -3607,6 +3651,7 @@
 		ceph_mdsmap_destroy(mdsc->mdsmap);
 	kfree(mdsc->sessions);
 	ceph_caps_finalize(mdsc);
+	ceph_pool_perm_destroy(mdsc);
 }
 
 void ceph_mdsc_destroy(struct ceph_fs_client *fsc)
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 1875b5d..762757e 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -139,7 +139,6 @@
 	int		  s_cap_reconnect;
 	int		  s_readonly;
 	struct list_head  s_cap_releases; /* waiting cap_release messages */
-	struct list_head  s_cap_releases_done; /* ready to send */
 	struct ceph_cap  *s_cap_iterator;
 
 	/* protected by mutex */
@@ -228,7 +227,7 @@
 	int r_err;
 	bool r_aborted;
 
-	unsigned long r_timeout;  /* optional.  jiffies */
+	unsigned long r_timeout;  /* optional.  jiffies, 0 is "wait forever" */
 	unsigned long r_started;  /* start time to measure timeout against */
 	unsigned long r_request_started; /* start time for mds request only,
 					    used to measure lease durations */
@@ -254,12 +253,21 @@
 	bool		  r_got_unsafe, r_got_safe, r_got_result;
 
 	bool              r_did_prepopulate;
+	long long	  r_dir_release_cnt;
+	long long	  r_dir_ordered_cnt;
+	int		  r_readdir_cache_idx;
 	u32               r_readdir_offset;
 
 	struct ceph_cap_reservation r_caps_reservation;
 	int r_num_caps;
 };
 
+struct ceph_pool_perm {
+	struct rb_node node;
+	u32 pool;
+	int perm;
+};
+
 /*
  * mds client state
  */
@@ -284,12 +292,15 @@
 	 * references (implying they contain no inodes with caps) that
 	 * should be destroyed.
 	 */
+	u64			last_snap_seq;
 	struct rw_semaphore     snap_rwsem;
 	struct rb_root          snap_realms;
 	struct list_head        snap_empty;
 	spinlock_t              snap_empty_lock;  /* protect snap_empty */
 
 	u64                    last_tid;      /* most recent mds request */
+	u64                    oldest_tid;    /* oldest incomplete mds request,
+						 excluding setfilelock requests */
 	struct rb_root         request_tree;  /* pending mds requests */
 	struct delayed_work    delayed_work;  /* delayed work */
 	unsigned long    last_renew_caps;  /* last time we renewed our caps */
@@ -298,7 +309,8 @@
 	struct list_head snap_flush_list;  /* cap_snaps ready to flush */
 	spinlock_t       snap_flush_lock;
 
-	u64               cap_flush_seq;
+	u64               last_cap_flush_tid;
+	struct rb_root    cap_flush_tree;
 	struct list_head  cap_dirty;        /* inodes with dirty caps */
 	struct list_head  cap_dirty_migrating; /* ...that are migration... */
 	int               num_cap_flushing; /* # caps we are flushing */
@@ -328,6 +340,9 @@
 	spinlock_t	  dentry_lru_lock;
 	struct list_head  dentry_lru;
 	int		  num_dentry;
+
+	struct rw_semaphore     pool_perm_rwsem;
+	struct rb_root		pool_perm_tree;
 };
 
 extern const char *ceph_mds_op_name(int op);
@@ -379,8 +394,6 @@
 	kref_put(&req->r_kref, ceph_mdsc_release_request);
 }
 
-extern int ceph_add_cap_releases(struct ceph_mds_client *mdsc,
-				 struct ceph_mds_session *session);
 extern void ceph_send_cap_releases(struct ceph_mds_client *mdsc,
 				   struct ceph_mds_session *session);
 
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index a97e39f..233d906a 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -296,7 +296,7 @@
 }
 
 
-static struct ceph_snap_context *empty_snapc;
+struct ceph_snap_context *ceph_empty_snapc;
 
 /*
  * build the snap context for a given realm.
@@ -338,9 +338,9 @@
 		return 0;
 	}
 
-	if (num == 0 && realm->seq == empty_snapc->seq) {
-		ceph_get_snap_context(empty_snapc);
-		snapc = empty_snapc;
+	if (num == 0 && realm->seq == ceph_empty_snapc->seq) {
+		ceph_get_snap_context(ceph_empty_snapc);
+		snapc = ceph_empty_snapc;
 		goto done;
 	}
 
@@ -436,6 +436,14 @@
 	return 0;
 }
 
+static bool has_new_snaps(struct ceph_snap_context *o,
+			  struct ceph_snap_context *n)
+{
+	if (n->num_snaps == 0)
+		return false;
+	/* snaps are in descending order */
+	return n->snaps[0] > o->seq;
+}
 
 /*
  * When a snapshot is applied, the size/mtime inode metadata is queued
@@ -455,6 +463,7 @@
 {
 	struct inode *inode = &ci->vfs_inode;
 	struct ceph_cap_snap *capsnap;
+	struct ceph_snap_context *old_snapc, *new_snapc;
 	int used, dirty;
 
 	capsnap = kzalloc(sizeof(*capsnap), GFP_NOFS);
@@ -467,6 +476,9 @@
 	used = __ceph_caps_used(ci);
 	dirty = __ceph_caps_dirty(ci);
 
+	old_snapc = ci->i_head_snapc;
+	new_snapc = ci->i_snap_realm->cached_context;
+
 	/*
 	 * If there is a write in progress, treat that as a dirty Fw,
 	 * even though it hasn't completed yet; by the time we finish
@@ -481,76 +493,95 @@
 		   writes in progress now were started before the previous
 		   cap_snap.  lucky us. */
 		dout("queue_cap_snap %p already pending\n", inode);
-		kfree(capsnap);
-	} else if (ci->i_snap_realm->cached_context == empty_snapc) {
-		dout("queue_cap_snap %p empty snapc\n", inode);
-		kfree(capsnap);
-	} else if (dirty & (CEPH_CAP_AUTH_EXCL|CEPH_CAP_XATTR_EXCL|
-			    CEPH_CAP_FILE_EXCL|CEPH_CAP_FILE_WR)) {
-		struct ceph_snap_context *snapc = ci->i_head_snapc;
-
-		/*
-		 * if we are a sync write, we may need to go to the snaprealm
-		 * to get the current snapc.
-		 */
-		if (!snapc)
-			snapc = ci->i_snap_realm->cached_context;
-
-		dout("queue_cap_snap %p cap_snap %p queuing under %p %s\n",
-		     inode, capsnap, snapc, ceph_cap_string(dirty));
-		ihold(inode);
-
-		atomic_set(&capsnap->nref, 1);
-		capsnap->ci = ci;
-		INIT_LIST_HEAD(&capsnap->ci_item);
-		INIT_LIST_HEAD(&capsnap->flushing_item);
-
-		capsnap->follows = snapc->seq;
-		capsnap->issued = __ceph_caps_issued(ci, NULL);
-		capsnap->dirty = dirty;
-
-		capsnap->mode = inode->i_mode;
-		capsnap->uid = inode->i_uid;
-		capsnap->gid = inode->i_gid;
-
-		if (dirty & CEPH_CAP_XATTR_EXCL) {
-			__ceph_build_xattrs_blob(ci);
-			capsnap->xattr_blob =
-				ceph_buffer_get(ci->i_xattrs.blob);
-			capsnap->xattr_version = ci->i_xattrs.version;
-		} else {
-			capsnap->xattr_blob = NULL;
-			capsnap->xattr_version = 0;
-		}
-
-		capsnap->inline_data = ci->i_inline_version != CEPH_INLINE_NONE;
-
-		/* dirty page count moved from _head to this cap_snap;
-		   all subsequent writes page dirties occur _after_ this
-		   snapshot. */
-		capsnap->dirty_pages = ci->i_wrbuffer_ref_head;
-		ci->i_wrbuffer_ref_head = 0;
-		capsnap->context = snapc;
-		ci->i_head_snapc =
-			ceph_get_snap_context(ci->i_snap_realm->cached_context);
-		dout(" new snapc is %p\n", ci->i_head_snapc);
-		list_add_tail(&capsnap->ci_item, &ci->i_cap_snaps);
-
-		if (used & CEPH_CAP_FILE_WR) {
-			dout("queue_cap_snap %p cap_snap %p snapc %p"
-			     " seq %llu used WR, now pending\n", inode,
-			     capsnap, snapc, snapc->seq);
-			capsnap->writing = 1;
-		} else {
-			/* note mtime, size NOW. */
-			__ceph_finish_cap_snap(ci, capsnap);
-		}
-	} else {
+		goto update_snapc;
+	}
+	if (ci->i_wrbuffer_ref_head == 0 &&
+	    !(dirty & (CEPH_CAP_ANY_EXCL|CEPH_CAP_FILE_WR))) {
 		dout("queue_cap_snap %p nothing dirty|writing\n", inode);
-		kfree(capsnap);
+		goto update_snapc;
 	}
 
+	BUG_ON(!old_snapc);
+
+	/*
+	 * There is no need to send FLUSHSNAP message to MDS if there is
+	 * no new snapshot. But when there is dirty pages or on-going
+	 * writes, we still need to create cap_snap. cap_snap is needed
+	 * by the write path and page writeback path.
+	 *
+	 * also see ceph_try_drop_cap_snap()
+	 */
+	if (has_new_snaps(old_snapc, new_snapc)) {
+		if (dirty & (CEPH_CAP_ANY_EXCL|CEPH_CAP_FILE_WR))
+			capsnap->need_flush = true;
+	} else {
+		if (!(used & CEPH_CAP_FILE_WR) &&
+		    ci->i_wrbuffer_ref_head == 0) {
+			dout("queue_cap_snap %p "
+			     "no new_snap|dirty_page|writing\n", inode);
+			goto update_snapc;
+		}
+	}
+
+	dout("queue_cap_snap %p cap_snap %p queuing under %p %s %s\n",
+	     inode, capsnap, old_snapc, ceph_cap_string(dirty),
+	     capsnap->need_flush ? "" : "no_flush");
+	ihold(inode);
+
+	atomic_set(&capsnap->nref, 1);
+	capsnap->ci = ci;
+	INIT_LIST_HEAD(&capsnap->ci_item);
+	INIT_LIST_HEAD(&capsnap->flushing_item);
+
+	capsnap->follows = old_snapc->seq;
+	capsnap->issued = __ceph_caps_issued(ci, NULL);
+	capsnap->dirty = dirty;
+
+	capsnap->mode = inode->i_mode;
+	capsnap->uid = inode->i_uid;
+	capsnap->gid = inode->i_gid;
+
+	if (dirty & CEPH_CAP_XATTR_EXCL) {
+		__ceph_build_xattrs_blob(ci);
+		capsnap->xattr_blob =
+			ceph_buffer_get(ci->i_xattrs.blob);
+		capsnap->xattr_version = ci->i_xattrs.version;
+	} else {
+		capsnap->xattr_blob = NULL;
+		capsnap->xattr_version = 0;
+	}
+
+	capsnap->inline_data = ci->i_inline_version != CEPH_INLINE_NONE;
+
+	/* dirty page count moved from _head to this cap_snap;
+	   all subsequent writes page dirties occur _after_ this
+	   snapshot. */
+	capsnap->dirty_pages = ci->i_wrbuffer_ref_head;
+	ci->i_wrbuffer_ref_head = 0;
+	capsnap->context = old_snapc;
+	list_add_tail(&capsnap->ci_item, &ci->i_cap_snaps);
+	old_snapc = NULL;
+
+	if (used & CEPH_CAP_FILE_WR) {
+		dout("queue_cap_snap %p cap_snap %p snapc %p"
+		     " seq %llu used WR, now pending\n", inode,
+		     capsnap, old_snapc, old_snapc->seq);
+		capsnap->writing = 1;
+	} else {
+		/* note mtime, size NOW. */
+		__ceph_finish_cap_snap(ci, capsnap);
+	}
+	capsnap = NULL;
+
+update_snapc:
+	if (ci->i_head_snapc) {
+		ci->i_head_snapc = ceph_get_snap_context(new_snapc);
+		dout(" new snapc is %p\n", new_snapc);
+	}
 	spin_unlock(&ci->i_ceph_lock);
+
+	kfree(capsnap);
+	ceph_put_snap_context(old_snapc);
 }
 
 /*
@@ -699,6 +730,8 @@
 
 		/* queue realm for cap_snap creation */
 		list_add(&realm->dirty_item, &dirty_realms);
+		if (realm->seq > mdsc->last_snap_seq)
+			mdsc->last_snap_seq = realm->seq;
 
 		invalidate = 1;
 	} else if (!realm->cached_context) {
@@ -964,14 +997,14 @@
 
 int __init ceph_snap_init(void)
 {
-	empty_snapc = ceph_create_snap_context(0, GFP_NOFS);
-	if (!empty_snapc)
+	ceph_empty_snapc = ceph_create_snap_context(0, GFP_NOFS);
+	if (!ceph_empty_snapc)
 		return -ENOMEM;
-	empty_snapc->seq = 1;
+	ceph_empty_snapc->seq = 1;
 	return 0;
 }
 
 void ceph_snap_exit(void)
 {
-	ceph_put_snap_context(empty_snapc);
+	ceph_put_snap_context(ceph_empty_snapc);
 }
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 4e99053..d1c833c 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -134,10 +134,12 @@
 	Opt_noino32,
 	Opt_fscache,
 	Opt_nofscache,
+	Opt_poolperm,
+	Opt_nopoolperm,
 #ifdef CONFIG_CEPH_FS_POSIX_ACL
 	Opt_acl,
 #endif
-	Opt_noacl
+	Opt_noacl,
 };
 
 static match_table_t fsopt_tokens = {
@@ -165,6 +167,8 @@
 	{Opt_noino32, "noino32"},
 	{Opt_fscache, "fsc"},
 	{Opt_nofscache, "nofsc"},
+	{Opt_poolperm, "poolperm"},
+	{Opt_nopoolperm, "nopoolperm"},
 #ifdef CONFIG_CEPH_FS_POSIX_ACL
 	{Opt_acl, "acl"},
 #endif
@@ -268,6 +272,13 @@
 	case Opt_nofscache:
 		fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE;
 		break;
+	case Opt_poolperm:
+		fsopt->flags &= ~CEPH_MOUNT_OPT_NOPOOLPERM;
+		printk ("pool perm");
+		break;
+	case Opt_nopoolperm:
+		fsopt->flags |= CEPH_MOUNT_OPT_NOPOOLPERM;
+		break;
 #ifdef CONFIG_CEPH_FS_POSIX_ACL
 	case Opt_acl:
 		fsopt->sb_flags |= MS_POSIXACL;
@@ -436,6 +447,8 @@
 		seq_puts(m, ",nodcache");
 	if (fsopt->flags & CEPH_MOUNT_OPT_FSCACHE)
 		seq_puts(m, ",fsc");
+	if (fsopt->flags & CEPH_MOUNT_OPT_NOPOOLPERM)
+		seq_puts(m, ",nopoolperm");
 
 #ifdef CONFIG_CEPH_FS_POSIX_ACL
 	if (fsopt->sb_flags & MS_POSIXACL)
@@ -609,6 +622,7 @@
  */
 struct kmem_cache *ceph_inode_cachep;
 struct kmem_cache *ceph_cap_cachep;
+struct kmem_cache *ceph_cap_flush_cachep;
 struct kmem_cache *ceph_dentry_cachep;
 struct kmem_cache *ceph_file_cachep;
 
@@ -634,6 +648,10 @@
 				     SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD);
 	if (ceph_cap_cachep == NULL)
 		goto bad_cap;
+	ceph_cap_flush_cachep = KMEM_CACHE(ceph_cap_flush,
+					   SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD);
+	if (ceph_cap_flush_cachep == NULL)
+		goto bad_cap_flush;
 
 	ceph_dentry_cachep = KMEM_CACHE(ceph_dentry_info,
 					SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD);
@@ -652,6 +670,8 @@
 bad_file:
 	kmem_cache_destroy(ceph_dentry_cachep);
 bad_dentry:
+	kmem_cache_destroy(ceph_cap_flush_cachep);
+bad_cap_flush:
 	kmem_cache_destroy(ceph_cap_cachep);
 bad_cap:
 	kmem_cache_destroy(ceph_inode_cachep);
@@ -668,6 +688,7 @@
 
 	kmem_cache_destroy(ceph_inode_cachep);
 	kmem_cache_destroy(ceph_cap_cachep);
+	kmem_cache_destroy(ceph_cap_flush_cachep);
 	kmem_cache_destroy(ceph_dentry_cachep);
 	kmem_cache_destroy(ceph_file_cachep);
 
@@ -729,7 +750,7 @@
 	req->r_ino1.ino = CEPH_INO_ROOT;
 	req->r_ino1.snap = CEPH_NOSNAP;
 	req->r_started = started;
-	req->r_timeout = fsc->client->options->mount_timeout * HZ;
+	req->r_timeout = fsc->client->options->mount_timeout;
 	req->r_args.getattr.mask = cpu_to_le32(CEPH_STAT_CAP_INODE);
 	req->r_num_caps = 2;
 	err = ceph_mdsc_do_request(mdsc, NULL, req);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index fa20e13..860cc016 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -35,6 +35,7 @@
 #define CEPH_MOUNT_OPT_INO32           (1<<8) /* 32 bit inos */
 #define CEPH_MOUNT_OPT_DCACHE          (1<<9) /* use dcache for readdir etc */
 #define CEPH_MOUNT_OPT_FSCACHE         (1<<10) /* use fscache */
+#define CEPH_MOUNT_OPT_NOPOOLPERM      (1<<11) /* no pool permission check */
 
 #define CEPH_MOUNT_OPT_DEFAULT    (CEPH_MOUNT_OPT_RBYTES | \
 				   CEPH_MOUNT_OPT_DCACHE)
@@ -121,11 +122,21 @@
 	struct rb_node ci_node;          /* per-ci cap tree */
 	struct ceph_mds_session *session;
 	struct list_head session_caps;   /* per-session caplist */
-	int mds;
 	u64 cap_id;       /* unique cap id (mds provided) */
-	int issued;       /* latest, from the mds */
-	int implemented;  /* implemented superset of issued (for revocation) */
-	int mds_wanted;
+	union {
+		/* in-use caps */
+		struct {
+			int issued;       /* latest, from the mds */
+			int implemented;  /* implemented superset of
+					     issued (for revocation) */
+			int mds, mds_wanted;
+		};
+		/* caps to release */
+		struct {
+			u64 cap_ino;
+			int queue_release;
+		};
+	};
 	u32 seq, issue_seq, mseq;
 	u32 cap_gen;      /* active/stale cycle */
 	unsigned long last_used;
@@ -163,6 +174,7 @@
 	int writing;   /* a sync write is still in progress */
 	int dirty_pages;     /* dirty pages awaiting writeback */
 	bool inline_data;
+	bool need_flush;
 };
 
 static inline void ceph_put_cap_snap(struct ceph_cap_snap *capsnap)
@@ -174,6 +186,17 @@
 	}
 }
 
+struct ceph_cap_flush {
+	u64 tid;
+	int caps;
+	bool kick;
+	struct rb_node g_node; // global
+	union {
+		struct rb_node i_node; // inode
+		struct list_head list;
+	};
+};
+
 /*
  * The frag tree describes how a directory is fragmented, potentially across
  * multiple metadata servers.  It is also used to indicate points where
@@ -259,9 +282,9 @@
 	u32 i_time_warp_seq;
 
 	unsigned i_ceph_flags;
-	int i_ordered_count;
-	atomic_t i_release_count;
-	atomic_t i_complete_count;
+	atomic64_t i_release_count;
+	atomic64_t i_ordered_count;
+	atomic64_t i_complete_seq[2];
 
 	struct ceph_dir_layout i_dir_layout;
 	struct ceph_file_layout i_layout;
@@ -283,11 +306,11 @@
 	struct ceph_cap *i_auth_cap;     /* authoritative cap, if any */
 	unsigned i_dirty_caps, i_flushing_caps;     /* mask of dirtied fields */
 	struct list_head i_dirty_item, i_flushing_item;
-	u64 i_cap_flush_seq;
 	/* we need to track cap writeback on a per-cap-bit basis, to allow
 	 * overlapping, pipelined cap flushes to the mds.  we can probably
 	 * reduce the tid to 8 bits if we're concerned about inode size. */
-	u16 i_cap_flush_last_tid, i_cap_flush_tid[CEPH_CAP_BITS];
+	struct ceph_cap_flush *i_prealloc_cap_flush;
+	struct rb_root i_cap_flush_tree;
 	wait_queue_head_t i_cap_wq;      /* threads waiting on a capability */
 	unsigned long i_hold_caps_min; /* jiffies */
 	unsigned long i_hold_caps_max; /* jiffies */
@@ -438,36 +461,46 @@
 /*
  * Ceph inode.
  */
-#define CEPH_I_DIR_ORDERED	1  /* dentries in dir are ordered */
-#define CEPH_I_NODELAY		4  /* do not delay cap release */
-#define CEPH_I_FLUSH		8  /* do not delay flush of dirty metadata */
-#define CEPH_I_NOFLUSH		16 /* do not flush dirty caps */
+#define CEPH_I_DIR_ORDERED	(1 << 0)  /* dentries in dir are ordered */
+#define CEPH_I_NODELAY		(1 << 1)  /* do not delay cap release */
+#define CEPH_I_FLUSH		(1 << 2)  /* do not delay flush of dirty metadata */
+#define CEPH_I_NOFLUSH		(1 << 3)  /* do not flush dirty caps */
+#define CEPH_I_POOL_PERM	(1 << 4)  /* pool rd/wr bits are valid */
+#define CEPH_I_POOL_RD		(1 << 5)  /* can read from pool */
+#define CEPH_I_POOL_WR		(1 << 6)  /* can write to pool */
+
 
 static inline void __ceph_dir_set_complete(struct ceph_inode_info *ci,
-					   int release_count, int ordered_count)
+					   long long release_count,
+					   long long ordered_count)
 {
-	atomic_set(&ci->i_complete_count, release_count);
-	if (ci->i_ordered_count == ordered_count)
-		ci->i_ceph_flags |= CEPH_I_DIR_ORDERED;
-	else
-		ci->i_ceph_flags &= ~CEPH_I_DIR_ORDERED;
+	smp_mb__before_atomic();
+	atomic64_set(&ci->i_complete_seq[0], release_count);
+	atomic64_set(&ci->i_complete_seq[1], ordered_count);
 }
 
 static inline void __ceph_dir_clear_complete(struct ceph_inode_info *ci)
 {
-	atomic_inc(&ci->i_release_count);
+	atomic64_inc(&ci->i_release_count);
+}
+
+static inline void __ceph_dir_clear_ordered(struct ceph_inode_info *ci)
+{
+	atomic64_inc(&ci->i_ordered_count);
 }
 
 static inline bool __ceph_dir_is_complete(struct ceph_inode_info *ci)
 {
-	return atomic_read(&ci->i_complete_count) ==
-		atomic_read(&ci->i_release_count);
+	return atomic64_read(&ci->i_complete_seq[0]) ==
+		atomic64_read(&ci->i_release_count);
 }
 
 static inline bool __ceph_dir_is_complete_ordered(struct ceph_inode_info *ci)
 {
-	return __ceph_dir_is_complete(ci) &&
-		(ci->i_ceph_flags & CEPH_I_DIR_ORDERED);
+	return  atomic64_read(&ci->i_complete_seq[0]) ==
+		atomic64_read(&ci->i_release_count) &&
+		atomic64_read(&ci->i_complete_seq[1]) ==
+		atomic64_read(&ci->i_ordered_count);
 }
 
 static inline void ceph_dir_clear_complete(struct inode *inode)
@@ -477,20 +510,13 @@
 
 static inline void ceph_dir_clear_ordered(struct inode *inode)
 {
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	spin_lock(&ci->i_ceph_lock);
-	ci->i_ordered_count++;
-	ci->i_ceph_flags &= ~CEPH_I_DIR_ORDERED;
-	spin_unlock(&ci->i_ceph_lock);
+	__ceph_dir_clear_ordered(ceph_inode(inode));
 }
 
 static inline bool ceph_dir_is_complete_ordered(struct inode *inode)
 {
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	bool ret;
-	spin_lock(&ci->i_ceph_lock);
-	ret = __ceph_dir_is_complete_ordered(ci);
-	spin_unlock(&ci->i_ceph_lock);
+	bool ret = __ceph_dir_is_complete_ordered(ceph_inode(inode));
+	smp_rmb();
 	return ret;
 }
 
@@ -552,7 +578,10 @@
 {
 	return ci->i_dirty_caps | ci->i_flushing_caps;
 }
-extern int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask);
+extern struct ceph_cap_flush *ceph_alloc_cap_flush(void);
+extern void ceph_free_cap_flush(struct ceph_cap_flush *cf);
+extern int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask,
+				  struct ceph_cap_flush **pcf);
 
 extern int __ceph_caps_revoking_other(struct ceph_inode_info *ci,
 				      struct ceph_cap *ocap, int mask);
@@ -606,16 +635,20 @@
 	unsigned offset;       /* offset of last chunk, adjusted for . and .. */
 	unsigned next_offset;  /* offset of next chunk (last_name's + 1) */
 	char *last_name;       /* last entry in previous chunk */
-	struct dentry *dentry; /* next dentry (for dcache readdir) */
-	int dir_release_count;
-	int dir_ordered_count;
+	long long dir_release_count;
+	long long dir_ordered_count;
+	int readdir_cache_idx;
 
 	/* used for -o dirstat read() on directory thing */
 	char *dir_info;
 	int dir_info_len;
 };
 
-
+struct ceph_readdir_cache_control {
+	struct page  *page;
+	struct dentry **dentries;
+	int index;
+};
 
 /*
  * A "snap realm" describes a subset of the file hierarchy sharing
@@ -687,6 +720,7 @@
 
 
 /* snap.c */
+extern struct ceph_snap_context *ceph_empty_snapc;
 struct ceph_snap_realm *ceph_lookup_snap_realm(struct ceph_mds_client *mdsc,
 					       u64 ino);
 extern void ceph_get_snap_realm(struct ceph_mds_client *mdsc,
@@ -713,8 +747,8 @@
 static inline bool __ceph_have_pending_cap_snap(struct ceph_inode_info *ci)
 {
 	return !list_empty(&ci->i_cap_snaps) &&
-		list_entry(ci->i_cap_snaps.prev, struct ceph_cap_snap,
-			   ci_item)->writing;
+	       list_last_entry(&ci->i_cap_snaps, struct ceph_cap_snap,
+			       ci_item)->writing;
 }
 
 /* inode.c */
@@ -838,12 +872,12 @@
 			 struct ceph_cap *cap);
 extern int ceph_is_any_caps(struct inode *inode);
 
-extern void __queue_cap_release(struct ceph_mds_session *session, u64 ino,
-				u64 cap_id, u32 migrate_seq, u32 issue_seq);
 extern void ceph_queue_caps_release(struct inode *inode);
 extern int ceph_write_inode(struct inode *inode, struct writeback_control *wbc);
 extern int ceph_fsync(struct file *file, loff_t start, loff_t end,
 		      int datasync);
+extern void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc,
+					  struct ceph_mds_session *session);
 extern void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc,
 				    struct ceph_mds_session *session);
 extern struct ceph_cap *ceph_get_cap_for_mds(struct ceph_inode_info *ci,
@@ -879,6 +913,9 @@
 /* addr.c */
 extern const struct address_space_operations ceph_aops;
 extern int ceph_mmap(struct file *file, struct vm_area_struct *vma);
+extern int ceph_uninline_data(struct file *filp, struct page *locked_page);
+extern int ceph_pool_perm_check(struct ceph_inode_info *ci, int need);
+extern void ceph_pool_perm_destroy(struct ceph_mds_client* mdsc);
 
 /* file.c */
 extern const struct file_operations ceph_file_fops;
@@ -890,7 +927,6 @@
 extern int ceph_release(struct inode *inode, struct file *filp);
 extern void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
 				  char *data, size_t len);
-int ceph_uninline_data(struct file *filp, struct page *locked_page);
 /* dir.c */
 extern const struct file_operations ceph_dir_fops;
 extern const struct file_operations ceph_snapdir_fops;
@@ -911,6 +947,7 @@
 extern void ceph_invalidate_dentry_lease(struct dentry *dentry);
 extern unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn);
 extern struct inode *ceph_get_dentry_parent_inode(struct dentry *dentry);
+extern void ceph_readdir_cache_release(struct ceph_readdir_cache_control *ctl);
 
 /*
  * our d_ops vary depending on whether the inode is live,
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index cd7ffad4..819163d 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -911,6 +911,8 @@
 	struct inode *inode = d_inode(dentry);
 	struct ceph_vxattr *vxattr;
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(dentry->d_sb)->mdsc;
+	struct ceph_cap_flush *prealloc_cf = NULL;
 	int issued;
 	int err;
 	int dirty = 0;
@@ -920,6 +922,7 @@
 	char *newval = NULL;
 	struct ceph_inode_xattr *xattr = NULL;
 	int required_blob_size;
+	bool lock_snap_rwsem = false;
 
 	if (!ceph_is_valid_xattr(name))
 		return -EOPNOTSUPP;
@@ -948,12 +951,27 @@
 	if (!xattr)
 		goto out;
 
+	prealloc_cf = ceph_alloc_cap_flush();
+	if (!prealloc_cf)
+		goto out;
+
 	spin_lock(&ci->i_ceph_lock);
 retry:
 	issued = __ceph_caps_issued(ci, NULL);
-	dout("setxattr %p issued %s\n", inode, ceph_cap_string(issued));
 	if (ci->i_xattrs.version == 0 || !(issued & CEPH_CAP_XATTR_EXCL))
 		goto do_sync;
+
+	if (!lock_snap_rwsem && !ci->i_head_snapc) {
+		lock_snap_rwsem = true;
+		if (!down_read_trylock(&mdsc->snap_rwsem)) {
+			spin_unlock(&ci->i_ceph_lock);
+			down_read(&mdsc->snap_rwsem);
+			spin_lock(&ci->i_ceph_lock);
+			goto retry;
+		}
+	}
+
+	dout("setxattr %p issued %s\n", inode, ceph_cap_string(issued));
 	__build_xattrs(inode);
 
 	required_blob_size = __get_required_blob_size(ci, name_len, val_len);
@@ -966,7 +984,7 @@
 		dout(" preaallocating new blob size=%d\n", required_blob_size);
 		blob = ceph_buffer_new(required_blob_size, GFP_NOFS);
 		if (!blob)
-			goto out;
+			goto do_sync_unlocked;
 		spin_lock(&ci->i_ceph_lock);
 		if (ci->i_xattrs.prealloc_blob)
 			ceph_buffer_put(ci->i_xattrs.prealloc_blob);
@@ -978,21 +996,28 @@
 			  flags, value ? 1 : -1, &xattr);
 
 	if (!err) {
-		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
+		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL,
+					       &prealloc_cf);
 		ci->i_xattrs.dirty = true;
 		inode->i_ctime = CURRENT_TIME;
 	}
 
 	spin_unlock(&ci->i_ceph_lock);
+	if (lock_snap_rwsem)
+		up_read(&mdsc->snap_rwsem);
 	if (dirty)
 		__mark_inode_dirty(inode, dirty);
+	ceph_free_cap_flush(prealloc_cf);
 	return err;
 
 do_sync:
 	spin_unlock(&ci->i_ceph_lock);
 do_sync_unlocked:
+	if (lock_snap_rwsem)
+		up_read(&mdsc->snap_rwsem);
 	err = ceph_sync_setxattr(dentry, name, value, size, flags);
 out:
+	ceph_free_cap_flush(prealloc_cf);
 	kfree(newname);
 	kfree(newval);
 	kfree(xattr);
@@ -1044,10 +1069,13 @@
 	struct inode *inode = d_inode(dentry);
 	struct ceph_vxattr *vxattr;
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(dentry->d_sb)->mdsc;
+	struct ceph_cap_flush *prealloc_cf = NULL;
 	int issued;
 	int err;
 	int required_blob_size;
 	int dirty;
+	bool lock_snap_rwsem = false;
 
 	if (!ceph_is_valid_xattr(name))
 		return -EOPNOTSUPP;
@@ -1060,14 +1088,29 @@
 	if (!strncmp(name, XATTR_CEPH_PREFIX, XATTR_CEPH_PREFIX_LEN))
 		goto do_sync_unlocked;
 
+	prealloc_cf = ceph_alloc_cap_flush();
+	if (!prealloc_cf)
+		return -ENOMEM;
+
 	err = -ENOMEM;
 	spin_lock(&ci->i_ceph_lock);
 retry:
 	issued = __ceph_caps_issued(ci, NULL);
-	dout("removexattr %p issued %s\n", inode, ceph_cap_string(issued));
-
 	if (ci->i_xattrs.version == 0 || !(issued & CEPH_CAP_XATTR_EXCL))
 		goto do_sync;
+
+	if (!lock_snap_rwsem && !ci->i_head_snapc) {
+		lock_snap_rwsem = true;
+		if (!down_read_trylock(&mdsc->snap_rwsem)) {
+			spin_unlock(&ci->i_ceph_lock);
+			down_read(&mdsc->snap_rwsem);
+			spin_lock(&ci->i_ceph_lock);
+			goto retry;
+		}
+	}
+
+	dout("removexattr %p issued %s\n", inode, ceph_cap_string(issued));
+
 	__build_xattrs(inode);
 
 	required_blob_size = __get_required_blob_size(ci, 0, 0);
@@ -1080,7 +1123,7 @@
 		dout(" preaallocating new blob size=%d\n", required_blob_size);
 		blob = ceph_buffer_new(required_blob_size, GFP_NOFS);
 		if (!blob)
-			goto out;
+			goto do_sync_unlocked;
 		spin_lock(&ci->i_ceph_lock);
 		if (ci->i_xattrs.prealloc_blob)
 			ceph_buffer_put(ci->i_xattrs.prealloc_blob);
@@ -1090,18 +1133,24 @@
 
 	err = __remove_xattr_by_name(ceph_inode(inode), name);
 
-	dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
+	dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL,
+				       &prealloc_cf);
 	ci->i_xattrs.dirty = true;
 	inode->i_ctime = CURRENT_TIME;
 	spin_unlock(&ci->i_ceph_lock);
+	if (lock_snap_rwsem)
+		up_read(&mdsc->snap_rwsem);
 	if (dirty)
 		__mark_inode_dirty(inode, dirty);
+	ceph_free_cap_flush(prealloc_cf);
 	return err;
 do_sync:
 	spin_unlock(&ci->i_ceph_lock);
 do_sync_unlocked:
+	if (lock_snap_rwsem)
+		up_read(&mdsc->snap_rwsem);
+	ceph_free_cap_flush(prealloc_cf);
 	err = ceph_send_removexattr(dentry, name);
-out:
 	return err;
 }
 
diff --git a/fs/coda/coda_linux.h b/fs/coda/coda_linux.h
index d6f7a76..f829fe9 100644
--- a/fs/coda/coda_linux.h
+++ b/fs/coda/coda_linux.h
@@ -79,7 +79,7 @@
 
 static inline struct coda_inode_info *ITOC(struct inode *inode)
 {
-	return list_entry(inode, struct coda_inode_info, vfs_inode);
+	return container_of(inode, struct coda_inode_info, vfs_inode);
 }
 
 static __inline__ struct CodaFid *coda_i2f(struct inode *inode)
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index 8d89f5f..eae8757 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -236,7 +236,7 @@
 
 	if (dentry) {
 		spin_lock(&dentry->d_lock);
-		if (!d_unhashed(dentry) && d_really_is_positive(dentry)) {
+		if (simple_positive(dentry)) {
 			dget_dlock(dentry);
 			__d_drop(dentry);
 			spin_unlock(&dentry->d_lock);
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
index 5373567..a8f3b58 100644
--- a/fs/configfs/mount.c
+++ b/fs/configfs/mount.c
@@ -129,8 +129,6 @@
 }
 
 
-static struct kobject *config_kobj;
-
 static int __init configfs_init(void)
 {
 	int err = -ENOMEM;
@@ -141,8 +139,8 @@
 	if (!configfs_dir_cachep)
 		goto out;
 
-	config_kobj = kobject_create_and_add("config", kernel_kobj);
-	if (!config_kobj)
+	err = sysfs_create_mount_point(kernel_kobj, "config");
+	if (err)
 		goto out2;
 
 	err = register_filesystem(&configfs_fs_type);
@@ -152,7 +150,7 @@
 	return 0;
 out3:
 	pr_err("Unable to register filesystem!\n");
-	kobject_put(config_kobj);
+	sysfs_remove_mount_point(kernel_kobj, "config");
 out2:
 	kmem_cache_destroy(configfs_dir_cachep);
 	configfs_dir_cachep = NULL;
@@ -163,7 +161,7 @@
 static void __exit configfs_exit(void)
 {
 	unregister_filesystem(&configfs_fs_type);
-	kobject_put(config_kobj);
+	sysfs_remove_mount_point(kernel_kobj, "config");
 	kmem_cache_destroy(configfs_dir_cachep);
 	configfs_dir_cachep = NULL;
 }
diff --git a/fs/coredump.c b/fs/coredump.c
index e52e006..c5ecde6 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -140,7 +140,7 @@
 		goto put_exe_file;
 	}
 
-	path = d_path(&exe_file->f_path, pathbuf, PATH_MAX);
+	path = file_path(exe_file, pathbuf, PATH_MAX);
 	if (IS_ERR(path)) {
 		ret = PTR_ERR(path);
 		goto free_buf;
diff --git a/fs/dax.c b/fs/dax.c
index 99b5fbc..c3e21cc 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -155,7 +155,7 @@
 		}
 
 		if (iov_iter_rw(iter) == WRITE)
-			len = copy_from_iter(addr, max - pos, iter);
+			len = copy_from_iter_nocache(addr, max - pos, iter);
 		else if (!hole)
 			len = copy_to_iter(addr, max - pos, iter);
 		else
@@ -209,7 +209,8 @@
 	}
 
 	/* Protects against truncate */
-	inode_dio_begin(inode);
+	if (!(flags & DIO_SKIP_DIO_COUNT))
+		inode_dio_begin(inode);
 
 	retval = dax_io(inode, iter, pos, end, get_block, &bh);
 
@@ -219,7 +220,8 @@
 	if ((retval > 0) && end_io)
 		end_io(iocb, pos, retval, bh.b_private);
 
-	inode_dio_end(inode);
+	if (!(flags & DIO_SKIP_DIO_COUNT))
+		inode_dio_end(inode);
  out:
 	return retval;
 }
diff --git a/fs/dcache.c b/fs/dcache.c
index 592c4b5..7a3f3e5 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1673,7 +1673,8 @@
 				DCACHE_OP_COMPARE	|
 				DCACHE_OP_REVALIDATE	|
 				DCACHE_OP_WEAK_REVALIDATE	|
-				DCACHE_OP_DELETE ));
+				DCACHE_OP_DELETE	|
+				DCACHE_OP_SELECT_INODE));
 	dentry->d_op = op;
 	if (!op)
 		return;
@@ -1689,6 +1690,8 @@
 		dentry->d_flags |= DCACHE_OP_DELETE;
 	if (op->d_prune)
 		dentry->d_flags |= DCACHE_OP_PRUNE;
+	if (op->d_select_inode)
+		dentry->d_flags |= DCACHE_OP_SELECT_INODE;
 
 }
 EXPORT_SYMBOL(d_set_d_op);
@@ -2927,17 +2930,6 @@
 				vfsmnt = &mnt->mnt;
 				continue;
 			}
-			/*
-			 * Filesystems needing to implement special "root names"
-			 * should do so with ->d_dname()
-			 */
-			if (IS_ROOT(dentry) &&
-			   (dentry->d_name.len != 1 ||
-			    dentry->d_name.name[0] != '/')) {
-				WARN(1, "Root dentry has weird name <%.*s>\n",
-				     (int) dentry->d_name.len,
-				     dentry->d_name.name);
-			}
 			if (!error)
 				error = is_mounted(vfsmnt) ? 1 : 2;
 			break;
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 7eaec88..c711be8 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -44,11 +44,6 @@
 	return inode;
 }
 
-static inline int debugfs_positive(struct dentry *dentry)
-{
-	return d_really_is_positive(dentry) && !d_unhashed(dentry);
-}
-
 struct debugfs_mount_opts {
 	kuid_t uid;
 	kgid_t gid;
@@ -522,7 +517,7 @@
 {
 	int ret = 0;
 
-	if (debugfs_positive(dentry)) {
+	if (simple_positive(dentry)) {
 		dget(dentry);
 		if (d_is_dir(dentry))
 			ret = simple_rmdir(d_inode(parent), dentry);
@@ -602,7 +597,7 @@
 	 */
 	spin_lock(&parent->d_lock);
 	list_for_each_entry(child, &parent->d_subdirs, d_child) {
-		if (!debugfs_positive(child))
+		if (!simple_positive(child))
 			continue;
 
 		/* perhaps simple_empty(child) makes more sense */
@@ -623,7 +618,7 @@
 		 * from d_subdirs. When releasing the parent->d_lock we can
 		 * no longer trust that the next pointer is valid.
 		 * Restart the loop. We'll skip this one with the
-		 * debugfs_positive() check.
+		 * simple_positive() check.
 		 */
 		goto loop;
 	}
@@ -716,20 +711,17 @@
 }
 EXPORT_SYMBOL_GPL(debugfs_initialized);
 
-
-static struct kobject *debug_kobj;
-
 static int __init debugfs_init(void)
 {
 	int retval;
 
-	debug_kobj = kobject_create_and_add("debug", kernel_kobj);
-	if (!debug_kobj)
-		return -EINVAL;
+	retval = sysfs_create_mount_point(kernel_kobj, "debug");
+	if (retval)
+		return retval;
 
 	retval = register_filesystem(&debug_fs_type);
 	if (retval)
-		kobject_put(debug_kobj);
+		sysfs_remove_mount_point(kernel_kobj, "debug");
 	else
 		debugfs_registered = true;
 
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index add5663..c35ffdc 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -142,6 +142,8 @@
 	if (inode->i_sb->s_magic == DEVPTS_SUPER_MAGIC)
 		return inode->i_sb;
 #endif
+	if (!devpts_mnt)
+		return NULL;
 	return devpts_mnt->mnt_sb;
 }
 
@@ -525,10 +527,14 @@
 int devpts_new_index(struct inode *ptmx_inode)
 {
 	struct super_block *sb = pts_sb_from_inode(ptmx_inode);
-	struct pts_fs_info *fsi = DEVPTS_SB(sb);
+	struct pts_fs_info *fsi;
 	int index;
 	int ida_ret;
 
+	if (!sb)
+		return -ENODEV;
+
+	fsi = DEVPTS_SB(sb);
 retry:
 	if (!ida_pre_get(&fsi->allocated_ptys, GFP_KERNEL))
 		return -ENOMEM;
@@ -584,11 +590,18 @@
 	struct dentry *dentry;
 	struct super_block *sb = pts_sb_from_inode(ptmx_inode);
 	struct inode *inode;
-	struct dentry *root = sb->s_root;
-	struct pts_fs_info *fsi = DEVPTS_SB(sb);
-	struct pts_mount_opts *opts = &fsi->mount_opts;
+	struct dentry *root;
+	struct pts_fs_info *fsi;
+	struct pts_mount_opts *opts;
 	char s[12];
 
+	if (!sb)
+		return ERR_PTR(-ENODEV);
+
+	root = sb->s_root;
+	fsi = DEVPTS_SB(sb);
+	opts = &fsi->mount_opts;
+
 	inode = new_inode(sb);
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
@@ -676,12 +689,16 @@
 	struct ctl_table_header *table;
 
 	if (!err) {
+		struct vfsmount *mnt;
+
 		table = register_sysctl_table(pty_root_table);
-		devpts_mnt = kern_mount(&devpts_fs_type);
-		if (IS_ERR(devpts_mnt)) {
-			err = PTR_ERR(devpts_mnt);
+		mnt = kern_mount(&devpts_fs_type);
+		if (IS_ERR(mnt)) {
+			err = PTR_ERR(mnt);
 			unregister_filesystem(&devpts_fs_type);
 			unregister_sysctl_table(table);
+		} else {
+			devpts_mnt = mnt;
 		}
 	}
 	return err;
diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c
index 4deb0b0..e5bb2ab 100644
--- a/fs/exofs/dir.c
+++ b/fs/exofs/dir.c
@@ -44,12 +44,6 @@
 	page_cache_release(page);
 }
 
-/* Accesses dir's inode->i_size must be called under inode lock */
-static inline unsigned long dir_pages(struct inode *inode)
-{
-	return (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-}
-
 static unsigned exofs_last_byte(struct inode *inode, unsigned long page_nr)
 {
 	loff_t last_byte = inode->i_size;
diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c
index 796b491..0c6638b 100644
--- a/fs/ext2/dir.c
+++ b/fs/ext2/dir.c
@@ -70,11 +70,6 @@
 	page_cache_release(page);
 }
 
-static inline unsigned long dir_pages(struct inode *inode)
-{
-	return (inode->i_size+PAGE_CACHE_SIZE-1)>>PAGE_CACHE_SHIFT;
-}
-
 /*
  * Return the offset into page `page_nr' of the last valid
  * byte in that page, plus one.
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index aadb728..2553aa8 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -504,7 +504,7 @@
 	struct buffer_head		*bh;
 	int				err;
 
-	bh = sb_getblk(inode->i_sb, pblk);
+	bh = sb_getblk_gfp(inode->i_sb, pblk, __GFP_MOVABLE | GFP_NOFS);
 	if (unlikely(!bh))
 		return ERR_PTR(-ENOMEM);
 
@@ -1089,7 +1089,7 @@
 		err = -EIO;
 		goto cleanup;
 	}
-	bh = sb_getblk(inode->i_sb, newblock);
+	bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS);
 	if (unlikely(!bh)) {
 		err = -ENOMEM;
 		goto cleanup;
@@ -1283,7 +1283,7 @@
 	if (newblock == 0)
 		return err;
 
-	bh = sb_getblk(inode->i_sb, newblock);
+	bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS);
 	if (unlikely(!bh))
 		return -ENOMEM;
 	lock_buffer(bh);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 41f8e55..cecf9aa 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1323,7 +1323,7 @@
 					     unsigned int offset,
 					     unsigned int length)
 {
-	int to_release = 0;
+	int to_release = 0, contiguous_blks = 0;
 	struct buffer_head *head, *bh;
 	unsigned int curr_off = 0;
 	struct inode *inode = page->mapping->host;
@@ -1344,14 +1344,23 @@
 
 		if ((offset <= curr_off) && (buffer_delay(bh))) {
 			to_release++;
+			contiguous_blks++;
 			clear_buffer_delay(bh);
+		} else if (contiguous_blks) {
+			lblk = page->index <<
+			       (PAGE_CACHE_SHIFT - inode->i_blkbits);
+			lblk += (curr_off >> inode->i_blkbits) -
+				contiguous_blks;
+			ext4_es_remove_extent(inode, lblk, contiguous_blks);
+			contiguous_blks = 0;
 		}
 		curr_off = next_off;
 	} while ((bh = bh->b_this_page) != head);
 
-	if (to_release) {
+	if (contiguous_blks) {
 		lblk = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
-		ext4_es_remove_extent(inode, lblk, to_release);
+		lblk += (curr_off >> inode->i_blkbits) - contiguous_blks;
+		ext4_es_remove_extent(inode, lblk, contiguous_blks);
 	}
 
 	/* If we have released all the blocks belonging to a cluster, then we
@@ -4344,7 +4353,12 @@
 	int inode_size = EXT4_INODE_SIZE(sb);
 
 	oi.orig_ino = orig_ino;
-	ino = (orig_ino & ~(inodes_per_block - 1)) + 1;
+	/*
+	 * Calculate the first inode in the inode table block.  Inode
+	 * numbers are one-based.  That is, the first inode in a block
+	 * (assuming 4k blocks and 256 byte inodes) is (n*16 + 1).
+	 */
+	ino = ((orig_ino - 1) & ~(inodes_per_block - 1)) + 1;
 	for (i = 0; i < inodes_per_block; i++, ino++, buf += inode_size) {
 		if (ino == orig_ino)
 			continue;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index f6aedf8..34b610e 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4816,18 +4816,12 @@
 		/*
 		 * blocks being freed are metadata. these blocks shouldn't
 		 * be used until this transaction is committed
+		 *
+		 * We use __GFP_NOFAIL because ext4_free_blocks() is not allowed
+		 * to fail.
 		 */
-	retry:
-		new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS);
-		if (!new_entry) {
-			/*
-			 * We use a retry loop because
-			 * ext4_free_blocks() is not allowed to fail.
-			 */
-			cond_resched();
-			congestion_wait(BLK_RW_ASYNC, HZ/50);
-			goto retry;
-		}
+		new_entry = kmem_cache_alloc(ext4_free_data_cachep,
+				GFP_NOFS|__GFP_NOFAIL);
 		new_entry->efd_start_cluster = bit;
 		new_entry->efd_group = block_group;
 		new_entry->efd_count = count_clusters;
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index b52374e..6163ad2 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -620,6 +620,7 @@
 	struct ext4_inode_info		*ei = EXT4_I(inode);
 	struct ext4_extent		*ex;
 	unsigned int			i, len;
+	ext4_lblk_t			start, end;
 	ext4_fsblk_t			blk;
 	handle_t			*handle;
 	int				ret;
@@ -633,6 +634,14 @@
 				       EXT4_FEATURE_RO_COMPAT_BIGALLOC))
 		return -EOPNOTSUPP;
 
+	/*
+	 * In order to get correct extent info, force all delayed allocation
+	 * blocks to be allocated, otherwise delayed allocation blocks may not
+	 * be reflected and bypass the checks on extent header.
+	 */
+	if (test_opt(inode->i_sb, DELALLOC))
+		ext4_alloc_da_blocks(inode);
+
 	handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
@@ -650,11 +659,13 @@
 		goto errout;
 	}
 	if (eh->eh_entries == 0)
-		blk = len = 0;
+		blk = len = start = end = 0;
 	else {
 		len = le16_to_cpu(ex->ee_len);
 		blk = ext4_ext_pblock(ex);
-		if (len > EXT4_NDIR_BLOCKS) {
+		start = le32_to_cpu(ex->ee_block);
+		end = start + len - 1;
+		if (end >= EXT4_NDIR_BLOCKS) {
 			ret = -EOPNOTSUPP;
 			goto errout;
 		}
@@ -662,7 +673,7 @@
 
 	ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
 	memset(ei->i_data, 0, sizeof(ei->i_data));
-	for (i=0; i < len; i++)
+	for (i = start; i <= end; i++)
 		ei->i_data[i] = cpu_to_le32(blk++);
 	ext4_mark_inode_dirty(handle, inode);
 errout:
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 5c78764..58987b5 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -452,7 +452,7 @@
 	es = EXT4_SB(inode->i_sb)->s_es;
 	es->s_last_error_ino = cpu_to_le32(inode->i_ino);
 	if (ext4_error_ratelimit(inode->i_sb)) {
-		path = d_path(&(file->f_path), pathname, sizeof(pathname));
+		path = file_path(file, pathname, sizeof(pathname));
 		if (IS_ERR(path))
 			path = "(unknown)";
 		va_start(args, fmt);
diff --git a/fs/file.c b/fs/file.c
index 93c5f89..6c672ad 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -147,6 +147,13 @@
 
 	spin_unlock(&files->file_lock);
 	new_fdt = alloc_fdtable(nr);
+
+	/* make sure all __fd_install() have seen resize_in_progress
+	 * or have finished their rcu_read_lock_sched() section.
+	 */
+	if (atomic_read(&files->count) > 1)
+		synchronize_sched();
+
 	spin_lock(&files->file_lock);
 	if (!new_fdt)
 		return -ENOMEM;
@@ -158,21 +165,14 @@
 		__free_fdtable(new_fdt);
 		return -EMFILE;
 	}
-	/*
-	 * Check again since another task may have expanded the fd table while
-	 * we dropped the lock
-	 */
 	cur_fdt = files_fdtable(files);
-	if (nr >= cur_fdt->max_fds) {
-		/* Continue as planned */
-		copy_fdtable(new_fdt, cur_fdt);
-		rcu_assign_pointer(files->fdt, new_fdt);
-		if (cur_fdt != &files->fdtab)
-			call_rcu(&cur_fdt->rcu, free_fdtable_rcu);
-	} else {
-		/* Somebody else expanded, so undo our attempt */
-		__free_fdtable(new_fdt);
-	}
+	BUG_ON(nr < cur_fdt->max_fds);
+	copy_fdtable(new_fdt, cur_fdt);
+	rcu_assign_pointer(files->fdt, new_fdt);
+	if (cur_fdt != &files->fdtab)
+		call_rcu(&cur_fdt->rcu, free_fdtable_rcu);
+	/* coupled with smp_rmb() in __fd_install() */
+	smp_wmb();
 	return 1;
 }
 
@@ -185,21 +185,38 @@
  * The files->file_lock should be held on entry, and will be held on exit.
  */
 static int expand_files(struct files_struct *files, int nr)
+	__releases(files->file_lock)
+	__acquires(files->file_lock)
 {
 	struct fdtable *fdt;
+	int expanded = 0;
 
+repeat:
 	fdt = files_fdtable(files);
 
 	/* Do we need to expand? */
 	if (nr < fdt->max_fds)
-		return 0;
+		return expanded;
 
 	/* Can we expand? */
 	if (nr >= sysctl_nr_open)
 		return -EMFILE;
 
+	if (unlikely(files->resize_in_progress)) {
+		spin_unlock(&files->file_lock);
+		expanded = 1;
+		wait_event(files->resize_wait, !files->resize_in_progress);
+		spin_lock(&files->file_lock);
+		goto repeat;
+	}
+
 	/* All good, so we try */
-	return expand_fdtable(files, nr);
+	files->resize_in_progress = true;
+	expanded = expand_fdtable(files, nr);
+	files->resize_in_progress = false;
+
+	wake_up_all(&files->resize_wait);
+	return expanded;
 }
 
 static inline void __set_close_on_exec(int fd, struct fdtable *fdt)
@@ -256,6 +273,8 @@
 	atomic_set(&newf->count, 1);
 
 	spin_lock_init(&newf->file_lock);
+	newf->resize_in_progress = false;
+	init_waitqueue_head(&newf->resize_wait);
 	newf->next_fd = 0;
 	new_fdt = &newf->fdtab;
 	new_fdt->max_fds = NR_OPEN_DEFAULT;
@@ -553,11 +572,21 @@
 		struct file *file)
 {
 	struct fdtable *fdt;
-	spin_lock(&files->file_lock);
-	fdt = files_fdtable(files);
+
+	might_sleep();
+	rcu_read_lock_sched();
+
+	while (unlikely(files->resize_in_progress)) {
+		rcu_read_unlock_sched();
+		wait_event(files->resize_wait, !files->resize_in_progress);
+		rcu_read_lock_sched();
+	}
+	/* coupled with smp_wmb() in expand_fdtable() */
+	smp_rmb();
+	fdt = rcu_dereference_sched(files->fdt);
 	BUG_ON(fdt->fd[fd] != NULL);
 	rcu_assign_pointer(fdt->fd[fd], file);
-	spin_unlock(&files->file_lock);
+	rcu_read_unlock_sched();
 }
 
 void fd_install(unsigned int fd, struct file *file)
@@ -635,11 +664,17 @@
 	struct file *file;
 
 	rcu_read_lock();
+loop:
 	file = fcheck_files(files, fd);
 	if (file) {
-		/* File object ref couldn't be taken */
-		if ((file->f_mode & mask) || !get_file_rcu(file))
+		/* File object ref couldn't be taken.
+		 * dup2() atomicity guarantee is the reason
+		 * we loop to catch the new file (or NULL pointer)
+		 */
+		if (file->f_mode & mask)
 			file = NULL;
+		else if (!get_file_rcu(file))
+			goto loop;
 	}
 	rcu_read_unlock();
 
diff --git a/fs/file_table.c b/fs/file_table.c
index 294174d..7f9d407 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -20,7 +20,6 @@
 #include <linux/cdev.h>
 #include <linux/fsnotify.h>
 #include <linux/sysctl.h>
-#include <linux/lglock.h>
 #include <linux/percpu_counter.h>
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
diff --git a/fs/freevxfs/vxfs_lookup.c b/fs/freevxfs/vxfs_lookup.c
index 99c7f0a..484b32d 100644
--- a/fs/freevxfs/vxfs_lookup.c
+++ b/fs/freevxfs/vxfs_lookup.c
@@ -61,13 +61,6 @@
 	.iterate =		vxfs_readdir,
 };
 
- 
-static inline u_long
-dir_pages(struct inode *inode)
-{
-	return (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-}
- 
 static inline u_long
 dir_blocks(struct inode *ip)
 {
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index 89acec7..d403c69 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -327,7 +327,8 @@
 
 object_already_extant:
 	ret = -ENOBUFS;
-	if (fscache_object_is_dead(object)) {
+	if (fscache_object_is_dying(object) ||
+	    fscache_cache_is_broken(object)) {
 		spin_unlock(&cookie->lock);
 		goto error;
 	}
@@ -671,7 +672,7 @@
 	if (!op)
 		return -ENOMEM;
 
-	fscache_operation_init(op, NULL, NULL);
+	fscache_operation_init(op, NULL, NULL, NULL);
 	op->flags = FSCACHE_OP_MYTHREAD |
 		(1 << FSCACHE_OP_WAITING) |
 		(1 << FSCACHE_OP_UNUSE_COOKIE);
@@ -695,8 +696,7 @@
 	/* the work queue now carries its own ref on the object */
 	spin_unlock(&cookie->lock);
 
-	ret = fscache_wait_for_operation_activation(object, op,
-						    NULL, NULL, NULL);
+	ret = fscache_wait_for_operation_activation(object, op, NULL, NULL);
 	if (ret == 0) {
 		/* ask the cache to honour the operation */
 		ret = object->cache->ops->check_consistency(op);
diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h
index 7872a62..97ec451 100644
--- a/fs/fscache/internal.h
+++ b/fs/fscache/internal.h
@@ -124,8 +124,7 @@
 				       struct fscache_operation *);
 extern int fscache_submit_op(struct fscache_object *,
 			     struct fscache_operation *);
-extern int fscache_cancel_op(struct fscache_operation *,
-			     void (*)(struct fscache_operation *));
+extern int fscache_cancel_op(struct fscache_operation *, bool);
 extern void fscache_cancel_all_ops(struct fscache_object *);
 extern void fscache_abort_object(struct fscache_object *);
 extern void fscache_start_operations(struct fscache_object *);
@@ -138,8 +137,7 @@
 extern int fscache_wait_for_operation_activation(struct fscache_object *,
 						 struct fscache_operation *,
 						 atomic_t *,
-						 atomic_t *,
-						 void (*)(struct fscache_operation *));
+						 atomic_t *);
 extern void fscache_invalidate_writes(struct fscache_cookie *);
 
 /*
@@ -164,6 +162,7 @@
 extern atomic_t fscache_n_op_run;
 extern atomic_t fscache_n_op_enqueue;
 extern atomic_t fscache_n_op_deferred_release;
+extern atomic_t fscache_n_op_initialised;
 extern atomic_t fscache_n_op_release;
 extern atomic_t fscache_n_op_gc;
 extern atomic_t fscache_n_op_cancelled;
@@ -271,6 +270,11 @@
 extern atomic_t fscache_n_cop_uncache_page;
 extern atomic_t fscache_n_cop_dissociate_pages;
 
+extern atomic_t fscache_n_cache_no_space_reject;
+extern atomic_t fscache_n_cache_stale_objects;
+extern atomic_t fscache_n_cache_retired_objects;
+extern atomic_t fscache_n_cache_culled_objects;
+
 static inline void fscache_stat(atomic_t *stat)
 {
 	atomic_inc(stat);
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index da032da..9e792e3 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -328,6 +328,17 @@
 EXPORT_SYMBOL(fscache_object_init);
 
 /*
+ * Mark the object as no longer being live, making sure that we synchronise
+ * against op submission.
+ */
+static inline void fscache_mark_object_dead(struct fscache_object *object)
+{
+	spin_lock(&object->lock);
+	clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags);
+	spin_unlock(&object->lock);
+}
+
+/*
  * Abort object initialisation before we start it.
  */
 static const struct fscache_state *fscache_abort_initialisation(struct fscache_object *object,
@@ -610,6 +621,8 @@
 	object->cache->ops->lookup_complete(object);
 	fscache_stat_d(&fscache_n_cop_lookup_complete);
 
+	set_bit(FSCACHE_OBJECT_KILLED_BY_CACHE, &object->flags);
+
 	cookie = object->cookie;
 	set_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags);
 	if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags))
@@ -629,7 +642,7 @@
 	_enter("{OBJ%x,%d,%d},%d",
 	       object->debug_id, object->n_ops, object->n_children, event);
 
-	clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags);
+	fscache_mark_object_dead(object);
 	object->oob_event_mask = 0;
 
 	if (list_empty(&object->dependents) &&
@@ -948,7 +961,8 @@
 	if (!op)
 		goto nomem;
 
-	fscache_operation_init(op, object->cache->ops->invalidate_object, NULL);
+	fscache_operation_init(op, object->cache->ops->invalidate_object,
+			       NULL, NULL);
 	op->flags = FSCACHE_OP_ASYNC |
 		(1 << FSCACHE_OP_EXCLUSIVE) |
 		(1 << FSCACHE_OP_UNUSE_COOKIE);
@@ -974,13 +988,13 @@
 	return transit_to(UPDATE_OBJECT);
 
 nomem:
-	clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags);
+	fscache_mark_object_dead(object);
 	fscache_unuse_cookie(object);
 	_leave(" [ENOMEM]");
 	return transit_to(KILL_OBJECT);
 
 submit_op_failed:
-	clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags);
+	fscache_mark_object_dead(object);
 	spin_unlock(&cookie->lock);
 	fscache_unuse_cookie(object);
 	kfree(op);
@@ -1016,3 +1030,50 @@
 	_leave("");
 	return transit_to(WAIT_FOR_CMD);
 }
+
+/**
+ * fscache_object_retrying_stale - Note retrying stale object
+ * @object: The object that will be retried
+ *
+ * Note that an object lookup found an on-disk object that was adjudged to be
+ * stale and has been deleted.  The lookup will be retried.
+ */
+void fscache_object_retrying_stale(struct fscache_object *object)
+{
+	fscache_stat(&fscache_n_cache_no_space_reject);
+}
+EXPORT_SYMBOL(fscache_object_retrying_stale);
+
+/**
+ * fscache_object_mark_killed - Note that an object was killed
+ * @object: The object that was culled
+ * @why: The reason the object was killed.
+ *
+ * Note that an object was killed.  Returns true if the object was
+ * already marked killed, false if it wasn't.
+ */
+void fscache_object_mark_killed(struct fscache_object *object,
+				enum fscache_why_object_killed why)
+{
+	if (test_and_set_bit(FSCACHE_OBJECT_KILLED_BY_CACHE, &object->flags)) {
+		pr_err("Error: Object already killed by cache [%s]\n",
+		       object->cache->identifier);
+		return;
+	}
+
+	switch (why) {
+	case FSCACHE_OBJECT_NO_SPACE:
+		fscache_stat(&fscache_n_cache_no_space_reject);
+		break;
+	case FSCACHE_OBJECT_IS_STALE:
+		fscache_stat(&fscache_n_cache_stale_objects);
+		break;
+	case FSCACHE_OBJECT_WAS_RETIRED:
+		fscache_stat(&fscache_n_cache_retired_objects);
+		break;
+	case FSCACHE_OBJECT_WAS_CULLED:
+		fscache_stat(&fscache_n_cache_culled_objects);
+		break;
+	}
+}
+EXPORT_SYMBOL(fscache_object_mark_killed);
diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c
index e7b87a0..de67745 100644
--- a/fs/fscache/operation.c
+++ b/fs/fscache/operation.c
@@ -20,6 +20,35 @@
 atomic_t fscache_op_debug_id;
 EXPORT_SYMBOL(fscache_op_debug_id);
 
+static void fscache_operation_dummy_cancel(struct fscache_operation *op)
+{
+}
+
+/**
+ * fscache_operation_init - Do basic initialisation of an operation
+ * @op: The operation to initialise
+ * @release: The release function to assign
+ *
+ * Do basic initialisation of an operation.  The caller must still set flags,
+ * object and processor if needed.
+ */
+void fscache_operation_init(struct fscache_operation *op,
+			    fscache_operation_processor_t processor,
+			    fscache_operation_cancel_t cancel,
+			    fscache_operation_release_t release)
+{
+	INIT_WORK(&op->work, fscache_op_work_func);
+	atomic_set(&op->usage, 1);
+	op->state = FSCACHE_OP_ST_INITIALISED;
+	op->debug_id = atomic_inc_return(&fscache_op_debug_id);
+	op->processor = processor;
+	op->cancel = cancel ?: fscache_operation_dummy_cancel;
+	op->release = release;
+	INIT_LIST_HEAD(&op->pend_link);
+	fscache_stat(&fscache_n_op_initialised);
+}
+EXPORT_SYMBOL(fscache_operation_init);
+
 /**
  * fscache_enqueue_operation - Enqueue an operation for processing
  * @op: The operation to enqueue
@@ -76,69 +105,6 @@
 }
 
 /*
- * submit an exclusive operation for an object
- * - other ops are excluded from running simultaneously with this one
- * - this gets any extra refs it needs on an op
- */
-int fscache_submit_exclusive_op(struct fscache_object *object,
-				struct fscache_operation *op)
-{
-	int ret;
-
-	_enter("{OBJ%x OP%x},", object->debug_id, op->debug_id);
-
-	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_INITIALISED);
-	ASSERTCMP(atomic_read(&op->usage), >, 0);
-
-	spin_lock(&object->lock);
-	ASSERTCMP(object->n_ops, >=, object->n_in_progress);
-	ASSERTCMP(object->n_ops, >=, object->n_exclusive);
-	ASSERT(list_empty(&op->pend_link));
-
-	op->state = FSCACHE_OP_ST_PENDING;
-	if (fscache_object_is_active(object)) {
-		op->object = object;
-		object->n_ops++;
-		object->n_exclusive++;	/* reads and writes must wait */
-
-		if (object->n_in_progress > 0) {
-			atomic_inc(&op->usage);
-			list_add_tail(&op->pend_link, &object->pending_ops);
-			fscache_stat(&fscache_n_op_pend);
-		} else if (!list_empty(&object->pending_ops)) {
-			atomic_inc(&op->usage);
-			list_add_tail(&op->pend_link, &object->pending_ops);
-			fscache_stat(&fscache_n_op_pend);
-			fscache_start_operations(object);
-		} else {
-			ASSERTCMP(object->n_in_progress, ==, 0);
-			fscache_run_op(object, op);
-		}
-
-		/* need to issue a new write op after this */
-		clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
-		ret = 0;
-	} else if (test_bit(FSCACHE_OBJECT_IS_LOOKED_UP, &object->flags)) {
-		op->object = object;
-		object->n_ops++;
-		object->n_exclusive++;	/* reads and writes must wait */
-		atomic_inc(&op->usage);
-		list_add_tail(&op->pend_link, &object->pending_ops);
-		fscache_stat(&fscache_n_op_pend);
-		ret = 0;
-	} else {
-		/* If we're in any other state, there must have been an I/O
-		 * error of some nature.
-		 */
-		ASSERT(test_bit(FSCACHE_IOERROR, &object->cache->flags));
-		ret = -EIO;
-	}
-
-	spin_unlock(&object->lock);
-	return ret;
-}
-
-/*
  * report an unexpected submission
  */
 static void fscache_report_unexpected_submission(struct fscache_object *object,
@@ -176,6 +142,87 @@
 }
 
 /*
+ * submit an exclusive operation for an object
+ * - other ops are excluded from running simultaneously with this one
+ * - this gets any extra refs it needs on an op
+ */
+int fscache_submit_exclusive_op(struct fscache_object *object,
+				struct fscache_operation *op)
+{
+	const struct fscache_state *ostate;
+	unsigned long flags;
+	int ret;
+
+	_enter("{OBJ%x OP%x},", object->debug_id, op->debug_id);
+
+	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_INITIALISED);
+	ASSERTCMP(atomic_read(&op->usage), >, 0);
+
+	spin_lock(&object->lock);
+	ASSERTCMP(object->n_ops, >=, object->n_in_progress);
+	ASSERTCMP(object->n_ops, >=, object->n_exclusive);
+	ASSERT(list_empty(&op->pend_link));
+
+	ostate = object->state;
+	smp_rmb();
+
+	op->state = FSCACHE_OP_ST_PENDING;
+	flags = READ_ONCE(object->flags);
+	if (unlikely(!(flags & BIT(FSCACHE_OBJECT_IS_LIVE)))) {
+		fscache_stat(&fscache_n_op_rejected);
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		ret = -ENOBUFS;
+	} else if (unlikely(fscache_cache_is_broken(object))) {
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		ret = -EIO;
+	} else if (flags & BIT(FSCACHE_OBJECT_IS_AVAILABLE)) {
+		op->object = object;
+		object->n_ops++;
+		object->n_exclusive++;	/* reads and writes must wait */
+
+		if (object->n_in_progress > 0) {
+			atomic_inc(&op->usage);
+			list_add_tail(&op->pend_link, &object->pending_ops);
+			fscache_stat(&fscache_n_op_pend);
+		} else if (!list_empty(&object->pending_ops)) {
+			atomic_inc(&op->usage);
+			list_add_tail(&op->pend_link, &object->pending_ops);
+			fscache_stat(&fscache_n_op_pend);
+			fscache_start_operations(object);
+		} else {
+			ASSERTCMP(object->n_in_progress, ==, 0);
+			fscache_run_op(object, op);
+		}
+
+		/* need to issue a new write op after this */
+		clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
+		ret = 0;
+	} else if (flags & BIT(FSCACHE_OBJECT_IS_LOOKED_UP)) {
+		op->object = object;
+		object->n_ops++;
+		object->n_exclusive++;	/* reads and writes must wait */
+		atomic_inc(&op->usage);
+		list_add_tail(&op->pend_link, &object->pending_ops);
+		fscache_stat(&fscache_n_op_pend);
+		ret = 0;
+	} else if (flags & BIT(FSCACHE_OBJECT_KILLED_BY_CACHE)) {
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		ret = -ENOBUFS;
+	} else {
+		fscache_report_unexpected_submission(object, op, ostate);
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		ret = -ENOBUFS;
+	}
+
+	spin_unlock(&object->lock);
+	return ret;
+}
+
+/*
  * submit an operation for an object
  * - objects may be submitted only in the following states:
  *   - during object creation (write ops may be submitted)
@@ -187,6 +234,7 @@
 		      struct fscache_operation *op)
 {
 	const struct fscache_state *ostate;
+	unsigned long flags;
 	int ret;
 
 	_enter("{OBJ%x OP%x},{%u}",
@@ -204,7 +252,17 @@
 	smp_rmb();
 
 	op->state = FSCACHE_OP_ST_PENDING;
-	if (fscache_object_is_active(object)) {
+	flags = READ_ONCE(object->flags);
+	if (unlikely(!(flags & BIT(FSCACHE_OBJECT_IS_LIVE)))) {
+		fscache_stat(&fscache_n_op_rejected);
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		ret = -ENOBUFS;
+	} else if (unlikely(fscache_cache_is_broken(object))) {
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		ret = -EIO;
+	} else if (flags & BIT(FSCACHE_OBJECT_IS_AVAILABLE)) {
 		op->object = object;
 		object->n_ops++;
 
@@ -222,23 +280,21 @@
 			fscache_run_op(object, op);
 		}
 		ret = 0;
-	} else if (test_bit(FSCACHE_OBJECT_IS_LOOKED_UP, &object->flags)) {
+	} else if (flags & BIT(FSCACHE_OBJECT_IS_LOOKED_UP)) {
 		op->object = object;
 		object->n_ops++;
 		atomic_inc(&op->usage);
 		list_add_tail(&op->pend_link, &object->pending_ops);
 		fscache_stat(&fscache_n_op_pend);
 		ret = 0;
-	} else if (fscache_object_is_dying(object)) {
-		fscache_stat(&fscache_n_op_rejected);
-		op->state = FSCACHE_OP_ST_CANCELLED;
-		ret = -ENOBUFS;
-	} else if (!test_bit(FSCACHE_IOERROR, &object->cache->flags)) {
-		fscache_report_unexpected_submission(object, op, ostate);
-		ASSERT(!fscache_object_is_active(object));
+	} else if (flags & BIT(FSCACHE_OBJECT_KILLED_BY_CACHE)) {
+		op->cancel(op);
 		op->state = FSCACHE_OP_ST_CANCELLED;
 		ret = -ENOBUFS;
 	} else {
+		fscache_report_unexpected_submission(object, op, ostate);
+		ASSERT(!fscache_object_is_active(object));
+		op->cancel(op);
 		op->state = FSCACHE_OP_ST_CANCELLED;
 		ret = -ENOBUFS;
 	}
@@ -293,9 +349,10 @@
  * cancel an operation that's pending on an object
  */
 int fscache_cancel_op(struct fscache_operation *op,
-		      void (*do_cancel)(struct fscache_operation *))
+		      bool cancel_in_progress_op)
 {
 	struct fscache_object *object = op->object;
+	bool put = false;
 	int ret;
 
 	_enter("OBJ%x OP%x}", op->object->debug_id, op->debug_id);
@@ -309,19 +366,37 @@
 	ret = -EBUSY;
 	if (op->state == FSCACHE_OP_ST_PENDING) {
 		ASSERT(!list_empty(&op->pend_link));
-		fscache_stat(&fscache_n_op_cancelled);
 		list_del_init(&op->pend_link);
-		if (do_cancel)
-			do_cancel(op);
+		put = true;
+
+		fscache_stat(&fscache_n_op_cancelled);
+		op->cancel(op);
 		op->state = FSCACHE_OP_ST_CANCELLED;
 		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
 			object->n_exclusive--;
 		if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
 			wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
-		fscache_put_operation(op);
+		ret = 0;
+	} else if (op->state == FSCACHE_OP_ST_IN_PROGRESS && cancel_in_progress_op) {
+		ASSERTCMP(object->n_in_progress, >, 0);
+		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
+			object->n_exclusive--;
+		object->n_in_progress--;
+		if (object->n_in_progress == 0)
+			fscache_start_operations(object);
+
+		fscache_stat(&fscache_n_op_cancelled);
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
+			object->n_exclusive--;
+		if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
+			wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
 		ret = 0;
 	}
 
+	if (put)
+		fscache_put_operation(op);
 	spin_unlock(&object->lock);
 	_leave(" = %d", ret);
 	return ret;
@@ -345,6 +420,7 @@
 		list_del_init(&op->pend_link);
 
 		ASSERTCMP(op->state, ==, FSCACHE_OP_ST_PENDING);
+		op->cancel(op);
 		op->state = FSCACHE_OP_ST_CANCELLED;
 
 		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
@@ -377,8 +453,12 @@
 
 	spin_lock(&object->lock);
 
-	op->state = cancelled ?
-		FSCACHE_OP_ST_CANCELLED : FSCACHE_OP_ST_COMPLETE;
+	if (!cancelled) {
+		op->state = FSCACHE_OP_ST_COMPLETE;
+	} else {
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+	}
 
 	if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
 		object->n_exclusive--;
@@ -409,9 +489,9 @@
 		return;
 
 	_debug("PUT OP");
-	ASSERTIFCMP(op->state != FSCACHE_OP_ST_COMPLETE,
+	ASSERTIFCMP(op->state != FSCACHE_OP_ST_INITIALISED &&
+		    op->state != FSCACHE_OP_ST_COMPLETE,
 		    op->state, ==, FSCACHE_OP_ST_CANCELLED);
-	op->state = FSCACHE_OP_ST_DEAD;
 
 	fscache_stat(&fscache_n_op_release);
 
@@ -419,37 +499,39 @@
 		op->release(op);
 		op->release = NULL;
 	}
+	op->state = FSCACHE_OP_ST_DEAD;
 
 	object = op->object;
+	if (likely(object)) {
+		if (test_bit(FSCACHE_OP_DEC_READ_CNT, &op->flags))
+			atomic_dec(&object->n_reads);
+		if (test_bit(FSCACHE_OP_UNUSE_COOKIE, &op->flags))
+			fscache_unuse_cookie(object);
 
-	if (test_bit(FSCACHE_OP_DEC_READ_CNT, &op->flags))
-		atomic_dec(&object->n_reads);
-	if (test_bit(FSCACHE_OP_UNUSE_COOKIE, &op->flags))
-		fscache_unuse_cookie(object);
+		/* now... we may get called with the object spinlock held, so we
+		 * complete the cleanup here only if we can immediately acquire the
+		 * lock, and defer it otherwise */
+		if (!spin_trylock(&object->lock)) {
+			_debug("defer put");
+			fscache_stat(&fscache_n_op_deferred_release);
 
-	/* now... we may get called with the object spinlock held, so we
-	 * complete the cleanup here only if we can immediately acquire the
-	 * lock, and defer it otherwise */
-	if (!spin_trylock(&object->lock)) {
-		_debug("defer put");
-		fscache_stat(&fscache_n_op_deferred_release);
+			cache = object->cache;
+			spin_lock(&cache->op_gc_list_lock);
+			list_add_tail(&op->pend_link, &cache->op_gc_list);
+			spin_unlock(&cache->op_gc_list_lock);
+			schedule_work(&cache->op_gc);
+			_leave(" [defer]");
+			return;
+		}
 
-		cache = object->cache;
-		spin_lock(&cache->op_gc_list_lock);
-		list_add_tail(&op->pend_link, &cache->op_gc_list);
-		spin_unlock(&cache->op_gc_list_lock);
-		schedule_work(&cache->op_gc);
-		_leave(" [defer]");
-		return;
+		ASSERTCMP(object->n_ops, >, 0);
+		object->n_ops--;
+		if (object->n_ops == 0)
+			fscache_raise_event(object, FSCACHE_OBJECT_EV_CLEARED);
+
+		spin_unlock(&object->lock);
 	}
 
-	ASSERTCMP(object->n_ops, >, 0);
-	object->n_ops--;
-	if (object->n_ops == 0)
-		fscache_raise_event(object, FSCACHE_OBJECT_EV_CLEARED);
-
-	spin_unlock(&object->lock);
-
 	kfree(op);
 	_leave(" [done]");
 }
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index de33b3f..483bbc6 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -213,7 +213,7 @@
 		return -ENOMEM;
 	}
 
-	fscache_operation_init(op, fscache_attr_changed_op, NULL);
+	fscache_operation_init(op, fscache_attr_changed_op, NULL, NULL);
 	op->flags = FSCACHE_OP_ASYNC |
 		(1 << FSCACHE_OP_EXCLUSIVE) |
 		(1 << FSCACHE_OP_UNUSE_COOKIE);
@@ -239,7 +239,7 @@
 	wake_cookie = __fscache_unuse_cookie(cookie);
 nobufs:
 	spin_unlock(&cookie->lock);
-	kfree(op);
+	fscache_put_operation(op);
 	if (wake_cookie)
 		__fscache_wake_unused_cookie(cookie);
 	fscache_stat(&fscache_n_attr_changed_nobufs);
@@ -249,6 +249,17 @@
 EXPORT_SYMBOL(__fscache_attr_changed);
 
 /*
+ * Handle cancellation of a pending retrieval op
+ */
+static void fscache_do_cancel_retrieval(struct fscache_operation *_op)
+{
+	struct fscache_retrieval *op =
+		container_of(_op, struct fscache_retrieval, op);
+
+	atomic_set(&op->n_pages, 0);
+}
+
+/*
  * release a retrieval op reference
  */
 static void fscache_release_retrieval_op(struct fscache_operation *_op)
@@ -258,11 +269,12 @@
 
 	_enter("{OP%x}", op->op.debug_id);
 
-	ASSERTCMP(atomic_read(&op->n_pages), ==, 0);
+	ASSERTIFCMP(op->op.state != FSCACHE_OP_ST_INITIALISED,
+		    atomic_read(&op->n_pages), ==, 0);
 
 	fscache_hist(fscache_retrieval_histogram, op->start_time);
 	if (op->context)
-		fscache_put_context(op->op.object->cookie, op->context);
+		fscache_put_context(op->cookie, op->context);
 
 	_leave("");
 }
@@ -285,15 +297,24 @@
 		return NULL;
 	}
 
-	fscache_operation_init(&op->op, NULL, fscache_release_retrieval_op);
+	fscache_operation_init(&op->op, NULL,
+			       fscache_do_cancel_retrieval,
+			       fscache_release_retrieval_op);
 	op->op.flags	= FSCACHE_OP_MYTHREAD |
 		(1UL << FSCACHE_OP_WAITING) |
 		(1UL << FSCACHE_OP_UNUSE_COOKIE);
+	op->cookie	= cookie;
 	op->mapping	= mapping;
 	op->end_io_func	= end_io_func;
 	op->context	= context;
 	op->start_time	= jiffies;
 	INIT_LIST_HEAD(&op->to_do);
+
+	/* Pin the netfs read context in case we need to do the actual netfs
+	 * read because we've encountered a cache read failure.
+	 */
+	if (context)
+		fscache_get_context(op->cookie, context);
 	return op;
 }
 
@@ -330,24 +351,12 @@
 }
 
 /*
- * Handle cancellation of a pending retrieval op
- */
-static void fscache_do_cancel_retrieval(struct fscache_operation *_op)
-{
-	struct fscache_retrieval *op =
-		container_of(_op, struct fscache_retrieval, op);
-
-	atomic_set(&op->n_pages, 0);
-}
-
-/*
  * wait for an object to become active (or dead)
  */
 int fscache_wait_for_operation_activation(struct fscache_object *object,
 					  struct fscache_operation *op,
 					  atomic_t *stat_op_waits,
-					  atomic_t *stat_object_dead,
-					  void (*do_cancel)(struct fscache_operation *))
+					  atomic_t *stat_object_dead)
 {
 	int ret;
 
@@ -359,7 +368,7 @@
 		fscache_stat(stat_op_waits);
 	if (wait_on_bit(&op->flags, FSCACHE_OP_WAITING,
 			TASK_INTERRUPTIBLE) != 0) {
-		ret = fscache_cancel_op(op, do_cancel);
+		ret = fscache_cancel_op(op, false);
 		if (ret == 0)
 			return -ERESTARTSYS;
 
@@ -377,11 +386,13 @@
 		_leave(" = -ENOBUFS [cancelled]");
 		return -ENOBUFS;
 	}
-	if (unlikely(fscache_object_is_dead(object))) {
-		pr_err("%s() = -ENOBUFS [obj dead %d]\n", __func__, op->state);
-		fscache_cancel_op(op, do_cancel);
+	if (unlikely(fscache_object_is_dying(object) ||
+		     fscache_cache_is_broken(object))) {
+		enum fscache_operation_state state = op->state;
+		fscache_cancel_op(op, true);
 		if (stat_object_dead)
 			fscache_stat(stat_object_dead);
+		_leave(" = -ENOBUFS [obj dead %d]", state);
 		return -ENOBUFS;
 	}
 	return 0;
@@ -453,17 +464,12 @@
 
 	fscache_stat(&fscache_n_retrieval_ops);
 
-	/* pin the netfs read context in case we need to do the actual netfs
-	 * read because we've encountered a cache read failure */
-	fscache_get_context(object->cookie, op->context);
-
 	/* we wait for the operation to become active, and then process it
 	 * *here*, in this thread, and not in the thread pool */
 	ret = fscache_wait_for_operation_activation(
 		object, &op->op,
 		__fscache_stat(&fscache_n_retrieval_op_waits),
-		__fscache_stat(&fscache_n_retrievals_object_dead),
-		fscache_do_cancel_retrieval);
+		__fscache_stat(&fscache_n_retrievals_object_dead));
 	if (ret < 0)
 		goto error;
 
@@ -503,7 +509,7 @@
 	spin_unlock(&cookie->lock);
 	if (wake_cookie)
 		__fscache_wake_unused_cookie(cookie);
-	kfree(op);
+	fscache_put_retrieval(op);
 nobufs:
 	fscache_stat(&fscache_n_retrievals_nobufs);
 	_leave(" = -ENOBUFS");
@@ -584,17 +590,12 @@
 
 	fscache_stat(&fscache_n_retrieval_ops);
 
-	/* pin the netfs read context in case we need to do the actual netfs
-	 * read because we've encountered a cache read failure */
-	fscache_get_context(object->cookie, op->context);
-
 	/* we wait for the operation to become active, and then process it
 	 * *here*, in this thread, and not in the thread pool */
 	ret = fscache_wait_for_operation_activation(
 		object, &op->op,
 		__fscache_stat(&fscache_n_retrieval_op_waits),
-		__fscache_stat(&fscache_n_retrievals_object_dead),
-		fscache_do_cancel_retrieval);
+		__fscache_stat(&fscache_n_retrievals_object_dead));
 	if (ret < 0)
 		goto error;
 
@@ -632,7 +633,7 @@
 	wake_cookie = __fscache_unuse_cookie(cookie);
 nobufs_unlock:
 	spin_unlock(&cookie->lock);
-	kfree(op);
+	fscache_put_retrieval(op);
 	if (wake_cookie)
 		__fscache_wake_unused_cookie(cookie);
 nobufs:
@@ -700,8 +701,7 @@
 	ret = fscache_wait_for_operation_activation(
 		object, &op->op,
 		__fscache_stat(&fscache_n_alloc_op_waits),
-		__fscache_stat(&fscache_n_allocs_object_dead),
-		fscache_do_cancel_retrieval);
+		__fscache_stat(&fscache_n_allocs_object_dead));
 	if (ret < 0)
 		goto error;
 
@@ -726,7 +726,7 @@
 	wake_cookie = __fscache_unuse_cookie(cookie);
 nobufs_unlock:
 	spin_unlock(&cookie->lock);
-	kfree(op);
+	fscache_put_retrieval(op);
 	if (wake_cookie)
 		__fscache_wake_unused_cookie(cookie);
 nobufs:
@@ -944,7 +944,7 @@
 	if (!op)
 		goto nomem;
 
-	fscache_operation_init(&op->op, fscache_write_op,
+	fscache_operation_init(&op->op, fscache_write_op, NULL,
 			       fscache_release_write_op);
 	op->op.flags = FSCACHE_OP_ASYNC |
 		(1 << FSCACHE_OP_WAITING) |
@@ -1016,7 +1016,7 @@
 	spin_unlock(&object->lock);
 	spin_unlock(&cookie->lock);
 	radix_tree_preload_end();
-	kfree(op);
+	fscache_put_operation(&op->op);
 	fscache_stat(&fscache_n_stores_ok);
 	_leave(" = 0");
 	return 0;
@@ -1036,7 +1036,7 @@
 nobufs:
 	spin_unlock(&cookie->lock);
 	radix_tree_preload_end();
-	kfree(op);
+	fscache_put_operation(&op->op);
 	if (wake_cookie)
 		__fscache_wake_unused_cookie(cookie);
 	fscache_stat(&fscache_n_stores_nobufs);
@@ -1044,7 +1044,7 @@
 	return -ENOBUFS;
 
 nomem_free:
-	kfree(op);
+	fscache_put_operation(&op->op);
 nomem:
 	fscache_stat(&fscache_n_stores_oom);
 	_leave(" = -ENOMEM");
diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c
index 40d13c7..7cfa0aa 100644
--- a/fs/fscache/stats.c
+++ b/fs/fscache/stats.c
@@ -23,6 +23,7 @@
 atomic_t fscache_n_op_enqueue;
 atomic_t fscache_n_op_requeue;
 atomic_t fscache_n_op_deferred_release;
+atomic_t fscache_n_op_initialised;
 atomic_t fscache_n_op_release;
 atomic_t fscache_n_op_gc;
 atomic_t fscache_n_op_cancelled;
@@ -130,6 +131,11 @@
 atomic_t fscache_n_cop_uncache_page;
 atomic_t fscache_n_cop_dissociate_pages;
 
+atomic_t fscache_n_cache_no_space_reject;
+atomic_t fscache_n_cache_stale_objects;
+atomic_t fscache_n_cache_retired_objects;
+atomic_t fscache_n_cache_culled_objects;
+
 /*
  * display the general statistics
  */
@@ -246,7 +252,8 @@
 		   atomic_read(&fscache_n_op_enqueue),
 		   atomic_read(&fscache_n_op_cancelled),
 		   atomic_read(&fscache_n_op_rejected));
-	seq_printf(m, "Ops    : dfr=%u rel=%u gc=%u\n",
+	seq_printf(m, "Ops    : ini=%u dfr=%u rel=%u gc=%u\n",
+		   atomic_read(&fscache_n_op_initialised),
 		   atomic_read(&fscache_n_op_deferred_release),
 		   atomic_read(&fscache_n_op_release),
 		   atomic_read(&fscache_n_op_gc));
@@ -271,6 +278,11 @@
 		   atomic_read(&fscache_n_cop_write_page),
 		   atomic_read(&fscache_n_cop_uncache_page),
 		   atomic_read(&fscache_n_cop_dissociate_pages));
+	seq_printf(m, "CacheEv: nsp=%d stl=%d rtr=%d cul=%d\n",
+		   atomic_read(&fscache_n_cache_no_space_reject),
+		   atomic_read(&fscache_n_cache_stale_objects),
+		   atomic_read(&fscache_n_cache_retired_objects),
+		   atomic_read(&fscache_n_cache_culled_objects));
 	return 0;
 }
 
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index e5bbf74..eae2c11 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -489,6 +489,7 @@
  */
 static int cuse_channel_open(struct inode *inode, struct file *file)
 {
+	struct fuse_dev *fud;
 	struct cuse_conn *cc;
 	int rc;
 
@@ -499,17 +500,22 @@
 
 	fuse_conn_init(&cc->fc);
 
+	fud = fuse_dev_alloc(&cc->fc);
+	if (!fud) {
+		kfree(cc);
+		return -ENOMEM;
+	}
+
 	INIT_LIST_HEAD(&cc->list);
 	cc->fc.release = cuse_fc_release;
 
-	cc->fc.connected = 1;
 	cc->fc.initialized = 1;
 	rc = cuse_send_init(cc);
 	if (rc) {
-		fuse_conn_put(&cc->fc);
+		fuse_dev_free(fud);
 		return rc;
 	}
-	file->private_data = &cc->fc;	/* channel owns base reference to cc */
+	file->private_data = fud;
 
 	return 0;
 }
@@ -527,7 +533,8 @@
  */
 static int cuse_channel_release(struct inode *inode, struct file *file)
 {
-	struct cuse_conn *cc = fc_to_cc(file->private_data);
+	struct fuse_dev *fud = file->private_data;
+	struct cuse_conn *cc = fc_to_cc(fud->fc);
 	int rc;
 
 	/* remove from the conntbl, no more access from this point on */
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index c8b68ab..80cc1b3 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -25,13 +25,13 @@
 
 static struct kmem_cache *fuse_req_cachep;
 
-static struct fuse_conn *fuse_get_conn(struct file *file)
+static struct fuse_dev *fuse_get_dev(struct file *file)
 {
 	/*
 	 * Lockless access is OK, because file->private data is set
 	 * once during mount and is valid until the file is released.
 	 */
-	return file->private_data;
+	return ACCESS_ONCE(file->private_data);
 }
 
 static void fuse_request_init(struct fuse_req *req, struct page **pages,
@@ -48,6 +48,7 @@
 	req->pages = pages;
 	req->page_descs = page_descs;
 	req->max_pages = npages;
+	__set_bit(FR_PENDING, &req->flags);
 }
 
 static struct fuse_req *__fuse_request_alloc(unsigned npages, gfp_t flags)
@@ -168,6 +169,10 @@
 	if (!fc->connected)
 		goto out;
 
+	err = -ECONNREFUSED;
+	if (fc->conn_error)
+		goto out;
+
 	req = fuse_request_alloc(npages);
 	err = -ENOMEM;
 	if (!req) {
@@ -177,8 +182,10 @@
 	}
 
 	fuse_req_init_context(req);
-	req->waiting = 1;
-	req->background = for_background;
+	__set_bit(FR_WAITING, &req->flags);
+	if (for_background)
+		__set_bit(FR_BACKGROUND, &req->flags);
+
 	return req;
 
  out:
@@ -268,15 +275,15 @@
 		req = get_reserved_req(fc, file);
 
 	fuse_req_init_context(req);
-	req->waiting = 1;
-	req->background = 0;
+	__set_bit(FR_WAITING, &req->flags);
+	__clear_bit(FR_BACKGROUND, &req->flags);
 	return req;
 }
 
 void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req)
 {
 	if (atomic_dec_and_test(&req->count)) {
-		if (unlikely(req->background)) {
+		if (test_bit(FR_BACKGROUND, &req->flags)) {
 			/*
 			 * We get here in the unlikely case that a background
 			 * request was allocated but not sent
@@ -287,8 +294,10 @@
 			spin_unlock(&fc->lock);
 		}
 
-		if (req->waiting)
+		if (test_bit(FR_WAITING, &req->flags)) {
+			__clear_bit(FR_WAITING, &req->flags);
 			atomic_dec(&fc->num_waiting);
+		}
 
 		if (req->stolen_file)
 			put_reserved_req(fc, req);
@@ -309,46 +318,38 @@
 	return nbytes;
 }
 
-static u64 fuse_get_unique(struct fuse_conn *fc)
+static u64 fuse_get_unique(struct fuse_iqueue *fiq)
 {
-	fc->reqctr++;
-	/* zero is special */
-	if (fc->reqctr == 0)
-		fc->reqctr = 1;
-
-	return fc->reqctr;
+	return ++fiq->reqctr;
 }
 
-static void queue_request(struct fuse_conn *fc, struct fuse_req *req)
+static void queue_request(struct fuse_iqueue *fiq, struct fuse_req *req)
 {
 	req->in.h.len = sizeof(struct fuse_in_header) +
 		len_args(req->in.numargs, (struct fuse_arg *) req->in.args);
-	list_add_tail(&req->list, &fc->pending);
-	req->state = FUSE_REQ_PENDING;
-	if (!req->waiting) {
-		req->waiting = 1;
-		atomic_inc(&fc->num_waiting);
-	}
-	wake_up(&fc->waitq);
-	kill_fasync(&fc->fasync, SIGIO, POLL_IN);
+	list_add_tail(&req->list, &fiq->pending);
+	wake_up_locked(&fiq->waitq);
+	kill_fasync(&fiq->fasync, SIGIO, POLL_IN);
 }
 
 void fuse_queue_forget(struct fuse_conn *fc, struct fuse_forget_link *forget,
 		       u64 nodeid, u64 nlookup)
 {
+	struct fuse_iqueue *fiq = &fc->iq;
+
 	forget->forget_one.nodeid = nodeid;
 	forget->forget_one.nlookup = nlookup;
 
-	spin_lock(&fc->lock);
-	if (fc->connected) {
-		fc->forget_list_tail->next = forget;
-		fc->forget_list_tail = forget;
-		wake_up(&fc->waitq);
-		kill_fasync(&fc->fasync, SIGIO, POLL_IN);
+	spin_lock(&fiq->waitq.lock);
+	if (fiq->connected) {
+		fiq->forget_list_tail->next = forget;
+		fiq->forget_list_tail = forget;
+		wake_up_locked(&fiq->waitq);
+		kill_fasync(&fiq->fasync, SIGIO, POLL_IN);
 	} else {
 		kfree(forget);
 	}
-	spin_unlock(&fc->lock);
+	spin_unlock(&fiq->waitq.lock);
 }
 
 static void flush_bg_queue(struct fuse_conn *fc)
@@ -356,12 +357,15 @@
 	while (fc->active_background < fc->max_background &&
 	       !list_empty(&fc->bg_queue)) {
 		struct fuse_req *req;
+		struct fuse_iqueue *fiq = &fc->iq;
 
 		req = list_entry(fc->bg_queue.next, struct fuse_req, list);
 		list_del(&req->list);
 		fc->active_background++;
-		req->in.h.unique = fuse_get_unique(fc);
-		queue_request(fc, req);
+		spin_lock(&fiq->waitq.lock);
+		req->in.h.unique = fuse_get_unique(fiq);
+		queue_request(fiq, req);
+		spin_unlock(&fiq->waitq.lock);
 	}
 }
 
@@ -372,20 +376,22 @@
  * was closed.  The requester thread is woken up (if still waiting),
  * the 'end' callback is called if given, else the reference to the
  * request is released
- *
- * Called with fc->lock, unlocks it
  */
 static void request_end(struct fuse_conn *fc, struct fuse_req *req)
-__releases(fc->lock)
 {
-	void (*end) (struct fuse_conn *, struct fuse_req *) = req->end;
-	req->end = NULL;
-	list_del(&req->list);
-	list_del(&req->intr_entry);
-	req->state = FUSE_REQ_FINISHED;
-	if (req->background) {
-		req->background = 0;
+	struct fuse_iqueue *fiq = &fc->iq;
 
+	if (test_and_set_bit(FR_FINISHED, &req->flags))
+		return;
+
+	spin_lock(&fiq->waitq.lock);
+	list_del_init(&req->intr_entry);
+	spin_unlock(&fiq->waitq.lock);
+	WARN_ON(test_bit(FR_PENDING, &req->flags));
+	WARN_ON(test_bit(FR_SENT, &req->flags));
+	if (test_bit(FR_BACKGROUND, &req->flags)) {
+		spin_lock(&fc->lock);
+		clear_bit(FR_BACKGROUND, &req->flags);
 		if (fc->num_background == fc->max_background)
 			fc->blocked = 0;
 
@@ -401,122 +407,105 @@
 		fc->num_background--;
 		fc->active_background--;
 		flush_bg_queue(fc);
+		spin_unlock(&fc->lock);
 	}
-	spin_unlock(&fc->lock);
 	wake_up(&req->waitq);
-	if (end)
-		end(fc, req);
+	if (req->end)
+		req->end(fc, req);
 	fuse_put_request(fc, req);
 }
 
-static void wait_answer_interruptible(struct fuse_conn *fc,
-				      struct fuse_req *req)
-__releases(fc->lock)
-__acquires(fc->lock)
+static void queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req)
 {
-	if (signal_pending(current))
-		return;
-
-	spin_unlock(&fc->lock);
-	wait_event_interruptible(req->waitq, req->state == FUSE_REQ_FINISHED);
-	spin_lock(&fc->lock);
-}
-
-static void queue_interrupt(struct fuse_conn *fc, struct fuse_req *req)
-{
-	list_add_tail(&req->intr_entry, &fc->interrupts);
-	wake_up(&fc->waitq);
-	kill_fasync(&fc->fasync, SIGIO, POLL_IN);
+	spin_lock(&fiq->waitq.lock);
+	if (list_empty(&req->intr_entry)) {
+		list_add_tail(&req->intr_entry, &fiq->interrupts);
+		wake_up_locked(&fiq->waitq);
+	}
+	spin_unlock(&fiq->waitq.lock);
+	kill_fasync(&fiq->fasync, SIGIO, POLL_IN);
 }
 
 static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req)
-__releases(fc->lock)
-__acquires(fc->lock)
 {
+	struct fuse_iqueue *fiq = &fc->iq;
+	int err;
+
 	if (!fc->no_interrupt) {
 		/* Any signal may interrupt this */
-		wait_answer_interruptible(fc, req);
-
-		if (req->aborted)
-			goto aborted;
-		if (req->state == FUSE_REQ_FINISHED)
+		err = wait_event_interruptible(req->waitq,
+					test_bit(FR_FINISHED, &req->flags));
+		if (!err)
 			return;
 
-		req->interrupted = 1;
-		if (req->state == FUSE_REQ_SENT)
-			queue_interrupt(fc, req);
+		set_bit(FR_INTERRUPTED, &req->flags);
+		/* matches barrier in fuse_dev_do_read() */
+		smp_mb__after_atomic();
+		if (test_bit(FR_SENT, &req->flags))
+			queue_interrupt(fiq, req);
 	}
 
-	if (!req->force) {
+	if (!test_bit(FR_FORCE, &req->flags)) {
 		sigset_t oldset;
 
 		/* Only fatal signals may interrupt this */
 		block_sigs(&oldset);
-		wait_answer_interruptible(fc, req);
+		err = wait_event_interruptible(req->waitq,
+					test_bit(FR_FINISHED, &req->flags));
 		restore_sigs(&oldset);
 
-		if (req->aborted)
-			goto aborted;
-		if (req->state == FUSE_REQ_FINISHED)
+		if (!err)
 			return;
 
+		spin_lock(&fiq->waitq.lock);
 		/* Request is not yet in userspace, bail out */
-		if (req->state == FUSE_REQ_PENDING) {
+		if (test_bit(FR_PENDING, &req->flags)) {
 			list_del(&req->list);
+			spin_unlock(&fiq->waitq.lock);
 			__fuse_put_request(req);
 			req->out.h.error = -EINTR;
 			return;
 		}
+		spin_unlock(&fiq->waitq.lock);
 	}
 
 	/*
 	 * Either request is already in userspace, or it was forced.
 	 * Wait it out.
 	 */
-	spin_unlock(&fc->lock);
-	wait_event(req->waitq, req->state == FUSE_REQ_FINISHED);
-	spin_lock(&fc->lock);
-
-	if (!req->aborted)
-		return;
-
- aborted:
-	BUG_ON(req->state != FUSE_REQ_FINISHED);
-	if (req->locked) {
-		/* This is uninterruptible sleep, because data is
-		   being copied to/from the buffers of req.  During
-		   locked state, there mustn't be any filesystem
-		   operation (e.g. page fault), since that could lead
-		   to deadlock */
-		spin_unlock(&fc->lock);
-		wait_event(req->waitq, !req->locked);
-		spin_lock(&fc->lock);
-	}
+	wait_event(req->waitq, test_bit(FR_FINISHED, &req->flags));
 }
 
 static void __fuse_request_send(struct fuse_conn *fc, struct fuse_req *req)
 {
-	BUG_ON(req->background);
-	spin_lock(&fc->lock);
-	if (!fc->connected)
+	struct fuse_iqueue *fiq = &fc->iq;
+
+	BUG_ON(test_bit(FR_BACKGROUND, &req->flags));
+	spin_lock(&fiq->waitq.lock);
+	if (!fiq->connected) {
+		spin_unlock(&fiq->waitq.lock);
 		req->out.h.error = -ENOTCONN;
-	else if (fc->conn_error)
-		req->out.h.error = -ECONNREFUSED;
-	else {
-		req->in.h.unique = fuse_get_unique(fc);
-		queue_request(fc, req);
+	} else {
+		req->in.h.unique = fuse_get_unique(fiq);
+		queue_request(fiq, req);
 		/* acquire extra reference, since request is still needed
 		   after request_end() */
 		__fuse_get_request(req);
+		spin_unlock(&fiq->waitq.lock);
 
 		request_wait_answer(fc, req);
+		/* Pairs with smp_wmb() in request_end() */
+		smp_rmb();
 	}
-	spin_unlock(&fc->lock);
 }
 
 void fuse_request_send(struct fuse_conn *fc, struct fuse_req *req)
 {
-	req->isreply = 1;
+	__set_bit(FR_ISREPLY, &req->flags);
+	if (!test_bit(FR_WAITING, &req->flags)) {
+		__set_bit(FR_WAITING, &req->flags);
+		atomic_inc(&fc->num_waiting);
+	}
 	__fuse_request_send(fc, req);
 }
 EXPORT_SYMBOL_GPL(fuse_request_send);
@@ -586,10 +575,20 @@
 	return ret;
 }
 
-static void fuse_request_send_nowait_locked(struct fuse_conn *fc,
-					    struct fuse_req *req)
+/*
+ * Called under fc->lock
+ *
+ * fc->connected must have been checked previously
+ */
+void fuse_request_send_background_locked(struct fuse_conn *fc,
+					 struct fuse_req *req)
 {
-	BUG_ON(!req->background);
+	BUG_ON(!test_bit(FR_BACKGROUND, &req->flags));
+	if (!test_bit(FR_WAITING, &req->flags)) {
+		__set_bit(FR_WAITING, &req->flags);
+		atomic_inc(&fc->num_waiting);
+	}
+	__set_bit(FR_ISREPLY, &req->flags);
 	fc->num_background++;
 	if (fc->num_background == fc->max_background)
 		fc->blocked = 1;
@@ -602,22 +601,19 @@
 	flush_bg_queue(fc);
 }
 
-static void fuse_request_send_nowait(struct fuse_conn *fc, struct fuse_req *req)
-{
-	spin_lock(&fc->lock);
-	if (fc->connected) {
-		fuse_request_send_nowait_locked(fc, req);
-		spin_unlock(&fc->lock);
-	} else {
-		req->out.h.error = -ENOTCONN;
-		request_end(fc, req);
-	}
-}
-
 void fuse_request_send_background(struct fuse_conn *fc, struct fuse_req *req)
 {
-	req->isreply = 1;
-	fuse_request_send_nowait(fc, req);
+	BUG_ON(!req->end);
+	spin_lock(&fc->lock);
+	if (fc->connected) {
+		fuse_request_send_background_locked(fc, req);
+		spin_unlock(&fc->lock);
+	} else {
+		spin_unlock(&fc->lock);
+		req->out.h.error = -ENOTCONN;
+		req->end(fc, req);
+		fuse_put_request(fc, req);
+	}
 }
 EXPORT_SYMBOL_GPL(fuse_request_send_background);
 
@@ -625,31 +621,20 @@
 					  struct fuse_req *req, u64 unique)
 {
 	int err = -ENODEV;
+	struct fuse_iqueue *fiq = &fc->iq;
 
-	req->isreply = 0;
+	__clear_bit(FR_ISREPLY, &req->flags);
 	req->in.h.unique = unique;
-	spin_lock(&fc->lock);
-	if (fc->connected) {
-		queue_request(fc, req);
+	spin_lock(&fiq->waitq.lock);
+	if (fiq->connected) {
+		queue_request(fiq, req);
 		err = 0;
 	}
-	spin_unlock(&fc->lock);
+	spin_unlock(&fiq->waitq.lock);
 
 	return err;
 }
 
-/*
- * Called under fc->lock
- *
- * fc->connected must have been checked previously
- */
-void fuse_request_send_background_locked(struct fuse_conn *fc,
-					 struct fuse_req *req)
-{
-	req->isreply = 1;
-	fuse_request_send_nowait_locked(fc, req);
-}
-
 void fuse_force_forget(struct file *file, u64 nodeid)
 {
 	struct inode *inode = file_inode(file);
@@ -665,7 +650,7 @@
 	req->in.numargs = 1;
 	req->in.args[0].size = sizeof(inarg);
 	req->in.args[0].value = &inarg;
-	req->isreply = 0;
+	__clear_bit(FR_ISREPLY, &req->flags);
 	__fuse_request_send(fc, req);
 	/* ignore errors */
 	fuse_put_request(fc, req);
@@ -676,38 +661,39 @@
  * anything that could cause a page-fault.  If the request was already
  * aborted bail out.
  */
-static int lock_request(struct fuse_conn *fc, struct fuse_req *req)
+static int lock_request(struct fuse_req *req)
 {
 	int err = 0;
 	if (req) {
-		spin_lock(&fc->lock);
-		if (req->aborted)
+		spin_lock(&req->waitq.lock);
+		if (test_bit(FR_ABORTED, &req->flags))
 			err = -ENOENT;
 		else
-			req->locked = 1;
-		spin_unlock(&fc->lock);
+			set_bit(FR_LOCKED, &req->flags);
+		spin_unlock(&req->waitq.lock);
 	}
 	return err;
 }
 
 /*
- * Unlock request.  If it was aborted during being locked, the
- * requester thread is currently waiting for it to be unlocked, so
- * wake it up.
+ * Unlock request.  If it was aborted while locked, caller is responsible
+ * for unlocking and ending the request.
  */
-static void unlock_request(struct fuse_conn *fc, struct fuse_req *req)
+static int unlock_request(struct fuse_req *req)
 {
+	int err = 0;
 	if (req) {
-		spin_lock(&fc->lock);
-		req->locked = 0;
-		if (req->aborted)
-			wake_up(&req->waitq);
-		spin_unlock(&fc->lock);
+		spin_lock(&req->waitq.lock);
+		if (test_bit(FR_ABORTED, &req->flags))
+			err = -ENOENT;
+		else
+			clear_bit(FR_LOCKED, &req->flags);
+		spin_unlock(&req->waitq.lock);
 	}
+	return err;
 }
 
 struct fuse_copy_state {
-	struct fuse_conn *fc;
 	int write;
 	struct fuse_req *req;
 	struct iov_iter *iter;
@@ -721,13 +707,10 @@
 	unsigned move_pages:1;
 };
 
-static void fuse_copy_init(struct fuse_copy_state *cs,
-			   struct fuse_conn *fc,
-			   int write,
+static void fuse_copy_init(struct fuse_copy_state *cs, int write,
 			   struct iov_iter *iter)
 {
 	memset(cs, 0, sizeof(*cs));
-	cs->fc = fc;
 	cs->write = write;
 	cs->iter = iter;
 }
@@ -760,7 +743,10 @@
 	struct page *page;
 	int err;
 
-	unlock_request(cs->fc, cs->req);
+	err = unlock_request(cs->req);
+	if (err)
+		return err;
+
 	fuse_copy_finish(cs);
 	if (cs->pipebufs) {
 		struct pipe_buffer *buf = cs->pipebufs;
@@ -809,7 +795,7 @@
 		iov_iter_advance(cs->iter, err);
 	}
 
-	return lock_request(cs->fc, cs->req);
+	return lock_request(cs->req);
 }
 
 /* Do as much copy to/from userspace buffer as we can */
@@ -860,7 +846,10 @@
 	struct page *newpage;
 	struct pipe_buffer *buf = cs->pipebufs;
 
-	unlock_request(cs->fc, cs->req);
+	err = unlock_request(cs->req);
+	if (err)
+		return err;
+
 	fuse_copy_finish(cs);
 
 	err = buf->ops->confirm(cs->pipe, buf);
@@ -914,12 +903,12 @@
 		lru_cache_add_file(newpage);
 
 	err = 0;
-	spin_lock(&cs->fc->lock);
-	if (cs->req->aborted)
+	spin_lock(&cs->req->waitq.lock);
+	if (test_bit(FR_ABORTED, &cs->req->flags))
 		err = -ENOENT;
 	else
 		*pagep = newpage;
-	spin_unlock(&cs->fc->lock);
+	spin_unlock(&cs->req->waitq.lock);
 
 	if (err) {
 		unlock_page(newpage);
@@ -939,7 +928,7 @@
 	cs->pg = buf->page;
 	cs->offset = buf->offset;
 
-	err = lock_request(cs->fc, cs->req);
+	err = lock_request(cs->req);
 	if (err)
 		return err;
 
@@ -950,11 +939,15 @@
 			 unsigned offset, unsigned count)
 {
 	struct pipe_buffer *buf;
+	int err;
 
 	if (cs->nr_segs == cs->pipe->buffers)
 		return -EIO;
 
-	unlock_request(cs->fc, cs->req);
+	err = unlock_request(cs->req);
+	if (err)
+		return err;
+
 	fuse_copy_finish(cs);
 
 	buf = cs->pipebufs;
@@ -1065,36 +1058,15 @@
 	return err;
 }
 
-static int forget_pending(struct fuse_conn *fc)
+static int forget_pending(struct fuse_iqueue *fiq)
 {
-	return fc->forget_list_head.next != NULL;
+	return fiq->forget_list_head.next != NULL;
 }
 
-static int request_pending(struct fuse_conn *fc)
+static int request_pending(struct fuse_iqueue *fiq)
 {
-	return !list_empty(&fc->pending) || !list_empty(&fc->interrupts) ||
-		forget_pending(fc);
-}
-
-/* Wait until a request is available on the pending list */
-static void request_wait(struct fuse_conn *fc)
-__releases(fc->lock)
-__acquires(fc->lock)
-{
-	DECLARE_WAITQUEUE(wait, current);
-
-	add_wait_queue_exclusive(&fc->waitq, &wait);
-	while (fc->connected && !request_pending(fc)) {
-		set_current_state(TASK_INTERRUPTIBLE);
-		if (signal_pending(current))
-			break;
-
-		spin_unlock(&fc->lock);
-		schedule();
-		spin_lock(&fc->lock);
-	}
-	set_current_state(TASK_RUNNING);
-	remove_wait_queue(&fc->waitq, &wait);
+	return !list_empty(&fiq->pending) || !list_empty(&fiq->interrupts) ||
+		forget_pending(fiq);
 }
 
 /*
@@ -1103,11 +1075,12 @@
  * Unlike other requests this is assembled on demand, without a need
  * to allocate a separate fuse_req structure.
  *
- * Called with fc->lock held, releases it
+ * Called with fiq->waitq.lock held, releases it
  */
-static int fuse_read_interrupt(struct fuse_conn *fc, struct fuse_copy_state *cs,
+static int fuse_read_interrupt(struct fuse_iqueue *fiq,
+			       struct fuse_copy_state *cs,
 			       size_t nbytes, struct fuse_req *req)
-__releases(fc->lock)
+__releases(fiq->waitq.lock)
 {
 	struct fuse_in_header ih;
 	struct fuse_interrupt_in arg;
@@ -1115,7 +1088,7 @@
 	int err;
 
 	list_del_init(&req->intr_entry);
-	req->intr_unique = fuse_get_unique(fc);
+	req->intr_unique = fuse_get_unique(fiq);
 	memset(&ih, 0, sizeof(ih));
 	memset(&arg, 0, sizeof(arg));
 	ih.len = reqsize;
@@ -1123,7 +1096,7 @@
 	ih.unique = req->intr_unique;
 	arg.unique = req->in.h.unique;
 
-	spin_unlock(&fc->lock);
+	spin_unlock(&fiq->waitq.lock);
 	if (nbytes < reqsize)
 		return -EINVAL;
 
@@ -1135,21 +1108,21 @@
 	return err ? err : reqsize;
 }
 
-static struct fuse_forget_link *dequeue_forget(struct fuse_conn *fc,
+static struct fuse_forget_link *dequeue_forget(struct fuse_iqueue *fiq,
 					       unsigned max,
 					       unsigned *countp)
 {
-	struct fuse_forget_link *head = fc->forget_list_head.next;
+	struct fuse_forget_link *head = fiq->forget_list_head.next;
 	struct fuse_forget_link **newhead = &head;
 	unsigned count;
 
 	for (count = 0; *newhead != NULL && count < max; count++)
 		newhead = &(*newhead)->next;
 
-	fc->forget_list_head.next = *newhead;
+	fiq->forget_list_head.next = *newhead;
 	*newhead = NULL;
-	if (fc->forget_list_head.next == NULL)
-		fc->forget_list_tail = &fc->forget_list_head;
+	if (fiq->forget_list_head.next == NULL)
+		fiq->forget_list_tail = &fiq->forget_list_head;
 
 	if (countp != NULL)
 		*countp = count;
@@ -1157,24 +1130,24 @@
 	return head;
 }
 
-static int fuse_read_single_forget(struct fuse_conn *fc,
+static int fuse_read_single_forget(struct fuse_iqueue *fiq,
 				   struct fuse_copy_state *cs,
 				   size_t nbytes)
-__releases(fc->lock)
+__releases(fiq->waitq.lock)
 {
 	int err;
-	struct fuse_forget_link *forget = dequeue_forget(fc, 1, NULL);
+	struct fuse_forget_link *forget = dequeue_forget(fiq, 1, NULL);
 	struct fuse_forget_in arg = {
 		.nlookup = forget->forget_one.nlookup,
 	};
 	struct fuse_in_header ih = {
 		.opcode = FUSE_FORGET,
 		.nodeid = forget->forget_one.nodeid,
-		.unique = fuse_get_unique(fc),
+		.unique = fuse_get_unique(fiq),
 		.len = sizeof(ih) + sizeof(arg),
 	};
 
-	spin_unlock(&fc->lock);
+	spin_unlock(&fiq->waitq.lock);
 	kfree(forget);
 	if (nbytes < ih.len)
 		return -EINVAL;
@@ -1190,9 +1163,9 @@
 	return ih.len;
 }
 
-static int fuse_read_batch_forget(struct fuse_conn *fc,
+static int fuse_read_batch_forget(struct fuse_iqueue *fiq,
 				   struct fuse_copy_state *cs, size_t nbytes)
-__releases(fc->lock)
+__releases(fiq->waitq.lock)
 {
 	int err;
 	unsigned max_forgets;
@@ -1201,18 +1174,18 @@
 	struct fuse_batch_forget_in arg = { .count = 0 };
 	struct fuse_in_header ih = {
 		.opcode = FUSE_BATCH_FORGET,
-		.unique = fuse_get_unique(fc),
+		.unique = fuse_get_unique(fiq),
 		.len = sizeof(ih) + sizeof(arg),
 	};
 
 	if (nbytes < ih.len) {
-		spin_unlock(&fc->lock);
+		spin_unlock(&fiq->waitq.lock);
 		return -EINVAL;
 	}
 
 	max_forgets = (nbytes - ih.len) / sizeof(struct fuse_forget_one);
-	head = dequeue_forget(fc, max_forgets, &count);
-	spin_unlock(&fc->lock);
+	head = dequeue_forget(fiq, max_forgets, &count);
+	spin_unlock(&fiq->waitq.lock);
 
 	arg.count = count;
 	ih.len += count * sizeof(struct fuse_forget_one);
@@ -1239,14 +1212,15 @@
 	return ih.len;
 }
 
-static int fuse_read_forget(struct fuse_conn *fc, struct fuse_copy_state *cs,
+static int fuse_read_forget(struct fuse_conn *fc, struct fuse_iqueue *fiq,
+			    struct fuse_copy_state *cs,
 			    size_t nbytes)
-__releases(fc->lock)
+__releases(fiq->waitq.lock)
 {
-	if (fc->minor < 16 || fc->forget_list_head.next->next == NULL)
-		return fuse_read_single_forget(fc, cs, nbytes);
+	if (fc->minor < 16 || fiq->forget_list_head.next->next == NULL)
+		return fuse_read_single_forget(fiq, cs, nbytes);
 	else
-		return fuse_read_batch_forget(fc, cs, nbytes);
+		return fuse_read_batch_forget(fiq, cs, nbytes);
 }
 
 /*
@@ -1258,46 +1232,51 @@
  * request_end().  Otherwise add it to the processing list, and set
  * the 'sent' flag.
  */
-static ssize_t fuse_dev_do_read(struct fuse_conn *fc, struct file *file,
+static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file,
 				struct fuse_copy_state *cs, size_t nbytes)
 {
-	int err;
+	ssize_t err;
+	struct fuse_conn *fc = fud->fc;
+	struct fuse_iqueue *fiq = &fc->iq;
+	struct fuse_pqueue *fpq = &fud->pq;
 	struct fuse_req *req;
 	struct fuse_in *in;
 	unsigned reqsize;
 
  restart:
-	spin_lock(&fc->lock);
+	spin_lock(&fiq->waitq.lock);
 	err = -EAGAIN;
-	if ((file->f_flags & O_NONBLOCK) && fc->connected &&
-	    !request_pending(fc))
+	if ((file->f_flags & O_NONBLOCK) && fiq->connected &&
+	    !request_pending(fiq))
 		goto err_unlock;
 
-	request_wait(fc);
+	err = wait_event_interruptible_exclusive_locked(fiq->waitq,
+				!fiq->connected || request_pending(fiq));
+	if (err)
+		goto err_unlock;
+
 	err = -ENODEV;
-	if (!fc->connected)
-		goto err_unlock;
-	err = -ERESTARTSYS;
-	if (!request_pending(fc))
+	if (!fiq->connected)
 		goto err_unlock;
 
-	if (!list_empty(&fc->interrupts)) {
-		req = list_entry(fc->interrupts.next, struct fuse_req,
+	if (!list_empty(&fiq->interrupts)) {
+		req = list_entry(fiq->interrupts.next, struct fuse_req,
 				 intr_entry);
-		return fuse_read_interrupt(fc, cs, nbytes, req);
+		return fuse_read_interrupt(fiq, cs, nbytes, req);
 	}
 
-	if (forget_pending(fc)) {
-		if (list_empty(&fc->pending) || fc->forget_batch-- > 0)
-			return fuse_read_forget(fc, cs, nbytes);
+	if (forget_pending(fiq)) {
+		if (list_empty(&fiq->pending) || fiq->forget_batch-- > 0)
+			return fuse_read_forget(fc, fiq, cs, nbytes);
 
-		if (fc->forget_batch <= -8)
-			fc->forget_batch = 16;
+		if (fiq->forget_batch <= -8)
+			fiq->forget_batch = 16;
 	}
 
-	req = list_entry(fc->pending.next, struct fuse_req, list);
-	req->state = FUSE_REQ_READING;
-	list_move(&req->list, &fc->io);
+	req = list_entry(fiq->pending.next, struct fuse_req, list);
+	clear_bit(FR_PENDING, &req->flags);
+	list_del_init(&req->list);
+	spin_unlock(&fiq->waitq.lock);
 
 	in = &req->in;
 	reqsize = in->h.len;
@@ -1310,37 +1289,48 @@
 		request_end(fc, req);
 		goto restart;
 	}
-	spin_unlock(&fc->lock);
+	spin_lock(&fpq->lock);
+	list_add(&req->list, &fpq->io);
+	spin_unlock(&fpq->lock);
 	cs->req = req;
 	err = fuse_copy_one(cs, &in->h, sizeof(in->h));
 	if (!err)
 		err = fuse_copy_args(cs, in->numargs, in->argpages,
 				     (struct fuse_arg *) in->args, 0);
 	fuse_copy_finish(cs);
-	spin_lock(&fc->lock);
-	req->locked = 0;
-	if (req->aborted) {
-		request_end(fc, req);
-		return -ENODEV;
+	spin_lock(&fpq->lock);
+	clear_bit(FR_LOCKED, &req->flags);
+	if (!fpq->connected) {
+		err = -ENODEV;
+		goto out_end;
 	}
 	if (err) {
 		req->out.h.error = -EIO;
-		request_end(fc, req);
-		return err;
+		goto out_end;
 	}
-	if (!req->isreply)
-		request_end(fc, req);
-	else {
-		req->state = FUSE_REQ_SENT;
-		list_move_tail(&req->list, &fc->processing);
-		if (req->interrupted)
-			queue_interrupt(fc, req);
-		spin_unlock(&fc->lock);
+	if (!test_bit(FR_ISREPLY, &req->flags)) {
+		err = reqsize;
+		goto out_end;
 	}
+	list_move_tail(&req->list, &fpq->processing);
+	spin_unlock(&fpq->lock);
+	set_bit(FR_SENT, &req->flags);
+	/* matches barrier in request_wait_answer() */
+	smp_mb__after_atomic();
+	if (test_bit(FR_INTERRUPTED, &req->flags))
+		queue_interrupt(fiq, req);
+
 	return reqsize;
 
+out_end:
+	if (!test_bit(FR_PRIVATE, &req->flags))
+		list_del_init(&req->list);
+	spin_unlock(&fpq->lock);
+	request_end(fc, req);
+	return err;
+
  err_unlock:
-	spin_unlock(&fc->lock);
+	spin_unlock(&fiq->waitq.lock);
 	return err;
 }
 
@@ -1359,16 +1349,17 @@
 {
 	struct fuse_copy_state cs;
 	struct file *file = iocb->ki_filp;
-	struct fuse_conn *fc = fuse_get_conn(file);
-	if (!fc)
+	struct fuse_dev *fud = fuse_get_dev(file);
+
+	if (!fud)
 		return -EPERM;
 
 	if (!iter_is_iovec(to))
 		return -EINVAL;
 
-	fuse_copy_init(&cs, fc, 1, to);
+	fuse_copy_init(&cs, 1, to);
 
-	return fuse_dev_do_read(fc, file, &cs, iov_iter_count(to));
+	return fuse_dev_do_read(fud, file, &cs, iov_iter_count(to));
 }
 
 static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
@@ -1380,18 +1371,19 @@
 	int do_wakeup = 0;
 	struct pipe_buffer *bufs;
 	struct fuse_copy_state cs;
-	struct fuse_conn *fc = fuse_get_conn(in);
-	if (!fc)
+	struct fuse_dev *fud = fuse_get_dev(in);
+
+	if (!fud)
 		return -EPERM;
 
 	bufs = kmalloc(pipe->buffers * sizeof(struct pipe_buffer), GFP_KERNEL);
 	if (!bufs)
 		return -ENOMEM;
 
-	fuse_copy_init(&cs, fc, 1, NULL);
+	fuse_copy_init(&cs, 1, NULL);
 	cs.pipebufs = bufs;
 	cs.pipe = pipe;
-	ret = fuse_dev_do_read(fc, in, &cs, len);
+	ret = fuse_dev_do_read(fud, in, &cs, len);
 	if (ret < 0)
 		goto out;
 
@@ -1830,11 +1822,11 @@
 }
 
 /* Look up request on processing list by unique ID */
-static struct fuse_req *request_find(struct fuse_conn *fc, u64 unique)
+static struct fuse_req *request_find(struct fuse_pqueue *fpq, u64 unique)
 {
 	struct fuse_req *req;
 
-	list_for_each_entry(req, &fc->processing, list) {
+	list_for_each_entry(req, &fpq->processing, list) {
 		if (req->in.h.unique == unique || req->intr_unique == unique)
 			return req;
 	}
@@ -1871,10 +1863,12 @@
  * it from the list and copy the rest of the buffer to the request.
  * The request is finished by calling request_end()
  */
-static ssize_t fuse_dev_do_write(struct fuse_conn *fc,
+static ssize_t fuse_dev_do_write(struct fuse_dev *fud,
 				 struct fuse_copy_state *cs, size_t nbytes)
 {
 	int err;
+	struct fuse_conn *fc = fud->fc;
+	struct fuse_pqueue *fpq = &fud->pq;
 	struct fuse_req *req;
 	struct fuse_out_header oh;
 
@@ -1902,63 +1896,60 @@
 	if (oh.error <= -1000 || oh.error > 0)
 		goto err_finish;
 
-	spin_lock(&fc->lock);
+	spin_lock(&fpq->lock);
 	err = -ENOENT;
-	if (!fc->connected)
-		goto err_unlock;
+	if (!fpq->connected)
+		goto err_unlock_pq;
 
-	req = request_find(fc, oh.unique);
+	req = request_find(fpq, oh.unique);
 	if (!req)
-		goto err_unlock;
+		goto err_unlock_pq;
 
-	if (req->aborted) {
-		spin_unlock(&fc->lock);
-		fuse_copy_finish(cs);
-		spin_lock(&fc->lock);
-		request_end(fc, req);
-		return -ENOENT;
-	}
 	/* Is it an interrupt reply? */
 	if (req->intr_unique == oh.unique) {
+		spin_unlock(&fpq->lock);
+
 		err = -EINVAL;
 		if (nbytes != sizeof(struct fuse_out_header))
-			goto err_unlock;
+			goto err_finish;
 
 		if (oh.error == -ENOSYS)
 			fc->no_interrupt = 1;
 		else if (oh.error == -EAGAIN)
-			queue_interrupt(fc, req);
+			queue_interrupt(&fc->iq, req);
 
-		spin_unlock(&fc->lock);
 		fuse_copy_finish(cs);
 		return nbytes;
 	}
 
-	req->state = FUSE_REQ_WRITING;
-	list_move(&req->list, &fc->io);
+	clear_bit(FR_SENT, &req->flags);
+	list_move(&req->list, &fpq->io);
 	req->out.h = oh;
-	req->locked = 1;
+	set_bit(FR_LOCKED, &req->flags);
+	spin_unlock(&fpq->lock);
 	cs->req = req;
 	if (!req->out.page_replace)
 		cs->move_pages = 0;
-	spin_unlock(&fc->lock);
 
 	err = copy_out_args(cs, &req->out, nbytes);
 	fuse_copy_finish(cs);
 
-	spin_lock(&fc->lock);
-	req->locked = 0;
-	if (!err) {
-		if (req->aborted)
-			err = -ENOENT;
-	} else if (!req->aborted)
+	spin_lock(&fpq->lock);
+	clear_bit(FR_LOCKED, &req->flags);
+	if (!fpq->connected)
+		err = -ENOENT;
+	else if (err)
 		req->out.h.error = -EIO;
+	if (!test_bit(FR_PRIVATE, &req->flags))
+		list_del_init(&req->list);
+	spin_unlock(&fpq->lock);
+
 	request_end(fc, req);
 
 	return err ? err : nbytes;
 
- err_unlock:
-	spin_unlock(&fc->lock);
+ err_unlock_pq:
+	spin_unlock(&fpq->lock);
  err_finish:
 	fuse_copy_finish(cs);
 	return err;
@@ -1967,16 +1958,17 @@
 static ssize_t fuse_dev_write(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct fuse_copy_state cs;
-	struct fuse_conn *fc = fuse_get_conn(iocb->ki_filp);
-	if (!fc)
+	struct fuse_dev *fud = fuse_get_dev(iocb->ki_filp);
+
+	if (!fud)
 		return -EPERM;
 
 	if (!iter_is_iovec(from))
 		return -EINVAL;
 
-	fuse_copy_init(&cs, fc, 0, from);
+	fuse_copy_init(&cs, 0, from);
 
-	return fuse_dev_do_write(fc, &cs, iov_iter_count(from));
+	return fuse_dev_do_write(fud, &cs, iov_iter_count(from));
 }
 
 static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
@@ -1987,12 +1979,12 @@
 	unsigned idx;
 	struct pipe_buffer *bufs;
 	struct fuse_copy_state cs;
-	struct fuse_conn *fc;
+	struct fuse_dev *fud;
 	size_t rem;
 	ssize_t ret;
 
-	fc = fuse_get_conn(out);
-	if (!fc)
+	fud = fuse_get_dev(out);
+	if (!fud)
 		return -EPERM;
 
 	bufs = kmalloc(pipe->buffers * sizeof(struct pipe_buffer), GFP_KERNEL);
@@ -2039,7 +2031,7 @@
 	}
 	pipe_unlock(pipe);
 
-	fuse_copy_init(&cs, fc, 0, NULL);
+	fuse_copy_init(&cs, 0, NULL);
 	cs.pipebufs = bufs;
 	cs.nr_segs = nbuf;
 	cs.pipe = pipe;
@@ -2047,7 +2039,7 @@
 	if (flags & SPLICE_F_MOVE)
 		cs.move_pages = 1;
 
-	ret = fuse_dev_do_write(fc, &cs, len);
+	ret = fuse_dev_do_write(fud, &cs, len);
 
 	for (idx = 0; idx < nbuf; idx++) {
 		struct pipe_buffer *buf = &bufs[idx];
@@ -2061,18 +2053,21 @@
 static unsigned fuse_dev_poll(struct file *file, poll_table *wait)
 {
 	unsigned mask = POLLOUT | POLLWRNORM;
-	struct fuse_conn *fc = fuse_get_conn(file);
-	if (!fc)
+	struct fuse_iqueue *fiq;
+	struct fuse_dev *fud = fuse_get_dev(file);
+
+	if (!fud)
 		return POLLERR;
 
-	poll_wait(file, &fc->waitq, wait);
+	fiq = &fud->fc->iq;
+	poll_wait(file, &fiq->waitq, wait);
 
-	spin_lock(&fc->lock);
-	if (!fc->connected)
+	spin_lock(&fiq->waitq.lock);
+	if (!fiq->connected)
 		mask = POLLERR;
-	else if (request_pending(fc))
+	else if (request_pending(fiq))
 		mask |= POLLIN | POLLRDNORM;
-	spin_unlock(&fc->lock);
+	spin_unlock(&fiq->waitq.lock);
 
 	return mask;
 }
@@ -2083,67 +2078,18 @@
  * This function releases and reacquires fc->lock
  */
 static void end_requests(struct fuse_conn *fc, struct list_head *head)
-__releases(fc->lock)
-__acquires(fc->lock)
 {
 	while (!list_empty(head)) {
 		struct fuse_req *req;
 		req = list_entry(head->next, struct fuse_req, list);
 		req->out.h.error = -ECONNABORTED;
-		request_end(fc, req);
-		spin_lock(&fc->lock);
-	}
-}
-
-/*
- * Abort requests under I/O
- *
- * The requests are set to aborted and finished, and the request
- * waiter is woken up.  This will make request_wait_answer() wait
- * until the request is unlocked and then return.
- *
- * If the request is asynchronous, then the end function needs to be
- * called after waiting for the request to be unlocked (if it was
- * locked).
- */
-static void end_io_requests(struct fuse_conn *fc)
-__releases(fc->lock)
-__acquires(fc->lock)
-{
-	while (!list_empty(&fc->io)) {
-		struct fuse_req *req =
-			list_entry(fc->io.next, struct fuse_req, list);
-		void (*end) (struct fuse_conn *, struct fuse_req *) = req->end;
-
-		req->aborted = 1;
-		req->out.h.error = -ECONNABORTED;
-		req->state = FUSE_REQ_FINISHED;
+		clear_bit(FR_PENDING, &req->flags);
+		clear_bit(FR_SENT, &req->flags);
 		list_del_init(&req->list);
-		wake_up(&req->waitq);
-		if (end) {
-			req->end = NULL;
-			__fuse_get_request(req);
-			spin_unlock(&fc->lock);
-			wait_event(req->waitq, !req->locked);
-			end(fc, req);
-			fuse_put_request(fc, req);
-			spin_lock(&fc->lock);
-		}
+		request_end(fc, req);
 	}
 }
 
-static void end_queued_requests(struct fuse_conn *fc)
-__releases(fc->lock)
-__acquires(fc->lock)
-{
-	fc->max_background = UINT_MAX;
-	flush_bg_queue(fc);
-	end_requests(fc, &fc->pending);
-	end_requests(fc, &fc->processing);
-	while (forget_pending(fc))
-		kfree(dequeue_forget(fc, 1, NULL));
-}
-
 static void end_polls(struct fuse_conn *fc)
 {
 	struct rb_node *p;
@@ -2162,67 +2108,156 @@
 /*
  * Abort all requests.
  *
- * Emergency exit in case of a malicious or accidental deadlock, or
- * just a hung filesystem.
+ * Emergency exit in case of a malicious or accidental deadlock, or just a hung
+ * filesystem.
  *
- * The same effect is usually achievable through killing the
- * filesystem daemon and all users of the filesystem.  The exception
- * is the combination of an asynchronous request and the tricky
- * deadlock (see Documentation/filesystems/fuse.txt).
+ * The same effect is usually achievable through killing the filesystem daemon
+ * and all users of the filesystem.  The exception is the combination of an
+ * asynchronous request and the tricky deadlock (see
+ * Documentation/filesystems/fuse.txt).
  *
- * During the aborting, progression of requests from the pending and
- * processing lists onto the io list, and progression of new requests
- * onto the pending list is prevented by req->connected being false.
- *
- * Progression of requests under I/O to the processing list is
- * prevented by the req->aborted flag being true for these requests.
- * For this reason requests on the io list must be aborted first.
+ * Aborting requests under I/O goes as follows: 1: Separate out unlocked
+ * requests, they should be finished off immediately.  Locked requests will be
+ * finished after unlock; see unlock_request(). 2: Finish off the unlocked
+ * requests.  It is possible that some request will finish before we can.  This
+ * is OK, the request will in that case be removed from the list before we touch
+ * it.
  */
 void fuse_abort_conn(struct fuse_conn *fc)
 {
+	struct fuse_iqueue *fiq = &fc->iq;
+
 	spin_lock(&fc->lock);
 	if (fc->connected) {
+		struct fuse_dev *fud;
+		struct fuse_req *req, *next;
+		LIST_HEAD(to_end1);
+		LIST_HEAD(to_end2);
+
 		fc->connected = 0;
 		fc->blocked = 0;
 		fuse_set_initialized(fc);
-		end_io_requests(fc);
-		end_queued_requests(fc);
+		list_for_each_entry(fud, &fc->devices, entry) {
+			struct fuse_pqueue *fpq = &fud->pq;
+
+			spin_lock(&fpq->lock);
+			fpq->connected = 0;
+			list_for_each_entry_safe(req, next, &fpq->io, list) {
+				req->out.h.error = -ECONNABORTED;
+				spin_lock(&req->waitq.lock);
+				set_bit(FR_ABORTED, &req->flags);
+				if (!test_bit(FR_LOCKED, &req->flags)) {
+					set_bit(FR_PRIVATE, &req->flags);
+					list_move(&req->list, &to_end1);
+				}
+				spin_unlock(&req->waitq.lock);
+			}
+			list_splice_init(&fpq->processing, &to_end2);
+			spin_unlock(&fpq->lock);
+		}
+		fc->max_background = UINT_MAX;
+		flush_bg_queue(fc);
+
+		spin_lock(&fiq->waitq.lock);
+		fiq->connected = 0;
+		list_splice_init(&fiq->pending, &to_end2);
+		while (forget_pending(fiq))
+			kfree(dequeue_forget(fiq, 1, NULL));
+		wake_up_all_locked(&fiq->waitq);
+		spin_unlock(&fiq->waitq.lock);
+		kill_fasync(&fiq->fasync, SIGIO, POLL_IN);
 		end_polls(fc);
-		wake_up_all(&fc->waitq);
 		wake_up_all(&fc->blocked_waitq);
-		kill_fasync(&fc->fasync, SIGIO, POLL_IN);
+		spin_unlock(&fc->lock);
+
+		while (!list_empty(&to_end1)) {
+			req = list_first_entry(&to_end1, struct fuse_req, list);
+			__fuse_get_request(req);
+			list_del_init(&req->list);
+			request_end(fc, req);
+		}
+		end_requests(fc, &to_end2);
+	} else {
+		spin_unlock(&fc->lock);
 	}
-	spin_unlock(&fc->lock);
 }
 EXPORT_SYMBOL_GPL(fuse_abort_conn);
 
 int fuse_dev_release(struct inode *inode, struct file *file)
 {
-	struct fuse_conn *fc = fuse_get_conn(file);
-	if (fc) {
-		spin_lock(&fc->lock);
-		fc->connected = 0;
-		fc->blocked = 0;
-		fuse_set_initialized(fc);
-		end_queued_requests(fc);
-		end_polls(fc);
-		wake_up_all(&fc->blocked_waitq);
-		spin_unlock(&fc->lock);
-		fuse_conn_put(fc);
-	}
+	struct fuse_dev *fud = fuse_get_dev(file);
 
+	if (fud) {
+		struct fuse_conn *fc = fud->fc;
+		struct fuse_pqueue *fpq = &fud->pq;
+
+		WARN_ON(!list_empty(&fpq->io));
+		end_requests(fc, &fpq->processing);
+		/* Are we the last open device? */
+		if (atomic_dec_and_test(&fc->dev_count)) {
+			WARN_ON(fc->iq.fasync != NULL);
+			fuse_abort_conn(fc);
+		}
+		fuse_dev_free(fud);
+	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(fuse_dev_release);
 
 static int fuse_dev_fasync(int fd, struct file *file, int on)
 {
-	struct fuse_conn *fc = fuse_get_conn(file);
-	if (!fc)
+	struct fuse_dev *fud = fuse_get_dev(file);
+
+	if (!fud)
 		return -EPERM;
 
 	/* No locking - fasync_helper does its own locking */
-	return fasync_helper(fd, file, on, &fc->fasync);
+	return fasync_helper(fd, file, on, &fud->fc->iq.fasync);
+}
+
+static int fuse_device_clone(struct fuse_conn *fc, struct file *new)
+{
+	struct fuse_dev *fud;
+
+	if (new->private_data)
+		return -EINVAL;
+
+	fud = fuse_dev_alloc(fc);
+	if (!fud)
+		return -ENOMEM;
+
+	new->private_data = fud;
+	atomic_inc(&fc->dev_count);
+
+	return 0;
+}
+
+static long fuse_dev_ioctl(struct file *file, unsigned int cmd,
+			   unsigned long arg)
+{
+	int err = -ENOTTY;
+
+	if (cmd == FUSE_DEV_IOC_CLONE) {
+		int oldfd;
+
+		err = -EFAULT;
+		if (!get_user(oldfd, (__u32 __user *) arg)) {
+			struct file *old = fget(oldfd);
+
+			err = -EINVAL;
+			if (old) {
+				struct fuse_dev *fud = fuse_get_dev(old);
+
+				if (fud) {
+					mutex_lock(&fuse_mutex);
+					err = fuse_device_clone(fud->fc, file);
+					mutex_unlock(&fuse_mutex);
+				}
+				fput(old);
+			}
+		}
+	}
+	return err;
 }
 
 const struct file_operations fuse_dev_operations = {
@@ -2236,6 +2271,8 @@
 	.poll		= fuse_dev_poll,
 	.release	= fuse_dev_release,
 	.fasync		= fuse_dev_fasync,
+	.unlocked_ioctl = fuse_dev_ioctl,
+	.compat_ioctl   = fuse_dev_ioctl,
 };
 EXPORT_SYMBOL_GPL(fuse_dev_operations);
 
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 8c5e2fa..f523f2f 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -96,17 +96,17 @@
 			 * Drop the release request when client does not
 			 * implement 'open'
 			 */
-			req->background = 0;
+			__clear_bit(FR_BACKGROUND, &req->flags);
 			iput(req->misc.release.inode);
 			fuse_put_request(ff->fc, req);
 		} else if (sync) {
-			req->background = 0;
+			__clear_bit(FR_BACKGROUND, &req->flags);
 			fuse_request_send(ff->fc, req);
 			iput(req->misc.release.inode);
 			fuse_put_request(ff->fc, req);
 		} else {
 			req->end = fuse_release_end;
-			req->background = 1;
+			__set_bit(FR_BACKGROUND, &req->flags);
 			fuse_request_send_background(ff->fc, req);
 		}
 		kfree(ff);
@@ -299,8 +299,8 @@
 {
 	WARN_ON(atomic_read(&ff->count) > 1);
 	fuse_prepare_release(ff, flags, FUSE_RELEASE);
-	ff->reserved_req->force = 1;
-	ff->reserved_req->background = 0;
+	__set_bit(FR_FORCE, &ff->reserved_req->flags);
+	__clear_bit(FR_BACKGROUND, &ff->reserved_req->flags);
 	fuse_request_send(ff->fc, ff->reserved_req);
 	fuse_put_request(ff->fc, ff->reserved_req);
 	kfree(ff);
@@ -426,7 +426,7 @@
 	req->in.numargs = 1;
 	req->in.args[0].size = sizeof(inarg);
 	req->in.args[0].value = &inarg;
-	req->force = 1;
+	__set_bit(FR_FORCE, &req->flags);
 	fuse_request_send(fc, req);
 	err = req->out.h.error;
 	fuse_put_request(fc, req);
@@ -1169,7 +1169,7 @@
 	if (err <= 0)
 		goto out;
 
-	err = file_remove_suid(file);
+	err = file_remove_privs(file);
 	if (err)
 		goto out;
 
@@ -1611,7 +1611,8 @@
 	if (!req)
 		goto err;
 
-	req->background = 1; /* writeback always goes to bg_queue */
+	/* writeback always goes to bg_queue */
+	__set_bit(FR_BACKGROUND, &req->flags);
 	tmp_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
 	if (!tmp_page)
 		goto err_free;
@@ -1742,8 +1743,7 @@
 		}
 	}
 
-	if (old_req->num_pages == 1 && (old_req->state == FUSE_REQ_INIT ||
-					old_req->state == FUSE_REQ_PENDING)) {
+	if (old_req->num_pages == 1 && test_bit(FR_PENDING, &old_req->flags)) {
 		struct backing_dev_info *bdi = inode_to_bdi(page->mapping->host);
 
 		copy_highpage(old_req->pages[0], page);
@@ -1830,7 +1830,7 @@
 		req->misc.write.in.write_flags |= FUSE_WRITE_CACHE;
 		req->misc.write.next = NULL;
 		req->in.argpages = 1;
-		req->background = 1;
+		__set_bit(FR_BACKGROUND, &req->flags);
 		req->num_pages = 0;
 		req->end = fuse_writepage_end;
 		req->inode = inode;
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 7354dc1..4051131 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -241,16 +241,6 @@
 
 #define FUSE_ARGS(args) struct fuse_args args = {}
 
-/** The request state */
-enum fuse_req_state {
-	FUSE_REQ_INIT = 0,
-	FUSE_REQ_PENDING,
-	FUSE_REQ_READING,
-	FUSE_REQ_SENT,
-	FUSE_REQ_WRITING,
-	FUSE_REQ_FINISHED
-};
-
 /** The request IO state (for asynchronous processing) */
 struct fuse_io_priv {
 	int async;
@@ -267,7 +257,40 @@
 };
 
 /**
+ * Request flags
+ *
+ * FR_ISREPLY:		set if the request has reply
+ * FR_FORCE:		force sending of the request even if interrupted
+ * FR_BACKGROUND:	request is sent in the background
+ * FR_WAITING:		request is counted as "waiting"
+ * FR_ABORTED:		the request was aborted
+ * FR_INTERRUPTED:	the request has been interrupted
+ * FR_LOCKED:		data is being copied to/from the request
+ * FR_PENDING:		request is not yet in userspace
+ * FR_SENT:		request is in userspace, waiting for an answer
+ * FR_FINISHED:		request is finished
+ * FR_PRIVATE:		request is on private list
+ */
+enum fuse_req_flag {
+	FR_ISREPLY,
+	FR_FORCE,
+	FR_BACKGROUND,
+	FR_WAITING,
+	FR_ABORTED,
+	FR_INTERRUPTED,
+	FR_LOCKED,
+	FR_PENDING,
+	FR_SENT,
+	FR_FINISHED,
+	FR_PRIVATE,
+};
+
+/**
  * A request to the client
+ *
+ * .waitq.lock protects the following fields:
+ *   - FR_ABORTED
+ *   - FR_LOCKED (may also be modified under fc->lock, tested under both)
  */
 struct fuse_req {
 	/** This can be on either pending processing or io lists in
@@ -283,35 +306,8 @@
 	/** Unique ID for the interrupt request */
 	u64 intr_unique;
 
-	/*
-	 * The following bitfields are either set once before the
-	 * request is queued or setting/clearing them is protected by
-	 * fuse_conn->lock
-	 */
-
-	/** True if the request has reply */
-	unsigned isreply:1;
-
-	/** Force sending of the request even if interrupted */
-	unsigned force:1;
-
-	/** The request was aborted */
-	unsigned aborted:1;
-
-	/** Request is sent in the background */
-	unsigned background:1;
-
-	/** The request has been interrupted */
-	unsigned interrupted:1;
-
-	/** Data is being copied to/from the request */
-	unsigned locked:1;
-
-	/** Request is counted as "waiting" */
-	unsigned waiting:1;
-
-	/** State of the request */
-	enum fuse_req_state state;
+	/* Request flags, updated with test/set/clear_bit() */
+	unsigned long flags;
 
 	/** The request input */
 	struct fuse_in in;
@@ -380,6 +376,61 @@
 	struct file *stolen_file;
 };
 
+struct fuse_iqueue {
+	/** Connection established */
+	unsigned connected;
+
+	/** Readers of the connection are waiting on this */
+	wait_queue_head_t waitq;
+
+	/** The next unique request id */
+	u64 reqctr;
+
+	/** The list of pending requests */
+	struct list_head pending;
+
+	/** Pending interrupts */
+	struct list_head interrupts;
+
+	/** Queue of pending forgets */
+	struct fuse_forget_link forget_list_head;
+	struct fuse_forget_link *forget_list_tail;
+
+	/** Batching of FORGET requests (positive indicates FORGET batch) */
+	int forget_batch;
+
+	/** O_ASYNC requests */
+	struct fasync_struct *fasync;
+};
+
+struct fuse_pqueue {
+	/** Connection established */
+	unsigned connected;
+
+	/** Lock protecting accessess to  members of this structure */
+	spinlock_t lock;
+
+	/** The list of requests being processed */
+	struct list_head processing;
+
+	/** The list of requests under I/O */
+	struct list_head io;
+};
+
+/**
+ * Fuse device instance
+ */
+struct fuse_dev {
+	/** Fuse connection for this device */
+	struct fuse_conn *fc;
+
+	/** Processing queue */
+	struct fuse_pqueue pq;
+
+	/** list entry on fc->devices */
+	struct list_head entry;
+};
+
 /**
  * A Fuse connection.
  *
@@ -394,6 +445,9 @@
 	/** Refcount */
 	atomic_t count;
 
+	/** Number of fuse_dev's */
+	atomic_t dev_count;
+
 	struct rcu_head rcu;
 
 	/** The user id for this mount */
@@ -411,17 +465,8 @@
 	/** Maximum write size */
 	unsigned max_write;
 
-	/** Readers of the connection are waiting on this */
-	wait_queue_head_t waitq;
-
-	/** The list of pending requests */
-	struct list_head pending;
-
-	/** The list of requests being processed */
-	struct list_head processing;
-
-	/** The list of requests under I/O */
-	struct list_head io;
+	/** Input queue */
+	struct fuse_iqueue iq;
 
 	/** The next unique kernel file handle */
 	u64 khctr;
@@ -444,16 +489,6 @@
 	/** The list of background requests set aside for later queuing */
 	struct list_head bg_queue;
 
-	/** Pending interrupts */
-	struct list_head interrupts;
-
-	/** Queue of pending forgets */
-	struct fuse_forget_link forget_list_head;
-	struct fuse_forget_link *forget_list_tail;
-
-	/** Batching of FORGET requests (positive indicates FORGET batch) */
-	int forget_batch;
-
 	/** Flag indicating that INIT reply has been received. Allocating
 	 * any fuse request will be suspended until the flag is set */
 	int initialized;
@@ -469,9 +504,6 @@
 	/** waitq for reserved requests */
 	wait_queue_head_t reserved_req_waitq;
 
-	/** The next unique request id */
-	u64 reqctr;
-
 	/** Connection established, cleared on umount, connection
 	    abort and device release */
 	unsigned connected;
@@ -594,9 +626,6 @@
 	/** number of dentries used in the above array */
 	int ctl_ndents;
 
-	/** O_ASYNC requests */
-	struct fasync_struct *fasync;
-
 	/** Key for lock owner ID scrambling */
 	u32 scramble_key[4];
 
@@ -614,6 +643,9 @@
 
 	/** Read/write semaphore to hold when accessing sb. */
 	struct rw_semaphore killsb;
+
+	/** List of device instances belonging to this connection */
+	struct list_head devices;
 };
 
 static inline struct fuse_conn *get_fuse_conn_super(struct super_block *sb)
@@ -826,6 +858,9 @@
  */
 void fuse_conn_put(struct fuse_conn *fc);
 
+struct fuse_dev *fuse_dev_alloc(struct fuse_conn *fc);
+void fuse_dev_free(struct fuse_dev *fud);
+
 /**
  * Add connection to control filesystem
  */
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 082ac1c..2913db2 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -362,8 +362,8 @@
 	if (req && fc->conn_init) {
 		fc->destroy_req = NULL;
 		req->in.h.opcode = FUSE_DESTROY;
-		req->force = 1;
-		req->background = 0;
+		__set_bit(FR_FORCE, &req->flags);
+		__clear_bit(FR_BACKGROUND, &req->flags);
 		fuse_request_send(fc, req);
 		fuse_put_request(fc, req);
 	}
@@ -567,30 +567,46 @@
 	return 0;
 }
 
+static void fuse_iqueue_init(struct fuse_iqueue *fiq)
+{
+	memset(fiq, 0, sizeof(struct fuse_iqueue));
+	init_waitqueue_head(&fiq->waitq);
+	INIT_LIST_HEAD(&fiq->pending);
+	INIT_LIST_HEAD(&fiq->interrupts);
+	fiq->forget_list_tail = &fiq->forget_list_head;
+	fiq->connected = 1;
+}
+
+static void fuse_pqueue_init(struct fuse_pqueue *fpq)
+{
+	memset(fpq, 0, sizeof(struct fuse_pqueue));
+	spin_lock_init(&fpq->lock);
+	INIT_LIST_HEAD(&fpq->processing);
+	INIT_LIST_HEAD(&fpq->io);
+	fpq->connected = 1;
+}
+
 void fuse_conn_init(struct fuse_conn *fc)
 {
 	memset(fc, 0, sizeof(*fc));
 	spin_lock_init(&fc->lock);
 	init_rwsem(&fc->killsb);
 	atomic_set(&fc->count, 1);
-	init_waitqueue_head(&fc->waitq);
+	atomic_set(&fc->dev_count, 1);
 	init_waitqueue_head(&fc->blocked_waitq);
 	init_waitqueue_head(&fc->reserved_req_waitq);
-	INIT_LIST_HEAD(&fc->pending);
-	INIT_LIST_HEAD(&fc->processing);
-	INIT_LIST_HEAD(&fc->io);
-	INIT_LIST_HEAD(&fc->interrupts);
+	fuse_iqueue_init(&fc->iq);
 	INIT_LIST_HEAD(&fc->bg_queue);
 	INIT_LIST_HEAD(&fc->entry);
-	fc->forget_list_tail = &fc->forget_list_head;
+	INIT_LIST_HEAD(&fc->devices);
 	atomic_set(&fc->num_waiting, 0);
 	fc->max_background = FUSE_DEFAULT_MAX_BACKGROUND;
 	fc->congestion_threshold = FUSE_DEFAULT_CONGESTION_THRESHOLD;
 	fc->khctr = 0;
 	fc->polled_files = RB_ROOT;
-	fc->reqctr = 0;
 	fc->blocked = 0;
 	fc->initialized = 0;
+	fc->connected = 1;
 	fc->attr_version = 1;
 	get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key));
 }
@@ -930,6 +946,7 @@
 
 static void fuse_free_conn(struct fuse_conn *fc)
 {
+	WARN_ON(!list_empty(&fc->devices));
 	kfree_rcu(fc, rcu);
 }
 
@@ -975,8 +992,42 @@
 	return 0;
 }
 
+struct fuse_dev *fuse_dev_alloc(struct fuse_conn *fc)
+{
+	struct fuse_dev *fud;
+
+	fud = kzalloc(sizeof(struct fuse_dev), GFP_KERNEL);
+	if (fud) {
+		fud->fc = fuse_conn_get(fc);
+		fuse_pqueue_init(&fud->pq);
+
+		spin_lock(&fc->lock);
+		list_add_tail(&fud->entry, &fc->devices);
+		spin_unlock(&fc->lock);
+	}
+
+	return fud;
+}
+EXPORT_SYMBOL_GPL(fuse_dev_alloc);
+
+void fuse_dev_free(struct fuse_dev *fud)
+{
+	struct fuse_conn *fc = fud->fc;
+
+	if (fc) {
+		spin_lock(&fc->lock);
+		list_del(&fud->entry);
+		spin_unlock(&fc->lock);
+
+		fuse_conn_put(fc);
+	}
+	kfree(fud);
+}
+EXPORT_SYMBOL_GPL(fuse_dev_free);
+
 static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 {
+	struct fuse_dev *fud;
 	struct fuse_conn *fc;
 	struct inode *root;
 	struct fuse_mount_data d;
@@ -1026,12 +1077,17 @@
 		goto err_fput;
 
 	fuse_conn_init(fc);
+	fc->release = fuse_free_conn;
+
+	fud = fuse_dev_alloc(fc);
+	if (!fud)
+		goto err_put_conn;
 
 	fc->dev = sb->s_dev;
 	fc->sb = sb;
 	err = fuse_bdi_init(fc, sb);
 	if (err)
-		goto err_put_conn;
+		goto err_dev_free;
 
 	sb->s_bdi = &fc->bdi;
 
@@ -1040,7 +1096,6 @@
 		fc->dont_mask = 1;
 	sb->s_flags |= MS_POSIXACL;
 
-	fc->release = fuse_free_conn;
 	fc->flags = d.flags;
 	fc->user_id = d.user_id;
 	fc->group_id = d.group_id;
@@ -1053,14 +1108,14 @@
 	root = fuse_get_root_inode(sb, d.rootmode);
 	root_dentry = d_make_root(root);
 	if (!root_dentry)
-		goto err_put_conn;
+		goto err_dev_free;
 	/* only now - we want root dentry with NULL ->d_op */
 	sb->s_d_op = &fuse_dentry_operations;
 
 	init_req = fuse_request_alloc(0);
 	if (!init_req)
 		goto err_put_root;
-	init_req->background = 1;
+	__set_bit(FR_BACKGROUND, &init_req->flags);
 
 	if (is_bdev) {
 		fc->destroy_req = fuse_request_alloc(0);
@@ -1079,8 +1134,7 @@
 
 	list_add_tail(&fc->entry, &fuse_conn_list);
 	sb->s_root = root_dentry;
-	fc->connected = 1;
-	file->private_data = fuse_conn_get(fc);
+	file->private_data = fud;
 	mutex_unlock(&fuse_mutex);
 	/*
 	 * atomic_dec_and_test() in fput() provides the necessary
@@ -1099,6 +1153,8 @@
 	fuse_request_free(init_req);
  err_put_root:
 	dput(root_dentry);
+ err_dev_free:
+	fuse_dev_free(fud);
  err_put_conn:
 	fuse_bdi_destroy(fc);
 	fuse_conn_put(fc);
@@ -1238,7 +1294,6 @@
 }
 
 static struct kobject *fuse_kobj;
-static struct kobject *connections_kobj;
 
 static int fuse_sysfs_init(void)
 {
@@ -1250,11 +1305,9 @@
 		goto out_err;
 	}
 
-	connections_kobj = kobject_create_and_add("connections", fuse_kobj);
-	if (!connections_kobj) {
-		err = -ENOMEM;
+	err = sysfs_create_mount_point(fuse_kobj, "connections");
+	if (err)
 		goto out_fuse_unregister;
-	}
 
 	return 0;
 
@@ -1266,7 +1319,7 @@
 
 static void fuse_sysfs_cleanup(void)
 {
-	kobject_put(connections_kobj);
+	sysfs_remove_mount_point(fuse_kobj, "connections");
 	kobject_put(fuse_kobj);
 }
 
diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h
index 95d2552..1f1c7dc 100644
--- a/fs/hfs/hfs_fs.h
+++ b/fs/hfs/hfs_fs.h
@@ -252,7 +252,7 @@
 #define __hfs_u_to_mtime(sec)	cpu_to_be32(sec + 2082844800U - sys_tz.tz_minuteswest * 60)
 #define __hfs_m_to_utime(sec)	(be32_to_cpu(sec) - 2082844800U  + sys_tz.tz_minuteswest * 60)
 
-#define HFS_I(inode)	(list_entry(inode, struct hfs_inode_info, vfs_inode))
+#define HFS_I(inode)	(container_of(inode, struct hfs_inode_info, vfs_inode))
 #define HFS_SB(sb)	((struct hfs_sb_info *)(sb)->s_fs_info)
 
 #define hfs_m_to_utime(time)	(struct timespec){ .tv_sec = __hfs_m_to_utime(time) }
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index b0441d6..f91a1fa 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -263,7 +263,7 @@
 
 static inline struct hfsplus_inode_info *HFSPLUS_I(struct inode *inode)
 {
-	return list_entry(inode, struct hfsplus_inode_info, vfs_inode);
+	return container_of(inode, struct hfsplus_inode_info, vfs_inode);
 }
 
 /*
diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h
index b63b75f..bb04b58 100644
--- a/fs/hpfs/hpfs_fn.h
+++ b/fs/hpfs/hpfs_fn.h
@@ -304,7 +304,7 @@
 
 static inline struct hpfs_inode_info *hpfs_i(struct inode *inode)
 {
-	return list_entry(inode, struct hpfs_inode_info, vfs_inode);
+	return container_of(inode, struct hpfs_inode_info, vfs_inode);
 }
 
 static inline struct hpfs_sb_info *hpfs_sb(struct super_block *sb)
diff --git a/fs/inode.c b/fs/inode.c
index 069721f..d30640f 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -841,7 +841,11 @@
 	}
 #endif
 
-	*p = ++res;
+	res++;
+	/* get_next_ino should not provide a 0 inode number */
+	if (unlikely(!res))
+		res++;
+	*p = res;
 	put_cpu_var(last_ino);
 	return res;
 }
@@ -1674,7 +1678,31 @@
 }
 EXPORT_SYMBOL(should_remove_suid);
 
-static int __remove_suid(struct dentry *dentry, int kill)
+/*
+ * Return mask of changes for notify_change() that need to be done as a
+ * response to write or truncate. Return 0 if nothing has to be changed.
+ * Negative value on error (change should be denied).
+ */
+int dentry_needs_remove_privs(struct dentry *dentry)
+{
+	struct inode *inode = d_inode(dentry);
+	int mask = 0;
+	int ret;
+
+	if (IS_NOSEC(inode))
+		return 0;
+
+	mask = should_remove_suid(dentry);
+	ret = security_inode_need_killpriv(dentry);
+	if (ret < 0)
+		return ret;
+	if (ret)
+		mask |= ATTR_KILL_PRIV;
+	return mask;
+}
+EXPORT_SYMBOL(dentry_needs_remove_privs);
+
+static int __remove_privs(struct dentry *dentry, int kill)
 {
 	struct iattr newattrs;
 
@@ -1686,33 +1714,32 @@
 	return notify_change(dentry, &newattrs, NULL);
 }
 
-int file_remove_suid(struct file *file)
+/*
+ * Remove special file priviledges (suid, capabilities) when file is written
+ * to or truncated.
+ */
+int file_remove_privs(struct file *file)
 {
 	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = d_inode(dentry);
-	int killsuid;
-	int killpriv;
+	int kill;
 	int error = 0;
 
 	/* Fast path for nothing security related */
 	if (IS_NOSEC(inode))
 		return 0;
 
-	killsuid = should_remove_suid(dentry);
-	killpriv = security_inode_need_killpriv(dentry);
-
-	if (killpriv < 0)
-		return killpriv;
-	if (killpriv)
-		error = security_inode_killpriv(dentry);
-	if (!error && killsuid)
-		error = __remove_suid(dentry, killsuid);
-	if (!error && (inode->i_sb->s_flags & MS_NOSEC))
-		inode->i_flags |= S_NOSEC;
+	kill = file_needs_remove_privs(file);
+	if (kill < 0)
+		return kill;
+	if (kill)
+		error = __remove_privs(dentry, kill);
+	if (!error)
+		inode_has_no_xattr(inode);
 
 	return error;
 }
-EXPORT_SYMBOL(file_remove_suid);
+EXPORT_SYMBOL(file_remove_privs);
 
 /**
  *	file_update_time	-	update mtime and ctime time
@@ -1967,9 +1994,8 @@
  * inode is being instantiated).  The reason for the cmpxchg() loop
  * --- which wouldn't be necessary if all code paths which modify
  * i_flags actually followed this rule, is that there is at least one
- * code path which doesn't today --- for example,
- * __generic_file_aio_write() calls file_remove_suid() without holding
- * i_mutex --- so we use cmpxchg() out of an abundance of caution.
+ * code path which doesn't today so we use cmpxchg() out of an abundance
+ * of caution.
  *
  * In the long run, i_mutex is overkill, and we should probably look
  * at using the i_lock spinlock to protect i_flags, and then make sure
diff --git a/fs/internal.h b/fs/internal.h
index 01dce1d..4d5af58 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -107,6 +107,7 @@
 extern long do_handle_open(int mountdirfd,
 			   struct file_handle __user *ufh, int open_flag);
 extern int open_check_o_direct(struct file *f);
+extern int vfs_open(const struct path *, struct file *, const struct cred *);
 
 /*
  * inode.c
diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h
index d200a9b..824e61e 100644
--- a/fs/jffs2/os-linux.h
+++ b/fs/jffs2/os-linux.h
@@ -19,7 +19,7 @@
 struct kstatfs;
 struct kvec;
 
-#define JFFS2_INODE_INFO(i) (list_entry(i, struct jffs2_inode_info, vfs_inode))
+#define JFFS2_INODE_INFO(i) (container_of(i, struct jffs2_inode_info, vfs_inode))
 #define OFNI_EDONI_2SFFJ(f)  (&(f)->vfs_inode)
 #define JFFS2_SB_INFO(sb) (sb->s_fs_info)
 #define OFNI_BS_2SFFJ(c)  ((struct super_block *)c->os_priv)
diff --git a/fs/jfs/jfs_incore.h b/fs/jfs/jfs_incore.h
index fa7e795..1f26d19 100644
--- a/fs/jfs/jfs_incore.h
+++ b/fs/jfs/jfs_incore.h
@@ -206,7 +206,7 @@
 
 static inline struct jfs_inode_info *JFS_IP(struct inode *inode)
 {
-	return list_entry(inode, struct jfs_inode_info, vfs_inode);
+	return container_of(inode, struct jfs_inode_info, vfs_inode);
 }
 
 static inline int jfs_dirtable_inline(struct inode *inode)
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index fffca95..2d48d28 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -592,6 +592,9 @@
 		goto out_unlock;
 
 	ret = -ENOENT;
+	if (parent->flags & KERNFS_EMPTY_DIR)
+		goto out_unlock;
+
 	if ((parent->flags & KERNFS_ACTIVATED) && !kernfs_active(parent))
 		goto out_unlock;
 
@@ -783,6 +786,38 @@
 	return ERR_PTR(rc);
 }
 
+/**
+ * kernfs_create_empty_dir - create an always empty directory
+ * @parent: parent in which to create a new directory
+ * @name: name of the new directory
+ *
+ * Returns the created node on success, ERR_PTR() value on failure.
+ */
+struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent,
+					    const char *name)
+{
+	struct kernfs_node *kn;
+	int rc;
+
+	/* allocate */
+	kn = kernfs_new_node(parent, name, S_IRUGO|S_IXUGO|S_IFDIR, KERNFS_DIR);
+	if (!kn)
+		return ERR_PTR(-ENOMEM);
+
+	kn->flags |= KERNFS_EMPTY_DIR;
+	kn->dir.root = parent->dir.root;
+	kn->ns = NULL;
+	kn->priv = NULL;
+
+	/* link in */
+	rc = kernfs_add_one(kn);
+	if (!rc)
+		return kn;
+
+	kernfs_put(kn);
+	return ERR_PTR(rc);
+}
+
 static struct dentry *kernfs_iop_lookup(struct inode *dir,
 					struct dentry *dentry,
 					unsigned int flags)
@@ -1254,7 +1289,8 @@
 	mutex_lock(&kernfs_mutex);
 
 	error = -ENOENT;
-	if (!kernfs_active(kn) || !kernfs_active(new_parent))
+	if (!kernfs_active(kn) || !kernfs_active(new_parent) ||
+	    (new_parent->flags & KERNFS_EMPTY_DIR))
 		goto out;
 
 	error = 0;
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index 2da8493..756dd56 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -296,6 +296,8 @@
 	case KERNFS_DIR:
 		inode->i_op = &kernfs_dir_iops;
 		inode->i_fop = &kernfs_dir_fops;
+		if (kn->flags & KERNFS_EMPTY_DIR)
+			make_empty_dir_inode(inode);
 		break;
 	case KERNFS_FILE:
 		inode->i_size = kn->attr.size;
diff --git a/fs/libfs.c b/fs/libfs.c
index 65e1fec..102edfd 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -20,11 +20,6 @@
 
 #include "internal.h"
 
-static inline int simple_positive(struct dentry *dentry)
-{
-	return d_really_is_positive(dentry) && !d_unhashed(dentry);
-}
-
 int simple_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		   struct kstat *stat)
 {
@@ -1108,3 +1103,98 @@
 	.readlink = generic_readlink
 };
 EXPORT_SYMBOL(simple_symlink_inode_operations);
+
+/*
+ * Operations for a permanently empty directory.
+ */
+static struct dentry *empty_dir_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
+{
+	return ERR_PTR(-ENOENT);
+}
+
+static int empty_dir_getattr(struct vfsmount *mnt, struct dentry *dentry,
+				 struct kstat *stat)
+{
+	struct inode *inode = d_inode(dentry);
+	generic_fillattr(inode, stat);
+	return 0;
+}
+
+static int empty_dir_setattr(struct dentry *dentry, struct iattr *attr)
+{
+	return -EPERM;
+}
+
+static int empty_dir_setxattr(struct dentry *dentry, const char *name,
+			      const void *value, size_t size, int flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static ssize_t empty_dir_getxattr(struct dentry *dentry, const char *name,
+				  void *value, size_t size)
+{
+	return -EOPNOTSUPP;
+}
+
+static int empty_dir_removexattr(struct dentry *dentry, const char *name)
+{
+	return -EOPNOTSUPP;
+}
+
+static ssize_t empty_dir_listxattr(struct dentry *dentry, char *list, size_t size)
+{
+	return -EOPNOTSUPP;
+}
+
+static const struct inode_operations empty_dir_inode_operations = {
+	.lookup		= empty_dir_lookup,
+	.permission	= generic_permission,
+	.setattr	= empty_dir_setattr,
+	.getattr	= empty_dir_getattr,
+	.setxattr	= empty_dir_setxattr,
+	.getxattr	= empty_dir_getxattr,
+	.removexattr	= empty_dir_removexattr,
+	.listxattr	= empty_dir_listxattr,
+};
+
+static loff_t empty_dir_llseek(struct file *file, loff_t offset, int whence)
+{
+	/* An empty directory has two entries . and .. at offsets 0 and 1 */
+	return generic_file_llseek_size(file, offset, whence, 2, 2);
+}
+
+static int empty_dir_readdir(struct file *file, struct dir_context *ctx)
+{
+	dir_emit_dots(file, ctx);
+	return 0;
+}
+
+static const struct file_operations empty_dir_operations = {
+	.llseek		= empty_dir_llseek,
+	.read		= generic_read_dir,
+	.iterate	= empty_dir_readdir,
+	.fsync		= noop_fsync,
+};
+
+
+void make_empty_dir_inode(struct inode *inode)
+{
+	set_nlink(inode, 2);
+	inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO;
+	inode->i_uid = GLOBAL_ROOT_UID;
+	inode->i_gid = GLOBAL_ROOT_GID;
+	inode->i_rdev = 0;
+	inode->i_size = 2;
+	inode->i_blkbits = PAGE_SHIFT;
+	inode->i_blocks = 0;
+
+	inode->i_op = &empty_dir_inode_operations;
+	inode->i_fop = &empty_dir_operations;
+}
+
+bool is_empty_dir_inode(struct inode *inode)
+{
+	return (inode->i_fop == &empty_dir_operations) &&
+		(inode->i_op == &empty_dir_inode_operations);
+}
diff --git a/fs/minix/dir.c b/fs/minix/dir.c
index 118e4e7..d19ac25 100644
--- a/fs/minix/dir.c
+++ b/fs/minix/dir.c
@@ -45,11 +45,6 @@
 	return last_byte;
 }
 
-static inline unsigned long dir_pages(struct inode *inode)
-{
-	return (inode->i_size+PAGE_CACHE_SIZE-1)>>PAGE_CACHE_SHIFT;
-}
-
 static int dir_commit_chunk(struct page *page, loff_t pos, unsigned len)
 {
 	struct address_space *mapping = page->mapping;
diff --git a/fs/minix/minix.h b/fs/minix/minix.h
index 1ebd118..01ad81d 100644
--- a/fs/minix/minix.h
+++ b/fs/minix/minix.h
@@ -84,7 +84,7 @@
 
 static inline struct minix_inode_info *minix_i(struct inode *inode)
 {
-	return list_entry(inode, struct minix_inode_info, vfs_inode);
+	return container_of(inode, struct minix_inode_info, vfs_inode);
 }
 
 static inline unsigned minix_blocks_needed(unsigned bits, unsigned blocksize)
diff --git a/fs/mount.h b/fs/mount.h
index b5b8082..14db05d 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -118,7 +118,6 @@
 }
 
 struct proc_mounts {
-	struct seq_file m;
 	struct mnt_namespace *ns;
 	struct path root;
 	int (*show)(struct seq_file *, struct vfsmount *);
@@ -127,8 +126,6 @@
 	loff_t cached_index;
 };
 
-#define proc_mounts(p) (container_of((p), struct proc_mounts, m))
-
 extern const struct seq_operations mounts_op;
 
 extern bool __is_local_mountpoint(struct dentry *dentry);
diff --git a/fs/namei.c b/fs/namei.c
index 2dad0ea..ae4e4c1 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -792,7 +792,7 @@
 	get_fs_root(current->fs, &nd->root);
 }
 
-static unsigned set_root_rcu(struct nameidata *nd)
+static void set_root_rcu(struct nameidata *nd)
 {
 	struct fs_struct *fs = current->fs;
 	unsigned seq;
@@ -802,7 +802,6 @@
 		nd->root = fs->root;
 		nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq);
 	} while (read_seqcount_retry(&fs->seq, seq));
-	return nd->root_seq;
 }
 
 static void path_put_conditional(struct path *path, struct nameidata *nd)
@@ -1998,7 +1997,8 @@
 	if (*s == '/') {
 		if (flags & LOOKUP_RCU) {
 			rcu_read_lock();
-			nd->seq = set_root_rcu(nd);
+			set_root_rcu(nd);
+			nd->seq = nd->root_seq;
 		} else {
 			set_root(nd);
 			path_get(&nd->root);
diff --git a/fs/namespace.c b/fs/namespace.c
index 9c1c43d..c7cb8a5 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1226,7 +1226,7 @@
 /* iterator; we want it to have access to namespace_sem, thus here... */
 static void *m_start(struct seq_file *m, loff_t *pos)
 {
-	struct proc_mounts *p = proc_mounts(m);
+	struct proc_mounts *p = m->private;
 
 	down_read(&namespace_sem);
 	if (p->cached_event == p->ns->event) {
@@ -1247,7 +1247,7 @@
 
 static void *m_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct proc_mounts *p = proc_mounts(m);
+	struct proc_mounts *p = m->private;
 
 	p->cached_mount = seq_list_next(v, &p->ns->list, pos);
 	p->cached_index = *pos;
@@ -1261,7 +1261,7 @@
 
 static int m_show(struct seq_file *m, void *v)
 {
-	struct proc_mounts *p = proc_mounts(m);
+	struct proc_mounts *p = m->private;
 	struct mount *r = list_entry(v, struct mount, mnt_list);
 	return p->show(m, &r->mnt);
 }
@@ -2343,6 +2343,8 @@
 	return err;
 }
 
+static bool fs_fully_visible(struct file_system_type *fs_type, int *new_mnt_flags);
+
 /*
  * create a new mount for userspace and request it to be added into the
  * namespace's tree
@@ -2374,6 +2376,10 @@
 			flags |= MS_NODEV;
 			mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV;
 		}
+		if (type->fs_flags & FS_USERNS_VISIBLE) {
+			if (!fs_fully_visible(type, &mnt_flags))
+				return -EPERM;
+		}
 	}
 
 	mnt = vfs_kern_mount(type, flags, name, data);
@@ -3175,9 +3181,10 @@
 	return chrooted;
 }
 
-bool fs_fully_visible(struct file_system_type *type)
+static bool fs_fully_visible(struct file_system_type *type, int *new_mnt_flags)
 {
 	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
+	int new_flags = *new_mnt_flags;
 	struct mount *mnt;
 	bool visible = false;
 
@@ -3196,16 +3203,36 @@
 		if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root)
 			continue;
 
-		/* This mount is not fully visible if there are any child mounts
-		 * that cover anything except for empty directories.
+		/* Verify the mount flags are equal to or more permissive
+		 * than the proposed new mount.
+		 */
+		if ((mnt->mnt.mnt_flags & MNT_LOCK_READONLY) &&
+		    !(new_flags & MNT_READONLY))
+			continue;
+		if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) &&
+		    !(new_flags & MNT_NODEV))
+			continue;
+		if ((mnt->mnt.mnt_flags & MNT_LOCK_ATIME) &&
+		    ((mnt->mnt.mnt_flags & MNT_ATIME_MASK) != (new_flags & MNT_ATIME_MASK)))
+			continue;
+
+		/* This mount is not fully visible if there are any
+		 * locked child mounts that cover anything except for
+		 * empty directories.
 		 */
 		list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
 			struct inode *inode = child->mnt_mountpoint->d_inode;
-			if (!S_ISDIR(inode->i_mode))
-				goto next;
-			if (inode->i_nlink > 2)
+			/* Only worry about locked mounts */
+			if (!(mnt->mnt.mnt_flags & MNT_LOCKED))
+				continue;
+			/* Is the directory permanetly empty? */
+			if (!is_empty_dir_inode(inode))
 				goto next;
 		}
+		/* Preserve the locked attributes */
+		*new_mnt_flags |= mnt->mnt.mnt_flags & (MNT_LOCK_READONLY | \
+							MNT_LOCK_NODEV    | \
+							MNT_LOCK_ATIME);
 		visible = true;
 		goto found;
 	next:	;
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index 80021c7..93575e9 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -1145,6 +1145,8 @@
 		case 0x00:
 			ncp_dbg(1, "renamed %pd -> %pd\n",
 				old_dentry, new_dentry);
+			ncp_d_prune(old_dentry);
+			ncp_d_prune(new_dentry);
 			break;
 		case 0x9E:
 			error = -ENAMETOOLONG;
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 8d129bb..682529c 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -458,7 +458,7 @@
  * pg_authenticate method for nfsv4 callback threads.
  *
  * The authflavor has been negotiated, so an incorrect flavor is a server
- * bug. Drop packets with incorrect authflavor.
+ * bug. Deny packets with incorrect authflavor.
  *
  * All other checking done after NFS decoding where the nfs_client can be
  * found in nfs4_callback_compound
@@ -468,12 +468,12 @@
 	switch (rqstp->rq_authop->flavour) {
 	case RPC_AUTH_NULL:
 		if (rqstp->rq_proc != CB_NULL)
-			return SVC_DROP;
+			return SVC_DENIED;
 		break;
 	case RPC_AUTH_GSS:
 		/* No RPC_AUTH_GSS support yet in NFSv4.1 */
 		 if (svc_is_backchannel(rqstp))
-			return SVC_DROP;
+			return SVC_DENIED;
 	}
 	return SVC_OK;
 }
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 197806f..29e3c1b 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -327,10 +327,8 @@
 	dprintk("%s slot table seqid: %u\n", __func__, slot->seq_nr);
 
 	/* Normal */
-	if (likely(args->csa_sequenceid == slot->seq_nr + 1)) {
-		slot->seq_nr++;
+	if (likely(args->csa_sequenceid == slot->seq_nr + 1))
 		goto out_ok;
-	}
 
 	/* Replay */
 	if (args->csa_sequenceid == slot->seq_nr) {
@@ -418,6 +416,7 @@
 			      struct cb_process_state *cps)
 {
 	struct nfs4_slot_table *tbl;
+	struct nfs4_slot *slot;
 	struct nfs_client *clp;
 	int i;
 	__be32 status = htonl(NFS4ERR_BADSESSION);
@@ -429,25 +428,32 @@
 
 	if (!(clp->cl_session->flags & SESSION4_BACK_CHAN))
 		goto out;
+
 	tbl = &clp->cl_session->bc_slot_table;
+	slot = tbl->slots + args->csa_slotid;
 
 	spin_lock(&tbl->slot_tbl_lock);
 	/* state manager is resetting the session */
 	if (test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state)) {
-		spin_unlock(&tbl->slot_tbl_lock);
 		status = htonl(NFS4ERR_DELAY);
 		/* Return NFS4ERR_BADSESSION if we're draining the session
 		 * in order to reset it.
 		 */
 		if (test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state))
 			status = htonl(NFS4ERR_BADSESSION);
-		goto out;
+		goto out_unlock;
 	}
 
-	status = validate_seqid(&clp->cl_session->bc_slot_table, args);
-	spin_unlock(&tbl->slot_tbl_lock);
+	memcpy(&res->csr_sessionid, &args->csa_sessionid,
+	       sizeof(res->csr_sessionid));
+	res->csr_sequenceid = args->csa_sequenceid;
+	res->csr_slotid = args->csa_slotid;
+	res->csr_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
+	res->csr_target_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
+
+	status = validate_seqid(tbl, args);
 	if (status)
-		goto out;
+		goto out_unlock;
 
 	cps->slotid = args->csa_slotid;
 
@@ -458,15 +464,17 @@
 	 */
 	if (referring_call_exists(clp, args->csa_nrclists, args->csa_rclists)) {
 		status = htonl(NFS4ERR_DELAY);
-		goto out;
+		goto out_unlock;
 	}
 
-	memcpy(&res->csr_sessionid, &args->csa_sessionid,
-	       sizeof(res->csr_sessionid));
-	res->csr_sequenceid = args->csa_sequenceid;
-	res->csr_slotid = args->csa_slotid;
-	res->csr_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
-	res->csr_target_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
+	/*
+	 * RFC5661 20.9.3
+	 * If CB_SEQUENCE returns an error, then the state of the slot
+	 * (sequence ID, cached reply) MUST NOT change.
+	 */
+	slot->seq_nr++;
+out_unlock:
+	spin_unlock(&tbl->slot_tbl_lock);
 
 out:
 	cps->clp = clp; /* put in nfs4_callback_compound */
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 19ca95c..6b1697a 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -909,7 +909,7 @@
 	xdr_init_encode(&xdr_out, &rqstp->rq_res, p);
 
 	status = decode_compound_hdr_arg(&xdr_in, &hdr_arg);
-	if (status == __constant_htonl(NFS4ERR_RESOURCE))
+	if (status == htonl(NFS4ERR_RESOURCE))
 		return rpc_garbage_args;
 
 	if (hdr_arg.minorversion == 0) {
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 892aeff..ecebb40 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -825,7 +825,6 @@
  * Load up the server record from information gained in an fsinfo record
  */
 static void nfs_server_set_fsinfo(struct nfs_server *server,
-				  struct nfs_fh *mntfh,
 				  struct nfs_fsinfo *fsinfo)
 {
 	unsigned long max_rpc_payload;
@@ -901,7 +900,7 @@
 	if (error < 0)
 		goto out_error;
 
-	nfs_server_set_fsinfo(server, mntfh, &fsinfo);
+	nfs_server_set_fsinfo(server, &fsinfo);
 
 	/* Get some general file system info */
 	if (server->namelen == 0) {
@@ -1193,8 +1192,6 @@
 }
 
 #ifdef CONFIG_PROC_FS
-static struct proc_dir_entry *proc_fs_nfs;
-
 static int nfs_server_list_open(struct inode *inode, struct file *file);
 static void *nfs_server_list_start(struct seq_file *p, loff_t *pos);
 static void *nfs_server_list_next(struct seq_file *p, void *v, loff_t *pos);
@@ -1364,27 +1361,29 @@
 {
 	struct nfs_server *server;
 	struct nfs_client *clp;
-	char dev[8], fsid[17];
+	char dev[13];	// 8 for 2^24, 1 for ':', 3 for 2^8, 1 for '\0'
+	char fsid[34];	// 2 * 16 for %llx, 1 for ':', 1 for '\0'
 	struct nfs_net *nn = net_generic(seq_file_net(m), nfs_net_id);
 
 	/* display header on line 1 */
 	if (v == &nn->nfs_volume_list) {
-		seq_puts(m, "NV SERVER   PORT DEV     FSID              FSC\n");
+		seq_puts(m, "NV SERVER   PORT DEV          FSID"
+			    "                              FSC\n");
 		return 0;
 	}
 	/* display one transport per line on subsequent lines */
 	server = list_entry(v, struct nfs_server, master_link);
 	clp = server->nfs_client;
 
-	snprintf(dev, 8, "%u:%u",
+	snprintf(dev, sizeof(dev), "%u:%u",
 		 MAJOR(server->s_dev), MINOR(server->s_dev));
 
-	snprintf(fsid, 17, "%llx:%llx",
+	snprintf(fsid, sizeof(fsid), "%llx:%llx",
 		 (unsigned long long) server->fsid.major,
 		 (unsigned long long) server->fsid.minor);
 
 	rcu_read_lock();
-	seq_printf(m, "v%u %s %s %-7s %-17s %s\n",
+	seq_printf(m, "v%u %s %s %-12s %-33s %s\n",
 		   clp->rpc_ops->version,
 		   rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_ADDR),
 		   rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_PORT),
@@ -1434,27 +1433,20 @@
  */
 int __init nfs_fs_proc_init(void)
 {
-	struct proc_dir_entry *p;
-
-	proc_fs_nfs = proc_mkdir("fs/nfsfs", NULL);
-	if (!proc_fs_nfs)
+	if (!proc_mkdir("fs/nfsfs", NULL))
 		goto error_0;
 
 	/* a file of servers with which we're dealing */
-	p = proc_symlink("servers", proc_fs_nfs, "../../net/nfsfs/servers");
-	if (!p)
+	if (!proc_symlink("fs/nfsfs/servers", NULL, "../../net/nfsfs/servers"))
 		goto error_1;
 
 	/* a file of volumes that we have mounted */
-	p = proc_symlink("volumes", proc_fs_nfs, "../../net/nfsfs/volumes");
-	if (!p)
-		goto error_2;
-	return 0;
+	if (!proc_symlink("fs/nfsfs/volumes", NULL, "../../net/nfsfs/volumes"))
+		goto error_1;
 
-error_2:
-	remove_proc_entry("servers", proc_fs_nfs);
+	return 0;
 error_1:
-	remove_proc_entry("fs/nfsfs", NULL);
+	remove_proc_subtree("fs/nfsfs", NULL);
 error_0:
 	return -ENOMEM;
 }
@@ -1464,9 +1456,7 @@
  */
 void nfs_fs_proc_exit(void)
 {
-	remove_proc_entry("volumes", proc_fs_nfs);
-	remove_proc_entry("servers", proc_fs_nfs);
-	remove_proc_entry("fs/nfsfs", NULL);
+	remove_proc_subtree("fs/nfsfs", NULL);
 }
 
 #endif /* CONFIG_PROC_FS */
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index b2c8b31..547308a 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1470,9 +1470,6 @@
 {
 	int err;
 
-	if ((open_flags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
-		*opened |= FILE_CREATED;
-
 	err = finish_open(file, dentry, do_open, opened);
 	if (err)
 		goto out;
@@ -1771,7 +1768,7 @@
 
 static void nfs_dentry_handle_enoent(struct dentry *dentry)
 {
-	if (d_really_is_positive(dentry) && !d_unhashed(dentry))
+	if (simple_positive(dentry))
 		d_delete(dentry);
 }
 
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 8b8d83a..cc4fa1e 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -555,31 +555,22 @@
 	return nfs_wb_page(inode, page);
 }
 
-#ifdef CONFIG_NFS_SWAP
 static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 						sector_t *span)
 {
-	int ret;
 	struct rpc_clnt *clnt = NFS_CLIENT(file->f_mapping->host);
 
 	*span = sis->pages;
 
-	rcu_read_lock();
-	ret = xs_swapper(rcu_dereference(clnt->cl_xprt), 1);
-	rcu_read_unlock();
-
-	return ret;
+	return rpc_clnt_swap_activate(clnt);
 }
 
 static void nfs_swap_deactivate(struct file *file)
 {
 	struct rpc_clnt *clnt = NFS_CLIENT(file->f_mapping->host);
 
-	rcu_read_lock();
-	xs_swapper(rcu_dereference(clnt->cl_xprt), 0);
-	rcu_read_unlock();
+	rpc_clnt_swap_deactivate(clnt);
 }
-#endif
 
 const struct address_space_operations nfs_file_aops = {
 	.readpage = nfs_readpage,
@@ -596,10 +587,8 @@
 	.launder_page = nfs_launder_page,
 	.is_dirty_writeback = nfs_check_dirty_writeback,
 	.error_remove_page = generic_error_remove_page,
-#ifdef CONFIG_NFS_SWAP
 	.swap_activate = nfs_swap_activate,
 	.swap_deactivate = nfs_swap_deactivate,
-#endif
 };
 
 /*
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 7d05089..c12951b 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -20,6 +20,7 @@
 #include "../nfs4trace.h"
 #include "../iostat.h"
 #include "../nfs.h"
+#include "../nfs42.h"
 
 #define NFSDBG_FACILITY         NFSDBG_PNFS_LD
 
@@ -182,17 +183,14 @@
 
 static void ff_layout_sort_mirrors(struct nfs4_ff_layout_segment *fls)
 {
-	struct nfs4_ff_layout_mirror *tmp;
 	int i, j;
 
 	for (i = 0; i < fls->mirror_array_cnt - 1; i++) {
 		for (j = i + 1; j < fls->mirror_array_cnt; j++)
 			if (fls->mirror_array[i]->efficiency <
-			    fls->mirror_array[j]->efficiency) {
-				tmp = fls->mirror_array[i];
-				fls->mirror_array[i] = fls->mirror_array[j];
-				fls->mirror_array[j] = tmp;
-			}
+			    fls->mirror_array[j]->efficiency)
+				swap(fls->mirror_array[i],
+				     fls->mirror_array[j]);
 	}
 }
 
@@ -274,6 +272,7 @@
 
 		spin_lock_init(&fls->mirror_array[i]->lock);
 		fls->mirror_array[i]->ds_count = ds_count;
+		fls->mirror_array[i]->lseg = &fls->generic_hdr;
 
 		/* deviceid */
 		rc = decode_deviceid(&stream, &devid);
@@ -344,6 +343,10 @@
 			fls->mirror_array[i]->gid);
 	}
 
+	p = xdr_inline_decode(&stream, 4);
+	if (p)
+		fls->flags = be32_to_cpup(p);
+
 	ff_layout_sort_mirrors(fls);
 	rc = ff_layout_check_layout(lgr);
 	if (rc)
@@ -415,6 +418,146 @@
 	return 1;
 }
 
+static void
+nfs4_ff_start_busy_timer(struct nfs4_ff_busy_timer *timer)
+{
+	/* first IO request? */
+	if (atomic_inc_return(&timer->n_ops) == 1) {
+		timer->start_time = ktime_get();
+	}
+}
+
+static ktime_t
+nfs4_ff_end_busy_timer(struct nfs4_ff_busy_timer *timer)
+{
+	ktime_t start, now;
+
+	if (atomic_dec_return(&timer->n_ops) < 0)
+		WARN_ON_ONCE(1);
+
+	now = ktime_get();
+	start = timer->start_time;
+	timer->start_time = now;
+	return ktime_sub(now, start);
+}
+
+static ktime_t
+nfs4_ff_layout_calc_completion_time(struct rpc_task *task)
+{
+	return ktime_sub(ktime_get(), task->tk_start);
+}
+
+static bool
+nfs4_ff_layoutstat_start_io(struct nfs4_ff_layout_mirror *mirror,
+			    struct nfs4_ff_layoutstat *layoutstat)
+{
+	static const ktime_t notime = {0};
+	ktime_t now = ktime_get();
+
+	nfs4_ff_start_busy_timer(&layoutstat->busy_timer);
+	if (ktime_equal(mirror->start_time, notime))
+		mirror->start_time = now;
+	if (ktime_equal(mirror->last_report_time, notime))
+		mirror->last_report_time = now;
+	if (ktime_to_ms(ktime_sub(now, mirror->last_report_time)) >=
+			FF_LAYOUTSTATS_REPORT_INTERVAL) {
+		mirror->last_report_time = now;
+		return true;
+	}
+
+	return false;
+}
+
+static void
+nfs4_ff_layout_stat_io_update_requested(struct nfs4_ff_layoutstat *layoutstat,
+		__u64 requested)
+{
+	struct nfs4_ff_io_stat *iostat = &layoutstat->io_stat;
+
+	iostat->ops_requested++;
+	iostat->bytes_requested += requested;
+}
+
+static void
+nfs4_ff_layout_stat_io_update_completed(struct nfs4_ff_layoutstat *layoutstat,
+		__u64 requested,
+		__u64 completed,
+		ktime_t time_completed)
+{
+	struct nfs4_ff_io_stat *iostat = &layoutstat->io_stat;
+	ktime_t timer;
+
+	iostat->ops_completed++;
+	iostat->bytes_completed += completed;
+	iostat->bytes_not_delivered += requested - completed;
+
+	timer = nfs4_ff_end_busy_timer(&layoutstat->busy_timer);
+	iostat->total_busy_time =
+			ktime_add(iostat->total_busy_time, timer);
+	iostat->aggregate_completion_time =
+			ktime_add(iostat->aggregate_completion_time, time_completed);
+}
+
+static void
+nfs4_ff_layout_stat_io_start_read(struct nfs4_ff_layout_mirror *mirror,
+		__u64 requested)
+{
+	bool report;
+
+	spin_lock(&mirror->lock);
+	report = nfs4_ff_layoutstat_start_io(mirror, &mirror->read_stat);
+	nfs4_ff_layout_stat_io_update_requested(&mirror->read_stat, requested);
+	spin_unlock(&mirror->lock);
+
+	if (report)
+		pnfs_report_layoutstat(mirror->lseg->pls_layout->plh_inode);
+}
+
+static void
+nfs4_ff_layout_stat_io_end_read(struct rpc_task *task,
+		struct nfs4_ff_layout_mirror *mirror,
+		__u64 requested,
+		__u64 completed)
+{
+	spin_lock(&mirror->lock);
+	nfs4_ff_layout_stat_io_update_completed(&mirror->read_stat,
+			requested, completed,
+			nfs4_ff_layout_calc_completion_time(task));
+	spin_unlock(&mirror->lock);
+}
+
+static void
+nfs4_ff_layout_stat_io_start_write(struct nfs4_ff_layout_mirror *mirror,
+		__u64 requested)
+{
+	bool report;
+
+	spin_lock(&mirror->lock);
+	report = nfs4_ff_layoutstat_start_io(mirror , &mirror->write_stat);
+	nfs4_ff_layout_stat_io_update_requested(&mirror->write_stat, requested);
+	spin_unlock(&mirror->lock);
+
+	if (report)
+		pnfs_report_layoutstat(mirror->lseg->pls_layout->plh_inode);
+}
+
+static void
+nfs4_ff_layout_stat_io_end_write(struct rpc_task *task,
+		struct nfs4_ff_layout_mirror *mirror,
+		__u64 requested,
+		__u64 completed,
+		enum nfs3_stable_how committed)
+{
+	if (committed == NFS_UNSTABLE)
+		requested = completed = 0;
+
+	spin_lock(&mirror->lock);
+	nfs4_ff_layout_stat_io_update_completed(&mirror->write_stat,
+			requested, completed,
+			nfs4_ff_layout_calc_completion_time(task));
+	spin_unlock(&mirror->lock);
+}
+
 static int
 ff_layout_alloc_commit_info(struct pnfs_layout_segment *lseg,
 			    struct nfs_commit_info *cinfo,
@@ -631,7 +774,7 @@
 			nfs_direct_set_resched_writes(hdr->dreq);
 			/* fake unstable write to let common nfs resend pages */
 			hdr->verf.committed = NFS_UNSTABLE;
-			hdr->good_bytes = 0;
+			hdr->good_bytes = hdr->args.count;
 		}
 		return;
 	}
@@ -879,6 +1022,12 @@
 	return 0;
 }
 
+static bool
+ff_layout_need_layoutcommit(struct pnfs_layout_segment *lseg)
+{
+	return !(FF_LAYOUT_LSEG(lseg)->flags & FF_FLAGS_NO_LAYOUTCOMMIT);
+}
+
 /*
  * We reference the rpc_cred of the first WRITE that triggers the need for
  * a LAYOUTCOMMIT, and use it to send the layoutcommit compound.
@@ -891,6 +1040,9 @@
 static void
 ff_layout_set_layoutcommit(struct nfs_pgio_header *hdr)
 {
+	if (!ff_layout_need_layoutcommit(hdr->lseg))
+		return;
+
 	pnfs_set_layoutcommit(hdr->inode, hdr->lseg,
 			hdr->mds_offset + hdr->res.count);
 	dprintk("%s inode %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino,
@@ -909,6 +1061,10 @@
 static int ff_layout_read_prepare_common(struct rpc_task *task,
 					 struct nfs_pgio_header *hdr)
 {
+	nfs4_ff_layout_stat_io_start_read(
+			FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx),
+			hdr->args.count);
+
 	if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) {
 		rpc_exit(task, -EIO);
 		return -EIO;
@@ -962,15 +1118,15 @@
 {
 	struct nfs_pgio_header *hdr = data;
 
-	if (ff_layout_read_prepare_common(task, hdr))
-		return;
-
 	if (ff_layout_setup_sequence(hdr->ds_clp,
 				     &hdr->args.seq_args,
 				     &hdr->res.seq_res,
 				     task))
 		return;
 
+	if (ff_layout_read_prepare_common(task, hdr))
+		return;
+
 	if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context,
 			hdr->args.lock_context, FMODE_READ) == -EIO)
 		rpc_exit(task, -EIO); /* lost lock, terminate I/O */
@@ -982,6 +1138,10 @@
 
 	dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status);
 
+	nfs4_ff_layout_stat_io_end_read(task,
+			FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx),
+			hdr->args.count, hdr->res.count);
+
 	if (test_bit(NFS_IOHDR_REDO, &hdr->flags) &&
 	    task->tk_status == 0) {
 		nfs4_sequence_done(task, &hdr->res.seq_res);
@@ -1074,7 +1234,8 @@
 		return -EAGAIN;
 	}
 
-	if (data->verf.committed == NFS_UNSTABLE)
+	if (data->verf.committed == NFS_UNSTABLE
+	    && ff_layout_need_layoutcommit(data->lseg))
 		pnfs_set_layoutcommit(data->inode, data->lseg, data->lwb);
 
 	return 0;
@@ -1083,6 +1244,10 @@
 static int ff_layout_write_prepare_common(struct rpc_task *task,
 					  struct nfs_pgio_header *hdr)
 {
+	nfs4_ff_layout_stat_io_start_write(
+			FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx),
+			hdr->args.count);
+
 	if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) {
 		rpc_exit(task, -EIO);
 		return -EIO;
@@ -1116,15 +1281,15 @@
 {
 	struct nfs_pgio_header *hdr = data;
 
-	if (ff_layout_write_prepare_common(task, hdr))
-		return;
-
 	if (ff_layout_setup_sequence(hdr->ds_clp,
 				     &hdr->args.seq_args,
 				     &hdr->res.seq_res,
 				     task))
 		return;
 
+	if (ff_layout_write_prepare_common(task, hdr))
+		return;
+
 	if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context,
 			hdr->args.lock_context, FMODE_WRITE) == -EIO)
 		rpc_exit(task, -EIO); /* lost lock, terminate I/O */
@@ -1134,6 +1299,11 @@
 {
 	struct nfs_pgio_header *hdr = data;
 
+	nfs4_ff_layout_stat_io_end_write(task,
+			FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx),
+			hdr->args.count, hdr->res.count,
+			hdr->res.verf->committed);
+
 	if (test_bit(NFS_IOHDR_REDO, &hdr->flags) &&
 	    task->tk_status == 0) {
 		nfs4_sequence_done(task, &hdr->res.seq_res);
@@ -1152,8 +1322,17 @@
 	    &NFS_CLIENT(hdr->inode)->cl_metrics[NFSPROC4_CLNT_WRITE]);
 }
 
+static void ff_layout_commit_prepare_common(struct rpc_task *task,
+		struct nfs_commit_data *cdata)
+{
+	nfs4_ff_layout_stat_io_start_write(
+			FF_LAYOUT_COMP(cdata->lseg, cdata->ds_commit_index),
+			0);
+}
+
 static void ff_layout_commit_prepare_v3(struct rpc_task *task, void *data)
 {
+	ff_layout_commit_prepare_common(task, data);
 	rpc_call_start(task);
 }
 
@@ -1161,10 +1340,30 @@
 {
 	struct nfs_commit_data *wdata = data;
 
-	ff_layout_setup_sequence(wdata->ds_clp,
+	if (ff_layout_setup_sequence(wdata->ds_clp,
 				 &wdata->args.seq_args,
 				 &wdata->res.seq_res,
-				 task);
+				 task))
+		return;
+	ff_layout_commit_prepare_common(task, data);
+}
+
+static void ff_layout_commit_done(struct rpc_task *task, void *data)
+{
+	struct nfs_commit_data *cdata = data;
+	struct nfs_page *req;
+	__u64 count = 0;
+
+	if (task->tk_status == 0) {
+		list_for_each_entry(req, &cdata->pages, wb_list)
+			count += req->wb_bytes;
+	}
+
+	nfs4_ff_layout_stat_io_end_write(task,
+			FF_LAYOUT_COMP(cdata->lseg, cdata->ds_commit_index),
+			count, count, NFS_FILE_SYNC);
+
+	pnfs_generic_write_commit_done(task, data);
 }
 
 static void ff_layout_commit_count_stats(struct rpc_task *task, void *data)
@@ -1205,14 +1404,14 @@
 
 static const struct rpc_call_ops ff_layout_commit_call_ops_v3 = {
 	.rpc_call_prepare = ff_layout_commit_prepare_v3,
-	.rpc_call_done = pnfs_generic_write_commit_done,
+	.rpc_call_done = ff_layout_commit_done,
 	.rpc_count_stats = ff_layout_commit_count_stats,
 	.rpc_release = pnfs_generic_commit_release,
 };
 
 static const struct rpc_call_ops ff_layout_commit_call_ops_v4 = {
 	.rpc_call_prepare = ff_layout_commit_prepare_v4,
-	.rpc_call_done = pnfs_generic_write_commit_done,
+	.rpc_call_done = ff_layout_commit_done,
 	.rpc_count_stats = ff_layout_commit_count_stats,
 	.rpc_release = pnfs_generic_commit_release,
 };
@@ -1256,7 +1455,6 @@
 	fh = nfs4_ff_layout_select_ds_fh(lseg, idx);
 	if (fh)
 		hdr->args.fh = fh;
-
 	/*
 	 * Note that if we ever decide to split across DSes,
 	 * then we may need to handle dense-like offsets.
@@ -1385,6 +1583,7 @@
 	fh = select_ds_fh_from_commit(lseg, data->ds_commit_index);
 	if (fh)
 		data->args.fh = fh;
+
 	return nfs_initiate_commit(ds_clnt, data, ds->ds_clp->rpc_ops,
 				   vers == 3 ? &ff_layout_commit_call_ops_v3 :
 					       &ff_layout_commit_call_ops_v4,
@@ -1488,6 +1687,247 @@
 	dprintk("%s: Return\n", __func__);
 }
 
+static int
+ff_layout_ntop4(const struct sockaddr *sap, char *buf, const size_t buflen)
+{
+	const struct sockaddr_in *sin = (struct sockaddr_in *)sap;
+
+	return snprintf(buf, buflen, "%pI4", &sin->sin_addr);
+}
+
+static size_t
+ff_layout_ntop6_noscopeid(const struct sockaddr *sap, char *buf,
+			  const int buflen)
+{
+	const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
+	const struct in6_addr *addr = &sin6->sin6_addr;
+
+	/*
+	 * RFC 4291, Section 2.2.2
+	 *
+	 * Shorthanded ANY address
+	 */
+	if (ipv6_addr_any(addr))
+		return snprintf(buf, buflen, "::");
+
+	/*
+	 * RFC 4291, Section 2.2.2
+	 *
+	 * Shorthanded loopback address
+	 */
+	if (ipv6_addr_loopback(addr))
+		return snprintf(buf, buflen, "::1");
+
+	/*
+	 * RFC 4291, Section 2.2.3
+	 *
+	 * Special presentation address format for mapped v4
+	 * addresses.
+	 */
+	if (ipv6_addr_v4mapped(addr))
+		return snprintf(buf, buflen, "::ffff:%pI4",
+					&addr->s6_addr32[3]);
+
+	/*
+	 * RFC 4291, Section 2.2.1
+	 */
+	return snprintf(buf, buflen, "%pI6c", addr);
+}
+
+/* Derived from rpc_sockaddr2uaddr */
+static void
+ff_layout_encode_netaddr(struct xdr_stream *xdr, struct nfs4_pnfs_ds_addr *da)
+{
+	struct sockaddr *sap = (struct sockaddr *)&da->da_addr;
+	char portbuf[RPCBIND_MAXUADDRPLEN];
+	char addrbuf[RPCBIND_MAXUADDRLEN];
+	char *netid;
+	unsigned short port;
+	int len, netid_len;
+	__be32 *p;
+
+	switch (sap->sa_family) {
+	case AF_INET:
+		if (ff_layout_ntop4(sap, addrbuf, sizeof(addrbuf)) == 0)
+			return;
+		port = ntohs(((struct sockaddr_in *)sap)->sin_port);
+		netid = "tcp";
+		netid_len = 3;
+		break;
+	case AF_INET6:
+		if (ff_layout_ntop6_noscopeid(sap, addrbuf, sizeof(addrbuf)) == 0)
+			return;
+		port = ntohs(((struct sockaddr_in6 *)sap)->sin6_port);
+		netid = "tcp6";
+		netid_len = 4;
+		break;
+	default:
+		/* we only support tcp and tcp6 */
+		WARN_ON_ONCE(1);
+		return;
+	}
+
+	snprintf(portbuf, sizeof(portbuf), ".%u.%u", port >> 8, port & 0xff);
+	len = strlcat(addrbuf, portbuf, sizeof(addrbuf));
+
+	p = xdr_reserve_space(xdr, 4 + netid_len);
+	xdr_encode_opaque(p, netid, netid_len);
+
+	p = xdr_reserve_space(xdr, 4 + len);
+	xdr_encode_opaque(p, addrbuf, len);
+}
+
+static void
+ff_layout_encode_nfstime(struct xdr_stream *xdr,
+			 ktime_t t)
+{
+	struct timespec64 ts;
+	__be32 *p;
+
+	p = xdr_reserve_space(xdr, 12);
+	ts = ktime_to_timespec64(t);
+	p = xdr_encode_hyper(p, ts.tv_sec);
+	*p++ = cpu_to_be32(ts.tv_nsec);
+}
+
+static void
+ff_layout_encode_io_latency(struct xdr_stream *xdr,
+			    struct nfs4_ff_io_stat *stat)
+{
+	__be32 *p;
+
+	p = xdr_reserve_space(xdr, 5 * 8);
+	p = xdr_encode_hyper(p, stat->ops_requested);
+	p = xdr_encode_hyper(p, stat->bytes_requested);
+	p = xdr_encode_hyper(p, stat->ops_completed);
+	p = xdr_encode_hyper(p, stat->bytes_completed);
+	p = xdr_encode_hyper(p, stat->bytes_not_delivered);
+	ff_layout_encode_nfstime(xdr, stat->total_busy_time);
+	ff_layout_encode_nfstime(xdr, stat->aggregate_completion_time);
+}
+
+static void
+ff_layout_encode_layoutstats(struct xdr_stream *xdr,
+			     struct nfs42_layoutstat_args *args,
+			     struct nfs42_layoutstat_devinfo *devinfo)
+{
+	struct nfs4_ff_layout_mirror *mirror = devinfo->layout_private;
+	struct nfs4_pnfs_ds_addr *da;
+	struct nfs4_pnfs_ds *ds = mirror->mirror_ds->ds;
+	struct nfs_fh *fh = &mirror->fh_versions[0];
+	__be32 *p, *start;
+
+	da = list_first_entry(&ds->ds_addrs, struct nfs4_pnfs_ds_addr, da_node);
+	dprintk("%s: DS %s: encoding address %s\n",
+		__func__, ds->ds_remotestr, da->da_remotestr);
+	/* layoutupdate length */
+	start = xdr_reserve_space(xdr, 4);
+	/* netaddr4 */
+	ff_layout_encode_netaddr(xdr, da);
+	/* nfs_fh4 */
+	p = xdr_reserve_space(xdr, 4 + fh->size);
+	xdr_encode_opaque(p, fh->data, fh->size);
+	/* ff_io_latency4 read */
+	spin_lock(&mirror->lock);
+	ff_layout_encode_io_latency(xdr, &mirror->read_stat.io_stat);
+	/* ff_io_latency4 write */
+	ff_layout_encode_io_latency(xdr, &mirror->write_stat.io_stat);
+	spin_unlock(&mirror->lock);
+	/* nfstime4 */
+	ff_layout_encode_nfstime(xdr, ktime_sub(ktime_get(), mirror->start_time));
+	/* bool */
+	p = xdr_reserve_space(xdr, 4);
+	*p = cpu_to_be32(false);
+
+	*start = cpu_to_be32((xdr->p - start - 1) * 4);
+}
+
+static bool
+ff_layout_mirror_prepare_stats(struct nfs42_layoutstat_args *args,
+			       struct pnfs_layout_segment *pls,
+			       int *dev_count, int dev_limit)
+{
+	struct nfs4_ff_layout_mirror *mirror;
+	struct nfs4_deviceid_node *dev;
+	struct nfs42_layoutstat_devinfo *devinfo;
+	int i;
+
+	for (i = 0; i <= FF_LAYOUT_MIRROR_COUNT(pls); i++) {
+		if (*dev_count >= dev_limit)
+			break;
+		mirror = FF_LAYOUT_COMP(pls, i);
+		if (!mirror || !mirror->mirror_ds)
+			continue;
+		dev = FF_LAYOUT_DEVID_NODE(pls, i);
+		devinfo = &args->devinfo[*dev_count];
+		memcpy(&devinfo->dev_id, &dev->deviceid, NFS4_DEVICEID4_SIZE);
+		devinfo->offset = pls->pls_range.offset;
+		devinfo->length = pls->pls_range.length;
+		/* well, we don't really know if IO is continuous or not! */
+		devinfo->read_count = mirror->read_stat.io_stat.bytes_completed;
+		devinfo->read_bytes = mirror->read_stat.io_stat.bytes_completed;
+		devinfo->write_count = mirror->write_stat.io_stat.bytes_completed;
+		devinfo->write_bytes = mirror->write_stat.io_stat.bytes_completed;
+		devinfo->layout_type = LAYOUT_FLEX_FILES;
+		devinfo->layoutstats_encode = ff_layout_encode_layoutstats;
+		devinfo->layout_private = mirror;
+		/* lseg refcount put in cleanup_layoutstats */
+		pnfs_get_lseg(pls);
+
+		++(*dev_count);
+	}
+
+	return *dev_count < dev_limit;
+}
+
+static int
+ff_layout_prepare_layoutstats(struct nfs42_layoutstat_args *args)
+{
+	struct pnfs_layout_segment *pls;
+	int dev_count = 0;
+
+	spin_lock(&args->inode->i_lock);
+	list_for_each_entry(pls, &NFS_I(args->inode)->layout->plh_segs, pls_list) {
+		dev_count += FF_LAYOUT_MIRROR_COUNT(pls);
+	}
+	spin_unlock(&args->inode->i_lock);
+	/* For now, send at most PNFS_LAYOUTSTATS_MAXDEV statistics */
+	if (dev_count > PNFS_LAYOUTSTATS_MAXDEV) {
+		dprintk("%s: truncating devinfo to limit (%d:%d)\n",
+			__func__, dev_count, PNFS_LAYOUTSTATS_MAXDEV);
+		dev_count = PNFS_LAYOUTSTATS_MAXDEV;
+	}
+	args->devinfo = kmalloc(dev_count * sizeof(*args->devinfo), GFP_KERNEL);
+	if (!args->devinfo)
+		return -ENOMEM;
+
+	dev_count = 0;
+	spin_lock(&args->inode->i_lock);
+	list_for_each_entry(pls, &NFS_I(args->inode)->layout->plh_segs, pls_list) {
+		if (!ff_layout_mirror_prepare_stats(args, pls, &dev_count,
+						    PNFS_LAYOUTSTATS_MAXDEV)) {
+			break;
+		}
+	}
+	spin_unlock(&args->inode->i_lock);
+	args->num_dev = dev_count;
+
+	return 0;
+}
+
+static void
+ff_layout_cleanup_layoutstats(struct nfs42_layoutstat_data *data)
+{
+	struct nfs4_ff_layout_mirror *mirror;
+	int i;
+
+	for (i = 0; i < data->args.num_dev; i++) {
+		mirror = data->args.devinfo[i].layout_private;
+		data->args.devinfo[i].layout_private = NULL;
+		pnfs_put_lseg(mirror->lseg);
+	}
+}
+
 static struct pnfs_layoutdriver_type flexfilelayout_type = {
 	.id			= LAYOUT_FLEX_FILES,
 	.name			= "LAYOUT_FLEX_FILES",
@@ -1510,6 +1950,8 @@
 	.alloc_deviceid_node    = ff_layout_alloc_deviceid_node,
 	.encode_layoutreturn    = ff_layout_encode_layoutreturn,
 	.sync			= pnfs_nfs_generic_sync,
+	.prepare_layoutstats	= ff_layout_prepare_layoutstats,
+	.cleanup_layoutstats	= ff_layout_cleanup_layoutstats,
 };
 
 static int __init nfs4flexfilelayout_init(void)
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h
index 070f204..f92f9a0 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.h
+++ b/fs/nfs/flexfilelayout/flexfilelayout.h
@@ -9,12 +9,17 @@
 #ifndef FS_NFS_NFS4FLEXFILELAYOUT_H
 #define FS_NFS_NFS4FLEXFILELAYOUT_H
 
+#define FF_FLAGS_NO_LAYOUTCOMMIT 1
+
 #include "../pnfs.h"
 
 /* XXX: Let's filter out insanely large mirror count for now to avoid oom
  * due to network error etc. */
 #define NFS4_FLEXFILE_LAYOUT_MAX_MIRROR_CNT 4096
 
+/* LAYOUTSTATS report interval in ms */
+#define FF_LAYOUTSTATS_REPORT_INTERVAL (60000L)
+
 struct nfs4_ff_ds_version {
 	u32				version;
 	u32				minor_version;
@@ -41,24 +46,48 @@
 	struct nfs4_deviceid		deviceid;
 };
 
+struct nfs4_ff_io_stat {
+	__u64				ops_requested;
+	__u64				bytes_requested;
+	__u64				ops_completed;
+	__u64				bytes_completed;
+	__u64				bytes_not_delivered;
+	ktime_t				total_busy_time;
+	ktime_t				aggregate_completion_time;
+};
+
+struct nfs4_ff_busy_timer {
+	ktime_t start_time;
+	atomic_t n_ops;
+};
+
+struct nfs4_ff_layoutstat {
+	struct nfs4_ff_io_stat io_stat;
+	struct nfs4_ff_busy_timer busy_timer;
+};
+
 struct nfs4_ff_layout_mirror {
+	struct pnfs_layout_segment	*lseg; /* back pointer */
 	u32				ds_count;
 	u32				efficiency;
 	struct nfs4_ff_layout_ds	*mirror_ds;
 	u32				fh_versions_cnt;
 	struct nfs_fh			*fh_versions;
 	nfs4_stateid			stateid;
-	struct nfs4_string		user_name;
-	struct nfs4_string		group_name;
 	u32				uid;
 	u32				gid;
 	struct rpc_cred			*cred;
 	spinlock_t			lock;
+	struct nfs4_ff_layoutstat	read_stat;
+	struct nfs4_ff_layoutstat	write_stat;
+	ktime_t				start_time;
+	ktime_t				last_report_time;
 };
 
 struct nfs4_ff_layout_segment {
 	struct pnfs_layout_segment	generic_hdr;
 	u64				stripe_unit;
+	u32				flags;
 	u32				mirror_array_cnt;
 	struct nfs4_ff_layout_mirror	**mirror_array;
 };
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index 77a2d02..f13e196 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -324,7 +324,8 @@
 				__func__, PTR_ERR(cred));
 			return PTR_ERR(cred);
 		} else {
-			mirror->cred = cred;
+			if (cmpxchg(&mirror->cred, NULL, cred))
+				put_rpccred(cred);
 		}
 	}
 	return 0;
@@ -386,7 +387,7 @@
 	/* matching smp_wmb() in _nfs4_pnfs_v3/4_ds_connect */
 	smp_rmb();
 	if (ds->ds_clp)
-		goto out;
+		goto out_update_creds;
 
 	flavor = nfs4_ff_layout_choose_authflavor(mirror);
 
@@ -430,7 +431,7 @@
 			}
 		}
 	}
-
+out_update_creds:
 	if (ff_layout_update_mirror_cred(mirror, ds))
 		ds = NULL;
 out:
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index f734562..b77b328 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -678,6 +678,8 @@
 	if (!err) {
 		generic_fillattr(inode, stat);
 		stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode));
+		if (S_ISDIR(inode->i_mode))
+			stat->blksize = NFS_SERVER(inode)->dtsize;
 	}
 out:
 	trace_nfs_getattr_exit(inode, err);
@@ -2008,17 +2010,15 @@
 	if (err)
 		goto out1;
 
-#ifdef CONFIG_PROC_FS
 	rpc_proc_register(&init_net, &nfs_rpcstat);
-#endif
-	if ((err = register_nfs_fs()) != 0)
+
+	err = register_nfs_fs();
+	if (err)
 		goto out0;
 
 	return 0;
 out0:
-#ifdef CONFIG_PROC_FS
 	rpc_proc_unregister(&init_net, "nfs");
-#endif
 	nfs_destroy_directcache();
 out1:
 	nfs_destroy_writepagecache();
@@ -2049,9 +2049,7 @@
 	nfs_destroy_nfspagecache();
 	nfs_fscache_unregister();
 	unregister_pernet_subsys(&nfs_net_ops);
-#ifdef CONFIG_PROC_FS
 	rpc_proc_unregister(&init_net, "nfs");
-#endif
 	unregister_nfs_fs();
 	nfs_fs_proc_exit();
 	nfsiod_stop();
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 53852a4..9b04c2e 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -1342,7 +1342,7 @@
 	if (args->npages != 0)
 		xdr_write_pages(xdr, args->pages, 0, args->len);
 	else
-		xdr_reserve_space(xdr, NFS_ACL_INLINE_BUFSIZE);
+		xdr_reserve_space(xdr, args->len);
 
 	error = nfsacl_encode(xdr->buf, base, args->inode,
 			    (args->mask & NFS_ACL) ?
diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
index 7afb894..ff66ae7 100644
--- a/fs/nfs/nfs42.h
+++ b/fs/nfs/nfs42.h
@@ -5,11 +5,18 @@
 #ifndef __LINUX_FS_NFS_NFS4_2_H
 #define __LINUX_FS_NFS_NFS4_2_H
 
+/*
+ * FIXME:  four LAYOUTSTATS calls per compound at most! Do we need to support
+ * more? Need to consider not to pre-alloc too much for a compound.
+ */
+#define PNFS_LAYOUTSTATS_MAXDEV (4)
+
 /* nfs4.2proc.c */
 int nfs42_proc_allocate(struct file *, loff_t, loff_t);
 int nfs42_proc_deallocate(struct file *, loff_t, loff_t);
 loff_t nfs42_proc_llseek(struct file *, loff_t, int);
-
+int nfs42_proc_layoutstats_generic(struct nfs_server *,
+				   struct nfs42_layoutstat_data *);
 /* nfs4.2xdr.h */
 extern struct rpc_procinfo nfs4_2_procedures[];
 
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 3a9e752..f486b80 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -10,6 +10,11 @@
 #include <linux/nfs_fs.h>
 #include "nfs4_fs.h"
 #include "nfs42.h"
+#include "iostat.h"
+#include "pnfs.h"
+#include "internal.h"
+
+#define NFSDBG_FACILITY NFSDBG_PNFS
 
 static int nfs42_set_rw_stateid(nfs4_stateid *dst, struct file *file,
 				fmode_t fmode)
@@ -165,3 +170,85 @@
 
 	return vfs_setpos(filep, res.sr_offset, inode->i_sb->s_maxbytes);
 }
+
+static void
+nfs42_layoutstat_prepare(struct rpc_task *task, void *calldata)
+{
+	struct nfs42_layoutstat_data *data = calldata;
+	struct nfs_server *server = NFS_SERVER(data->args.inode);
+
+	nfs41_setup_sequence(nfs4_get_session(server), &data->args.seq_args,
+			     &data->res.seq_res, task);
+}
+
+static void
+nfs42_layoutstat_done(struct rpc_task *task, void *calldata)
+{
+	struct nfs42_layoutstat_data *data = calldata;
+
+	if (!nfs4_sequence_done(task, &data->res.seq_res))
+		return;
+
+	switch (task->tk_status) {
+	case 0:
+		break;
+	case -ENOTSUPP:
+	case -EOPNOTSUPP:
+		NFS_SERVER(data->inode)->caps &= ~NFS_CAP_LAYOUTSTATS;
+	default:
+		dprintk("%s server returns %d\n", __func__, task->tk_status);
+	}
+}
+
+static void
+nfs42_layoutstat_release(void *calldata)
+{
+	struct nfs42_layoutstat_data *data = calldata;
+	struct nfs_server *nfss = NFS_SERVER(data->args.inode);
+
+	if (nfss->pnfs_curr_ld->cleanup_layoutstats)
+		nfss->pnfs_curr_ld->cleanup_layoutstats(data);
+
+	pnfs_put_layout_hdr(NFS_I(data->args.inode)->layout);
+	smp_mb__before_atomic();
+	clear_bit(NFS_INO_LAYOUTSTATS, &NFS_I(data->args.inode)->flags);
+	smp_mb__after_atomic();
+	nfs_iput_and_deactive(data->inode);
+	kfree(data->args.devinfo);
+	kfree(data);
+}
+
+static const struct rpc_call_ops nfs42_layoutstat_ops = {
+	.rpc_call_prepare = nfs42_layoutstat_prepare,
+	.rpc_call_done = nfs42_layoutstat_done,
+	.rpc_release = nfs42_layoutstat_release,
+};
+
+int nfs42_proc_layoutstats_generic(struct nfs_server *server,
+				   struct nfs42_layoutstat_data *data)
+{
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LAYOUTSTATS],
+		.rpc_argp = &data->args,
+		.rpc_resp = &data->res,
+	};
+	struct rpc_task_setup task_setup = {
+		.rpc_client = server->client,
+		.rpc_message = &msg,
+		.callback_ops = &nfs42_layoutstat_ops,
+		.callback_data = data,
+		.flags = RPC_TASK_ASYNC,
+	};
+	struct rpc_task *task;
+
+	data->inode = nfs_igrab_and_active(data->args.inode);
+	if (!data->inode) {
+		nfs42_layoutstat_release(data);
+		return -EAGAIN;
+	}
+	nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0);
+	task = rpc_run_task(&task_setup);
+	if (IS_ERR(task))
+		return PTR_ERR(task);
+	return 0;
+}
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 1a25b27..a6bd27d 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -4,6 +4,8 @@
 #ifndef __LINUX_FS_NFS_NFS4_2XDR_H
 #define __LINUX_FS_NFS_NFS4_2XDR_H
 
+#include "nfs42.h"
+
 #define encode_fallocate_maxsz		(encode_stateid_maxsz + \
 					 2 /* offset */ + \
 					 2 /* length */)
@@ -22,6 +24,16 @@
 					 1 /* whence */ + \
 					 2 /* offset */ + \
 					 2 /* length */)
+#define encode_io_info_maxsz		4
+#define encode_layoutstats_maxsz	(op_decode_hdr_maxsz + \
+					2 /* offset */ + \
+					2 /* length */ + \
+					encode_stateid_maxsz + \
+					encode_io_info_maxsz + \
+					encode_io_info_maxsz + \
+					1 /* opaque devaddr4 length */ + \
+					XDR_QUADLEN(PNFS_LAYOUTSTATS_MAXSIZE))
+#define decode_layoutstats_maxsz	(op_decode_hdr_maxsz)
 
 #define NFS4_enc_allocate_sz		(compound_encode_hdr_maxsz + \
 					 encode_putfh_maxsz + \
@@ -45,6 +57,14 @@
 #define NFS4_dec_seek_sz		(compound_decode_hdr_maxsz + \
 					 decode_putfh_maxsz + \
 					 decode_seek_maxsz)
+#define NFS4_enc_layoutstats_sz		(compound_encode_hdr_maxsz + \
+					 encode_sequence_maxsz + \
+					 encode_putfh_maxsz + \
+					 PNFS_LAYOUTSTATS_MAXDEV * encode_layoutstats_maxsz)
+#define NFS4_dec_layoutstats_sz		(compound_decode_hdr_maxsz + \
+					 decode_sequence_maxsz + \
+					 decode_putfh_maxsz + \
+					 PNFS_LAYOUTSTATS_MAXDEV * decode_layoutstats_maxsz)
 
 
 static void encode_fallocate(struct xdr_stream *xdr,
@@ -81,6 +101,33 @@
 	encode_uint32(xdr, args->sa_what);
 }
 
+static void encode_layoutstats(struct xdr_stream *xdr,
+			       struct nfs42_layoutstat_args *args,
+			       struct nfs42_layoutstat_devinfo *devinfo,
+			       struct compound_hdr *hdr)
+{
+	__be32 *p;
+
+	encode_op_hdr(xdr, OP_LAYOUTSTATS, decode_layoutstats_maxsz, hdr);
+	p = reserve_space(xdr, 8 + 8);
+	p = xdr_encode_hyper(p, devinfo->offset);
+	p = xdr_encode_hyper(p, devinfo->length);
+	encode_nfs4_stateid(xdr, &args->stateid);
+	p = reserve_space(xdr, 4*8 + NFS4_DEVICEID4_SIZE + 4);
+	p = xdr_encode_hyper(p, devinfo->read_count);
+	p = xdr_encode_hyper(p, devinfo->read_bytes);
+	p = xdr_encode_hyper(p, devinfo->write_count);
+	p = xdr_encode_hyper(p, devinfo->write_bytes);
+	p = xdr_encode_opaque_fixed(p, devinfo->dev_id.data,
+			NFS4_DEVICEID4_SIZE);
+	/* Encode layoutupdate4 */
+	*p++ = cpu_to_be32(devinfo->layout_type);
+	if (devinfo->layoutstats_encode != NULL)
+		devinfo->layoutstats_encode(xdr, args, devinfo);
+	else
+		encode_uint32(xdr, 0);
+}
+
 /*
  * Encode ALLOCATE request
  */
@@ -137,6 +184,28 @@
 	encode_nops(&hdr);
 }
 
+/*
+ * Encode LAYOUTSTATS request
+ */
+static void nfs4_xdr_enc_layoutstats(struct rpc_rqst *req,
+				     struct xdr_stream *xdr,
+				     struct nfs42_layoutstat_args *args)
+{
+	int i;
+
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->fh, &hdr);
+	WARN_ON(args->num_dev > PNFS_LAYOUTSTATS_MAXDEV);
+	for (i = 0; i < args->num_dev; i++)
+		encode_layoutstats(xdr, args, &args->devinfo[i], &hdr);
+	encode_nops(&hdr);
+}
+
 static int decode_allocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res)
 {
 	return decode_op_hdr(xdr, OP_ALLOCATE);
@@ -169,6 +238,12 @@
 	return -EIO;
 }
 
+static int decode_layoutstats(struct xdr_stream *xdr,
+			      struct nfs42_layoutstat_res *res)
+{
+	return decode_op_hdr(xdr, OP_LAYOUTSTATS);
+}
+
 /*
  * Decode ALLOCATE request
  */
@@ -246,4 +321,35 @@
 out:
 	return status;
 }
+
+/*
+ * Decode LAYOUTSTATS request
+ */
+static int nfs4_xdr_dec_layoutstats(struct rpc_rqst *rqstp,
+				    struct xdr_stream *xdr,
+				    struct nfs42_layoutstat_res *res)
+{
+	struct compound_hdr hdr;
+	int status, i;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	WARN_ON(res->num_dev > PNFS_LAYOUTSTATS_MAXDEV);
+	for (i = 0; i < res->num_dev; i++) {
+		status = decode_layoutstats(xdr, res);
+		if (status)
+			goto out;
+	}
+out:
+	res->rpc_status = status;
+	return status;
+}
+
 #endif /* __LINUX_FS_NFS_NFS4_2XDR_H */
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index fdef424..ea3bee9 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -233,6 +233,7 @@
 extern int nfs4_call_sync(struct rpc_clnt *, struct nfs_server *,
 			  struct rpc_message *, struct nfs4_sequence_args *,
 			  struct nfs4_sequence_res *, int);
+extern void nfs4_init_sequence(struct nfs4_sequence_args *, struct nfs4_sequence_res *, int);
 extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *);
 extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setclientid_res *arg, struct rpc_cred *);
 extern int nfs4_proc_get_rootfh(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *, bool);
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index e42be52..3aa6a9b 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -676,7 +676,6 @@
 		break;
 	}
 
-	/* No matching nfs_client found. */
 	spin_unlock(&nn->nfs_client_lock);
 	dprintk("NFS: <-- %s status = %d\n", __func__, status);
 	nfs_put_client(prev);
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index f58c17b..dcd39d4 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -41,6 +41,10 @@
 
 	dprintk("NFS: open file(%pd2)\n", dentry);
 
+	err = nfs_check_flags(openflags);
+	if (err)
+		return err;
+
 	if ((openflags & O_ACCMODE) == 3)
 		openflags--;
 
diff --git a/fs/nfs/nfs4getroot.c b/fs/nfs/nfs4getroot.c
index c0b3a16..039b3eb 100644
--- a/fs/nfs/nfs4getroot.c
+++ b/fs/nfs/nfs4getroot.c
@@ -35,13 +35,6 @@
 		goto out;
 	}
 
-	if (fsinfo.fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) {
-		printk(KERN_ERR "nfs4_get_rootfh:"
-		       " getroot obtained referral\n");
-		ret = -EREMOTE;
-		goto out;
-	}
-
 	memcpy(&server->fsid, &fsinfo.fattr->fsid, sizeof(server->fsid));
 out:
 	nfs_free_fattr(fsinfo.fattr);
diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c
index 2e1737c..535dfc6 100644
--- a/fs/nfs/nfs4idmap.c
+++ b/fs/nfs/nfs4idmap.c
@@ -494,12 +494,7 @@
 
 int nfs_idmap_init(void)
 {
-	int ret;
-	ret = nfs_idmap_init_keyring();
-	if (ret != 0)
-		goto out;
-out:
-	return ret;
+	return nfs_idmap_init_keyring();
 }
 
 void nfs_idmap_quit(void)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 55e1e3a..6f228b5 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -356,6 +356,9 @@
 		case 0:
 			return 0;
 		case -NFS4ERR_OPENMODE:
+		case -NFS4ERR_DELEG_REVOKED:
+		case -NFS4ERR_ADMIN_REVOKED:
+		case -NFS4ERR_BAD_STATEID:
 			if (inode && nfs4_have_delegation(inode, FMODE_READ)) {
 				nfs4_inode_return_delegation(inode);
 				exception->retry = 1;
@@ -367,15 +370,6 @@
 			if (ret < 0)
 				break;
 			goto wait_on_recovery;
-		case -NFS4ERR_DELEG_REVOKED:
-		case -NFS4ERR_ADMIN_REVOKED:
-		case -NFS4ERR_BAD_STATEID:
-			if (state == NULL)
-				break;
-			ret = nfs4_schedule_stateid_recovery(server, state);
-			if (ret < 0)
-				break;
-			goto wait_on_recovery;
 		case -NFS4ERR_EXPIRED:
 			if (state != NULL) {
 				ret = nfs4_schedule_stateid_recovery(server, state);
@@ -482,8 +476,8 @@
 	struct nfs4_sequence_res *seq_res;
 };
 
-static void nfs4_init_sequence(struct nfs4_sequence_args *args,
-			       struct nfs4_sequence_res *res, int cache_reply)
+void nfs4_init_sequence(struct nfs4_sequence_args *args,
+			struct nfs4_sequence_res *res, int cache_reply)
 {
 	args->sa_slot = NULL;
 	args->sa_cache_this = cache_reply;
@@ -1553,6 +1547,13 @@
 	struct nfs4_state *newstate;
 	int ret;
 
+	if ((opendata->o_arg.claim == NFS4_OPEN_CLAIM_DELEGATE_CUR ||
+	     opendata->o_arg.claim == NFS4_OPEN_CLAIM_DELEG_CUR_FH) &&
+	    (opendata->o_arg.u.delegation_type & fmode) != fmode)
+		/* This mode can't have been delegated, so we must have
+		 * a valid open_stateid to cover it - not need to reclaim.
+		 */
+		return 0;
 	opendata->o_arg.open_flags = 0;
 	opendata->o_arg.fmode = fmode;
 	opendata->o_arg.share_access = nfs4_map_atomic_open_share(
@@ -1684,6 +1685,7 @@
 					"%d.\n", __func__, err);
 		case 0:
 		case -ENOENT:
+		case -EAGAIN:
 		case -ESTALE:
 			break;
 		case -NFS4ERR_BADSESSION:
@@ -3355,6 +3357,8 @@
 			goto out;
 		case -NFS4ERR_MOVED:
 			err = nfs4_get_referral(client, dir, name, fattr, fhandle);
+			if (err == -NFS4ERR_MOVED)
+				err = nfs4_handle_exception(NFS_SERVER(dir), err, &exception);
 			goto out;
 		case -NFS4ERR_WRONGSEC:
 			err = -EPERM;
@@ -4955,49 +4959,128 @@
 	memcpy(bootverf->data, verf, sizeof(bootverf->data));
 }
 
-static unsigned int
-nfs4_init_nonuniform_client_string(struct nfs_client *clp,
-				   char *buf, size_t len)
+static int
+nfs4_init_nonuniform_client_string(struct nfs_client *clp)
 {
-	unsigned int result;
+	int result;
+	size_t len;
+	char *str;
+	bool retried = false;
 
 	if (clp->cl_owner_id != NULL)
-		return strlcpy(buf, clp->cl_owner_id, len);
+		return 0;
+retry:
+	rcu_read_lock();
+	len = 10 + strlen(clp->cl_ipaddr) + 1 +
+		strlen(rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR)) +
+		1 +
+		strlen(rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_PROTO)) +
+		1;
+	rcu_read_unlock();
+
+	if (len > NFS4_OPAQUE_LIMIT + 1)
+		return -EINVAL;
+
+	/*
+	 * Since this string is allocated at mount time, and held until the
+	 * nfs_client is destroyed, we can use GFP_KERNEL here w/o worrying
+	 * about a memory-reclaim deadlock.
+	 */
+	str = kmalloc(len, GFP_KERNEL);
+	if (!str)
+		return -ENOMEM;
 
 	rcu_read_lock();
-	result = scnprintf(buf, len, "Linux NFSv4.0 %s/%s %s",
-				clp->cl_ipaddr,
-				rpc_peeraddr2str(clp->cl_rpcclient,
-							RPC_DISPLAY_ADDR),
-				rpc_peeraddr2str(clp->cl_rpcclient,
-							RPC_DISPLAY_PROTO));
+	result = scnprintf(str, len, "Linux NFSv4.0 %s/%s %s",
+			clp->cl_ipaddr,
+			rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR),
+			rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_PROTO));
 	rcu_read_unlock();
-	clp->cl_owner_id = kstrdup(buf, GFP_KERNEL);
-	return result;
+
+	/* Did something change? */
+	if (result >= len) {
+		kfree(str);
+		if (retried)
+			return -EINVAL;
+		retried = true;
+		goto retry;
+	}
+	clp->cl_owner_id = str;
+	return 0;
 }
 
-static unsigned int
-nfs4_init_uniform_client_string(struct nfs_client *clp,
-				char *buf, size_t len)
+static int
+nfs4_init_uniquifier_client_string(struct nfs_client *clp)
 {
-	const char *nodename = clp->cl_rpcclient->cl_nodename;
-	unsigned int result;
+	int result;
+	size_t len;
+	char *str;
+
+	len = 10 + 10 + 1 + 10 + 1 +
+		strlen(nfs4_client_id_uniquifier) + 1 +
+		strlen(clp->cl_rpcclient->cl_nodename) + 1;
+
+	if (len > NFS4_OPAQUE_LIMIT + 1)
+		return -EINVAL;
+
+	/*
+	 * Since this string is allocated at mount time, and held until the
+	 * nfs_client is destroyed, we can use GFP_KERNEL here w/o worrying
+	 * about a memory-reclaim deadlock.
+	 */
+	str = kmalloc(len, GFP_KERNEL);
+	if (!str)
+		return -ENOMEM;
+
+	result = scnprintf(str, len, "Linux NFSv%u.%u %s/%s",
+			clp->rpc_ops->version, clp->cl_minorversion,
+			nfs4_client_id_uniquifier,
+			clp->cl_rpcclient->cl_nodename);
+	if (result >= len) {
+		kfree(str);
+		return -EINVAL;
+	}
+	clp->cl_owner_id = str;
+	return 0;
+}
+
+static int
+nfs4_init_uniform_client_string(struct nfs_client *clp)
+{
+	int result;
+	size_t len;
+	char *str;
 
 	if (clp->cl_owner_id != NULL)
-		return strlcpy(buf, clp->cl_owner_id, len);
+		return 0;
 
 	if (nfs4_client_id_uniquifier[0] != '\0')
-		result = scnprintf(buf, len, "Linux NFSv%u.%u %s/%s",
-				clp->rpc_ops->version,
-				clp->cl_minorversion,
-				nfs4_client_id_uniquifier,
-				nodename);
-	else
-		result = scnprintf(buf, len, "Linux NFSv%u.%u %s",
-				clp->rpc_ops->version, clp->cl_minorversion,
-				nodename);
-	clp->cl_owner_id = kstrdup(buf, GFP_KERNEL);
-	return result;
+		return nfs4_init_uniquifier_client_string(clp);
+
+	len = 10 + 10 + 1 + 10 + 1 +
+		strlen(clp->cl_rpcclient->cl_nodename) + 1;
+
+	if (len > NFS4_OPAQUE_LIMIT + 1)
+		return -EINVAL;
+
+	/*
+	 * Since this string is allocated at mount time, and held until the
+	 * nfs_client is destroyed, we can use GFP_KERNEL here w/o worrying
+	 * about a memory-reclaim deadlock.
+	 */
+	str = kmalloc(len, GFP_KERNEL);
+	if (!str)
+		return -ENOMEM;
+
+	result = scnprintf(str, len, "Linux NFSv%u.%u %s",
+			clp->rpc_ops->version, clp->cl_minorversion,
+			clp->cl_rpcclient->cl_nodename);
+	if (result >= len) {
+		kfree(str);
+		return -EINVAL;
+	}
+	clp->cl_owner_id = str;
+	return 0;
 }
 
 /*
@@ -5044,7 +5127,7 @@
 	struct nfs4_setclientid setclientid = {
 		.sc_verifier = &sc_verifier,
 		.sc_prog = program,
-		.sc_cb_ident = clp->cl_cb_ident,
+		.sc_clnt = clp,
 	};
 	struct rpc_message msg = {
 		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SETCLIENTID],
@@ -5064,16 +5147,15 @@
 
 	/* nfs_client_id4 */
 	nfs4_init_boot_verifier(clp, &sc_verifier);
+
 	if (test_bit(NFS_CS_MIGRATION, &clp->cl_flags))
-		setclientid.sc_name_len =
-				nfs4_init_uniform_client_string(clp,
-						setclientid.sc_name,
-						sizeof(setclientid.sc_name));
+		status = nfs4_init_uniform_client_string(clp);
 	else
-		setclientid.sc_name_len =
-				nfs4_init_nonuniform_client_string(clp,
-						setclientid.sc_name,
-						sizeof(setclientid.sc_name));
+		status = nfs4_init_nonuniform_client_string(clp);
+
+	if (status)
+		goto out;
+
 	/* cb_client4 */
 	setclientid.sc_netid_len =
 				nfs4_init_callback_netid(clp,
@@ -5083,9 +5165,9 @@
 				sizeof(setclientid.sc_uaddr), "%s.%u.%u",
 				clp->cl_ipaddr, port >> 8, port & 255);
 
-	dprintk("NFS call  setclientid auth=%s, '%.*s'\n",
+	dprintk("NFS call  setclientid auth=%s, '%s'\n",
 		clp->cl_rpcclient->cl_auth->au_ops->au_name,
-		setclientid.sc_name_len, setclientid.sc_name);
+		clp->cl_owner_id);
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task)) {
 		status = PTR_ERR(task);
@@ -5402,6 +5484,7 @@
 	atomic_inc(&lsp->ls_count);
 	/* Ensure we don't close file until we're done freeing locks! */
 	p->ctx = get_nfs_open_context(ctx);
+	get_file(fl->fl_file);
 	memcpy(&p->fl, fl, sizeof(p->fl));
 	p->server = NFS_SERVER(inode);
 	return p;
@@ -5413,6 +5496,7 @@
 	nfs_free_seqid(calldata->arg.seqid);
 	nfs4_put_lock_state(calldata->lsp);
 	put_nfs_open_context(calldata->ctx);
+	fput(calldata->fl.fl_file);
 	kfree(calldata);
 }
 
@@ -6846,11 +6930,14 @@
 	};
 
 	nfs4_init_boot_verifier(clp, &verifier);
-	args.id_len = nfs4_init_uniform_client_string(clp, args.id,
-							sizeof(args.id));
-	dprintk("NFS call  exchange_id auth=%s, '%.*s'\n",
+
+	status = nfs4_init_uniform_client_string(clp);
+	if (status)
+		goto out;
+
+	dprintk("NFS call  exchange_id auth=%s, '%s'\n",
 		clp->cl_rpcclient->cl_auth->au_ops->au_name,
-		args.id_len, args.id);
+		clp->cl_owner_id);
 
 	res.server_owner = kzalloc(sizeof(struct nfs41_server_owner),
 					GFP_NOFS);
@@ -6885,7 +6972,7 @@
 		/* unsupported! */
 		WARN_ON_ONCE(1);
 		status = -EINVAL;
-		goto out_server_scope;
+		goto out_impl_id;
 	}
 
 	status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
@@ -6913,6 +7000,7 @@
 		/* use the most recent implementation id */
 		kfree(clp->cl_implid);
 		clp->cl_implid = res.impl_id;
+		res.impl_id = NULL;
 
 		if (clp->cl_serverscope != NULL &&
 		    !nfs41_same_server_scope(clp->cl_serverscope,
@@ -6926,15 +7014,16 @@
 
 		if (clp->cl_serverscope == NULL) {
 			clp->cl_serverscope = res.server_scope;
-			goto out;
+			res.server_scope = NULL;
 		}
-	} else
-		kfree(res.impl_id);
+	}
 
-out_server_owner:
-	kfree(res.server_owner);
+out_impl_id:
+	kfree(res.impl_id);
 out_server_scope:
 	kfree(res.server_scope);
+out_server_owner:
+	kfree(res.server_owner);
 out:
 	if (clp->cl_implid != NULL)
 		dprintk("NFS reply exchange_id: Server Implementation ID: "
@@ -8061,9 +8150,8 @@
 	struct rpc_task *task;
 	int status = 0;
 
-	dprintk("NFS: %4d initiating layoutcommit call. sync %d "
-		"lbw: %llu inode %lu\n",
-		data->task.tk_pid, sync,
+	dprintk("NFS: initiating layoutcommit call. sync %d "
+		"lbw: %llu inode %lu\n", sync,
 		data->args.lastbytewritten,
 		data->args.inode->i_ino);
 
@@ -8557,7 +8645,8 @@
 		| NFS_CAP_ATOMIC_OPEN_V1
 		| NFS_CAP_ALLOCATE
 		| NFS_CAP_DEALLOCATE
-		| NFS_CAP_SEEK,
+		| NFS_CAP_SEEK
+		| NFS_CAP_LAYOUTSTATS,
 	.init_client = nfs41_init_client,
 	.shutdown_client = nfs41_shutdown_client,
 	.match_stateid = nfs41_match_stateid,
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 2782cfc..605840d 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -309,7 +309,6 @@
 
 	if (test_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state))
 		goto do_confirm;
-	nfs4_begin_drain_session(clp);
 	status = nfs4_proc_exchange_id(clp, cred);
 	if (status != 0)
 		goto out;
@@ -1482,6 +1481,8 @@
 					spin_unlock(&state->state_lock);
 				}
 				nfs4_put_open_state(state);
+				clear_bit(NFS4CLNT_RECLAIM_NOGRACE,
+					&state->flags);
 				spin_lock(&sp->so_lock);
 				goto restart;
 			}
@@ -1830,6 +1831,7 @@
 		clp->cl_mvops->reboot_recovery_ops;
 	int status;
 
+	nfs4_begin_drain_session(clp);
 	cred = nfs4_get_clid_cred(clp);
 	if (cred == NULL)
 		return -ENOENT;
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 0aea978..558cd65d 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -139,7 +139,8 @@
 #define encode_setclientid_maxsz \
 				(op_encode_hdr_maxsz + \
 				XDR_QUADLEN(NFS4_VERIFIER_SIZE) + \
-				XDR_QUADLEN(NFS4_SETCLIENTID_NAMELEN) + \
+				/* client name */ \
+				1 + XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + \
 				1 /* sc_prog */ + \
 				1 + XDR_QUADLEN(RPCBIND_MAXNETIDLEN) + \
 				1 + XDR_QUADLEN(RPCBIND_MAXUADDRLEN) + \
@@ -288,7 +289,8 @@
 #define encode_exchange_id_maxsz (op_encode_hdr_maxsz + \
 				encode_verifier_maxsz + \
 				1 /* co_ownerid.len */ + \
-				XDR_QUADLEN(NFS4_EXCHANGE_ID_LEN) + \
+				/* eia_clientowner */ \
+				1 + XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + \
 				1 /* flags */ + \
 				1 /* spa_how */ + \
 				/* max is SP4_MACH_CRED (for now) */ + \
@@ -1667,13 +1669,14 @@
 	encode_op_hdr(xdr, OP_SETCLIENTID, decode_setclientid_maxsz, hdr);
 	encode_nfs4_verifier(xdr, setclientid->sc_verifier);
 
-	encode_string(xdr, setclientid->sc_name_len, setclientid->sc_name);
+	encode_string(xdr, strlen(setclientid->sc_clnt->cl_owner_id),
+			setclientid->sc_clnt->cl_owner_id);
 	p = reserve_space(xdr, 4);
 	*p = cpu_to_be32(setclientid->sc_prog);
 	encode_string(xdr, setclientid->sc_netid_len, setclientid->sc_netid);
 	encode_string(xdr, setclientid->sc_uaddr_len, setclientid->sc_uaddr);
 	p = reserve_space(xdr, 4);
-	*p = cpu_to_be32(setclientid->sc_cb_ident);
+	*p = cpu_to_be32(setclientid->sc_clnt->cl_cb_ident);
 }
 
 static void encode_setclientid_confirm(struct xdr_stream *xdr, const struct nfs4_setclientid_res *arg, struct compound_hdr *hdr)
@@ -1747,7 +1750,8 @@
 	encode_op_hdr(xdr, OP_EXCHANGE_ID, decode_exchange_id_maxsz, hdr);
 	encode_nfs4_verifier(xdr, args->verifier);
 
-	encode_string(xdr, args->id_len, args->id);
+	encode_string(xdr, strlen(args->client->cl_owner_id),
+			args->client->cl_owner_id);
 
 	encode_uint32(xdr, args->flags);
 	encode_uint32(xdr, args->state_protect.how);
@@ -7427,6 +7431,7 @@
 	PROC(SEEK,		enc_seek,		dec_seek),
 	PROC(ALLOCATE,		enc_allocate,		dec_allocate),
 	PROC(DEALLOCATE,	enc_deallocate,		dec_deallocate),
+	PROC(LAYOUTSTATS,	enc_layoutstats,	dec_layoutstats),
 #endif /* CONFIG_NFS_V4_2 */
 };
 
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 282b393..1da68d3 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -636,9 +636,8 @@
 
 	hdr->rw_ops->rw_initiate(hdr, &msg, rpc_ops, &task_setup_data, how);
 
-	dprintk("NFS: %5u initiated pgio call "
+	dprintk("NFS: initiated pgio call "
 		"(req %s/%llu, %u bytes @ offset %llu)\n",
-		hdr->task.tk_pid,
 		hdr->inode->i_sb->s_id,
 		(unsigned long long)NFS_FILEID(hdr->inode),
 		hdr->args.count,
@@ -690,8 +689,6 @@
 static void nfs_pgio_release(void *calldata)
 {
 	struct nfs_pgio_header *hdr = calldata;
-	if (hdr->rw_ops->rw_release)
-		hdr->rw_ops->rw_release(hdr);
 	nfs_pgio_data_destroy(hdr);
 	hdr->completion_ops->completion(hdr);
 }
@@ -711,7 +708,9 @@
  * nfs_pageio_init - initialise a page io descriptor
  * @desc: pointer to descriptor
  * @inode: pointer to inode
- * @doio: pointer to io function
+ * @pg_ops: pointer to pageio operations
+ * @compl_ops: pointer to pageio completion operations
+ * @rw_ops: pointer to nfs read/write operations
  * @bsize: io block size
  * @io_flags: extra parameters for the io function
  */
@@ -1186,6 +1185,7 @@
  * nfs_pageio_complete_mirror - Complete I/O on the current mirror of an
  *				nfs_pageio_descriptor
  * @desc: pointer to io descriptor
+ * @mirror_idx: pointer to mirror index
  */
 static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc,
 				       u32 mirror_idx)
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 2306062..0ba9a02 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -35,6 +35,7 @@
 #include "iostat.h"
 #include "nfs4trace.h"
 #include "delegation.h"
+#include "nfs42.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PNFS
 #define PNFS_LAYOUTGET_RETRY_TIMEOUT (120*HZ)
@@ -1821,6 +1822,7 @@
 	/* Resend all requests through the MDS */
 	nfs_pageio_init_write(&pgio, hdr->inode, FLUSH_STABLE, true,
 			      hdr->completion_ops);
+	set_bit(NFS_CONTEXT_RESEND_WRITES, &hdr->args.context->flags);
 	return nfs_pageio_resend(&pgio, hdr);
 }
 EXPORT_SYMBOL_GPL(pnfs_write_done_resend_to_mds);
@@ -1865,6 +1867,7 @@
 		mirror->pg_recoalesce = 1;
 	}
 	nfs_pgio_data_destroy(hdr);
+	hdr->release(hdr);
 }
 
 static enum pnfs_try_status
@@ -1979,6 +1982,7 @@
 		mirror->pg_recoalesce = 1;
 	}
 	nfs_pgio_data_destroy(hdr);
+	hdr->release(hdr);
 }
 
 /*
@@ -2247,3 +2251,63 @@
 	}
 	return thp;
 }
+
+#if IS_ENABLED(CONFIG_NFS_V4_2)
+int
+pnfs_report_layoutstat(struct inode *inode)
+{
+	struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
+	struct nfs_server *server = NFS_SERVER(inode);
+	struct nfs_inode *nfsi = NFS_I(inode);
+	struct nfs42_layoutstat_data *data;
+	struct pnfs_layout_hdr *hdr;
+	int status = 0;
+
+	if (!pnfs_enabled_sb(server) || !ld->prepare_layoutstats)
+		goto out;
+
+	if (!nfs_server_capable(inode, NFS_CAP_LAYOUTSTATS))
+		goto out;
+
+	if (test_and_set_bit(NFS_INO_LAYOUTSTATS, &nfsi->flags))
+		goto out;
+
+	spin_lock(&inode->i_lock);
+	if (!NFS_I(inode)->layout) {
+		spin_unlock(&inode->i_lock);
+		goto out;
+	}
+	hdr = NFS_I(inode)->layout;
+	pnfs_get_layout_hdr(hdr);
+	spin_unlock(&inode->i_lock);
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data) {
+		status = -ENOMEM;
+		goto out_put;
+	}
+
+	data->args.fh = NFS_FH(inode);
+	data->args.inode = inode;
+	nfs4_stateid_copy(&data->args.stateid, &hdr->plh_stateid);
+	status = ld->prepare_layoutstats(&data->args);
+	if (status)
+		goto out_free;
+
+	status = nfs42_proc_layoutstats_generic(NFS_SERVER(inode), data);
+
+out:
+	dprintk("%s returns %d\n", __func__, status);
+	return status;
+
+out_free:
+	kfree(data);
+out_put:
+	pnfs_put_layout_hdr(hdr);
+	smp_mb__before_atomic();
+	clear_bit(NFS_INO_LAYOUTSTATS, &nfsi->flags);
+	smp_mb__after_atomic();
+	goto out;
+}
+EXPORT_SYMBOL_GPL(pnfs_report_layoutstat);
+#endif
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 1e6308f..3e6ab7b 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -178,6 +178,8 @@
 	void (*encode_layoutcommit) (struct pnfs_layout_hdr *lo,
 				     struct xdr_stream *xdr,
 				     const struct nfs4_layoutcommit_args *args);
+	int (*prepare_layoutstats) (struct nfs42_layoutstat_args *args);
+	void (*cleanup_layoutstats) (struct nfs42_layoutstat_data *data);
 };
 
 struct pnfs_layout_hdr {
@@ -290,7 +292,6 @@
 struct nfs4_threshold *pnfs_mdsthreshold_alloc(void);
 void pnfs_error_mark_layout_for_return(struct inode *inode,
 				       struct pnfs_layout_segment *lseg);
-
 /* nfs4_deviceid_flags */
 enum {
 	NFS_DEVICEID_INVALID = 0,       /* set when MDS clientid recalled */
@@ -689,4 +690,14 @@
 
 #endif /* CONFIG_NFS_V4_1 */
 
+#if IS_ENABLED(CONFIG_NFS_V4_2)
+int pnfs_report_layoutstat(struct inode *inode);
+#else
+static inline int
+pnfs_report_layoutstat(struct inode *inode)
+{
+	return 0;
+}
+#endif
+
 #endif /* FS_NFS_PNFS_H */
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index f175b83..aa62004 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2847,7 +2847,7 @@
 	*((unsigned int *)kp->arg) = num;
 	return 0;
 }
-static struct kernel_param_ops param_ops_portnr = {
+static const struct kernel_param_ops param_ops_portnr = {
 	.set = param_set_portnr,
 	.get = param_get_uint,
 };
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index e6c2625..65869ca 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1290,6 +1290,7 @@
 static void nfs_redirty_request(struct nfs_page *req)
 {
 	nfs_mark_request_dirty(req);
+	set_bit(NFS_CONTEXT_RESEND_WRITES, &req->wb_context->flags);
 	nfs_unlock_request(req);
 	nfs_end_page_writeback(req);
 	nfs_release_request(req);
@@ -1348,11 +1349,6 @@
 	NFS_PROTO(data->inode)->commit_rpc_prepare(task, data);
 }
 
-static void nfs_writeback_release_common(struct nfs_pgio_header *hdr)
-{
-	/* do nothing! */
-}
-
 /*
  * Special version of should_remove_suid() that ignores capabilities.
  */
@@ -1556,7 +1552,7 @@
 	/* Set up the initial task struct.  */
 	nfs_ops->commit_setup(data, &msg);
 
-	dprintk("NFS: %5u initiated commit call\n", data->task.tk_pid);
+	dprintk("NFS: initiated commit call\n");
 
 	nfs4_state_protect(NFS_SERVER(data->inode)->nfs_client,
 		NFS_SP4_MACH_CRED_COMMIT, &task_setup_data.rpc_client, &msg);
@@ -2013,7 +2009,6 @@
 	.rw_mode		= FMODE_WRITE,
 	.rw_alloc_header	= nfs_writehdr_alloc,
 	.rw_free_header		= nfs_writehdr_free,
-	.rw_release		= nfs_writeback_release_common,
 	.rw_done		= nfs_writeback_done,
 	.rw_result		= nfs_writeback_result,
 	.rw_initiate		= nfs_initiate_write,
diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c
index 0ee0bed..6b8b92b 100644
--- a/fs/nilfs2/dir.c
+++ b/fs/nilfs2/dir.c
@@ -61,11 +61,6 @@
 	page_cache_release(page);
 }
 
-static inline unsigned long dir_pages(struct inode *inode)
-{
-	return (inode->i_size+PAGE_CACHE_SIZE-1)>>PAGE_CACHE_SHIFT;
-}
-
 /*
  * Return the offset into page `page_nr' of the last valid
  * byte in that page, plus one.
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 258d9fe..4a73d6d 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -307,31 +307,13 @@
 static ssize_t
 nilfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 {
-	struct file *file = iocb->ki_filp;
-	struct address_space *mapping = file->f_mapping;
-	struct inode *inode = file->f_mapping->host;
-	size_t count = iov_iter_count(iter);
-	ssize_t size;
+	struct inode *inode = file_inode(iocb->ki_filp);
 
 	if (iov_iter_rw(iter) == WRITE)
 		return 0;
 
 	/* Needs synchronization with the cleaner */
-	size = blockdev_direct_IO(iocb, inode, iter, offset, nilfs_get_block);
-
-	/*
-	 * In case of error extending write may have instantiated a few
-	 * blocks outside i_size. Trim these off again.
-	 */
-	if (unlikely(iov_iter_rw(iter) == WRITE && size < 0)) {
-		loff_t isize = i_size_read(inode);
-		loff_t end = offset + count;
-
-		if (end > isize)
-			nilfs_write_failed(mapping, end);
-	}
-
-	return size;
+	return blockdev_direct_IO(iocb, inode, iter, offset, nilfs_get_block);
 }
 
 const struct address_space_operations nilfs_aops = {
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 45064869..5b1e2a4 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -26,7 +26,7 @@
 #include <linux/fs.h> /* struct inode */
 #include <linux/fsnotify_backend.h>
 #include <linux/idr.h>
-#include <linux/init.h> /* module_init */
+#include <linux/init.h> /* fs_initcall */
 #include <linux/inotify.h>
 #include <linux/kernel.h> /* roundup() */
 #include <linux/namei.h> /* LOOKUP_FOLLOW */
@@ -812,4 +812,4 @@
 
 	return 0;
 }
-module_init(inotify_user_setup);
+fs_initcall(inotify_user_setup);
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index 2cd6536..262561f 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -382,7 +382,7 @@
 	base_ni = ni;
 	if (NInoAttr(ni))
 		base_ni = ni->ext.base_ntfs_ino;
-	err = file_remove_suid(file);
+	err = file_remove_privs(file);
 	if (unlikely(err))
 		goto out;
 	/*
diff --git a/fs/ntfs/inode.h b/fs/ntfs/inode.h
index 76b6cfb..b3c3469 100644
--- a/fs/ntfs/inode.h
+++ b/fs/ntfs/inode.h
@@ -239,7 +239,7 @@
  */
 static inline ntfs_inode *NTFS_I(struct inode *inode)
 {
-	return (ntfs_inode *)list_entry(inode, big_ntfs_inode, vfs_inode);
+	return (ntfs_inode *)container_of(inode, big_ntfs_inode, vfs_inode);
 }
 
 static inline struct inode *VFS_I(ntfs_inode *ni)
diff --git a/fs/open.c b/fs/open.c
index e0250bd..e33dab2 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -51,8 +51,10 @@
 		newattrs.ia_valid |= ATTR_FILE;
 	}
 
-	/* Remove suid/sgid on truncate too */
-	ret = should_remove_suid(dentry);
+	/* Remove suid, sgid, and file capabilities on truncate too */
+	ret = dentry_needs_remove_privs(dentry);
+	if (ret < 0)
+		return ret;
 	if (ret)
 		newattrs.ia_valid |= ret | ATTR_FORCE;
 
@@ -678,18 +680,18 @@
 }
 
 static int do_dentry_open(struct file *f,
+			  struct inode *inode,
 			  int (*open)(struct inode *, struct file *),
 			  const struct cred *cred)
 {
 	static const struct file_operations empty_fops = {};
-	struct inode *inode;
 	int error;
 
 	f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK |
 				FMODE_PREAD | FMODE_PWRITE;
 
 	path_get(&f->f_path);
-	inode = f->f_inode = f->f_path.dentry->d_inode;
+	f->f_inode = inode;
 	f->f_mapping = inode->i_mapping;
 
 	if (unlikely(f->f_flags & O_PATH)) {
@@ -793,7 +795,8 @@
 	BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
 
 	file->f_path.dentry = dentry;
-	error = do_dentry_open(file, open, current_cred());
+	error = do_dentry_open(file, d_backing_inode(dentry), open,
+			       current_cred());
 	if (!error)
 		*opened |= FILE_OPENED;
 
@@ -822,6 +825,34 @@
 }
 EXPORT_SYMBOL(finish_no_open);
 
+char *file_path(struct file *filp, char *buf, int buflen)
+{
+	return d_path(&filp->f_path, buf, buflen);
+}
+EXPORT_SYMBOL(file_path);
+
+/**
+ * vfs_open - open the file at the given path
+ * @path: path to open
+ * @file: newly allocated file with f_flag initialized
+ * @cred: credentials to use
+ */
+int vfs_open(const struct path *path, struct file *file,
+	     const struct cred *cred)
+{
+	struct dentry *dentry = path->dentry;
+	struct inode *inode = dentry->d_inode;
+
+	file->f_path = *path;
+	if (dentry->d_flags & DCACHE_OP_SELECT_INODE) {
+		inode = dentry->d_op->d_select_inode(dentry, file->f_flags);
+		if (IS_ERR(inode))
+			return PTR_ERR(inode);
+	}
+
+	return do_dentry_open(file, inode, NULL, cred);
+}
+
 struct file *dentry_open(const struct path *path, int flags,
 			 const struct cred *cred)
 {
@@ -853,26 +884,6 @@
 }
 EXPORT_SYMBOL(dentry_open);
 
-/**
- * vfs_open - open the file at the given path
- * @path: path to open
- * @filp: newly allocated file with f_flag initialized
- * @cred: credentials to use
- */
-int vfs_open(const struct path *path, struct file *filp,
-	     const struct cred *cred)
-{
-	struct inode *inode = path->dentry->d_inode;
-
-	if (inode->i_op->dentry_open)
-		return inode->i_op->dentry_open(path->dentry, filp, cred);
-	else {
-		filp->f_path = *path;
-		return do_dentry_open(filp, NULL, cred);
-	}
-}
-EXPORT_SYMBOL(vfs_open);
-
 static inline int build_open_flags(int flags, umode_t mode, struct open_flags *op)
 {
 	int lookup_flags = 0;
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 308379b..f140e3db 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -337,37 +337,30 @@
 	return true;
 }
 
-static int ovl_dentry_open(struct dentry *dentry, struct file *file,
-		    const struct cred *cred)
+struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags)
 {
 	int err;
 	struct path realpath;
 	enum ovl_path_type type;
-	bool want_write = false;
 
 	type = ovl_path_real(dentry, &realpath);
-	if (ovl_open_need_copy_up(file->f_flags, type, realpath.dentry)) {
-		want_write = true;
+	if (ovl_open_need_copy_up(file_flags, type, realpath.dentry)) {
 		err = ovl_want_write(dentry);
 		if (err)
-			goto out;
+			return ERR_PTR(err);
 
-		if (file->f_flags & O_TRUNC)
+		if (file_flags & O_TRUNC)
 			err = ovl_copy_up_last(dentry, NULL, true);
 		else
 			err = ovl_copy_up(dentry);
+		ovl_drop_write(dentry);
 		if (err)
-			goto out_drop_write;
+			return ERR_PTR(err);
 
 		ovl_path_upper(dentry, &realpath);
 	}
 
-	err = vfs_open(&realpath, file, cred);
-out_drop_write:
-	if (want_write)
-		ovl_drop_write(dentry);
-out:
-	return err;
+	return d_backing_inode(realpath.dentry);
 }
 
 static const struct inode_operations ovl_file_inode_operations = {
@@ -378,7 +371,6 @@
 	.getxattr	= ovl_getxattr,
 	.listxattr	= ovl_listxattr,
 	.removexattr	= ovl_removexattr,
-	.dentry_open	= ovl_dentry_open,
 };
 
 static const struct inode_operations ovl_symlink_inode_operations = {
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 17ac5af..ea5a40b 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -173,6 +173,7 @@
 		     void *value, size_t size);
 ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size);
 int ovl_removexattr(struct dentry *dentry, const char *name);
+struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags);
 
 struct inode *ovl_new_inode(struct super_block *sb, umode_t mode,
 			    struct ovl_entry *oe);
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 907870e..70e9af5 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -23,6 +23,7 @@
 	u64 ino;
 	struct list_head l_node;
 	struct rb_node node;
+	struct ovl_cache_entry *next_maybe_whiteout;
 	bool is_whiteout;
 	char name[];
 };
@@ -39,7 +40,7 @@
 	struct rb_root root;
 	struct list_head *list;
 	struct list_head middle;
-	struct dentry *dir;
+	struct ovl_cache_entry *first_maybe_whiteout;
 	int count;
 	int err;
 };
@@ -79,7 +80,7 @@
 	return NULL;
 }
 
-static struct ovl_cache_entry *ovl_cache_entry_new(struct dentry *dir,
+static struct ovl_cache_entry *ovl_cache_entry_new(struct ovl_readdir_data *rdd,
 						   const char *name, int len,
 						   u64 ino, unsigned int d_type)
 {
@@ -98,29 +99,8 @@
 	p->is_whiteout = false;
 
 	if (d_type == DT_CHR) {
-		struct dentry *dentry;
-		const struct cred *old_cred;
-		struct cred *override_cred;
-
-		override_cred = prepare_creds();
-		if (!override_cred) {
-			kfree(p);
-			return NULL;
-		}
-
-		/*
-		 * CAP_DAC_OVERRIDE for lookup
-		 */
-		cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE);
-		old_cred = override_creds(override_cred);
-
-		dentry = lookup_one_len(name, dir, len);
-		if (!IS_ERR(dentry)) {
-			p->is_whiteout = ovl_is_whiteout(dentry);
-			dput(dentry);
-		}
-		revert_creds(old_cred);
-		put_cred(override_cred);
+		p->next_maybe_whiteout = rdd->first_maybe_whiteout;
+		rdd->first_maybe_whiteout = p;
 	}
 	return p;
 }
@@ -148,7 +128,7 @@
 			return 0;
 	}
 
-	p = ovl_cache_entry_new(rdd->dir, name, len, ino, d_type);
+	p = ovl_cache_entry_new(rdd, name, len, ino, d_type);
 	if (p == NULL)
 		return -ENOMEM;
 
@@ -169,7 +149,7 @@
 	if (p) {
 		list_move_tail(&p->l_node, &rdd->middle);
 	} else {
-		p = ovl_cache_entry_new(rdd->dir, name, namelen, ino, d_type);
+		p = ovl_cache_entry_new(rdd, name, namelen, ino, d_type);
 		if (p == NULL)
 			rdd->err = -ENOMEM;
 		else
@@ -219,6 +199,43 @@
 		return ovl_fill_lower(rdd, name, namelen, offset, ino, d_type);
 }
 
+static int ovl_check_whiteouts(struct dentry *dir, struct ovl_readdir_data *rdd)
+{
+	int err;
+	struct ovl_cache_entry *p;
+	struct dentry *dentry;
+	const struct cred *old_cred;
+	struct cred *override_cred;
+
+	override_cred = prepare_creds();
+	if (!override_cred)
+		return -ENOMEM;
+
+	/*
+	 * CAP_DAC_OVERRIDE for lookup
+	 */
+	cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE);
+	old_cred = override_creds(override_cred);
+
+	err = mutex_lock_killable(&dir->d_inode->i_mutex);
+	if (!err) {
+		while (rdd->first_maybe_whiteout) {
+			p = rdd->first_maybe_whiteout;
+			rdd->first_maybe_whiteout = p->next_maybe_whiteout;
+			dentry = lookup_one_len(p->name, dir, p->len);
+			if (!IS_ERR(dentry)) {
+				p->is_whiteout = ovl_is_whiteout(dentry);
+				dput(dentry);
+			}
+		}
+		mutex_unlock(&dir->d_inode->i_mutex);
+	}
+	revert_creds(old_cred);
+	put_cred(override_cred);
+
+	return err;
+}
+
 static inline int ovl_dir_read(struct path *realpath,
 			       struct ovl_readdir_data *rdd)
 {
@@ -229,7 +246,7 @@
 	if (IS_ERR(realfile))
 		return PTR_ERR(realfile);
 
-	rdd->dir = realpath->dentry;
+	rdd->first_maybe_whiteout = NULL;
 	rdd->ctx.pos = 0;
 	do {
 		rdd->count = 0;
@@ -238,6 +255,10 @@
 		if (err >= 0)
 			err = rdd->err;
 	} while (!err && rdd->count);
+
+	if (!err && rdd->first_maybe_whiteout)
+		err = ovl_check_whiteouts(realpath->dentry, rdd);
+
 	fput(realfile);
 
 	return err;
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index bf8537c..7466ff3 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -273,8 +273,56 @@
 	}
 }
 
+static int ovl_dentry_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+	unsigned int i;
+	int ret = 1;
+
+	for (i = 0; i < oe->numlower; i++) {
+		struct dentry *d = oe->lowerstack[i].dentry;
+
+		if (d->d_flags & DCACHE_OP_REVALIDATE) {
+			ret = d->d_op->d_revalidate(d, flags);
+			if (ret < 0)
+				return ret;
+			if (!ret) {
+				if (!(flags & LOOKUP_RCU))
+					d_invalidate(d);
+				return -ESTALE;
+			}
+		}
+	}
+	return 1;
+}
+
+static int ovl_dentry_weak_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+	unsigned int i;
+	int ret = 1;
+
+	for (i = 0; i < oe->numlower; i++) {
+		struct dentry *d = oe->lowerstack[i].dentry;
+
+		if (d->d_flags & DCACHE_OP_WEAK_REVALIDATE) {
+			ret = d->d_op->d_weak_revalidate(d, flags);
+			if (ret <= 0)
+				break;
+		}
+	}
+	return ret;
+}
+
 static const struct dentry_operations ovl_dentry_operations = {
 	.d_release = ovl_dentry_release,
+	.d_select_inode = ovl_d_select_inode,
+};
+
+static const struct dentry_operations ovl_reval_dentry_operations = {
+	.d_release = ovl_dentry_release,
+	.d_revalidate = ovl_dentry_revalidate,
+	.d_weak_revalidate = ovl_dentry_weak_revalidate,
 };
 
 static struct ovl_entry *ovl_alloc_entry(unsigned int numlower)
@@ -288,6 +336,20 @@
 	return oe;
 }
 
+static bool ovl_dentry_remote(struct dentry *dentry)
+{
+	return dentry->d_flags &
+		(DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE);
+}
+
+static bool ovl_dentry_weird(struct dentry *dentry)
+{
+	return dentry->d_flags & (DCACHE_NEED_AUTOMOUNT |
+				  DCACHE_MANAGE_TRANSIT |
+				  DCACHE_OP_HASH |
+				  DCACHE_OP_COMPARE);
+}
+
 static inline struct dentry *ovl_lookup_real(struct dentry *dir,
 					     struct qstr *name)
 {
@@ -303,6 +365,10 @@
 	} else if (!dentry->d_inode) {
 		dput(dentry);
 		dentry = NULL;
+	} else if (ovl_dentry_weird(dentry)) {
+		dput(dentry);
+		/* Don't support traversing automounts and other weirdness */
+		dentry = ERR_PTR(-EREMOTE);
 	}
 	return dentry;
 }
@@ -350,6 +416,11 @@
 			goto out;
 
 		if (this) {
+			if (unlikely(ovl_dentry_remote(this))) {
+				dput(this);
+				err = -EREMOTE;
+				goto out;
+			}
 			if (ovl_is_whiteout(this)) {
 				dput(this);
 				this = NULL;
@@ -694,25 +765,6 @@
 	}
 }
 
-static bool ovl_is_allowed_fs_type(struct dentry *root)
-{
-	const struct dentry_operations *dop = root->d_op;
-
-	/*
-	 * We don't support:
-	 *  - automount filesystems
-	 *  - filesystems with revalidate (FIXME for lower layer)
-	 *  - filesystems with case insensitive names
-	 */
-	if (dop &&
-	    (dop->d_manage || dop->d_automount ||
-	     dop->d_revalidate || dop->d_weak_revalidate ||
-	     dop->d_compare || dop->d_hash)) {
-		return false;
-	}
-	return true;
-}
-
 static int ovl_mount_dir_noesc(const char *name, struct path *path)
 {
 	int err = -EINVAL;
@@ -727,7 +779,7 @@
 		goto out;
 	}
 	err = -EINVAL;
-	if (!ovl_is_allowed_fs_type(path->dentry)) {
+	if (ovl_dentry_weird(path->dentry)) {
 		pr_err("overlayfs: filesystem on '%s' not supported\n", name);
 		goto out_put;
 	}
@@ -751,13 +803,21 @@
 	if (tmp) {
 		ovl_unescape(tmp);
 		err = ovl_mount_dir_noesc(tmp, path);
+
+		if (!err)
+			if (ovl_dentry_remote(path->dentry)) {
+				pr_err("overlayfs: filesystem on '%s' not supported as upperdir\n",
+				       tmp);
+				path_put(path);
+				err = -EINVAL;
+			}
 		kfree(tmp);
 	}
 	return err;
 }
 
 static int ovl_lower_dir(const char *name, struct path *path, long *namelen,
-			 int *stack_depth)
+			 int *stack_depth, bool *remote)
 {
 	int err;
 	struct kstatfs statfs;
@@ -774,6 +834,9 @@
 	*namelen = max(*namelen, statfs.f_namelen);
 	*stack_depth = max(*stack_depth, path->mnt->mnt_sb->s_stack_depth);
 
+	if (ovl_dentry_remote(path->dentry))
+		*remote = true;
+
 	return 0;
 
 out_put:
@@ -827,6 +890,7 @@
 	unsigned int numlower;
 	unsigned int stacklen = 0;
 	unsigned int i;
+	bool remote = false;
 	int err;
 
 	err = -ENOMEM;
@@ -900,7 +964,8 @@
 	lower = lowertmp;
 	for (numlower = 0; numlower < stacklen; numlower++) {
 		err = ovl_lower_dir(lower, &stack[numlower],
-				    &ufs->lower_namelen, &sb->s_stack_depth);
+				    &ufs->lower_namelen, &sb->s_stack_depth,
+				    &remote);
 		if (err)
 			goto out_put_lowerpath;
 
@@ -958,7 +1023,10 @@
 	if (!ufs->upper_mnt)
 		sb->s_flags |= MS_RDONLY;
 
-	sb->s_d_op = &ovl_dentry_operations;
+	if (remote)
+		sb->s_d_op = &ovl_reval_dentry_operations;
+	else
+		sb->s_d_op = &ovl_dentry_operations;
 
 	err = -ENOMEM;
 	oe = ovl_alloc_entry(numlower);
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 84bb65b8..4fb17de 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -547,51 +547,45 @@
 		struct posix_acl **default_acl, struct posix_acl **acl)
 {
 	struct posix_acl *p;
+	struct posix_acl *clone;
 	int ret;
 
+	*acl = NULL;
+	*default_acl = NULL;
+
 	if (S_ISLNK(*mode) || !IS_POSIXACL(dir))
-		goto no_acl;
+		return 0;
 
 	p = get_acl(dir, ACL_TYPE_DEFAULT);
-	if (IS_ERR(p)) {
-		if (p == ERR_PTR(-EOPNOTSUPP))
-			goto apply_umask;
-		return PTR_ERR(p);
+	if (!p || p == ERR_PTR(-EOPNOTSUPP)) {
+		*mode &= ~current_umask();
+		return 0;
 	}
+	if (IS_ERR(p))
+		return PTR_ERR(p);
 
-	if (!p)
-		goto apply_umask;
-
-	*acl = posix_acl_clone(p, GFP_NOFS);
-	if (!*acl)
+	clone = posix_acl_clone(p, GFP_NOFS);
+	if (!clone)
 		goto no_mem;
 
-	ret = posix_acl_create_masq(*acl, mode);
+	ret = posix_acl_create_masq(clone, mode);
 	if (ret < 0)
 		goto no_mem_clone;
 
-	if (ret == 0) {
-		posix_acl_release(*acl);
-		*acl = NULL;
-	}
+	if (ret == 0)
+		posix_acl_release(clone);
+	else
+		*acl = clone;
 
-	if (!S_ISDIR(*mode)) {
+	if (!S_ISDIR(*mode))
 		posix_acl_release(p);
-		*default_acl = NULL;
-	} else {
+	else
 		*default_acl = p;
-	}
-	return 0;
 
-apply_umask:
-	*mode &= ~current_umask();
-no_acl:
-	*default_acl = NULL;
-	*acl = NULL;
 	return 0;
 
 no_mem_clone:
-	posix_acl_release(*acl);
+	posix_acl_release(clone);
 no_mem:
 	posix_acl_release(p);
 	return -ENOMEM;
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 1d540b3..87782e8 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -491,14 +491,17 @@
 }
 #endif
 
-#ifdef CONFIG_SCHEDSTATS
+#ifdef CONFIG_SCHED_INFO
 /*
  * Provides /proc/PID/schedstat
  */
 static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns,
 			      struct pid *pid, struct task_struct *task)
 {
-	seq_printf(m, "%llu %llu %lu\n",
+	if (unlikely(!sched_info_on()))
+		seq_printf(m, "0 0 0\n");
+	else
+		seq_printf(m, "%llu %llu %lu\n",
 		   (unsigned long long)task->se.sum_exec_runtime,
 		   (unsigned long long)task->sched_info.run_delay,
 		   task->sched_info.pcount);
@@ -2787,7 +2790,7 @@
 #ifdef CONFIG_STACKTRACE
 	ONE("stack",      S_IRUSR, proc_pid_stack),
 #endif
-#ifdef CONFIG_SCHEDSTATS
+#ifdef CONFIG_SCHED_INFO
 	ONE("schedstat",  S_IRUGO, proc_pid_schedstat),
 #endif
 #ifdef CONFIG_LATENCYTOP
@@ -3135,7 +3138,7 @@
 #ifdef CONFIG_STACKTRACE
 	ONE("stack",      S_IRUSR, proc_pid_stack),
 #endif
-#ifdef CONFIG_SCHEDSTATS
+#ifdef CONFIG_SCHED_INFO
 	ONE("schedstat", S_IRUGO, proc_pid_schedstat),
 #endif
 #ifdef CONFIG_LATENCYTOP
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index df6327a..e5dee5c 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -373,6 +373,10 @@
 		WARN(1, "create '/proc/%s' by hand\n", qstr.name);
 		return NULL;
 	}
+	if (is_empty_pde(*parent)) {
+		WARN(1, "attempt to add to permanently empty directory");
+		return NULL;
+	}
 
 	ent = kzalloc(sizeof(struct proc_dir_entry) + qstr.len + 1, GFP_KERNEL);
 	if (!ent)
@@ -455,6 +459,25 @@
 }
 EXPORT_SYMBOL(proc_mkdir);
 
+struct proc_dir_entry *proc_create_mount_point(const char *name)
+{
+	umode_t mode = S_IFDIR | S_IRUGO | S_IXUGO;
+	struct proc_dir_entry *ent, *parent = NULL;
+
+	ent = __proc_create(&parent, name, mode, 2);
+	if (ent) {
+		ent->data = NULL;
+		ent->proc_fops = NULL;
+		ent->proc_iops = NULL;
+		if (proc_register(parent, ent) < 0) {
+			kfree(ent);
+			parent->nlink--;
+			ent = NULL;
+		}
+	}
+	return ent;
+}
+
 struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
 					struct proc_dir_entry *parent,
 					const struct file_operations *proc_fops,
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index afe232b..bd95b9f 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -422,6 +422,10 @@
 		inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
 		PROC_I(inode)->pde = de;
 
+		if (is_empty_pde(de)) {
+			make_empty_dir_inode(inode);
+			return inode;
+		}
 		if (de->mode) {
 			inode->i_mode = de->mode;
 			inode->i_uid = de->uid;
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index c835b94..aa27810 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -191,6 +191,12 @@
 }
 extern void pde_put(struct proc_dir_entry *);
 
+static inline bool is_empty_pde(const struct proc_dir_entry *pde)
+{
+	return S_ISDIR(pde->mode) && !pde->proc_iops;
+}
+struct proc_dir_entry *proc_create_mount_point(const char *name);
+
 /*
  * inode.c
  */
diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
index d4a3574..f8595e8 100644
--- a/fs/proc/nommu.c
+++ b/fs/proc/nommu.c
@@ -64,7 +64,7 @@
 
 	if (file) {
 		seq_pad(m, ' ');
-		seq_path(m, &file->f_path, "");
+		seq_file_path(m, file, "");
 	}
 
 	seq_putc(m, '\n');
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index fea2561..fdda62e 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -19,6 +19,28 @@
 static const struct file_operations proc_sys_dir_file_operations;
 static const struct inode_operations proc_sys_dir_operations;
 
+/* Support for permanently empty directories */
+
+struct ctl_table sysctl_mount_point[] = {
+	{ }
+};
+
+static bool is_empty_dir(struct ctl_table_header *head)
+{
+	return head->ctl_table[0].child == sysctl_mount_point;
+}
+
+static void set_empty_dir(struct ctl_dir *dir)
+{
+	dir->header.ctl_table[0].child = sysctl_mount_point;
+}
+
+static void clear_empty_dir(struct ctl_dir *dir)
+
+{
+	dir->header.ctl_table[0].child = NULL;
+}
+
 void proc_sys_poll_notify(struct ctl_table_poll *poll)
 {
 	if (!poll)
@@ -187,6 +209,17 @@
 	struct ctl_table *entry;
 	int err;
 
+	/* Is this a permanently empty directory? */
+	if (is_empty_dir(&dir->header))
+		return -EROFS;
+
+	/* Am I creating a permanently empty directory? */
+	if (header->ctl_table == sysctl_mount_point) {
+		if (!RB_EMPTY_ROOT(&dir->root))
+			return -EINVAL;
+		set_empty_dir(dir);
+	}
+
 	dir->header.nreg++;
 	header->parent = dir;
 	err = insert_links(header);
@@ -202,6 +235,8 @@
 	erase_header(header);
 	put_links(header);
 fail_links:
+	if (header->ctl_table == sysctl_mount_point)
+		clear_empty_dir(dir);
 	header->parent = NULL;
 	drop_sysctl_table(&dir->header);
 	return err;
@@ -419,6 +454,8 @@
 		inode->i_mode |= S_IFDIR;
 		inode->i_op = &proc_sys_dir_operations;
 		inode->i_fop = &proc_sys_dir_file_operations;
+		if (is_empty_dir(head))
+			make_empty_dir_inode(inode);
 	}
 out:
 	return inode;
diff --git a/fs/proc/root.c b/fs/proc/root.c
index b7fa4bf..68feb0f 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -112,9 +112,6 @@
 		ns = task_active_pid_ns(current);
 		options = data;
 
-		if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
-			return ERR_PTR(-EPERM);
-
 		/* Does the mounter have privilege over the pid namespace? */
 		if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
 			return ERR_PTR(-EPERM);
@@ -159,7 +156,7 @@
 	.name		= "proc",
 	.mount		= proc_mount,
 	.kill_sb	= proc_kill_sb,
-	.fs_flags	= FS_USERNS_MOUNT,
+	.fs_flags	= FS_USERNS_VISIBLE | FS_USERNS_MOUNT,
 };
 
 void __init proc_root_init(void)
@@ -182,10 +179,10 @@
 #endif
 	proc_mkdir("fs", NULL);
 	proc_mkdir("driver", NULL);
-	proc_mkdir("fs/nfsd", NULL); /* somewhere for the nfsd filesystem to be mounted */
+	proc_create_mount_point("fs/nfsd"); /* somewhere for the nfsd filesystem to be mounted */
 #if defined(CONFIG_SUN_OPENPROMFS) || defined(CONFIG_SUN_OPENPROMFS_MODULE)
 	/* just give it a mountpoint */
-	proc_mkdir("openprom", NULL);
+	proc_create_mount_point("openprom");
 #endif
 	proc_tty_init();
 	proc_mkdir("bus", NULL);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 6dee68d..ca1e091 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -310,7 +310,7 @@
 	 */
 	if (file) {
 		seq_pad(m, ' ');
-		seq_path(m, &file->f_path, "\n");
+		seq_file_path(m, file, "\n");
 		goto done;
 	}
 
@@ -1509,7 +1509,7 @@
 
 	if (file) {
 		seq_puts(m, " file=");
-		seq_path(m, &file->f_path, "\n\t= ");
+		seq_file_path(m, file, "\n\t= ");
 	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
 		seq_puts(m, " heap");
 	} else {
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 599ec2e..e0d64c9 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -180,7 +180,7 @@
 
 	if (file) {
 		seq_pad(m, ' ');
-		seq_path(m, &file->f_path, "");
+		seq_file_path(m, file, "");
 	} else if (mm) {
 		pid_t tid = pid_of_stack(priv, vma, is_pid);
 
diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c
index 8db932d..8ebd9a3 100644
--- a/fs/proc_namespace.c
+++ b/fs/proc_namespace.c
@@ -17,7 +17,8 @@
 
 static unsigned mounts_poll(struct file *file, poll_table *wait)
 {
-	struct proc_mounts *p = proc_mounts(file->private_data);
+	struct seq_file *m = file->private_data;
+	struct proc_mounts *p = m->private;
 	struct mnt_namespace *ns = p->ns;
 	unsigned res = POLLIN | POLLRDNORM;
 	int event;
@@ -25,8 +26,8 @@
 	poll_wait(file, &p->ns->poll, wait);
 
 	event = ACCESS_ONCE(ns->event);
-	if (p->m.poll_event != event) {
-		p->m.poll_event = event;
+	if (m->poll_event != event) {
+		m->poll_event = event;
 		res |= POLLERR | POLLPRI;
 	}
 
@@ -92,7 +93,7 @@
 
 static int show_vfsmnt(struct seq_file *m, struct vfsmount *mnt)
 {
-	struct proc_mounts *p = proc_mounts(m);
+	struct proc_mounts *p = m->private;
 	struct mount *r = real_mount(mnt);
 	int err = 0;
 	struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
@@ -126,7 +127,7 @@
 
 static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt)
 {
-	struct proc_mounts *p = proc_mounts(m);
+	struct proc_mounts *p = m->private;
 	struct mount *r = real_mount(mnt);
 	struct super_block *sb = mnt->mnt_sb;
 	struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
@@ -186,7 +187,7 @@
 
 static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt)
 {
-	struct proc_mounts *p = proc_mounts(m);
+	struct proc_mounts *p = m->private;
 	struct mount *r = real_mount(mnt);
 	struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
 	struct super_block *sb = mnt_path.dentry->d_sb;
@@ -236,6 +237,7 @@
 	struct mnt_namespace *ns = NULL;
 	struct path root;
 	struct proc_mounts *p;
+	struct seq_file *m;
 	int ret = -EINVAL;
 
 	if (!task)
@@ -260,26 +262,21 @@
 	task_unlock(task);
 	put_task_struct(task);
 
-	ret = -ENOMEM;
-	p = kmalloc(sizeof(struct proc_mounts), GFP_KERNEL);
-	if (!p)
+	ret = seq_open_private(file, &mounts_op, sizeof(struct proc_mounts));
+	if (ret)
 		goto err_put_path;
 
-	file->private_data = &p->m;
-	ret = seq_open(file, &mounts_op);
-	if (ret)
-		goto err_free;
+	m = file->private_data;
+	m->poll_event = ns->event;
 
+	p = m->private;
 	p->ns = ns;
 	p->root = root;
-	p->m.poll_event = ns->event;
 	p->show = show;
 	p->cached_event = ~0ULL;
 
 	return 0;
 
- err_free:
-	kfree(p);
  err_put_path:
 	path_put(&root);
  err_put_ns:
@@ -290,10 +287,11 @@
 
 static int mounts_release(struct inode *inode, struct file *file)
 {
-	struct proc_mounts *p = proc_mounts(file->private_data);
+	struct seq_file *m = file->private_data;
+	struct proc_mounts *p = m->private;
 	path_put(&p->root);
 	put_mnt_ns(p->ns);
-	return seq_release(inode, file);
+	return seq_release_private(inode, file);
 }
 
 static int mounts_open(struct inode *inode, struct file *file)
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index dc43b5f..3adcc46 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -461,22 +461,18 @@
 	.kill_sb	= pstore_kill_sb,
 };
 
-static struct kobject *pstore_kobj;
-
 static int __init init_pstore_fs(void)
 {
-	int err = 0;
+	int err;
 
 	/* Create a convenient mount point for people to access pstore */
-	pstore_kobj = kobject_create_and_add("pstore", fs_kobj);
-	if (!pstore_kobj) {
-		err = -ENOMEM;
+	err = sysfs_create_mount_point(fs_kobj, "pstore");
+	if (err)
 		goto out;
-	}
 
 	err = register_filesystem(&pstore_fs_type);
 	if (err < 0)
-		kobject_put(pstore_kobj);
+		sysfs_remove_mount_point(fs_kobj, "pstore");
 
 out:
 	return err;
diff --git a/fs/qnx6/dir.c b/fs/qnx6/dir.c
index 8d64bb5..e1f3727 100644
--- a/fs/qnx6/dir.c
+++ b/fs/qnx6/dir.c
@@ -32,11 +32,6 @@
 	return page;
 }
 
-static inline unsigned long dir_pages(struct inode *inode)
-{
-	return (inode->i_size+PAGE_CACHE_SIZE-1)>>PAGE_CACHE_SHIFT;
-}
-
 static unsigned last_entry(struct inode *inode, unsigned long page_nr)
 {
 	unsigned long last_byte = inode->i_size;
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 52b4927..ce9e39f 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -48,18 +48,21 @@
  *	ERR_PTR(error).  In the end of sequence they return %NULL. ->show()
  *	returns 0 in case of success and negative number in case of error.
  *	Returning SEQ_SKIP means "discard this element and move on".
+ *	Note: seq_open() will allocate a struct seq_file and store its
+ *	pointer in @file->private_data. This pointer should not be modified.
  */
 int seq_open(struct file *file, const struct seq_operations *op)
 {
-	struct seq_file *p = file->private_data;
+	struct seq_file *p;
 
-	if (!p) {
-		p = kmalloc(sizeof(*p), GFP_KERNEL);
-		if (!p)
-			return -ENOMEM;
-		file->private_data = p;
-	}
-	memset(p, 0, sizeof(*p));
+	WARN_ON(file->private_data);
+
+	p = kzalloc(sizeof(*p), GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	file->private_data = p;
+
 	mutex_init(&p->lock);
 	p->op = op;
 #ifdef CONFIG_USER_NS
@@ -487,6 +490,20 @@
 }
 EXPORT_SYMBOL(seq_path);
 
+/**
+ * seq_file_path - seq_file interface to print a pathname of a file
+ * @m: the seq_file handle
+ * @file: the struct file to print
+ * @esc: set of characters to escape in the output
+ *
+ * return the absolute path to the file.
+ */
+int seq_file_path(struct seq_file *m, struct file *file, const char *esc)
+{
+	return seq_path(m, &file->f_path, esc);
+}
+EXPORT_SYMBOL(seq_file_path);
+
 /*
  * Same as seq_path, but relative to supplied root.
  */
diff --git a/fs/squashfs/squashfs_fs_i.h b/fs/squashfs/squashfs_fs_i.h
index 73588e7..d09fcd6 100644
--- a/fs/squashfs/squashfs_fs_i.h
+++ b/fs/squashfs/squashfs_fs_i.h
@@ -49,6 +49,6 @@
 
 static inline struct squashfs_inode_info *squashfs_i(struct inode *inode)
 {
-	return list_entry(inode, struct squashfs_inode_info, vfs_inode);
+	return container_of(inode, struct squashfs_inode_info, vfs_inode);
 }
 #endif
diff --git a/fs/super.c b/fs/super.c
index 928c20f..b613723 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -842,7 +842,7 @@
 	else if (error)
 		return -EAGAIN;
 
-	if (dev == (1 << MINORBITS)) {
+	if (dev >= (1 << MINORBITS)) {
 		spin_lock(&unnamed_dev_lock);
 		ida_remove(&unnamed_dev_ida, dev);
 		if (unnamed_dev_start > dev)
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 0b45ff4..94374e4 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -121,3 +121,37 @@
 
 	return kernfs_rename_ns(kn, new_parent, kn->name, new_ns);
 }
+
+/**
+ * sysfs_create_mount_point - create an always empty directory
+ * @parent_kobj:  kobject that will contain this always empty directory
+ * @name: The name of the always empty directory to add
+ */
+int sysfs_create_mount_point(struct kobject *parent_kobj, const char *name)
+{
+	struct kernfs_node *kn, *parent = parent_kobj->sd;
+
+	kn = kernfs_create_empty_dir(parent, name);
+	if (IS_ERR(kn)) {
+		if (PTR_ERR(kn) == -EEXIST)
+			sysfs_warn_dup(parent, name);
+		return PTR_ERR(kn);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(sysfs_create_mount_point);
+
+/**
+ *	sysfs_remove_mount_point - remove an always empty directory.
+ *	@parent_kobj: kobject that will contain this always empty directory
+ *	@name: The name of the always empty directory to remove
+ *
+ */
+void sysfs_remove_mount_point(struct kobject *parent_kobj, const char *name)
+{
+	struct kernfs_node *parent = parent_kobj->sd;
+
+	kernfs_remove_by_name_ns(parent, name, NULL);
+}
+EXPORT_SYMBOL_GPL(sysfs_remove_mount_point);
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 8a49486..1c6ac6f 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -31,9 +31,6 @@
 	bool new_sb;
 
 	if (!(flags & MS_KERNMOUNT)) {
-		if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
-			return ERR_PTR(-EPERM);
-
 		if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET))
 			return ERR_PTR(-EPERM);
 	}
@@ -58,7 +55,7 @@
 	.name		= "sysfs",
 	.mount		= sysfs_mount,
 	.kill_sb	= sysfs_kill_sb,
-	.fs_flags	= FS_USERNS_MOUNT,
+	.fs_flags	= FS_USERNS_VISIBLE | FS_USERNS_MOUNT,
 };
 
 int __init sysfs_init(void)
diff --git a/fs/sysv/dir.c b/fs/sysv/dir.c
index 8f3555f..63c1bcb 100644
--- a/fs/sysv/dir.c
+++ b/fs/sysv/dir.c
@@ -33,11 +33,6 @@
 	page_cache_release(page);
 }
 
-static inline unsigned long dir_pages(struct inode *inode)
-{
-	return (inode->i_size+PAGE_CACHE_SIZE-1)>>PAGE_CACHE_SHIFT;
-}
-
 static int dir_commit_chunk(struct page *page, loff_t pos, unsigned len)
 {
 	struct address_space *mapping = page->mapping;
diff --git a/fs/sysv/sysv.h b/fs/sysv/sysv.h
index 2c13525..6c21228 100644
--- a/fs/sysv/sysv.h
+++ b/fs/sysv/sysv.h
@@ -73,7 +73,7 @@
 
 static inline struct sysv_inode_info *SYSV_I(struct inode *inode)
 {
-	return list_entry(inode, struct sysv_inode_info, vfs_inode);
+	return container_of(inode, struct sysv_inode_info, vfs_inode);
 }
 
 static inline struct sysv_sb_info *SYSV_SB(struct super_block *sb)
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index d92bdf3..cbc8d5d 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -496,16 +496,11 @@
 	return dentry;
 }
 
-static inline int tracefs_positive(struct dentry *dentry)
-{
-	return dentry->d_inode && !d_unhashed(dentry);
-}
-
 static int __tracefs_remove(struct dentry *dentry, struct dentry *parent)
 {
 	int ret = 0;
 
-	if (tracefs_positive(dentry)) {
+	if (simple_positive(dentry)) {
 		if (dentry->d_inode) {
 			dget(dentry);
 			switch (dentry->d_inode->i_mode & S_IFMT) {
@@ -582,7 +577,7 @@
 	 */
 	spin_lock(&parent->d_lock);
 	list_for_each_entry(child, &parent->d_subdirs, d_child) {
-		if (!tracefs_positive(child))
+		if (!simple_positive(child))
 			continue;
 
 		/* perhaps simple_empty(child) makes more sense */
@@ -603,7 +598,7 @@
 		 * from d_subdirs. When releasing the parent->d_lock we can
 		 * no longer trust that the next pointer is valid.
 		 * Restart the loop. We'll skip this one with the
-		 * tracefs_positive() check.
+		 * simple_positive() check.
 		 */
 		goto loop;
 	}
@@ -631,14 +626,12 @@
 	return tracefs_registered;
 }
 
-static struct kobject *trace_kobj;
-
 static int __init tracefs_init(void)
 {
 	int retval;
 
-	trace_kobj = kobject_create_and_add("tracing", kernel_kobj);
-	if (!trace_kobj)
+	retval = sysfs_create_mount_point(kernel_kobj, "tracing");
+	if (retval)
 		return -EINVAL;
 
 	retval = register_filesystem(&trace_fs_type);
diff --git a/fs/udf/udf_i.h b/fs/udf/udf_i.h
index b5cd8ed..b1b9a63 100644
--- a/fs/udf/udf_i.h
+++ b/fs/udf/udf_i.h
@@ -56,7 +56,7 @@
 
 static inline struct udf_inode_info *UDF_I(struct inode *inode)
 {
-	return list_entry(inode, struct udf_inode_info, vfs_inode);
+	return container_of(inode, struct udf_inode_info, vfs_inode);
 }
 
 #endif /* _UDF_I_H) */
diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c
index 2c10360..a7106ed 100644
--- a/fs/ufs/balloc.c
+++ b/fs/ufs/balloc.c
@@ -51,8 +51,8 @@
 	
 	if (ufs_fragnum(fragment) + count > uspi->s_fpg)
 		ufs_error (sb, "ufs_free_fragments", "internal error");
-	
-	lock_ufs(sb);
+
+	mutex_lock(&UFS_SB(sb)->s_lock);
 	
 	cgno = ufs_dtog(uspi, fragment);
 	bit = ufs_dtogd(uspi, fragment);
@@ -115,13 +115,13 @@
 	if (sb->s_flags & MS_SYNCHRONOUS)
 		ubh_sync_block(UCPI_UBH(ucpi));
 	ufs_mark_sb_dirty(sb);
-	
-	unlock_ufs(sb);
+
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	UFSD("EXIT\n");
 	return;
 
 failed:
-	unlock_ufs(sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	UFSD("EXIT (FAILED)\n");
 	return;
 }
@@ -151,7 +151,7 @@
 		goto failed;
 	}
 
-	lock_ufs(sb);
+	mutex_lock(&UFS_SB(sb)->s_lock);
 	
 do_more:
 	overflow = 0;
@@ -211,12 +211,12 @@
 	}
 
 	ufs_mark_sb_dirty(sb);
-	unlock_ufs(sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	UFSD("EXIT\n");
 	return;
 
 failed_unlock:
-	unlock_ufs(sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 failed:
 	UFSD("EXIT (FAILED)\n");
 	return;
@@ -357,7 +357,7 @@
 	usb1 = ubh_get_usb_first(uspi);
 	*err = -ENOSPC;
 
-	lock_ufs(sb);
+	mutex_lock(&UFS_SB(sb)->s_lock);
 	tmp = ufs_data_ptr_to_cpu(sb, p);
 
 	if (count + ufs_fragnum(fragment) > uspi->s_fpb) {
@@ -378,19 +378,19 @@
 				  "fragment %llu, tmp %llu\n",
 				  (unsigned long long)fragment,
 				  (unsigned long long)tmp);
-			unlock_ufs(sb);
+			mutex_unlock(&UFS_SB(sb)->s_lock);
 			return INVBLOCK;
 		}
 		if (fragment < UFS_I(inode)->i_lastfrag) {
 			UFSD("EXIT (ALREADY ALLOCATED)\n");
-			unlock_ufs(sb);
+			mutex_unlock(&UFS_SB(sb)->s_lock);
 			return 0;
 		}
 	}
 	else {
 		if (tmp) {
 			UFSD("EXIT (ALREADY ALLOCATED)\n");
-			unlock_ufs(sb);
+			mutex_unlock(&UFS_SB(sb)->s_lock);
 			return 0;
 		}
 	}
@@ -399,7 +399,7 @@
 	 * There is not enough space for user on the device
 	 */
 	if (!capable(CAP_SYS_RESOURCE) && ufs_freespace(uspi, UFS_MINFREE) <= 0) {
-		unlock_ufs(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		UFSD("EXIT (FAILED)\n");
 		return 0;
 	}
@@ -424,7 +424,7 @@
 			ufs_clear_frags(inode, result + oldcount,
 					newcount - oldcount, locked_page != NULL);
 		}
-		unlock_ufs(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		UFSD("EXIT, result %llu\n", (unsigned long long)result);
 		return result;
 	}
@@ -439,7 +439,7 @@
 						fragment + count);
 		ufs_clear_frags(inode, result + oldcount, newcount - oldcount,
 				locked_page != NULL);
-		unlock_ufs(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		UFSD("EXIT, result %llu\n", (unsigned long long)result);
 		return result;
 	}
@@ -477,7 +477,7 @@
 		*err = 0;
 		UFS_I(inode)->i_lastfrag = max(UFS_I(inode)->i_lastfrag,
 						fragment + count);
-		unlock_ufs(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		if (newcount < request)
 			ufs_free_fragments (inode, result + newcount, request - newcount);
 		ufs_free_fragments (inode, tmp, oldcount);
@@ -485,7 +485,7 @@
 		return result;
 	}
 
-	unlock_ufs(sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	UFSD("EXIT (FAILED)\n");
 	return 0;
 }		
diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c
index 1bfe8ca..74f2e80 100644
--- a/fs/ufs/dir.c
+++ b/fs/ufs/dir.c
@@ -65,11 +65,6 @@
 	page_cache_release(page);
 }
 
-static inline unsigned long ufs_dir_pages(struct inode *inode)
-{
-	return (inode->i_size+PAGE_CACHE_SIZE-1)>>PAGE_CACHE_SHIFT;
-}
-
 ino_t ufs_inode_by_name(struct inode *dir, const struct qstr *qstr)
 {
 	ino_t res = 0;
@@ -87,7 +82,8 @@
 
 /* Releases the page */
 void ufs_set_link(struct inode *dir, struct ufs_dir_entry *de,
-		  struct page *page, struct inode *inode)
+		  struct page *page, struct inode *inode,
+		  bool update_times)
 {
 	loff_t pos = page_offset(page) +
 			(char *) de - (char *) page_address(page);
@@ -103,7 +99,8 @@
 
 	err = ufs_commit_chunk(page, pos, len);
 	ufs_put_page(page);
-	dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
+	if (update_times)
+		dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
 	mark_inode_dirty(dir);
 }
 
@@ -256,7 +253,7 @@
 	int namelen = qstr->len;
 	unsigned reclen = UFS_DIR_REC_LEN(namelen);
 	unsigned long start, n;
-	unsigned long npages = ufs_dir_pages(dir);
+	unsigned long npages = dir_pages(dir);
 	struct page *page = NULL;
 	struct ufs_inode_info *ui = UFS_I(dir);
 	struct ufs_dir_entry *de;
@@ -320,7 +317,7 @@
 	unsigned short rec_len, name_len;
 	struct page *page = NULL;
 	struct ufs_dir_entry *de;
-	unsigned long npages = ufs_dir_pages(dir);
+	unsigned long npages = dir_pages(dir);
 	unsigned long n;
 	char *kaddr;
 	loff_t pos;
@@ -437,7 +434,7 @@
 	struct super_block *sb = inode->i_sb;
 	unsigned int offset = pos & ~PAGE_CACHE_MASK;
 	unsigned long n = pos >> PAGE_CACHE_SHIFT;
-	unsigned long npages = ufs_dir_pages(inode);
+	unsigned long npages = dir_pages(inode);
 	unsigned chunk_mask = ~(UFS_SB(sb)->s_uspi->s_dirblksize - 1);
 	int need_revalidate = file->f_version != inode->i_version;
 	unsigned flags = UFS_SB(sb)->s_flags;
@@ -608,7 +605,7 @@
 {
 	struct super_block *sb = inode->i_sb;
 	struct page *page = NULL;
-	unsigned long i, npages = ufs_dir_pages(inode);
+	unsigned long i, npages = dir_pages(inode);
 
 	for (i = 0; i < npages; i++) {
 		char *kaddr;
diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c
index 7caa016..fd0203c 100644
--- a/fs/ufs/ialloc.c
+++ b/fs/ufs/ialloc.c
@@ -69,11 +69,11 @@
 	
 	ino = inode->i_ino;
 
-	lock_ufs(sb);
+	mutex_lock(&UFS_SB(sb)->s_lock);
 
 	if (!((ino > 1) && (ino < (uspi->s_ncg * uspi->s_ipg )))) {
 		ufs_warning(sb, "ufs_free_inode", "reserved inode or nonexistent inode %u\n", ino);
-		unlock_ufs(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		return;
 	}
 	
@@ -81,7 +81,7 @@
 	bit = ufs_inotocgoff (ino);
 	ucpi = ufs_load_cylinder (sb, cg);
 	if (!ucpi) {
-		unlock_ufs(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		return;
 	}
 	ucg = ubh_get_ucg(UCPI_UBH(ucpi));
@@ -115,7 +115,7 @@
 		ubh_sync_block(UCPI_UBH(ucpi));
 	
 	ufs_mark_sb_dirty(sb);
-	unlock_ufs(sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	UFSD("EXIT\n");
 }
 
@@ -193,7 +193,7 @@
 	sbi = UFS_SB(sb);
 	uspi = sbi->s_uspi;
 
-	lock_ufs(sb);
+	mutex_lock(&sbi->s_lock);
 
 	/*
 	 * Try to place the inode in its parent directory
@@ -331,21 +331,21 @@
 			sync_dirty_buffer(bh);
 		brelse(bh);
 	}
-	unlock_ufs(sb);
+	mutex_unlock(&sbi->s_lock);
 
 	UFSD("allocating inode %lu\n", inode->i_ino);
 	UFSD("EXIT\n");
 	return inode;
 
 fail_remove_inode:
-	unlock_ufs(sb);
+	mutex_unlock(&sbi->s_lock);
 	clear_nlink(inode);
 	unlock_new_inode(inode);
 	iput(inode);
 	UFSD("EXIT (FAILED): err %d\n", err);
 	return ERR_PTR(err);
 failed:
-	unlock_ufs(sb);
+	mutex_unlock(&sbi->s_lock);
 	make_bad_inode(inode);
 	iput (inode);
 	UFSD("EXIT (FAILED): err %d\n", err);
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index 99aaf5c..f913a69 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -903,6 +903,9 @@
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
 
-	if (want_delete)
+	if (want_delete) {
+		lock_ufs(inode->i_sb);
 		ufs_free_inode(inode);
+		unlock_ufs(inode->i_sb);
+	}
 }
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index f773deb..4796655 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -56,11 +56,9 @@
 	if (dentry->d_name.len > UFS_MAXNAMLEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
-	lock_ufs(dir->i_sb);
 	ino = ufs_inode_by_name(dir, &dentry->d_name);
 	if (ino)
 		inode = ufs_iget(dir->i_sb, ino);
-	unlock_ufs(dir->i_sb);
 	return d_splice_alias(inode, dentry);
 }
 
@@ -76,24 +74,16 @@
 		bool excl)
 {
 	struct inode *inode;
-	int err;
-
-	UFSD("BEGIN\n");
 
 	inode = ufs_new_inode(dir, mode);
-	err = PTR_ERR(inode);
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
 
-	if (!IS_ERR(inode)) {
-		inode->i_op = &ufs_file_inode_operations;
-		inode->i_fop = &ufs_file_operations;
-		inode->i_mapping->a_ops = &ufs_aops;
-		mark_inode_dirty(inode);
-		lock_ufs(dir->i_sb);
-		err = ufs_add_nondir(dentry, inode);
-		unlock_ufs(dir->i_sb);
-	}
-	UFSD("END: err=%d\n", err);
-	return err;
+	inode->i_op = &ufs_file_inode_operations;
+	inode->i_fop = &ufs_file_operations;
+	inode->i_mapping->a_ops = &ufs_aops;
+	mark_inode_dirty(inode);
+	return ufs_add_nondir(dentry, inode);
 }
 
 static int ufs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev)
@@ -110,9 +100,7 @@
 		init_special_inode(inode, mode, rdev);
 		ufs_set_inode_dev(inode->i_sb, UFS_I(inode), rdev);
 		mark_inode_dirty(inode);
-		lock_ufs(dir->i_sb);
 		err = ufs_add_nondir(dentry, inode);
-		unlock_ufs(dir->i_sb);
 	}
 	return err;
 }
@@ -121,19 +109,18 @@
 	const char * symname)
 {
 	struct super_block * sb = dir->i_sb;
-	int err = -ENAMETOOLONG;
+	int err;
 	unsigned l = strlen(symname)+1;
 	struct inode * inode;
 
 	if (l > sb->s_blocksize)
-		goto out_notlocked;
+		return -ENAMETOOLONG;
 
 	inode = ufs_new_inode(dir, S_IFLNK | S_IRWXUGO);
 	err = PTR_ERR(inode);
 	if (IS_ERR(inode))
-		goto out_notlocked;
+		return err;
 
-	lock_ufs(dir->i_sb);
 	if (l > UFS_SB(sb)->s_uspi->s_maxsymlinklen) {
 		/* slow symlink */
 		inode->i_op = &ufs_symlink_inode_operations;
@@ -150,17 +137,13 @@
 	}
 	mark_inode_dirty(inode);
 
-	err = ufs_add_nondir(dentry, inode);
-out:
-	unlock_ufs(dir->i_sb);
-out_notlocked:
-	return err;
+	return ufs_add_nondir(dentry, inode);
 
 out_fail:
 	inode_dec_link_count(inode);
 	unlock_new_inode(inode);
 	iput(inode);
-	goto out;
+	return err;
 }
 
 static int ufs_link (struct dentry * old_dentry, struct inode * dir,
@@ -169,14 +152,16 @@
 	struct inode *inode = d_inode(old_dentry);
 	int error;
 
-	lock_ufs(dir->i_sb);
-
 	inode->i_ctime = CURRENT_TIME_SEC;
 	inode_inc_link_count(inode);
 	ihold(inode);
 
-	error = ufs_add_nondir(dentry, inode);
-	unlock_ufs(dir->i_sb);
+	error = ufs_add_link(dentry, inode);
+	if (error) {
+		inode_dec_link_count(inode);
+		iput(inode);
+	} else
+		d_instantiate(dentry, inode);
 	return error;
 }
 
@@ -185,9 +170,12 @@
 	struct inode * inode;
 	int err;
 
+	inode_inc_link_count(dir);
+
 	inode = ufs_new_inode(dir, S_IFDIR|mode);
+	err = PTR_ERR(inode);
 	if (IS_ERR(inode))
-		return PTR_ERR(inode);
+		goto out_dir;
 
 	inode->i_op = &ufs_dir_inode_operations;
 	inode->i_fop = &ufs_dir_operations;
@@ -195,9 +183,6 @@
 
 	inode_inc_link_count(inode);
 
-	lock_ufs(dir->i_sb);
-	inode_inc_link_count(dir);
-
 	err = ufs_make_empty(inode, dir);
 	if (err)
 		goto out_fail;
@@ -205,20 +190,19 @@
 	err = ufs_add_link(dentry, inode);
 	if (err)
 		goto out_fail;
-	unlock_ufs(dir->i_sb);
 
+	unlock_new_inode(inode);
 	d_instantiate(dentry, inode);
-out:
-	return err;
+	return 0;
 
 out_fail:
 	inode_dec_link_count(inode);
 	inode_dec_link_count(inode);
 	unlock_new_inode(inode);
 	iput (inode);
+out_dir:
 	inode_dec_link_count(dir);
-	unlock_ufs(dir->i_sb);
-	goto out;
+	return err;
 }
 
 static int ufs_unlink(struct inode *dir, struct dentry *dentry)
@@ -248,7 +232,6 @@
 	struct inode * inode = d_inode(dentry);
 	int err= -ENOTEMPTY;
 
-	lock_ufs(dir->i_sb);
 	if (ufs_empty_dir (inode)) {
 		err = ufs_unlink(dir, dentry);
 		if (!err) {
@@ -257,7 +240,6 @@
 			inode_dec_link_count(dir);
 		}
 	}
-	unlock_ufs(dir->i_sb);
 	return err;
 }
 
@@ -295,7 +277,7 @@
 		new_de = ufs_find_entry(new_dir, &new_dentry->d_name, &new_page);
 		if (!new_de)
 			goto out_dir;
-		ufs_set_link(new_dir, new_de, new_page, old_inode);
+		ufs_set_link(new_dir, new_de, new_page, old_inode, 1);
 		new_inode->i_ctime = CURRENT_TIME_SEC;
 		if (dir_de)
 			drop_nlink(new_inode);
@@ -318,7 +300,12 @@
 	mark_inode_dirty(old_inode);
 
 	if (dir_de) {
-		ufs_set_link(old_inode, dir_de, dir_page, new_dir);
+		if (old_dir != new_dir)
+			ufs_set_link(old_inode, dir_de, dir_page, new_dir, 0);
+		else {
+			kunmap(dir_page);
+			page_cache_release(dir_page);
+		}
 		inode_dec_link_count(old_dir);
 	}
 	return 0;
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index 098508a..250579a 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -695,6 +695,7 @@
 	unsigned flags;
 
 	lock_ufs(sb);
+	mutex_lock(&UFS_SB(sb)->s_lock);
 
 	UFSD("ENTER\n");
 
@@ -712,6 +713,7 @@
 	ufs_put_cstotal(sb);
 
 	UFSD("EXIT\n");
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	unlock_ufs(sb);
 
 	return 0;
@@ -800,6 +802,7 @@
 	UFSD("flag %u\n", (int)(sb->s_flags & MS_RDONLY));
 	
 	mutex_init(&sbi->mutex);
+	mutex_init(&sbi->s_lock);
 	spin_lock_init(&sbi->work_lock);
 	INIT_DELAYED_WORK(&sbi->sync_work, delayed_sync_fs);
 	/*
@@ -1278,6 +1281,7 @@
 
 	sync_filesystem(sb);
 	lock_ufs(sb);
+	mutex_lock(&UFS_SB(sb)->s_lock);
 	uspi = UFS_SB(sb)->s_uspi;
 	flags = UFS_SB(sb)->s_flags;
 	usb1 = ubh_get_usb_first(uspi);
@@ -1291,6 +1295,7 @@
 	new_mount_opt = 0;
 	ufs_set_opt (new_mount_opt, ONERROR_LOCK);
 	if (!ufs_parse_options (data, &new_mount_opt)) {
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		unlock_ufs(sb);
 		return -EINVAL;
 	}
@@ -1298,12 +1303,14 @@
 		new_mount_opt |= ufstype;
 	} else if ((new_mount_opt & UFS_MOUNT_UFSTYPE) != ufstype) {
 		pr_err("ufstype can't be changed during remount\n");
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		unlock_ufs(sb);
 		return -EINVAL;
 	}
 
 	if ((*mount_flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) {
 		UFS_SB(sb)->s_mount_opt = new_mount_opt;
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		unlock_ufs(sb);
 		return 0;
 	}
@@ -1327,6 +1334,7 @@
 	 */
 #ifndef CONFIG_UFS_FS_WRITE
 		pr_err("ufs was compiled with read-only support, can't be mounted as read-write\n");
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		unlock_ufs(sb);
 		return -EINVAL;
 #else
@@ -1336,11 +1344,13 @@
 		    ufstype != UFS_MOUNT_UFSTYPE_SUNx86 &&
 		    ufstype != UFS_MOUNT_UFSTYPE_UFS2) {
 			pr_err("this ufstype is read-only supported\n");
+			mutex_unlock(&UFS_SB(sb)->s_lock);
 			unlock_ufs(sb);
 			return -EINVAL;
 		}
 		if (!ufs_read_cylinder_structures(sb)) {
 			pr_err("failed during remounting\n");
+			mutex_unlock(&UFS_SB(sb)->s_lock);
 			unlock_ufs(sb);
 			return -EPERM;
 		}
@@ -1348,6 +1358,7 @@
 #endif
 	}
 	UFS_SB(sb)->s_mount_opt = new_mount_opt;
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	unlock_ufs(sb);
 	return 0;
 }
diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h
index 2a07396..2e31ea2 100644
--- a/fs/ufs/ufs.h
+++ b/fs/ufs/ufs.h
@@ -30,6 +30,7 @@
 	int work_queued; /* non-zero if the delayed work is queued */
 	struct delayed_work sync_work; /* FS sync delayed work */
 	spinlock_t work_lock; /* protects sync_work and work_queued */
+	struct mutex s_lock;
 };
 
 struct ufs_inode_info {
@@ -105,7 +106,7 @@
 extern int ufs_empty_dir (struct inode *);
 extern struct ufs_dir_entry *ufs_dotdot(struct inode *, struct page **);
 extern void ufs_set_link(struct inode *dir, struct ufs_dir_entry *de,
-			 struct page *page, struct inode *inode);
+			 struct page *page, struct inode *inode, bool update_times);
 
 /* file.c */
 extern const struct inode_operations ufs_file_inode_operations;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 874507d..f0e8249 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -577,6 +577,13 @@
 	if (error)
 		return error;
 
+	/* For changing security info in file_remove_privs() we need i_mutex */
+	if (*iolock == XFS_IOLOCK_SHARED && !IS_NOSEC(inode)) {
+		xfs_rw_iunlock(ip, *iolock);
+		*iolock = XFS_IOLOCK_EXCL;
+		xfs_rw_ilock(ip, *iolock);
+		goto restart;
+	}
 	/*
 	 * If the offset is beyond the size of the file, we need to zero any
 	 * blocks that fall between the existing EOF and the start of this
@@ -637,7 +644,9 @@
 	 * setgid bits if the process is not being run by root.  This keeps
 	 * people from modifying setuid and setgid binaries.
 	 */
-	return file_remove_suid(file);
+	if (!IS_NOSEC(inode))
+		return file_remove_privs(file);
+	return 0;
 }
 
 /*
diff --git a/include/acpi/acnames.h b/include/acpi/acnames.h
index 273de70..b52c0dc 100644
--- a/include/acpi/acnames.h
+++ b/include/acpi/acnames.h
@@ -51,6 +51,7 @@
 #define METHOD_NAME__BBN        "_BBN"
 #define METHOD_NAME__CBA        "_CBA"
 #define METHOD_NAME__CID        "_CID"
+#define METHOD_NAME__CLS        "_CLS"
 #define METHOD_NAME__CRS        "_CRS"
 #define METHOD_NAME__DDN        "_DDN"
 #define METHOD_NAME__HID        "_HID"
diff --git a/include/acpi/acoutput.h b/include/acpi/acoutput.h
index a8f3443..f56de8c 100644
--- a/include/acpi/acoutput.h
+++ b/include/acpi/acoutput.h
@@ -294,8 +294,12 @@
 
 /* DEBUG_PRINT functions */
 
-#define ACPI_DEBUG_PRINT(plist)         ACPI_ACTUAL_DEBUG plist
-#define ACPI_DEBUG_PRINT_RAW(plist)     ACPI_ACTUAL_DEBUG_RAW plist
+#ifndef COMPILER_VA_MACRO
+
+#define ACPI_DEBUG_PRINT(plist)         acpi_debug_print plist
+#define ACPI_DEBUG_PRINT_RAW(plist)     acpi_debug_print_raw plist
+
+#else
 
 /* Helper macros for DEBUG_PRINT */
 
@@ -315,6 +319,11 @@
 	ACPI_DO_DEBUG_PRINT (acpi_debug_print_raw, level, line, \
 		filename, modulename, component, __VA_ARGS__)
 
+#define ACPI_DEBUG_PRINT(plist)         ACPI_ACTUAL_DEBUG plist
+#define ACPI_DEBUG_PRINT_RAW(plist)     ACPI_ACTUAL_DEBUG_RAW plist
+
+#endif
+
 /*
  * Function entry tracing
  *
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index b43276f..83061ca 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -420,7 +420,7 @@
 	return fwnode && fwnode->type == FWNODE_ACPI;
 }
 
-static inline struct acpi_device *acpi_node(struct fwnode_handle *fwnode)
+static inline struct acpi_device *to_acpi_node(struct fwnode_handle *fwnode)
 {
 	return is_acpi_node(fwnode) ?
 		container_of(fwnode, struct acpi_device, fwnode) : NULL;
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index d68f1cd..e8ec18a 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -46,7 +46,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION                 0x20150515
+#define ACPI_CA_VERSION                 0x20150619
 
 #include <acpi/acconfig.h>
 #include <acpi/actypes.h>
@@ -195,9 +195,18 @@
  * address. Although ACPICA adheres to the ACPI specification which
  * requires the use of the corresponding 64-bit address if it is non-zero,
  * some machines have been found to have a corrupted non-zero 64-bit
- * address. Default is TRUE, favor the 32-bit addresses.
+ * address. Default is FALSE, do not favor the 32-bit addresses.
  */
-ACPI_INIT_GLOBAL(u8, acpi_gbl_use32_bit_fadt_addresses, TRUE);
+ACPI_INIT_GLOBAL(u8, acpi_gbl_use32_bit_fadt_addresses, FALSE);
+
+/*
+ * Optionally use 32-bit FACS table addresses.
+ * It is reported that some platforms fail to resume from system suspending
+ * if 64-bit FACS table address is selected:
+ * https://bugzilla.kernel.org/show_bug.cgi?id=74021
+ * Default is TRUE, favor the 32-bit addresses.
+ */
+ACPI_INIT_GLOBAL(u8, acpi_gbl_use32_bit_facs_addresses, TRUE);
 
 /*
  * Optionally truncate I/O addresses to 16 bits. Provides compatibility
@@ -220,6 +229,11 @@
 ACPI_INIT_GLOBAL(u8, acpi_gbl_disable_ssdt_table_install, FALSE);
 
 /*
+ * Optionally enable runtime namespace override.
+ */
+ACPI_INIT_GLOBAL(u8, acpi_gbl_runtime_namespace_override, TRUE);
+
+/*
  * We keep track of the latest version of Windows that has been requested by
  * the BIOS. ACPI 5.0.
  */
@@ -814,8 +828,12 @@
 ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_leave_sleep_state(u8 sleep_state))
 
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
-				acpi_set_firmware_waking_vector(u32
-								physical_address))
+				acpi_set_firmware_waking_vectors
+				(acpi_physical_address physical_address,
+				 acpi_physical_address physical_address64))
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				 acpi_set_firmware_waking_vector(u32
+								 physical_address))
 #if ACPI_MACHINE_WIDTH == 64
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				acpi_set_firmware_waking_vector64(u64
diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h
index cb8a6b9..2d5faf5 100644
--- a/include/acpi/actbl.h
+++ b/include/acpi/actbl.h
@@ -65,6 +65,7 @@
 #define ACPI_SIG_DSDT           "DSDT"	/* Differentiated System Description Table */
 #define ACPI_SIG_FADT           "FACP"	/* Fixed ACPI Description Table */
 #define ACPI_SIG_FACS           "FACS"	/* Firmware ACPI Control Structure */
+#define ACPI_SIG_OSDT           "OSDT"	/* Override System Description Table */
 #define ACPI_SIG_PSDT           "PSDT"	/* Persistent System Description Table */
 #define ACPI_SIG_RSDP           "RSD PTR "	/* Root System Description Pointer */
 #define ACPI_SIG_RSDT           "RSDT"	/* Root System Description Table */
diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h
index 06b61f0..fcd5709 100644
--- a/include/acpi/actbl1.h
+++ b/include/acpi/actbl1.h
@@ -835,6 +835,17 @@
 	u8 reserved2[3];	/* reserved - must be zero */
 };
 
+/* Values for Version field above */
+
+enum acpi_madt_gic_version {
+	ACPI_MADT_GIC_VERSION_NONE = 0,
+	ACPI_MADT_GIC_VERSION_V1 = 1,
+	ACPI_MADT_GIC_VERSION_V2 = 2,
+	ACPI_MADT_GIC_VERSION_V3 = 3,
+	ACPI_MADT_GIC_VERSION_V4 = 4,
+	ACPI_MADT_GIC_VERSION_RESERVED = 5	/* 5 and greater are reserved */
+};
+
 /* 13: Generic MSI Frame (ACPI 5.1) */
 
 struct acpi_madt_generic_msi_frame {
diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h
index 370d69d..a948fc5 100644
--- a/include/acpi/actbl2.h
+++ b/include/acpi/actbl2.h
@@ -51,8 +51,8 @@
  * These tables are not consumed directly by the ACPICA subsystem, but are
  * included here to support device drivers and the AML disassembler.
  *
- * The tables in this file are defined by third-party specifications, and are
- * not defined directly by the ACPI specification itself.
+ * Generally, the tables in this file are defined by third-party specifications,
+ * and are not defined directly by the ACPI specification itself.
  *
  ******************************************************************************/
 
@@ -80,6 +80,7 @@
 #define ACPI_SIG_SPCR           "SPCR"	/* Serial Port Console Redirection table */
 #define ACPI_SIG_SPMI           "SPMI"	/* Server Platform Management Interface table */
 #define ACPI_SIG_TCPA           "TCPA"	/* Trusted Computing Platform Alliance table */
+#define ACPI_SIG_TPM2           "TPM2"	/* Trusted Platform Module 2.0 H/W interface table */
 #define ACPI_SIG_UEFI           "UEFI"	/* Uefi Boot Optimization Table */
 #define ACPI_SIG_VRTC           "VRTC"	/* Virtual Real Time Clock Table */
 #define ACPI_SIG_WAET           "WAET"	/* Windows ACPI Emulated devices Table */
@@ -1179,20 +1180,85 @@
 /*******************************************************************************
  *
  * TCPA - Trusted Computing Platform Alliance table
- *        Version 1
+ *        Version 2
  *
- * Conforms to "TCG PC Specific Implementation Specification",
- * Version 1.1, August 18, 2003
+ * Conforms to "TCG ACPI Specification, Family 1.2 and 2.0",
+ * December 19, 2014
+ *
+ * NOTE: There are two versions of the table with the same signature --
+ * the client version and the server version.
  *
  ******************************************************************************/
 
-struct acpi_table_tcpa {
+struct acpi_table_tcpa_client {
 	struct acpi_table_header header;	/* Common ACPI table header */
-	u16 reserved;
-	u32 max_log_length;	/* Maximum length for the event log area */
+	u16 platform_class;
+	u32 minimum_log_length;	/* Minimum length for the event log area */
 	u64 log_address;	/* Address of the event log area */
 };
 
+struct acpi_table_tcpa_server {
+	struct acpi_table_header header;	/* Common ACPI table header */
+	u16 platform_class;
+	u16 reserved;
+	u64 minimum_log_length;	/* Minimum length for the event log area */
+	u64 log_address;	/* Address of the event log area */
+	u16 spec_revision;
+	u8 device_flags;
+	u8 interrupt_flags;
+	u8 gpe_number;
+	u8 reserved2[3];
+	u32 global_interrupt;
+	struct acpi_generic_address address;
+	u32 reserved3;
+	struct acpi_generic_address config_address;
+	u8 group;
+	u8 bus;			/* PCI Bus/Segment/Function numbers */
+	u8 device;
+	u8 function;
+};
+
+/* Values for device_flags above */
+
+#define ACPI_TCPA_PCI_DEVICE            (1)
+#define ACPI_TCPA_BUS_PNP               (1<<1)
+#define ACPI_TCPA_ADDRESS_VALID         (1<<2)
+
+/* Values for interrupt_flags above */
+
+#define ACPI_TCPA_INTERRUPT_MODE        (1)
+#define ACPI_TCPA_INTERRUPT_POLARITY    (1<<1)
+#define ACPI_TCPA_SCI_VIA_GPE           (1<<2)
+#define ACPI_TCPA_GLOBAL_INTERRUPT      (1<<3)
+
+/*******************************************************************************
+ *
+ * TPM2 - Trusted Platform Module (TPM) 2.0 Hardware Interface Table
+ *        Version 4
+ *
+ * Conforms to "TCG ACPI Specification, Family 1.2 and 2.0",
+ * December 19, 2014
+ *
+ ******************************************************************************/
+
+struct acpi_table_tpm2 {
+	struct acpi_table_header header;	/* Common ACPI table header */
+	u16 platform_class;
+	u16 reserved;
+	u64 control_address;
+	u32 start_method;
+
+	/* Platform-specific data follows */
+};
+
+/* Values for start_method above */
+
+#define ACPI_TPM2_NOT_ALLOWED                       0
+#define ACPI_TPM2_START_METHOD                      2
+#define ACPI_TPM2_MEMORY_MAPPED                     6
+#define ACPI_TPM2_COMMAND_BUFFER                    7
+#define ACPI_TPM2_COMMAND_BUFFER_WITH_START_METHOD  8
+
 /*******************************************************************************
  *
  * UEFI - UEFI Boot optimization Table
diff --git a/include/acpi/actbl3.h b/include/acpi/actbl3.h
index 4018986..1df8916 100644
--- a/include/acpi/actbl3.h
+++ b/include/acpi/actbl3.h
@@ -51,7 +51,8 @@
  * These tables are not consumed directly by the ACPICA subsystem, but are
  * included here to support device drivers and the AML disassembler.
  *
- * The tables in this file are fully defined within the ACPI specification.
+ * In general, the tables in this file are fully defined within the ACPI
+ * specification.
  *
  ******************************************************************************/
 
@@ -69,7 +70,6 @@
 #define ACPI_SIG_PMTT           "PMTT"	/* Platform Memory Topology Table */
 #define ACPI_SIG_RASF           "RASF"	/* RAS Feature table */
 #define ACPI_SIG_STAO           "STAO"	/* Status Override table */
-#define ACPI_SIG_TPM2           "TPM2"	/* Trusted Platform Module 2.0 H/W interface table */
 #define ACPI_SIG_WPBT           "WPBT"	/* Windows Platform Binary Table */
 #define ACPI_SIG_XENV           "XENV"	/* Xen Environment table */
 
@@ -722,36 +722,6 @@
 
 /*******************************************************************************
  *
- * TPM2 - Trusted Platform Module (TPM) 2.0 Hardware Interface Table
- *        Version 3
- *
- * Conforms to "TPM 2.0 Hardware Interface Table (TPM2)" 29 November 2011
- *
- ******************************************************************************/
-
-struct acpi_table_tpm2 {
-	struct acpi_table_header header;	/* Common ACPI table header */
-	u32 flags;
-	u64 control_address;
-	u32 start_method;
-};
-
-/* Control area structure (not part of table, pointed to by control_address) */
-
-struct acpi_tpm2_control {
-	u32 reserved;
-	u32 error;
-	u32 cancel;
-	u32 start;
-	u64 interrupt_control;
-	u32 command_size;
-	u64 command_address;
-	u32 response_size;
-	u64 response_address;
-};
-
-/*******************************************************************************
- *
  * WPBT - Windows Platform Environment Table (ACPI 6.0)
  *        Version 1
  *
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index 63fd7f5..c2a41d2 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -542,14 +542,14 @@
 #define ACPI_COMPARE_NAME(a,b)          (*ACPI_CAST_PTR (u32, (a)) == *ACPI_CAST_PTR (u32, (b)))
 #define ACPI_MOVE_NAME(dest,src)        (*ACPI_CAST_PTR (u32, (dest)) = *ACPI_CAST_PTR (u32, (src)))
 #else
-#define ACPI_COMPARE_NAME(a,b)          (!ACPI_STRNCMP (ACPI_CAST_PTR (char, (a)), ACPI_CAST_PTR (char, (b)), ACPI_NAME_SIZE))
-#define ACPI_MOVE_NAME(dest,src)        (ACPI_STRNCPY (ACPI_CAST_PTR (char, (dest)), ACPI_CAST_PTR (char, (src)), ACPI_NAME_SIZE))
+#define ACPI_COMPARE_NAME(a,b)          (!strncmp (ACPI_CAST_PTR (char, (a)), ACPI_CAST_PTR (char, (b)), ACPI_NAME_SIZE))
+#define ACPI_MOVE_NAME(dest,src)        (strncpy (ACPI_CAST_PTR (char, (dest)), ACPI_CAST_PTR (char, (src)), ACPI_NAME_SIZE))
 #endif
 
 /* Support for the special RSDP signature (8 characters) */
 
-#define ACPI_VALIDATE_RSDP_SIG(a)       (!ACPI_STRNCMP (ACPI_CAST_PTR (char, (a)), ACPI_SIG_RSDP, 8))
-#define ACPI_MAKE_RSDP_SIG(dest)        (ACPI_MEMCPY (ACPI_CAST_PTR (char, (dest)), ACPI_SIG_RSDP, 8))
+#define ACPI_VALIDATE_RSDP_SIG(a)       (!strncmp (ACPI_CAST_PTR (char, (a)), ACPI_SIG_RSDP, 8))
+#define ACPI_MAKE_RSDP_SIG(dest)        (memcpy (ACPI_CAST_PTR (char, (dest)), ACPI_SIG_RSDP, 8))
 
 /*******************************************************************************
  *
@@ -568,6 +568,7 @@
 #define ACPI_NO_ACPI_ENABLE             0x10
 #define ACPI_NO_DEVICE_INIT             0x20
 #define ACPI_NO_OBJECT_INIT             0x40
+#define ACPI_NO_FACS_INIT               0x80
 
 /*
  * Initialization state
@@ -1140,6 +1141,10 @@
 
 #define ACPI_UUID_LENGTH                16
 
+/* Length of 3-byte PCI class code values when converted back to a string */
+
+#define ACPI_PCICLS_STRING_SIZE         7	/* Includes null terminator */
+
 /* Structures used for device/processor HID, UID, CID, and SUB */
 
 struct acpi_pnp_device_id {
@@ -1162,7 +1167,7 @@
 	u32 name;		/* ACPI object Name */
 	acpi_object_type type;	/* ACPI object Type */
 	u8 param_count;		/* If a method, required parameter count */
-	u8 valid;		/* Indicates which optional fields are valid */
+	u16 valid;		/* Indicates which optional fields are valid */
 	u8 flags;		/* Miscellaneous info */
 	u8 highest_dstates[4];	/* _sx_d values: 0xFF indicates not valid */
 	u8 lowest_dstates[5];	/* _sx_w values: 0xFF indicates not valid */
@@ -1171,6 +1176,7 @@
 	struct acpi_pnp_device_id hardware_id;	/* _HID value */
 	struct acpi_pnp_device_id unique_id;	/* _UID value */
 	struct acpi_pnp_device_id subsystem_id;	/* _SUB value */
+	struct acpi_pnp_device_id class_code;	/* _CLS value */
 	struct acpi_pnp_device_id_list compatible_id_list;	/* _CID list <must be last> */
 };
 
@@ -1180,14 +1186,15 @@
 
 /* Flags for Valid field above (acpi_get_object_info) */
 
-#define ACPI_VALID_STA                  0x01
-#define ACPI_VALID_ADR                  0x02
-#define ACPI_VALID_HID                  0x04
-#define ACPI_VALID_UID                  0x08
-#define ACPI_VALID_SUB                  0x10
-#define ACPI_VALID_CID                  0x20
-#define ACPI_VALID_SXDS                 0x40
-#define ACPI_VALID_SXWS                 0x80
+#define ACPI_VALID_STA                  0x0001
+#define ACPI_VALID_ADR                  0x0002
+#define ACPI_VALID_HID                  0x0004
+#define ACPI_VALID_UID                  0x0008
+#define ACPI_VALID_SUB                  0x0010
+#define ACPI_VALID_CID                  0x0020
+#define ACPI_VALID_CLS                  0x0040
+#define ACPI_VALID_SXDS                 0x0100
+#define ACPI_VALID_SXWS                 0x0200
 
 /* Flags for _STA return value (current_status above) */
 
diff --git a/include/acpi/platform/acenv.h b/include/acpi/platform/acenv.h
index 073997d..3cedd43 100644
--- a/include/acpi/platform/acenv.h
+++ b/include/acpi/platform/acenv.h
@@ -346,29 +346,6 @@
 
 /* We will be linking to the standard Clib functions */
 
-#define ACPI_STRSTR(s1,s2)      strstr((s1), (s2))
-#define ACPI_STRCHR(s1,c)       strchr((s1), (c))
-#define ACPI_STRLEN(s)          (acpi_size) strlen((s))
-#define ACPI_STRCPY(d,s)        (void) strcpy((d), (s))
-#define ACPI_STRNCPY(d,s,n)     (void) strncpy((d), (s), (acpi_size)(n))
-#define ACPI_STRNCMP(d,s,n)     strncmp((d), (s), (acpi_size)(n))
-#define ACPI_STRCMP(d,s)        strcmp((d), (s))
-#define ACPI_STRCAT(d,s)        (void) strcat((d), (s))
-#define ACPI_STRNCAT(d,s,n)     strncat((d), (s), (acpi_size)(n))
-#define ACPI_STRTOUL(d,s,n)     strtoul((d), (s), (acpi_size)(n))
-#define ACPI_MEMCMP(s1,s2,n)    memcmp((const char *)(s1), (const char *)(s2), (acpi_size)(n))
-#define ACPI_MEMCPY(d,s,n)      (void) memcpy((d), (s), (acpi_size)(n))
-#define ACPI_MEMSET(d,s,n)      (void) memset((d), (s), (acpi_size)(n))
-
-#define ACPI_TOUPPER(i)         toupper((int) (i))
-#define ACPI_TOLOWER(i)         tolower((int) (i))
-#define ACPI_IS_XDIGIT(i)       isxdigit((int) (i))
-#define ACPI_IS_DIGIT(i)        isdigit((int) (i))
-#define ACPI_IS_SPACE(i)        isspace((int) (i))
-#define ACPI_IS_UPPER(i)        isupper((int) (i))
-#define ACPI_IS_PRINT(i)        isprint((int) (i))
-#define ACPI_IS_ALPHA(i)        isalpha((int) (i))
-
 #else
 
 /******************************************************************************
@@ -406,22 +383,6 @@
 
 /* Use the local (ACPICA) definitions of the clib functions */
 
-#define ACPI_STRSTR(s1,s2)      acpi_ut_strstr ((s1), (s2))
-#define ACPI_STRCHR(s1,c)       acpi_ut_strchr ((s1), (c))
-#define ACPI_STRLEN(s)          (acpi_size) acpi_ut_strlen ((s))
-#define ACPI_STRCPY(d,s)        (void) acpi_ut_strcpy ((d), (s))
-#define ACPI_STRNCPY(d,s,n)     (void) acpi_ut_strncpy ((d), (s), (acpi_size)(n))
-#define ACPI_STRNCMP(d,s,n)     acpi_ut_strncmp ((d), (s), (acpi_size)(n))
-#define ACPI_STRCMP(d,s)        acpi_ut_strcmp ((d), (s))
-#define ACPI_STRCAT(d,s)        (void) acpi_ut_strcat ((d), (s))
-#define ACPI_STRNCAT(d,s,n)     acpi_ut_strncat ((d), (s), (acpi_size)(n))
-#define ACPI_STRTOUL(d,s,n)     acpi_ut_strtoul ((d), (s), (acpi_size)(n))
-#define ACPI_MEMCMP(s1,s2,n)    acpi_ut_memcmp((const char *)(s1), (const char *)(s2), (acpi_size)(n))
-#define ACPI_MEMCPY(d,s,n)      (void) acpi_ut_memcpy ((d), (s), (acpi_size)(n))
-#define ACPI_MEMSET(d,v,n)      (void) acpi_ut_memset ((d), (v), (acpi_size)(n))
-#define ACPI_TOUPPER(c)         acpi_ut_to_upper ((int) (c))
-#define ACPI_TOLOWER(c)         acpi_ut_to_lower ((int) (c))
-
 #endif				/* ACPI_USE_SYSTEM_CLIBRARY */
 
 #ifndef ACPI_FILE
diff --git a/include/acpi/platform/acenvex.h b/include/acpi/platform/acenvex.h
index 14dc6f6..0a7dc8e 100644
--- a/include/acpi/platform/acenvex.h
+++ b/include/acpi/platform/acenvex.h
@@ -56,6 +56,12 @@
 #if defined(_LINUX) || defined(__linux__)
 #include <acpi/platform/aclinuxex.h>
 
+#elif defined(_AED_EFI)
+#include "acefiex.h"
+
+#elif defined(_GNU_EFI)
+#include "acefiex.h"
+
 #elif defined(__DragonFly__)
 #include "acdragonflyex.h"
 
diff --git a/include/acpi/platform/acgcc.h b/include/acpi/platform/acgcc.h
index f54de0a..5457a06 100644
--- a/include/acpi/platform/acgcc.h
+++ b/include/acpi/platform/acgcc.h
@@ -75,4 +75,8 @@
 #undef strchr
 #endif
 
+/* GCC supports __VA_ARGS__ in macros */
+
+#define COMPILER_VA_MACRO               1
+
 #endif				/* __ACGCC_H__ */
diff --git a/include/acpi/video.h b/include/acpi/video.h
index a7d7f10..e840b29 100644
--- a/include/acpi/video.h
+++ b/include/acpi/video.h
@@ -43,7 +43,7 @@
 {
 	return acpi_backlight_vendor;
 }
-static void acpi_video_set_dmi_backlight_type(enum acpi_backlight_type type)
+static inline void acpi_video_set_dmi_backlight_type(enum acpi_backlight_type type)
 {
 }
 #endif
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index e6a83d7..55e3abc 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -55,17 +55,43 @@
 #endif
 
 #ifdef CONFIG_SMP
+
+#ifndef smp_mb
 #define smp_mb()	mb()
+#endif
+
+#ifndef smp_rmb
 #define smp_rmb()	rmb()
+#endif
+
+#ifndef smp_wmb
 #define smp_wmb()	wmb()
+#endif
+
+#ifndef smp_read_barrier_depends
 #define smp_read_barrier_depends()	read_barrier_depends()
-#else
+#endif
+
+#else	/* !CONFIG_SMP */
+
+#ifndef smp_mb
 #define smp_mb()	barrier()
+#endif
+
+#ifndef smp_rmb
 #define smp_rmb()	barrier()
+#endif
+
+#ifndef smp_wmb
 #define smp_wmb()	barrier()
+#endif
+
+#ifndef smp_read_barrier_depends
 #define smp_read_barrier_depends()	do { } while (0)
 #endif
 
+#endif	/* CONFIG_SMP */
+
 #ifndef smp_store_mb
 #define smp_store_mb(var, value)  do { WRITE_ONCE(var, value); mb(); } while (0)
 #endif
diff --git a/include/drm/drm_mem_util.h b/include/drm/drm_mem_util.h
index 19a2404..e42495a 100644
--- a/include/drm/drm_mem_util.h
+++ b/include/drm/drm_mem_util.h
@@ -56,10 +56,7 @@
 
 static __inline void drm_free_large(void *ptr)
 {
-	if (!is_vmalloc_addr(ptr))
-		return kfree(ptr);
-
-	vfree(ptr);
+	kvfree(ptr);
 }
 
 #endif
diff --git a/include/dt-bindings/clock/bcm-cygnus.h b/include/dt-bindings/clock/bcm-cygnus.h
new file mode 100644
index 0000000..32fbc47
--- /dev/null
+++ b/include/dt-bindings/clock/bcm-cygnus.h
@@ -0,0 +1,68 @@
+/*
+ *  BSD LICENSE
+ *
+ *  Copyright(c) 2014 Broadcom Corporation.  All rights reserved.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Broadcom Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _CLOCK_BCM_CYGNUS_H
+#define _CLOCK_BCM_CYGNUS_H
+
+/* GENPLL clock ID */
+#define BCM_CYGNUS_GENPLL                     0
+#define BCM_CYGNUS_GENPLL_AXI21_CLK           1
+#define BCM_CYGNUS_GENPLL_250MHZ_CLK          2
+#define BCM_CYGNUS_GENPLL_IHOST_SYS_CLK       3
+#define BCM_CYGNUS_GENPLL_ENET_SW_CLK         4
+#define BCM_CYGNUS_GENPLL_AUDIO_125_CLK       5
+#define BCM_CYGNUS_GENPLL_CAN_CLK             6
+
+/* LCPLL0 clock ID */
+#define BCM_CYGNUS_LCPLL0                     0
+#define BCM_CYGNUS_LCPLL0_PCIE_PHY_REF_CLK    1
+#define BCM_CYGNUS_LCPLL0_DDR_PHY_CLK         2
+#define BCM_CYGNUS_LCPLL0_SDIO_CLK            3
+#define BCM_CYGNUS_LCPLL0_USB_PHY_REF_CLK     4
+#define BCM_CYGNUS_LCPLL0_SMART_CARD_CLK      5
+#define BCM_CYGNUS_LCPLL0_CH5_UNUSED          6
+
+/* MIPI PLL clock ID */
+#define BCM_CYGNUS_MIPIPLL                    0
+#define BCM_CYGNUS_MIPIPLL_CH0_UNUSED         1
+#define BCM_CYGNUS_MIPIPLL_CH1_LCD            2
+#define BCM_CYGNUS_MIPIPLL_CH2_V3D            3
+#define BCM_CYGNUS_MIPIPLL_CH3_UNUSED         4
+#define BCM_CYGNUS_MIPIPLL_CH4_UNUSED         5
+#define BCM_CYGNUS_MIPIPLL_CH5_UNUSED         6
+
+/* ASIU clock ID */
+#define BCM_CYGNUS_ASIU_KEYPAD_CLK    0
+#define BCM_CYGNUS_ASIU_ADC_CLK       1
+#define BCM_CYGNUS_ASIU_PWM_CLK       2
+
+#endif /* _CLOCK_BCM_CYGNUS_H */
diff --git a/include/dt-bindings/clock/hi6220-clock.h b/include/dt-bindings/clock/hi6220-clock.h
new file mode 100644
index 0000000..70ee383
--- /dev/null
+++ b/include/dt-bindings/clock/hi6220-clock.h
@@ -0,0 +1,173 @@
+/*
+ * Copyright (c) 2015 Hisilicon Limited.
+ *
+ * Author: Bintian Wang <bintian.wang@huawei.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __DT_BINDINGS_CLOCK_HI6220_H
+#define __DT_BINDINGS_CLOCK_HI6220_H
+
+/* clk in Hi6220 AO (always on) controller */
+#define HI6220_NONE_CLOCK	0
+
+/* fixed rate clocks */
+#define HI6220_REF32K		1
+#define HI6220_CLK_TCXO		2
+#define HI6220_MMC1_PAD		3
+#define HI6220_MMC2_PAD		4
+#define HI6220_MMC0_PAD		5
+#define HI6220_PLL_BBP		6
+#define HI6220_PLL_GPU		7
+#define HI6220_PLL1_DDR		8
+#define HI6220_PLL_SYS		9
+#define HI6220_PLL_SYS_MEDIA	10
+#define HI6220_DDR_SRC		11
+#define HI6220_PLL_MEDIA	12
+#define HI6220_PLL_DDR		13
+
+/* fixed factor clocks */
+#define HI6220_300M		14
+#define HI6220_150M		15
+#define HI6220_PICOPHY_SRC	16
+#define HI6220_MMC0_SRC_SEL	17
+#define HI6220_MMC1_SRC_SEL	18
+#define HI6220_MMC2_SRC_SEL	19
+#define HI6220_VPU_CODEC	20
+#define HI6220_MMC0_SMP		21
+#define HI6220_MMC1_SMP		22
+#define HI6220_MMC2_SMP		23
+
+/* gate clocks */
+#define HI6220_WDT0_PCLK	24
+#define HI6220_WDT1_PCLK	25
+#define HI6220_WDT2_PCLK	26
+#define HI6220_TIMER0_PCLK	27
+#define HI6220_TIMER1_PCLK	28
+#define HI6220_TIMER2_PCLK	29
+#define HI6220_TIMER3_PCLK	30
+#define HI6220_TIMER4_PCLK	31
+#define HI6220_TIMER5_PCLK	32
+#define HI6220_TIMER6_PCLK	33
+#define HI6220_TIMER7_PCLK	34
+#define HI6220_TIMER8_PCLK	35
+#define HI6220_UART0_PCLK	36
+
+#define HI6220_AO_NR_CLKS	37
+
+/* clk in Hi6220 systrl */
+/* gate clock */
+#define HI6220_MMC0_CLK		1
+#define HI6220_MMC0_CIUCLK	2
+#define HI6220_MMC1_CLK		3
+#define HI6220_MMC1_CIUCLK	4
+#define HI6220_MMC2_CLK		5
+#define HI6220_MMC2_CIUCLK	6
+#define HI6220_USBOTG_HCLK	7
+#define HI6220_CLK_PICOPHY	8
+#define HI6220_HIFI		9
+#define HI6220_DACODEC_PCLK	10
+#define HI6220_EDMAC_ACLK	11
+#define HI6220_CS_ATB		12
+#define HI6220_I2C0_CLK		13
+#define HI6220_I2C1_CLK		14
+#define HI6220_I2C2_CLK		15
+#define HI6220_I2C3_CLK		16
+#define HI6220_UART1_PCLK	17
+#define HI6220_UART2_PCLK	18
+#define HI6220_UART3_PCLK	19
+#define HI6220_UART4_PCLK	20
+#define HI6220_SPI_CLK		21
+#define HI6220_TSENSOR_CLK	22
+#define HI6220_MMU_CLK		23
+#define HI6220_HIFI_SEL		24
+#define HI6220_MMC0_SYSPLL	25
+#define HI6220_MMC1_SYSPLL	26
+#define HI6220_MMC2_SYSPLL	27
+#define HI6220_MMC0_SEL		28
+#define HI6220_MMC1_SEL		29
+#define HI6220_BBPPLL_SEL	30
+#define HI6220_MEDIA_PLL_SRC	31
+#define HI6220_MMC2_SEL		32
+#define HI6220_CS_ATB_SYSPLL	33
+
+/* mux clocks */
+#define HI6220_MMC0_SRC		34
+#define HI6220_MMC0_SMP_IN	35
+#define HI6220_MMC1_SRC		36
+#define HI6220_MMC1_SMP_IN	37
+#define HI6220_MMC2_SRC		38
+#define HI6220_MMC2_SMP_IN	39
+#define HI6220_HIFI_SRC		40
+#define HI6220_UART1_SRC	41
+#define HI6220_UART2_SRC	42
+#define HI6220_UART3_SRC	43
+#define HI6220_UART4_SRC	44
+#define HI6220_MMC0_MUX0	45
+#define HI6220_MMC1_MUX0	46
+#define HI6220_MMC2_MUX0	47
+#define HI6220_MMC0_MUX1	48
+#define HI6220_MMC1_MUX1	49
+#define HI6220_MMC2_MUX1	50
+
+/* divider clocks */
+#define HI6220_CLK_BUS		51
+#define HI6220_MMC0_DIV		52
+#define HI6220_MMC1_DIV		53
+#define HI6220_MMC2_DIV		54
+#define HI6220_HIFI_DIV		55
+#define HI6220_BBPPLL0_DIV	56
+#define HI6220_CS_DAPB		57
+#define HI6220_CS_ATB_DIV	58
+
+#define HI6220_SYS_NR_CLKS	59
+
+/* clk in Hi6220 media controller */
+/* gate clocks */
+#define HI6220_DSI_PCLK		1
+#define HI6220_G3D_PCLK		2
+#define HI6220_ACLK_CODEC_VPU	3
+#define HI6220_ISP_SCLK		4
+#define HI6220_ADE_CORE		5
+#define HI6220_MED_MMU		6
+#define HI6220_CFG_CSI4PHY	7
+#define HI6220_CFG_CSI2PHY	8
+#define HI6220_ISP_SCLK_GATE	9
+#define HI6220_ISP_SCLK_GATE1	10
+#define HI6220_ADE_CORE_GATE	11
+#define HI6220_CODEC_VPU_GATE	12
+#define HI6220_MED_SYSPLL	13
+
+/* mux clocks */
+#define HI6220_1440_1200	14
+#define HI6220_1000_1200	15
+#define HI6220_1000_1440	16
+
+/* divider clocks */
+#define HI6220_CODEC_JPEG	17
+#define HI6220_ISP_SCLK_SRC	18
+#define HI6220_ISP_SCLK1	19
+#define HI6220_ADE_CORE_SRC	20
+#define HI6220_ADE_PIX_SRC	21
+#define HI6220_G3D_CLK		22
+#define HI6220_CODEC_VPU_SRC	23
+
+#define HI6220_MEDIA_NR_CLKS	24
+
+/* clk in Hi6220 power controller */
+/* gate clocks */
+#define HI6220_PLL_GPU_GATE	1
+#define HI6220_PLL1_DDR_GATE	2
+#define HI6220_PLL_DDR_GATE	3
+#define HI6220_PLL_MEDIA_GATE	4
+#define HI6220_PLL0_BBP_GATE	5
+
+/* divider clocks */
+#define HI6220_DDRC_SRC		6
+#define HI6220_DDRC_AXI1	7
+
+#define HI6220_POWER_NR_CLKS	8
+#endif
diff --git a/include/dt-bindings/clock/lpc18xx-ccu.h b/include/dt-bindings/clock/lpc18xx-ccu.h
new file mode 100644
index 0000000..bbfe00b
--- /dev/null
+++ b/include/dt-bindings/clock/lpc18xx-ccu.h
@@ -0,0 +1,74 @@
+/*
+ * Copyright (c) 2015 Joachim Eastwood <manabian@gmail.com>
+ *
+ * This code is released using a dual license strategy: BSD/GPL
+ * You can choose the licence that better fits your requirements.
+ *
+ * Released under the terms of 3-clause BSD License
+ * Released under the terms of GNU General Public License Version 2.0
+ *
+ */
+
+/* Clock Control Unit 1 (CCU1) clock offsets */
+#define CLK_APB3_BUS		0x100
+#define CLK_APB3_I2C1		0x108
+#define CLK_APB3_DAC		0x110
+#define CLK_APB3_ADC0		0x118
+#define CLK_APB3_ADC1		0x120
+#define CLK_APB3_CAN0		0x128
+#define CLK_APB1_BUS		0x200
+#define CLK_APB1_MOTOCON_PWM	0x208
+#define CLK_APB1_I2C0		0x210
+#define CLK_APB1_I2S		0x218
+#define CLK_APB1_CAN1		0x220
+#define CLK_SPIFI		0x300
+#define CLK_CPU_BUS		0x400
+#define CLK_CPU_SPIFI		0x408
+#define CLK_CPU_GPIO		0x410
+#define CLK_CPU_LCD		0x418
+#define CLK_CPU_ETHERNET	0x420
+#define CLK_CPU_USB0		0x428
+#define CLK_CPU_EMC		0x430
+#define CLK_CPU_SDIO		0x438
+#define CLK_CPU_DMA		0x440
+#define CLK_CPU_CORE		0x448
+#define CLK_CPU_SCT		0x468
+#define CLK_CPU_USB1		0x470
+#define CLK_CPU_EMCDIV		0x478
+#define CLK_CPU_FLASHA		0x480
+#define CLK_CPU_FLASHB		0x488
+#define CLK_CPU_M0APP		0x490
+#define CLK_CPU_ADCHS		0x498
+#define CLK_CPU_EEPROM		0x4a0
+#define CLK_CPU_WWDT		0x500
+#define CLK_CPU_UART0		0x508
+#define CLK_CPU_UART1		0x510
+#define CLK_CPU_SSP0		0x518
+#define CLK_CPU_TIMER0		0x520
+#define CLK_CPU_TIMER1		0x528
+#define CLK_CPU_SCU		0x530
+#define CLK_CPU_CREG		0x538
+#define CLK_CPU_RITIMER		0x600
+#define CLK_CPU_UART2		0x608
+#define CLK_CPU_UART3		0x610
+#define CLK_CPU_TIMER2		0x618
+#define CLK_CPU_TIMER3		0x620
+#define CLK_CPU_SSP1		0x628
+#define CLK_CPU_QEI		0x630
+#define CLK_PERIPH_BUS		0x700
+#define CLK_PERIPH_CORE		0x710
+#define CLK_PERIPH_SGPIO	0x718
+#define CLK_USB0		0x800
+#define CLK_USB1		0x900
+#define CLK_SPI			0xA00
+#define CLK_ADCHS		0xB00
+
+/* Clock Control Unit 2 (CCU2) clock offsets */
+#define CLK_AUDIO		0x100
+#define CLK_APB2_UART3		0x200
+#define CLK_APB2_UART2		0x300
+#define CLK_APB0_UART1		0x400
+#define CLK_APB0_UART0		0x500
+#define CLK_APB2_SSP1		0x600
+#define CLK_APB0_SSP0		0x700
+#define CLK_SDIO		0x800
diff --git a/include/dt-bindings/clock/lpc18xx-cgu.h b/include/dt-bindings/clock/lpc18xx-cgu.h
new file mode 100644
index 0000000..6e57c6d
--- /dev/null
+++ b/include/dt-bindings/clock/lpc18xx-cgu.h
@@ -0,0 +1,41 @@
+/*
+ * Copyright (c) 2015 Joachim Eastwood <manabian@gmail.com>
+ *
+ * This code is released using a dual license strategy: BSD/GPL
+ * You can choose the licence that better fits your requirements.
+ *
+ * Released under the terms of 3-clause BSD License
+ * Released under the terms of GNU General Public License Version 2.0
+ *
+ */
+
+/* LPC18xx/43xx base clock ids */
+#define BASE_SAFE_CLK		0
+#define BASE_USB0_CLK		1
+#define BASE_PERIPH_CLK		2
+#define BASE_USB1_CLK		3
+#define BASE_CPU_CLK		4
+#define BASE_SPIFI_CLK		5
+#define BASE_SPI_CLK		6
+#define BASE_PHY_RX_CLK		7
+#define BASE_PHY_TX_CLK		8
+#define BASE_APB1_CLK		9
+#define BASE_APB3_CLK		10
+#define BASE_LCD_CLK		11
+#define BASE_ADCHS_CLK		12
+#define BASE_SDIO_CLK		13
+#define BASE_SSP0_CLK		14
+#define BASE_SSP1_CLK		15
+#define BASE_UART0_CLK		16
+#define BASE_UART1_CLK		17
+#define BASE_UART2_CLK		18
+#define BASE_UART3_CLK		19
+#define BASE_OUT_CLK		20
+#define BASE_RES1_CLK		21
+#define BASE_RES2_CLK		22
+#define BASE_RES3_CLK		23
+#define BASE_RES4_CLK		24
+#define BASE_AUDIO_CLK		25
+#define BASE_CGU_OUT0_CLK	26
+#define BASE_CGU_OUT1_CLK	27
+#define BASE_CLK_MAX		(BASE_CGU_OUT1_CLK + 1)
diff --git a/include/dt-bindings/clock/marvell,mmp2.h b/include/dt-bindings/clock/marvell,mmp2.h
index 591f7fb..7a51038 100644
--- a/include/dt-bindings/clock/marvell,mmp2.h
+++ b/include/dt-bindings/clock/marvell,mmp2.h
@@ -48,6 +48,7 @@
 #define MMP2_CLK_SSP1			78
 #define MMP2_CLK_SSP2			79
 #define MMP2_CLK_SSP3			80
+#define MMP2_CLK_TIMER			81
 
 /* axi periphrals */
 #define MMP2_CLK_SDH0			101
diff --git a/include/dt-bindings/clock/marvell,pxa168.h b/include/dt-bindings/clock/marvell,pxa168.h
index 79630b9..3e45bdf 100644
--- a/include/dt-bindings/clock/marvell,pxa168.h
+++ b/include/dt-bindings/clock/marvell,pxa168.h
@@ -18,7 +18,9 @@
 #define PXA168_CLK_PLL1_13_1_5		18
 #define PXA168_CLK_PLL1_2_1_5		19
 #define PXA168_CLK_PLL1_3_16		20
+#define PXA168_CLK_PLL1_192		21
 #define PXA168_CLK_UART_PLL		27
+#define PXA168_CLK_USB_PLL		28
 
 /* apb periphrals */
 #define PXA168_CLK_TWSI0		60
@@ -40,6 +42,7 @@
 #define PXA168_CLK_SSP2			76
 #define PXA168_CLK_SSP3			77
 #define PXA168_CLK_SSP4			78
+#define PXA168_CLK_TIMER		79
 
 /* axi periphrals */
 #define PXA168_CLK_DFC			100
diff --git a/include/dt-bindings/clock/marvell,pxa1928.h b/include/dt-bindings/clock/marvell,pxa1928.h
new file mode 100644
index 0000000..d4f2e18
--- /dev/null
+++ b/include/dt-bindings/clock/marvell,pxa1928.h
@@ -0,0 +1,57 @@
+#ifndef __DTS_MARVELL_PXA1928_CLOCK_H
+#define __DTS_MARVELL_PXA1928_CLOCK_H
+
+/*
+ * Clock ID values here correspond to the control register offset/4.
+ */
+
+/* apb peripherals */
+#define PXA1928_CLK_RTC			0x00
+#define PXA1928_CLK_TWSI0		0x01
+#define PXA1928_CLK_TWSI1		0x02
+#define PXA1928_CLK_TWSI2		0x03
+#define PXA1928_CLK_TWSI3		0x04
+#define PXA1928_CLK_OWIRE		0x05
+#define PXA1928_CLK_KPC			0x06
+#define PXA1928_CLK_TB_ROTARY		0x07
+#define PXA1928_CLK_SW_JTAG		0x08
+#define PXA1928_CLK_TIMER1		0x09
+#define PXA1928_CLK_UART0		0x0b
+#define PXA1928_CLK_UART1		0x0c
+#define PXA1928_CLK_UART2		0x0d
+#define PXA1928_CLK_GPIO		0x0e
+#define PXA1928_CLK_PWM0		0x0f
+#define PXA1928_CLK_PWM1		0x10
+#define PXA1928_CLK_PWM2		0x11
+#define PXA1928_CLK_PWM3		0x12
+#define PXA1928_CLK_SSP0		0x13
+#define PXA1928_CLK_SSP1		0x14
+#define PXA1928_CLK_SSP2		0x15
+
+#define PXA1928_CLK_TWSI4		0x1f
+#define PXA1928_CLK_TWSI5		0x20
+#define PXA1928_CLK_UART3		0x22
+#define PXA1928_CLK_THSENS_GLOB		0x24
+#define PXA1928_CLK_THSENS_CPU		0x26
+#define PXA1928_CLK_THSENS_VPU		0x27
+#define PXA1928_CLK_THSENS_GC		0x28
+#define PXA1928_APBC_NR_CLKS		0x30
+
+
+/* axi peripherals */
+#define PXA1928_CLK_SDH0		0x15
+#define PXA1928_CLK_SDH1		0x16
+#define PXA1928_CLK_USB			0x17
+#define PXA1928_CLK_NAND		0x18
+#define PXA1928_CLK_DMA			0x19
+
+#define PXA1928_CLK_SDH2		0x3a
+#define PXA1928_CLK_SDH3		0x3b
+#define PXA1928_CLK_HSIC		0x3e
+#define PXA1928_CLK_SDH4		0x57
+#define PXA1928_CLK_GC3D		0x5d
+#define PXA1928_CLK_GC2D		0x5f
+
+#define PXA1928_APMU_NR_CLKS		0x60
+
+#endif
diff --git a/include/dt-bindings/clock/marvell,pxa910.h b/include/dt-bindings/clock/marvell,pxa910.h
index 719cffb..135082a 100644
--- a/include/dt-bindings/clock/marvell,pxa910.h
+++ b/include/dt-bindings/clock/marvell,pxa910.h
@@ -18,7 +18,9 @@
 #define PXA910_CLK_PLL1_13_1_5		18
 #define PXA910_CLK_PLL1_2_1_5		19
 #define PXA910_CLK_PLL1_3_16		20
+#define PXA910_CLK_PLL1_192		21
 #define PXA910_CLK_UART_PLL		27
+#define PXA910_CLK_USB_PLL		28
 
 /* apb periphrals */
 #define PXA910_CLK_TWSI0		60
@@ -37,6 +39,8 @@
 #define PXA910_CLK_UART2		73
 #define PXA910_CLK_SSP0			74
 #define PXA910_CLK_SSP1			75
+#define PXA910_CLK_TIMER0		76
+#define PXA910_CLK_TIMER1		77
 
 /* axi periphrals */
 #define PXA910_CLK_DFC			100
diff --git a/include/dt-bindings/clock/meson8b-clkc.h b/include/dt-bindings/clock/meson8b-clkc.h
new file mode 100644
index 0000000..bd2720d
--- /dev/null
+++ b/include/dt-bindings/clock/meson8b-clkc.h
@@ -0,0 +1,25 @@
+/*
+ * Meson8b clock tree IDs
+ */
+
+#ifndef __MESON8B_CLKC_H
+#define __MESON8B_CLKC_H
+
+#define CLKID_UNUSED		0
+#define CLKID_XTAL		1
+#define CLKID_PLL_FIXED		2
+#define CLKID_PLL_VID		3
+#define CLKID_PLL_SYS		4
+#define CLKID_FCLK_DIV2		5
+#define CLKID_FCLK_DIV3		6
+#define CLKID_FCLK_DIV4		7
+#define CLKID_FCLK_DIV5		8
+#define CLKID_FCLK_DIV7		9
+#define CLKID_CLK81		10
+#define CLKID_MALI		11
+#define CLKID_CPUCLK		12
+#define CLKID_ZERO		13
+
+#define CLK_NR_CLKS		(CLKID_ZERO + 1)
+
+#endif /* __MESON8B_CLKC_H */
diff --git a/include/dt-bindings/clock/mt8135-clk.h b/include/dt-bindings/clock/mt8135-clk.h
new file mode 100644
index 0000000..6dac6c0
--- /dev/null
+++ b/include/dt-bindings/clock/mt8135-clk.h
@@ -0,0 +1,194 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ * Author: James Liao <jamesjj.liao@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DT_BINDINGS_CLK_MT8135_H
+#define _DT_BINDINGS_CLK_MT8135_H
+
+/* TOPCKGEN */
+
+#define CLK_TOP_DSI0_LNTC_DSICLK	1
+#define CLK_TOP_HDMITX_CLKDIG_CTS	2
+#define CLK_TOP_CLKPH_MCK		3
+#define CLK_TOP_CPUM_TCK_IN		4
+#define CLK_TOP_MAINPLL_806M		5
+#define CLK_TOP_MAINPLL_537P3M		6
+#define CLK_TOP_MAINPLL_322P4M		7
+#define CLK_TOP_MAINPLL_230P3M		8
+#define CLK_TOP_UNIVPLL_624M		9
+#define CLK_TOP_UNIVPLL_416M		10
+#define CLK_TOP_UNIVPLL_249P6M		11
+#define CLK_TOP_UNIVPLL_178P3M		12
+#define CLK_TOP_UNIVPLL_48M		13
+#define CLK_TOP_MMPLL_D2		14
+#define CLK_TOP_MMPLL_D3		15
+#define CLK_TOP_MMPLL_D5		16
+#define CLK_TOP_MMPLL_D7		17
+#define CLK_TOP_MMPLL_D4		18
+#define CLK_TOP_MMPLL_D6		19
+#define CLK_TOP_SYSPLL_D2		20
+#define CLK_TOP_SYSPLL_D4		21
+#define CLK_TOP_SYSPLL_D6		22
+#define CLK_TOP_SYSPLL_D8		23
+#define CLK_TOP_SYSPLL_D10		24
+#define CLK_TOP_SYSPLL_D12		25
+#define CLK_TOP_SYSPLL_D16		26
+#define CLK_TOP_SYSPLL_D24		27
+#define CLK_TOP_SYSPLL_D3		28
+#define CLK_TOP_SYSPLL_D2P5		29
+#define CLK_TOP_SYSPLL_D5		30
+#define CLK_TOP_SYSPLL_D3P5		31
+#define CLK_TOP_UNIVPLL1_D2		32
+#define CLK_TOP_UNIVPLL1_D4		33
+#define CLK_TOP_UNIVPLL1_D6		34
+#define CLK_TOP_UNIVPLL1_D8		35
+#define CLK_TOP_UNIVPLL1_D10		36
+#define CLK_TOP_UNIVPLL2_D2		37
+#define CLK_TOP_UNIVPLL2_D4		38
+#define CLK_TOP_UNIVPLL2_D6		39
+#define CLK_TOP_UNIVPLL2_D8		40
+#define CLK_TOP_UNIVPLL_D3		41
+#define CLK_TOP_UNIVPLL_D5		42
+#define CLK_TOP_UNIVPLL_D7		43
+#define CLK_TOP_UNIVPLL_D10		44
+#define CLK_TOP_UNIVPLL_D26		45
+#define CLK_TOP_APLL			46
+#define CLK_TOP_APLL_D4			47
+#define CLK_TOP_APLL_D8			48
+#define CLK_TOP_APLL_D16		49
+#define CLK_TOP_APLL_D24		50
+#define CLK_TOP_LVDSPLL_D2		51
+#define CLK_TOP_LVDSPLL_D4		52
+#define CLK_TOP_LVDSPLL_D8		53
+#define CLK_TOP_LVDSTX_CLKDIG_CT	54
+#define CLK_TOP_VPLL_DPIX		55
+#define CLK_TOP_TVHDMI_H		56
+#define CLK_TOP_HDMITX_CLKDIG_D2	57
+#define CLK_TOP_HDMITX_CLKDIG_D3	58
+#define CLK_TOP_TVHDMI_D2		59
+#define CLK_TOP_TVHDMI_D4		60
+#define CLK_TOP_MEMPLL_MCK_D4		61
+#define CLK_TOP_AXI_SEL			62
+#define CLK_TOP_SMI_SEL			63
+#define CLK_TOP_MFG_SEL			64
+#define CLK_TOP_IRDA_SEL		65
+#define CLK_TOP_CAM_SEL			66
+#define CLK_TOP_AUD_INTBUS_SEL		67
+#define CLK_TOP_JPG_SEL			68
+#define CLK_TOP_DISP_SEL		69
+#define CLK_TOP_MSDC30_1_SEL		70
+#define CLK_TOP_MSDC30_2_SEL		71
+#define CLK_TOP_MSDC30_3_SEL		72
+#define CLK_TOP_MSDC30_4_SEL		73
+#define CLK_TOP_USB20_SEL		74
+#define CLK_TOP_VENC_SEL		75
+#define CLK_TOP_SPI_SEL			76
+#define CLK_TOP_UART_SEL		77
+#define CLK_TOP_MEM_SEL			78
+#define CLK_TOP_CAMTG_SEL		79
+#define CLK_TOP_AUDIO_SEL		80
+#define CLK_TOP_FIX_SEL			81
+#define CLK_TOP_VDEC_SEL		82
+#define CLK_TOP_DDRPHYCFG_SEL		83
+#define CLK_TOP_DPILVDS_SEL		84
+#define CLK_TOP_PMICSPI_SEL		85
+#define CLK_TOP_MSDC30_0_SEL		86
+#define CLK_TOP_SMI_MFG_AS_SEL		87
+#define CLK_TOP_GCPU_SEL		88
+#define CLK_TOP_DPI1_SEL		89
+#define CLK_TOP_CCI_SEL			90
+#define CLK_TOP_APLL_SEL		91
+#define CLK_TOP_HDMIPLL_SEL		92
+#define CLK_TOP_NR_CLK			93
+
+/* APMIXED_SYS */
+
+#define CLK_APMIXED_ARMPLL1		1
+#define CLK_APMIXED_ARMPLL2		2
+#define CLK_APMIXED_MAINPLL		3
+#define CLK_APMIXED_UNIVPLL		4
+#define CLK_APMIXED_MMPLL		5
+#define CLK_APMIXED_MSDCPLL		6
+#define CLK_APMIXED_TVDPLL		7
+#define CLK_APMIXED_LVDSPLL		8
+#define CLK_APMIXED_AUDPLL		9
+#define CLK_APMIXED_VDECPLL		10
+#define CLK_APMIXED_NR_CLK		11
+
+/* INFRA_SYS */
+
+#define CLK_INFRA_PMIC_WRAP		1
+#define CLK_INFRA_PMICSPI		2
+#define CLK_INFRA_CCIF1_AP_CTRL		3
+#define CLK_INFRA_CCIF0_AP_CTRL		4
+#define CLK_INFRA_KP			5
+#define CLK_INFRA_CPUM			6
+#define CLK_INFRA_M4U			7
+#define CLK_INFRA_MFGAXI		8
+#define CLK_INFRA_DEVAPC		9
+#define CLK_INFRA_AUDIO			10
+#define CLK_INFRA_MFG_BUS		11
+#define CLK_INFRA_SMI			12
+#define CLK_INFRA_DBGCLK		13
+#define CLK_INFRA_NR_CLK		14
+
+/* PERI_SYS */
+
+#define CLK_PERI_I2C5			1
+#define CLK_PERI_I2C4			2
+#define CLK_PERI_I2C3			3
+#define CLK_PERI_I2C2			4
+#define CLK_PERI_I2C1			5
+#define CLK_PERI_I2C0			6
+#define CLK_PERI_UART3			7
+#define CLK_PERI_UART2			8
+#define CLK_PERI_UART1			9
+#define CLK_PERI_UART0			10
+#define CLK_PERI_IRDA			11
+#define CLK_PERI_NLI			12
+#define CLK_PERI_MD_HIF			13
+#define CLK_PERI_AP_HIF			14
+#define CLK_PERI_MSDC30_3		15
+#define CLK_PERI_MSDC30_2		16
+#define CLK_PERI_MSDC30_1		17
+#define CLK_PERI_MSDC20_2		18
+#define CLK_PERI_MSDC20_1		19
+#define CLK_PERI_AP_DMA			20
+#define CLK_PERI_USB1			21
+#define CLK_PERI_USB0			22
+#define CLK_PERI_PWM			23
+#define CLK_PERI_PWM7			24
+#define CLK_PERI_PWM6			25
+#define CLK_PERI_PWM5			26
+#define CLK_PERI_PWM4			27
+#define CLK_PERI_PWM3			28
+#define CLK_PERI_PWM2			29
+#define CLK_PERI_PWM1			30
+#define CLK_PERI_THERM			31
+#define CLK_PERI_NFI			32
+#define CLK_PERI_USBSLV			33
+#define CLK_PERI_USB1_MCU		34
+#define CLK_PERI_USB0_MCU		35
+#define CLK_PERI_GCPU			36
+#define CLK_PERI_FHCTL			37
+#define CLK_PERI_SPI1			38
+#define CLK_PERI_AUXADC			39
+#define CLK_PERI_PERI_PWRAP		40
+#define CLK_PERI_I2C6			41
+#define CLK_PERI_UART0_SEL		42
+#define CLK_PERI_UART1_SEL		43
+#define CLK_PERI_UART2_SEL		44
+#define CLK_PERI_UART3_SEL		45
+#define CLK_PERI_NR_CLK			46
+
+#endif /* _DT_BINDINGS_CLK_MT8135_H */
diff --git a/include/dt-bindings/clock/mt8173-clk.h b/include/dt-bindings/clock/mt8173-clk.h
new file mode 100644
index 0000000..4ad76ed
--- /dev/null
+++ b/include/dt-bindings/clock/mt8173-clk.h
@@ -0,0 +1,235 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ * Author: James Liao <jamesjj.liao@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DT_BINDINGS_CLK_MT8173_H
+#define _DT_BINDINGS_CLK_MT8173_H
+
+/* TOPCKGEN */
+
+#define CLK_TOP_CLKPH_MCK_O		1
+#define CLK_TOP_DPI			2
+#define CLK_TOP_USB_SYSPLL_125M		3
+#define CLK_TOP_HDMITX_DIG_CTS		4
+#define CLK_TOP_ARMCA7PLL_754M		5
+#define CLK_TOP_ARMCA7PLL_502M		6
+#define CLK_TOP_MAIN_H546M		7
+#define CLK_TOP_MAIN_H364M		8
+#define CLK_TOP_MAIN_H218P4M		9
+#define CLK_TOP_MAIN_H156M		10
+#define CLK_TOP_TVDPLL_445P5M		11
+#define CLK_TOP_TVDPLL_594M		12
+#define CLK_TOP_UNIV_624M		13
+#define CLK_TOP_UNIV_416M		14
+#define CLK_TOP_UNIV_249P6M		15
+#define CLK_TOP_UNIV_178P3M		16
+#define CLK_TOP_UNIV_48M		17
+#define CLK_TOP_CLKRTC_EXT		18
+#define CLK_TOP_CLKRTC_INT		19
+#define CLK_TOP_FPC			20
+#define CLK_TOP_HDMITXPLL_D2		21
+#define CLK_TOP_HDMITXPLL_D3		22
+#define CLK_TOP_ARMCA7PLL_D2		23
+#define CLK_TOP_ARMCA7PLL_D3		24
+#define CLK_TOP_APLL1			25
+#define CLK_TOP_APLL2			26
+#define CLK_TOP_DMPLL			27
+#define CLK_TOP_DMPLL_D2		28
+#define CLK_TOP_DMPLL_D4		29
+#define CLK_TOP_DMPLL_D8		30
+#define CLK_TOP_DMPLL_D16		31
+#define CLK_TOP_LVDSPLL_D2		32
+#define CLK_TOP_LVDSPLL_D4		33
+#define CLK_TOP_LVDSPLL_D8		34
+#define CLK_TOP_MMPLL			35
+#define CLK_TOP_MMPLL_D2		36
+#define CLK_TOP_MSDCPLL			37
+#define CLK_TOP_MSDCPLL_D2		38
+#define CLK_TOP_MSDCPLL_D4		39
+#define CLK_TOP_MSDCPLL2		40
+#define CLK_TOP_MSDCPLL2_D2		41
+#define CLK_TOP_MSDCPLL2_D4		42
+#define CLK_TOP_SYSPLL_D2		43
+#define CLK_TOP_SYSPLL1_D2		44
+#define CLK_TOP_SYSPLL1_D4		45
+#define CLK_TOP_SYSPLL1_D8		46
+#define CLK_TOP_SYSPLL1_D16		47
+#define CLK_TOP_SYSPLL_D3		48
+#define CLK_TOP_SYSPLL2_D2		49
+#define CLK_TOP_SYSPLL2_D4		50
+#define CLK_TOP_SYSPLL_D5		51
+#define CLK_TOP_SYSPLL3_D2		52
+#define CLK_TOP_SYSPLL3_D4		53
+#define CLK_TOP_SYSPLL_D7		54
+#define CLK_TOP_SYSPLL4_D2		55
+#define CLK_TOP_SYSPLL4_D4		56
+#define CLK_TOP_TVDPLL			57
+#define CLK_TOP_TVDPLL_D2		58
+#define CLK_TOP_TVDPLL_D4		59
+#define CLK_TOP_TVDPLL_D8		60
+#define CLK_TOP_TVDPLL_D16		61
+#define CLK_TOP_UNIVPLL_D2		62
+#define CLK_TOP_UNIVPLL1_D2		63
+#define CLK_TOP_UNIVPLL1_D4		64
+#define CLK_TOP_UNIVPLL1_D8		65
+#define CLK_TOP_UNIVPLL_D3		66
+#define CLK_TOP_UNIVPLL2_D2		67
+#define CLK_TOP_UNIVPLL2_D4		68
+#define CLK_TOP_UNIVPLL2_D8		69
+#define CLK_TOP_UNIVPLL_D5		70
+#define CLK_TOP_UNIVPLL3_D2		71
+#define CLK_TOP_UNIVPLL3_D4		72
+#define CLK_TOP_UNIVPLL3_D8		73
+#define CLK_TOP_UNIVPLL_D7		74
+#define CLK_TOP_UNIVPLL_D26		75
+#define CLK_TOP_UNIVPLL_D52		76
+#define CLK_TOP_VCODECPLL		77
+#define CLK_TOP_VCODECPLL_370P5		78
+#define CLK_TOP_VENCPLL			79
+#define CLK_TOP_VENCPLL_D2		80
+#define CLK_TOP_VENCPLL_D4		81
+#define CLK_TOP_AXI_SEL			82
+#define CLK_TOP_MEM_SEL			83
+#define CLK_TOP_DDRPHYCFG_SEL		84
+#define CLK_TOP_MM_SEL			85
+#define CLK_TOP_PWM_SEL			86
+#define CLK_TOP_VDEC_SEL		87
+#define CLK_TOP_VENC_SEL		88
+#define CLK_TOP_MFG_SEL			89
+#define CLK_TOP_CAMTG_SEL		90
+#define CLK_TOP_UART_SEL		91
+#define CLK_TOP_SPI_SEL			92
+#define CLK_TOP_USB20_SEL		93
+#define CLK_TOP_USB30_SEL		94
+#define CLK_TOP_MSDC50_0_H_SEL		95
+#define CLK_TOP_MSDC50_0_SEL		96
+#define CLK_TOP_MSDC30_1_SEL		97
+#define CLK_TOP_MSDC30_2_SEL		98
+#define CLK_TOP_MSDC30_3_SEL		99
+#define CLK_TOP_AUDIO_SEL		100
+#define CLK_TOP_AUD_INTBUS_SEL		101
+#define CLK_TOP_PMICSPI_SEL		102
+#define CLK_TOP_SCP_SEL			103
+#define CLK_TOP_ATB_SEL			104
+#define CLK_TOP_VENC_LT_SEL		105
+#define CLK_TOP_DPI0_SEL		106
+#define CLK_TOP_IRDA_SEL		107
+#define CLK_TOP_CCI400_SEL		108
+#define CLK_TOP_AUD_1_SEL		109
+#define CLK_TOP_AUD_2_SEL		110
+#define CLK_TOP_MEM_MFG_IN_SEL		111
+#define CLK_TOP_AXI_MFG_IN_SEL		112
+#define CLK_TOP_SCAM_SEL		113
+#define CLK_TOP_SPINFI_IFR_SEL		114
+#define CLK_TOP_HDMI_SEL		115
+#define CLK_TOP_DPILVDS_SEL		116
+#define CLK_TOP_MSDC50_2_H_SEL		117
+#define CLK_TOP_HDCP_SEL		118
+#define CLK_TOP_HDCP_24M_SEL		119
+#define CLK_TOP_RTC_SEL			120
+#define CLK_TOP_APLL1_DIV0		121
+#define CLK_TOP_APLL1_DIV1		122
+#define CLK_TOP_APLL1_DIV2		123
+#define CLK_TOP_APLL1_DIV3		124
+#define CLK_TOP_APLL1_DIV4		125
+#define CLK_TOP_APLL1_DIV5		126
+#define CLK_TOP_APLL2_DIV0		127
+#define CLK_TOP_APLL2_DIV1		128
+#define CLK_TOP_APLL2_DIV2		129
+#define CLK_TOP_APLL2_DIV3		130
+#define CLK_TOP_APLL2_DIV4		131
+#define CLK_TOP_APLL2_DIV5		132
+#define CLK_TOP_I2S0_M_SEL		133
+#define CLK_TOP_I2S1_M_SEL		134
+#define CLK_TOP_I2S2_M_SEL		135
+#define CLK_TOP_I2S3_M_SEL		136
+#define CLK_TOP_I2S3_B_SEL		137
+#define CLK_TOP_NR_CLK			138
+
+/* APMIXED_SYS */
+
+#define CLK_APMIXED_ARMCA15PLL	1
+#define CLK_APMIXED_ARMCA7PLL	2
+#define CLK_APMIXED_MAINPLL		3
+#define CLK_APMIXED_UNIVPLL		4
+#define CLK_APMIXED_MMPLL		5
+#define CLK_APMIXED_MSDCPLL		6
+#define CLK_APMIXED_VENCPLL		7
+#define CLK_APMIXED_TVDPLL		8
+#define CLK_APMIXED_MPLL		9
+#define CLK_APMIXED_VCODECPLL		10
+#define CLK_APMIXED_APLL1		11
+#define CLK_APMIXED_APLL2		12
+#define CLK_APMIXED_LVDSPLL		13
+#define CLK_APMIXED_MSDCPLL2		14
+#define CLK_APMIXED_NR_CLK		15
+
+/* INFRA_SYS */
+
+#define CLK_INFRA_DBGCLK		1
+#define CLK_INFRA_SMI			2
+#define CLK_INFRA_AUDIO			3
+#define CLK_INFRA_GCE			4
+#define CLK_INFRA_L2C_SRAM		5
+#define CLK_INFRA_M4U			6
+#define CLK_INFRA_CPUM			7
+#define CLK_INFRA_KP			8
+#define CLK_INFRA_CEC			9
+#define CLK_INFRA_PMICSPI		10
+#define CLK_INFRA_PMICWRAP		11
+#define CLK_INFRA_NR_CLK		12
+
+/* PERI_SYS */
+
+#define CLK_PERI_NFI			1
+#define CLK_PERI_THERM			2
+#define CLK_PERI_PWM1			3
+#define CLK_PERI_PWM2			4
+#define CLK_PERI_PWM3			5
+#define CLK_PERI_PWM4			6
+#define CLK_PERI_PWM5			7
+#define CLK_PERI_PWM6			8
+#define CLK_PERI_PWM7			9
+#define CLK_PERI_PWM			10
+#define CLK_PERI_USB0			11
+#define CLK_PERI_USB1			12
+#define CLK_PERI_AP_DMA			13
+#define CLK_PERI_MSDC30_0		14
+#define CLK_PERI_MSDC30_1		15
+#define CLK_PERI_MSDC30_2		16
+#define CLK_PERI_MSDC30_3		17
+#define CLK_PERI_NLI_ARB		18
+#define CLK_PERI_IRDA			19
+#define CLK_PERI_UART0			20
+#define CLK_PERI_UART1			21
+#define CLK_PERI_UART2			22
+#define CLK_PERI_UART3			23
+#define CLK_PERI_I2C0			24
+#define CLK_PERI_I2C1			25
+#define CLK_PERI_I2C2			26
+#define CLK_PERI_I2C3			27
+#define CLK_PERI_I2C4			28
+#define CLK_PERI_AUXADC			29
+#define CLK_PERI_SPI0			30
+#define CLK_PERI_I2C5			31
+#define CLK_PERI_NFIECC			32
+#define CLK_PERI_SPI			33
+#define CLK_PERI_IRRX			34
+#define CLK_PERI_I2C6			35
+#define CLK_PERI_UART0_SEL		36
+#define CLK_PERI_UART1_SEL		37
+#define CLK_PERI_UART2_SEL		38
+#define CLK_PERI_UART3_SEL		39
+#define CLK_PERI_NR_CLK			40
+
+#endif /* _DT_BINDINGS_CLK_MT8173_H */
diff --git a/include/dt-bindings/reset-controller/mt8135-resets.h b/include/dt-bindings/reset-controller/mt8135-resets.h
new file mode 100644
index 0000000..1fb6295
--- /dev/null
+++ b/include/dt-bindings/reset-controller/mt8135-resets.h
@@ -0,0 +1,64 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ * Author: Flora Fu, MediaTek
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DT_BINDINGS_RESET_CONTROLLER_MT8135
+#define _DT_BINDINGS_RESET_CONTROLLER_MT8135
+
+/* INFRACFG resets */
+#define MT8135_INFRA_EMI_REG_RST        0
+#define MT8135_INFRA_DRAMC0_A0_RST      1
+#define MT8135_INFRA_CCIF0_RST          2
+#define MT8135_INFRA_APCIRQ_EINT_RST    3
+#define MT8135_INFRA_APXGPT_RST         4
+#define MT8135_INFRA_SCPSYS_RST         5
+#define MT8135_INFRA_CCIF1_RST          6
+#define MT8135_INFRA_PMIC_WRAP_RST      7
+#define MT8135_INFRA_KP_RST             8
+#define MT8135_INFRA_EMI_RST            32
+#define MT8135_INFRA_DRAMC0_RST         34
+#define MT8135_INFRA_SMI_RST            35
+#define MT8135_INFRA_M4U_RST            36
+
+/*  PERICFG resets */
+#define MT8135_PERI_UART0_SW_RST        0
+#define MT8135_PERI_UART1_SW_RST        1
+#define MT8135_PERI_UART2_SW_RST        2
+#define MT8135_PERI_UART3_SW_RST        3
+#define MT8135_PERI_IRDA_SW_RST         4
+#define MT8135_PERI_PTP_SW_RST          5
+#define MT8135_PERI_AP_HIF_SW_RST       6
+#define MT8135_PERI_GPCU_SW_RST         7
+#define MT8135_PERI_MD_HIF_SW_RST       8
+#define MT8135_PERI_NLI_SW_RST          9
+#define MT8135_PERI_AUXADC_SW_RST       10
+#define MT8135_PERI_DMA_SW_RST          11
+#define MT8135_PERI_NFI_SW_RST          14
+#define MT8135_PERI_PWM_SW_RST          15
+#define MT8135_PERI_THERM_SW_RST        16
+#define MT8135_PERI_MSDC0_SW_RST        17
+#define MT8135_PERI_MSDC1_SW_RST        18
+#define MT8135_PERI_MSDC2_SW_RST        19
+#define MT8135_PERI_MSDC3_SW_RST        20
+#define MT8135_PERI_I2C0_SW_RST         22
+#define MT8135_PERI_I2C1_SW_RST         23
+#define MT8135_PERI_I2C2_SW_RST         24
+#define MT8135_PERI_I2C3_SW_RST         25
+#define MT8135_PERI_I2C4_SW_RST         26
+#define MT8135_PERI_I2C5_SW_RST         27
+#define MT8135_PERI_I2C6_SW_RST         28
+#define MT8135_PERI_USB_SW_RST          29
+#define MT8135_PERI_SPI1_SW_RST         33
+#define MT8135_PERI_PWRAP_BRIDGE_SW_RST 34
+
+#endif  /* _DT_BINDINGS_RESET_CONTROLLER_MT8135 */
diff --git a/include/dt-bindings/reset-controller/mt8173-resets.h b/include/dt-bindings/reset-controller/mt8173-resets.h
new file mode 100644
index 0000000..9464b37
--- /dev/null
+++ b/include/dt-bindings/reset-controller/mt8173-resets.h
@@ -0,0 +1,63 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ * Author: Flora Fu, MediaTek
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DT_BINDINGS_RESET_CONTROLLER_MT8173
+#define _DT_BINDINGS_RESET_CONTROLLER_MT8173
+
+/* INFRACFG resets */
+#define MT8173_INFRA_EMI_REG_RST        0
+#define MT8173_INFRA_DRAMC0_A0_RST      1
+#define MT8173_INFRA_APCIRQ_EINT_RST    3
+#define MT8173_INFRA_APXGPT_RST         4
+#define MT8173_INFRA_SCPSYS_RST         5
+#define MT8173_INFRA_KP_RST             6
+#define MT8173_INFRA_PMIC_WRAP_RST      7
+#define MT8173_INFRA_MPIP_RST           8
+#define MT8173_INFRA_CEC_RST            9
+#define MT8173_INFRA_EMI_RST            32
+#define MT8173_INFRA_DRAMC0_RST         34
+#define MT8173_INFRA_APMIXEDSYS_RST     35
+#define MT8173_INFRA_MIPI_DSI_RST       36
+#define MT8173_INFRA_TRNG_RST           37
+#define MT8173_INFRA_SYSIRQ_RST         38
+#define MT8173_INFRA_MIPI_CSI_RST       39
+#define MT8173_INFRA_GCE_FAXI_RST       40
+#define MT8173_INFRA_MMIOMMURST         47
+
+
+/*  PERICFG resets */
+#define MT8173_PERI_UART0_SW_RST        0
+#define MT8173_PERI_UART1_SW_RST        1
+#define MT8173_PERI_UART2_SW_RST        2
+#define MT8173_PERI_UART3_SW_RST        3
+#define MT8173_PERI_IRRX_SW_RST         4
+#define MT8173_PERI_PWM_SW_RST          8
+#define MT8173_PERI_AUXADC_SW_RST       10
+#define MT8173_PERI_DMA_SW_RST          11
+#define MT8173_PERI_I2C6_SW_RST         13
+#define MT8173_PERI_NFI_SW_RST          14
+#define MT8173_PERI_THERM_SW_RST        16
+#define MT8173_PERI_MSDC2_SW_RST        17
+#define MT8173_PERI_MSDC3_SW_RST        18
+#define MT8173_PERI_MSDC0_SW_RST        19
+#define MT8173_PERI_MSDC1_SW_RST        20
+#define MT8173_PERI_I2C0_SW_RST         22
+#define MT8173_PERI_I2C1_SW_RST         23
+#define MT8173_PERI_I2C2_SW_RST         24
+#define MT8173_PERI_I2C3_SW_RST         25
+#define MT8173_PERI_I2C4_SW_RST         26
+#define MT8173_PERI_HDMI_SW_RST         29
+#define MT8173_PERI_SPI0_SW_RST         33
+
+#endif  /* _DT_BINDINGS_RESET_CONTROLLER_MT8173 */
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 1618cdf..c471dfc 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -53,7 +53,7 @@
 	return adev ? adev->handle : NULL;
 }
 
-#define ACPI_COMPANION(dev)		acpi_node((dev)->fwnode)
+#define ACPI_COMPANION(dev)		to_acpi_node((dev)->fwnode)
 #define ACPI_COMPANION_SET(dev, adev)	set_primary_fwnode(dev, (adev) ? \
 	acpi_fwnode_handle(adev) : NULL)
 #define ACPI_HANDLE(dev)		acpi_device_handle(ACPI_COMPANION(dev))
@@ -454,7 +454,7 @@
 	return false;
 }
 
-static inline struct acpi_device *acpi_node(struct fwnode_handle *fwnode)
+static inline struct acpi_device *to_acpi_node(struct fwnode_handle *fwnode)
 {
 	return NULL;
 }
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index a48d90e..a23209b 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -50,10 +50,10 @@
  */
 struct bdi_writeback_congested {
 	unsigned long state;		/* WB_[a]sync_congested flags */
+	atomic_t refcnt;		/* nr of attached wb's and blkg */
 
 #ifdef CONFIG_CGROUP_WRITEBACK
 	struct backing_dev_info *bdi;	/* the associated bdi */
-	atomic_t refcnt;		/* nr of attached wb's and blkg */
 	int blkcg_id;			/* ID of the associated blkcg */
 	struct rb_node rb_node;		/* on bdi->cgwb_congestion_tree */
 #endif
@@ -150,11 +150,12 @@
 	atomic_long_t tot_write_bandwidth;
 
 	struct bdi_writeback wb;  /* the root writeback info for this bdi */
-	struct bdi_writeback_congested wb_congested; /* its congested state */
 #ifdef CONFIG_CGROUP_WRITEBACK
 	struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */
 	struct rb_root cgwb_congested_tree; /* their congested states */
 	atomic_t usage_cnt; /* counts both cgwbs and cgwb_contested's */
+#else
+	struct bdi_writeback_congested *wb_congested;
 #endif
 	wait_queue_head_t wb_waitq;
 
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 0e6d482..0fe9df9 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -15,6 +15,7 @@
 #include <linux/writeback.h>
 #include <linux/blk-cgroup.h>
 #include <linux/backing-dev-defs.h>
+#include <linux/slab.h>
 
 int __must_check bdi_init(struct backing_dev_info *bdi);
 void bdi_destroy(struct backing_dev_info *bdi);
@@ -465,11 +466,14 @@
 static inline struct bdi_writeback_congested *
 wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp)
 {
-	return bdi->wb.congested;
+	atomic_inc(&bdi->wb_congested->refcnt);
+	return bdi->wb_congested;
 }
 
 static inline void wb_congested_put(struct bdi_writeback_congested *congested)
 {
+	if (atomic_dec_and_test(&congested->refcnt))
+		kfree(congested);
 }
 
 static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi)
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 73b4522..e6797de 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -317,6 +317,13 @@
 	return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE);
 }
 
+
+static inline struct buffer_head *
+sb_getblk_gfp(struct super_block *sb, sector_t block, gfp_t gfp)
+{
+	return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, gfp);
+}
+
 static inline struct buffer_head *
 sb_find_get_block(struct super_block *sb, sector_t block)
 {
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 30f92ce..9ebee53 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -43,9 +43,9 @@
 	int flags;
 	struct ceph_fsid fsid;
 	struct ceph_entity_addr my_addr;
-	int mount_timeout;
-	int osd_idle_ttl;
-	int osd_keepalive_timeout;
+	unsigned long mount_timeout;		/* jiffies */
+	unsigned long osd_idle_ttl;		/* jiffies */
+	unsigned long osd_keepalive_timeout;	/* jiffies */
 
 	/*
 	 * any type that can't be simply compared or doesn't need need
@@ -63,9 +63,9 @@
 /*
  * defaults
  */
-#define CEPH_MOUNT_TIMEOUT_DEFAULT  60
-#define CEPH_OSD_KEEPALIVE_DEFAULT  5
-#define CEPH_OSD_IDLE_TTL_DEFAULT    60
+#define CEPH_MOUNT_TIMEOUT_DEFAULT	msecs_to_jiffies(60 * 1000)
+#define CEPH_OSD_KEEPALIVE_DEFAULT	msecs_to_jiffies(5 * 1000)
+#define CEPH_OSD_IDLE_TTL_DEFAULT	msecs_to_jiffies(60 * 1000)
 
 #define CEPH_MSG_MAX_FRONT_LEN	(16*1024*1024)
 #define CEPH_MSG_MAX_MIDDLE_LEN	(16*1024*1024)
@@ -93,13 +93,9 @@
 	CEPH_MOUNT_SHUTDOWN,
 };
 
-/*
- * subtract jiffies
- */
-static inline unsigned long time_sub(unsigned long a, unsigned long b)
+static inline unsigned long ceph_timeout_jiffies(unsigned long timeout)
 {
-	BUG_ON(time_after(b, a));
-	return (long)a - (long)b;
+	return timeout ?: MAX_SCHEDULE_TIMEOUT;
 }
 
 struct ceph_mds_client;
@@ -178,6 +174,7 @@
 
 extern struct kmem_cache *ceph_inode_cachep;
 extern struct kmem_cache *ceph_cap_cachep;
+extern struct kmem_cache *ceph_cap_flush_cachep;
 extern struct kmem_cache *ceph_dentry_cachep;
 extern struct kmem_cache *ceph_file_cachep;
 
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 61b19c4..7506b48 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -249,7 +249,7 @@
 				 struct ceph_msg *msg);
 
 extern void osd_req_op_init(struct ceph_osd_request *osd_req,
-					unsigned int which, u16 opcode);
+			    unsigned int which, u16 opcode, u32 flags);
 
 extern void osd_req_op_raw_data_in_pages(struct ceph_osd_request *,
 					unsigned int which,
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index df69531..78842f4 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -31,6 +31,7 @@
 #define CLK_GET_RATE_NOCACHE	BIT(6) /* do not use the cached clk rate */
 #define CLK_SET_RATE_NO_REPARENT BIT(7) /* don't re-parent on rate change */
 #define CLK_GET_ACCURACY_NOCACHE BIT(8) /* do not use the cached clk accuracy */
+#define CLK_RECALC_NEW_RATES	BIT(9) /* recalc rates after notifications */
 
 struct clk_hw;
 struct clk_core;
@@ -209,7 +210,7 @@
 struct clk_init_data {
 	const char		*name;
 	const struct clk_ops	*ops;
-	const char		**parent_names;
+	const char		* const *parent_names;
 	u8			num_parents;
 	unsigned long		flags;
 };
@@ -426,12 +427,14 @@
 extern const struct clk_ops clk_mux_ro_ops;
 
 struct clk *clk_register_mux(struct device *dev, const char *name,
-		const char **parent_names, u8 num_parents, unsigned long flags,
+		const char * const *parent_names, u8 num_parents,
+		unsigned long flags,
 		void __iomem *reg, u8 shift, u8 width,
 		u8 clk_mux_flags, spinlock_t *lock);
 
 struct clk *clk_register_mux_table(struct device *dev, const char *name,
-		const char **parent_names, u8 num_parents, unsigned long flags,
+		const char * const *parent_names, u8 num_parents,
+		unsigned long flags,
 		void __iomem *reg, u8 shift, u32 mask,
 		u8 clk_mux_flags, u32 *table, spinlock_t *lock);
 
@@ -457,7 +460,7 @@
 	unsigned int	div;
 };
 
-extern struct clk_ops clk_fixed_factor_ops;
+extern const struct clk_ops clk_fixed_factor_ops;
 struct clk *clk_register_fixed_factor(struct device *dev, const char *name,
 		const char *parent_name, unsigned long flags,
 		unsigned int mult, unsigned int div);
@@ -518,7 +521,7 @@
 };
 
 struct clk *clk_register_composite(struct device *dev, const char *name,
-		const char **parent_names, int num_parents,
+		const char * const *parent_names, int num_parents,
 		struct clk_hw *mux_hw, const struct clk_ops *mux_ops,
 		struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
 		struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
@@ -589,6 +592,7 @@
 			      unsigned long max_rate,
 			      unsigned long *best_parent_rate,
 			      struct clk_hw **best_parent_p);
+void clk_hw_reparent(struct clk_hw *hw, struct clk_hw *new_parent);
 
 static inline void __clk_hw_set_clk(struct clk_hw *dst, struct clk_hw *src)
 {
@@ -624,6 +628,8 @@
 				  void *data);
 struct clk *of_clk_src_onecell_get(struct of_phandle_args *clkspec, void *data);
 int of_clk_get_parent_count(struct device_node *np);
+int of_clk_parent_fill(struct device_node *np, const char **parents,
+		       unsigned int size);
 const char *of_clk_get_parent_name(struct device_node *np, int index);
 
 void of_clk_init(const struct of_device_id *matches);
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 26fc8bc..7f8ad95 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -475,6 +475,21 @@
 	(volatile typeof(x) *)&(x); })
 #define ACCESS_ONCE(x) (*__ACCESS_ONCE(x))
 
+/**
+ * lockless_dereference() - safely load a pointer for later dereference
+ * @p: The pointer to load
+ *
+ * Similar to rcu_dereference(), but for situations where the pointed-to
+ * object's lifetime is managed by something other than RCU.  That
+ * "something other" might be reference counting or simple immortality.
+ */
+#define lockless_dereference(p) \
+({ \
+	typeof(p) _________p1 = READ_ONCE(p); \
+	smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
+	(_________p1); \
+})
+
 /* Ignore/forbid kprobes attach on very low level functions marked by this attribute: */
 #ifdef CONFIG_KPROBES
 # define __kprobes	__attribute__((__section__(".kprobes.text")))
diff --git a/include/linux/crc-t10dif.h b/include/linux/crc-t10dif.h
index cf53d07..d81961e 100644
--- a/include/linux/crc-t10dif.h
+++ b/include/linux/crc-t10dif.h
@@ -9,5 +9,6 @@
 extern __u16 crc_t10dif_generic(__u16 crc, const unsigned char *buffer,
 				size_t len);
 extern __u16 crc_t10dif(unsigned char const *, size_t);
+extern __u16 crc_t10dif_update(__u16 crc, unsigned char const *, size_t);
 
 #endif
diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h
index 48a1a7d1..48b4930 100644
--- a/include/linux/crush/crush.h
+++ b/include/linux/crush/crush.h
@@ -1,7 +1,11 @@
 #ifndef CEPH_CRUSH_CRUSH_H
 #define CEPH_CRUSH_CRUSH_H
 
-#include <linux/types.h>
+#ifdef __KERNEL__
+# include <linux/types.h>
+#else
+# include "crush_compat.h"
+#endif
 
 /*
  * CRUSH is a pseudo-random data distribution algorithm that
@@ -20,7 +24,11 @@
 #define CRUSH_MAGIC 0x00010000ul   /* for detecting algorithm revisions */
 
 #define CRUSH_MAX_DEPTH 10  /* max crush hierarchy depth */
+#define CRUSH_MAX_RULESET (1<<8)  /* max crush ruleset number */
+#define CRUSH_MAX_RULES CRUSH_MAX_RULESET  /* should be the same as max rulesets */
 
+#define CRUSH_MAX_DEVICE_WEIGHT (100u * 0x10000u)
+#define CRUSH_MAX_BUCKET_WEIGHT (65535u * 0x10000u)
 
 #define CRUSH_ITEM_UNDEF  0x7ffffffe  /* undefined result (internal use only) */
 #define CRUSH_ITEM_NONE   0x7fffffff  /* no result */
@@ -108,6 +116,15 @@
 };
 extern const char *crush_bucket_alg_name(int alg);
 
+/*
+ * although tree was a legacy algorithm, it has been buggy, so
+ * exclude it.
+ */
+#define CRUSH_LEGACY_ALLOWED_BUCKET_ALGS (	\
+		(1 << CRUSH_BUCKET_UNIFORM) |	\
+		(1 << CRUSH_BUCKET_LIST) |	\
+		(1 << CRUSH_BUCKET_STRAW))
+
 struct crush_bucket {
 	__s32 id;        /* this'll be negative */
 	__u16 type;      /* non-zero; type=0 is reserved for devices */
@@ -174,7 +191,7 @@
 	/* choose local attempts using a fallback permutation before
 	 * re-descent */
 	__u32 choose_local_fallback_tries;
-	/* choose attempts before giving up */ 
+	/* choose attempts before giving up */
 	__u32 choose_total_tries;
 	/* attempt chooseleaf inner descent once for firstn mode; on
 	 * reject retry outer descent.  Note that this does *not*
@@ -187,6 +204,25 @@
 	 * that want to limit reshuffling, a value of 3 or 4 will make the
 	 * mappings line up a bit better with previous mappings. */
 	__u8 chooseleaf_vary_r;
+
+#ifndef __KERNEL__
+	/*
+	 * version 0 (original) of straw_calc has various flaws.  version 1
+	 * fixes a few of them.
+	 */
+	__u8 straw_calc_version;
+
+	/*
+	 * allowed bucket algs is a bitmask, here the bit positions
+	 * are CRUSH_BUCKET_*.  note that these are *bits* and
+	 * CRUSH_BUCKET_* values are not, so we need to or together (1
+	 * << CRUSH_BUCKET_WHATEVER).  The 0th bit is not used to
+	 * minimize confusion (bucket type values start at 1).
+	 */
+	__u32 allowed_bucket_algs;
+
+	__u32 *choose_tries;
+#endif
 };
 
 
diff --git a/include/linux/crush/hash.h b/include/linux/crush/hash.h
index 91e8842..d1d9025 100644
--- a/include/linux/crush/hash.h
+++ b/include/linux/crush/hash.h
@@ -1,6 +1,12 @@
 #ifndef CEPH_CRUSH_HASH_H
 #define CEPH_CRUSH_HASH_H
 
+#ifdef __KERNEL__
+# include <linux/types.h>
+#else
+# include "crush_compat.h"
+#endif
+
 #define CRUSH_HASH_RJENKINS1   0
 
 #define CRUSH_HASH_DEFAULT CRUSH_HASH_RJENKINS1
diff --git a/include/linux/crush/mapper.h b/include/linux/crush/mapper.h
index eab3674..5dfd5b1 100644
--- a/include/linux/crush/mapper.h
+++ b/include/linux/crush/mapper.h
@@ -8,7 +8,7 @@
  * LGPL2
  */
 
-#include <linux/crush/crush.h>
+#include "crush.h"
 
 extern int crush_find_rule(const struct crush_map *map, int ruleset, int type, int size);
 extern int crush_do_rule(const struct crush_map *map,
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index df334cb..d2d5024 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -160,6 +160,7 @@
 	char *(*d_dname)(struct dentry *, char *, int);
 	struct vfsmount *(*d_automount)(struct path *);
 	int (*d_manage)(struct dentry *, bool);
+	struct inode *(*d_select_inode)(struct dentry *, unsigned);
 } ____cacheline_aligned;
 
 /*
@@ -225,6 +226,7 @@
 
 #define DCACHE_MAY_FREE			0x00800000
 #define DCACHE_FALLTHRU			0x01000000 /* Fall through to lower layer */
+#define DCACHE_OP_SELECT_INODE		0x02000000 /* Unioned entry: dcache op selects inode */
 
 extern seqlock_t rename_lock;
 
@@ -505,6 +507,11 @@
 	return dentry->d_inode != NULL;
 }
 
+static inline int simple_positive(struct dentry *dentry)
+{
+	return d_really_is_positive(dentry) && !d_unhashed(dentry);
+}
+
 extern void d_set_fallthru(struct dentry *dentry);
 
 static inline bool d_is_fallthru(const struct dentry *dentry)
diff --git a/include/linux/device.h b/include/linux/device.h
index 00ac57c..5a31bf3 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1300,4 +1300,26 @@
 } \
 module_exit(__driver##_exit);
 
+/**
+ * builtin_driver() - Helper macro for drivers that don't do anything
+ * special in init and have no exit. This eliminates some boilerplate.
+ * Each driver may only use this macro once, and calling it replaces
+ * device_initcall (or in some cases, the legacy __initcall).  This is
+ * meant to be a direct parallel of module_driver() above but without
+ * the __exit stuff that is not used for builtin cases.
+ *
+ * @__driver: driver name
+ * @__register: register function for this driver type
+ * @...: Additional arguments to be passed to __register
+ *
+ * Use this macro to construct bus specific macros for registering
+ * drivers, and do not use it on its own.
+ */
+#define builtin_driver(__driver, __register, ...) \
+static int __init __driver##_init(void) \
+{ \
+	return __register(&(__driver) , ##__VA_ARGS__); \
+} \
+device_initcall(__driver##_init);
+
 #endif /* _DEVICE_H_ */
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index 230f87b..fbb8874 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -47,6 +47,9 @@
    * read mostly part
    */
 	atomic_t count;
+	bool resize_in_progress;
+	wait_queue_head_t resize_wait;
+
 	struct fdtable __rcu *fdt;
 	struct fdtable fdtab;
   /*
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3f1a846..a0653e5 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1654,7 +1654,6 @@
 	int (*set_acl)(struct inode *, struct posix_acl *, int);
 
 	/* WARNING: probably going away soon, do not use! */
-	int (*dentry_open)(struct dentry *, struct file *, const struct cred *);
 } ____cacheline_aligned;
 
 ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
@@ -1917,6 +1916,7 @@
 #define FS_HAS_SUBTYPE		4
 #define FS_USERNS_MOUNT		8	/* Can be mounted by userns root */
 #define FS_USERNS_DEV_MOUNT	16 /* A userns mount does not imply MNT_NODEV */
+#define FS_USERNS_VISIBLE	32	/* FS must already be visible */
 #define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
 	struct dentry *(*mount) (struct file_system_type *, int,
 		       const char *, void *);
@@ -2004,7 +2004,6 @@
 extern int freeze_super(struct super_block *super);
 extern int thaw_super(struct super_block *super);
 extern bool our_mnt(struct vfsmount *mnt);
-extern bool fs_fully_visible(struct file_system_type *);
 
 extern int current_umask(void);
 
@@ -2213,7 +2212,6 @@
 extern struct file *filp_open(const char *, int, umode_t);
 extern struct file *file_open_root(struct dentry *, struct vfsmount *,
 				   const char *, int);
-extern int vfs_open(const struct path *, struct file *, const struct cred *);
 extern struct file * dentry_open(const struct path *, int, const struct cred *);
 extern int filp_close(struct file *, fl_owner_t id);
 
@@ -2530,6 +2528,8 @@
 extern int is_subdir(struct dentry *, struct dentry *);
 extern int path_is_under(struct path *, struct path *);
 
+extern char *file_path(struct file *, char *, int);
+
 #include <linux/err.h>
 
 /* needed for stackable file system support */
@@ -2581,7 +2581,12 @@
 extern struct inode *new_inode(struct super_block *sb);
 extern void free_inode_nonrcu(struct inode *inode);
 extern int should_remove_suid(struct dentry *);
-extern int file_remove_suid(struct file *);
+extern int file_remove_privs(struct file *);
+extern int dentry_needs_remove_privs(struct dentry *dentry);
+static inline int file_needs_remove_privs(struct file *file)
+{
+	return dentry_needs_remove_privs(file->f_path.dentry);
+}
 
 extern void __insert_inode_hash(struct inode *, unsigned long hashval);
 static inline void insert_inode_hash(struct inode *inode)
@@ -2816,6 +2821,8 @@
 extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
 extern const struct file_operations simple_dir_operations;
 extern const struct inode_operations simple_dir_inode_operations;
+extern void make_empty_dir_inode(struct inode *inode);
+extern bool is_empty_dir_inode(struct inode *inode);
 struct tree_descr { char *name; const struct file_operations *ops; int mode; };
 struct dentry *d_alloc_name(struct dentry *, const char *);
 extern int simple_fill_super(struct super_block *, unsigned long, struct tree_descr *);
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index 7714849..604e152 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -74,6 +74,7 @@
  */
 typedef void (*fscache_operation_release_t)(struct fscache_operation *op);
 typedef void (*fscache_operation_processor_t)(struct fscache_operation *op);
+typedef void (*fscache_operation_cancel_t)(struct fscache_operation *op);
 
 enum fscache_operation_state {
 	FSCACHE_OP_ST_BLANK,		/* Op is not yet submitted */
@@ -109,6 +110,9 @@
 	 *   the op in a non-pool thread */
 	fscache_operation_processor_t processor;
 
+	/* Operation cancellation cleanup (optional) */
+	fscache_operation_cancel_t cancel;
+
 	/* operation releaser */
 	fscache_operation_release_t release;
 };
@@ -119,33 +123,17 @@
 extern void fscache_enqueue_operation(struct fscache_operation *);
 extern void fscache_op_complete(struct fscache_operation *, bool);
 extern void fscache_put_operation(struct fscache_operation *);
-
-/**
- * fscache_operation_init - Do basic initialisation of an operation
- * @op: The operation to initialise
- * @release: The release function to assign
- *
- * Do basic initialisation of an operation.  The caller must still set flags,
- * object and processor if needed.
- */
-static inline void fscache_operation_init(struct fscache_operation *op,
-					fscache_operation_processor_t processor,
-					fscache_operation_release_t release)
-{
-	INIT_WORK(&op->work, fscache_op_work_func);
-	atomic_set(&op->usage, 1);
-	op->state = FSCACHE_OP_ST_INITIALISED;
-	op->debug_id = atomic_inc_return(&fscache_op_debug_id);
-	op->processor = processor;
-	op->release = release;
-	INIT_LIST_HEAD(&op->pend_link);
-}
+extern void fscache_operation_init(struct fscache_operation *,
+				   fscache_operation_processor_t,
+				   fscache_operation_cancel_t,
+				   fscache_operation_release_t);
 
 /*
  * data read operation
  */
 struct fscache_retrieval {
 	struct fscache_operation op;
+	struct fscache_cookie	*cookie;	/* The netfs cookie */
 	struct address_space	*mapping;	/* netfs pages */
 	fscache_rw_complete_t	end_io_func;	/* function to call on I/O completion */
 	void			*context;	/* netfs read context (pinned) */
@@ -371,6 +359,7 @@
 #define FSCACHE_OBJECT_IS_LOOKED_UP	4	/* T if object has been looked up */
 #define FSCACHE_OBJECT_IS_AVAILABLE	5	/* T if object has become active */
 #define FSCACHE_OBJECT_RETIRED		6	/* T if object was retired on relinquishment */
+#define FSCACHE_OBJECT_KILLED_BY_CACHE	7	/* T if object was killed by the cache */
 
 	struct list_head	cache_link;	/* link in cache->object_list */
 	struct hlist_node	cookie_link;	/* link in cookie->backing_objects */
@@ -410,17 +399,16 @@
 	return test_bit(FSCACHE_OBJECT_IS_AVAILABLE, &object->flags);
 }
 
+static inline bool fscache_cache_is_broken(struct fscache_object *object)
+{
+	return test_bit(FSCACHE_IOERROR, &object->cache->flags);
+}
+
 static inline bool fscache_object_is_active(struct fscache_object *object)
 {
 	return fscache_object_is_available(object) &&
 		fscache_object_is_live(object) &&
-		!test_bit(FSCACHE_IOERROR, &object->cache->flags);
-}
-
-static inline bool fscache_object_is_dead(struct fscache_object *object)
-{
-	return fscache_object_is_dying(object) &&
-		test_bit(FSCACHE_IOERROR, &object->cache->flags);
+		!fscache_cache_is_broken(object);
 }
 
 /**
@@ -551,4 +539,15 @@
 					       const void *data,
 					       uint16_t datalen);
 
+extern void fscache_object_retrying_stale(struct fscache_object *object);
+
+enum fscache_why_object_killed {
+	FSCACHE_OBJECT_IS_STALE,
+	FSCACHE_OBJECT_NO_SPACE,
+	FSCACHE_OBJECT_WAS_RETIRED,
+	FSCACHE_OBJECT_WAS_CULLED,
+};
+extern void fscache_object_mark_killed(struct fscache_object *object,
+				       enum fscache_why_object_killed why);
+
 #endif /* _LINUX_FSCACHE_CACHE_H */
diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h
index 1ccaab4..5383bb1 100644
--- a/include/linux/genalloc.h
+++ b/include/linux/genalloc.h
@@ -119,16 +119,16 @@
 
 extern struct gen_pool *devm_gen_pool_create(struct device *dev,
 		int min_alloc_order, int nid);
-extern struct gen_pool *dev_get_gen_pool(struct device *dev);
+extern struct gen_pool *gen_pool_get(struct device *dev);
 
 bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start,
 			size_t size);
 
 #ifdef CONFIG_OF
-extern struct gen_pool *of_get_named_gen_pool(struct device_node *np,
+extern struct gen_pool *of_gen_pool_get(struct device_node *np,
 	const char *propname, int index);
 #else
-static inline struct gen_pool *of_get_named_gen_pool(struct device_node *np,
+static inline struct gen_pool *of_gen_pool_get(struct device_node *np,
 	const char *propname, int index)
 {
 	return NULL;
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 6ba7cf2..ad35f30 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -384,6 +384,14 @@
 void drain_all_pages(struct zone *zone);
 void drain_local_pages(struct zone *zone);
 
+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+void page_alloc_init_late(void);
+#else
+static inline void page_alloc_init_late(void)
+{
+}
+#endif
+
 /*
  * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what
  * GFP flags are used before interrupts are enabled. Once interrupts are
diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index fd09816..adac255 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -407,6 +407,21 @@
 	return -EINVAL;
 }
 
+/* Child properties interface */
+struct fwnode_handle;
+
+static inline struct gpio_desc *fwnode_get_named_gpiod(
+	struct fwnode_handle *fwnode, const char *propname)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline struct gpio_desc *devm_get_gpiod_from_child(
+	struct device *dev, const char *con_id, struct fwnode_handle *child)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
 #endif /* CONFIG_GPIOLIB */
 
 /*
diff --git a/include/linux/hwspinlock.h b/include/linux/hwspinlock.h
index 3343298..859d673 100644
--- a/include/linux/hwspinlock.h
+++ b/include/linux/hwspinlock.h
@@ -26,6 +26,7 @@
 #define HWLOCK_IRQ	0x02	/* Disable interrupts, don't save state */
 
 struct device;
+struct device_node;
 struct hwspinlock;
 struct hwspinlock_device;
 struct hwspinlock_ops;
@@ -66,6 +67,7 @@
 struct hwspinlock *hwspin_lock_request(void);
 struct hwspinlock *hwspin_lock_request_specific(unsigned int id);
 int hwspin_lock_free(struct hwspinlock *hwlock);
+int of_hwspin_lock_get_id(struct device_node *np, int index);
 int hwspin_lock_get_id(struct hwspinlock *hwlock);
 int __hwspin_lock_timeout(struct hwspinlock *, unsigned int, int,
 							unsigned long *);
@@ -120,6 +122,11 @@
 {
 }
 
+static inline int of_hwspin_lock_get_id(struct device_node *np, int index)
+{
+	return 0;
+}
+
 static inline int hwspin_lock_get_id(struct hwspinlock *hwlock)
 {
 	return 0;
diff --git a/include/linux/init.h b/include/linux/init.h
index 21b6d76..7c68c36 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -91,14 +91,6 @@
 
 #define __exit          __section(.exit.text) __exitused __cold notrace
 
-/* temporary, until all users are removed */
-#define __cpuinit
-#define __cpuinitdata
-#define __cpuinitconst
-#define __cpuexit
-#define __cpuexitdata
-#define __cpuexitconst
-
 /* Used for MEMORY_HOTPLUG */
 #define __meminit        __section(.meminit.text) __cold notrace
 #define __meminitdata    __section(.meminit.data)
@@ -116,9 +108,6 @@
 #define __INITRODATA	.section	".init.rodata","a",%progbits
 #define __FINITDATA	.previous
 
-/* temporary, until all users are removed */
-#define __CPUINIT
-
 #define __MEMINIT        .section	".meminit.text", "ax"
 #define __MEMINITDATA    .section	".meminit.data", "aw"
 #define __MEMINITRODATA  .section	".meminit.rodata", "a"
diff --git a/include/linux/input/touchscreen.h b/include/linux/input/touchscreen.h
index 08a5ef6..eecc9ea 100644
--- a/include/linux/input/touchscreen.h
+++ b/include/linux/input/touchscreen.h
@@ -12,9 +12,10 @@
 #include <linux/input.h>
 
 #ifdef CONFIG_OF
-void touchscreen_parse_of_params(struct input_dev *dev);
+void touchscreen_parse_of_params(struct input_dev *dev, bool multitouch);
 #else
-static inline void touchscreen_parse_of_params(struct input_dev *dev)
+static inline void touchscreen_parse_of_params(struct input_dev *dev,
+					       bool multitouch)
 {
 }
 #endif
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 81214916..92188b0 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -407,7 +407,6 @@
 	IRQCHIP_EOI_THREADED		= (1 <<  6),
 };
 
-/* This include will go away once we isolated irq_desc usage to core code */
 #include <linux/irqdesc.h>
 
 /*
diff --git a/include/linux/irqchip.h b/include/linux/irqchip.h
index 14d7913..6388873 100644
--- a/include/linux/irqchip.h
+++ b/include/linux/irqchip.h
@@ -11,6 +11,20 @@
 #ifndef _LINUX_IRQCHIP_H
 #define _LINUX_IRQCHIP_H
 
+#include <linux/of.h>
+
+/*
+ * This macro must be used by the different irqchip drivers to declare
+ * the association between their DT compatible string and their
+ * initialization function.
+ *
+ * @name: name that must be unique accross all IRQCHIP_DECLARE of the
+ * same file.
+ * @compstr: compatible string of the irqchip driver
+ * @fn: initialization function
+ */
+#define IRQCHIP_DECLARE(name, compat, fn) OF_DECLARE_2(irqchip, name, compat, fn)
+
 #ifdef CONFIG_IRQCHIP
 void irqchip_init(void);
 #else
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index c52d148..624a668 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -3,9 +3,6 @@
 
 /*
  * Core internal functions to deal with irq descriptors
- *
- * This include will move to kernel/irq once we cleaned up the tree.
- * For now it's included from <linux/irq.h>
  */
 
 struct irq_affinity_notify;
@@ -103,6 +100,11 @@
 #endif
 }
 
+static inline unsigned int irq_desc_get_irq(struct irq_desc *desc)
+{
+	return desc->irq_data.irq;
+}
+
 static inline struct irq_data *irq_desc_get_irq_data(struct irq_desc *desc)
 {
 	return &desc->irq_data;
@@ -188,6 +190,47 @@
 	desc->name = name;
 }
 
+/**
+ * irq_set_handler_locked - Set irq handler from a locked region
+ * @data:	Pointer to the irq_data structure which identifies the irq
+ * @handler:	Flow control handler function for this interrupt
+ *
+ * Sets the handler in the irq descriptor associated to @data.
+ *
+ * Must be called with irq_desc locked and valid parameters. Typical
+ * call site is the irq_set_type() callback.
+ */
+static inline void irq_set_handler_locked(struct irq_data *data,
+					  irq_flow_handler_t handler)
+{
+	struct irq_desc *desc = irq_data_to_desc(data);
+
+	desc->handle_irq = handler;
+}
+
+/**
+ * irq_set_chip_handler_name_locked - Set chip, handler and name from a locked region
+ * @data:	Pointer to the irq_data structure for which the chip is set
+ * @chip:	Pointer to the new irq chip
+ * @handler:	Flow control handler function for this interrupt
+ * @name:	Name of the interrupt
+ *
+ * Replace the irq chip at the proper hierarchy level in @data and
+ * sets the handler and name in the associated irq descriptor.
+ *
+ * Must be called with irq_desc locked and valid parameters.
+ */
+static inline void
+irq_set_chip_handler_name_locked(struct irq_data *data, struct irq_chip *chip,
+				 irq_flow_handler_t handler, const char *name)
+{
+	struct irq_desc *desc = irq_data_to_desc(data);
+
+	desc->handle_irq = handler;
+	desc->name = name;
+	data->chip = chip;
+}
+
 static inline int irq_balancing_disabled(unsigned int irq)
 {
 	struct irq_desc *desc;
diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h
index fdd5cc1..9669bf9 100644
--- a/include/linux/irqnr.h
+++ b/include/linux/irqnr.h
@@ -23,12 +23,6 @@
 			;						\
 		else
 
-#ifdef CONFIG_SMP
-#define irq_node(irq)	(irq_get_irq_data(irq)->node)
-#else
-#define irq_node(irq)	0
-#endif
-
 # define for_each_active_irq(irq)			\
 	for (irq = irq_get_next_irq(0); irq < nr_irqs;	\
 	     irq = irq_get_next_irq(irq + 1))
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 5acf5b7..5f0be58 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -439,6 +439,9 @@
 extern int panic_on_io_nmi;
 extern int panic_on_warn;
 extern int sysctl_panic_on_stackoverflow;
+
+extern bool crash_kexec_post_notifiers;
+
 /*
  * Only to be used by arch init code. If the user over-wrote the default
  * CONFIG_PANIC_TIMEOUT, honor it.
@@ -813,13 +816,15 @@
 #endif
 
 /* Permissions on a sysfs file: you didn't miss the 0 prefix did you? */
-#define VERIFY_OCTAL_PERMISSIONS(perms)					\
-	(BUILD_BUG_ON_ZERO((perms) < 0) +				\
-	 BUILD_BUG_ON_ZERO((perms) > 0777) +				\
-	 /* User perms >= group perms >= other perms */			\
-	 BUILD_BUG_ON_ZERO(((perms) >> 6) < (((perms) >> 3) & 7)) +	\
-	 BUILD_BUG_ON_ZERO((((perms) >> 3) & 7) < ((perms) & 7)) +	\
-	 /* Other writable?  Generally considered a bad idea. */	\
-	 BUILD_BUG_ON_ZERO((perms) & 2) +				\
+#define VERIFY_OCTAL_PERMISSIONS(perms)						\
+	(BUILD_BUG_ON_ZERO((perms) < 0) +					\
+	 BUILD_BUG_ON_ZERO((perms) > 0777) +					\
+	 /* USER_READABLE >= GROUP_READABLE >= OTHER_READABLE */		\
+	 BUILD_BUG_ON_ZERO((((perms) >> 6) & 4) < (((perms) >> 3) & 4)) +	\
+	 BUILD_BUG_ON_ZERO((((perms) >> 3) & 4) < ((perms) & 4)) +		\
+	 /* USER_WRITABLE >= GROUP_WRITABLE */					\
+	 BUILD_BUG_ON_ZERO((((perms) >> 6) & 2) < (((perms) >> 3) & 2)) +	\
+	 /* OTHER_WRITABLE?  Generally considered a bad idea. */		\
+	 BUILD_BUG_ON_ZERO((perms) & 2) +					\
 	 (perms))
 #endif
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index e6b2f7d..123be25 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -45,6 +45,7 @@
 	KERNFS_LOCKDEP		= 0x0100,
 	KERNFS_SUICIDAL		= 0x0400,
 	KERNFS_SUICIDED		= 0x0800,
+	KERNFS_EMPTY_DIR	= 0x1000,
 };
 
 /* @flags for kernfs_create_root() */
@@ -286,6 +287,8 @@
 struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
 					 const char *name, umode_t mode,
 					 void *priv, const void *ns);
+struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent,
+					    const char *name);
 struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
 					 const char *name,
 					 umode_t mode, loff_t size,
diff --git a/include/linux/leds.h b/include/linux/leds.h
index 9a2b000..b122eea 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -12,6 +12,7 @@
 #ifndef __LINUX_LEDS_H_INCLUDED
 #define __LINUX_LEDS_H_INCLUDED
 
+#include <linux/device.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
 #include <linux/rwsem.h>
@@ -222,6 +223,11 @@
 	struct list_head  next_trig;
 };
 
+ssize_t led_trigger_store(struct device *dev, struct device_attribute *attr,
+			const char *buf, size_t count);
+ssize_t led_trigger_show(struct device *dev, struct device_attribute *attr,
+			char *buf);
+
 /* Registration functions for complex triggers */
 extern int led_trigger_register(struct led_trigger *trigger);
 extern void led_trigger_unregister(struct led_trigger *trigger);
@@ -238,6 +244,16 @@
 				      unsigned long *delay_on,
 				      unsigned long *delay_off,
 				      int invert);
+extern void led_trigger_set_default(struct led_classdev *led_cdev);
+extern void led_trigger_set(struct led_classdev *led_cdev,
+			struct led_trigger *trigger);
+extern void led_trigger_remove(struct led_classdev *led_cdev);
+
+static inline void *led_get_trigger_data(struct led_classdev *led_cdev)
+{
+	return led_cdev->trigger_data;
+}
+
 /**
  * led_trigger_rename_static - rename a trigger
  * @name: the new trigger name
@@ -267,6 +283,15 @@
 static inline void led_trigger_unregister_simple(struct led_trigger *trigger) {}
 static inline void led_trigger_event(struct led_trigger *trigger,
 				enum led_brightness event) {}
+static inline void led_trigger_set_default(struct led_classdev *led_cdev) {}
+static inline void led_trigger_set(struct led_classdev *led_cdev,
+				struct led_trigger *trigger) {}
+static inline void led_trigger_remove(struct led_classdev *led_cdev) {}
+static inline void *led_get_trigger_data(struct led_classdev *led_cdev)
+{
+	return NULL;
+}
+
 #endif /* CONFIG_LEDS_TRIGGERS */
 
 /* Trigger specific functions */
diff --git a/include/linux/libfdt_env.h b/include/linux/libfdt_env.h
index 01508c7..2a663c6 100644
--- a/include/linux/libfdt_env.h
+++ b/include/linux/libfdt_env.h
@@ -5,6 +5,10 @@
 
 #include <asm/byteorder.h>
 
+typedef __be16 fdt16_t;
+typedef __be32 fdt32_t;
+typedef __be64 fdt64_t;
+
 #define fdt32_to_cpu(x) be32_to_cpu(x)
 #define cpu_to_fdt32(x) cpu_to_be32(x)
 #define fdt64_to_cpu(x) be64_to_cpu(x)
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 0215ffd..cc4b019 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -101,6 +101,9 @@
 			  struct memblock_type *type_b, phys_addr_t *out_start,
 			  phys_addr_t *out_end, int *out_nid);
 
+void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start,
+			       phys_addr_t *out_end);
+
 /**
  * for_each_mem_range - iterate through memblock areas from type_a and not
  * included in type_b. Or just type_a if type_b is NULL.
@@ -142,6 +145,21 @@
 	     __next_mem_range_rev(&i, nid, flags, type_a, type_b,	\
 				  p_start, p_end, p_nid))
 
+/**
+ * for_each_reserved_mem_region - iterate over all reserved memblock areas
+ * @i: u64 used as loop variable
+ * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
+ * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
+ *
+ * Walks over reserved areas of memblock. Available as soon as memblock
+ * is initialized.
+ */
+#define for_each_reserved_mem_region(i, p_start, p_end)			\
+	for (i = 0UL,							\
+	     __next_reserved_mem_region(&i, p_start, p_end);		\
+	     i != (u64)ULLONG_MAX;					\
+	     __next_reserved_mem_region(&i, p_start, p_end))
+
 #ifdef CONFIG_MOVABLE_NODE
 static inline bool memblock_is_hotpluggable(struct memblock_region *m)
 {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 99959a3..2e872f9 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1635,6 +1635,8 @@
 extern void adjust_managed_page_count(struct page *page, long count);
 extern void mem_init_print_info(const char *str);
 
+extern void reserve_bootmem_region(unsigned long start, unsigned long end);
+
 /* Free the reserved page into the buddy system, so it gets managed. */
 static inline void __free_reserved_page(struct page *page)
 {
@@ -1724,7 +1726,8 @@
 
 #if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \
     !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID)
-static inline int __early_pfn_to_nid(unsigned long pfn)
+static inline int __early_pfn_to_nid(unsigned long pfn,
+					struct mminit_pfnnid_cache *state)
 {
 	return 0;
 }
@@ -1732,7 +1735,8 @@
 /* please see mm/page_alloc.c */
 extern int __meminit early_pfn_to_nid(unsigned long pfn);
 /* there is a per-arch backend function. */
-extern int __meminit __early_pfn_to_nid(unsigned long pfn);
+extern int __meminit __early_pfn_to_nid(unsigned long pfn,
+					struct mminit_pfnnid_cache *state);
 #endif
 
 extern void set_dma_reserve(unsigned long new_dma_reserve);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 54d74f6..754c259 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -762,6 +762,14 @@
 	/* Number of pages migrated during the rate limiting time interval */
 	unsigned long numabalancing_migrate_nr_pages;
 #endif
+
+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+	/*
+	 * If memory initialisation on large machines is deferred then this
+	 * is the first PFN that needs to be initialised.
+	 */
+	unsigned long first_deferred_pfn;
+#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
 } pg_data_t;
 
 #define node_present_pages(nid)	(NODE_DATA(nid)->node_present_pages)
@@ -1216,11 +1224,16 @@
 #define sparse_index_init(_sec, _nid)  do {} while (0)
 #endif /* CONFIG_SPARSEMEM */
 
-#ifdef CONFIG_NODES_SPAN_OTHER_NODES
-bool early_pfn_in_nid(unsigned long pfn, int nid);
-#else
-#define early_pfn_in_nid(pfn, nid)	(1)
-#endif
+/*
+ * During memory init memblocks map pfns to nids. The search is expensive and
+ * this caches recent lookups. The implementation of __early_pfn_to_nid
+ * may treat start/end as pfns or sections.
+ */
+struct mminit_pfnnid_cache {
+	unsigned long last_start;
+	unsigned long last_end;
+	int last_nid;
+};
 
 #ifndef early_pfn_valid
 #define early_pfn_valid(pfn)	(1)
diff --git a/include/linux/module.h b/include/linux/module.h
index 7ffe085..d67b193 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -17,6 +17,7 @@
 #include <linux/moduleparam.h>
 #include <linux/jump_label.h>
 #include <linux/export.h>
+#include <linux/rbtree_latch.h>
 
 #include <linux/percpu.h>
 #include <asm/module.h>
@@ -210,6 +211,13 @@
 	MODULE_STATE_UNFORMED,	/* Still setting it up. */
 };
 
+struct module;
+
+struct mod_tree_node {
+	struct module *mod;
+	struct latch_tree_node node;
+};
+
 struct module {
 	enum module_state state;
 
@@ -232,6 +240,9 @@
 	unsigned int num_syms;
 
 	/* Kernel parameters. */
+#ifdef CONFIG_SYSFS
+	struct mutex param_lock;
+#endif
 	struct kernel_param *kp;
 	unsigned int num_kp;
 
@@ -271,8 +282,15 @@
 	/* Startup function. */
 	int (*init)(void);
 
-	/* If this is non-NULL, vfree after init() returns */
-	void *module_init;
+	/*
+	 * If this is non-NULL, vfree() after init() returns.
+	 *
+	 * Cacheline align here, such that:
+	 *   module_init, module_core, init_size, core_size,
+	 *   init_text_size, core_text_size and mtn_core::{mod,node[0]}
+	 * are on the same cacheline.
+	 */
+	void *module_init	____cacheline_aligned;
 
 	/* Here is the actual code + data, vfree'd on unload. */
 	void *module_core;
@@ -283,6 +301,16 @@
 	/* The size of the executable code in each section.  */
 	unsigned int init_text_size, core_text_size;
 
+#ifdef CONFIG_MODULES_TREE_LOOKUP
+	/*
+	 * We want mtn_core::{mod,node[0]} to be in the same cacheline as the
+	 * above entries such that a regular lookup will only touch one
+	 * cacheline.
+	 */
+	struct mod_tree_node	mtn_core;
+	struct mod_tree_node	mtn_init;
+#endif
+
 	/* Size of RO sections of the module (text+rodata) */
 	unsigned int init_ro_size, core_ro_size;
 
@@ -369,7 +397,7 @@
 	ctor_fn_t *ctors;
 	unsigned int num_ctors;
 #endif
-};
+} ____cacheline_aligned;
 #ifndef MODULE_ARCH_INIT
 #define MODULE_ARCH_INIT {}
 #endif
@@ -423,14 +451,22 @@
 	bool unused;
 };
 
-/* Search for an exported symbol by name. */
+/*
+ * Search for an exported symbol by name.
+ *
+ * Must be called with module_mutex held or preemption disabled.
+ */
 const struct kernel_symbol *find_symbol(const char *name,
 					struct module **owner,
 					const unsigned long **crc,
 					bool gplok,
 					bool warn);
 
-/* Walk the exported symbol table */
+/*
+ * Walk the exported symbol table
+ *
+ * Must be called with module_mutex held or preemption disabled.
+ */
 bool each_symbol_section(bool (*fn)(const struct symsearch *arr,
 				    struct module *owner,
 				    void *data), void *data);
diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 6480dca..c12f214 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -67,8 +67,9 @@
 
 struct kernel_param {
 	const char *name;
+	struct module *mod;
 	const struct kernel_param_ops *ops;
-	u16 perm;
+	const u16 perm;
 	s8 level;
 	u8 flags;
 	union {
@@ -108,7 +109,7 @@
  *
  * @perm is 0 if the the variable is not to appear in sysfs, or 0444
  * for world-readable, 0644 for root-writable, etc.  Note that if it
- * is writable, you may need to use kparam_block_sysfs_write() around
+ * is writable, you may need to use kernel_param_lock() around
  * accesses (esp. charp, which can be kfreed when it changes).
  *
  * The @type is simply pasted to refer to a param_ops_##type and a
@@ -216,16 +217,16 @@
    parameters. */
 #define __module_param_call(prefix, name, ops, arg, perm, level, flags)	\
 	/* Default value instead of permissions? */			\
-	static const char __param_str_##name[] = prefix #name; \
+	static const char __param_str_##name[] = prefix #name;		\
 	static struct kernel_param __moduleparam_const __param_##name	\
 	__used								\
     __attribute__ ((unused,__section__ ("__param"),aligned(sizeof(void *)))) \
-	= { __param_str_##name, ops, VERIFY_OCTAL_PERMISSIONS(perm),	\
-	    level, flags, { arg } }
+	= { __param_str_##name, THIS_MODULE, ops,			\
+	    VERIFY_OCTAL_PERMISSIONS(perm), level, flags, { arg } }
 
 /* Obsolete - use module_param_cb() */
 #define module_param_call(name, set, get, arg, perm)			\
-	static struct kernel_param_ops __param_ops_##name =		\
+	static const struct kernel_param_ops __param_ops_##name =		\
 		{ .flags = 0, (void *)set, (void *)get };		\
 	__module_param_call(MODULE_PARAM_PREFIX,			\
 			    name, &__param_ops_##name, arg,		\
@@ -238,58 +239,14 @@
 	return 0;
 }
 
-/**
- * kparam_block_sysfs_write - make sure a parameter isn't written via sysfs.
- * @name: the name of the parameter
- *
- * There's no point blocking write on a paramter that isn't writable via sysfs!
- */
-#define kparam_block_sysfs_write(name)			\
-	do {						\
-		BUG_ON(!(__param_##name.perm & 0222));	\
-		__kernel_param_lock();			\
-	} while (0)
-
-/**
- * kparam_unblock_sysfs_write - allows sysfs to write to a parameter again.
- * @name: the name of the parameter
- */
-#define kparam_unblock_sysfs_write(name)		\
-	do {						\
-		BUG_ON(!(__param_##name.perm & 0222));	\
-		__kernel_param_unlock();		\
-	} while (0)
-
-/**
- * kparam_block_sysfs_read - make sure a parameter isn't read via sysfs.
- * @name: the name of the parameter
- *
- * This also blocks sysfs writes.
- */
-#define kparam_block_sysfs_read(name)			\
-	do {						\
-		BUG_ON(!(__param_##name.perm & 0444));	\
-		__kernel_param_lock();			\
-	} while (0)
-
-/**
- * kparam_unblock_sysfs_read - allows sysfs to read a parameter again.
- * @name: the name of the parameter
- */
-#define kparam_unblock_sysfs_read(name)			\
-	do {						\
-		BUG_ON(!(__param_##name.perm & 0444));	\
-		__kernel_param_unlock();		\
-	} while (0)
-
 #ifdef CONFIG_SYSFS
-extern void __kernel_param_lock(void);
-extern void __kernel_param_unlock(void);
+extern void kernel_param_lock(struct module *mod);
+extern void kernel_param_unlock(struct module *mod);
 #else
-static inline void __kernel_param_lock(void)
+static inline void kernel_param_lock(struct module *mod)
 {
 }
-static inline void __kernel_param_unlock(void)
+static inline void kernel_param_unlock(struct module *mod)
 {
 }
 #endif
@@ -386,64 +343,70 @@
 #define __param_check(name, p, type) \
 	static inline type __always_unused *__check_##name(void) { return(p); }
 
-extern struct kernel_param_ops param_ops_byte;
+extern const struct kernel_param_ops param_ops_byte;
 extern int param_set_byte(const char *val, const struct kernel_param *kp);
 extern int param_get_byte(char *buffer, const struct kernel_param *kp);
 #define param_check_byte(name, p) __param_check(name, p, unsigned char)
 
-extern struct kernel_param_ops param_ops_short;
+extern const struct kernel_param_ops param_ops_short;
 extern int param_set_short(const char *val, const struct kernel_param *kp);
 extern int param_get_short(char *buffer, const struct kernel_param *kp);
 #define param_check_short(name, p) __param_check(name, p, short)
 
-extern struct kernel_param_ops param_ops_ushort;
+extern const struct kernel_param_ops param_ops_ushort;
 extern int param_set_ushort(const char *val, const struct kernel_param *kp);
 extern int param_get_ushort(char *buffer, const struct kernel_param *kp);
 #define param_check_ushort(name, p) __param_check(name, p, unsigned short)
 
-extern struct kernel_param_ops param_ops_int;
+extern const struct kernel_param_ops param_ops_int;
 extern int param_set_int(const char *val, const struct kernel_param *kp);
 extern int param_get_int(char *buffer, const struct kernel_param *kp);
 #define param_check_int(name, p) __param_check(name, p, int)
 
-extern struct kernel_param_ops param_ops_uint;
+extern const struct kernel_param_ops param_ops_uint;
 extern int param_set_uint(const char *val, const struct kernel_param *kp);
 extern int param_get_uint(char *buffer, const struct kernel_param *kp);
 #define param_check_uint(name, p) __param_check(name, p, unsigned int)
 
-extern struct kernel_param_ops param_ops_long;
+extern const struct kernel_param_ops param_ops_long;
 extern int param_set_long(const char *val, const struct kernel_param *kp);
 extern int param_get_long(char *buffer, const struct kernel_param *kp);
 #define param_check_long(name, p) __param_check(name, p, long)
 
-extern struct kernel_param_ops param_ops_ulong;
+extern const struct kernel_param_ops param_ops_ulong;
 extern int param_set_ulong(const char *val, const struct kernel_param *kp);
 extern int param_get_ulong(char *buffer, const struct kernel_param *kp);
 #define param_check_ulong(name, p) __param_check(name, p, unsigned long)
 
-extern struct kernel_param_ops param_ops_ullong;
+extern const struct kernel_param_ops param_ops_ullong;
 extern int param_set_ullong(const char *val, const struct kernel_param *kp);
 extern int param_get_ullong(char *buffer, const struct kernel_param *kp);
 #define param_check_ullong(name, p) __param_check(name, p, unsigned long long)
 
-extern struct kernel_param_ops param_ops_charp;
+extern const struct kernel_param_ops param_ops_charp;
 extern int param_set_charp(const char *val, const struct kernel_param *kp);
 extern int param_get_charp(char *buffer, const struct kernel_param *kp);
 #define param_check_charp(name, p) __param_check(name, p, char *)
 
 /* We used to allow int as well as bool.  We're taking that away! */
-extern struct kernel_param_ops param_ops_bool;
+extern const struct kernel_param_ops param_ops_bool;
 extern int param_set_bool(const char *val, const struct kernel_param *kp);
 extern int param_get_bool(char *buffer, const struct kernel_param *kp);
 #define param_check_bool(name, p) __param_check(name, p, bool)
 
-extern struct kernel_param_ops param_ops_invbool;
+extern const struct kernel_param_ops param_ops_bool_enable_only;
+extern int param_set_bool_enable_only(const char *val,
+				      const struct kernel_param *kp);
+/* getter is the same as for the regular bool */
+#define param_check_bool_enable_only param_check_bool
+
+extern const struct kernel_param_ops param_ops_invbool;
 extern int param_set_invbool(const char *val, const struct kernel_param *kp);
 extern int param_get_invbool(char *buffer, const struct kernel_param *kp);
 #define param_check_invbool(name, p) __param_check(name, p, bool)
 
 /* An int, which can only be set like a bool (though it shows as an int). */
-extern struct kernel_param_ops param_ops_bint;
+extern const struct kernel_param_ops param_ops_bint;
 extern int param_set_bint(const char *val, const struct kernel_param *kp);
 #define param_get_bint param_get_int
 #define param_check_bint param_check_int
@@ -487,9 +450,9 @@
 			    perm, -1, 0);				\
 	__MODULE_PARM_TYPE(name, "array of " #type)
 
-extern struct kernel_param_ops param_array_ops;
+extern const struct kernel_param_ops param_array_ops;
 
-extern struct kernel_param_ops param_ops_string;
+extern const struct kernel_param_ops param_ops_string;
 extern int param_set_copystring(const char *val, const struct kernel_param *);
 extern int param_get_string(char *buffer, const struct kernel_param *kp);
 
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 32201c2..b8e72aa 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -500,6 +500,7 @@
 	NFSPROC4_CLNT_SEEK,
 	NFSPROC4_CLNT_ALLOCATE,
 	NFSPROC4_CLNT_DEALLOCATE,
+	NFSPROC4_CLNT_LAYOUTSTATS,
 };
 
 /* nfs41 types */
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index b95f914..f91b5ad 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -219,6 +219,7 @@
 #define NFS_INO_COMMIT		(7)		/* inode is committing unstable writes */
 #define NFS_INO_LAYOUTCOMMIT	(9)		/* layoutcommit required */
 #define NFS_INO_LAYOUTCOMMITTING (10)		/* layoutcommit inflight */
+#define NFS_INO_LAYOUTSTATS	(11)		/* layoutstats inflight */
 
 static inline struct nfs_inode *NFS_I(const struct inode *inode)
 {
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 5e1273d..a2ea149 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -237,5 +237,6 @@
 #define NFS_CAP_SEEK		(1U << 19)
 #define NFS_CAP_ALLOCATE	(1U << 20)
 #define NFS_CAP_DEALLOCATE	(1U << 21)
+#define NFS_CAP_LAYOUTSTATS	(1U << 22)
 
 #endif
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index 3eb072d..f2f650f 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -67,7 +67,6 @@
 	const fmode_t rw_mode;
 	struct nfs_pgio_header *(*rw_alloc_header)(void);
 	void (*rw_free_header)(struct nfs_pgio_header *);
-	void (*rw_release)(struct nfs_pgio_header *);
 	int  (*rw_done)(struct rpc_task *, struct nfs_pgio_header *,
 			struct inode *);
 	void (*rw_result)(struct rpc_task *, struct nfs_pgio_header *);
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 93ab607..7bbe505 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -316,6 +316,49 @@
 	int rpc_status;
 };
 
+#define PNFS_LAYOUTSTATS_MAXSIZE 256
+
+struct nfs42_layoutstat_args;
+struct nfs42_layoutstat_devinfo;
+typedef	void (*layoutstats_encode_t)(struct xdr_stream *,
+		struct nfs42_layoutstat_args *,
+		struct nfs42_layoutstat_devinfo *);
+
+/* Per file per deviceid layoutstats */
+struct nfs42_layoutstat_devinfo {
+	struct nfs4_deviceid dev_id;
+	__u64 offset;
+	__u64 length;
+	__u64 read_count;
+	__u64 read_bytes;
+	__u64 write_count;
+	__u64 write_bytes;
+	__u32 layout_type;
+	layoutstats_encode_t layoutstats_encode;
+	void *layout_private;
+};
+
+struct nfs42_layoutstat_args {
+	struct nfs4_sequence_args seq_args;
+	struct nfs_fh *fh;
+	struct inode *inode;
+	nfs4_stateid stateid;
+	int num_dev;
+	struct nfs42_layoutstat_devinfo *devinfo;
+};
+
+struct nfs42_layoutstat_res {
+	struct nfs4_sequence_res seq_res;
+	int num_dev;
+	int rpc_status;
+};
+
+struct nfs42_layoutstat_data {
+	struct inode *inode;
+	struct nfs42_layoutstat_args args;
+	struct nfs42_layoutstat_res res;
+};
+
 struct stateowner_id {
 	__u64	create_time;
 	__u32	uniquifier;
@@ -984,17 +1027,14 @@
 	struct nfs4_sequence_res	seq_res;
 };
 
-#define NFS4_SETCLIENTID_NAMELEN	(127)
 struct nfs4_setclientid {
 	const nfs4_verifier *		sc_verifier;
-	unsigned int			sc_name_len;
-	char				sc_name[NFS4_SETCLIENTID_NAMELEN + 1];
 	u32				sc_prog;
 	unsigned int			sc_netid_len;
 	char				sc_netid[RPCBIND_MAXNETIDLEN + 1];
 	unsigned int			sc_uaddr_len;
 	char				sc_uaddr[RPCBIND_MAXUADDRLEN + 1];
-	u32				sc_cb_ident;
+	struct nfs_client		*sc_clnt;
 	struct rpc_cred			*sc_cred;
 };
 
@@ -1142,12 +1182,9 @@
 	struct nfs4_op_map allow;
 };
 
-#define NFS4_EXCHANGE_ID_LEN	(48)
 struct nfs41_exchange_id_args {
 	struct nfs_client		*client;
 	nfs4_verifier			*verifier;
-	unsigned int 			id_len;
-	char 				id[NFS4_EXCHANGE_ID_LEN];
 	u32				flags;
 	struct nfs41_state_protection	state_protect;
 };
diff --git a/include/linux/ntb.h b/include/linux/ntb.h
index 9ac1a62..b02f72b 100644
--- a/include/linux/ntb.h
+++ b/include/linux/ntb.h
@@ -4,15 +4,20 @@
  *
  *   GPL LICENSE SUMMARY
  *
- *   Copyright(c) 2012 Intel Corporation. All rights reserved.
+ *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
  *
  *   This program is free software; you can redistribute it and/or modify
  *   it under the terms of version 2 of the GNU General Public License as
  *   published by the Free Software Foundation.
  *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *   General Public License for more details.
+ *
  *   BSD LICENSE
  *
- *   Copyright(c) 2012 Intel Corporation. All rights reserved.
+ *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
  *
  *   Redistribution and use in source and binary forms, with or without
  *   modification, are permitted provided that the following conditions
@@ -40,49 +45,940 @@
  *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
  *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
- * Intel PCIe NTB Linux driver
+ * PCIe NTB Linux driver
  *
  * Contact Information:
- * Jon Mason <jon.mason@intel.com>
+ * Allen Hubbe <Allen.Hubbe@emc.com>
  */
 
-struct ntb_transport_qp;
+#ifndef _NTB_H_
+#define _NTB_H_
 
+#include <linux/completion.h>
+#include <linux/device.h>
+
+struct ntb_client;
+struct ntb_dev;
+struct pci_dev;
+
+/**
+ * enum ntb_topo - NTB connection topology
+ * @NTB_TOPO_NONE:	Topology is unknown or invalid.
+ * @NTB_TOPO_PRI:	On primary side of local ntb.
+ * @NTB_TOPO_SEC:	On secondary side of remote ntb.
+ * @NTB_TOPO_B2B_USD:	On primary side of local ntb upstream of remote ntb.
+ * @NTB_TOPO_B2B_DSD:	On primary side of local ntb downstream of remote ntb.
+ */
+enum ntb_topo {
+	NTB_TOPO_NONE = -1,
+	NTB_TOPO_PRI,
+	NTB_TOPO_SEC,
+	NTB_TOPO_B2B_USD,
+	NTB_TOPO_B2B_DSD,
+};
+
+static inline int ntb_topo_is_b2b(enum ntb_topo topo)
+{
+	switch ((int)topo) {
+	case NTB_TOPO_B2B_USD:
+	case NTB_TOPO_B2B_DSD:
+		return 1;
+	}
+	return 0;
+}
+
+static inline char *ntb_topo_string(enum ntb_topo topo)
+{
+	switch (topo) {
+	case NTB_TOPO_NONE:	return "NTB_TOPO_NONE";
+	case NTB_TOPO_PRI:	return "NTB_TOPO_PRI";
+	case NTB_TOPO_SEC:	return "NTB_TOPO_SEC";
+	case NTB_TOPO_B2B_USD:	return "NTB_TOPO_B2B_USD";
+	case NTB_TOPO_B2B_DSD:	return "NTB_TOPO_B2B_DSD";
+	}
+	return "NTB_TOPO_INVALID";
+}
+
+/**
+ * enum ntb_speed - NTB link training speed
+ * @NTB_SPEED_AUTO:	Request the max supported speed.
+ * @NTB_SPEED_NONE:	Link is not trained to any speed.
+ * @NTB_SPEED_GEN1:	Link is trained to gen1 speed.
+ * @NTB_SPEED_GEN2:	Link is trained to gen2 speed.
+ * @NTB_SPEED_GEN3:	Link is trained to gen3 speed.
+ */
+enum ntb_speed {
+	NTB_SPEED_AUTO = -1,
+	NTB_SPEED_NONE = 0,
+	NTB_SPEED_GEN1 = 1,
+	NTB_SPEED_GEN2 = 2,
+	NTB_SPEED_GEN3 = 3,
+};
+
+/**
+ * enum ntb_width - NTB link training width
+ * @NTB_WIDTH_AUTO:	Request the max supported width.
+ * @NTB_WIDTH_NONE:	Link is not trained to any width.
+ * @NTB_WIDTH_1:	Link is trained to 1 lane width.
+ * @NTB_WIDTH_2:	Link is trained to 2 lane width.
+ * @NTB_WIDTH_4:	Link is trained to 4 lane width.
+ * @NTB_WIDTH_8:	Link is trained to 8 lane width.
+ * @NTB_WIDTH_12:	Link is trained to 12 lane width.
+ * @NTB_WIDTH_16:	Link is trained to 16 lane width.
+ * @NTB_WIDTH_32:	Link is trained to 32 lane width.
+ */
+enum ntb_width {
+	NTB_WIDTH_AUTO = -1,
+	NTB_WIDTH_NONE = 0,
+	NTB_WIDTH_1 = 1,
+	NTB_WIDTH_2 = 2,
+	NTB_WIDTH_4 = 4,
+	NTB_WIDTH_8 = 8,
+	NTB_WIDTH_12 = 12,
+	NTB_WIDTH_16 = 16,
+	NTB_WIDTH_32 = 32,
+};
+
+/**
+ * struct ntb_client_ops - ntb client operations
+ * @probe:		Notify client of a new device.
+ * @remove:		Notify client to remove a device.
+ */
+struct ntb_client_ops {
+	int (*probe)(struct ntb_client *client, struct ntb_dev *ntb);
+	void (*remove)(struct ntb_client *client, struct ntb_dev *ntb);
+};
+
+static inline int ntb_client_ops_is_valid(const struct ntb_client_ops *ops)
+{
+	/* commented callbacks are not required: */
+	return
+		ops->probe			&&
+		ops->remove			&&
+		1;
+}
+
+/**
+ * struct ntb_ctx_ops - ntb driver context operations
+ * @link_event:		See ntb_link_event().
+ * @db_event:		See ntb_db_event().
+ */
+struct ntb_ctx_ops {
+	void (*link_event)(void *ctx);
+	void (*db_event)(void *ctx, int db_vector);
+};
+
+static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops)
+{
+	/* commented callbacks are not required: */
+	return
+		/* ops->link_event		&& */
+		/* ops->db_event		&& */
+		1;
+}
+
+/**
+ * struct ntb_ctx_ops - ntb device operations
+ * @mw_count:		See ntb_mw_count().
+ * @mw_get_range:	See ntb_mw_get_range().
+ * @mw_set_trans:	See ntb_mw_set_trans().
+ * @mw_clear_trans:	See ntb_mw_clear_trans().
+ * @link_is_up:		See ntb_link_is_up().
+ * @link_enable:	See ntb_link_enable().
+ * @link_disable:	See ntb_link_disable().
+ * @db_is_unsafe:	See ntb_db_is_unsafe().
+ * @db_valid_mask:	See ntb_db_valid_mask().
+ * @db_vector_count:	See ntb_db_vector_count().
+ * @db_vector_mask:	See ntb_db_vector_mask().
+ * @db_read:		See ntb_db_read().
+ * @db_set:		See ntb_db_set().
+ * @db_clear:		See ntb_db_clear().
+ * @db_read_mask:	See ntb_db_read_mask().
+ * @db_set_mask:	See ntb_db_set_mask().
+ * @db_clear_mask:	See ntb_db_clear_mask().
+ * @peer_db_addr:	See ntb_peer_db_addr().
+ * @peer_db_read:	See ntb_peer_db_read().
+ * @peer_db_set:	See ntb_peer_db_set().
+ * @peer_db_clear:	See ntb_peer_db_clear().
+ * @peer_db_read_mask:	See ntb_peer_db_read_mask().
+ * @peer_db_set_mask:	See ntb_peer_db_set_mask().
+ * @peer_db_clear_mask:	See ntb_peer_db_clear_mask().
+ * @spad_is_unsafe:	See ntb_spad_is_unsafe().
+ * @spad_count:		See ntb_spad_count().
+ * @spad_read:		See ntb_spad_read().
+ * @spad_write:		See ntb_spad_write().
+ * @peer_spad_addr:	See ntb_peer_spad_addr().
+ * @peer_spad_read:	See ntb_peer_spad_read().
+ * @peer_spad_write:	See ntb_peer_spad_write().
+ */
+struct ntb_dev_ops {
+	int (*mw_count)(struct ntb_dev *ntb);
+	int (*mw_get_range)(struct ntb_dev *ntb, int idx,
+			    phys_addr_t *base, resource_size_t *size,
+			resource_size_t *align, resource_size_t *align_size);
+	int (*mw_set_trans)(struct ntb_dev *ntb, int idx,
+			    dma_addr_t addr, resource_size_t size);
+	int (*mw_clear_trans)(struct ntb_dev *ntb, int idx);
+
+	int (*link_is_up)(struct ntb_dev *ntb,
+			  enum ntb_speed *speed, enum ntb_width *width);
+	int (*link_enable)(struct ntb_dev *ntb,
+			   enum ntb_speed max_speed, enum ntb_width max_width);
+	int (*link_disable)(struct ntb_dev *ntb);
+
+	int (*db_is_unsafe)(struct ntb_dev *ntb);
+	u64 (*db_valid_mask)(struct ntb_dev *ntb);
+	int (*db_vector_count)(struct ntb_dev *ntb);
+	u64 (*db_vector_mask)(struct ntb_dev *ntb, int db_vector);
+
+	u64 (*db_read)(struct ntb_dev *ntb);
+	int (*db_set)(struct ntb_dev *ntb, u64 db_bits);
+	int (*db_clear)(struct ntb_dev *ntb, u64 db_bits);
+
+	u64 (*db_read_mask)(struct ntb_dev *ntb);
+	int (*db_set_mask)(struct ntb_dev *ntb, u64 db_bits);
+	int (*db_clear_mask)(struct ntb_dev *ntb, u64 db_bits);
+
+	int (*peer_db_addr)(struct ntb_dev *ntb,
+			    phys_addr_t *db_addr, resource_size_t *db_size);
+	u64 (*peer_db_read)(struct ntb_dev *ntb);
+	int (*peer_db_set)(struct ntb_dev *ntb, u64 db_bits);
+	int (*peer_db_clear)(struct ntb_dev *ntb, u64 db_bits);
+
+	u64 (*peer_db_read_mask)(struct ntb_dev *ntb);
+	int (*peer_db_set_mask)(struct ntb_dev *ntb, u64 db_bits);
+	int (*peer_db_clear_mask)(struct ntb_dev *ntb, u64 db_bits);
+
+	int (*spad_is_unsafe)(struct ntb_dev *ntb);
+	int (*spad_count)(struct ntb_dev *ntb);
+
+	u32 (*spad_read)(struct ntb_dev *ntb, int idx);
+	int (*spad_write)(struct ntb_dev *ntb, int idx, u32 val);
+
+	int (*peer_spad_addr)(struct ntb_dev *ntb, int idx,
+			      phys_addr_t *spad_addr);
+	u32 (*peer_spad_read)(struct ntb_dev *ntb, int idx);
+	int (*peer_spad_write)(struct ntb_dev *ntb, int idx, u32 val);
+};
+
+static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops)
+{
+	/* commented callbacks are not required: */
+	return
+		ops->mw_count				&&
+		ops->mw_get_range			&&
+		ops->mw_set_trans			&&
+		/* ops->mw_clear_trans			&& */
+		ops->link_is_up				&&
+		ops->link_enable			&&
+		ops->link_disable			&&
+		/* ops->db_is_unsafe			&& */
+		ops->db_valid_mask			&&
+
+		/* both set, or both unset */
+		(!ops->db_vector_count == !ops->db_vector_mask) &&
+
+		ops->db_read				&&
+		/* ops->db_set				&& */
+		ops->db_clear				&&
+		/* ops->db_read_mask			&& */
+		ops->db_set_mask			&&
+		ops->db_clear_mask			&&
+		ops->peer_db_addr			&&
+		/* ops->peer_db_read			&& */
+		ops->peer_db_set			&&
+		/* ops->peer_db_clear			&& */
+		/* ops->peer_db_read_mask		&& */
+		/* ops->peer_db_set_mask		&& */
+		/* ops->peer_db_clear_mask		&& */
+		/* ops->spad_is_unsafe			&& */
+		ops->spad_count				&&
+		ops->spad_read				&&
+		ops->spad_write				&&
+		ops->peer_spad_addr			&&
+		/* ops->peer_spad_read			&& */
+		ops->peer_spad_write			&&
+		1;
+}
+
+/**
+ * struct ntb_client - client interested in ntb devices
+ * @drv:		Linux driver object.
+ * @ops:		See &ntb_client_ops.
+ */
 struct ntb_client {
-	struct device_driver driver;
-	int (*probe)(struct pci_dev *pdev);
-	void (*remove)(struct pci_dev *pdev);
+	struct device_driver		drv;
+	const struct ntb_client_ops	ops;
 };
 
-enum {
-	NTB_LINK_DOWN = 0,
-	NTB_LINK_UP,
+#define drv_ntb_client(__drv) container_of((__drv), struct ntb_client, drv)
+
+/**
+ * struct ntb_device - ntb device
+ * @dev:		Linux device object.
+ * @pdev:		Pci device entry of the ntb.
+ * @topo:		Detected topology of the ntb.
+ * @ops:		See &ntb_dev_ops.
+ * @ctx:		See &ntb_ctx_ops.
+ * @ctx_ops:		See &ntb_ctx_ops.
+ */
+struct ntb_dev {
+	struct device			dev;
+	struct pci_dev			*pdev;
+	enum ntb_topo			topo;
+	const struct ntb_dev_ops	*ops;
+	void				*ctx;
+	const struct ntb_ctx_ops	*ctx_ops;
+
+	/* private: */
+
+	/* synchronize setting, clearing, and calling ctx_ops */
+	spinlock_t			ctx_lock;
+	/* block unregister until device is fully released */
+	struct completion		released;
 };
 
-int ntb_register_client(struct ntb_client *drvr);
-void ntb_unregister_client(struct ntb_client *drvr);
-int ntb_register_client_dev(char *device_name);
-void ntb_unregister_client_dev(char *device_name);
+#define dev_ntb(__dev) container_of((__dev), struct ntb_dev, dev)
 
-struct ntb_queue_handlers {
-	void (*rx_handler)(struct ntb_transport_qp *qp, void *qp_data,
-			   void *data, int len);
-	void (*tx_handler)(struct ntb_transport_qp *qp, void *qp_data,
-			   void *data, int len);
-	void (*event_handler)(void *data, int status);
-};
+/**
+ * ntb_register_client() - register a client for interest in ntb devices
+ * @client:	Client context.
+ *
+ * The client will be added to the list of clients interested in ntb devices.
+ * The client will be notified of any ntb devices that are not already
+ * associated with a client, or if ntb devices are registered later.
+ *
+ * Return: Zero if the client is registered, otherwise an error number.
+ */
+#define ntb_register_client(client) \
+	__ntb_register_client((client), THIS_MODULE, KBUILD_MODNAME)
 
-unsigned char ntb_transport_qp_num(struct ntb_transport_qp *qp);
-unsigned int ntb_transport_max_size(struct ntb_transport_qp *qp);
-struct ntb_transport_qp *
-ntb_transport_create_queue(void *data, struct pci_dev *pdev,
-			   const struct ntb_queue_handlers *handlers);
-void ntb_transport_free_queue(struct ntb_transport_qp *qp);
-int ntb_transport_rx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data,
-			     unsigned int len);
-int ntb_transport_tx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data,
-			     unsigned int len);
-void *ntb_transport_rx_remove(struct ntb_transport_qp *qp, unsigned int *len);
-void ntb_transport_link_up(struct ntb_transport_qp *qp);
-void ntb_transport_link_down(struct ntb_transport_qp *qp);
-bool ntb_transport_link_query(struct ntb_transport_qp *qp);
+int __ntb_register_client(struct ntb_client *client, struct module *mod,
+			  const char *mod_name);
+
+/**
+ * ntb_unregister_client() - unregister a client for interest in ntb devices
+ * @client:	Client context.
+ *
+ * The client will be removed from the list of clients interested in ntb
+ * devices.  If any ntb devices are associated with the client, the client will
+ * be notified to remove those devices.
+ */
+void ntb_unregister_client(struct ntb_client *client);
+
+#define module_ntb_client(__ntb_client) \
+	module_driver(__ntb_client, ntb_register_client, \
+			ntb_unregister_client)
+
+/**
+ * ntb_register_device() - register a ntb device
+ * @ntb:	NTB device context.
+ *
+ * The device will be added to the list of ntb devices.  If any clients are
+ * interested in ntb devices, each client will be notified of the ntb device,
+ * until at most one client accepts the device.
+ *
+ * Return: Zero if the device is registered, otherwise an error number.
+ */
+int ntb_register_device(struct ntb_dev *ntb);
+
+/**
+ * ntb_register_device() - unregister a ntb device
+ * @ntb:	NTB device context.
+ *
+ * The device will be removed from the list of ntb devices.  If the ntb device
+ * is associated with a client, the client will be notified to remove the
+ * device.
+ */
+void ntb_unregister_device(struct ntb_dev *ntb);
+
+/**
+ * ntb_set_ctx() - associate a driver context with an ntb device
+ * @ntb:	NTB device context.
+ * @ctx:	Driver context.
+ * @ctx_ops:	Driver context operations.
+ *
+ * Associate a driver context and operations with a ntb device.  The context is
+ * provided by the client driver, and the driver may associate a different
+ * context with each ntb device.
+ *
+ * Return: Zero if the context is associated, otherwise an error number.
+ */
+int ntb_set_ctx(struct ntb_dev *ntb, void *ctx,
+		const struct ntb_ctx_ops *ctx_ops);
+
+/**
+ * ntb_clear_ctx() - disassociate any driver context from an ntb device
+ * @ntb:	NTB device context.
+ *
+ * Clear any association that may exist between a driver context and the ntb
+ * device.
+ */
+void ntb_clear_ctx(struct ntb_dev *ntb);
+
+/**
+ * ntb_link_event() - notify driver context of a change in link status
+ * @ntb:	NTB device context.
+ *
+ * Notify the driver context that the link status may have changed.  The driver
+ * should call ntb_link_is_up() to get the current status.
+ */
+void ntb_link_event(struct ntb_dev *ntb);
+
+/**
+ * ntb_db_event() - notify driver context of a doorbell event
+ * @ntb:	NTB device context.
+ * @vector:	Interrupt vector number.
+ *
+ * Notify the driver context of a doorbell event.  If hardware supports
+ * multiple interrupt vectors for doorbells, the vector number indicates which
+ * vector received the interrupt.  The vector number is relative to the first
+ * vector used for doorbells, starting at zero, and must be less than
+ ** ntb_db_vector_count().  The driver may call ntb_db_read() to check which
+ * doorbell bits need service, and ntb_db_vector_mask() to determine which of
+ * those bits are associated with the vector number.
+ */
+void ntb_db_event(struct ntb_dev *ntb, int vector);
+
+/**
+ * ntb_mw_count() - get the number of memory windows
+ * @ntb:	NTB device context.
+ *
+ * Hardware and topology may support a different number of memory windows.
+ *
+ * Return: the number of memory windows.
+ */
+static inline int ntb_mw_count(struct ntb_dev *ntb)
+{
+	return ntb->ops->mw_count(ntb);
+}
+
+/**
+ * ntb_mw_get_range() - get the range of a memory window
+ * @ntb:	NTB device context.
+ * @idx:	Memory window number.
+ * @base:	OUT - the base address for mapping the memory window
+ * @size:	OUT - the size for mapping the memory window
+ * @align:	OUT - the base alignment for translating the memory window
+ * @align_size:	OUT - the size alignment for translating the memory window
+ *
+ * Get the range of a memory window.  NULL may be given for any output
+ * parameter if the value is not needed.  The base and size may be used for
+ * mapping the memory window, to access the peer memory.  The alignment and
+ * size may be used for translating the memory window, for the peer to access
+ * memory on the local system.
+ *
+ * Return: Zero on success, otherwise an error number.
+ */
+static inline int ntb_mw_get_range(struct ntb_dev *ntb, int idx,
+				   phys_addr_t *base, resource_size_t *size,
+		resource_size_t *align, resource_size_t *align_size)
+{
+	return ntb->ops->mw_get_range(ntb, idx, base, size,
+			align, align_size);
+}
+
+/**
+ * ntb_mw_set_trans() - set the translation of a memory window
+ * @ntb:	NTB device context.
+ * @idx:	Memory window number.
+ * @addr:	The dma address local memory to expose to the peer.
+ * @size:	The size of the local memory to expose to the peer.
+ *
+ * Set the translation of a memory window.  The peer may access local memory
+ * through the window starting at the address, up to the size.  The address
+ * must be aligned to the alignment specified by ntb_mw_get_range().  The size
+ * must be aligned to the size alignment specified by ntb_mw_get_range().
+ *
+ * Return: Zero on success, otherwise an error number.
+ */
+static inline int ntb_mw_set_trans(struct ntb_dev *ntb, int idx,
+				   dma_addr_t addr, resource_size_t size)
+{
+	return ntb->ops->mw_set_trans(ntb, idx, addr, size);
+}
+
+/**
+ * ntb_mw_clear_trans() - clear the translation of a memory window
+ * @ntb:	NTB device context.
+ * @idx:	Memory window number.
+ *
+ * Clear the translation of a memory window.  The peer may no longer access
+ * local memory through the window.
+ *
+ * Return: Zero on success, otherwise an error number.
+ */
+static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int idx)
+{
+	if (!ntb->ops->mw_clear_trans)
+		return ntb->ops->mw_set_trans(ntb, idx, 0, 0);
+
+	return ntb->ops->mw_clear_trans(ntb, idx);
+}
+
+/**
+ * ntb_link_is_up() - get the current ntb link state
+ * @ntb:	NTB device context.
+ * @speed:	OUT - The link speed expressed as PCIe generation number.
+ * @width:	OUT - The link width expressed as the number of PCIe lanes.
+ *
+ * Set the translation of a memory window.  The peer may access local memory
+ * through the window starting at the address, up to the size.  The address
+ * must be aligned to the alignment specified by ntb_mw_get_range().  The size
+ * must be aligned to the size alignment specified by ntb_mw_get_range().
+ *
+ * Return: One if the link is up, zero if the link is down, otherwise a
+ *		negative value indicating the error number.
+ */
+static inline int ntb_link_is_up(struct ntb_dev *ntb,
+				 enum ntb_speed *speed, enum ntb_width *width)
+{
+	return ntb->ops->link_is_up(ntb, speed, width);
+}
+
+/**
+ * ntb_link_enable() - enable the link on the secondary side of the ntb
+ * @ntb:	NTB device context.
+ * @max_speed:	The maximum link speed expressed as PCIe generation number.
+ * @max_width:	The maximum link width expressed as the number of PCIe lanes.
+ *
+ * Enable the link on the secondary side of the ntb.  This can only be done
+ * from the primary side of the ntb in primary or b2b topology.  The ntb device
+ * should train the link to its maximum speed and width, or the requested speed
+ * and width, whichever is smaller, if supported.
+ *
+ * Return: Zero on success, otherwise an error number.
+ */
+static inline int ntb_link_enable(struct ntb_dev *ntb,
+				  enum ntb_speed max_speed,
+				  enum ntb_width max_width)
+{
+	return ntb->ops->link_enable(ntb, max_speed, max_width);
+}
+
+/**
+ * ntb_link_disable() - disable the link on the secondary side of the ntb
+ * @ntb:	NTB device context.
+ *
+ * Disable the link on the secondary side of the ntb.  This can only be
+ * done from the primary side of the ntb in primary or b2b topology.  The ntb
+ * device should disable the link.  Returning from this call must indicate that
+ * a barrier has passed, though with no more writes may pass in either
+ * direction across the link, except if this call returns an error number.
+ *
+ * Return: Zero on success, otherwise an error number.
+ */
+static inline int ntb_link_disable(struct ntb_dev *ntb)
+{
+	return ntb->ops->link_disable(ntb);
+}
+
+/**
+ * ntb_db_is_unsafe() - check if it is safe to use hardware doorbell
+ * @ntb:	NTB device context.
+ *
+ * It is possible for some ntb hardware to be affected by errata.  Hardware
+ * drivers can advise clients to avoid using doorbells.  Clients may ignore
+ * this advice, though caution is recommended.
+ *
+ * Return: Zero if it is safe to use doorbells, or One if it is not safe.
+ */
+static inline int ntb_db_is_unsafe(struct ntb_dev *ntb)
+{
+	if (!ntb->ops->db_is_unsafe)
+		return 0;
+
+	return ntb->ops->db_is_unsafe(ntb);
+}
+
+/**
+ * ntb_db_valid_mask() - get a mask of doorbell bits supported by the ntb
+ * @ntb:	NTB device context.
+ *
+ * Hardware may support different number or arrangement of doorbell bits.
+ *
+ * Return: A mask of doorbell bits supported by the ntb.
+ */
+static inline u64 ntb_db_valid_mask(struct ntb_dev *ntb)
+{
+	return ntb->ops->db_valid_mask(ntb);
+}
+
+/**
+ * ntb_db_vector_count() - get the number of doorbell interrupt vectors
+ * @ntb:	NTB device context.
+ *
+ * Hardware may support different number of interrupt vectors.
+ *
+ * Return: The number of doorbell interrupt vectors.
+ */
+static inline int ntb_db_vector_count(struct ntb_dev *ntb)
+{
+	if (!ntb->ops->db_vector_count)
+		return 1;
+
+	return ntb->ops->db_vector_count(ntb);
+}
+
+/**
+ * ntb_db_vector_mask() - get a mask of doorbell bits serviced by a vector
+ * @ntb:	NTB device context.
+ * @vector:	Doorbell vector number.
+ *
+ * Each interrupt vector may have a different number or arrangement of bits.
+ *
+ * Return: A mask of doorbell bits serviced by a vector.
+ */
+static inline u64 ntb_db_vector_mask(struct ntb_dev *ntb, int vector)
+{
+	if (!ntb->ops->db_vector_mask)
+		return ntb_db_valid_mask(ntb);
+
+	return ntb->ops->db_vector_mask(ntb, vector);
+}
+
+/**
+ * ntb_db_read() - read the local doorbell register
+ * @ntb:	NTB device context.
+ *
+ * Read the local doorbell register, and return the bits that are set.
+ *
+ * Return: The bits currently set in the local doorbell register.
+ */
+static inline u64 ntb_db_read(struct ntb_dev *ntb)
+{
+	return ntb->ops->db_read(ntb);
+}
+
+/**
+ * ntb_db_set() - set bits in the local doorbell register
+ * @ntb:	NTB device context.
+ * @db_bits:	Doorbell bits to set.
+ *
+ * Set bits in the local doorbell register, which may generate a local doorbell
+ * interrupt.  Bits that were already set must remain set.
+ *
+ * This is unusual, and hardware may not support it.
+ *
+ * Return: Zero on success, otherwise an error number.
+ */
+static inline int ntb_db_set(struct ntb_dev *ntb, u64 db_bits)
+{
+	if (!ntb->ops->db_set)
+		return -EINVAL;
+
+	return ntb->ops->db_set(ntb, db_bits);
+}
+
+/**
+ * ntb_db_clear() - clear bits in the local doorbell register
+ * @ntb:	NTB device context.
+ * @db_bits:	Doorbell bits to clear.
+ *
+ * Clear bits in the local doorbell register, arming the bits for the next
+ * doorbell.
+ *
+ * Return: Zero on success, otherwise an error number.
+ */
+static inline int ntb_db_clear(struct ntb_dev *ntb, u64 db_bits)
+{
+	return ntb->ops->db_clear(ntb, db_bits);
+}
+
+/**
+ * ntb_db_read_mask() - read the local doorbell mask
+ * @ntb:	NTB device context.
+ *
+ * Read the local doorbell mask register, and return the bits that are set.
+ *
+ * This is unusual, though hardware is likely to support it.
+ *
+ * Return: The bits currently set in the local doorbell mask register.
+ */
+static inline u64 ntb_db_read_mask(struct ntb_dev *ntb)
+{
+	if (!ntb->ops->db_read_mask)
+		return 0;
+
+	return ntb->ops->db_read_mask(ntb);
+}
+
+/**
+ * ntb_db_set_mask() - set bits in the local doorbell mask
+ * @ntb:	NTB device context.
+ * @db_bits:	Doorbell mask bits to set.
+ *
+ * Set bits in the local doorbell mask register, preventing doorbell interrupts
+ * from being generated for those doorbell bits.  Bits that were already set
+ * must remain set.
+ *
+ * Return: Zero on success, otherwise an error number.
+ */
+static inline int ntb_db_set_mask(struct ntb_dev *ntb, u64 db_bits)
+{
+	return ntb->ops->db_set_mask(ntb, db_bits);
+}
+
+/**
+ * ntb_db_clear_mask() - clear bits in the local doorbell mask
+ * @ntb:	NTB device context.
+ * @db_bits:	Doorbell bits to clear.
+ *
+ * Clear bits in the local doorbell mask register, allowing doorbell interrupts
+ * from being generated for those doorbell bits.  If a doorbell bit is already
+ * set at the time the mask is cleared, and the corresponding mask bit is
+ * changed from set to clear, then the ntb driver must ensure that
+ * ntb_db_event() is called.  If the hardware does not generate the interrupt
+ * on clearing the mask bit, then the driver must call ntb_db_event() anyway.
+ *
+ * Return: Zero on success, otherwise an error number.
+ */
+static inline int ntb_db_clear_mask(struct ntb_dev *ntb, u64 db_bits)
+{
+	return ntb->ops->db_clear_mask(ntb, db_bits);
+}
+
+/**
+ * ntb_peer_db_addr() - address and size of the peer doorbell register
+ * @ntb:	NTB device context.
+ * @db_addr:	OUT - The address of the peer doorbell register.
+ * @db_size:	OUT - The number of bytes to write the peer doorbell register.
+ *
+ * Return the address of the peer doorbell register.  This may be used, for
+ * example, by drivers that offload memory copy operations to a dma engine.
+ * The drivers may wish to ring the peer doorbell at the completion of memory
+ * copy operations.  For efficiency, and to simplify ordering of operations
+ * between the dma memory copies and the ringing doorbell, the driver may
+ * append one additional dma memory copy with the doorbell register as the
+ * destination, after the memory copy operations.
+ *
+ * Return: Zero on success, otherwise an error number.
+ */
+static inline int ntb_peer_db_addr(struct ntb_dev *ntb,
+				   phys_addr_t *db_addr,
+				   resource_size_t *db_size)
+{
+	return ntb->ops->peer_db_addr(ntb, db_addr, db_size);
+}
+
+/**
+ * ntb_peer_db_read() - read the peer doorbell register
+ * @ntb:	NTB device context.
+ *
+ * Read the peer doorbell register, and return the bits that are set.
+ *
+ * This is unusual, and hardware may not support it.
+ *
+ * Return: The bits currently set in the peer doorbell register.
+ */
+static inline u64 ntb_peer_db_read(struct ntb_dev *ntb)
+{
+	if (!ntb->ops->peer_db_read)
+		return 0;
+
+	return ntb->ops->peer_db_read(ntb);
+}
+
+/**
+ * ntb_peer_db_set() - set bits in the peer doorbell register
+ * @ntb:	NTB device context.
+ * @db_bits:	Doorbell bits to set.
+ *
+ * Set bits in the peer doorbell register, which may generate a peer doorbell
+ * interrupt.  Bits that were already set must remain set.
+ *
+ * Return: Zero on success, otherwise an error number.
+ */
+static inline int ntb_peer_db_set(struct ntb_dev *ntb, u64 db_bits)
+{
+	return ntb->ops->peer_db_set(ntb, db_bits);
+}
+
+/**
+ * ntb_peer_db_clear() - clear bits in the local doorbell register
+ * @ntb:	NTB device context.
+ * @db_bits:	Doorbell bits to clear.
+ *
+ * Clear bits in the peer doorbell register, arming the bits for the next
+ * doorbell.
+ *
+ * This is unusual, and hardware may not support it.
+ *
+ * Return: Zero on success, otherwise an error number.
+ */
+static inline int ntb_peer_db_clear(struct ntb_dev *ntb, u64 db_bits)
+{
+	if (!ntb->ops->db_clear)
+		return -EINVAL;
+
+	return ntb->ops->peer_db_clear(ntb, db_bits);
+}
+
+/**
+ * ntb_peer_db_read_mask() - read the peer doorbell mask
+ * @ntb:	NTB device context.
+ *
+ * Read the peer doorbell mask register, and return the bits that are set.
+ *
+ * This is unusual, and hardware may not support it.
+ *
+ * Return: The bits currently set in the peer doorbell mask register.
+ */
+static inline u64 ntb_peer_db_read_mask(struct ntb_dev *ntb)
+{
+	if (!ntb->ops->db_read_mask)
+		return 0;
+
+	return ntb->ops->peer_db_read_mask(ntb);
+}
+
+/**
+ * ntb_peer_db_set_mask() - set bits in the peer doorbell mask
+ * @ntb:	NTB device context.
+ * @db_bits:	Doorbell mask bits to set.
+ *
+ * Set bits in the peer doorbell mask register, preventing doorbell interrupts
+ * from being generated for those doorbell bits.  Bits that were already set
+ * must remain set.
+ *
+ * This is unusual, and hardware may not support it.
+ *
+ * Return: Zero on success, otherwise an error number.
+ */
+static inline int ntb_peer_db_set_mask(struct ntb_dev *ntb, u64 db_bits)
+{
+	if (!ntb->ops->db_set_mask)
+		return -EINVAL;
+
+	return ntb->ops->peer_db_set_mask(ntb, db_bits);
+}
+
+/**
+ * ntb_peer_db_clear_mask() - clear bits in the peer doorbell mask
+ * @ntb:	NTB device context.
+ * @db_bits:	Doorbell bits to clear.
+ *
+ * Clear bits in the peer doorbell mask register, allowing doorbell interrupts
+ * from being generated for those doorbell bits.  If the hardware does not
+ * generate the interrupt on clearing the mask bit, then the driver should not
+ * implement this function!
+ *
+ * This is unusual, and hardware may not support it.
+ *
+ * Return: Zero on success, otherwise an error number.
+ */
+static inline int ntb_peer_db_clear_mask(struct ntb_dev *ntb, u64 db_bits)
+{
+	if (!ntb->ops->db_clear_mask)
+		return -EINVAL;
+
+	return ntb->ops->peer_db_clear_mask(ntb, db_bits);
+}
+
+/**
+ * ntb_spad_is_unsafe() - check if it is safe to use the hardware scratchpads
+ * @ntb:	NTB device context.
+ *
+ * It is possible for some ntb hardware to be affected by errata.  Hardware
+ * drivers can advise clients to avoid using scratchpads.  Clients may ignore
+ * this advice, though caution is recommended.
+ *
+ * Return: Zero if it is safe to use scratchpads, or One if it is not safe.
+ */
+static inline int ntb_spad_is_unsafe(struct ntb_dev *ntb)
+{
+	if (!ntb->ops->spad_is_unsafe)
+		return 0;
+
+	return ntb->ops->spad_is_unsafe(ntb);
+}
+
+/**
+ * ntb_mw_count() - get the number of scratchpads
+ * @ntb:	NTB device context.
+ *
+ * Hardware and topology may support a different number of scratchpads.
+ *
+ * Return: the number of scratchpads.
+ */
+static inline int ntb_spad_count(struct ntb_dev *ntb)
+{
+	return ntb->ops->spad_count(ntb);
+}
+
+/**
+ * ntb_spad_read() - read the local scratchpad register
+ * @ntb:	NTB device context.
+ * @idx:	Scratchpad index.
+ *
+ * Read the local scratchpad register, and return the value.
+ *
+ * Return: The value of the local scratchpad register.
+ */
+static inline u32 ntb_spad_read(struct ntb_dev *ntb, int idx)
+{
+	return ntb->ops->spad_read(ntb, idx);
+}
+
+/**
+ * ntb_spad_write() - write the local scratchpad register
+ * @ntb:	NTB device context.
+ * @idx:	Scratchpad index.
+ * @val:	Scratchpad value.
+ *
+ * Write the value to the local scratchpad register.
+ *
+ * Return: Zero on success, otherwise an error number.
+ */
+static inline int ntb_spad_write(struct ntb_dev *ntb, int idx, u32 val)
+{
+	return ntb->ops->spad_write(ntb, idx, val);
+}
+
+/**
+ * ntb_peer_spad_addr() - address of the peer scratchpad register
+ * @ntb:	NTB device context.
+ * @idx:	Scratchpad index.
+ * @spad_addr:	OUT - The address of the peer scratchpad register.
+ *
+ * Return the address of the peer doorbell register.  This may be used, for
+ * example, by drivers that offload memory copy operations to a dma engine.
+ *
+ * Return: Zero on success, otherwise an error number.
+ */
+static inline int ntb_peer_spad_addr(struct ntb_dev *ntb, int idx,
+				     phys_addr_t *spad_addr)
+{
+	return ntb->ops->peer_spad_addr(ntb, idx, spad_addr);
+}
+
+/**
+ * ntb_peer_spad_read() - read the peer scratchpad register
+ * @ntb:	NTB device context.
+ * @idx:	Scratchpad index.
+ *
+ * Read the peer scratchpad register, and return the value.
+ *
+ * Return: The value of the local scratchpad register.
+ */
+static inline u32 ntb_peer_spad_read(struct ntb_dev *ntb, int idx)
+{
+	return ntb->ops->peer_spad_read(ntb, idx);
+}
+
+/**
+ * ntb_peer_spad_write() - write the peer scratchpad register
+ * @ntb:	NTB device context.
+ * @idx:	Scratchpad index.
+ * @val:	Scratchpad value.
+ *
+ * Write the value to the peer scratchpad register.
+ *
+ * Return: Zero on success, otherwise an error number.
+ */
+static inline int ntb_peer_spad_write(struct ntb_dev *ntb, int idx, u32 val)
+{
+	return ntb->ops->peer_spad_write(ntb, idx, val);
+}
+
+#endif
diff --git a/include/linux/ntb_transport.h b/include/linux/ntb_transport.h
new file mode 100644
index 0000000..2862861
--- /dev/null
+++ b/include/linux/ntb_transport.h
@@ -0,0 +1,85 @@
+/*
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ *   redistributing this file, you may do so under either license.
+ *
+ *   GPL LICENSE SUMMARY
+ *
+ *   Copyright(c) 2012 Intel Corporation. All rights reserved.
+ *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of version 2 of the GNU General Public License as
+ *   published by the Free Software Foundation.
+ *
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2012 Intel Corporation. All rights reserved.
+ *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copy
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of Intel Corporation nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * PCIe NTB Transport Linux driver
+ *
+ * Contact Information:
+ * Jon Mason <jon.mason@intel.com>
+ */
+
+struct ntb_transport_qp;
+
+struct ntb_transport_client {
+	struct device_driver driver;
+	int (*probe)(struct device *client_dev);
+	void (*remove)(struct device *client_dev);
+};
+
+int ntb_transport_register_client(struct ntb_transport_client *drvr);
+void ntb_transport_unregister_client(struct ntb_transport_client *drvr);
+int ntb_transport_register_client_dev(char *device_name);
+void ntb_transport_unregister_client_dev(char *device_name);
+
+struct ntb_queue_handlers {
+	void (*rx_handler)(struct ntb_transport_qp *qp, void *qp_data,
+			   void *data, int len);
+	void (*tx_handler)(struct ntb_transport_qp *qp, void *qp_data,
+			   void *data, int len);
+	void (*event_handler)(void *data, int status);
+};
+
+unsigned char ntb_transport_qp_num(struct ntb_transport_qp *qp);
+unsigned int ntb_transport_max_size(struct ntb_transport_qp *qp);
+struct ntb_transport_qp *
+ntb_transport_create_queue(void *data, struct device *client_dev,
+			   const struct ntb_queue_handlers *handlers);
+void ntb_transport_free_queue(struct ntb_transport_qp *qp);
+int ntb_transport_rx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data,
+			     unsigned int len);
+int ntb_transport_tx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data,
+			     unsigned int len);
+void *ntb_transport_rx_remove(struct ntb_transport_qp *qp, unsigned int *len);
+void ntb_transport_link_up(struct ntb_transport_qp *qp);
+void ntb_transport_link_down(struct ntb_transport_qp *qp);
+bool ntb_transport_link_query(struct ntb_transport_qp *qp);
diff --git a/include/linux/of.h b/include/linux/of.h
index b871ff9..edc068d 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -120,6 +120,12 @@
 extern struct device_node *of_stdout;
 extern raw_spinlock_t devtree_lock;
 
+/* flag descriptions (need to be visible even when !CONFIG_OF) */
+#define OF_DYNAMIC	1 /* node and properties were allocated via kmalloc */
+#define OF_DETACHED	2 /* node has been detached from the device tree */
+#define OF_POPULATED	3 /* device already created for the node */
+#define OF_POPULATED_BUS	4 /* of_platform_populate recursed to children of this node */
+
 #ifdef CONFIG_OF
 void of_core_init(void);
 
@@ -128,7 +134,7 @@
 	return fwnode && fwnode->type == FWNODE_OF;
 }
 
-static inline struct device_node *of_node(struct fwnode_handle *fwnode)
+static inline struct device_node *to_of_node(struct fwnode_handle *fwnode)
 {
 	return fwnode ? container_of(fwnode, struct device_node, fwnode) : NULL;
 }
@@ -219,12 +225,6 @@
 #define of_node_cmp(s1, s2)		strcasecmp((s1), (s2))
 #endif
 
-/* flag descriptions */
-#define OF_DYNAMIC	1 /* node and properties were allocated via kmalloc */
-#define OF_DETACHED	2 /* node has been detached from the device tree */
-#define OF_POPULATED	3 /* device already created for the node */
-#define OF_POPULATED_BUS	4 /* of_platform_populate recursed to children of this node */
-
 #define OF_IS_DYNAMIC(x) test_bit(OF_DYNAMIC, &x->_flags)
 #define OF_MARK_DYNAMIC(x) set_bit(OF_DYNAMIC, &x->_flags)
 
@@ -387,7 +387,7 @@
 	return false;
 }
 
-static inline struct device_node *of_node(struct fwnode_handle *fwnode)
+static inline struct device_node *to_of_node(struct fwnode_handle *fwnode)
 {
 	return NULL;
 }
@@ -428,6 +428,11 @@
 	return NULL;
 }
 
+static inline struct device_node *of_find_node_by_phandle(phandle handle)
+{
+	return NULL;
+}
+
 static inline struct device_node *of_get_parent(const struct device_node *node)
 {
 	return NULL;
@@ -673,7 +678,10 @@
 #if defined(CONFIG_OF) && defined(CONFIG_NUMA)
 extern int of_node_to_nid(struct device_node *np);
 #else
-static inline int of_node_to_nid(struct device_node *device) { return 0; }
+static inline int of_node_to_nid(struct device_node *device)
+{
+	return NUMA_NO_NODE;
+}
 #endif
 
 static inline struct device_node *of_find_matching_node(
@@ -821,7 +829,7 @@
  * @propname:	name of the property to be searched.
  *
  * Search for a property in a device node.
- * Returns true if the property exist false otherwise.
+ * Returns true if the property exists false otherwise.
  */
 static inline bool of_property_read_bool(const struct device_node *np,
 					 const char *propname)
diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index 22801b1..4c50854 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -33,6 +33,8 @@
 extern int of_device_register(struct platform_device *ofdev);
 extern void of_device_unregister(struct platform_device *ofdev);
 
+extern const void *of_device_get_match_data(const struct device *dev);
+
 extern ssize_t of_device_get_modalias(struct device *dev,
 					char *str, ssize_t len);
 
@@ -65,6 +67,11 @@
 static inline void of_device_uevent(struct device *dev,
 			struct kobj_uevent_env *env) { }
 
+static inline const void *of_device_get_match_data(const struct device *dev)
+{
+	return NULL;
+}
+
 static inline int of_device_get_modalias(struct device *dev,
 				   char *str, ssize_t len)
 {
diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h
index fd627a5..df9ef38 100644
--- a/include/linux/of_fdt.h
+++ b/include/linux/of_fdt.h
@@ -37,7 +37,7 @@
 				 unsigned long node);
 extern int of_fdt_match(const void *blob, unsigned long node,
 			const char *const *compat);
-extern void of_fdt_unflatten_tree(unsigned long *blob,
+extern void of_fdt_unflatten_tree(const unsigned long *blob,
 			       struct device_node **mynodes);
 
 /* TBD: Temporary export of fdt globals - remove when code fully merged */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index fb0814c..a6c78e0 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -671,4 +671,10 @@
 	return error;
 }
 
+static inline unsigned long dir_pages(struct inode *inode)
+{
+	return (unsigned long)(inode->i_size + PAGE_CACHE_SIZE - 1) >>
+			       PAGE_CACHE_SHIFT;
+}
+
 #endif /* _LINUX_PAGEMAP_H */
diff --git a/include/linux/platform_data/wkup_m3.h b/include/linux/platform_data/wkup_m3.h
new file mode 100644
index 0000000..3f1d77e
--- /dev/null
+++ b/include/linux/platform_data/wkup_m3.h
@@ -0,0 +1,30 @@
+/*
+ * TI Wakeup M3 remote processor platform data
+ *
+ * Copyright (C) 2014-2015 Texas Instruments, Inc.
+ *
+ * Dave Gerlach <d-gerlach@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _LINUX_PLATFORM_DATA_WKUP_M3_H
+#define _LINUX_PLATFORM_DATA_WKUP_M3_H
+
+struct platform_device;
+
+struct wkup_m3_platform_data {
+	const char *reset_name;
+
+	int (*assert_reset)(struct platform_device *pdev, const char *name);
+	int (*deassert_reset)(struct platform_device *pdev, const char *name);
+};
+
+#endif /* _LINUX_PLATFORM_DATA_WKUP_M3_H */
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index 58f1e75..bba08f4 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -222,6 +222,15 @@
 	module_driver(__platform_driver, platform_driver_register, \
 			platform_driver_unregister)
 
+/* builtin_platform_driver() - Helper macro for builtin drivers that
+ * don't do anything special in driver init.  This eliminates some
+ * boilerplate.  Each driver may only use this macro once, and
+ * calling it replaces device_initcall().  Note this is meant to be
+ * a parallel of module_platform_driver() above, but w/o _exit stuff.
+ */
+#define builtin_platform_driver(__platform_driver) \
+	builtin_driver(__platform_driver, platform_driver_register)
+
 /* module_platform_driver_probe() - Helper macro for drivers that don't do
  * anything special in module init/exit.  This eliminates a lot of
  * boilerplate.  Each module may only use this macro once, and
@@ -240,6 +249,20 @@
 } \
 module_exit(__platform_driver##_exit);
 
+/* builtin_platform_driver_probe() - Helper macro for drivers that don't do
+ * anything special in device init.  This eliminates some boilerplate.  Each
+ * driver may only use this macro once, and using it replaces device_initcall.
+ * This is meant to be a parallel of module_platform_driver_probe above, but
+ * without the __exit parts.
+ */
+#define builtin_platform_driver_probe(__platform_driver, __platform_probe) \
+static int __init __platform_driver##_init(void) \
+{ \
+	return platform_driver_probe(&(__platform_driver), \
+				     __platform_probe);    \
+} \
+device_initcall(__platform_driver##_init); \
+
 #define platform_create_bundle(driver, probe, res, n_res, data, size) \
 	__platform_create_bundle(driver, probe, res, n_res, data, size, THIS_MODULE)
 extern struct platform_device *__platform_create_bundle(
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 0f1534a..84991f1 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -293,6 +293,8 @@
 	struct preempt_ops *ops;
 };
 
+void preempt_notifier_inc(void);
+void preempt_notifier_dec(void);
 void preempt_notifier_register(struct preempt_notifier *notifier);
 void preempt_notifier_unregister(struct preempt_notifier *notifier);
 
diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h
index fb31765..830c499 100644
--- a/include/linux/rbtree.h
+++ b/include/linux/rbtree.h
@@ -31,6 +31,7 @@
 
 #include <linux/kernel.h>
 #include <linux/stddef.h>
+#include <linux/rcupdate.h>
 
 struct rb_node {
 	unsigned long  __rb_parent_color;
@@ -73,11 +74,11 @@
 extern struct rb_node *rb_next_postorder(const struct rb_node *);
 
 /* Fast replacement of a single node without remove/rebalance/add/rebalance */
-extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, 
+extern void rb_replace_node(struct rb_node *victim, struct rb_node *new,
 			    struct rb_root *root);
 
-static inline void rb_link_node(struct rb_node * node, struct rb_node * parent,
-				struct rb_node ** rb_link)
+static inline void rb_link_node(struct rb_node *node, struct rb_node *parent,
+				struct rb_node **rb_link)
 {
 	node->__rb_parent_color = (unsigned long)parent;
 	node->rb_left = node->rb_right = NULL;
@@ -85,6 +86,15 @@
 	*rb_link = node;
 }
 
+static inline void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent,
+				    struct rb_node **rb_link)
+{
+	node->__rb_parent_color = (unsigned long)parent;
+	node->rb_left = node->rb_right = NULL;
+
+	rcu_assign_pointer(*rb_link, node);
+}
+
 #define rb_entry_safe(ptr, type, member) \
 	({ typeof(ptr) ____ptr = (ptr); \
 	   ____ptr ? rb_entry(____ptr, type, member) : NULL; \
diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h
index 378c5ee..14d7b83 100644
--- a/include/linux/rbtree_augmented.h
+++ b/include/linux/rbtree_augmented.h
@@ -123,11 +123,11 @@
 {
 	if (parent) {
 		if (parent->rb_left == old)
-			parent->rb_left = new;
+			WRITE_ONCE(parent->rb_left, new);
 		else
-			parent->rb_right = new;
+			WRITE_ONCE(parent->rb_right, new);
 	} else
-		root->rb_node = new;
+		WRITE_ONCE(root->rb_node, new);
 }
 
 extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
@@ -137,7 +137,8 @@
 __rb_erase_augmented(struct rb_node *node, struct rb_root *root,
 		     const struct rb_augment_callbacks *augment)
 {
-	struct rb_node *child = node->rb_right, *tmp = node->rb_left;
+	struct rb_node *child = node->rb_right;
+	struct rb_node *tmp = node->rb_left;
 	struct rb_node *parent, *rebalance;
 	unsigned long pc;
 
@@ -167,6 +168,7 @@
 		tmp = parent;
 	} else {
 		struct rb_node *successor = child, *child2;
+
 		tmp = child->rb_left;
 		if (!tmp) {
 			/*
@@ -180,6 +182,7 @@
 			 */
 			parent = successor;
 			child2 = successor->rb_right;
+
 			augment->copy(node, successor);
 		} else {
 			/*
@@ -201,19 +204,23 @@
 				successor = tmp;
 				tmp = tmp->rb_left;
 			} while (tmp);
-			parent->rb_left = child2 = successor->rb_right;
-			successor->rb_right = child;
+			child2 = successor->rb_right;
+			WRITE_ONCE(parent->rb_left, child2);
+			WRITE_ONCE(successor->rb_right, child);
 			rb_set_parent(child, successor);
+
 			augment->copy(node, successor);
 			augment->propagate(parent, successor);
 		}
 
-		successor->rb_left = tmp = node->rb_left;
+		tmp = node->rb_left;
+		WRITE_ONCE(successor->rb_left, tmp);
 		rb_set_parent(tmp, successor);
 
 		pc = node->__rb_parent_color;
 		tmp = __rb_parent(pc);
 		__rb_change_child(node, successor, tmp, root);
+
 		if (child2) {
 			successor->__rb_parent_color = pc;
 			rb_set_parent_color(child2, parent, RB_BLACK);
diff --git a/include/linux/rbtree_latch.h b/include/linux/rbtree_latch.h
new file mode 100644
index 0000000..4f3432c
--- /dev/null
+++ b/include/linux/rbtree_latch.h
@@ -0,0 +1,212 @@
+/*
+ * Latched RB-trees
+ *
+ * Copyright (C) 2015 Intel Corp., Peter Zijlstra <peterz@infradead.org>
+ *
+ * Since RB-trees have non-atomic modifications they're not immediately suited
+ * for RCU/lockless queries. Even though we made RB-tree lookups non-fatal for
+ * lockless lookups; we cannot guarantee they return a correct result.
+ *
+ * The simplest solution is a seqlock + RB-tree, this will allow lockless
+ * lookups; but has the constraint (inherent to the seqlock) that read sides
+ * cannot nest in write sides.
+ *
+ * If we need to allow unconditional lookups (say as required for NMI context
+ * usage) we need a more complex setup; this data structure provides this by
+ * employing the latch technique -- see @raw_write_seqcount_latch -- to
+ * implement a latched RB-tree which does allow for unconditional lookups by
+ * virtue of always having (at least) one stable copy of the tree.
+ *
+ * However, while we have the guarantee that there is at all times one stable
+ * copy, this does not guarantee an iteration will not observe modifications.
+ * What might have been a stable copy at the start of the iteration, need not
+ * remain so for the duration of the iteration.
+ *
+ * Therefore, this does require a lockless RB-tree iteration to be non-fatal;
+ * see the comment in lib/rbtree.c. Note however that we only require the first
+ * condition -- not seeing partial stores -- because the latch thing isolates
+ * us from loops. If we were to interrupt a modification the lookup would be
+ * pointed at the stable tree and complete while the modification was halted.
+ */
+
+#ifndef RB_TREE_LATCH_H
+#define RB_TREE_LATCH_H
+
+#include <linux/rbtree.h>
+#include <linux/seqlock.h>
+
+struct latch_tree_node {
+	struct rb_node node[2];
+};
+
+struct latch_tree_root {
+	seqcount_t	seq;
+	struct rb_root	tree[2];
+};
+
+/**
+ * latch_tree_ops - operators to define the tree order
+ * @less: used for insertion; provides the (partial) order between two elements.
+ * @comp: used for lookups; provides the order between the search key and an element.
+ *
+ * The operators are related like:
+ *
+ *	comp(a->key,b) < 0  := less(a,b)
+ *	comp(a->key,b) > 0  := less(b,a)
+ *	comp(a->key,b) == 0 := !less(a,b) && !less(b,a)
+ *
+ * If these operators define a partial order on the elements we make no
+ * guarantee on which of the elements matching the key is found. See
+ * latch_tree_find().
+ */
+struct latch_tree_ops {
+	bool (*less)(struct latch_tree_node *a, struct latch_tree_node *b);
+	int  (*comp)(void *key,                 struct latch_tree_node *b);
+};
+
+static __always_inline struct latch_tree_node *
+__lt_from_rb(struct rb_node *node, int idx)
+{
+	return container_of(node, struct latch_tree_node, node[idx]);
+}
+
+static __always_inline void
+__lt_insert(struct latch_tree_node *ltn, struct latch_tree_root *ltr, int idx,
+	    bool (*less)(struct latch_tree_node *a, struct latch_tree_node *b))
+{
+	struct rb_root *root = &ltr->tree[idx];
+	struct rb_node **link = &root->rb_node;
+	struct rb_node *node = &ltn->node[idx];
+	struct rb_node *parent = NULL;
+	struct latch_tree_node *ltp;
+
+	while (*link) {
+		parent = *link;
+		ltp = __lt_from_rb(parent, idx);
+
+		if (less(ltn, ltp))
+			link = &parent->rb_left;
+		else
+			link = &parent->rb_right;
+	}
+
+	rb_link_node_rcu(node, parent, link);
+	rb_insert_color(node, root);
+}
+
+static __always_inline void
+__lt_erase(struct latch_tree_node *ltn, struct latch_tree_root *ltr, int idx)
+{
+	rb_erase(&ltn->node[idx], &ltr->tree[idx]);
+}
+
+static __always_inline struct latch_tree_node *
+__lt_find(void *key, struct latch_tree_root *ltr, int idx,
+	  int (*comp)(void *key, struct latch_tree_node *node))
+{
+	struct rb_node *node = rcu_dereference_raw(ltr->tree[idx].rb_node);
+	struct latch_tree_node *ltn;
+	int c;
+
+	while (node) {
+		ltn = __lt_from_rb(node, idx);
+		c = comp(key, ltn);
+
+		if (c < 0)
+			node = rcu_dereference_raw(node->rb_left);
+		else if (c > 0)
+			node = rcu_dereference_raw(node->rb_right);
+		else
+			return ltn;
+	}
+
+	return NULL;
+}
+
+/**
+ * latch_tree_insert() - insert @node into the trees @root
+ * @node: nodes to insert
+ * @root: trees to insert @node into
+ * @ops: operators defining the node order
+ *
+ * It inserts @node into @root in an ordered fashion such that we can always
+ * observe one complete tree. See the comment for raw_write_seqcount_latch().
+ *
+ * The inserts use rcu_assign_pointer() to publish the element such that the
+ * tree structure is stored before we can observe the new @node.
+ *
+ * All modifications (latch_tree_insert, latch_tree_remove) are assumed to be
+ * serialized.
+ */
+static __always_inline void
+latch_tree_insert(struct latch_tree_node *node,
+		  struct latch_tree_root *root,
+		  const struct latch_tree_ops *ops)
+{
+	raw_write_seqcount_latch(&root->seq);
+	__lt_insert(node, root, 0, ops->less);
+	raw_write_seqcount_latch(&root->seq);
+	__lt_insert(node, root, 1, ops->less);
+}
+
+/**
+ * latch_tree_erase() - removes @node from the trees @root
+ * @node: nodes to remote
+ * @root: trees to remove @node from
+ * @ops: operators defining the node order
+ *
+ * Removes @node from the trees @root in an ordered fashion such that we can
+ * always observe one complete tree. See the comment for
+ * raw_write_seqcount_latch().
+ *
+ * It is assumed that @node will observe one RCU quiescent state before being
+ * reused of freed.
+ *
+ * All modifications (latch_tree_insert, latch_tree_remove) are assumed to be
+ * serialized.
+ */
+static __always_inline void
+latch_tree_erase(struct latch_tree_node *node,
+		 struct latch_tree_root *root,
+		 const struct latch_tree_ops *ops)
+{
+	raw_write_seqcount_latch(&root->seq);
+	__lt_erase(node, root, 0);
+	raw_write_seqcount_latch(&root->seq);
+	__lt_erase(node, root, 1);
+}
+
+/**
+ * latch_tree_find() - find the node matching @key in the trees @root
+ * @key: search key
+ * @root: trees to search for @key
+ * @ops: operators defining the node order
+ *
+ * Does a lockless lookup in the trees @root for the node matching @key.
+ *
+ * It is assumed that this is called while holding the appropriate RCU read
+ * side lock.
+ *
+ * If the operators define a partial order on the elements (there are multiple
+ * elements which have the same key value) it is undefined which of these
+ * elements will be found. Nor is it possible to iterate the tree to find
+ * further elements with the same key value.
+ *
+ * Returns: a pointer to the node matching @key or NULL.
+ */
+static __always_inline struct latch_tree_node *
+latch_tree_find(void *key, struct latch_tree_root *root,
+		const struct latch_tree_ops *ops)
+{
+	struct latch_tree_node *node;
+	unsigned int seq;
+
+	do {
+		seq = raw_read_seqcount_latch(&root->seq);
+		node = __lt_find(key, root, seq & 1, ops->comp);
+	} while (read_seqcount_retry(&root->seq, seq));
+
+	return node;
+}
+
+#endif /* RB_TREE_LATCH_H */
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 33a056b..4cf5f51 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -633,21 +633,6 @@
 #define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v)
 
 /**
- * lockless_dereference() - safely load a pointer for later dereference
- * @p: The pointer to load
- *
- * Similar to rcu_dereference(), but for situations where the pointed-to
- * object's lifetime is managed by something other than RCU.  That
- * "something other" might be reference counting or simple immortality.
- */
-#define lockless_dereference(p) \
-({ \
-	typeof(p) _________p1 = READ_ONCE(p); \
-	smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
-	(_________p1); \
-})
-
-/**
  * rcu_assign_pointer() - assign to RCU-protected pointer
  * @p: pointer to assign to
  * @v: value to assign (publish)
diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
index 78b8a9b..9c4e138 100644
--- a/include/linux/remoteproc.h
+++ b/include/linux/remoteproc.h
@@ -36,11 +36,11 @@
 #define REMOTEPROC_H
 
 #include <linux/types.h>
-#include <linux/klist.h>
 #include <linux/mutex.h>
 #include <linux/virtio.h>
 #include <linux/completion.h>
 #include <linux/idr.h>
+#include <linux/of.h>
 
 /**
  * struct resource_table - firmware resource table header
@@ -330,11 +330,13 @@
  * @start:	power on the device and boot it
  * @stop:	power off the device
  * @kick:	kick a virtqueue (virtqueue id given as a parameter)
+ * @da_to_va:	optional platform hook to perform address translations
  */
 struct rproc_ops {
 	int (*start)(struct rproc *rproc);
 	int (*stop)(struct rproc *rproc);
 	void (*kick)(struct rproc *rproc, int vqid);
+	void * (*da_to_va)(struct rproc *rproc, u64 da, int len);
 };
 
 /**
@@ -375,7 +377,7 @@
 
 /**
  * struct rproc - represents a physical remote processor device
- * @node: klist node of this rproc object
+ * @node: list node of this rproc object
  * @domain: iommu domain
  * @name: human readable name of the rproc
  * @firmware: name of firmware file to be loaded
@@ -407,7 +409,7 @@
  * @has_iommu: flag to indicate if remote processor is behind an MMU
  */
 struct rproc {
-	struct klist_node node;
+	struct list_head node;
 	struct iommu_domain *domain;
 	const char *name;
 	const char *firmware;
@@ -481,6 +483,7 @@
 	u32 rsc_offset;
 };
 
+struct rproc *rproc_get_by_phandle(phandle phandle);
 struct rproc *rproc_alloc(struct device *dev, const char *name,
 				const struct rproc_ops *ops,
 				const char *firmware, int len);
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index 50a8486..9b1ef0c 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -265,13 +265,16 @@
 	unsigned long offset, unsigned long size,
 	gfp_t gfp_mask);
 
+size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, void *buf,
+		      size_t buflen, off_t skip, bool to_buffer);
+
 size_t sg_copy_from_buffer(struct scatterlist *sgl, unsigned int nents,
-			   void *buf, size_t buflen);
+			   const void *buf, size_t buflen);
 size_t sg_copy_to_buffer(struct scatterlist *sgl, unsigned int nents,
 			 void *buf, size_t buflen);
 
 size_t sg_pcopy_from_buffer(struct scatterlist *sgl, unsigned int nents,
-			    void *buf, size_t buflen, off_t skip);
+			    const void *buf, size_t buflen, off_t skip);
 size_t sg_pcopy_to_buffer(struct scatterlist *sgl, unsigned int nents,
 			  void *buf, size_t buflen, off_t skip);
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8aa4a25..ae21f15 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -192,8 +192,6 @@
 #ifdef CONFIG_SCHED_DEBUG
 extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m);
 extern void proc_sched_set_task(struct task_struct *p);
-extern void
-print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
 #endif
 
 /*
@@ -838,7 +836,7 @@
 struct backing_dev_info;
 struct reclaim_state;
 
-#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
+#ifdef CONFIG_SCHED_INFO
 struct sched_info {
 	/* cumulative counters */
 	unsigned long pcount;	      /* # of times run on this cpu */
@@ -848,7 +846,7 @@
 	unsigned long long last_arrival,/* when we last ran on a cpu */
 			   last_queued;	/* when we were last queued to run */
 };
-#endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */
+#endif /* CONFIG_SCHED_INFO */
 
 #ifdef CONFIG_TASK_DELAY_ACCT
 struct task_delay_info {
@@ -1397,7 +1395,7 @@
 	int rcu_tasks_idle_cpu;
 #endif /* #ifdef CONFIG_TASKS_RCU */
 
-#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
+#ifdef CONFIG_SCHED_INFO
 	struct sched_info sched_info;
 #endif
 
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index afbb1fd..912a7c4 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -123,6 +123,7 @@
 __printf(2, 0) int seq_vprintf(struct seq_file *, const char *, va_list args);
 
 int seq_path(struct seq_file *, const struct path *, const char *);
+int seq_file_path(struct seq_file *, struct file *, const char *);
 int seq_dentry(struct seq_file *, struct dentry *, const char *);
 int seq_path_root(struct seq_file *m, const struct path *path,
 		  const struct path *root, const char *esc);
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 486e685..e058210 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -35,6 +35,7 @@
 #include <linux/spinlock.h>
 #include <linux/preempt.h>
 #include <linux/lockdep.h>
+#include <linux/compiler.h>
 #include <asm/processor.h>
 
 /*
@@ -274,9 +275,87 @@
 	s->sequence++;
 }
 
-/*
+static inline int raw_read_seqcount_latch(seqcount_t *s)
+{
+	return lockless_dereference(s->sequence);
+}
+
+/**
  * raw_write_seqcount_latch - redirect readers to even/odd copy
  * @s: pointer to seqcount_t
+ *
+ * The latch technique is a multiversion concurrency control method that allows
+ * queries during non-atomic modifications. If you can guarantee queries never
+ * interrupt the modification -- e.g. the concurrency is strictly between CPUs
+ * -- you most likely do not need this.
+ *
+ * Where the traditional RCU/lockless data structures rely on atomic
+ * modifications to ensure queries observe either the old or the new state the
+ * latch allows the same for non-atomic updates. The trade-off is doubling the
+ * cost of storage; we have to maintain two copies of the entire data
+ * structure.
+ *
+ * Very simply put: we first modify one copy and then the other. This ensures
+ * there is always one copy in a stable state, ready to give us an answer.
+ *
+ * The basic form is a data structure like:
+ *
+ * struct latch_struct {
+ *	seqcount_t		seq;
+ *	struct data_struct	data[2];
+ * };
+ *
+ * Where a modification, which is assumed to be externally serialized, does the
+ * following:
+ *
+ * void latch_modify(struct latch_struct *latch, ...)
+ * {
+ *	smp_wmb();	<- Ensure that the last data[1] update is visible
+ *	latch->seq++;
+ *	smp_wmb();	<- Ensure that the seqcount update is visible
+ *
+ *	modify(latch->data[0], ...);
+ *
+ *	smp_wmb();	<- Ensure that the data[0] update is visible
+ *	latch->seq++;
+ *	smp_wmb();	<- Ensure that the seqcount update is visible
+ *
+ *	modify(latch->data[1], ...);
+ * }
+ *
+ * The query will have a form like:
+ *
+ * struct entry *latch_query(struct latch_struct *latch, ...)
+ * {
+ *	struct entry *entry;
+ *	unsigned seq, idx;
+ *
+ *	do {
+ *		seq = lockless_dereference(latch->seq);
+ *
+ *		idx = seq & 0x01;
+ *		entry = data_query(latch->data[idx], ...);
+ *
+ *		smp_rmb();
+ *	} while (seq != latch->seq);
+ *
+ *	return entry;
+ * }
+ *
+ * So during the modification, queries are first redirected to data[1]. Then we
+ * modify data[0]. When that is complete, we redirect queries back to data[0]
+ * and we can modify data[1].
+ *
+ * NOTE: The non-requirement for atomic modifications does _NOT_ include
+ *       the publishing of new entries in the case where data is a dynamic
+ *       data structure.
+ *
+ *       An iteration might start in data[0] and get suspended long enough
+ *       to miss an entire modification sequence, once it resumes it might
+ *       observe the new entry.
+ *
+ * NOTE: When data is a dynamic data structure; one should use regular RCU
+ *       patterns to manage the lifetimes of the objects within.
  */
 static inline void raw_write_seqcount_latch(seqcount_t *s)
 {
diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h
index 2ca67b5..8df43c9f 100644
--- a/include/linux/sunrpc/bc_xprt.h
+++ b/include/linux/sunrpc/bc_xprt.h
@@ -37,7 +37,6 @@
 void xprt_free_bc_request(struct rpc_rqst *req);
 int xprt_setup_backchannel(struct rpc_xprt *, unsigned int min_reqs);
 void xprt_destroy_backchannel(struct rpc_xprt *, unsigned int max_reqs);
-int bc_send(struct rpc_rqst *req);
 
 /*
  * Determine if a shared backchannel is in use
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 598ba80..131032f 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -56,6 +56,7 @@
 	struct rpc_rtt *	cl_rtt;		/* RTO estimator data */
 	const struct rpc_timeout *cl_timeout;	/* Timeout strategy */
 
+	atomic_t		cl_swapper;	/* swapfile count */
 	int			cl_nodelen;	/* nodename length */
 	char 			cl_nodename[UNX_MAXNODENAME+1];
 	struct rpc_pipe_dir_head cl_pipedir_objects;
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 5f1e6bd..d703f0e 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -205,8 +205,7 @@
  */
 struct rpc_task *rpc_new_task(const struct rpc_task_setup *);
 struct rpc_task *rpc_run_task(const struct rpc_task_setup *);
-struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req,
-				const struct rpc_call_ops *ops);
+struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req);
 void		rpc_put_task(struct rpc_task *);
 void		rpc_put_task_async(struct rpc_task *);
 void		rpc_exit_task(struct rpc_task *);
@@ -269,4 +268,20 @@
 }
 #endif
 
+#if IS_ENABLED(CONFIG_SUNRPC_SWAP)
+int rpc_clnt_swap_activate(struct rpc_clnt *clnt);
+void rpc_clnt_swap_deactivate(struct rpc_clnt *clnt);
+#else
+static inline int
+rpc_clnt_swap_activate(struct rpc_clnt *clnt)
+{
+	return -EINVAL;
+}
+
+static inline void
+rpc_clnt_swap_deactivate(struct rpc_clnt *clnt)
+{
+}
+#endif /* CONFIG_SUNRPC_SWAP */
+
 #endif /* _LINUX_SUNRPC_SCHED_H_ */
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 8b93ef5..0fb9acb 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -133,6 +133,9 @@
 	void		(*close)(struct rpc_xprt *xprt);
 	void		(*destroy)(struct rpc_xprt *xprt);
 	void		(*print_stats)(struct rpc_xprt *xprt, struct seq_file *seq);
+	int		(*enable_swap)(struct rpc_xprt *xprt);
+	void		(*disable_swap)(struct rpc_xprt *xprt);
+	void		(*inject_disconnect)(struct rpc_xprt *xprt);
 };
 
 /*
@@ -180,7 +183,7 @@
 	atomic_t		num_reqs;	/* total slots */
 	unsigned long		state;		/* transport state */
 	unsigned char		resvport   : 1; /* use a reserved port */
-	unsigned int		swapper;	/* we're swapping over this
+	atomic_t		swapper;	/* we're swapping over this
 						   transport */
 	unsigned int		bind_index;	/* bind function index */
 
@@ -212,7 +215,8 @@
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
 	struct svc_serv		*bc_serv;       /* The RPC service which will */
 						/* process the callback */
-	unsigned int		bc_alloc_count;	/* Total number of preallocs */
+	int			bc_alloc_count;	/* Total number of preallocs */
+	atomic_t		bc_free_slots;
 	spinlock_t		bc_pa_lock;	/* Protects the preallocated
 						 * items */
 	struct list_head	bc_pa_list;	/* List of preallocated
@@ -241,6 +245,7 @@
 	const char		*address_strings[RPC_DISPLAY_MAX];
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	struct dentry		*debugfs;		/* debugfs directory */
+	atomic_t		inject_disconnect;
 #endif
 };
 
@@ -327,6 +332,18 @@
 	return p + xprt->tsh_size;
 }
 
+static inline int
+xprt_enable_swap(struct rpc_xprt *xprt)
+{
+	return xprt->ops->enable_swap(xprt);
+}
+
+static inline void
+xprt_disable_swap(struct rpc_xprt *xprt)
+{
+	xprt->ops->disable_swap(xprt);
+}
+
 /*
  * Transport switch helper functions
  */
@@ -345,7 +362,6 @@
 void			xprt_disconnect_done(struct rpc_xprt *xprt);
 void			xprt_force_disconnect(struct rpc_xprt *xprt);
 void			xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie);
-int			xs_swapper(struct rpc_xprt *xprt, int enable);
 
 bool			xprt_lock_connect(struct rpc_xprt *, struct rpc_task *, void *);
 void			xprt_unlock_connect(struct rpc_xprt *, void *);
@@ -431,6 +447,23 @@
 	return test_and_set_bit(XPRT_BINDING, &xprt->state);
 }
 
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
+extern unsigned int rpc_inject_disconnect;
+static inline void xprt_inject_disconnect(struct rpc_xprt *xprt)
+{
+	if (!rpc_inject_disconnect)
+		return;
+	if (atomic_dec_return(&xprt->inject_disconnect))
+		return;
+	atomic_set(&xprt->inject_disconnect, rpc_inject_disconnect);
+	xprt->ops->inject_disconnect(xprt);
+}
+#else
+static inline void xprt_inject_disconnect(struct rpc_xprt *xprt)
+{
+}
+#endif
+
 #endif /* __KERNEL__*/
 
 #endif /* _LINUX_SUNRPC_XPRT_H */
diff --git a/include/linux/sunrpc/xprtrdma.h b/include/linux/sunrpc/xprtrdma.h
index c984c85..b176130 100644
--- a/include/linux/sunrpc/xprtrdma.h
+++ b/include/linux/sunrpc/xprtrdma.h
@@ -56,7 +56,8 @@
 
 #define RPCRDMA_INLINE_PAD_THRESH  (512)/* payload threshold to pad (bytes) */
 
-/* memory registration strategies */
+/* Memory registration strategies, by number.
+ * This is part of a kernel / user space API. Do not remove. */
 enum rpcrdma_memreg {
 	RPCRDMA_BOUNCEBUFFERS = 0,
 	RPCRDMA_REGISTER,
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 795d5fe..fa7bc29 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -188,6 +188,9 @@
 void unregister_sysctl_table(struct ctl_table_header * table);
 
 extern int sysctl_init(void);
+
+extern struct ctl_table sysctl_mount_point[];
+
 #else /* CONFIG_SYSCTL */
 static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * table)
 {
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index 99382c0..9f65758 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -210,6 +210,10 @@
 int __must_check sysfs_move_dir_ns(struct kobject *kobj,
 				   struct kobject *new_parent_kobj,
 				   const void *new_ns);
+int __must_check sysfs_create_mount_point(struct kobject *parent_kobj,
+					  const char *name);
+void sysfs_remove_mount_point(struct kobject *parent_kobj,
+			      const char *name);
 
 int __must_check sysfs_create_file_ns(struct kobject *kobj,
 				      const struct attribute *attr,
@@ -298,6 +302,17 @@
 	return 0;
 }
 
+static inline int sysfs_create_mount_point(struct kobject *parent_kobj,
+					   const char *name)
+{
+	return 0;
+}
+
+static inline void sysfs_remove_mount_point(struct kobject *parent_kobj,
+					    const char *name)
+{
+}
+
 static inline int sysfs_create_file_ns(struct kobject *kobj,
 				       const struct attribute *attr,
 				       const void *ns)
diff --git a/include/linux/virtio_byteorder.h b/include/linux/virtio_byteorder.h
index 51865d0..ce63a2c 100644
--- a/include/linux/virtio_byteorder.h
+++ b/include/linux/virtio_byteorder.h
@@ -3,17 +3,21 @@
 #include <linux/types.h>
 #include <uapi/linux/virtio_types.h>
 
-/*
- * Low-level memory accessors for handling virtio in modern little endian and in
- * compatibility native endian format.
- */
+static inline bool virtio_legacy_is_little_endian(void)
+{
+#ifdef __LITTLE_ENDIAN
+	return true;
+#else
+	return false;
+#endif
+}
 
 static inline u16 __virtio16_to_cpu(bool little_endian, __virtio16 val)
 {
 	if (little_endian)
 		return le16_to_cpu((__force __le16)val);
 	else
-		return (__force u16)val;
+		return be16_to_cpu((__force __be16)val);
 }
 
 static inline __virtio16 __cpu_to_virtio16(bool little_endian, u16 val)
@@ -21,7 +25,7 @@
 	if (little_endian)
 		return (__force __virtio16)cpu_to_le16(val);
 	else
-		return (__force __virtio16)val;
+		return (__force __virtio16)cpu_to_be16(val);
 }
 
 static inline u32 __virtio32_to_cpu(bool little_endian, __virtio32 val)
@@ -29,7 +33,7 @@
 	if (little_endian)
 		return le32_to_cpu((__force __le32)val);
 	else
-		return (__force u32)val;
+		return be32_to_cpu((__force __be32)val);
 }
 
 static inline __virtio32 __cpu_to_virtio32(bool little_endian, u32 val)
@@ -37,7 +41,7 @@
 	if (little_endian)
 		return (__force __virtio32)cpu_to_le32(val);
 	else
-		return (__force __virtio32)val;
+		return (__force __virtio32)cpu_to_be32(val);
 }
 
 static inline u64 __virtio64_to_cpu(bool little_endian, __virtio64 val)
@@ -45,7 +49,7 @@
 	if (little_endian)
 		return le64_to_cpu((__force __le64)val);
 	else
-		return (__force u64)val;
+		return be64_to_cpu((__force __be64)val);
 }
 
 static inline __virtio64 __cpu_to_virtio64(bool little_endian, u64 val)
@@ -53,7 +57,7 @@
 	if (little_endian)
 		return (__force __virtio64)cpu_to_le64(val);
 	else
-		return (__force __virtio64)val;
+		return (__force __virtio64)cpu_to_be64(val);
 }
 
 #endif /* _LINUX_VIRTIO_BYTEORDER */
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 1e306f7..e5ce8ab 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -205,35 +205,41 @@
 	return 0;
 }
 
+static inline bool virtio_is_little_endian(struct virtio_device *vdev)
+{
+	return virtio_has_feature(vdev, VIRTIO_F_VERSION_1) ||
+		virtio_legacy_is_little_endian();
+}
+
 /* Memory accessors */
 static inline u16 virtio16_to_cpu(struct virtio_device *vdev, __virtio16 val)
 {
-	return __virtio16_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+	return __virtio16_to_cpu(virtio_is_little_endian(vdev), val);
 }
 
 static inline __virtio16 cpu_to_virtio16(struct virtio_device *vdev, u16 val)
 {
-	return __cpu_to_virtio16(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+	return __cpu_to_virtio16(virtio_is_little_endian(vdev), val);
 }
 
 static inline u32 virtio32_to_cpu(struct virtio_device *vdev, __virtio32 val)
 {
-	return __virtio32_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+	return __virtio32_to_cpu(virtio_is_little_endian(vdev), val);
 }
 
 static inline __virtio32 cpu_to_virtio32(struct virtio_device *vdev, u32 val)
 {
-	return __cpu_to_virtio32(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+	return __cpu_to_virtio32(virtio_is_little_endian(vdev), val);
 }
 
 static inline u64 virtio64_to_cpu(struct virtio_device *vdev, __virtio64 val)
 {
-	return __virtio64_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+	return __virtio64_to_cpu(virtio_is_little_endian(vdev), val);
 }
 
 static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
 {
-	return __cpu_to_virtio64(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+	return __cpu_to_virtio64(virtio_is_little_endian(vdev), val);
 }
 
 /* Config space accessors. */
diff --git a/include/linux/vringh.h b/include/linux/vringh.h
index a3fa537..bc6c28d 100644
--- a/include/linux/vringh.h
+++ b/include/linux/vringh.h
@@ -226,33 +226,39 @@
 		vrh->notify(vrh);
 }
 
+static inline bool vringh_is_little_endian(const struct vringh *vrh)
+{
+	return vrh->little_endian ||
+		virtio_legacy_is_little_endian();
+}
+
 static inline u16 vringh16_to_cpu(const struct vringh *vrh, __virtio16 val)
 {
-	return __virtio16_to_cpu(vrh->little_endian, val);
+	return __virtio16_to_cpu(vringh_is_little_endian(vrh), val);
 }
 
 static inline __virtio16 cpu_to_vringh16(const struct vringh *vrh, u16 val)
 {
-	return __cpu_to_virtio16(vrh->little_endian, val);
+	return __cpu_to_virtio16(vringh_is_little_endian(vrh), val);
 }
 
 static inline u32 vringh32_to_cpu(const struct vringh *vrh, __virtio32 val)
 {
-	return __virtio32_to_cpu(vrh->little_endian, val);
+	return __virtio32_to_cpu(vringh_is_little_endian(vrh), val);
 }
 
 static inline __virtio32 cpu_to_vringh32(const struct vringh *vrh, u32 val)
 {
-	return __cpu_to_virtio32(vrh->little_endian, val);
+	return __cpu_to_virtio32(vringh_is_little_endian(vrh), val);
 }
 
 static inline u64 vringh64_to_cpu(const struct vringh *vrh, __virtio64 val)
 {
-	return __virtio64_to_cpu(vrh->little_endian, val);
+	return __virtio64_to_cpu(vringh_is_little_endian(vrh), val);
 }
 
 static inline __virtio64 cpu_to_vringh64(const struct vringh *vrh, u64 val)
 {
-	return __cpu_to_virtio64(vrh->little_endian, val);
+	return __cpu_to_virtio64(vringh_is_little_endian(vrh), val);
 }
 #endif /* _LINUX_VRINGH_H */
diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h
index a746bf5..f47fead 100644
--- a/include/linux/watchdog.h
+++ b/include/linux/watchdog.h
@@ -65,6 +65,8 @@
  * @driver-data:Pointer to the drivers private data.
  * @lock:	Lock for watchdog core internal use only.
  * @status:	Field that contains the devices internal status bits.
+ * @deferred: entry in wtd_deferred_reg_list which is used to
+ *			   register early initialized watchdogs.
  *
  * The watchdog_device structure contains all information about a
  * watchdog timer device.
@@ -95,6 +97,7 @@
 #define WDOG_ALLOW_RELEASE	2	/* Did we receive the magic char ? */
 #define WDOG_NO_WAY_OUT		3	/* Is 'nowayout' feature set ? */
 #define WDOG_UNREGISTERED	4	/* Has the device been unregistered */
+	struct list_head deferred;
 };
 
 #define WATCHDOG_NOWAYOUT		IS_BUILTIN(CONFIG_WATCHDOG_NOWAYOUT)
diff --git a/include/media/v4l2-flash-led-class.h b/include/media/v4l2-flash-led-class.h
new file mode 100644
index 0000000..098236c
--- /dev/null
+++ b/include/media/v4l2-flash-led-class.h
@@ -0,0 +1,148 @@
+/*
+ * V4L2 flash LED sub-device registration helpers.
+ *
+ *	Copyright (C) 2015 Samsung Electronics Co., Ltd
+ *	Author: Jacek Anaszewski <j.anaszewski@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _V4L2_FLASH_H
+#define _V4L2_FLASH_H
+
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-subdev.h>
+
+struct led_classdev_flash;
+struct led_classdev;
+struct v4l2_flash;
+enum led_brightness;
+
+/*
+ * struct v4l2_flash_ctrl_data - flash control initialization data, filled
+ *				basing on the features declared by the LED flash
+ *				class driver in the v4l2_flash_config
+ * @config:	initialization data for a control
+ * @cid:	contains v4l2 flash control id if the config
+ *		field was initialized, 0 otherwise
+ */
+struct v4l2_flash_ctrl_data {
+	struct v4l2_ctrl_config config;
+	u32 cid;
+};
+
+struct v4l2_flash_ops {
+	/* setup strobing the flash by hardware pin state assertion */
+	int (*external_strobe_set)(struct v4l2_flash *v4l2_flash,
+					bool enable);
+	/* convert intensity to brightness in a device specific manner */
+	enum led_brightness (*intensity_to_led_brightness)
+		(struct v4l2_flash *v4l2_flash, s32 intensity);
+	/* convert brightness to intensity in a device specific manner */
+	s32 (*led_brightness_to_intensity)
+		(struct v4l2_flash *v4l2_flash, enum led_brightness);
+};
+
+/**
+ * struct v4l2_flash_config - V4L2 Flash sub-device initialization data
+ * @dev_name:			the name of the media entity,
+				unique in the system
+ * @torch_intensity:		constraints for the LED in torch mode
+ * @indicator_intensity:	constraints for the indicator LED
+ * @flash_faults:		bitmask of flash faults that the LED flash class
+				device can report; corresponding LED_FAULT* bit
+				definitions are available in the header file
+				<linux/led-class-flash.h>
+ * @has_external_strobe:	external strobe capability
+ */
+struct v4l2_flash_config {
+	char dev_name[32];
+	struct led_flash_setting torch_intensity;
+	struct led_flash_setting indicator_intensity;
+	u32 flash_faults;
+	unsigned int has_external_strobe:1;
+};
+
+/**
+ * struct v4l2_flash - Flash sub-device context
+ * @fled_cdev:		LED flash class device controlled by this sub-device
+ * @iled_cdev:		LED class device representing indicator LED associated
+ *			with the LED flash class device
+ * @ops:		V4L2 specific flash ops
+ * @sd:			V4L2 sub-device
+ * @hdl:		flash controls handler
+ * @ctrls:		array of pointers to controls, whose values define
+ *			the sub-device state
+ */
+struct v4l2_flash {
+	struct led_classdev_flash *fled_cdev;
+	struct led_classdev_flash *iled_cdev;
+	const struct v4l2_flash_ops *ops;
+
+	struct v4l2_subdev sd;
+	struct v4l2_ctrl_handler hdl;
+	struct v4l2_ctrl **ctrls;
+};
+
+static inline struct v4l2_flash *v4l2_subdev_to_v4l2_flash(
+							struct v4l2_subdev *sd)
+{
+	return container_of(sd, struct v4l2_flash, sd);
+}
+
+static inline struct v4l2_flash *v4l2_ctrl_to_v4l2_flash(struct v4l2_ctrl *c)
+{
+	return container_of(c->handler, struct v4l2_flash, hdl);
+}
+
+#if IS_ENABLED(CONFIG_V4L2_FLASH_LED_CLASS)
+/**
+ * v4l2_flash_init - initialize V4L2 flash led sub-device
+ * @dev:	flash device, e.g. an I2C device
+ * @of_node:	of_node of the LED, may be NULL if the same as device's
+ * @fled_cdev:	LED flash class device to wrap
+ * @iled_cdev:	LED flash class device representing indicator LED associated
+ *		with fled_cdev, may be NULL
+ * @flash_ops:	V4L2 Flash device ops
+ * @config:	initialization data for V4L2 Flash sub-device
+ *
+ * Create V4L2 Flash sub-device wrapping given LED subsystem device.
+ *
+ * Returns: A valid pointer, or, when an error occurs, the return
+ * value is encoded using ERR_PTR(). Use IS_ERR() to check and
+ * PTR_ERR() to obtain the numeric return value.
+ */
+struct v4l2_flash *v4l2_flash_init(
+	struct device *dev, struct device_node *of_node,
+	struct led_classdev_flash *fled_cdev,
+	struct led_classdev_flash *iled_cdev,
+	const struct v4l2_flash_ops *ops,
+	struct v4l2_flash_config *config);
+
+/**
+ * v4l2_flash_release - release V4L2 Flash sub-device
+ * @flash: the V4L2 Flash sub-device to release
+ *
+ * Release V4L2 Flash sub-device.
+ */
+void v4l2_flash_release(struct v4l2_flash *v4l2_flash);
+
+#else
+static inline struct v4l2_flash *v4l2_flash_init(
+	struct device *dev, struct device_node *of_node,
+	struct led_classdev_flash *fled_cdev,
+	struct led_classdev_flash *iled_cdev,
+	const struct v4l2_flash_ops *ops,
+	struct v4l2_flash_config *config)
+{
+	return NULL;
+}
+
+static inline void v4l2_flash_release(struct v4l2_flash *v4l2_flash)
+{
+}
+#endif /* CONFIG_V4L2_FLASH_LED_CLASS */
+
+#endif /* _V4L2_FLASH_H */
diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index dc20102..4e18318 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -605,6 +605,8 @@
 	struct video_device *devnode;
 	/* pointer to the physical device, if any */
 	struct device *dev;
+	/* The device_node of the subdev, usually the same as dev->of_node. */
+	struct device_node *of_node;
 	/* Links this subdev to a global subdev_list or @notifier->done list. */
 	struct list_head async_list;
 	/* Pointer to respective struct v4l2_async_subdev. */
diff --git a/include/net/ax25.h b/include/net/ax25.h
index 16a923a..e602f81 100644
--- a/include/net/ax25.h
+++ b/include/net/ax25.h
@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/atomic.h>
 #include <net/neighbour.h>
+#include <net/sock.h>
 
 #define	AX25_T1CLAMPLO  		1
 #define	AX25_T1CLAMPHI 			(30 * HZ)
@@ -246,7 +247,20 @@
 	atomic_t		refcount;
 } ax25_cb;
 
-#define ax25_sk(__sk) ((ax25_cb *)(__sk)->sk_protinfo)
+struct ax25_sock {
+	struct sock		sk;
+	struct ax25_cb		*cb;
+};
+
+static inline struct ax25_sock *ax25_sk(const struct sock *sk)
+{
+	return (struct ax25_sock *) sk;
+}
+
+static inline struct ax25_cb *sk_to_ax25(const struct sock *sk)
+{
+	return ax25_sk(sk)->cb;
+}
 
 #define ax25_for_each(__ax25, list) \
 	hlist_for_each_entry(__ax25, list, ax25_node)
diff --git a/include/net/sock.h b/include/net/sock.h
index 14d539c..05a8c1a 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -277,7 +277,6 @@
   *	@sk_incoming_cpu: record cpu processing incoming packets
   *	@sk_txhash: computed flow hash for use on transmit
   *	@sk_filter: socket filtering instructions
-  *	@sk_protinfo: private area, net family specific, when not using slab
   *	@sk_timer: sock cleanup timer
   *	@sk_stamp: time stamp of last packet received
   *	@sk_tsflags: SO_TIMESTAMPING socket options
@@ -416,7 +415,6 @@
 	const struct cred	*sk_peer_cred;
 	long			sk_rcvtimeo;
 	long			sk_sndtimeo;
-	void			*sk_protinfo;
 	struct timer_list	sk_timer;
 	ktime_t			sk_stamp;
 	u16			sk_tsflags;
diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h
index 006983b..34117b8 100644
--- a/include/target/iscsi/iscsi_target_core.h
+++ b/include/target/iscsi/iscsi_target_core.h
@@ -247,10 +247,6 @@
 	u8	DataDigest;			/* [0,1] == [None,CRC32C] */
 	u32	MaxRecvDataSegmentLength;	/* [512..2**24-1] */
 	u32	MaxXmitDataSegmentLength;	/* [512..2**24-1] */
-	u8	OFMarker;			/* [0,1] == [No,Yes] */
-	u8	IFMarker;			/* [0,1] == [No,Yes] */
-	u32	OFMarkInt;			/* [1..65535] */
-	u32	IFMarkInt;			/* [1..65535] */
 	/*
 	 * iSER specific connection parameters
 	 */
@@ -531,12 +527,6 @@
 	u32			exp_statsn;
 	/* Per connection status sequence number */
 	u32			stat_sn;
-	/* IFMarkInt's Current Value */
-	u32			if_marker;
-	/* OFMarkInt's Current Value */
-	u32			of_marker;
-	/* Used for calculating OFMarker offset to next PDU */
-	u32			of_marker_offset;
 #define IPV6_ADDRESS_SPACE				48
 	unsigned char		login_ip[IPV6_ADDRESS_SPACE];
 	unsigned char		local_ip[IPV6_ADDRESS_SPACE];
@@ -754,10 +744,10 @@
 };
 
 struct iscsi_node_acl {
+	struct se_node_acl	se_node_acl;
 	struct iscsi_node_attrib node_attrib;
 	struct iscsi_node_auth	node_auth;
 	struct iscsi_node_stat_grps node_stat_grps;
-	struct se_node_acl	se_node_acl;
 };
 
 struct iscsi_tpg_attrib {
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 5f12257..1e5c8f9 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -3,18 +3,7 @@
 
 #define TRANSPORT_FLAG_PASSTHROUGH		1
 
-struct target_backend_cits {
-	struct config_item_type tb_dev_cit;
-	struct config_item_type tb_dev_attrib_cit;
-	struct config_item_type tb_dev_pr_cit;
-	struct config_item_type tb_dev_wwn_cit;
-	struct config_item_type tb_dev_alua_tg_pt_gps_cit;
-	struct config_item_type tb_dev_stat_cit;
-};
-
-struct se_subsystem_api {
-	struct list_head sub_api_list;
-
+struct target_backend_ops {
 	char name[16];
 	char inquiry_prod[16];
 	char inquiry_rev[4];
@@ -52,7 +41,7 @@
 	int (*format_prot)(struct se_device *);
 	void (*free_prot)(struct se_device *);
 
-	struct target_backend_cits tb_cits;
+	struct configfs_attribute **tb_dev_attrib_attrs;
 };
 
 struct sbc_ops {
@@ -60,12 +49,12 @@
 				     u32, enum dma_data_direction);
 	sense_reason_t (*execute_sync_cache)(struct se_cmd *cmd);
 	sense_reason_t (*execute_write_same)(struct se_cmd *cmd);
-	sense_reason_t (*execute_write_same_unmap)(struct se_cmd *cmd);
-	sense_reason_t (*execute_unmap)(struct se_cmd *cmd);
+	sense_reason_t (*execute_unmap)(struct se_cmd *cmd,
+				sector_t lba, sector_t nolb);
 };
 
-int	transport_subsystem_register(struct se_subsystem_api *);
-void	transport_subsystem_release(struct se_subsystem_api *);
+int	transport_backend_register(const struct target_backend_ops *);
+void	target_backend_unregister(const struct target_backend_ops *);
 
 void	target_complete_cmd(struct se_cmd *, u8);
 void	target_complete_cmd_with_length(struct se_cmd *, u8, int);
@@ -79,22 +68,19 @@
 u32	sbc_get_device_rev(struct se_device *dev);
 u32	sbc_get_device_type(struct se_device *dev);
 sector_t	sbc_get_write_same_sectors(struct se_cmd *cmd);
-sense_reason_t sbc_execute_unmap(struct se_cmd *cmd,
-	sense_reason_t (*do_unmap_fn)(struct se_cmd *cmd, void *priv,
-				      sector_t lba, sector_t nolb),
-	void *priv);
 void	sbc_dif_generate(struct se_cmd *);
-sense_reason_t	sbc_dif_verify_write(struct se_cmd *, sector_t, unsigned int,
+sense_reason_t	sbc_dif_verify(struct se_cmd *, sector_t, unsigned int,
 				     unsigned int, struct scatterlist *, int);
-sense_reason_t	sbc_dif_verify_read(struct se_cmd *, sector_t, unsigned int,
-				    unsigned int, struct scatterlist *, int);
-sense_reason_t	sbc_dif_read_strip(struct se_cmd *);
-
+void sbc_dif_copy_prot(struct se_cmd *, unsigned int, bool,
+		       struct scatterlist *, int);
 void	transport_set_vpd_proto_id(struct t10_vpd *, unsigned char *);
 int	transport_set_vpd_assoc(struct t10_vpd *, unsigned char *);
 int	transport_set_vpd_ident_type(struct t10_vpd *, unsigned char *);
 int	transport_set_vpd_ident(struct t10_vpd *, unsigned char *);
 
+extern struct configfs_attribute *sbc_attrib_attrs[];
+extern struct configfs_attribute *passthrough_attrib_attrs[];
+
 /* core helpers also used by command snooping in pscsi */
 void	*transport_kmap_data_sg(struct se_cmd *);
 void	transport_kunmap_data_sg(struct se_cmd *);
@@ -103,39 +89,7 @@
 sense_reason_t	transport_generic_map_mem_to_cmd(struct se_cmd *,
 		struct scatterlist *, u32, struct scatterlist *, u32);
 
-void	array_free(void *array, int n);
-
-/* From target_core_configfs.c to setup default backend config_item_types */
-void	target_core_setup_sub_cits(struct se_subsystem_api *);
-
-/* attribute helpers from target_core_device.c for backend drivers */
-bool	se_dev_check_wce(struct se_device *);
-int	se_dev_set_max_unmap_lba_count(struct se_device *, u32);
-int	se_dev_set_max_unmap_block_desc_count(struct se_device *, u32);
-int	se_dev_set_unmap_granularity(struct se_device *, u32);
-int	se_dev_set_unmap_granularity_alignment(struct se_device *, u32);
-int	se_dev_set_max_write_same_len(struct se_device *, u32);
-int	se_dev_set_emulate_model_alias(struct se_device *, int);
-int	se_dev_set_emulate_dpo(struct se_device *, int);
-int	se_dev_set_emulate_fua_write(struct se_device *, int);
-int	se_dev_set_emulate_fua_read(struct se_device *, int);
-int	se_dev_set_emulate_write_cache(struct se_device *, int);
-int	se_dev_set_emulate_ua_intlck_ctrl(struct se_device *, int);
-int	se_dev_set_emulate_tas(struct se_device *, int);
-int	se_dev_set_emulate_tpu(struct se_device *, int);
-int	se_dev_set_emulate_tpws(struct se_device *, int);
-int	se_dev_set_emulate_caw(struct se_device *, int);
-int	se_dev_set_emulate_3pc(struct se_device *, int);
-int	se_dev_set_pi_prot_type(struct se_device *, int);
-int	se_dev_set_pi_prot_format(struct se_device *, int);
-int	se_dev_set_enforce_pr_isids(struct se_device *, int);
-int	se_dev_set_force_pr_aptpl(struct se_device *, int);
-int	se_dev_set_is_nonrot(struct se_device *, int);
-int	se_dev_set_emulate_rest_reord(struct se_device *dev, int);
-int	se_dev_set_queue_depth(struct se_device *, u32);
-int	se_dev_set_max_sectors(struct se_device *, u32);
-int	se_dev_set_optimal_sectors(struct se_device *, u32);
-int	se_dev_set_block_size(struct se_device *, u32);
+bool	target_lun_is_rdonly(struct se_cmd *);
 sense_reason_t passthrough_parse_cdb(struct se_cmd *cmd,
 	sense_reason_t (*exec_cmd)(struct se_cmd *cmd));
 
diff --git a/include/target/target_core_backend_configfs.h b/include/target/target_core_backend_configfs.h
deleted file mode 100644
index 186f7a9..0000000
--- a/include/target/target_core_backend_configfs.h
+++ /dev/null
@@ -1,118 +0,0 @@
-#ifndef TARGET_CORE_BACKEND_CONFIGFS_H
-#define TARGET_CORE_BACKEND_CONFIGFS_H
-
-#include <target/configfs_macros.h>
-
-#define DEF_TB_DEV_ATTRIB_SHOW(_backend, _name)				\
-static ssize_t _backend##_dev_show_attr_##_name(			\
-	struct se_dev_attrib *da,					\
-	char *page)							\
-{									\
-	return snprintf(page, PAGE_SIZE, "%u\n",			\
-			(u32)da->da_dev->dev_attrib._name);		\
-}
-
-#define DEF_TB_DEV_ATTRIB_STORE(_backend, _name)			\
-static ssize_t _backend##_dev_store_attr_##_name(			\
-	struct se_dev_attrib *da,					\
-	const char *page,						\
-	size_t count)							\
-{									\
-	unsigned long val;						\
-	int ret;							\
-									\
-	ret = kstrtoul(page, 0, &val);					\
-	if (ret < 0) {							\
-		pr_err("kstrtoul() failed with ret: %d\n", ret);	\
-		return -EINVAL;						\
-	}								\
-	ret = se_dev_set_##_name(da->da_dev, (u32)val);			\
-									\
-	return (!ret) ? count : -EINVAL;				\
-}
-
-#define DEF_TB_DEV_ATTRIB(_backend, _name)				\
-DEF_TB_DEV_ATTRIB_SHOW(_backend, _name);				\
-DEF_TB_DEV_ATTRIB_STORE(_backend, _name);
-
-#define DEF_TB_DEV_ATTRIB_RO(_backend, name)				\
-DEF_TB_DEV_ATTRIB_SHOW(_backend, name);
-
-CONFIGFS_EATTR_STRUCT(target_backend_dev_attrib, se_dev_attrib);
-#define TB_DEV_ATTR(_backend, _name, _mode)				\
-static struct target_backend_dev_attrib_attribute _backend##_dev_attrib_##_name = \
-		__CONFIGFS_EATTR(_name, _mode,				\
-		_backend##_dev_show_attr_##_name,			\
-		_backend##_dev_store_attr_##_name);
-
-#define TB_DEV_ATTR_RO(_backend, _name)						\
-static struct target_backend_dev_attrib_attribute _backend##_dev_attrib_##_name = \
-	__CONFIGFS_EATTR_RO(_name,					\
-	_backend##_dev_show_attr_##_name);
-
-/*
- * Default list of target backend device attributes as defined by
- * struct se_dev_attrib
- */
-
-#define DEF_TB_DEFAULT_ATTRIBS(_backend)				\
-	DEF_TB_DEV_ATTRIB(_backend, emulate_model_alias);		\
-	TB_DEV_ATTR(_backend, emulate_model_alias, S_IRUGO | S_IWUSR);	\
-	DEF_TB_DEV_ATTRIB(_backend, emulate_dpo);			\
-	TB_DEV_ATTR(_backend, emulate_dpo, S_IRUGO | S_IWUSR);		\
-	DEF_TB_DEV_ATTRIB(_backend, emulate_fua_write);			\
-	TB_DEV_ATTR(_backend, emulate_fua_write, S_IRUGO | S_IWUSR);	\
-	DEF_TB_DEV_ATTRIB(_backend, emulate_fua_read);			\
-	TB_DEV_ATTR(_backend, emulate_fua_read, S_IRUGO | S_IWUSR);	\
-	DEF_TB_DEV_ATTRIB(_backend, emulate_write_cache);		\
-	TB_DEV_ATTR(_backend, emulate_write_cache, S_IRUGO | S_IWUSR);	\
-	DEF_TB_DEV_ATTRIB(_backend, emulate_ua_intlck_ctrl);		\
-	TB_DEV_ATTR(_backend, emulate_ua_intlck_ctrl, S_IRUGO | S_IWUSR); \
-	DEF_TB_DEV_ATTRIB(_backend, emulate_tas);			\
-	TB_DEV_ATTR(_backend, emulate_tas, S_IRUGO | S_IWUSR);		\
-	DEF_TB_DEV_ATTRIB(_backend, emulate_tpu);			\
-	TB_DEV_ATTR(_backend, emulate_tpu, S_IRUGO | S_IWUSR);		\
-	DEF_TB_DEV_ATTRIB(_backend, emulate_tpws);			\
-	TB_DEV_ATTR(_backend, emulate_tpws, S_IRUGO | S_IWUSR);		\
-	DEF_TB_DEV_ATTRIB(_backend, emulate_caw);			\
-	TB_DEV_ATTR(_backend, emulate_caw, S_IRUGO | S_IWUSR);		\
-	DEF_TB_DEV_ATTRIB(_backend, emulate_3pc);			\
-	TB_DEV_ATTR(_backend, emulate_3pc, S_IRUGO | S_IWUSR);		\
-	DEF_TB_DEV_ATTRIB(_backend, pi_prot_type);			\
-	TB_DEV_ATTR(_backend, pi_prot_type, S_IRUGO | S_IWUSR);		\
-	DEF_TB_DEV_ATTRIB_RO(_backend, hw_pi_prot_type);		\
-	TB_DEV_ATTR_RO(_backend, hw_pi_prot_type);			\
-	DEF_TB_DEV_ATTRIB(_backend, pi_prot_format);			\
-	TB_DEV_ATTR(_backend, pi_prot_format, S_IRUGO | S_IWUSR);	\
-	DEF_TB_DEV_ATTRIB(_backend, enforce_pr_isids);			\
-	TB_DEV_ATTR(_backend, enforce_pr_isids, S_IRUGO | S_IWUSR);	\
-	DEF_TB_DEV_ATTRIB(_backend, is_nonrot);				\
-	TB_DEV_ATTR(_backend, is_nonrot, S_IRUGO | S_IWUSR);		\
-	DEF_TB_DEV_ATTRIB(_backend, emulate_rest_reord);		\
-	TB_DEV_ATTR(_backend, emulate_rest_reord, S_IRUGO | S_IWUSR);	\
-	DEF_TB_DEV_ATTRIB(_backend, force_pr_aptpl);			\
-	TB_DEV_ATTR(_backend, force_pr_aptpl, S_IRUGO | S_IWUSR);	\
-	DEF_TB_DEV_ATTRIB_RO(_backend, hw_block_size);			\
-	TB_DEV_ATTR_RO(_backend, hw_block_size);			\
-	DEF_TB_DEV_ATTRIB(_backend, block_size);			\
-	TB_DEV_ATTR(_backend, block_size, S_IRUGO | S_IWUSR);		\
-	DEF_TB_DEV_ATTRIB_RO(_backend, hw_max_sectors);			\
-	TB_DEV_ATTR_RO(_backend, hw_max_sectors);			\
-	DEF_TB_DEV_ATTRIB(_backend, optimal_sectors);			\
-	TB_DEV_ATTR(_backend, optimal_sectors, S_IRUGO | S_IWUSR);	\
-	DEF_TB_DEV_ATTRIB_RO(_backend, hw_queue_depth);			\
-	TB_DEV_ATTR_RO(_backend, hw_queue_depth);			\
-	DEF_TB_DEV_ATTRIB(_backend, queue_depth);			\
-	TB_DEV_ATTR(_backend, queue_depth, S_IRUGO | S_IWUSR);		\
-	DEF_TB_DEV_ATTRIB(_backend, max_unmap_lba_count);		\
-	TB_DEV_ATTR(_backend, max_unmap_lba_count, S_IRUGO | S_IWUSR);	\
-	DEF_TB_DEV_ATTRIB(_backend, max_unmap_block_desc_count);	\
-	TB_DEV_ATTR(_backend, max_unmap_block_desc_count, S_IRUGO | S_IWUSR); \
-	DEF_TB_DEV_ATTRIB(_backend, unmap_granularity);			\
-	TB_DEV_ATTR(_backend, unmap_granularity, S_IRUGO | S_IWUSR);	\
-	DEF_TB_DEV_ATTRIB(_backend, unmap_granularity_alignment);	\
-	TB_DEV_ATTR(_backend, unmap_granularity_alignment, S_IRUGO | S_IWUSR); \
-	DEF_TB_DEV_ATTRIB(_backend, max_write_same_len);		\
-	TB_DEV_ATTR(_backend, max_write_same_len, S_IRUGO | S_IWUSR);
-
-#endif /* TARGET_CORE_BACKEND_CONFIGFS_H */
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index aec6f6a..17ae2d6 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -9,12 +9,8 @@
 #include <net/sock.h>
 #include <net/tcp.h>
 
-#define TARGET_CORE_MOD_VERSION		"v4.1.0"
-#define TARGET_CORE_VERSION		TARGET_CORE_MOD_VERSION
+#define TARGET_CORE_VERSION		"v5.0"
 
-/* Maximum Number of LUNs per Target Portal Group */
-/* Don't raise above 511 or REPORT_LUNS needs to handle >1 page */
-#define TRANSPORT_MAX_LUNS_PER_TPG		256
 /*
  * Maximum size of a CDB that can be stored in se_cmd without allocating
  * memory dynamically for the CDB.
@@ -70,12 +66,6 @@
 #define DA_MAX_WRITE_SAME_LEN			0
 /* Use a model alias based on the configfs backend device name */
 #define DA_EMULATE_MODEL_ALIAS			0
-/* Emulation for Direct Page Out */
-#define DA_EMULATE_DPO				0
-/* Emulation for Forced Unit Access WRITEs */
-#define DA_EMULATE_FUA_WRITE			1
-/* Emulation for Forced Unit Access READs */
-#define DA_EMULATE_FUA_READ			0
 /* Emulation for WriteCache and SYNCHRONIZE_CACHE */
 #define DA_EMULATE_WRITE_CACHE			0
 /* Emulation for UNIT ATTENTION Interlock Control */
@@ -116,18 +106,6 @@
 	HBA_FLAGS_PSCSI_MODE	= 0x02,
 };
 
-/* struct se_lun->lun_status */
-enum transport_lun_status_table {
-	TRANSPORT_LUN_STATUS_FREE = 0,
-	TRANSPORT_LUN_STATUS_ACTIVE = 1,
-};
-
-/* struct se_portal_group->se_tpg_type */
-enum transport_tpg_type_table {
-	TRANSPORT_TPG_TYPE_NORMAL = 0,
-	TRANSPORT_TPG_TYPE_DISCOVERY = 1,
-};
-
 /* Special transport agnostic struct se_cmd->t_states */
 enum transport_state_table {
 	TRANSPORT_NO_STATE	= 0,
@@ -158,14 +136,13 @@
 	SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC = 0x00020000,
 	SCF_COMPARE_AND_WRITE		= 0x00080000,
 	SCF_COMPARE_AND_WRITE_POST	= 0x00100000,
+	SCF_PASSTHROUGH_PROT_SG_TO_MEM_NOALLOC = 0x00200000,
 };
 
 /* struct se_dev_entry->lun_flags and struct se_lun->lun_access */
 enum transport_lunflags_table {
-	TRANSPORT_LUNFLAGS_NO_ACCESS		= 0x00,
-	TRANSPORT_LUNFLAGS_INITIATOR_ACCESS	= 0x01,
-	TRANSPORT_LUNFLAGS_READ_ONLY		= 0x02,
-	TRANSPORT_LUNFLAGS_READ_WRITE		= 0x04,
+	TRANSPORT_LUNFLAGS_READ_ONLY		= 0x01,
+	TRANSPORT_LUNFLAGS_READ_WRITE		= 0x02,
 };
 
 /*
@@ -314,22 +291,13 @@
 	struct se_device *tg_pt_gp_dev;
 	struct config_group tg_pt_gp_group;
 	struct list_head tg_pt_gp_list;
-	struct list_head tg_pt_gp_mem_list;
-	struct se_port *tg_pt_gp_alua_port;
+	struct list_head tg_pt_gp_lun_list;
+	struct se_lun *tg_pt_gp_alua_lun;
 	struct se_node_acl *tg_pt_gp_alua_nacl;
 	struct delayed_work tg_pt_gp_transition_work;
 	struct completion *tg_pt_gp_transition_complete;
 };
 
-struct t10_alua_tg_pt_gp_member {
-	bool tg_pt_gp_assoc;
-	atomic_t tg_pt_gp_mem_ref_cnt;
-	spinlock_t tg_pt_gp_mem_lock;
-	struct t10_alua_tg_pt_gp *tg_pt_gp;
-	struct se_port *tg_pt;
-	struct list_head tg_pt_gp_mem_list;
-};
-
 struct t10_vpd {
 	unsigned char device_identifier[INQUIRY_VPD_DEVICE_IDENTIFIER_LEN];
 	int protocol_identifier_set;
@@ -374,15 +342,16 @@
 	int pr_res_scope;
 	/* Used for fabric initiator WWPNs using a ISID */
 	bool isid_present_at_reg;
-	u32 pr_res_mapped_lun;
-	u32 pr_aptpl_target_lun;
+	u64 pr_res_mapped_lun;
+	u64 pr_aptpl_target_lun;
+	u16 tg_pt_sep_rtpi;
 	u32 pr_res_generation;
 	u64 pr_reg_bin_isid;
 	u64 pr_res_key;
 	atomic_t pr_res_holders;
 	struct se_node_acl *pr_reg_nacl;
+	/* Used by ALL_TG_PT=1 registration with deve->pr_ref taken */
 	struct se_dev_entry *pr_reg_deve;
-	struct se_lun *pr_reg_tg_pt_lun;
 	struct list_head pr_reg_list;
 	struct list_head pr_reg_abort_list;
 	struct list_head pr_reg_aptpl_list;
@@ -422,7 +391,7 @@
 	u8			response;
 	int			call_transport;
 	/* Reference to ITT that Task Mgmt should be performed */
-	u32			ref_task_tag;
+	u64			ref_task_tag;
 	void 			*fabric_tmr_ptr;
 	struct se_cmd		*task_cmd;
 	struct se_device	*tmr_dev;
@@ -475,6 +444,7 @@
 	u8			scsi_asc;
 	u8			scsi_ascq;
 	u16			scsi_sense_length;
+	u64			tag; /* SAM command identifier aka task tag */
 	/* Delay for ALUA Active/NonOptimized state access in milliseconds */
 	int			alua_nonop_delay;
 	/* See include/linux/dma-mapping.h */
@@ -493,7 +463,7 @@
 	/* Total size in bytes associated with command */
 	u32			data_length;
 	u32			residual_count;
-	u32			orig_fe_lun;
+	u64			orig_fe_lun;
 	/* Persistent Reservation key */
 	u64			pr_res_key;
 	/* Used for sense data */
@@ -501,7 +471,6 @@
 	struct list_head	se_delayed_node;
 	struct list_head	se_qf_node;
 	struct se_device      *se_dev;
-	struct se_dev_entry   *se_deve;
 	struct se_lun		*se_lun;
 	/* Only used for internal passthrough and legacy TCM fabric modules */
 	struct se_session	*se_sess;
@@ -511,9 +480,8 @@
 	struct kref		cmd_kref;
 	const struct target_core_fabric_ops *se_tfo;
 	sense_reason_t		(*execute_cmd)(struct se_cmd *);
-	sense_reason_t		(*execute_rw)(struct se_cmd *, struct scatterlist *,
-					      u32, enum dma_data_direction);
 	sense_reason_t (*transport_complete_callback)(struct se_cmd *, bool);
+	void			*protocol_data;
 
 	unsigned char		*t_task_cdb;
 	unsigned char		__t_task_cdb[TCM_MAX_COMMAND_SIZE];
@@ -569,7 +537,6 @@
 struct se_ua {
 	u8			ua_asc;
 	u8			ua_ascq;
-	struct se_node_acl	*ua_nacl;
 	struct list_head	ua_nacl_list;
 };
 
@@ -585,10 +552,10 @@
 	char			acl_tag[MAX_ACL_TAG_SIZE];
 	/* Used for PR SPEC_I_PT=1 and REGISTER_AND_MOVE */
 	atomic_t		acl_pr_ref_count;
-	struct se_dev_entry	**device_list;
+	struct hlist_head	lun_entry_hlist;
 	struct se_session	*nacl_sess;
 	struct se_portal_group *se_tpg;
-	spinlock_t		device_list_lock;
+	struct mutex		lun_entry_mutex;
 	spinlock_t		nacl_sess_lock;
 	struct config_group	acl_group;
 	struct config_group	acl_attrib_group;
@@ -632,33 +599,37 @@
 
 struct se_lun_acl {
 	char			initiatorname[TRANSPORT_IQN_LEN];
-	u32			mapped_lun;
+	u64			mapped_lun;
 	struct se_node_acl	*se_lun_nacl;
 	struct se_lun		*se_lun;
-	struct list_head	lacl_list;
 	struct config_group	se_lun_group;
 	struct se_ml_stat_grps	ml_stat_grps;
 };
 
 struct se_dev_entry {
-	bool			def_pr_registered;
 	/* See transport_lunflags_table */
-	u32			lun_flags;
-	u32			mapped_lun;
-	u32			total_cmds;
+	u64			mapped_lun;
 	u64			pr_res_key;
 	u64			creation_time;
+	u32			lun_flags;
 	u32			attach_count;
-	u64			read_bytes;
-	u64			write_bytes;
+	atomic_long_t		total_cmds;
+	atomic_long_t		read_bytes;
+	atomic_long_t		write_bytes;
 	atomic_t		ua_count;
 	/* Used for PR SPEC_I_PT=1 and REGISTER_AND_MOVE */
-	atomic_t		pr_ref_count;
-	struct se_lun_acl	*se_lun_acl;
+	struct kref		pr_kref;
+	struct completion	pr_comp;
+	struct se_lun_acl __rcu	*se_lun_acl;
 	spinlock_t		ua_lock;
-	struct se_lun		*se_lun;
+	struct se_lun __rcu	*se_lun;
+#define DEF_PR_REG_ACTIVE		1
+	unsigned long		deve_flags;
 	struct list_head	alua_port_list;
+	struct list_head	lun_link;
 	struct list_head	ua_list;
+	struct hlist_node	link;
+	struct rcu_head		rcu_head;
 };
 
 struct se_dev_attrib {
@@ -703,25 +674,48 @@
 	struct config_group scsi_transport_group;
 };
 
+struct scsi_port_stats {
+	atomic_long_t	cmd_pdus;
+	atomic_long_t	tx_data_octets;
+	atomic_long_t	rx_data_octets;
+};
+
 struct se_lun {
+	u64			unpacked_lun;
 #define SE_LUN_LINK_MAGIC			0xffff7771
 	u32			lun_link_magic;
-	/* See transport_lun_status_table */
-	enum transport_lun_status_table lun_status;
 	u32			lun_access;
 	u32			lun_flags;
-	u32			unpacked_lun;
+	u32			lun_index;
+
+	/* RELATIVE TARGET PORT IDENTIFER */
+	u16			lun_rtpi;
 	atomic_t		lun_acl_count;
-	spinlock_t		lun_acl_lock;
-	spinlock_t		lun_sep_lock;
-	struct completion	lun_shutdown_comp;
-	struct list_head	lun_acl_list;
-	struct se_device	*lun_se_dev;
-	struct se_port		*lun_sep;
+	struct se_device __rcu	*lun_se_dev;
+
+	struct list_head	lun_deve_list;
+	spinlock_t		lun_deve_lock;
+
+	/* ALUA state */
+	int			lun_tg_pt_secondary_stat;
+	int			lun_tg_pt_secondary_write_md;
+	atomic_t		lun_tg_pt_secondary_offline;
+	struct mutex		lun_tg_pt_md_mutex;
+
+	/* ALUA target port group linkage */
+	struct list_head	lun_tg_pt_gp_link;
+	struct t10_alua_tg_pt_gp *lun_tg_pt_gp;
+	spinlock_t		lun_tg_pt_gp_lock;
+
+	struct se_portal_group	*lun_tpg;
+	struct scsi_port_stats	lun_stats;
 	struct config_group	lun_group;
 	struct se_port_stat_grps port_stat_grps;
 	struct completion	lun_ref_comp;
 	struct percpu_ref	lun_ref;
+	struct list_head	lun_dev_link;
+	struct hlist_node	link;
+	struct rcu_head		rcu_head;
 };
 
 struct se_dev_stat_grps {
@@ -744,7 +738,6 @@
 #define DF_EMULATED_VPD_UNIT_SERIAL		0x00000004
 #define DF_USING_UDEV_PATH			0x00000008
 #define DF_USING_ALIAS				0x00000010
-	u32			dev_port_count;
 	/* Physical device queue depth */
 	u32			queue_depth;
 	/* Used for SPC-2 reservations enforce of ISIDs */
@@ -761,7 +754,7 @@
 	atomic_t		dev_ordered_id;
 	atomic_t		dev_ordered_sync;
 	atomic_t		dev_qf_count;
-	int			export_count;
+	u32			export_count;
 	spinlock_t		delayed_cmd_lock;
 	spinlock_t		execute_task_lock;
 	spinlock_t		dev_reservation_lock;
@@ -803,12 +796,15 @@
 #define SE_UDEV_PATH_LEN 512		/* must be less than PAGE_SIZE */
 	unsigned char		udev_path[SE_UDEV_PATH_LEN];
 	/* Pointer to template of function pointers for transport */
-	struct se_subsystem_api *transport;
+	const struct target_backend_ops *transport;
 	/* Linked list for struct se_hba struct se_device list */
 	struct list_head	dev_list;
 	struct se_lun		xcopy_lun;
 	/* Protection Information */
 	int			prot_length;
+	/* For se_lun->lun_se_dev RCU read-side critical access */
+	u32			hba_index;
+	struct rcu_head		rcu_head;
 };
 
 struct se_hba {
@@ -825,33 +821,7 @@
 	spinlock_t		device_lock;
 	struct config_group	hba_group;
 	struct mutex		hba_access_mutex;
-	struct se_subsystem_api *transport;
-};
-
-struct scsi_port_stats {
-       u64     cmd_pdus;
-       u64     tx_data_octets;
-       u64     rx_data_octets;
-};
-
-struct se_port {
-	/* RELATIVE TARGET PORT IDENTIFER */
-	u16		sep_rtpi;
-	int		sep_tg_pt_secondary_stat;
-	int		sep_tg_pt_secondary_write_md;
-	u32		sep_index;
-	struct scsi_port_stats sep_stats;
-	/* Used for ALUA Target Port Groups membership */
-	atomic_t	sep_tg_pt_secondary_offline;
-	/* Used for PR ALL_TG_PT=1 */
-	atomic_t	sep_tg_pt_ref_cnt;
-	spinlock_t	sep_alua_lock;
-	struct mutex	sep_tg_pt_md_mutex;
-	struct t10_alua_tg_pt_gp_member *sep_alua_tg_pt_gp_mem;
-	struct se_lun *sep_lun;
-	struct se_portal_group *sep_tpg;
-	struct list_head sep_alua_list;
-	struct list_head sep_list;
+	struct target_backend	*backend;
 };
 
 struct se_tpg_np {
@@ -860,24 +830,26 @@
 };
 
 struct se_portal_group {
-	/* Type of target portal group, see transport_tpg_type_table */
-	enum transport_tpg_type_table se_tpg_type;
+	/*
+	 * PROTOCOL IDENTIFIER value per SPC4, 7.5.1.
+	 *
+	 * Negative values can be used by fabric drivers for internal use TPGs.
+	 */
+	int			proto_id;
 	/* Number of ACLed Initiator Nodes for this TPG */
 	u32			num_node_acls;
 	/* Used for PR SPEC_I_PT=1 and REGISTER_AND_MOVE */
 	atomic_t		tpg_pr_ref_count;
 	/* Spinlock for adding/removing ACLed Nodes */
-	spinlock_t		acl_node_lock;
+	struct mutex		acl_node_mutex;
 	/* Spinlock for adding/removing sessions */
 	spinlock_t		session_lock;
-	spinlock_t		tpg_lun_lock;
-	/* Pointer to $FABRIC_MOD portal group */
-	void			*se_tpg_fabric_ptr;
+	struct mutex		tpg_lun_mutex;
 	struct list_head	se_tpg_node;
 	/* linked list for initiator ACL list */
 	struct list_head	acl_node_list;
-	struct se_lun		**tpg_lun_list;
-	struct se_lun		tpg_virt_lun0;
+	struct hlist_head	tpg_lun_hlist;
+	struct se_lun		*tpg_virt_lun0;
 	/* List of TCM sessions associated wth this TPG */
 	struct list_head	tpg_sess_list;
 	/* Pointer to $FABRIC_MOD dependent code */
diff --git a/include/target/target_core_configfs.h b/include/target/target_core_configfs.h
deleted file mode 100644
index b99c011..0000000
--- a/include/target/target_core_configfs.h
+++ /dev/null
@@ -1,48 +0,0 @@
-#define TARGET_CORE_CONFIGFS_VERSION TARGET_CORE_MOD_VERSION
-
-#define TARGET_CORE_CONFIG_ROOT	"/sys/kernel/config"
-
-#define TARGET_CORE_NAME_MAX_LEN	64
-#define TARGET_FABRIC_NAME_SIZE		32
-
-struct target_fabric_configfs_template {
-	struct config_item_type tfc_discovery_cit;
-	struct config_item_type	tfc_wwn_cit;
-	struct config_item_type tfc_wwn_fabric_stats_cit;
-	struct config_item_type tfc_tpg_cit;
-	struct config_item_type tfc_tpg_base_cit;
-	struct config_item_type tfc_tpg_lun_cit;
-	struct config_item_type tfc_tpg_port_cit;
-	struct config_item_type tfc_tpg_port_stat_cit;
-	struct config_item_type tfc_tpg_np_cit;
-	struct config_item_type tfc_tpg_np_base_cit;
-	struct config_item_type tfc_tpg_attrib_cit;
-	struct config_item_type tfc_tpg_auth_cit;
-	struct config_item_type tfc_tpg_param_cit;
-	struct config_item_type tfc_tpg_nacl_cit;
-	struct config_item_type tfc_tpg_nacl_base_cit;
-	struct config_item_type tfc_tpg_nacl_attrib_cit;
-	struct config_item_type tfc_tpg_nacl_auth_cit;
-	struct config_item_type tfc_tpg_nacl_param_cit;
-	struct config_item_type tfc_tpg_nacl_stat_cit;
-	struct config_item_type tfc_tpg_mappedlun_cit;
-	struct config_item_type tfc_tpg_mappedlun_stat_cit;
-};
-
-struct target_fabric_configfs {
-	char			tf_name[TARGET_FABRIC_NAME_SIZE];
-	atomic_t		tf_access_cnt;
-	struct list_head	tf_list;
-	struct config_group	tf_group;
-	struct config_group	tf_disc_group;
-	struct config_group	*tf_default_groups[2];
-	/* Pointer to fabric's config_item */
-	struct config_item	*tf_fabric;
-	/* Passed from fabric modules */
-	struct config_item_type	*tf_fabric_cit;
-	/* Pointer to fabric's struct module */
-	struct module *tf_module;
-	struct target_core_fabric_ops tf_ops;
-	struct target_fabric_configfs_template tf_cit_tmpl;
-};
-
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index 0f4dc37..18afef9 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -4,20 +4,11 @@
 struct target_core_fabric_ops {
 	struct module *module;
 	const char *name;
+	size_t node_acl_size;
 	char *(*get_fabric_name)(void);
-	u8 (*get_fabric_proto_ident)(struct se_portal_group *);
 	char *(*tpg_get_wwn)(struct se_portal_group *);
 	u16 (*tpg_get_tag)(struct se_portal_group *);
 	u32 (*tpg_get_default_depth)(struct se_portal_group *);
-	u32 (*tpg_get_pr_transport_id)(struct se_portal_group *,
-				struct se_node_acl *,
-				struct t10_pr_registration *, int *,
-				unsigned char *);
-	u32 (*tpg_get_pr_transport_id_len)(struct se_portal_group *,
-				struct se_node_acl *,
-				struct t10_pr_registration *, int *);
-	char *(*tpg_parse_pr_out_transport_id)(struct se_portal_group *,
-				const char *, u32 *, char **);
 	int (*tpg_check_demo_mode)(struct se_portal_group *);
 	int (*tpg_check_demo_mode_cache)(struct se_portal_group *);
 	int (*tpg_check_demo_mode_write_protect)(struct se_portal_group *);
@@ -36,10 +27,6 @@
 	 * WRITE_STRIP and READ_INSERT operations.
 	 */
 	int (*tpg_check_prot_fabric_only)(struct se_portal_group *);
-	struct se_node_acl *(*tpg_alloc_fabric_acl)(
-					struct se_portal_group *);
-	void (*tpg_release_fabric_acl)(struct se_portal_group *,
-					struct se_node_acl *);
 	u32 (*tpg_get_inst_index)(struct se_portal_group *);
 	/*
 	 * Optional to release struct se_cmd and fabric dependent allocated
@@ -50,7 +37,6 @@
 	 */
 	int (*check_stop_free)(struct se_cmd *);
 	void (*release_cmd)(struct se_cmd *);
-	void (*put_session)(struct se_session *);
 	/*
 	 * Called with spin_lock_bh(struct se_portal_group->session_lock held.
 	 */
@@ -66,7 +52,6 @@
 	int (*write_pending)(struct se_cmd *);
 	int (*write_pending_status)(struct se_cmd *);
 	void (*set_default_node_attributes)(struct se_node_acl *);
-	u32 (*get_task_tag)(struct se_cmd *);
 	int (*get_cmd_state)(struct se_cmd *);
 	int (*queue_data_in)(struct se_cmd *);
 	int (*queue_status)(struct se_cmd *);
@@ -88,9 +73,8 @@
 	struct se_tpg_np *(*fabric_make_np)(struct se_portal_group *,
 				struct config_group *, const char *);
 	void (*fabric_drop_np)(struct se_tpg_np *);
-	struct se_node_acl *(*fabric_make_nodeacl)(struct se_portal_group *,
-				struct config_group *, const char *);
-	void (*fabric_drop_nodeacl)(struct se_node_acl *);
+	int (*fabric_init_nodeacl)(struct se_node_acl *, const char *);
+	void (*fabric_cleanup_nodeacl)(struct se_node_acl *);
 
 	struct configfs_attribute **tfc_discovery_attrs;
 	struct configfs_attribute **tfc_wwn_attrs;
@@ -132,16 +116,16 @@
 void	transport_init_se_cmd(struct se_cmd *,
 		const struct target_core_fabric_ops *,
 		struct se_session *, u32, int, int, unsigned char *);
-sense_reason_t transport_lookup_cmd_lun(struct se_cmd *, u32);
+sense_reason_t transport_lookup_cmd_lun(struct se_cmd *, u64);
 sense_reason_t target_setup_cmd_from_cdb(struct se_cmd *, unsigned char *);
 int	target_submit_cmd_map_sgls(struct se_cmd *, struct se_session *,
-		unsigned char *, unsigned char *, u32, u32, int, int, int,
+		unsigned char *, unsigned char *, u64, u32, int, int, int,
 		struct scatterlist *, u32, struct scatterlist *, u32,
 		struct scatterlist *, u32);
 int	target_submit_cmd(struct se_cmd *, struct se_session *, unsigned char *,
-		unsigned char *, u32, u32, int, int, int);
+		unsigned char *, u64, u32, int, int, int);
 int	target_submit_tmr(struct se_cmd *se_cmd, struct se_session *se_sess,
-		unsigned char *sense, u32 unpacked_lun,
+		unsigned char *sense, u64 unpacked_lun,
 		void *fabric_tmr_ptr, unsigned char tm_type,
 		gfp_t, unsigned int, int);
 int	transport_handle_cdb_direct(struct se_cmd *);
@@ -155,8 +139,8 @@
 int	transport_check_aborted_status(struct se_cmd *, int);
 int	transport_send_check_condition_and_sense(struct se_cmd *,
 		sense_reason_t, int);
-int	target_get_sess_cmd(struct se_session *, struct se_cmd *, bool);
-int	target_put_sess_cmd(struct se_session *, struct se_cmd *);
+int	target_get_sess_cmd(struct se_cmd *, bool);
+int	target_put_sess_cmd(struct se_cmd *);
 void	target_sess_cmd_list_set_waiting(struct se_session *);
 void	target_wait_for_sess_cmds(struct se_session *);
 
@@ -167,52 +151,19 @@
 int	transport_generic_handle_tmr(struct se_cmd *);
 void	transport_generic_request_failure(struct se_cmd *, sense_reason_t);
 void	__target_execute_cmd(struct se_cmd *);
-int	transport_lookup_tmr_lun(struct se_cmd *, u32);
+int	transport_lookup_tmr_lun(struct se_cmd *, u64);
 
 struct se_node_acl *core_tpg_get_initiator_node_acl(struct se_portal_group *tpg,
 		unsigned char *);
 struct se_node_acl *core_tpg_check_initiator_node_acl(struct se_portal_group *,
 		unsigned char *);
-void	core_tpg_clear_object_luns(struct se_portal_group *);
-struct se_node_acl *core_tpg_add_initiator_node_acl(struct se_portal_group *,
-		struct se_node_acl *, const char *, u32);
-int	core_tpg_del_initiator_node_acl(struct se_portal_group *,
-		struct se_node_acl *, int);
 int	core_tpg_set_initiator_node_queue_depth(struct se_portal_group *,
 		unsigned char *, u32, int);
 int	core_tpg_set_initiator_node_tag(struct se_portal_group *,
 		struct se_node_acl *, const char *);
-int	core_tpg_register(const struct target_core_fabric_ops *,
-		struct se_wwn *, struct se_portal_group *, void *, int);
+int	core_tpg_register(struct se_wwn *, struct se_portal_group *, int);
 int	core_tpg_deregister(struct se_portal_group *);
 
-/* SAS helpers */
-u8	sas_get_fabric_proto_ident(struct se_portal_group *);
-u32	sas_get_pr_transport_id(struct se_portal_group *, struct se_node_acl *,
-		struct t10_pr_registration *, int *, unsigned char *);
-u32	sas_get_pr_transport_id_len(struct se_portal_group *, struct se_node_acl *,
-		struct t10_pr_registration *, int *);
-char	*sas_parse_pr_out_transport_id(struct se_portal_group *, const char *,
-		u32 *, char **);
-
-/* FC helpers */
-u8	fc_get_fabric_proto_ident(struct se_portal_group *);
-u32	fc_get_pr_transport_id(struct se_portal_group *, struct se_node_acl *,
-		struct t10_pr_registration *, int *, unsigned char *);
-u32	fc_get_pr_transport_id_len(struct se_portal_group *, struct se_node_acl *,
-		struct t10_pr_registration *, int *);
-char	*fc_parse_pr_out_transport_id(struct se_portal_group *, const char *,
-		u32 *, char **);
-
-/* iSCSI helpers */
-u8	iscsi_get_fabric_proto_ident(struct se_portal_group *);
-u32	iscsi_get_pr_transport_id(struct se_portal_group *, struct se_node_acl *,
-		struct t10_pr_registration *, int *, unsigned char *);
-u32	iscsi_get_pr_transport_id_len(struct se_portal_group *, struct se_node_acl *,
-		struct t10_pr_registration *, int *);
-char	*iscsi_parse_pr_out_transport_id(struct se_portal_group *, const char *,
-		u32 *, char **);
-
 /*
  * The LIO target core uses DMA_TO_DEVICE to mean that data is going
  * to the target (eg handling a WRITE) and DMA_FROM_DEVICE to mean
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index d3f4832..b6fce90 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -313,6 +313,9 @@
 #define AMDGPU_VA_OP_MAP			1
 #define AMDGPU_VA_OP_UNMAP			2
 
+/* Delay the page table update till the next CS */
+#define AMDGPU_VM_DELAY_UPDATE		(1 << 0)
+
 /* Mapping flags */
 /* readable mapping */
 #define AMDGPU_VM_PAGE_READABLE		(1 << 1)
@@ -348,6 +351,7 @@
 
 #define AMDGPU_CHUNK_ID_IB		0x01
 #define AMDGPU_CHUNK_ID_FENCE		0x02
+#define AMDGPU_CHUNK_ID_DEPENDENCIES	0x03
 
 struct drm_amdgpu_cs_chunk {
 	uint32_t		chunk_id;
@@ -399,6 +403,14 @@
 	uint32_t ring;
 };
 
+struct drm_amdgpu_cs_chunk_dep {
+	uint32_t ip_type;
+	uint32_t ip_instance;
+	uint32_t ring;
+	uint32_t ctx_id;
+	uint64_t handle;
+};
+
 struct drm_amdgpu_cs_chunk_fence {
 	uint32_t handle;
 	uint32_t offset;
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 25084a0..c9aca04 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -755,4 +755,7 @@
 	uint64_t	dummy4;
 };
 
+/* Device ioctls: */
+#define FUSE_DEV_IOC_CLONE	_IOR(229, 0, uint32_t)
+
 #endif /* _LINUX_FUSE_H */
diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h
index 50ae243..3cb5e1d 100644
--- a/include/uapi/linux/if_tun.h
+++ b/include/uapi/linux/if_tun.h
@@ -50,6 +50,12 @@
 #define TUNGETFILTER _IOR('T', 219, struct sock_fprog)
 #define TUNSETVNETLE _IOW('T', 220, int)
 #define TUNGETVNETLE _IOR('T', 221, int)
+/* The TUNSETVNETBE and TUNGETVNETBE ioctls are for cross-endian support on
+ * little-endian hosts. Not all kernel configurations support them, but all
+ * configurations that support SET also support GET.
+ */
+#define TUNSETVNETBE _IOW('T', 222, int)
+#define TUNGETVNETBE _IOR('T', 223, int)
 
 /* TUNSETIFF ifr flags */
 #define IFF_TUN		0x0001
diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index 83d6236..eaf9491 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -19,8 +19,10 @@
 #define _UAPI_LINUX_IN_H
 
 #include <linux/types.h>
+#include <linux/libc-compat.h>
 #include <linux/socket.h>
 
+#if __UAPI_DEF_IN_IPPROTO
 /* Standard well-defined IP protocols.  */
 enum {
   IPPROTO_IP = 0,		/* Dummy protocol for TCP		*/
@@ -75,12 +77,14 @@
 #define IPPROTO_RAW		IPPROTO_RAW
   IPPROTO_MAX
 };
+#endif
 
-
+#if __UAPI_DEF_IN_ADDR
 /* Internet address. */
 struct in_addr {
 	__be32	s_addr;
 };
+#endif
 
 #define IP_TOS		1
 #define IP_TTL		2
@@ -158,6 +162,7 @@
 
 /* Request struct for multicast socket ops */
 
+#if __UAPI_DEF_IP_MREQ
 struct ip_mreq  {
 	struct in_addr imr_multiaddr;	/* IP multicast address of group */
 	struct in_addr imr_interface;	/* local IP address of interface */
@@ -209,14 +214,18 @@
 #define GROUP_FILTER_SIZE(numsrc) \
 	(sizeof(struct group_filter) - sizeof(struct __kernel_sockaddr_storage) \
 	+ (numsrc) * sizeof(struct __kernel_sockaddr_storage))
+#endif
 
+#if __UAPI_DEF_IN_PKTINFO
 struct in_pktinfo {
 	int		ipi_ifindex;
 	struct in_addr	ipi_spec_dst;
 	struct in_addr	ipi_addr;
 };
+#endif
 
 /* Structure describing an Internet (IP) socket address. */
+#if  __UAPI_DEF_SOCKADDR_IN
 #define __SOCK_SIZE__	16		/* sizeof(struct sockaddr)	*/
 struct sockaddr_in {
   __kernel_sa_family_t	sin_family;	/* Address family		*/
@@ -228,8 +237,9 @@
 			sizeof(unsigned short int) - sizeof(struct in_addr)];
 };
 #define sin_zero	__pad		/* for BSD UNIX comp. -FvK	*/
+#endif
 
-
+#if __UAPI_DEF_IN_CLASS
 /*
  * Definitions of the bits in an Internet address integer.
  * On subnets, host and network parts are found according
@@ -280,7 +290,7 @@
 #define INADDR_ALLHOSTS_GROUP 	0xe0000001U	/* 224.0.0.1   */
 #define INADDR_ALLRTRS_GROUP    0xe0000002U	/* 224.0.0.2 */
 #define INADDR_MAX_LOCAL_GROUP  0xe00000ffU	/* 224.0.0.255 */
-
+#endif
 
 /* <asm/byteorder.h> contains the htonl type stuff.. */
 #include <asm/byteorder.h> 
diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h
index fa673e9..7d024ce 100644
--- a/include/uapi/linux/libc-compat.h
+++ b/include/uapi/linux/libc-compat.h
@@ -56,6 +56,13 @@
 
 /* GLIBC headers included first so don't define anything
  * that would already be defined. */
+#define __UAPI_DEF_IN_ADDR		0
+#define __UAPI_DEF_IN_IPPROTO		0
+#define __UAPI_DEF_IN_PKTINFO		0
+#define __UAPI_DEF_IP_MREQ		0
+#define __UAPI_DEF_SOCKADDR_IN		0
+#define __UAPI_DEF_IN_CLASS		0
+
 #define __UAPI_DEF_IN6_ADDR		0
 /* The exception is the in6_addr macros which must be defined
  * if the glibc code didn't define them. This guard matches
@@ -78,6 +85,13 @@
 /* Linux headers included first, and we must define everything
  * we need. The expectation is that glibc will check the
  * __UAPI_DEF_* defines and adjust appropriately. */
+#define __UAPI_DEF_IN_ADDR		1
+#define __UAPI_DEF_IN_IPPROTO		1
+#define __UAPI_DEF_IN_PKTINFO		1
+#define __UAPI_DEF_IP_MREQ		1
+#define __UAPI_DEF_SOCKADDR_IN		1
+#define __UAPI_DEF_IN_CLASS		1
+
 #define __UAPI_DEF_IN6_ADDR		1
 /* We unconditionally define the in6_addr macros and glibc must
  * coordinate. */
@@ -103,6 +117,14 @@
  * that we need. */
 #else /* !defined(__GLIBC__) */
 
+/* Definitions for in.h */
+#define __UAPI_DEF_IN_ADDR		1
+#define __UAPI_DEF_IN_IPPROTO		1
+#define __UAPI_DEF_IN_PKTINFO		1
+#define __UAPI_DEF_IP_MREQ		1
+#define __UAPI_DEF_SOCKADDR_IN		1
+#define __UAPI_DEF_IN_CLASS		1
+
 /* Definitions for in6.h */
 #define __UAPI_DEF_IN6_ADDR		1
 #define __UAPI_DEF_IN6_ADDR_ALT		1
diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
index bb6a5b4..ab373191 100644
--- a/include/uapi/linux/vhost.h
+++ b/include/uapi/linux/vhost.h
@@ -103,6 +103,20 @@
 /* Get accessor: reads index, writes value in num */
 #define VHOST_GET_VRING_BASE _IOWR(VHOST_VIRTIO, 0x12, struct vhost_vring_state)
 
+/* Set the vring byte order in num. Valid values are VHOST_VRING_LITTLE_ENDIAN
+ * or VHOST_VRING_BIG_ENDIAN (other values return -EINVAL).
+ * The byte order cannot be changed while the device is active: trying to do so
+ * returns -EBUSY.
+ * This is a legacy only API that is simply ignored when VIRTIO_F_VERSION_1 is
+ * set.
+ * Not all kernel configurations support this ioctl, but all configurations that
+ * support SET also support GET.
+ */
+#define VHOST_VRING_LITTLE_ENDIAN 0
+#define VHOST_VRING_BIG_ENDIAN 1
+#define VHOST_SET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x13, struct vhost_vring_state)
+#define VHOST_GET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x14, struct vhost_vring_state)
+
 /* The following ioctls use eventfd file descriptors to signal and poll
  * for events. */
 
diff --git a/init/Kconfig b/init/Kconfig
index 7d1ffd2..af09b4f 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -435,6 +435,7 @@
 config TASK_DELAY_ACCT
 	bool "Enable per-task delay accounting"
 	depends on TASKSTATS
+	select SCHED_INFO
 	help
 	  Collect information on time spent by a task waiting for system
 	  resources like cpu, synchronous block I/O completion and swapping
@@ -820,7 +821,7 @@
 
 config LOG_BUF_SHIFT
 	int "Kernel log buffer size (16 => 64KB, 17 => 128KB)"
-	range 12 21
+	range 12 25
 	default 17
 	depends on PRINTK
 	help
@@ -1941,26 +1942,21 @@
 	bool "Compress modules on installation"
 	depends on MODULES
 	help
-	  This option compresses the kernel modules when 'make
-	  modules_install' is run.
 
-	  The modules will be compressed either using gzip or xz depend on the
-	  choice made in "Compression algorithm".
+	  Compresses kernel modules when 'make modules_install' is run; gzip or
+	  xz depending on "Compression algorithm" below.
 
-	  module-init-tools has support for gzip format while kmod handle gzip
-	  and xz compressed modules.
+	  module-init-tools MAY support gzip, and kmod MAY support gzip and xz.
 
-	  When a kernel module is installed from outside of the main kernel
-	  source and uses the Kbuild system for installing modules then that
-	  kernel module will also be compressed when it is installed.
+	  Out-of-tree kernel modules installed using Kbuild will also be
+	  compressed upon installation.
 
-	  This option provides little benefit when the modules are to be used inside
-	  an initrd or initramfs, it generally is more efficient to compress the whole
-	  initrd or initramfs instead.
+	  Note: for modules inside an initrd or initramfs, it's more efficient
+	  to compress the whole initrd or initramfs instead.
 
-	  This is fully compatible with signed modules while the signed module is
-	  compressed. module-init-tools or kmod handles decompression and provide to
-	  other layer the uncompressed but signed payload.
+	  Note: This is fully compatible with signed modules.
+
+	  If in doubt, say N.
 
 choice
 	prompt "Compression algorithm"
@@ -1982,6 +1978,10 @@
 
 endif # MODULES
 
+config MODULES_TREE_LOOKUP
+	def_bool y
+	depends on PERF_EVENTS || TRACING
+
 config INIT_ALL_POSSIBLE
 	bool
 	help
diff --git a/init/main.c b/init/main.c
index c599aea..c5d5626 100644
--- a/init/main.c
+++ b/init/main.c
@@ -1004,6 +1004,8 @@
 	smp_init();
 	sched_init_smp();
 
+	page_alloc_init_late();
+
 	do_basic_setup();
 
 	/* Open the /dev/console on the rootfs, this should never fail */
diff --git a/ipc/msg.c b/ipc/msg.c
index 2b6fdbb..66c4f56 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -76,7 +76,7 @@
 
 static inline struct msg_queue *msq_obtain_object(struct ipc_namespace *ns, int id)
 {
-	struct kern_ipc_perm *ipcp = ipc_obtain_object(&msg_ids(ns), id);
+	struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&msg_ids(ns), id);
 
 	if (IS_ERR(ipcp))
 		return ERR_CAST(ipcp);
@@ -196,7 +196,7 @@
 		 * or dealing with -EAGAIN cases. See lockless receive part 1
 		 * and 2 in do_msgrcv().
 		 */
-		smp_mb();
+		smp_wmb(); /* barrier (B) */
 		msr->r_msg = ERR_PTR(res);
 	}
 }
@@ -580,7 +580,8 @@
 				/* initialize pipelined send ordering */
 				msr->r_msg = NULL;
 				wake_up_process(msr->r_tsk);
-				smp_mb(); /* see barrier comment below */
+				/* barrier (B) see barrier comment below */
+				smp_wmb();
 				msr->r_msg = ERR_PTR(-E2BIG);
 			} else {
 				msr->r_msg = NULL;
@@ -589,11 +590,12 @@
 				wake_up_process(msr->r_tsk);
 				/*
 				 * Ensure that the wakeup is visible before
-				 * setting r_msg, as the receiving end depends
-				 * on it. See lockless receive part 1 and 2 in
-				 * do_msgrcv().
+				 * setting r_msg, as the receiving can otherwise
+				 * exit - once r_msg is set, the receiver can
+				 * continue. See lockless receive part 1 and 2
+				 * in do_msgrcv(). Barrier (B).
 				 */
-				smp_mb();
+				smp_wmb();
 				msr->r_msg = msg;
 
 				return 1;
@@ -932,12 +934,38 @@
 		/* Lockless receive, part 2:
 		 * Wait until pipelined_send or expunge_all are outside of
 		 * wake_up_process(). There is a race with exit(), see
-		 * ipc/mqueue.c for the details.
+		 * ipc/mqueue.c for the details. The correct serialization
+		 * ensures that a receiver cannot continue without the wakeup
+		 * being visibible _before_ setting r_msg:
+		 *
+		 * CPU 0                             CPU 1
+		 * <loop receiver>
+		 *   smp_rmb(); (A) <-- pair -.      <waker thread>
+		 *   <load ->r_msg>           |        msr->r_msg = NULL;
+		 *                            |        wake_up_process();
+		 * <continue>                 `------> smp_wmb(); (B)
+		 *                                     msr->r_msg = msg;
+		 *
+		 * Where (A) orders the message value read and where (B) orders
+		 * the write to the r_msg -- done in both pipelined_send and
+		 * expunge_all.
 		 */
-		msg = (struct msg_msg *)msr_d.r_msg;
-		while (msg == NULL) {
-			cpu_relax();
+		for (;;) {
+			/*
+			 * Pairs with writer barrier in pipelined_send
+			 * or expunge_all.
+			 */
+			smp_rmb(); /* barrier (A) */
 			msg = (struct msg_msg *)msr_d.r_msg;
+			if (msg)
+				break;
+
+			/*
+			 * The cpu_relax() call is a compiler barrier
+			 * which forces everything in this loop to be
+			 * re-loaded.
+			 */
+			cpu_relax();
 		}
 
 		/* Lockless receive, part 3:
diff --git a/ipc/sem.c b/ipc/sem.c
index d1a6edd..bc3d530 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -391,7 +391,7 @@
 	struct kern_ipc_perm *ipcp;
 	struct sem_array *sma;
 
-	ipcp = ipc_obtain_object(&sem_ids(ns), id);
+	ipcp = ipc_obtain_object_idr(&sem_ids(ns), id);
 	if (IS_ERR(ipcp))
 		return ERR_CAST(ipcp);
 
@@ -410,7 +410,7 @@
 
 static inline struct sem_array *sem_obtain_object(struct ipc_namespace *ns, int id)
 {
-	struct kern_ipc_perm *ipcp = ipc_obtain_object(&sem_ids(ns), id);
+	struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&sem_ids(ns), id);
 
 	if (IS_ERR(ipcp))
 		return ERR_CAST(ipcp);
diff --git a/ipc/shm.c b/ipc/shm.c
index 6d76707..06e5cf2 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -129,7 +129,7 @@
 
 static inline struct shmid_kernel *shm_obtain_object(struct ipc_namespace *ns, int id)
 {
-	struct kern_ipc_perm *ipcp = ipc_obtain_object(&shm_ids(ns), id);
+	struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&shm_ids(ns), id);
 
 	if (IS_ERR(ipcp))
 		return ERR_CAST(ipcp);
@@ -155,8 +155,11 @@
 {
 	struct kern_ipc_perm *ipcp = ipc_lock(&shm_ids(ns), id);
 
-	if (IS_ERR(ipcp))
-		return (struct shmid_kernel *)ipcp;
+	/*
+	 * We raced in the idr lookup or with shm_destroy().  Either way, the
+	 * ID is busted.
+	 */
+	BUG_ON(IS_ERR(ipcp));
 
 	return container_of(ipcp, struct shmid_kernel, shm_perm);
 }
@@ -191,7 +194,6 @@
 	struct shmid_kernel *shp;
 
 	shp = shm_lock(sfd->ns, sfd->id);
-	BUG_ON(IS_ERR(shp));
 	shp->shm_atim = get_seconds();
 	shp->shm_lprid = task_tgid_vnr(current);
 	shp->shm_nattch++;
@@ -258,7 +260,6 @@
 	down_write(&shm_ids(ns).rwsem);
 	/* remove from the list of attaches of the shm segment */
 	shp = shm_lock(ns, sfd->id);
-	BUG_ON(IS_ERR(shp));
 	shp->shm_lprid = task_tgid_vnr(current);
 	shp->shm_dtim = get_seconds();
 	shp->shm_nattch--;
@@ -1191,7 +1192,6 @@
 out_nattch:
 	down_write(&shm_ids(ns).rwsem);
 	shp = shm_lock(ns, shmid);
-	BUG_ON(IS_ERR(shp));
 	shp->shm_nattch--;
 	if (shm_may_destroy(ns, shp))
 		shm_destroy(ns, shp);
diff --git a/ipc/util.c b/ipc/util.c
index ff3323e..be42300 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -467,10 +467,7 @@
 {
 	struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
 
-	if (is_vmalloc_addr(p))
-		vfree(p);
-	else
-		kfree(p);
+	kvfree(p);
 }
 
 /**
@@ -558,7 +555,7 @@
  * Call inside the RCU critical section.
  * The ipc object is *not* locked on exit.
  */
-struct kern_ipc_perm *ipc_obtain_object(struct ipc_ids *ids, int id)
+struct kern_ipc_perm *ipc_obtain_object_idr(struct ipc_ids *ids, int id)
 {
 	struct kern_ipc_perm *out;
 	int lid = ipcid_to_idx(id);
@@ -584,21 +581,24 @@
 	struct kern_ipc_perm *out;
 
 	rcu_read_lock();
-	out = ipc_obtain_object(ids, id);
+	out = ipc_obtain_object_idr(ids, id);
 	if (IS_ERR(out))
-		goto err1;
+		goto err;
 
 	spin_lock(&out->lock);
 
-	/* ipc_rmid() may have already freed the ID while ipc_lock
-	 * was spinning: here verify that the structure is still valid
+	/*
+	 * ipc_rmid() may have already freed the ID while ipc_lock()
+	 * was spinning: here verify that the structure is still valid.
+	 * Upon races with RMID, return -EIDRM, thus indicating that
+	 * the ID points to a removed identifier.
 	 */
 	if (ipc_valid_object(out))
 		return out;
 
 	spin_unlock(&out->lock);
-	out = ERR_PTR(-EINVAL);
-err1:
+	out = ERR_PTR(-EIDRM);
+err:
 	rcu_read_unlock();
 	return out;
 }
@@ -608,7 +608,7 @@
  * @ids: ipc identifier set
  * @id: ipc id to look for
  *
- * Similar to ipc_obtain_object() but also checks
+ * Similar to ipc_obtain_object_idr() but also checks
  * the ipc object reference counter.
  *
  * Call inside the RCU critical section.
@@ -616,13 +616,13 @@
  */
 struct kern_ipc_perm *ipc_obtain_object_check(struct ipc_ids *ids, int id)
 {
-	struct kern_ipc_perm *out = ipc_obtain_object(ids, id);
+	struct kern_ipc_perm *out = ipc_obtain_object_idr(ids, id);
 
 	if (IS_ERR(out))
 		goto out;
 
 	if (ipc_checkid(out, id))
-		return ERR_PTR(-EIDRM);
+		return ERR_PTR(-EINVAL);
 out:
 	return out;
 }
diff --git a/ipc/util.h b/ipc/util.h
index 1a5a0fc..3a8a5a0 100644
--- a/ipc/util.h
+++ b/ipc/util.h
@@ -132,7 +132,7 @@
 void ipc_rcu_free(struct rcu_head *head);
 
 struct kern_ipc_perm *ipc_lock(struct ipc_ids *, int);
-struct kern_ipc_perm *ipc_obtain_object(struct ipc_ids *ids, int id);
+struct kern_ipc_perm *ipc_obtain_object_idr(struct ipc_ids *ids, int id);
 
 void kernel_to_ipc64_perm(struct kern_ipc_perm *in, struct ipc64_perm *out);
 void ipc64_perm_to_ipc_perm(struct ipc64_perm *in, struct ipc_perm *out);
diff --git a/kernel/Makefile b/kernel/Makefile
index 60c302c..43c4c92 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -137,7 +137,7 @@
 
 ifneq ($(wildcard $(obj)/.x509.list),)
 ifneq ($(shell cat $(obj)/.x509.list),$(X509_CERTIFICATES))
-$(info X.509 certificate list changed)
+$(warning X.509 certificate list changed to "$(X509_CERTIFICATES)" from "$(shell cat $(obj)/.x509.list)")
 $(shell rm $(obj)/.x509.list)
 endif
 endif
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 9ef9fc8..f89d929 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1939,8 +1939,6 @@
 	.kill_sb = cgroup_kill_sb,
 };
 
-static struct kobject *cgroup_kobj;
-
 /**
  * task_cgroup_path - cgroup path of a task in the first cgroup hierarchy
  * @task: target task
@@ -5070,13 +5068,13 @@
 			ss->bind(init_css_set.subsys[ssid]);
 	}
 
-	cgroup_kobj = kobject_create_and_add("cgroup", fs_kobj);
-	if (!cgroup_kobj)
-		return -ENOMEM;
+	err = sysfs_create_mount_point(fs_kobj, "cgroup");
+	if (err)
+		return err;
 
 	err = register_filesystem(&cgroup_fs_type);
 	if (err < 0) {
-		kobject_put(cgroup_kobj);
+		sysfs_remove_mount_point(fs_kobj, "cgroup");
 		return err;
 	}
 
diff --git a/kernel/configs/xen.config b/kernel/configs/xen.config
new file mode 100644
index 0000000..ff75622
--- /dev/null
+++ b/kernel/configs/xen.config
@@ -0,0 +1,48 @@
+# global stuff - these enable us to allow some
+# of the not so generic stuff below for xen
+CONFIG_PARAVIRT=y
+CONFIG_NET=y
+CONFIG_NET_CORE=y
+CONFIG_NETDEVICES=y
+CONFIG_BLOCK=y
+CONFIG_WATCHDOG=y
+CONFIG_TARGET_CORE=y
+CONFIG_SCSI=y
+CONFIG_FB=y
+CONFIG_INPUT_MISC=y
+CONFIG_MEMORY_HOTPLUG=y
+CONFIG_TTY=y
+# Technically not required but otherwise produces
+# pretty useless systems starting from allnoconfig
+# You want TCP/IP and ELF binaries right?
+CONFIG_INET=y
+CONFIG_BINFMT_ELF=y
+# generic config
+CONFIG_XEN=y
+CONFIG_XEN_DOM0=y
+# backend drivers
+CONFIG_XEN_BACKEND=y
+CONFIG_XEN_BLKDEV_BACKEND=m
+CONFIG_XEN_NETDEV_BACKEND=m
+CONFIG_HVC_XEN=y
+CONFIG_XEN_WDT=m
+CONFIG_XEN_SCSI_BACKEND=m
+# frontend drivers
+CONFIG_XEN_FBDEV_FRONTEND=m
+CONFIG_HVC_XEN_FRONTEND=y
+CONFIG_INPUT_XEN_KBDDEV_FRONTEND=m
+CONFIG_XEN_SCSI_FRONTEND=m
+# others
+CONFIG_XEN_BALLOON=y
+CONFIG_XEN_SCRUB_PAGES=y
+CONFIG_XEN_DEV_EVTCHN=m
+CONFIG_XEN_BLKDEV_FRONTEND=m
+CONFIG_XEN_NETDEV_FRONTEND=m
+CONFIG_XENFS=m
+CONFIG_XEN_COMPAT_XENFS=y
+CONFIG_XEN_SYS_HYPERVISOR=y
+CONFIG_XEN_XENBUS_FRONTEND=y
+CONFIG_XEN_GNTDEV=m
+CONFIG_XEN_GRANT_DEV_ALLOC=m
+CONFIG_SWIOTLB_XEN=y
+CONFIG_XEN_PRIVCMD=m
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d1f37dd..d3dae34 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4358,14 +4358,6 @@
 	rcu_read_unlock();
 }
 
-static void rb_free_rcu(struct rcu_head *rcu_head)
-{
-	struct ring_buffer *rb;
-
-	rb = container_of(rcu_head, struct ring_buffer, rcu_head);
-	rb_free(rb);
-}
-
 struct ring_buffer *ring_buffer_get(struct perf_event *event)
 {
 	struct ring_buffer *rb;
@@ -5794,7 +5786,7 @@
 		 * need to add enough zero bytes after the string to handle
 		 * the 64bit alignment we do later.
 		 */
-		name = d_path(&file->f_path, buf, PATH_MAX - sizeof(u64));
+		name = file_path(file, buf, PATH_MAX - sizeof(u64));
 		if (IS_ERR(name)) {
 			name = "//toolong";
 			goto cpy_name;
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 2deb24c..2bbad9c 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -11,6 +11,7 @@
 struct ring_buffer {
 	atomic_t			refcount;
 	struct rcu_head			rcu_head;
+	struct irq_work			irq_work;
 #ifdef CONFIG_PERF_USE_VMALLOC
 	struct work_struct		work;
 	int				page_order;	/* allocation order  */
@@ -55,6 +56,15 @@
 };
 
 extern void rb_free(struct ring_buffer *rb);
+
+static inline void rb_free_rcu(struct rcu_head *rcu_head)
+{
+	struct ring_buffer *rb;
+
+	rb = container_of(rcu_head, struct ring_buffer, rcu_head);
+	rb_free(rb);
+}
+
 extern struct ring_buffer *
 rb_alloc(int nr_pages, long watermark, int cpu, int flags);
 extern void perf_event_wakeup(struct perf_event *event);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 9647282..b2be01b 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -221,6 +221,8 @@
 	rcu_read_unlock();
 }
 
+static void rb_irq_work(struct irq_work *work);
+
 static void
 ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
 {
@@ -241,6 +243,16 @@
 
 	INIT_LIST_HEAD(&rb->event_list);
 	spin_lock_init(&rb->event_lock);
+	init_irq_work(&rb->irq_work, rb_irq_work);
+}
+
+static void ring_buffer_put_async(struct ring_buffer *rb)
+{
+	if (!atomic_dec_and_test(&rb->refcount))
+		return;
+
+	rb->rcu_head.next = (void *)rb;
+	irq_work_queue(&rb->irq_work);
 }
 
 /*
@@ -319,7 +331,7 @@
 	rb_free_aux(rb);
 
 err:
-	ring_buffer_put(rb);
+	ring_buffer_put_async(rb);
 	handle->event = NULL;
 
 	return NULL;
@@ -370,7 +382,7 @@
 
 	local_set(&rb->aux_nest, 0);
 	rb_free_aux(rb);
-	ring_buffer_put(rb);
+	ring_buffer_put_async(rb);
 }
 
 /*
@@ -557,7 +569,18 @@
 void rb_free_aux(struct ring_buffer *rb)
 {
 	if (atomic_dec_and_test(&rb->aux_refcount))
+		irq_work_queue(&rb->irq_work);
+}
+
+static void rb_irq_work(struct irq_work *work)
+{
+	struct ring_buffer *rb = container_of(work, struct ring_buffer, irq_work);
+
+	if (!atomic_read(&rb->aux_refcount))
 		__rb_free_aux(rb);
+
+	if (rb->rcu_head.next == (void *)rb)
+		call_rcu(&rb->rcu_head, rb_free_rcu);
 }
 
 #ifndef CONFIG_PERF_USE_VMALLOC
diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c
index a744098..7080ae1 100644
--- a/kernel/gcov/base.c
+++ b/kernel/gcov/base.c
@@ -92,6 +92,12 @@
 }
 EXPORT_SYMBOL(__gcov_merge_time_profile);
 
+void __gcov_merge_icall_topn(gcov_type *counters, unsigned int n_counters)
+{
+	/* Unused. */
+}
+EXPORT_SYMBOL(__gcov_merge_icall_topn);
+
 /**
  * gcov_enable_events - enable event reporting through gcov_event()
  *
diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c
index 826ba9f..e25e92f 100644
--- a/kernel/gcov/gcc_4_7.c
+++ b/kernel/gcov/gcc_4_7.c
@@ -18,7 +18,9 @@
 #include <linux/vmalloc.h>
 #include "gcov.h"
 
-#if __GNUC__ == 4 && __GNUC_MINOR__ >= 9
+#if __GNUC__ == 5 && __GNUC_MINOR__ >= 1
+#define GCOV_COUNTERS			10
+#elif __GNUC__ == 4 && __GNUC_MINOR__ >= 9
 #define GCOV_COUNTERS			9
 #else
 #define GCOV_COUNTERS			8
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 9019f15..52ebaca 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -302,7 +302,7 @@
 			continue;
 
 		key = iterk;
-		if (__module_address(iter->key) == mod) {
+		if (within_module(iter->key, mod)) {
 			/*
 			 * Set key->entries to iter, but preserve JUMP_LABEL_TRUE_BRANCH.
 			 */
@@ -339,7 +339,7 @@
 
 		key = (struct static_key *)(unsigned long)iter->key;
 
-		if (__module_address(iter->key) == mod)
+		if (within_module(iter->key, mod))
 			continue;
 
 		prev = &key->next;
@@ -443,14 +443,16 @@
 {
 	struct jump_entry *stop = __stop___jump_table;
 	struct jump_entry *entry = jump_label_get_entries(key);
-
 #ifdef CONFIG_MODULES
-	struct module *mod = __module_address((unsigned long)key);
+	struct module *mod;
 
 	__jump_label_mod_update(key, enable);
 
+	preempt_disable();
+	mod = __module_address((unsigned long)key);
 	if (mod)
 		stop = mod->jump_entries + mod->num_jump_entries;
+	preempt_enable();
 #endif
 	/* if there are no users, entry can be NULL */
 	if (entry)
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 7a36fdc..a785c10 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -84,6 +84,17 @@
 
 int kexec_should_crash(struct task_struct *p)
 {
+	/*
+	 * If crash_kexec_post_notifiers is enabled, don't run
+	 * crash_kexec() here yet, which must be run after panic
+	 * notifiers in panic().
+	 */
+	if (crash_kexec_post_notifiers)
+		return 0;
+	/*
+	 * There are 4 panic() calls in do_exit() path, each of which
+	 * corresponds to each of these 4 conditions.
+	 */
 	if (in_interrupt() || !p->pid || is_global_init(p) || panic_on_oops)
 		return 1;
 	return 0;
diff --git a/kernel/module.c b/kernel/module.c
index f80a97f..3e0e197 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -101,48 +101,201 @@
 DEFINE_MUTEX(module_mutex);
 EXPORT_SYMBOL_GPL(module_mutex);
 static LIST_HEAD(modules);
+
+#ifdef CONFIG_MODULES_TREE_LOOKUP
+
+/*
+ * Use a latched RB-tree for __module_address(); this allows us to use
+ * RCU-sched lookups of the address from any context.
+ *
+ * Because modules have two address ranges: init and core, we need two
+ * latch_tree_nodes entries. Therefore we need the back-pointer from
+ * mod_tree_node.
+ *
+ * Because init ranges are short lived we mark them unlikely and have placed
+ * them outside the critical cacheline in struct module.
+ *
+ * This is conditional on PERF_EVENTS || TRACING because those can really hit
+ * __module_address() hard by doing a lot of stack unwinding; potentially from
+ * NMI context.
+ */
+
+static __always_inline unsigned long __mod_tree_val(struct latch_tree_node *n)
+{
+	struct mod_tree_node *mtn = container_of(n, struct mod_tree_node, node);
+	struct module *mod = mtn->mod;
+
+	if (unlikely(mtn == &mod->mtn_init))
+		return (unsigned long)mod->module_init;
+
+	return (unsigned long)mod->module_core;
+}
+
+static __always_inline unsigned long __mod_tree_size(struct latch_tree_node *n)
+{
+	struct mod_tree_node *mtn = container_of(n, struct mod_tree_node, node);
+	struct module *mod = mtn->mod;
+
+	if (unlikely(mtn == &mod->mtn_init))
+		return (unsigned long)mod->init_size;
+
+	return (unsigned long)mod->core_size;
+}
+
+static __always_inline bool
+mod_tree_less(struct latch_tree_node *a, struct latch_tree_node *b)
+{
+	return __mod_tree_val(a) < __mod_tree_val(b);
+}
+
+static __always_inline int
+mod_tree_comp(void *key, struct latch_tree_node *n)
+{
+	unsigned long val = (unsigned long)key;
+	unsigned long start, end;
+
+	start = __mod_tree_val(n);
+	if (val < start)
+		return -1;
+
+	end = start + __mod_tree_size(n);
+	if (val >= end)
+		return 1;
+
+	return 0;
+}
+
+static const struct latch_tree_ops mod_tree_ops = {
+	.less = mod_tree_less,
+	.comp = mod_tree_comp,
+};
+
+static struct mod_tree_root {
+	struct latch_tree_root root;
+	unsigned long addr_min;
+	unsigned long addr_max;
+} mod_tree __cacheline_aligned = {
+	.addr_min = -1UL,
+};
+
+#define module_addr_min mod_tree.addr_min
+#define module_addr_max mod_tree.addr_max
+
+static noinline void __mod_tree_insert(struct mod_tree_node *node)
+{
+	latch_tree_insert(&node->node, &mod_tree.root, &mod_tree_ops);
+}
+
+static void __mod_tree_remove(struct mod_tree_node *node)
+{
+	latch_tree_erase(&node->node, &mod_tree.root, &mod_tree_ops);
+}
+
+/*
+ * These modifications: insert, remove_init and remove; are serialized by the
+ * module_mutex.
+ */
+static void mod_tree_insert(struct module *mod)
+{
+	mod->mtn_core.mod = mod;
+	mod->mtn_init.mod = mod;
+
+	__mod_tree_insert(&mod->mtn_core);
+	if (mod->init_size)
+		__mod_tree_insert(&mod->mtn_init);
+}
+
+static void mod_tree_remove_init(struct module *mod)
+{
+	if (mod->init_size)
+		__mod_tree_remove(&mod->mtn_init);
+}
+
+static void mod_tree_remove(struct module *mod)
+{
+	__mod_tree_remove(&mod->mtn_core);
+	mod_tree_remove_init(mod);
+}
+
+static struct module *mod_find(unsigned long addr)
+{
+	struct latch_tree_node *ltn;
+
+	ltn = latch_tree_find((void *)addr, &mod_tree.root, &mod_tree_ops);
+	if (!ltn)
+		return NULL;
+
+	return container_of(ltn, struct mod_tree_node, node)->mod;
+}
+
+#else /* MODULES_TREE_LOOKUP */
+
+static unsigned long module_addr_min = -1UL, module_addr_max = 0;
+
+static void mod_tree_insert(struct module *mod) { }
+static void mod_tree_remove_init(struct module *mod) { }
+static void mod_tree_remove(struct module *mod) { }
+
+static struct module *mod_find(unsigned long addr)
+{
+	struct module *mod;
+
+	list_for_each_entry_rcu(mod, &modules, list) {
+		if (within_module(addr, mod))
+			return mod;
+	}
+
+	return NULL;
+}
+
+#endif /* MODULES_TREE_LOOKUP */
+
+/*
+ * Bounds of module text, for speeding up __module_address.
+ * Protected by module_mutex.
+ */
+static void __mod_update_bounds(void *base, unsigned int size)
+{
+	unsigned long min = (unsigned long)base;
+	unsigned long max = min + size;
+
+	if (min < module_addr_min)
+		module_addr_min = min;
+	if (max > module_addr_max)
+		module_addr_max = max;
+}
+
+static void mod_update_bounds(struct module *mod)
+{
+	__mod_update_bounds(mod->module_core, mod->core_size);
+	if (mod->init_size)
+		__mod_update_bounds(mod->module_init, mod->init_size);
+}
+
 #ifdef CONFIG_KGDB_KDB
 struct list_head *kdb_modules = &modules; /* kdb needs the list of modules */
 #endif /* CONFIG_KGDB_KDB */
 
-#ifdef CONFIG_MODULE_SIG
-#ifdef CONFIG_MODULE_SIG_FORCE
-static bool sig_enforce = true;
-#else
-static bool sig_enforce = false;
-
-static int param_set_bool_enable_only(const char *val,
-				      const struct kernel_param *kp)
+static void module_assert_mutex(void)
 {
-	int err;
-	bool test;
-	struct kernel_param dummy_kp = *kp;
-
-	dummy_kp.arg = &test;
-
-	err = param_set_bool(val, &dummy_kp);
-	if (err)
-		return err;
-
-	/* Don't let them unset it once it's set! */
-	if (!test && sig_enforce)
-		return -EROFS;
-
-	if (test)
-		sig_enforce = true;
-	return 0;
+	lockdep_assert_held(&module_mutex);
 }
 
-static const struct kernel_param_ops param_ops_bool_enable_only = {
-	.flags = KERNEL_PARAM_OPS_FL_NOARG,
-	.set = param_set_bool_enable_only,
-	.get = param_get_bool,
-};
-#define param_check_bool_enable_only param_check_bool
+static void module_assert_mutex_or_preempt(void)
+{
+#ifdef CONFIG_LOCKDEP
+	if (unlikely(!debug_locks))
+		return;
 
+	WARN_ON(!rcu_read_lock_sched_held() &&
+		!lockdep_is_held(&module_mutex));
+#endif
+}
+
+static bool sig_enforce = IS_ENABLED(CONFIG_MODULE_SIG_FORCE);
+#ifndef CONFIG_MODULE_SIG_FORCE
 module_param(sig_enforce, bool_enable_only, 0644);
 #endif /* !CONFIG_MODULE_SIG_FORCE */
-#endif /* CONFIG_MODULE_SIG */
 
 /* Block module loading/unloading? */
 int modules_disabled = 0;
@@ -153,10 +306,6 @@
 
 static BLOCKING_NOTIFIER_HEAD(module_notify_list);
 
-/* Bounds of module allocation, for speeding __module_address.
- * Protected by module_mutex. */
-static unsigned long module_addr_min = -1UL, module_addr_max = 0;
-
 int register_module_notifier(struct notifier_block *nb)
 {
 	return blocking_notifier_chain_register(&module_notify_list, nb);
@@ -318,6 +467,8 @@
 #endif
 	};
 
+	module_assert_mutex_or_preempt();
+
 	if (each_symbol_in_section(arr, ARRAY_SIZE(arr), NULL, fn, data))
 		return true;
 
@@ -457,6 +608,8 @@
 {
 	struct module *mod;
 
+	module_assert_mutex();
+
 	list_for_each_entry(mod, &modules, list) {
 		if (!even_unformed && mod->state == MODULE_STATE_UNFORMED)
 			continue;
@@ -1169,11 +1322,17 @@
 {
 	const unsigned long *crc;
 
-	/* Since this should be found in kernel (which can't be removed),
-	 * no locking is necessary. */
+	/*
+	 * Since this should be found in kernel (which can't be removed), no
+	 * locking is necessary -- use preempt_disable() to placate lockdep.
+	 */
+	preempt_disable();
 	if (!find_symbol(VMLINUX_SYMBOL_STR(module_layout), NULL,
-			 &crc, true, false))
+			 &crc, true, false)) {
+		preempt_enable();
 		BUG();
+	}
+	preempt_enable();
 	return check_version(sechdrs, versindex,
 			     VMLINUX_SYMBOL_STR(module_layout), mod, crc,
 			     NULL);
@@ -1661,6 +1820,10 @@
 	mod_kobject_put(mod);
 }
 
+static void init_param_lock(struct module *mod)
+{
+	mutex_init(&mod->param_lock);
+}
 #else /* !CONFIG_SYSFS */
 
 static int mod_sysfs_setup(struct module *mod,
@@ -1683,6 +1846,9 @@
 {
 }
 
+static void init_param_lock(struct module *mod)
+{
+}
 #endif /* CONFIG_SYSFS */
 
 static void mod_sysfs_teardown(struct module *mod)
@@ -1852,10 +2018,11 @@
 	mutex_lock(&module_mutex);
 	/* Unlink carefully: kallsyms could be walking list. */
 	list_del_rcu(&mod->list);
+	mod_tree_remove(mod);
 	/* Remove this module from bug list, this uses list_del_rcu */
 	module_bug_cleanup(mod);
-	/* Wait for RCU synchronizing before releasing mod->list and buglist. */
-	synchronize_rcu();
+	/* Wait for RCU-sched synchronizing before releasing mod->list and buglist. */
+	synchronize_sched();
 	mutex_unlock(&module_mutex);
 
 	/* This may be NULL, but that's OK */
@@ -2384,22 +2551,6 @@
 	return vmalloc_exec(size);
 }
 
-static void *module_alloc_update_bounds(unsigned long size)
-{
-	void *ret = module_alloc(size);
-
-	if (ret) {
-		mutex_lock(&module_mutex);
-		/* Update module bounds. */
-		if ((unsigned long)ret < module_addr_min)
-			module_addr_min = (unsigned long)ret;
-		if ((unsigned long)ret + size > module_addr_max)
-			module_addr_max = (unsigned long)ret + size;
-		mutex_unlock(&module_mutex);
-	}
-	return ret;
-}
-
 #ifdef CONFIG_DEBUG_KMEMLEAK
 static void kmemleak_load_module(const struct module *mod,
 				 const struct load_info *info)
@@ -2805,7 +2956,7 @@
 	void *ptr;
 
 	/* Do the allocs. */
-	ptr = module_alloc_update_bounds(mod->core_size);
+	ptr = module_alloc(mod->core_size);
 	/*
 	 * The pointer to this block is stored in the module structure
 	 * which is inside the block. Just mark it as not being a
@@ -2819,7 +2970,7 @@
 	mod->module_core = ptr;
 
 	if (mod->init_size) {
-		ptr = module_alloc_update_bounds(mod->init_size);
+		ptr = module_alloc(mod->init_size);
 		/*
 		 * The pointer to this block is stored in the module structure
 		 * which is inside the block. This block doesn't need to be
@@ -3119,6 +3270,7 @@
 	mod->symtab = mod->core_symtab;
 	mod->strtab = mod->core_strtab;
 #endif
+	mod_tree_remove_init(mod);
 	unset_module_init_ro_nx(mod);
 	module_arch_freeing_init(mod);
 	mod->module_init = NULL;
@@ -3127,11 +3279,11 @@
 	mod->init_text_size = 0;
 	/*
 	 * We want to free module_init, but be aware that kallsyms may be
-	 * walking this with preempt disabled.  In all the failure paths,
-	 * we call synchronize_rcu/synchronize_sched, but we don't want
-	 * to slow down the success path, so use actual RCU here.
+	 * walking this with preempt disabled.  In all the failure paths, we
+	 * call synchronize_sched(), but we don't want to slow down the success
+	 * path, so use actual RCU here.
 	 */
-	call_rcu(&freeinit->rcu, do_free_init);
+	call_rcu_sched(&freeinit->rcu, do_free_init);
 	mutex_unlock(&module_mutex);
 	wake_up_all(&module_wq);
 
@@ -3188,7 +3340,9 @@
 		err = -EEXIST;
 		goto out;
 	}
+	mod_update_bounds(mod);
 	list_add_rcu(&mod->list, &modules);
+	mod_tree_insert(mod);
 	err = 0;
 
 out:
@@ -3304,6 +3458,8 @@
 	if (err)
 		goto unlink_mod;
 
+	init_param_lock(mod);
+
 	/* Now we've got everything in the final locations, we can
 	 * find optional sections. */
 	err = find_module_sections(mod, info);
@@ -3402,8 +3558,8 @@
 	/* Unlink carefully: kallsyms could be walking list. */
 	list_del_rcu(&mod->list);
 	wake_up_all(&module_wq);
-	/* Wait for RCU synchronizing before releasing mod->list. */
-	synchronize_rcu();
+	/* Wait for RCU-sched synchronizing before releasing mod->list. */
+	synchronize_sched();
 	mutex_unlock(&module_mutex);
  free_module:
 	/* Free lock-classes; relies on the preceding sync_rcu() */
@@ -3527,19 +3683,15 @@
 			    char **modname,
 			    char *namebuf)
 {
-	struct module *mod;
 	const char *ret = NULL;
+	struct module *mod;
 
 	preempt_disable();
-	list_for_each_entry_rcu(mod, &modules, list) {
-		if (mod->state == MODULE_STATE_UNFORMED)
-			continue;
-		if (within_module(addr, mod)) {
-			if (modname)
-				*modname = mod->name;
-			ret = get_ksymbol(mod, addr, size, offset);
-			break;
-		}
+	mod = __module_address(addr);
+	if (mod) {
+		if (modname)
+			*modname = mod->name;
+		ret = get_ksymbol(mod, addr, size, offset);
 	}
 	/* Make a copy in here where it's safe */
 	if (ret) {
@@ -3547,6 +3699,7 @@
 		ret = namebuf;
 	}
 	preempt_enable();
+
 	return ret;
 }
 
@@ -3670,6 +3823,8 @@
 	unsigned int i;
 	int ret;
 
+	module_assert_mutex();
+
 	list_for_each_entry(mod, &modules, list) {
 		if (mod->state == MODULE_STATE_UNFORMED)
 			continue;
@@ -3844,13 +3999,15 @@
 	if (addr < module_addr_min || addr > module_addr_max)
 		return NULL;
 
-	list_for_each_entry_rcu(mod, &modules, list) {
+	module_assert_mutex_or_preempt();
+
+	mod = mod_find(addr);
+	if (mod) {
+		BUG_ON(!within_module(addr, mod));
 		if (mod->state == MODULE_STATE_UNFORMED)
-			continue;
-		if (within_module(addr, mod))
-			return mod;
+			mod = NULL;
 	}
-	return NULL;
+	return mod;
 }
 EXPORT_SYMBOL_GPL(__module_address);
 
diff --git a/kernel/panic.c b/kernel/panic.c
index 8136ad7..04e91ff 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -32,7 +32,7 @@
 static int pause_on_oops;
 static int pause_on_oops_flag;
 static DEFINE_SPINLOCK(pause_on_oops_lock);
-static bool crash_kexec_post_notifiers;
+bool crash_kexec_post_notifiers;
 int panic_on_warn __read_mostly;
 
 int panic_timeout = CONFIG_PANIC_TIMEOUT;
@@ -142,7 +142,8 @@
 	 * Note: since some panic_notifiers can make crashed kernel
 	 * more unstable, it can increase risks of the kdump failure too.
 	 */
-	crash_kexec(NULL);
+	if (crash_kexec_post_notifiers)
+		crash_kexec(NULL);
 
 	bust_spinlocks(0);
 
diff --git a/kernel/params.c b/kernel/params.c
index 30288c1..b6554aa 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -25,15 +25,34 @@
 #include <linux/slab.h>
 #include <linux/ctype.h>
 
-/* Protects all parameters, and incidentally kmalloced_param list. */
+#ifdef CONFIG_SYSFS
+/* Protects all built-in parameters, modules use their own param_lock */
 static DEFINE_MUTEX(param_lock);
 
+/* Use the module's mutex, or if built-in use the built-in mutex */
+#ifdef CONFIG_MODULES
+#define KPARAM_MUTEX(mod)	((mod) ? &(mod)->param_lock : &param_lock)
+#else
+#define KPARAM_MUTEX(mod)	(&param_lock)
+#endif
+
+static inline void check_kparam_locked(struct module *mod)
+{
+	BUG_ON(!mutex_is_locked(KPARAM_MUTEX(mod)));
+}
+#else
+static inline void check_kparam_locked(struct module *mod)
+{
+}
+#endif /* !CONFIG_SYSFS */
+
 /* This just allows us to keep track of which parameters are kmalloced. */
 struct kmalloced_param {
 	struct list_head list;
 	char val[];
 };
 static LIST_HEAD(kmalloced_params);
+static DEFINE_SPINLOCK(kmalloced_params_lock);
 
 static void *kmalloc_parameter(unsigned int size)
 {
@@ -43,7 +62,10 @@
 	if (!p)
 		return NULL;
 
+	spin_lock(&kmalloced_params_lock);
 	list_add(&p->list, &kmalloced_params);
+	spin_unlock(&kmalloced_params_lock);
+
 	return p->val;
 }
 
@@ -52,6 +74,7 @@
 {
 	struct kmalloced_param *p;
 
+	spin_lock(&kmalloced_params_lock);
 	list_for_each_entry(p, &kmalloced_params, list) {
 		if (p->val == param) {
 			list_del(&p->list);
@@ -59,6 +82,7 @@
 			break;
 		}
 	}
+	spin_unlock(&kmalloced_params_lock);
 }
 
 static char dash2underscore(char c)
@@ -119,10 +143,10 @@
 				return -EINVAL;
 			pr_debug("handling %s with %p\n", param,
 				params[i].ops->set);
-			mutex_lock(&param_lock);
+			kernel_param_lock(params[i].mod);
 			param_check_unsafe(&params[i]);
 			err = params[i].ops->set(val, &params[i]);
-			mutex_unlock(&param_lock);
+			kernel_param_unlock(params[i].mod);
 			return err;
 		}
 	}
@@ -254,7 +278,7 @@
 		return scnprintf(buffer, PAGE_SIZE, format,		\
 				*((type *)kp->arg));			\
 	}								\
-	struct kernel_param_ops param_ops_##name = {			\
+	const struct kernel_param_ops param_ops_##name = {			\
 		.set = param_set_##name,				\
 		.get = param_get_##name,				\
 	};								\
@@ -306,7 +330,7 @@
 	maybe_kfree_parameter(*((char **)arg));
 }
 
-struct kernel_param_ops param_ops_charp = {
+const struct kernel_param_ops param_ops_charp = {
 	.set = param_set_charp,
 	.get = param_get_charp,
 	.free = param_free_charp,
@@ -331,13 +355,44 @@
 }
 EXPORT_SYMBOL(param_get_bool);
 
-struct kernel_param_ops param_ops_bool = {
+const struct kernel_param_ops param_ops_bool = {
 	.flags = KERNEL_PARAM_OPS_FL_NOARG,
 	.set = param_set_bool,
 	.get = param_get_bool,
 };
 EXPORT_SYMBOL(param_ops_bool);
 
+int param_set_bool_enable_only(const char *val, const struct kernel_param *kp)
+{
+	int err = 0;
+	bool new_value;
+	bool orig_value = *(bool *)kp->arg;
+	struct kernel_param dummy_kp = *kp;
+
+	dummy_kp.arg = &new_value;
+
+	err = param_set_bool(val, &dummy_kp);
+	if (err)
+		return err;
+
+	/* Don't let them unset it once it's set! */
+	if (!new_value && orig_value)
+		return -EROFS;
+
+	if (new_value)
+		err = param_set_bool(val, kp);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(param_set_bool_enable_only);
+
+const struct kernel_param_ops param_ops_bool_enable_only = {
+	.flags = KERNEL_PARAM_OPS_FL_NOARG,
+	.set = param_set_bool_enable_only,
+	.get = param_get_bool,
+};
+EXPORT_SYMBOL_GPL(param_ops_bool_enable_only);
+
 /* This one must be bool. */
 int param_set_invbool(const char *val, const struct kernel_param *kp)
 {
@@ -359,7 +414,7 @@
 }
 EXPORT_SYMBOL(param_get_invbool);
 
-struct kernel_param_ops param_ops_invbool = {
+const struct kernel_param_ops param_ops_invbool = {
 	.set = param_set_invbool,
 	.get = param_get_invbool,
 };
@@ -367,12 +422,11 @@
 
 int param_set_bint(const char *val, const struct kernel_param *kp)
 {
-	struct kernel_param boolkp;
+	/* Match bool exactly, by re-using it. */
+	struct kernel_param boolkp = *kp;
 	bool v;
 	int ret;
 
-	/* Match bool exactly, by re-using it. */
-	boolkp = *kp;
 	boolkp.arg = &v;
 
 	ret = param_set_bool(val, &boolkp);
@@ -382,7 +436,7 @@
 }
 EXPORT_SYMBOL(param_set_bint);
 
-struct kernel_param_ops param_ops_bint = {
+const struct kernel_param_ops param_ops_bint = {
 	.flags = KERNEL_PARAM_OPS_FL_NOARG,
 	.set = param_set_bint,
 	.get = param_get_int,
@@ -390,7 +444,8 @@
 EXPORT_SYMBOL(param_ops_bint);
 
 /* We break the rule and mangle the string. */
-static int param_array(const char *name,
+static int param_array(struct module *mod,
+		       const char *name,
 		       const char *val,
 		       unsigned int min, unsigned int max,
 		       void *elem, int elemsize,
@@ -421,7 +476,7 @@
 		/* nul-terminate and parse */
 		save = val[len];
 		((char *)val)[len] = '\0';
-		BUG_ON(!mutex_is_locked(&param_lock));
+		check_kparam_locked(mod);
 		ret = set(val, &kp);
 
 		if (ret != 0)
@@ -443,7 +498,7 @@
 	const struct kparam_array *arr = kp->arr;
 	unsigned int temp_num;
 
-	return param_array(kp->name, val, 1, arr->max, arr->elem,
+	return param_array(kp->mod, kp->name, val, 1, arr->max, arr->elem,
 			   arr->elemsize, arr->ops->set, kp->level,
 			   arr->num ?: &temp_num);
 }
@@ -452,14 +507,13 @@
 {
 	int i, off, ret;
 	const struct kparam_array *arr = kp->arr;
-	struct kernel_param p;
+	struct kernel_param p = *kp;
 
-	p = *kp;
 	for (i = off = 0; i < (arr->num ? *arr->num : arr->max); i++) {
 		if (i)
 			buffer[off++] = ',';
 		p.arg = arr->elem + arr->elemsize * i;
-		BUG_ON(!mutex_is_locked(&param_lock));
+		check_kparam_locked(p.mod);
 		ret = arr->ops->get(buffer + off, &p);
 		if (ret < 0)
 			return ret;
@@ -479,7 +533,7 @@
 			arr->ops->free(arr->elem + arr->elemsize * i);
 }
 
-struct kernel_param_ops param_array_ops = {
+const struct kernel_param_ops param_array_ops = {
 	.set = param_array_set,
 	.get = param_array_get,
 	.free = param_array_free,
@@ -507,7 +561,7 @@
 }
 EXPORT_SYMBOL(param_get_string);
 
-struct kernel_param_ops param_ops_string = {
+const struct kernel_param_ops param_ops_string = {
 	.set = param_set_copystring,
 	.get = param_get_string,
 };
@@ -542,9 +596,9 @@
 	if (!attribute->param->ops->get)
 		return -EPERM;
 
-	mutex_lock(&param_lock);
+	kernel_param_lock(mk->mod);
 	count = attribute->param->ops->get(buf, attribute->param);
-	mutex_unlock(&param_lock);
+	kernel_param_unlock(mk->mod);
 	if (count > 0) {
 		strcat(buf, "\n");
 		++count;
@@ -554,7 +608,7 @@
 
 /* sysfs always hands a nul-terminated string in buf.  We rely on that. */
 static ssize_t param_attr_store(struct module_attribute *mattr,
-				struct module_kobject *km,
+				struct module_kobject *mk,
 				const char *buf, size_t len)
 {
  	int err;
@@ -563,10 +617,10 @@
 	if (!attribute->param->ops->set)
 		return -EPERM;
 
-	mutex_lock(&param_lock);
+	kernel_param_lock(mk->mod);
 	param_check_unsafe(attribute->param);
 	err = attribute->param->ops->set(buf, attribute->param);
-	mutex_unlock(&param_lock);
+	kernel_param_unlock(mk->mod);
 	if (!err)
 		return len;
 	return err;
@@ -580,17 +634,18 @@
 #endif
 
 #ifdef CONFIG_SYSFS
-void __kernel_param_lock(void)
+void kernel_param_lock(struct module *mod)
 {
-	mutex_lock(&param_lock);
+	mutex_lock(KPARAM_MUTEX(mod));
 }
-EXPORT_SYMBOL(__kernel_param_lock);
 
-void __kernel_param_unlock(void)
+void kernel_param_unlock(struct module *mod)
 {
-	mutex_unlock(&param_lock);
+	mutex_unlock(KPARAM_MUTEX(mod));
 }
-EXPORT_SYMBOL(__kernel_param_unlock);
+
+EXPORT_SYMBOL(kernel_param_lock);
+EXPORT_SYMBOL(kernel_param_unlock);
 
 /*
  * add_sysfs_param - add a parameter to sysfs
@@ -856,6 +911,7 @@
 		mk = locate_module_kobject(vattr->module_name);
 		if (mk) {
 			err = sysfs_create_file(&mk->kobj, &vattr->mattr.attr);
+			WARN_ON_ONCE(err);
 			kobject_uevent(&mk->kobj, KOBJ_ADD);
 			kobject_put(&mk->kobj);
 		}
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 7e01f78..9e30231 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -187,7 +187,7 @@
 config DPM_WATCHDOG_TIMEOUT
 	int "Watchdog timeout in seconds"
 	range 1 120
-	default 12
+	default 60
 	depends on DPM_WATCHDOG
 
 config PM_TRACE
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 2329daa..690f78f 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -552,7 +552,7 @@
 
 	error = disable_nonboot_cpus();
 	if (error)
-		goto Platform_finish;
+		goto Enable_cpus;
 
 	local_irq_disable();
 	syscore_suspend();
@@ -568,6 +568,8 @@
  Power_up:
 	syscore_resume();
 	local_irq_enable();
+
+ Enable_cpus:
 	enable_nonboot_cpus();
 
  Platform_finish:
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index de55384..cf8c242 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -207,14 +207,14 @@
  * need to be changed in the future, when the requirements change.
  *
  * /dev/kmsg exports the structured data in the following line format:
- *   "<level>,<sequnum>,<timestamp>,<contflag>;<message text>\n"
+ *   "<level>,<sequnum>,<timestamp>,<contflag>[,additional_values, ... ];<message text>\n"
+ *
+ * Users of the export format should ignore possible additional values
+ * separated by ',', and find the message after the ';' character.
  *
  * The optional key/value pairs are attached as continuation lines starting
  * with a space character and terminated by a newline. All possible
  * non-prinatable characters are escaped in the "\xff" notation.
- *
- * Users of the export format should ignore possible additional values
- * separated by ',', and find the message after the ';' character.
  */
 
 enum log_flags {
diff --git a/kernel/relay.c b/kernel/relay.c
index e9dbaeb..0b4570c 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -81,10 +81,7 @@
  */
 static void relay_free_page_array(struct page **array)
 {
-	if (is_vmalloc_addr(array))
-		vfree(array);
-	else
-		kfree(array);
+	kvfree(array);
 }
 
 /**
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b803e1b..78b4bad10 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2164,7 +2164,7 @@
 	set_task_cpu(p, cpu);
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
-#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
+#ifdef CONFIG_SCHED_INFO
 	if (likely(sched_info_on()))
 		memset(&p->sched_info, 0, sizeof(p->sched_info));
 #endif
@@ -2320,13 +2320,27 @@
 
 static struct static_key preempt_notifier_key = STATIC_KEY_INIT_FALSE;
 
+void preempt_notifier_inc(void)
+{
+	static_key_slow_inc(&preempt_notifier_key);
+}
+EXPORT_SYMBOL_GPL(preempt_notifier_inc);
+
+void preempt_notifier_dec(void)
+{
+	static_key_slow_dec(&preempt_notifier_key);
+}
+EXPORT_SYMBOL_GPL(preempt_notifier_dec);
+
 /**
  * preempt_notifier_register - tell me when current is being preempted & rescheduled
  * @notifier: notifier struct to register
  */
 void preempt_notifier_register(struct preempt_notifier *notifier)
 {
-	static_key_slow_inc(&preempt_notifier_key);
+	if (!static_key_false(&preempt_notifier_key))
+		WARN(1, "registering preempt_notifier while notifiers disabled\n");
+
 	hlist_add_head(&notifier->link, &current->preempt_notifiers);
 }
 EXPORT_SYMBOL_GPL(preempt_notifier_register);
@@ -2340,7 +2354,6 @@
 void preempt_notifier_unregister(struct preempt_notifier *notifier)
 {
 	hlist_del(&notifier->link);
-	static_key_slow_dec(&preempt_notifier_key);
 }
 EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
 
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 315c68e..4222ec5 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -142,7 +142,7 @@
 		0LL, 0L);
 #endif
 #ifdef CONFIG_NUMA_BALANCING
-	SEQ_printf(m, " %d", task_node(p));
+	SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p));
 #endif
 #ifdef CONFIG_CGROUP_SCHED
 	SEQ_printf(m, " %s", task_group_path(task_group(p)));
@@ -517,11 +517,21 @@
 	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
 
 
+#ifdef CONFIG_NUMA_BALANCING
+void print_numa_stats(struct seq_file *m, int node, unsigned long tsf,
+		unsigned long tpf, unsigned long gsf, unsigned long gpf)
+{
+	SEQ_printf(m, "numa_faults node=%d ", node);
+	SEQ_printf(m, "task_private=%lu task_shared=%lu ", tsf, tpf);
+	SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gsf, gpf);
+}
+#endif
+
+
 static void sched_show_numa(struct task_struct *p, struct seq_file *m)
 {
 #ifdef CONFIG_NUMA_BALANCING
 	struct mempolicy *pol;
-	int node, i;
 
 	if (p->mm)
 		P(mm->numa_scan_seq);
@@ -533,26 +543,12 @@
 	mpol_get(pol);
 	task_unlock(p);
 
-	SEQ_printf(m, "numa_migrations, %ld\n", xchg(&p->numa_pages_migrated, 0));
-
-	for_each_online_node(node) {
-		for (i = 0; i < 2; i++) {
-			unsigned long nr_faults = -1;
-			int cpu_current, home_node;
-
-			if (p->numa_faults)
-				nr_faults = p->numa_faults[2*node + i];
-
-			cpu_current = !i ? (task_node(p) == node) :
-				(pol && node_isset(node, pol->v.nodes));
-
-			home_node = (p->numa_preferred_nid == node);
-
-			SEQ_printf(m, "numa_faults_memory, %d, %d, %d, %d, %ld\n",
-				i, node, cpu_current, home_node, nr_faults);
-		}
-	}
-
+	P(numa_pages_migrated);
+	P(numa_preferred_nid);
+	P(total_numa_faults);
+	SEQ_printf(m, "current_node=%d, numa_group_id=%d\n",
+			task_node(p), task_numa_group_id(p));
+	show_numa_stats(p, m);
 	mpol_put(pol);
 #endif
 }
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 3d57cc0..65c8f3e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8473,7 +8473,27 @@
 		print_cfs_rq(m, cpu, cfs_rq);
 	rcu_read_unlock();
 }
-#endif
+
+#ifdef CONFIG_NUMA_BALANCING
+void show_numa_stats(struct task_struct *p, struct seq_file *m)
+{
+	int node;
+	unsigned long tsf = 0, tpf = 0, gsf = 0, gpf = 0;
+
+	for_each_online_node(node) {
+		if (p->numa_faults) {
+			tsf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 0)];
+			tpf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 1)];
+		}
+		if (p->numa_group) {
+			gsf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 0)],
+			gpf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 1)];
+		}
+		print_numa_stats(m, node, tsf, tpf, gsf, gpf);
+	}
+}
+#endif /* CONFIG_NUMA_BALANCING */
+#endif /* CONFIG_SCHED_DEBUG */
 
 __init void init_sched_fair_class(void)
 {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 8858891..84d4879 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1689,9 +1689,22 @@
 
 extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq);
 extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq);
+
+#ifdef	CONFIG_SCHED_DEBUG
 extern void print_cfs_stats(struct seq_file *m, int cpu);
 extern void print_rt_stats(struct seq_file *m, int cpu);
 extern void print_dl_stats(struct seq_file *m, int cpu);
+extern void
+print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
+
+#ifdef CONFIG_NUMA_BALANCING
+extern void
+show_numa_stats(struct task_struct *p, struct seq_file *m);
+extern void
+print_numa_stats(struct seq_file *m, int node, unsigned long tsf,
+	unsigned long tpf, unsigned long gsf, unsigned long gpf);
+#endif /* CONFIG_NUMA_BALANCING */
+#endif /* CONFIG_SCHED_DEBUG */
 
 extern void init_cfs_rq(struct cfs_rq *cfs_rq);
 extern void init_rt_rq(struct rt_rq *rt_rq);
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 077ebbd..b0fbc76 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -47,7 +47,7 @@
 # define schedstat_set(var, val)	do { } while (0)
 #endif
 
-#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
+#ifdef CONFIG_SCHED_INFO
 static inline void sched_info_reset_dequeued(struct task_struct *t)
 {
 	t->sched_info.last_queued = 0;
@@ -156,7 +156,7 @@
 #define sched_info_depart(rq, t)		do { } while (0)
 #define sched_info_arrive(rq, next)		do { } while (0)
 #define sched_info_switch(rq, t, next)		do { } while (0)
-#endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */
+#endif /* CONFIG_SCHED_INFO */
 
 /*
  * The following are functions that support scheduler-internal time accounting.
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 812fcc3..19b62b5 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1538,12 +1538,6 @@
 	{ }
 };
 
-#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
-static struct ctl_table binfmt_misc_table[] = {
-	{ }
-};
-#endif
-
 static struct ctl_table fs_table[] = {
 	{
 		.procname	= "inode-nr",
@@ -1697,7 +1691,7 @@
 	{
 		.procname	= "binfmt_misc",
 		.mode		= 0555,
-		.child		= binfmt_misc_table,
+		.child		= sysctl_mount_point,
 	},
 #endif
 	{
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index ffc4cc3..49eca0b 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -12,5 +12,3 @@
 obj-$(CONFIG_TIMER_STATS)			+= timer_stats.o
 obj-$(CONFIG_DEBUG_FS)				+= timekeeping_debug.o
 obj-$(CONFIG_TEST_UDELAY)			+= test_udelay.o
-
-$(obj)/time.o: $(objtree)/include/config/
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 30b7a40..bca3667 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -319,32 +319,7 @@
  * We want to use this from any context including NMI and tracing /
  * instrumenting the timekeeping code itself.
  *
- * So we handle this differently than the other timekeeping accessor
- * functions which retry when the sequence count has changed. The
- * update side does:
- *
- * smp_wmb();	<- Ensure that the last base[1] update is visible
- * tkf->seq++;
- * smp_wmb();	<- Ensure that the seqcount update is visible
- * update(tkf->base[0], tkr);
- * smp_wmb();	<- Ensure that the base[0] update is visible
- * tkf->seq++;
- * smp_wmb();	<- Ensure that the seqcount update is visible
- * update(tkf->base[1], tkr);
- *
- * The reader side does:
- *
- * do {
- *	seq = tkf->seq;
- *	smp_rmb();
- *	idx = seq & 0x01;
- *	now = now(tkf->base[idx]);
- *	smp_rmb();
- * } while (seq != tkf->seq)
- *
- * As long as we update base[0] readers are forced off to
- * base[1]. Once base[0] is updated readers are redirected to base[0]
- * and the base[1] update takes place.
+ * Employ the latch technique; see @raw_write_seqcount_latch.
  *
  * So if a NMI hits the update of base[0] then it will use base[1]
  * which is still consistent. In the worst case this can result is a
@@ -407,7 +382,7 @@
 	u64 now;
 
 	do {
-		seq = raw_read_seqcount(&tkf->seq);
+		seq = raw_read_seqcount_latch(&tkf->seq);
 		tkr = tkf->base + (seq & 0x01);
 		now = ktime_to_ns(tkr->base) + timekeeping_get_ns(tkr);
 	} while (read_seqcount_retry(&tkf->seq, seq));
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 520499d..5e097fa 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1566,7 +1566,7 @@
 
 	BUG_ON(cpu_online(cpu));
 	old_base = per_cpu_ptr(&tvec_bases, cpu);
-	new_base = this_cpu_ptr(&tvec_bases);
+	new_base = get_cpu_ptr(&tvec_bases);
 	/*
 	 * The caller is globally serialized and nobody else
 	 * takes two locks at once, deadlock is not possible.
@@ -1590,6 +1590,7 @@
 
 	spin_unlock(&old_base->lock);
 	spin_unlock_irq(&new_base->lock);
+	put_cpu_ptr(&tvec_bases);
 }
 
 static int timer_cpu_notify(struct notifier_block *self,
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 5243d4b..4c4f061 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -285,12 +285,7 @@
 module_param_named(disable_numa, wq_disable_numa, bool, 0444);
 
 /* see the comment above the definition of WQ_POWER_EFFICIENT */
-#ifdef CONFIG_WQ_POWER_EFFICIENT_DEFAULT
-static bool wq_power_efficient = true;
-#else
-static bool wq_power_efficient;
-#endif
-
+static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT);
 module_param_named(power_efficient, wq_power_efficient, bool, 0444);
 
 static bool wq_numa_enabled;		/* unbound NUMA affinity enabled */
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index b908048..e2894b2 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -841,9 +841,14 @@
 	  that can help debug the scheduler. The runtime overhead of this
 	  option is minimal.
 
+config SCHED_INFO
+	bool
+	default n
+
 config SCHEDSTATS
 	bool "Collect scheduler statistics"
 	depends on DEBUG_KERNEL && PROC_FS
+	select SCHED_INFO
 	help
 	  If you say Y here, additional code will be inserted into the
 	  scheduler and related routines to collect statistics about
diff --git a/lib/Makefile b/lib/Makefile
index ff37c8c..6897b52 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -45,6 +45,9 @@
 CFLAGS_kobject_uevent.o += -DDEBUG
 endif
 
+obj-$(CONFIG_DEBUG_INFO_REDUCED) += debug_info.o
+CFLAGS_debug_info.o += $(call cc-option, -femit-struct-debug-detailed=any)
+
 obj-$(CONFIG_GENERIC_IOMAP) += iomap.o
 obj-$(CONFIG_GENERIC_PCI_IOMAP) += pci_iomap.o
 obj-$(CONFIG_HAS_IOMEM) += iomap_copy.o devres.o
diff --git a/lib/bug.c b/lib/bug.c
index 0c3bd95..cff145f 100644
--- a/lib/bug.c
+++ b/lib/bug.c
@@ -66,7 +66,7 @@
 	struct module *mod;
 	const struct bug_entry *bug = NULL;
 
-	rcu_read_lock();
+	rcu_read_lock_sched();
 	list_for_each_entry_rcu(mod, &module_bug_list, bug_list) {
 		unsigned i;
 
@@ -77,7 +77,7 @@
 	}
 	bug = NULL;
 out:
-	rcu_read_unlock();
+	rcu_read_unlock_sched();
 
 	return bug;
 }
@@ -88,6 +88,8 @@
 	char *secstrings;
 	unsigned int i;
 
+	lockdep_assert_held(&module_mutex);
+
 	mod->bug_table = NULL;
 	mod->num_bugs = 0;
 
@@ -113,6 +115,7 @@
 
 void module_bug_cleanup(struct module *mod)
 {
+	lockdep_assert_held(&module_mutex);
 	list_del_rcu(&mod->bug_list);
 }
 
diff --git a/lib/crc-t10dif.c b/lib/crc-t10dif.c
index dfe6ec1..1ad33e5 100644
--- a/lib/crc-t10dif.c
+++ b/lib/crc-t10dif.c
@@ -19,7 +19,7 @@
 static struct crypto_shash *crct10dif_tfm;
 static struct static_key crct10dif_fallback __read_mostly;
 
-__u16 crc_t10dif(const unsigned char *buffer, size_t len)
+__u16 crc_t10dif_update(__u16 crc, const unsigned char *buffer, size_t len)
 {
 	struct {
 		struct shash_desc shash;
@@ -28,17 +28,23 @@
 	int err;
 
 	if (static_key_false(&crct10dif_fallback))
-		return crc_t10dif_generic(0, buffer, len);
+		return crc_t10dif_generic(crc, buffer, len);
 
 	desc.shash.tfm = crct10dif_tfm;
 	desc.shash.flags = 0;
-	*(__u16 *)desc.ctx = 0;
+	*(__u16 *)desc.ctx = crc;
 
 	err = crypto_shash_update(&desc.shash, buffer, len);
 	BUG_ON(err);
 
 	return *(__u16 *)desc.ctx;
 }
+EXPORT_SYMBOL(crc_t10dif_update);
+
+__u16 crc_t10dif(const unsigned char *buffer, size_t len)
+{
+	return crc_t10dif_update(0, buffer, len);
+}
 EXPORT_SYMBOL(crc_t10dif);
 
 static int __init crc_t10dif_mod_init(void)
diff --git a/lib/debug_info.c b/lib/debug_info.c
new file mode 100644
index 0000000..2edbe27
--- /dev/null
+++ b/lib/debug_info.c
@@ -0,0 +1,27 @@
+/*
+ * This file exists solely to ensure debug information for some core
+ * data structures is included in the final image even for
+ * CONFIG_DEBUG_INFO_REDUCED. Please do not add actual code. However,
+ * adding appropriate #includes is fine.
+ */
+#include <stdarg.h>
+
+#include <linux/cred.h>
+#include <linux/crypto.h>
+#include <linux/dcache.h>
+#include <linux/device.h>
+#include <linux/fs.h>
+#include <linux/fscache-cache.h>
+#include <linux/io.h>
+#include <linux/kallsyms.h>
+#include <linux/kernel.h>
+#include <linux/kobject.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <net/addrconf.h>
+#include <net/sock.h>
+#include <net/tcp.h>
diff --git a/lib/genalloc.c b/lib/genalloc.c
index d214866..daf0afb 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -602,12 +602,12 @@
 EXPORT_SYMBOL(devm_gen_pool_create);
 
 /**
- * dev_get_gen_pool - Obtain the gen_pool (if any) for a device
+ * gen_pool_get - Obtain the gen_pool (if any) for a device
  * @dev: device to retrieve the gen_pool from
  *
  * Returns the gen_pool for the device if one is present, or NULL.
  */
-struct gen_pool *dev_get_gen_pool(struct device *dev)
+struct gen_pool *gen_pool_get(struct device *dev)
 {
 	struct gen_pool **p = devres_find(dev, devm_gen_pool_release, NULL,
 					NULL);
@@ -616,11 +616,11 @@
 		return NULL;
 	return *p;
 }
-EXPORT_SYMBOL_GPL(dev_get_gen_pool);
+EXPORT_SYMBOL_GPL(gen_pool_get);
 
 #ifdef CONFIG_OF
 /**
- * of_get_named_gen_pool - find a pool by phandle property
+ * of_gen_pool_get - find a pool by phandle property
  * @np: device node
  * @propname: property name containing phandle(s)
  * @index: index into the phandle array
@@ -629,7 +629,7 @@
  * address of the device tree node pointed at by the phandle property,
  * or NULL if not found.
  */
-struct gen_pool *of_get_named_gen_pool(struct device_node *np,
+struct gen_pool *of_gen_pool_get(struct device_node *np,
 	const char *propname, int index)
 {
 	struct platform_device *pdev;
@@ -642,7 +642,7 @@
 	of_node_put(np_pool);
 	if (!pdev)
 		return NULL;
-	return dev_get_gen_pool(&pdev->dev);
+	return gen_pool_get(&pdev->dev);
 }
-EXPORT_SYMBOL_GPL(of_get_named_gen_pool);
+EXPORT_SYMBOL_GPL(of_gen_pool_get);
 #endif /* CONFIG_OF */
diff --git a/lib/list_sort.c b/lib/list_sort.c
index b290151..3fe4010 100644
--- a/lib/list_sort.c
+++ b/lib/list_sort.c
@@ -289,5 +289,5 @@
 	kfree(elts);
 	return err;
 }
-module_init(list_sort_test);
+late_initcall(list_sort_test);
 #endif /* CONFIG_TEST_LIST_SORT */
diff --git a/lib/rbtree.c b/lib/rbtree.c
index c16c81a..1356454 100644
--- a/lib/rbtree.c
+++ b/lib/rbtree.c
@@ -44,6 +44,30 @@
  *  parentheses and have some accompanying text comment.
  */
 
+/*
+ * Notes on lockless lookups:
+ *
+ * All stores to the tree structure (rb_left and rb_right) must be done using
+ * WRITE_ONCE(). And we must not inadvertently cause (temporary) loops in the
+ * tree structure as seen in program order.
+ *
+ * These two requirements will allow lockless iteration of the tree -- not
+ * correct iteration mind you, tree rotations are not atomic so a lookup might
+ * miss entire subtrees.
+ *
+ * But they do guarantee that any such traversal will only see valid elements
+ * and that it will indeed complete -- does not get stuck in a loop.
+ *
+ * It also guarantees that if the lookup returns an element it is the 'correct'
+ * one. But not returning an element does _NOT_ mean it's not present.
+ *
+ * NOTE:
+ *
+ * Stores to __rb_parent_color are not important for simple lookups so those
+ * are left undone as of now. Nor did I check for loops involving parent
+ * pointers.
+ */
+
 static inline void rb_set_black(struct rb_node *rb)
 {
 	rb->__rb_parent_color |= RB_BLACK;
@@ -129,8 +153,9 @@
 				 * This still leaves us in violation of 4), the
 				 * continuation into Case 3 will fix that.
 				 */
-				parent->rb_right = tmp = node->rb_left;
-				node->rb_left = parent;
+				tmp = node->rb_left;
+				WRITE_ONCE(parent->rb_right, tmp);
+				WRITE_ONCE(node->rb_left, parent);
 				if (tmp)
 					rb_set_parent_color(tmp, parent,
 							    RB_BLACK);
@@ -149,8 +174,8 @@
 			 *     /                 \
 			 *    n                   U
 			 */
-			gparent->rb_left = tmp;  /* == parent->rb_right */
-			parent->rb_right = gparent;
+			WRITE_ONCE(gparent->rb_left, tmp); /* == parent->rb_right */
+			WRITE_ONCE(parent->rb_right, gparent);
 			if (tmp)
 				rb_set_parent_color(tmp, gparent, RB_BLACK);
 			__rb_rotate_set_parents(gparent, parent, root, RB_RED);
@@ -171,8 +196,9 @@
 			tmp = parent->rb_left;
 			if (node == tmp) {
 				/* Case 2 - right rotate at parent */
-				parent->rb_left = tmp = node->rb_right;
-				node->rb_right = parent;
+				tmp = node->rb_right;
+				WRITE_ONCE(parent->rb_left, tmp);
+				WRITE_ONCE(node->rb_right, parent);
 				if (tmp)
 					rb_set_parent_color(tmp, parent,
 							    RB_BLACK);
@@ -183,8 +209,8 @@
 			}
 
 			/* Case 3 - left rotate at gparent */
-			gparent->rb_right = tmp;  /* == parent->rb_left */
-			parent->rb_left = gparent;
+			WRITE_ONCE(gparent->rb_right, tmp); /* == parent->rb_left */
+			WRITE_ONCE(parent->rb_left, gparent);
 			if (tmp)
 				rb_set_parent_color(tmp, gparent, RB_BLACK);
 			__rb_rotate_set_parents(gparent, parent, root, RB_RED);
@@ -224,8 +250,9 @@
 				 *      / \         / \
 				 *     Sl  Sr      N   Sl
 				 */
-				parent->rb_right = tmp1 = sibling->rb_left;
-				sibling->rb_left = parent;
+				tmp1 = sibling->rb_left;
+				WRITE_ONCE(parent->rb_right, tmp1);
+				WRITE_ONCE(sibling->rb_left, parent);
 				rb_set_parent_color(tmp1, parent, RB_BLACK);
 				__rb_rotate_set_parents(parent, sibling, root,
 							RB_RED);
@@ -275,9 +302,10 @@
 				 *                       \
 				 *                        Sr
 				 */
-				sibling->rb_left = tmp1 = tmp2->rb_right;
-				tmp2->rb_right = sibling;
-				parent->rb_right = tmp2;
+				tmp1 = tmp2->rb_right;
+				WRITE_ONCE(sibling->rb_left, tmp1);
+				WRITE_ONCE(tmp2->rb_right, sibling);
+				WRITE_ONCE(parent->rb_right, tmp2);
 				if (tmp1)
 					rb_set_parent_color(tmp1, sibling,
 							    RB_BLACK);
@@ -297,8 +325,9 @@
 			 *        / \         / \
 			 *      (sl) sr      N  (sl)
 			 */
-			parent->rb_right = tmp2 = sibling->rb_left;
-			sibling->rb_left = parent;
+			tmp2 = sibling->rb_left;
+			WRITE_ONCE(parent->rb_right, tmp2);
+			WRITE_ONCE(sibling->rb_left, parent);
 			rb_set_parent_color(tmp1, sibling, RB_BLACK);
 			if (tmp2)
 				rb_set_parent(tmp2, parent);
@@ -310,8 +339,9 @@
 			sibling = parent->rb_left;
 			if (rb_is_red(sibling)) {
 				/* Case 1 - right rotate at parent */
-				parent->rb_left = tmp1 = sibling->rb_right;
-				sibling->rb_right = parent;
+				tmp1 = sibling->rb_right;
+				WRITE_ONCE(parent->rb_left, tmp1);
+				WRITE_ONCE(sibling->rb_right, parent);
 				rb_set_parent_color(tmp1, parent, RB_BLACK);
 				__rb_rotate_set_parents(parent, sibling, root,
 							RB_RED);
@@ -336,9 +366,10 @@
 					break;
 				}
 				/* Case 3 - right rotate at sibling */
-				sibling->rb_right = tmp1 = tmp2->rb_left;
-				tmp2->rb_left = sibling;
-				parent->rb_left = tmp2;
+				tmp1 = tmp2->rb_left;
+				WRITE_ONCE(sibling->rb_right, tmp1);
+				WRITE_ONCE(tmp2->rb_left, sibling);
+				WRITE_ONCE(parent->rb_left, tmp2);
 				if (tmp1)
 					rb_set_parent_color(tmp1, sibling,
 							    RB_BLACK);
@@ -347,8 +378,9 @@
 				sibling = tmp2;
 			}
 			/* Case 4 - left rotate at parent + color flips */
-			parent->rb_left = tmp2 = sibling->rb_right;
-			sibling->rb_right = parent;
+			tmp2 = sibling->rb_right;
+			WRITE_ONCE(parent->rb_left, tmp2);
+			WRITE_ONCE(sibling->rb_right, parent);
 			rb_set_parent_color(tmp1, sibling, RB_BLACK);
 			if (tmp2)
 				rb_set_parent(tmp2, parent);
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index 99fbc2f..d105a9f 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -650,9 +650,8 @@
  * Returns the number of copied bytes.
  *
  **/
-static size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents,
-			     void *buf, size_t buflen, off_t skip,
-			     bool to_buffer)
+size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, void *buf,
+		      size_t buflen, off_t skip, bool to_buffer)
 {
 	unsigned int offset = 0;
 	struct sg_mapping_iter miter;
@@ -689,6 +688,7 @@
 	local_irq_restore(flags);
 	return offset;
 }
+EXPORT_SYMBOL(sg_copy_buffer);
 
 /**
  * sg_copy_from_buffer - Copy from a linear buffer to an SG list
@@ -701,9 +701,9 @@
  *
  **/
 size_t sg_copy_from_buffer(struct scatterlist *sgl, unsigned int nents,
-			   void *buf, size_t buflen)
+			   const void *buf, size_t buflen)
 {
-	return sg_copy_buffer(sgl, nents, buf, buflen, 0, false);
+	return sg_copy_buffer(sgl, nents, (void *)buf, buflen, 0, false);
 }
 EXPORT_SYMBOL(sg_copy_from_buffer);
 
@@ -729,16 +729,16 @@
  * @sgl:		 The SG list
  * @nents:		 Number of SG entries
  * @buf:		 Where to copy from
- * @skip:		 Number of bytes to skip before copying
  * @buflen:		 The number of bytes to copy
+ * @skip:		 Number of bytes to skip before copying
  *
  * Returns the number of copied bytes.
  *
  **/
 size_t sg_pcopy_from_buffer(struct scatterlist *sgl, unsigned int nents,
-			    void *buf, size_t buflen, off_t skip)
+			    const void *buf, size_t buflen, off_t skip)
 {
-	return sg_copy_buffer(sgl, nents, buf, buflen, skip, false);
+	return sg_copy_buffer(sgl, nents, (void *)buf, buflen, skip, false);
 }
 EXPORT_SYMBOL(sg_pcopy_from_buffer);
 
@@ -747,8 +747,8 @@
  * @sgl:		 The SG list
  * @nents:		 Number of SG entries
  * @buf:		 Where to copy to
- * @skip:		 Number of bytes to skip before copying
  * @buflen:		 The number of bytes to copy
+ * @skip:		 Number of bytes to skip before copying
  *
  * Returns the number of copied bytes.
  *
diff --git a/mm/Kconfig b/mm/Kconfig
index c180af8..e79de2b 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -636,3 +636,21 @@
 	  changed to a smaller value in which case that is used.
 
 	  A sane initial value is 80 MB.
+
+# For architectures that support deferred memory initialisation
+config ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
+	bool
+
+config DEFERRED_STRUCT_PAGE_INIT
+	bool "Defer initialisation of struct pages to kswapd"
+	default n
+	depends on ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
+	depends on MEMORY_HOTPLUG
+	help
+	  Ordinarily all struct pages are initialised during early boot in a
+	  single thread. On very large machines this can take a considerable
+	  amount of time. If this option is set, large machines will bring up
+	  a subset of memmap at boot and then initialise the rest in parallel
+	  when kswapd starts. This has a potential performance impact on
+	  processes running early in the lifetime of the systemm until kswapd
+	  finishes the initialisation.
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 7756da3..dac5bf5 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -287,7 +287,7 @@
 #define INIT_BW		(100 << (20 - PAGE_SHIFT))
 
 static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
-		   gfp_t gfp)
+		   int blkcg_id, gfp_t gfp)
 {
 	int i, err;
 
@@ -311,21 +311,29 @@
 	INIT_LIST_HEAD(&wb->work_list);
 	INIT_DELAYED_WORK(&wb->dwork, wb_workfn);
 
+	wb->congested = wb_congested_get_create(bdi, blkcg_id, gfp);
+	if (!wb->congested)
+		return -ENOMEM;
+
 	err = fprop_local_init_percpu(&wb->completions, gfp);
 	if (err)
-		return err;
+		goto out_put_cong;
 
 	for (i = 0; i < NR_WB_STAT_ITEMS; i++) {
 		err = percpu_counter_init(&wb->stat[i], 0, gfp);
-		if (err) {
-			while (--i)
-				percpu_counter_destroy(&wb->stat[i]);
-			fprop_local_destroy_percpu(&wb->completions);
-			return err;
-		}
+		if (err)
+			goto out_destroy_stat;
 	}
 
 	return 0;
+
+out_destroy_stat:
+	while (--i)
+		percpu_counter_destroy(&wb->stat[i]);
+	fprop_local_destroy_percpu(&wb->completions);
+out_put_cong:
+	wb_congested_put(wb->congested);
+	return err;
 }
 
 /*
@@ -361,6 +369,7 @@
 		percpu_counter_destroy(&wb->stat[i]);
 
 	fprop_local_destroy_percpu(&wb->completions);
+	wb_congested_put(wb->congested);
 }
 
 #ifdef CONFIG_CGROUP_WRITEBACK
@@ -392,9 +401,6 @@
 	struct bdi_writeback_congested *new_congested = NULL, *congested;
 	struct rb_node **node, *parent;
 	unsigned long flags;
-
-	if (blkcg_id == 1)
-		return &bdi->wb_congested;
 retry:
 	spin_lock_irqsave(&cgwb_lock, flags);
 
@@ -419,7 +425,6 @@
 		new_congested = NULL;
 		rb_link_node(&congested->rb_node, parent, node);
 		rb_insert_color(&congested->rb_node, &bdi->cgwb_congested_tree);
-		atomic_inc(&bdi->usage_cnt);
 		goto found;
 	}
 
@@ -450,24 +455,23 @@
  */
 void wb_congested_put(struct bdi_writeback_congested *congested)
 {
-	struct backing_dev_info *bdi = congested->bdi;
 	unsigned long flags;
 
-	if (congested->blkcg_id == 1)
-		return;
-
 	local_irq_save(flags);
 	if (!atomic_dec_and_lock(&congested->refcnt, &cgwb_lock)) {
 		local_irq_restore(flags);
 		return;
 	}
 
-	rb_erase(&congested->rb_node, &congested->bdi->cgwb_congested_tree);
+	/* bdi might already have been destroyed leaving @congested unlinked */
+	if (congested->bdi) {
+		rb_erase(&congested->rb_node,
+			 &congested->bdi->cgwb_congested_tree);
+		congested->bdi = NULL;
+	}
+
 	spin_unlock_irqrestore(&cgwb_lock, flags);
 	kfree(congested);
-
-	if (atomic_dec_and_test(&bdi->usage_cnt))
-		wake_up_all(&cgwb_release_wait);
 }
 
 static void cgwb_release_workfn(struct work_struct *work)
@@ -480,7 +484,6 @@
 
 	css_put(wb->memcg_css);
 	css_put(wb->blkcg_css);
-	wb_congested_put(wb->congested);
 
 	fprop_local_destroy_percpu(&wb->memcg_completions);
 	percpu_ref_exit(&wb->refcnt);
@@ -541,7 +544,7 @@
 	if (!wb)
 		return -ENOMEM;
 
-	ret = wb_init(wb, bdi, gfp);
+	ret = wb_init(wb, bdi, blkcg_css->id, gfp);
 	if (ret)
 		goto err_free;
 
@@ -553,12 +556,6 @@
 	if (ret)
 		goto err_ref_exit;
 
-	wb->congested = wb_congested_get_create(bdi, blkcg_css->id, gfp);
-	if (!wb->congested) {
-		ret = -ENOMEM;
-		goto err_fprop_exit;
-	}
-
 	wb->memcg_css = memcg_css;
 	wb->blkcg_css = blkcg_css;
 	INIT_WORK(&wb->release_work, cgwb_release_workfn);
@@ -588,12 +585,10 @@
 	if (ret) {
 		if (ret == -EEXIST)
 			ret = 0;
-		goto err_put_congested;
+		goto err_fprop_exit;
 	}
 	goto out_put;
 
-err_put_congested:
-	wb_congested_put(wb->congested);
 err_fprop_exit:
 	fprop_local_destroy_percpu(&wb->memcg_completions);
 err_ref_exit:
@@ -662,26 +657,41 @@
 	return wb;
 }
 
-static void cgwb_bdi_init(struct backing_dev_info *bdi)
+static int cgwb_bdi_init(struct backing_dev_info *bdi)
 {
-	bdi->wb.memcg_css = mem_cgroup_root_css;
-	bdi->wb.blkcg_css = blkcg_root_css;
-	bdi->wb_congested.blkcg_id = 1;
+	int ret;
+
 	INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC);
 	bdi->cgwb_congested_tree = RB_ROOT;
 	atomic_set(&bdi->usage_cnt, 1);
+
+	ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL);
+	if (!ret) {
+		bdi->wb.memcg_css = mem_cgroup_root_css;
+		bdi->wb.blkcg_css = blkcg_root_css;
+	}
+	return ret;
 }
 
 static void cgwb_bdi_destroy(struct backing_dev_info *bdi)
 {
 	struct radix_tree_iter iter;
+	struct bdi_writeback_congested *congested, *congested_n;
 	void **slot;
 
 	WARN_ON(test_bit(WB_registered, &bdi->wb.state));
 
 	spin_lock_irq(&cgwb_lock);
+
 	radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0)
 		cgwb_kill(*slot);
+
+	rbtree_postorder_for_each_entry_safe(congested, congested_n,
+					&bdi->cgwb_congested_tree, rb_node) {
+		rb_erase(&congested->rb_node, &bdi->cgwb_congested_tree);
+		congested->bdi = NULL;	/* mark @congested unlinked */
+	}
+
 	spin_unlock_irq(&cgwb_lock);
 
 	/*
@@ -732,15 +742,28 @@
 
 #else	/* CONFIG_CGROUP_WRITEBACK */
 
-static void cgwb_bdi_init(struct backing_dev_info *bdi) { }
+static int cgwb_bdi_init(struct backing_dev_info *bdi)
+{
+	int err;
+
+	bdi->wb_congested = kzalloc(sizeof(*bdi->wb_congested), GFP_KERNEL);
+	if (!bdi->wb_congested)
+		return -ENOMEM;
+
+	err = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL);
+	if (err) {
+		kfree(bdi->wb_congested);
+		return err;
+	}
+	return 0;
+}
+
 static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { }
 
 #endif	/* CONFIG_CGROUP_WRITEBACK */
 
 int bdi_init(struct backing_dev_info *bdi)
 {
-	int err;
-
 	bdi->dev = NULL;
 
 	bdi->min_ratio = 0;
@@ -749,15 +772,7 @@
 	INIT_LIST_HEAD(&bdi->bdi_list);
 	init_waitqueue_head(&bdi->wb_waitq);
 
-	err = wb_init(&bdi->wb, bdi, GFP_KERNEL);
-	if (err)
-		return err;
-
-	bdi->wb_congested.state = 0;
-	bdi->wb.congested = &bdi->wb_congested;
-
-	cgwb_bdi_init(bdi);
-	return 0;
+	return cgwb_bdi_init(bdi);
 }
 EXPORT_SYMBOL(bdi_init);
 
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 477be69..a23dd19 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -164,7 +164,7 @@
 	end = PFN_DOWN(physaddr + size);
 
 	for (; cursor < end; cursor++) {
-		__free_pages_bootmem(pfn_to_page(cursor), 0);
+		__free_pages_bootmem(pfn_to_page(cursor), cursor, 0);
 		totalram_pages++;
 	}
 }
@@ -172,7 +172,7 @@
 static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 {
 	struct page *page;
-	unsigned long *map, start, end, pages, count = 0;
+	unsigned long *map, start, end, pages, cur, count = 0;
 
 	if (!bdata->node_bootmem_map)
 		return 0;
@@ -210,17 +210,17 @@
 		if (IS_ALIGNED(start, BITS_PER_LONG) && vec == ~0UL) {
 			int order = ilog2(BITS_PER_LONG);
 
-			__free_pages_bootmem(pfn_to_page(start), order);
+			__free_pages_bootmem(pfn_to_page(start), start, order);
 			count += BITS_PER_LONG;
 			start += BITS_PER_LONG;
 		} else {
-			unsigned long cur = start;
+			cur = start;
 
 			start = ALIGN(start + 1, BITS_PER_LONG);
 			while (vec && cur != start) {
 				if (vec & 1) {
 					page = pfn_to_page(cur);
-					__free_pages_bootmem(page, 0);
+					__free_pages_bootmem(page, cur, 0);
 					count++;
 				}
 				vec >>= 1;
@@ -229,12 +229,13 @@
 		}
 	}
 
+	cur = bdata->node_min_pfn;
 	page = virt_to_page(bdata->node_bootmem_map);
 	pages = bdata->node_low_pfn - bdata->node_min_pfn;
 	pages = bootmem_bootmap_pages(pages);
 	count += pages;
 	while (pages--)
-		__free_pages_bootmem(page++, 0);
+		__free_pages_bootmem(page++, cur++, 0);
 
 	bdebug("nid=%td released=%lx\n", bdata - bootmem_node_data, count);
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 11f10ef..1283fc8 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2563,7 +2563,7 @@
 
 	/* We can write back this queue in page reclaim */
 	current->backing_dev_info = inode_to_bdi(inode);
-	err = file_remove_suid(file);
+	err = file_remove_privs(file);
 	if (err)
 		goto out;
 
diff --git a/mm/internal.h b/mm/internal.h
index a25e359..36b23f1 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -155,7 +155,8 @@
 }
 
 extern int __isolate_free_page(struct page *page, unsigned int order);
-extern void __free_pages_bootmem(struct page *page, unsigned int order);
+extern void __free_pages_bootmem(struct page *page, unsigned long pfn,
+					unsigned int order);
 extern void prep_compound_page(struct page *page, unsigned long order);
 #ifdef CONFIG_MEMORY_FAILURE
 extern bool is_free_buddy_page(struct page *page);
@@ -361,10 +362,7 @@
 } while (0)
 
 extern void mminit_verify_pageflags_layout(void);
-extern void mminit_verify_page_links(struct page *page,
-		enum zone_type zone, unsigned long nid, unsigned long pfn);
 extern void mminit_verify_zonelist(void);
-
 #else
 
 static inline void mminit_dprintk(enum mminit_level level,
@@ -376,11 +374,6 @@
 {
 }
 
-static inline void mminit_verify_page_links(struct page *page,
-		enum zone_type zone, unsigned long nid, unsigned long pfn)
-{
-}
-
 static inline void mminit_verify_zonelist(void)
 {
 }
diff --git a/mm/memblock.c b/mm/memblock.c
index 1b444c7..87108e7 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -820,6 +820,38 @@
 
 
 /**
+ * __next_reserved_mem_region - next function for for_each_reserved_region()
+ * @idx: pointer to u64 loop variable
+ * @out_start: ptr to phys_addr_t for start address of the region, can be %NULL
+ * @out_end: ptr to phys_addr_t for end address of the region, can be %NULL
+ *
+ * Iterate over all reserved memory regions.
+ */
+void __init_memblock __next_reserved_mem_region(u64 *idx,
+					   phys_addr_t *out_start,
+					   phys_addr_t *out_end)
+{
+	struct memblock_type *rsv = &memblock.reserved;
+
+	if (*idx >= 0 && *idx < rsv->cnt) {
+		struct memblock_region *r = &rsv->regions[*idx];
+		phys_addr_t base = r->base;
+		phys_addr_t size = r->size;
+
+		if (out_start)
+			*out_start = base;
+		if (out_end)
+			*out_end = base + size - 1;
+
+		*idx += 1;
+		return;
+	}
+
+	/* signal end of iteration */
+	*idx = ULLONG_MAX;
+}
+
+/**
  * __next__mem_range - next function for for_each_free_mem_range() etc.
  * @idx: pointer to u64 loop variable
  * @nid: node selector, %NUMA_NO_NODE for all nodes
@@ -1387,7 +1419,7 @@
 	end = PFN_DOWN(base + size);
 
 	for (; cursor < end; cursor++) {
-		__free_pages_bootmem(pfn_to_page(cursor), 0);
+		__free_pages_bootmem(pfn_to_page(cursor), cursor, 0);
 		totalram_pages++;
 	}
 }
diff --git a/mm/memory.c b/mm/memory.c
index 11b9ca1..a84fbb7 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3726,7 +3726,7 @@
 		if (buf) {
 			char *p;
 
-			p = d_path(&f->f_path, buf, PAGE_SIZE);
+			p = file_path(f, buf, PAGE_SIZE);
 			if (IS_ERR(p))
 				p = "?";
 			printk("%s%s[%lx+%lx]", prefix, kbasename(p),
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 5f420f7..fdadf91 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -11,6 +11,7 @@
 #include <linux/export.h>
 #include <linux/memory.h>
 #include <linux/notifier.h>
+#include <linux/sched.h>
 #include "internal.h"
 
 #ifdef CONFIG_DEBUG_MEMORY_INIT
@@ -130,14 +131,6 @@
 	BUG_ON(or_mask != add_mask);
 }
 
-void __meminit mminit_verify_page_links(struct page *page, enum zone_type zone,
-			unsigned long nid, unsigned long pfn)
-{
-	BUG_ON(page_to_nid(page) != nid);
-	BUG_ON(page_zonenum(page) != zone);
-	BUG_ON(page_to_pfn(page) != pfn);
-}
-
 static __init int set_mminit_loglevel(char *str)
 {
 	get_option(&str, &mminit_loglevel);
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index 5258386..e57cf24 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -86,7 +86,7 @@
 	end = PFN_DOWN(addr + size);
 
 	for (; cursor < end; cursor++) {
-		__free_pages_bootmem(pfn_to_page(cursor), 0);
+		__free_pages_bootmem(pfn_to_page(cursor), cursor, 0);
 		totalram_pages++;
 	}
 }
@@ -101,7 +101,7 @@
 		while (start + (1UL << order) > end)
 			order--;
 
-		__free_pages_bootmem(pfn_to_page(start), order);
+		__free_pages_bootmem(pfn_to_page(start), start, order);
 
 		start += (1UL << order);
 	}
@@ -130,6 +130,9 @@
 
 	memblock_clear_hotplug(0, -1);
 
+	for_each_reserved_mem_region(i, &start, &end)
+		reserve_bootmem_region(start, end);
+
 	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end,
 				NULL)
 		count += __free_memory_core(start, end);
diff --git a/mm/nommu.c b/mm/nommu.c
index 05e7447..58ea364 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -2085,7 +2085,7 @@
 	sysctl_user_reserve_kbytes = min(free_kbytes / 32, 1UL << 17);
 	return 0;
 }
-module_init(init_user_reserve)
+subsys_initcall(init_user_reserve);
 
 /*
  * Initialise sysctl_admin_reserve_kbytes.
@@ -2106,4 +2106,4 @@
 	sysctl_admin_reserve_kbytes = min(free_kbytes / 32, 1UL << 13);
 	return 0;
 }
-module_init(init_admin_reserve)
+subsys_initcall(init_admin_reserve);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5e6fa06..506eac8 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -18,6 +18,7 @@
 #include <linux/mm.h>
 #include <linux/swap.h>
 #include <linux/interrupt.h>
+#include <linux/rwsem.h>
 #include <linux/pagemap.h>
 #include <linux/jiffies.h>
 #include <linux/bootmem.h>
@@ -61,6 +62,7 @@
 #include <linux/hugetlb.h>
 #include <linux/sched/rt.h>
 #include <linux/page_owner.h>
+#include <linux/kthread.h>
 
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
@@ -235,6 +237,77 @@
 
 int page_group_by_mobility_disabled __read_mostly;
 
+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+static inline void reset_deferred_meminit(pg_data_t *pgdat)
+{
+	pgdat->first_deferred_pfn = ULONG_MAX;
+}
+
+/* Returns true if the struct page for the pfn is uninitialised */
+static inline bool __meminit early_page_uninitialised(unsigned long pfn)
+{
+	int nid = early_pfn_to_nid(pfn);
+
+	if (pfn >= NODE_DATA(nid)->first_deferred_pfn)
+		return true;
+
+	return false;
+}
+
+static inline bool early_page_nid_uninitialised(unsigned long pfn, int nid)
+{
+	if (pfn >= NODE_DATA(nid)->first_deferred_pfn)
+		return true;
+
+	return false;
+}
+
+/*
+ * Returns false when the remaining initialisation should be deferred until
+ * later in the boot cycle when it can be parallelised.
+ */
+static inline bool update_defer_init(pg_data_t *pgdat,
+				unsigned long pfn, unsigned long zone_end,
+				unsigned long *nr_initialised)
+{
+	/* Always populate low zones for address-contrained allocations */
+	if (zone_end < pgdat_end_pfn(pgdat))
+		return true;
+
+	/* Initialise at least 2G of the highest zone */
+	(*nr_initialised)++;
+	if (*nr_initialised > (2UL << (30 - PAGE_SHIFT)) &&
+	    (pfn & (PAGES_PER_SECTION - 1)) == 0) {
+		pgdat->first_deferred_pfn = pfn;
+		return false;
+	}
+
+	return true;
+}
+#else
+static inline void reset_deferred_meminit(pg_data_t *pgdat)
+{
+}
+
+static inline bool early_page_uninitialised(unsigned long pfn)
+{
+	return false;
+}
+
+static inline bool early_page_nid_uninitialised(unsigned long pfn, int nid)
+{
+	return false;
+}
+
+static inline bool update_defer_init(pg_data_t *pgdat,
+				unsigned long pfn, unsigned long zone_end,
+				unsigned long *nr_initialised)
+{
+	return true;
+}
+#endif
+
+
 void set_pageblock_migratetype(struct page *page, int migratetype)
 {
 	if (unlikely(page_group_by_mobility_disabled &&
@@ -764,6 +837,75 @@
 	return 0;
 }
 
+static void __meminit __init_single_page(struct page *page, unsigned long pfn,
+				unsigned long zone, int nid)
+{
+	set_page_links(page, zone, nid, pfn);
+	init_page_count(page);
+	page_mapcount_reset(page);
+	page_cpupid_reset_last(page);
+
+	INIT_LIST_HEAD(&page->lru);
+#ifdef WANT_PAGE_VIRTUAL
+	/* The shift won't overflow because ZONE_NORMAL is below 4G. */
+	if (!is_highmem_idx(zone))
+		set_page_address(page, __va(pfn << PAGE_SHIFT));
+#endif
+}
+
+static void __meminit __init_single_pfn(unsigned long pfn, unsigned long zone,
+					int nid)
+{
+	return __init_single_page(pfn_to_page(pfn), pfn, zone, nid);
+}
+
+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+static void init_reserved_page(unsigned long pfn)
+{
+	pg_data_t *pgdat;
+	int nid, zid;
+
+	if (!early_page_uninitialised(pfn))
+		return;
+
+	nid = early_pfn_to_nid(pfn);
+	pgdat = NODE_DATA(nid);
+
+	for (zid = 0; zid < MAX_NR_ZONES; zid++) {
+		struct zone *zone = &pgdat->node_zones[zid];
+
+		if (pfn >= zone->zone_start_pfn && pfn < zone_end_pfn(zone))
+			break;
+	}
+	__init_single_pfn(pfn, zid, nid);
+}
+#else
+static inline void init_reserved_page(unsigned long pfn)
+{
+}
+#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
+
+/*
+ * Initialised pages do not have PageReserved set. This function is
+ * called for each range allocated by the bootmem allocator and
+ * marks the pages PageReserved. The remaining valid pages are later
+ * sent to the buddy page allocator.
+ */
+void __meminit reserve_bootmem_region(unsigned long start, unsigned long end)
+{
+	unsigned long start_pfn = PFN_DOWN(start);
+	unsigned long end_pfn = PFN_UP(end);
+
+	for (; start_pfn < end_pfn; start_pfn++) {
+		if (pfn_valid(start_pfn)) {
+			struct page *page = pfn_to_page(start_pfn);
+
+			init_reserved_page(start_pfn);
+			SetPageReserved(page);
+		}
+	}
+}
+
 static bool free_pages_prepare(struct page *page, unsigned int order)
 {
 	bool compound = PageCompound(page);
@@ -818,7 +960,8 @@
 	local_irq_restore(flags);
 }
 
-void __init __free_pages_bootmem(struct page *page, unsigned int order)
+static void __init __free_pages_boot_core(struct page *page,
+					unsigned long pfn, unsigned int order)
 {
 	unsigned int nr_pages = 1 << order;
 	struct page *p = page;
@@ -838,6 +981,223 @@
 	__free_pages(page, order);
 }
 
+#if defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) || \
+	defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP)
+/* Only safe to use early in boot when initialisation is single-threaded */
+static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata;
+
+int __meminit early_pfn_to_nid(unsigned long pfn)
+{
+	int nid;
+
+	/* The system will behave unpredictably otherwise */
+	BUG_ON(system_state != SYSTEM_BOOTING);
+
+	nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache);
+	if (nid >= 0)
+		return nid;
+	/* just returns 0 */
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_NODES_SPAN_OTHER_NODES
+static inline bool __meminit meminit_pfn_in_nid(unsigned long pfn, int node,
+					struct mminit_pfnnid_cache *state)
+{
+	int nid;
+
+	nid = __early_pfn_to_nid(pfn, state);
+	if (nid >= 0 && nid != node)
+		return false;
+	return true;
+}
+
+/* Only safe to use early in boot when initialisation is single-threaded */
+static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
+{
+	return meminit_pfn_in_nid(pfn, node, &early_pfnnid_cache);
+}
+
+#else
+
+static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
+{
+	return true;
+}
+static inline bool __meminit meminit_pfn_in_nid(unsigned long pfn, int node,
+					struct mminit_pfnnid_cache *state)
+{
+	return true;
+}
+#endif
+
+
+void __init __free_pages_bootmem(struct page *page, unsigned long pfn,
+							unsigned int order)
+{
+	if (early_page_uninitialised(pfn))
+		return;
+	return __free_pages_boot_core(page, pfn, order);
+}
+
+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+static void __init deferred_free_range(struct page *page,
+					unsigned long pfn, int nr_pages)
+{
+	int i;
+
+	if (!page)
+		return;
+
+	/* Free a large naturally-aligned chunk if possible */
+	if (nr_pages == MAX_ORDER_NR_PAGES &&
+	    (pfn & (MAX_ORDER_NR_PAGES-1)) == 0) {
+		set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+		__free_pages_boot_core(page, pfn, MAX_ORDER-1);
+		return;
+	}
+
+	for (i = 0; i < nr_pages; i++, page++, pfn++)
+		__free_pages_boot_core(page, pfn, 0);
+}
+
+static __initdata DECLARE_RWSEM(pgdat_init_rwsem);
+
+/* Initialise remaining memory on a node */
+static int __init deferred_init_memmap(void *data)
+{
+	pg_data_t *pgdat = data;
+	int nid = pgdat->node_id;
+	struct mminit_pfnnid_cache nid_init_state = { };
+	unsigned long start = jiffies;
+	unsigned long nr_pages = 0;
+	unsigned long walk_start, walk_end;
+	int i, zid;
+	struct zone *zone;
+	unsigned long first_init_pfn = pgdat->first_deferred_pfn;
+	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
+
+	if (first_init_pfn == ULONG_MAX) {
+		up_read(&pgdat_init_rwsem);
+		return 0;
+	}
+
+	/* Bind memory initialisation thread to a local node if possible */
+	if (!cpumask_empty(cpumask))
+		set_cpus_allowed_ptr(current, cpumask);
+
+	/* Sanity check boundaries */
+	BUG_ON(pgdat->first_deferred_pfn < pgdat->node_start_pfn);
+	BUG_ON(pgdat->first_deferred_pfn > pgdat_end_pfn(pgdat));
+	pgdat->first_deferred_pfn = ULONG_MAX;
+
+	/* Only the highest zone is deferred so find it */
+	for (zid = 0; zid < MAX_NR_ZONES; zid++) {
+		zone = pgdat->node_zones + zid;
+		if (first_init_pfn < zone_end_pfn(zone))
+			break;
+	}
+
+	for_each_mem_pfn_range(i, nid, &walk_start, &walk_end, NULL) {
+		unsigned long pfn, end_pfn;
+		struct page *page = NULL;
+		struct page *free_base_page = NULL;
+		unsigned long free_base_pfn = 0;
+		int nr_to_free = 0;
+
+		end_pfn = min(walk_end, zone_end_pfn(zone));
+		pfn = first_init_pfn;
+		if (pfn < walk_start)
+			pfn = walk_start;
+		if (pfn < zone->zone_start_pfn)
+			pfn = zone->zone_start_pfn;
+
+		for (; pfn < end_pfn; pfn++) {
+			if (!pfn_valid_within(pfn))
+				goto free_range;
+
+			/*
+			 * Ensure pfn_valid is checked every
+			 * MAX_ORDER_NR_PAGES for memory holes
+			 */
+			if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0) {
+				if (!pfn_valid(pfn)) {
+					page = NULL;
+					goto free_range;
+				}
+			}
+
+			if (!meminit_pfn_in_nid(pfn, nid, &nid_init_state)) {
+				page = NULL;
+				goto free_range;
+			}
+
+			/* Minimise pfn page lookups and scheduler checks */
+			if (page && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0) {
+				page++;
+			} else {
+				nr_pages += nr_to_free;
+				deferred_free_range(free_base_page,
+						free_base_pfn, nr_to_free);
+				free_base_page = NULL;
+				free_base_pfn = nr_to_free = 0;
+
+				page = pfn_to_page(pfn);
+				cond_resched();
+			}
+
+			if (page->flags) {
+				VM_BUG_ON(page_zone(page) != zone);
+				goto free_range;
+			}
+
+			__init_single_page(page, pfn, zid, nid);
+			if (!free_base_page) {
+				free_base_page = page;
+				free_base_pfn = pfn;
+				nr_to_free = 0;
+			}
+			nr_to_free++;
+
+			/* Where possible, batch up pages for a single free */
+			continue;
+free_range:
+			/* Free the current block of pages to allocator */
+			nr_pages += nr_to_free;
+			deferred_free_range(free_base_page, free_base_pfn,
+								nr_to_free);
+			free_base_page = NULL;
+			free_base_pfn = nr_to_free = 0;
+		}
+
+		first_init_pfn = max(end_pfn, first_init_pfn);
+	}
+
+	/* Sanity check that the next zone really is unpopulated */
+	WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone));
+
+	pr_info("node %d initialised, %lu pages in %ums\n", nid, nr_pages,
+					jiffies_to_msecs(jiffies - start));
+	up_read(&pgdat_init_rwsem);
+	return 0;
+}
+
+void __init page_alloc_init_late(void)
+{
+	int nid;
+
+	for_each_node_state(nid, N_MEMORY) {
+		down_read(&pgdat_init_rwsem);
+		kthread_run(deferred_init_memmap, NODE_DATA(nid), "pgdatinit%d", nid);
+	}
+
+	/* Block until all are initialised */
+	down_write(&pgdat_init_rwsem);
+	up_write(&pgdat_init_rwsem);
+}
+#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
+
 #ifdef CONFIG_CMA
 /* Free whole pageblock and set its migration type to MIGRATE_CMA. */
 void __init init_cma_reserved_pageblock(struct page *page)
@@ -4150,6 +4510,9 @@
 	zone->nr_migrate_reserve_block = reserve;
 
 	for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
+		if (!early_page_nid_uninitialised(pfn, zone_to_nid(zone)))
+			return;
+
 		if (!pfn_valid(pfn))
 			continue;
 		page = pfn_to_page(pfn);
@@ -4212,15 +4575,16 @@
 void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		unsigned long start_pfn, enum memmap_context context)
 {
-	struct page *page;
+	pg_data_t *pgdat = NODE_DATA(nid);
 	unsigned long end_pfn = start_pfn + size;
 	unsigned long pfn;
 	struct zone *z;
+	unsigned long nr_initialised = 0;
 
 	if (highest_memmap_pfn < end_pfn - 1)
 		highest_memmap_pfn = end_pfn - 1;
 
-	z = &NODE_DATA(nid)->node_zones[zone];
+	z = &pgdat->node_zones[zone];
 	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
 		/*
 		 * There can be holes in boot-time mem_map[]s
@@ -4232,14 +4596,11 @@
 				continue;
 			if (!early_pfn_in_nid(pfn, nid))
 				continue;
+			if (!update_defer_init(pgdat, pfn, end_pfn,
+						&nr_initialised))
+				break;
 		}
-		page = pfn_to_page(pfn);
-		set_page_links(page, zone, nid, pfn);
-		mminit_verify_page_links(page, zone, nid, pfn);
-		init_page_count(page);
-		page_mapcount_reset(page);
-		page_cpupid_reset_last(page);
-		SetPageReserved(page);
+
 		/*
 		 * Mark the block movable so that blocks are reserved for
 		 * movable at startup. This will force kernel allocations
@@ -4254,17 +4615,14 @@
 		 * check here not to call set_pageblock_migratetype() against
 		 * pfn out of zone.
 		 */
-		if ((z->zone_start_pfn <= pfn)
-		    && (pfn < zone_end_pfn(z))
-		    && !(pfn & (pageblock_nr_pages - 1)))
-			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+		if (!(pfn & (pageblock_nr_pages - 1))) {
+			struct page *page = pfn_to_page(pfn);
 
-		INIT_LIST_HEAD(&page->lru);
-#ifdef WANT_PAGE_VIRTUAL
-		/* The shift won't overflow because ZONE_NORMAL is below 4G. */
-		if (!is_highmem_idx(zone))
-			set_page_address(page, __va(pfn << PAGE_SHIFT));
-#endif
+			__init_single_page(page, pfn, zone, nid);
+			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+		} else {
+			__init_single_pfn(pfn, zone, nid);
+		}
 	}
 }
 
@@ -4522,57 +4880,30 @@
 
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 #ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
+
 /*
  * Required by SPARSEMEM. Given a PFN, return what node the PFN is on.
  */
-int __meminit __early_pfn_to_nid(unsigned long pfn)
+int __meminit __early_pfn_to_nid(unsigned long pfn,
+					struct mminit_pfnnid_cache *state)
 {
 	unsigned long start_pfn, end_pfn;
 	int nid;
-	/*
-	 * NOTE: The following SMP-unsafe globals are only used early in boot
-	 * when the kernel is running single-threaded.
-	 */
-	static unsigned long __meminitdata last_start_pfn, last_end_pfn;
-	static int __meminitdata last_nid;
 
-	if (last_start_pfn <= pfn && pfn < last_end_pfn)
-		return last_nid;
+	if (state->last_start <= pfn && pfn < state->last_end)
+		return state->last_nid;
 
 	nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn);
 	if (nid != -1) {
-		last_start_pfn = start_pfn;
-		last_end_pfn = end_pfn;
-		last_nid = nid;
+		state->last_start = start_pfn;
+		state->last_end = end_pfn;
+		state->last_nid = nid;
 	}
 
 	return nid;
 }
 #endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */
 
-int __meminit early_pfn_to_nid(unsigned long pfn)
-{
-	int nid;
-
-	nid = __early_pfn_to_nid(pfn);
-	if (nid >= 0)
-		return nid;
-	/* just returns 0 */
-	return 0;
-}
-
-#ifdef CONFIG_NODES_SPAN_OTHER_NODES
-bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
-{
-	int nid;
-
-	nid = __early_pfn_to_nid(pfn);
-	if (nid >= 0 && nid != node)
-		return false;
-	return true;
-}
-#endif
-
 /**
  * free_bootmem_with_active_regions - Call memblock_free_early_nid for each active range
  * @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed.
@@ -5090,6 +5421,7 @@
 	/* pg_data_t should be reset to zero when it's allocated */
 	WARN_ON(pgdat->nr_zones || pgdat->classzone_idx);
 
+	reset_deferred_meminit(pgdat);
 	pgdat->node_id = nid;
 	pgdat->node_start_pfn = node_start_pfn;
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 0993f5f..bd5f842 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -310,4 +310,4 @@
 
 	return 0;
 }
-module_init(pageowner_init)
+late_initcall(pageowner_init)
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 983b786..3e5f8f2 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -855,7 +855,7 @@
 	}
 }
 
-static void new_kmalloc_cache(int idx, unsigned long flags)
+static void __init new_kmalloc_cache(int idx, unsigned long flags)
 {
 	kmalloc_caches[idx] = create_kmalloc_cache(kmalloc_info[idx].name,
 					kmalloc_info[idx].size, flags);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index a7e7210..41e4581 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2032,7 +2032,7 @@
 	}
 
 	file = si->swap_file;
-	len = seq_path(swap, &file->f_path, " \t\n\\");
+	len = seq_file_path(swap, file, " \t\n\\");
 	seq_printf(swap, "%*s%s\t%u\t%u\t%d\n",
 			len < 40 ? 40 - len : 1, " ",
 			S_ISBLK(file_inode(file)->i_mode) ?
diff --git a/net/9p/client.c b/net/9p/client.c
index 6f4c4c8..498454b 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -843,7 +843,8 @@
 	if (err < 0) {
 		if (err == -EIO)
 			c->status = Disconnected;
-		goto reterr;
+		if (err != -ERESTARTSYS)
+			goto reterr;
 	}
 	if (req->status == REQ_STATUS_ERROR) {
 		p9_debug(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err);
@@ -1582,6 +1583,10 @@
 			p9_free_req(clnt, req);
 			break;
 		}
+		if (rsize < count) {
+			pr_err("bogus RREAD count (%d > %d)\n", count, rsize);
+			count = rsize;
+		}
 
 		p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", count);
 		if (!count) {
@@ -1647,6 +1652,11 @@
 		if (*err) {
 			trace_9p_protocol_dump(clnt, req->rc);
 			p9_free_req(clnt, req);
+			break;
+		}
+		if (rsize < count) {
+			pr_err("bogus RWRITE count (%d > %d)\n", count, rsize);
+			count = rsize;
 		}
 
 		p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", count);
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 9c891d0..ae3a47f 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -57,7 +57,7 @@
 
 static void ax25_free_sock(struct sock *sk)
 {
-	ax25_cb_put(ax25_sk(sk));
+	ax25_cb_put(sk_to_ax25(sk));
 }
 
 /*
@@ -306,7 +306,7 @@
 		while ((skb = skb_dequeue(&ax25->sk->sk_receive_queue)) != NULL) {
 			if (skb->sk != ax25->sk) {
 				/* A pending connection */
-				ax25_cb *sax25 = ax25_sk(skb->sk);
+				ax25_cb *sax25 = sk_to_ax25(skb->sk);
 
 				/* Queue the unaccepted socket for death */
 				sock_orphan(skb->sk);
@@ -551,7 +551,7 @@
 		return -EFAULT;
 
 	lock_sock(sk);
-	ax25 = ax25_sk(sk);
+	ax25 = sk_to_ax25(sk);
 
 	switch (optname) {
 	case AX25_WINDOW:
@@ -697,7 +697,7 @@
 	length = min_t(unsigned int, maxlen, sizeof(int));
 
 	lock_sock(sk);
-	ax25 = ax25_sk(sk);
+	ax25 = sk_to_ax25(sk);
 
 	switch (optname) {
 	case AX25_WINDOW:
@@ -796,7 +796,7 @@
 static struct proto ax25_proto = {
 	.name	  = "AX25",
 	.owner	  = THIS_MODULE,
-	.obj_size = sizeof(struct sock),
+	.obj_size = sizeof(struct ax25_sock),
 };
 
 static int ax25_create(struct net *net, struct socket *sock, int protocol,
@@ -858,7 +858,7 @@
 	if (sk == NULL)
 		return -ENOMEM;
 
-	ax25 = sk->sk_protinfo = ax25_create_cb();
+	ax25 = ax25_sk(sk)->cb = ax25_create_cb();
 	if (!ax25) {
 		sk_free(sk);
 		return -ENOMEM;
@@ -910,7 +910,7 @@
 	sk->sk_state    = TCP_ESTABLISHED;
 	sock_copy_flags(sk, osk);
 
-	oax25 = ax25_sk(osk);
+	oax25 = sk_to_ax25(osk);
 
 	ax25->modulus = oax25->modulus;
 	ax25->backoff = oax25->backoff;
@@ -938,7 +938,7 @@
 		}
 	}
 
-	sk->sk_protinfo = ax25;
+	ax25_sk(sk)->cb = ax25;
 	sk->sk_destruct = ax25_free_sock;
 	ax25->sk    = sk;
 
@@ -956,7 +956,7 @@
 	sock_hold(sk);
 	sock_orphan(sk);
 	lock_sock(sk);
-	ax25 = ax25_sk(sk);
+	ax25 = sk_to_ax25(sk);
 
 	if (sk->sk_type == SOCK_SEQPACKET) {
 		switch (ax25->state) {
@@ -1066,7 +1066,7 @@
 
 	lock_sock(sk);
 
-	ax25 = ax25_sk(sk);
+	ax25 = sk_to_ax25(sk);
 	if (!sock_flag(sk, SOCK_ZAPPED)) {
 		err = -EINVAL;
 		goto out;
@@ -1113,7 +1113,7 @@
 	struct sockaddr *uaddr, int addr_len, int flags)
 {
 	struct sock *sk = sock->sk;
-	ax25_cb *ax25 = ax25_sk(sk), *ax25t;
+	ax25_cb *ax25 = sk_to_ax25(sk), *ax25t;
 	struct full_sockaddr_ax25 *fsa = (struct full_sockaddr_ax25 *)uaddr;
 	ax25_digi *digi = NULL;
 	int ct = 0, err = 0;
@@ -1394,7 +1394,7 @@
 
 	memset(fsa, 0, sizeof(*fsa));
 	lock_sock(sk);
-	ax25 = ax25_sk(sk);
+	ax25 = sk_to_ax25(sk);
 
 	if (peer != 0) {
 		if (sk->sk_state != TCP_ESTABLISHED) {
@@ -1446,7 +1446,7 @@
 		return -EINVAL;
 
 	lock_sock(sk);
-	ax25 = ax25_sk(sk);
+	ax25 = sk_to_ax25(sk);
 
 	if (sock_flag(sk, SOCK_ZAPPED)) {
 		err = -EADDRNOTAVAIL;
@@ -1621,7 +1621,7 @@
 	if (skb == NULL)
 		goto out;
 
-	if (!ax25_sk(sk)->pidincl)
+	if (!sk_to_ax25(sk)->pidincl)
 		skb_pull(skb, 1);		/* Remove PID */
 
 	skb_reset_transport_header(skb);
@@ -1762,7 +1762,7 @@
 
 	case SIOCAX25GETINFO:
 	case SIOCAX25GETINFOOLD: {
-		ax25_cb *ax25 = ax25_sk(sk);
+		ax25_cb *ax25 = sk_to_ax25(sk);
 		struct ax25_info_struct ax25_info;
 
 		ax25_info.t1        = ax25->t1   / HZ;
diff --git a/net/ax25/ax25_in.c b/net/ax25/ax25_in.c
index 29a3687..bb5a0e4 100644
--- a/net/ax25/ax25_in.c
+++ b/net/ax25/ax25_in.c
@@ -353,7 +353,7 @@
 			return 0;
 		}
 
-		ax25 = ax25_sk(make);
+		ax25 = sk_to_ax25(make);
 		skb_set_owner_r(skb, make);
 		skb_queue_head(&sk->sk_receive_queue, skb);
 
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 9070dfd..f1a117f 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -915,6 +915,7 @@
 	session->conn = l2cap_conn_get(conn);
 	session->user.probe = hidp_session_probe;
 	session->user.remove = hidp_session_remove;
+	INIT_LIST_HEAD(&session->user.list);
 	session->ctrl_sock = ctrl_sock;
 	session->intr_sock = intr_sock;
 	skb_queue_head_init(&session->ctrl_transmit);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 51594fb..45fffa4 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1634,7 +1634,7 @@
 	if (list_empty(&user->list))
 		goto out_unlock;
 
-	list_del(&user->list);
+	list_del_init(&user->list);
 	user->remove(conn, user);
 
 out_unlock:
@@ -1648,7 +1648,7 @@
 
 	while (!list_empty(&conn->users)) {
 		user = list_first_entry(&conn->users, struct l2cap_user, list);
-		list_del(&user->list);
+		list_del_init(&user->list);
 		user->remove(conn, user);
 	}
 }
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 79e8f71..cb7db32 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -352,8 +352,8 @@
 	/* start with defaults */
 	opt->flags = CEPH_OPT_DEFAULT;
 	opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT;
-	opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; /* seconds */
-	opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT;   /* seconds */
+	opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT;
+	opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT;
 
 	/* get mon ip(s) */
 	/* ip1[:port1][,ip2[:port2]...] */
@@ -439,13 +439,32 @@
 			pr_warn("ignoring deprecated osdtimeout option\n");
 			break;
 		case Opt_osdkeepalivetimeout:
-			opt->osd_keepalive_timeout = intval;
+			/* 0 isn't well defined right now, reject it */
+			if (intval < 1 || intval > INT_MAX / 1000) {
+				pr_err("osdkeepalive out of range\n");
+				err = -EINVAL;
+				goto out;
+			}
+			opt->osd_keepalive_timeout =
+					msecs_to_jiffies(intval * 1000);
 			break;
 		case Opt_osd_idle_ttl:
-			opt->osd_idle_ttl = intval;
+			/* 0 isn't well defined right now, reject it */
+			if (intval < 1 || intval > INT_MAX / 1000) {
+				pr_err("osd_idle_ttl out of range\n");
+				err = -EINVAL;
+				goto out;
+			}
+			opt->osd_idle_ttl = msecs_to_jiffies(intval * 1000);
 			break;
 		case Opt_mount_timeout:
-			opt->mount_timeout = intval;
+			/* 0 is "wait forever" (i.e. infinite timeout) */
+			if (intval < 0 || intval > INT_MAX / 1000) {
+				pr_err("mount_timeout out of range\n");
+				err = -EINVAL;
+				goto out;
+			}
+			opt->mount_timeout = msecs_to_jiffies(intval * 1000);
 			break;
 
 		case Opt_share:
@@ -512,12 +531,14 @@
 		seq_puts(m, "notcp_nodelay,");
 
 	if (opt->mount_timeout != CEPH_MOUNT_TIMEOUT_DEFAULT)
-		seq_printf(m, "mount_timeout=%d,", opt->mount_timeout);
+		seq_printf(m, "mount_timeout=%d,",
+			   jiffies_to_msecs(opt->mount_timeout) / 1000);
 	if (opt->osd_idle_ttl != CEPH_OSD_IDLE_TTL_DEFAULT)
-		seq_printf(m, "osd_idle_ttl=%d,", opt->osd_idle_ttl);
+		seq_printf(m, "osd_idle_ttl=%d,",
+			   jiffies_to_msecs(opt->osd_idle_ttl) / 1000);
 	if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT)
 		seq_printf(m, "osdkeepalivetimeout=%d,",
-			   opt->osd_keepalive_timeout);
+		    jiffies_to_msecs(opt->osd_keepalive_timeout) / 1000);
 
 	/* drop redundant comma */
 	if (m->count != pos)
@@ -626,8 +647,8 @@
  */
 int __ceph_open_session(struct ceph_client *client, unsigned long started)
 {
-	int err;
-	unsigned long timeout = client->options->mount_timeout * HZ;
+	unsigned long timeout = client->options->mount_timeout;
+	long err;
 
 	/* open session, and wait for mon and osd maps */
 	err = ceph_monc_open_session(&client->monc);
@@ -635,16 +656,15 @@
 		return err;
 
 	while (!have_mon_and_osd_map(client)) {
-		err = -EIO;
 		if (timeout && time_after_eq(jiffies, started + timeout))
-			return err;
+			return -ETIMEDOUT;
 
 		/* wait */
 		dout("mount waiting for mon_map\n");
 		err = wait_event_interruptible_timeout(client->auth_wq,
 			have_mon_and_osd_map(client) || (client->auth_err < 0),
-			timeout);
-		if (err == -EINTR || err == -ERESTARTSYS)
+			ceph_timeout_jiffies(timeout));
+		if (err < 0)
 			return err;
 		if (client->auth_err < 0)
 			return client->auth_err;
@@ -721,5 +741,5 @@
 MODULE_AUTHOR("Sage Weil <sage@newdream.net>");
 MODULE_AUTHOR("Yehuda Sadeh <yehuda@hq.newdream.net>");
 MODULE_AUTHOR("Patience Warnick <patience@newdream.net>");
-MODULE_DESCRIPTION("Ceph filesystem for Linux");
+MODULE_DESCRIPTION("Ceph core library");
 MODULE_LICENSE("GPL");
diff --git a/net/ceph/crush/crush.c b/net/ceph/crush/crush.c
index 9d84ce4..80d7c3a 100644
--- a/net/ceph/crush/crush.c
+++ b/net/ceph/crush/crush.c
@@ -1,15 +1,11 @@
-
 #ifdef __KERNEL__
 # include <linux/slab.h>
+# include <linux/crush/crush.h>
 #else
-# include <stdlib.h>
-# include <assert.h>
-# define kfree(x) do { if (x) free(x); } while (0)
-# define BUG_ON(x) assert(!(x))
+# include "crush_compat.h"
+# include "crush.h"
 #endif
 
-#include <linux/crush/crush.h>
-
 const char *crush_bucket_alg_name(int alg)
 {
 	switch (alg) {
@@ -134,6 +130,9 @@
 		kfree(map->rules);
 	}
 
+#ifndef __KERNEL__
+	kfree(map->choose_tries);
+#endif
 	kfree(map);
 }
 
diff --git a/net/ceph/crush/crush_ln_table.h b/net/ceph/crush/crush_ln_table.h
index 6192c7f..aae534c 100644
--- a/net/ceph/crush/crush_ln_table.h
+++ b/net/ceph/crush/crush_ln_table.h
@@ -10,20 +10,20 @@
  *
  */
 
-#if defined(__linux__)
-#include <linux/types.h>
-#elif defined(__FreeBSD__)
-#include <sys/types.h>
-#endif
-
 #ifndef CEPH_CRUSH_LN_H
 #define CEPH_CRUSH_LN_H
 
+#ifdef __KERNEL__
+# include <linux/types.h>
+#else
+# include "crush_compat.h"
+#endif
 
-// RH_LH_tbl[2*k] = 2^48/(1.0+k/128.0)
-// RH_LH_tbl[2*k+1] = 2^48*log2(1.0+k/128.0)
-
-static int64_t __RH_LH_tbl[128*2+2] = {
+/*
+ * RH_LH_tbl[2*k] = 2^48/(1.0+k/128.0)
+ * RH_LH_tbl[2*k+1] = 2^48*log2(1.0+k/128.0)
+ */
+static __s64 __RH_LH_tbl[128*2+2] = {
   0x0001000000000000ll, 0x0000000000000000ll, 0x0000fe03f80fe040ll, 0x000002dfca16dde1ll,
   0x0000fc0fc0fc0fc1ll, 0x000005b9e5a170b4ll, 0x0000fa232cf25214ll, 0x0000088e68ea899all,
   0x0000f83e0f83e0f9ll, 0x00000b5d69bac77ell, 0x0000f6603d980f67ll, 0x00000e26fd5c8555ll,
@@ -89,11 +89,12 @@
   0x0000820820820821ll, 0x0000fa2f045e7832ll, 0x000081848da8faf1ll, 0x0000fba577877d7dll,
   0x0000810204081021ll, 0x0000fd1a708bbe11ll, 0x0000808080808081ll, 0x0000fe8df263f957ll,
   0x0000800000000000ll, 0x0000ffff00000000ll,
-  };
+};
 
-
-    // LL_tbl[k] = 2^48*log2(1.0+k/2^15);
-static int64_t __LL_tbl[256] = {
+/*
+ * LL_tbl[k] = 2^48*log2(1.0+k/2^15)
+ */
+static __s64 __LL_tbl[256] = {
   0x0000000000000000ull, 0x00000002e2a60a00ull, 0x000000070cb64ec5ull, 0x00000009ef50ce67ull,
   0x0000000cd1e588fdull, 0x0000000fb4747e9cull, 0x0000001296fdaf5eull, 0x0000001579811b58ull,
   0x000000185bfec2a1ull, 0x0000001b3e76a552ull, 0x0000001e20e8c380ull, 0x0000002103551d43ull,
@@ -160,7 +161,4 @@
   0x000002d4562d2ec6ull, 0x000002d73330209dull, 0x000002da102d63b0ull, 0x000002dced24f814ull,
 };
 
-
-
-
 #endif
diff --git a/net/ceph/crush/hash.c b/net/ceph/crush/hash.c
index 5bb63e3..ed123af 100644
--- a/net/ceph/crush/hash.c
+++ b/net/ceph/crush/hash.c
@@ -1,6 +1,8 @@
-
-#include <linux/types.h>
-#include <linux/crush/hash.h>
+#ifdef __KERNEL__
+# include <linux/crush/hash.h>
+#else
+# include "hash.h"
+#endif
 
 /*
  * Robert Jenkins' function for mixing 32-bit values
diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index 5b47736..393bfb2 100644
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -1,27 +1,31 @@
+/*
+ * Ceph - scalable distributed file system
+ *
+ * Copyright (C) 2015 Intel Corporation All Rights Reserved
+ *
+ * This is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License version 2.1, as published by the Free Software
+ * Foundation.  See file COPYING.
+ *
+ */
 
 #ifdef __KERNEL__
 # include <linux/string.h>
 # include <linux/slab.h>
 # include <linux/bug.h>
 # include <linux/kernel.h>
-# ifndef dprintk
-#  define dprintk(args...)
-# endif
+# include <linux/crush/crush.h>
+# include <linux/crush/hash.h>
 #else
-# include <string.h>
-# include <stdio.h>
-# include <stdlib.h>
-# include <assert.h>
-# define BUG_ON(x) assert(!(x))
-# define dprintk(args...) /* printf(args) */
-# define kmalloc(x, f) malloc(x)
-# define kfree(x) free(x)
+# include "crush_compat.h"
+# include "crush.h"
+# include "hash.h"
 #endif
-
-#include <linux/crush/crush.h>
-#include <linux/crush/hash.h>
 #include "crush_ln_table.h"
 
+#define dprintk(args...) /* printf(args) */
+
 /*
  * Implement the core CRUSH mapping algorithm.
  */
@@ -139,7 +143,7 @@
 	int i;
 
 	for (i = bucket->h.size-1; i >= 0; i--) {
-		__u64 w = crush_hash32_4(bucket->h.hash,x, bucket->h.items[i],
+		__u64 w = crush_hash32_4(bucket->h.hash, x, bucket->h.items[i],
 					 r, bucket->h.id);
 		w &= 0xffff;
 		dprintk("list_choose i=%d x=%d r=%d item %d weight %x "
@@ -238,43 +242,46 @@
 	return bucket->h.items[high];
 }
 
-// compute 2^44*log2(input+1)
-uint64_t crush_ln(unsigned xin)
+/* compute 2^44*log2(input+1) */
+static __u64 crush_ln(unsigned int xin)
 {
-    unsigned x=xin, x1;
-    int iexpon, index1, index2;
-    uint64_t RH, LH, LL, xl64, result;
+	unsigned int x = xin, x1;
+	int iexpon, index1, index2;
+	__u64 RH, LH, LL, xl64, result;
 
-    x++;
+	x++;
 
-    // normalize input
-    iexpon = 15;
-    while(!(x&0x18000)) { x<<=1; iexpon--; }
+	/* normalize input */
+	iexpon = 15;
+	while (!(x & 0x18000)) {
+		x <<= 1;
+		iexpon--;
+	}
 
-    index1 = (x>>8)<<1;
-    // RH ~ 2^56/index1
-    RH = __RH_LH_tbl[index1 - 256];
-    // LH ~ 2^48 * log2(index1/256)
-    LH = __RH_LH_tbl[index1 + 1 - 256];
+	index1 = (x >> 8) << 1;
+	/* RH ~ 2^56/index1 */
+	RH = __RH_LH_tbl[index1 - 256];
+	/* LH ~ 2^48 * log2(index1/256) */
+	LH = __RH_LH_tbl[index1 + 1 - 256];
 
-    // RH*x ~ 2^48 * (2^15 + xf), xf<2^8
-    xl64 = (int64_t)x * RH;
-    xl64 >>= 48;
-    x1 = xl64;
+	/* RH*x ~ 2^48 * (2^15 + xf), xf<2^8 */
+	xl64 = (__s64)x * RH;
+	xl64 >>= 48;
+	x1 = xl64;
 
-    result = iexpon;
-    result <<= (12 + 32);
+	result = iexpon;
+	result <<= (12 + 32);
 
-    index2 = x1 & 0xff;
-    // LL ~ 2^48*log2(1.0+index2/2^15)
-    LL = __LL_tbl[index2];
+	index2 = x1 & 0xff;
+	/* LL ~ 2^48*log2(1.0+index2/2^15) */
+	LL = __LL_tbl[index2];
 
-    LH = LH + LL;
+	LH = LH + LL;
 
-    LH >>= (48-12 - 32);
-    result += LH;
+	LH >>= (48 - 12 - 32);
+	result += LH;
 
-    return result;
+	return result;
 }
 
 
@@ -290,9 +297,9 @@
 static int bucket_straw2_choose(struct crush_bucket_straw2 *bucket,
 				int x, int r)
 {
-	unsigned i, high = 0;
-	unsigned u;
-	unsigned w;
+	unsigned int i, high = 0;
+	unsigned int u;
+	unsigned int w;
 	__s64 ln, draw, high_draw = 0;
 
 	for (i = 0; i < bucket->h.size; i++) {
@@ -567,6 +574,10 @@
 		out[outpos] = item;
 		outpos++;
 		count--;
+#ifndef __KERNEL__
+		if (map->choose_tries && ftotal <= map->choose_total_tries)
+			map->choose_tries[ftotal]++;
+#endif
 	}
 
 	dprintk("CHOOSE returns %d\n", outpos);
@@ -610,6 +621,20 @@
 	}
 
 	for (ftotal = 0; left > 0 && ftotal < tries; ftotal++) {
+#ifdef DEBUG_INDEP
+		if (out2 && ftotal) {
+			dprintk("%u %d a: ", ftotal, left);
+			for (rep = outpos; rep < endpos; rep++) {
+				dprintk(" %d", out[rep]);
+			}
+			dprintk("\n");
+			dprintk("%u %d b: ", ftotal, left);
+			for (rep = outpos; rep < endpos; rep++) {
+				dprintk(" %d", out2[rep]);
+			}
+			dprintk("\n");
+		}
+#endif
 		for (rep = outpos; rep < endpos; rep++) {
 			if (out[rep] != CRUSH_ITEM_UNDEF)
 				continue;
@@ -726,6 +751,24 @@
 			out2[rep] = CRUSH_ITEM_NONE;
 		}
 	}
+#ifndef __KERNEL__
+	if (map->choose_tries && ftotal <= map->choose_total_tries)
+		map->choose_tries[ftotal]++;
+#endif
+#ifdef DEBUG_INDEP
+	if (out2) {
+		dprintk("%u %d a: ", ftotal, left);
+		for (rep = outpos; rep < endpos; rep++) {
+			dprintk(" %d", out[rep]);
+		}
+		dprintk("\n");
+		dprintk("%u %d b: ", ftotal, left);
+		for (rep = outpos; rep < endpos; rep++) {
+			dprintk(" %d", out2[rep]);
+		}
+		dprintk("\n");
+	}
+#endif
 }
 
 /**
@@ -790,8 +833,15 @@
 
 		switch (curstep->op) {
 		case CRUSH_RULE_TAKE:
-			w[0] = curstep->arg1;
-			wsize = 1;
+			if ((curstep->arg1 >= 0 &&
+			     curstep->arg1 < map->max_devices) ||
+			    (-1-curstep->arg1 < map->max_buckets &&
+			     map->buckets[-1-curstep->arg1])) {
+				w[0] = curstep->arg1;
+				wsize = 1;
+			} else {
+				dprintk(" bad take value %d\n", curstep->arg1);
+			}
 			break;
 
 		case CRUSH_RULE_SET_CHOOSE_TRIES:
@@ -877,7 +927,7 @@
 						0);
 				} else {
 					out_size = ((numrep < (result_max-osize)) ?
-                                                    numrep : (result_max-osize));
+						    numrep : (result_max-osize));
 					crush_choose_indep(
 						map,
 						map->buckets[-1-w[i]],
@@ -923,5 +973,3 @@
 	}
 	return result_len;
 }
-
-
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 073262f..1679f47 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -278,7 +278,6 @@
 	ceph_msgr_slab_exit();
 
 	BUG_ON(zero_page == NULL);
-	kunmap(zero_page);
 	page_cache_release(zero_page);
 	zero_page = NULL;
 }
@@ -1545,7 +1544,7 @@
 		page = ceph_msg_data_next(&msg->cursor, &page_offset, &length,
 							&last_piece);
 		ret = ceph_tcp_sendpage(con->sock, page, page_offset,
-				      length, last_piece);
+					length, !last_piece);
 		if (ret <= 0) {
 			if (do_datacrc)
 				msg->footer.data_crc = cpu_to_le32(crc);
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 2b3cf05..9d6ff12 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -298,21 +298,28 @@
 }
 EXPORT_SYMBOL(ceph_monc_request_next_osdmap);
 
+/*
+ * Wait for an osdmap with a given epoch.
+ *
+ * @epoch: epoch to wait for
+ * @timeout: in jiffies, 0 means "wait forever"
+ */
 int ceph_monc_wait_osdmap(struct ceph_mon_client *monc, u32 epoch,
 			  unsigned long timeout)
 {
 	unsigned long started = jiffies;
-	int ret;
+	long ret;
 
 	mutex_lock(&monc->mutex);
 	while (monc->have_osdmap < epoch) {
 		mutex_unlock(&monc->mutex);
 
-		if (timeout != 0 && time_after_eq(jiffies, started + timeout))
+		if (timeout && time_after_eq(jiffies, started + timeout))
 			return -ETIMEDOUT;
 
 		ret = wait_event_interruptible_timeout(monc->client->auth_wq,
-					 monc->have_osdmap >= epoch, timeout);
+						monc->have_osdmap >= epoch,
+						ceph_timeout_jiffies(timeout));
 		if (ret < 0)
 			return ret;
 
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index c4ec923..5003367 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -296,6 +296,9 @@
 	case CEPH_OSD_OP_CMPXATTR:
 		ceph_osd_data_release(&op->xattr.osd_data);
 		break;
+	case CEPH_OSD_OP_STAT:
+		ceph_osd_data_release(&op->raw_data_in);
+		break;
 	default:
 		break;
 	}
@@ -450,7 +453,7 @@
  */
 static struct ceph_osd_req_op *
 _osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which,
-				u16 opcode)
+		 u16 opcode, u32 flags)
 {
 	struct ceph_osd_req_op *op;
 
@@ -460,14 +463,15 @@
 	op = &osd_req->r_ops[which];
 	memset(op, 0, sizeof (*op));
 	op->op = opcode;
+	op->flags = flags;
 
 	return op;
 }
 
 void osd_req_op_init(struct ceph_osd_request *osd_req,
-				unsigned int which, u16 opcode)
+		     unsigned int which, u16 opcode, u32 flags)
 {
-	(void)_osd_req_op_init(osd_req, which, opcode);
+	(void)_osd_req_op_init(osd_req, which, opcode, flags);
 }
 EXPORT_SYMBOL(osd_req_op_init);
 
@@ -476,7 +480,8 @@
 				u64 offset, u64 length,
 				u64 truncate_size, u32 truncate_seq)
 {
-	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which, opcode);
+	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
+						      opcode, 0);
 	size_t payload_len = 0;
 
 	BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE &&
@@ -515,7 +520,8 @@
 void osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which,
 			u16 opcode, const char *class, const char *method)
 {
-	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which, opcode);
+	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
+						      opcode, 0);
 	struct ceph_pagelist *pagelist;
 	size_t payload_len = 0;
 	size_t size;
@@ -552,7 +558,8 @@
 			  u16 opcode, const char *name, const void *value,
 			  size_t size, u8 cmp_op, u8 cmp_mode)
 {
-	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which, opcode);
+	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
+						      opcode, 0);
 	struct ceph_pagelist *pagelist;
 	size_t payload_len;
 
@@ -585,7 +592,8 @@
 				unsigned int which, u16 opcode,
 				u64 cookie, u64 version, int flag)
 {
-	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which, opcode);
+	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
+						      opcode, 0);
 
 	BUG_ON(opcode != CEPH_OSD_OP_NOTIFY_ACK && opcode != CEPH_OSD_OP_WATCH);
 
@@ -602,7 +610,8 @@
 				u64 expected_write_size)
 {
 	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
-						      CEPH_OSD_OP_SETALLOCHINT);
+						      CEPH_OSD_OP_SETALLOCHINT,
+						      0);
 
 	op->alloc_hint.expected_object_size = expected_object_size;
 	op->alloc_hint.expected_write_size = expected_write_size;
@@ -786,7 +795,7 @@
 	}
 
 	if (opcode == CEPH_OSD_OP_CREATE || opcode == CEPH_OSD_OP_DELETE) {
-		osd_req_op_init(req, which, opcode);
+		osd_req_op_init(req, which, opcode, 0);
 	} else {
 		u32 object_size = le32_to_cpu(layout->fl_object_size);
 		u32 object_base = off - objoff;
@@ -1088,7 +1097,7 @@
 	BUG_ON(!list_empty(&osd->o_osd_lru));
 
 	list_add_tail(&osd->o_osd_lru, &osdc->osd_lru);
-	osd->lru_ttl = jiffies + osdc->client->options->osd_idle_ttl * HZ;
+	osd->lru_ttl = jiffies + osdc->client->options->osd_idle_ttl;
 }
 
 static void maybe_move_osd_to_lru(struct ceph_osd_client *osdc,
@@ -1199,7 +1208,7 @@
 static void __schedule_osd_timeout(struct ceph_osd_client *osdc)
 {
 	schedule_delayed_work(&osdc->timeout_work,
-			osdc->client->options->osd_keepalive_timeout * HZ);
+			      osdc->client->options->osd_keepalive_timeout);
 }
 
 static void __cancel_osd_timeout(struct ceph_osd_client *osdc)
@@ -1567,10 +1576,9 @@
 {
 	struct ceph_osd_client *osdc =
 		container_of(work, struct ceph_osd_client, timeout_work.work);
+	struct ceph_options *opts = osdc->client->options;
 	struct ceph_osd_request *req;
 	struct ceph_osd *osd;
-	unsigned long keepalive =
-		osdc->client->options->osd_keepalive_timeout * HZ;
 	struct list_head slow_osds;
 	dout("timeout\n");
 	down_read(&osdc->map_sem);
@@ -1586,7 +1594,8 @@
 	 */
 	INIT_LIST_HEAD(&slow_osds);
 	list_for_each_entry(req, &osdc->req_lru, r_req_lru_item) {
-		if (time_before(jiffies, req->r_stamp + keepalive))
+		if (time_before(jiffies,
+				req->r_stamp + opts->osd_keepalive_timeout))
 			break;
 
 		osd = req->r_osd;
@@ -1613,8 +1622,7 @@
 	struct ceph_osd_client *osdc =
 		container_of(work, struct ceph_osd_client,
 			     osds_timeout_work.work);
-	unsigned long delay =
-		osdc->client->options->osd_idle_ttl * HZ >> 2;
+	unsigned long delay = osdc->client->options->osd_idle_ttl / 4;
 
 	dout("osds timeout\n");
 	down_read(&osdc->map_sem);
@@ -2619,7 +2627,7 @@
 	osdc->event_count = 0;
 
 	schedule_delayed_work(&osdc->osds_timeout_work,
-	   round_jiffies_relative(osdc->client->options->osd_idle_ttl * HZ));
+	    round_jiffies_relative(osdc->client->options->osd_idle_ttl));
 
 	err = -ENOMEM;
 	osdc->req_mempool = mempool_create_kmalloc_pool(10,
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 1579669..4a31258 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -89,7 +89,7 @@
 {
 	int j;
 	dout("crush_decode_tree_bucket %p to %p\n", *p, end);
-	ceph_decode_32_safe(p, end, b->num_nodes, bad);
+	ceph_decode_8_safe(p, end, b->num_nodes, bad);
 	b->node_weights = kcalloc(b->num_nodes, sizeof(u32), GFP_NOFS);
 	if (b->node_weights == NULL)
 		return -ENOMEM;
diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c
index 096d914..d4f5f22 100644
--- a/net/ceph/pagevec.c
+++ b/net/ceph/pagevec.c
@@ -51,10 +51,7 @@
 			set_page_dirty_lock(pages[i]);
 		put_page(pages[i]);
 	}
-	if (is_vmalloc_addr(pages))
-		vfree(pages);
-	else
-		kfree(pages);
+	kvfree(pages);
 }
 EXPORT_SYMBOL(ceph_put_page_vector);
 
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 476e5dd..2a834c6 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -129,7 +129,7 @@
 	struct flow_dissector_key_ports *key_ports;
 	struct flow_dissector_key_tags *key_tags;
 	struct flow_dissector_key_keyid *key_keyid;
-	u8 ip_proto;
+	u8 ip_proto = 0;
 
 	if (!data) {
 		data = skb->data;
diff --git a/net/core/sock.c b/net/core/sock.c
index 1e1fe9a..08f16db 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1454,7 +1454,7 @@
 
 static void __sk_free(struct sock *sk)
 {
-	if (unlikely(sock_diag_has_destroy_listeners(sk)))
+	if (unlikely(sock_diag_has_destroy_listeners(sk) && sk->sk_net_refcnt))
 		sock_diag_broadcast_destroy(sk);
 	else
 		sk_destruct(sk);
@@ -2269,7 +2269,6 @@
 
 static void sock_def_destruct(struct sock *sk)
 {
-	kfree(sk->sk_protinfo);
 }
 
 void sk_send_sigurg(struct sock *sk)
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 04ffad3..0917123 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -112,7 +112,7 @@
 
 clear_promisc:
 	if (dev->flags & IFF_PROMISC)
-		dev_set_promiscuity(master, 0);
+		dev_set_promiscuity(master, -1);
 clear_allmulti:
 	if (dev->flags & IFF_ALLMULTI)
 		dev_set_allmulti(master, -1);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 3bfccd8..c7358ea 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1045,7 +1045,7 @@
 		    nla_put_u32(skb, RTA_OIF, fi->fib_nh->nh_oif))
 			goto nla_put_failure;
 		if (fi->fib_nh->nh_flags & RTNH_F_LINKDOWN) {
-			in_dev = __in_dev_get_rcu(fi->fib_nh->nh_dev);
+			in_dev = __in_dev_get_rtnl(fi->fib_nh->nh_dev);
 			if (in_dev &&
 			    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev))
 				rtm->rtm_flags |= RTNH_F_DEAD;
@@ -1074,7 +1074,7 @@
 
 			rtnh->rtnh_flags = nh->nh_flags & 0xFF;
 			if (nh->nh_flags & RTNH_F_LINKDOWN) {
-				in_dev = __in_dev_get_rcu(nh->nh_dev);
+				in_dev = __in_dev_get_rtnl(nh->nh_dev);
 				if (in_dev &&
 				    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev))
 					rtnh->rtnh_flags |= RTNH_F_DEAD;
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index 65de068..61eafc9 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -197,11 +197,4 @@
 {
 	return nf_register_afinfo(&nf_ip_afinfo);
 }
-
-static void __exit ipv4_netfilter_fini(void)
-{
-	nf_unregister_afinfo(&nf_ip_afinfo);
-}
-
-module_init(ipv4_netfilter_init);
-module_exit(ipv4_netfilter_fini);
+subsys_initcall(ipv4_netfilter_init);
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index 36ba7c4..fda33f9 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -103,7 +103,7 @@
 	const struct rate_control_ops *ops;
 	const char *alg_name;
 
-	kparam_block_sysfs_write(ieee80211_default_rc_algo);
+	kernel_param_lock(THIS_MODULE);
 	if (!name)
 		alg_name = ieee80211_default_rc_algo;
 	else
@@ -117,7 +117,7 @@
 	/* try built-in one if specific alg requested but not found */
 	if (!ops && strlen(CONFIG_MAC80211_RC_DEFAULT))
 		ops = ieee80211_try_rate_control_ops_get(CONFIG_MAC80211_RC_DEFAULT);
-	kparam_unblock_sysfs_write(ieee80211_default_rc_algo);
+	kernel_param_unlock(THIS_MODULE);
 
 	return ops;
 }
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index b92d3f4..9d37ccd 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -216,8 +216,8 @@
 	[TCA_FLOWER_KEY_IPV6_DST_MASK]	= { .len = sizeof(struct in6_addr) },
 	[TCA_FLOWER_KEY_TCP_SRC]	= { .type = NLA_U16 },
 	[TCA_FLOWER_KEY_TCP_DST]	= { .type = NLA_U16 },
-	[TCA_FLOWER_KEY_TCP_SRC]	= { .type = NLA_U16 },
-	[TCA_FLOWER_KEY_TCP_DST]	= { .type = NLA_U16 },
+	[TCA_FLOWER_KEY_UDP_SRC]	= { .type = NLA_U16 },
+	[TCA_FLOWER_KEY_UDP_DST]	= { .type = NLA_U16 },
 };
 
 static void fl_set_key_val(struct nlattr **tb,
diff --git a/net/sctp/output.c b/net/sctp/output.c
index fc5e45b..abe7c2d 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -599,7 +599,9 @@
 	return err;
 no_route:
 	kfree_skb(nskb);
-	IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
+
+	if (asoc)
+		IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
 
 	/* FIXME: Returning the 'err' will effect all the associations
 	 * associated with a socket, although only one of the paths of the
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 5f6c4e6..1425ec2 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -2121,12 +2121,6 @@
 	if (sp->subscribe.sctp_data_io_event)
 		sctp_ulpevent_read_sndrcvinfo(event, msg);
 
-#if 0
-	/* FIXME: we should be calling IP/IPv6 layers.  */
-	if (sk->sk_protinfo.af_inet.cmsg_flags)
-		ip_cmsg_recv(msg, skb);
-#endif
-
 	err = copied;
 
 	/* If skb's length exceeds the user's buffer, update the skb and
diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile
index 936ad0a..b512fbd 100644
--- a/net/sunrpc/Makefile
+++ b/net/sunrpc/Makefile
@@ -14,6 +14,6 @@
 	    sunrpc_syms.o cache.o rpc_pipe.o \
 	    svc_xprt.o
 sunrpc-$(CONFIG_SUNRPC_DEBUG) += debugfs.o
-sunrpc-$(CONFIG_SUNRPC_BACKCHANNEL) += backchannel_rqst.o bc_svc.o
+sunrpc-$(CONFIG_SUNRPC_BACKCHANNEL) += backchannel_rqst.o
 sunrpc-$(CONFIG_PROC_FS) += stats.o
 sunrpc-$(CONFIG_SYSCTL) += sysctl.o
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index 47f38be..02f5367 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -72,7 +72,7 @@
 
 #define param_check_hashtbl_sz(name, p) __param_check(name, p, unsigned int);
 
-static struct kernel_param_ops param_ops_hashtbl_sz = {
+static const struct kernel_param_ops param_ops_hashtbl_sz = {
 	.set = param_set_hashtbl_sz,
 	.get = param_get_hashtbl_sz,
 };
diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c
index 9dd0ea8d..9825ff0 100644
--- a/net/sunrpc/backchannel_rqst.c
+++ b/net/sunrpc/backchannel_rqst.c
@@ -37,16 +37,18 @@
  */
 static inline int xprt_need_to_requeue(struct rpc_xprt *xprt)
 {
-	return xprt->bc_alloc_count > 0;
+	return xprt->bc_alloc_count < atomic_read(&xprt->bc_free_slots);
 }
 
 static inline void xprt_inc_alloc_count(struct rpc_xprt *xprt, unsigned int n)
 {
+	atomic_add(n, &xprt->bc_free_slots);
 	xprt->bc_alloc_count += n;
 }
 
 static inline int xprt_dec_alloc_count(struct rpc_xprt *xprt, unsigned int n)
 {
+	atomic_sub(n, &xprt->bc_free_slots);
 	return xprt->bc_alloc_count -= n;
 }
 
@@ -60,13 +62,62 @@
 
 	dprintk("RPC:        free allocations for req= %p\n", req);
 	WARN_ON_ONCE(test_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state));
-	xbufp = &req->rq_private_buf;
+	xbufp = &req->rq_rcv_buf;
 	free_page((unsigned long)xbufp->head[0].iov_base);
 	xbufp = &req->rq_snd_buf;
 	free_page((unsigned long)xbufp->head[0].iov_base);
 	kfree(req);
 }
 
+static int xprt_alloc_xdr_buf(struct xdr_buf *buf, gfp_t gfp_flags)
+{
+	struct page *page;
+	/* Preallocate one XDR receive buffer */
+	page = alloc_page(gfp_flags);
+	if (page == NULL)
+		return -ENOMEM;
+	buf->head[0].iov_base = page_address(page);
+	buf->head[0].iov_len = PAGE_SIZE;
+	buf->tail[0].iov_base = NULL;
+	buf->tail[0].iov_len = 0;
+	buf->page_len = 0;
+	buf->len = 0;
+	buf->buflen = PAGE_SIZE;
+	return 0;
+}
+
+static
+struct rpc_rqst *xprt_alloc_bc_req(struct rpc_xprt *xprt, gfp_t gfp_flags)
+{
+	struct rpc_rqst *req;
+
+	/* Pre-allocate one backchannel rpc_rqst */
+	req = kzalloc(sizeof(*req), gfp_flags);
+	if (req == NULL)
+		return NULL;
+
+	req->rq_xprt = xprt;
+	INIT_LIST_HEAD(&req->rq_list);
+	INIT_LIST_HEAD(&req->rq_bc_list);
+
+	/* Preallocate one XDR receive buffer */
+	if (xprt_alloc_xdr_buf(&req->rq_rcv_buf, gfp_flags) < 0) {
+		printk(KERN_ERR "Failed to create bc receive xbuf\n");
+		goto out_free;
+	}
+	req->rq_rcv_buf.len = PAGE_SIZE;
+
+	/* Preallocate one XDR send buffer */
+	if (xprt_alloc_xdr_buf(&req->rq_snd_buf, gfp_flags) < 0) {
+		printk(KERN_ERR "Failed to create bc snd xbuf\n");
+		goto out_free;
+	}
+	return req;
+out_free:
+	xprt_free_allocation(req);
+	return NULL;
+}
+
 /*
  * Preallocate up to min_reqs structures and related buffers for use
  * by the backchannel.  This function can be called multiple times
@@ -87,9 +138,7 @@
  */
 int xprt_setup_backchannel(struct rpc_xprt *xprt, unsigned int min_reqs)
 {
-	struct page *page_rcv = NULL, *page_snd = NULL;
-	struct xdr_buf *xbufp = NULL;
-	struct rpc_rqst *req, *tmp;
+	struct rpc_rqst *req;
 	struct list_head tmp_list;
 	int i;
 
@@ -106,7 +155,7 @@
 	INIT_LIST_HEAD(&tmp_list);
 	for (i = 0; i < min_reqs; i++) {
 		/* Pre-allocate one backchannel rpc_rqst */
-		req = kzalloc(sizeof(struct rpc_rqst), GFP_KERNEL);
+		req = xprt_alloc_bc_req(xprt, GFP_KERNEL);
 		if (req == NULL) {
 			printk(KERN_ERR "Failed to create bc rpc_rqst\n");
 			goto out_free;
@@ -115,41 +164,6 @@
 		/* Add the allocated buffer to the tmp list */
 		dprintk("RPC:       adding req= %p\n", req);
 		list_add(&req->rq_bc_pa_list, &tmp_list);
-
-		req->rq_xprt = xprt;
-		INIT_LIST_HEAD(&req->rq_list);
-		INIT_LIST_HEAD(&req->rq_bc_list);
-
-		/* Preallocate one XDR receive buffer */
-		page_rcv = alloc_page(GFP_KERNEL);
-		if (page_rcv == NULL) {
-			printk(KERN_ERR "Failed to create bc receive xbuf\n");
-			goto out_free;
-		}
-		xbufp = &req->rq_rcv_buf;
-		xbufp->head[0].iov_base = page_address(page_rcv);
-		xbufp->head[0].iov_len = PAGE_SIZE;
-		xbufp->tail[0].iov_base = NULL;
-		xbufp->tail[0].iov_len = 0;
-		xbufp->page_len = 0;
-		xbufp->len = PAGE_SIZE;
-		xbufp->buflen = PAGE_SIZE;
-
-		/* Preallocate one XDR send buffer */
-		page_snd = alloc_page(GFP_KERNEL);
-		if (page_snd == NULL) {
-			printk(KERN_ERR "Failed to create bc snd xbuf\n");
-			goto out_free;
-		}
-
-		xbufp = &req->rq_snd_buf;
-		xbufp->head[0].iov_base = page_address(page_snd);
-		xbufp->head[0].iov_len = 0;
-		xbufp->tail[0].iov_base = NULL;
-		xbufp->tail[0].iov_len = 0;
-		xbufp->page_len = 0;
-		xbufp->len = 0;
-		xbufp->buflen = PAGE_SIZE;
 	}
 
 	/*
@@ -167,7 +181,10 @@
 	/*
 	 * Memory allocation failed, free the temporary list
 	 */
-	list_for_each_entry_safe(req, tmp, &tmp_list, rq_bc_pa_list) {
+	while (!list_empty(&tmp_list)) {
+		req = list_first_entry(&tmp_list,
+				struct rpc_rqst,
+				rq_bc_pa_list);
 		list_del(&req->rq_bc_pa_list);
 		xprt_free_allocation(req);
 	}
@@ -217,9 +234,15 @@
 	struct rpc_rqst *req = NULL;
 
 	dprintk("RPC:       allocate a backchannel request\n");
-	if (list_empty(&xprt->bc_pa_list))
+	if (atomic_read(&xprt->bc_free_slots) <= 0)
 		goto not_found;
-
+	if (list_empty(&xprt->bc_pa_list)) {
+		req = xprt_alloc_bc_req(xprt, GFP_ATOMIC);
+		if (!req)
+			goto not_found;
+		/* Note: this 'free' request adds it to xprt->bc_pa_list */
+		xprt_free_bc_request(req);
+	}
 	req = list_first_entry(&xprt->bc_pa_list, struct rpc_rqst,
 				rq_bc_pa_list);
 	req->rq_reply_bytes_recvd = 0;
@@ -245,11 +268,21 @@
 
 	req->rq_connect_cookie = xprt->connect_cookie - 1;
 	smp_mb__before_atomic();
-	WARN_ON_ONCE(!test_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state));
 	clear_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state);
 	smp_mb__after_atomic();
 
-	if (!xprt_need_to_requeue(xprt)) {
+	/*
+	 * Return it to the list of preallocations so that it
+	 * may be reused by a new callback request.
+	 */
+	spin_lock_bh(&xprt->bc_pa_lock);
+	if (xprt_need_to_requeue(xprt)) {
+		list_add_tail(&req->rq_bc_pa_list, &xprt->bc_pa_list);
+		xprt->bc_alloc_count++;
+		req = NULL;
+	}
+	spin_unlock_bh(&xprt->bc_pa_lock);
+	if (req != NULL) {
 		/*
 		 * The last remaining session was destroyed while this
 		 * entry was in use.  Free the entry and don't attempt
@@ -260,14 +293,6 @@
 		xprt_free_allocation(req);
 		return;
 	}
-
-	/*
-	 * Return it to the list of preallocations so that it
-	 * may be reused by a new callback request.
-	 */
-	spin_lock_bh(&xprt->bc_pa_lock);
-	list_add_tail(&req->rq_bc_pa_list, &xprt->bc_pa_list);
-	spin_unlock_bh(&xprt->bc_pa_lock);
 }
 
 /*
@@ -311,6 +336,7 @@
 
 	spin_lock(&xprt->bc_pa_lock);
 	list_del(&req->rq_bc_pa_list);
+	xprt->bc_alloc_count--;
 	spin_unlock(&xprt->bc_pa_lock);
 
 	req->rq_private_buf.len = copied;
diff --git a/net/sunrpc/bc_svc.c b/net/sunrpc/bc_svc.c
deleted file mode 100644
index 15c7a8a..0000000
--- a/net/sunrpc/bc_svc.c
+++ /dev/null
@@ -1,63 +0,0 @@
-/******************************************************************************
-
-(c) 2007 Network Appliance, Inc.  All Rights Reserved.
-(c) 2009 NetApp.  All Rights Reserved.
-
-NetApp provides this source code under the GPL v2 License.
-The GPL v2 license is available at
-http://opensource.org/licenses/gpl-license.php.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
-"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
-LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
-A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
-CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
-EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
-PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
-PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
-LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
-NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
-SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-******************************************************************************/
-
-/*
- * The NFSv4.1 callback service helper routines.
- * They implement the transport level processing required to send the
- * reply over an existing open connection previously established by the client.
- */
-
-#include <linux/module.h>
-
-#include <linux/sunrpc/xprt.h>
-#include <linux/sunrpc/sched.h>
-#include <linux/sunrpc/bc_xprt.h>
-
-#define RPCDBG_FACILITY	RPCDBG_SVCDSP
-
-/* Empty callback ops */
-static const struct rpc_call_ops nfs41_callback_ops = {
-};
-
-
-/*
- * Send the callback reply
- */
-int bc_send(struct rpc_rqst *req)
-{
-	struct rpc_task *task;
-	int ret;
-
-	dprintk("RPC:       bc_send req= %p\n", req);
-	task = rpc_run_bc_task(req, &nfs41_callback_ops);
-	if (IS_ERR(task))
-		ret = PTR_ERR(task);
-	else {
-		WARN_ON_ONCE(atomic_read(&task->tk_count) != 1);
-		ret = task->tk_status;
-		rpc_put_task(task);
-	}
-	dprintk("RPC:       bc_send ret= %d\n", ret);
-	return ret;
-}
-
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index e6ce151..cbc6af9 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -891,15 +891,8 @@
 			task->tk_flags |= RPC_TASK_SOFT;
 		if (clnt->cl_noretranstimeo)
 			task->tk_flags |= RPC_TASK_NO_RETRANS_TIMEOUT;
-		if (sk_memalloc_socks()) {
-			struct rpc_xprt *xprt;
-
-			rcu_read_lock();
-			xprt = rcu_dereference(clnt->cl_xprt);
-			if (xprt->swapper)
-				task->tk_flags |= RPC_TASK_SWAPPER;
-			rcu_read_unlock();
-		}
+		if (atomic_read(&clnt->cl_swapper))
+			task->tk_flags |= RPC_TASK_SWAPPER;
 		/* Add to the client's list of all tasks */
 		spin_lock(&clnt->cl_lock);
 		list_add_tail(&task->tk_task, &clnt->cl_tasks);
@@ -1031,15 +1024,14 @@
  * rpc_run_bc_task - Allocate a new RPC task for backchannel use, then run
  * rpc_execute against it
  * @req: RPC request
- * @tk_ops: RPC call ops
  */
-struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req,
-				const struct rpc_call_ops *tk_ops)
+struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req)
 {
 	struct rpc_task *task;
 	struct xdr_buf *xbufp = &req->rq_snd_buf;
 	struct rpc_task_setup task_setup_data = {
-		.callback_ops = tk_ops,
+		.callback_ops = &rpc_default_ops,
+		.flags = RPC_TASK_SOFTCONN,
 	};
 
 	dprintk("RPC: rpc_run_bc_task req= %p\n", req);
@@ -1614,6 +1606,7 @@
 					req->rq_callsize + req->rq_rcvsize);
 	if (req->rq_buffer != NULL)
 		return;
+	xprt_inject_disconnect(xprt);
 
 	dprintk("RPC: %5u rpc_buffer allocation failed\n", task->tk_pid);
 
@@ -1951,33 +1944,36 @@
 {
 	struct rpc_rqst *req = task->tk_rqstp;
 
-	if (!xprt_prepare_transmit(task)) {
-		/*
-		 * Could not reserve the transport. Try again after the
-		 * transport is released.
-		 */
-		task->tk_status = 0;
-		task->tk_action = call_bc_transmit;
-		return;
-	}
+	if (!xprt_prepare_transmit(task))
+		goto out_retry;
 
-	task->tk_action = rpc_exit_task;
 	if (task->tk_status < 0) {
 		printk(KERN_NOTICE "RPC: Could not send backchannel reply "
 			"error: %d\n", task->tk_status);
-		return;
+		goto out_done;
 	}
+	if (req->rq_connect_cookie != req->rq_xprt->connect_cookie)
+		req->rq_bytes_sent = 0;
 
 	xprt_transmit(task);
+
+	if (task->tk_status == -EAGAIN)
+		goto out_nospace;
+
 	xprt_end_transmit(task);
 	dprint_status(task);
 	switch (task->tk_status) {
 	case 0:
 		/* Success */
-		break;
 	case -EHOSTDOWN:
 	case -EHOSTUNREACH:
 	case -ENETUNREACH:
+	case -ECONNRESET:
+	case -ECONNREFUSED:
+	case -EADDRINUSE:
+	case -ENOTCONN:
+	case -EPIPE:
+		break;
 	case -ETIMEDOUT:
 		/*
 		 * Problem reaching the server.  Disconnect and let the
@@ -2002,6 +1998,13 @@
 		break;
 	}
 	rpc_wake_up_queued_task(&req->rq_xprt->pending, task);
+out_done:
+	task->tk_action = rpc_exit_task;
+	return;
+out_nospace:
+	req->rq_connect_cookie = req->rq_xprt->connect_cookie;
+out_retry:
+	task->tk_status = 0;
 }
 #endif /* CONFIG_SUNRPC_BACKCHANNEL */
 
@@ -2476,3 +2479,59 @@
 	spin_unlock(&sn->rpc_client_lock);
 }
 #endif
+
+#if IS_ENABLED(CONFIG_SUNRPC_SWAP)
+int
+rpc_clnt_swap_activate(struct rpc_clnt *clnt)
+{
+	int ret = 0;
+	struct rpc_xprt	*xprt;
+
+	if (atomic_inc_return(&clnt->cl_swapper) == 1) {
+retry:
+		rcu_read_lock();
+		xprt = xprt_get(rcu_dereference(clnt->cl_xprt));
+		rcu_read_unlock();
+		if (!xprt) {
+			/*
+			 * If we didn't get a reference, then we likely are
+			 * racing with a migration event. Wait for a grace
+			 * period and try again.
+			 */
+			synchronize_rcu();
+			goto retry;
+		}
+
+		ret = xprt_enable_swap(xprt);
+		xprt_put(xprt);
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(rpc_clnt_swap_activate);
+
+void
+rpc_clnt_swap_deactivate(struct rpc_clnt *clnt)
+{
+	struct rpc_xprt	*xprt;
+
+	if (atomic_dec_if_positive(&clnt->cl_swapper) == 0) {
+retry:
+		rcu_read_lock();
+		xprt = xprt_get(rcu_dereference(clnt->cl_xprt));
+		rcu_read_unlock();
+		if (!xprt) {
+			/*
+			 * If we didn't get a reference, then we likely are
+			 * racing with a migration event. Wait for a grace
+			 * period and try again.
+			 */
+			synchronize_rcu();
+			goto retry;
+		}
+
+		xprt_disable_swap(xprt);
+		xprt_put(xprt);
+	}
+}
+EXPORT_SYMBOL_GPL(rpc_clnt_swap_deactivate);
+#endif /* CONFIG_SUNRPC_SWAP */
diff --git a/net/sunrpc/debugfs.c b/net/sunrpc/debugfs.c
index 82962f7..e7b4d93 100644
--- a/net/sunrpc/debugfs.c
+++ b/net/sunrpc/debugfs.c
@@ -10,9 +10,12 @@
 #include "netns.h"
 
 static struct dentry *topdir;
+static struct dentry *rpc_fault_dir;
 static struct dentry *rpc_clnt_dir;
 static struct dentry *rpc_xprt_dir;
 
+unsigned int rpc_inject_disconnect;
+
 struct rpc_clnt_iter {
 	struct rpc_clnt	*clnt;
 	loff_t		pos;
@@ -257,6 +260,8 @@
 		debugfs_remove_recursive(xprt->debugfs);
 		xprt->debugfs = NULL;
 	}
+
+	atomic_set(&xprt->inject_disconnect, rpc_inject_disconnect);
 }
 
 void
@@ -266,11 +271,79 @@
 	xprt->debugfs = NULL;
 }
 
+static int
+fault_open(struct inode *inode, struct file *filp)
+{
+	filp->private_data = kmalloc(128, GFP_KERNEL);
+	if (!filp->private_data)
+		return -ENOMEM;
+	return 0;
+}
+
+static int
+fault_release(struct inode *inode, struct file *filp)
+{
+	kfree(filp->private_data);
+	return 0;
+}
+
+static ssize_t
+fault_disconnect_read(struct file *filp, char __user *user_buf,
+		      size_t len, loff_t *offset)
+{
+	char *buffer = (char *)filp->private_data;
+	size_t size;
+
+	size = sprintf(buffer, "%u\n", rpc_inject_disconnect);
+	return simple_read_from_buffer(user_buf, len, offset, buffer, size);
+}
+
+static ssize_t
+fault_disconnect_write(struct file *filp, const char __user *user_buf,
+		       size_t len, loff_t *offset)
+{
+	char buffer[16];
+
+	if (len >= sizeof(buffer))
+		len = sizeof(buffer) - 1;
+	if (copy_from_user(buffer, user_buf, len))
+		return -EFAULT;
+	buffer[len] = '\0';
+	if (kstrtouint(buffer, 10, &rpc_inject_disconnect))
+		return -EINVAL;
+	return len;
+}
+
+static const struct file_operations fault_disconnect_fops = {
+	.owner		= THIS_MODULE,
+	.open		= fault_open,
+	.read		= fault_disconnect_read,
+	.write		= fault_disconnect_write,
+	.release	= fault_release,
+};
+
+static struct dentry *
+inject_fault_dir(struct dentry *topdir)
+{
+	struct dentry *faultdir;
+
+	faultdir = debugfs_create_dir("inject_fault", topdir);
+	if (!faultdir)
+		return NULL;
+
+	if (!debugfs_create_file("disconnect", S_IFREG | S_IRUSR, faultdir,
+				 NULL, &fault_disconnect_fops))
+		return NULL;
+
+	return faultdir;
+}
+
 void __exit
 sunrpc_debugfs_exit(void)
 {
 	debugfs_remove_recursive(topdir);
 	topdir = NULL;
+	rpc_fault_dir = NULL;
 	rpc_clnt_dir = NULL;
 	rpc_xprt_dir = NULL;
 }
@@ -282,6 +355,10 @@
 	if (!topdir)
 		return;
 
+	rpc_fault_dir = inject_fault_dir(topdir);
+	if (!rpc_fault_dir)
+		goto out_remove;
+
 	rpc_clnt_dir = debugfs_create_dir("rpc_clnt", topdir);
 	if (!rpc_clnt_dir)
 		goto out_remove;
@@ -294,5 +371,6 @@
 out_remove:
 	debugfs_remove_recursive(topdir);
 	topdir = NULL;
+	rpc_fault_dir = NULL;
 	rpc_clnt_dir = NULL;
 }
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 852ae60..5a16d8d 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1350,6 +1350,11 @@
 {
 	struct kvec	*argv = &rqstp->rq_arg.head[0];
 	struct kvec	*resv = &rqstp->rq_res.head[0];
+	struct rpc_task *task;
+	int proc_error;
+	int error;
+
+	dprintk("svc: %s(%p)\n", __func__, req);
 
 	/* Build the svc_rqst used by the common processing routine */
 	rqstp->rq_xprt = serv->sv_bc_xprt;
@@ -1372,21 +1377,36 @@
 
 	/*
 	 * Skip the next two words because they've already been
-	 * processed in the trasport
+	 * processed in the transport
 	 */
 	svc_getu32(argv);	/* XID */
 	svc_getnl(argv);	/* CALLDIR */
 
-	/* Returns 1 for send, 0 for drop */
-	if (svc_process_common(rqstp, argv, resv)) {
-		memcpy(&req->rq_snd_buf, &rqstp->rq_res,
-						sizeof(req->rq_snd_buf));
-		return bc_send(req);
-	} else {
-		/* drop request */
+	/* Parse and execute the bc call */
+	proc_error = svc_process_common(rqstp, argv, resv);
+
+	atomic_inc(&req->rq_xprt->bc_free_slots);
+	if (!proc_error) {
+		/* Processing error: drop the request */
 		xprt_free_bc_request(req);
 		return 0;
 	}
+
+	/* Finally, send the reply synchronously */
+	memcpy(&req->rq_snd_buf, &rqstp->rq_res, sizeof(req->rq_snd_buf));
+	task = rpc_run_bc_task(req);
+	if (IS_ERR(task)) {
+		error = PTR_ERR(task);
+		goto out;
+	}
+
+	WARN_ON_ONCE(atomic_read(&task->tk_count) != 1);
+	error = task->tk_status;
+	rpc_put_task(task);
+
+out:
+	dprintk("svc: %s(), error=%d\n", __func__, error);
+	return error;
 }
 EXPORT_SYMBOL_GPL(bc_svc_process);
 #endif /* CONFIG_SUNRPC_BACKCHANNEL */
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 1d4fe24..ab5dd62 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -68,6 +68,7 @@
 static void	xprt_request_init(struct rpc_task *, struct rpc_xprt *);
 static void	xprt_connect_status(struct rpc_task *task);
 static int      __xprt_get_cong(struct rpc_xprt *, struct rpc_task *);
+static void     __xprt_put_cong(struct rpc_xprt *, struct rpc_rqst *);
 static void	 xprt_destroy(struct rpc_xprt *xprt);
 
 static DEFINE_SPINLOCK(xprt_list_lock);
@@ -250,6 +251,8 @@
 	}
 	xprt_clear_locked(xprt);
 out_sleep:
+	if (req)
+		__xprt_put_cong(xprt, req);
 	dprintk("RPC: %5u failed to lock transport %p\n", task->tk_pid, xprt);
 	task->tk_timeout = 0;
 	task->tk_status = -EAGAIN;
@@ -608,8 +611,8 @@
 	struct rpc_xprt *xprt =
 		container_of(work, struct rpc_xprt, task_cleanup);
 
-	xprt->ops->close(xprt);
 	clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
+	xprt->ops->close(xprt);
 	xprt_release_write(xprt, NULL);
 }
 
@@ -967,6 +970,7 @@
 		task->tk_status = status;
 		return;
 	}
+	xprt_inject_disconnect(xprt);
 
 	dprintk("RPC: %5u xmit complete\n", task->tk_pid);
 	task->tk_flags |= RPC_TASK_SENT;
@@ -1285,6 +1289,7 @@
 	spin_unlock_bh(&xprt->transport_lock);
 	if (req->rq_buffer)
 		xprt->ops->buf_free(req->rq_buffer);
+	xprt_inject_disconnect(xprt);
 	if (req->rq_cred != NULL)
 		put_rpccred(req->rq_cred);
 	task->tk_rqstp = NULL;
diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c
index 302d4eb..f1e8daf 100644
--- a/net/sunrpc/xprtrdma/fmr_ops.c
+++ b/net/sunrpc/xprtrdma/fmr_ops.c
@@ -11,6 +11,21 @@
  * can take tens of usecs to complete.
  */
 
+/* Normal operation
+ *
+ * A Memory Region is prepared for RDMA READ or WRITE using the
+ * ib_map_phys_fmr verb (fmr_op_map). When the RDMA operation is
+ * finished, the Memory Region is unmapped using the ib_unmap_fmr
+ * verb (fmr_op_unmap).
+ */
+
+/* Transport recovery
+ *
+ * After a transport reconnect, fmr_op_map re-uses the MR already
+ * allocated for the RPC, but generates a fresh rkey then maps the
+ * MR again. This process is synchronous.
+ */
+
 #include "xprt_rdma.h"
 
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
@@ -50,19 +65,28 @@
 	struct rpcrdma_mw *r;
 	int i, rc;
 
+	spin_lock_init(&buf->rb_mwlock);
 	INIT_LIST_HEAD(&buf->rb_mws);
 	INIT_LIST_HEAD(&buf->rb_all);
 
-	i = (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS;
-	dprintk("RPC:       %s: initializing %d FMRs\n", __func__, i);
+	i = max_t(int, RPCRDMA_MAX_DATA_SEGS / RPCRDMA_MAX_FMR_SGES, 1);
+	i += 2;				/* head + tail */
+	i *= buf->rb_max_requests;	/* one set for each RPC slot */
+	dprintk("RPC:       %s: initalizing %d FMRs\n", __func__, i);
 
+	rc = -ENOMEM;
 	while (i--) {
 		r = kzalloc(sizeof(*r), GFP_KERNEL);
 		if (!r)
-			return -ENOMEM;
+			goto out;
 
-		r->r.fmr = ib_alloc_fmr(pd, mr_access_flags, &fmr_attr);
-		if (IS_ERR(r->r.fmr))
+		r->r.fmr.physaddrs = kmalloc(RPCRDMA_MAX_FMR_SGES *
+					     sizeof(u64), GFP_KERNEL);
+		if (!r->r.fmr.physaddrs)
+			goto out_free;
+
+		r->r.fmr.fmr = ib_alloc_fmr(pd, mr_access_flags, &fmr_attr);
+		if (IS_ERR(r->r.fmr.fmr))
 			goto out_fmr_err;
 
 		list_add(&r->mw_list, &buf->rb_mws);
@@ -71,12 +95,24 @@
 	return 0;
 
 out_fmr_err:
-	rc = PTR_ERR(r->r.fmr);
+	rc = PTR_ERR(r->r.fmr.fmr);
 	dprintk("RPC:       %s: ib_alloc_fmr status %i\n", __func__, rc);
+	kfree(r->r.fmr.physaddrs);
+out_free:
 	kfree(r);
+out:
 	return rc;
 }
 
+static int
+__fmr_unmap(struct rpcrdma_mw *r)
+{
+	LIST_HEAD(l);
+
+	list_add(&r->r.fmr.fmr->list, &l);
+	return ib_unmap_fmr(&l);
+}
+
 /* Use the ib_map_phys_fmr() verb to register a memory region
  * for remote access via RDMA READ or RDMA WRITE.
  */
@@ -85,12 +121,24 @@
 	   int nsegs, bool writing)
 {
 	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
-	struct ib_device *device = ia->ri_id->device;
+	struct ib_device *device = ia->ri_device;
 	enum dma_data_direction direction = rpcrdma_data_dir(writing);
 	struct rpcrdma_mr_seg *seg1 = seg;
-	struct rpcrdma_mw *mw = seg1->rl_mw;
-	u64 physaddrs[RPCRDMA_MAX_DATA_SEGS];
 	int len, pageoff, i, rc;
+	struct rpcrdma_mw *mw;
+
+	mw = seg1->rl_mw;
+	seg1->rl_mw = NULL;
+	if (!mw) {
+		mw = rpcrdma_get_mw(r_xprt);
+		if (!mw)
+			return -ENOMEM;
+	} else {
+		/* this is a retransmit; generate a fresh rkey */
+		rc = __fmr_unmap(mw);
+		if (rc)
+			return rc;
+	}
 
 	pageoff = offset_in_page(seg1->mr_offset);
 	seg1->mr_offset -= pageoff;	/* start of page */
@@ -100,7 +148,7 @@
 		nsegs = RPCRDMA_MAX_FMR_SGES;
 	for (i = 0; i < nsegs;) {
 		rpcrdma_map_one(device, seg, direction);
-		physaddrs[i] = seg->mr_dma;
+		mw->r.fmr.physaddrs[i] = seg->mr_dma;
 		len += seg->mr_len;
 		++seg;
 		++i;
@@ -110,11 +158,13 @@
 			break;
 	}
 
-	rc = ib_map_phys_fmr(mw->r.fmr, physaddrs, i, seg1->mr_dma);
+	rc = ib_map_phys_fmr(mw->r.fmr.fmr, mw->r.fmr.physaddrs,
+			     i, seg1->mr_dma);
 	if (rc)
 		goto out_maperr;
 
-	seg1->mr_rkey = mw->r.fmr->rkey;
+	seg1->rl_mw = mw;
+	seg1->mr_rkey = mw->r.fmr.fmr->rkey;
 	seg1->mr_base = seg1->mr_dma + pageoff;
 	seg1->mr_nsegs = i;
 	seg1->mr_len = len;
@@ -137,48 +187,28 @@
 {
 	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
 	struct rpcrdma_mr_seg *seg1 = seg;
-	struct ib_device *device;
+	struct rpcrdma_mw *mw = seg1->rl_mw;
 	int rc, nsegs = seg->mr_nsegs;
-	LIST_HEAD(l);
 
-	list_add(&seg1->rl_mw->r.fmr->list, &l);
-	rc = ib_unmap_fmr(&l);
-	read_lock(&ia->ri_qplock);
-	device = ia->ri_id->device;
+	dprintk("RPC:       %s: FMR %p\n", __func__, mw);
+
+	seg1->rl_mw = NULL;
 	while (seg1->mr_nsegs--)
-		rpcrdma_unmap_one(device, seg++);
-	read_unlock(&ia->ri_qplock);
+		rpcrdma_unmap_one(ia->ri_device, seg++);
+	rc = __fmr_unmap(mw);
 	if (rc)
 		goto out_err;
+	rpcrdma_put_mw(r_xprt, mw);
 	return nsegs;
 
 out_err:
+	/* The FMR is abandoned, but remains in rb_all. fmr_op_destroy
+	 * will attempt to release it when the transport is destroyed.
+	 */
 	dprintk("RPC:       %s: ib_unmap_fmr status %i\n", __func__, rc);
 	return nsegs;
 }
 
-/* After a disconnect, unmap all FMRs.
- *
- * This is invoked only in the transport connect worker in order
- * to serialize with rpcrdma_register_fmr_external().
- */
-static void
-fmr_op_reset(struct rpcrdma_xprt *r_xprt)
-{
-	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
-	struct rpcrdma_mw *r;
-	LIST_HEAD(list);
-	int rc;
-
-	list_for_each_entry(r, &buf->rb_all, mw_all)
-		list_add(&r->r.fmr->list, &list);
-
-	rc = ib_unmap_fmr(&list);
-	if (rc)
-		dprintk("RPC:       %s: ib_unmap_fmr failed %i\n",
-			__func__, rc);
-}
-
 static void
 fmr_op_destroy(struct rpcrdma_buffer *buf)
 {
@@ -188,10 +218,13 @@
 	while (!list_empty(&buf->rb_all)) {
 		r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all);
 		list_del(&r->mw_all);
-		rc = ib_dealloc_fmr(r->r.fmr);
+		kfree(r->r.fmr.physaddrs);
+
+		rc = ib_dealloc_fmr(r->r.fmr.fmr);
 		if (rc)
 			dprintk("RPC:       %s: ib_dealloc_fmr failed %i\n",
 				__func__, rc);
+
 		kfree(r);
 	}
 }
@@ -202,7 +235,6 @@
 	.ro_open			= fmr_op_open,
 	.ro_maxpages			= fmr_op_maxpages,
 	.ro_init			= fmr_op_init,
-	.ro_reset			= fmr_op_reset,
 	.ro_destroy			= fmr_op_destroy,
 	.ro_displayname			= "fmr",
 };
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index d234521..04ea914 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -11,12 +11,136 @@
  * but most complex memory registration mode.
  */
 
+/* Normal operation
+ *
+ * A Memory Region is prepared for RDMA READ or WRITE using a FAST_REG
+ * Work Request (frmr_op_map). When the RDMA operation is finished, this
+ * Memory Region is invalidated using a LOCAL_INV Work Request
+ * (frmr_op_unmap).
+ *
+ * Typically these Work Requests are not signaled, and neither are RDMA
+ * SEND Work Requests (with the exception of signaling occasionally to
+ * prevent provider work queue overflows). This greatly reduces HCA
+ * interrupt workload.
+ *
+ * As an optimization, frwr_op_unmap marks MRs INVALID before the
+ * LOCAL_INV WR is posted. If posting succeeds, the MR is placed on
+ * rb_mws immediately so that no work (like managing a linked list
+ * under a spinlock) is needed in the completion upcall.
+ *
+ * But this means that frwr_op_map() can occasionally encounter an MR
+ * that is INVALID but the LOCAL_INV WR has not completed. Work Queue
+ * ordering prevents a subsequent FAST_REG WR from executing against
+ * that MR while it is still being invalidated.
+ */
+
+/* Transport recovery
+ *
+ * ->op_map and the transport connect worker cannot run at the same
+ * time, but ->op_unmap can fire while the transport connect worker
+ * is running. Thus MR recovery is handled in ->op_map, to guarantee
+ * that recovered MRs are owned by a sending RPC, and not one where
+ * ->op_unmap could fire at the same time transport reconnect is
+ * being done.
+ *
+ * When the underlying transport disconnects, MRs are left in one of
+ * three states:
+ *
+ * INVALID:	The MR was not in use before the QP entered ERROR state.
+ *		(Or, the LOCAL_INV WR has not completed or flushed yet).
+ *
+ * STALE:	The MR was being registered or unregistered when the QP
+ *		entered ERROR state, and the pending WR was flushed.
+ *
+ * VALID:	The MR was registered before the QP entered ERROR state.
+ *
+ * When frwr_op_map encounters STALE and VALID MRs, they are recovered
+ * with ib_dereg_mr and then are re-initialized. Beause MR recovery
+ * allocates fresh resources, it is deferred to a workqueue, and the
+ * recovered MRs are placed back on the rb_mws list when recovery is
+ * complete. frwr_op_map allocates another MR for the current RPC while
+ * the broken MR is reset.
+ *
+ * To ensure that frwr_op_map doesn't encounter an MR that is marked
+ * INVALID but that is about to be flushed due to a previous transport
+ * disconnect, the transport connect worker attempts to drain all
+ * pending send queue WRs before the transport is reconnected.
+ */
+
 #include "xprt_rdma.h"
 
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_TRANS
 #endif
 
+static struct workqueue_struct *frwr_recovery_wq;
+
+#define FRWR_RECOVERY_WQ_FLAGS		(WQ_UNBOUND | WQ_MEM_RECLAIM)
+
+int
+frwr_alloc_recovery_wq(void)
+{
+	frwr_recovery_wq = alloc_workqueue("frwr_recovery",
+					   FRWR_RECOVERY_WQ_FLAGS, 0);
+	return !frwr_recovery_wq ? -ENOMEM : 0;
+}
+
+void
+frwr_destroy_recovery_wq(void)
+{
+	struct workqueue_struct *wq;
+
+	if (!frwr_recovery_wq)
+		return;
+
+	wq = frwr_recovery_wq;
+	frwr_recovery_wq = NULL;
+	destroy_workqueue(wq);
+}
+
+/* Deferred reset of a single FRMR. Generate a fresh rkey by
+ * replacing the MR.
+ *
+ * There's no recovery if this fails. The FRMR is abandoned, but
+ * remains in rb_all. It will be cleaned up when the transport is
+ * destroyed.
+ */
+static void
+__frwr_recovery_worker(struct work_struct *work)
+{
+	struct rpcrdma_mw *r = container_of(work, struct rpcrdma_mw,
+					    r.frmr.fr_work);
+	struct rpcrdma_xprt *r_xprt = r->r.frmr.fr_xprt;
+	unsigned int depth = r_xprt->rx_ia.ri_max_frmr_depth;
+	struct ib_pd *pd = r_xprt->rx_ia.ri_pd;
+
+	if (ib_dereg_mr(r->r.frmr.fr_mr))
+		goto out_fail;
+
+	r->r.frmr.fr_mr = ib_alloc_fast_reg_mr(pd, depth);
+	if (IS_ERR(r->r.frmr.fr_mr))
+		goto out_fail;
+
+	dprintk("RPC:       %s: recovered FRMR %p\n", __func__, r);
+	r->r.frmr.fr_state = FRMR_IS_INVALID;
+	rpcrdma_put_mw(r_xprt, r);
+	return;
+
+out_fail:
+	pr_warn("RPC:       %s: FRMR %p unrecovered\n",
+		__func__, r);
+}
+
+/* A broken MR was discovered in a context that can't sleep.
+ * Defer recovery to the recovery worker.
+ */
+static void
+__frwr_queue_recovery(struct rpcrdma_mw *r)
+{
+	INIT_WORK(&r->r.frmr.fr_work, __frwr_recovery_worker);
+	queue_work(frwr_recovery_wq, &r->r.frmr.fr_work);
+}
+
 static int
 __frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, struct ib_device *device,
 	    unsigned int depth)
@@ -128,7 +252,7 @@
 
 	/* WARNING: Only wr_id and status are reliable at this point */
 	r = (struct rpcrdma_mw *)(unsigned long)wc->wr_id;
-	dprintk("RPC:       %s: frmr %p (stale), status %s (%d)\n",
+	pr_warn("RPC:       %s: frmr %p flushed, status %s (%d)\n",
 		__func__, r, ib_wc_status_msg(wc->status), wc->status);
 	r->r.frmr.fr_state = FRMR_IS_STALE;
 }
@@ -137,16 +261,19 @@
 frwr_op_init(struct rpcrdma_xprt *r_xprt)
 {
 	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
-	struct ib_device *device = r_xprt->rx_ia.ri_id->device;
+	struct ib_device *device = r_xprt->rx_ia.ri_device;
 	unsigned int depth = r_xprt->rx_ia.ri_max_frmr_depth;
 	struct ib_pd *pd = r_xprt->rx_ia.ri_pd;
 	int i;
 
+	spin_lock_init(&buf->rb_mwlock);
 	INIT_LIST_HEAD(&buf->rb_mws);
 	INIT_LIST_HEAD(&buf->rb_all);
 
-	i = (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS;
-	dprintk("RPC:       %s: initializing %d FRMRs\n", __func__, i);
+	i = max_t(int, RPCRDMA_MAX_DATA_SEGS / depth, 1);
+	i += 2;				/* head + tail */
+	i *= buf->rb_max_requests;	/* one set for each RPC slot */
+	dprintk("RPC:       %s: initalizing %d FRMRs\n", __func__, i);
 
 	while (i--) {
 		struct rpcrdma_mw *r;
@@ -165,6 +292,7 @@
 		list_add(&r->mw_list, &buf->rb_mws);
 		list_add(&r->mw_all, &buf->rb_all);
 		r->mw_sendcompletion = frwr_sendcompletion;
+		r->r.frmr.fr_xprt = r_xprt;
 	}
 
 	return 0;
@@ -178,12 +306,12 @@
 	    int nsegs, bool writing)
 {
 	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
-	struct ib_device *device = ia->ri_id->device;
+	struct ib_device *device = ia->ri_device;
 	enum dma_data_direction direction = rpcrdma_data_dir(writing);
 	struct rpcrdma_mr_seg *seg1 = seg;
-	struct rpcrdma_mw *mw = seg1->rl_mw;
-	struct rpcrdma_frmr *frmr = &mw->r.frmr;
-	struct ib_mr *mr = frmr->fr_mr;
+	struct rpcrdma_mw *mw;
+	struct rpcrdma_frmr *frmr;
+	struct ib_mr *mr;
 	struct ib_send_wr fastreg_wr, *bad_wr;
 	u8 key;
 	int len, pageoff;
@@ -192,12 +320,25 @@
 	u64 pa;
 	int page_no;
 
+	mw = seg1->rl_mw;
+	seg1->rl_mw = NULL;
+	do {
+		if (mw)
+			__frwr_queue_recovery(mw);
+		mw = rpcrdma_get_mw(r_xprt);
+		if (!mw)
+			return -ENOMEM;
+	} while (mw->r.frmr.fr_state != FRMR_IS_INVALID);
+	frmr = &mw->r.frmr;
+	frmr->fr_state = FRMR_IS_VALID;
+
 	pageoff = offset_in_page(seg1->mr_offset);
 	seg1->mr_offset -= pageoff;	/* start of page */
 	seg1->mr_len += pageoff;
 	len = -pageoff;
 	if (nsegs > ia->ri_max_frmr_depth)
 		nsegs = ia->ri_max_frmr_depth;
+
 	for (page_no = i = 0; i < nsegs;) {
 		rpcrdma_map_one(device, seg, direction);
 		pa = seg->mr_dma;
@@ -216,8 +357,6 @@
 	dprintk("RPC:       %s: Using frmr %p to map %d segments (%d bytes)\n",
 		__func__, mw, i, len);
 
-	frmr->fr_state = FRMR_IS_VALID;
-
 	memset(&fastreg_wr, 0, sizeof(fastreg_wr));
 	fastreg_wr.wr_id = (unsigned long)(void *)mw;
 	fastreg_wr.opcode = IB_WR_FAST_REG_MR;
@@ -229,6 +368,7 @@
 	fastreg_wr.wr.fast_reg.access_flags = writing ?
 				IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE :
 				IB_ACCESS_REMOTE_READ;
+	mr = frmr->fr_mr;
 	key = (u8)(mr->rkey & 0x000000FF);
 	ib_update_fast_reg_key(mr, ++key);
 	fastreg_wr.wr.fast_reg.rkey = mr->rkey;
@@ -238,6 +378,7 @@
 	if (rc)
 		goto out_senderr;
 
+	seg1->rl_mw = mw;
 	seg1->mr_rkey = mr->rkey;
 	seg1->mr_base = seg1->mr_dma + pageoff;
 	seg1->mr_nsegs = i;
@@ -246,10 +387,9 @@
 
 out_senderr:
 	dprintk("RPC:       %s: ib_post_send status %i\n", __func__, rc);
-	ib_update_fast_reg_key(mr, --key);
-	frmr->fr_state = FRMR_IS_INVALID;
 	while (i--)
 		rpcrdma_unmap_one(device, --seg);
+	__frwr_queue_recovery(mw);
 	return rc;
 }
 
@@ -261,78 +401,46 @@
 {
 	struct rpcrdma_mr_seg *seg1 = seg;
 	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+	struct rpcrdma_mw *mw = seg1->rl_mw;
 	struct ib_send_wr invalidate_wr, *bad_wr;
 	int rc, nsegs = seg->mr_nsegs;
-	struct ib_device *device;
 
-	seg1->rl_mw->r.frmr.fr_state = FRMR_IS_INVALID;
+	dprintk("RPC:       %s: FRMR %p\n", __func__, mw);
+
+	seg1->rl_mw = NULL;
+	mw->r.frmr.fr_state = FRMR_IS_INVALID;
 
 	memset(&invalidate_wr, 0, sizeof(invalidate_wr));
-	invalidate_wr.wr_id = (unsigned long)(void *)seg1->rl_mw;
+	invalidate_wr.wr_id = (unsigned long)(void *)mw;
 	invalidate_wr.opcode = IB_WR_LOCAL_INV;
-	invalidate_wr.ex.invalidate_rkey = seg1->rl_mw->r.frmr.fr_mr->rkey;
+	invalidate_wr.ex.invalidate_rkey = mw->r.frmr.fr_mr->rkey;
 	DECR_CQCOUNT(&r_xprt->rx_ep);
 
-	read_lock(&ia->ri_qplock);
-	device = ia->ri_id->device;
 	while (seg1->mr_nsegs--)
-		rpcrdma_unmap_one(device, seg++);
+		rpcrdma_unmap_one(ia->ri_device, seg++);
+	read_lock(&ia->ri_qplock);
 	rc = ib_post_send(ia->ri_id->qp, &invalidate_wr, &bad_wr);
 	read_unlock(&ia->ri_qplock);
 	if (rc)
 		goto out_err;
+
+	rpcrdma_put_mw(r_xprt, mw);
 	return nsegs;
 
 out_err:
-	/* Force rpcrdma_buffer_get() to retry */
-	seg1->rl_mw->r.frmr.fr_state = FRMR_IS_STALE;
 	dprintk("RPC:       %s: ib_post_send status %i\n", __func__, rc);
+	__frwr_queue_recovery(mw);
 	return nsegs;
 }
 
-/* After a disconnect, a flushed FAST_REG_MR can leave an FRMR in
- * an unusable state. Find FRMRs in this state and dereg / reg
- * each.  FRMRs that are VALID and attached to an rpcrdma_req are
- * also torn down.
- *
- * This gives all in-use FRMRs a fresh rkey and leaves them INVALID.
- *
- * This is invoked only in the transport connect worker in order
- * to serialize with rpcrdma_register_frmr_external().
- */
-static void
-frwr_op_reset(struct rpcrdma_xprt *r_xprt)
-{
-	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
-	struct ib_device *device = r_xprt->rx_ia.ri_id->device;
-	unsigned int depth = r_xprt->rx_ia.ri_max_frmr_depth;
-	struct ib_pd *pd = r_xprt->rx_ia.ri_pd;
-	struct rpcrdma_mw *r;
-	int rc;
-
-	list_for_each_entry(r, &buf->rb_all, mw_all) {
-		if (r->r.frmr.fr_state == FRMR_IS_INVALID)
-			continue;
-
-		__frwr_release(r);
-		rc = __frwr_init(r, pd, device, depth);
-		if (rc) {
-			dprintk("RPC:       %s: mw %p left %s\n",
-				__func__, r,
-				(r->r.frmr.fr_state == FRMR_IS_STALE ?
-					"stale" : "valid"));
-			continue;
-		}
-
-		r->r.frmr.fr_state = FRMR_IS_INVALID;
-	}
-}
-
 static void
 frwr_op_destroy(struct rpcrdma_buffer *buf)
 {
 	struct rpcrdma_mw *r;
 
+	/* Ensure stale MWs for "buf" are no longer in flight */
+	flush_workqueue(frwr_recovery_wq);
+
 	while (!list_empty(&buf->rb_all)) {
 		r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all);
 		list_del(&r->mw_all);
@@ -347,7 +455,6 @@
 	.ro_open			= frwr_op_open,
 	.ro_maxpages			= frwr_op_maxpages,
 	.ro_init			= frwr_op_init,
-	.ro_reset			= frwr_op_reset,
 	.ro_destroy			= frwr_op_destroy,
 	.ro_displayname			= "frwr",
 };
diff --git a/net/sunrpc/xprtrdma/physical_ops.c b/net/sunrpc/xprtrdma/physical_ops.c
index ba518af..41985d0 100644
--- a/net/sunrpc/xprtrdma/physical_ops.c
+++ b/net/sunrpc/xprtrdma/physical_ops.c
@@ -50,8 +50,7 @@
 {
 	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
 
-	rpcrdma_map_one(ia->ri_id->device, seg,
-			rpcrdma_data_dir(writing));
+	rpcrdma_map_one(ia->ri_device, seg, rpcrdma_data_dir(writing));
 	seg->mr_rkey = ia->ri_bind_mem->rkey;
 	seg->mr_base = seg->mr_dma;
 	seg->mr_nsegs = 1;
@@ -65,19 +64,11 @@
 {
 	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
 
-	read_lock(&ia->ri_qplock);
-	rpcrdma_unmap_one(ia->ri_id->device, seg);
-	read_unlock(&ia->ri_qplock);
-
+	rpcrdma_unmap_one(ia->ri_device, seg);
 	return 1;
 }
 
 static void
-physical_op_reset(struct rpcrdma_xprt *r_xprt)
-{
-}
-
-static void
 physical_op_destroy(struct rpcrdma_buffer *buf)
 {
 }
@@ -88,7 +79,6 @@
 	.ro_open			= physical_op_open,
 	.ro_maxpages			= physical_op_maxpages,
 	.ro_init			= physical_op_init,
-	.ro_reset			= physical_op_reset,
 	.ro_destroy			= physical_op_destroy,
 	.ro_displayname			= "physical",
 };
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 2c53ea9..84ea37d 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -284,9 +284,6 @@
 	return (unsigned char *)iptr - (unsigned char *)headerp;
 
 out:
-	if (r_xprt->rx_ia.ri_memreg_strategy == RPCRDMA_FRMR)
-		return n;
-
 	for (pos = 0; nchunks--;)
 		pos += r_xprt->rx_ia.ri_ops->ro_unmap(r_xprt,
 						      &req->rl_segments[pos]);
@@ -732,8 +729,8 @@
 	struct rpcrdma_msg *headerp;
 	struct rpcrdma_req *req;
 	struct rpc_rqst *rqst;
-	struct rpc_xprt *xprt = rep->rr_xprt;
-	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
+	struct rpcrdma_xprt *r_xprt = rep->rr_rxprt;
+	struct rpc_xprt *xprt = &r_xprt->rx_xprt;
 	__be32 *iptr;
 	int rdmalen, status;
 	unsigned long cwnd;
@@ -770,7 +767,6 @@
 			rep->rr_len);
 repost:
 		r_xprt->rx_stats.bad_reply_count++;
-		rep->rr_func = rpcrdma_reply_handler;
 		if (rpcrdma_ep_post_recv(&r_xprt->rx_ia, &r_xprt->rx_ep, rep))
 			rpcrdma_recv_buffer_put(rep);
 
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 436da2c..680f888 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -240,6 +240,16 @@
 	xprt_clear_connecting(xprt);
 }
 
+static void
+xprt_rdma_inject_disconnect(struct rpc_xprt *xprt)
+{
+	struct rpcrdma_xprt *r_xprt = container_of(xprt, struct rpcrdma_xprt,
+						   rx_xprt);
+
+	pr_info("rpcrdma: injecting transport disconnect on xprt=%p\n", xprt);
+	rdma_disconnect(r_xprt->rx_ia.ri_id);
+}
+
 /*
  * xprt_rdma_destroy
  *
@@ -612,12 +622,6 @@
 	if (req->rl_reply == NULL) 		/* e.g. reconnection */
 		rpcrdma_recv_buffer_get(req);
 
-	if (req->rl_reply) {
-		req->rl_reply->rr_func = rpcrdma_reply_handler;
-		/* this need only be done once, but... */
-		req->rl_reply->rr_xprt = xprt;
-	}
-
 	/* Must suppress retransmit to maintain credits */
 	if (req->rl_connect_cookie == xprt->connect_cookie)
 		goto drop_connection;
@@ -676,6 +680,17 @@
 	   r_xprt->rx_stats.bad_reply_count);
 }
 
+static int
+xprt_rdma_enable_swap(struct rpc_xprt *xprt)
+{
+	return -EINVAL;
+}
+
+static void
+xprt_rdma_disable_swap(struct rpc_xprt *xprt)
+{
+}
+
 /*
  * Plumbing for rpc transport switch and kernel module
  */
@@ -694,7 +709,10 @@
 	.send_request		= xprt_rdma_send_request,
 	.close			= xprt_rdma_close,
 	.destroy		= xprt_rdma_destroy,
-	.print_stats		= xprt_rdma_print_stats
+	.print_stats		= xprt_rdma_print_stats,
+	.enable_swap		= xprt_rdma_enable_swap,
+	.disable_swap		= xprt_rdma_disable_swap,
+	.inject_disconnect	= xprt_rdma_inject_disconnect
 };
 
 static struct xprt_class xprt_rdma = {
@@ -720,17 +738,24 @@
 	if (rc)
 		dprintk("RPC:       %s: xprt_unregister returned %i\n",
 			__func__, rc);
+
+	frwr_destroy_recovery_wq();
 }
 
 int xprt_rdma_init(void)
 {
 	int rc;
 
-	rc = xprt_register_transport(&xprt_rdma);
-
+	rc = frwr_alloc_recovery_wq();
 	if (rc)
 		return rc;
 
+	rc = xprt_register_transport(&xprt_rdma);
+	if (rc) {
+		frwr_destroy_recovery_wq();
+		return rc;
+	}
+
 	dprintk("RPCRDMA Module Init, register RPC RDMA transport\n");
 
 	dprintk("Defaults:\n");
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 52df265..891c4ed 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -80,7 +80,6 @@
 rpcrdma_run_tasklet(unsigned long data)
 {
 	struct rpcrdma_rep *rep;
-	void (*func)(struct rpcrdma_rep *);
 	unsigned long flags;
 
 	data = data;
@@ -89,14 +88,9 @@
 		rep = list_entry(rpcrdma_tasklets_g.next,
 				 struct rpcrdma_rep, rr_list);
 		list_del(&rep->rr_list);
-		func = rep->rr_func;
-		rep->rr_func = NULL;
 		spin_unlock_irqrestore(&rpcrdma_tk_lock_g, flags);
 
-		if (func)
-			func(rep);
-		else
-			rpcrdma_recv_buffer_put(rep);
+		rpcrdma_reply_handler(rep);
 
 		spin_lock_irqsave(&rpcrdma_tk_lock_g, flags);
 	}
@@ -236,7 +230,7 @@
 		__func__, rep, wc->byte_len);
 
 	rep->rr_len = wc->byte_len;
-	ib_dma_sync_single_for_cpu(rdmab_to_ia(rep->rr_buffer)->ri_id->device,
+	ib_dma_sync_single_for_cpu(rep->rr_device,
 				   rdmab_addr(rep->rr_rdmabuf),
 				   rep->rr_len, DMA_FROM_DEVICE);
 	prefetch(rdmab_to_msg(rep->rr_rdmabuf));
@@ -407,7 +401,7 @@
 
 		pr_info("rpcrdma: connection to %pIS:%u on %s, memreg '%s', %d credits, %d responders%s\n",
 			sap, rpc_get_port(sap),
-			ia->ri_id->device->name,
+			ia->ri_device->name,
 			ia->ri_ops->ro_displayname,
 			xprt->rx_buf.rb_max_requests,
 			ird, ird < 4 && ird < tird / 2 ? " (low!)" : "");
@@ -508,8 +502,9 @@
 		rc = PTR_ERR(ia->ri_id);
 		goto out1;
 	}
+	ia->ri_device = ia->ri_id->device;
 
-	ia->ri_pd = ib_alloc_pd(ia->ri_id->device);
+	ia->ri_pd = ib_alloc_pd(ia->ri_device);
 	if (IS_ERR(ia->ri_pd)) {
 		rc = PTR_ERR(ia->ri_pd);
 		dprintk("RPC:       %s: ib_alloc_pd() failed %i\n",
@@ -517,7 +512,7 @@
 		goto out2;
 	}
 
-	rc = ib_query_device(ia->ri_id->device, devattr);
+	rc = ib_query_device(ia->ri_device, devattr);
 	if (rc) {
 		dprintk("RPC:       %s: ib_query_device failed %d\n",
 			__func__, rc);
@@ -526,7 +521,7 @@
 
 	if (devattr->device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY) {
 		ia->ri_have_dma_lkey = 1;
-		ia->ri_dma_lkey = ia->ri_id->device->local_dma_lkey;
+		ia->ri_dma_lkey = ia->ri_device->local_dma_lkey;
 	}
 
 	if (memreg == RPCRDMA_FRMR) {
@@ -541,7 +536,7 @@
 		}
 	}
 	if (memreg == RPCRDMA_MTHCAFMR) {
-		if (!ia->ri_id->device->alloc_fmr) {
+		if (!ia->ri_device->alloc_fmr) {
 			dprintk("RPC:       %s: MTHCAFMR registration "
 				"not supported by HCA\n", __func__);
 			memreg = RPCRDMA_ALLPHYSICAL;
@@ -590,9 +585,6 @@
 	dprintk("RPC:       %s: memory registration strategy is '%s'\n",
 		__func__, ia->ri_ops->ro_displayname);
 
-	/* Else will do memory reg/dereg for each chunk */
-	ia->ri_memreg_strategy = memreg;
-
 	rwlock_init(&ia->ri_qplock);
 	return 0;
 
@@ -622,17 +614,17 @@
 		dprintk("RPC:       %s: ib_dereg_mr returned %i\n",
 			__func__, rc);
 	}
+
 	if (ia->ri_id != NULL && !IS_ERR(ia->ri_id)) {
 		if (ia->ri_id->qp)
 			rdma_destroy_qp(ia->ri_id);
 		rdma_destroy_id(ia->ri_id);
 		ia->ri_id = NULL;
 	}
-	if (ia->ri_pd != NULL && !IS_ERR(ia->ri_pd)) {
-		rc = ib_dealloc_pd(ia->ri_pd);
-		dprintk("RPC:       %s: ib_dealloc_pd returned %i\n",
-			__func__, rc);
-	}
+
+	/* If the pd is still busy, xprtrdma missed freeing a resource */
+	if (ia->ri_pd && !IS_ERR(ia->ri_pd))
+		WARN_ON(ib_dealloc_pd(ia->ri_pd));
 }
 
 /*
@@ -693,8 +685,8 @@
 	INIT_DELAYED_WORK(&ep->rep_connect_worker, rpcrdma_connect_worker);
 
 	cq_attr.cqe = ep->rep_attr.cap.max_send_wr + 1;
-	sendcq = ib_create_cq(ia->ri_id->device, rpcrdma_sendcq_upcall,
-				  rpcrdma_cq_async_error_upcall, ep, &cq_attr);
+	sendcq = ib_create_cq(ia->ri_device, rpcrdma_sendcq_upcall,
+			      rpcrdma_cq_async_error_upcall, ep, &cq_attr);
 	if (IS_ERR(sendcq)) {
 		rc = PTR_ERR(sendcq);
 		dprintk("RPC:       %s: failed to create send CQ: %i\n",
@@ -710,8 +702,8 @@
 	}
 
 	cq_attr.cqe = ep->rep_attr.cap.max_recv_wr + 1;
-	recvcq = ib_create_cq(ia->ri_id->device, rpcrdma_recvcq_upcall,
-				  rpcrdma_cq_async_error_upcall, ep, &cq_attr);
+	recvcq = ib_create_cq(ia->ri_device, rpcrdma_recvcq_upcall,
+			      rpcrdma_cq_async_error_upcall, ep, &cq_attr);
 	if (IS_ERR(recvcq)) {
 		rc = PTR_ERR(recvcq);
 		dprintk("RPC:       %s: failed to create recv CQ: %i\n",
@@ -817,8 +809,6 @@
 		rpcrdma_flush_cqs(ep);
 
 		xprt = container_of(ia, struct rpcrdma_xprt, rx_ia);
-		ia->ri_ops->ro_reset(xprt);
-
 		id = rpcrdma_create_id(xprt, ia,
 				(struct sockaddr *)&xprt->rx_data.addr);
 		if (IS_ERR(id)) {
@@ -832,7 +822,7 @@
 		 * More stuff I haven't thought of!
 		 * Rrrgh!
 		 */
-		if (ia->ri_id->device != id->device) {
+		if (ia->ri_device != id->device) {
 			printk("RPC:       %s: can't reconnect on "
 				"different device!\n", __func__);
 			rdma_destroy_id(id);
@@ -974,7 +964,8 @@
 		goto out_free;
 	}
 
-	rep->rr_buffer = &r_xprt->rx_buf;
+	rep->rr_device = ia->ri_device;
+	rep->rr_rxprt = r_xprt;
 	return rep;
 
 out_free:
@@ -1098,31 +1089,33 @@
 	kfree(buf->rb_pool);
 }
 
-/* "*mw" can be NULL when rpcrdma_buffer_get_mrs() fails, leaving
- * some req segments uninitialized.
- */
-static void
-rpcrdma_buffer_put_mr(struct rpcrdma_mw **mw, struct rpcrdma_buffer *buf)
+struct rpcrdma_mw *
+rpcrdma_get_mw(struct rpcrdma_xprt *r_xprt)
 {
-	if (*mw) {
-		list_add_tail(&(*mw)->mw_list, &buf->rb_mws);
-		*mw = NULL;
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+	struct rpcrdma_mw *mw = NULL;
+
+	spin_lock(&buf->rb_mwlock);
+	if (!list_empty(&buf->rb_mws)) {
+		mw = list_first_entry(&buf->rb_mws,
+				      struct rpcrdma_mw, mw_list);
+		list_del_init(&mw->mw_list);
 	}
+	spin_unlock(&buf->rb_mwlock);
+
+	if (!mw)
+		pr_err("RPC:       %s: no MWs available\n", __func__);
+	return mw;
 }
 
-/* Cycle mw's back in reverse order, and "spin" them.
- * This delays and scrambles reuse as much as possible.
- */
-static void
-rpcrdma_buffer_put_mrs(struct rpcrdma_req *req, struct rpcrdma_buffer *buf)
+void
+rpcrdma_put_mw(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mw *mw)
 {
-	struct rpcrdma_mr_seg *seg = req->rl_segments;
-	struct rpcrdma_mr_seg *seg1 = seg;
-	int i;
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
 
-	for (i = 1, seg++; i < RPCRDMA_MAX_SEGS; seg++, i++)
-		rpcrdma_buffer_put_mr(&seg->rl_mw, buf);
-	rpcrdma_buffer_put_mr(&seg1->rl_mw, buf);
+	spin_lock(&buf->rb_mwlock);
+	list_add_tail(&mw->mw_list, &buf->rb_mws);
+	spin_unlock(&buf->rb_mwlock);
 }
 
 static void
@@ -1132,115 +1125,10 @@
 	req->rl_niovs = 0;
 	if (req->rl_reply) {
 		buf->rb_recv_bufs[--buf->rb_recv_index] = req->rl_reply;
-		req->rl_reply->rr_func = NULL;
 		req->rl_reply = NULL;
 	}
 }
 
-/* rpcrdma_unmap_one() was already done during deregistration.
- * Redo only the ib_post_send().
- */
-static void
-rpcrdma_retry_local_inv(struct rpcrdma_mw *r, struct rpcrdma_ia *ia)
-{
-	struct rpcrdma_xprt *r_xprt =
-				container_of(ia, struct rpcrdma_xprt, rx_ia);
-	struct ib_send_wr invalidate_wr, *bad_wr;
-	int rc;
-
-	dprintk("RPC:       %s: FRMR %p is stale\n", __func__, r);
-
-	/* When this FRMR is re-inserted into rb_mws, it is no longer stale */
-	r->r.frmr.fr_state = FRMR_IS_INVALID;
-
-	memset(&invalidate_wr, 0, sizeof(invalidate_wr));
-	invalidate_wr.wr_id = (unsigned long)(void *)r;
-	invalidate_wr.opcode = IB_WR_LOCAL_INV;
-	invalidate_wr.ex.invalidate_rkey = r->r.frmr.fr_mr->rkey;
-	DECR_CQCOUNT(&r_xprt->rx_ep);
-
-	dprintk("RPC:       %s: frmr %p invalidating rkey %08x\n",
-		__func__, r, r->r.frmr.fr_mr->rkey);
-
-	read_lock(&ia->ri_qplock);
-	rc = ib_post_send(ia->ri_id->qp, &invalidate_wr, &bad_wr);
-	read_unlock(&ia->ri_qplock);
-	if (rc) {
-		/* Force rpcrdma_buffer_get() to retry */
-		r->r.frmr.fr_state = FRMR_IS_STALE;
-		dprintk("RPC:       %s: ib_post_send failed, %i\n",
-			__func__, rc);
-	}
-}
-
-static void
-rpcrdma_retry_flushed_linv(struct list_head *stale,
-			   struct rpcrdma_buffer *buf)
-{
-	struct rpcrdma_ia *ia = rdmab_to_ia(buf);
-	struct list_head *pos;
-	struct rpcrdma_mw *r;
-	unsigned long flags;
-
-	list_for_each(pos, stale) {
-		r = list_entry(pos, struct rpcrdma_mw, mw_list);
-		rpcrdma_retry_local_inv(r, ia);
-	}
-
-	spin_lock_irqsave(&buf->rb_lock, flags);
-	list_splice_tail(stale, &buf->rb_mws);
-	spin_unlock_irqrestore(&buf->rb_lock, flags);
-}
-
-static struct rpcrdma_req *
-rpcrdma_buffer_get_frmrs(struct rpcrdma_req *req, struct rpcrdma_buffer *buf,
-			 struct list_head *stale)
-{
-	struct rpcrdma_mw *r;
-	int i;
-
-	i = RPCRDMA_MAX_SEGS - 1;
-	while (!list_empty(&buf->rb_mws)) {
-		r = list_entry(buf->rb_mws.next,
-			       struct rpcrdma_mw, mw_list);
-		list_del(&r->mw_list);
-		if (r->r.frmr.fr_state == FRMR_IS_STALE) {
-			list_add(&r->mw_list, stale);
-			continue;
-		}
-		req->rl_segments[i].rl_mw = r;
-		if (unlikely(i-- == 0))
-			return req;	/* Success */
-	}
-
-	/* Not enough entries on rb_mws for this req */
-	rpcrdma_buffer_put_sendbuf(req, buf);
-	rpcrdma_buffer_put_mrs(req, buf);
-	return NULL;
-}
-
-static struct rpcrdma_req *
-rpcrdma_buffer_get_fmrs(struct rpcrdma_req *req, struct rpcrdma_buffer *buf)
-{
-	struct rpcrdma_mw *r;
-	int i;
-
-	i = RPCRDMA_MAX_SEGS - 1;
-	while (!list_empty(&buf->rb_mws)) {
-		r = list_entry(buf->rb_mws.next,
-			       struct rpcrdma_mw, mw_list);
-		list_del(&r->mw_list);
-		req->rl_segments[i].rl_mw = r;
-		if (unlikely(i-- == 0))
-			return req;	/* Success */
-	}
-
-	/* Not enough entries on rb_mws for this req */
-	rpcrdma_buffer_put_sendbuf(req, buf);
-	rpcrdma_buffer_put_mrs(req, buf);
-	return NULL;
-}
-
 /*
  * Get a set of request/reply buffers.
  *
@@ -1253,12 +1141,11 @@
 struct rpcrdma_req *
 rpcrdma_buffer_get(struct rpcrdma_buffer *buffers)
 {
-	struct rpcrdma_ia *ia = rdmab_to_ia(buffers);
-	struct list_head stale;
 	struct rpcrdma_req *req;
 	unsigned long flags;
 
 	spin_lock_irqsave(&buffers->rb_lock, flags);
+
 	if (buffers->rb_send_index == buffers->rb_max_requests) {
 		spin_unlock_irqrestore(&buffers->rb_lock, flags);
 		dprintk("RPC:       %s: out of request buffers\n", __func__);
@@ -1277,20 +1164,7 @@
 	}
 	buffers->rb_send_bufs[buffers->rb_send_index++] = NULL;
 
-	INIT_LIST_HEAD(&stale);
-	switch (ia->ri_memreg_strategy) {
-	case RPCRDMA_FRMR:
-		req = rpcrdma_buffer_get_frmrs(req, buffers, &stale);
-		break;
-	case RPCRDMA_MTHCAFMR:
-		req = rpcrdma_buffer_get_fmrs(req, buffers);
-		break;
-	default:
-		break;
-	}
 	spin_unlock_irqrestore(&buffers->rb_lock, flags);
-	if (!list_empty(&stale))
-		rpcrdma_retry_flushed_linv(&stale, buffers);
 	return req;
 }
 
@@ -1302,19 +1176,10 @@
 rpcrdma_buffer_put(struct rpcrdma_req *req)
 {
 	struct rpcrdma_buffer *buffers = req->rl_buffer;
-	struct rpcrdma_ia *ia = rdmab_to_ia(buffers);
 	unsigned long flags;
 
 	spin_lock_irqsave(&buffers->rb_lock, flags);
 	rpcrdma_buffer_put_sendbuf(req, buffers);
-	switch (ia->ri_memreg_strategy) {
-	case RPCRDMA_FRMR:
-	case RPCRDMA_MTHCAFMR:
-		rpcrdma_buffer_put_mrs(req, buffers);
-		break;
-	default:
-		break;
-	}
 	spin_unlock_irqrestore(&buffers->rb_lock, flags);
 }
 
@@ -1344,10 +1209,9 @@
 void
 rpcrdma_recv_buffer_put(struct rpcrdma_rep *rep)
 {
-	struct rpcrdma_buffer *buffers = rep->rr_buffer;
+	struct rpcrdma_buffer *buffers = &rep->rr_rxprt->rx_buf;
 	unsigned long flags;
 
-	rep->rr_func = NULL;
 	spin_lock_irqsave(&buffers->rb_lock, flags);
 	buffers->rb_recv_bufs[--buffers->rb_recv_index] = rep;
 	spin_unlock_irqrestore(&buffers->rb_lock, flags);
@@ -1376,9 +1240,9 @@
 	/*
 	 * All memory passed here was kmalloc'ed, therefore phys-contiguous.
 	 */
-	iov->addr = ib_dma_map_single(ia->ri_id->device,
+	iov->addr = ib_dma_map_single(ia->ri_device,
 			va, len, DMA_BIDIRECTIONAL);
-	if (ib_dma_mapping_error(ia->ri_id->device, iov->addr))
+	if (ib_dma_mapping_error(ia->ri_device, iov->addr))
 		return -ENOMEM;
 
 	iov->length = len;
@@ -1422,8 +1286,8 @@
 {
 	int rc;
 
-	ib_dma_unmap_single(ia->ri_id->device,
-			iov->addr, iov->length, DMA_BIDIRECTIONAL);
+	ib_dma_unmap_single(ia->ri_device,
+			    iov->addr, iov->length, DMA_BIDIRECTIONAL);
 
 	if (NULL == mr)
 		return 0;
@@ -1516,15 +1380,18 @@
 	send_wr.num_sge = req->rl_niovs;
 	send_wr.opcode = IB_WR_SEND;
 	if (send_wr.num_sge == 4)	/* no need to sync any pad (constant) */
-		ib_dma_sync_single_for_device(ia->ri_id->device,
-			req->rl_send_iov[3].addr, req->rl_send_iov[3].length,
-			DMA_TO_DEVICE);
-	ib_dma_sync_single_for_device(ia->ri_id->device,
-		req->rl_send_iov[1].addr, req->rl_send_iov[1].length,
-		DMA_TO_DEVICE);
-	ib_dma_sync_single_for_device(ia->ri_id->device,
-		req->rl_send_iov[0].addr, req->rl_send_iov[0].length,
-		DMA_TO_DEVICE);
+		ib_dma_sync_single_for_device(ia->ri_device,
+					      req->rl_send_iov[3].addr,
+					      req->rl_send_iov[3].length,
+					      DMA_TO_DEVICE);
+	ib_dma_sync_single_for_device(ia->ri_device,
+				      req->rl_send_iov[1].addr,
+				      req->rl_send_iov[1].length,
+				      DMA_TO_DEVICE);
+	ib_dma_sync_single_for_device(ia->ri_device,
+				      req->rl_send_iov[0].addr,
+				      req->rl_send_iov[0].length,
+				      DMA_TO_DEVICE);
 
 	if (DECR_CQCOUNT(ep) > 0)
 		send_wr.send_flags = 0;
@@ -1557,7 +1424,7 @@
 	recv_wr.sg_list = &rep->rr_rdmabuf->rg_iov;
 	recv_wr.num_sge = 1;
 
-	ib_dma_sync_single_for_cpu(ia->ri_id->device,
+	ib_dma_sync_single_for_cpu(ia->ri_device,
 				   rdmab_addr(rep->rr_rdmabuf),
 				   rdmab_length(rep->rr_rdmabuf),
 				   DMA_BIDIRECTIONAL);
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 58163b8..f49dd8b 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -62,6 +62,7 @@
 struct rpcrdma_ia {
 	const struct rpcrdma_memreg_ops	*ri_ops;
 	rwlock_t		ri_qplock;
+	struct ib_device	*ri_device;
 	struct rdma_cm_id 	*ri_id;
 	struct ib_pd		*ri_pd;
 	struct ib_mr		*ri_bind_mem;
@@ -69,7 +70,6 @@
 	int			ri_have_dma_lkey;
 	struct completion	ri_done;
 	int			ri_async_rc;
-	enum rpcrdma_memreg	ri_memreg_strategy;
 	unsigned int		ri_max_frmr_depth;
 	struct ib_device_attr	ri_devattr;
 	struct ib_qp_attr	ri_qp_attr;
@@ -173,9 +173,8 @@
 
 struct rpcrdma_rep {
 	unsigned int		rr_len;
-	struct rpcrdma_buffer	*rr_buffer;
-	struct rpc_xprt		*rr_xprt;
-	void			(*rr_func)(struct rpcrdma_rep *);
+	struct ib_device	*rr_device;
+	struct rpcrdma_xprt	*rr_rxprt;
 	struct list_head	rr_list;
 	struct rpcrdma_regbuf	*rr_rdmabuf;
 };
@@ -203,11 +202,18 @@
 	struct ib_fast_reg_page_list	*fr_pgl;
 	struct ib_mr			*fr_mr;
 	enum rpcrdma_frmr_state		fr_state;
+	struct work_struct		fr_work;
+	struct rpcrdma_xprt		*fr_xprt;
+};
+
+struct rpcrdma_fmr {
+	struct ib_fmr		*fmr;
+	u64			*physaddrs;
 };
 
 struct rpcrdma_mw {
 	union {
-		struct ib_fmr		*fmr;
+		struct rpcrdma_fmr	fmr;
 		struct rpcrdma_frmr	frmr;
 	} r;
 	void			(*mw_sendcompletion)(struct ib_wc *);
@@ -281,15 +287,17 @@
  * One of these is associated with a transport instance
  */
 struct rpcrdma_buffer {
-	spinlock_t	rb_lock;	/* protects indexes */
-	u32		rb_max_requests;/* client max requests */
-	struct list_head rb_mws;	/* optional memory windows/fmrs/frmrs */
-	struct list_head rb_all;
-	int		rb_send_index;
+	spinlock_t		rb_mwlock;	/* protect rb_mws list */
+	struct list_head	rb_mws;
+	struct list_head	rb_all;
+	char			*rb_pool;
+
+	spinlock_t		rb_lock;	/* protect buf arrays */
+	u32			rb_max_requests;
+	int			rb_send_index;
+	int			rb_recv_index;
 	struct rpcrdma_req	**rb_send_bufs;
-	int		rb_recv_index;
 	struct rpcrdma_rep	**rb_recv_bufs;
-	char		*rb_pool;
 };
 #define rdmab_to_ia(b) (&container_of((b), struct rpcrdma_xprt, rx_buf)->rx_ia)
 
@@ -350,7 +358,6 @@
 				   struct rpcrdma_create_data_internal *);
 	size_t		(*ro_maxpages)(struct rpcrdma_xprt *);
 	int		(*ro_init)(struct rpcrdma_xprt *);
-	void		(*ro_reset)(struct rpcrdma_xprt *);
 	void		(*ro_destroy)(struct rpcrdma_buffer *);
 	const char	*ro_displayname;
 };
@@ -413,6 +420,8 @@
 int rpcrdma_buffer_create(struct rpcrdma_xprt *);
 void rpcrdma_buffer_destroy(struct rpcrdma_buffer *);
 
+struct rpcrdma_mw *rpcrdma_get_mw(struct rpcrdma_xprt *);
+void rpcrdma_put_mw(struct rpcrdma_xprt *, struct rpcrdma_mw *);
 struct rpcrdma_req *rpcrdma_buffer_get(struct rpcrdma_buffer *);
 void rpcrdma_buffer_put(struct rpcrdma_req *);
 void rpcrdma_recv_buffer_get(struct rpcrdma_req *);
@@ -425,6 +434,9 @@
 
 unsigned int rpcrdma_max_segments(struct rpcrdma_xprt *);
 
+int frwr_alloc_recovery_wq(void);
+void frwr_destroy_recovery_wq(void);
+
 /*
  * Wrappers for chunk registration, shared by read/write chunk code.
  */
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 66891e3..e193c2b 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -623,24 +623,6 @@
 }
 
 /**
- * xs_tcp_shutdown - gracefully shut down a TCP socket
- * @xprt: transport
- *
- * Initiates a graceful shutdown of the TCP socket by calling the
- * equivalent of shutdown(SHUT_RDWR);
- */
-static void xs_tcp_shutdown(struct rpc_xprt *xprt)
-{
-	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
-	struct socket *sock = transport->sock;
-
-	if (sock != NULL) {
-		kernel_sock_shutdown(sock, SHUT_RDWR);
-		trace_rpc_socket_shutdown(xprt, sock);
-	}
-}
-
-/**
  * xs_tcp_send_request - write an RPC request to a TCP socket
  * @task: address of RPC task that manages the state of an RPC request
  *
@@ -786,6 +768,7 @@
 	xs_sock_reset_connection_flags(xprt);
 	/* Mark transport as closed and wake up all pending tasks */
 	xprt_disconnect_done(xprt);
+	xprt_force_disconnect(xprt);
 }
 
 /**
@@ -827,6 +810,9 @@
 	if (sk == NULL)
 		return;
 
+	if (atomic_read(&transport->xprt.swapper))
+		sk_clear_memalloc(sk);
+
 	write_lock_bh(&sk->sk_callback_lock);
 	transport->inet = NULL;
 	transport->sock = NULL;
@@ -863,6 +849,13 @@
 	xprt_disconnect_done(xprt);
 }
 
+static void xs_inject_disconnect(struct rpc_xprt *xprt)
+{
+	dprintk("RPC:       injecting transport disconnect on xprt=%p\n",
+		xprt);
+	xprt_disconnect_done(xprt);
+}
+
 static void xs_xprt_free(struct rpc_xprt *xprt)
 {
 	xs_free_peer_addresses(xprt);
@@ -901,7 +894,6 @@
 /**
  * xs_local_data_ready - "data ready" callback for AF_LOCAL sockets
  * @sk: socket with data to read
- * @len: how much data to read
  *
  * Currently this assumes we can read the whole reply in a single gulp.
  */
@@ -965,7 +957,6 @@
 /**
  * xs_udp_data_ready - "data ready" callback for UDP sockets
  * @sk: socket with data to read
- * @len: how much data to read
  *
  */
 static void xs_udp_data_ready(struct sock *sk)
@@ -1389,7 +1380,6 @@
 /**
  * xs_tcp_data_ready - "data ready" callback for TCP sockets
  * @sk: socket with data to read
- * @bytes: how much data to read
  *
  */
 static void xs_tcp_data_ready(struct sock *sk)
@@ -1886,9 +1876,7 @@
 
 /**
  * xs_local_setup_socket - create AF_LOCAL socket, connect to a local endpoint
- * @xprt: RPC transport to connect
  * @transport: socket transport to connect
- * @create_sock: function to create a socket of the correct type
  */
 static int xs_local_setup_socket(struct sock_xprt *transport)
 {
@@ -1960,43 +1948,84 @@
 		msleep_interruptible(15000);
 }
 
-#ifdef CONFIG_SUNRPC_SWAP
+#if IS_ENABLED(CONFIG_SUNRPC_SWAP)
+/*
+ * Note that this should be called with XPRT_LOCKED held (or when we otherwise
+ * know that we have exclusive access to the socket), to guard against
+ * races with xs_reset_transport.
+ */
 static void xs_set_memalloc(struct rpc_xprt *xprt)
 {
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt,
 			xprt);
 
-	if (xprt->swapper)
+	/*
+	 * If there's no sock, then we have nothing to set. The
+	 * reconnecting process will get it for us.
+	 */
+	if (!transport->inet)
+		return;
+	if (atomic_read(&xprt->swapper))
 		sk_set_memalloc(transport->inet);
 }
 
 /**
- * xs_swapper - Tag this transport as being used for swap.
+ * xs_enable_swap - Tag this transport as being used for swap.
  * @xprt: transport to tag
- * @enable: enable/disable
  *
+ * Take a reference to this transport on behalf of the rpc_clnt, and
+ * optionally mark it for swapping if it wasn't already.
  */
-int xs_swapper(struct rpc_xprt *xprt, int enable)
+static int
+xs_enable_swap(struct rpc_xprt *xprt)
 {
-	struct sock_xprt *transport = container_of(xprt, struct sock_xprt,
-			xprt);
-	int err = 0;
+	struct sock_xprt *xs = container_of(xprt, struct sock_xprt, xprt);
 
-	if (enable) {
-		xprt->swapper++;
-		xs_set_memalloc(xprt);
-	} else if (xprt->swapper) {
-		xprt->swapper--;
-		sk_clear_memalloc(transport->inet);
-	}
-
-	return err;
+	if (atomic_inc_return(&xprt->swapper) != 1)
+		return 0;
+	if (wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_KILLABLE))
+		return -ERESTARTSYS;
+	if (xs->inet)
+		sk_set_memalloc(xs->inet);
+	xprt_release_xprt(xprt, NULL);
+	return 0;
 }
-EXPORT_SYMBOL_GPL(xs_swapper);
+
+/**
+ * xs_disable_swap - Untag this transport as being used for swap.
+ * @xprt: transport to tag
+ *
+ * Drop a "swapper" reference to this xprt on behalf of the rpc_clnt. If the
+ * swapper refcount goes to 0, untag the socket as a memalloc socket.
+ */
+static void
+xs_disable_swap(struct rpc_xprt *xprt)
+{
+	struct sock_xprt *xs = container_of(xprt, struct sock_xprt, xprt);
+
+	if (!atomic_dec_and_test(&xprt->swapper))
+		return;
+	if (wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_KILLABLE))
+		return;
+	if (xs->inet)
+		sk_clear_memalloc(xs->inet);
+	xprt_release_xprt(xprt, NULL);
+}
 #else
 static void xs_set_memalloc(struct rpc_xprt *xprt)
 {
 }
+
+static int
+xs_enable_swap(struct rpc_xprt *xprt)
+{
+	return -EINVAL;
+}
+
+static void
+xs_disable_swap(struct rpc_xprt *xprt)
+{
+}
 #endif
 
 static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
@@ -2057,6 +2086,27 @@
 	xprt_wake_pending_tasks(xprt, status);
 }
 
+/**
+ * xs_tcp_shutdown - gracefully shut down a TCP socket
+ * @xprt: transport
+ *
+ * Initiates a graceful shutdown of the TCP socket by calling the
+ * equivalent of shutdown(SHUT_RDWR);
+ */
+static void xs_tcp_shutdown(struct rpc_xprt *xprt)
+{
+	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+	struct socket *sock = transport->sock;
+
+	if (sock == NULL)
+		return;
+	if (xprt_connected(xprt)) {
+		kernel_sock_shutdown(sock, SHUT_RDWR);
+		trace_rpc_socket_shutdown(xprt, sock);
+	} else
+		xs_reset_transport(transport);
+}
+
 static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 {
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
@@ -2067,6 +2117,7 @@
 		unsigned int keepidle = xprt->timeout->to_initval / HZ;
 		unsigned int keepcnt = xprt->timeout->to_retries + 1;
 		unsigned int opt_on = 1;
+		unsigned int timeo;
 
 		/* TCP Keepalive options */
 		kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE,
@@ -2078,6 +2129,12 @@
 		kernel_setsockopt(sock, SOL_TCP, TCP_KEEPCNT,
 				(char *)&keepcnt, sizeof(keepcnt));
 
+		/* TCP user timeout (see RFC5482) */
+		timeo = jiffies_to_msecs(xprt->timeout->to_initval) *
+			(xprt->timeout->to_retries + 1);
+		kernel_setsockopt(sock, SOL_TCP, TCP_USER_TIMEOUT,
+				(char *)&timeo, sizeof(timeo));
+
 		write_lock_bh(&sk->sk_callback_lock);
 
 		xs_save_old_callbacks(transport, sk);
@@ -2125,9 +2182,6 @@
 
 /**
  * xs_tcp_setup_socket - create a TCP socket and connect to a remote endpoint
- * @xprt: RPC transport to connect
- * @transport: socket transport to connect
- * @create_sock: function to create a socket of the correct type
  *
  * Invoked by a work queue tasklet.
  */
@@ -2463,6 +2517,8 @@
 	.close			= xs_close,
 	.destroy		= xs_destroy,
 	.print_stats		= xs_local_print_stats,
+	.enable_swap		= xs_enable_swap,
+	.disable_swap		= xs_disable_swap,
 };
 
 static struct rpc_xprt_ops xs_udp_ops = {
@@ -2482,6 +2538,9 @@
 	.close			= xs_close,
 	.destroy		= xs_destroy,
 	.print_stats		= xs_udp_print_stats,
+	.enable_swap		= xs_enable_swap,
+	.disable_swap		= xs_disable_swap,
+	.inject_disconnect	= xs_inject_disconnect,
 };
 
 static struct rpc_xprt_ops xs_tcp_ops = {
@@ -2498,6 +2557,9 @@
 	.close			= xs_tcp_shutdown,
 	.destroy		= xs_destroy,
 	.print_stats		= xs_tcp_print_stats,
+	.enable_swap		= xs_enable_swap,
+	.disable_swap		= xs_disable_swap,
+	.inject_disconnect	= xs_inject_disconnect,
 };
 
 /*
@@ -2515,6 +2577,9 @@
 	.close			= bc_close,
 	.destroy		= bc_destroy,
 	.print_stats		= xs_tcp_print_stats,
+	.enable_swap		= xs_enable_swap,
+	.disable_swap		= xs_disable_swap,
+	.inject_disconnect	= xs_inject_disconnect,
 };
 
 static int xs_init_anyaddr(const int family, struct sockaddr *sap)
@@ -2982,7 +3047,7 @@
 			RPC_MAX_RESVPORT);
 }
 
-static struct kernel_param_ops param_ops_portnr = {
+static const struct kernel_param_ops param_ops_portnr = {
 	.set = param_set_portnr,
 	.get = param_get_uint,
 };
@@ -3001,7 +3066,7 @@
 			RPC_MAX_SLOT_TABLE);
 }
 
-static struct kernel_param_ops param_ops_slot_table_size = {
+static const struct kernel_param_ops param_ops_slot_table_size = {
 	.set = param_set_slot_table_size,
 	.get = param_get_uint,
 };
@@ -3017,7 +3082,7 @@
 			RPC_MAX_SLOT_TABLE_LIMIT);
 }
 
-static struct kernel_param_ops param_ops_max_slot_table_size = {
+static const struct kernel_param_ops param_ops_max_slot_table_size = {
 	.set = param_set_max_slot_table_size,
 	.get = param_get_uint,
 };
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index 4906ca3..a816382 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -108,6 +108,11 @@
 
 	tipc_bclink_lock(net);
 	tipc_nmap_remove(&tn->bclink->bcast_nodes, addr);
+
+	/* Last node? => reset backlog queue */
+	if (!tn->bclink->bcast_nodes.count)
+		tipc_link_purge_backlog(&tn->bclink->link);
+
 	tipc_bclink_unlock(net);
 }
 
diff --git a/net/tipc/link.c b/net/tipc/link.c
index ca8b8e0..eaa9fe5 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -404,7 +404,7 @@
 	l_ptr->reasm_buf = NULL;
 }
 
-static void tipc_link_purge_backlog(struct tipc_link *l)
+void tipc_link_purge_backlog(struct tipc_link *l)
 {
 	__skb_queue_purge(&l->backlogq);
 	l->backlog[TIPC_LOW_IMPORTANCE].len = 0;
diff --git a/net/tipc/link.h b/net/tipc/link.h
index 0c02c97..ae0a0ea 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -218,6 +218,7 @@
 int tipc_link_is_up(struct tipc_link *l_ptr);
 int tipc_link_is_active(struct tipc_link *l_ptr);
 void tipc_link_purge_queues(struct tipc_link *l_ptr);
+void tipc_link_purge_backlog(struct tipc_link *l);
 void tipc_link_reset_all(struct tipc_node *node);
 void tipc_link_reset(struct tipc_link *l_ptr);
 int tipc_link_xmit_skb(struct net *net, struct sk_buff *skb, u32 dest,
diff --git a/scripts/dtc/checks.c b/scripts/dtc/checks.c
index ee96a25..e81a8c74 100644
--- a/scripts/dtc/checks.c
+++ b/scripts/dtc/checks.c
@@ -53,7 +53,7 @@
 	void *data;
 	bool warn, error;
 	enum checkstatus status;
-	int inprogress;
+	bool inprogress;
 	int num_prereqs;
 	struct check **prereq;
 };
@@ -113,6 +113,7 @@
 		vfprintf(stderr, fmt, ap);
 		fprintf(stderr, "\n");
 	}
+	va_end(ap);
 }
 
 #define FAIL(c, ...) \
@@ -141,9 +142,9 @@
 		check_nodes_props(c, dt, child);
 }
 
-static int run_check(struct check *c, struct node *dt)
+static bool run_check(struct check *c, struct node *dt)
 {
-	int error = 0;
+	bool error = false;
 	int i;
 
 	assert(!c->inprogress);
@@ -151,11 +152,11 @@
 	if (c->status != UNCHECKED)
 		goto out;
 
-	c->inprogress = 1;
+	c->inprogress = true;
 
 	for (i = 0; i < c->num_prereqs; i++) {
 		struct check *prq = c->prereq[i];
-		error |= run_check(prq, dt);
+		error = error || run_check(prq, dt);
 		if (prq->status != PASSED) {
 			c->status = PREREQ;
 			check_msg(c, "Failed prerequisite '%s'",
@@ -177,9 +178,9 @@
 	TRACE(c, "\tCompleted, status %d", c->status);
 
 out:
-	c->inprogress = 0;
+	c->inprogress = false;
 	if ((c->status != PASSED) && (c->error))
-		error = 1;
+		error = true;
 	return error;
 }
 
@@ -624,11 +625,11 @@
 	if (!reg && !ranges)
 		return;
 
-	if ((node->parent->addr_cells == -1))
+	if (node->parent->addr_cells == -1)
 		FAIL(c, "Relying on default #address-cells value for %s",
 		     node->fullpath);
 
-	if ((node->parent->size_cells == -1))
+	if (node->parent->size_cells == -1)
 		FAIL(c, "Relying on default #size-cells value for %s",
 		     node->fullpath);
 }
@@ -706,15 +707,15 @@
 	c->error = c->error && !error;
 }
 
-void parse_checks_option(bool warn, bool error, const char *optarg)
+void parse_checks_option(bool warn, bool error, const char *arg)
 {
 	int i;
-	const char *name = optarg;
+	const char *name = arg;
 	bool enable = true;
 
-	if ((strncmp(optarg, "no-", 3) == 0)
-	    || (strncmp(optarg, "no_", 3) == 0)) {
-		name = optarg + 3;
+	if ((strncmp(arg, "no-", 3) == 0)
+	    || (strncmp(arg, "no_", 3) == 0)) {
+		name = arg + 3;
 		enable = false;
 	}
 
@@ -733,7 +734,7 @@
 	die("Unrecognized check name \"%s\"\n", name);
 }
 
-void process_checks(int force, struct boot_info *bi)
+void process_checks(bool force, struct boot_info *bi)
 {
 	struct node *dt = bi->dt;
 	int i;
diff --git a/scripts/dtc/data.c b/scripts/dtc/data.c
index 4a40c5b..8cae237 100644
--- a/scripts/dtc/data.c
+++ b/scripts/dtc/data.c
@@ -74,7 +74,7 @@
 	struct data d;
 	char *q;
 
-	d = data_grow_for(empty_data, strlen(s)+1);
+	d = data_grow_for(empty_data, len + 1);
 
 	q = d.val;
 	while (i < len) {
@@ -250,20 +250,20 @@
 	return data_append_markers(d, m);
 }
 
-int data_is_one_string(struct data d)
+bool data_is_one_string(struct data d)
 {
 	int i;
 	int len = d.len;
 
 	if (len == 0)
-		return 0;
+		return false;
 
 	for (i = 0; i < len-1; i++)
 		if (d.val[i] == '\0')
-			return 0;
+			return false;
 
 	if (d.val[len-1] != '\0')
-		return 0;
+		return false;
 
-	return 1;
+	return true;
 }
diff --git a/scripts/dtc/dtc-lexer.l b/scripts/dtc/dtc-lexer.l
index 3b41bfc..0ee1caf 100644
--- a/scripts/dtc/dtc-lexer.l
+++ b/scripts/dtc/dtc-lexer.l
@@ -20,7 +20,6 @@
 
 %option noyywrap nounput noinput never-interactive
 
-%x INCLUDE
 %x BYTESTRING
 %x PROPNODENAME
 %s V1
@@ -40,6 +39,7 @@
 #include "dtc-parser.tab.h"
 
 YYLTYPE yylloc;
+extern bool treesource_error;
 
 /* CAUTION: this will stop working if we ever use yyless() or yyunput() */
 #define	YY_USER_ACTION \
@@ -61,7 +61,8 @@
 				BEGIN(V1); \
 
 static void push_input_file(const char *filename);
-static int pop_input_file(void);
+static bool pop_input_file(void);
+static void lexical_error(const char *fmt, ...);
 %}
 
 %%
@@ -75,11 +76,11 @@
 			char *line, *tmp, *fn;
 			/* skip text before line # */
 			line = yytext;
-			while (!isdigit(*line))
+			while (!isdigit((unsigned char)*line))
 				line++;
 			/* skip digits in line # */
 			tmp = line;
-			while (!isspace(*tmp))
+			while (!isspace((unsigned char)*tmp))
 				tmp++;
 			/* "NULL"-terminate line # */
 			*tmp = '\0';
@@ -146,15 +147,42 @@
 		}
 
 <V1>([0-9]+|0[xX][0-9a-fA-F]+)(U|L|UL|LL|ULL)? {
-			yylval.literal = xstrdup(yytext);
-			DPRINT("Literal: '%s'\n", yylval.literal);
+			char *e;
+			DPRINT("Integer Literal: '%s'\n", yytext);
+
+			errno = 0;
+			yylval.integer = strtoull(yytext, &e, 0);
+
+			assert(!(*e) || !e[strspn(e, "UL")]);
+
+			if (errno == ERANGE)
+				lexical_error("Integer literal '%s' out of range",
+					      yytext);
+			else
+				/* ERANGE is the only strtoull error triggerable
+				 *  by strings matching the pattern */
+				assert(errno == 0);
 			return DT_LITERAL;
 		}
 
 <*>{CHAR_LITERAL}	{
-			yytext[yyleng-1] = '\0';
-			yylval.literal = xstrdup(yytext+1);
-			DPRINT("Character literal: %s\n", yylval.literal);
+			struct data d;
+			DPRINT("Character literal: %s\n", yytext);
+
+			d = data_copy_escape_string(yytext+1, yyleng-2);
+			if (d.len == 1) {
+				lexical_error("Empty character literal");
+				yylval.integer = 0;
+				return DT_CHAR_LITERAL;
+			}
+
+			yylval.integer = (unsigned char)d.val[0];
+
+			if (d.len > 2)
+				lexical_error("Character literal has %d"
+					      " characters instead of 1",
+					      d.len - 1);
+
 			return DT_CHAR_LITERAL;
 		}
 
@@ -164,7 +192,7 @@
 			return DT_REF;
 		}
 
-<*>"&{/"{PATHCHAR}+\}	{	/* new-style path reference */
+<*>"&{/"{PATHCHAR}*\}	{	/* new-style path reference */
 			yytext[yyleng-1] = '\0';
 			DPRINT("Ref: %s\n", yytext+2);
 			yylval.labelref = xstrdup(yytext+2);
@@ -238,13 +266,24 @@
 }
 
 
-static int pop_input_file(void)
+static bool pop_input_file(void)
 {
 	if (srcfile_pop() == 0)
-		return 0;
+		return false;
 
 	yypop_buffer_state();
 	yyin = current_srcfile->f;
 
-	return 1;
+	return true;
+}
+
+static void lexical_error(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	srcpos_verror(&yylloc, "Lexical error", fmt, ap);
+	va_end(ap);
+
+	treesource_error = true;
 }
diff --git a/scripts/dtc/dtc-lexer.lex.c_shipped b/scripts/dtc/dtc-lexer.lex.c_shipped
index 2d30f41..11cd78e 100644
--- a/scripts/dtc/dtc-lexer.lex.c_shipped
+++ b/scripts/dtc/dtc-lexer.lex.c_shipped
@@ -9,7 +9,7 @@
 #define FLEX_SCANNER
 #define YY_FLEX_MAJOR_VERSION 2
 #define YY_FLEX_MINOR_VERSION 5
-#define YY_FLEX_SUBMINOR_VERSION 35
+#define YY_FLEX_SUBMINOR_VERSION 39
 #if YY_FLEX_SUBMINOR_VERSION > 0
 #define FLEX_BETA
 #endif
@@ -162,7 +162,12 @@
 typedef struct yy_buffer_state *YY_BUFFER_STATE;
 #endif
 
-extern int yyleng;
+#ifndef YY_TYPEDEF_YY_SIZE_T
+#define YY_TYPEDEF_YY_SIZE_T
+typedef size_t yy_size_t;
+#endif
+
+extern yy_size_t yyleng;
 
 extern FILE *yyin, *yyout;
 
@@ -171,6 +176,7 @@
 #define EOB_ACT_LAST_MATCH 2
 
     #define YY_LESS_LINENO(n)
+    #define YY_LINENO_REWIND_TO(ptr)
     
 /* Return all but the first "n" matched characters back to the input stream. */
 #define yyless(n) \
@@ -188,11 +194,6 @@
 
 #define unput(c) yyunput( c, (yytext_ptr)  )
 
-#ifndef YY_TYPEDEF_YY_SIZE_T
-#define YY_TYPEDEF_YY_SIZE_T
-typedef size_t yy_size_t;
-#endif
-
 #ifndef YY_STRUCT_YY_BUFFER_STATE
 #define YY_STRUCT_YY_BUFFER_STATE
 struct yy_buffer_state
@@ -210,7 +211,7 @@
 	/* Number of characters read into yy_ch_buf, not including EOB
 	 * characters.
 	 */
-	int yy_n_chars;
+	yy_size_t yy_n_chars;
 
 	/* Whether we "own" the buffer - i.e., we know we created it,
 	 * and can realloc() it to grow it, and should free() it to
@@ -280,8 +281,8 @@
 
 /* yy_hold_char holds the character lost when yytext is formed. */
 static char yy_hold_char;
-static int yy_n_chars;		/* number of characters read into yy_ch_buf */
-int yyleng;
+static yy_size_t yy_n_chars;		/* number of characters read into yy_ch_buf */
+yy_size_t yyleng;
 
 /* Points to current character in buffer. */
 static char *yy_c_buf_p = (char *) 0;
@@ -309,7 +310,7 @@
 
 YY_BUFFER_STATE yy_scan_buffer (char *base,yy_size_t size  );
 YY_BUFFER_STATE yy_scan_string (yyconst char *yy_str  );
-YY_BUFFER_STATE yy_scan_bytes (yyconst char *bytes,int len  );
+YY_BUFFER_STATE yy_scan_bytes (yyconst char *bytes,yy_size_t len  );
 
 void *yyalloc (yy_size_t  );
 void *yyrealloc (void *,yy_size_t  );
@@ -341,7 +342,7 @@
 
 /* Begin user sect3 */
 
-#define yywrap(n) 1
+#define yywrap() 1
 #define YY_SKIP_YYWRAP
 
 typedef unsigned char YY_CHAR;
@@ -381,25 +382,25 @@
 	flex_int32_t yy_verify;
 	flex_int32_t yy_nxt;
 	};
-static yyconst flex_int16_t yy_accept[161] =
+static yyconst flex_int16_t yy_accept[159] =
     {   0,
-        0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
-       31,   29,   18,   18,   29,   29,   29,   29,   29,   29,
-       29,   29,   29,   29,   29,   29,   29,   29,   15,   16,
-       16,   29,   16,   10,   10,   18,   26,    0,    3,    0,
-       27,   12,    0,    0,   11,    0,    0,    0,    0,    0,
-        0,    0,   21,   23,   25,   24,   22,    0,    9,   28,
-        0,    0,    0,   14,   14,   16,   16,   16,   10,   10,
-       10,    0,   12,    0,   11,    0,    0,    0,   20,    0,
-        0,    0,    0,    0,    0,    0,    0,   16,   10,   10,
-       10,    0,   19,    0,    0,    0,    0,    0,    0,    0,
+        0,    0,    0,    0,    0,    0,    0,    0,   31,   29,
+       18,   18,   29,   29,   29,   29,   29,   29,   29,   29,
+       29,   29,   29,   29,   29,   29,   15,   16,   16,   29,
+       16,   10,   10,   18,   26,    0,    3,    0,   27,   12,
+        0,    0,   11,    0,    0,    0,    0,    0,    0,    0,
+       21,   23,   25,   24,   22,    0,    9,   28,    0,    0,
+        0,   14,   14,   16,   16,   16,   10,   10,   10,    0,
+       12,    0,   11,    0,    0,    0,   20,    0,    0,    0,
+        0,    0,    0,    0,    0,   16,   10,   10,   10,    0,
+       13,   19,    0,    0,    0,    0,    0,    0,    0,    0,
 
-        0,    0,   16,   13,    0,    0,    0,    0,    0,    0,
-        0,    0,    0,   16,    6,    0,    0,    0,    0,    0,
-        0,    2,    0,    0,    0,    0,    0,    0,    0,    0,
-        4,   17,    0,    0,    2,    0,    0,    0,    0,    0,
-        0,    0,    0,    0,    0,    0,    0,    1,    0,    0,
-        0,    0,    5,    8,    0,    0,    0,    0,    7,    0
+        0,   16,    0,    0,    0,    0,    0,    0,    0,    0,
+        0,   16,    6,    0,    0,    0,    0,    0,    0,    2,
+        0,    0,    0,    0,    0,    0,    0,    0,    4,   17,
+        0,    0,    2,    0,    0,    0,    0,    0,    0,    0,
+        0,    0,    0,    0,    0,    1,    0,    0,    0,    0,
+        5,    8,    0,    0,    0,    0,    7,    0
     } ;
 
 static yyconst flex_int32_t yy_ec[256] =
@@ -440,157 +441,157 @@
         2,    2,    4,    5,    5,    5,    6,    1,    1,    1,
         7,    8,    8,    8,    8,    1,    1,    7,    7,    7,
         7,    8,    8,    8,    8,    8,    8,    8,    8,    8,
-        8,    8,    8,    3,    1,    1
+        8,    8,    8,    3,    1,    4
     } ;
 
-static yyconst flex_int16_t yy_base[175] =
+static yyconst flex_int16_t yy_base[173] =
     {   0,
-        0,  385,  378,   40,   41,  383,   72,  382,   34,   44,
-      388,  393,   61,  117,  368,  116,  115,  115,  115,   48,
-      367,  107,  368,  339,  127,  120,    0,  147,  393,    0,
-      127,    0,  133,  156,  168,  153,  393,  125,  393,  380,
-      393,    0,  369,  127,  393,  160,  371,  377,  347,   21,
-      343,  346,  393,  393,  393,  393,  393,  359,  393,  393,
-      183,  343,  339,  393,  356,    0,  183,  340,  187,  348,
-      347,    0,    0,    0,  178,  359,  195,  365,  354,  326,
-      332,  325,  334,  328,  204,  326,  331,  324,  393,  335,
-      150,  311,  343,  342,  315,  322,  340,  179,  313,  207,
+        0,  383,   34,  382,   65,  381,   37,  105,  387,  391,
+       54,  111,  367,  110,  109,  109,  112,   41,  366,  104,
+      367,  338,  124,  117,    0,  144,  391,    0,  121,    0,
+      135,  155,  140,  179,  391,  160,  391,  379,  391,    0,
+      368,  141,  391,  167,  370,  376,  346,  103,  342,  345,
+      391,  391,  391,  391,  391,  358,  391,  391,  175,  342,
+      338,  391,  355,    0,  185,  339,  184,  347,  346,    0,
+        0,  322,  175,  357,  175,  363,  352,  324,  330,  323,
+      332,  326,  201,  324,  329,  322,  391,  333,  181,  309,
+      391,  341,  340,  313,  320,  338,  178,  311,  146,  317,
 
-      319,  316,  317,  393,  337,  333,  305,  302,  311,  301,
-      310,  190,  338,  337,  393,  307,  322,  301,  305,  277,
-      208,  311,  307,  278,  271,  270,  248,  246,  213,  130,
-      393,  393,  263,  235,  207,  221,  218,  229,  213,  213,
-      206,  234,  218,  210,  208,  193,  219,  393,  223,  204,
-      176,  157,  393,  393,  120,  106,   97,  119,  393,  393,
-      245,  251,  259,  263,  267,  273,  280,  284,  292,  300,
-      304,  310,  318,  326
+      314,  315,  335,  331,  303,  300,  309,  299,  308,  188,
+      336,  335,  391,  305,  320,  281,  283,  271,  203,  288,
+      281,  271,  266,  264,  245,  242,  208,  104,  391,  391,
+      244,  218,  204,  219,  206,  224,  201,  212,  204,  229,
+      215,  208,  207,  200,  219,  391,  233,  221,  200,  181,
+      391,  391,  149,  122,   86,   41,  391,  391,  245,  251,
+      259,  263,  267,  273,  280,  284,  292,  300,  304,  310,
+      318,  326
     } ;
 
-static yyconst flex_int16_t yy_def[175] =
+static yyconst flex_int16_t yy_def[173] =
     {   0,
-      160,    1,    1,    1,    1,    5,  160,    7,    1,    1,
-      160,  160,  160,  160,  160,  161,  162,  163,  160,  160,
-      160,  160,  164,  160,  160,  160,  165,  164,  160,  166,
-      167,  166,  166,  160,  160,  160,  160,  161,  160,  161,
-      160,  168,  160,  163,  160,  163,  169,  170,  160,  160,
-      160,  160,  160,  160,  160,  160,  160,  164,  160,  160,
-      160,  160,  160,  160,  164,  166,  167,  166,  160,  160,
-      160,  171,  168,  172,  163,  169,  169,  170,  160,  160,
-      160,  160,  160,  160,  160,  160,  160,  166,  160,  160,
-      171,  172,  160,  160,  160,  160,  160,  160,  160,  160,
+      158,    1,    1,    3,  158,    5,    1,    1,  158,  158,
+      158,  158,  158,  159,  160,  161,  158,  158,  158,  158,
+      162,  158,  158,  158,  163,  162,  158,  164,  165,  164,
+      164,  158,  158,  158,  158,  159,  158,  159,  158,  166,
+      158,  161,  158,  161,  167,  168,  158,  158,  158,  158,
+      158,  158,  158,  158,  158,  162,  158,  158,  158,  158,
+      158,  158,  162,  164,  165,  164,  158,  158,  158,  169,
+      166,  170,  161,  167,  167,  168,  158,  158,  158,  158,
+      158,  158,  158,  158,  158,  164,  158,  158,  169,  170,
+      158,  158,  158,  158,  158,  158,  158,  158,  158,  158,
 
-      160,  160,  166,  160,  160,  160,  160,  160,  160,  160,
-      160,  173,  160,  166,  160,  160,  160,  160,  160,  160,
-      173,  160,  173,  160,  160,  160,  160,  160,  160,  160,
-      160,  160,  160,  160,  160,  160,  160,  160,  160,  160,
-      160,  160,  174,  160,  160,  160,  174,  160,  174,  160,
-      160,  160,  160,  160,  160,  160,  160,  160,  160,    0,
-      160,  160,  160,  160,  160,  160,  160,  160,  160,  160,
-      160,  160,  160,  160
+      158,  164,  158,  158,  158,  158,  158,  158,  158,  171,
+      158,  164,  158,  158,  158,  158,  158,  158,  171,  158,
+      171,  158,  158,  158,  158,  158,  158,  158,  158,  158,
+      158,  158,  158,  158,  158,  158,  158,  158,  158,  158,
+      172,  158,  158,  158,  172,  158,  172,  158,  158,  158,
+      158,  158,  158,  158,  158,  158,  158,    0,  158,  158,
+      158,  158,  158,  158,  158,  158,  158,  158,  158,  158,
+      158,  158
     } ;
 
-static yyconst flex_int16_t yy_nxt[440] =
+static yyconst flex_int16_t yy_nxt[438] =
     {   0,
-       12,   13,   14,   13,   15,   16,   12,   17,   18,   12,
-       12,   12,   19,   12,   12,   12,   12,   20,   21,   22,
-       23,   23,   23,   23,   23,   12,   12,   23,   23,   23,
-       23,   23,   23,   23,   23,   23,   23,   23,   23,   23,
-       23,   23,   23,   12,   24,   12,   25,   34,   35,   35,
-       25,   81,   26,   26,   27,   27,   27,   34,   35,   35,
-       82,   28,   36,   36,   36,   53,   54,   29,   28,   28,
-       28,   28,   12,   13,   14,   13,   15,   16,   30,   17,
-       18,   30,   30,   30,   26,   30,   30,   30,   12,   20,
-       21,   22,   31,   31,   31,   31,   31,   32,   12,   31,
+       10,   11,   12,   11,   13,   14,   10,   15,   16,   10,
+       10,   10,   17,   10,   10,   10,   10,   18,   19,   20,
+       21,   21,   21,   21,   21,   10,   10,   21,   21,   21,
+       21,   21,   21,   21,   21,   21,   21,   21,   21,   21,
+       21,   21,   21,   10,   22,   10,   24,   25,   25,   25,
+       32,   33,   33,  157,   26,   34,   34,   34,   51,   52,
+       27,   26,   26,   26,   26,   10,   11,   12,   11,   13,
+       14,   28,   15,   16,   28,   28,   28,   24,   28,   28,
+       28,   10,   18,   19,   20,   29,   29,   29,   29,   29,
+       30,   10,   29,   29,   29,   29,   29,   29,   29,   29,
 
-       31,   31,   31,   31,   31,   31,   31,   31,   31,   31,
-       31,   31,   31,   31,   31,   12,   24,   12,   36,   36,
-       36,   39,   41,   45,   47,   56,   57,   48,   61,   47,
-       39,  159,   48,   66,   61,   45,   66,   66,   66,  158,
-       46,   40,   49,   59,   50,  157,   51,   49,   52,   50,
-       40,   63,   46,   52,   36,   36,   36,  156,   43,   62,
-       65,   65,   65,   59,  136,   68,  137,   65,   75,   69,
-       69,   69,   70,   71,   65,   65,   65,   65,   70,   71,
-       72,   69,   69,   69,   61,   46,   45,  155,  154,   66,
-       70,   71,   66,   66,   66,  122,   85,   85,   85,   59,
+       29,   29,   29,   29,   29,   29,   29,   29,   10,   22,
+       10,   23,   34,   34,   34,   37,   39,   43,   32,   33,
+       33,   45,   54,   55,   46,   59,   45,   64,  156,   46,
+       64,   64,   64,   79,   44,   38,   59,   57,  134,   47,
+      135,   48,   80,   49,   47,   50,   48,   99,   61,   43,
+       50,  110,   41,   67,   67,   67,   60,   63,   63,   63,
+       57,  155,   68,   69,   63,   37,   44,   66,   67,   67,
+       67,   63,   63,   63,   63,   73,   59,   68,   69,   70,
+       34,   34,   34,   43,   75,   38,  154,   92,   83,   83,
+       83,   64,   44,  120,   64,   64,   64,   67,   67,   67,
 
-       69,   69,   69,   46,   77,  100,  109,   93,  100,   70,
-       71,  110,  112,  122,  129,  123,  153,   85,   85,   85,
-      135,  135,  135,  148,  148,  160,  135,  135,  135,  152,
-      142,  142,  142,  123,  143,  142,  142,  142,  151,  143,
-      150,  146,  145,  149,  149,   38,   38,   38,   38,   38,
-       38,   38,   38,   42,  144,  141,  140,   42,   42,   44,
-       44,   44,   44,   44,   44,   44,   44,   58,   58,   58,
-       58,   64,  139,   64,   66,  138,  134,   66,  133,   66,
-       66,   67,  132,  131,   67,   67,   67,   67,   73,  130,
-       73,   73,   76,   76,   76,   76,   76,   76,   76,   76,
+       44,   57,   99,   68,   69,  107,   68,   69,  120,  127,
+      108,  153,  152,  121,   83,   83,   83,  133,  133,  133,
+      146,  133,  133,  133,  146,  140,  140,  140,  121,  141,
+      140,  140,  140,  151,  141,  158,  150,  149,  148,  144,
+      147,  143,  142,  139,  147,   36,   36,   36,   36,   36,
+       36,   36,   36,   40,  138,  137,  136,   40,   40,   42,
+       42,   42,   42,   42,   42,   42,   42,   56,   56,   56,
+       56,   62,  132,   62,   64,  131,  130,   64,  129,   64,
+       64,   65,  128,  158,   65,   65,   65,   65,   71,  127,
+       71,   71,   74,   74,   74,   74,   74,   74,   74,   74,
 
-       78,   78,   78,   78,   78,   78,   78,   78,   91,  160,
-       91,   92,  129,   92,   92,  128,   92,   92,  121,  121,
-      121,  121,  121,  121,  121,  121,  147,  147,  147,  147,
-      147,  147,  147,  147,  127,  126,  125,  124,   61,   61,
-      120,  119,  118,  117,  116,  115,   47,  114,  110,  113,
-      111,  108,  107,  106,   48,  105,  104,   89,  103,  102,
-      101,   99,   98,   97,   96,   95,   94,   79,   77,   90,
-       89,   88,   59,   87,   86,   59,   84,   83,   80,   79,
-       77,   74,  160,   60,   59,   55,   37,  160,   33,   25,
-       26,   25,   11,  160,  160,  160,  160,  160,  160,  160,
+       76,   76,   76,   76,   76,   76,   76,   76,   89,  126,
+       89,   90,  125,   90,   90,  124,   90,   90,  119,  119,
+      119,  119,  119,  119,  119,  119,  145,  145,  145,  145,
+      145,  145,  145,  145,  123,  122,   59,   59,  118,  117,
+      116,  115,  114,  113,   45,  112,  108,  111,  109,  106,
+      105,  104,   46,  103,   91,   87,  102,  101,  100,   98,
+       97,   96,   95,   94,   93,   77,   75,   91,   88,   87,
+       86,   57,   85,   84,   57,   82,   81,   78,   77,   75,
+       72,  158,   58,   57,   53,   35,  158,   31,   23,   23,
+        9,  158,  158,  158,  158,  158,  158,  158,  158,  158,
 
-      160,  160,  160,  160,  160,  160,  160,  160,  160,  160,
-      160,  160,  160,  160,  160,  160,  160,  160,  160,  160,
-      160,  160,  160,  160,  160,  160,  160,  160,  160,  160,
-      160,  160,  160,  160,  160,  160,  160,  160,  160
+      158,  158,  158,  158,  158,  158,  158,  158,  158,  158,
+      158,  158,  158,  158,  158,  158,  158,  158,  158,  158,
+      158,  158,  158,  158,  158,  158,  158,  158,  158,  158,
+      158,  158,  158,  158,  158,  158,  158
     } ;
 
-static yyconst flex_int16_t yy_chk[440] =
+static yyconst flex_int16_t yy_chk[438] =
     {   0,
         1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
         1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
         1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
         1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
-        1,    1,    1,    1,    1,    1,    4,    9,    9,    9,
-       10,   50,    4,    5,    5,    5,    5,   10,   10,   10,
-       50,    5,   13,   13,   13,   20,   20,    5,    5,    5,
-        5,    5,    7,    7,    7,    7,    7,    7,    7,    7,
-        7,    7,    7,    7,    7,    7,    7,    7,    7,    7,
-        7,    7,    7,    7,    7,    7,    7,    7,    7,    7,
+        1,    1,    1,    1,    1,    1,    3,    3,    3,    3,
+        7,    7,    7,  156,    3,   11,   11,   11,   18,   18,
+        3,    3,    3,    3,    3,    5,    5,    5,    5,    5,
+        5,    5,    5,    5,    5,    5,    5,    5,    5,    5,
+        5,    5,    5,    5,    5,    5,    5,    5,    5,    5,
+        5,    5,    5,    5,    5,    5,    5,    5,    5,    5,
 
-        7,    7,    7,    7,    7,    7,    7,    7,    7,    7,
-        7,    7,    7,    7,    7,    7,    7,    7,   14,   14,
-       14,   16,   17,   18,   19,   22,   22,   19,   25,   26,
-       38,  158,   26,   31,   33,   44,   31,   31,   31,  157,
-       18,   16,   19,   31,   19,  156,   19,   26,   19,   26,
-       38,   26,   44,   26,   36,   36,   36,  155,   17,   25,
-       28,   28,   28,   28,  130,   33,  130,   28,   46,   34,
-       34,   34,   91,   91,   28,   28,   28,   28,   34,   34,
-       34,   35,   35,   35,   61,   46,   75,  152,  151,   67,
-       35,   35,   67,   67,   67,  112,   61,   61,   61,   67,
+        5,    5,    5,    5,    5,    5,    5,    5,    5,    5,
+        5,    8,   12,   12,   12,   14,   15,   16,    8,    8,
+        8,   17,   20,   20,   17,   23,   24,   29,  155,   24,
+       29,   29,   29,   48,   16,   14,   31,   29,  128,   17,
+      128,   17,   48,   17,   24,   17,   24,   99,   24,   42,
+       24,   99,   15,   33,   33,   33,   23,   26,   26,   26,
+       26,  154,   33,   33,   26,   36,   42,   31,   32,   32,
+       32,   26,   26,   26,   26,   44,   59,   32,   32,   32,
+       34,   34,   34,   73,   75,   36,  153,   75,   59,   59,
+       59,   65,   44,  110,   65,   65,   65,   67,   67,   67,
 
-       69,   69,   69,   75,   77,   85,   98,   77,  100,   69,
-       69,   98,  100,  121,  129,  112,  150,   85,   85,   85,
-      135,  135,  135,  143,  147,  149,  129,  129,  129,  146,
-      138,  138,  138,  121,  138,  142,  142,  142,  145,  142,
-      144,  141,  140,  143,  147,  161,  161,  161,  161,  161,
-      161,  161,  161,  162,  139,  137,  136,  162,  162,  163,
-      163,  163,  163,  163,  163,  163,  163,  164,  164,  164,
-      164,  165,  134,  165,  166,  133,  128,  166,  127,  166,
-      166,  167,  126,  125,  167,  167,  167,  167,  168,  124,
-      168,  168,  169,  169,  169,  169,  169,  169,  169,  169,
+       73,   65,   83,   89,   89,   97,   67,   67,  119,  127,
+       97,  150,  149,  110,   83,   83,   83,  133,  133,  133,
+      141,  127,  127,  127,  145,  136,  136,  136,  119,  136,
+      140,  140,  140,  148,  140,  147,  144,  143,  142,  139,
+      141,  138,  137,  135,  145,  159,  159,  159,  159,  159,
+      159,  159,  159,  160,  134,  132,  131,  160,  160,  161,
+      161,  161,  161,  161,  161,  161,  161,  162,  162,  162,
+      162,  163,  126,  163,  164,  125,  124,  164,  123,  164,
+      164,  165,  122,  121,  165,  165,  165,  165,  166,  120,
+      166,  166,  167,  167,  167,  167,  167,  167,  167,  167,
 
-      170,  170,  170,  170,  170,  170,  170,  170,  171,  123,
-      171,  172,  122,  172,  172,  120,  172,  172,  173,  173,
-      173,  173,  173,  173,  173,  173,  174,  174,  174,  174,
-      174,  174,  174,  174,  119,  118,  117,  116,  114,  113,
-      111,  110,  109,  108,  107,  106,  105,  103,  102,  101,
-       99,   97,   96,   95,   94,   93,   92,   90,   88,   87,
-       86,   84,   83,   82,   81,   80,   79,   78,   76,   71,
-       70,   68,   65,   63,   62,   58,   52,   51,   49,   48,
-       47,   43,   40,   24,   23,   21,   15,   11,    8,    6,
-        3,    2,  160,  160,  160,  160,  160,  160,  160,  160,
+      168,  168,  168,  168,  168,  168,  168,  168,  169,  118,
+      169,  170,  117,  170,  170,  116,  170,  170,  171,  171,
+      171,  171,  171,  171,  171,  171,  172,  172,  172,  172,
+      172,  172,  172,  172,  115,  114,  112,  111,  109,  108,
+      107,  106,  105,  104,  103,  102,  101,  100,   98,   96,
+       95,   94,   93,   92,   90,   88,   86,   85,   84,   82,
+       81,   80,   79,   78,   77,   76,   74,   72,   69,   68,
+       66,   63,   61,   60,   56,   50,   49,   47,   46,   45,
+       41,   38,   22,   21,   19,   13,    9,    6,    4,    2,
+      158,  158,  158,  158,  158,  158,  158,  158,  158,  158,
 
-      160,  160,  160,  160,  160,  160,  160,  160,  160,  160,
-      160,  160,  160,  160,  160,  160,  160,  160,  160,  160,
-      160,  160,  160,  160,  160,  160,  160,  160,  160,  160,
-      160,  160,  160,  160,  160,  160,  160,  160,  160
+      158,  158,  158,  158,  158,  158,  158,  158,  158,  158,
+      158,  158,  158,  158,  158,  158,  158,  158,  158,  158,
+      158,  158,  158,  158,  158,  158,  158,  158,  158,  158,
+      158,  158,  158,  158,  158,  158,  158
     } ;
 
 static yy_state_type yy_last_accepting_state;
@@ -631,13 +632,13 @@
 
 
 
-
-#line 38 "dtc-lexer.l"
+#line 37 "dtc-lexer.l"
 #include "dtc.h"
 #include "srcpos.h"
 #include "dtc-parser.tab.h"
 
 YYLTYPE yylloc;
+extern bool treesource_error;
 
 /* CAUTION: this will stop working if we ever use yyless() or yyunput() */
 #define	YY_USER_ACTION \
@@ -659,14 +660,14 @@
 				BEGIN(V1); \
 
 static void push_input_file(const char *filename);
-static int pop_input_file(void);
-#line 664 "dtc-lexer.lex.c"
+static bool pop_input_file(void);
+static void lexical_error(const char *fmt, ...);
+#line 666 "dtc-lexer.lex.c"
 
 #define INITIAL 0
-#define INCLUDE 1
-#define BYTESTRING 2
-#define PROPNODENAME 3
-#define V1 4
+#define BYTESTRING 1
+#define PROPNODENAME 2
+#define V1 3
 
 #ifndef YY_NO_UNISTD_H
 /* Special case for "unistd.h", since it is non-ANSI. We include it way
@@ -703,7 +704,7 @@
 
 void yyset_out  (FILE * out_str  );
 
-int yyget_leng (void );
+yy_size_t yyget_leng (void );
 
 char *yyget_text (void );
 
@@ -852,10 +853,6 @@
 	register char *yy_cp, *yy_bp;
 	register int yy_act;
     
-#line 67 "dtc-lexer.l"
-
-#line 858 "dtc-lexer.lex.c"
-
 	if ( !(yy_init) )
 		{
 		(yy_init) = 1;
@@ -882,6 +879,11 @@
 		yy_load_buffer_state( );
 		}
 
+	{
+#line 68 "dtc-lexer.l"
+
+#line 886 "dtc-lexer.lex.c"
+
 	while ( 1 )		/* loops until end-of-file is reached */
 		{
 		yy_cp = (yy_c_buf_p);
@@ -899,7 +901,7 @@
 yy_match:
 		do
 			{
-			register YY_CHAR yy_c = yy_ec[YY_SC_TO_UI(*yy_cp)];
+			register YY_CHAR yy_c = yy_ec[YY_SC_TO_UI(*yy_cp)] ;
 			if ( yy_accept[yy_current_state] )
 				{
 				(yy_last_accepting_state) = yy_current_state;
@@ -908,13 +910,13 @@
 			while ( yy_chk[yy_base[yy_current_state] + yy_c] != yy_current_state )
 				{
 				yy_current_state = (int) yy_def[yy_current_state];
-				if ( yy_current_state >= 161 )
+				if ( yy_current_state >= 159 )
 					yy_c = yy_meta[(unsigned int) yy_c];
 				}
 			yy_current_state = yy_nxt[yy_base[yy_current_state] + (unsigned int) yy_c];
 			++yy_cp;
 			}
-		while ( yy_current_state != 160 );
+		while ( yy_current_state != 158 );
 		yy_cp = (yy_last_accepting_cpos);
 		yy_current_state = (yy_last_accepting_state);
 
@@ -937,7 +939,7 @@
 case 1:
 /* rule 1 can match eol */
 YY_RULE_SETUP
-#line 68 "dtc-lexer.l"
+#line 69 "dtc-lexer.l"
 {
 			char *name = strchr(yytext, '\"') + 1;
 			yytext[yyleng-1] = '\0';
@@ -947,16 +949,16 @@
 case 2:
 /* rule 2 can match eol */
 YY_RULE_SETUP
-#line 74 "dtc-lexer.l"
+#line 75 "dtc-lexer.l"
 {
 			char *line, *tmp, *fn;
 			/* skip text before line # */
 			line = yytext;
-			while (!isdigit(*line))
+			while (!isdigit((unsigned char)*line))
 				line++;
 			/* skip digits in line # */
 			tmp = line;
-			while (!isspace(*tmp))
+			while (!isspace((unsigned char)*tmp))
 				tmp++;
 			/* "NULL"-terminate line # */
 			*tmp = '\0';
@@ -970,11 +972,10 @@
 		}
 	YY_BREAK
 case YY_STATE_EOF(INITIAL):
-case YY_STATE_EOF(INCLUDE):
 case YY_STATE_EOF(BYTESTRING):
 case YY_STATE_EOF(PROPNODENAME):
 case YY_STATE_EOF(V1):
-#line 95 "dtc-lexer.l"
+#line 96 "dtc-lexer.l"
 {
 			if (!pop_input_file()) {
 				yyterminate();
@@ -984,7 +985,7 @@
 case 3:
 /* rule 3 can match eol */
 YY_RULE_SETUP
-#line 101 "dtc-lexer.l"
+#line 102 "dtc-lexer.l"
 {
 			DPRINT("String: %s\n", yytext);
 			yylval.data = data_copy_escape_string(yytext+1,
@@ -994,7 +995,7 @@
 	YY_BREAK
 case 4:
 YY_RULE_SETUP
-#line 108 "dtc-lexer.l"
+#line 109 "dtc-lexer.l"
 {
 			DPRINT("Keyword: /dts-v1/\n");
 			dts_version = 1;
@@ -1004,7 +1005,7 @@
 	YY_BREAK
 case 5:
 YY_RULE_SETUP
-#line 115 "dtc-lexer.l"
+#line 116 "dtc-lexer.l"
 {
 			DPRINT("Keyword: /memreserve/\n");
 			BEGIN_DEFAULT();
@@ -1013,7 +1014,7 @@
 	YY_BREAK
 case 6:
 YY_RULE_SETUP
-#line 121 "dtc-lexer.l"
+#line 122 "dtc-lexer.l"
 {
 			DPRINT("Keyword: /bits/\n");
 			BEGIN_DEFAULT();
@@ -1022,7 +1023,7 @@
 	YY_BREAK
 case 7:
 YY_RULE_SETUP
-#line 127 "dtc-lexer.l"
+#line 128 "dtc-lexer.l"
 {
 			DPRINT("Keyword: /delete-property/\n");
 			DPRINT("<PROPNODENAME>\n");
@@ -1032,7 +1033,7 @@
 	YY_BREAK
 case 8:
 YY_RULE_SETUP
-#line 134 "dtc-lexer.l"
+#line 135 "dtc-lexer.l"
 {
 			DPRINT("Keyword: /delete-node/\n");
 			DPRINT("<PROPNODENAME>\n");
@@ -1042,7 +1043,7 @@
 	YY_BREAK
 case 9:
 YY_RULE_SETUP
-#line 141 "dtc-lexer.l"
+#line 142 "dtc-lexer.l"
 {
 			DPRINT("Label: %s\n", yytext);
 			yylval.labelref = xstrdup(yytext);
@@ -1052,27 +1053,54 @@
 	YY_BREAK
 case 10:
 YY_RULE_SETUP
-#line 148 "dtc-lexer.l"
+#line 149 "dtc-lexer.l"
 {
-			yylval.literal = xstrdup(yytext);
-			DPRINT("Literal: '%s'\n", yylval.literal);
+			char *e;
+			DPRINT("Integer Literal: '%s'\n", yytext);
+
+			errno = 0;
+			yylval.integer = strtoull(yytext, &e, 0);
+
+			assert(!(*e) || !e[strspn(e, "UL")]);
+
+			if (errno == ERANGE)
+				lexical_error("Integer literal '%s' out of range",
+					      yytext);
+			else
+				/* ERANGE is the only strtoull error triggerable
+				 *  by strings matching the pattern */
+				assert(errno == 0);
 			return DT_LITERAL;
 		}
 	YY_BREAK
 case 11:
 /* rule 11 can match eol */
 YY_RULE_SETUP
-#line 154 "dtc-lexer.l"
+#line 168 "dtc-lexer.l"
 {
-			yytext[yyleng-1] = '\0';
-			yylval.literal = xstrdup(yytext+1);
-			DPRINT("Character literal: %s\n", yylval.literal);
+			struct data d;
+			DPRINT("Character literal: %s\n", yytext);
+
+			d = data_copy_escape_string(yytext+1, yyleng-2);
+			if (d.len == 1) {
+				lexical_error("Empty character literal");
+				yylval.integer = 0;
+				return DT_CHAR_LITERAL;
+			}
+
+			yylval.integer = (unsigned char)d.val[0];
+
+			if (d.len > 2)
+				lexical_error("Character literal has %d"
+					      " characters instead of 1",
+					      d.len - 1);
+
 			return DT_CHAR_LITERAL;
 		}
 	YY_BREAK
 case 12:
 YY_RULE_SETUP
-#line 161 "dtc-lexer.l"
+#line 189 "dtc-lexer.l"
 {	/* label reference */
 			DPRINT("Ref: %s\n", yytext+1);
 			yylval.labelref = xstrdup(yytext+1);
@@ -1081,7 +1109,7 @@
 	YY_BREAK
 case 13:
 YY_RULE_SETUP
-#line 167 "dtc-lexer.l"
+#line 195 "dtc-lexer.l"
 {	/* new-style path reference */
 			yytext[yyleng-1] = '\0';
 			DPRINT("Ref: %s\n", yytext+2);
@@ -1091,7 +1119,7 @@
 	YY_BREAK
 case 14:
 YY_RULE_SETUP
-#line 174 "dtc-lexer.l"
+#line 202 "dtc-lexer.l"
 {
 			yylval.byte = strtol(yytext, NULL, 16);
 			DPRINT("Byte: %02x\n", (int)yylval.byte);
@@ -1100,7 +1128,7 @@
 	YY_BREAK
 case 15:
 YY_RULE_SETUP
-#line 180 "dtc-lexer.l"
+#line 208 "dtc-lexer.l"
 {
 			DPRINT("/BYTESTRING\n");
 			BEGIN_DEFAULT();
@@ -1109,7 +1137,7 @@
 	YY_BREAK
 case 16:
 YY_RULE_SETUP
-#line 186 "dtc-lexer.l"
+#line 214 "dtc-lexer.l"
 {
 			DPRINT("PropNodeName: %s\n", yytext);
 			yylval.propnodename = xstrdup((yytext[0] == '\\') ?
@@ -1120,7 +1148,7 @@
 	YY_BREAK
 case 17:
 YY_RULE_SETUP
-#line 194 "dtc-lexer.l"
+#line 222 "dtc-lexer.l"
 {
 			DPRINT("Binary Include\n");
 			return DT_INCBIN;
@@ -1129,64 +1157,64 @@
 case 18:
 /* rule 18 can match eol */
 YY_RULE_SETUP
-#line 199 "dtc-lexer.l"
+#line 227 "dtc-lexer.l"
 /* eat whitespace */
 	YY_BREAK
 case 19:
 /* rule 19 can match eol */
 YY_RULE_SETUP
-#line 200 "dtc-lexer.l"
+#line 228 "dtc-lexer.l"
 /* eat C-style comments */
 	YY_BREAK
 case 20:
 /* rule 20 can match eol */
 YY_RULE_SETUP
-#line 201 "dtc-lexer.l"
+#line 229 "dtc-lexer.l"
 /* eat C++-style comments */
 	YY_BREAK
 case 21:
 YY_RULE_SETUP
-#line 203 "dtc-lexer.l"
+#line 231 "dtc-lexer.l"
 { return DT_LSHIFT; };
 	YY_BREAK
 case 22:
 YY_RULE_SETUP
-#line 204 "dtc-lexer.l"
+#line 232 "dtc-lexer.l"
 { return DT_RSHIFT; };
 	YY_BREAK
 case 23:
 YY_RULE_SETUP
-#line 205 "dtc-lexer.l"
+#line 233 "dtc-lexer.l"
 { return DT_LE; };
 	YY_BREAK
 case 24:
 YY_RULE_SETUP
-#line 206 "dtc-lexer.l"
+#line 234 "dtc-lexer.l"
 { return DT_GE; };
 	YY_BREAK
 case 25:
 YY_RULE_SETUP
-#line 207 "dtc-lexer.l"
+#line 235 "dtc-lexer.l"
 { return DT_EQ; };
 	YY_BREAK
 case 26:
 YY_RULE_SETUP
-#line 208 "dtc-lexer.l"
+#line 236 "dtc-lexer.l"
 { return DT_NE; };
 	YY_BREAK
 case 27:
 YY_RULE_SETUP
-#line 209 "dtc-lexer.l"
+#line 237 "dtc-lexer.l"
 { return DT_AND; };
 	YY_BREAK
 case 28:
 YY_RULE_SETUP
-#line 210 "dtc-lexer.l"
+#line 238 "dtc-lexer.l"
 { return DT_OR; };
 	YY_BREAK
 case 29:
 YY_RULE_SETUP
-#line 212 "dtc-lexer.l"
+#line 240 "dtc-lexer.l"
 {
 			DPRINT("Char: %c (\\x%02x)\n", yytext[0],
 				(unsigned)yytext[0]);
@@ -1204,10 +1232,10 @@
 	YY_BREAK
 case 30:
 YY_RULE_SETUP
-#line 227 "dtc-lexer.l"
+#line 255 "dtc-lexer.l"
 ECHO;
 	YY_BREAK
-#line 1211 "dtc-lexer.lex.c"
+#line 1239 "dtc-lexer.lex.c"
 
 	case YY_END_OF_BUFFER:
 		{
@@ -1337,6 +1365,7 @@
 			"fatal flex scanner internal error--no action found" );
 	} /* end of action switch */
 		} /* end of scanning one token */
+	} /* end of user's declarations */
 } /* end of yylex */
 
 /* yy_get_next_buffer - try to read in a new buffer
@@ -1392,21 +1421,21 @@
 
 	else
 		{
-			int num_to_read =
+			yy_size_t num_to_read =
 			YY_CURRENT_BUFFER_LVALUE->yy_buf_size - number_to_move - 1;
 
 		while ( num_to_read <= 0 )
 			{ /* Not enough room in the buffer - grow it. */
 
 			/* just a shorter name for the current buffer */
-			YY_BUFFER_STATE b = YY_CURRENT_BUFFER;
+			YY_BUFFER_STATE b = YY_CURRENT_BUFFER_LVALUE;
 
 			int yy_c_buf_p_offset =
 				(int) ((yy_c_buf_p) - b->yy_ch_buf);
 
 			if ( b->yy_is_our_buffer )
 				{
-				int new_size = b->yy_buf_size * 2;
+				yy_size_t new_size = b->yy_buf_size * 2;
 
 				if ( new_size <= 0 )
 					b->yy_buf_size += b->yy_buf_size / 8;
@@ -1437,7 +1466,7 @@
 
 		/* Read in more data. */
 		YY_INPUT( (&YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[number_to_move]),
-			(yy_n_chars), (size_t) num_to_read );
+			(yy_n_chars), num_to_read );
 
 		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
 		}
@@ -1499,7 +1528,7 @@
 		while ( yy_chk[yy_base[yy_current_state] + yy_c] != yy_current_state )
 			{
 			yy_current_state = (int) yy_def[yy_current_state];
-			if ( yy_current_state >= 161 )
+			if ( yy_current_state >= 159 )
 				yy_c = yy_meta[(unsigned int) yy_c];
 			}
 		yy_current_state = yy_nxt[yy_base[yy_current_state] + (unsigned int) yy_c];
@@ -1527,13 +1556,13 @@
 	while ( yy_chk[yy_base[yy_current_state] + yy_c] != yy_current_state )
 		{
 		yy_current_state = (int) yy_def[yy_current_state];
-		if ( yy_current_state >= 161 )
+		if ( yy_current_state >= 159 )
 			yy_c = yy_meta[(unsigned int) yy_c];
 		}
 	yy_current_state = yy_nxt[yy_base[yy_current_state] + (unsigned int) yy_c];
-	yy_is_jam = (yy_current_state == 160);
+	yy_is_jam = (yy_current_state == 158);
 
-	return yy_is_jam ? 0 : yy_current_state;
+		return yy_is_jam ? 0 : yy_current_state;
 }
 
 #ifndef YY_NO_INPUT
@@ -1560,7 +1589,7 @@
 
 		else
 			{ /* need more input */
-			int offset = (yy_c_buf_p) - (yytext_ptr);
+			yy_size_t offset = (yy_c_buf_p) - (yytext_ptr);
 			++(yy_c_buf_p);
 
 			switch ( yy_get_next_buffer(  ) )
@@ -1834,7 +1863,7 @@
  */
 static void yyensure_buffer_stack (void)
 {
-	int num_to_alloc;
+	yy_size_t num_to_alloc;
     
 	if (!(yy_buffer_stack)) {
 
@@ -1931,12 +1960,12 @@
  * 
  * @return the newly allocated buffer state object.
  */
-YY_BUFFER_STATE yy_scan_bytes  (yyconst char * yybytes, int  _yybytes_len )
+YY_BUFFER_STATE yy_scan_bytes  (yyconst char * yybytes, yy_size_t  _yybytes_len )
 {
 	YY_BUFFER_STATE b;
 	char *buf;
 	yy_size_t n;
-	int i;
+	yy_size_t i;
     
 	/* Get memory for full buffer, including space for trailing EOB's. */
 	n = _yybytes_len + 2;
@@ -2018,7 +2047,7 @@
 /** Get the length of the current token.
  * 
  */
-int yyget_leng  (void)
+yy_size_t yyget_leng  (void)
 {
         return yyleng;
 }
@@ -2166,7 +2195,7 @@
 
 #define YYTABLES_NAME "yytables"
 
-#line 227 "dtc-lexer.l"
+#line 254 "dtc-lexer.l"
 
 
 
@@ -2182,14 +2211,25 @@
 }
 
 
-static int pop_input_file(void)
+static bool pop_input_file(void)
 {
 	if (srcfile_pop() == 0)
-		return 0;
+		return false;
 
 	yypop_buffer_state();
 	yyin = current_srcfile->f;
 
-	return 1;
+	return true;
+}
+
+static void lexical_error(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	srcpos_verror(&yylloc, "Lexical error", fmt, ap);
+	va_end(ap);
+
+	treesource_error = true;
 }
 
diff --git a/scripts/dtc/dtc-parser.tab.c_shipped b/scripts/dtc/dtc-parser.tab.c_shipped
index c8769d5..116458c 100644
--- a/scripts/dtc/dtc-parser.tab.c_shipped
+++ b/scripts/dtc/dtc-parser.tab.c_shipped
@@ -1,19 +1,19 @@
-/* A Bison parser, made by GNU Bison 2.7.12-4996.  */
+/* A Bison parser, made by GNU Bison 3.0.2.  */
 
 /* Bison implementation for Yacc-like parsers in C
-   
-      Copyright (C) 1984, 1989-1990, 2000-2013 Free Software Foundation, Inc.
-   
+
+   Copyright (C) 1984, 1989-1990, 2000-2013 Free Software Foundation, Inc.
+
    This program is free software: you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
    the Free Software Foundation, either version 3 of the License, or
    (at your option) any later version.
-   
+
    This program is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
    GNU General Public License for more details.
-   
+
    You should have received a copy of the GNU General Public License
    along with this program.  If not, see <http://www.gnu.org/licenses/>.  */
 
@@ -26,7 +26,7 @@
    special exception, which will cause the skeleton and the resulting
    Bison output files to be licensed under the GNU General Public
    License without this special exception.
-   
+
    This special exception was added by the Free Software Foundation in
    version 2.2 of Bison.  */
 
@@ -44,7 +44,7 @@
 #define YYBISON 1
 
 /* Bison version.  */
-#define YYBISON_VERSION "2.7.12-4996"
+#define YYBISON_VERSION "3.0.2"
 
 /* Skeleton name.  */
 #define YYSKELETON_NAME "yacc.c"
@@ -62,34 +62,31 @@
 
 
 /* Copy the first part of user declarations.  */
-/* Line 371 of yacc.c  */
-#line 21 "dtc-parser.y"
+#line 20 "dtc-parser.y" /* yacc.c:339  */
 
 #include <stdio.h>
 
 #include "dtc.h"
 #include "srcpos.h"
 
-YYLTYPE yylloc;
-
 extern int yylex(void);
-extern void print_error(char const *fmt, ...);
 extern void yyerror(char const *s);
+#define ERROR(loc, ...) \
+	do { \
+		srcpos_error((loc), "Error", __VA_ARGS__); \
+		treesource_error = true; \
+	} while (0)
 
 extern struct boot_info *the_boot_info;
-extern int treesource_error;
+extern bool treesource_error;
 
-static unsigned long long eval_literal(const char *s, int base, int bits);
-static unsigned char eval_char_literal(const char *s);
+#line 84 "dtc-parser.tab.c" /* yacc.c:339  */
 
-/* Line 371 of yacc.c  */
-#line 87 "dtc-parser.tab.c"
-
-# ifndef YY_NULL
+# ifndef YY_NULLPTR
 #  if defined __cplusplus && 201103L <= __cplusplus
-#   define YY_NULL nullptr
+#   define YY_NULLPTR nullptr
 #  else
-#   define YY_NULL 0
+#   define YY_NULLPTR 0
 #  endif
 # endif
 
@@ -105,7 +102,7 @@
    by #include "dtc-parser.tab.h".  */
 #ifndef YY_YY_DTC_PARSER_TAB_H_INCLUDED
 # define YY_YY_DTC_PARSER_TAB_H_INCLUDED
-/* Enabling traces.  */
+/* Debug traces.  */
 #ifndef YYDEBUG
 # define YYDEBUG 0
 #endif
@@ -113,48 +110,44 @@
 extern int yydebug;
 #endif
 
-/* Tokens.  */
+/* Token type.  */
 #ifndef YYTOKENTYPE
 # define YYTOKENTYPE
-   /* Put the tokens into the symbol table, so that GDB and other debuggers
-      know about them.  */
-   enum yytokentype {
-     DT_V1 = 258,
-     DT_MEMRESERVE = 259,
-     DT_LSHIFT = 260,
-     DT_RSHIFT = 261,
-     DT_LE = 262,
-     DT_GE = 263,
-     DT_EQ = 264,
-     DT_NE = 265,
-     DT_AND = 266,
-     DT_OR = 267,
-     DT_BITS = 268,
-     DT_DEL_PROP = 269,
-     DT_DEL_NODE = 270,
-     DT_PROPNODENAME = 271,
-     DT_LITERAL = 272,
-     DT_CHAR_LITERAL = 273,
-     DT_BASE = 274,
-     DT_BYTE = 275,
-     DT_STRING = 276,
-     DT_LABEL = 277,
-     DT_REF = 278,
-     DT_INCBIN = 279
-   };
+  enum yytokentype
+  {
+    DT_V1 = 258,
+    DT_MEMRESERVE = 259,
+    DT_LSHIFT = 260,
+    DT_RSHIFT = 261,
+    DT_LE = 262,
+    DT_GE = 263,
+    DT_EQ = 264,
+    DT_NE = 265,
+    DT_AND = 266,
+    DT_OR = 267,
+    DT_BITS = 268,
+    DT_DEL_PROP = 269,
+    DT_DEL_NODE = 270,
+    DT_PROPNODENAME = 271,
+    DT_LITERAL = 272,
+    DT_CHAR_LITERAL = 273,
+    DT_BYTE = 274,
+    DT_STRING = 275,
+    DT_LABEL = 276,
+    DT_REF = 277,
+    DT_INCBIN = 278
+  };
 #endif
 
-
+/* Value type.  */
 #if ! defined YYSTYPE && ! defined YYSTYPE_IS_DECLARED
-typedef union YYSTYPE
+typedef union YYSTYPE YYSTYPE;
+union YYSTYPE
 {
-/* Line 387 of yacc.c  */
-#line 40 "dtc-parser.y"
+#line 38 "dtc-parser.y" /* yacc.c:355  */
 
 	char *propnodename;
-	char *literal;
 	char *labelref;
-	unsigned int cbase;
 	uint8_t byte;
 	struct data data;
 
@@ -170,37 +163,36 @@
 	struct reserve_info *re;
 	uint64_t integer;
 
-
-/* Line 387 of yacc.c  */
-#line 176 "dtc-parser.tab.c"
-} YYSTYPE;
+#line 167 "dtc-parser.tab.c" /* yacc.c:355  */
+};
 # define YYSTYPE_IS_TRIVIAL 1
-# define yystype YYSTYPE /* obsolescent; will be withdrawn */
 # define YYSTYPE_IS_DECLARED 1
 #endif
 
-extern YYSTYPE yylval;
+/* Location type.  */
+#if ! defined YYLTYPE && ! defined YYLTYPE_IS_DECLARED
+typedef struct YYLTYPE YYLTYPE;
+struct YYLTYPE
+{
+  int first_line;
+  int first_column;
+  int last_line;
+  int last_column;
+};
+# define YYLTYPE_IS_DECLARED 1
+# define YYLTYPE_IS_TRIVIAL 1
+#endif
 
-#ifdef YYPARSE_PARAM
-#if defined __STDC__ || defined __cplusplus
-int yyparse (void *YYPARSE_PARAM);
-#else
-int yyparse ();
-#endif
-#else /* ! YYPARSE_PARAM */
-#if defined __STDC__ || defined __cplusplus
+
+extern YYSTYPE yylval;
+extern YYLTYPE yylloc;
 int yyparse (void);
-#else
-int yyparse ();
-#endif
-#endif /* ! YYPARSE_PARAM */
 
 #endif /* !YY_YY_DTC_PARSER_TAB_H_INCLUDED  */
 
 /* Copy the second part of user declarations.  */
 
-/* Line 390 of yacc.c  */
-#line 204 "dtc-parser.tab.c"
+#line 196 "dtc-parser.tab.c" /* yacc.c:358  */
 
 #ifdef short
 # undef short
@@ -214,11 +206,8 @@
 
 #ifdef YYTYPE_INT8
 typedef YYTYPE_INT8 yytype_int8;
-#elif (defined __STDC__ || defined __C99__FUNC__ \
-     || defined __cplusplus || defined _MSC_VER)
-typedef signed char yytype_int8;
 #else
-typedef short int yytype_int8;
+typedef signed char yytype_int8;
 #endif
 
 #ifdef YYTYPE_UINT16
@@ -238,8 +227,7 @@
 #  define YYSIZE_T __SIZE_TYPE__
 # elif defined size_t
 #  define YYSIZE_T size_t
-# elif ! defined YYSIZE_T && (defined __STDC__ || defined __C99__FUNC__ \
-     || defined __cplusplus || defined _MSC_VER)
+# elif ! defined YYSIZE_T
 #  include <stddef.h> /* INFRINGES ON USER NAME SPACE */
 #  define YYSIZE_T size_t
 # else
@@ -261,11 +249,30 @@
 # endif
 #endif
 
-#ifndef __attribute__
-/* This feature is available in gcc versions 2.5 and later.  */
-# if (! defined __GNUC__ || __GNUC__ < 2 \
-      || (__GNUC__ == 2 && __GNUC_MINOR__ < 5))
-#  define __attribute__(Spec) /* empty */
+#ifndef YY_ATTRIBUTE
+# if (defined __GNUC__                                               \
+      && (2 < __GNUC__ || (__GNUC__ == 2 && 96 <= __GNUC_MINOR__)))  \
+     || defined __SUNPRO_C && 0x5110 <= __SUNPRO_C
+#  define YY_ATTRIBUTE(Spec) __attribute__(Spec)
+# else
+#  define YY_ATTRIBUTE(Spec) /* empty */
+# endif
+#endif
+
+#ifndef YY_ATTRIBUTE_PURE
+# define YY_ATTRIBUTE_PURE   YY_ATTRIBUTE ((__pure__))
+#endif
+
+#ifndef YY_ATTRIBUTE_UNUSED
+# define YY_ATTRIBUTE_UNUSED YY_ATTRIBUTE ((__unused__))
+#endif
+
+#if !defined _Noreturn \
+     && (!defined __STDC_VERSION__ || __STDC_VERSION__ < 201112)
+# if defined _MSC_VER && 1200 <= _MSC_VER
+#  define _Noreturn __declspec (noreturn)
+# else
+#  define _Noreturn YY_ATTRIBUTE ((__noreturn__))
 # endif
 #endif
 
@@ -276,24 +283,25 @@
 # define YYUSE(E) /* empty */
 #endif
 
+#if defined __GNUC__ && 407 <= __GNUC__ * 100 + __GNUC_MINOR__
+/* Suppress an incorrect diagnostic about yylval being uninitialized.  */
+# define YY_IGNORE_MAYBE_UNINITIALIZED_BEGIN \
+    _Pragma ("GCC diagnostic push") \
+    _Pragma ("GCC diagnostic ignored \"-Wuninitialized\"")\
+    _Pragma ("GCC diagnostic ignored \"-Wmaybe-uninitialized\"")
+# define YY_IGNORE_MAYBE_UNINITIALIZED_END \
+    _Pragma ("GCC diagnostic pop")
+#else
+# define YY_INITIAL_VALUE(Value) Value
+#endif
+#ifndef YY_IGNORE_MAYBE_UNINITIALIZED_BEGIN
+# define YY_IGNORE_MAYBE_UNINITIALIZED_BEGIN
+# define YY_IGNORE_MAYBE_UNINITIALIZED_END
+#endif
+#ifndef YY_INITIAL_VALUE
+# define YY_INITIAL_VALUE(Value) /* Nothing. */
+#endif
 
-/* Identity function, used to suppress warnings about constant conditions.  */
-#ifndef lint
-# define YYID(N) (N)
-#else
-#if (defined __STDC__ || defined __C99__FUNC__ \
-     || defined __cplusplus || defined _MSC_VER)
-static int
-YYID (int yyi)
-#else
-static int
-YYID (yyi)
-    int yyi;
-#endif
-{
-  return yyi;
-}
-#endif
 
 #if ! defined yyoverflow || YYERROR_VERBOSE
 
@@ -312,8 +320,7 @@
 #    define alloca _alloca
 #   else
 #    define YYSTACK_ALLOC alloca
-#    if ! defined _ALLOCA_H && ! defined EXIT_SUCCESS && (defined __STDC__ || defined __C99__FUNC__ \
-     || defined __cplusplus || defined _MSC_VER)
+#    if ! defined _ALLOCA_H && ! defined EXIT_SUCCESS
 #     include <stdlib.h> /* INFRINGES ON USER NAME SPACE */
       /* Use EXIT_SUCCESS as a witness for stdlib.h.  */
 #     ifndef EXIT_SUCCESS
@@ -325,8 +332,8 @@
 # endif
 
 # ifdef YYSTACK_ALLOC
-   /* Pacify GCC's `empty if-body' warning.  */
-#  define YYSTACK_FREE(Ptr) do { /* empty */; } while (YYID (0))
+   /* Pacify GCC's 'empty if-body' warning.  */
+#  define YYSTACK_FREE(Ptr) do { /* empty */; } while (0)
 #  ifndef YYSTACK_ALLOC_MAXIMUM
     /* The OS might guarantee only one guard page at the bottom of the stack,
        and a page size can be as small as 4096 bytes.  So we cannot safely
@@ -342,7 +349,7 @@
 #  endif
 #  if (defined __cplusplus && ! defined EXIT_SUCCESS \
        && ! ((defined YYMALLOC || defined malloc) \
-	     && (defined YYFREE || defined free)))
+             && (defined YYFREE || defined free)))
 #   include <stdlib.h> /* INFRINGES ON USER NAME SPACE */
 #   ifndef EXIT_SUCCESS
 #    define EXIT_SUCCESS 0
@@ -350,15 +357,13 @@
 #  endif
 #  ifndef YYMALLOC
 #   define YYMALLOC malloc
-#   if ! defined malloc && ! defined EXIT_SUCCESS && (defined __STDC__ || defined __C99__FUNC__ \
-     || defined __cplusplus || defined _MSC_VER)
+#   if ! defined malloc && ! defined EXIT_SUCCESS
 void *malloc (YYSIZE_T); /* INFRINGES ON USER NAME SPACE */
 #   endif
 #  endif
 #  ifndef YYFREE
 #   define YYFREE free
-#   if ! defined free && ! defined EXIT_SUCCESS && (defined __STDC__ || defined __C99__FUNC__ \
-     || defined __cplusplus || defined _MSC_VER)
+#   if ! defined free && ! defined EXIT_SUCCESS
 void free (void *); /* INFRINGES ON USER NAME SPACE */
 #   endif
 #  endif
@@ -368,13 +373,15 @@
 
 #if (! defined yyoverflow \
      && (! defined __cplusplus \
-	 || (defined YYSTYPE_IS_TRIVIAL && YYSTYPE_IS_TRIVIAL)))
+         || (defined YYLTYPE_IS_TRIVIAL && YYLTYPE_IS_TRIVIAL \
+             && defined YYSTYPE_IS_TRIVIAL && YYSTYPE_IS_TRIVIAL)))
 
 /* A type that is properly aligned for any stack member.  */
 union yyalloc
 {
   yytype_int16 yyss_alloc;
   YYSTYPE yyvs_alloc;
+  YYLTYPE yyls_alloc;
 };
 
 /* The size of the maximum gap between one aligned stack and the next.  */
@@ -383,8 +390,8 @@
 /* The size of an array large to enough to hold all stacks, each with
    N elements.  */
 # define YYSTACK_BYTES(N) \
-     ((N) * (sizeof (yytype_int16) + sizeof (YYSTYPE)) \
-      + YYSTACK_GAP_MAXIMUM)
+     ((N) * (sizeof (yytype_int16) + sizeof (YYSTYPE) + sizeof (YYLTYPE)) \
+      + 2 * YYSTACK_GAP_MAXIMUM)
 
 # define YYCOPY_NEEDED 1
 
@@ -393,16 +400,16 @@
    elements in the stack, and YYPTR gives the new location of the
    stack.  Advance YYPTR to a properly aligned location for the next
    stack.  */
-# define YYSTACK_RELOCATE(Stack_alloc, Stack)				\
-    do									\
-      {									\
-	YYSIZE_T yynewbytes;						\
-	YYCOPY (&yyptr->Stack_alloc, Stack, yysize);			\
-	Stack = &yyptr->Stack_alloc;					\
-	yynewbytes = yystacksize * sizeof (*Stack) + YYSTACK_GAP_MAXIMUM; \
-	yyptr += yynewbytes / sizeof (*yyptr);				\
-      }									\
-    while (YYID (0))
+# define YYSTACK_RELOCATE(Stack_alloc, Stack)                           \
+    do                                                                  \
+      {                                                                 \
+        YYSIZE_T yynewbytes;                                            \
+        YYCOPY (&yyptr->Stack_alloc, Stack, yysize);                    \
+        Stack = &yyptr->Stack_alloc;                                    \
+        yynewbytes = yystacksize * sizeof (*Stack) + YYSTACK_GAP_MAXIMUM; \
+        yyptr += yynewbytes / sizeof (*yyptr);                          \
+      }                                                                 \
+    while (0)
 
 #endif
 
@@ -421,7 +428,7 @@
           for (yyi = 0; yyi < (Count); yyi++)   \
             (Dst)[yyi] = (Src)[yyi];            \
         }                                       \
-      while (YYID (0))
+      while (0)
 #  endif
 # endif
 #endif /* !YYCOPY_NEEDED */
@@ -429,40 +436,42 @@
 /* YYFINAL -- State number of the termination state.  */
 #define YYFINAL  4
 /* YYLAST -- Last index in YYTABLE.  */
-#define YYLAST   133
+#define YYLAST   136
 
 /* YYNTOKENS -- Number of terminals.  */
-#define YYNTOKENS  48
+#define YYNTOKENS  47
 /* YYNNTS -- Number of nonterminals.  */
 #define YYNNTS  28
 /* YYNRULES -- Number of rules.  */
-#define YYNRULES  79
-/* YYNRULES -- Number of states.  */
-#define YYNSTATES  141
+#define YYNRULES  80
+/* YYNSTATES -- Number of states.  */
+#define YYNSTATES  144
 
-/* YYTRANSLATE(YYLEX) -- Bison symbol number corresponding to YYLEX.  */
+/* YYTRANSLATE[YYX] -- Symbol number corresponding to YYX as returned
+   by yylex, with out-of-bounds checking.  */
 #define YYUNDEFTOK  2
-#define YYMAXUTOK   279
+#define YYMAXUTOK   278
 
-#define YYTRANSLATE(YYX)						\
+#define YYTRANSLATE(YYX)                                                \
   ((unsigned int) (YYX) <= YYMAXUTOK ? yytranslate[YYX] : YYUNDEFTOK)
 
-/* YYTRANSLATE[YYLEX] -- Bison symbol number corresponding to YYLEX.  */
+/* YYTRANSLATE[TOKEN-NUM] -- Symbol number corresponding to TOKEN-NUM
+   as returned by yylex, without out-of-bounds checking.  */
 static const yytype_uint8 yytranslate[] =
 {
        0,     2,     2,     2,     2,     2,     2,     2,     2,     2,
        2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
        2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
-       2,     2,     2,    47,     2,     2,     2,    45,    41,     2,
-      33,    35,    44,    42,    34,    43,     2,    26,     2,     2,
-       2,     2,     2,     2,     2,     2,     2,     2,    38,    25,
-      36,    29,    30,    37,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,    46,     2,     2,     2,    44,    40,     2,
+      32,    34,    43,    41,    33,    42,     2,    25,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,    37,    24,
+      35,    28,    29,    36,     2,     2,     2,     2,     2,     2,
        2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
        2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
-       2,    31,     2,    32,    40,     2,     2,     2,     2,     2,
+       2,    30,     2,    31,    39,     2,     2,     2,     2,     2,
        2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
        2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
-       2,     2,     2,    27,    39,    28,    46,     2,     2,     2,
+       2,     2,     2,    26,    38,    27,    45,     2,     2,     2,
        2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
        2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
        2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
@@ -477,67 +486,22 @@
        2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
        2,     2,     2,     2,     2,     2,     1,     2,     3,     4,
        5,     6,     7,     8,     9,    10,    11,    12,    13,    14,
-      15,    16,    17,    18,    19,    20,    21,    22,    23,    24
+      15,    16,    17,    18,    19,    20,    21,    22,    23
 };
 
 #if YYDEBUG
-/* YYPRHS[YYN] -- Index of the first RHS symbol of rule number YYN in
-   YYRHS.  */
-static const yytype_uint16 yyprhs[] =
-{
-       0,     0,     3,     8,     9,    12,    17,    20,    23,    27,
-      31,    36,    42,    43,    46,    51,    54,    58,    61,    64,
-      68,    73,    76,    86,    92,    95,    96,    99,   102,   106,
-     108,   111,   114,   117,   119,   121,   125,   127,   129,   135,
-     137,   141,   143,   147,   149,   153,   155,   159,   161,   165,
-     167,   171,   175,   177,   181,   185,   189,   193,   197,   201,
-     203,   207,   211,   213,   217,   221,   225,   227,   229,   232,
-     235,   238,   239,   242,   245,   246,   249,   252,   255,   259
-};
-
-/* YYRHS -- A `-1'-separated list of the rules' RHS.  */
-static const yytype_int8 yyrhs[] =
-{
-      49,     0,    -1,     3,    25,    50,    52,    -1,    -1,    51,
-      50,    -1,     4,    59,    59,    25,    -1,    22,    51,    -1,
-      26,    53,    -1,    52,    26,    53,    -1,    52,    23,    53,
-      -1,    52,    15,    23,    25,    -1,    27,    54,    74,    28,
-      25,    -1,    -1,    54,    55,    -1,    16,    29,    56,    25,
-      -1,    16,    25,    -1,    14,    16,    25,    -1,    22,    55,
-      -1,    57,    21,    -1,    57,    58,    30,    -1,    57,    31,
-      73,    32,    -1,    57,    23,    -1,    57,    24,    33,    21,
-      34,    59,    34,    59,    35,    -1,    57,    24,    33,    21,
-      35,    -1,    56,    22,    -1,    -1,    56,    34,    -1,    57,
-      22,    -1,    13,    17,    36,    -1,    36,    -1,    58,    59,
-      -1,    58,    23,    -1,    58,    22,    -1,    17,    -1,    18,
-      -1,    33,    60,    35,    -1,    61,    -1,    62,    -1,    62,
-      37,    60,    38,    61,    -1,    63,    -1,    62,    12,    63,
-      -1,    64,    -1,    63,    11,    64,    -1,    65,    -1,    64,
-      39,    65,    -1,    66,    -1,    65,    40,    66,    -1,    67,
-      -1,    66,    41,    67,    -1,    68,    -1,    67,     9,    68,
-      -1,    67,    10,    68,    -1,    69,    -1,    68,    36,    69,
-      -1,    68,    30,    69,    -1,    68,     7,    69,    -1,    68,
-       8,    69,    -1,    69,     5,    70,    -1,    69,     6,    70,
-      -1,    70,    -1,    70,    42,    71,    -1,    70,    43,    71,
-      -1,    71,    -1,    71,    44,    72,    -1,    71,    26,    72,
-      -1,    71,    45,    72,    -1,    72,    -1,    59,    -1,    43,
-      72,    -1,    46,    72,    -1,    47,    72,    -1,    -1,    73,
-      20,    -1,    73,    22,    -1,    -1,    75,    74,    -1,    75,
-      55,    -1,    16,    53,    -1,    15,    16,    25,    -1,    22,
-      75,    -1
-};
-
-/* YYRLINE[YYN] -- source line where rule number YYN was defined.  */
+  /* YYRLINE[YYN] -- Source line where rule number YYN was defined.  */
 static const yytype_uint16 yyrline[] =
 {
-       0,   109,   109,   118,   121,   128,   132,   140,   144,   148,
-     158,   172,   180,   183,   190,   194,   198,   202,   210,   214,
-     218,   222,   226,   243,   253,   261,   264,   268,   275,   290,
-     295,   315,   329,   336,   340,   344,   351,   355,   356,   360,
-     361,   365,   366,   370,   371,   375,   376,   380,   381,   385,
-     386,   387,   391,   392,   393,   394,   395,   399,   400,   401,
-     405,   406,   407,   411,   412,   413,   414,   418,   419,   420,
-     421,   426,   429,   433,   441,   444,   448,   456,   460,   464
+       0,   104,   104,   113,   116,   123,   127,   135,   139,   144,
+     155,   165,   180,   188,   191,   198,   202,   206,   210,   218,
+     222,   226,   230,   234,   250,   260,   268,   271,   275,   282,
+     298,   303,   322,   336,   343,   344,   345,   352,   356,   357,
+     361,   362,   366,   367,   371,   372,   376,   377,   381,   382,
+     386,   387,   388,   392,   393,   394,   395,   396,   400,   401,
+     402,   406,   407,   408,   412,   413,   414,   415,   419,   420,
+     421,   422,   427,   430,   434,   442,   445,   449,   457,   461,
+     465
 };
 #endif
 
@@ -549,209 +513,199 @@
   "$end", "error", "$undefined", "DT_V1", "DT_MEMRESERVE", "DT_LSHIFT",
   "DT_RSHIFT", "DT_LE", "DT_GE", "DT_EQ", "DT_NE", "DT_AND", "DT_OR",
   "DT_BITS", "DT_DEL_PROP", "DT_DEL_NODE", "DT_PROPNODENAME", "DT_LITERAL",
-  "DT_CHAR_LITERAL", "DT_BASE", "DT_BYTE", "DT_STRING", "DT_LABEL",
-  "DT_REF", "DT_INCBIN", "';'", "'/'", "'{'", "'}'", "'='", "'>'", "'['",
-  "']'", "'('", "','", "')'", "'<'", "'?'", "':'", "'|'", "'^'", "'&'",
-  "'+'", "'-'", "'*'", "'%'", "'~'", "'!'", "$accept", "sourcefile",
+  "DT_CHAR_LITERAL", "DT_BYTE", "DT_STRING", "DT_LABEL", "DT_REF",
+  "DT_INCBIN", "';'", "'/'", "'{'", "'}'", "'='", "'>'", "'['", "']'",
+  "'('", "','", "')'", "'<'", "'?'", "':'", "'|'", "'^'", "'&'", "'+'",
+  "'-'", "'*'", "'%'", "'~'", "'!'", "$accept", "sourcefile",
   "memreserves", "memreserve", "devicetree", "nodedef", "proplist",
   "propdef", "propdata", "propdataprefix", "arrayprefix", "integer_prim",
   "integer_expr", "integer_trinary", "integer_or", "integer_and",
   "integer_bitor", "integer_bitxor", "integer_bitand", "integer_eq",
   "integer_rela", "integer_shift", "integer_add", "integer_mul",
-  "integer_unary", "bytestring", "subnodes", "subnode", YY_NULL
+  "integer_unary", "bytestring", "subnodes", "subnode", YY_NULLPTR
 };
 #endif
 
 # ifdef YYPRINT
-/* YYTOKNUM[YYLEX-NUM] -- Internal token number corresponding to
-   token YYLEX-NUM.  */
+/* YYTOKNUM[NUM] -- (External) token number corresponding to the
+   (internal) symbol number NUM (which must be that of a token).  */
 static const yytype_uint16 yytoknum[] =
 {
        0,   256,   257,   258,   259,   260,   261,   262,   263,   264,
      265,   266,   267,   268,   269,   270,   271,   272,   273,   274,
-     275,   276,   277,   278,   279,    59,    47,   123,   125,    61,
-      62,    91,    93,    40,    44,    41,    60,    63,    58,   124,
-      94,    38,    43,    45,    42,    37,   126,    33
+     275,   276,   277,   278,    59,    47,   123,   125,    61,    62,
+      91,    93,    40,    44,    41,    60,    63,    58,   124,    94,
+      38,    43,    45,    42,    37,   126,    33
 };
 # endif
 
-/* YYR1[YYN] -- Symbol number of symbol that rule YYN derives.  */
-static const yytype_uint8 yyr1[] =
-{
-       0,    48,    49,    50,    50,    51,    51,    52,    52,    52,
-      52,    53,    54,    54,    55,    55,    55,    55,    56,    56,
-      56,    56,    56,    56,    56,    57,    57,    57,    58,    58,
-      58,    58,    58,    59,    59,    59,    60,    61,    61,    62,
-      62,    63,    63,    64,    64,    65,    65,    66,    66,    67,
-      67,    67,    68,    68,    68,    68,    68,    69,    69,    69,
-      70,    70,    70,    71,    71,    71,    71,    72,    72,    72,
-      72,    73,    73,    73,    74,    74,    74,    75,    75,    75
-};
-
-/* YYR2[YYN] -- Number of symbols composing right hand side of rule YYN.  */
-static const yytype_uint8 yyr2[] =
-{
-       0,     2,     4,     0,     2,     4,     2,     2,     3,     3,
-       4,     5,     0,     2,     4,     2,     3,     2,     2,     3,
-       4,     2,     9,     5,     2,     0,     2,     2,     3,     1,
-       2,     2,     2,     1,     1,     3,     1,     1,     5,     1,
-       3,     1,     3,     1,     3,     1,     3,     1,     3,     1,
-       3,     3,     1,     3,     3,     3,     3,     3,     3,     1,
-       3,     3,     1,     3,     3,     3,     1,     1,     2,     2,
-       2,     0,     2,     2,     0,     2,     2,     2,     3,     2
-};
-
-/* YYDEFACT[STATE-NAME] -- Default reduction number in state STATE-NUM.
-   Performed when YYTABLE doesn't specify something else to do.  Zero
-   means the default is an error.  */
-static const yytype_uint8 yydefact[] =
-{
-       0,     0,     0,     3,     1,     0,     0,     0,     3,    33,
-      34,     0,     0,     6,     0,     2,     4,     0,     0,     0,
-      67,     0,    36,    37,    39,    41,    43,    45,    47,    49,
-      52,    59,    62,    66,     0,    12,     7,     0,     0,     0,
-      68,    69,    70,    35,     0,     0,     0,     0,     0,     0,
-       0,     0,     0,     0,     0,     0,     0,     0,     0,     0,
-       0,     0,     0,     5,    74,     0,     9,     8,    40,     0,
-      42,    44,    46,    48,    50,    51,    55,    56,    54,    53,
-      57,    58,    60,    61,    64,    63,    65,     0,     0,     0,
-       0,    13,     0,    74,    10,     0,     0,     0,    15,    25,
-      77,    17,    79,     0,    76,    75,    38,    16,    78,     0,
-       0,    11,    24,    14,    26,     0,    18,    27,    21,     0,
-      71,    29,     0,     0,     0,     0,    32,    31,    19,    30,
-      28,     0,    72,    73,    20,     0,    23,     0,     0,     0,
-      22
-};
-
-/* YYDEFGOTO[NTERM-NUM].  */
-static const yytype_int8 yydefgoto[] =
-{
-      -1,     2,     7,     8,    15,    36,    64,    91,   109,   110,
-     122,    20,    21,    22,    23,    24,    25,    26,    27,    28,
-      29,    30,    31,    32,    33,   125,    92,    93
-};
-
-/* YYPACT[STATE-NUM] -- Index in YYTABLE of the portion describing
-   STATE-NUM.  */
-#define YYPACT_NINF -78
-static const yytype_int8 yypact[] =
-{
-      22,    11,    51,    10,   -78,    23,    10,     2,    10,   -78,
-     -78,    -9,    23,   -78,    30,    38,   -78,    -9,    -9,    -9,
-     -78,    35,   -78,    -6,    52,    29,    48,    49,    33,     3,
-      71,    36,     0,   -78,    64,   -78,   -78,    68,    30,    30,
-     -78,   -78,   -78,   -78,    -9,    -9,    -9,    -9,    -9,    -9,
-      -9,    -9,    -9,    -9,    -9,    -9,    -9,    -9,    -9,    -9,
-      -9,    -9,    -9,   -78,    44,    67,   -78,   -78,    52,    55,
-      29,    48,    49,    33,     3,     3,    71,    71,    71,    71,
-      36,    36,     0,     0,   -78,   -78,   -78,    78,    79,    42,
-      44,   -78,    69,    44,   -78,    -9,    73,    74,   -78,   -78,
-     -78,   -78,   -78,    75,   -78,   -78,   -78,   -78,   -78,    -7,
-      -1,   -78,   -78,   -78,   -78,    84,   -78,   -78,   -78,    63,
-     -78,   -78,    32,    66,    82,    -3,   -78,   -78,   -78,   -78,
-     -78,    46,   -78,   -78,   -78,    23,   -78,    70,    23,    72,
-     -78
-};
-
-/* YYPGOTO[NTERM-NUM].  */
-static const yytype_int8 yypgoto[] =
-{
-     -78,   -78,    97,   100,   -78,   -37,   -78,   -77,   -78,   -78,
-     -78,    -5,    65,    13,   -78,    76,    77,    62,    80,    83,
-      34,    20,    26,    28,   -14,   -78,    18,    24
-};
-
-/* YYTABLE[YYPACT[STATE-NUM]].  What to do in state STATE-NUM.  If
-   positive, shift that token.  If negative, reduce the rule which
-   number is the opposite.  If YYTABLE_NINF, syntax error.  */
-#define YYTABLE_NINF -1
-static const yytype_uint8 yytable[] =
-{
-      12,    66,    67,    40,    41,    42,    44,    34,     9,    10,
-      52,    53,   115,   101,     5,   112,   104,   132,   113,   133,
-     116,   117,   118,   119,    11,     1,    60,   114,    14,   134,
-     120,    45,     6,    54,    17,   121,     3,    18,    19,    55,
-       9,    10,    50,    51,    61,    62,    84,    85,    86,     9,
-      10,     4,   100,    37,   126,   127,    11,    35,    87,    88,
-      89,    38,   128,    46,    39,    11,    90,    98,    47,    35,
-      43,    99,    76,    77,    78,    79,    56,    57,    58,    59,
-     135,   136,    80,    81,    74,    75,    82,    83,    48,    63,
-      49,    65,    94,    95,    96,    97,   124,   103,   107,   108,
-     111,   123,   130,   131,   138,    16,    13,   140,   106,    71,
-      69,   105,     0,     0,   102,     0,     0,   129,     0,     0,
-      68,     0,     0,    70,     0,     0,     0,     0,    72,     0,
-     137,     0,    73,   139
-};
+#define YYPACT_NINF -81
 
 #define yypact_value_is_default(Yystate) \
-  (!!((Yystate) == (-78)))
+  (!!((Yystate) == (-81)))
+
+#define YYTABLE_NINF -1
 
 #define yytable_value_is_error(Yytable_value) \
-  YYID (0)
+  0
+
+  /* YYPACT[STATE-NUM] -- Index in YYTABLE of the portion describing
+     STATE-NUM.  */
+static const yytype_int8 yypact[] =
+{
+      16,   -11,    21,    10,   -81,    25,    10,    19,    10,   -81,
+     -81,    -9,    25,   -81,     2,    51,   -81,    -9,    -9,    -9,
+     -81,     1,   -81,    -6,    50,    14,    28,    29,    36,     3,
+      58,    44,    -3,   -81,    47,   -81,   -81,    65,    68,     2,
+       2,   -81,   -81,   -81,   -81,    -9,    -9,    -9,    -9,    -9,
+      -9,    -9,    -9,    -9,    -9,    -9,    -9,    -9,    -9,    -9,
+      -9,    -9,    -9,    -9,   -81,    63,    69,     2,   -81,   -81,
+      50,    57,    14,    28,    29,    36,     3,     3,    58,    58,
+      58,    58,    44,    44,    -3,    -3,   -81,   -81,   -81,    79,
+      80,    -8,    63,   -81,    72,    63,   -81,   -81,    -9,    76,
+      77,   -81,   -81,   -81,   -81,   -81,    78,   -81,   -81,   -81,
+     -81,   -81,    35,     4,   -81,   -81,   -81,   -81,    86,   -81,
+     -81,   -81,    73,   -81,   -81,    33,    71,    84,    39,   -81,
+     -81,   -81,   -81,   -81,    41,   -81,   -81,   -81,    25,   -81,
+      74,    25,    75,   -81
+};
+
+  /* YYDEFACT[STATE-NUM] -- Default reduction number in state STATE-NUM.
+     Performed when YYTABLE does not specify something else to do.  Zero
+     means the default is an error.  */
+static const yytype_uint8 yydefact[] =
+{
+       0,     0,     0,     3,     1,     0,     0,     0,     3,    34,
+      35,     0,     0,     6,     0,     2,     4,     0,     0,     0,
+      68,     0,    37,    38,    40,    42,    44,    46,    48,    50,
+      53,    60,    63,    67,     0,    13,     7,     0,     0,     0,
+       0,    69,    70,    71,    36,     0,     0,     0,     0,     0,
+       0,     0,     0,     0,     0,     0,     0,     0,     0,     0,
+       0,     0,     0,     0,     5,    75,     0,     0,    10,     8,
+      41,     0,    43,    45,    47,    49,    51,    52,    56,    57,
+      55,    54,    58,    59,    61,    62,    65,    64,    66,     0,
+       0,     0,     0,    14,     0,    75,    11,     9,     0,     0,
+       0,    16,    26,    78,    18,    80,     0,    77,    76,    39,
+      17,    79,     0,     0,    12,    25,    15,    27,     0,    19,
+      28,    22,     0,    72,    30,     0,     0,     0,     0,    33,
+      32,    20,    31,    29,     0,    73,    74,    21,     0,    24,
+       0,     0,     0,    23
+};
+
+  /* YYPGOTO[NTERM-NUM].  */
+static const yytype_int8 yypgoto[] =
+{
+     -81,   -81,   100,   104,   -81,   -38,   -81,   -80,   -81,   -81,
+     -81,    -5,    66,    13,   -81,    70,    67,    81,    64,    82,
+      37,    27,    34,    38,   -14,   -81,    22,    24
+};
+
+  /* YYDEFGOTO[NTERM-NUM].  */
+static const yytype_int16 yydefgoto[] =
+{
+      -1,     2,     7,     8,    15,    36,    65,    93,   112,   113,
+     125,    20,    21,    22,    23,    24,    25,    26,    27,    28,
+      29,    30,    31,    32,    33,   128,    94,    95
+};
+
+  /* YYTABLE[YYPACT[STATE-NUM]] -- What to do in state STATE-NUM.  If
+     positive, shift that token.  If negative, reduce the rule whose
+     number is the opposite.  If YYTABLE_NINF, syntax error.  */
+static const yytype_uint8 yytable[] =
+{
+      12,    68,    69,    41,    42,    43,    45,    34,     9,    10,
+      53,    54,   104,     3,     5,   107,   101,   118,    35,     1,
+     102,     4,    61,    11,   119,   120,   121,   122,    35,    97,
+      46,     6,    55,    17,   123,    44,    18,    19,    56,   124,
+      62,    63,     9,    10,    14,    51,    52,    86,    87,    88,
+       9,    10,    48,   103,   129,   130,   115,    11,   135,   116,
+     136,    47,   131,    57,    58,    11,    37,    49,   117,    50,
+     137,    64,    38,    39,   138,   139,    40,    89,    90,    91,
+      78,    79,    80,    81,    92,    59,    60,    66,    76,    77,
+      67,    82,    83,    96,    98,    99,   100,    84,    85,   106,
+     110,   111,   114,   126,   134,   127,   133,   141,    16,   143,
+      13,   109,    71,    74,    72,    70,   105,   108,     0,     0,
+     132,     0,     0,     0,     0,     0,     0,     0,     0,    73,
+       0,     0,    75,   140,     0,     0,   142
+};
 
 static const yytype_int16 yycheck[] =
 {
-       5,    38,    39,    17,    18,    19,    12,    12,    17,    18,
-       7,     8,    13,    90,     4,    22,    93,    20,    25,    22,
-      21,    22,    23,    24,    33,     3,    26,    34,    26,    32,
-      31,    37,    22,    30,    43,    36,    25,    46,    47,    36,
-      17,    18,     9,    10,    44,    45,    60,    61,    62,    17,
-      18,     0,    89,    15,    22,    23,    33,    27,    14,    15,
-      16,    23,    30,    11,    26,    33,    22,    25,    39,    27,
-      35,    29,    52,    53,    54,    55,     5,     6,    42,    43,
-      34,    35,    56,    57,    50,    51,    58,    59,    40,    25,
-      41,    23,    25,    38,    16,    16,    33,    28,    25,    25,
-      25,    17,    36,    21,    34,     8,     6,    35,    95,    47,
-      45,    93,    -1,    -1,    90,    -1,    -1,   122,    -1,    -1,
-      44,    -1,    -1,    46,    -1,    -1,    -1,    -1,    48,    -1,
-     135,    -1,    49,   138
+       5,    39,    40,    17,    18,    19,    12,    12,    17,    18,
+       7,     8,    92,    24,     4,    95,    24,    13,    26,     3,
+      28,     0,    25,    32,    20,    21,    22,    23,    26,    67,
+      36,    21,    29,    42,    30,    34,    45,    46,    35,    35,
+      43,    44,    17,    18,    25,     9,    10,    61,    62,    63,
+      17,    18,    38,    91,    21,    22,    21,    32,    19,    24,
+      21,    11,    29,     5,     6,    32,    15,    39,    33,    40,
+      31,    24,    21,    22,    33,    34,    25,    14,    15,    16,
+      53,    54,    55,    56,    21,    41,    42,    22,    51,    52,
+      22,    57,    58,    24,    37,    16,    16,    59,    60,    27,
+      24,    24,    24,    17,    20,    32,    35,    33,     8,    34,
+       6,    98,    46,    49,    47,    45,    92,    95,    -1,    -1,
+     125,    -1,    -1,    -1,    -1,    -1,    -1,    -1,    -1,    48,
+      -1,    -1,    50,   138,    -1,    -1,   141
 };
 
-/* YYSTOS[STATE-NUM] -- The (internal number of the) accessing
-   symbol of state STATE-NUM.  */
+  /* YYSTOS[STATE-NUM] -- The (internal number of the) accessing
+     symbol of state STATE-NUM.  */
 static const yytype_uint8 yystos[] =
 {
-       0,     3,    49,    25,     0,     4,    22,    50,    51,    17,
-      18,    33,    59,    51,    26,    52,    50,    43,    46,    47,
-      59,    60,    61,    62,    63,    64,    65,    66,    67,    68,
-      69,    70,    71,    72,    59,    27,    53,    15,    23,    26,
-      72,    72,    72,    35,    12,    37,    11,    39,    40,    41,
-       9,    10,     7,     8,    30,    36,     5,     6,    42,    43,
-      26,    44,    45,    25,    54,    23,    53,    53,    63,    60,
-      64,    65,    66,    67,    68,    68,    69,    69,    69,    69,
-      70,    70,    71,    71,    72,    72,    72,    14,    15,    16,
-      22,    55,    74,    75,    25,    38,    16,    16,    25,    29,
-      53,    55,    75,    28,    55,    74,    61,    25,    25,    56,
-      57,    25,    22,    25,    34,    13,    21,    22,    23,    24,
-      31,    36,    58,    17,    33,    73,    22,    23,    30,    59,
-      36,    21,    20,    22,    32,    34,    35,    59,    34,    59,
-      35
+       0,     3,    48,    24,     0,     4,    21,    49,    50,    17,
+      18,    32,    58,    50,    25,    51,    49,    42,    45,    46,
+      58,    59,    60,    61,    62,    63,    64,    65,    66,    67,
+      68,    69,    70,    71,    58,    26,    52,    15,    21,    22,
+      25,    71,    71,    71,    34,    12,    36,    11,    38,    39,
+      40,     9,    10,     7,     8,    29,    35,     5,     6,    41,
+      42,    25,    43,    44,    24,    53,    22,    22,    52,    52,
+      62,    59,    63,    64,    65,    66,    67,    67,    68,    68,
+      68,    68,    69,    69,    70,    70,    71,    71,    71,    14,
+      15,    16,    21,    54,    73,    74,    24,    52,    37,    16,
+      16,    24,    28,    52,    54,    74,    27,    54,    73,    60,
+      24,    24,    55,    56,    24,    21,    24,    33,    13,    20,
+      21,    22,    23,    30,    35,    57,    17,    32,    72,    21,
+      22,    29,    58,    35,    20,    19,    21,    31,    33,    34,
+      58,    33,    58,    34
 };
 
-#define yyerrok		(yyerrstatus = 0)
-#define yyclearin	(yychar = YYEMPTY)
-#define YYEMPTY		(-2)
-#define YYEOF		0
+  /* YYR1[YYN] -- Symbol number of symbol that rule YYN derives.  */
+static const yytype_uint8 yyr1[] =
+{
+       0,    47,    48,    49,    49,    50,    50,    51,    51,    51,
+      51,    51,    52,    53,    53,    54,    54,    54,    54,    55,
+      55,    55,    55,    55,    55,    55,    56,    56,    56,    57,
+      57,    57,    57,    57,    58,    58,    58,    59,    60,    60,
+      61,    61,    62,    62,    63,    63,    64,    64,    65,    65,
+      66,    66,    66,    67,    67,    67,    67,    67,    68,    68,
+      68,    69,    69,    69,    70,    70,    70,    70,    71,    71,
+      71,    71,    72,    72,    72,    73,    73,    73,    74,    74,
+      74
+};
 
-#define YYACCEPT	goto yyacceptlab
-#define YYABORT		goto yyabortlab
-#define YYERROR		goto yyerrorlab
+  /* YYR2[YYN] -- Number of symbols on the right hand side of rule YYN.  */
+static const yytype_uint8 yyr2[] =
+{
+       0,     2,     4,     0,     2,     4,     2,     2,     3,     4,
+       3,     4,     5,     0,     2,     4,     2,     3,     2,     2,
+       3,     4,     2,     9,     5,     2,     0,     2,     2,     3,
+       1,     2,     2,     2,     1,     1,     3,     1,     1,     5,
+       1,     3,     1,     3,     1,     3,     1,     3,     1,     3,
+       1,     3,     3,     1,     3,     3,     3,     3,     3,     3,
+       1,     3,     3,     1,     3,     3,     3,     1,     1,     2,
+       2,     2,     0,     2,     2,     0,     2,     2,     2,     3,
+       2
+};
 
 
-/* Like YYERROR except do call yyerror.  This remains here temporarily
-   to ease the transition to the new meaning of YYERROR, for GCC.
-   Once GCC version 2 has supplanted version 1, this can go.  However,
-   YYFAIL appears to be in use.  Nevertheless, it is formally deprecated
-   in Bison 2.4.2's NEWS entry, where a plan to phase it out is
-   discussed.  */
+#define yyerrok         (yyerrstatus = 0)
+#define yyclearin       (yychar = YYEMPTY)
+#define YYEMPTY         (-2)
+#define YYEOF           0
 
-#define YYFAIL		goto yyerrlab
-#if defined YYFAIL
-  /* This is here to suppress warnings from the GCC cpp's
-     -Wunused-macros.  Normally we don't worry about that warning, but
-     some users do, and we want to make it easy for users to remove
-     YYFAIL uses, which will produce warnings from Bison 2.5.  */
-#endif
+#define YYACCEPT        goto yyacceptlab
+#define YYABORT         goto yyabortlab
+#define YYERROR         goto yyerrorlab
+
 
 #define YYRECOVERING()  (!!yyerrstatus)
 
@@ -768,27 +722,41 @@
   else                                                          \
     {                                                           \
       yyerror (YY_("syntax error: cannot back up")); \
-      YYERROR;							\
-    }								\
-while (YYID (0))
+      YYERROR;                                                  \
+    }                                                           \
+while (0)
 
 /* Error token number */
-#define YYTERROR	1
-#define YYERRCODE	256
+#define YYTERROR        1
+#define YYERRCODE       256
 
 
-/* This macro is provided for backward compatibility. */
-#ifndef YY_LOCATION_PRINT
-# define YY_LOCATION_PRINT(File, Loc) ((void) 0)
+/* YYLLOC_DEFAULT -- Set CURRENT to span from RHS[1] to RHS[N].
+   If N is 0, then set CURRENT to the empty location which ends
+   the previous symbol: RHS[0] (always defined).  */
+
+#ifndef YYLLOC_DEFAULT
+# define YYLLOC_DEFAULT(Current, Rhs, N)                                \
+    do                                                                  \
+      if (N)                                                            \
+        {                                                               \
+          (Current).first_line   = YYRHSLOC (Rhs, 1).first_line;        \
+          (Current).first_column = YYRHSLOC (Rhs, 1).first_column;      \
+          (Current).last_line    = YYRHSLOC (Rhs, N).last_line;         \
+          (Current).last_column  = YYRHSLOC (Rhs, N).last_column;       \
+        }                                                               \
+      else                                                              \
+        {                                                               \
+          (Current).first_line   = (Current).last_line   =              \
+            YYRHSLOC (Rhs, 0).last_line;                                \
+          (Current).first_column = (Current).last_column =              \
+            YYRHSLOC (Rhs, 0).last_column;                              \
+        }                                                               \
+    while (0)
 #endif
 
+#define YYRHSLOC(Rhs, K) ((Rhs)[K])
 
-/* YYLEX -- calling `yylex' with the right arguments.  */
-#ifdef YYLEX_PARAM
-# define YYLEX yylex (YYLEX_PARAM)
-#else
-# define YYLEX yylex ()
-#endif
 
 /* Enable debugging if requested.  */
 #if YYDEBUG
@@ -798,50 +766,84 @@
 #  define YYFPRINTF fprintf
 # endif
 
-# define YYDPRINTF(Args)			\
-do {						\
-  if (yydebug)					\
-    YYFPRINTF Args;				\
-} while (YYID (0))
-
-# define YY_SYMBOL_PRINT(Title, Type, Value, Location)			  \
-do {									  \
-  if (yydebug)								  \
-    {									  \
-      YYFPRINTF (stderr, "%s ", Title);					  \
-      yy_symbol_print (stderr,						  \
-		  Type, Value); \
-      YYFPRINTF (stderr, "\n");						  \
-    }									  \
-} while (YYID (0))
+# define YYDPRINTF(Args)                        \
+do {                                            \
+  if (yydebug)                                  \
+    YYFPRINTF Args;                             \
+} while (0)
 
 
-/*--------------------------------.
-| Print this symbol on YYOUTPUT.  |
-`--------------------------------*/
+/* YY_LOCATION_PRINT -- Print the location on the stream.
+   This macro was not mandated originally: define only if we know
+   we won't break user code: when these are the locations we know.  */
 
-/*ARGSUSED*/
-#if (defined __STDC__ || defined __C99__FUNC__ \
-     || defined __cplusplus || defined _MSC_VER)
-static void
-yy_symbol_value_print (FILE *yyoutput, int yytype, YYSTYPE const * const yyvaluep)
-#else
-static void
-yy_symbol_value_print (yyoutput, yytype, yyvaluep)
-    FILE *yyoutput;
-    int yytype;
-    YYSTYPE const * const yyvaluep;
+#ifndef YY_LOCATION_PRINT
+# if defined YYLTYPE_IS_TRIVIAL && YYLTYPE_IS_TRIVIAL
+
+/* Print *YYLOCP on YYO.  Private, do not rely on its existence. */
+
+YY_ATTRIBUTE_UNUSED
+static unsigned
+yy_location_print_ (FILE *yyo, YYLTYPE const * const yylocp)
+{
+  unsigned res = 0;
+  int end_col = 0 != yylocp->last_column ? yylocp->last_column - 1 : 0;
+  if (0 <= yylocp->first_line)
+    {
+      res += YYFPRINTF (yyo, "%d", yylocp->first_line);
+      if (0 <= yylocp->first_column)
+        res += YYFPRINTF (yyo, ".%d", yylocp->first_column);
+    }
+  if (0 <= yylocp->last_line)
+    {
+      if (yylocp->first_line < yylocp->last_line)
+        {
+          res += YYFPRINTF (yyo, "-%d", yylocp->last_line);
+          if (0 <= end_col)
+            res += YYFPRINTF (yyo, ".%d", end_col);
+        }
+      else if (0 <= end_col && yylocp->first_column < end_col)
+        res += YYFPRINTF (yyo, "-%d", end_col);
+    }
+  return res;
+ }
+
+#  define YY_LOCATION_PRINT(File, Loc)          \
+  yy_location_print_ (File, &(Loc))
+
+# else
+#  define YY_LOCATION_PRINT(File, Loc) ((void) 0)
+# endif
 #endif
+
+
+# define YY_SYMBOL_PRINT(Title, Type, Value, Location)                    \
+do {                                                                      \
+  if (yydebug)                                                            \
+    {                                                                     \
+      YYFPRINTF (stderr, "%s ", Title);                                   \
+      yy_symbol_print (stderr,                                            \
+                  Type, Value, Location); \
+      YYFPRINTF (stderr, "\n");                                           \
+    }                                                                     \
+} while (0)
+
+
+/*----------------------------------------.
+| Print this symbol's value on YYOUTPUT.  |
+`----------------------------------------*/
+
+static void
+yy_symbol_value_print (FILE *yyoutput, int yytype, YYSTYPE const * const yyvaluep, YYLTYPE const * const yylocationp)
 {
   FILE *yyo = yyoutput;
   YYUSE (yyo);
+  YYUSE (yylocationp);
   if (!yyvaluep)
     return;
 # ifdef YYPRINT
   if (yytype < YYNTOKENS)
     YYPRINT (yyoutput, yytoknum[yytype], *yyvaluep);
-# else
-  YYUSE (yyoutput);
 # endif
   YYUSE (yytype);
 }
@@ -851,24 +853,15 @@
 | Print this symbol on YYOUTPUT.  |
 `--------------------------------*/
 
-#if (defined __STDC__ || defined __C99__FUNC__ \
-     || defined __cplusplus || defined _MSC_VER)
 static void
-yy_symbol_print (FILE *yyoutput, int yytype, YYSTYPE const * const yyvaluep)
-#else
-static void
-yy_symbol_print (yyoutput, yytype, yyvaluep)
-    FILE *yyoutput;
-    int yytype;
-    YYSTYPE const * const yyvaluep;
-#endif
+yy_symbol_print (FILE *yyoutput, int yytype, YYSTYPE const * const yyvaluep, YYLTYPE const * const yylocationp)
 {
-  if (yytype < YYNTOKENS)
-    YYFPRINTF (yyoutput, "token %s (", yytname[yytype]);
-  else
-    YYFPRINTF (yyoutput, "nterm %s (", yytname[yytype]);
+  YYFPRINTF (yyoutput, "%s %s (",
+             yytype < YYNTOKENS ? "token" : "nterm", yytname[yytype]);
 
-  yy_symbol_value_print (yyoutput, yytype, yyvaluep);
+  YY_LOCATION_PRINT (yyoutput, *yylocationp);
+  YYFPRINTF (yyoutput, ": ");
+  yy_symbol_value_print (yyoutput, yytype, yyvaluep, yylocationp);
   YYFPRINTF (yyoutput, ")");
 }
 
@@ -877,16 +870,8 @@
 | TOP (included).                                                   |
 `------------------------------------------------------------------*/
 
-#if (defined __STDC__ || defined __C99__FUNC__ \
-     || defined __cplusplus || defined _MSC_VER)
 static void
 yy_stack_print (yytype_int16 *yybottom, yytype_int16 *yytop)
-#else
-static void
-yy_stack_print (yybottom, yytop)
-    yytype_int16 *yybottom;
-    yytype_int16 *yytop;
-#endif
 {
   YYFPRINTF (stderr, "Stack now");
   for (; yybottom <= yytop; yybottom++)
@@ -897,49 +882,42 @@
   YYFPRINTF (stderr, "\n");
 }
 
-# define YY_STACK_PRINT(Bottom, Top)				\
-do {								\
-  if (yydebug)							\
-    yy_stack_print ((Bottom), (Top));				\
-} while (YYID (0))
+# define YY_STACK_PRINT(Bottom, Top)                            \
+do {                                                            \
+  if (yydebug)                                                  \
+    yy_stack_print ((Bottom), (Top));                           \
+} while (0)
 
 
 /*------------------------------------------------.
 | Report that the YYRULE is going to be reduced.  |
 `------------------------------------------------*/
 
-#if (defined __STDC__ || defined __C99__FUNC__ \
-     || defined __cplusplus || defined _MSC_VER)
 static void
-yy_reduce_print (YYSTYPE *yyvsp, int yyrule)
-#else
-static void
-yy_reduce_print (yyvsp, yyrule)
-    YYSTYPE *yyvsp;
-    int yyrule;
-#endif
+yy_reduce_print (yytype_int16 *yyssp, YYSTYPE *yyvsp, YYLTYPE *yylsp, int yyrule)
 {
+  unsigned long int yylno = yyrline[yyrule];
   int yynrhs = yyr2[yyrule];
   int yyi;
-  unsigned long int yylno = yyrline[yyrule];
   YYFPRINTF (stderr, "Reducing stack by rule %d (line %lu):\n",
-	     yyrule - 1, yylno);
+             yyrule - 1, yylno);
   /* The symbols being reduced.  */
   for (yyi = 0; yyi < yynrhs; yyi++)
     {
       YYFPRINTF (stderr, "   $%d = ", yyi + 1);
-      yy_symbol_print (stderr, yyrhs[yyprhs[yyrule] + yyi],
-		       &(yyvsp[(yyi + 1) - (yynrhs)])
-		       		       );
+      yy_symbol_print (stderr,
+                       yystos[yyssp[yyi + 1 - yynrhs]],
+                       &(yyvsp[(yyi + 1) - (yynrhs)])
+                       , &(yylsp[(yyi + 1) - (yynrhs)])                       );
       YYFPRINTF (stderr, "\n");
     }
 }
 
-# define YY_REDUCE_PRINT(Rule)		\
-do {					\
-  if (yydebug)				\
-    yy_reduce_print (yyvsp, Rule); \
-} while (YYID (0))
+# define YY_REDUCE_PRINT(Rule)          \
+do {                                    \
+  if (yydebug)                          \
+    yy_reduce_print (yyssp, yyvsp, yylsp, Rule); \
+} while (0)
 
 /* Nonzero means print parse trace.  It is left uninitialized so that
    multiple parsers can coexist.  */
@@ -953,7 +931,7 @@
 
 
 /* YYINITDEPTH -- initial size of the parser's stacks.  */
-#ifndef	YYINITDEPTH
+#ifndef YYINITDEPTH
 # define YYINITDEPTH 200
 #endif
 
@@ -976,15 +954,8 @@
 #   define yystrlen strlen
 #  else
 /* Return the length of YYSTR.  */
-#if (defined __STDC__ || defined __C99__FUNC__ \
-     || defined __cplusplus || defined _MSC_VER)
 static YYSIZE_T
 yystrlen (const char *yystr)
-#else
-static YYSIZE_T
-yystrlen (yystr)
-    const char *yystr;
-#endif
 {
   YYSIZE_T yylen;
   for (yylen = 0; yystr[yylen]; yylen++)
@@ -1000,16 +971,8 @@
 #  else
 /* Copy YYSRC to YYDEST, returning the address of the terminating '\0' in
    YYDEST.  */
-#if (defined __STDC__ || defined __C99__FUNC__ \
-     || defined __cplusplus || defined _MSC_VER)
 static char *
 yystpcpy (char *yydest, const char *yysrc)
-#else
-static char *
-yystpcpy (yydest, yysrc)
-    char *yydest;
-    const char *yysrc;
-#endif
 {
   char *yyd = yydest;
   const char *yys = yysrc;
@@ -1039,27 +1002,27 @@
       char const *yyp = yystr;
 
       for (;;)
-	switch (*++yyp)
-	  {
-	  case '\'':
-	  case ',':
-	    goto do_not_strip_quotes;
+        switch (*++yyp)
+          {
+          case '\'':
+          case ',':
+            goto do_not_strip_quotes;
 
-	  case '\\':
-	    if (*++yyp != '\\')
-	      goto do_not_strip_quotes;
-	    /* Fall through.  */
-	  default:
-	    if (yyres)
-	      yyres[yyn] = *yyp;
-	    yyn++;
-	    break;
+          case '\\':
+            if (*++yyp != '\\')
+              goto do_not_strip_quotes;
+            /* Fall through.  */
+          default:
+            if (yyres)
+              yyres[yyn] = *yyp;
+            yyn++;
+            break;
 
-	  case '"':
-	    if (yyres)
-	      yyres[yyn] = '\0';
-	    return yyn;
-	  }
+          case '"':
+            if (yyres)
+              yyres[yyn] = '\0';
+            return yyn;
+          }
     do_not_strip_quotes: ;
     }
 
@@ -1082,11 +1045,11 @@
 yysyntax_error (YYSIZE_T *yymsg_alloc, char **yymsg,
                 yytype_int16 *yyssp, int yytoken)
 {
-  YYSIZE_T yysize0 = yytnamerr (YY_NULL, yytname[yytoken]);
+  YYSIZE_T yysize0 = yytnamerr (YY_NULLPTR, yytname[yytoken]);
   YYSIZE_T yysize = yysize0;
   enum { YYERROR_VERBOSE_ARGS_MAXIMUM = 5 };
   /* Internationalized format string. */
-  const char *yyformat = YY_NULL;
+  const char *yyformat = YY_NULLPTR;
   /* Arguments of yyformat. */
   char const *yyarg[YYERROR_VERBOSE_ARGS_MAXIMUM];
   /* Number of reported tokens (one for the "unexpected", one per
@@ -1094,10 +1057,6 @@
   int yycount = 0;
 
   /* There are many possibilities here to consider:
-     - Assume YYFAIL is not used.  It's too flawed to consider.  See
-       <http://lists.gnu.org/archive/html/bison-patches/2009-12/msg00024.html>
-       for details.  YYERROR is fine as it does not invoke this
-       function.
      - If this state is a consistent state with a default action, then
        the only way this function was invoked is if the default action
        is an error action.  In that case, don't check for expected
@@ -1147,7 +1106,7 @@
                   }
                 yyarg[yycount++] = yytname[yyx];
                 {
-                  YYSIZE_T yysize1 = yysize + yytnamerr (YY_NULL, yytname[yyx]);
+                  YYSIZE_T yysize1 = yysize + yytnamerr (YY_NULLPTR, yytname[yyx]);
                   if (! (yysize <= yysize1
                          && yysize1 <= YYSTACK_ALLOC_MAXIMUM))
                     return 2;
@@ -1214,26 +1173,18 @@
 | Release the memory associated to this symbol.  |
 `-----------------------------------------------*/
 
-/*ARGSUSED*/
-#if (defined __STDC__ || defined __C99__FUNC__ \
-     || defined __cplusplus || defined _MSC_VER)
 static void
-yydestruct (const char *yymsg, int yytype, YYSTYPE *yyvaluep)
-#else
-static void
-yydestruct (yymsg, yytype, yyvaluep)
-    const char *yymsg;
-    int yytype;
-    YYSTYPE *yyvaluep;
-#endif
+yydestruct (const char *yymsg, int yytype, YYSTYPE *yyvaluep, YYLTYPE *yylocationp)
 {
   YYUSE (yyvaluep);
-
+  YYUSE (yylocationp);
   if (!yymsg)
     yymsg = "Deleting";
   YY_SYMBOL_PRINT (yymsg, yytype, yyvaluep, yylocationp);
 
+  YY_IGNORE_MAYBE_UNINITIALIZED_BEGIN
   YYUSE (yytype);
+  YY_IGNORE_MAYBE_UNINITIALIZED_END
 }
 
 
@@ -1242,18 +1193,14 @@
 /* The lookahead symbol.  */
 int yychar;
 
-
-#ifndef YY_IGNORE_MAYBE_UNINITIALIZED_BEGIN
-# define YY_IGNORE_MAYBE_UNINITIALIZED_BEGIN
-# define YY_IGNORE_MAYBE_UNINITIALIZED_END
-#endif
-#ifndef YY_INITIAL_VALUE
-# define YY_INITIAL_VALUE(Value) /* Nothing. */
-#endif
-
 /* The semantic value of the lookahead symbol.  */
-YYSTYPE yylval YY_INITIAL_VALUE(yyval_default);
-
+YYSTYPE yylval;
+/* Location data for the lookahead symbol.  */
+YYLTYPE yylloc
+# if defined YYLTYPE_IS_TRIVIAL && YYLTYPE_IS_TRIVIAL
+  = { 1, 1, 1, 1 }
+# endif
+;
 /* Number of syntax errors so far.  */
 int yynerrs;
 
@@ -1262,35 +1209,17 @@
 | yyparse.  |
 `----------*/
 
-#ifdef YYPARSE_PARAM
-#if (defined __STDC__ || defined __C99__FUNC__ \
-     || defined __cplusplus || defined _MSC_VER)
-int
-yyparse (void *YYPARSE_PARAM)
-#else
-int
-yyparse (YYPARSE_PARAM)
-    void *YYPARSE_PARAM;
-#endif
-#else /* ! YYPARSE_PARAM */
-#if (defined __STDC__ || defined __C99__FUNC__ \
-     || defined __cplusplus || defined _MSC_VER)
 int
 yyparse (void)
-#else
-int
-yyparse ()
-
-#endif
-#endif
 {
     int yystate;
     /* Number of tokens to shift before error messages enabled.  */
     int yyerrstatus;
 
     /* The stacks and their tools:
-       `yyss': related to states.
-       `yyvs': related to semantic values.
+       'yyss': related to states.
+       'yyvs': related to semantic values.
+       'yyls': related to locations.
 
        Refer to the stacks through separate pointers, to allow yyoverflow
        to reallocate them elsewhere.  */
@@ -1305,6 +1234,14 @@
     YYSTYPE *yyvs;
     YYSTYPE *yyvsp;
 
+    /* The location stack.  */
+    YYLTYPE yylsa[YYINITDEPTH];
+    YYLTYPE *yyls;
+    YYLTYPE *yylsp;
+
+    /* The locations where the error started and ended.  */
+    YYLTYPE yyerror_range[3];
+
     YYSIZE_T yystacksize;
 
   int yyn;
@@ -1314,6 +1251,7 @@
   /* The variables used to return semantic value and location from the
      action routines.  */
   YYSTYPE yyval;
+  YYLTYPE yyloc;
 
 #if YYERROR_VERBOSE
   /* Buffer for error messages, and its allocated size.  */
@@ -1322,7 +1260,7 @@
   YYSIZE_T yymsg_alloc = sizeof yymsgbuf;
 #endif
 
-#define YYPOPSTACK(N)   (yyvsp -= (N), yyssp -= (N))
+#define YYPOPSTACK(N)   (yyvsp -= (N), yyssp -= (N), yylsp -= (N))
 
   /* The number of symbols on the RHS of the reduced rule.
      Keep to zero when no symbol should be popped.  */
@@ -1330,6 +1268,7 @@
 
   yyssp = yyss = yyssa;
   yyvsp = yyvs = yyvsa;
+  yylsp = yyls = yylsa;
   yystacksize = YYINITDEPTH;
 
   YYDPRINTF ((stderr, "Starting parse\n"));
@@ -1338,6 +1277,7 @@
   yyerrstatus = 0;
   yynerrs = 0;
   yychar = YYEMPTY; /* Cause a token to be read.  */
+  yylsp[0] = yylloc;
   goto yysetstate;
 
 /*------------------------------------------------------------.
@@ -1358,23 +1298,26 @@
 
 #ifdef yyoverflow
       {
-	/* Give user a chance to reallocate the stack.  Use copies of
-	   these so that the &'s don't force the real ones into
-	   memory.  */
-	YYSTYPE *yyvs1 = yyvs;
-	yytype_int16 *yyss1 = yyss;
+        /* Give user a chance to reallocate the stack.  Use copies of
+           these so that the &'s don't force the real ones into
+           memory.  */
+        YYSTYPE *yyvs1 = yyvs;
+        yytype_int16 *yyss1 = yyss;
+        YYLTYPE *yyls1 = yyls;
 
-	/* Each stack pointer address is followed by the size of the
-	   data in use in that stack, in bytes.  This used to be a
-	   conditional around just the two extra args, but that might
-	   be undefined if yyoverflow is a macro.  */
-	yyoverflow (YY_("memory exhausted"),
-		    &yyss1, yysize * sizeof (*yyssp),
-		    &yyvs1, yysize * sizeof (*yyvsp),
-		    &yystacksize);
+        /* Each stack pointer address is followed by the size of the
+           data in use in that stack, in bytes.  This used to be a
+           conditional around just the two extra args, but that might
+           be undefined if yyoverflow is a macro.  */
+        yyoverflow (YY_("memory exhausted"),
+                    &yyss1, yysize * sizeof (*yyssp),
+                    &yyvs1, yysize * sizeof (*yyvsp),
+                    &yyls1, yysize * sizeof (*yylsp),
+                    &yystacksize);
 
-	yyss = yyss1;
-	yyvs = yyvs1;
+        yyls = yyls1;
+        yyss = yyss1;
+        yyvs = yyvs1;
       }
 #else /* no yyoverflow */
 # ifndef YYSTACK_RELOCATE
@@ -1382,34 +1325,36 @@
 # else
       /* Extend the stack our own way.  */
       if (YYMAXDEPTH <= yystacksize)
-	goto yyexhaustedlab;
+        goto yyexhaustedlab;
       yystacksize *= 2;
       if (YYMAXDEPTH < yystacksize)
-	yystacksize = YYMAXDEPTH;
+        yystacksize = YYMAXDEPTH;
 
       {
-	yytype_int16 *yyss1 = yyss;
-	union yyalloc *yyptr =
-	  (union yyalloc *) YYSTACK_ALLOC (YYSTACK_BYTES (yystacksize));
-	if (! yyptr)
-	  goto yyexhaustedlab;
-	YYSTACK_RELOCATE (yyss_alloc, yyss);
-	YYSTACK_RELOCATE (yyvs_alloc, yyvs);
+        yytype_int16 *yyss1 = yyss;
+        union yyalloc *yyptr =
+          (union yyalloc *) YYSTACK_ALLOC (YYSTACK_BYTES (yystacksize));
+        if (! yyptr)
+          goto yyexhaustedlab;
+        YYSTACK_RELOCATE (yyss_alloc, yyss);
+        YYSTACK_RELOCATE (yyvs_alloc, yyvs);
+        YYSTACK_RELOCATE (yyls_alloc, yyls);
 #  undef YYSTACK_RELOCATE
-	if (yyss1 != yyssa)
-	  YYSTACK_FREE (yyss1);
+        if (yyss1 != yyssa)
+          YYSTACK_FREE (yyss1);
       }
 # endif
 #endif /* no yyoverflow */
 
       yyssp = yyss + yysize - 1;
       yyvsp = yyvs + yysize - 1;
+      yylsp = yyls + yysize - 1;
 
       YYDPRINTF ((stderr, "Stack size increased to %lu\n",
-		  (unsigned long int) yystacksize));
+                  (unsigned long int) yystacksize));
 
       if (yyss + yystacksize - 1 <= yyssp)
-	YYABORT;
+        YYABORT;
     }
 
   YYDPRINTF ((stderr, "Entering state %d\n", yystate));
@@ -1438,7 +1383,7 @@
   if (yychar == YYEMPTY)
     {
       YYDPRINTF ((stderr, "Reading a token: "));
-      yychar = YYLEX;
+      yychar = yylex ();
     }
 
   if (yychar <= YYEOF)
@@ -1481,7 +1426,7 @@
   YY_IGNORE_MAYBE_UNINITIALIZED_BEGIN
   *++yyvsp = yylval;
   YY_IGNORE_MAYBE_UNINITIALIZED_END
-
+  *++yylsp = yylloc;
   goto yynewstate;
 
 
@@ -1503,7 +1448,7 @@
   yylen = yyr2[yyn];
 
   /* If YYLEN is nonzero, implement the default value of the action:
-     `$$ = $1'.
+     '$$ = $1'.
 
      Otherwise, the following line sets YYVAL to garbage.
      This behavior is undocumented and Bison
@@ -1512,287 +1457,303 @@
      GCC warning that YYVAL may be used uninitialized.  */
   yyval = yyvsp[1-yylen];
 
-
+  /* Default location.  */
+  YYLLOC_DEFAULT (yyloc, (yylsp - yylen), yylen);
   YY_REDUCE_PRINT (yyn);
   switch (yyn)
     {
         case 2:
-/* Line 1787 of yacc.c  */
-#line 110 "dtc-parser.y"
+#line 105 "dtc-parser.y" /* yacc.c:1646  */
     {
-			the_boot_info = build_boot_info((yyvsp[(3) - (4)].re), (yyvsp[(4) - (4)].node),
-							guess_boot_cpuid((yyvsp[(4) - (4)].node)));
+			the_boot_info = build_boot_info((yyvsp[-1].re), (yyvsp[0].node),
+							guess_boot_cpuid((yyvsp[0].node)));
 		}
+#line 1472 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 3:
-/* Line 1787 of yacc.c  */
-#line 118 "dtc-parser.y"
+#line 113 "dtc-parser.y" /* yacc.c:1646  */
     {
 			(yyval.re) = NULL;
 		}
+#line 1480 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 4:
-/* Line 1787 of yacc.c  */
-#line 122 "dtc-parser.y"
+#line 117 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.re) = chain_reserve_entry((yyvsp[(1) - (2)].re), (yyvsp[(2) - (2)].re));
+			(yyval.re) = chain_reserve_entry((yyvsp[-1].re), (yyvsp[0].re));
 		}
+#line 1488 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 5:
-/* Line 1787 of yacc.c  */
-#line 129 "dtc-parser.y"
+#line 124 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.re) = build_reserve_entry((yyvsp[(2) - (4)].integer), (yyvsp[(3) - (4)].integer));
+			(yyval.re) = build_reserve_entry((yyvsp[-2].integer), (yyvsp[-1].integer));
 		}
+#line 1496 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 6:
-/* Line 1787 of yacc.c  */
-#line 133 "dtc-parser.y"
+#line 128 "dtc-parser.y" /* yacc.c:1646  */
     {
-			add_label(&(yyvsp[(2) - (2)].re)->labels, (yyvsp[(1) - (2)].labelref));
-			(yyval.re) = (yyvsp[(2) - (2)].re);
+			add_label(&(yyvsp[0].re)->labels, (yyvsp[-1].labelref));
+			(yyval.re) = (yyvsp[0].re);
 		}
+#line 1505 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 7:
-/* Line 1787 of yacc.c  */
-#line 141 "dtc-parser.y"
+#line 136 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.node) = name_node((yyvsp[(2) - (2)].node), "");
+			(yyval.node) = name_node((yyvsp[0].node), "");
 		}
+#line 1513 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 8:
-/* Line 1787 of yacc.c  */
-#line 145 "dtc-parser.y"
+#line 140 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.node) = merge_nodes((yyvsp[(1) - (3)].node), (yyvsp[(3) - (3)].node));
+			(yyval.node) = merge_nodes((yyvsp[-2].node), (yyvsp[0].node));
 		}
+#line 1521 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 9:
-/* Line 1787 of yacc.c  */
-#line 149 "dtc-parser.y"
+#line 145 "dtc-parser.y" /* yacc.c:1646  */
     {
-			struct node *target = get_node_by_ref((yyvsp[(1) - (3)].node), (yyvsp[(2) - (3)].labelref));
+			struct node *target = get_node_by_ref((yyvsp[-3].node), (yyvsp[-1].labelref));
 
+			add_label(&target->labels, (yyvsp[-2].labelref));
 			if (target)
-				merge_nodes(target, (yyvsp[(3) - (3)].node));
+				merge_nodes(target, (yyvsp[0].node));
 			else
-				print_error("label or path, '%s', not found", (yyvsp[(2) - (3)].labelref));
-			(yyval.node) = (yyvsp[(1) - (3)].node);
+				ERROR(&(yylsp[-1]), "Label or path %s not found", (yyvsp[-1].labelref));
+			(yyval.node) = (yyvsp[-3].node);
 		}
+#line 1536 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 10:
-/* Line 1787 of yacc.c  */
-#line 159 "dtc-parser.y"
+#line 156 "dtc-parser.y" /* yacc.c:1646  */
     {
-			struct node *target = get_node_by_ref((yyvsp[(1) - (4)].node), (yyvsp[(3) - (4)].labelref));
+			struct node *target = get_node_by_ref((yyvsp[-2].node), (yyvsp[-1].labelref));
 
-			if (!target)
-				print_error("label or path, '%s', not found", (yyvsp[(3) - (4)].labelref));
+			if (target)
+				merge_nodes(target, (yyvsp[0].node));
 			else
-				delete_node(target);
-
-			(yyval.node) = (yyvsp[(1) - (4)].node);
+				ERROR(&(yylsp[-1]), "Label or path %s not found", (yyvsp[-1].labelref));
+			(yyval.node) = (yyvsp[-2].node);
 		}
+#line 1550 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 11:
-/* Line 1787 of yacc.c  */
-#line 173 "dtc-parser.y"
+#line 166 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.node) = build_node((yyvsp[(2) - (5)].proplist), (yyvsp[(3) - (5)].nodelist));
+			struct node *target = get_node_by_ref((yyvsp[-3].node), (yyvsp[-1].labelref));
+
+			if (target)
+				delete_node(target);
+			else
+				ERROR(&(yylsp[-1]), "Label or path %s not found", (yyvsp[-1].labelref));
+
+
+			(yyval.node) = (yyvsp[-3].node);
 		}
+#line 1566 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 12:
-/* Line 1787 of yacc.c  */
-#line 180 "dtc-parser.y"
+#line 181 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.proplist) = NULL;
+			(yyval.node) = build_node((yyvsp[-3].proplist), (yyvsp[-2].nodelist));
 		}
+#line 1574 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 13:
-/* Line 1787 of yacc.c  */
-#line 184 "dtc-parser.y"
+#line 188 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.proplist) = chain_property((yyvsp[(2) - (2)].prop), (yyvsp[(1) - (2)].proplist));
+			(yyval.proplist) = NULL;
 		}
+#line 1582 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 14:
-/* Line 1787 of yacc.c  */
-#line 191 "dtc-parser.y"
+#line 192 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.prop) = build_property((yyvsp[(1) - (4)].propnodename), (yyvsp[(3) - (4)].data));
+			(yyval.proplist) = chain_property((yyvsp[0].prop), (yyvsp[-1].proplist));
 		}
+#line 1590 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 15:
-/* Line 1787 of yacc.c  */
-#line 195 "dtc-parser.y"
+#line 199 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.prop) = build_property((yyvsp[(1) - (2)].propnodename), empty_data);
+			(yyval.prop) = build_property((yyvsp[-3].propnodename), (yyvsp[-1].data));
 		}
+#line 1598 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 16:
-/* Line 1787 of yacc.c  */
-#line 199 "dtc-parser.y"
+#line 203 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.prop) = build_property_delete((yyvsp[(2) - (3)].propnodename));
+			(yyval.prop) = build_property((yyvsp[-1].propnodename), empty_data);
 		}
+#line 1606 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 17:
-/* Line 1787 of yacc.c  */
-#line 203 "dtc-parser.y"
+#line 207 "dtc-parser.y" /* yacc.c:1646  */
     {
-			add_label(&(yyvsp[(2) - (2)].prop)->labels, (yyvsp[(1) - (2)].labelref));
-			(yyval.prop) = (yyvsp[(2) - (2)].prop);
+			(yyval.prop) = build_property_delete((yyvsp[-1].propnodename));
 		}
+#line 1614 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 18:
-/* Line 1787 of yacc.c  */
-#line 211 "dtc-parser.y"
+#line 211 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.data) = data_merge((yyvsp[(1) - (2)].data), (yyvsp[(2) - (2)].data));
+			add_label(&(yyvsp[0].prop)->labels, (yyvsp[-1].labelref));
+			(yyval.prop) = (yyvsp[0].prop);
 		}
+#line 1623 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 19:
-/* Line 1787 of yacc.c  */
-#line 215 "dtc-parser.y"
+#line 219 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.data) = data_merge((yyvsp[(1) - (3)].data), (yyvsp[(2) - (3)].array).data);
+			(yyval.data) = data_merge((yyvsp[-1].data), (yyvsp[0].data));
 		}
+#line 1631 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 20:
-/* Line 1787 of yacc.c  */
-#line 219 "dtc-parser.y"
+#line 223 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.data) = data_merge((yyvsp[(1) - (4)].data), (yyvsp[(3) - (4)].data));
+			(yyval.data) = data_merge((yyvsp[-2].data), (yyvsp[-1].array).data);
 		}
+#line 1639 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 21:
-/* Line 1787 of yacc.c  */
-#line 223 "dtc-parser.y"
+#line 227 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.data) = data_add_marker((yyvsp[(1) - (2)].data), REF_PATH, (yyvsp[(2) - (2)].labelref));
+			(yyval.data) = data_merge((yyvsp[-3].data), (yyvsp[-1].data));
 		}
+#line 1647 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 22:
-/* Line 1787 of yacc.c  */
-#line 227 "dtc-parser.y"
+#line 231 "dtc-parser.y" /* yacc.c:1646  */
     {
-			FILE *f = srcfile_relative_open((yyvsp[(4) - (9)].data).val, NULL);
-			struct data d;
-
-			if ((yyvsp[(6) - (9)].integer) != 0)
-				if (fseek(f, (yyvsp[(6) - (9)].integer), SEEK_SET) != 0)
-					print_error("Couldn't seek to offset %llu in \"%s\": %s",
-						     (unsigned long long)(yyvsp[(6) - (9)].integer),
-						     (yyvsp[(4) - (9)].data).val,
-						     strerror(errno));
-
-			d = data_copy_file(f, (yyvsp[(8) - (9)].integer));
-
-			(yyval.data) = data_merge((yyvsp[(1) - (9)].data), d);
-			fclose(f);
+			(yyval.data) = data_add_marker((yyvsp[-1].data), REF_PATH, (yyvsp[0].labelref));
 		}
+#line 1655 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 23:
-/* Line 1787 of yacc.c  */
-#line 244 "dtc-parser.y"
+#line 235 "dtc-parser.y" /* yacc.c:1646  */
     {
-			FILE *f = srcfile_relative_open((yyvsp[(4) - (5)].data).val, NULL);
+			FILE *f = srcfile_relative_open((yyvsp[-5].data).val, NULL);
+			struct data d;
+
+			if ((yyvsp[-3].integer) != 0)
+				if (fseek(f, (yyvsp[-3].integer), SEEK_SET) != 0)
+					die("Couldn't seek to offset %llu in \"%s\": %s",
+					    (unsigned long long)(yyvsp[-3].integer), (yyvsp[-5].data).val,
+					    strerror(errno));
+
+			d = data_copy_file(f, (yyvsp[-1].integer));
+
+			(yyval.data) = data_merge((yyvsp[-8].data), d);
+			fclose(f);
+		}
+#line 1675 "dtc-parser.tab.c" /* yacc.c:1646  */
+    break;
+
+  case 24:
+#line 251 "dtc-parser.y" /* yacc.c:1646  */
+    {
+			FILE *f = srcfile_relative_open((yyvsp[-1].data).val, NULL);
 			struct data d = empty_data;
 
 			d = data_copy_file(f, -1);
 
-			(yyval.data) = data_merge((yyvsp[(1) - (5)].data), d);
+			(yyval.data) = data_merge((yyvsp[-4].data), d);
 			fclose(f);
 		}
-    break;
-
-  case 24:
-/* Line 1787 of yacc.c  */
-#line 254 "dtc-parser.y"
-    {
-			(yyval.data) = data_add_marker((yyvsp[(1) - (2)].data), LABEL, (yyvsp[(2) - (2)].labelref));
-		}
+#line 1689 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 25:
-/* Line 1787 of yacc.c  */
-#line 261 "dtc-parser.y"
+#line 261 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.data) = empty_data;
+			(yyval.data) = data_add_marker((yyvsp[-1].data), LABEL, (yyvsp[0].labelref));
 		}
+#line 1697 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 26:
-/* Line 1787 of yacc.c  */
-#line 265 "dtc-parser.y"
+#line 268 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.data) = (yyvsp[(1) - (2)].data);
+			(yyval.data) = empty_data;
 		}
+#line 1705 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 27:
-/* Line 1787 of yacc.c  */
-#line 269 "dtc-parser.y"
+#line 272 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.data) = data_add_marker((yyvsp[(1) - (2)].data), LABEL, (yyvsp[(2) - (2)].labelref));
+			(yyval.data) = (yyvsp[-1].data);
 		}
+#line 1713 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 28:
-/* Line 1787 of yacc.c  */
-#line 276 "dtc-parser.y"
+#line 276 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.array).data = empty_data;
-			(yyval.array).bits = eval_literal((yyvsp[(2) - (3)].literal), 0, 7);
-
-			if (((yyval.array).bits !=  8) &&
-			    ((yyval.array).bits != 16) &&
-			    ((yyval.array).bits != 32) &&
-			    ((yyval.array).bits != 64))
-			{
-				print_error("Only 8, 16, 32 and 64-bit elements"
-					    " are currently supported");
-				(yyval.array).bits = 32;
-			}
+			(yyval.data) = data_add_marker((yyvsp[-1].data), LABEL, (yyvsp[0].labelref));
 		}
+#line 1721 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 29:
-/* Line 1787 of yacc.c  */
-#line 291 "dtc-parser.y"
+#line 283 "dtc-parser.y" /* yacc.c:1646  */
+    {
+			unsigned long long bits;
+
+			bits = (yyvsp[-1].integer);
+
+			if ((bits !=  8) && (bits != 16) &&
+			    (bits != 32) && (bits != 64)) {
+				ERROR(&(yylsp[-1]), "Array elements must be"
+				      " 8, 16, 32 or 64-bits");
+				bits = 32;
+			}
+
+			(yyval.array).data = empty_data;
+			(yyval.array).bits = bits;
+		}
+#line 1741 "dtc-parser.tab.c" /* yacc.c:1646  */
+    break;
+
+  case 30:
+#line 299 "dtc-parser.y" /* yacc.c:1646  */
     {
 			(yyval.array).data = empty_data;
 			(yyval.array).bits = 32;
 		}
+#line 1750 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
-  case 30:
-/* Line 1787 of yacc.c  */
-#line 296 "dtc-parser.y"
+  case 31:
+#line 304 "dtc-parser.y" /* yacc.c:1646  */
     {
-			if ((yyvsp[(1) - (2)].array).bits < 64) {
-				uint64_t mask = (1ULL << (yyvsp[(1) - (2)].array).bits) - 1;
+			if ((yyvsp[-1].array).bits < 64) {
+				uint64_t mask = (1ULL << (yyvsp[-1].array).bits) - 1;
 				/*
 				 * Bits above mask must either be all zero
 				 * (positive within range of mask) or all one
@@ -1801,275 +1762,258 @@
 				 * within the mask to one (i.e. | in the
 				 * mask), all bits are one.
 				 */
-				if (((yyvsp[(2) - (2)].integer) > mask) && (((yyvsp[(2) - (2)].integer) | mask) != -1ULL))
-					print_error(
-						"integer value out of range "
-						"%016lx (%d bits)", (yyvsp[(1) - (2)].array).bits);
+				if (((yyvsp[0].integer) > mask) && (((yyvsp[0].integer) | mask) != -1ULL))
+					ERROR(&(yylsp[0]), "Value out of range for"
+					      " %d-bit array element", (yyvsp[-1].array).bits);
 			}
 
-			(yyval.array).data = data_append_integer((yyvsp[(1) - (2)].array).data, (yyvsp[(2) - (2)].integer), (yyvsp[(1) - (2)].array).bits);
+			(yyval.array).data = data_append_integer((yyvsp[-1].array).data, (yyvsp[0].integer), (yyvsp[-1].array).bits);
 		}
-    break;
-
-  case 31:
-/* Line 1787 of yacc.c  */
-#line 316 "dtc-parser.y"
-    {
-			uint64_t val = ~0ULL >> (64 - (yyvsp[(1) - (2)].array).bits);
-
-			if ((yyvsp[(1) - (2)].array).bits == 32)
-				(yyvsp[(1) - (2)].array).data = data_add_marker((yyvsp[(1) - (2)].array).data,
-							  REF_PHANDLE,
-							  (yyvsp[(2) - (2)].labelref));
-			else
-				print_error("References are only allowed in "
-					    "arrays with 32-bit elements.");
-
-			(yyval.array).data = data_append_integer((yyvsp[(1) - (2)].array).data, val, (yyvsp[(1) - (2)].array).bits);
-		}
+#line 1773 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 32:
-/* Line 1787 of yacc.c  */
-#line 330 "dtc-parser.y"
+#line 323 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.array).data = data_add_marker((yyvsp[(1) - (2)].array).data, LABEL, (yyvsp[(2) - (2)].labelref));
+			uint64_t val = ~0ULL >> (64 - (yyvsp[-1].array).bits);
+
+			if ((yyvsp[-1].array).bits == 32)
+				(yyvsp[-1].array).data = data_add_marker((yyvsp[-1].array).data,
+							  REF_PHANDLE,
+							  (yyvsp[0].labelref));
+			else
+				ERROR(&(yylsp[0]), "References are only allowed in "
+					    "arrays with 32-bit elements.");
+
+			(yyval.array).data = data_append_integer((yyvsp[-1].array).data, val, (yyvsp[-1].array).bits);
 		}
+#line 1791 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 33:
-/* Line 1787 of yacc.c  */
-#line 337 "dtc-parser.y"
+#line 337 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.integer) = eval_literal((yyvsp[(1) - (1)].literal), 0, 64);
+			(yyval.array).data = data_add_marker((yyvsp[-1].array).data, LABEL, (yyvsp[0].labelref));
 		}
+#line 1799 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
-  case 34:
-/* Line 1787 of yacc.c  */
-#line 341 "dtc-parser.y"
+  case 36:
+#line 346 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.integer) = eval_char_literal((yyvsp[(1) - (1)].literal));
+			(yyval.integer) = (yyvsp[-1].integer);
 		}
+#line 1807 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
-  case 35:
-/* Line 1787 of yacc.c  */
-#line 345 "dtc-parser.y"
-    {
-			(yyval.integer) = (yyvsp[(2) - (3)].integer);
-		}
+  case 39:
+#line 357 "dtc-parser.y" /* yacc.c:1646  */
+    { (yyval.integer) = (yyvsp[-4].integer) ? (yyvsp[-2].integer) : (yyvsp[0].integer); }
+#line 1813 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
-  case 38:
-/* Line 1787 of yacc.c  */
-#line 356 "dtc-parser.y"
-    { (yyval.integer) = (yyvsp[(1) - (5)].integer) ? (yyvsp[(3) - (5)].integer) : (yyvsp[(5) - (5)].integer); }
+  case 41:
+#line 362 "dtc-parser.y" /* yacc.c:1646  */
+    { (yyval.integer) = (yyvsp[-2].integer) || (yyvsp[0].integer); }
+#line 1819 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
-  case 40:
-/* Line 1787 of yacc.c  */
-#line 361 "dtc-parser.y"
-    { (yyval.integer) = (yyvsp[(1) - (3)].integer) || (yyvsp[(3) - (3)].integer); }
+  case 43:
+#line 367 "dtc-parser.y" /* yacc.c:1646  */
+    { (yyval.integer) = (yyvsp[-2].integer) && (yyvsp[0].integer); }
+#line 1825 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
-  case 42:
-/* Line 1787 of yacc.c  */
-#line 366 "dtc-parser.y"
-    { (yyval.integer) = (yyvsp[(1) - (3)].integer) && (yyvsp[(3) - (3)].integer); }
+  case 45:
+#line 372 "dtc-parser.y" /* yacc.c:1646  */
+    { (yyval.integer) = (yyvsp[-2].integer) | (yyvsp[0].integer); }
+#line 1831 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
-  case 44:
-/* Line 1787 of yacc.c  */
-#line 371 "dtc-parser.y"
-    { (yyval.integer) = (yyvsp[(1) - (3)].integer) | (yyvsp[(3) - (3)].integer); }
+  case 47:
+#line 377 "dtc-parser.y" /* yacc.c:1646  */
+    { (yyval.integer) = (yyvsp[-2].integer) ^ (yyvsp[0].integer); }
+#line 1837 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
-  case 46:
-/* Line 1787 of yacc.c  */
-#line 376 "dtc-parser.y"
-    { (yyval.integer) = (yyvsp[(1) - (3)].integer) ^ (yyvsp[(3) - (3)].integer); }
-    break;
-
-  case 48:
-/* Line 1787 of yacc.c  */
-#line 381 "dtc-parser.y"
-    { (yyval.integer) = (yyvsp[(1) - (3)].integer) & (yyvsp[(3) - (3)].integer); }
-    break;
-
-  case 50:
-/* Line 1787 of yacc.c  */
-#line 386 "dtc-parser.y"
-    { (yyval.integer) = (yyvsp[(1) - (3)].integer) == (yyvsp[(3) - (3)].integer); }
+  case 49:
+#line 382 "dtc-parser.y" /* yacc.c:1646  */
+    { (yyval.integer) = (yyvsp[-2].integer) & (yyvsp[0].integer); }
+#line 1843 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 51:
-/* Line 1787 of yacc.c  */
-#line 387 "dtc-parser.y"
-    { (yyval.integer) = (yyvsp[(1) - (3)].integer) != (yyvsp[(3) - (3)].integer); }
+#line 387 "dtc-parser.y" /* yacc.c:1646  */
+    { (yyval.integer) = (yyvsp[-2].integer) == (yyvsp[0].integer); }
+#line 1849 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
-  case 53:
-/* Line 1787 of yacc.c  */
-#line 392 "dtc-parser.y"
-    { (yyval.integer) = (yyvsp[(1) - (3)].integer) < (yyvsp[(3) - (3)].integer); }
+  case 52:
+#line 388 "dtc-parser.y" /* yacc.c:1646  */
+    { (yyval.integer) = (yyvsp[-2].integer) != (yyvsp[0].integer); }
+#line 1855 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 54:
-/* Line 1787 of yacc.c  */
-#line 393 "dtc-parser.y"
-    { (yyval.integer) = (yyvsp[(1) - (3)].integer) > (yyvsp[(3) - (3)].integer); }
+#line 393 "dtc-parser.y" /* yacc.c:1646  */
+    { (yyval.integer) = (yyvsp[-2].integer) < (yyvsp[0].integer); }
+#line 1861 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 55:
-/* Line 1787 of yacc.c  */
-#line 394 "dtc-parser.y"
-    { (yyval.integer) = (yyvsp[(1) - (3)].integer) <= (yyvsp[(3) - (3)].integer); }
+#line 394 "dtc-parser.y" /* yacc.c:1646  */
+    { (yyval.integer) = (yyvsp[-2].integer) > (yyvsp[0].integer); }
+#line 1867 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 56:
-/* Line 1787 of yacc.c  */
-#line 395 "dtc-parser.y"
-    { (yyval.integer) = (yyvsp[(1) - (3)].integer) >= (yyvsp[(3) - (3)].integer); }
+#line 395 "dtc-parser.y" /* yacc.c:1646  */
+    { (yyval.integer) = (yyvsp[-2].integer) <= (yyvsp[0].integer); }
+#line 1873 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 57:
-/* Line 1787 of yacc.c  */
-#line 399 "dtc-parser.y"
-    { (yyval.integer) = (yyvsp[(1) - (3)].integer) << (yyvsp[(3) - (3)].integer); }
+#line 396 "dtc-parser.y" /* yacc.c:1646  */
+    { (yyval.integer) = (yyvsp[-2].integer) >= (yyvsp[0].integer); }
+#line 1879 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 58:
-/* Line 1787 of yacc.c  */
-#line 400 "dtc-parser.y"
-    { (yyval.integer) = (yyvsp[(1) - (3)].integer) >> (yyvsp[(3) - (3)].integer); }
+#line 400 "dtc-parser.y" /* yacc.c:1646  */
+    { (yyval.integer) = (yyvsp[-2].integer) << (yyvsp[0].integer); }
+#line 1885 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
-  case 60:
-/* Line 1787 of yacc.c  */
-#line 405 "dtc-parser.y"
-    { (yyval.integer) = (yyvsp[(1) - (3)].integer) + (yyvsp[(3) - (3)].integer); }
+  case 59:
+#line 401 "dtc-parser.y" /* yacc.c:1646  */
+    { (yyval.integer) = (yyvsp[-2].integer) >> (yyvsp[0].integer); }
+#line 1891 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 61:
-/* Line 1787 of yacc.c  */
-#line 406 "dtc-parser.y"
-    { (yyval.integer) = (yyvsp[(1) - (3)].integer) - (yyvsp[(3) - (3)].integer); }
+#line 406 "dtc-parser.y" /* yacc.c:1646  */
+    { (yyval.integer) = (yyvsp[-2].integer) + (yyvsp[0].integer); }
+#line 1897 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
-  case 63:
-/* Line 1787 of yacc.c  */
-#line 411 "dtc-parser.y"
-    { (yyval.integer) = (yyvsp[(1) - (3)].integer) * (yyvsp[(3) - (3)].integer); }
+  case 62:
+#line 407 "dtc-parser.y" /* yacc.c:1646  */
+    { (yyval.integer) = (yyvsp[-2].integer) - (yyvsp[0].integer); }
+#line 1903 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 64:
-/* Line 1787 of yacc.c  */
-#line 412 "dtc-parser.y"
-    { (yyval.integer) = (yyvsp[(1) - (3)].integer) / (yyvsp[(3) - (3)].integer); }
+#line 412 "dtc-parser.y" /* yacc.c:1646  */
+    { (yyval.integer) = (yyvsp[-2].integer) * (yyvsp[0].integer); }
+#line 1909 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 65:
-/* Line 1787 of yacc.c  */
-#line 413 "dtc-parser.y"
-    { (yyval.integer) = (yyvsp[(1) - (3)].integer) % (yyvsp[(3) - (3)].integer); }
+#line 413 "dtc-parser.y" /* yacc.c:1646  */
+    { (yyval.integer) = (yyvsp[-2].integer) / (yyvsp[0].integer); }
+#line 1915 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
-  case 68:
-/* Line 1787 of yacc.c  */
-#line 419 "dtc-parser.y"
-    { (yyval.integer) = -(yyvsp[(2) - (2)].integer); }
+  case 66:
+#line 414 "dtc-parser.y" /* yacc.c:1646  */
+    { (yyval.integer) = (yyvsp[-2].integer) % (yyvsp[0].integer); }
+#line 1921 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 69:
-/* Line 1787 of yacc.c  */
-#line 420 "dtc-parser.y"
-    { (yyval.integer) = ~(yyvsp[(2) - (2)].integer); }
+#line 420 "dtc-parser.y" /* yacc.c:1646  */
+    { (yyval.integer) = -(yyvsp[0].integer); }
+#line 1927 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 70:
-/* Line 1787 of yacc.c  */
-#line 421 "dtc-parser.y"
-    { (yyval.integer) = !(yyvsp[(2) - (2)].integer); }
+#line 421 "dtc-parser.y" /* yacc.c:1646  */
+    { (yyval.integer) = ~(yyvsp[0].integer); }
+#line 1933 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 71:
-/* Line 1787 of yacc.c  */
-#line 426 "dtc-parser.y"
-    {
-			(yyval.data) = empty_data;
-		}
+#line 422 "dtc-parser.y" /* yacc.c:1646  */
+    { (yyval.integer) = !(yyvsp[0].integer); }
+#line 1939 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 72:
-/* Line 1787 of yacc.c  */
-#line 430 "dtc-parser.y"
+#line 427 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.data) = data_append_byte((yyvsp[(1) - (2)].data), (yyvsp[(2) - (2)].byte));
+			(yyval.data) = empty_data;
 		}
+#line 1947 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 73:
-/* Line 1787 of yacc.c  */
-#line 434 "dtc-parser.y"
+#line 431 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.data) = data_add_marker((yyvsp[(1) - (2)].data), LABEL, (yyvsp[(2) - (2)].labelref));
+			(yyval.data) = data_append_byte((yyvsp[-1].data), (yyvsp[0].byte));
 		}
+#line 1955 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 74:
-/* Line 1787 of yacc.c  */
-#line 441 "dtc-parser.y"
+#line 435 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.nodelist) = NULL;
+			(yyval.data) = data_add_marker((yyvsp[-1].data), LABEL, (yyvsp[0].labelref));
 		}
+#line 1963 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 75:
-/* Line 1787 of yacc.c  */
-#line 445 "dtc-parser.y"
+#line 442 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.nodelist) = chain_node((yyvsp[(1) - (2)].node), (yyvsp[(2) - (2)].nodelist));
+			(yyval.nodelist) = NULL;
 		}
+#line 1971 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 76:
-/* Line 1787 of yacc.c  */
-#line 449 "dtc-parser.y"
+#line 446 "dtc-parser.y" /* yacc.c:1646  */
     {
-			print_error("syntax error: properties must precede subnodes");
-			YYERROR;
+			(yyval.nodelist) = chain_node((yyvsp[-1].node), (yyvsp[0].nodelist));
 		}
+#line 1979 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 77:
-/* Line 1787 of yacc.c  */
-#line 457 "dtc-parser.y"
+#line 450 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.node) = name_node((yyvsp[(2) - (2)].node), (yyvsp[(1) - (2)].propnodename));
+			ERROR(&(yylsp[0]), "Properties must precede subnodes");
+			YYERROR;
 		}
+#line 1988 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 78:
-/* Line 1787 of yacc.c  */
-#line 461 "dtc-parser.y"
+#line 458 "dtc-parser.y" /* yacc.c:1646  */
     {
-			(yyval.node) = name_node(build_node_delete(), (yyvsp[(2) - (3)].propnodename));
+			(yyval.node) = name_node((yyvsp[0].node), (yyvsp[-1].propnodename));
 		}
+#line 1996 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
   case 79:
-/* Line 1787 of yacc.c  */
-#line 465 "dtc-parser.y"
+#line 462 "dtc-parser.y" /* yacc.c:1646  */
     {
-			add_label(&(yyvsp[(2) - (2)].node)->labels, (yyvsp[(1) - (2)].labelref));
-			(yyval.node) = (yyvsp[(2) - (2)].node);
+			(yyval.node) = name_node(build_node_delete(), (yyvsp[-1].propnodename));
 		}
+#line 2004 "dtc-parser.tab.c" /* yacc.c:1646  */
+    break;
+
+  case 80:
+#line 466 "dtc-parser.y" /* yacc.c:1646  */
+    {
+			add_label(&(yyvsp[0].node)->labels, (yyvsp[-1].labelref));
+			(yyval.node) = (yyvsp[0].node);
+		}
+#line 2013 "dtc-parser.tab.c" /* yacc.c:1646  */
     break;
 
 
-/* Line 1787 of yacc.c  */
-#line 2073 "dtc-parser.tab.c"
+#line 2017 "dtc-parser.tab.c" /* yacc.c:1646  */
       default: break;
     }
   /* User semantic actions sometimes alter yychar, and that requires
@@ -2090,8 +2034,9 @@
   YY_STACK_PRINT (yyss, yyssp);
 
   *++yyvsp = yyval;
+  *++yylsp = yyloc;
 
-  /* Now `shift' the result of the reduction.  Determine what state
+  /* Now 'shift' the result of the reduction.  Determine what state
      that goes to, based on the state we popped back to and the rule
      number reduced by.  */
 
@@ -2106,9 +2051,9 @@
   goto yynewstate;
 
 
-/*------------------------------------.
-| yyerrlab -- here on detecting error |
-`------------------------------------*/
+/*--------------------------------------.
+| yyerrlab -- here on detecting error.  |
+`--------------------------------------*/
 yyerrlab:
   /* Make sure we have latest lookahead translation.  See comments at
      user semantic actions for why this is necessary.  */
@@ -2154,25 +2099,25 @@
 #endif
     }
 
-
+  yyerror_range[1] = yylloc;
 
   if (yyerrstatus == 3)
     {
       /* If just tried and failed to reuse lookahead token after an
-	 error, discard it.  */
+         error, discard it.  */
 
       if (yychar <= YYEOF)
-	{
-	  /* Return failure if at end of input.  */
-	  if (yychar == YYEOF)
-	    YYABORT;
-	}
+        {
+          /* Return failure if at end of input.  */
+          if (yychar == YYEOF)
+            YYABORT;
+        }
       else
-	{
-	  yydestruct ("Error: discarding",
-		      yytoken, &yylval);
-	  yychar = YYEMPTY;
-	}
+        {
+          yydestruct ("Error: discarding",
+                      yytoken, &yylval, &yylloc);
+          yychar = YYEMPTY;
+        }
     }
 
   /* Else will try to reuse lookahead token after shifting the error
@@ -2191,7 +2136,8 @@
   if (/*CONSTCOND*/ 0)
      goto yyerrorlab;
 
-  /* Do not reclaim the symbols of the rule which action triggered
+  yyerror_range[1] = yylsp[1-yylen];
+  /* Do not reclaim the symbols of the rule whose action triggered
      this YYERROR.  */
   YYPOPSTACK (yylen);
   yylen = 0;
@@ -2204,29 +2150,29 @@
 | yyerrlab1 -- common code for both syntax error and YYERROR.  |
 `-------------------------------------------------------------*/
 yyerrlab1:
-  yyerrstatus = 3;	/* Each real token shifted decrements this.  */
+  yyerrstatus = 3;      /* Each real token shifted decrements this.  */
 
   for (;;)
     {
       yyn = yypact[yystate];
       if (!yypact_value_is_default (yyn))
-	{
-	  yyn += YYTERROR;
-	  if (0 <= yyn && yyn <= YYLAST && yycheck[yyn] == YYTERROR)
-	    {
-	      yyn = yytable[yyn];
-	      if (0 < yyn)
-		break;
-	    }
-	}
+        {
+          yyn += YYTERROR;
+          if (0 <= yyn && yyn <= YYLAST && yycheck[yyn] == YYTERROR)
+            {
+              yyn = yytable[yyn];
+              if (0 < yyn)
+                break;
+            }
+        }
 
       /* Pop the current state because it cannot handle the error token.  */
       if (yyssp == yyss)
-	YYABORT;
+        YYABORT;
 
-
+      yyerror_range[1] = *yylsp;
       yydestruct ("Error: popping",
-		  yystos[yystate], yyvsp);
+                  yystos[yystate], yyvsp, yylsp);
       YYPOPSTACK (1);
       yystate = *yyssp;
       YY_STACK_PRINT (yyss, yyssp);
@@ -2236,6 +2182,11 @@
   *++yyvsp = yylval;
   YY_IGNORE_MAYBE_UNINITIALIZED_END
 
+  yyerror_range[2] = yylloc;
+  /* Using YYLLOC is tempting, but would change the location of
+     the lookahead.  YYLOC is available though.  */
+  YYLLOC_DEFAULT (yyloc, yyerror_range, 2);
+  *++yylsp = yyloc;
 
   /* Shift the error token.  */
   YY_SYMBOL_PRINT ("Shifting", yystos[yyn], yyvsp, yylsp);
@@ -2275,16 +2226,16 @@
          user semantic actions for why this is necessary.  */
       yytoken = YYTRANSLATE (yychar);
       yydestruct ("Cleanup: discarding lookahead",
-                  yytoken, &yylval);
+                  yytoken, &yylval, &yylloc);
     }
-  /* Do not reclaim the symbols of the rule which action triggered
+  /* Do not reclaim the symbols of the rule whose action triggered
      this YYABORT or YYACCEPT.  */
   YYPOPSTACK (yylen);
   YY_STACK_PRINT (yyss, yyssp);
   while (yyssp != yyss)
     {
       yydestruct ("Cleanup: popping",
-		  yystos[*yyssp], yyvsp);
+                  yystos[*yyssp], yyvsp, yylsp);
       YYPOPSTACK (1);
     }
 #ifndef yyoverflow
@@ -2295,72 +2246,12 @@
   if (yymsg != yymsgbuf)
     YYSTACK_FREE (yymsg);
 #endif
-  /* Make sure YYID is used.  */
-  return YYID (yyresult);
+  return yyresult;
 }
+#line 472 "dtc-parser.y" /* yacc.c:1906  */
 
 
-/* Line 2050 of yacc.c  */
-#line 471 "dtc-parser.y"
-
-
-void print_error(char const *fmt, ...)
+void yyerror(char const *s)
 {
-	va_list va;
-
-	va_start(va, fmt);
-	srcpos_verror(&yylloc, fmt, va);
-	va_end(va);
-
-	treesource_error = 1;
-}
-
-void yyerror(char const *s) {
-	print_error("%s", s);
-}
-
-static unsigned long long eval_literal(const char *s, int base, int bits)
-{
-	unsigned long long val;
-	char *e;
-
-	errno = 0;
-	val = strtoull(s, &e, base);
-	if (*e) {
-		size_t uls = strspn(e, "UL");
-		if (e[uls])
-			print_error("bad characters in literal");
-	}
-	if ((errno == ERANGE)
-		 || ((bits < 64) && (val >= (1ULL << bits))))
-		print_error("literal out of range");
-	else if (errno != 0)
-		print_error("bad literal");
-	return val;
-}
-
-static unsigned char eval_char_literal(const char *s)
-{
-	int i = 1;
-	char c = s[0];
-
-	if (c == '\0')
-	{
-		print_error("empty character literal");
-		return 0;
-	}
-
-	/*
-	 * If the first character in the character literal is a \ then process
-	 * the remaining characters as an escape encoding. If the first
-	 * character is neither an escape or a terminator it should be the only
-	 * character in the literal and will be returned.
-	 */
-	if (c == '\\')
-		c = get_escape_char(s, &i);
-
-	if (s[i] != '\0')
-		print_error("malformed character literal");
-
-	return c;
+	ERROR(&yylloc, "%s", s);
 }
diff --git a/scripts/dtc/dtc-parser.tab.h_shipped b/scripts/dtc/dtc-parser.tab.h_shipped
index b2e7a86..30867c6 100644
--- a/scripts/dtc/dtc-parser.tab.h_shipped
+++ b/scripts/dtc/dtc-parser.tab.h_shipped
@@ -1,19 +1,19 @@
-/* A Bison parser, made by GNU Bison 2.7.12-4996.  */
+/* A Bison parser, made by GNU Bison 3.0.2.  */
 
 /* Bison interface for Yacc-like parsers in C
-   
-      Copyright (C) 1984, 1989-1990, 2000-2013 Free Software Foundation, Inc.
-   
+
+   Copyright (C) 1984, 1989-1990, 2000-2013 Free Software Foundation, Inc.
+
    This program is free software: you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
    the Free Software Foundation, either version 3 of the License, or
    (at your option) any later version.
-   
+
    This program is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
    GNU General Public License for more details.
-   
+
    You should have received a copy of the GNU General Public License
    along with this program.  If not, see <http://www.gnu.org/licenses/>.  */
 
@@ -26,13 +26,13 @@
    special exception, which will cause the skeleton and the resulting
    Bison output files to be licensed under the GNU General Public
    License without this special exception.
-   
+
    This special exception was added by the Free Software Foundation in
    version 2.2 of Bison.  */
 
 #ifndef YY_YY_DTC_PARSER_TAB_H_INCLUDED
 # define YY_YY_DTC_PARSER_TAB_H_INCLUDED
-/* Enabling traces.  */
+/* Debug traces.  */
 #ifndef YYDEBUG
 # define YYDEBUG 0
 #endif
@@ -40,48 +40,44 @@
 extern int yydebug;
 #endif
 
-/* Tokens.  */
+/* Token type.  */
 #ifndef YYTOKENTYPE
 # define YYTOKENTYPE
-   /* Put the tokens into the symbol table, so that GDB and other debuggers
-      know about them.  */
-   enum yytokentype {
-     DT_V1 = 258,
-     DT_MEMRESERVE = 259,
-     DT_LSHIFT = 260,
-     DT_RSHIFT = 261,
-     DT_LE = 262,
-     DT_GE = 263,
-     DT_EQ = 264,
-     DT_NE = 265,
-     DT_AND = 266,
-     DT_OR = 267,
-     DT_BITS = 268,
-     DT_DEL_PROP = 269,
-     DT_DEL_NODE = 270,
-     DT_PROPNODENAME = 271,
-     DT_LITERAL = 272,
-     DT_CHAR_LITERAL = 273,
-     DT_BASE = 274,
-     DT_BYTE = 275,
-     DT_STRING = 276,
-     DT_LABEL = 277,
-     DT_REF = 278,
-     DT_INCBIN = 279
-   };
+  enum yytokentype
+  {
+    DT_V1 = 258,
+    DT_MEMRESERVE = 259,
+    DT_LSHIFT = 260,
+    DT_RSHIFT = 261,
+    DT_LE = 262,
+    DT_GE = 263,
+    DT_EQ = 264,
+    DT_NE = 265,
+    DT_AND = 266,
+    DT_OR = 267,
+    DT_BITS = 268,
+    DT_DEL_PROP = 269,
+    DT_DEL_NODE = 270,
+    DT_PROPNODENAME = 271,
+    DT_LITERAL = 272,
+    DT_CHAR_LITERAL = 273,
+    DT_BYTE = 274,
+    DT_STRING = 275,
+    DT_LABEL = 276,
+    DT_REF = 277,
+    DT_INCBIN = 278
+  };
 #endif
 
-
+/* Value type.  */
 #if ! defined YYSTYPE && ! defined YYSTYPE_IS_DECLARED
-typedef union YYSTYPE
+typedef union YYSTYPE YYSTYPE;
+union YYSTYPE
 {
-/* Line 2053 of yacc.c  */
-#line 40 "dtc-parser.y"
+#line 38 "dtc-parser.y" /* yacc.c:1909  */
 
 	char *propnodename;
-	char *literal;
 	char *labelref;
-	unsigned int cbase;
 	uint8_t byte;
 	struct data data;
 
@@ -97,29 +93,29 @@
 	struct reserve_info *re;
 	uint64_t integer;
 
-
-/* Line 2053 of yacc.c  */
-#line 103 "dtc-parser.tab.h"
-} YYSTYPE;
+#line 97 "dtc-parser.tab.h" /* yacc.c:1909  */
+};
 # define YYSTYPE_IS_TRIVIAL 1
-# define yystype YYSTYPE /* obsolescent; will be withdrawn */
 # define YYSTYPE_IS_DECLARED 1
 #endif
 
-extern YYSTYPE yylval;
+/* Location type.  */
+#if ! defined YYLTYPE && ! defined YYLTYPE_IS_DECLARED
+typedef struct YYLTYPE YYLTYPE;
+struct YYLTYPE
+{
+  int first_line;
+  int first_column;
+  int last_line;
+  int last_column;
+};
+# define YYLTYPE_IS_DECLARED 1
+# define YYLTYPE_IS_TRIVIAL 1
+#endif
 
-#ifdef YYPARSE_PARAM
-#if defined __STDC__ || defined __cplusplus
-int yyparse (void *YYPARSE_PARAM);
-#else
-int yyparse ();
-#endif
-#else /* ! YYPARSE_PARAM */
-#if defined __STDC__ || defined __cplusplus
+
+extern YYSTYPE yylval;
+extern YYLTYPE yylloc;
 int yyparse (void);
-#else
-int yyparse ();
-#endif
-#endif /* ! YYPARSE_PARAM */
 
 #endif /* !YY_YY_DTC_PARSER_TAB_H_INCLUDED  */
diff --git a/scripts/dtc/dtc-parser.y b/scripts/dtc/dtc-parser.y
index f412460..5a897e3 100644
--- a/scripts/dtc/dtc-parser.y
+++ b/scripts/dtc/dtc-parser.y
@@ -17,31 +17,27 @@
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
  *                                                                   USA
  */
-
 %{
 #include <stdio.h>
 
 #include "dtc.h"
 #include "srcpos.h"
 
-YYLTYPE yylloc;
-
 extern int yylex(void);
-extern void print_error(char const *fmt, ...);
 extern void yyerror(char const *s);
+#define ERROR(loc, ...) \
+	do { \
+		srcpos_error((loc), "Error", __VA_ARGS__); \
+		treesource_error = true; \
+	} while (0)
 
 extern struct boot_info *the_boot_info;
-extern int treesource_error;
-
-static unsigned long long eval_literal(const char *s, int base, int bits);
-static unsigned char eval_char_literal(const char *s);
+extern bool treesource_error;
 %}
 
 %union {
 	char *propnodename;
-	char *literal;
 	char *labelref;
-	unsigned int cbase;
 	uint8_t byte;
 	struct data data;
 
@@ -65,9 +61,8 @@
 %token DT_DEL_PROP
 %token DT_DEL_NODE
 %token <propnodename> DT_PROPNODENAME
-%token <literal> DT_LITERAL
-%token <literal> DT_CHAR_LITERAL
-%token <cbase> DT_BASE
+%token <integer> DT_LITERAL
+%token <integer> DT_CHAR_LITERAL
 %token <byte> DT_BYTE
 %token <data> DT_STRING
 %token <labelref> DT_LABEL
@@ -145,6 +140,18 @@
 		{
 			$$ = merge_nodes($1, $3);
 		}
+
+	| devicetree DT_LABEL DT_REF nodedef
+		{
+			struct node *target = get_node_by_ref($1, $3);
+
+			add_label(&target->labels, $2);
+			if (target)
+				merge_nodes(target, $4);
+			else
+				ERROR(&@3, "Label or path %s not found", $3);
+			$$ = $1;
+		}
 	| devicetree DT_REF nodedef
 		{
 			struct node *target = get_node_by_ref($1, $2);
@@ -152,17 +159,18 @@
 			if (target)
 				merge_nodes(target, $3);
 			else
-				print_error("label or path, '%s', not found", $2);
+				ERROR(&@2, "Label or path %s not found", $2);
 			$$ = $1;
 		}
 	| devicetree DT_DEL_NODE DT_REF ';'
 		{
 			struct node *target = get_node_by_ref($1, $3);
 
-			if (!target)
-				print_error("label or path, '%s', not found", $3);
-			else
+			if (target)
 				delete_node(target);
+			else
+				ERROR(&@3, "Label or path %s not found", $3);
+
 
 			$$ = $1;
 		}
@@ -230,10 +238,9 @@
 
 			if ($6 != 0)
 				if (fseek(f, $6, SEEK_SET) != 0)
-					print_error("Couldn't seek to offset %llu in \"%s\": %s",
-						     (unsigned long long)$6,
-						     $4.val,
-						     strerror(errno));
+					die("Couldn't seek to offset %llu in \"%s\": %s",
+					    (unsigned long long)$6, $4.val,
+					    strerror(errno));
 
 			d = data_copy_file(f, $8);
 
@@ -274,18 +281,19 @@
 arrayprefix:
 	DT_BITS DT_LITERAL '<'
 		{
-			$$.data = empty_data;
-			$$.bits = eval_literal($2, 0, 7);
+			unsigned long long bits;
 
-			if (($$.bits !=  8) &&
-			    ($$.bits != 16) &&
-			    ($$.bits != 32) &&
-			    ($$.bits != 64))
-			{
-				print_error("Only 8, 16, 32 and 64-bit elements"
-					    " are currently supported");
-				$$.bits = 32;
+			bits = $2;
+
+			if ((bits !=  8) && (bits != 16) &&
+			    (bits != 32) && (bits != 64)) {
+				ERROR(&@2, "Array elements must be"
+				      " 8, 16, 32 or 64-bits");
+				bits = 32;
 			}
+
+			$$.data = empty_data;
+			$$.bits = bits;
 		}
 	| '<'
 		{
@@ -305,9 +313,8 @@
 				 * mask), all bits are one.
 				 */
 				if (($2 > mask) && (($2 | mask) != -1ULL))
-					print_error(
-						"integer value out of range "
-						"%016lx (%d bits)", $1.bits);
+					ERROR(&@2, "Value out of range for"
+					      " %d-bit array element", $1.bits);
 			}
 
 			$$.data = data_append_integer($1.data, $2, $1.bits);
@@ -321,7 +328,7 @@
 							  REF_PHANDLE,
 							  $2);
 			else
-				print_error("References are only allowed in "
+				ERROR(&@2, "References are only allowed in "
 					    "arrays with 32-bit elements.");
 
 			$$.data = data_append_integer($1.data, val, $1.bits);
@@ -334,13 +341,7 @@
 
 integer_prim:
 	  DT_LITERAL
-		{
-			$$ = eval_literal($1, 0, 64);
-		}
 	| DT_CHAR_LITERAL
-		{
-			$$ = eval_char_literal($1);
-		}
 	| '(' integer_expr ')'
 		{
 			$$ = $2;
@@ -447,7 +448,7 @@
 		}
 	| subnode propdef
 		{
-			print_error("syntax error: properties must precede subnodes");
+			ERROR(&@2, "Properties must precede subnodes");
 			YYERROR;
 		}
 	;
@@ -470,63 +471,7 @@
 
 %%
 
-void print_error(char const *fmt, ...)
+void yyerror(char const *s)
 {
-	va_list va;
-
-	va_start(va, fmt);
-	srcpos_verror(&yylloc, fmt, va);
-	va_end(va);
-
-	treesource_error = 1;
-}
-
-void yyerror(char const *s) {
-	print_error("%s", s);
-}
-
-static unsigned long long eval_literal(const char *s, int base, int bits)
-{
-	unsigned long long val;
-	char *e;
-
-	errno = 0;
-	val = strtoull(s, &e, base);
-	if (*e) {
-		size_t uls = strspn(e, "UL");
-		if (e[uls])
-			print_error("bad characters in literal");
-	}
-	if ((errno == ERANGE)
-		 || ((bits < 64) && (val >= (1ULL << bits))))
-		print_error("literal out of range");
-	else if (errno != 0)
-		print_error("bad literal");
-	return val;
-}
-
-static unsigned char eval_char_literal(const char *s)
-{
-	int i = 1;
-	char c = s[0];
-
-	if (c == '\0')
-	{
-		print_error("empty character literal");
-		return 0;
-	}
-
-	/*
-	 * If the first character in the character literal is a \ then process
-	 * the remaining characters as an escape encoding. If the first
-	 * character is neither an escape or a terminator it should be the only
-	 * character in the literal and will be returned.
-	 */
-	if (c == '\\')
-		c = get_escape_char(s, &i);
-
-	if (s[i] != '\0')
-		print_error("malformed character literal");
-
-	return c;
+	ERROR(&yylloc, "%s", s);
 }
diff --git a/scripts/dtc/dtc.c b/scripts/dtc/dtc.c
index e3c9653..8c4add6 100644
--- a/scripts/dtc/dtc.c
+++ b/scripts/dtc/dtc.c
@@ -48,6 +48,8 @@
 }
 
 /* Usage related data. */
+#define FDT_VERSION(version)	_FDT_VERSION(version)
+#define _FDT_VERSION(version)	#version
 static const char usage_synopsis[] = "dtc [options] <input file>";
 static const char usage_short_opts[] = "qI:O:o:V:d:R:S:p:fb:i:H:sW:E:hv";
 static struct option const usage_long_opts[] = {
@@ -82,9 +84,9 @@
 	 "\t\tdts - device tree source text\n"
 	 "\t\tdtb - device tree blob\n"
 	 "\t\tasm - assembler source",
-	"\n\tBlob version to produce, defaults to %d (for dtb and asm output)", //, DEFAULT_FDT_VERSION);
+	"\n\tBlob version to produce, defaults to "FDT_VERSION(DEFAULT_FDT_VERSION)" (for dtb and asm output)",
 	"\n\tOutput dependency file",
-	"\n\ttMake space for <number> reserve map entries (for dtb and asm output)",
+	"\n\tMake space for <number> reserve map entries (for dtb and asm output)",
 	"\n\tMake the blob at least <bytes> long (extra space)",
 	"\n\tAdd padding to the blob of <bytes> long (extra space)",
 	"\n\tSet the physical boot cpu",
@@ -109,7 +111,7 @@
 	const char *outform = "dts";
 	const char *outname = "-";
 	const char *depname = NULL;
-	int force = 0, sort = 0;
+	bool force = false, sort = false;
 	const char *arg;
 	int opt;
 	FILE *outf = NULL;
@@ -148,7 +150,7 @@
 			padsize = strtol(optarg, NULL, 0);
 			break;
 		case 'f':
-			force = 1;
+			force = true;
 			break;
 		case 'q':
 			quiet++;
@@ -174,7 +176,7 @@
 			break;
 
 		case 's':
-			sort = 1;
+			sort = true;
 			break;
 
 		case 'W':
@@ -237,7 +239,7 @@
 	if (streq(outname, "-")) {
 		outf = stdout;
 	} else {
-		outf = fopen(outname, "w");
+		outf = fopen(outname, "wb");
 		if (! outf)
 			die("Couldn't open output file %s: %s\n",
 			    outname, strerror(errno));
diff --git a/scripts/dtc/dtc.h b/scripts/dtc/dtc.h
index 264a20c..56212c8 100644
--- a/scripts/dtc/dtc.h
+++ b/scripts/dtc/dtc.h
@@ -38,9 +38,9 @@
 #include "util.h"
 
 #ifdef DEBUG
-#define debug(fmt,args...)	printf(fmt, ##args)
+#define debug(...)	printf(__VA_ARGS__)
 #else
-#define debug(fmt,args...)
+#define debug(...)
 #endif
 
 
@@ -88,7 +88,7 @@
 };
 
 
-#define empty_data ((struct data){ /* all .members = 0 or NULL */ })
+#define empty_data ((struct data){ 0 /* all .members = 0 or NULL */ })
 
 #define for_each_marker(m) \
 	for (; (m); (m) = (m)->next)
@@ -118,7 +118,7 @@
 
 struct data data_add_marker(struct data d, enum markertype type, char *ref);
 
-int data_is_one_string(struct data d);
+bool data_is_one_string(struct data d);
 
 /* DT constraints */
 
@@ -127,13 +127,13 @@
 
 /* Live trees */
 struct label {
-	int deleted;
+	bool deleted;
 	char *label;
 	struct label *next;
 };
 
 struct property {
-	int deleted;
+	bool deleted;
 	char *name;
 	struct data val;
 
@@ -143,7 +143,7 @@
 };
 
 struct node {
-	int deleted;
+	bool deleted;
 	char *name;
 	struct property *proplist;
 	struct node *children;
@@ -247,8 +247,8 @@
 
 /* Checks */
 
-void parse_checks_option(bool warn, bool error, const char *optarg);
-void process_checks(int force, struct boot_info *bi);
+void parse_checks_option(bool warn, bool error, const char *arg);
+void process_checks(bool force, struct boot_info *bi);
 
 /* Flattened trees */
 
diff --git a/scripts/dtc/flattree.c b/scripts/dtc/flattree.c
index 665dad7..bd99fa2 100644
--- a/scripts/dtc/flattree.c
+++ b/scripts/dtc/flattree.c
@@ -261,7 +261,7 @@
 {
 	struct property *prop;
 	struct node *child;
-	int seen_name_prop = 0;
+	bool seen_name_prop = false;
 
 	if (tree->deleted)
 		return;
@@ -279,7 +279,7 @@
 		int nameoff;
 
 		if (streq(prop->name, "name"))
-			seen_name_prop = 1;
+			seen_name_prop = true;
 
 		nameoff = stringtable_insert(strbuf, prop->name);
 
diff --git a/scripts/dtc/fstree.c b/scripts/dtc/fstree.c
index e464727c..6d1beec 100644
--- a/scripts/dtc/fstree.c
+++ b/scripts/dtc/fstree.c
@@ -37,26 +37,26 @@
 	tree = build_node(NULL, NULL);
 
 	while ((de = readdir(d)) != NULL) {
-		char *tmpnam;
+		char *tmpname;
 
 		if (streq(de->d_name, ".")
 		    || streq(de->d_name, ".."))
 			continue;
 
-		tmpnam = join_path(dirname, de->d_name);
+		tmpname = join_path(dirname, de->d_name);
 
-		if (lstat(tmpnam, &st) < 0)
-			die("stat(%s): %s\n", tmpnam, strerror(errno));
+		if (lstat(tmpname, &st) < 0)
+			die("stat(%s): %s\n", tmpname, strerror(errno));
 
 		if (S_ISREG(st.st_mode)) {
 			struct property *prop;
 			FILE *pfile;
 
-			pfile = fopen(tmpnam, "r");
+			pfile = fopen(tmpname, "rb");
 			if (! pfile) {
 				fprintf(stderr,
 					"WARNING: Cannot open %s: %s\n",
-					tmpnam, strerror(errno));
+					tmpname, strerror(errno));
 			} else {
 				prop = build_property(xstrdup(de->d_name),
 						      data_copy_file(pfile,
@@ -67,12 +67,12 @@
 		} else if (S_ISDIR(st.st_mode)) {
 			struct node *newchild;
 
-			newchild = read_fstree(tmpnam);
+			newchild = read_fstree(tmpname);
 			newchild = name_node(newchild, xstrdup(de->d_name));
 			add_child(tree, newchild);
 		}
 
-		free(tmpnam);
+		free(tmpname);
 	}
 
 	closedir(d);
@@ -88,3 +88,4 @@
 
 	return build_boot_info(NULL, tree, guess_boot_cpuid(tree));
 }
+
diff --git a/scripts/dtc/libfdt/Makefile.libfdt b/scripts/dtc/libfdt/Makefile.libfdt
index 91126c0..09c322ed 100644
--- a/scripts/dtc/libfdt/Makefile.libfdt
+++ b/scripts/dtc/libfdt/Makefile.libfdt
@@ -6,5 +6,6 @@
 LIBFDT_soname = libfdt.$(SHAREDLIB_EXT).1
 LIBFDT_INCLUDES = fdt.h libfdt.h libfdt_env.h
 LIBFDT_VERSION = version.lds
-LIBFDT_SRCS = fdt.c fdt_ro.c fdt_wip.c fdt_sw.c fdt_rw.c fdt_strerror.c fdt_empty_tree.c
+LIBFDT_SRCS = fdt.c fdt_ro.c fdt_wip.c fdt_sw.c fdt_rw.c fdt_strerror.c fdt_empty_tree.c \
+	fdt_addresses.c
 LIBFDT_OBJS = $(LIBFDT_SRCS:%.c=%.o)
diff --git a/scripts/dtc/libfdt/fdt.c b/scripts/dtc/libfdt/fdt.c
index e56833a..2ce6a44 100644
--- a/scripts/dtc/libfdt/fdt.c
+++ b/scripts/dtc/libfdt/fdt.c
@@ -92,7 +92,7 @@
 
 uint32_t fdt_next_tag(const void *fdt, int startoffset, int *nextoffset)
 {
-	const uint32_t *tagp, *lenp;
+	const fdt32_t *tagp, *lenp;
 	uint32_t tag;
 	int offset = startoffset;
 	const char *p;
@@ -198,6 +198,34 @@
 	return offset;
 }
 
+int fdt_first_subnode(const void *fdt, int offset)
+{
+	int depth = 0;
+
+	offset = fdt_next_node(fdt, offset, &depth);
+	if (offset < 0 || depth != 1)
+		return -FDT_ERR_NOTFOUND;
+
+	return offset;
+}
+
+int fdt_next_subnode(const void *fdt, int offset)
+{
+	int depth = 1;
+
+	/*
+	 * With respect to the parent, the depth of the next subnode will be
+	 * the same as the last.
+	 */
+	do {
+		offset = fdt_next_node(fdt, offset, &depth);
+		if (offset < 0 || depth < 1)
+			return -FDT_ERR_NOTFOUND;
+	} while (depth > 1);
+
+	return offset;
+}
+
 const char *_fdt_find_string(const char *strtab, int tabsize, const char *s)
 {
 	int len = strlen(s) + 1;
diff --git a/scripts/dtc/libfdt/fdt.h b/scripts/dtc/libfdt/fdt.h
index 48ccfd9..526aedb 100644
--- a/scripts/dtc/libfdt/fdt.h
+++ b/scripts/dtc/libfdt/fdt.h
@@ -1,48 +1,99 @@
 #ifndef _FDT_H
 #define _FDT_H
+/*
+ * libfdt - Flat Device Tree manipulation
+ * Copyright (C) 2006 David Gibson, IBM Corporation.
+ * Copyright 2012 Kim Phillips, Freescale Semiconductor.
+ *
+ * libfdt is dual licensed: you can use it either under the terms of
+ * the GPL, or the BSD license, at your option.
+ *
+ *  a) This library is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This library is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *     You should have received a copy of the GNU General Public
+ *     License along with this library; if not, write to the Free
+ *     Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston,
+ *     MA 02110-1301 USA
+ *
+ * Alternatively,
+ *
+ *  b) Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *     1. Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *     2. Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ *     THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+ *     CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ *     INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *     MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *     DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+ *     CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *     SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+ *     NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ *     LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ *     HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ *     OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
+ *     EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
 
 #ifndef __ASSEMBLY__
 
 struct fdt_header {
-	uint32_t magic;			 /* magic word FDT_MAGIC */
-	uint32_t totalsize;		 /* total size of DT block */
-	uint32_t off_dt_struct;		 /* offset to structure */
-	uint32_t off_dt_strings;	 /* offset to strings */
-	uint32_t off_mem_rsvmap;	 /* offset to memory reserve map */
-	uint32_t version;		 /* format version */
-	uint32_t last_comp_version;	 /* last compatible version */
+	fdt32_t magic;			 /* magic word FDT_MAGIC */
+	fdt32_t totalsize;		 /* total size of DT block */
+	fdt32_t off_dt_struct;		 /* offset to structure */
+	fdt32_t off_dt_strings;		 /* offset to strings */
+	fdt32_t off_mem_rsvmap;		 /* offset to memory reserve map */
+	fdt32_t version;		 /* format version */
+	fdt32_t last_comp_version;	 /* last compatible version */
 
 	/* version 2 fields below */
-	uint32_t boot_cpuid_phys;	 /* Which physical CPU id we're
+	fdt32_t boot_cpuid_phys;	 /* Which physical CPU id we're
 					    booting on */
 	/* version 3 fields below */
-	uint32_t size_dt_strings;	 /* size of the strings block */
+	fdt32_t size_dt_strings;	 /* size of the strings block */
 
 	/* version 17 fields below */
-	uint32_t size_dt_struct;	 /* size of the structure block */
+	fdt32_t size_dt_struct;		 /* size of the structure block */
 };
 
 struct fdt_reserve_entry {
-	uint64_t address;
-	uint64_t size;
+	fdt64_t address;
+	fdt64_t size;
 };
 
 struct fdt_node_header {
-	uint32_t tag;
+	fdt32_t tag;
 	char name[0];
 };
 
 struct fdt_property {
-	uint32_t tag;
-	uint32_t len;
-	uint32_t nameoff;
+	fdt32_t tag;
+	fdt32_t len;
+	fdt32_t nameoff;
 	char data[0];
 };
 
 #endif /* !__ASSEMBLY */
 
 #define FDT_MAGIC	0xd00dfeed	/* 4: version, 4: total size */
-#define FDT_TAGSIZE	sizeof(uint32_t)
+#define FDT_TAGSIZE	sizeof(fdt32_t)
 
 #define FDT_BEGIN_NODE	0x1		/* Start node: full name */
 #define FDT_END_NODE	0x2		/* End node */
@@ -51,10 +102,10 @@
 #define FDT_NOP		0x4		/* nop */
 #define FDT_END		0x9
 
-#define FDT_V1_SIZE	(7*sizeof(uint32_t))
-#define FDT_V2_SIZE	(FDT_V1_SIZE + sizeof(uint32_t))
-#define FDT_V3_SIZE	(FDT_V2_SIZE + sizeof(uint32_t))
+#define FDT_V1_SIZE	(7*sizeof(fdt32_t))
+#define FDT_V2_SIZE	(FDT_V1_SIZE + sizeof(fdt32_t))
+#define FDT_V3_SIZE	(FDT_V2_SIZE + sizeof(fdt32_t))
 #define FDT_V16_SIZE	FDT_V3_SIZE
-#define FDT_V17_SIZE	(FDT_V16_SIZE + sizeof(uint32_t))
+#define FDT_V17_SIZE	(FDT_V16_SIZE + sizeof(fdt32_t))
 
 #endif /* _FDT_H */
diff --git a/scripts/dtc/libfdt/fdt_empty_tree.c b/scripts/dtc/libfdt/fdt_empty_tree.c
index f2ae9b7..f72d13b 100644
--- a/scripts/dtc/libfdt/fdt_empty_tree.c
+++ b/scripts/dtc/libfdt/fdt_empty_tree.c
@@ -81,3 +81,4 @@
 
 	return fdt_open_into(buf, buf, bufsize);
 }
+
diff --git a/scripts/dtc/libfdt/fdt_ro.c b/scripts/dtc/libfdt/fdt_ro.c
index 02b6d68..a65e4b5 100644
--- a/scripts/dtc/libfdt/fdt_ro.c
+++ b/scripts/dtc/libfdt/fdt_ro.c
@@ -154,9 +154,9 @@
 	return fdt_subnode_offset_namelen(fdt, parentoffset, name, strlen(name));
 }
 
-int fdt_path_offset(const void *fdt, const char *path)
+int fdt_path_offset_namelen(const void *fdt, const char *path, int namelen)
 {
-	const char *end = path + strlen(path);
+	const char *end = path + namelen;
 	const char *p = path;
 	int offset = 0;
 
@@ -164,7 +164,7 @@
 
 	/* see if we have an alias */
 	if (*path != '/') {
-		const char *q = strchr(path, '/');
+		const char *q = memchr(path, '/', end - p);
 
 		if (!q)
 			q = end;
@@ -177,14 +177,15 @@
 		p = q;
 	}
 
-	while (*p) {
+	while (p < end) {
 		const char *q;
 
-		while (*p == '/')
+		while (*p == '/') {
 			p++;
-		if (! *p)
-			return offset;
-		q = strchr(p, '/');
+			if (p == end)
+				return offset;
+		}
+		q = memchr(p, '/', end - p);
 		if (! q)
 			q = end;
 
@@ -198,6 +199,11 @@
 	return offset;
 }
 
+int fdt_path_offset(const void *fdt, const char *path)
+{
+	return fdt_path_offset_namelen(fdt, path, strlen(path));
+}
+
 const char *fdt_get_name(const void *fdt, int nodeoffset, int *len)
 {
 	const struct fdt_node_header *nh = _fdt_offset_ptr(fdt, nodeoffset);
@@ -322,7 +328,7 @@
 
 uint32_t fdt_get_phandle(const void *fdt, int nodeoffset)
 {
-	const uint32_t *php;
+	const fdt32_t *php;
 	int len;
 
 	/* FIXME: This is a bit sub-optimal, since we potentially scan
@@ -515,8 +521,7 @@
 	return offset; /* error from fdt_next_node() */
 }
 
-static int _fdt_stringlist_contains(const char *strlist, int listlen,
-				    const char *str)
+int fdt_stringlist_contains(const char *strlist, int listlen, const char *str)
 {
 	int len = strlen(str);
 	const char *p;
@@ -542,7 +547,7 @@
 	prop = fdt_getprop(fdt, nodeoffset, "compatible", &len);
 	if (!prop)
 		return len;
-	if (_fdt_stringlist_contains(prop, len, compatible))
+	if (fdt_stringlist_contains(prop, len, compatible))
 		return 0;
 	else
 		return 1;
diff --git a/scripts/dtc/libfdt/fdt_rw.c b/scripts/dtc/libfdt/fdt_rw.c
index 24437df..70adec6 100644
--- a/scripts/dtc/libfdt/fdt_rw.c
+++ b/scripts/dtc/libfdt/fdt_rw.c
@@ -84,9 +84,9 @@
 
 #define FDT_RW_CHECK_HEADER(fdt) \
 	{ \
-		int err; \
-		if ((err = _fdt_rw_check_header(fdt)) != 0) \
-			return err; \
+		int __err; \
+		if ((__err = _fdt_rw_check_header(fdt)) != 0) \
+			return __err; \
 	}
 
 static inline int _fdt_data_size(void *fdt)
@@ -339,7 +339,7 @@
 	int nodelen;
 	int err;
 	uint32_t tag;
-	uint32_t *endtag;
+	fdt32_t *endtag;
 
 	FDT_RW_CHECK_HEADER(fdt);
 
@@ -366,7 +366,7 @@
 	nh->tag = cpu_to_fdt32(FDT_BEGIN_NODE);
 	memset(nh->name, 0, FDT_TAGALIGN(namelen+1));
 	memcpy(nh->name, name, namelen);
-	endtag = (uint32_t *)((char *)nh + nodelen - FDT_TAGSIZE);
+	endtag = (fdt32_t *)((char *)nh + nodelen - FDT_TAGSIZE);
 	*endtag = cpu_to_fdt32(FDT_END_NODE);
 
 	return offset;
diff --git a/scripts/dtc/libfdt/fdt_sw.c b/scripts/dtc/libfdt/fdt_sw.c
index 55ebebf..6a80485 100644
--- a/scripts/dtc/libfdt/fdt_sw.c
+++ b/scripts/dtc/libfdt/fdt_sw.c
@@ -107,6 +107,38 @@
 	return 0;
 }
 
+int fdt_resize(void *fdt, void *buf, int bufsize)
+{
+	size_t headsize, tailsize;
+	char *oldtail, *newtail;
+
+	FDT_SW_CHECK_HEADER(fdt);
+
+	headsize = fdt_off_dt_struct(fdt);
+	tailsize = fdt_size_dt_strings(fdt);
+
+	if ((headsize + tailsize) > bufsize)
+		return -FDT_ERR_NOSPACE;
+
+	oldtail = (char *)fdt + fdt_totalsize(fdt) - tailsize;
+	newtail = (char *)buf + bufsize - tailsize;
+
+	/* Two cases to avoid clobbering data if the old and new
+	 * buffers partially overlap */
+	if (buf <= fdt) {
+		memmove(buf, fdt, headsize);
+		memmove(newtail, oldtail, tailsize);
+	} else {
+		memmove(newtail, oldtail, tailsize);
+		memmove(buf, fdt, headsize);
+	}
+
+	fdt_set_off_dt_strings(buf, bufsize);
+	fdt_set_totalsize(buf, bufsize);
+
+	return 0;
+}
+
 int fdt_add_reservemap_entry(void *fdt, uint64_t addr, uint64_t size)
 {
 	struct fdt_reserve_entry *re;
@@ -153,7 +185,7 @@
 
 int fdt_end_node(void *fdt)
 {
-	uint32_t *en;
+	fdt32_t *en;
 
 	FDT_SW_CHECK_HEADER(fdt);
 
@@ -213,7 +245,7 @@
 int fdt_finish(void *fdt)
 {
 	char *p = (char *)fdt;
-	uint32_t *end;
+	fdt32_t *end;
 	int oldstroffset, newstroffset;
 	uint32_t tag;
 	int offset, nextoffset;
diff --git a/scripts/dtc/libfdt/fdt_wip.c b/scripts/dtc/libfdt/fdt_wip.c
index 6025fa1..c5bbb68 100644
--- a/scripts/dtc/libfdt/fdt_wip.c
+++ b/scripts/dtc/libfdt/fdt_wip.c
@@ -74,7 +74,7 @@
 
 static void _fdt_nop_region(void *start, int len)
 {
-	uint32_t *p;
+	fdt32_t *p;
 
 	for (p = start; (char *)p < ((char *)start + len); p++)
 		*p = cpu_to_fdt32(FDT_NOP);
diff --git a/scripts/dtc/libfdt/libfdt.h b/scripts/dtc/libfdt/libfdt.h
index 73f4975..ea35ac3 100644
--- a/scripts/dtc/libfdt/libfdt.h
+++ b/scripts/dtc/libfdt/libfdt.h
@@ -51,8 +51,8 @@
  *     EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
-#include <libfdt_env.h>
-#include <fdt.h>
+#include "libfdt_env.h"
+#include "fdt.h"
 
 #define FDT_FIRST_SUPPORTED_VERSION	0x10
 #define FDT_LAST_SUPPORTED_VERSION	0x11
@@ -116,7 +116,12 @@
 	 * Should never be returned, if it is, it indicates a bug in
 	 * libfdt itself. */
 
-#define FDT_ERR_MAX		13
+/* Errors in device tree content */
+#define FDT_ERR_BADNCELLS	14
+	/* FDT_ERR_BADNCELLS: Device tree has a #address-cells, #size-cells
+	 * or similar property with a bad format or value */
+
+#define FDT_ERR_MAX		14
 
 /**********************************************************************/
 /* Low-level functions (you probably don't need these)                */
@@ -136,6 +141,28 @@
 
 int fdt_next_node(const void *fdt, int offset, int *depth);
 
+/**
+ * fdt_first_subnode() - get offset of first direct subnode
+ *
+ * @fdt:	FDT blob
+ * @offset:	Offset of node to check
+ * @return offset of first subnode, or -FDT_ERR_NOTFOUND if there is none
+ */
+int fdt_first_subnode(const void *fdt, int offset);
+
+/**
+ * fdt_next_subnode() - get offset of next direct subnode
+ *
+ * After first calling fdt_first_subnode(), call this function repeatedly to
+ * get direct subnodes of a parent node.
+ *
+ * @fdt:	FDT blob
+ * @offset:	Offset of previous subnode
+ * @return offset of next subnode, or -FDT_ERR_NOTFOUND if there are no more
+ * subnodes
+ */
+int fdt_next_subnode(const void *fdt, int offset);
+
 /**********************************************************************/
 /* General functions                                                  */
 /**********************************************************************/
@@ -296,6 +323,17 @@
 int fdt_subnode_offset(const void *fdt, int parentoffset, const char *name);
 
 /**
+ * fdt_path_offset_namelen - find a tree node by its full path
+ * @fdt: pointer to the device tree blob
+ * @path: full path of the node to locate
+ * @namelen: number of characters of path to consider
+ *
+ * Identical to fdt_path_offset(), but only consider the first namelen
+ * characters of path as the path name.
+ */
+int fdt_path_offset_namelen(const void *fdt, const char *path, int namelen);
+
+/**
  * fdt_path_offset - find a tree node by its full path
  * @fdt: pointer to the device tree blob
  * @path: full path of the node to locate
@@ -582,7 +620,7 @@
  * value of the property named 'name' in the node /aliases.
  *
  * returns:
- *	a pointer to the expansion of the alias named 'name', of it exists
+ *	a pointer to the expansion of the alias named 'name', if it exists
  *	NULL, if the given alias or the /aliases node does not exist
  */
 const char *fdt_get_alias(const void *fdt, const char *name);
@@ -816,6 +854,75 @@
 int fdt_node_offset_by_compatible(const void *fdt, int startoffset,
 				  const char *compatible);
 
+/**
+ * fdt_stringlist_contains - check a string list property for a string
+ * @strlist: Property containing a list of strings to check
+ * @listlen: Length of property
+ * @str: String to search for
+ *
+ * This is a utility function provided for convenience. The list contains
+ * one or more strings, each terminated by \0, as is found in a device tree
+ * "compatible" property.
+ *
+ * @return: 1 if the string is found in the list, 0 not found, or invalid list
+ */
+int fdt_stringlist_contains(const char *strlist, int listlen, const char *str);
+
+/**********************************************************************/
+/* Read-only functions (addressing related)                           */
+/**********************************************************************/
+
+/**
+ * FDT_MAX_NCELLS - maximum value for #address-cells and #size-cells
+ *
+ * This is the maximum value for #address-cells, #size-cells and
+ * similar properties that will be processed by libfdt.  IEE1275
+ * requires that OF implementations handle values up to 4.
+ * Implementations may support larger values, but in practice higher
+ * values aren't used.
+ */
+#define FDT_MAX_NCELLS		4
+
+/**
+ * fdt_address_cells - retrieve address size for a bus represented in the tree
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node to find the address size for
+ *
+ * When the node has a valid #address-cells property, returns its value.
+ *
+ * returns:
+ *	0 <= n < FDT_MAX_NCELLS, on success
+ *      2, if the node has no #address-cells property
+ *      -FDT_ERR_BADNCELLS, if the node has a badly formatted or invalid #address-cells property
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_TRUNCATED, standard meanings
+ */
+int fdt_address_cells(const void *fdt, int nodeoffset);
+
+/**
+ * fdt_size_cells - retrieve address range size for a bus represented in the
+ *                  tree
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node to find the address range size for
+ *
+ * When the node has a valid #size-cells property, returns its value.
+ *
+ * returns:
+ *	0 <= n < FDT_MAX_NCELLS, on success
+ *      2, if the node has no #address-cells property
+ *      -FDT_ERR_BADNCELLS, if the node has a badly formatted or invalid #size-cells property
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_TRUNCATED, standard meanings
+ */
+int fdt_size_cells(const void *fdt, int nodeoffset);
+
+
 /**********************************************************************/
 /* Write-in-place functions                                           */
 /**********************************************************************/
@@ -882,8 +989,8 @@
 static inline int fdt_setprop_inplace_u32(void *fdt, int nodeoffset,
 					  const char *name, uint32_t val)
 {
-	val = cpu_to_fdt32(val);
-	return fdt_setprop_inplace(fdt, nodeoffset, name, &val, sizeof(val));
+	fdt32_t tmp = cpu_to_fdt32(val);
+	return fdt_setprop_inplace(fdt, nodeoffset, name, &tmp, sizeof(tmp));
 }
 
 /**
@@ -917,8 +1024,8 @@
 static inline int fdt_setprop_inplace_u64(void *fdt, int nodeoffset,
 					  const char *name, uint64_t val)
 {
-	val = cpu_to_fdt64(val);
-	return fdt_setprop_inplace(fdt, nodeoffset, name, &val, sizeof(val));
+	fdt64_t tmp = cpu_to_fdt64(val);
+	return fdt_setprop_inplace(fdt, nodeoffset, name, &tmp, sizeof(tmp));
 }
 
 /**
@@ -987,19 +1094,20 @@
 /**********************************************************************/
 
 int fdt_create(void *buf, int bufsize);
+int fdt_resize(void *fdt, void *buf, int bufsize);
 int fdt_add_reservemap_entry(void *fdt, uint64_t addr, uint64_t size);
 int fdt_finish_reservemap(void *fdt);
 int fdt_begin_node(void *fdt, const char *name);
 int fdt_property(void *fdt, const char *name, const void *val, int len);
 static inline int fdt_property_u32(void *fdt, const char *name, uint32_t val)
 {
-	val = cpu_to_fdt32(val);
-	return fdt_property(fdt, name, &val, sizeof(val));
+	fdt32_t tmp = cpu_to_fdt32(val);
+	return fdt_property(fdt, name, &tmp, sizeof(tmp));
 }
 static inline int fdt_property_u64(void *fdt, const char *name, uint64_t val)
 {
-	val = cpu_to_fdt64(val);
-	return fdt_property(fdt, name, &val, sizeof(val));
+	fdt64_t tmp = cpu_to_fdt64(val);
+	return fdt_property(fdt, name, &tmp, sizeof(tmp));
 }
 static inline int fdt_property_cell(void *fdt, const char *name, uint32_t val)
 {
@@ -1154,8 +1262,8 @@
 static inline int fdt_setprop_u32(void *fdt, int nodeoffset, const char *name,
 				  uint32_t val)
 {
-	val = cpu_to_fdt32(val);
-	return fdt_setprop(fdt, nodeoffset, name, &val, sizeof(val));
+	fdt32_t tmp = cpu_to_fdt32(val);
+	return fdt_setprop(fdt, nodeoffset, name, &tmp, sizeof(tmp));
 }
 
 /**
@@ -1189,8 +1297,8 @@
 static inline int fdt_setprop_u64(void *fdt, int nodeoffset, const char *name,
 				  uint64_t val)
 {
-	val = cpu_to_fdt64(val);
-	return fdt_setprop(fdt, nodeoffset, name, &val, sizeof(val));
+	fdt64_t tmp = cpu_to_fdt64(val);
+	return fdt_setprop(fdt, nodeoffset, name, &tmp, sizeof(tmp));
 }
 
 /**
@@ -1296,8 +1404,8 @@
 static inline int fdt_appendprop_u32(void *fdt, int nodeoffset,
 				     const char *name, uint32_t val)
 {
-	val = cpu_to_fdt32(val);
-	return fdt_appendprop(fdt, nodeoffset, name, &val, sizeof(val));
+	fdt32_t tmp = cpu_to_fdt32(val);
+	return fdt_appendprop(fdt, nodeoffset, name, &tmp, sizeof(tmp));
 }
 
 /**
@@ -1331,8 +1439,8 @@
 static inline int fdt_appendprop_u64(void *fdt, int nodeoffset,
 				     const char *name, uint64_t val)
 {
-	val = cpu_to_fdt64(val);
-	return fdt_appendprop(fdt, nodeoffset, name, &val, sizeof(val));
+	fdt64_t tmp = cpu_to_fdt64(val);
+	return fdt_appendprop(fdt, nodeoffset, name, &tmp, sizeof(tmp));
 }
 
 /**
diff --git a/scripts/dtc/libfdt/libfdt_env.h b/scripts/dtc/libfdt/libfdt_env.h
index 213d7fb..9dea97d 100644
--- a/scripts/dtc/libfdt/libfdt_env.h
+++ b/scripts/dtc/libfdt/libfdt_env.h
@@ -1,29 +1,111 @@
 #ifndef _LIBFDT_ENV_H
 #define _LIBFDT_ENV_H
+/*
+ * libfdt - Flat Device Tree manipulation
+ * Copyright (C) 2006 David Gibson, IBM Corporation.
+ * Copyright 2012 Kim Phillips, Freescale Semiconductor.
+ *
+ * libfdt is dual licensed: you can use it either under the terms of
+ * the GPL, or the BSD license, at your option.
+ *
+ *  a) This library is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This library is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *     You should have received a copy of the GNU General Public
+ *     License along with this library; if not, write to the Free
+ *     Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston,
+ *     MA 02110-1301 USA
+ *
+ * Alternatively,
+ *
+ *  b) Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *     1. Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *     2. Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ *     THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+ *     CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ *     INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *     MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *     DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+ *     CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *     SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+ *     NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ *     LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ *     HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ *     OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
+ *     EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
 
 #include <stddef.h>
 #include <stdint.h>
 #include <string.h>
 
-#define EXTRACT_BYTE(n)	((unsigned long long)((uint8_t *)&x)[n])
-static inline uint16_t fdt16_to_cpu(uint16_t x)
-{
-	return (EXTRACT_BYTE(0) << 8) | EXTRACT_BYTE(1);
-}
-#define cpu_to_fdt16(x) fdt16_to_cpu(x)
+#ifdef __CHECKER__
+#define __force __attribute__((force))
+#define __bitwise __attribute__((bitwise))
+#else
+#define __force
+#define __bitwise
+#endif
 
-static inline uint32_t fdt32_to_cpu(uint32_t x)
-{
-	return (EXTRACT_BYTE(0) << 24) | (EXTRACT_BYTE(1) << 16) | (EXTRACT_BYTE(2) << 8) | EXTRACT_BYTE(3);
-}
-#define cpu_to_fdt32(x) fdt32_to_cpu(x)
+typedef uint16_t __bitwise fdt16_t;
+typedef uint32_t __bitwise fdt32_t;
+typedef uint64_t __bitwise fdt64_t;
 
-static inline uint64_t fdt64_to_cpu(uint64_t x)
+#define EXTRACT_BYTE(x, n)	((unsigned long long)((uint8_t *)&x)[n])
+#define CPU_TO_FDT16(x) ((EXTRACT_BYTE(x, 0) << 8) | EXTRACT_BYTE(x, 1))
+#define CPU_TO_FDT32(x) ((EXTRACT_BYTE(x, 0) << 24) | (EXTRACT_BYTE(x, 1) << 16) | \
+			 (EXTRACT_BYTE(x, 2) << 8) | EXTRACT_BYTE(x, 3))
+#define CPU_TO_FDT64(x) ((EXTRACT_BYTE(x, 0) << 56) | (EXTRACT_BYTE(x, 1) << 48) | \
+			 (EXTRACT_BYTE(x, 2) << 40) | (EXTRACT_BYTE(x, 3) << 32) | \
+			 (EXTRACT_BYTE(x, 4) << 24) | (EXTRACT_BYTE(x, 5) << 16) | \
+			 (EXTRACT_BYTE(x, 6) << 8) | EXTRACT_BYTE(x, 7))
+
+static inline uint16_t fdt16_to_cpu(fdt16_t x)
 {
-	return (EXTRACT_BYTE(0) << 56) | (EXTRACT_BYTE(1) << 48) | (EXTRACT_BYTE(2) << 40) | (EXTRACT_BYTE(3) << 32)
-		| (EXTRACT_BYTE(4) << 24) | (EXTRACT_BYTE(5) << 16) | (EXTRACT_BYTE(6) << 8) | EXTRACT_BYTE(7);
+	return (__force uint16_t)CPU_TO_FDT16(x);
 }
-#define cpu_to_fdt64(x) fdt64_to_cpu(x)
+static inline fdt16_t cpu_to_fdt16(uint16_t x)
+{
+	return (__force fdt16_t)CPU_TO_FDT16(x);
+}
+
+static inline uint32_t fdt32_to_cpu(fdt32_t x)
+{
+	return (__force uint32_t)CPU_TO_FDT32(x);
+}
+static inline fdt32_t cpu_to_fdt32(uint32_t x)
+{
+	return (__force fdt32_t)CPU_TO_FDT32(x);
+}
+
+static inline uint64_t fdt64_to_cpu(fdt64_t x)
+{
+	return (__force uint64_t)CPU_TO_FDT64(x);
+}
+static inline fdt64_t cpu_to_fdt64(uint64_t x)
+{
+	return (__force fdt64_t)CPU_TO_FDT64(x);
+}
+#undef CPU_TO_FDT64
+#undef CPU_TO_FDT32
+#undef CPU_TO_FDT16
 #undef EXTRACT_BYTE
 
 #endif /* _LIBFDT_ENV_H */
diff --git a/scripts/dtc/libfdt/libfdt_internal.h b/scripts/dtc/libfdt/libfdt_internal.h
index 381133b..02cfa6f 100644
--- a/scripts/dtc/libfdt/libfdt_internal.h
+++ b/scripts/dtc/libfdt/libfdt_internal.h
@@ -57,9 +57,9 @@
 
 #define FDT_CHECK_HEADER(fdt) \
 	{ \
-		int err; \
-		if ((err = fdt_check_header(fdt)) != 0) \
-			return err; \
+		int __err; \
+		if ((__err = fdt_check_header(fdt)) != 0) \
+			return __err; \
 	}
 
 int _fdt_check_node_offset(const void *fdt, int offset);
diff --git a/scripts/dtc/livetree.c b/scripts/dtc/livetree.c
index b61465f..e229b84 100644
--- a/scripts/dtc/livetree.c
+++ b/scripts/dtc/livetree.c
@@ -511,7 +511,9 @@
 
 struct node *get_node_by_ref(struct node *tree, const char *ref)
 {
-	if (ref[0] == '/')
+	if (streq(ref, "/"))
+		return tree;
+	else if (ref[0] == '/')
 		return get_node_by_path(tree, ref);
 	else
 		return get_node_by_label(tree, ref);
diff --git a/scripts/dtc/srcpos.c b/scripts/dtc/srcpos.c
index c20bc53..f534c22 100644
--- a/scripts/dtc/srcpos.c
+++ b/scripts/dtc/srcpos.c
@@ -34,7 +34,7 @@
 static struct search_path *search_path_head, **search_path_tail;
 
 
-static char *dirname(const char *path)
+static char *get_dirname(const char *path)
 {
 	const char *slash = strrchr(path, '/');
 
@@ -77,7 +77,7 @@
 	else
 		fullname = join_path(dirname, fname);
 
-	*fp = fopen(fullname, "r");
+	*fp = fopen(fullname, "rb");
 	if (!*fp) {
 		free(fullname);
 		fullname = NULL;
@@ -150,7 +150,7 @@
 	srcfile = xmalloc(sizeof(*srcfile));
 
 	srcfile->f = srcfile_relative_open(fname, &srcfile->name);
-	srcfile->dir = dirname(srcfile->name);
+	srcfile->dir = get_dirname(srcfile->name);
 	srcfile->prev = current_srcfile;
 
 	srcfile->lineno = 1;
@@ -159,7 +159,7 @@
 	current_srcfile = srcfile;
 }
 
-int srcfile_pop(void)
+bool srcfile_pop(void)
 {
 	struct srcfile_state *srcfile = current_srcfile;
 
@@ -177,7 +177,7 @@
 	 * fix this we could either allocate all the files from a
 	 * table, or use a pool allocator. */
 
-	return current_srcfile ? 1 : 0;
+	return current_srcfile ? true : false;
 }
 
 void srcfile_add_search_path(const char *dirname)
@@ -290,42 +290,27 @@
 	return pos_str;
 }
 
-void
-srcpos_verror(struct srcpos *pos, char const *fmt, va_list va)
+void srcpos_verror(struct srcpos *pos, const char *prefix,
+		   const char *fmt, va_list va)
 {
-       const char *srcstr;
-
-       srcstr = srcpos_string(pos);
-
-       fprintf(stderr, "Error: %s ", srcstr);
-       vfprintf(stderr, fmt, va);
-       fprintf(stderr, "\n");
-}
-
-void
-srcpos_error(struct srcpos *pos, char const *fmt, ...)
-{
-	va_list va;
-
-	va_start(va, fmt);
-	srcpos_verror(pos, fmt, va);
-	va_end(va);
-}
-
-
-void
-srcpos_warn(struct srcpos *pos, char const *fmt, ...)
-{
-	const char *srcstr;
-	va_list va;
-	va_start(va, fmt);
+	char *srcstr;
 
 	srcstr = srcpos_string(pos);
 
-	fprintf(stderr, "Warning: %s ", srcstr);
+	fprintf(stderr, "%s: %s ", prefix, srcstr);
 	vfprintf(stderr, fmt, va);
 	fprintf(stderr, "\n");
 
+	free(srcstr);
+}
+
+void srcpos_error(struct srcpos *pos, const char *prefix,
+		  const char *fmt, ...)
+{
+	va_list va;
+
+	va_start(va, fmt);
+	srcpos_verror(pos, prefix, fmt, va);
 	va_end(va);
 }
 
diff --git a/scripts/dtc/srcpos.h b/scripts/dtc/srcpos.h
index 93a2712..f81827b 100644
--- a/scripts/dtc/srcpos.h
+++ b/scripts/dtc/srcpos.h
@@ -21,6 +21,7 @@
 #define _SRCPOS_H_
 
 #include <stdio.h>
+#include <stdbool.h>
 
 struct srcfile_state {
 	FILE *f;
@@ -55,7 +56,7 @@
 FILE *srcfile_relative_open(const char *fname, char **fullnamep);
 
 void srcfile_push(const char *fname);
-int srcfile_pop(void);
+bool srcfile_pop(void);
 
 /**
  * Add a new directory to the search path for input files
@@ -106,12 +107,12 @@
 extern char *srcpos_string(struct srcpos *pos);
 extern void srcpos_dump(struct srcpos *pos);
 
-extern void srcpos_verror(struct srcpos *pos, char const *, va_list va)
-     __attribute__((format(printf, 2, 0)));
-extern void srcpos_error(struct srcpos *pos, char const *, ...)
-     __attribute__((format(printf, 2, 3)));
-extern void srcpos_warn(struct srcpos *pos, char const *, ...)
-     __attribute__((format(printf, 2, 3)));
+extern void srcpos_verror(struct srcpos *pos, const char *prefix,
+			  const char *fmt, va_list va)
+	__attribute__((format(printf, 3, 0)));
+extern void srcpos_error(struct srcpos *pos, const char *prefix,
+			 const char *fmt, ...)
+	__attribute__((format(printf, 3, 4)));
 
 extern void srcpos_set_line(char *f, int l);
 
diff --git a/scripts/dtc/treesource.c b/scripts/dtc/treesource.c
index 5740e69..a55d1d1 100644
--- a/scripts/dtc/treesource.c
+++ b/scripts/dtc/treesource.c
@@ -26,12 +26,12 @@
 extern YYLTYPE yylloc;
 
 struct boot_info *the_boot_info;
-int treesource_error;
+bool treesource_error;
 
 struct boot_info *dt_from_source(const char *fname)
 {
 	the_boot_info = NULL;
-	treesource_error = 0;
+	treesource_error = false;
 
 	srcfile_push(fname);
 	yyin = current_srcfile->f;
@@ -54,9 +54,9 @@
 		fputc('\t', f);
 }
 
-static int isstring(char c)
+static bool isstring(char c)
 {
-	return (isprint(c)
+	return (isprint((unsigned char)c)
 		|| (c == '\0')
 		|| strchr("\a\b\t\n\v\f\r", c));
 }
@@ -109,7 +109,7 @@
 			break;
 		case '\0':
 			fprintf(f, "\", ");
-			while (m && (m->offset < i)) {
+			while (m && (m->offset <= (i + 1))) {
 				if (m->type == LABEL) {
 					assert(m->offset == (i+1));
 					fprintf(f, "%s: ", m->ref);
@@ -119,7 +119,7 @@
 			fprintf(f, "\"");
 			break;
 		default:
-			if (isprint(c))
+			if (isprint((unsigned char)c))
 				fprintf(f, "%c", c);
 			else
 				fprintf(f, "\\x%02hhx", c);
@@ -178,7 +178,7 @@
 			m = m->next;
 		}
 
-		fprintf(f, "%02hhx", *bp++);
+		fprintf(f, "%02hhx", (unsigned char)(*bp++));
 		if ((const void *)bp >= propend)
 			break;
 		fprintf(f, " ");
@@ -281,3 +281,4 @@
 
 	write_tree_source_node(f, bi->dt, 0);
 }
+
diff --git a/scripts/dtc/update-dtc-source.sh b/scripts/dtc/update-dtc-source.sh
index feb01ef..f5cde79 100755
--- a/scripts/dtc/update-dtc-source.sh
+++ b/scripts/dtc/update-dtc-source.sh
@@ -34,6 +34,7 @@
 		srcpos.h treesource.c util.c util.h version_gen.h Makefile.dtc \
 		dtc-lexer.l dtc-parser.y"
 DTC_GENERATED="dtc-lexer.lex.c dtc-parser.tab.c dtc-parser.tab.h"
+LIBFDT_SOURCE="Makefile.libfdt fdt.c fdt.h fdt_empty_tree.c fdt_ro.c fdt_rw.c fdt_strerror.c fdt_sw.c fdt_wip.c libfdt.h libfdt_env.h libfdt_internal.h"
 
 # Build DTC
 cd $DTC_UPSTREAM_PATH
@@ -50,5 +51,13 @@
 	cp ${DTC_UPSTREAM_PATH}/$f ${f}_shipped
 	git add ${f}_shipped
 done
+for f in $LIBFDT_SOURCE; do
+       cp ${DTC_UPSTREAM_PATH}/libfdt/${f} libfdt/${f}
+       git add libfdt/${f}
+done
+
+sed -i -- 's/#include <libfdt_env.h>/#include "libfdt_env.h"/g' ./libfdt/libfdt.h
+sed -i -- 's/#include <fdt.h>/#include "fdt.h"/g' ./libfdt/libfdt.h
+git add ./libfdt/libfdt.h
 
 git commit -e -v -m "scripts/dtc: Update to upstream version [CHANGEME]"
diff --git a/scripts/dtc/util.c b/scripts/dtc/util.c
index 3055c16..9d65226 100644
--- a/scripts/dtc/util.c
+++ b/scripts/dtc/util.c
@@ -39,11 +39,11 @@
 char *xstrdup(const char *s)
 {
 	int len = strlen(s) + 1;
-	char *dup = xmalloc(len);
+	char *d = xmalloc(len);
 
-	memcpy(dup, s, len);
+	memcpy(d, s, len);
 
-	return dup;
+	return d;
 }
 
 char *join_path(const char *path, const char *name)
@@ -70,7 +70,7 @@
 	return str;
 }
 
-int util_is_printable_string(const void *data, int len)
+bool util_is_printable_string(const void *data, int len)
 {
 	const char *s = data;
 	const char *ss, *se;
@@ -87,7 +87,7 @@
 
 	while (s < se) {
 		ss = s;
-		while (s < se && *s && isprint(*s))
+		while (s < se && *s && isprint((unsigned char)*s))
 			s++;
 
 		/* not zero, or not done yet */
@@ -219,10 +219,6 @@
 		if (offset == bufsize) {
 			bufsize *= 2;
 			buf = xrealloc(buf, bufsize);
-			if (!buf) {
-				ret = ENOMEM;
-				break;
-			}
 		}
 
 		ret = read(fd, &buf[offset], bufsize - offset);
@@ -375,9 +371,9 @@
 		const uint32_t *cell = (const uint32_t *)data;
 
 		printf(" = <");
-		for (i = 0; i < len; i += 4)
+		for (i = 0, len /= 4; i < len; i++)
 			printf("0x%08x%s", fdt32_to_cpu(cell[i]),
-			       i < (len - 4) ? " " : "");
+			       i < (len - 1) ? " " : "");
 		printf(">");
 	} else {
 		printf(" = [");
diff --git a/scripts/dtc/util.h b/scripts/dtc/util.h
index 8f40b44..f800b60 100644
--- a/scripts/dtc/util.h
+++ b/scripts/dtc/util.h
@@ -2,6 +2,7 @@
 #define _UTIL_H
 
 #include <stdarg.h>
+#include <stdbool.h>
 #include <getopt.h>
 
 /*
@@ -33,6 +34,7 @@
 	va_start(ap, str);
 	fprintf(stderr, "FATAL ERROR: ");
 	vfprintf(stderr, str, ap);
+	va_end(ap);
 	exit(1);
 }
 
@@ -68,7 +70,7 @@
  * @param len	The string length including terminator
  * @return 1 if a valid printable string, 0 if not
  */
-int util_is_printable_string(const void *data, int len);
+bool util_is_printable_string(const void *data, int len);
 
 /*
  * Parse an escaped character starting at index i in string s.  The resulting
diff --git a/scripts/dtc/version_gen.h b/scripts/dtc/version_gen.h
index 54d4e90..5b8c7d5 100644
--- a/scripts/dtc/version_gen.h
+++ b/scripts/dtc/version_gen.h
@@ -1 +1 @@
-#define DTC_VERSION "DTC 1.4.0-dirty"
+#define DTC_VERSION "DTC 1.4.1-g9d3649bd"
diff --git a/scripts/gdb/linux/dmesg.py b/scripts/gdb/linux/dmesg.py
index 3c947f0..927d0d2 100644
--- a/scripts/gdb/linux/dmesg.py
+++ b/scripts/gdb/linux/dmesg.py
@@ -12,7 +12,6 @@
 #
 
 import gdb
-import string
 
 from linux import utils
 
diff --git a/scripts/gdb/linux/lists.py b/scripts/gdb/linux/lists.py
new file mode 100644
index 0000000..3a3775b
--- /dev/null
+++ b/scripts/gdb/linux/lists.py
@@ -0,0 +1,92 @@
+#
+# gdb helper commands and functions for Linux kernel debugging
+#
+#  list tools
+#
+# Copyright (c) Thiebaud Weksteen, 2015
+#
+# Authors:
+#  Thiebaud Weksteen <thiebaud@weksteen.fr>
+#
+# This work is licensed under the terms of the GNU GPL version 2.
+#
+
+import gdb
+
+from linux import utils
+
+list_head = utils.CachedType("struct list_head")
+
+
+def list_check(head):
+    nb = 0
+    if (head.type == list_head.get_type().pointer()):
+        head = head.dereference()
+    elif (head.type != list_head.get_type()):
+        raise gdb.GdbError('argument must be of type (struct list_head [*])')
+    c = head
+    try:
+        gdb.write("Starting with: {}\n".format(c))
+    except gdb.MemoryError:
+        gdb.write('head is not accessible\n')
+        return
+    while True:
+        p = c['prev'].dereference()
+        n = c['next'].dereference()
+        try:
+            if p['next'] != c.address:
+                gdb.write('prev.next != current: '
+                          'current@{current_addr}={current} '
+                          'prev@{p_addr}={p}\n'.format(
+                              current_addr=c.address,
+                              current=c,
+                              p_addr=p.address,
+                              p=p,
+                          ))
+                return
+        except gdb.MemoryError:
+            gdb.write('prev is not accessible: '
+                      'current@{current_addr}={current}\n'.format(
+                          current_addr=c.address,
+                          current=c
+                      ))
+            return
+        try:
+            if n['prev'] != c.address:
+                gdb.write('next.prev != current: '
+                          'current@{current_addr}={current} '
+                          'next@{n_addr}={n}\n'.format(
+                              current_addr=c.address,
+                              current=c,
+                              n_addr=n.address,
+                              n=n,
+                          ))
+                return
+        except gdb.MemoryError:
+            gdb.write('next is not accessible: '
+                      'current@{current_addr}={current}\n'.format(
+                          current_addr=c.address,
+                          current=c
+                      ))
+            return
+        c = n
+        nb += 1
+        if c == head:
+            gdb.write("list is consistent: {} node(s)\n".format(nb))
+            return
+
+
+class LxListChk(gdb.Command):
+    """Verify a list consistency"""
+
+    def __init__(self):
+        super(LxListChk, self).__init__("lx-list-check", gdb.COMMAND_DATA,
+                                        gdb.COMPLETE_EXPRESSION)
+
+    def invoke(self, arg, from_tty):
+        argv = gdb.string_to_argv(arg)
+        if len(argv) != 1:
+            raise gdb.GdbError("lx-list-check takes one argument")
+        list_check(gdb.parse_and_eval(argv[0]))
+
+LxListChk()
diff --git a/scripts/gdb/linux/symbols.py b/scripts/gdb/linux/symbols.py
index cd5bea9..627750c 100644
--- a/scripts/gdb/linux/symbols.py
+++ b/scripts/gdb/linux/symbols.py
@@ -14,9 +14,8 @@
 import gdb
 import os
 import re
-import string
 
-from linux import modules, utils
+from linux import modules
 
 
 if hasattr(gdb, 'Breakpoint'):
@@ -97,7 +96,7 @@
             return ""
         attrs = sect_attrs['attrs']
         section_name_to_address = {
-            attrs[n]['name'].string() : attrs[n]['address']
+            attrs[n]['name'].string(): attrs[n]['address']
             for n in range(int(sect_attrs['nsections']))}
         args = []
         for section_name in [".data", ".data..read_mostly", ".rodata", ".bss"]:
@@ -124,7 +123,7 @@
                 addr=module_addr,
                 sections=self._section_arguments(module))
             gdb.execute(cmdline, to_string=True)
-            if not module_name in self.loaded_modules:
+            if module_name not in self.loaded_modules:
                 self.loaded_modules.append(module_name)
         else:
             gdb.write("no module object found for '{0}'\n".format(module_name))
@@ -164,7 +163,7 @@
         self.load_all_symbols()
 
         if hasattr(gdb, 'Breakpoint'):
-            if not self.breakpoint is None:
+            if self.breakpoint is not None:
                 self.breakpoint.delete()
                 self.breakpoint = None
             self.breakpoint = LoadModuleBreakpoint(
diff --git a/scripts/gdb/linux/tasks.py b/scripts/gdb/linux/tasks.py
index e2037d9..862a4ae 100644
--- a/scripts/gdb/linux/tasks.py
+++ b/scripts/gdb/linux/tasks.py
@@ -18,8 +18,8 @@
 
 task_type = utils.CachedType("struct task_struct")
 
+
 def task_lists():
-    global task_type
     task_ptr_type = task_type.get_type().pointer()
     init_task = gdb.parse_and_eval("init_task").address
     t = g = init_task
@@ -38,6 +38,7 @@
         if t == init_task:
             return
 
+
 def get_task_by_pid(pid):
     for task in task_lists():
         if int(task['pid']) == pid:
@@ -65,13 +66,28 @@
 LxTaskByPidFunc()
 
 
+class LxPs(gdb.Command):
+    """Dump Linux tasks."""
+
+    def __init__(self):
+        super(LxPs, self).__init__("lx-ps", gdb.COMMAND_DATA)
+
+    def invoke(self, arg, from_tty):
+        for task in task_lists():
+            gdb.write("{address} {pid} {comm}\n".format(
+                address=task,
+                pid=task["pid"],
+                comm=task["comm"].string()))
+
+LxPs()
+
+
 thread_info_type = utils.CachedType("struct thread_info")
 
 ia64_task_size = None
 
 
 def get_thread_info(task):
-    global thread_info_type
     thread_info_ptr_type = thread_info_type.get_type().pointer()
     if utils.is_target_arch("ia64"):
         global ia64_task_size
diff --git a/scripts/gdb/linux/utils.py b/scripts/gdb/linux/utils.py
index 128c306..0893b32 100644
--- a/scripts/gdb/linux/utils.py
+++ b/scripts/gdb/linux/utils.py
@@ -83,7 +83,7 @@
         elif "big endian" in endian:
             target_endianness = BIG_ENDIAN
         else:
-            raise gdb.GdgError("unknown endianness '{0}'".format(str(endian)))
+            raise gdb.GdbError("unknown endianness '{0}'".format(str(endian)))
     return target_endianness
 
 
@@ -151,6 +151,6 @@
             gdbserver_type = GDBSERVER_QEMU
         elif probe_kgdb():
             gdbserver_type = GDBSERVER_KGDB
-        if not gdbserver_type is None and hasattr(gdb, 'events'):
+        if gdbserver_type is not None and hasattr(gdb, 'events'):
             gdb.events.exited.connect(exit_handler)
     return gdbserver_type
diff --git a/scripts/gdb/vmlinux-gdb.py b/scripts/gdb/vmlinux-gdb.py
index 4848928..ce82bf5 100644
--- a/scripts/gdb/vmlinux-gdb.py
+++ b/scripts/gdb/vmlinux-gdb.py
@@ -28,3 +28,4 @@
     import linux.dmesg
     import linux.tasks
     import linux.cpus
+    import linux.lists
diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile
index d9b1fef..aceaaed 100644
--- a/scripts/kconfig/Makefile
+++ b/scripts/kconfig/Makefile
@@ -86,7 +86,7 @@
 PHONY += oldnoconfig savedefconfig defconfig
 
 # oldnoconfig is an alias of olddefconfig, because people already are dependent
-# on its behavior(sets new symbols to their default value but not 'n') with the
+# on its behavior (sets new symbols to their default value but not 'n') with the
 # counter-intuitive name.
 oldnoconfig: olddefconfig
 
@@ -115,6 +115,10 @@
 kvmconfig: kvm_guest.config
 	@:
 
+PHONY += xenconfig
+xenconfig: xen.config
+	@:
+
 PHONY += tinyconfig
 tinyconfig:
 	$(Q)$(MAKE) -f $(srctree)/Makefile allnoconfig tiny.config
@@ -122,10 +126,11 @@
 # Help text used by make help
 help:
 	@echo  '  config	  - Update current config utilising a line-oriented program'
-	@echo  '  nconfig         - Update current config utilising a ncurses menu based program'
+	@echo  '  nconfig         - Update current config utilising a ncurses menu based'
+	@echo  '                    program'
 	@echo  '  menuconfig	  - Update current config utilising a menu based program'
-	@echo  '  xconfig	  - Update current config utilising a QT based front-end'
-	@echo  '  gconfig	  - Update current config utilising a GTK based front-end'
+	@echo  '  xconfig	  - Update current config utilising a Qt based front-end'
+	@echo  '  gconfig	  - Update current config utilising a GTK+ based front-end'
 	@echo  '  oldconfig	  - Update current config utilising a provided .config as base'
 	@echo  '  localmodconfig  - Update current config disabling modules not loaded'
 	@echo  '  localyesconfig  - Update current config converting local mods to core'
@@ -138,8 +143,10 @@
 	@echo  '  alldefconfig    - New config with all symbols set to default'
 	@echo  '  randconfig	  - New config with random answer to all options'
 	@echo  '  listnewconfig   - List new options'
-	@echo  '  olddefconfig	  - Same as silentoldconfig but sets new symbols to their default value'
-	@echo  '  kvmconfig	  - Enable additional options for guest kernel support'
+	@echo  '  olddefconfig	  - Same as silentoldconfig but sets new symbols to their'
+	@echo  '                    default value'
+	@echo  '  kvmconfig	  - Enable additional options for kvm guest kernel support'
+	@echo  '  xenconfig       - Enable additional options for xen dom0 and guest kernel support'
 	@echo  '  tinyconfig	  - Configure the tiniest possible kernel'
 
 # lxdialog stuff
@@ -158,9 +165,9 @@
 # mconf:  Used for the menuconfig target
 #         Utilizes the lxdialog package
 # qconf:  Used for the xconfig target
-#         Based on QT which needs to be installed to compile it
+#         Based on Qt which needs to be installed to compile it
 # gconf:  Used for the gconfig target
-#         Based on GTK which needs to be installed to compile it
+#         Based on GTK+ which needs to be installed to compile it
 # object files used by all kconfig flavours
 
 lxdialog := lxdialog/checklist.o lxdialog/util.o lxdialog/inputbox.o
@@ -217,11 +224,11 @@
 $(obj)/.tmp_qtcheck: $(src)/Makefile
 -include $(obj)/.tmp_qtcheck
 
-# QT needs some extra effort...
+# Qt needs some extra effort...
 $(obj)/.tmp_qtcheck:
 	@set -e; $(kecho) "  CHECK   qt"; dir=""; pkg=""; \
 	if ! pkg-config --exists QtCore 2> /dev/null; then \
-	    echo "* Unable to find the QT4 tool qmake. Trying to use QT3"; \
+	    echo "* Unable to find the Qt4 tool qmake. Trying to use Qt3"; \
 	    pkg-config --exists qt 2> /dev/null && pkg=qt; \
 	    pkg-config --exists qt-mt 2> /dev/null && pkg=qt-mt; \
 	    if [ -n "$$pkg" ]; then \
@@ -235,8 +242,8 @@
 	      done; \
 	      if [ -z "$$dir" ]; then \
 	        echo >&2 "*"; \
-	        echo >&2 "* Unable to find any QT installation. Please make sure that"; \
-	        echo >&2 "* the QT4 or QT3 development package is correctly installed and"; \
+	        echo >&2 "* Unable to find any Qt installation. Please make sure that"; \
+	        echo >&2 "* the Qt4 or Qt3 development package is correctly installed and"; \
 	        echo >&2 "* either qmake can be found or install pkg-config or set"; \
 	        echo >&2 "* the QTDIR environment variable to the correct location."; \
 	        echo >&2 "*"; \
@@ -273,7 +280,7 @@
 ifeq ($(MAKECMDGOALS),gconfig)
 -include $(obj)/.tmp_gtkcheck
 
-# GTK needs some extra effort, too...
+# GTK+ needs some extra effort, too...
 $(obj)/.tmp_gtkcheck:
 	@if `pkg-config --exists gtk+-2.0 gmodule-2.0 libglade-2.0`; then		\
 		if `pkg-config --atleast-version=2.0.0 gtk+-2.0`; then			\
@@ -304,7 +311,7 @@
 $(obj)/%.moc: $(src)/%.h $(obj)/.tmp_qtcheck
 	$(call cmd,moc)
 
-# Extract gconf menu items for I18N support
+# Extract gconf menu items for i18n support
 $(obj)/gconf.glade.h: $(obj)/gconf.glade
 	$(Q)intltool-extract --type=gettext/glade --srcdir=$(srctree) \
 	$(obj)/gconf.glade
diff --git a/scripts/kconfig/expr.c b/scripts/kconfig/expr.c
index fb0a2a2..667d1aa 100644
--- a/scripts/kconfig/expr.c
+++ b/scripts/kconfig/expr.c
@@ -13,9 +13,6 @@
 
 static int expr_eq(struct expr *e1, struct expr *e2);
 static struct expr *expr_eliminate_yn(struct expr *e);
-static struct expr *expr_extract_eq_and(struct expr **ep1, struct expr **ep2);
-static struct expr *expr_extract_eq_or(struct expr **ep1, struct expr **ep2);
-static void expr_extract_eq(enum expr_type type, struct expr **ep, struct expr **ep1, struct expr **ep2);
 
 struct expr *expr_alloc_symbol(struct symbol *sym)
 {
@@ -82,6 +79,10 @@
 		e->left.expr = expr_copy(org->left.expr);
 		break;
 	case E_EQUAL:
+	case E_GEQ:
+	case E_GTH:
+	case E_LEQ:
+	case E_LTH:
 	case E_UNEQUAL:
 		e->left.sym = org->left.sym;
 		e->right.sym = org->right.sym;
@@ -114,6 +115,10 @@
 		expr_free(e->left.expr);
 		return;
 	case E_EQUAL:
+	case E_GEQ:
+	case E_GTH:
+	case E_LEQ:
+	case E_LTH:
 	case E_UNEQUAL:
 		break;
 	case E_OR:
@@ -200,6 +205,10 @@
 		return 0;
 	switch (e1->type) {
 	case E_EQUAL:
+	case E_GEQ:
+	case E_GTH:
+	case E_LEQ:
+	case E_LTH:
 	case E_UNEQUAL:
 		return e1->left.sym == e2->left.sym && e1->right.sym == e2->right.sym;
 	case E_SYMBOL:
@@ -559,62 +568,6 @@
 #undef e2
 }
 
-static void expr_eliminate_dups2(enum expr_type type, struct expr **ep1, struct expr **ep2)
-{
-#define e1 (*ep1)
-#define e2 (*ep2)
-	struct expr *tmp, *tmp1, *tmp2;
-
-	if (e1->type == type) {
-		expr_eliminate_dups2(type, &e1->left.expr, &e2);
-		expr_eliminate_dups2(type, &e1->right.expr, &e2);
-		return;
-	}
-	if (e2->type == type) {
-		expr_eliminate_dups2(type, &e1, &e2->left.expr);
-		expr_eliminate_dups2(type, &e1, &e2->right.expr);
-	}
-	if (e1 == e2)
-		return;
-
-	switch (e1->type) {
-	case E_OR:
-		expr_eliminate_dups2(e1->type, &e1, &e1);
-		// (FOO || BAR) && (!FOO && !BAR) -> n
-		tmp1 = expr_transform(expr_alloc_one(E_NOT, expr_copy(e1)));
-		tmp2 = expr_copy(e2);
-		tmp = expr_extract_eq_and(&tmp1, &tmp2);
-		if (expr_is_yes(tmp1)) {
-			expr_free(e1);
-			e1 = expr_alloc_symbol(&symbol_no);
-			trans_count++;
-		}
-		expr_free(tmp2);
-		expr_free(tmp1);
-		expr_free(tmp);
-		break;
-	case E_AND:
-		expr_eliminate_dups2(e1->type, &e1, &e1);
-		// (FOO && BAR) || (!FOO || !BAR) -> y
-		tmp1 = expr_transform(expr_alloc_one(E_NOT, expr_copy(e1)));
-		tmp2 = expr_copy(e2);
-		tmp = expr_extract_eq_or(&tmp1, &tmp2);
-		if (expr_is_no(tmp1)) {
-			expr_free(e1);
-			e1 = expr_alloc_symbol(&symbol_yes);
-			trans_count++;
-		}
-		expr_free(tmp2);
-		expr_free(tmp1);
-		expr_free(tmp);
-		break;
-	default:
-		;
-	}
-#undef e1
-#undef e2
-}
-
 struct expr *expr_eliminate_dups(struct expr *e)
 {
 	int oldcount;
@@ -627,7 +580,6 @@
 		switch (e->type) {
 		case E_OR: case E_AND:
 			expr_eliminate_dups1(e->type, &e, &e);
-			expr_eliminate_dups2(e->type, &e, &e);
 		default:
 			;
 		}
@@ -647,6 +599,10 @@
 		return NULL;
 	switch (e->type) {
 	case E_EQUAL:
+	case E_GEQ:
+	case E_GTH:
+	case E_LEQ:
+	case E_LTH:
 	case E_UNEQUAL:
 	case E_SYMBOL:
 	case E_LIST:
@@ -719,6 +675,22 @@
 			e = tmp;
 			e->type = e->type == E_EQUAL ? E_UNEQUAL : E_EQUAL;
 			break;
+		case E_LEQ:
+		case E_GEQ:
+			// !a<='x' -> a>'x'
+			tmp = e->left.expr;
+			free(e);
+			e = tmp;
+			e->type = e->type == E_LEQ ? E_GTH : E_LTH;
+			break;
+		case E_LTH:
+		case E_GTH:
+			// !a<'x' -> a>='x'
+			tmp = e->left.expr;
+			free(e);
+			e = tmp;
+			e->type = e->type == E_LTH ? E_GEQ : E_LEQ;
+			break;
 		case E_OR:
 			// !(a || b) -> !a && !b
 			tmp = e->left.expr;
@@ -789,6 +761,10 @@
 	case E_SYMBOL:
 		return dep->left.sym == sym;
 	case E_EQUAL:
+	case E_GEQ:
+	case E_GTH:
+	case E_LEQ:
+	case E_LTH:
 	case E_UNEQUAL:
 		return dep->left.sym == sym ||
 		       dep->right.sym == sym;
@@ -829,57 +805,6 @@
  	return false;
 }
 
-static struct expr *expr_extract_eq_and(struct expr **ep1, struct expr **ep2)
-{
-	struct expr *tmp = NULL;
-	expr_extract_eq(E_AND, &tmp, ep1, ep2);
-	if (tmp) {
-		*ep1 = expr_eliminate_yn(*ep1);
-		*ep2 = expr_eliminate_yn(*ep2);
-	}
-	return tmp;
-}
-
-static struct expr *expr_extract_eq_or(struct expr **ep1, struct expr **ep2)
-{
-	struct expr *tmp = NULL;
-	expr_extract_eq(E_OR, &tmp, ep1, ep2);
-	if (tmp) {
-		*ep1 = expr_eliminate_yn(*ep1);
-		*ep2 = expr_eliminate_yn(*ep2);
-	}
-	return tmp;
-}
-
-static void expr_extract_eq(enum expr_type type, struct expr **ep, struct expr **ep1, struct expr **ep2)
-{
-#define e1 (*ep1)
-#define e2 (*ep2)
-	if (e1->type == type) {
-		expr_extract_eq(type, ep, &e1->left.expr, &e2);
-		expr_extract_eq(type, ep, &e1->right.expr, &e2);
-		return;
-	}
-	if (e2->type == type) {
-		expr_extract_eq(type, ep, ep1, &e2->left.expr);
-		expr_extract_eq(type, ep, ep1, &e2->right.expr);
-		return;
-	}
-	if (expr_eq(e1, e2)) {
-		*ep = *ep ? expr_alloc_two(type, *ep, e1) : e1;
-		expr_free(e2);
-		if (type == E_AND) {
-			e1 = expr_alloc_symbol(&symbol_yes);
-			e2 = expr_alloc_symbol(&symbol_yes);
-		} else if (type == E_OR) {
-			e1 = expr_alloc_symbol(&symbol_no);
-			e2 = expr_alloc_symbol(&symbol_no);
-		}
-	}
-#undef e1
-#undef e2
-}
-
 struct expr *expr_trans_compare(struct expr *e, enum expr_type type, struct symbol *sym)
 {
 	struct expr *e1, *e2;
@@ -914,6 +839,10 @@
 	case E_NOT:
 		return expr_trans_compare(e->left.expr, type == E_EQUAL ? E_UNEQUAL : E_EQUAL, sym);
 	case E_UNEQUAL:
+	case E_LTH:
+	case E_LEQ:
+	case E_GTH:
+	case E_GEQ:
 	case E_EQUAL:
 		if (type == E_EQUAL) {
 			if (sym == &symbol_yes)
@@ -941,10 +870,57 @@
 	return NULL;
 }
 
+enum string_value_kind {
+	k_string,
+	k_signed,
+	k_unsigned,
+	k_invalid
+};
+
+union string_value {
+	unsigned long long u;
+	signed long long s;
+};
+
+static enum string_value_kind expr_parse_string(const char *str,
+						enum symbol_type type,
+						union string_value *val)
+{
+	char *tail;
+	enum string_value_kind kind;
+
+	errno = 0;
+	switch (type) {
+	case S_BOOLEAN:
+	case S_TRISTATE:
+		return k_string;
+	case S_INT:
+		val->s = strtoll(str, &tail, 10);
+		kind = k_signed;
+		break;
+	case S_HEX:
+		val->u = strtoull(str, &tail, 16);
+		kind = k_unsigned;
+		break;
+	case S_STRING:
+	case S_UNKNOWN:
+		val->s = strtoll(str, &tail, 0);
+		kind = k_signed;
+		break;
+	default:
+		return k_invalid;
+	}
+	return !errno && !*tail && tail > str && isxdigit(tail[-1])
+	       ? kind : k_string;
+}
+
 tristate expr_calc_value(struct expr *e)
 {
 	tristate val1, val2;
 	const char *str1, *str2;
+	enum string_value_kind k1 = k_string, k2 = k_string;
+	union string_value lval = {}, rval = {};
+	int res;
 
 	if (!e)
 		return yes;
@@ -965,21 +941,57 @@
 		val1 = expr_calc_value(e->left.expr);
 		return EXPR_NOT(val1);
 	case E_EQUAL:
-		sym_calc_value(e->left.sym);
-		sym_calc_value(e->right.sym);
-		str1 = sym_get_string_value(e->left.sym);
-		str2 = sym_get_string_value(e->right.sym);
-		return !strcmp(str1, str2) ? yes : no;
+	case E_GEQ:
+	case E_GTH:
+	case E_LEQ:
+	case E_LTH:
 	case E_UNEQUAL:
-		sym_calc_value(e->left.sym);
-		sym_calc_value(e->right.sym);
-		str1 = sym_get_string_value(e->left.sym);
-		str2 = sym_get_string_value(e->right.sym);
-		return !strcmp(str1, str2) ? no : yes;
+		break;
 	default:
 		printf("expr_calc_value: %d?\n", e->type);
 		return no;
 	}
+
+	sym_calc_value(e->left.sym);
+	sym_calc_value(e->right.sym);
+	str1 = sym_get_string_value(e->left.sym);
+	str2 = sym_get_string_value(e->right.sym);
+
+	if (e->left.sym->type != S_STRING || e->right.sym->type != S_STRING) {
+		k1 = expr_parse_string(str1, e->left.sym->type, &lval);
+		k2 = expr_parse_string(str2, e->right.sym->type, &rval);
+	}
+
+	if (k1 == k_string || k2 == k_string)
+		res = strcmp(str1, str2);
+	else if (k1 == k_invalid || k2 == k_invalid) {
+		if (e->type != E_EQUAL && e->type != E_UNEQUAL) {
+			printf("Cannot compare \"%s\" and \"%s\"\n", str1, str2);
+			return no;
+		}
+		res = strcmp(str1, str2);
+	} else if (k1 == k_unsigned || k2 == k_unsigned)
+		res = (lval.u > rval.u) - (lval.u < rval.u);
+	else /* if (k1 == k_signed && k2 == k_signed) */
+		res = (lval.s > rval.s) - (lval.s < rval.s);
+
+	switch(e->type) {
+	case E_EQUAL:
+		return res ? no : yes;
+	case E_GEQ:
+		return res >= 0 ? yes : no;
+	case E_GTH:
+		return res > 0 ? yes : no;
+	case E_LEQ:
+		return res <= 0 ? yes : no;
+	case E_LTH:
+		return res < 0 ? yes : no;
+	case E_UNEQUAL:
+		return res ? yes : no;
+	default:
+		printf("expr_calc_value: relation %d?\n", e->type);
+		return no;
+	}
 }
 
 static int expr_compare_type(enum expr_type t1, enum expr_type t2)
@@ -987,6 +999,12 @@
 	if (t1 == t2)
 		return 0;
 	switch (t1) {
+	case E_LEQ:
+	case E_LTH:
+	case E_GEQ:
+	case E_GTH:
+		if (t2 == E_EQUAL || t2 == E_UNEQUAL)
+			return 1;
 	case E_EQUAL:
 	case E_UNEQUAL:
 		if (t2 == E_NOT)
@@ -1080,6 +1098,24 @@
 		fn(data, NULL, "=");
 		fn(data, e->right.sym, e->right.sym->name);
 		break;
+	case E_LEQ:
+	case E_LTH:
+		if (e->left.sym->name)
+			fn(data, e->left.sym, e->left.sym->name);
+		else
+			fn(data, NULL, "<choice>");
+		fn(data, NULL, e->type == E_LEQ ? "<=" : "<");
+		fn(data, e->right.sym, e->right.sym->name);
+		break;
+	case E_GEQ:
+	case E_GTH:
+		if (e->left.sym->name)
+			fn(data, e->left.sym, e->left.sym->name);
+		else
+			fn(data, NULL, "<choice>");
+		fn(data, NULL, e->type == E_LEQ ? ">=" : ">");
+		fn(data, e->right.sym, e->right.sym->name);
+		break;
 	case E_UNEQUAL:
 		if (e->left.sym->name)
 			fn(data, e->left.sym, e->left.sym->name);
diff --git a/scripts/kconfig/expr.h b/scripts/kconfig/expr.h
index a2fc96a..973b6f7 100644
--- a/scripts/kconfig/expr.h
+++ b/scripts/kconfig/expr.h
@@ -29,7 +29,9 @@
 } tristate;
 
 enum expr_type {
-	E_NONE, E_OR, E_AND, E_NOT, E_EQUAL, E_UNEQUAL, E_LIST, E_SYMBOL, E_RANGE
+	E_NONE, E_OR, E_AND, E_NOT,
+	E_EQUAL, E_UNEQUAL, E_LTH, E_LEQ, E_GTH, E_GEQ,
+	E_LIST, E_SYMBOL, E_RANGE
 };
 
 union expr_data {
diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index 6731377..70c5ee1 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -1166,6 +1166,10 @@
 	case E_NOT:
 		return sym_check_expr_deps(e->left.expr);
 	case E_EQUAL:
+	case E_GEQ:
+	case E_GTH:
+	case E_LEQ:
+	case E_LTH:
 	case E_UNEQUAL:
 		sym = sym_check_deps(e->left.sym);
 		if (sym)
diff --git a/scripts/kconfig/zconf.l b/scripts/kconfig/zconf.l
index 6c62d93..200a3fe 100644
--- a/scripts/kconfig/zconf.l
+++ b/scripts/kconfig/zconf.l
@@ -122,6 +122,10 @@
 	"!"	return T_NOT;
 	"="	return T_EQUAL;
 	"!="	return T_UNEQUAL;
+	"<="	return T_LESS_EQUAL;
+	">="	return T_GREATER_EQUAL;
+	"<"	return T_LESS;
+	">"	return T_GREATER;
 	\"|\'	{
 		str = yytext[0];
 		new_string();
@@ -141,7 +145,12 @@
 	}
 	#.*	/* comment */
 	\\\n	current_file->lineno++;
-	.
+	[[:blank:]]+
+	.	{
+		fprintf(stderr,
+		        "%s:%d:warning: ignoring unsupported character '%c'\n",
+		        zconf_curname(), zconf_lineno(), *yytext);
+	}
 	<<EOF>> {
 		BEGIN(INITIAL);
 	}
diff --git a/scripts/kconfig/zconf.lex.c_shipped b/scripts/kconfig/zconf.lex.c_shipped
index 349a7f2..dd4e86c 100644
--- a/scripts/kconfig/zconf.lex.c_shipped
+++ b/scripts/kconfig/zconf.lex.c_shipped
@@ -365,323 +365,354 @@
 
 extern char *zconftext;
 #define yytext_ptr zconftext
-static yyconst flex_int16_t yy_nxt[][17] =
+static yyconst flex_int16_t yy_nxt[][19] =
     {
     {
         0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
-        0,    0,    0,    0,    0,    0,    0
+        0,    0,    0,    0,    0,    0,    0,    0,    0
     },
 
     {
        11,   12,   13,   14,   12,   12,   15,   12,   12,   12,
-       12,   12,   12,   12,   12,   12,   12
+       12,   12,   12,   12,   12,   12,   12,   12,   12
     },
 
     {
        11,   12,   13,   14,   12,   12,   15,   12,   12,   12,
-       12,   12,   12,   12,   12,   12,   12
+       12,   12,   12,   12,   12,   12,   12,   12,   12
     },
 
     {
        11,   16,   16,   17,   16,   16,   16,   16,   16,   16,
-       16,   16,   16,   18,   16,   16,   16
+       16,   16,   16,   18,   16,   16,   16,   16,   16
     },
 
     {
        11,   16,   16,   17,   16,   16,   16,   16,   16,   16,
-       16,   16,   16,   18,   16,   16,   16
+       16,   16,   16,   18,   16,   16,   16,   16,   16
 
     },
 
     {
        11,   19,   20,   21,   19,   19,   19,   19,   19,   19,
-       19,   19,   19,   19,   19,   19,   19
+       19,   19,   19,   19,   19,   19,   19,   19,   19
     },
 
     {
        11,   19,   20,   21,   19,   19,   19,   19,   19,   19,
-       19,   19,   19,   19,   19,   19,   19
+       19,   19,   19,   19,   19,   19,   19,   19,   19
     },
 
     {
        11,   22,   22,   23,   22,   24,   22,   22,   24,   22,
-       22,   22,   22,   22,   22,   25,   22
+       22,   22,   22,   22,   22,   22,   22,   25,   22
     },
 
     {
        11,   22,   22,   23,   22,   24,   22,   22,   24,   22,
-       22,   22,   22,   22,   22,   25,   22
+       22,   22,   22,   22,   22,   22,   22,   25,   22
     },
 
     {
-       11,   26,   26,   27,   28,   29,   30,   31,   29,   32,
-       33,   34,   35,   35,   36,   37,   38
+       11,   26,   27,   28,   29,   30,   31,   32,   30,   33,
+       34,   35,   36,   36,   37,   38,   39,   40,   41
 
     },
 
     {
-       11,   26,   26,   27,   28,   29,   30,   31,   29,   32,
-       33,   34,   35,   35,   36,   37,   38
+       11,   26,   27,   28,   29,   30,   31,   32,   30,   33,
+       34,   35,   36,   36,   37,   38,   39,   40,   41
     },
 
     {
       -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,
-      -11,  -11,  -11,  -11,  -11,  -11,  -11
+      -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11
     },
 
     {
        11,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,
-      -12,  -12,  -12,  -12,  -12,  -12,  -12
+      -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12
     },
 
     {
-       11,  -13,   39,   40,  -13,  -13,   41,  -13,  -13,  -13,
-      -13,  -13,  -13,  -13,  -13,  -13,  -13
+       11,  -13,   42,   43,  -13,  -13,   44,  -13,  -13,  -13,
+      -13,  -13,  -13,  -13,  -13,  -13,  -13,  -13,  -13
     },
 
     {
        11,  -14,  -14,  -14,  -14,  -14,  -14,  -14,  -14,  -14,
-      -14,  -14,  -14,  -14,  -14,  -14,  -14
+      -14,  -14,  -14,  -14,  -14,  -14,  -14,  -14,  -14
 
     },
 
     {
-       11,   42,   42,   43,   42,   42,   42,   42,   42,   42,
-       42,   42,   42,   42,   42,   42,   42
+       11,   45,   45,   46,   45,   45,   45,   45,   45,   45,
+       45,   45,   45,   45,   45,   45,   45,   45,   45
     },
 
     {
        11,  -16,  -16,  -16,  -16,  -16,  -16,  -16,  -16,  -16,
-      -16,  -16,  -16,  -16,  -16,  -16,  -16
+      -16,  -16,  -16,  -16,  -16,  -16,  -16,  -16,  -16
     },
 
     {
        11,  -17,  -17,  -17,  -17,  -17,  -17,  -17,  -17,  -17,
-      -17,  -17,  -17,  -17,  -17,  -17,  -17
+      -17,  -17,  -17,  -17,  -17,  -17,  -17,  -17,  -17
     },
 
     {
        11,  -18,  -18,  -18,  -18,  -18,  -18,  -18,  -18,  -18,
-      -18,  -18,  -18,   44,  -18,  -18,  -18
+      -18,  -18,  -18,   47,  -18,  -18,  -18,  -18,  -18
     },
 
     {
-       11,   45,   45,  -19,   45,   45,   45,   45,   45,   45,
-       45,   45,   45,   45,   45,   45,   45
+       11,   48,   48,  -19,   48,   48,   48,   48,   48,   48,
+       48,   48,   48,   48,   48,   48,   48,   48,   48
 
     },
 
     {
-       11,  -20,   46,   47,  -20,  -20,  -20,  -20,  -20,  -20,
-      -20,  -20,  -20,  -20,  -20,  -20,  -20
+       11,  -20,   49,   50,  -20,  -20,  -20,  -20,  -20,  -20,
+      -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20
     },
 
     {
-       11,   48,  -21,  -21,   48,   48,   48,   48,   48,   48,
-       48,   48,   48,   48,   48,   48,   48
+       11,   51,  -21,  -21,   51,   51,   51,   51,   51,   51,
+       51,   51,   51,   51,   51,   51,   51,   51,   51
     },
 
     {
-       11,   49,   49,   50,   49,  -22,   49,   49,  -22,   49,
-       49,   49,   49,   49,   49,  -22,   49
+       11,   52,   52,   53,   52,  -22,   52,   52,  -22,   52,
+       52,   52,   52,   52,   52,   52,   52,  -22,   52
     },
 
     {
        11,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,
-      -23,  -23,  -23,  -23,  -23,  -23,  -23
+      -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23
     },
 
     {
        11,  -24,  -24,  -24,  -24,  -24,  -24,  -24,  -24,  -24,
-      -24,  -24,  -24,  -24,  -24,  -24,  -24
+      -24,  -24,  -24,  -24,  -24,  -24,  -24,  -24,  -24
 
     },
 
     {
-       11,   51,   51,   52,   51,   51,   51,   51,   51,   51,
-       51,   51,   51,   51,   51,   51,   51
+       11,   54,   54,   55,   54,   54,   54,   54,   54,   54,
+       54,   54,   54,   54,   54,   54,   54,   54,   54
     },
 
     {
        11,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,
-      -26,  -26,  -26,  -26,  -26,  -26,  -26
+      -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26
     },
 
     {
-       11,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,
-      -27,  -27,  -27,  -27,  -27,  -27,  -27
+       11,  -27,   56,  -27,  -27,  -27,  -27,  -27,  -27,  -27,
+      -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27
     },
 
     {
        11,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,
-      -28,  -28,  -28,  -28,   53,  -28,  -28
+      -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28
     },
 
     {
        11,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,
-      -29,  -29,  -29,  -29,  -29,  -29,  -29
+      -29,  -29,  -29,  -29,  -29,   57,  -29,  -29,  -29
 
     },
 
     {
-       11,   54,   54,  -30,   54,   54,   54,   54,   54,   54,
-       54,   54,   54,   54,   54,   54,   54
+       11,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,
+      -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30
     },
 
     {
-       11,  -31,  -31,  -31,  -31,  -31,  -31,   55,  -31,  -31,
-      -31,  -31,  -31,  -31,  -31,  -31,  -31
+       11,   58,   58,  -31,   58,   58,   58,   58,   58,   58,
+       58,   58,   58,   58,   58,   58,   58,   58,   58
     },
 
     {
-       11,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,
-      -32,  -32,  -32,  -32,  -32,  -32,  -32
+       11,  -32,  -32,  -32,  -32,  -32,  -32,   59,  -32,  -32,
+      -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32
     },
 
     {
        11,  -33,  -33,  -33,  -33,  -33,  -33,  -33,  -33,  -33,
-      -33,  -33,  -33,  -33,  -33,  -33,  -33
+      -33,  -33,  -33,  -33,  -33,  -33,  -33,  -33,  -33
     },
 
     {
        11,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,
-      -34,   56,   57,   57,  -34,  -34,  -34
+      -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34
 
     },
 
     {
        11,  -35,  -35,  -35,  -35,  -35,  -35,  -35,  -35,  -35,
-      -35,   57,   57,   57,  -35,  -35,  -35
+      -35,   60,   61,   61,  -35,  -35,  -35,  -35,  -35
     },
 
     {
        11,  -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,
-      -36,  -36,  -36,  -36,  -36,  -36,  -36
+      -36,   61,   61,   61,  -36,  -36,  -36,  -36,  -36
     },
 
     {
-       11,  -37,  -37,   58,  -37,  -37,  -37,  -37,  -37,  -37,
-      -37,  -37,  -37,  -37,  -37,  -37,  -37
+       11,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,
+      -37,  -37,  -37,  -37,  -37,   62,  -37,  -37,  -37
     },
 
     {
        11,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,
-      -38,  -38,  -38,  -38,  -38,  -38,   59
+      -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38
     },
 
     {
-       11,  -39,   39,   40,  -39,  -39,   41,  -39,  -39,  -39,
-      -39,  -39,  -39,  -39,  -39,  -39,  -39
+       11,  -39,  -39,  -39,  -39,  -39,  -39,  -39,  -39,  -39,
+      -39,  -39,  -39,  -39,  -39,   63,  -39,  -39,  -39
 
     },
 
     {
-       11,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,
-      -40,  -40,  -40,  -40,  -40,  -40,  -40
+       11,  -40,  -40,   64,  -40,  -40,  -40,  -40,  -40,  -40,
+      -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40
     },
 
     {
-       11,   42,   42,   43,   42,   42,   42,   42,   42,   42,
-       42,   42,   42,   42,   42,   42,   42
+       11,  -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,
+      -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,   65
     },
 
     {
-       11,   42,   42,   43,   42,   42,   42,   42,   42,   42,
-       42,   42,   42,   42,   42,   42,   42
+       11,  -42,   42,   43,  -42,  -42,   44,  -42,  -42,  -42,
+      -42,  -42,  -42,  -42,  -42,  -42,  -42,  -42,  -42
     },
 
     {
        11,  -43,  -43,  -43,  -43,  -43,  -43,  -43,  -43,  -43,
-      -43,  -43,  -43,  -43,  -43,  -43,  -43
+      -43,  -43,  -43,  -43,  -43,  -43,  -43,  -43,  -43
     },
 
     {
-       11,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,
-      -44,  -44,  -44,   44,  -44,  -44,  -44
+       11,   45,   45,   46,   45,   45,   45,   45,   45,   45,
+       45,   45,   45,   45,   45,   45,   45,   45,   45
 
     },
 
     {
-       11,   45,   45,  -45,   45,   45,   45,   45,   45,   45,
-       45,   45,   45,   45,   45,   45,   45
+       11,   45,   45,   46,   45,   45,   45,   45,   45,   45,
+       45,   45,   45,   45,   45,   45,   45,   45,   45
     },
 
     {
-       11,  -46,   46,   47,  -46,  -46,  -46,  -46,  -46,  -46,
-      -46,  -46,  -46,  -46,  -46,  -46,  -46
+       11,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,
+      -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46
     },
 
     {
-       11,   48,  -47,  -47,   48,   48,   48,   48,   48,   48,
-       48,   48,   48,   48,   48,   48,   48
+       11,  -47,  -47,  -47,  -47,  -47,  -47,  -47,  -47,  -47,
+      -47,  -47,  -47,   47,  -47,  -47,  -47,  -47,  -47
     },
 
     {
-       11,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,
-      -48,  -48,  -48,  -48,  -48,  -48,  -48
+       11,   48,   48,  -48,   48,   48,   48,   48,   48,   48,
+       48,   48,   48,   48,   48,   48,   48,   48,   48
     },
 
     {
-       11,   49,   49,   50,   49,  -49,   49,   49,  -49,   49,
-       49,   49,   49,   49,   49,  -49,   49
+       11,  -49,   49,   50,  -49,  -49,  -49,  -49,  -49,  -49,
+      -49,  -49,  -49,  -49,  -49,  -49,  -49,  -49,  -49
 
     },
 
     {
-       11,  -50,  -50,  -50,  -50,  -50,  -50,  -50,  -50,  -50,
-      -50,  -50,  -50,  -50,  -50,  -50,  -50
+       11,   51,  -50,  -50,   51,   51,   51,   51,   51,   51,
+       51,   51,   51,   51,   51,   51,   51,   51,   51
     },
 
     {
-       11,  -51,  -51,   52,  -51,  -51,  -51,  -51,  -51,  -51,
-      -51,  -51,  -51,  -51,  -51,  -51,  -51
+       11,  -51,  -51,  -51,  -51,  -51,  -51,  -51,  -51,  -51,
+      -51,  -51,  -51,  -51,  -51,  -51,  -51,  -51,  -51
     },
 
     {
-       11,  -52,  -52,  -52,  -52,  -52,  -52,  -52,  -52,  -52,
-      -52,  -52,  -52,  -52,  -52,  -52,  -52
+       11,   52,   52,   53,   52,  -52,   52,   52,  -52,   52,
+       52,   52,   52,   52,   52,   52,   52,  -52,   52
     },
 
     {
        11,  -53,  -53,  -53,  -53,  -53,  -53,  -53,  -53,  -53,
-      -53,  -53,  -53,  -53,  -53,  -53,  -53
+      -53,  -53,  -53,  -53,  -53,  -53,  -53,  -53,  -53
     },
 
     {
-       11,   54,   54,  -54,   54,   54,   54,   54,   54,   54,
-       54,   54,   54,   54,   54,   54,   54
+       11,  -54,  -54,   55,  -54,  -54,  -54,  -54,  -54,  -54,
+      -54,  -54,  -54,  -54,  -54,  -54,  -54,  -54,  -54
 
     },
 
     {
        11,  -55,  -55,  -55,  -55,  -55,  -55,  -55,  -55,  -55,
-      -55,  -55,  -55,  -55,  -55,  -55,  -55
+      -55,  -55,  -55,  -55,  -55,  -55,  -55,  -55,  -55
     },
 
     {
-       11,  -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,
-      -56,   60,   57,   57,  -56,  -56,  -56
+       11,  -56,   56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,
+      -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56
     },
 
     {
        11,  -57,  -57,  -57,  -57,  -57,  -57,  -57,  -57,  -57,
-      -57,   57,   57,   57,  -57,  -57,  -57
+      -57,  -57,  -57,  -57,  -57,  -57,  -57,  -57,  -57
     },
 
     {
-       11,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,
-      -58,  -58,  -58,  -58,  -58,  -58,  -58
+       11,   58,   58,  -58,   58,   58,   58,   58,   58,   58,
+       58,   58,   58,   58,   58,   58,   58,   58,   58
     },
 
     {
        11,  -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59,
-      -59,  -59,  -59,  -59,  -59,  -59,  -59
+      -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59
 
     },
 
     {
        11,  -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60,
-      -60,   57,   57,   57,  -60,  -60,  -60
+      -60,   66,   61,   61,  -60,  -60,  -60,  -60,  -60
+    },
+
+    {
+       11,  -61,  -61,  -61,  -61,  -61,  -61,  -61,  -61,  -61,
+      -61,   61,   61,   61,  -61,  -61,  -61,  -61,  -61
+    },
+
+    {
+       11,  -62,  -62,  -62,  -62,  -62,  -62,  -62,  -62,  -62,
+      -62,  -62,  -62,  -62,  -62,  -62,  -62,  -62,  -62
+    },
+
+    {
+       11,  -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,
+      -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63
+    },
+
+    {
+       11,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,
+      -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64
+
+    },
+
+    {
+       11,  -65,  -65,  -65,  -65,  -65,  -65,  -65,  -65,  -65,
+      -65,  -65,  -65,  -65,  -65,  -65,  -65,  -65,  -65
+    },
+
+    {
+       11,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,
+      -66,   61,   61,   61,  -66,  -66,  -66,  -66,  -66
     },
 
     } ;
@@ -701,8 +732,8 @@
 	*yy_cp = '\0'; \
 	(yy_c_buf_p) = yy_cp;
 
-#define YY_NUM_RULES 33
-#define YY_END_OF_BUFFER 34
+#define YY_NUM_RULES 38
+#define YY_END_OF_BUFFER 39
 /* This struct is not used in this scanner,
    but its presence is necessary. */
 struct yy_trans_info
@@ -710,14 +741,15 @@
 	flex_int32_t yy_verify;
 	flex_int32_t yy_nxt;
 	};
-static yyconst flex_int16_t yy_accept[61] =
+static yyconst flex_int16_t yy_accept[67] =
     {   0,
         0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
-       34,    5,    4,    2,    3,    7,    8,    6,   32,   29,
-       31,   24,   28,   27,   26,   22,   17,   13,   16,   20,
-       22,   11,   12,   19,   19,   14,   22,   22,    4,    2,
-        3,    3,    1,    6,   32,   29,   31,   30,   24,   23,
-       26,   25,   15,   20,    9,   19,   19,   21,   10,   18
+       39,    5,    4,    2,    3,    7,    8,    6,   37,   34,
+       36,   29,   33,   32,   31,   27,   26,   21,   13,   20,
+       24,   27,   11,   12,   23,   23,   18,   14,   19,   27,
+       27,    4,    2,    3,    3,    1,    6,   37,   34,   36,
+       35,   29,   28,   31,   30,   26,   15,   24,    9,   23,
+       23,   16,   17,   25,   10,   22
     } ;
 
 static yyconst flex_int32_t yy_ec[256] =
@@ -727,15 +759,15 @@
         1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
         1,    2,    4,    5,    6,    1,    1,    7,    8,    9,
        10,    1,    1,    1,   11,   12,   12,   13,   13,   13,
-       13,   13,   13,   13,   13,   13,   13,    1,    1,    1,
-       14,    1,    1,    1,   13,   13,   13,   13,   13,   13,
+       13,   13,   13,   13,   13,   13,   13,    1,    1,   14,
+       15,   16,    1,    1,   13,   13,   13,   13,   13,   13,
        13,   13,   13,   13,   13,   13,   13,   13,   13,   13,
        13,   13,   13,   13,   13,   13,   13,   13,   13,   13,
-        1,   15,    1,    1,   13,    1,   13,   13,   13,   13,
+        1,   17,    1,    1,   13,    1,   13,   13,   13,   13,
 
        13,   13,   13,   13,   13,   13,   13,   13,   13,   13,
        13,   13,   13,   13,   13,   13,   13,   13,   13,   13,
-       13,   13,    1,   16,    1,    1,    1,    1,    1,    1,
+       13,   13,    1,   18,    1,    1,    1,    1,    1,    1,
         1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
         1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
         1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
@@ -920,7 +952,7 @@
 /* This used to be an fputs(), but since the string might contain NUL's,
  * we now use fwrite().
  */
-#define ECHO do { if (fwrite( zconftext, zconfleng, 1, zconfout )) {} } while (0)
+#define ECHO fwrite( zconftext, zconfleng, 1, zconfout )
 #endif
 
 /* Gets input and stuffs it into "buf".  number of characters read, or YY_NULL,
@@ -1142,22 +1174,38 @@
 	YY_BREAK
 case 16:
 YY_RULE_SETUP
+return T_LESS_EQUAL;
+	YY_BREAK
+case 17:
+YY_RULE_SETUP
+return T_GREATER_EQUAL;
+	YY_BREAK
+case 18:
+YY_RULE_SETUP
+return T_LESS;
+	YY_BREAK
+case 19:
+YY_RULE_SETUP
+return T_GREATER;
+	YY_BREAK
+case 20:
+YY_RULE_SETUP
 {
 		str = zconftext[0];
 		new_string();
 		BEGIN(STRING);
 	}
 	YY_BREAK
-case 17:
-/* rule 17 can match eol */
+case 21:
+/* rule 21 can match eol */
 YY_RULE_SETUP
 BEGIN(INITIAL); current_file->lineno++; return T_EOL;
 	YY_BREAK
-case 18:
+case 22:
 YY_RULE_SETUP
 /* ignore */
 	YY_BREAK
-case 19:
+case 23:
 YY_RULE_SETUP
 {
 		const struct kconf_id *id = kconf_id_lookup(zconftext, zconfleng);
@@ -1170,27 +1218,35 @@
 		return T_WORD;
 	}
 	YY_BREAK
-case 20:
+case 24:
 YY_RULE_SETUP
 /* comment */
 	YY_BREAK
-case 21:
-/* rule 21 can match eol */
+case 25:
+/* rule 25 can match eol */
 YY_RULE_SETUP
 current_file->lineno++;
 	YY_BREAK
-case 22:
+case 26:
 YY_RULE_SETUP
 
 	YY_BREAK
+case 27:
+YY_RULE_SETUP
+{
+		fprintf(stderr,
+		        "%s:%d:warning: ignoring unsupported character '%c'\n",
+		        zconf_curname(), zconf_lineno(), *zconftext);
+	}
+	YY_BREAK
 case YY_STATE_EOF(PARAM):
 {
 		BEGIN(INITIAL);
 	}
 	YY_BREAK
 
-case 23:
-/* rule 23 can match eol */
+case 28:
+/* rule 28 can match eol */
 *yy_cp = (yy_hold_char); /* undo effects of setting up zconftext */
 (yy_c_buf_p) = yy_cp -= 1;
 YY_DO_BEFORE_ACTION; /* set up zconftext again */
@@ -1201,14 +1257,14 @@
 		return T_WORD_QUOTE;
 	}
 	YY_BREAK
-case 24:
+case 29:
 YY_RULE_SETUP
 {
 		append_string(zconftext, zconfleng);
 	}
 	YY_BREAK
-case 25:
-/* rule 25 can match eol */
+case 30:
+/* rule 30 can match eol */
 *yy_cp = (yy_hold_char); /* undo effects of setting up zconftext */
 (yy_c_buf_p) = yy_cp -= 1;
 YY_DO_BEFORE_ACTION; /* set up zconftext again */
@@ -1219,13 +1275,13 @@
 		return T_WORD_QUOTE;
 	}
 	YY_BREAK
-case 26:
+case 31:
 YY_RULE_SETUP
 {
 		append_string(zconftext + 1, zconfleng - 1);
 	}
 	YY_BREAK
-case 27:
+case 32:
 YY_RULE_SETUP
 {
 		if (str == zconftext[0]) {
@@ -1236,8 +1292,8 @@
 			append_string(zconftext, 1);
 	}
 	YY_BREAK
-case 28:
-/* rule 28 can match eol */
+case 33:
+/* rule 33 can match eol */
 YY_RULE_SETUP
 {
 		printf("%s:%d:warning: multi-line strings not supported\n", zconf_curname(), zconf_lineno());
@@ -1252,7 +1308,7 @@
 	}
 	YY_BREAK
 
-case 29:
+case 34:
 YY_RULE_SETUP
 {
 		ts = 0;
@@ -1277,8 +1333,8 @@
 		}
 	}
 	YY_BREAK
-case 30:
-/* rule 30 can match eol */
+case 35:
+/* rule 35 can match eol */
 *yy_cp = (yy_hold_char); /* undo effects of setting up zconftext */
 (yy_c_buf_p) = yy_cp -= 1;
 YY_DO_BEFORE_ACTION; /* set up zconftext again */
@@ -1289,15 +1345,15 @@
 		return T_HELPTEXT;
 	}
 	YY_BREAK
-case 31:
-/* rule 31 can match eol */
+case 36:
+/* rule 36 can match eol */
 YY_RULE_SETUP
 {
 		current_file->lineno++;
 		append_string("\n", 1);
 	}
 	YY_BREAK
-case 32:
+case 37:
 YY_RULE_SETUP
 {
 		while (zconfleng) {
@@ -1328,7 +1384,7 @@
 	yyterminate();
 }
 	YY_BREAK
-case 33:
+case 38:
 YY_RULE_SETUP
 YY_FATAL_ERROR( "flex scanner jammed" );
 	YY_BREAK
diff --git a/scripts/kconfig/zconf.tab.c_shipped b/scripts/kconfig/zconf.tab.c_shipped
index de5e84e..7a4d658 100644
--- a/scripts/kconfig/zconf.tab.c_shipped
+++ b/scripts/kconfig/zconf.tab.c_shipped
@@ -1,8 +1,8 @@
-/* A Bison parser, made by GNU Bison 2.5.  */
+/* A Bison parser, made by GNU Bison 2.5.1.  */
 
 /* Bison implementation for Yacc-like parsers in C
    
-      Copyright (C) 1984, 1989-1990, 2000-2011 Free Software Foundation, Inc.
+      Copyright (C) 1984, 1989-1990, 2000-2012 Free Software Foundation, Inc.
    
    This program is free software: you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
@@ -44,7 +44,7 @@
 #define YYBISON 1
 
 /* Bison version.  */
-#define YYBISON_VERSION "2.5"
+#define YYBISON_VERSION "2.5.1"
 
 /* Skeleton name.  */
 #define YYSKELETON_NAME "yacc.c"
@@ -108,6 +108,14 @@
 
 
 
+# ifndef YY_NULL
+#  if defined __cplusplus && 201103L <= __cplusplus
+#   define YY_NULL nullptr
+#  else
+#   define YY_NULL 0
+#  endif
+# endif
+
 /* Enabling traces.  */
 #ifndef YYDEBUG
 # define YYDEBUG 1
@@ -159,13 +167,17 @@
      T_WORD = 281,
      T_WORD_QUOTE = 282,
      T_UNEQUAL = 283,
-     T_CLOSE_PAREN = 284,
-     T_OPEN_PAREN = 285,
-     T_EOL = 286,
-     T_OR = 287,
-     T_AND = 288,
-     T_EQUAL = 289,
-     T_NOT = 290
+     T_LESS = 284,
+     T_LESS_EQUAL = 285,
+     T_GREATER = 286,
+     T_GREATER_EQUAL = 287,
+     T_CLOSE_PAREN = 288,
+     T_OPEN_PAREN = 289,
+     T_EOL = 290,
+     T_OR = 291,
+     T_AND = 292,
+     T_EQUAL = 293,
+     T_NOT = 294
    };
 #endif
 
@@ -304,6 +316,7 @@
 #    if ! defined _ALLOCA_H && ! defined EXIT_SUCCESS && (defined __STDC__ || defined __C99__FUNC__ \
      || defined __cplusplus || defined _MSC_VER)
 #     include <stdlib.h> /* INFRINGES ON USER NAME SPACE */
+      /* Use EXIT_SUCCESS as a witness for stdlib.h.  */
 #     ifndef EXIT_SUCCESS
 #      define EXIT_SUCCESS 0
 #     endif
@@ -395,20 +408,20 @@
 #endif
 
 #if defined YYCOPY_NEEDED && YYCOPY_NEEDED
-/* Copy COUNT objects from FROM to TO.  The source and destination do
+/* Copy COUNT objects from SRC to DST.  The source and destination do
    not overlap.  */
 # ifndef YYCOPY
 #  if defined __GNUC__ && 1 < __GNUC__
-#   define YYCOPY(To, From, Count) \
-      __builtin_memcpy (To, From, (Count) * sizeof (*(From)))
+#   define YYCOPY(Dst, Src, Count) \
+      __builtin_memcpy (Dst, Src, (Count) * sizeof (*(Src)))
 #  else
-#   define YYCOPY(To, From, Count)		\
-      do					\
-	{					\
-	  YYSIZE_T yyi;				\
-	  for (yyi = 0; yyi < (Count); yyi++)	\
-	    (To)[yyi] = (From)[yyi];		\
-	}					\
+#   define YYCOPY(Dst, Src, Count)              \
+      do                                        \
+        {                                       \
+          YYSIZE_T yyi;                         \
+          for (yyi = 0; yyi < (Count); yyi++)   \
+            (Dst)[yyi] = (Src)[yyi];            \
+        }                                       \
       while (YYID (0))
 #  endif
 # endif
@@ -417,20 +430,20 @@
 /* YYFINAL -- State number of the termination state.  */
 #define YYFINAL  11
 /* YYLAST -- Last index in YYTABLE.  */
-#define YYLAST   290
+#define YYLAST   298
 
 /* YYNTOKENS -- Number of terminals.  */
-#define YYNTOKENS  36
+#define YYNTOKENS  40
 /* YYNNTS -- Number of nonterminals.  */
 #define YYNNTS  50
 /* YYNRULES -- Number of rules.  */
-#define YYNRULES  118
+#define YYNRULES  122
 /* YYNRULES -- Number of states.  */
-#define YYNSTATES  191
+#define YYNSTATES  199
 
 /* YYTRANSLATE(YYLEX) -- Bison symbol number corresponding to YYLEX.  */
 #define YYUNDEFTOK  2
-#define YYMAXUTOK   290
+#define YYMAXUTOK   294
 
 #define YYTRANSLATE(YYX)						\
   ((unsigned int) (YYX) <= YYMAXUTOK ? yytranslate[YYX] : YYUNDEFTOK)
@@ -467,7 +480,7 @@
        5,     6,     7,     8,     9,    10,    11,    12,    13,    14,
       15,    16,    17,    18,    19,    20,    21,    22,    23,    24,
       25,    26,    27,    28,    29,    30,    31,    32,    33,    34,
-      35
+      35,    36,    37,    38,    39
 };
 
 #if YYDEBUG
@@ -486,64 +499,67 @@
      235,   238,   241,   244,   248,   252,   255,   258,   261,   262,
      265,   268,   271,   276,   277,   280,   283,   286,   287,   290,
      292,   294,   297,   300,   303,   305,   308,   309,   312,   314,
-     318,   322,   326,   329,   333,   337,   339,   341,   342
+     318,   322,   326,   330,   334,   338,   342,   345,   349,   353,
+     355,   357,   358
 };
 
 /* YYRHS -- A `-1'-separated list of the rules' RHS.  */
 static const yytype_int8 yyrhs[] =
 {
-      37,     0,    -1,    81,    38,    -1,    38,    -1,    63,    39,
-      -1,    39,    -1,    -1,    39,    41,    -1,    39,    55,    -1,
-      39,    67,    -1,    39,    80,    -1,    39,    26,     1,    31,
-      -1,    39,    40,     1,    31,    -1,    39,     1,    31,    -1,
+      41,     0,    -1,    85,    42,    -1,    42,    -1,    67,    43,
+      -1,    43,    -1,    -1,    43,    45,    -1,    43,    59,    -1,
+      43,    71,    -1,    43,    84,    -1,    43,    26,     1,    35,
+      -1,    43,    44,     1,    35,    -1,    43,     1,    35,    -1,
       16,    -1,    18,    -1,    19,    -1,    21,    -1,    17,    -1,
-      22,    -1,    20,    -1,    23,    -1,    31,    -1,    61,    -1,
-      71,    -1,    44,    -1,    46,    -1,    69,    -1,    26,     1,
-      31,    -1,     1,    31,    -1,    10,    26,    31,    -1,    43,
-      47,    -1,    11,    26,    31,    -1,    45,    47,    -1,    -1,
-      47,    48,    -1,    47,    49,    -1,    47,    75,    -1,    47,
-      73,    -1,    47,    42,    -1,    47,    31,    -1,    19,    78,
-      31,    -1,    18,    79,    82,    31,    -1,    20,    83,    82,
-      31,    -1,    21,    26,    82,    31,    -1,    22,    84,    84,
-      82,    31,    -1,    24,    50,    31,    -1,    -1,    50,    26,
-      51,    -1,    -1,    34,    79,    -1,     7,    85,    31,    -1,
-      52,    56,    -1,    80,    -1,    53,    58,    54,    -1,    -1,
-      56,    57,    -1,    56,    75,    -1,    56,    73,    -1,    56,
-      31,    -1,    56,    42,    -1,    18,    79,    82,    31,    -1,
-      19,    78,    31,    -1,    17,    31,    -1,    20,    26,    82,
-      31,    -1,    -1,    58,    41,    -1,    14,    83,    81,    -1,
-      80,    -1,    59,    62,    60,    -1,    -1,    62,    41,    -1,
-      62,    67,    -1,    62,    55,    -1,     3,    79,    81,    -1,
-       4,    79,    31,    -1,    64,    76,    74,    -1,    80,    -1,
-      65,    68,    66,    -1,    -1,    68,    41,    -1,    68,    67,
-      -1,    68,    55,    -1,     6,    79,    31,    -1,     9,    79,
-      31,    -1,    70,    74,    -1,    12,    31,    -1,    72,    13,
-      -1,    -1,    74,    75,    -1,    74,    31,    -1,    74,    42,
-      -1,    16,    25,    83,    31,    -1,    -1,    76,    77,    -1,
-      76,    31,    -1,    23,    82,    -1,    -1,    79,    82,    -1,
-      26,    -1,    27,    -1,     5,    31,    -1,     8,    31,    -1,
-      15,    31,    -1,    31,    -1,    81,    31,    -1,    -1,    14,
-      83,    -1,    84,    -1,    84,    34,    84,    -1,    84,    28,
-      84,    -1,    30,    83,    29,    -1,    35,    83,    -1,    83,
-      32,    83,    -1,    83,    33,    83,    -1,    26,    -1,    27,
-      -1,    -1,    26,    -1
+      22,    -1,    20,    -1,    23,    -1,    35,    -1,    65,    -1,
+      75,    -1,    48,    -1,    50,    -1,    73,    -1,    26,     1,
+      35,    -1,     1,    35,    -1,    10,    26,    35,    -1,    47,
+      51,    -1,    11,    26,    35,    -1,    49,    51,    -1,    -1,
+      51,    52,    -1,    51,    53,    -1,    51,    79,    -1,    51,
+      77,    -1,    51,    46,    -1,    51,    35,    -1,    19,    82,
+      35,    -1,    18,    83,    86,    35,    -1,    20,    87,    86,
+      35,    -1,    21,    26,    86,    35,    -1,    22,    88,    88,
+      86,    35,    -1,    24,    54,    35,    -1,    -1,    54,    26,
+      55,    -1,    -1,    38,    83,    -1,     7,    89,    35,    -1,
+      56,    60,    -1,    84,    -1,    57,    62,    58,    -1,    -1,
+      60,    61,    -1,    60,    79,    -1,    60,    77,    -1,    60,
+      35,    -1,    60,    46,    -1,    18,    83,    86,    35,    -1,
+      19,    82,    35,    -1,    17,    35,    -1,    20,    26,    86,
+      35,    -1,    -1,    62,    45,    -1,    14,    87,    85,    -1,
+      84,    -1,    63,    66,    64,    -1,    -1,    66,    45,    -1,
+      66,    71,    -1,    66,    59,    -1,     3,    83,    85,    -1,
+       4,    83,    35,    -1,    68,    80,    78,    -1,    84,    -1,
+      69,    72,    70,    -1,    -1,    72,    45,    -1,    72,    71,
+      -1,    72,    59,    -1,     6,    83,    35,    -1,     9,    83,
+      35,    -1,    74,    78,    -1,    12,    35,    -1,    76,    13,
+      -1,    -1,    78,    79,    -1,    78,    35,    -1,    78,    46,
+      -1,    16,    25,    87,    35,    -1,    -1,    80,    81,    -1,
+      80,    35,    -1,    23,    86,    -1,    -1,    83,    86,    -1,
+      26,    -1,    27,    -1,     5,    35,    -1,     8,    35,    -1,
+      15,    35,    -1,    35,    -1,    85,    35,    -1,    -1,    14,
+      87,    -1,    88,    -1,    88,    29,    88,    -1,    88,    30,
+      88,    -1,    88,    31,    88,    -1,    88,    32,    88,    -1,
+      88,    38,    88,    -1,    88,    28,    88,    -1,    34,    87,
+      33,    -1,    39,    87,    -1,    87,    36,    87,    -1,    87,
+      37,    87,    -1,    26,    -1,    27,    -1,    -1,    26,    -1
 };
 
 /* YYRLINE[YYN] -- source line where rule number YYN was defined.  */
 static const yytype_uint16 yyrline[] =
 {
-       0,   103,   103,   103,   105,   105,   107,   109,   110,   111,
-     112,   113,   114,   118,   122,   122,   122,   122,   122,   122,
-     122,   122,   126,   127,   128,   129,   130,   131,   135,   136,
-     142,   150,   156,   164,   174,   176,   177,   178,   179,   180,
-     181,   184,   192,   198,   208,   214,   220,   223,   225,   236,
-     237,   242,   251,   256,   264,   267,   269,   270,   271,   272,
-     273,   276,   282,   293,   299,   309,   311,   316,   324,   332,
-     335,   337,   338,   339,   344,   351,   358,   363,   371,   374,
-     376,   377,   378,   381,   389,   396,   403,   409,   416,   418,
-     419,   420,   423,   431,   433,   434,   437,   444,   446,   451,
-     452,   455,   456,   457,   461,   462,   465,   466,   469,   470,
-     471,   472,   473,   474,   475,   478,   479,   482,   483
+       0,   108,   108,   108,   110,   110,   112,   114,   115,   116,
+     117,   118,   119,   123,   127,   127,   127,   127,   127,   127,
+     127,   127,   131,   132,   133,   134,   135,   136,   140,   141,
+     147,   155,   161,   169,   179,   181,   182,   183,   184,   185,
+     186,   189,   197,   203,   213,   219,   225,   228,   230,   241,
+     242,   247,   256,   261,   269,   272,   274,   275,   276,   277,
+     278,   281,   287,   298,   304,   314,   316,   321,   329,   337,
+     340,   342,   343,   344,   349,   356,   363,   368,   376,   379,
+     381,   382,   383,   386,   394,   401,   408,   414,   421,   423,
+     424,   425,   428,   436,   438,   439,   442,   449,   451,   456,
+     457,   460,   461,   462,   466,   467,   470,   471,   474,   475,
+     476,   477,   478,   479,   480,   481,   482,   483,   484,   487,
+     488,   491,   492
 };
 #endif
 
@@ -557,6 +573,7 @@
   "T_MENUCONFIG", "T_HELP", "T_HELPTEXT", "T_IF", "T_ENDIF", "T_DEPENDS",
   "T_OPTIONAL", "T_PROMPT", "T_TYPE", "T_DEFAULT", "T_SELECT", "T_RANGE",
   "T_VISIBLE", "T_OPTION", "T_ON", "T_WORD", "T_WORD_QUOTE", "T_UNEQUAL",
+  "T_LESS", "T_LESS_EQUAL", "T_GREATER", "T_GREATER_EQUAL",
   "T_CLOSE_PAREN", "T_OPEN_PAREN", "T_EOL", "T_OR", "T_AND", "T_EQUAL",
   "T_NOT", "$accept", "input", "start", "stmt_list", "option_name",
   "common_stmt", "option_error", "config_entry_start", "config_stmt",
@@ -568,7 +585,7 @@
   "menu_entry", "menu_end", "menu_stmt", "menu_block", "source_stmt",
   "comment", "comment_stmt", "help_start", "help", "depends_list",
   "depends", "visibility_list", "visible", "prompt_stmt_opt", "prompt",
-  "end", "nl", "if_expr", "expr", "symbol", "word_opt", 0
+  "end", "nl", "if_expr", "expr", "symbol", "word_opt", YY_NULL
 };
 #endif
 
@@ -580,25 +597,26 @@
        0,   256,   257,   258,   259,   260,   261,   262,   263,   264,
      265,   266,   267,   268,   269,   270,   271,   272,   273,   274,
      275,   276,   277,   278,   279,   280,   281,   282,   283,   284,
-     285,   286,   287,   288,   289,   290
+     285,   286,   287,   288,   289,   290,   291,   292,   293,   294
 };
 # endif
 
 /* YYR1[YYN] -- Symbol number of symbol that rule YYN derives.  */
 static const yytype_uint8 yyr1[] =
 {
-       0,    36,    37,    37,    38,    38,    39,    39,    39,    39,
-      39,    39,    39,    39,    40,    40,    40,    40,    40,    40,
-      40,    40,    41,    41,    41,    41,    41,    41,    42,    42,
-      43,    44,    45,    46,    47,    47,    47,    47,    47,    47,
-      47,    48,    48,    48,    48,    48,    49,    50,    50,    51,
-      51,    52,    53,    54,    55,    56,    56,    56,    56,    56,
-      56,    57,    57,    57,    57,    58,    58,    59,    60,    61,
-      62,    62,    62,    62,    63,    64,    65,    66,    67,    68,
-      68,    68,    68,    69,    70,    71,    72,    73,    74,    74,
-      74,    74,    75,    76,    76,    76,    77,    78,    78,    79,
-      79,    80,    80,    80,    81,    81,    82,    82,    83,    83,
-      83,    83,    83,    83,    83,    84,    84,    85,    85
+       0,    40,    41,    41,    42,    42,    43,    43,    43,    43,
+      43,    43,    43,    43,    44,    44,    44,    44,    44,    44,
+      44,    44,    45,    45,    45,    45,    45,    45,    46,    46,
+      47,    48,    49,    50,    51,    51,    51,    51,    51,    51,
+      51,    52,    52,    52,    52,    52,    53,    54,    54,    55,
+      55,    56,    57,    58,    59,    60,    60,    60,    60,    60,
+      60,    61,    61,    61,    61,    62,    62,    63,    64,    65,
+      66,    66,    66,    66,    67,    68,    69,    70,    71,    72,
+      72,    72,    72,    73,    74,    75,    76,    77,    78,    78,
+      78,    78,    79,    80,    80,    80,    81,    82,    82,    83,
+      83,    84,    84,    84,    85,    85,    86,    86,    87,    87,
+      87,    87,    87,    87,    87,    87,    87,    87,    87,    88,
+      88,    89,    89
 };
 
 /* YYR2[YYN] -- Number of symbols composing right hand side of rule YYN.  */
@@ -615,7 +633,8 @@
        2,     2,     2,     3,     3,     2,     2,     2,     0,     2,
        2,     2,     4,     0,     2,     2,     2,     0,     2,     1,
        1,     2,     2,     2,     1,     2,     0,     2,     1,     3,
-       3,     3,     2,     3,     3,     1,     1,     0,     1
+       3,     3,     3,     3,     3,     3,     2,     3,     3,     1,
+       1,     0,     1
 };
 
 /* YYDEFACT[STATE-NAME] -- Default reduction number in state STATE-NUM.
@@ -624,72 +643,72 @@
 static const yytype_uint8 yydefact[] =
 {
        6,     0,   104,     0,     3,     0,     6,     6,    99,   100,
-       0,     1,     0,     0,     0,     0,   117,     0,     0,     0,
+       0,     1,     0,     0,     0,     0,   121,     0,     0,     0,
        0,     0,     0,    14,    18,    15,    16,    20,    17,    19,
       21,     0,    22,     0,     7,    34,    25,    34,    26,    55,
       65,     8,    70,    23,    93,    79,     9,    27,    88,    24,
-      10,     0,   105,     2,    74,    13,     0,   101,     0,   118,
-       0,   102,     0,     0,     0,   115,   116,     0,     0,     0,
+      10,     0,   105,     2,    74,    13,     0,   101,     0,   122,
+       0,   102,     0,     0,     0,   119,   120,     0,     0,     0,
      108,   103,     0,     0,     0,     0,     0,     0,     0,    88,
-       0,     0,    75,    83,    51,    84,    30,    32,     0,   112,
-       0,     0,    67,     0,     0,    11,    12,     0,     0,     0,
-       0,    97,     0,     0,     0,    47,     0,    40,    39,    35,
-      36,     0,    38,    37,     0,     0,    97,     0,    59,    60,
-      56,    58,    57,    66,    54,    53,    71,    73,    69,    72,
-      68,   106,    95,     0,    94,    80,    82,    78,    81,    77,
-      90,    91,    89,   111,   113,   114,   110,   109,    29,    86,
-       0,   106,     0,   106,   106,   106,     0,     0,     0,    87,
-      63,   106,     0,   106,     0,    96,     0,     0,    41,    98,
-       0,     0,   106,    49,    46,    28,     0,    62,     0,   107,
-      92,    42,    43,    44,     0,     0,    48,    61,    64,    45,
-      50
+       0,     0,    75,    83,    51,    84,    30,    32,     0,   116,
+       0,     0,    67,     0,     0,     0,     0,     0,     0,    11,
+      12,     0,     0,     0,     0,    97,     0,     0,     0,    47,
+       0,    40,    39,    35,    36,     0,    38,    37,     0,     0,
+      97,     0,    59,    60,    56,    58,    57,    66,    54,    53,
+      71,    73,    69,    72,    68,   106,    95,     0,    94,    80,
+      82,    78,    81,    77,    90,    91,    89,   115,   117,   118,
+     114,   109,   110,   111,   112,   113,    29,    86,     0,   106,
+       0,   106,   106,   106,     0,     0,     0,    87,    63,   106,
+       0,   106,     0,    96,     0,     0,    41,    98,     0,     0,
+     106,    49,    46,    28,     0,    62,     0,   107,    92,    42,
+      43,    44,     0,     0,    48,    61,    64,    45,    50
 };
 
 /* YYDEFGOTO[NTERM-NUM].  */
 static const yytype_int16 yydefgoto[] =
 {
-      -1,     3,     4,     5,    33,    34,   108,    35,    36,    37,
-      38,    74,   109,   110,   157,   186,    39,    40,   124,    41,
-      76,   120,    77,    42,   128,    43,    78,     6,    44,    45,
-     137,    46,    80,    47,    48,    49,   111,   112,    81,   113,
-      79,   134,   152,   153,    50,     7,   165,    69,    70,    60
+      -1,     3,     4,     5,    33,    34,   112,    35,    36,    37,
+      38,    74,   113,   114,   165,   194,    39,    40,   128,    41,
+      76,   124,    77,    42,   132,    43,    78,     6,    44,    45,
+     141,    46,    80,    47,    48,    49,   115,   116,    81,   117,
+      79,   138,   160,   161,    50,     7,   173,    69,    70,    60
 };
 
 /* YYPACT[STATE-NUM] -- Index in YYTABLE of the portion describing
    STATE-NUM.  */
-#define YYPACT_NINF -90
+#define YYPACT_NINF -91
 static const yytype_int16 yypact[] =
 {
-       4,    42,   -90,    96,   -90,   111,   -90,    15,   -90,   -90,
-      75,   -90,    82,    42,   104,    42,   110,   107,    42,   115,
-     125,    -4,   121,   -90,   -90,   -90,   -90,   -90,   -90,   -90,
-     -90,   162,   -90,   163,   -90,   -90,   -90,   -90,   -90,   -90,
-     -90,   -90,   -90,   -90,   -90,   -90,   -90,   -90,   -90,   -90,
-     -90,   139,   -90,   -90,   138,   -90,   142,   -90,   143,   -90,
-     152,   -90,   164,   167,   168,   -90,   -90,    -4,    -4,    77,
-     -18,   -90,   177,   185,    33,    71,   195,   247,   236,    -2,
-     236,   171,   -90,   -90,   -90,   -90,   -90,   -90,    41,   -90,
-      -4,    -4,   138,    97,    97,   -90,   -90,   186,   187,   194,
-      42,    42,    -4,   196,    97,   -90,   219,   -90,   -90,   -90,
-     -90,   210,   -90,   -90,   204,    42,    42,   199,   -90,   -90,
-     -90,   -90,   -90,   -90,   -90,   -90,   -90,   -90,   -90,   -90,
-     -90,   222,   -90,   223,   -90,   -90,   -90,   -90,   -90,   -90,
-     -90,   -90,   -90,   -90,   215,   -90,   -90,   -90,   -90,   -90,
-      -4,   222,   228,   222,    -5,   222,    97,    35,   229,   -90,
-     -90,   222,   232,   222,    -4,   -90,   135,   233,   -90,   -90,
-     234,   235,   222,   240,   -90,   -90,   237,   -90,   239,   -13,
-     -90,   -90,   -90,   -90,   244,    42,   -90,   -90,   -90,   -90,
-     -90
+      19,    37,   -91,    13,   -91,    79,   -91,    20,   -91,   -91,
+     -16,   -91,    21,    37,    25,    37,    41,    36,    37,    78,
+      83,    31,    56,   -91,   -91,   -91,   -91,   -91,   -91,   -91,
+     -91,   116,   -91,   127,   -91,   -91,   -91,   -91,   -91,   -91,
+     -91,   -91,   -91,   -91,   -91,   -91,   -91,   -91,   -91,   -91,
+     -91,   147,   -91,   -91,   105,   -91,   109,   -91,   111,   -91,
+     114,   -91,   136,   137,   142,   -91,   -91,    31,    31,    76,
+     254,   -91,   143,   146,    27,   115,   207,   258,   243,   -14,
+     243,   179,   -91,   -91,   -91,   -91,   -91,   -91,    -7,   -91,
+      31,    31,   105,    51,    51,    51,    51,    51,    51,   -91,
+     -91,   156,   168,   181,    37,    37,    31,   178,    51,   -91,
+     206,   -91,   -91,   -91,   -91,   196,   -91,   -91,   175,    37,
+      37,   185,   -91,   -91,   -91,   -91,   -91,   -91,   -91,   -91,
+     -91,   -91,   -91,   -91,   -91,   214,   -91,   230,   -91,   -91,
+     -91,   -91,   -91,   -91,   -91,   -91,   -91,   -91,   183,   -91,
+     -91,   -91,   -91,   -91,   -91,   -91,   -91,   -91,    31,   214,
+     194,   214,    45,   214,    51,    26,   195,   -91,   -91,   214,
+     197,   214,    31,   -91,   139,   208,   -91,   -91,   220,   224,
+     214,   222,   -91,   -91,   226,   -91,   227,   123,   -91,   -91,
+     -91,   -91,   235,    37,   -91,   -91,   -91,   -91,   -91
 };
 
 /* YYPGOTO[NTERM-NUM].  */
 static const yytype_int16 yypgoto[] =
 {
-     -90,   -90,   269,   271,   -90,    23,   -70,   -90,   -90,   -90,
-     -90,   243,   -90,   -90,   -90,   -90,   -90,   -90,   -90,   -48,
-     -90,   -90,   -90,   -90,   -90,   -90,   -90,   -90,   -90,   -90,
-     -90,   -20,   -90,   -90,   -90,   -90,   -90,   206,   205,   -68,
-     -90,   -90,   169,    -1,    27,    -7,   118,   -66,   -89,   -90
+     -91,   -91,   264,   268,   -91,    30,   -65,   -91,   -91,   -91,
+     -91,   238,   -91,   -91,   -91,   -91,   -91,   -91,   -91,   -12,
+     -91,   -91,   -91,   -91,   -91,   -91,   -91,   -91,   -91,   -91,
+     -91,    -5,   -91,   -91,   -91,   -91,   -91,   200,   209,   -61,
+     -91,   -91,   170,    -1,    65,     0,   118,   -66,   -90,   -91
 };
 
 /* YYTABLE[YYPACT[STATE-NUM]].  What to do in state STATE-NUM.  If
@@ -698,102 +717,102 @@
 #define YYTABLE_NINF -86
 static const yytype_int16 yytable[] =
 {
-      10,    88,    89,    54,   146,   147,   119,     1,   122,   164,
-      93,   141,    56,   142,    58,   156,    94,    62,     1,    90,
-      91,   131,    65,    66,   144,   145,    67,    90,    91,   132,
-     127,    68,   136,   -31,    97,     2,   154,   -31,   -31,   -31,
-     -31,   -31,   -31,   -31,   -31,    98,    52,   -31,   -31,    99,
-     -31,   100,   101,   102,   103,   104,   -31,   105,   129,   106,
-     138,   173,    92,   141,   107,   142,   174,   172,     8,     9,
-     143,   -33,    97,    90,    91,   -33,   -33,   -33,   -33,   -33,
-     -33,   -33,   -33,    98,   166,   -33,   -33,    99,   -33,   100,
-     101,   102,   103,   104,   -33,   105,    11,   106,   179,   151,
-     123,   126,   107,   135,   125,   130,     2,   139,     2,    90,
-      91,    -5,    12,    55,   161,    13,    14,    15,    16,    17,
-      18,    19,    20,    65,    66,    21,    22,    23,    24,    25,
-      26,    27,    28,    29,    30,    57,    59,    31,    61,    -4,
-      12,    63,    32,    13,    14,    15,    16,    17,    18,    19,
-      20,    64,    71,    21,    22,    23,    24,    25,    26,    27,
-      28,    29,    30,    72,    73,    31,   180,    90,    91,    52,
-      32,   -85,    97,    82,    83,   -85,   -85,   -85,   -85,   -85,
-     -85,   -85,   -85,    84,   190,   -85,   -85,    99,   -85,   -85,
-     -85,   -85,   -85,   -85,   -85,    85,    97,   106,    86,    87,
-     -52,   -52,   140,   -52,   -52,   -52,   -52,    98,    95,   -52,
-     -52,    99,   114,   115,   116,   117,    96,   148,   149,   150,
-     158,   106,   155,   159,    97,   163,   118,   -76,   -76,   -76,
-     -76,   -76,   -76,   -76,   -76,   160,   164,   -76,   -76,    99,
-      13,    14,    15,    16,    17,    18,    19,    20,    91,   106,
-      21,    22,    14,    15,   140,    17,    18,    19,    20,   168,
-     175,    21,    22,   177,   181,   182,   183,    32,   187,   167,
-     188,   169,   170,   171,   185,   189,    53,    51,    32,   176,
-      75,   178,   121,     0,   133,   162,     0,     0,     0,     0,
-     184
+      10,    88,    89,   150,   151,   152,   153,   154,   155,   135,
+      54,   123,    56,    11,    58,   126,   145,    62,   164,     2,
+     146,   136,     1,     1,   148,   149,   147,   -31,   101,    90,
+      91,   -31,   -31,   -31,   -31,   -31,   -31,   -31,   -31,   102,
+     162,   -31,   -31,   103,   -31,   104,   105,   106,   107,   108,
+     -31,   109,   181,   110,     2,    52,    55,    65,    66,   172,
+      57,   182,   111,     8,     9,    67,   131,    59,   140,    92,
+      68,    61,   145,   133,   180,   142,   146,    65,    66,    -5,
+      12,    90,    91,    13,    14,    15,    16,    17,    18,    19,
+      20,    71,   174,    21,    22,    23,    24,    25,    26,    27,
+      28,    29,    30,   159,    63,    31,   187,   127,   130,    64,
+     139,     2,    90,    91,    32,   -33,   101,    72,   169,   -33,
+     -33,   -33,   -33,   -33,   -33,   -33,   -33,   102,    73,   -33,
+     -33,   103,   -33,   104,   105,   106,   107,   108,   -33,   109,
+      52,   110,   129,   134,    82,   143,    83,    -4,    12,    84,
+     111,    13,    14,    15,    16,    17,    18,    19,    20,    90,
+      91,    21,    22,    23,    24,    25,    26,    27,    28,    29,
+      30,    85,    86,    31,   188,    90,    91,    87,    99,   -85,
+     101,   100,    32,   -85,   -85,   -85,   -85,   -85,   -85,   -85,
+     -85,   156,   198,   -85,   -85,   103,   -85,   -85,   -85,   -85,
+     -85,   -85,   -85,   157,   163,   110,   158,   166,   101,   167,
+     168,   171,   -52,   -52,   144,   -52,   -52,   -52,   -52,   102,
+      91,   -52,   -52,   103,   118,   119,   120,   121,   172,   176,
+     183,   101,   185,   110,   -76,   -76,   -76,   -76,   -76,   -76,
+     -76,   -76,   122,   189,   -76,   -76,   103,    13,    14,    15,
+      16,    17,    18,    19,    20,   190,   110,    21,    22,   191,
+     193,   195,   196,    14,    15,   144,    17,    18,    19,    20,
+     197,    53,    21,    22,    51,    75,   125,   175,    32,   177,
+     178,   179,    93,    94,    95,    96,    97,   184,   137,   186,
+     170,     0,    98,    32,     0,     0,     0,     0,   192
 };
 
 #define yypact_value_is_default(yystate) \
-  ((yystate) == (-90))
+  ((yystate) == (-91))
 
 #define yytable_value_is_error(yytable_value) \
   YYID (0)
 
 static const yytype_int16 yycheck[] =
 {
-       1,    67,    68,    10,    93,    94,    76,     3,    76,    14,
-      28,    81,    13,    81,    15,   104,    34,    18,     3,    32,
-      33,    23,    26,    27,    90,    91,    30,    32,    33,    31,
-      78,    35,    80,     0,     1,    31,   102,     4,     5,     6,
-       7,     8,     9,    10,    11,    12,    31,    14,    15,    16,
-      17,    18,    19,    20,    21,    22,    23,    24,    78,    26,
-      80,    26,    69,   133,    31,   133,    31,   156,    26,    27,
-      29,     0,     1,    32,    33,     4,     5,     6,     7,     8,
-       9,    10,    11,    12,   150,    14,    15,    16,    17,    18,
-      19,    20,    21,    22,    23,    24,     0,    26,   164,   100,
-      77,    78,    31,    80,    77,    78,    31,    80,    31,    32,
-      33,     0,     1,    31,   115,     4,     5,     6,     7,     8,
-       9,    10,    11,    26,    27,    14,    15,    16,    17,    18,
-      19,    20,    21,    22,    23,    31,    26,    26,    31,     0,
-       1,    26,    31,     4,     5,     6,     7,     8,     9,    10,
-      11,    26,    31,    14,    15,    16,    17,    18,    19,    20,
-      21,    22,    23,     1,     1,    26,    31,    32,    33,    31,
-      31,     0,     1,    31,    31,     4,     5,     6,     7,     8,
-       9,    10,    11,    31,   185,    14,    15,    16,    17,    18,
-      19,    20,    21,    22,    23,    31,     1,    26,    31,    31,
-       5,     6,    31,     8,     9,    10,    11,    12,    31,    14,
-      15,    16,    17,    18,    19,    20,    31,    31,    31,    25,
-       1,    26,    26,    13,     1,    26,    31,     4,     5,     6,
-       7,     8,     9,    10,    11,    31,    14,    14,    15,    16,
-       4,     5,     6,     7,     8,     9,    10,    11,    33,    26,
-      14,    15,     5,     6,    31,     8,     9,    10,    11,    31,
-      31,    14,    15,    31,    31,    31,    31,    31,    31,   151,
-      31,   153,   154,   155,    34,    31,     7,     6,    31,   161,
-      37,   163,    76,    -1,    79,   116,    -1,    -1,    -1,    -1,
-     172
+       1,    67,    68,    93,    94,    95,    96,    97,    98,    23,
+      10,    76,    13,     0,    15,    76,    81,    18,   108,    35,
+      81,    35,     3,     3,    90,    91,    33,     0,     1,    36,
+      37,     4,     5,     6,     7,     8,     9,    10,    11,    12,
+     106,    14,    15,    16,    17,    18,    19,    20,    21,    22,
+      23,    24,    26,    26,    35,    35,    35,    26,    27,    14,
+      35,    35,    35,    26,    27,    34,    78,    26,    80,    69,
+      39,    35,   137,    78,   164,    80,   137,    26,    27,     0,
+       1,    36,    37,     4,     5,     6,     7,     8,     9,    10,
+      11,    35,   158,    14,    15,    16,    17,    18,    19,    20,
+      21,    22,    23,   104,    26,    26,   172,    77,    78,    26,
+      80,    35,    36,    37,    35,     0,     1,     1,   119,     4,
+       5,     6,     7,     8,     9,    10,    11,    12,     1,    14,
+      15,    16,    17,    18,    19,    20,    21,    22,    23,    24,
+      35,    26,    77,    78,    35,    80,    35,     0,     1,    35,
+      35,     4,     5,     6,     7,     8,     9,    10,    11,    36,
+      37,    14,    15,    16,    17,    18,    19,    20,    21,    22,
+      23,    35,    35,    26,    35,    36,    37,    35,    35,     0,
+       1,    35,    35,     4,     5,     6,     7,     8,     9,    10,
+      11,    35,   193,    14,    15,    16,    17,    18,    19,    20,
+      21,    22,    23,    35,    26,    26,    25,     1,     1,    13,
+      35,    26,     5,     6,    35,     8,     9,    10,    11,    12,
+      37,    14,    15,    16,    17,    18,    19,    20,    14,    35,
+      35,     1,    35,    26,     4,     5,     6,     7,     8,     9,
+      10,    11,    35,    35,    14,    15,    16,     4,     5,     6,
+       7,     8,     9,    10,    11,    35,    26,    14,    15,    35,
+      38,    35,    35,     5,     6,    35,     8,     9,    10,    11,
+      35,     7,    14,    15,     6,    37,    76,   159,    35,   161,
+     162,   163,    28,    29,    30,    31,    32,   169,    79,   171,
+     120,    -1,    38,    35,    -1,    -1,    -1,    -1,   180
 };
 
 /* YYSTOS[STATE-NUM] -- The (internal number of the) accessing
    symbol of state STATE-NUM.  */
 static const yytype_uint8 yystos[] =
 {
-       0,     3,    31,    37,    38,    39,    63,    81,    26,    27,
-      79,     0,     1,     4,     5,     6,     7,     8,     9,    10,
+       0,     3,    35,    41,    42,    43,    67,    85,    26,    27,
+      83,     0,     1,     4,     5,     6,     7,     8,     9,    10,
       11,    14,    15,    16,    17,    18,    19,    20,    21,    22,
-      23,    26,    31,    40,    41,    43,    44,    45,    46,    52,
-      53,    55,    59,    61,    64,    65,    67,    69,    70,    71,
-      80,    39,    31,    38,    81,    31,    79,    31,    79,    26,
-      85,    31,    79,    26,    26,    26,    27,    30,    35,    83,
-      84,    31,     1,     1,    47,    47,    56,    58,    62,    76,
-      68,    74,    31,    31,    31,    31,    31,    31,    83,    83,
-      32,    33,    81,    28,    34,    31,    31,     1,    12,    16,
-      18,    19,    20,    21,    22,    24,    26,    31,    42,    48,
-      49,    72,    73,    75,    17,    18,    19,    20,    31,    42,
-      57,    73,    75,    41,    54,    80,    41,    55,    60,    67,
-      80,    23,    31,    74,    77,    41,    55,    66,    67,    80,
-      31,    42,    75,    29,    83,    83,    84,    84,    31,    31,
-      25,    79,    78,    79,    83,    26,    84,    50,     1,    13,
-      31,    79,    78,    26,    14,    82,    83,    82,    31,    82,
-      82,    82,    84,    26,    31,    31,    82,    31,    82,    83,
-      31,    31,    31,    31,    82,    34,    51,    31,    31,    31,
-      79
+      23,    26,    35,    44,    45,    47,    48,    49,    50,    56,
+      57,    59,    63,    65,    68,    69,    71,    73,    74,    75,
+      84,    43,    35,    42,    85,    35,    83,    35,    83,    26,
+      89,    35,    83,    26,    26,    26,    27,    34,    39,    87,
+      88,    35,     1,     1,    51,    51,    60,    62,    66,    80,
+      72,    78,    35,    35,    35,    35,    35,    35,    87,    87,
+      36,    37,    85,    28,    29,    30,    31,    32,    38,    35,
+      35,     1,    12,    16,    18,    19,    20,    21,    22,    24,
+      26,    35,    46,    52,    53,    76,    77,    79,    17,    18,
+      19,    20,    35,    46,    61,    77,    79,    45,    58,    84,
+      45,    59,    64,    71,    84,    23,    35,    78,    81,    45,
+      59,    70,    71,    84,    35,    46,    79,    33,    87,    87,
+      88,    88,    88,    88,    88,    88,    35,    35,    25,    83,
+      82,    83,    87,    26,    88,    54,     1,    13,    35,    83,
+      82,    26,    14,    86,    87,    86,    35,    86,    86,    86,
+      88,    26,    35,    35,    86,    35,    86,    87,    35,    35,
+      35,    35,    86,    38,    55,    35,    35,    35,    83
 };
 
 #define yyerrok		(yyerrstatus = 0)
@@ -823,17 +842,18 @@
 
 #define YYRECOVERING()  (!!yyerrstatus)
 
-#define YYBACKUP(Token, Value)					\
-do								\
-  if (yychar == YYEMPTY && yylen == 1)				\
-    {								\
-      yychar = (Token);						\
-      yylval = (Value);						\
-      YYPOPSTACK (1);						\
-      goto yybackup;						\
-    }								\
-  else								\
-    {								\
+#define YYBACKUP(Token, Value)                                  \
+do                                                              \
+  if (yychar == YYEMPTY)                                        \
+    {                                                           \
+      yychar = (Token);                                         \
+      yylval = (Value);                                         \
+      YYPOPSTACK (yylen);                                       \
+      yystate = *yyssp;                                         \
+      goto yybackup;                                            \
+    }                                                           \
+  else                                                          \
+    {                                                           \
       yyerror (YY_("syntax error: cannot back up")); \
       YYERROR;							\
     }								\
@@ -928,6 +948,8 @@
     YYSTYPE const * const yyvaluep;
 #endif
 {
+  FILE *yyo = yyoutput;
+  YYUSE (yyo);
   if (!yyvaluep)
     return;
 # ifdef YYPRINT
@@ -1179,12 +1201,12 @@
 yysyntax_error (YYSIZE_T *yymsg_alloc, char **yymsg,
                 yytype_int16 *yyssp, int yytoken)
 {
-  YYSIZE_T yysize0 = yytnamerr (0, yytname[yytoken]);
+  YYSIZE_T yysize0 = yytnamerr (YY_NULL, yytname[yytoken]);
   YYSIZE_T yysize = yysize0;
   YYSIZE_T yysize1;
   enum { YYERROR_VERBOSE_ARGS_MAXIMUM = 5 };
   /* Internationalized format string. */
-  const char *yyformat = 0;
+  const char *yyformat = YY_NULL;
   /* Arguments of yyformat. */
   char const *yyarg[YYERROR_VERBOSE_ARGS_MAXIMUM];
   /* Number of reported tokens (one for the "unexpected", one per
@@ -1244,7 +1266,7 @@
                     break;
                   }
                 yyarg[yycount++] = yytname[yyx];
-                yysize1 = yysize + yytnamerr (0, yytname[yyx]);
+                yysize1 = yysize + yytnamerr (YY_NULL, yytname[yyx]);
                 if (! (yysize <= yysize1
                        && yysize1 <= YYSTACK_ALLOC_MAXIMUM))
                   return 2;
@@ -1329,7 +1351,7 @@
 
   switch (yytype)
     {
-      case 53: /* "choice_entry" */
+      case 57: /* "choice_entry" */
 
 	{
 	fprintf(stderr, "%s:%d: missing end statement for this entry\n",
@@ -1339,7 +1361,7 @@
 };
 
 	break;
-      case 59: /* "if_entry" */
+      case 63: /* "if_entry" */
 
 	{
 	fprintf(stderr, "%s:%d: missing end statement for this entry\n",
@@ -1349,7 +1371,7 @@
 };
 
 	break;
-      case 65: /* "menu_entry" */
+      case 69: /* "menu_entry" */
 
 	{
 	fprintf(stderr, "%s:%d: missing end statement for this entry\n",
@@ -1426,7 +1448,7 @@
        `yyss': related to states.
        `yyvs': related to semantic values.
 
-       Refer to the stacks thru separate pointers, to allow yyoverflow
+       Refer to the stacks through separate pointers, to allow yyoverflow
        to reallocate them elsewhere.  */
 
     /* The state stack.  */
@@ -2012,46 +2034,66 @@
 
   case 109:
 
-    { (yyval.expr) = expr_alloc_comp(E_EQUAL, (yyvsp[(1) - (3)].symbol), (yyvsp[(3) - (3)].symbol)); }
+    { (yyval.expr) = expr_alloc_comp(E_LTH, (yyvsp[(1) - (3)].symbol), (yyvsp[(3) - (3)].symbol)); }
     break;
 
   case 110:
 
-    { (yyval.expr) = expr_alloc_comp(E_UNEQUAL, (yyvsp[(1) - (3)].symbol), (yyvsp[(3) - (3)].symbol)); }
+    { (yyval.expr) = expr_alloc_comp(E_LEQ, (yyvsp[(1) - (3)].symbol), (yyvsp[(3) - (3)].symbol)); }
     break;
 
   case 111:
 
-    { (yyval.expr) = (yyvsp[(2) - (3)].expr); }
+    { (yyval.expr) = expr_alloc_comp(E_GTH, (yyvsp[(1) - (3)].symbol), (yyvsp[(3) - (3)].symbol)); }
     break;
 
   case 112:
 
-    { (yyval.expr) = expr_alloc_one(E_NOT, (yyvsp[(2) - (2)].expr)); }
+    { (yyval.expr) = expr_alloc_comp(E_GEQ, (yyvsp[(1) - (3)].symbol), (yyvsp[(3) - (3)].symbol)); }
     break;
 
   case 113:
 
-    { (yyval.expr) = expr_alloc_two(E_OR, (yyvsp[(1) - (3)].expr), (yyvsp[(3) - (3)].expr)); }
+    { (yyval.expr) = expr_alloc_comp(E_EQUAL, (yyvsp[(1) - (3)].symbol), (yyvsp[(3) - (3)].symbol)); }
     break;
 
   case 114:
 
-    { (yyval.expr) = expr_alloc_two(E_AND, (yyvsp[(1) - (3)].expr), (yyvsp[(3) - (3)].expr)); }
+    { (yyval.expr) = expr_alloc_comp(E_UNEQUAL, (yyvsp[(1) - (3)].symbol), (yyvsp[(3) - (3)].symbol)); }
     break;
 
   case 115:
 
-    { (yyval.symbol) = sym_lookup((yyvsp[(1) - (1)].string), 0); free((yyvsp[(1) - (1)].string)); }
+    { (yyval.expr) = (yyvsp[(2) - (3)].expr); }
     break;
 
   case 116:
 
-    { (yyval.symbol) = sym_lookup((yyvsp[(1) - (1)].string), SYMBOL_CONST); free((yyvsp[(1) - (1)].string)); }
+    { (yyval.expr) = expr_alloc_one(E_NOT, (yyvsp[(2) - (2)].expr)); }
     break;
 
   case 117:
 
+    { (yyval.expr) = expr_alloc_two(E_OR, (yyvsp[(1) - (3)].expr), (yyvsp[(3) - (3)].expr)); }
+    break;
+
+  case 118:
+
+    { (yyval.expr) = expr_alloc_two(E_AND, (yyvsp[(1) - (3)].expr), (yyvsp[(3) - (3)].expr)); }
+    break;
+
+  case 119:
+
+    { (yyval.symbol) = sym_lookup((yyvsp[(1) - (1)].string), 0); free((yyvsp[(1) - (1)].string)); }
+    break;
+
+  case 120:
+
+    { (yyval.symbol) = sym_lookup((yyvsp[(1) - (1)].string), SYMBOL_CONST); free((yyvsp[(1) - (1)].string)); }
+    break;
+
+  case 121:
+
     { (yyval.string) = NULL; }
     break;
 
@@ -2243,7 +2285,7 @@
   yyresult = 1;
   goto yyreturn;
 
-#if !defined(yyoverflow) || YYERROR_VERBOSE
+#if !defined yyoverflow || YYERROR_VERBOSE
 /*-------------------------------------------------.
 | yyexhaustedlab -- memory exhaustion comes here.  |
 `-------------------------------------------------*/
diff --git a/scripts/kconfig/zconf.y b/scripts/kconfig/zconf.y
index 0f683cf..71bf8bf 100644
--- a/scripts/kconfig/zconf.y
+++ b/scripts/kconfig/zconf.y
@@ -69,6 +69,10 @@
 %token <string> T_WORD
 %token <string> T_WORD_QUOTE
 %token T_UNEQUAL
+%token T_LESS
+%token T_LESS_EQUAL
+%token T_GREATER
+%token T_GREATER_EQUAL
 %token T_CLOSE_PAREN
 %token T_OPEN_PAREN
 %token T_EOL
@@ -76,6 +80,7 @@
 %left T_OR
 %left T_AND
 %left T_EQUAL T_UNEQUAL
+%left T_LESS T_LESS_EQUAL T_GREATER T_GREATER_EQUAL
 %nonassoc T_NOT
 
 %type <string> prompt
@@ -467,6 +472,10 @@
 ;
 
 expr:	  symbol				{ $$ = expr_alloc_symbol($1); }
+	| symbol T_LESS symbol			{ $$ = expr_alloc_comp(E_LTH, $1, $3); }
+	| symbol T_LESS_EQUAL symbol		{ $$ = expr_alloc_comp(E_LEQ, $1, $3); }
+	| symbol T_GREATER symbol		{ $$ = expr_alloc_comp(E_GTH, $1, $3); }
+	| symbol T_GREATER_EQUAL symbol		{ $$ = expr_alloc_comp(E_GEQ, $1, $3); }
 	| symbol T_EQUAL symbol			{ $$ = expr_alloc_comp(E_EQUAL, $1, $3); }
 	| symbol T_UNEQUAL symbol		{ $$ = expr_alloc_comp(E_UNEQUAL, $1, $3); }
 	| T_OPEN_PAREN expr T_CLOSE_PAREN	{ $$ = $2; }
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 86a4fe7..1a10d8a 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -82,7 +82,7 @@
 		kallsymopt="${kallsymopt} --all-symbols"
 	fi
 
-	if [ -n "${CONFIG_ARM}" ] && [ -n "${CONFIG_PAGE_OFFSET}" ]; then
+	if [ -n "${CONFIG_ARM}" ] && [ -z "${CONFIG_XIP_KERNEL}" ] && [ -n "${CONFIG_PAGE_OFFSET}" ]; then
 		kallsymopt="${kallsymopt} --page-offset=$CONFIG_PAGE_OFFSET"
 	fi
 
@@ -111,7 +111,6 @@
 }
 
 # Delete output files in case of error
-trap cleanup SIGHUP SIGINT SIGQUIT SIGTERM ERR
 cleanup()
 {
 	rm -f .old_version
@@ -124,6 +123,20 @@
 	rm -f vmlinux.o
 }
 
+on_exit()
+{
+	if [ $? -ne 0 ]; then
+		cleanup
+	fi
+}
+trap on_exit EXIT
+
+on_signals()
+{
+	exit 1
+}
+trap on_signals HUP INT QUIT TERM
+
 #
 #
 # Use "make V=1" to debug this script
@@ -231,7 +244,6 @@
 	if ! cmp -s System.map .tmp_System.map; then
 		echo >&2 Inconsistent kallsyms data
 		echo >&2 Try "make KALLSYMS_EXTRA_PASS=1" as a workaround
-		cleanup
 		exit 1
 	fi
 fi
diff --git a/scripts/sortextable.c b/scripts/sortextable.c
index 1052d48..c2423d9 100644
--- a/scripts/sortextable.c
+++ b/scripts/sortextable.c
@@ -47,6 +47,10 @@
 #define EM_MICROBLAZE	189
 #endif
 
+#ifndef EM_ARCV2
+#define EM_ARCV2	195
+#endif
+
 static int fd_map;	/* File descriptor for file being modified. */
 static int mmap_failed; /* Boolean flag. */
 static void *ehdr_curr; /* current ElfXX_Ehdr *  for resource cleanup */
@@ -281,6 +285,7 @@
 		custom_sort = sort_relative_table;
 		break;
 	case EM_ARCOMPACT:
+	case EM_ARCV2:
 	case EM_ARM:
 	case EM_AARCH64:
 	case EM_MICROBLAZE:
diff --git a/scripts/tags.sh b/scripts/tags.sh
index cdb491d..c0a932d 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -154,7 +154,7 @@
 {
 	all_target_sources | xargs $1 -a                        \
 	-I __initdata,__exitdata,__initconst,			\
-	-I __cpuinitdata,__initdata_memblock			\
+	-I __initdata_memblock					\
 	-I __refdata,__attribute,__maybe_unused,__always_unused \
 	-I __acquires,__releases,__deprecated			\
 	-I __read_mostly,__aligned,____cacheline_aligned        \
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 5696874..dec607c 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -654,7 +654,7 @@
 static int param_set_aabool(const char *val, const struct kernel_param *kp);
 static int param_get_aabool(char *buffer, const struct kernel_param *kp);
 #define param_check_aabool param_check_bool
-static struct kernel_param_ops param_ops_aabool = {
+static const struct kernel_param_ops param_ops_aabool = {
 	.flags = KERNEL_PARAM_OPS_FL_NOARG,
 	.set = param_set_aabool,
 	.get = param_get_aabool
@@ -663,7 +663,7 @@
 static int param_set_aauint(const char *val, const struct kernel_param *kp);
 static int param_get_aauint(char *buffer, const struct kernel_param *kp);
 #define param_check_aauint param_check_uint
-static struct kernel_param_ops param_ops_aauint = {
+static const struct kernel_param_ops param_ops_aauint = {
 	.set = param_set_aauint,
 	.get = param_get_aauint
 };
@@ -671,7 +671,7 @@
 static int param_set_aalockpolicy(const char *val, const struct kernel_param *kp);
 static int param_get_aalockpolicy(char *buffer, const struct kernel_param *kp);
 #define param_check_aalockpolicy param_check_bool
-static struct kernel_param_ops param_ops_aalockpolicy = {
+static const struct kernel_param_ops param_ops_aalockpolicy = {
 	.flags = KERNEL_PARAM_OPS_FL_NOARG,
 	.set = param_set_aalockpolicy,
 	.get = param_get_aalockpolicy
diff --git a/security/inode.c b/security/inode.c
index 91503b7..16622ae 100644
--- a/security/inode.c
+++ b/security/inode.c
@@ -25,11 +25,6 @@
 static struct vfsmount *mount;
 static int mount_count;
 
-static inline int positive(struct dentry *dentry)
-{
-	return d_really_is_positive(dentry) && !d_unhashed(dentry);
-}
-
 static int fill_super(struct super_block *sb, void *data, int silent)
 {
 	static struct tree_descr files[] = {{""}};
@@ -201,33 +196,29 @@
 		return;
 
 	mutex_lock(&d_inode(parent)->i_mutex);
-	if (positive(dentry)) {
-		if (d_really_is_positive(dentry)) {
-			if (d_is_dir(dentry))
-				simple_rmdir(d_inode(parent), dentry);
-			else
-				simple_unlink(d_inode(parent), dentry);
-			dput(dentry);
-		}
+	if (simple_positive(dentry)) {
+		if (d_is_dir(dentry))
+			simple_rmdir(d_inode(parent), dentry);
+		else
+			simple_unlink(d_inode(parent), dentry);
+		dput(dentry);
 	}
 	mutex_unlock(&d_inode(parent)->i_mutex);
 	simple_release_fs(&mount, &mount_count);
 }
 EXPORT_SYMBOL_GPL(securityfs_remove);
 
-static struct kobject *security_kobj;
-
 static int __init securityfs_init(void)
 {
 	int retval;
 
-	security_kobj = kobject_create_and_add("security", kernel_kobj);
-	if (!security_kobj)
-		return -EINVAL;
+	retval = sysfs_create_mount_point(kernel_kobj, "security");
+	if (retval)
+		return retval;
 
 	retval = register_filesystem(&fs_type);
 	if (retval)
-		kobject_put(security_kobj);
+		sysfs_remove_mount_point(kernel_kobj, "security");
 	return retval;
 }
 
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index 686355f..e24121a 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -55,7 +55,7 @@
 	return 0;
 }
 
-static struct kernel_param_ops param_ops_bufsize = {
+static const struct kernel_param_ops param_ops_bufsize = {
 	.set = param_set_bufsize,
 	.get = param_get_uint,
 };
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index d2787cca..3d22014 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -1853,7 +1853,6 @@
 };
 
 struct vfsmount *selinuxfs_mount;
-static struct kobject *selinuxfs_kobj;
 
 static int __init init_sel_fs(void)
 {
@@ -1862,13 +1861,13 @@
 	if (!selinux_enabled)
 		return 0;
 
-	selinuxfs_kobj = kobject_create_and_add("selinux", fs_kobj);
-	if (!selinuxfs_kobj)
-		return -ENOMEM;
+	err = sysfs_create_mount_point(fs_kobj, "selinux");
+	if (err)
+		return err;
 
 	err = register_filesystem(&sel_fs_type);
 	if (err) {
-		kobject_put(selinuxfs_kobj);
+		sysfs_remove_mount_point(fs_kobj, "selinux");
 		return err;
 	}
 
@@ -1887,7 +1886,7 @@
 #ifdef CONFIG_SECURITY_SELINUX_DISABLE
 void exit_sel_fs(void)
 {
-	kobject_put(selinuxfs_kobj);
+	sysfs_remove_mount_point(fs_kobj, "selinux");
 	kern_unmount(selinuxfs_mount);
 	unregister_filesystem(&sel_fs_type);
 }
diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c
index 5e0a64e..2716d02 100644
--- a/security/smack/smackfs.c
+++ b/security/smack/smackfs.c
@@ -2314,16 +2314,16 @@
 	.llseek		= generic_file_llseek,
 };
 
-static struct kset *smackfs_kset;
 /**
  * smk_init_sysfs - initialize /sys/fs/smackfs
  *
  */
 static int smk_init_sysfs(void)
 {
-	smackfs_kset = kset_create_and_add("smackfs", NULL, fs_kobj);
-	if (!smackfs_kset)
-		return -ENOMEM;
+	int err;
+	err = sysfs_create_mount_point(fs_kobj, "smackfs");
+	if (err)
+		return err;
 	return 0;
 }
 
diff --git a/sound/core/ctljack.c b/sound/core/ctljack.c
index 9149a4a..84a3cd6 100644
--- a/sound/core/ctljack.c
+++ b/sound/core/ctljack.c
@@ -41,8 +41,11 @@
 	sid.iface = SNDRV_CTL_ELEM_IFACE_CARD;
 	strlcpy(sid.name, name, sizeof(sid.name));
 
-	while (snd_ctl_find_id(card, &sid))
+	while (snd_ctl_find_id(card, &sid)) {
 		sid.index++;
+		/* reset numid; otherwise snd_ctl_find_id() hits this again */
+		sid.numid = 0;
+	}
 
 	return sid.index;
 }
diff --git a/sound/core/init.c b/sound/core/init.c
index 3e0ceba..20f37fb 100644
--- a/sound/core/init.c
+++ b/sound/core/init.c
@@ -109,13 +109,12 @@
 
 static int init_info_for_card(struct snd_card *card)
 {
-	int err;
 	struct snd_info_entry *entry;
 
 	entry = snd_info_create_card_entry(card, "id", card->proc_root);
 	if (!entry) {
 		dev_dbg(card->dev, "unable to create card entry\n");
-		return err;
+		return -ENOMEM;
 	}
 	entry->c.text.read = snd_card_id_read;
 	card->proc_id = entry;
diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c
index 082509e..f05cb6a 100644
--- a/sound/core/memalloc.c
+++ b/sound/core/memalloc.c
@@ -124,7 +124,7 @@
 	dmab->addr = 0;
 
 	if (dev->of_node)
-		pool = of_get_named_gen_pool(dev->of_node, "iram", 0);
+		pool = of_gen_pool_get(dev->of_node, "iram", 0);
 
 	if (!pool)
 		return;
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 7dea798..745535d 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -171,7 +171,7 @@
 
 #ifdef CONFIG_PM
 static int param_set_xint(const char *val, const struct kernel_param *kp);
-static struct kernel_param_ops param_ops_xint = {
+static const struct kernel_param_ops param_ops_xint = {
 	.set = param_set_xint,
 	.get = param_get_int,
 };
@@ -2180,6 +2180,8 @@
 	{ PCI_DEVICE(0x1022, 0x780d),
 	  .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_ATI_SB },
 	/* ATI HDMI */
+	{ PCI_DEVICE(0x1002, 0x1308),
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	{ PCI_DEVICE(0x1002, 0x793b),
 	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
 	{ PCI_DEVICE(0x1002, 0x7919),
@@ -2188,6 +2190,8 @@
 	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
 	{ PCI_DEVICE(0x1002, 0x970f),
 	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
+	{ PCI_DEVICE(0x1002, 0x9840),
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	{ PCI_DEVICE(0x1002, 0xaa00),
 	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
 	{ PCI_DEVICE(0x1002, 0xaa08),
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index f852734..2f24338 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -591,7 +591,7 @@
 
 static void eld_proc_free(struct hdmi_spec_per_pin *per_pin)
 {
-	if (!per_pin->codec->bus->shutdown && per_pin->proc_entry) {
+	if (!per_pin->codec->bus->shutdown) {
 		snd_info_free_entry(per_pin->proc_entry);
 		per_pin->proc_entry = NULL;
 	}
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 431a20b..b3b4468 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4464,6 +4464,7 @@
 	ALC269_FIXUP_LIFEBOOK,
 	ALC269_FIXUP_LIFEBOOK_EXTMIC,
 	ALC269_FIXUP_LIFEBOOK_HP_PIN,
+	ALC269_FIXUP_LIFEBOOK_NO_HP_TO_LINEOUT,
 	ALC269_FIXUP_AMIC,
 	ALC269_FIXUP_DMIC,
 	ALC269VB_FIXUP_AMIC,
@@ -4484,6 +4485,7 @@
 	ALC269_FIXUP_DELL3_MIC_NO_PRESENCE,
 	ALC269_FIXUP_HEADSET_MODE,
 	ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC,
+	ALC269_FIXUP_ASPIRE_HEADSET_MIC,
 	ALC269_FIXUP_ASUS_X101_FUNC,
 	ALC269_FIXUP_ASUS_X101_VERB,
 	ALC269_FIXUP_ASUS_X101,
@@ -4511,6 +4513,7 @@
 	ALC255_FIXUP_HEADSET_MODE_NO_HP_MIC,
 	ALC293_FIXUP_DELL1_MIC_NO_PRESENCE,
 	ALC292_FIXUP_TPT440_DOCK,
+	ALC292_FIXUP_TPT440_DOCK2,
 	ALC283_FIXUP_BXBT2807_MIC,
 	ALC255_FIXUP_DELL_WMI_MIC_MUTE_LED,
 	ALC282_FIXUP_ASPIRE_V5_PINS,
@@ -4521,6 +4524,8 @@
 	ALC288_FIXUP_DELL_HEADSET_MODE,
 	ALC288_FIXUP_DELL1_MIC_NO_PRESENCE,
 	ALC288_FIXUP_DELL_XPS_13_GPIO6,
+	ALC288_FIXUP_DELL_XPS_13,
+	ALC288_FIXUP_DISABLE_AAMIX,
 	ALC292_FIXUP_DELL_E7X,
 	ALC292_FIXUP_DISABLE_AAMIX,
 	ALC298_FIXUP_DELL1_MIC_NO_PRESENCE,
@@ -4630,6 +4635,10 @@
 			{ }
 		},
 	},
+	[ALC269_FIXUP_LIFEBOOK_NO_HP_TO_LINEOUT] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc269_fixup_pincfg_no_hp_to_lineout,
+	},
 	[ALC269_FIXUP_AMIC] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -4758,6 +4767,15 @@
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_headset_mode_no_hp_mic,
 	},
+	[ALC269_FIXUP_ASPIRE_HEADSET_MIC] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x01a1913c }, /* headset mic w/o jack detect */
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HEADSET_MODE,
+	},
 	[ALC286_FIXUP_SONY_MIC_NO_PRESENCE] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -4960,6 +4978,12 @@
 		.chain_id = ALC269_FIXUP_HEADSET_MODE
 	},
 	[ALC292_FIXUP_TPT440_DOCK] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc269_fixup_pincfg_no_hp_to_lineout,
+		.chained = true,
+		.chain_id = ALC292_FIXUP_TPT440_DOCK2
+	},
+	[ALC292_FIXUP_TPT440_DOCK2] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
 			{ 0x16, 0x21211010 }, /* dock headphone */
@@ -5046,9 +5070,23 @@
 		.chained = true,
 		.chain_id = ALC288_FIXUP_DELL1_MIC_NO_PRESENCE
 	},
+	[ALC288_FIXUP_DISABLE_AAMIX] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_disable_aamix,
+		.chained = true,
+		.chain_id = ALC288_FIXUP_DELL_XPS_13_GPIO6
+	},
+	[ALC288_FIXUP_DELL_XPS_13] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_dell_xps13,
+		.chained = true,
+		.chain_id = ALC288_FIXUP_DISABLE_AAMIX
+	},
 	[ALC292_FIXUP_DISABLE_AAMIX] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_disable_aamix,
+		.chained = true,
+		.chain_id = ALC269_FIXUP_DELL2_MIC_NO_PRESENCE
 	},
 	[ALC292_FIXUP_DELL_E7X] = {
 		.type = HDA_FIXUP_FUNC,
@@ -5073,6 +5111,8 @@
 	SND_PCI_QUIRK(0x1025, 0x029b, "Acer 1810TZ", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x0349, "Acer AOD260", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x047c, "Acer AC700", ALC269_FIXUP_ACER_AC700),
+	SND_PCI_QUIRK(0x1025, 0x072d, "Acer Aspire V5-571G", ALC269_FIXUP_ASPIRE_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1025, 0x080d, "Acer Aspire V5-122P", ALC269_FIXUP_ASPIRE_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x0740, "Acer AO725", ALC271_FIXUP_HP_GATE_MIC_JACK),
 	SND_PCI_QUIRK(0x1025, 0x0742, "Acer AO756", ALC271_FIXUP_HP_GATE_MIC_JACK),
 	SND_PCI_QUIRK(0x1025, 0x0775, "Acer Aspire E1-572", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572),
@@ -5086,10 +5126,11 @@
 	SND_PCI_QUIRK(0x1028, 0x05f6, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0615, "Dell Vostro 5470", ALC290_FIXUP_SUBWOOFER_HSJACK),
 	SND_PCI_QUIRK(0x1028, 0x0616, "Dell Vostro 5470", ALC290_FIXUP_SUBWOOFER_HSJACK),
+	SND_PCI_QUIRK(0x1028, 0x062e, "Dell Latitude E7450", ALC292_FIXUP_DELL_E7X),
 	SND_PCI_QUIRK(0x1028, 0x0638, "Dell Inspiron 5439", ALC290_FIXUP_MONO_SPEAKERS_HSJACK),
 	SND_PCI_QUIRK(0x1028, 0x064a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x064b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x0665, "Dell XPS 13", ALC292_FIXUP_DELL_E7X),
+	SND_PCI_QUIRK(0x1028, 0x0665, "Dell XPS 13", ALC288_FIXUP_DELL_XPS_13),
 	SND_PCI_QUIRK(0x1028, 0x06c7, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x06d9, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x06da, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
@@ -5173,6 +5214,7 @@
 	SND_PCI_QUIRK(0x104d, 0x9084, "Sony VAIO", ALC275_FIXUP_SONY_HWEQ),
 	SND_PCI_QUIRK(0x104d, 0x9099, "Sony VAIO S13", ALC275_FIXUP_SONY_DISABLE_AAMIX),
 	SND_PCI_QUIRK(0x10cf, 0x1475, "Lifebook", ALC269_FIXUP_LIFEBOOK),
+	SND_PCI_QUIRK(0x10cf, 0x159f, "Lifebook E780", ALC269_FIXUP_LIFEBOOK_NO_HP_TO_LINEOUT),
 	SND_PCI_QUIRK(0x10cf, 0x15dc, "Lifebook T731", ALC269_FIXUP_LIFEBOOK_HP_PIN),
 	SND_PCI_QUIRK(0x10cf, 0x1757, "Lifebook E752", ALC269_FIXUP_LIFEBOOK_HP_PIN),
 	SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC),
diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c
index 0521be8..da53664 100644
--- a/sound/pci/hda/patch_via.c
+++ b/sound/pci/hda/patch_via.c
@@ -241,7 +241,9 @@
 				 struct snd_ctl_elem_value *ucontrol)
 {
 	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
-	ucontrol->value.enumerated.item[0] = codec->power_save_node;
+	struct via_spec *spec = codec->spec;
+
+	ucontrol->value.enumerated.item[0] = spec->gen.power_down_unused;
 	return 0;
 }
 
@@ -252,9 +254,9 @@
 	struct via_spec *spec = codec->spec;
 	bool val = !!ucontrol->value.enumerated.item[0];
 
-	if (val == codec->power_save_node)
+	if (val == spec->gen.power_down_unused)
 		return 0;
-	codec->power_save_node = val;
+	/* codec->power_save_node = val; */ /* widget PM seems yet broken */
 	spec->gen.power_down_unused = val;
 	analog_low_current_mode(codec);
 	return 1;
diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build
index a51244a..faca2bf 100644
--- a/tools/build/Makefile.build
+++ b/tools/build/Makefile.build
@@ -25,7 +25,7 @@
 include $(build-dir)/Build.include
 
 # do not force detected configuration
--include .config-detected
+-include $(OUTPUT).config-detected
 
 # Init all relevant variables used in build files so
 # 1) they have correct type
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index f0e7267..9098083 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -41,4 +41,62 @@
 
 #define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
 
+#include <linux/types.h>
+
+static __always_inline void __read_once_size(const volatile void *p, void *res, int size)
+{
+	switch (size) {
+	case 1: *(__u8 *)res = *(volatile __u8 *)p; break;
+	case 2: *(__u16 *)res = *(volatile __u16 *)p; break;
+	case 4: *(__u32 *)res = *(volatile __u32 *)p; break;
+	case 8: *(__u64 *)res = *(volatile __u64 *)p; break;
+	default:
+		barrier();
+		__builtin_memcpy((void *)res, (const void *)p, size);
+		barrier();
+	}
+}
+
+static __always_inline void __write_once_size(volatile void *p, void *res, int size)
+{
+	switch (size) {
+	case 1: *(volatile __u8 *)p = *(__u8 *)res; break;
+	case 2: *(volatile __u16 *)p = *(__u16 *)res; break;
+	case 4: *(volatile __u32 *)p = *(__u32 *)res; break;
+	case 8: *(volatile __u64 *)p = *(__u64 *)res; break;
+	default:
+		barrier();
+		__builtin_memcpy((void *)p, (const void *)res, size);
+		barrier();
+	}
+}
+
+/*
+ * Prevent the compiler from merging or refetching reads or writes. The
+ * compiler is also forbidden from reordering successive instances of
+ * READ_ONCE, WRITE_ONCE and ACCESS_ONCE (see below), but only when the
+ * compiler is aware of some particular ordering.  One way to make the
+ * compiler aware of ordering is to put the two invocations of READ_ONCE,
+ * WRITE_ONCE or ACCESS_ONCE() in different C statements.
+ *
+ * In contrast to ACCESS_ONCE these two macros will also work on aggregate
+ * data types like structs or unions. If the size of the accessed data
+ * type exceeds the word size of the machine (e.g., 32 bits or 64 bits)
+ * READ_ONCE() and WRITE_ONCE()  will fall back to memcpy and print a
+ * compile-time warning.
+ *
+ * Their two major use cases are: (1) Mediating communication between
+ * process-level code and irq/NMI handlers, all running on the same CPU,
+ * and (2) Ensuring that the compiler does not  fold, spindle, or otherwise
+ * mutilate accesses that either do not require ordering or that interact
+ * with an explicit memory barrier or atomic instruction that provides the
+ * required ordering.
+ */
+
+#define READ_ONCE(x) \
+	({ union { typeof(x) __val; char __c[1]; } __u; __read_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
+
+#define WRITE_ONCE(x, val) \
+	({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
+
 #endif /* _TOOLS_LINUX_COMPILER_H */
diff --git a/tools/include/linux/export.h b/tools/include/linux/export.h
deleted file mode 100644
index d07e586..0000000
--- a/tools/include/linux/export.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef _TOOLS_LINUX_EXPORT_H_
-#define _TOOLS_LINUX_EXPORT_H_
-
-#define EXPORT_SYMBOL(sym)
-#define EXPORT_SYMBOL_GPL(sym)
-#define EXPORT_SYMBOL_GPL_FUTURE(sym)
-#define EXPORT_UNUSED_SYMBOL(sym)
-#define EXPORT_UNUSED_SYMBOL_GPL(sym)
-
-#endif
diff --git a/tools/include/linux/rbtree.h b/tools/include/linux/rbtree.h
new file mode 100644
index 0000000..1125822
--- /dev/null
+++ b/tools/include/linux/rbtree.h
@@ -0,0 +1,104 @@
+/*
+  Red Black Trees
+  (C) 1999  Andrea Arcangeli <andrea@suse.de>
+
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of the GNU General Public License as published by
+  the Free Software Foundation; either version 2 of the License, or
+  (at your option) any later version.
+
+  This program is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+  GNU General Public License for more details.
+
+  You should have received a copy of the GNU General Public License
+  along with this program; if not, write to the Free Software
+  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+
+  linux/include/linux/rbtree.h
+
+  To use rbtrees you'll have to implement your own insert and search cores.
+  This will avoid us to use callbacks and to drop drammatically performances.
+  I know it's not the cleaner way,  but in C (not in C++) to get
+  performances and genericity...
+
+  See Documentation/rbtree.txt for documentation and samples.
+*/
+
+#ifndef __TOOLS_LINUX_PERF_RBTREE_H
+#define __TOOLS_LINUX_PERF_RBTREE_H
+
+#include <linux/kernel.h>
+#include <linux/stddef.h>
+
+struct rb_node {
+	unsigned long  __rb_parent_color;
+	struct rb_node *rb_right;
+	struct rb_node *rb_left;
+} __attribute__((aligned(sizeof(long))));
+    /* The alignment might seem pointless, but allegedly CRIS needs it */
+
+struct rb_root {
+	struct rb_node *rb_node;
+};
+
+
+#define rb_parent(r)   ((struct rb_node *)((r)->__rb_parent_color & ~3))
+
+#define RB_ROOT	(struct rb_root) { NULL, }
+#define	rb_entry(ptr, type, member) container_of(ptr, type, member)
+
+#define RB_EMPTY_ROOT(root)  ((root)->rb_node == NULL)
+
+/* 'empty' nodes are nodes that are known not to be inserted in an rbtree */
+#define RB_EMPTY_NODE(node)  \
+	((node)->__rb_parent_color == (unsigned long)(node))
+#define RB_CLEAR_NODE(node)  \
+	((node)->__rb_parent_color = (unsigned long)(node))
+
+
+extern void rb_insert_color(struct rb_node *, struct rb_root *);
+extern void rb_erase(struct rb_node *, struct rb_root *);
+
+
+/* Find logical next and previous nodes in a tree */
+extern struct rb_node *rb_next(const struct rb_node *);
+extern struct rb_node *rb_prev(const struct rb_node *);
+extern struct rb_node *rb_first(const struct rb_root *);
+extern struct rb_node *rb_last(const struct rb_root *);
+
+/* Postorder iteration - always visit the parent after its children */
+extern struct rb_node *rb_first_postorder(const struct rb_root *);
+extern struct rb_node *rb_next_postorder(const struct rb_node *);
+
+/* Fast replacement of a single node without remove/rebalance/add/rebalance */
+extern void rb_replace_node(struct rb_node *victim, struct rb_node *new,
+			    struct rb_root *root);
+
+static inline void rb_link_node(struct rb_node *node, struct rb_node *parent,
+				struct rb_node **rb_link)
+{
+	node->__rb_parent_color = (unsigned long)parent;
+	node->rb_left = node->rb_right = NULL;
+
+	*rb_link = node;
+}
+
+#define rb_entry_safe(ptr, type, member) \
+	({ typeof(ptr) ____ptr = (ptr); \
+	   ____ptr ? rb_entry(____ptr, type, member) : NULL; \
+	})
+
+
+/*
+ * Handy for checking that we are not deleting an entry that is
+ * already in a list, found in block/{blk-throttle,cfq-iosched}.c,
+ * probably should be moved to lib/rbtree.c...
+ */
+static inline void rb_erase_init(struct rb_node *n, struct rb_root *root)
+{
+	rb_erase(n, root);
+	RB_CLEAR_NODE(n);
+}
+#endif /* __TOOLS_LINUX_PERF_RBTREE_H */
diff --git a/tools/include/linux/rbtree_augmented.h b/tools/include/linux/rbtree_augmented.h
new file mode 100644
index 0000000..43be941
--- /dev/null
+++ b/tools/include/linux/rbtree_augmented.h
@@ -0,0 +1,245 @@
+/*
+  Red Black Trees
+  (C) 1999  Andrea Arcangeli <andrea@suse.de>
+  (C) 2002  David Woodhouse <dwmw2@infradead.org>
+  (C) 2012  Michel Lespinasse <walken@google.com>
+
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of the GNU General Public License as published by
+  the Free Software Foundation; either version 2 of the License, or
+  (at your option) any later version.
+
+  This program is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+  GNU General Public License for more details.
+
+  You should have received a copy of the GNU General Public License
+  along with this program; if not, write to the Free Software
+  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+
+  tools/linux/include/linux/rbtree_augmented.h
+
+  Copied from:
+  linux/include/linux/rbtree_augmented.h
+*/
+
+#ifndef _TOOLS_LINUX_RBTREE_AUGMENTED_H
+#define _TOOLS_LINUX_RBTREE_AUGMENTED_H
+
+#include <linux/compiler.h>
+#include <linux/rbtree.h>
+
+/*
+ * Please note - only struct rb_augment_callbacks and the prototypes for
+ * rb_insert_augmented() and rb_erase_augmented() are intended to be public.
+ * The rest are implementation details you are not expected to depend on.
+ *
+ * See Documentation/rbtree.txt for documentation and samples.
+ */
+
+struct rb_augment_callbacks {
+	void (*propagate)(struct rb_node *node, struct rb_node *stop);
+	void (*copy)(struct rb_node *old, struct rb_node *new);
+	void (*rotate)(struct rb_node *old, struct rb_node *new);
+};
+
+extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
+/*
+ * Fixup the rbtree and update the augmented information when rebalancing.
+ *
+ * On insertion, the user must update the augmented information on the path
+ * leading to the inserted node, then call rb_link_node() as usual and
+ * rb_augment_inserted() instead of the usual rb_insert_color() call.
+ * If rb_augment_inserted() rebalances the rbtree, it will callback into
+ * a user provided function to update the augmented information on the
+ * affected subtrees.
+ */
+static inline void
+rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+		    const struct rb_augment_callbacks *augment)
+{
+	__rb_insert_augmented(node, root, augment->rotate);
+}
+
+#define RB_DECLARE_CALLBACKS(rbstatic, rbname, rbstruct, rbfield,	\
+			     rbtype, rbaugmented, rbcompute)		\
+static inline void							\
+rbname ## _propagate(struct rb_node *rb, struct rb_node *stop)		\
+{									\
+	while (rb != stop) {						\
+		rbstruct *node = rb_entry(rb, rbstruct, rbfield);	\
+		rbtype augmented = rbcompute(node);			\
+		if (node->rbaugmented == augmented)			\
+			break;						\
+		node->rbaugmented = augmented;				\
+		rb = rb_parent(&node->rbfield);				\
+	}								\
+}									\
+static inline void							\
+rbname ## _copy(struct rb_node *rb_old, struct rb_node *rb_new)		\
+{									\
+	rbstruct *old = rb_entry(rb_old, rbstruct, rbfield);		\
+	rbstruct *new = rb_entry(rb_new, rbstruct, rbfield);		\
+	new->rbaugmented = old->rbaugmented;				\
+}									\
+static void								\
+rbname ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new)	\
+{									\
+	rbstruct *old = rb_entry(rb_old, rbstruct, rbfield);		\
+	rbstruct *new = rb_entry(rb_new, rbstruct, rbfield);		\
+	new->rbaugmented = old->rbaugmented;				\
+	old->rbaugmented = rbcompute(old);				\
+}									\
+rbstatic const struct rb_augment_callbacks rbname = {			\
+	rbname ## _propagate, rbname ## _copy, rbname ## _rotate	\
+};
+
+
+#define	RB_RED		0
+#define	RB_BLACK	1
+
+#define __rb_parent(pc)    ((struct rb_node *)(pc & ~3))
+
+#define __rb_color(pc)     ((pc) & 1)
+#define __rb_is_black(pc)  __rb_color(pc)
+#define __rb_is_red(pc)    (!__rb_color(pc))
+#define rb_color(rb)       __rb_color((rb)->__rb_parent_color)
+#define rb_is_red(rb)      __rb_is_red((rb)->__rb_parent_color)
+#define rb_is_black(rb)    __rb_is_black((rb)->__rb_parent_color)
+
+static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p)
+{
+	rb->__rb_parent_color = rb_color(rb) | (unsigned long)p;
+}
+
+static inline void rb_set_parent_color(struct rb_node *rb,
+				       struct rb_node *p, int color)
+{
+	rb->__rb_parent_color = (unsigned long)p | color;
+}
+
+static inline void
+__rb_change_child(struct rb_node *old, struct rb_node *new,
+		  struct rb_node *parent, struct rb_root *root)
+{
+	if (parent) {
+		if (parent->rb_left == old)
+			parent->rb_left = new;
+		else
+			parent->rb_right = new;
+	} else
+		root->rb_node = new;
+}
+
+extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
+
+static __always_inline struct rb_node *
+__rb_erase_augmented(struct rb_node *node, struct rb_root *root,
+		     const struct rb_augment_callbacks *augment)
+{
+	struct rb_node *child = node->rb_right, *tmp = node->rb_left;
+	struct rb_node *parent, *rebalance;
+	unsigned long pc;
+
+	if (!tmp) {
+		/*
+		 * Case 1: node to erase has no more than 1 child (easy!)
+		 *
+		 * Note that if there is one child it must be red due to 5)
+		 * and node must be black due to 4). We adjust colors locally
+		 * so as to bypass __rb_erase_color() later on.
+		 */
+		pc = node->__rb_parent_color;
+		parent = __rb_parent(pc);
+		__rb_change_child(node, child, parent, root);
+		if (child) {
+			child->__rb_parent_color = pc;
+			rebalance = NULL;
+		} else
+			rebalance = __rb_is_black(pc) ? parent : NULL;
+		tmp = parent;
+	} else if (!child) {
+		/* Still case 1, but this time the child is node->rb_left */
+		tmp->__rb_parent_color = pc = node->__rb_parent_color;
+		parent = __rb_parent(pc);
+		__rb_change_child(node, tmp, parent, root);
+		rebalance = NULL;
+		tmp = parent;
+	} else {
+		struct rb_node *successor = child, *child2;
+		tmp = child->rb_left;
+		if (!tmp) {
+			/*
+			 * Case 2: node's successor is its right child
+			 *
+			 *    (n)          (s)
+			 *    / \          / \
+			 *  (x) (s)  ->  (x) (c)
+			 *        \
+			 *        (c)
+			 */
+			parent = successor;
+			child2 = successor->rb_right;
+			augment->copy(node, successor);
+		} else {
+			/*
+			 * Case 3: node's successor is leftmost under
+			 * node's right child subtree
+			 *
+			 *    (n)          (s)
+			 *    / \          / \
+			 *  (x) (y)  ->  (x) (y)
+			 *      /            /
+			 *    (p)          (p)
+			 *    /            /
+			 *  (s)          (c)
+			 *    \
+			 *    (c)
+			 */
+			do {
+				parent = successor;
+				successor = tmp;
+				tmp = tmp->rb_left;
+			} while (tmp);
+			parent->rb_left = child2 = successor->rb_right;
+			successor->rb_right = child;
+			rb_set_parent(child, successor);
+			augment->copy(node, successor);
+			augment->propagate(parent, successor);
+		}
+
+		successor->rb_left = tmp = node->rb_left;
+		rb_set_parent(tmp, successor);
+
+		pc = node->__rb_parent_color;
+		tmp = __rb_parent(pc);
+		__rb_change_child(node, successor, tmp, root);
+		if (child2) {
+			successor->__rb_parent_color = pc;
+			rb_set_parent_color(child2, parent, RB_BLACK);
+			rebalance = NULL;
+		} else {
+			unsigned long pc2 = successor->__rb_parent_color;
+			successor->__rb_parent_color = pc;
+			rebalance = __rb_is_black(pc2) ? parent : NULL;
+		}
+		tmp = successor;
+	}
+
+	augment->propagate(tmp, NULL);
+	return rebalance;
+}
+
+static __always_inline void
+rb_erase_augmented(struct rb_node *node, struct rb_root *root,
+		   const struct rb_augment_callbacks *augment)
+{
+	struct rb_node *rebalance = __rb_erase_augmented(node, root, augment);
+	if (rebalance)
+		__rb_erase_color(rebalance, root, augment->rotate);
+}
+
+#endif	/* _TOOLS_LINUX_RBTREE_AUGMENTED_H */
diff --git a/tools/lib/rbtree.c b/tools/lib/rbtree.c
new file mode 100644
index 0000000..17c2b59
--- /dev/null
+++ b/tools/lib/rbtree.c
@@ -0,0 +1,548 @@
+/*
+  Red Black Trees
+  (C) 1999  Andrea Arcangeli <andrea@suse.de>
+  (C) 2002  David Woodhouse <dwmw2@infradead.org>
+  (C) 2012  Michel Lespinasse <walken@google.com>
+
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of the GNU General Public License as published by
+  the Free Software Foundation; either version 2 of the License, or
+  (at your option) any later version.
+
+  This program is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+  GNU General Public License for more details.
+
+  You should have received a copy of the GNU General Public License
+  along with this program; if not, write to the Free Software
+  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+
+  linux/lib/rbtree.c
+*/
+
+#include <linux/rbtree_augmented.h>
+
+/*
+ * red-black trees properties:  http://en.wikipedia.org/wiki/Rbtree
+ *
+ *  1) A node is either red or black
+ *  2) The root is black
+ *  3) All leaves (NULL) are black
+ *  4) Both children of every red node are black
+ *  5) Every simple path from root to leaves contains the same number
+ *     of black nodes.
+ *
+ *  4 and 5 give the O(log n) guarantee, since 4 implies you cannot have two
+ *  consecutive red nodes in a path and every red node is therefore followed by
+ *  a black. So if B is the number of black nodes on every simple path (as per
+ *  5), then the longest possible path due to 4 is 2B.
+ *
+ *  We shall indicate color with case, where black nodes are uppercase and red
+ *  nodes will be lowercase. Unknown color nodes shall be drawn as red within
+ *  parentheses and have some accompanying text comment.
+ */
+
+static inline void rb_set_black(struct rb_node *rb)
+{
+	rb->__rb_parent_color |= RB_BLACK;
+}
+
+static inline struct rb_node *rb_red_parent(struct rb_node *red)
+{
+	return (struct rb_node *)red->__rb_parent_color;
+}
+
+/*
+ * Helper function for rotations:
+ * - old's parent and color get assigned to new
+ * - old gets assigned new as a parent and 'color' as a color.
+ */
+static inline void
+__rb_rotate_set_parents(struct rb_node *old, struct rb_node *new,
+			struct rb_root *root, int color)
+{
+	struct rb_node *parent = rb_parent(old);
+	new->__rb_parent_color = old->__rb_parent_color;
+	rb_set_parent_color(old, new, color);
+	__rb_change_child(old, new, parent, root);
+}
+
+static __always_inline void
+__rb_insert(struct rb_node *node, struct rb_root *root,
+	    void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+	struct rb_node *parent = rb_red_parent(node), *gparent, *tmp;
+
+	while (true) {
+		/*
+		 * Loop invariant: node is red
+		 *
+		 * If there is a black parent, we are done.
+		 * Otherwise, take some corrective action as we don't
+		 * want a red root or two consecutive red nodes.
+		 */
+		if (!parent) {
+			rb_set_parent_color(node, NULL, RB_BLACK);
+			break;
+		} else if (rb_is_black(parent))
+			break;
+
+		gparent = rb_red_parent(parent);
+
+		tmp = gparent->rb_right;
+		if (parent != tmp) {	/* parent == gparent->rb_left */
+			if (tmp && rb_is_red(tmp)) {
+				/*
+				 * Case 1 - color flips
+				 *
+				 *       G            g
+				 *      / \          / \
+				 *     p   u  -->   P   U
+				 *    /            /
+				 *   n            n
+				 *
+				 * However, since g's parent might be red, and
+				 * 4) does not allow this, we need to recurse
+				 * at g.
+				 */
+				rb_set_parent_color(tmp, gparent, RB_BLACK);
+				rb_set_parent_color(parent, gparent, RB_BLACK);
+				node = gparent;
+				parent = rb_parent(node);
+				rb_set_parent_color(node, parent, RB_RED);
+				continue;
+			}
+
+			tmp = parent->rb_right;
+			if (node == tmp) {
+				/*
+				 * Case 2 - left rotate at parent
+				 *
+				 *      G             G
+				 *     / \           / \
+				 *    p   U  -->    n   U
+				 *     \           /
+				 *      n         p
+				 *
+				 * This still leaves us in violation of 4), the
+				 * continuation into Case 3 will fix that.
+				 */
+				parent->rb_right = tmp = node->rb_left;
+				node->rb_left = parent;
+				if (tmp)
+					rb_set_parent_color(tmp, parent,
+							    RB_BLACK);
+				rb_set_parent_color(parent, node, RB_RED);
+				augment_rotate(parent, node);
+				parent = node;
+				tmp = node->rb_right;
+			}
+
+			/*
+			 * Case 3 - right rotate at gparent
+			 *
+			 *        G           P
+			 *       / \         / \
+			 *      p   U  -->  n   g
+			 *     /                 \
+			 *    n                   U
+			 */
+			gparent->rb_left = tmp;  /* == parent->rb_right */
+			parent->rb_right = gparent;
+			if (tmp)
+				rb_set_parent_color(tmp, gparent, RB_BLACK);
+			__rb_rotate_set_parents(gparent, parent, root, RB_RED);
+			augment_rotate(gparent, parent);
+			break;
+		} else {
+			tmp = gparent->rb_left;
+			if (tmp && rb_is_red(tmp)) {
+				/* Case 1 - color flips */
+				rb_set_parent_color(tmp, gparent, RB_BLACK);
+				rb_set_parent_color(parent, gparent, RB_BLACK);
+				node = gparent;
+				parent = rb_parent(node);
+				rb_set_parent_color(node, parent, RB_RED);
+				continue;
+			}
+
+			tmp = parent->rb_left;
+			if (node == tmp) {
+				/* Case 2 - right rotate at parent */
+				parent->rb_left = tmp = node->rb_right;
+				node->rb_right = parent;
+				if (tmp)
+					rb_set_parent_color(tmp, parent,
+							    RB_BLACK);
+				rb_set_parent_color(parent, node, RB_RED);
+				augment_rotate(parent, node);
+				parent = node;
+				tmp = node->rb_left;
+			}
+
+			/* Case 3 - left rotate at gparent */
+			gparent->rb_right = tmp;  /* == parent->rb_left */
+			parent->rb_left = gparent;
+			if (tmp)
+				rb_set_parent_color(tmp, gparent, RB_BLACK);
+			__rb_rotate_set_parents(gparent, parent, root, RB_RED);
+			augment_rotate(gparent, parent);
+			break;
+		}
+	}
+}
+
+/*
+ * Inline version for rb_erase() use - we want to be able to inline
+ * and eliminate the dummy_rotate callback there
+ */
+static __always_inline void
+____rb_erase_color(struct rb_node *parent, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+	struct rb_node *node = NULL, *sibling, *tmp1, *tmp2;
+
+	while (true) {
+		/*
+		 * Loop invariants:
+		 * - node is black (or NULL on first iteration)
+		 * - node is not the root (parent is not NULL)
+		 * - All leaf paths going through parent and node have a
+		 *   black node count that is 1 lower than other leaf paths.
+		 */
+		sibling = parent->rb_right;
+		if (node != sibling) {	/* node == parent->rb_left */
+			if (rb_is_red(sibling)) {
+				/*
+				 * Case 1 - left rotate at parent
+				 *
+				 *     P               S
+				 *    / \             / \
+				 *   N   s    -->    p   Sr
+				 *      / \         / \
+				 *     Sl  Sr      N   Sl
+				 */
+				parent->rb_right = tmp1 = sibling->rb_left;
+				sibling->rb_left = parent;
+				rb_set_parent_color(tmp1, parent, RB_BLACK);
+				__rb_rotate_set_parents(parent, sibling, root,
+							RB_RED);
+				augment_rotate(parent, sibling);
+				sibling = tmp1;
+			}
+			tmp1 = sibling->rb_right;
+			if (!tmp1 || rb_is_black(tmp1)) {
+				tmp2 = sibling->rb_left;
+				if (!tmp2 || rb_is_black(tmp2)) {
+					/*
+					 * Case 2 - sibling color flip
+					 * (p could be either color here)
+					 *
+					 *    (p)           (p)
+					 *    / \           / \
+					 *   N   S    -->  N   s
+					 *      / \           / \
+					 *     Sl  Sr        Sl  Sr
+					 *
+					 * This leaves us violating 5) which
+					 * can be fixed by flipping p to black
+					 * if it was red, or by recursing at p.
+					 * p is red when coming from Case 1.
+					 */
+					rb_set_parent_color(sibling, parent,
+							    RB_RED);
+					if (rb_is_red(parent))
+						rb_set_black(parent);
+					else {
+						node = parent;
+						parent = rb_parent(node);
+						if (parent)
+							continue;
+					}
+					break;
+				}
+				/*
+				 * Case 3 - right rotate at sibling
+				 * (p could be either color here)
+				 *
+				 *   (p)           (p)
+				 *   / \           / \
+				 *  N   S    -->  N   Sl
+				 *     / \             \
+				 *    sl  Sr            s
+				 *                       \
+				 *                        Sr
+				 */
+				sibling->rb_left = tmp1 = tmp2->rb_right;
+				tmp2->rb_right = sibling;
+				parent->rb_right = tmp2;
+				if (tmp1)
+					rb_set_parent_color(tmp1, sibling,
+							    RB_BLACK);
+				augment_rotate(sibling, tmp2);
+				tmp1 = sibling;
+				sibling = tmp2;
+			}
+			/*
+			 * Case 4 - left rotate at parent + color flips
+			 * (p and sl could be either color here.
+			 *  After rotation, p becomes black, s acquires
+			 *  p's color, and sl keeps its color)
+			 *
+			 *      (p)             (s)
+			 *      / \             / \
+			 *     N   S     -->   P   Sr
+			 *        / \         / \
+			 *      (sl) sr      N  (sl)
+			 */
+			parent->rb_right = tmp2 = sibling->rb_left;
+			sibling->rb_left = parent;
+			rb_set_parent_color(tmp1, sibling, RB_BLACK);
+			if (tmp2)
+				rb_set_parent(tmp2, parent);
+			__rb_rotate_set_parents(parent, sibling, root,
+						RB_BLACK);
+			augment_rotate(parent, sibling);
+			break;
+		} else {
+			sibling = parent->rb_left;
+			if (rb_is_red(sibling)) {
+				/* Case 1 - right rotate at parent */
+				parent->rb_left = tmp1 = sibling->rb_right;
+				sibling->rb_right = parent;
+				rb_set_parent_color(tmp1, parent, RB_BLACK);
+				__rb_rotate_set_parents(parent, sibling, root,
+							RB_RED);
+				augment_rotate(parent, sibling);
+				sibling = tmp1;
+			}
+			tmp1 = sibling->rb_left;
+			if (!tmp1 || rb_is_black(tmp1)) {
+				tmp2 = sibling->rb_right;
+				if (!tmp2 || rb_is_black(tmp2)) {
+					/* Case 2 - sibling color flip */
+					rb_set_parent_color(sibling, parent,
+							    RB_RED);
+					if (rb_is_red(parent))
+						rb_set_black(parent);
+					else {
+						node = parent;
+						parent = rb_parent(node);
+						if (parent)
+							continue;
+					}
+					break;
+				}
+				/* Case 3 - right rotate at sibling */
+				sibling->rb_right = tmp1 = tmp2->rb_left;
+				tmp2->rb_left = sibling;
+				parent->rb_left = tmp2;
+				if (tmp1)
+					rb_set_parent_color(tmp1, sibling,
+							    RB_BLACK);
+				augment_rotate(sibling, tmp2);
+				tmp1 = sibling;
+				sibling = tmp2;
+			}
+			/* Case 4 - left rotate at parent + color flips */
+			parent->rb_left = tmp2 = sibling->rb_right;
+			sibling->rb_right = parent;
+			rb_set_parent_color(tmp1, sibling, RB_BLACK);
+			if (tmp2)
+				rb_set_parent(tmp2, parent);
+			__rb_rotate_set_parents(parent, sibling, root,
+						RB_BLACK);
+			augment_rotate(parent, sibling);
+			break;
+		}
+	}
+}
+
+/* Non-inline version for rb_erase_augmented() use */
+void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+	____rb_erase_color(parent, root, augment_rotate);
+}
+
+/*
+ * Non-augmented rbtree manipulation functions.
+ *
+ * We use dummy augmented callbacks here, and have the compiler optimize them
+ * out of the rb_insert_color() and rb_erase() function definitions.
+ */
+
+static inline void dummy_propagate(struct rb_node *node, struct rb_node *stop) {}
+static inline void dummy_copy(struct rb_node *old, struct rb_node *new) {}
+static inline void dummy_rotate(struct rb_node *old, struct rb_node *new) {}
+
+static const struct rb_augment_callbacks dummy_callbacks = {
+	dummy_propagate, dummy_copy, dummy_rotate
+};
+
+void rb_insert_color(struct rb_node *node, struct rb_root *root)
+{
+	__rb_insert(node, root, dummy_rotate);
+}
+
+void rb_erase(struct rb_node *node, struct rb_root *root)
+{
+	struct rb_node *rebalance;
+	rebalance = __rb_erase_augmented(node, root, &dummy_callbacks);
+	if (rebalance)
+		____rb_erase_color(rebalance, root, dummy_rotate);
+}
+
+/*
+ * Augmented rbtree manipulation functions.
+ *
+ * This instantiates the same __always_inline functions as in the non-augmented
+ * case, but this time with user-defined callbacks.
+ */
+
+void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+	__rb_insert(node, root, augment_rotate);
+}
+
+/*
+ * This function returns the first node (in sort order) of the tree.
+ */
+struct rb_node *rb_first(const struct rb_root *root)
+{
+	struct rb_node	*n;
+
+	n = root->rb_node;
+	if (!n)
+		return NULL;
+	while (n->rb_left)
+		n = n->rb_left;
+	return n;
+}
+
+struct rb_node *rb_last(const struct rb_root *root)
+{
+	struct rb_node	*n;
+
+	n = root->rb_node;
+	if (!n)
+		return NULL;
+	while (n->rb_right)
+		n = n->rb_right;
+	return n;
+}
+
+struct rb_node *rb_next(const struct rb_node *node)
+{
+	struct rb_node *parent;
+
+	if (RB_EMPTY_NODE(node))
+		return NULL;
+
+	/*
+	 * If we have a right-hand child, go down and then left as far
+	 * as we can.
+	 */
+	if (node->rb_right) {
+		node = node->rb_right;
+		while (node->rb_left)
+			node=node->rb_left;
+		return (struct rb_node *)node;
+	}
+
+	/*
+	 * No right-hand children. Everything down and left is smaller than us,
+	 * so any 'next' node must be in the general direction of our parent.
+	 * Go up the tree; any time the ancestor is a right-hand child of its
+	 * parent, keep going up. First time it's a left-hand child of its
+	 * parent, said parent is our 'next' node.
+	 */
+	while ((parent = rb_parent(node)) && node == parent->rb_right)
+		node = parent;
+
+	return parent;
+}
+
+struct rb_node *rb_prev(const struct rb_node *node)
+{
+	struct rb_node *parent;
+
+	if (RB_EMPTY_NODE(node))
+		return NULL;
+
+	/*
+	 * If we have a left-hand child, go down and then right as far
+	 * as we can.
+	 */
+	if (node->rb_left) {
+		node = node->rb_left;
+		while (node->rb_right)
+			node=node->rb_right;
+		return (struct rb_node *)node;
+	}
+
+	/*
+	 * No left-hand children. Go up till we find an ancestor which
+	 * is a right-hand child of its parent.
+	 */
+	while ((parent = rb_parent(node)) && node == parent->rb_left)
+		node = parent;
+
+	return parent;
+}
+
+void rb_replace_node(struct rb_node *victim, struct rb_node *new,
+		     struct rb_root *root)
+{
+	struct rb_node *parent = rb_parent(victim);
+
+	/* Set the surrounding nodes to point to the replacement */
+	__rb_change_child(victim, new, parent, root);
+	if (victim->rb_left)
+		rb_set_parent(victim->rb_left, new);
+	if (victim->rb_right)
+		rb_set_parent(victim->rb_right, new);
+
+	/* Copy the pointers/colour from the victim to the replacement */
+	*new = *victim;
+}
+
+static struct rb_node *rb_left_deepest_node(const struct rb_node *node)
+{
+	for (;;) {
+		if (node->rb_left)
+			node = node->rb_left;
+		else if (node->rb_right)
+			node = node->rb_right;
+		else
+			return (struct rb_node *)node;
+	}
+}
+
+struct rb_node *rb_next_postorder(const struct rb_node *node)
+{
+	const struct rb_node *parent;
+	if (!node)
+		return NULL;
+	parent = rb_parent(node);
+
+	/* If we're sitting on node, we've already seen our children */
+	if (parent && node == parent->rb_left && parent->rb_right) {
+		/* If we are the parent's left node, go to the parent's right
+		 * node then all the way down to the left */
+		return rb_left_deepest_node(parent->rb_right);
+	} else
+		/* Otherwise we are the parent's right node, and the parent
+		 * should be next */
+		return (struct rb_node *)parent;
+}
+
+struct rb_node *rb_first_postorder(const struct rb_root *root)
+{
+	if (!root->rb_node)
+		return NULL;
+
+	return rb_left_deepest_node(root->rb_node);
+}
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 04e150d..47469ab 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -144,6 +144,10 @@
 use --per-core in addition to -a. (system-wide).  The output includes the
 core number and the number of online logical processors on that physical processor.
 
+--per-thread::
+Aggregate counts per monitored threads, when monitoring threads (-t option)
+or processes (-p option).
+
 -D msecs::
 --delay msecs::
 After starting the program, wait msecs before measuring. This is useful to
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index fe50a1b..09dc0aa 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -18,6 +18,7 @@
 tools/arch/x86/include/asm/rmwcc.h
 tools/lib/traceevent
 tools/lib/api
+tools/lib/rbtree.c
 tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
 tools/lib/util/find_next_bit.c
@@ -44,6 +45,8 @@
 tools/include/linux/list.h
 tools/include/linux/log2.h
 tools/include/linux/poison.h
+tools/include/linux/rbtree.h
+tools/include/linux/rbtree_augmented.h
 tools/include/linux/types.h
 include/asm-generic/bitops/arch_hweight.h
 include/asm-generic/bitops/const_hweight.h
@@ -51,12 +54,10 @@
 include/asm-generic/bitops/__fls.h
 include/asm-generic/bitops/fls.h
 include/linux/perf_event.h
-include/linux/rbtree.h
 include/linux/list.h
 include/linux/hash.h
 include/linux/stringify.h
 lib/hweight.c
-lib/rbtree.c
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
 arch/*/include/uapi/asm/unistd*.h
@@ -65,7 +66,6 @@
 arch/*/lib/memset*.S
 include/linux/poison.h
 include/linux/hw_breakpoint.h
-include/linux/rbtree_augmented.h
 include/uapi/linux/perf_event.h
 include/uapi/linux/const.h
 include/uapi/linux/swab.h
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index d31a7bb..480546d 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -83,8 +83,8 @@
 #
 # All other targets get passed through:
 #
-%:
+%: FORCE
 	$(print_msg)
 	$(make)
 
-.PHONY: tags TAGS
+.PHONY: tags TAGS FORCE Makefile
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 1af0cfe..7a4b549 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -110,7 +110,7 @@
 	$(Q)touch $(OUTPUT)PERF-VERSION-FILE
 
 CC = $(CROSS_COMPILE)gcc
-LD = $(CROSS_COMPILE)ld
+LD ?= $(CROSS_COMPILE)ld
 AR = $(CROSS_COMPILE)ar
 PKG_CONFIG = $(CROSS_COMPILE)pkg-config
 
@@ -545,7 +545,7 @@
 clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean config-clean
 	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS)
 	$(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
-	$(Q)$(RM) .config-detected
+	$(Q)$(RM) $(OUTPUT).config-detected
 	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32
 	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 52ec66b..01b0649 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -630,12 +630,13 @@
 	if (inject.session == NULL)
 		return -1;
 
-	if (symbol__init(&inject.session->header.env) < 0)
-		return -1;
+	ret = symbol__init(&inject.session->header.env);
+	if (ret < 0)
+		goto out_delete;
 
 	ret = __cmd_inject(&inject);
 
+out_delete:
 	perf_session__delete(inject.session);
-
 	return ret;
 }
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 950f296..23b1faa 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1916,7 +1916,7 @@
 		if (!perf_evlist__find_tracepoint_by_name(session->evlist,
 							  "kmem:kmalloc")) {
 			pr_err(errmsg, "slab", "slab");
-			return -1;
+			goto out_delete;
 		}
 	}
 
@@ -1927,7 +1927,7 @@
 							     "kmem:mm_page_alloc");
 		if (evsel == NULL) {
 			pr_err(errmsg, "page", "page");
-			return -1;
+			goto out_delete;
 		}
 
 		kmem_page_size = pevent_get_page_size(evsel->tp_format->pevent);
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 74878cd..fc1cffb 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1061,8 +1061,10 @@
 
 	symbol__init(&kvm->session->header.env);
 
-	if (!perf_session__has_traces(kvm->session, "kvm record"))
-		return -EINVAL;
+	if (!perf_session__has_traces(kvm->session, "kvm record")) {
+		ret = -EINVAL;
+		goto out_delete;
+	}
 
 	/*
 	 * Do not use 'isa' recorded in kvm_exit tracepoint since it is not
@@ -1070,9 +1072,13 @@
 	 */
 	ret = cpu_isa_config(kvm);
 	if (ret < 0)
-		return ret;
+		goto out_delete;
 
-	return perf_session__process_events(kvm->session);
+	ret = perf_session__process_events(kvm->session);
+
+out_delete:
+	perf_session__delete(kvm->session);
+	return ret;
 }
 
 static int parse_target_str(struct perf_kvm_stat *kvm)
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index da2ec06..80170aa 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -124,7 +124,6 @@
 		.mode = PERF_DATA_MODE_READ,
 		.force = mem->force,
 	};
-	int err = -EINVAL;
 	int ret;
 	struct perf_session *session = perf_session__new(&file, false,
 							 &mem->tool);
@@ -135,24 +134,21 @@
 	if (mem->cpu_list) {
 		ret = perf_session__cpu_bitmap(session, mem->cpu_list,
 					       mem->cpu_bitmap);
-		if (ret)
+		if (ret < 0)
 			goto out_delete;
 	}
 
-	if (symbol__init(&session->header.env) < 0)
-		return -1;
+	ret = symbol__init(&session->header.env);
+	if (ret < 0)
+		goto out_delete;
 
 	printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
 
-	err = perf_session__process_events(session);
-	if (err)
-		return err;
-
-	return 0;
+	ret = perf_session__process_events(session);
 
 out_delete:
 	perf_session__delete(session);
-	return err;
+	return ret;
 }
 
 static int report_events(int argc, const char **argv, struct perf_mem *mem)
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 32626ea..95a4771 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -742,6 +742,17 @@
 
 	argc = parse_options(argc, argv, options, report_usage, 0);
 
+	if (symbol_conf.vmlinux_name &&
+	    access(symbol_conf.vmlinux_name, R_OK)) {
+		pr_err("Invalid file: %s\n", symbol_conf.vmlinux_name);
+		return -EINVAL;
+	}
+	if (symbol_conf.kallsyms_name &&
+	    access(symbol_conf.kallsyms_name, R_OK)) {
+		pr_err("Invalid file: %s\n", symbol_conf.kallsyms_name);
+		return -EINVAL;
+	}
+
 	if (report.use_stdio)
 		use_browser = 0;
 	else if (report.use_tui)
@@ -828,8 +839,10 @@
 	if (report.header || report.header_only) {
 		perf_session__fprintf_info(session, stdout,
 					   report.show_full_info);
-		if (report.header_only)
-			return 0;
+		if (report.header_only) {
+			ret = 0;
+			goto error;
+		}
 	} else if (use_browser == 0) {
 		fputs("# To display the perf.data header info, please use --header/--header-only options.\n#\n",
 		      stdout);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index fcf99bd..37e301a 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -67,10 +67,7 @@
 #define CNTR_NOT_SUPPORTED	"<not supported>"
 #define CNTR_NOT_COUNTED	"<not counted>"
 
-static void print_stat(int argc, const char **argv);
-static void print_counter_aggr(struct perf_evsel *counter, char *prefix);
-static void print_counter(struct perf_evsel *counter, char *prefix);
-static void print_aggr(char *prefix);
+static void print_counters(struct timespec *ts, int argc, const char **argv);
 
 /* Default events used for perf stat -T */
 static const char *transaction_attrs = {
@@ -141,96 +138,9 @@
 	}
 }
 
-static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
+static void perf_stat__reset_stats(void)
 {
-	return (evsel->cpus && !target.cpu_list) ? evsel->cpus : evsel_list->cpus;
-}
-
-static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
-{
-	return perf_evsel__cpus(evsel)->nr;
-}
-
-static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
-{
-	int i;
-	struct perf_stat *ps = evsel->priv;
-
-	for (i = 0; i < 3; i++)
-		init_stats(&ps->res_stats[i]);
-
-	perf_stat_evsel_id_init(evsel);
-}
-
-static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
-{
-	evsel->priv = zalloc(sizeof(struct perf_stat));
-	if (evsel->priv == NULL)
-		return -ENOMEM;
-	perf_evsel__reset_stat_priv(evsel);
-	return 0;
-}
-
-static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
-{
-	zfree(&evsel->priv);
-}
-
-static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel)
-{
-	struct perf_counts *counts;
-
-	counts = perf_counts__new(perf_evsel__nr_cpus(evsel));
-	if (counts)
-		evsel->prev_raw_counts = counts;
-
-	return counts ? 0 : -ENOMEM;
-}
-
-static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
-{
-	perf_counts__delete(evsel->prev_raw_counts);
-	evsel->prev_raw_counts = NULL;
-}
-
-static void perf_evlist__free_stats(struct perf_evlist *evlist)
-{
-	struct perf_evsel *evsel;
-
-	evlist__for_each(evlist, evsel) {
-		perf_evsel__free_stat_priv(evsel);
-		perf_evsel__free_counts(evsel);
-		perf_evsel__free_prev_raw_counts(evsel);
-	}
-}
-
-static int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw)
-{
-	struct perf_evsel *evsel;
-
-	evlist__for_each(evlist, evsel) {
-		if (perf_evsel__alloc_stat_priv(evsel) < 0 ||
-		    perf_evsel__alloc_counts(evsel, perf_evsel__nr_cpus(evsel)) < 0 ||
-		    (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel) < 0))
-			goto out_free;
-	}
-
-	return 0;
-
-out_free:
-	perf_evlist__free_stats(evlist);
-	return -1;
-}
-
-static void perf_stat__reset_stats(struct perf_evlist *evlist)
-{
-	struct perf_evsel *evsel;
-
-	evlist__for_each(evlist, evsel) {
-		perf_evsel__reset_stat_priv(evsel);
-		perf_evsel__reset_counts(evsel, perf_evsel__nr_cpus(evsel));
-	}
-
+	perf_evlist__reset_stats(evsel_list);
 	perf_stat__reset_shadow_stats();
 }
 
@@ -304,8 +214,9 @@
 	return 0;
 }
 
-static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
-		   struct perf_counts_values *count)
+static int
+process_counter_values(struct perf_evsel *evsel, int cpu, int thread,
+		       struct perf_counts_values *count)
 {
 	struct perf_counts_values *aggr = &evsel->counts->aggr;
 	static struct perf_counts_values zero;
@@ -320,13 +231,13 @@
 		count = &zero;
 
 	switch (aggr_mode) {
+	case AGGR_THREAD:
 	case AGGR_CORE:
 	case AGGR_SOCKET:
 	case AGGR_NONE:
 		if (!evsel->snapshot)
-			perf_evsel__compute_deltas(evsel, cpu, count);
+			perf_evsel__compute_deltas(evsel, cpu, thread, count);
 		perf_counts_values__scale(count, scale, NULL);
-		evsel->counts->cpu[cpu] = *count;
 		if (aggr_mode == AGGR_NONE)
 			perf_stat__update_shadow_stats(evsel, count->values, cpu);
 		break;
@@ -343,26 +254,48 @@
 	return 0;
 }
 
-static int read_counter(struct perf_evsel *counter);
+static int process_counter_maps(struct perf_evsel *counter)
+{
+	int nthreads = thread_map__nr(counter->threads);
+	int ncpus = perf_evsel__nr_cpus(counter);
+	int cpu, thread;
 
-/*
- * Read out the results of a single counter:
- * aggregate counts across CPUs in system-wide mode
- */
-static int read_counter_aggr(struct perf_evsel *counter)
+	if (counter->system_wide)
+		nthreads = 1;
+
+	for (thread = 0; thread < nthreads; thread++) {
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			if (process_counter_values(counter, cpu, thread,
+						   perf_counts(counter->counts, cpu, thread)))
+				return -1;
+		}
+	}
+
+	return 0;
+}
+
+static int process_counter(struct perf_evsel *counter)
 {
 	struct perf_counts_values *aggr = &counter->counts->aggr;
 	struct perf_stat *ps = counter->priv;
 	u64 *count = counter->counts->aggr.values;
-	int i;
+	int i, ret;
 
 	aggr->val = aggr->ena = aggr->run = 0;
+	init_stats(ps->res_stats);
 
-	if (read_counter(counter))
-		return -1;
+	if (counter->per_pkg)
+		zero_per_pkg(counter);
+
+	ret = process_counter_maps(counter);
+	if (ret)
+		return ret;
+
+	if (aggr_mode != AGGR_GLOBAL)
+		return 0;
 
 	if (!counter->snapshot)
-		perf_evsel__compute_deltas(counter, -1, aggr);
+		perf_evsel__compute_deltas(counter, -1, -1, aggr);
 	perf_counts_values__scale(aggr, scale, &counter->counts->scaled);
 
 	for (i = 0; i < 3; i++)
@@ -397,12 +330,12 @@
 	if (counter->system_wide)
 		nthreads = 1;
 
-	if (counter->per_pkg)
-		zero_per_pkg(counter);
-
 	for (thread = 0; thread < nthreads; thread++) {
 		for (cpu = 0; cpu < ncpus; cpu++) {
-			if (perf_evsel__read_cb(counter, cpu, thread, read_cb))
+			struct perf_counts_values *count;
+
+			count = perf_counts(counter->counts, cpu, thread);
+			if (perf_evsel__read(counter, cpu, thread, count))
 				return -1;
 		}
 	}
@@ -410,68 +343,34 @@
 	return 0;
 }
 
-static void print_interval(void)
+static void read_counters(bool close)
 {
-	static int num_print_interval;
 	struct perf_evsel *counter;
-	struct perf_stat *ps;
-	struct timespec ts, rs;
-	char prefix[64];
 
-	if (aggr_mode == AGGR_GLOBAL) {
-		evlist__for_each(evsel_list, counter) {
-			ps = counter->priv;
-			memset(ps->res_stats, 0, sizeof(ps->res_stats));
-			read_counter_aggr(counter);
-		}
-	} else	{
-		evlist__for_each(evsel_list, counter) {
-			ps = counter->priv;
-			memset(ps->res_stats, 0, sizeof(ps->res_stats));
-			read_counter(counter);
+	evlist__for_each(evsel_list, counter) {
+		if (read_counter(counter))
+			pr_warning("failed to read counter %s\n", counter->name);
+
+		if (process_counter(counter))
+			pr_warning("failed to process counter %s\n", counter->name);
+
+		if (close) {
+			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
+					     thread_map__nr(evsel_list->threads));
 		}
 	}
+}
+
+static void process_interval(void)
+{
+	struct timespec ts, rs;
+
+	read_counters(false);
 
 	clock_gettime(CLOCK_MONOTONIC, &ts);
 	diff_timespec(&rs, &ts, &ref_time);
-	sprintf(prefix, "%6lu.%09lu%s", rs.tv_sec, rs.tv_nsec, csv_sep);
 
-	if (num_print_interval == 0 && !csv_output) {
-		switch (aggr_mode) {
-		case AGGR_SOCKET:
-			fprintf(output, "#           time socket cpus             counts %*s events\n", unit_width, "unit");
-			break;
-		case AGGR_CORE:
-			fprintf(output, "#           time core         cpus             counts %*s events\n", unit_width, "unit");
-			break;
-		case AGGR_NONE:
-			fprintf(output, "#           time CPU                counts %*s events\n", unit_width, "unit");
-			break;
-		case AGGR_GLOBAL:
-		default:
-			fprintf(output, "#           time             counts %*s events\n", unit_width, "unit");
-		}
-	}
-
-	if (++num_print_interval == 25)
-		num_print_interval = 0;
-
-	switch (aggr_mode) {
-	case AGGR_CORE:
-	case AGGR_SOCKET:
-		print_aggr(prefix);
-		break;
-	case AGGR_NONE:
-		evlist__for_each(evsel_list, counter)
-			print_counter(counter, prefix);
-		break;
-	case AGGR_GLOBAL:
-	default:
-		evlist__for_each(evsel_list, counter)
-			print_counter_aggr(counter, prefix);
-	}
-
-	fflush(output);
+	print_counters(&rs, 0, NULL);
 }
 
 static void handle_initial_delay(void)
@@ -586,7 +485,7 @@
 		if (interval) {
 			while (!waitpid(child_pid, &status, WNOHANG)) {
 				nanosleep(&ts, NULL);
-				print_interval();
+				process_interval();
 			}
 		}
 		wait(&status);
@@ -604,7 +503,7 @@
 		while (!done) {
 			nanosleep(&ts, NULL);
 			if (interval)
-				print_interval();
+				process_interval();
 		}
 	}
 
@@ -612,18 +511,7 @@
 
 	update_stats(&walltime_nsecs_stats, t1 - t0);
 
-	if (aggr_mode == AGGR_GLOBAL) {
-		evlist__for_each(evsel_list, counter) {
-			read_counter_aggr(counter);
-			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
-					     thread_map__nr(evsel_list->threads));
-		}
-	} else {
-		evlist__for_each(evsel_list, counter) {
-			read_counter(counter);
-			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), 1);
-		}
-	}
+	read_counters(true);
 
 	return WEXITSTATUS(status);
 }
@@ -715,6 +603,14 @@
 			csv_output ? 0 : -4,
 			perf_evsel__cpus(evsel)->map[id], csv_sep);
 		break;
+	case AGGR_THREAD:
+		fprintf(output, "%*s-%*d%s",
+			csv_output ? 0 : 16,
+			thread_map__comm(evsel->threads, id),
+			csv_output ? 0 : -8,
+			thread_map__pid(evsel->threads, id),
+			csv_sep);
+		break;
 	case AGGR_GLOBAL:
 	default:
 		break;
@@ -815,9 +711,9 @@
 				s2 = aggr_get_id(evsel_list->cpus, cpu2);
 				if (s2 != id)
 					continue;
-				val += counter->counts->cpu[cpu].val;
-				ena += counter->counts->cpu[cpu].ena;
-				run += counter->counts->cpu[cpu].run;
+				val += perf_counts(counter->counts, cpu, 0)->val;
+				ena += perf_counts(counter->counts, cpu, 0)->ena;
+				run += perf_counts(counter->counts, cpu, 0)->run;
 				nr++;
 			}
 			if (prefix)
@@ -863,6 +759,40 @@
 	}
 }
 
+static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
+{
+	int nthreads = thread_map__nr(counter->threads);
+	int ncpus = cpu_map__nr(counter->cpus);
+	int cpu, thread;
+	double uval;
+
+	for (thread = 0; thread < nthreads; thread++) {
+		u64 ena = 0, run = 0, val = 0;
+
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			val += perf_counts(counter->counts, cpu, thread)->val;
+			ena += perf_counts(counter->counts, cpu, thread)->ena;
+			run += perf_counts(counter->counts, cpu, thread)->run;
+		}
+
+		if (prefix)
+			fprintf(output, "%s", prefix);
+
+		uval = val * counter->scale;
+
+		if (nsec_counter(counter))
+			nsec_printout(thread, 0, counter, uval);
+		else
+			abs_printout(thread, 0, counter, uval);
+
+		if (!csv_output)
+			print_noise(counter, 1.0);
+
+		print_running(run, ena);
+		fputc('\n', output);
+	}
+}
+
 /*
  * Print out the results of a single counter:
  * aggregated counts in system-wide mode
@@ -925,9 +855,9 @@
 	int cpu;
 
 	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-		val = counter->counts->cpu[cpu].val;
-		ena = counter->counts->cpu[cpu].ena;
-		run = counter->counts->cpu[cpu].run;
+		val = perf_counts(counter->counts, cpu, 0)->val;
+		ena = perf_counts(counter->counts, cpu, 0)->ena;
+		run = perf_counts(counter->counts, cpu, 0)->run;
 
 		if (prefix)
 			fprintf(output, "%s", prefix);
@@ -972,9 +902,38 @@
 	}
 }
 
-static void print_stat(int argc, const char **argv)
+static void print_interval(char *prefix, struct timespec *ts)
 {
-	struct perf_evsel *counter;
+	static int num_print_interval;
+
+	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
+
+	if (num_print_interval == 0 && !csv_output) {
+		switch (aggr_mode) {
+		case AGGR_SOCKET:
+			fprintf(output, "#           time socket cpus             counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_CORE:
+			fprintf(output, "#           time core         cpus             counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_NONE:
+			fprintf(output, "#           time CPU                counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_THREAD:
+			fprintf(output, "#           time             comm-pid                  counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_GLOBAL:
+		default:
+			fprintf(output, "#           time             counts %*s events\n", unit_width, "unit");
+		}
+	}
+
+	if (++num_print_interval == 25)
+		num_print_interval = 0;
+}
+
+static void print_header(int argc, const char **argv)
+{
 	int i;
 
 	fflush(stdout);
@@ -1000,36 +959,57 @@
 			fprintf(output, " (%d runs)", run_count);
 		fprintf(output, ":\n\n");
 	}
+}
+
+static void print_footer(void)
+{
+	if (!null_run)
+		fprintf(output, "\n");
+	fprintf(output, " %17.9f seconds time elapsed",
+			avg_stats(&walltime_nsecs_stats)/1e9);
+	if (run_count > 1) {
+		fprintf(output, "                                        ");
+		print_noise_pct(stddev_stats(&walltime_nsecs_stats),
+				avg_stats(&walltime_nsecs_stats));
+	}
+	fprintf(output, "\n\n");
+}
+
+static void print_counters(struct timespec *ts, int argc, const char **argv)
+{
+	struct perf_evsel *counter;
+	char buf[64], *prefix = NULL;
+
+	if (interval)
+		print_interval(prefix = buf, ts);
+	else
+		print_header(argc, argv);
 
 	switch (aggr_mode) {
 	case AGGR_CORE:
 	case AGGR_SOCKET:
-		print_aggr(NULL);
+		print_aggr(prefix);
+		break;
+	case AGGR_THREAD:
+		evlist__for_each(evsel_list, counter)
+			print_aggr_thread(counter, prefix);
 		break;
 	case AGGR_GLOBAL:
 		evlist__for_each(evsel_list, counter)
-			print_counter_aggr(counter, NULL);
+			print_counter_aggr(counter, prefix);
 		break;
 	case AGGR_NONE:
 		evlist__for_each(evsel_list, counter)
-			print_counter(counter, NULL);
+			print_counter(counter, prefix);
 		break;
 	default:
 		break;
 	}
 
-	if (!csv_output) {
-		if (!null_run)
-			fprintf(output, "\n");
-		fprintf(output, " %17.9f seconds time elapsed",
-				avg_stats(&walltime_nsecs_stats)/1e9);
-		if (run_count > 1) {
-			fprintf(output, "                                        ");
-			print_noise_pct(stddev_stats(&walltime_nsecs_stats),
-					avg_stats(&walltime_nsecs_stats));
-		}
-		fprintf(output, "\n\n");
-	}
+	if (!interval && !csv_output)
+		print_footer();
+
+	fflush(output);
 }
 
 static volatile int signr = -1;
@@ -1101,6 +1081,7 @@
 		break;
 	case AGGR_NONE:
 	case AGGR_GLOBAL:
+	case AGGR_THREAD:
 	default:
 		break;
 	}
@@ -1325,6 +1306,8 @@
 		     "aggregate counts per processor socket", AGGR_SOCKET),
 	OPT_SET_UINT(0, "per-core", &aggr_mode,
 		     "aggregate counts per physical processor core", AGGR_CORE),
+	OPT_SET_UINT(0, "per-thread", &aggr_mode,
+		     "aggregate counts per thread", AGGR_THREAD),
 	OPT_UINTEGER('D', "delay", &initial_delay,
 		     "ms to wait before starting measurement after program start"),
 	OPT_END()
@@ -1416,8 +1399,19 @@
 		run_count = 1;
 	}
 
-	/* no_aggr, cgroup are for system-wide only */
-	if ((aggr_mode != AGGR_GLOBAL || nr_cgroups) &&
+	if ((aggr_mode == AGGR_THREAD) && !target__has_task(&target)) {
+		fprintf(stderr, "The --per-thread option is only available "
+			"when monitoring via -p -t options.\n");
+		parse_options_usage(NULL, options, "p", 1);
+		parse_options_usage(NULL, options, "t", 1);
+		goto out;
+	}
+
+	/*
+	 * no_aggr, cgroup are for system-wide only
+	 * --per-thread is aggregated per thread, we dont mix it with cpu mode
+	 */
+	if (((aggr_mode != AGGR_GLOBAL && aggr_mode != AGGR_THREAD) || nr_cgroups) &&
 	    !target__has_cpu(&target)) {
 		fprintf(stderr, "both cgroup and no-aggregation "
 			"modes only available in system-wide mode\n");
@@ -1445,6 +1439,14 @@
 		}
 		goto out;
 	}
+
+	/*
+	 * Initialize thread_map with comm names,
+	 * so we could print it out on output.
+	 */
+	if (aggr_mode == AGGR_THREAD)
+		thread_map__read_comms(evsel_list->threads);
+
 	if (interval && interval < 100) {
 		pr_err("print interval must be >= 100ms\n");
 		parse_options_usage(stat_usage, options, "I", 1);
@@ -1478,13 +1480,13 @@
 
 		status = run_perf_stat(argc, argv);
 		if (forever && status != -1) {
-			print_stat(argc, argv);
-			perf_stat__reset_stats(evsel_list);
+			print_counters(NULL, argc, argv);
+			perf_stat__reset_stats();
 		}
 	}
 
 	if (!forever && status != -1 && !interval)
-		print_stat(argc, argv);
+		print_counters(NULL, argc, argv);
 
 	perf_evlist__free_stats(evsel_list);
 out:
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 619a869..ecf3197 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -586,27 +586,9 @@
 		hists->uid_filter_str = top->record_opts.target.uid_str;
 	}
 
-	while (true)  {
-		int key = perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
-							top->min_percent,
-							&top->session->header.env);
-
-		if (key != 'f')
-			break;
-
-		perf_evlist__toggle_enable(top->evlist);
-		/*
-		 * No need to refresh, resort/decay histogram entries
-		 * if we are not collecting samples:
-		 */
-		if (top->evlist->enabled) {
-			hbt.refresh = top->delay_secs;
-			help = "Press 'f' to disable the events or 'h' to see other hotkeys";
-		} else {
-			help = "Press 'f' again to re-enable the events";
-			hbt.refresh = 0;
-		}
-	}
+	perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
+				      top->min_percent,
+				      &top->session->header.env);
 
 	done = 1;
 	return NULL;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index de5d277..39ad4d0 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1617,6 +1617,34 @@
 	return syscall__set_arg_fmts(sc);
 }
 
+static int trace__validate_ev_qualifier(struct trace *trace)
+{
+	int err = 0;
+	struct str_node *pos;
+
+	strlist__for_each(pos, trace->ev_qualifier) {
+		const char *sc = pos->s;
+
+		if (audit_name_to_syscall(sc, trace->audit.machine) < 0) {
+			if (err == 0) {
+				fputs("Error:\tInvalid syscall ", trace->output);
+				err = -EINVAL;
+			} else {
+				fputs(", ", trace->output);
+			}
+
+			fputs(sc, trace->output);
+		}
+	}
+
+	if (err < 0) {
+		fputs("\nHint:\ttry 'perf list syscalls:sys_enter_*'"
+		      "\nHint:\tand: 'man syscalls'\n", trace->output);
+	}
+
+	return err;
+}
+
 /*
  * args is to be interpreted as a series of longs but we need to handle
  * 8-byte unaligned accesses. args points to raw_data within the event
@@ -2325,7 +2353,7 @@
 	 */
 	if (trace->filter_pids.nr > 0)
 		err = perf_evlist__set_filter_pids(evlist, trace->filter_pids.nr, trace->filter_pids.entries);
-	else if (evlist->threads->map[0] == -1)
+	else if (thread_map__pid(evlist->threads, 0) == -1)
 		err = perf_evlist__set_filter_pid(evlist, getpid());
 
 	if (err < 0) {
@@ -2343,7 +2371,7 @@
 	if (forks)
 		perf_evlist__start_workload(evlist);
 
-	trace->multiple_threads = evlist->threads->map[0] == -1 ||
+	trace->multiple_threads = thread_map__pid(evlist->threads, 0) == -1 ||
 				  evlist->threads->nr > 1 ||
 				  perf_evlist__first(evlist)->attr.inherit;
 again:
@@ -2862,6 +2890,10 @@
 			err = -ENOMEM;
 			goto out_close;
 		}
+
+		err = trace__validate_ev_qualifier(&trace);
+		if (err)
+			goto out_close;
 	}
 
 	err = target__validate(&trace.opts.target);
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 317001c..094ddae 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -11,9 +11,9 @@
 obj-perf := $(abspath $(obj-perf))/
 endif
 
-$(shell echo -n > .config-detected)
-detected     = $(shell echo "$(1)=y"       >> .config-detected)
-detected_var = $(shell echo "$(1)=$($(1))" >> .config-detected)
+$(shell echo -n > $(OUTPUT).config-detected)
+detected     = $(shell echo "$(1)=y"       >> $(OUTPUT).config-detected)
+detected_var = $(shell echo "$(1)=$($(1))" >> $(OUTPUT).config-detected)
 
 CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS)
 
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index ee41e70..d20d6e6 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -31,6 +31,7 @@
 perf-y += sample-parsing.o
 perf-y += parse-no-sample-id-all.o
 perf-y += kmod-path.o
+perf-y += thread-map.o
 
 perf-$(CONFIG_X86) += perf-time-to-tsc.o
 
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 87b9961..c1dde73 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -171,6 +171,10 @@
 		.func = test__kmod_path__parse,
 	},
 	{
+		.desc = "Test thread map",
+		.func = test__thread_map,
+	},
+	{
 		.func = NULL,
 	},
 };
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 22f8a00..39c784a 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -545,8 +545,8 @@
 	if (evlist) {
 		perf_evlist__delete(evlist);
 	} else {
-		cpu_map__delete(cpus);
-		thread_map__delete(threads);
+		cpu_map__put(cpus);
+		thread_map__put(threads);
 	}
 	machines__destroy_kernel_maps(&machines);
 	machine__delete_threads(machine);
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 5b171d1..4d4b983 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -144,8 +144,8 @@
 		perf_evlist__disable(evlist);
 		perf_evlist__delete(evlist);
 	} else {
-		cpu_map__delete(cpus);
-		thread_map__delete(threads);
+		cpu_map__put(cpus);
+		thread_map__put(threads);
 	}
 
 	return err;
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index 65280d2..729112f 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -1,5 +1,16 @@
+ifndef MK
+ifeq ($(MAKECMDGOALS),)
+# 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
+else
+# run only specific test over 'Makefile'
+%:
+	@echo "Testing Makefile";      $(MAKE) -sf tests/make MK=Makefile $@
+endif
+else
 PERF := .
-MK   := Makefile
 
 include config/Makefile.arch
 
@@ -47,6 +58,7 @@
 make_install_html   := install-html
 make_install_info   := install-info
 make_install_pdf    := install-pdf
+make_install_prefix := install prefix=/tmp/krava
 make_static         := LDFLAGS=-static
 
 # all the NO_* variable combined
@@ -57,7 +69,12 @@
 
 # $(run) contains all available tests
 run := make_pure
+# Targets 'clean all' can be run together only through top level
+# Makefile because we detect clean target in Makefile.perf and
+# disable features detection
+ifeq ($(MK),Makefile)
 run += make_clean_all
+endif
 run += make_python_perf_so
 run += make_debug
 run += make_no_libperl
@@ -83,6 +100,7 @@
 run += make_util_pmu_bison_o
 run += make_install
 run += make_install_bin
+run += make_install_prefix
 # FIXME 'install-*' commented out till they're fixed
 # run += make_install_doc
 # run += make_install_man
@@ -157,6 +175,12 @@
 test_make_install_bin   := $(call test_dest_files,$(installed_files_bin))
 test_make_install_bin_O := $(call test_dest_files,$(installed_files_bin))
 
+# We prefix all installed files for make_install_prefix
+# with '/tmp/krava' to match installed/prefix-ed files.
+installed_files_all_prefix := $(addprefix /tmp/krava/,$(installed_files_all))
+test_make_install_prefix   := $(call test_dest_files,$(installed_files_all_prefix))
+test_make_install_prefix_O := $(call test_dest_files,$(installed_files_all_prefix))
+
 # FIXME nothing gets installed
 test_make_install_man    := test -f $$TMP_DEST/share/man/man1/perf.1
 test_make_install_man_O  := $(test_make_install_man)
@@ -226,13 +250,13 @@
 	( eval $$cmd ) >> $@ 2>&1
 
 make_kernelsrc:
-	@echo " - make -C <kernelsrc> tools/perf"
+	@echo "- make -C <kernelsrc> tools/perf"
 	$(call clean); \
 	(make -C ../.. tools/perf) > $@ 2>&1 && \
 	test -x perf && rm -f $@ || (cat $@ ; false)
 
 make_kernelsrc_tools:
-	@echo " - make -C <kernelsrc>/tools perf"
+	@echo "- make -C <kernelsrc>/tools perf"
 	$(call clean); \
 	(make -C ../../tools perf) > $@ 2>&1 && \
 	test -x perf && rm -f $@ || (cat $@ ; false)
@@ -244,3 +268,4 @@
 	@echo OK
 
 .PHONY: all $(run) $(run_O) tarpkg clean
+endif # ifndef MK
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 5855cf4..666b67a 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -140,8 +140,8 @@
 	cpus	= NULL;
 	threads = NULL;
 out_free_cpus:
-	cpu_map__delete(cpus);
+	cpu_map__put(cpus);
 out_free_threads:
-	thread_map__delete(threads);
+	thread_map__put(threads);
 	return err;
 }
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 7f48efa..145050e 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -143,7 +143,7 @@
 						perf_event__process,
 						machine, 0, 500);
 
-	thread_map__delete(map);
+	thread_map__put(map);
 	return err;
 }
 
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index 9a7a116..a572f87 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -78,7 +78,7 @@
 	 * we use the auto allocation it will allocate just for 1 cpu,
 	 * as we start by cpu 0.
 	 */
-	if (perf_evsel__alloc_counts(evsel, cpus->nr) < 0) {
+	if (perf_evsel__alloc_counts(evsel, cpus->nr, 1) < 0) {
 		pr_debug("perf_evsel__alloc_counts(ncpus=%d)\n", cpus->nr);
 		goto out_close_fd;
 	}
@@ -98,9 +98,9 @@
 		}
 
 		expected = nr_openat_calls + cpu;
-		if (evsel->counts->cpu[cpu].val != expected) {
+		if (perf_counts(evsel->counts, cpu, 0)->val != expected) {
 			pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n",
-				 expected, cpus->map[cpu], evsel->counts->cpu[cpu].val);
+				 expected, cpus->map[cpu], perf_counts(evsel->counts, cpu, 0)->val);
 			err = -1;
 		}
 	}
@@ -111,6 +111,6 @@
 out_evsel_delete:
 	perf_evsel__delete(evsel);
 out_thread_map_delete:
-	thread_map__delete(threads);
+	thread_map__put(threads);
 	return err;
 }
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index 6245221..01a1962 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -45,7 +45,7 @@
 
 	perf_evsel__config(evsel, &opts);
 
-	evlist->threads->map[0] = getpid();
+	thread_map__set_pid(evlist->threads, 0, getpid());
 
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c
index 9f9491b..c9a37bc 100644
--- a/tools/perf/tests/openat-syscall.c
+++ b/tools/perf/tests/openat-syscall.c
@@ -44,9 +44,9 @@
 		goto out_close_fd;
 	}
 
-	if (evsel->counts->cpu[0].val != nr_openat_calls) {
+	if (perf_counts(evsel->counts, 0, 0)->val != nr_openat_calls) {
 		pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %" PRIu64 "\n",
-			 nr_openat_calls, evsel->counts->cpu[0].val);
+			 nr_openat_calls, perf_counts(evsel->counts, 0, 0)->val);
 		goto out_close_fd;
 	}
 
@@ -56,6 +56,6 @@
 out_evsel_delete:
 	perf_evsel__delete(evsel);
 out_thread_map_delete:
-	thread_map__delete(threads);
+	thread_map__put(threads);
 	return err;
 }
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index 0d31403..e698742 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -560,8 +560,8 @@
 		perf_evlist__disable(evlist);
 		perf_evlist__delete(evlist);
 	} else {
-		cpu_map__delete(cpus);
-		thread_map__delete(threads);
+		cpu_map__put(cpus);
+		thread_map__put(threads);
 	}
 
 	return err;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 8e5038b..ebb47d9 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -61,6 +61,7 @@
 int test__fdarray__filter(void);
 int test__fdarray__add(void);
 int test__kmod_path__parse(void);
+int test__thread_map(void);
 
 #if defined(__x86_64__) || defined(__i386__) || defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
new file mode 100644
index 0000000..5acf000
--- /dev/null
+++ b/tools/perf/tests/thread-map.c
@@ -0,0 +1,38 @@
+#include <sys/types.h>
+#include <unistd.h>
+#include "tests.h"
+#include "thread_map.h"
+#include "debug.h"
+
+int test__thread_map(void)
+{
+	struct thread_map *map;
+
+	/* test map on current pid */
+	map = thread_map__new_by_pid(getpid());
+	TEST_ASSERT_VAL("failed to alloc map", map);
+
+	thread_map__read_comms(map);
+
+	TEST_ASSERT_VAL("wrong nr", map->nr == 1);
+	TEST_ASSERT_VAL("wrong pid",
+			thread_map__pid(map, 0) == getpid());
+	TEST_ASSERT_VAL("wrong comm",
+			thread_map__comm(map, 0) &&
+			!strcmp(thread_map__comm(map, 0), "perf"));
+	thread_map__put(map);
+
+	/* test dummy pid */
+	map = thread_map__new_dummy();
+	TEST_ASSERT_VAL("failed to alloc map", map);
+
+	thread_map__read_comms(map);
+
+	TEST_ASSERT_VAL("wrong nr", map->nr == 1);
+	TEST_ASSERT_VAL("wrong pid", thread_map__pid(map, 0) == -1);
+	TEST_ASSERT_VAL("wrong comm",
+			thread_map__comm(map, 0) &&
+			!strcmp(thread_map__comm(map, 0), "dummy"));
+	thread_map__put(map);
+	return 0;
+}
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index c42adb6..7629bef 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1902,8 +1902,23 @@
 		case CTRL('c'):
 			goto out_free_stack;
 		case 'f':
-			if (!is_report_browser(hbt))
-				goto out_free_stack;
+			if (!is_report_browser(hbt)) {
+				struct perf_top *top = hbt->arg;
+
+				perf_evlist__toggle_enable(top->evlist);
+				/*
+				 * No need to refresh, resort/decay histogram
+				 * entries if we are not collecting samples:
+				 */
+				if (top->evlist->enabled) {
+					helpline = "Press 'f' to disable the events or 'h' to see other hotkeys";
+					hbt->refresh = delay_secs;
+				} else {
+					helpline = "Press 'f' again to re-enable the events";
+					hbt->refresh = 0;
+				}
+				continue;
+			}
 			/* Fall thru */
 		default:
 			helpline = "Press '?' for help on key bindings";
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 586a59d..601d114 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -139,7 +139,7 @@
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
-$(OUTPUT)util/rbtree.o: ../../lib/rbtree.c FORCE
+$(OUTPUT)util/rbtree.o: ../lib/rbtree.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index df66966..7e7405c 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -119,12 +119,12 @@
 	if (per_cpu) {
 		mp->cpu = evlist->cpus->map[idx];
 		if (evlist->threads)
-			mp->tid = evlist->threads->map[0];
+			mp->tid = thread_map__pid(evlist->threads, 0);
 		else
 			mp->tid = -1;
 	} else {
 		mp->cpu = -1;
-		mp->tid = evlist->threads->map[idx];
+		mp->tid = thread_map__pid(evlist->threads, idx);
 	}
 }
 
@@ -1182,6 +1182,13 @@
 		data2 = NULL;
 	}
 
+	if (itr->alignment) {
+		unsigned int unwanted = len1 % itr->alignment;
+
+		len1 -= unwanted;
+		size -= unwanted;
+	}
+
 	/* padding must be written by fn() e.g. record__process_auxtrace() */
 	padding = size & 7;
 	if (padding)
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index a171abb..471aecb 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -303,6 +303,7 @@
 				      const char *str);
 	u64 (*reference)(struct auxtrace_record *itr);
 	int (*read_finish)(struct auxtrace_record *itr, int idx);
+	unsigned int alignment;
 };
 
 #ifdef HAVE_AUXTRACE_SUPPORT
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index 85b5238..2babdda 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -7,11 +7,15 @@
 
 static unsigned long flag = PERF_FLAG_FD_CLOEXEC;
 
+#ifdef __GLIBC_PREREQ
+#if !__GLIBC_PREREQ(2, 6)
 int __weak sched_getcpu(void)
 {
 	errno = ENOSYS;
 	return -1;
 }
+#endif
+#endif
 
 static int perf_flag_probe(void)
 {
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index c4e55b7..3667e21 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -5,6 +5,7 @@
 #include <assert.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include "asm/bug.h"
 
 static struct cpu_map *cpu_map__default_new(void)
 {
@@ -22,6 +23,7 @@
 			cpus->map[i] = i;
 
 		cpus->nr = nr_cpus;
+		atomic_set(&cpus->refcnt, 1);
 	}
 
 	return cpus;
@@ -35,6 +37,7 @@
 	if (cpus != NULL) {
 		cpus->nr = nr_cpus;
 		memcpy(cpus->map, tmp_cpus, payload_size);
+		atomic_set(&cpus->refcnt, 1);
 	}
 
 	return cpus;
@@ -194,14 +197,32 @@
 	if (cpus != NULL) {
 		cpus->nr = 1;
 		cpus->map[0] = -1;
+		atomic_set(&cpus->refcnt, 1);
 	}
 
 	return cpus;
 }
 
-void cpu_map__delete(struct cpu_map *map)
+static void cpu_map__delete(struct cpu_map *map)
 {
-	free(map);
+	if (map) {
+		WARN_ONCE(atomic_read(&map->refcnt) != 0,
+			  "cpu_map refcnt unbalanced\n");
+		free(map);
+	}
+}
+
+struct cpu_map *cpu_map__get(struct cpu_map *map)
+{
+	if (map)
+		atomic_inc(&map->refcnt);
+	return map;
+}
+
+void cpu_map__put(struct cpu_map *map)
+{
+	if (map && atomic_dec_and_test(&map->refcnt))
+		cpu_map__delete(map);
 }
 
 int cpu_map__get_socket(struct cpu_map *map, int idx)
@@ -263,6 +284,7 @@
 	/* ensure we process id in increasing order */
 	qsort(c->map, c->nr, sizeof(int), cmp_ids);
 
+	atomic_set(&cpus->refcnt, 1);
 	*res = c;
 	return 0;
 }
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 61a6548..0af9cec 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -3,18 +3,19 @@
 
 #include <stdio.h>
 #include <stdbool.h>
+#include <linux/atomic.h>
 
 #include "perf.h"
 #include "util/debug.h"
 
 struct cpu_map {
+	atomic_t refcnt;
 	int nr;
 	int map[];
 };
 
 struct cpu_map *cpu_map__new(const char *cpu_list);
 struct cpu_map *cpu_map__dummy_new(void);
-void cpu_map__delete(struct cpu_map *map);
 struct cpu_map *cpu_map__read(FILE *file);
 size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
 int cpu_map__get_socket(struct cpu_map *map, int idx);
@@ -22,6 +23,9 @@
 int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp);
 int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep);
 
+struct cpu_map *cpu_map__get(struct cpu_map *map);
+void cpu_map__put(struct cpu_map *map);
+
 static inline int cpu_map__socket(struct cpu_map *sock, int s)
 {
 	if (!sock || s > sock->nr || s < 0)
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index d7d986d..67a977e 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -504,7 +504,7 @@
 	for (thread = 0; thread < threads->nr; ++thread) {
 		if (__event__synthesize_thread(comm_event, mmap_event,
 					       fork_event,
-					       threads->map[thread], 0,
+					       thread_map__pid(threads, thread), 0,
 					       process, tool, machine,
 					       mmap_data, proc_map_timeout)) {
 			err = -1;
@@ -515,12 +515,12 @@
 		 * comm.pid is set to thread group id by
 		 * perf_event__synthesize_comm
 		 */
-		if ((int) comm_event->comm.pid != threads->map[thread]) {
+		if ((int) comm_event->comm.pid != thread_map__pid(threads, thread)) {
 			bool need_leader = true;
 
 			/* is thread group leader in thread_map? */
 			for (j = 0; j < threads->nr; ++j) {
-				if ((int) comm_event->comm.pid == threads->map[j]) {
+				if ((int) comm_event->comm.pid == thread_map__pid(threads, j)) {
 					need_leader = false;
 					break;
 				}
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 8366511..6cfdee6 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -114,8 +114,8 @@
 {
 	perf_evlist__munmap(evlist);
 	perf_evlist__close(evlist);
-	cpu_map__delete(evlist->cpus);
-	thread_map__delete(evlist->threads);
+	cpu_map__put(evlist->cpus);
+	thread_map__put(evlist->threads);
 	evlist->cpus = NULL;
 	evlist->threads = NULL;
 	perf_evlist__purge(evlist);
@@ -548,7 +548,7 @@
 	else
 		sid->cpu = -1;
 	if (!evsel->system_wide && evlist->threads && thread >= 0)
-		sid->tid = evlist->threads->map[thread];
+		sid->tid = thread_map__pid(evlist->threads, thread);
 	else
 		sid->tid = -1;
 }
@@ -1101,6 +1101,31 @@
 	return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false);
 }
 
+static int perf_evlist__propagate_maps(struct perf_evlist *evlist,
+				       struct target *target)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		/*
+		 * We already have cpus for evsel (via PMU sysfs) so
+		 * keep it, if there's no target cpu list defined.
+		 */
+		if (evsel->cpus && target->cpu_list)
+			cpu_map__put(evsel->cpus);
+
+		if (!evsel->cpus || target->cpu_list)
+			evsel->cpus = cpu_map__get(evlist->cpus);
+
+		evsel->threads = thread_map__get(evlist->threads);
+
+		if (!evsel->cpus || !evsel->threads)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 {
 	evlist->threads = thread_map__new_str(target->pid, target->tid,
@@ -1117,10 +1142,10 @@
 	if (evlist->cpus == NULL)
 		goto out_delete_threads;
 
-	return 0;
+	return perf_evlist__propagate_maps(evlist, target);
 
 out_delete_threads:
-	thread_map__delete(evlist->threads);
+	thread_map__put(evlist->threads);
 	evlist->threads = NULL;
 	return -1;
 }
@@ -1353,7 +1378,7 @@
 out:
 	return err;
 out_free_cpus:
-	cpu_map__delete(evlist->cpus);
+	cpu_map__put(evlist->cpus);
 	evlist->cpus = NULL;
 	goto out;
 }
@@ -1475,7 +1500,7 @@
 				__func__, __LINE__);
 			goto out_close_pipes;
 		}
-		evlist->threads->map[0] = evlist->workload.pid;
+		thread_map__set_pid(evlist->threads, 0, evlist->workload.pid);
 	}
 
 	close(child_ready_pipe[1]);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index a8489b9..037633c 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -289,5 +289,4 @@
 
 void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 				     struct perf_evsel *tracking_evsel);
-
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 33449de..2936b30 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -885,6 +885,8 @@
 	perf_evsel__free_fd(evsel);
 	perf_evsel__free_id(evsel);
 	close_cgroup(evsel->cgrp);
+	cpu_map__put(evsel->cpus);
+	thread_map__put(evsel->threads);
 	zfree(&evsel->group_name);
 	zfree(&evsel->name);
 	perf_evsel__object.fini(evsel);
@@ -896,7 +898,7 @@
 	free(evsel);
 }
 
-void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
+void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread,
 				struct perf_counts_values *count)
 {
 	struct perf_counts_values tmp;
@@ -908,8 +910,8 @@
 		tmp = evsel->prev_raw_counts->aggr;
 		evsel->prev_raw_counts->aggr = *count;
 	} else {
-		tmp = evsel->prev_raw_counts->cpu[cpu];
-		evsel->prev_raw_counts->cpu[cpu] = *count;
+		tmp = *perf_counts(evsel->prev_raw_counts, cpu, thread);
+		*perf_counts(evsel->prev_raw_counts, cpu, thread) = *count;
 	}
 
 	count->val = count->val - tmp.val;
@@ -937,20 +939,18 @@
 		*pscaled = scaled;
 }
 
-int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread,
-			perf_evsel__read_cb_t cb)
+int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+		     struct perf_counts_values *count)
 {
-	struct perf_counts_values count;
-
-	memset(&count, 0, sizeof(count));
+	memset(count, 0, sizeof(*count));
 
 	if (FD(evsel, cpu, thread) < 0)
 		return -EINVAL;
 
-	if (readn(FD(evsel, cpu, thread), &count, sizeof(count)) < 0)
+	if (readn(FD(evsel, cpu, thread), count, sizeof(*count)) < 0)
 		return -errno;
 
-	return cb(evsel, cpu, thread, &count);
+	return 0;
 }
 
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
@@ -962,15 +962,15 @@
 	if (FD(evsel, cpu, thread) < 0)
 		return -EINVAL;
 
-	if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1) < 0)
+	if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1, thread + 1) < 0)
 		return -ENOMEM;
 
 	if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0)
 		return -errno;
 
-	perf_evsel__compute_deltas(evsel, cpu, &count);
+	perf_evsel__compute_deltas(evsel, cpu, thread, &count);
 	perf_counts_values__scale(&count, scale, NULL);
-	evsel->counts->cpu[cpu] = count;
+	*perf_counts(evsel->counts, cpu, thread) = count;
 	return 0;
 }
 
@@ -1167,7 +1167,7 @@
 			int group_fd;
 
 			if (!evsel->cgrp && !evsel->system_wide)
-				pid = threads->map[thread];
+				pid = thread_map__pid(threads, thread);
 
 			group_fd = get_group_fd(evsel, cpu, thread);
 retry_open:
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index bb0579e..4a7ed56 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -8,23 +8,8 @@
 #include <linux/types.h>
 #include "xyarray.h"
 #include "symbol.h"
-
-struct perf_counts_values {
-	union {
-		struct {
-			u64 val;
-			u64 ena;
-			u64 run;
-		};
-		u64 values[3];
-	};
-};
-
-struct perf_counts {
-	s8		   	  scaled;
-	struct perf_counts_values aggr;
-	struct perf_counts_values cpu[];
-};
+#include "cpumap.h"
+#include "stat.h"
 
 struct perf_evsel;
 
@@ -82,6 +67,7 @@
 	struct cgroup_sel	*cgrp;
 	void			*handler;
 	struct cpu_map		*cpus;
+	struct thread_map	*threads;
 	unsigned int		sample_size;
 	int			id_pos;
 	int			is_pos;
@@ -113,10 +99,20 @@
 struct perf_evlist;
 struct record_opts;
 
+static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
+{
+	return evsel->cpus;
+}
+
+static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
+{
+	return perf_evsel__cpus(evsel)->nr;
+}
+
 void perf_counts_values__scale(struct perf_counts_values *count,
 			       bool scale, s8 *pscaled);
 
-void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
+void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread,
 				struct perf_counts_values *count);
 
 int perf_evsel__object_config(size_t object_size,
@@ -233,12 +229,8 @@
 	 (a)->attr.type == (b)->attr.type &&	\
 	 (a)->attr.config == (b)->attr.config)
 
-typedef int (perf_evsel__read_cb_t)(struct perf_evsel *evsel,
-				    int cpu, int thread,
-				    struct perf_counts_values *count);
-
-int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread,
-			perf_evsel__read_cb_t cb);
+int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+		     struct perf_counts_values *count);
 
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 			      int cpu, int thread, bool scale);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 21a77e7..03ace57 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1063,8 +1063,7 @@
 	free(buf);
 	return events;
 error:
-	if (events)
-		free_event_desc(events);
+	free_event_desc(events);
 	events = NULL;
 	goto out;
 }
diff --git a/tools/perf/util/include/linux/rbtree.h b/tools/perf/util/include/linux/rbtree.h
deleted file mode 100644
index f06d89f..0000000
--- a/tools/perf/util/include/linux/rbtree.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef __TOOLS_LINUX_PERF_RBTREE_H
-#define __TOOLS_LINUX_PERF_RBTREE_H
-#include <stdbool.h>
-#include "../../../../include/linux/rbtree.h"
-
-/*
- * Handy for checking that we are not deleting an entry that is
- * already in a list, found in block/{blk-throttle,cfq-iosched}.c,
- * probably should be moved to lib/rbtree.c...
- */
-static inline void rb_erase_init(struct rb_node *n, struct rb_root *root)
-{
-	rb_erase(n, root);
-	RB_CLEAR_NODE(n);
-}
-#endif /* __TOOLS_LINUX_PERF_RBTREE_H */
diff --git a/tools/perf/util/include/linux/rbtree_augmented.h b/tools/perf/util/include/linux/rbtree_augmented.h
deleted file mode 100644
index 9d6fcdf..0000000
--- a/tools/perf/util/include/linux/rbtree_augmented.h
+++ /dev/null
@@ -1,2 +0,0 @@
-#include <stdbool.h>
-#include "../../../../include/linux/rbtree_augmented.h"
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 4744673..7ff6827 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1448,10 +1448,9 @@
 	case PERF_RECORD_AUX:
 		ret = machine__process_aux_event(machine, event); break;
 	case PERF_RECORD_ITRACE_START:
-		ret = machine__process_itrace_start_event(machine, event);
+		ret = machine__process_itrace_start_event(machine, event); break;
 	case PERF_RECORD_LOST_SAMPLES:
 		ret = machine__process_lost_samples_event(machine, event, sample); break;
-		break;
 	default:
 		ret = -1;
 		break;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 2a4d1ec..09f8d23 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -17,6 +17,7 @@
 #include "parse-events-flex.h"
 #include "pmu.h"
 #include "thread_map.h"
+#include "cpumap.h"
 #include "asm/bug.h"
 
 #define MAX_NAME_LEN 100
@@ -285,7 +286,9 @@
 	if (!evsel)
 		return NULL;
 
-	evsel->cpus = cpus;
+	if (cpus)
+		evsel->cpus = cpu_map__get(cpus);
+
 	if (name)
 		evsel->name = strdup(name);
 	list_add_tail(&evsel->node, list);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 09e738f..13cef3c 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -119,8 +119,8 @@
 num_dec		[0-9]+
 num_hex		0x[a-fA-F0-9]+
 num_raw_hex	[a-fA-F0-9]+
-name		[a-zA-Z_*?][a-zA-Z0-9_*?]*
-name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?]*
+name		[a-zA-Z_*?][a-zA-Z0-9_*?.]*
+name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.]*
 /* If you add a modifier you need to update check_modifier() */
 modifier_event	[ukhpGHSDI]+
 modifier_bp	[rwx]{1,3}
@@ -165,7 +165,6 @@
 			return PE_EVENT_NAME;
 		}
 
-.		|
 <<EOF>>		{
 			BEGIN(INITIAL);
 			REWIND(0);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 0fcc624..7bcb8c3 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1,4 +1,5 @@
 #include <linux/list.h>
+#include <linux/compiler.h>
 #include <sys/types.h>
 #include <unistd.h>
 #include <stdio.h>
@@ -205,17 +206,12 @@
 	return 0;
 }
 
-static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file)
+static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
+				 char *desc __maybe_unused, char *val)
 {
 	struct perf_pmu_alias *alias;
-	char buf[256];
 	int ret;
 
-	ret = fread(buf, 1, sizeof(buf), file);
-	if (ret == 0)
-		return -EINVAL;
-	buf[ret] = 0;
-
 	alias = malloc(sizeof(*alias));
 	if (!alias)
 		return -ENOMEM;
@@ -225,26 +221,43 @@
 	alias->unit[0] = '\0';
 	alias->per_pkg = false;
 
-	ret = parse_events_terms(&alias->terms, buf);
+	ret = parse_events_terms(&alias->terms, val);
 	if (ret) {
+		pr_err("Cannot parse alias %s: %d\n", val, ret);
 		free(alias);
 		return ret;
 	}
 
 	alias->name = strdup(name);
-	/*
-	 * load unit name and scale if available
-	 */
-	perf_pmu__parse_unit(alias, dir, name);
-	perf_pmu__parse_scale(alias, dir, name);
-	perf_pmu__parse_per_pkg(alias, dir, name);
-	perf_pmu__parse_snapshot(alias, dir, name);
+	if (dir) {
+		/*
+		 * load unit name and scale if available
+		 */
+		perf_pmu__parse_unit(alias, dir, name);
+		perf_pmu__parse_scale(alias, dir, name);
+		perf_pmu__parse_per_pkg(alias, dir, name);
+		perf_pmu__parse_snapshot(alias, dir, name);
+	}
 
 	list_add_tail(&alias->list, list);
 
 	return 0;
 }
 
+static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file)
+{
+	char buf[256];
+	int ret;
+
+	ret = fread(buf, 1, sizeof(buf), file);
+	if (ret == 0)
+		return -EINVAL;
+
+	buf[ret] = 0;
+
+	return __perf_pmu__new_alias(list, dir, name, NULL, buf);
+}
+
 static inline bool pmu_alias_info_file(char *name)
 {
 	size_t len;
@@ -436,7 +449,7 @@
 	return cpus;
 }
 
-struct perf_event_attr *__attribute__((weak))
+struct perf_event_attr * __weak
 perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
 {
 	return NULL;
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 076527b..381f23a 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -249,8 +249,12 @@
 static bool kprobe_blacklist__listed(unsigned long address);
 static bool kprobe_warn_out_range(const char *symbol, unsigned long address)
 {
+	u64 etext_addr;
+
 	/* Get the address of _etext for checking non-probable text symbol */
-	if (kernel_get_symbol_address_by_name("_etext", false) < address)
+	etext_addr = kernel_get_symbol_address_by_name("_etext", false);
+
+	if (etext_addr != 0 && etext_addr < address)
 		pr_warning("%s is out of .text, skip it.\n", symbol);
 	else if (kprobe_blacklist__listed(address))
 		pr_warning("%s is blacklisted function, skip it.\n", symbol);
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 5925fec..e23ded4 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -20,3 +20,4 @@
 util/strlist.c
 util/trace-event.c
 ../../lib/rbtree.c
+util/string.c
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index d906d0ad..626422e 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -384,7 +384,7 @@
 
 static void pyrf_cpu_map__delete(struct pyrf_cpu_map *pcpus)
 {
-	cpu_map__delete(pcpus->cpus);
+	cpu_map__put(pcpus->cpus);
 	pcpus->ob_type->tp_free((PyObject*)pcpus);
 }
 
@@ -453,7 +453,7 @@
 
 static void pyrf_thread_map__delete(struct pyrf_thread_map *pthreads)
 {
-	thread_map__delete(pthreads->threads);
+	thread_map__put(pthreads->threads);
 	pthreads->ob_type->tp_free((PyObject*)pthreads);
 }
 
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index d457c52..1f7becb 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -64,7 +64,7 @@
 	if (!cpus)
 		return false;
 	cpu = cpus->map[0];
-	cpu_map__delete(cpus);
+	cpu_map__put(cpus);
 
 	do {
 		ret = perf_do_probe_api(fn, cpu, try[i++]);
@@ -226,7 +226,7 @@
 		struct cpu_map *cpus = cpu_map__new(NULL);
 
 		cpu =  cpus ? cpus->map[0] : 0;
-		cpu_map__delete(cpus);
+		cpu_map__put(cpus);
 	} else {
 		cpu = evlist->cpus->map[0];
 	}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index aa482c1..ed9dc25 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -686,6 +686,8 @@
 				  union perf_event *event __maybe_unused,
 				  struct ordered_events *oe)
 {
+	if (dump_trace)
+		fprintf(stdout, "\n");
 	return ordered_events__flush(oe, OE_FLUSH__ROUND);
 }
 
@@ -1726,7 +1728,7 @@
 	if (perf_header__has_feat(&session->header, HEADER_AUXTRACE))
 		msg = " (excludes AUX area (e.g. instruction trace) decoded / synthesized events)";
 
-	ret = fprintf(fp, "Aggregated stats:%s\n", msg);
+	ret = fprintf(fp, "\nAggregated stats:%s\n", msg);
 
 	ret += events_stats__fprintf(&session->evlist->stats, fp);
 	return ret;
@@ -1893,7 +1895,7 @@
 	err = 0;
 
 out_delete_map:
-	cpu_map__delete(map);
+	cpu_map__put(map);
 	return err;
 }
 
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 4014b70..f2a0d15 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -1,6 +1,8 @@
 #include <math.h>
 #include "stat.h"
+#include "evlist.h"
 #include "evsel.h"
+#include "thread_map.h"
 
 void update_stats(struct stats *stats, u64 val)
 {
@@ -95,33 +97,46 @@
 	}
 }
 
-struct perf_counts *perf_counts__new(int ncpus)
+struct perf_counts *perf_counts__new(int ncpus, int nthreads)
 {
-	int size = sizeof(struct perf_counts) +
-		   ncpus * sizeof(struct perf_counts_values);
+	struct perf_counts *counts = zalloc(sizeof(*counts));
 
-	return zalloc(size);
+	if (counts) {
+		struct xyarray *values;
+
+		values = xyarray__new(ncpus, nthreads, sizeof(struct perf_counts_values));
+		if (!values) {
+			free(counts);
+			return NULL;
+		}
+
+		counts->values = values;
+	}
+
+	return counts;
 }
 
 void perf_counts__delete(struct perf_counts *counts)
 {
-	free(counts);
+	if (counts) {
+		xyarray__delete(counts->values);
+		free(counts);
+	}
 }
 
-static void perf_counts__reset(struct perf_counts *counts, int ncpus)
+static void perf_counts__reset(struct perf_counts *counts)
 {
-	memset(counts, 0, (sizeof(*counts) +
-	       (ncpus * sizeof(struct perf_counts_values))));
+	xyarray__reset(counts->values);
 }
 
-void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus)
+void perf_evsel__reset_counts(struct perf_evsel *evsel)
 {
-	perf_counts__reset(evsel->counts, ncpus);
+	perf_counts__reset(evsel->counts);
 }
 
-int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus)
+int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
-	evsel->counts = perf_counts__new(ncpus);
+	evsel->counts = perf_counts__new(ncpus, nthreads);
 	return evsel->counts != NULL ? 0 : -ENOMEM;
 }
 
@@ -130,3 +145,96 @@
 	perf_counts__delete(evsel->counts);
 	evsel->counts = NULL;
 }
+
+void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
+{
+	int i;
+	struct perf_stat *ps = evsel->priv;
+
+	for (i = 0; i < 3; i++)
+		init_stats(&ps->res_stats[i]);
+
+	perf_stat_evsel_id_init(evsel);
+}
+
+int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
+{
+	evsel->priv = zalloc(sizeof(struct perf_stat));
+	if (evsel->priv == NULL)
+		return -ENOMEM;
+	perf_evsel__reset_stat_priv(evsel);
+	return 0;
+}
+
+void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
+{
+	zfree(&evsel->priv);
+}
+
+int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
+				      int ncpus, int nthreads)
+{
+	struct perf_counts *counts;
+
+	counts = perf_counts__new(ncpus, nthreads);
+	if (counts)
+		evsel->prev_raw_counts = counts;
+
+	return counts ? 0 : -ENOMEM;
+}
+
+void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
+{
+	perf_counts__delete(evsel->prev_raw_counts);
+	evsel->prev_raw_counts = NULL;
+}
+
+int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw)
+{
+	int ncpus = perf_evsel__nr_cpus(evsel);
+	int nthreads = thread_map__nr(evsel->threads);
+
+	if (perf_evsel__alloc_stat_priv(evsel) < 0 ||
+	    perf_evsel__alloc_counts(evsel, ncpus, nthreads) < 0 ||
+	    (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel, ncpus, nthreads) < 0))
+		return -ENOMEM;
+
+	return 0;
+}
+
+int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		if (perf_evsel__alloc_stats(evsel, alloc_raw))
+			goto out_free;
+	}
+
+	return 0;
+
+out_free:
+	perf_evlist__free_stats(evlist);
+	return -1;
+}
+
+void perf_evlist__free_stats(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		perf_evsel__free_stat_priv(evsel);
+		perf_evsel__free_counts(evsel);
+		perf_evsel__free_prev_raw_counts(evsel);
+	}
+}
+
+void perf_evlist__reset_stats(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		perf_evsel__reset_stat_priv(evsel);
+		perf_evsel__reset_counts(evsel);
+	}
+}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 093dc3c..1cfbe0a 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -3,6 +3,7 @@
 
 #include <linux/types.h>
 #include <stdio.h>
+#include "xyarray.h"
 
 struct stats
 {
@@ -29,8 +30,32 @@
 	AGGR_GLOBAL,
 	AGGR_SOCKET,
 	AGGR_CORE,
+	AGGR_THREAD,
 };
 
+struct perf_counts_values {
+	union {
+		struct {
+			u64 val;
+			u64 ena;
+			u64 run;
+		};
+		u64 values[3];
+	};
+};
+
+struct perf_counts {
+	s8			  scaled;
+	struct perf_counts_values aggr;
+	struct xyarray		  *values;
+};
+
+static inline struct perf_counts_values*
+perf_counts(struct perf_counts *counts, int cpu, int thread)
+{
+	return xyarray__entry(counts->values, cpu, thread);
+}
+
 void update_stats(struct stats *stats, u64 val);
 double avg_stats(struct stats *stats);
 double stddev_stats(struct stats *stats);
@@ -46,6 +71,8 @@
 }
 
 struct perf_evsel;
+struct perf_evlist;
+
 bool __perf_evsel_stat__is(struct perf_evsel *evsel,
 			   enum perf_stat_evsel_id id);
 
@@ -62,10 +89,24 @@
 void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 				   double avg, int cpu, enum aggr_mode aggr);
 
-struct perf_counts *perf_counts__new(int ncpus);
+struct perf_counts *perf_counts__new(int ncpus, int nthreads);
 void perf_counts__delete(struct perf_counts *counts);
 
-void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus);
-int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
+void perf_evsel__reset_counts(struct perf_evsel *evsel);
+int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads);
 void perf_evsel__free_counts(struct perf_evsel *evsel);
+
+void perf_evsel__reset_stat_priv(struct perf_evsel *evsel);
+int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel);
+void perf_evsel__free_stat_priv(struct perf_evsel *evsel);
+
+int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
+				      int ncpus, int nthreads);
+void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel);
+
+int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw);
+
+int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
+void perf_evlist__free_stats(struct perf_evlist *evlist);
+void perf_evlist__reset_stats(struct perf_evlist *evlist);
 #endif
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 283d3e7..eec6c11 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -748,7 +748,7 @@
 		set_bit(c, cpumask_bits(b));
 	}
 
-	cpu_map__delete(m);
+	cpu_map__put(m);
 
 	return ret;
 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 504f2d7..48b588c 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1132,8 +1132,11 @@
 	INIT_LIST_HEAD(&md.maps);
 
 	fd = open(kcore_filename, O_RDONLY);
-	if (fd < 0)
+	if (fd < 0) {
+		pr_err("%s requires CAP_SYS_RAWIO capability to access.\n",
+			kcore_filename);
 		return -EINVAL;
+	}
 
 	/* Read new maps into temporary lists */
 	err = file__read_maps(fd, md.type == MAP__FUNCTION, kcore_mapfn, &md,
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index f4822bd..da7646d 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -8,8 +8,11 @@
 #include <unistd.h>
 #include "strlist.h"
 #include <string.h>
+#include <api/fs/fs.h>
+#include "asm/bug.h"
 #include "thread_map.h"
 #include "util.h"
+#include "debug.h"
 
 /* Skip "." and ".." directories */
 static int filter(const struct dirent *dir)
@@ -20,11 +23,26 @@
 		return 1;
 }
 
+static void thread_map__reset(struct thread_map *map, int start, int nr)
+{
+	size_t size = (nr - start) * sizeof(map->map[0]);
+
+	memset(&map->map[start], 0, size);
+}
+
 static struct thread_map *thread_map__realloc(struct thread_map *map, int nr)
 {
-	size_t size = sizeof(*map) + sizeof(pid_t) * nr;
+	size_t size = sizeof(*map) + sizeof(map->map[0]) * nr;
+	int start = map ? map->nr : 0;
 
-	return realloc(map, size);
+	map = realloc(map, size);
+	/*
+	 * We only realloc to add more items, let's reset new items.
+	 */
+	if (map)
+		thread_map__reset(map, start, nr);
+
+	return map;
 }
 
 #define thread_map__alloc(__nr) thread_map__realloc(NULL, __nr)
@@ -45,8 +63,9 @@
 	threads = thread_map__alloc(items);
 	if (threads != NULL) {
 		for (i = 0; i < items; i++)
-			threads->map[i] = atoi(namelist[i]->d_name);
+			thread_map__set_pid(threads, i, atoi(namelist[i]->d_name));
 		threads->nr = items;
+		atomic_set(&threads->refcnt, 1);
 	}
 
 	for (i=0; i<items; i++)
@@ -61,8 +80,9 @@
 	struct thread_map *threads = thread_map__alloc(1);
 
 	if (threads != NULL) {
-		threads->map[0] = tid;
-		threads->nr	= 1;
+		thread_map__set_pid(threads, 0, tid);
+		threads->nr = 1;
+		atomic_set(&threads->refcnt, 1);
 	}
 
 	return threads;
@@ -84,6 +104,7 @@
 		goto out_free_threads;
 
 	threads->nr = 0;
+	atomic_set(&threads->refcnt, 1);
 
 	while (!readdir_r(proc, &dirent, &next) && next) {
 		char *end;
@@ -123,8 +144,10 @@
 			threads = tmp;
 		}
 
-		for (i = 0; i < items; i++)
-			threads->map[threads->nr + i] = atoi(namelist[i]->d_name);
+		for (i = 0; i < items; i++) {
+			thread_map__set_pid(threads, threads->nr + i,
+					    atoi(namelist[i]->d_name));
+		}
 
 		for (i = 0; i < items; i++)
 			zfree(&namelist[i]);
@@ -201,7 +224,7 @@
 		threads = nt;
 
 		for (i = 0; i < items; i++) {
-			threads->map[j++] = atoi(namelist[i]->d_name);
+			thread_map__set_pid(threads, j++, atoi(namelist[i]->d_name));
 			zfree(&namelist[i]);
 		}
 		threads->nr = total_tasks;
@@ -210,6 +233,8 @@
 
 out:
 	strlist__delete(slist);
+	if (threads)
+		atomic_set(&threads->refcnt, 1);
 	return threads;
 
 out_free_namelist:
@@ -227,8 +252,9 @@
 	struct thread_map *threads = thread_map__alloc(1);
 
 	if (threads != NULL) {
-		threads->map[0]	= -1;
-		threads->nr	= 1;
+		thread_map__set_pid(threads, 0, -1);
+		threads->nr = 1;
+		atomic_set(&threads->refcnt, 1);
 	}
 	return threads;
 }
@@ -267,10 +293,12 @@
 			goto out_free_threads;
 
 		threads = nt;
-		threads->map[ntasks - 1] = tid;
-		threads->nr		 = ntasks;
+		thread_map__set_pid(threads, ntasks - 1, tid);
+		threads->nr = ntasks;
 	}
 out:
+	if (threads)
+		atomic_set(&threads->refcnt, 1);
 	return threads;
 
 out_free_threads:
@@ -290,9 +318,30 @@
 	return thread_map__new_by_tid_str(tid);
 }
 
-void thread_map__delete(struct thread_map *threads)
+static void thread_map__delete(struct thread_map *threads)
 {
-	free(threads);
+	if (threads) {
+		int i;
+
+		WARN_ONCE(atomic_read(&threads->refcnt) != 0,
+			  "thread map refcnt unbalanced\n");
+		for (i = 0; i < threads->nr; i++)
+			free(thread_map__comm(threads, i));
+		free(threads);
+	}
+}
+
+struct thread_map *thread_map__get(struct thread_map *map)
+{
+	if (map)
+		atomic_inc(&map->refcnt);
+	return map;
+}
+
+void thread_map__put(struct thread_map *map)
+{
+	if (map && atomic_dec_and_test(&map->refcnt))
+		thread_map__delete(map);
 }
 
 size_t thread_map__fprintf(struct thread_map *threads, FILE *fp)
@@ -301,7 +350,60 @@
 	size_t printed = fprintf(fp, "%d thread%s: ",
 				 threads->nr, threads->nr > 1 ? "s" : "");
 	for (i = 0; i < threads->nr; ++i)
-		printed += fprintf(fp, "%s%d", i ? ", " : "", threads->map[i]);
+		printed += fprintf(fp, "%s%d", i ? ", " : "", thread_map__pid(threads, i));
 
 	return printed + fprintf(fp, "\n");
 }
+
+static int get_comm(char **comm, pid_t pid)
+{
+	char *path;
+	size_t size;
+	int err;
+
+	if (asprintf(&path, "%s/%d/comm", procfs__mountpoint(), pid) == -1)
+		return -ENOMEM;
+
+	err = filename__read_str(path, comm, &size);
+	if (!err) {
+		/*
+		 * We're reading 16 bytes, while filename__read_str
+		 * allocates data per BUFSIZ bytes, so we can safely
+		 * mark the end of the string.
+		 */
+		(*comm)[size] = 0;
+		rtrim(*comm);
+	}
+
+	free(path);
+	return err;
+}
+
+static void comm_init(struct thread_map *map, int i)
+{
+	pid_t pid = thread_map__pid(map, i);
+	char *comm = NULL;
+
+	/* dummy pid comm initialization */
+	if (pid == -1) {
+		map->map[i].comm = strdup("dummy");
+		return;
+	}
+
+	/*
+	 * The comm name is like extra bonus ;-),
+	 * so just warn if we fail for any reason.
+	 */
+	if (get_comm(&comm, pid))
+		pr_warning("Couldn't resolve comm name for pid %d\n", pid);
+
+	map->map[i].comm = comm;
+}
+
+void thread_map__read_comms(struct thread_map *threads)
+{
+	int i;
+
+	for (i = 0; i < threads->nr; ++i)
+		comm_init(threads, i);
+}
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index 95313f4..af679d8 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -3,10 +3,17 @@
 
 #include <sys/types.h>
 #include <stdio.h>
+#include <linux/atomic.h>
+
+struct thread_map_data {
+	pid_t    pid;
+	char	*comm;
+};
 
 struct thread_map {
+	atomic_t refcnt;
 	int nr;
-	pid_t map[];
+	struct thread_map_data map[];
 };
 
 struct thread_map *thread_map__new_dummy(void);
@@ -15,11 +22,12 @@
 struct thread_map *thread_map__new_by_uid(uid_t uid);
 struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid);
 
+struct thread_map *thread_map__get(struct thread_map *map);
+void thread_map__put(struct thread_map *map);
+
 struct thread_map *thread_map__new_str(const char *pid,
 		const char *tid, uid_t uid);
 
-void thread_map__delete(struct thread_map *threads);
-
 size_t thread_map__fprintf(struct thread_map *threads, FILE *fp);
 
 static inline int thread_map__nr(struct thread_map *threads)
@@ -27,4 +35,21 @@
 	return threads ? threads->nr : 1;
 }
 
+static inline pid_t thread_map__pid(struct thread_map *map, int thread)
+{
+	return map->map[thread].pid;
+}
+
+static inline void
+thread_map__set_pid(struct thread_map *map, int thread, pid_t pid)
+{
+	map->map[thread].pid = pid;
+}
+
+static inline char *thread_map__comm(struct thread_map *map, int thread)
+{
+	return map->map[thread].comm;
+}
+
+void thread_map__read_comms(struct thread_map *threads);
 #endif	/* __PERF_THREAD_MAP_H */
diff --git a/tools/power/acpi/common/getopt.c b/tools/power/acpi/common/getopt.c
index 5da129e..326e826 100644
--- a/tools/power/acpi/common/getopt.c
+++ b/tools/power/acpi/common/getopt.c
@@ -127,7 +127,7 @@
 		    argv[acpi_gbl_optind][0] != '-' ||
 		    argv[acpi_gbl_optind][1] == '\0') {
 			return (ACPI_OPT_END);
-		} else if (ACPI_STRCMP(argv[acpi_gbl_optind], "--") == 0) {
+		} else if (strcmp(argv[acpi_gbl_optind], "--") == 0) {
 			acpi_gbl_optind++;
 			return (ACPI_OPT_END);
 		}
@@ -140,7 +140,7 @@
 	/* Make sure that the option is legal */
 
 	if (current_char == ':' ||
-	    (opts_ptr = ACPI_STRCHR(opts, current_char)) == NULL) {
+	    (opts_ptr = strchr(opts, current_char)) == NULL) {
 		ACPI_OPTION_ERROR("Illegal option: -", current_char);
 
 		if (argv[acpi_gbl_optind][++current_char_ptr] == '\0') {
diff --git a/tools/power/acpi/man/acpidump.8 b/tools/power/acpi/man/acpidump.8
index 38f095d..79e2d1d 100644
--- a/tools/power/acpi/man/acpidump.8
+++ b/tools/power/acpi/man/acpidump.8
@@ -22,9 +22,6 @@
 .B \-b
 Dump tables to binary files
 .TP
-.B \-c
-Dump customized tables
-.TP
 .B \-h \-?
 This help message
 .TP
@@ -48,15 +45,25 @@
 .B \-a <Address>
 Get table via a physical address
 .TP
+.B \-c <on|off>
+Turning on/off customized table dumping
+.TP
 .B \-f <BinaryFile>
 Get table via a binary file
 .TP
 .B \-n <Signature>
 Get table via a name/signature
 .TP
-Invocation without parameters dumps all available tables
+.B \-x
+Do not use but dump XSDT
 .TP
-Multiple mixed instances of -a, -f, and -n are supported
+.B \-x \-x
+Do not use or dump XSDT
+.TP
+.fi
+Invocation without parameters dumps all available tables.
+.TP
+Multiple mixed instances of -a, -f, and -n are supported.
 
 .SH EXAMPLES
 
diff --git a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
index db15c9d..dd5008b 100644
--- a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
+++ b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
@@ -222,7 +222,7 @@
 		goto exit;
 	}
 
-	ACPI_MEMCPY(local_table, mapped_table, table_length);
+	memcpy(local_table, mapped_table, table_length);
 
 exit:
 	osl_unmap_table(mapped_table);
@@ -531,7 +531,7 @@
 	gbl_rsdp_address =
 	    rsdp_base + (ACPI_CAST8(mapped_table) - rsdp_address);
 
-	ACPI_MEMCPY(&gbl_rsdp, mapped_table, sizeof(struct acpi_table_rsdp));
+	memcpy(&gbl_rsdp, mapped_table, sizeof(struct acpi_table_rsdp));
 	acpi_os_unmap_memory(rsdp_address, rsdp_size);
 
 	return (AE_OK);
@@ -582,65 +582,68 @@
 		return (AE_OK);
 	}
 
-	/* Get RSDP from memory */
-
-	status = osl_load_rsdp();
-	if (ACPI_FAILURE(status)) {
-		return (status);
-	}
-
-	/* Get XSDT from memory */
-
-	if (gbl_rsdp.revision && !gbl_do_not_dump_xsdt) {
-		if (gbl_xsdt) {
-			free(gbl_xsdt);
-			gbl_xsdt = NULL;
-		}
-
-		gbl_revision = 2;
-		status = osl_get_bios_table(ACPI_SIG_XSDT, 0,
-					    ACPI_CAST_PTR(struct
-							  acpi_table_header *,
-							  &gbl_xsdt), &address);
-		if (ACPI_FAILURE(status)) {
-			return (status);
-		}
-	}
-
-	/* Get RSDT from memory */
-
-	if (gbl_rsdp.rsdt_physical_address) {
-		if (gbl_rsdt) {
-			free(gbl_rsdt);
-			gbl_rsdt = NULL;
-		}
-
-		status = osl_get_bios_table(ACPI_SIG_RSDT, 0,
-					    ACPI_CAST_PTR(struct
-							  acpi_table_header *,
-							  &gbl_rsdt), &address);
-		if (ACPI_FAILURE(status)) {
-			return (status);
-		}
-	}
-
-	/* Get FADT from memory */
-
-	if (gbl_fadt) {
-		free(gbl_fadt);
-		gbl_fadt = NULL;
-	}
-
-	status = osl_get_bios_table(ACPI_SIG_FADT, 0,
-				    ACPI_CAST_PTR(struct acpi_table_header *,
-						  &gbl_fadt),
-				    &gbl_fadt_address);
-	if (ACPI_FAILURE(status)) {
-		return (status);
-	}
-
 	if (!gbl_dump_customized_tables) {
 
+		/* Get RSDP from memory */
+
+		status = osl_load_rsdp();
+		if (ACPI_FAILURE(status)) {
+			return (status);
+		}
+
+		/* Get XSDT from memory */
+
+		if (gbl_rsdp.revision && !gbl_do_not_dump_xsdt) {
+			if (gbl_xsdt) {
+				free(gbl_xsdt);
+				gbl_xsdt = NULL;
+			}
+
+			gbl_revision = 2;
+			status = osl_get_bios_table(ACPI_SIG_XSDT, 0,
+						    ACPI_CAST_PTR(struct
+								  acpi_table_header
+								  *, &gbl_xsdt),
+						    &address);
+			if (ACPI_FAILURE(status)) {
+				return (status);
+			}
+		}
+
+		/* Get RSDT from memory */
+
+		if (gbl_rsdp.rsdt_physical_address) {
+			if (gbl_rsdt) {
+				free(gbl_rsdt);
+				gbl_rsdt = NULL;
+			}
+
+			status = osl_get_bios_table(ACPI_SIG_RSDT, 0,
+						    ACPI_CAST_PTR(struct
+								  acpi_table_header
+								  *, &gbl_rsdt),
+						    &address);
+			if (ACPI_FAILURE(status)) {
+				return (status);
+			}
+		}
+
+		/* Get FADT from memory */
+
+		if (gbl_fadt) {
+			free(gbl_fadt);
+			gbl_fadt = NULL;
+		}
+
+		status = osl_get_bios_table(ACPI_SIG_FADT, 0,
+					    ACPI_CAST_PTR(struct
+							  acpi_table_header *,
+							  &gbl_fadt),
+					    &gbl_fadt_address);
+		if (ACPI_FAILURE(status)) {
+			return (status);
+		}
+
 		/* Add mandatory tables to global table list first */
 
 		status = osl_add_table_to_list(ACPI_RSDP_NAME, 0);
@@ -961,7 +964,7 @@
 		goto exit;
 	}
 
-	ACPI_MEMCPY(local_table, mapped_table, table_length);
+	memcpy(local_table, mapped_table, table_length);
 	*address = table_address;
 	*table = local_table;
 
diff --git a/tools/power/acpi/os_specific/service_layers/osunixmap.c b/tools/power/acpi/os_specific/service_layers/osunixmap.c
index 0b1fa29..44ad488 100644
--- a/tools/power/acpi/os_specific/service_layers/osunixmap.c
+++ b/tools/power/acpi/os_specific/service_layers/osunixmap.c
@@ -54,7 +54,7 @@
 #ifndef O_BINARY
 #define O_BINARY 0
 #endif
-#ifdef _free_BSD
+#if defined(_dragon_fly) || defined(_free_BSD)
 #define MMAP_FLAGS          MAP_SHARED
 #else
 #define MMAP_FLAGS          MAP_PRIVATE
diff --git a/tools/power/acpi/tools/acpidump/acpidump.h b/tools/power/acpi/tools/acpidump/acpidump.h
index 84bdef0..eed5344 100644
--- a/tools/power/acpi/tools/acpidump/acpidump.h
+++ b/tools/power/acpi/tools/acpidump/acpidump.h
@@ -66,7 +66,7 @@
 EXTERN u8 INIT_GLOBAL(gbl_summary_mode, FALSE);
 EXTERN u8 INIT_GLOBAL(gbl_verbose_mode, FALSE);
 EXTERN u8 INIT_GLOBAL(gbl_binary_mode, FALSE);
-EXTERN u8 INIT_GLOBAL(gbl_dump_customized_tables, FALSE);
+EXTERN u8 INIT_GLOBAL(gbl_dump_customized_tables, TRUE);
 EXTERN u8 INIT_GLOBAL(gbl_do_not_dump_xsdt, FALSE);
 EXTERN ACPI_FILE INIT_GLOBAL(gbl_output_file, NULL);
 EXTERN char INIT_GLOBAL(*gbl_output_filename, NULL);
diff --git a/tools/power/acpi/tools/acpidump/apdump.c b/tools/power/acpi/tools/acpidump/apdump.c
index c736adf..61d0de8 100644
--- a/tools/power/acpi/tools/acpidump/apdump.c
+++ b/tools/power/acpi/tools/acpidump/apdump.c
@@ -329,7 +329,7 @@
 	acpi_status status;
 	int table_status;
 
-	if (ACPI_STRLEN(signature) != ACPI_NAME_SIZE) {
+	if (strlen(signature) != ACPI_NAME_SIZE) {
 		acpi_log_error
 		    ("Invalid table signature [%s]: must be exactly 4 characters\n",
 		     signature);
@@ -338,15 +338,15 @@
 
 	/* Table signatures are expected to be uppercase */
 
-	ACPI_STRCPY(local_signature, signature);
+	strcpy(local_signature, signature);
 	acpi_ut_strupr(local_signature);
 
 	/* To be friendly, handle tables whose signatures do not match the name */
 
 	if (ACPI_COMPARE_NAME(local_signature, "FADT")) {
-		ACPI_STRCPY(local_signature, ACPI_SIG_FADT);
+		strcpy(local_signature, ACPI_SIG_FADT);
 	} else if (ACPI_COMPARE_NAME(local_signature, "MADT")) {
-		ACPI_STRCPY(local_signature, ACPI_SIG_MADT);
+		strcpy(local_signature, ACPI_SIG_MADT);
 	}
 
 	/* Dump all instances of this signature (to handle multiple SSDTs) */
diff --git a/tools/power/acpi/tools/acpidump/apfiles.c b/tools/power/acpi/tools/acpidump/apfiles.c
index 8f2fe16..a37f970 100644
--- a/tools/power/acpi/tools/acpidump/apfiles.c
+++ b/tools/power/acpi/tools/acpidump/apfiles.c
@@ -136,10 +136,10 @@
 	} else {
 		ACPI_MOVE_NAME(filename, table->signature);
 	}
-	filename[0] = (char)ACPI_TOLOWER(filename[0]);
-	filename[1] = (char)ACPI_TOLOWER(filename[1]);
-	filename[2] = (char)ACPI_TOLOWER(filename[2]);
-	filename[3] = (char)ACPI_TOLOWER(filename[3]);
+	filename[0] = (char)tolower((int)filename[0]);
+	filename[1] = (char)tolower((int)filename[1]);
+	filename[2] = (char)tolower((int)filename[2]);
+	filename[3] = (char)tolower((int)filename[3]);
 	filename[ACPI_NAME_SIZE] = 0;
 
 	/* Handle multiple SSDts - create different filenames for each */
@@ -147,10 +147,10 @@
 	if (instance > 0) {
 		acpi_ut_snprintf(instance_str, sizeof(instance_str), "%u",
 				 instance);
-		ACPI_STRCAT(filename, instance_str);
+		strcat(filename, instance_str);
 	}
 
-	ACPI_STRCAT(filename, ACPI_TABLE_FILE_SUFFIX);
+	strcat(filename, ACPI_TABLE_FILE_SUFFIX);
 
 	if (gbl_verbose_mode) {
 		acpi_log_error
diff --git a/tools/power/acpi/tools/acpidump/apmain.c b/tools/power/acpi/tools/acpidump/apmain.c
index d0ba653..57620f6 100644
--- a/tools/power/acpi/tools/acpidump/apmain.c
+++ b/tools/power/acpi/tools/acpidump/apmain.c
@@ -80,7 +80,7 @@
 u32 current_action = 0;
 
 #define AP_UTILITY_NAME             "ACPI Binary Table Dump Utility"
-#define AP_SUPPORTED_OPTIONS        "?a:bcf:hn:o:r:svxz"
+#define AP_SUPPORTED_OPTIONS        "?a:bc:f:hn:o:r:svxz"
 
 /******************************************************************************
  *
@@ -96,7 +96,6 @@
 	ACPI_USAGE_HEADER("acpidump [options]");
 
 	ACPI_OPTION("-b", "Dump tables to binary files");
-	ACPI_OPTION("-c", "Dump customized tables");
 	ACPI_OPTION("-h -?", "This help message");
 	ACPI_OPTION("-o <File>", "Redirect output to file");
 	ACPI_OPTION("-r <Address>", "Dump tables from specified RSDP");
@@ -107,6 +106,7 @@
 	ACPI_USAGE_TEXT("\nTable Options:\n");
 
 	ACPI_OPTION("-a <Address>", "Get table via a physical address");
+	ACPI_OPTION("-c <on|off>", "Turning on/off customized table dumping");
 	ACPI_OPTION("-f <BinaryFile>", "Get table via a binary file");
 	ACPI_OPTION("-n <Signature>", "Get table via a name/signature");
 	ACPI_OPTION("-x", "Do not use but dump XSDT");
@@ -181,7 +181,16 @@
 
 		case 'c':	/* Dump customized tables */
 
-			gbl_dump_customized_tables = TRUE;
+			if (!strcmp(acpi_gbl_optarg, "on")) {
+				gbl_dump_customized_tables = TRUE;
+			} else if (!strcmp(acpi_gbl_optarg, "off")) {
+				gbl_dump_customized_tables = FALSE;
+			} else {
+				acpi_log_error
+				    ("%s: Cannot handle this switch, please use on|off\n",
+				     acpi_gbl_optarg);
+				return (-1);
+			}
 			continue;
 
 		case 'h':
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 848af90..8b8a444 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -553,6 +553,8 @@
 	list_add(&kvm->vm_list, &vm_list);
 	spin_unlock(&kvm_lock);
 
+	preempt_notifier_inc();
+
 	return kvm;
 
 out_err:
@@ -620,6 +622,7 @@
 	cleanup_srcu_struct(&kvm->irq_srcu);
 	cleanup_srcu_struct(&kvm->srcu);
 	kvm_arch_free_vm(kvm);
+	preempt_notifier_dec();
 	hardware_disable_all();
 	mmdrop(mm);
 }