Merge 4.9-rc3 into usb-next

We want the USB fixes in here as well.
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

CREDITS

@@ -1864,10 +1864,11 @@ S: The Netherlands
 
 N: Martin Kepplinger
 E: martink@posteo.de
-E: martin.kepplinger@theobroma-systems.com
+E: martin.kepplinger@ginzinger.com
 W: http://www.martinkepplinger.com
 D: mma8452 accelerators iio driver
-D: Kernel cleanups
+D: pegasus_notetaker input driver
+D: Kernel fixes and cleanups
 S: Garnisonstraße 26
 S: 4020 Linz
 S: Austria

Documentation/ABI/testing/sysfs-class-cxl

@@ -220,8 +220,11 @@ What:           /sys/class/cxl/<card>/reset
 Date:           October 2014
 Contact:        linuxppc-dev@lists.ozlabs.org
 Description:    write only
-                Writing 1 will issue a PERST to card which may cause the card
-                to reload the FPGA depending on load_image_on_perst.
+                Writing 1 will issue a PERST to card provided there are no
+                contexts active on any one of the card AFUs. This may cause
+                the card to reload the FPGA depending on load_image_on_perst.
+                Writing -1 will do a force PERST irrespective of any active
+                contexts on the card AFUs.
 Users:		https://github.com/ibm-capi/libcxl
 
 What:		/sys/class/cxl/<card>/perst_reloads_same_image (not in a guest)

Documentation/device-mapper/dm-raid.txt

@@ -309,3 +309,4 @@ Version History
 	with a reshape in progress.
 1.9.0   Add support for RAID level takeover/reshape/region size
 	and set size reduction.
+1.9.1   Fix activation of existing RAID 4/10 mapped devices

Documentation/devicetree/bindings/clock/uniphier-clock.txt

@@ -24,7 +24,7 @@ Example:
 		reg = <0x61840000 0x4000>;
 
 		clock {
-			compatible = "socionext,uniphier-ld20-clock";
+			compatible = "socionext,uniphier-ld11-clock";
 			#clock-cells = <1>;
 		};
 
@@ -43,8 +43,8 @@ Provided clocks:
 21: USB3 ch1 PHY1
 
 
-Media I/O (MIO) clock
----------------------
+Media I/O (MIO) clock, SD clock
+-------------------------------
 
 Required properties:
 - compatible: should be one of the following:
@@ -52,10 +52,10 @@ Required properties:
     "socionext,uniphier-ld4-mio-clock"  - for LD4 SoC.
     "socionext,uniphier-pro4-mio-clock" - for Pro4 SoC.
     "socionext,uniphier-sld8-mio-clock" - for sLD8 SoC.
-    "socionext,uniphier-pro5-mio-clock" - for Pro5 SoC.
-    "socionext,uniphier-pxs2-mio-clock" - for PXs2/LD6b SoC.
+    "socionext,uniphier-pro5-sd-clock"  - for Pro5 SoC.
+    "socionext,uniphier-pxs2-sd-clock"  - for PXs2/LD6b SoC.
     "socionext,uniphier-ld11-mio-clock" - for LD11 SoC.
-    "socionext,uniphier-ld20-mio-clock" - for LD20 SoC.
+    "socionext,uniphier-ld20-sd-clock"  - for LD20 SoC.
 - #clock-cells: should be 1.
 
 Example:
@@ -66,7 +66,7 @@ Example:
 		reg = <0x59810000 0x800>;
 
 		clock {
-			compatible = "socionext,uniphier-ld20-mio-clock";
+			compatible = "socionext,uniphier-ld11-mio-clock";
 			#clock-cells = <1>;
 		};
 
@@ -112,7 +112,7 @@ Example:
 		reg = <0x59820000 0x200>;
 
 		clock {
-			compatible = "socionext,uniphier-ld20-peri-clock";
+			compatible = "socionext,uniphier-ld11-peri-clock";
 			#clock-cells = <1>;
 		};
 

Documentation/devicetree/bindings/ipmi/aspeed,ast2400-bt-bmc.txt

+* Aspeed BT (Block Transfer) IPMI interface
+
+The Aspeed SOCs (AST2400 and AST2500) are commonly used as BMCs
+(BaseBoard Management Controllers) and the BT interface can be used to
+perform in-band IPMI communication with their host.
+
+Required properties:
+
+- compatible : should be "aspeed,ast2400-bt-bmc"
+- reg: physical address and size of the registers
+
+Optional properties:
+
+- interrupts: interrupt generated by the BT interface. without an
+  interrupt, the driver will operate in poll mode.
+
+Example:
+
+	ibt@1e789140 {
+		compatible = "aspeed,ast2400-bt-bmc";
+		reg = <0x1e789140 0x18>;
+		interrupts = <8>;
+	};

Documentation/devicetree/bindings/pinctrl/pinctrl-aspeed.txt

@@ -43,7 +43,9 @@ aspeed,ast2500-pinctrl, aspeed,g5-pinctrl:
 
 GPID0 GPID2 GPIE0 I2C10 I2C11 I2C12 I2C13 I2C14 I2C3 I2C4 I2C5 I2C6 I2C7 I2C8
 I2C9 MAC1LINK MDIO1 MDIO2 OSCCLK PEWAKE PWM0 PWM1 PWM2 PWM3 PWM4 PWM5 PWM6 PWM7
-RGMII1 RGMII2 RMII1 RMII2 SD1 SPI1 TIMER4 TIMER5 TIMER6 TIMER7 TIMER8
+RGMII1 RGMII2 RMII1 RMII2 SD1 SPI1 SPI1DEBUG SPI1PASSTHRU TIMER4 TIMER5 TIMER6
+TIMER7 TIMER8 VGABIOSROM
+
 
 Examples:
 

Documentation/devicetree/bindings/reset/uniphier-reset.txt

@@ -6,25 +6,25 @@ System reset
 
 Required properties:
 - compatible: should be one of the following:
-    "socionext,uniphier-sld3-reset" - for PH1-sLD3 SoC.
-    "socionext,uniphier-ld4-reset"  - for PH1-LD4 SoC.
-    "socionext,uniphier-pro4-reset" - for PH1-Pro4 SoC.
-    "socionext,uniphier-sld8-reset" - for PH1-sLD8 SoC.
-    "socionext,uniphier-pro5-reset" - for PH1-Pro5 SoC.
-    "socionext,uniphier-pxs2-reset" - for ProXstream2/PH1-LD6b SoC.
-    "socionext,uniphier-ld11-reset" - for PH1-LD11 SoC.
-    "socionext,uniphier-ld20-reset" - for PH1-LD20 SoC.
+    "socionext,uniphier-sld3-reset" - for sLD3 SoC.
+    "socionext,uniphier-ld4-reset"  - for LD4 SoC.
+    "socionext,uniphier-pro4-reset" - for Pro4 SoC.
+    "socionext,uniphier-sld8-reset" - for sLD8 SoC.
+    "socionext,uniphier-pro5-reset" - for Pro5 SoC.
+    "socionext,uniphier-pxs2-reset" - for PXs2/LD6b SoC.
+    "socionext,uniphier-ld11-reset" - for LD11 SoC.
+    "socionext,uniphier-ld20-reset" - for LD20 SoC.
 - #reset-cells: should be 1.
 
 Example:
 
 	sysctrl@61840000 {
-		compatible = "socionext,uniphier-ld20-sysctrl",
+		compatible = "socionext,uniphier-ld11-sysctrl",
 			     "simple-mfd", "syscon";
 		reg = <0x61840000 0x4000>;
 
 		reset {
-			compatible = "socionext,uniphier-ld20-reset";
+			compatible = "socionext,uniphier-ld11-reset";
 			#reset-cells = <1>;
 		};
 
@@ -32,30 +32,30 @@ Example:
 	};
 
 
-Media I/O (MIO) reset
----------------------
+Media I/O (MIO) reset, SD reset
+-------------------------------
 
 Required properties:
 - compatible: should be one of the following:
-    "socionext,uniphier-sld3-mio-reset" - for PH1-sLD3 SoC.
-    "socionext,uniphier-ld4-mio-reset"  - for PH1-LD4 SoC.
-    "socionext,uniphier-pro4-mio-reset" - for PH1-Pro4 SoC.
-    "socionext,uniphier-sld8-mio-reset" - for PH1-sLD8 SoC.
-    "socionext,uniphier-pro5-mio-reset" - for PH1-Pro5 SoC.
-    "socionext,uniphier-pxs2-mio-reset" - for ProXstream2/PH1-LD6b SoC.
-    "socionext,uniphier-ld11-mio-reset" - for PH1-LD11 SoC.
-    "socionext,uniphier-ld20-mio-reset" - for PH1-LD20 SoC.
+    "socionext,uniphier-sld3-mio-reset" - for sLD3 SoC.
+    "socionext,uniphier-ld4-mio-reset"  - for LD4 SoC.
+    "socionext,uniphier-pro4-mio-reset" - for Pro4 SoC.
+    "socionext,uniphier-sld8-mio-reset" - for sLD8 SoC.
+    "socionext,uniphier-pro5-sd-reset"  - for Pro5 SoC.
+    "socionext,uniphier-pxs2-sd-reset"  - for PXs2/LD6b SoC.
+    "socionext,uniphier-ld11-mio-reset" - for LD11 SoC.
+    "socionext,uniphier-ld20-sd-reset"  - for LD20 SoC.
 - #reset-cells: should be 1.
 
 Example:
 
 	mioctrl@59810000 {
-		compatible = "socionext,uniphier-ld20-mioctrl",
+		compatible = "socionext,uniphier-ld11-mioctrl",
 			     "simple-mfd", "syscon";
 		reg = <0x59810000 0x800>;
 
 		reset {
-			compatible = "socionext,uniphier-ld20-mio-reset";
+			compatible = "socionext,uniphier-ld11-mio-reset";
 			#reset-cells = <1>;
 		};
 
@@ -68,24 +68,24 @@ Peripheral reset
 
 Required properties:
 - compatible: should be one of the following:
-    "socionext,uniphier-ld4-peri-reset"  - for PH1-LD4 SoC.
-    "socionext,uniphier-pro4-peri-reset" - for PH1-Pro4 SoC.
-    "socionext,uniphier-sld8-peri-reset" - for PH1-sLD8 SoC.
-    "socionext,uniphier-pro5-peri-reset" - for PH1-Pro5 SoC.
-    "socionext,uniphier-pxs2-peri-reset" - for ProXstream2/PH1-LD6b SoC.
-    "socionext,uniphier-ld11-peri-reset" - for PH1-LD11 SoC.
-    "socionext,uniphier-ld20-peri-reset" - for PH1-LD20 SoC.
+    "socionext,uniphier-ld4-peri-reset"  - for LD4 SoC.
+    "socionext,uniphier-pro4-peri-reset" - for Pro4 SoC.
+    "socionext,uniphier-sld8-peri-reset" - for sLD8 SoC.
+    "socionext,uniphier-pro5-peri-reset" - for Pro5 SoC.
+    "socionext,uniphier-pxs2-peri-reset" - for PXs2/LD6b SoC.
+    "socionext,uniphier-ld11-peri-reset" - for LD11 SoC.
+    "socionext,uniphier-ld20-peri-reset" - for LD20 SoC.
 - #reset-cells: should be 1.
 
 Example:
 
 	perictrl@59820000 {
-		compatible = "socionext,uniphier-ld20-perictrl",
+		compatible = "socionext,uniphier-ld11-perictrl",
 			     "simple-mfd", "syscon";
 		reg = <0x59820000 0x200>;
 
 		reset {
-			compatible = "socionext,uniphier-ld20-peri-reset";
+			compatible = "socionext,uniphier-ld11-peri-reset";
 			#reset-cells = <1>;
 		};
 

Documentation/devicetree/bindings/serial/cdns,uart.txt

 Binding for Cadence UART Controller
 
 Required properties:
-- compatible : should be "cdns,uart-r1p8", or "xlnx,xuartps"
+- compatible :
+  Use "xlnx,xuartps","cdns,uart-r1p8" for Zynq-7xxx SoC.
+  Use "xlnx,zynqmp-uart","cdns,uart-r1p12" for Zynq Ultrascale+ MPSoC.
 - reg: Should contain UART controller registers location and length.
 - interrupts: Should contain UART controller interrupts.
 - clocks: Must contain phandles to the UART clocks

Documentation/devicetree/bindings/serial/renesas,sci-serial.txt

@@ -9,6 +9,14 @@ Required properties:
     - "renesas,scifb-r8a73a4" for R8A73A4 (R-Mobile APE6) SCIFB compatible UART.
     - "renesas,scifa-r8a7740" for R8A7740 (R-Mobile A1) SCIFA compatible UART.
     - "renesas,scifb-r8a7740" for R8A7740 (R-Mobile A1) SCIFB compatible UART.
+    - "renesas,scif-r8a7743" for R8A7743 (RZ/G1M) SCIF compatible UART.
+    - "renesas,scifa-r8a7743" for R8A7743 (RZ/G1M) SCIFA compatible UART.
+    - "renesas,scifb-r8a7743" for R8A7743 (RZ/G1M) SCIFB compatible UART.
+    - "renesas,hscif-r8a7743" for R8A7743 (RZ/G1M) HSCIF compatible UART.
+    - "renesas,scif-r8a7745" for R8A7745 (RZ/G1E) SCIF compatible UART.
+    - "renesas,scifa-r8a7745" for R8A7745 (RZ/G1E) SCIFA compatible UART.
+    - "renesas,scifb-r8a7745" for R8A7745 (RZ/G1E) SCIFB compatible UART.
+    - "renesas,hscif-r8a7745" for R8A7745 (RZ/G1E) HSCIF compatible UART.
     - "renesas,scif-r8a7778" for R8A7778 (R-Car M1) SCIF compatible UART.
     - "renesas,scif-r8a7779" for R8A7779 (R-Car H1) SCIF compatible UART.
     - "renesas,scif-r8a7790" for R8A7790 (R-Car H2) SCIF compatible UART.

Documentation/devicetree/bindings/timer/jcore,pit.txt

+J-Core Programmable Interval Timer and Clocksource
+
+Required properties:
+
+- compatible: Must be "jcore,pit".
+
+- reg: Memory region(s) for timer/clocksource registers. For SMP,
+  there should be one region per cpu, indexed by the sequential,
+  zero-based hardware cpu number.
+
+- interrupts: An interrupt to assign for the timer. The actual pit
+  core is integrated with the aic and allows the timer interrupt
+  assignment to be programmed by software, but this property is
+  required in order to reserve an interrupt number that doesn't
+  conflict with other devices.
+
+
+Example:
+
+timer@200 {
+	compatible = "jcore,pit";
+	reg = < 0x200 0x30 0x500 0x30 >;
+	interrupts = < 0x48 >;
+};

Documentation/devicetree/bindings/usb/dwc2.txt

@@ -28,10 +28,7 @@ Refer to phy/phy-bindings.txt for generic phy consumer properties
 - g-use-dma: enable dma usage in gadget driver.
 - g-rx-fifo-size: size of rx fifo size in gadget mode.
 - g-np-tx-fifo-size: size of non-periodic tx fifo size in gadget mode.
-
-Deprecated properties:
-- g-tx-fifo-size: size of periodic tx fifo per endpoint (except ep0)
-  in gadget mode.
+- g-tx-fifo-size: size of periodic tx fifo per endpoint (except ep0) in gadget mode.
 
 Example:
 

Documentation/filesystems/proc.txt

@@ -395,32 +395,6 @@ is not associated with a file:
 
  or if empty, the mapping is anonymous.
 
-The /proc/PID/task/TID/maps is a view of the virtual memory from the viewpoint
-of the individual tasks of a process. In this file you will see a mapping marked
-as [stack] if that task sees it as a stack. Hence, for the example above, the
-task-level map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this:
-
-08048000-08049000 r-xp 00000000 03:00 8312       /opt/test
-08049000-0804a000 rw-p 00001000 03:00 8312       /opt/test
-0804a000-0806b000 rw-p 00000000 00:00 0          [heap]
-a7cb1000-a7cb2000 ---p 00000000 00:00 0
-a7cb2000-a7eb2000 rw-p 00000000 00:00 0
-a7eb2000-a7eb3000 ---p 00000000 00:00 0
-a7eb3000-a7ed5000 rw-p 00000000 00:00 0          [stack]
-a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
-a8008000-a800a000 r--p 00133000 03:00 4222       /lib/libc.so.6
-a800a000-a800b000 rw-p 00135000 03:00 4222       /lib/libc.so.6
-a800b000-a800e000 rw-p 00000000 00:00 0
-a800e000-a8022000 r-xp 00000000 03:00 14462      /lib/libpthread.so.0
-a8022000-a8023000 r--p 00013000 03:00 14462      /lib/libpthread.so.0
-a8023000-a8024000 rw-p 00014000 03:00 14462      /lib/libpthread.so.0
-a8024000-a8027000 rw-p 00000000 00:00 0
-a8027000-a8043000 r-xp 00000000 03:00 8317       /lib/ld-linux.so.2
-a8043000-a8044000 r--p 0001b000 03:00 8317       /lib/ld-linux.so.2
-a8044000-a8045000 rw-p 0001c000 03:00 8317       /lib/ld-linux.so.2
-aff35000-aff4a000 rw-p 00000000 00:00 0
-ffffe000-fffff000 r-xp 00000000 00:00 0          [vdso]
-
 The /proc/PID/smaps is an extension based on maps, showing the memory
 consumption for each of the process's mappings. For each of mappings there
 is a series of lines such as the following:

Documentation/gpio/board.txt

@@ -6,7 +6,7 @@ Note that it only applies to the new descriptor-based interface. For a
 description of the deprecated integer-based GPIO interface please refer to
 gpio-legacy.txt (actually, there is no real mapping possible with the old
 interface; you just fetch an integer from somewhere and request the
-corresponding GPIO.
+corresponding GPIO).
 
 All platforms can enable the GPIO library, but if the platform strictly
 requires GPIO functionality to be present, it needs to select GPIOLIB from its
@@ -162,6 +162,9 @@ The driver controlling "foo.0" will then be able to obtain its GPIOs as follows:
 
 Since the "led" GPIOs are mapped as active-high, this example will switch their
 signals to 1, i.e. enabling the LEDs. And for the "power" GPIO, which is mapped
-as active-low, its actual signal will be 0 after this code. Contrary to the legacy
-integer GPIO interface, the active-low property is handled during mapping and is
-thus transparent to GPIO consumers.
+as active-low, its actual signal will be 0 after this code. Contrary to the
+legacy integer GPIO interface, the active-low property is handled during
+mapping and is thus transparent to GPIO consumers.
+
+A set of functions such as gpiod_set_value() is available to work with
+the new descriptor-oriented interface.

MAINTAINERS

@@ -1442,6 +1442,7 @@ F:	drivers/cpufreq/mvebu-cpufreq.c
 F:	arch/arm/configs/mvebu_*_defconfig
 
 ARM/Marvell Berlin SoC support
+M:	Jisheng Zhang <jszhang@marvell.com>
 M:	Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
@@ -4620,8 +4621,9 @@ F:	sound/usb/misc/ua101.c
 
 EXTENSIBLE FIRMWARE INTERFACE (EFI)
 M:	Matt Fleming <matt@codeblueprint.co.uk>
+M:	Ard Biesheuvel <ard.biesheuvel@linaro.org>
 L:	linux-efi@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mfleming/efi.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi.git
 S:	Maintained
 F:	Documentation/efi-stub.txt
 F:	arch/ia64/kernel/efi.c
@@ -5286,6 +5288,12 @@ M:	Joe Perches <joe@perches.com>
 S:	Maintained
 F:	scripts/get_maintainer.pl
 
+GENWQE (IBM Generic Workqueue Card)
+M:	Frank Haverkamp <haver@linux.vnet.ibm.com>
+M:	Gabriel Krisman Bertazi <krisman@linux.vnet.ibm.com>
+S:	Supported
+F:	drivers/misc/genwqe/
+
 GFS2 FILE SYSTEM
 M:	Steven Whitehouse <swhiteho@redhat.com>
 M:	Bob Peterson <rpeterso@redhat.com>
@@ -8099,6 +8107,7 @@ S:	Maintained
 F:	drivers/media/dvb-frontends/mn88473*
 
 MODULE SUPPORT
+M:	Jessica Yu <jeyu@redhat.com>
 M:	Rusty Russell <rusty@rustcorp.com.au>
 S:	Maintained
 F:	include/linux/module.h
@@ -8212,7 +8221,7 @@ F:	include/linux/mfd/
 MULTIMEDIA CARD (MMC), SECURE DIGITAL (SD) AND SDIO SUBSYSTEM
 M:	Ulf Hansson <ulf.hansson@linaro.org>
 L:	linux-mmc@vger.kernel.org
-T:	git git://git.linaro.org/people/ulf.hansson/mmc.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc.git
 S:	Maintained
 F:	Documentation/devicetree/bindings/mmc/
 F:	drivers/mmc/
@@ -9299,7 +9308,7 @@ S:	Maintained
 F:	drivers/pci/host/*designware*
 
 PCI DRIVER FOR SYNOPSYS PROTOTYPING DEVICE
-M:	Joao Pinto <jpinto@synopsys.com>
+M:	Jose Abreu <Jose.Abreu@synopsys.com>
 L:	linux-pci@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/pci/designware-pcie.txt

Makefile

 VERSION = 4
 PATCHLEVEL = 9
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc3
 NAME = Psychotic Stoned Sheep
 
 # *DOCUMENTATION*

arch/alpha/kernel/ptrace.c

@@ -157,14 +157,16 @@ put_reg(struct task_struct *task, unsigned long regno, unsigned long data)
 static inline int
 read_int(struct task_struct *task, unsigned long addr, int * data)
 {
-	int copied = access_process_vm(task, addr, data, sizeof(int), 0);
+	int copied = access_process_vm(task, addr, data, sizeof(int),
+			FOLL_FORCE);
 	return (copied == sizeof(int)) ? 0 : -EIO;
 }
 
 static inline int
 write_int(struct task_struct *task, unsigned long addr, int data)
 {
-	int copied = access_process_vm(task, addr, &data, sizeof(int), 1);
+	int copied = access_process_vm(task, addr, &data, sizeof(int),
+			FOLL_FORCE | FOLL_WRITE);
 	return (copied == sizeof(int)) ? 0 : -EIO;
 }
 
@@ -281,7 +283,8 @@ long arch_ptrace(struct task_struct *child, long request,
 	/* When I and D space are separate, these will need to be fixed.  */
 	case PTRACE_PEEKTEXT: /* read word at location addr. */
 	case PTRACE_PEEKDATA:
-		copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
+		copied = access_process_vm(child, addr, &tmp, sizeof(tmp),
+				FOLL_FORCE);
 		ret = -EIO;
 		if (copied != sizeof(tmp))
 			break;

arch/arc/Kconfig

@@ -41,6 +41,8 @@ config ARC
 	select PERF_USE_VMALLOC
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_GENERIC_DMA_COHERENT
+	select HAVE_KERNEL_GZIP
+	select HAVE_KERNEL_LZMA
 
 config MIGHT_HAVE_PCI
 	bool
@@ -186,14 +188,6 @@ if SMP
 config ARC_HAS_COH_CACHES
 	def_bool n
 
-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
@@ -211,6 +205,15 @@ config ARC_SMP_HALT_ON_RESET
 
 endif	#SMP
 
+config ARC_MCIP
+	bool "ARConnect Multicore IP (MCIP) Support "
+	depends on ISA_ARCV2
+	default y if SMP
+	help
+	  This IP block enables SMP in ARC-HS38 cores.
+	  It provides for cross-core interrupts, multi-core debug
+	  hardware semaphores, shared memory,....
+
 menuconfig ARC_CACHE
 	bool "Enable Cache Support"
 	default y
@@ -537,14 +540,6 @@ config ARC_DBG_TLB_PARANOIA
 	bool "Paranoia Checks in Low Level TLB Handlers"
 	default n
 
-config ARC_DBG_TLB_MISS_COUNT
-	bool "Profile TLB Misses"
-	default n
-	select DEBUG_FS
-	help
-	  Counts number of I and D TLB Misses and exports them via Debugfs
-	  The counters can be cleared via Debugfs as well
-
 endif
 
 config ARC_UBOOT_SUPPORT

arch/arc/Makefile

@@ -50,9 +50,6 @@ atleast_gcc44 :=  $(call cc-ifversion, -ge, 0404, y)
 
 cflags-$(atleast_gcc44)			+= -fsection-anchors
 
-cflags-$(CONFIG_ARC_HAS_LLSC)		+= -mlock
-cflags-$(CONFIG_ARC_HAS_SWAPE)		+= -mswape
-
 ifdef CONFIG_ISA_ARCV2
 
 ifndef CONFIG_ARC_HAS_LL64

arch/arc/boot/Makefile

@@ -14,9 +14,15 @@ UIMAGE_ENTRYADDR   = $(LINUX_START_TEXT)
 
 suffix-y := bin
 suffix-$(CONFIG_KERNEL_GZIP)	:= gz
+suffix-$(CONFIG_KERNEL_LZMA)	:= lzma
 
-targets += uImage uImage.bin uImage.gz
-extra-y += vmlinux.bin vmlinux.bin.gz
+targets += uImage
+targets += uImage.bin
+targets += uImage.gz
+targets += uImage.lzma
+extra-y += vmlinux.bin
+extra-y += vmlinux.bin.gz
+extra-y += vmlinux.bin.lzma
 
 $(obj)/vmlinux.bin: vmlinux FORCE
 	$(call if_changed,objcopy)
@@ -24,12 +30,18 @@ $(obj)/vmlinux.bin: vmlinux FORCE
 $(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
 	$(call if_changed,gzip)
 
+$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,lzma)
+
 $(obj)/uImage.bin: $(obj)/vmlinux.bin FORCE
 	$(call if_changed,uimage,none)
 
 $(obj)/uImage.gz: $(obj)/vmlinux.bin.gz FORCE
 	$(call if_changed,uimage,gzip)
 
+$(obj)/uImage.lzma: $(obj)/vmlinux.bin.lzma FORCE
+	$(call if_changed,uimage,lzma)
+
 $(obj)/uImage: $(obj)/uImage.$(suffix-y)
 	@ln -sf $(notdir $<) $@
 	@echo '  Image $@ is ready'

arch/arc/include/asm/arcregs.h

@@ -349,10 +349,11 @@ struct cpuinfo_arc {
 	struct cpuinfo_arc_bpu bpu;
 	struct bcr_identity core;
 	struct bcr_isa isa;
+	const char *details, *name;
 	unsigned int vec_base;
 	struct cpuinfo_arc_ccm iccm, dccm;
 	struct {
-		unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, pad1:3,
+		unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, swape:1, pad1:2,
 			     fpu_sp:1, fpu_dp:1, pad2:6,
 			     debug:1, ap:1, smart:1, rtt:1, pad3:4,
 			     timer0:1, timer1:1, rtc:1, gfrc:1, pad4:4;

arch/arc/include/asm/cache.h

@@ -53,7 +53,7 @@ extern void arc_cache_init(void);
 extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len);
 extern void read_decode_cache_bcr(void);
 
-extern int ioc_exists;
+extern int ioc_enable;
 extern unsigned long perip_base, perip_end;
 
 #endif	/* !__ASSEMBLY__ */

arch/arc/include/asm/elf.h

@@ -54,7 +54,7 @@ extern int elf_check_arch(const struct elf32_hdr *);
  * the loader.  We need to make sure that it is out of the way of the program
  * that it will "exec", and that there is sufficient room for the brk.
  */
-#define ELF_ET_DYN_BASE		(2 * TASK_SIZE / 3)
+#define ELF_ET_DYN_BASE		(2UL * TASK_SIZE / 3)
 
 /*
  * When the program starts, a1 contains a pointer to a function to be

arch/arc/include/asm/mcip.h

@@ -55,6 +55,22 @@ struct mcip_cmd {
 #define IDU_M_DISTRI_DEST		0x2
 };
 
+struct mcip_bcr {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+		unsigned int pad3:8,
+			     idu:1, llm:1, num_cores:6,
+			     iocoh:1,  gfrc: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, gfrc:1, iocoh:1,
+			     num_cores:6, llm:1, idu:1,
+			     pad3:8;
+#endif
+};
+
 /*
  * MCIP programming model
  *

arch/arc/include/asm/module.h

@@ -18,6 +18,7 @@
 struct mod_arch_specific {
 	void *unw_info;
 	int unw_sec_idx;
+	const char *secstr;
 };
 #endif
 

arch/arc/include/asm/setup.h

@@ -27,11 +27,6 @@ struct id_to_str {
 	const char *str;
 };
 
-struct cpuinfo_data {
-	struct id_to_str info;
-	int up_range;
-};
-
 extern int root_mountflags, end_mem;
 
 void setup_processor(void);
@@ -43,5 +38,6 @@ void __init setup_arch_memory(void);
 #define IS_USED_RUN(v)		((v) ? "" : "(not used) ")
 #define IS_USED_CFG(cfg)	IS_USED_RUN(IS_ENABLED(cfg))
 #define IS_AVAIL2(v, s, cfg)	IS_AVAIL1(v, s), IS_AVAIL1(v, IS_USED_CFG(cfg))
+#define IS_AVAIL3(v, v2, s)	IS_AVAIL1(v, s), IS_AVAIL1(v, IS_DISABLED_RUN(v2))
 
 #endif /* __ASMARC_SETUP_H */

arch/arc/include/asm/syscalls.h

@@ -17,6 +17,7 @@ int sys_clone_wrapper(int, int, int, int, int);
 int sys_cacheflush(uint32_t, uint32_t uint32_t);
 int sys_arc_settls(void *);
 int sys_arc_gettls(void);
+int sys_arc_usr_cmpxchg(int *, int, int);
 
 #include <asm-generic/syscalls.h>
 

arch/arc/include/uapi/asm/unistd.h

@@ -27,18 +27,19 @@
 
 #define NR_syscalls	__NR_syscalls
 
+/* Generic syscall (fs/filesystems.c - lost in asm-generic/unistd.h */
+#define __NR_sysfs		(__NR_arch_specific_syscall + 3)
+
 /* ARC specific syscall */
 #define __NR_cacheflush		(__NR_arch_specific_syscall + 0)
 #define __NR_arc_settls		(__NR_arch_specific_syscall + 1)
 #define __NR_arc_gettls		(__NR_arch_specific_syscall + 2)
+#define __NR_arc_usr_cmpxchg	(__NR_arch_specific_syscall + 4)
 
 __SYSCALL(__NR_cacheflush, sys_cacheflush)
 __SYSCALL(__NR_arc_settls, sys_arc_settls)
 __SYSCALL(__NR_arc_gettls, sys_arc_gettls)
-
-
-/* Generic syscall (fs/filesystems.c - lost in asm-generic/unistd.h */
-#define __NR_sysfs		(__NR_arch_specific_syscall + 3)
+__SYSCALL(__NR_arc_usr_cmpxchg, sys_arc_usr_cmpxchg)
 __SYSCALL(__NR_sysfs, sys_sysfs)
 
 #undef __SYSCALL

arch/arc/kernel/mcip.c

@@ -15,11 +15,12 @@
 #include <asm/mcip.h>
 #include <asm/setup.h>
 
-static char smp_cpuinfo_buf[128];
-static int idu_detected;
-
 static DEFINE_RAW_SPINLOCK(mcip_lock);
 
+#ifdef CONFIG_SMP
+
+static char smp_cpuinfo_buf[128];
+
 static void mcip_setup_per_cpu(int cpu)
 {
 	smp_ipi_irq_setup(cpu, IPI_IRQ);
@@ -86,21 +87,7 @@ static void mcip_ipi_clear(int irq)
 
 static void mcip_probe_n_setup(void)
 {
-	struct mcip_bcr {
-#ifdef CONFIG_CPU_BIG_ENDIAN
-		unsigned int pad3:8,
-			     idu:1, llm:1, num_cores:6,
-			     iocoh:1,  gfrc: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, gfrc:1, iocoh:1,
-			     num_cores:6, llm:1, idu:1,
-			     pad3:8;
-#endif
-	} mp;
+	struct mcip_bcr mp;
 
 	READ_BCR(ARC_REG_MCIP_BCR, mp);
 
@@ -114,7 +101,6 @@ static void mcip_probe_n_setup(void)
 		IS_AVAIL1(mp.gfrc, "GFRC"));
 
 	cpuinfo_arc700[0].extn.gfrc = mp.gfrc;
-	idu_detected = mp.idu;
 
 	if (mp.dbg) {
 		__mcip_cmd_data(CMD_DEBUG_SET_SELECT, 0, 0xf);
@@ -130,6 +116,8 @@ struct plat_smp_ops plat_smp_ops = {
 	.ipi_clear	= mcip_ipi_clear,
 };
 
+#endif
+
 /***************************************************************************
  * ARCv2 Interrupt Distribution Unit (IDU)
  *
@@ -295,8 +283,11 @@ idu_of_init(struct device_node *intc, struct device_node *parent)
 	/* Read IDU BCR to confirm nr_irqs */
 	int nr_irqs = of_irq_count(intc);
 	int i, irq;
+	struct mcip_bcr mp;
+
+	READ_BCR(ARC_REG_MCIP_BCR, mp);
 
-	if (!idu_detected)
+	if (!mp.idu)
 		panic("IDU not detected, but DeviceTree using it");
 
 	pr_info("MCIP: IDU referenced from Devicetree %d irqs\n", nr_irqs);

arch/arc/kernel/module.c

@@ -30,17 +30,9 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
 			      char *secstr, struct module *mod)
 {
 #ifdef CONFIG_ARC_DW2_UNWIND
-	int i;
-
 	mod->arch.unw_sec_idx = 0;
 	mod->arch.unw_info = NULL;
-
-	for (i = 1; i < hdr->e_shnum; i++) {
-		if (strcmp(secstr+sechdrs[i].sh_name, ".eh_frame") == 0) {
-			mod->arch.unw_sec_idx = i;
-			break;
-		}
-	}
+	mod->arch.secstr = secstr;
 #endif
 	return 0;
 }
@@ -59,29 +51,33 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 		       unsigned int relsec,	/* sec index for relo sec */
 		       struct module *module)
 {
-	int i, n;
+	int i, n, relo_type;
 	Elf32_Rela *rel_entry = (void *)sechdrs[relsec].sh_addr;
 	Elf32_Sym *sym_entry, *sym_sec;
-	Elf32_Addr relocation;
-	Elf32_Addr location;
-	Elf32_Addr sec_to_patch;
-	int relo_type;
-
-	sec_to_patch = sechdrs[sechdrs[relsec].sh_info].sh_addr;
+	Elf32_Addr relocation, location, tgt_addr;
+	unsigned int tgtsec;
+
+	/*
+	 * @relsec has relocations e.g. .rela.init.text
+	 * @tgtsec is section to patch e.g. .init.text
+	 */
+	tgtsec = sechdrs[relsec].sh_info;
+	tgt_addr = sechdrs[tgtsec].sh_addr;
 	sym_sec = (Elf32_Sym *) sechdrs[symindex].sh_addr;
 	n = sechdrs[relsec].sh_size / sizeof(*rel_entry);
 
-	pr_debug("\n========== Module Sym reloc ===========================\n");
-	pr_debug("Section to fixup %x\n", sec_to_patch);
+	pr_debug("\nSection to fixup %s @%x\n",
+		 module->arch.secstr + sechdrs[tgtsec].sh_name, tgt_addr);
 	pr_debug("=========================================================\n");
-	pr_debug("rela->r_off | rela->addend | sym->st_value | ADDR | VALUE\n");
+	pr_debug("r_off\tr_add\tst_value ADDRESS  VALUE\n");
 	pr_debug("=========================================================\n");
 
 	/* Loop thru entries in relocation section */
 	for (i = 0; i < n; i++) {
+		const char *s;
 
 		/* This is where to make the change */
-		location = sec_to_patch + rel_entry[i].r_offset;
+		location = tgt_addr + rel_entry[i].r_offset;
 
 		/* This is the symbol it is referring to.  Note that all
 		   undefined symbols have been resolved.  */
@@ -89,10 +85,15 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 
 		relocation = sym_entry->st_value + rel_entry[i].r_addend;
 
-		pr_debug("\t%x\t\t%x\t\t%x  %x %x [%s]\n",
-			rel_entry[i].r_offset, rel_entry[i].r_addend,
-			sym_entry->st_value, location, relocation,
-			strtab + sym_entry->st_name);
+		if (sym_entry->st_name == 0 && ELF_ST_TYPE (sym_entry->st_info) == STT_SECTION) {
+			s = module->arch.secstr + sechdrs[sym_entry->st_shndx].sh_name;
+		} else {
+			s = strtab + sym_entry->st_name;
+		}
+
+		pr_debug("   %x\t%x\t%x %x %x [%s]\n",
+			 rel_entry[i].r_offset, rel_entry[i].r_addend,
+			 sym_entry->st_value, location, relocation, s);
 
 		/* This assumes modules are built with -mlong-calls
 		 * so any branches/jumps are absolute 32 bit jmps
@@ -111,6 +112,10 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 			goto relo_err;
 
 	}
+
+	if (strcmp(module->arch.secstr+sechdrs[tgtsec].sh_name, ".eh_frame") == 0)
+		module->arch.unw_sec_idx = tgtsec;
+
 	return 0;
 
 relo_err:

arch/arc/kernel/process.c

@@ -41,6 +41,39 @@ SYSCALL_DEFINE0(arc_gettls)
 	return task_thread_info(current)->thr_ptr;
 }
 
+SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new)
+{
+	int uval;
+	int ret;
+
+	/*
+	 * This is only for old cores lacking LLOCK/SCOND, which by defintion
+	 * can't possibly be SMP. Thus doesn't need to be SMP safe.
+	 * And this also helps reduce the overhead for serializing in
+	 * the UP case
+	 */
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_SMP));
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+		return -EFAULT;
+
+	preempt_disable();
+
+	ret = __get_user(uval, uaddr);
+	if (ret)
+		goto done;
+
+	if (uval != expected)
+		ret = -EAGAIN;
+	else
+		ret = __put_user(new, uaddr);
+
+done:
+	preempt_enable();
+
+	return ret;
+}
+
 void arch_cpu_idle(void)
 {
 	/* sleep, but enable all interrupts before committing */

arch/arc/kernel/setup.c

@@ -40,6 +40,29 @@ struct task_struct *_current_task[NR_CPUS];	/* For stack switching */
 
 struct cpuinfo_arc cpuinfo_arc700[NR_CPUS];
 
+static const struct id_to_str arc_cpu_rel[] = {
+#ifdef CONFIG_ISA_ARCOMPACT
+	{ 0x34, "R4.10"},
+	{ 0x35, "R4.11"},
+#else
+	{ 0x51, "R2.0" },
+	{ 0x52, "R2.1" },
+	{ 0x53, "R3.0" },
+#endif
+	{ 0x00, NULL   }
+};
+
+static const struct id_to_str arc_cpu_nm[] = {
+#ifdef CONFIG_ISA_ARCOMPACT
+	{ 0x20, "ARC 600"   },
+	{ 0x30, "ARC 770"   },  /* 750 identified seperately */
+#else
+	{ 0x40, "ARC EM"  },
+	{ 0x50, "ARC HS38"  },
+#endif
+	{ 0x00, "Unknown"   }
+};
+
 static void read_decode_ccm_bcr(struct cpuinfo_arc *cpu)
 {
 	if (is_isa_arcompact()) {
@@ -92,11 +115,26 @@ static void read_arc_build_cfg_regs(void)
 	struct bcr_timer timer;
 	struct bcr_generic bcr;
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
+	const struct id_to_str *tbl;
+
 	FIX_PTR(cpu);
 
 	READ_BCR(AUX_IDENTITY, cpu->core);
 	READ_BCR(ARC_REG_ISA_CFG_BCR, cpu->isa);
 
+	for (tbl = &arc_cpu_rel[0]; tbl->id != 0; tbl++) {
+		if (cpu->core.family == tbl->id) {
+			cpu->details = tbl->str;
+			break;
+		}
+	}
+
+	for (tbl = &arc_cpu_nm[0]; tbl->id != 0; tbl++) {
+		if ((cpu->core.family & 0xF0) == tbl->id)
+			break;
+	}
+	cpu->name = tbl->str;
+
 	READ_BCR(ARC_REG_TIMERS_BCR, timer);
 	cpu->extn.timer0 = timer.t0;
 	cpu->extn.timer1 = timer.t1;
@@ -111,6 +149,9 @@ static void read_arc_build_cfg_regs(void)
 	cpu->extn.swap = read_aux_reg(ARC_REG_SWAP_BCR) ? 1 : 0;        /* 1,3 */
 	cpu->extn.crc = read_aux_reg(ARC_REG_CRC_BCR) ? 1 : 0;
 	cpu->extn.minmax = read_aux_reg(ARC_REG_MIXMAX_BCR) > 1 ? 1 : 0; /* 2 */
+	cpu->extn.swape = (cpu->core.family >= 0x34) ? 1 :
+				IS_ENABLED(CONFIG_ARC_HAS_SWAPE);
+
 	READ_BCR(ARC_REG_XY_MEM_BCR, cpu->extn_xymem);
 
 	/* Read CCM BCRs for boot reporting even if not enabled in Kconfig */
@@ -160,64 +201,38 @@ static void read_arc_build_cfg_regs(void)
 	cpu->extn.rtt = bcr.ver ? 1 : 0;
 
 	cpu->extn.debug = cpu->extn.ap | cpu->extn.smart | cpu->extn.rtt;
-}
 
-static const struct cpuinfo_data arc_cpu_tbl[] = {
-#ifdef CONFIG_ISA_ARCOMPACT
-	{ {0x20, "ARC 600"      }, 0x2F},
-	{ {0x30, "ARC 700"      }, 0x33},
-	{ {0x34, "ARC 700 R4.10"}, 0x34},
-	{ {0x35, "ARC 700 R4.11"}, 0x35},
-#else
-	{ {0x50, "ARC HS38 R2.0"}, 0x51},
-	{ {0x52, "ARC HS38 R2.1"}, 0x52},
-	{ {0x53, "ARC HS38 R3.0"}, 0x53},
-#endif
-	{ {0x00, NULL		} }
-};
+	/* some hacks for lack of feature BCR info in old ARC700 cores */
+	if (is_isa_arcompact()) {
+		if (!cpu->isa.ver)	/* ISA BCR absent, use Kconfig info */
+			cpu->isa.atomic = IS_ENABLED(CONFIG_ARC_HAS_LLSC);
+		else
+			cpu->isa.atomic = cpu->isa.atomic1;
 
+		cpu->isa.be = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN);
+
+		 /* there's no direct way to distinguish 750 vs. 770 */
+		if (unlikely(cpu->core.family < 0x34 || cpu->mmu.ver < 3))
+			cpu->name = "ARC750";
+	}
+}
 
 static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 {
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[cpu_id];
 	struct bcr_identity *core = &cpu->core;
-	const struct cpuinfo_data *tbl;
-	char *isa_nm;
-	int i, be, atomic;
-	int n = 0;
+	int i, n = 0;
 
 	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,
 		       "\nIDENTITY\t: ARCVER [%#02x] ARCNUM [%#02x] CHIPID [%#4x]\n",
 		       core->family, core->cpu_id, core->chip_id);
 
-	for (tbl = &arc_cpu_tbl[0]; tbl->info.id != 0; tbl++) {
-		if ((core->family >= tbl->info.id) &&
-		    (core->family <= tbl->up_range)) {
-			n += scnprintf(buf + n, len - n,
-				       "processor [%d]\t: %s (%s ISA) %s\n",
-				       cpu_id, tbl->info.str, isa_nm,
-				       IS_AVAIL1(be, "[Big-Endian]"));
-			break;
-		}
-	}
-
-	if (tbl->info.id == 0)
-		n += scnprintf(buf + n, len - n, "UNKNOWN ARC Processor\n");
+	n += scnprintf(buf + n, len - n, "processor [%d]\t: %s %s (%s ISA) %s\n",
+		       cpu_id, cpu->name, cpu->details,
+		       is_isa_arcompact() ? "ARCompact" : "ARCv2",
+		       IS_AVAIL1(cpu->isa.be, "[Big-Endian]"));
 
 	n += scnprintf(buf + n, len - n, "Timers\t\t: %s%s%s%s\nISA Extn\t: ",
 		       IS_AVAIL1(cpu->extn.timer0, "Timer0 "),
@@ -226,7 +241,7 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 				 CONFIG_ARC_HAS_RTC));
 
 	n += i = scnprintf(buf + n, len - n, "%s%s%s%s%s",
-			   IS_AVAIL2(atomic, "atomic ", CONFIG_ARC_HAS_LLSC),
+			   IS_AVAIL2(cpu->isa.atomic, "atomic ", CONFIG_ARC_HAS_LLSC),
 			   IS_AVAIL2(cpu->isa.ldd, "ll64 ", CONFIG_ARC_HAS_LL64),
 			   IS_AVAIL1(cpu->isa.unalign, "unalign (not used)"));
 
@@ -253,7 +268,7 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 		       IS_AVAIL1(cpu->extn.swap, "swap "),
 		       IS_AVAIL1(cpu->extn.minmax, "minmax "),
 		       IS_AVAIL1(cpu->extn.crc, "crc "),
-		       IS_AVAIL2(1, "swape", CONFIG_ARC_HAS_SWAPE));
+		       IS_AVAIL2(cpu->extn.swape, "swape", CONFIG_ARC_HAS_SWAPE));
 
 	if (cpu->bpu.ver)
 		n += scnprintf(buf + n, len - n,
@@ -272,9 +287,7 @@ static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len)
 
 	FIX_PTR(cpu);
 
-	n += scnprintf(buf + n, len - n,
-		       "Vector Table\t: %#x\nPeripherals\t: %#lx:%#lx\n",
-		       cpu->vec_base, perip_base, perip_end);
+	n += scnprintf(buf + n, len - n, "Vector Table\t: %#x\n", cpu->vec_base);
 
 	if (cpu->extn.fpu_sp || cpu->extn.fpu_dp)
 		n += scnprintf(buf + n, len - n, "FPU\t\t: %s%s\n",
@@ -507,7 +520,7 @@ static void *c_start(struct seq_file *m, loff_t *pos)
 	 * way to pass it w/o having to kmalloc/free a 2 byte string.
 	 * Encode cpu-id as 0xFFcccc, which is decoded by show routine.
 	 */
-	return *pos < num_possible_cpus() ? cpu_to_ptr(*pos) : NULL;
+	return *pos < nr_cpu_ids ? cpu_to_ptr(*pos) : NULL;
 }
 
 static void *c_next(struct seq_file *m, void *v, loff_t *pos)

arch/arc/kernel/troubleshoot.c

@@ -237,113 +237,3 @@ void show_kernel_fault_diag(const char *str, struct pt_regs *regs,
 	if (!user_mode(regs))
 		show_stacktrace(current, regs);
 }
-
-#ifdef CONFIG_DEBUG_FS
-
-#include <linux/module.h>
-#include <linux/fs.h>
-#include <linux/mount.h>
-#include <linux/pagemap.h>
-#include <linux/init.h>
-#include <linux/namei.h>
-#include <linux/debugfs.h>
-
-static struct dentry *test_dentry;
-static struct dentry *test_dir;
-static struct dentry *test_u32_dentry;
-
-static u32 clr_on_read = 1;
-
-#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
-u32 numitlb, numdtlb, num_pte_not_present;
-
-static int fill_display_data(char *kbuf)
-{
-	size_t num = 0;
-	num += sprintf(kbuf + num, "I-TLB Miss %x\n", numitlb);
-	num += sprintf(kbuf + num, "D-TLB Miss %x\n", numdtlb);
-	num += sprintf(kbuf + num, "PTE not present %x\n", num_pte_not_present);
-
-	if (clr_on_read)
-		numitlb = numdtlb = num_pte_not_present = 0;
-
-	return num;
-}
-
-static int tlb_stats_open(struct inode *inode, struct file *file)
-{
-	file->private_data = (void *)__get_free_page(GFP_KERNEL);
-	return 0;
-}
-
-/* called on user read(): display the counters */
-static ssize_t tlb_stats_output(struct file *file,	/* file descriptor */
-				char __user *user_buf,	/* user buffer */
-				size_t len,		/* length of buffer */
-				loff_t *offset)		/* offset in the file */
-{
-	size_t num;
-	char *kbuf = (char *)file->private_data;
-
-	/* All of the data can he shoved in one iteration */
-	if (*offset != 0)
-		return 0;
-
-	num = fill_display_data(kbuf);
-
-	/* simple_read_from_buffer() is helper for copy to user space
-	   It copies up to @2 (num) bytes from kernel buffer @4 (kbuf) at offset
-	   @3 (offset) into the user space address starting at @1 (user_buf).
-	   @5 (len) is max size of user buffer
-	 */
-	return simple_read_from_buffer(user_buf, num, offset, kbuf, len);
-}
-
-/* called on user write : clears the counters */
-static ssize_t tlb_stats_clear(struct file *file, const char __user *user_buf,
-			       size_t length, loff_t *offset)
-{
-	numitlb = numdtlb = num_pte_not_present = 0;
-	return length;
-}
-
-static int tlb_stats_close(struct inode *inode, struct file *file)
-{
-	free_page((unsigned long)(file->private_data));
-	return 0;
-}
-
-static const struct file_operations tlb_stats_file_ops = {
-	.read = tlb_stats_output,
-	.write = tlb_stats_clear,
-	.open = tlb_stats_open,
-	.release = tlb_stats_close
-};
-#endif
-
-static int __init arc_debugfs_init(void)
-{
-	test_dir = debugfs_create_dir("arc", NULL);
-
-#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
-	test_dentry = debugfs_create_file("tlb_stats", 0444, test_dir, NULL,
-					  &tlb_stats_file_ops);
-#endif
-
-	test_u32_dentry =
-	    debugfs_create_u32("clr_on_read", 0444, test_dir, &clr_on_read);
-
-	return 0;
-}
-
-module_init(arc_debugfs_init);
-
-static void __exit arc_debugfs_exit(void)
-{
-	debugfs_remove(test_u32_dentry);
-	debugfs_remove(test_dentry);
-	debugfs_remove(test_dir);
-}
-module_exit(arc_debugfs_exit);
-
-#endif

arch/arc/mm/cache.c

@@ -22,8 +22,8 @@
 #include <asm/setup.h>
 
 static int l2_line_sz;
-int ioc_exists;
-volatile int slc_enable = 1, ioc_enable = 1;
+static int ioc_exists;
+int slc_enable = 1, ioc_enable = 1;
 unsigned long perip_base = ARC_UNCACHED_ADDR_SPACE; /* legacy value for boot */
 unsigned long perip_end = 0xFFFFFFFF; /* legacy value */
 
@@ -53,18 +53,15 @@ char *arc_cache_mumbojumbo(int c, char *buf, int len)
 	PR_CACHE(&cpuinfo_arc700[c].icache, CONFIG_ARC_HAS_ICACHE, "I-Cache");
 	PR_CACHE(&cpuinfo_arc700[c].dcache, CONFIG_ARC_HAS_DCACHE, "D-Cache");
 
-	if (!is_isa_arcv2())
-                return buf;
-
 	p = &cpuinfo_arc700[c].slc;
 	if (p->ver)
 		n += scnprintf(buf + n, len - n,
 			       "SLC\t\t: %uK, %uB Line%s\n",
 			       p->sz_k, p->line_len, IS_USED_RUN(slc_enable));
 
-	if (ioc_exists)
-		n += scnprintf(buf + n, len - n, "IOC\t\t:%s\n",
-				IS_DISABLED_RUN(ioc_enable));
+	n += scnprintf(buf + n, len - n, "Peripherals\t: %#lx%s%s\n",
+		       perip_base,
+		       IS_AVAIL3(ioc_exists, ioc_enable, ", IO-Coherency "));
 
 	return buf;
 }
@@ -113,8 +110,10 @@ static void read_decode_cache_bcr_arcv2(int cpu)
 	}
 
 	READ_BCR(ARC_REG_CLUSTER_BCR, cbcr);
-	if (cbcr.c && ioc_enable)
+	if (cbcr.c)
 		ioc_exists = 1;
+	else
+		ioc_enable = 0;
 
 	/* HS 2.0 didn't have AUX_VOL */
 	if (cpuinfo_arc700[cpu].core.family > 0x51) {
@@ -1002,7 +1001,7 @@ void arc_cache_init(void)
 			read_aux_reg(ARC_REG_SLC_CTRL) | SLC_CTRL_DISABLE);
 	}
 
-	if (is_isa_arcv2() && ioc_exists) {
+	if (is_isa_arcv2() && ioc_enable) {
 		/* IO coherency base - 0x8z */
 		write_aux_reg(ARC_REG_IO_COH_AP0_BASE, 0x80000);
 		/* IO coherency aperture size - 512Mb: 0x8z-0xAz */

arch/arc/mm/dma.c

@@ -45,7 +45,7 @@ static void *arc_dma_alloc(struct device *dev, size_t size,
 	 *   -For coherent data, Read/Write to buffers terminate early in cache
 	 *   (vs. always going to memory - thus are faster)
 	 */
-	if ((is_isa_arcv2() && ioc_exists) ||
+	if ((is_isa_arcv2() && ioc_enable) ||
 	    (attrs & DMA_ATTR_NON_CONSISTENT))
 		need_coh = 0;
 
@@ -97,7 +97,7 @@ static void arc_dma_free(struct device *dev, size_t size, void *vaddr,
 	int is_non_coh = 1;
 
 	is_non_coh = (attrs & DMA_ATTR_NON_CONSISTENT) ||
-			(is_isa_arcv2() && ioc_exists);
+			(is_isa_arcv2() && ioc_enable);
 
 	if (PageHighMem(page) || !is_non_coh)
 		iounmap((void __force __iomem *)vaddr);

arch/arc/mm/tlb.c

@@ -793,16 +793,16 @@ char *arc_mmu_mumbojumbo(int cpu_id, char *buf, int len)
 	char super_pg[64] = "";
 
 	if (p_mmu->s_pg_sz_m)
-		scnprintf(super_pg, 64, "%dM Super Page%s, ",
+		scnprintf(super_pg, 64, "%dM Super Page %s",
 			  p_mmu->s_pg_sz_m,
 			  IS_USED_CFG(CONFIG_TRANSPARENT_HUGEPAGE));
 
 	n += scnprintf(buf + n, len - n,
-		      "MMU [v%x]\t: %dk PAGE, %sJTLB %d (%dx%d), uDTLB %d, uITLB %d %s%s\n",
+		      "MMU [v%x]\t: %dk PAGE, %sJTLB %d (%dx%d), uDTLB %d, uITLB %d%s%s\n",
 		       p_mmu->ver, p_mmu->pg_sz_k, super_pg,
 		       p_mmu->sets * p_mmu->ways, p_mmu->sets, p_mmu->ways,
 		       p_mmu->u_dtlb, p_mmu->u_itlb,
-		       IS_AVAIL2(p_mmu->pae, "PAE40 ", CONFIG_ARC_HAS_PAE40));
+		       IS_AVAIL2(p_mmu->pae, ", PAE40 ", CONFIG_ARC_HAS_PAE40));
 
 	return buf;
 }

arch/arc/mm/tlbex.S

@@ -237,15 +237,6 @@ ex_saved_reg1:
 
 2:
 
-#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
-	and.f 0, r0, _PAGE_PRESENT
-	bz   1f
-	ld   r3, [num_pte_not_present]
-	add  r3, r3, 1
-	st   r3, [num_pte_not_present]
-1:
-#endif
-
 .endm
 
 ;-----------------------------------------------------------------
@@ -309,12 +300,6 @@ ENTRY(EV_TLBMissI)
 
 	TLBMISS_FREEUP_REGS
 
-#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
-	ld  r0, [@numitlb]
-	add r0, r0, 1
-	st  r0, [@numitlb]
-#endif
-
 	;----------------------------------------------------------------
 	; Get the PTE corresponding to V-addr accessed, r2 is setup with EFA
 	LOAD_FAULT_PTE
@@ -349,12 +334,6 @@ ENTRY(EV_TLBMissD)
 
 	TLBMISS_FREEUP_REGS
 
-#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
-	ld  r0, [@numdtlb]
-	add r0, r0, 1
-	st  r0, [@numdtlb]
-#endif
-
 	;----------------------------------------------------------------
 	; Get the PTE corresponding to V-addr accessed
 	; If PTE exists, it will setup, r0 = PTE, r1 = Ptr to PTE, r2 = EFA

arch/arm/boot/dts/ste-snowball.dts

@@ -239,14 +239,25 @@
 			arm,primecell-periphid = <0x10480180>;
 			max-frequency = <100000000>;
 			bus-width = <4>;
+			cap-sd-highspeed;
 			cap-mmc-highspeed;
+			sd-uhs-sdr12;
+			sd-uhs-sdr25;
+			/* All direction control is used */
+			st,sig-dir-cmd;
+			st,sig-dir-dat0;
+			st,sig-dir-dat2;
+			st,sig-dir-dat31;
+			st,sig-pin-fbclk;
+			full-pwr-cycle;
 			vmmc-supply = <&ab8500_ldo_aux3_reg>;
 			vqmmc-supply = <&vmmci>;
 			pinctrl-names = "default", "sleep";
 			pinctrl-0 = <&sdi0_default_mode>;
 			pinctrl-1 = <&sdi0_sleep_mode>;
 
-			cd-gpios  = <&gpio6 26 GPIO_ACTIVE_LOW>; // 218
+			/* GPIO218 MMC_CD */
+			cd-gpios  = <&gpio6 26 GPIO_ACTIVE_LOW>;
 
 			status = "okay";
 		};
@@ -549,7 +560,7 @@
 					/* VMMCI level-shifter enable */
 					snowball_cfg3 {
 						pins = "GPIO217_AH12";
-						ste,config = <&gpio_out_lo>;
+						ste,config = <&gpio_out_hi>;
 					};
 					/* VMMCI level-shifter voltage select */
 					snowball_cfg4 {

arch/arm/boot/dts/uniphier-pro5.dtsi

@@ -184,11 +184,11 @@
 };
 
 &mio_clk {
-	compatible = "socionext,uniphier-pro5-mio-clock";
+	compatible = "socionext,uniphier-pro5-sd-clock";
 };
 
 &mio_rst {
-	compatible = "socionext,uniphier-pro5-mio-reset";
+	compatible = "socionext,uniphier-pro5-sd-reset";
 };
 
 &peri_clk {

arch/arm/boot/dts/uniphier-pxs2.dtsi

@@ -197,11 +197,11 @@
 };
 
 &mio_clk {
-	compatible = "socionext,uniphier-pxs2-mio-clock";
+	compatible = "socionext,uniphier-pxs2-sd-clock";
 };
 
 &mio_rst {
-	compatible = "socionext,uniphier-pxs2-mio-reset";
+	compatible = "socionext,uniphier-pxs2-sd-reset";
 };
 
 &peri_clk {

arch/arm/boot/dts/vf500.dtsi

@@ -70,7 +70,7 @@
 			global_timer: timer@40002200 {
 				compatible = "arm,cortex-a9-global-timer";
 				reg = <0x40002200 0x20>;
-				interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>;
 				interrupt-parent = <&intc>;
 				clocks = <&clks VF610_CLK_PLATFORM_BUS>;
 			};

arch/arm/configs/multi_v7_defconfig

@@ -850,6 +850,7 @@ CONFIG_PWM_SUN4I=y
 CONFIG_PWM_TEGRA=y
 CONFIG_PWM_VT8500=y
 CONFIG_PHY_HIX5HD2_SATA=y
+CONFIG_E1000E=y
 CONFIG_PWM_STI=y
 CONFIG_PWM_BCM2835=y
 CONFIG_PWM_BRCMSTB=m

arch/arm/kvm/arm.c

@@ -1312,6 +1312,13 @@ static int init_hyp_mode(void)
 		goto out_err;
 	}
 
+	err = create_hyp_mappings(kvm_ksym_ref(__bss_start),
+				  kvm_ksym_ref(__bss_stop), PAGE_HYP_RO);
+	if (err) {
+		kvm_err("Cannot map bss section\n");
+		goto out_err;
+	}
+
 	/*
 	 * Map the Hyp stack pages
 	 */

arch/arm/mach-imx/gpc.c

@@ -408,7 +408,7 @@ static struct genpd_onecell_data imx_gpc_onecell_data = {
 static int imx_gpc_genpd_init(struct device *dev, struct regulator *pu_reg)
 {
 	struct clk *clk;
-	int i;
+	int i, ret;
 
 	imx6q_pu_domain.reg = pu_reg;
 
@@ -430,13 +430,22 @@ static int imx_gpc_genpd_init(struct device *dev, struct regulator *pu_reg)
 	if (!IS_ENABLED(CONFIG_PM_GENERIC_DOMAINS))
 		return 0;
 
-	pm_genpd_init(&imx6q_pu_domain.base, NULL, false);
-	return of_genpd_add_provider_onecell(dev->of_node,
+	for (i = 0; i < ARRAY_SIZE(imx_gpc_domains); i++)
+		pm_genpd_init(imx_gpc_domains[i], NULL, false);
+
+	ret =  of_genpd_add_provider_onecell(dev->of_node,
 					     &imx_gpc_onecell_data);
+	if (ret)
+		goto power_off;
+
+	return 0;
 
+power_off:
+	imx6q_pm_pu_power_off(&imx6q_pu_domain.base);
 clk_err:
 	while (i--)
 		clk_put(imx6q_pu_domain.clk[i]);
+	imx6q_pu_domain.reg = NULL;
 	return -EINVAL;
 }
 

arch/arm/mach-imx/mach-imx6q.c

@@ -173,7 +173,7 @@ static void __init imx6q_enet_phy_init(void)
 				ksz9021rn_phy_fixup);
 		phy_register_fixup_for_uid(PHY_ID_KSZ9031, MICREL_PHY_ID_MASK,
 				ksz9031rn_phy_fixup);
-		phy_register_fixup_for_uid(PHY_ID_AR8031, 0xffffffff,
+		phy_register_fixup_for_uid(PHY_ID_AR8031, 0xffffffef,
 				ar8031_phy_fixup);
 		phy_register_fixup_for_uid(PHY_ID_AR8035, 0xffffffef,
 				ar8035_phy_fixup);

arch/arm/mach-mvebu/Kconfig

@@ -23,6 +23,7 @@ config MACH_MVEBU_V7
 	select CACHE_L2X0
 	select ARM_CPU_SUSPEND
 	select MACH_MVEBU_ANY
+	select MVEBU_CLK_COREDIV
 
 config MACH_ARMADA_370
 	bool "Marvell Armada 370 boards"
@@ -32,7 +33,6 @@ config MACH_ARMADA_370
 	select CPU_PJ4B
 	select MACH_MVEBU_V7
 	select PINCTRL_ARMADA_370
-	select MVEBU_CLK_COREDIV
 	help
 	  Say 'Y' here if you want your kernel to support boards based
 	  on the Marvell Armada 370 SoC with device tree.
@@ -50,7 +50,6 @@ config MACH_ARMADA_375
 	select HAVE_SMP
 	select MACH_MVEBU_V7
 	select PINCTRL_ARMADA_375
-	select MVEBU_CLK_COREDIV
 	help
 	  Say 'Y' here if you want your kernel to support boards based
 	  on the Marvell Armada 375 SoC with device tree.
@@ -68,7 +67,6 @@ config MACH_ARMADA_38X
 	select HAVE_SMP
 	select MACH_MVEBU_V7
 	select PINCTRL_ARMADA_38X
-	select MVEBU_CLK_COREDIV
 	help
 	  Say 'Y' here if you want your kernel to support boards based
 	  on the Marvell Armada 380/385 SoC with device tree.

arch/arm/mach-uniphier/Kconfig

 config ARCH_UNIPHIER
 	bool "Socionext UniPhier SoCs"
 	depends on ARCH_MULTI_V7
+	select ARCH_HAS_RESET_CONTROLLER
 	select ARM_AMBA
 	select ARM_GLOBAL_TIMER
 	select ARM_GIC

arch/arm64/Kconfig

@@ -915,7 +915,7 @@ config RANDOMIZE_BASE
 
 config RANDOMIZE_MODULE_REGION_FULL
 	bool "Randomize the module region independently from the core kernel"
-	depends on RANDOMIZE_BASE
+	depends on RANDOMIZE_BASE && !DYNAMIC_FTRACE
 	default y
 	help
 	  Randomizes the location of the module region without considering the

arch/arm64/Kconfig.platforms

@@ -190,6 +190,7 @@ config ARCH_THUNDER
 
 config ARCH_UNIPHIER
 	bool "Socionext UniPhier SoC Family"
+	select ARCH_HAS_RESET_CONTROLLER
 	select PINCTRL
 	help
 	  This enables support for Socionext UniPhier SoC family.

arch/arm64/Makefile

@@ -15,7 +15,7 @@ CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET)
 GZFLAGS		:=-9
 
 ifneq ($(CONFIG_RELOCATABLE),)
-LDFLAGS_vmlinux		+= -pie -Bsymbolic
+LDFLAGS_vmlinux		+= -pie -shared -Bsymbolic
 endif
 
 ifeq ($(CONFIG_ARM64_ERRATUM_843419),y)

arch/arm64/boot/dts/broadcom/ns2-svk.dts

@@ -164,6 +164,8 @@
 		nand-ecc-mode = "hw";
 		nand-ecc-strength = <8>;
 		nand-ecc-step-size = <512>;
+		nand-bus-width = <16>;
+		brcm,nand-oob-sector-size = <16>;
 		#address-cells = <1>;
 		#size-cells = <1>;
 	};

arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi

@@ -123,6 +123,7 @@
 			     <1 14 0xf08>, /* Physical Non-Secure PPI */
 			     <1 11 0xf08>, /* Virtual PPI */
 			     <1 10 0xf08>; /* Hypervisor PPI */
+		fsl,erratum-a008585;
 	};
 
 	pmu {

arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi

@@ -195,6 +195,7 @@
 			     <1 14 4>, /* Physical Non-Secure PPI, active-low */
 			     <1 11 4>, /* Virtual PPI, active-low */
 			     <1 10 4>; /* Hypervisor PPI, active-low */
+		fsl,erratum-a008585;
 	};
 
 	pmu {

arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi

@@ -131,7 +131,7 @@
 				#address-cells = <0x1>;
 				#size-cells = <0x0>;
 				cell-index = <1>;
-				clocks = <&cpm_syscon0 0 3>;
+				clocks = <&cpm_syscon0 1 21>;
 				status = "disabled";
 			};
 

arch/arm64/boot/dts/rockchip/rk3368-geekbox.dts

@@ -116,7 +116,6 @@
 	cap-mmc-highspeed;
 	clock-frequency = <150000000>;
 	disable-wp;
-	keep-power-in-suspend;
 	non-removable;
 	num-slots = <1>;
 	vmmc-supply = <&vcc_io>;
@@ -258,8 +257,6 @@
 			};
 
 			vcc_sd: SWITCH_REG1 {
-				regulator-always-on;
-				regulator-boot-on;
 				regulator-name = "vcc_sd";
 			};
 

arch/arm64/boot/dts/rockchip/rk3368-orion-r68-meta.dts

@@ -152,8 +152,6 @@
 		gpio = <&gpio3 11 GPIO_ACTIVE_LOW>;
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <3300000>;
-		regulator-always-on;
-		regulator-boot-on;
 		vin-supply = <&vcc_io>;
 	};
 
@@ -201,7 +199,6 @@
 	bus-width = <8>;
 	cap-mmc-highspeed;
 	disable-wp;
-	keep-power-in-suspend;
 	mmc-pwrseq = <&emmc_pwrseq>;
 	mmc-hs200-1_2v;
 	mmc-hs200-1_8v;
@@ -350,7 +347,6 @@
 	clock-freq-min-max = <400000 50000000>;
 	cap-sd-highspeed;
 	card-detect-delay = <200>;
-	keep-power-in-suspend;
 	num-slots = <1>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_cd &sdmmc_bus4>;

arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi

@@ -257,18 +257,18 @@
 			reg = <0x59801000 0x400>;
 		};
 
-		mioctrl@59810000 {
-			compatible = "socionext,uniphier-mioctrl",
+		sdctrl@59810000 {
+			compatible = "socionext,uniphier-ld20-sdctrl",
 				     "simple-mfd", "syscon";
 			reg = <0x59810000 0x800>;
 
-			mio_clk: clock {
-				compatible = "socionext,uniphier-ld20-mio-clock";
+			sd_clk: clock {
+				compatible = "socionext,uniphier-ld20-sd-clock";
 				#clock-cells = <1>;
 			};
 
-			mio_rst: reset {
-				compatible = "socionext,uniphier-ld20-mio-reset";
+			sd_rst: reset {
+				compatible = "socionext,uniphier-ld20-sd-reset";
 				#reset-cells = <1>;
 			};
 		};

arch/arm64/include/asm/cpufeature.h

@@ -94,7 +94,7 @@ struct arm64_cpu_capabilities {
 	u16 capability;
 	int def_scope;			/* default scope */
 	bool (*matches)(const struct arm64_cpu_capabilities *caps, int scope);
-	void (*enable)(void *);		/* Called on all active CPUs */
+	int (*enable)(void *);		/* Called on all active CPUs */
 	union {
 		struct {	/* To be used for erratum handling only */
 			u32 midr_model;

arch/arm64/include/asm/exec.h

@@ -18,6 +18,9 @@
 #ifndef __ASM_EXEC_H
 #define __ASM_EXEC_H
 
+#include <linux/sched.h>
+
 extern unsigned long arch_align_stack(unsigned long sp);
+void uao_thread_switch(struct task_struct *next);
 
 #endif	/* __ASM_EXEC_H */

arch/arm64/include/asm/kvm_emulate.h

@@ -178,11 +178,6 @@ static inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu)
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_ISV);
 }
 
-static inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
-{
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR);
-}
-
 static inline bool kvm_vcpu_dabt_issext(const struct kvm_vcpu *vcpu)
 {
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SSE);
@@ -203,6 +198,12 @@ static inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu)
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_S1PTW);
 }
 
+static inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
+{
+	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR) ||
+		kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */
+}
+
 static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu)
 {
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_CM);

arch/arm64/include/asm/memory.h

@@ -217,7 +217,7 @@ static inline void *phys_to_virt(phys_addr_t x)
 #define _virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
 #else
 #define __virt_to_pgoff(kaddr)	(((u64)(kaddr) & ~PAGE_OFFSET) / PAGE_SIZE * sizeof(struct page))
-#define __page_to_voff(kaddr)	(((u64)(page) & ~VMEMMAP_START) * PAGE_SIZE / sizeof(struct page))
+#define __page_to_voff(page)	(((u64)(page) & ~VMEMMAP_START) * PAGE_SIZE / sizeof(struct page))
 
 #define page_to_virt(page)	((void *)((__page_to_voff(page)) | PAGE_OFFSET))
 #define virt_to_page(vaddr)	((struct page *)((__virt_to_pgoff(vaddr)) | VMEMMAP_START))

arch/arm64/include/asm/module.h

@@ -17,6 +17,7 @@
 #define __ASM_MODULE_H
 
 #include <asm-generic/module.h>
+#include <asm/memory.h>
 
 #define MODULE_ARCH_VERMAGIC	"aarch64"
 
@@ -32,6 +33,10 @@ u64 module_emit_plt_entry(struct module *mod, const Elf64_Rela *rela,
 			  Elf64_Sym *sym);
 
 #ifdef CONFIG_RANDOMIZE_BASE
+#ifdef CONFIG_MODVERSIONS
+#define ARCH_RELOCATES_KCRCTAB
+#define reloc_start 		(kimage_vaddr - KIMAGE_VADDR)
+#endif
 extern u64 module_alloc_base;
 #else
 #define module_alloc_base	((u64)_etext - MODULES_VSIZE)

arch/arm64/include/asm/percpu.h

@@ -44,48 +44,44 @@ static inline unsigned long __percpu_##op(void *ptr,			\
 									\
 	switch (size) {							\
 	case 1:								\
-		do {							\
-			asm ("//__per_cpu_" #op "_1\n"			\
-			"ldxrb	  %w[ret], %[ptr]\n"			\
+		asm ("//__per_cpu_" #op "_1\n"				\
+		"1:	ldxrb	  %w[ret], %[ptr]\n"			\
 			#asm_op " %w[ret], %w[ret], %w[val]\n"		\
-			"stxrb	  %w[loop], %w[ret], %[ptr]\n"		\
-			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
-			  [ptr] "+Q"(*(u8 *)ptr)			\
-			: [val] "Ir" (val));				\
-		} while (loop);						\
+		"	stxrb	  %w[loop], %w[ret], %[ptr]\n"		\
+		"	cbnz	  %w[loop], 1b"				\
+		: [loop] "=&r" (loop), [ret] "=&r" (ret),		\
+		  [ptr] "+Q"(*(u8 *)ptr)				\
+		: [val] "Ir" (val));					\
 		break;							\
 	case 2:								\
-		do {							\
-			asm ("//__per_cpu_" #op "_2\n"			\
-			"ldxrh	  %w[ret], %[ptr]\n"			\
+		asm ("//__per_cpu_" #op "_2\n"				\
+		"1:	ldxrh	  %w[ret], %[ptr]\n"			\
 			#asm_op " %w[ret], %w[ret], %w[val]\n"		\
-			"stxrh	  %w[loop], %w[ret], %[ptr]\n"		\
-			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
-			  [ptr]  "+Q"(*(u16 *)ptr)			\
-			: [val] "Ir" (val));				\
-		} while (loop);						\
+		"	stxrh	  %w[loop], %w[ret], %[ptr]\n"		\
+		"	cbnz	  %w[loop], 1b"				\
+		: [loop] "=&r" (loop), [ret] "=&r" (ret),		\
+		  [ptr]  "+Q"(*(u16 *)ptr)				\
+		: [val] "Ir" (val));					\
 		break;							\
 	case 4:								\
-		do {							\
-			asm ("//__per_cpu_" #op "_4\n"			\
-			"ldxr	  %w[ret], %[ptr]\n"			\
+		asm ("//__per_cpu_" #op "_4\n"				\
+		"1:	ldxr	  %w[ret], %[ptr]\n"			\
 			#asm_op " %w[ret], %w[ret], %w[val]\n"		\
-			"stxr	  %w[loop], %w[ret], %[ptr]\n"		\
-			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
-			  [ptr] "+Q"(*(u32 *)ptr)			\
-			: [val] "Ir" (val));				\
-		} while (loop);						\
+		"	stxr	  %w[loop], %w[ret], %[ptr]\n"		\
+		"	cbnz	  %w[loop], 1b"				\
+		: [loop] "=&r" (loop), [ret] "=&r" (ret),		\
+		  [ptr] "+Q"(*(u32 *)ptr)				\
+		: [val] "Ir" (val));					\
 		break;							\
 	case 8:								\
-		do {							\
-			asm ("//__per_cpu_" #op "_8\n"			\
-			"ldxr	  %[ret], %[ptr]\n"			\
+		asm ("//__per_cpu_" #op "_8\n"				\
+		"1:	ldxr	  %[ret], %[ptr]\n"			\
 			#asm_op " %[ret], %[ret], %[val]\n"		\
-			"stxr	  %w[loop], %[ret], %[ptr]\n"		\
-			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
-			  [ptr] "+Q"(*(u64 *)ptr)			\
-			: [val] "Ir" (val));				\
-		} while (loop);						\
+		"	stxr	  %w[loop], %[ret], %[ptr]\n"		\
+		"	cbnz	  %w[loop], 1b"				\
+		: [loop] "=&r" (loop), [ret] "=&r" (ret),		\
+		  [ptr] "+Q"(*(u64 *)ptr)				\
+		: [val] "Ir" (val));					\
 		break;							\
 	default:							\
 		BUILD_BUG();						\
@@ -150,44 +146,40 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
 
 	switch (size) {
 	case 1:
-		do {
-			asm ("//__percpu_xchg_1\n"
-			"ldxrb %w[ret], %[ptr]\n"
-			"stxrb %w[loop], %w[val], %[ptr]\n"
-			: [loop] "=&r"(loop), [ret] "=&r"(ret),
-			  [ptr] "+Q"(*(u8 *)ptr)
-			: [val] "r" (val));
-		} while (loop);
+		asm ("//__percpu_xchg_1\n"
+		"1:	ldxrb	%w[ret], %[ptr]\n"
+		"	stxrb	%w[loop], %w[val], %[ptr]\n"
+		"	cbnz	%w[loop], 1b"
+		: [loop] "=&r"(loop), [ret] "=&r"(ret),
+		  [ptr] "+Q"(*(u8 *)ptr)
+		: [val] "r" (val));
 		break;
 	case 2:
-		do {
-			asm ("//__percpu_xchg_2\n"
-			"ldxrh %w[ret], %[ptr]\n"
-			"stxrh %w[loop], %w[val], %[ptr]\n"
-			: [loop] "=&r"(loop), [ret] "=&r"(ret),
-			  [ptr] "+Q"(*(u16 *)ptr)
-			: [val] "r" (val));
-		} while (loop);
+		asm ("//__percpu_xchg_2\n"
+		"1:	ldxrh	%w[ret], %[ptr]\n"
+		"	stxrh	%w[loop], %w[val], %[ptr]\n"
+		"	cbnz	%w[loop], 1b"
+		: [loop] "=&r"(loop), [ret] "=&r"(ret),
+		  [ptr] "+Q"(*(u16 *)ptr)
+		: [val] "r" (val));
 		break;
 	case 4:
-		do {
-			asm ("//__percpu_xchg_4\n"
-			"ldxr %w[ret], %[ptr]\n"
-			"stxr %w[loop], %w[val], %[ptr]\n"
-			: [loop] "=&r"(loop), [ret] "=&r"(ret),
-			  [ptr] "+Q"(*(u32 *)ptr)
-			: [val] "r" (val));
-		} while (loop);
+		asm ("//__percpu_xchg_4\n"
+		"1:	ldxr	%w[ret], %[ptr]\n"
+		"	stxr	%w[loop], %w[val], %[ptr]\n"
+		"	cbnz	%w[loop], 1b"
+		: [loop] "=&r"(loop), [ret] "=&r"(ret),
+		  [ptr] "+Q"(*(u32 *)ptr)
+		: [val] "r" (val));
 		break;
 	case 8:
-		do {
-			asm ("//__percpu_xchg_8\n"
-			"ldxr %[ret], %[ptr]\n"
-			"stxr %w[loop], %[val], %[ptr]\n"
-			: [loop] "=&r"(loop), [ret] "=&r"(ret),
-			  [ptr] "+Q"(*(u64 *)ptr)
-			: [val] "r" (val));
-		} while (loop);
+		asm ("//__percpu_xchg_8\n"
+		"1:	ldxr	%[ret], %[ptr]\n"
+		"	stxr	%w[loop], %[val], %[ptr]\n"
+		"	cbnz	%w[loop], 1b"
+		: [loop] "=&r"(loop), [ret] "=&r"(ret),
+		  [ptr] "+Q"(*(u64 *)ptr)
+		: [val] "r" (val));
 		break;
 	default:
 		BUILD_BUG();

arch/arm64/include/asm/processor.h

@@ -188,8 +188,8 @@ static inline void spin_lock_prefetch(const void *ptr)
 
 #endif
 
-void cpu_enable_pan(void *__unused);
-void cpu_enable_uao(void *__unused);
-void cpu_enable_cache_maint_trap(void *__unused);
+int cpu_enable_pan(void *__unused);
+int cpu_enable_uao(void *__unused);
+int cpu_enable_cache_maint_trap(void *__unused);
 
 #endif /* __ASM_PROCESSOR_H */

arch/arm64/include/asm/sysreg.h

@@ -286,7 +286,7 @@ asm(
 
 #define write_sysreg_s(v, r) do {					\
 	u64 __val = (u64)v;						\
-	asm volatile("msr_s " __stringify(r) ", %0" : : "rZ" (__val));	\
+	asm volatile("msr_s " __stringify(r) ", %x0" : : "rZ" (__val));	\
 } while (0)
 
 static inline void config_sctlr_el1(u32 clear, u32 set)

arch/arm64/include/asm/uaccess.h

@@ -21,6 +21,7 @@
 /*
  * User space memory access functions
  */
+#include <linux/bitops.h>
 #include <linux/kasan-checks.h>
 #include <linux/string.h>
 #include <linux/thread_info.h>
@@ -102,6 +103,13 @@ static inline void set_fs(mm_segment_t fs)
 	flag;								\
 })
 
+/*
+ * When dealing with data aborts or instruction traps we may end up with
+ * a tagged userland pointer. Clear the tag to get a sane pointer to pass
+ * on to access_ok(), for instance.
+ */
+#define untagged_addr(addr)		sign_extend64(addr, 55)
+
 #define access_ok(type, addr, size)	__range_ok(addr, size)
 #define user_addr_max			get_fs
 

arch/arm64/kernel/armv8_deprecated.c

@@ -280,35 +280,43 @@ static void __init register_insn_emulation_sysctl(struct ctl_table *table)
 /*
  * Error-checking SWP macros implemented using ldxr{b}/stxr{b}
  */
-#define __user_swpX_asm(data, addr, res, temp, B)		\
+
+/* Arbitrary constant to ensure forward-progress of the LL/SC loop */
+#define __SWP_LL_SC_LOOPS	4
+
+#define __user_swpX_asm(data, addr, res, temp, temp2, B)	\
 	__asm__ __volatile__(					\
+	"	mov		%w3, %w7\n"			\
 	ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,	\
 		    CONFIG_ARM64_PAN)				\
-	"0:	ldxr"B"		%w2, [%3]\n"			\
-	"1:	stxr"B"		%w0, %w1, [%3]\n"		\
+	"0:	ldxr"B"		%w2, [%4]\n"			\
+	"1:	stxr"B"		%w0, %w1, [%4]\n"		\
 	"	cbz		%w0, 2f\n"			\
-	"	mov		%w0, %w4\n"			\
+	"	sub		%w3, %w3, #1\n"			\
+	"	cbnz		%w3, 0b\n"			\
+	"	mov		%w0, %w5\n"			\
 	"	b		3f\n"				\
 	"2:\n"							\
 	"	mov		%w1, %w2\n"			\
 	"3:\n"							\
 	"	.pushsection	 .fixup,\"ax\"\n"		\
 	"	.align		2\n"				\
-	"4:	mov		%w0, %w5\n"			\
+	"4:	mov		%w0, %w6\n"			\
 	"	b		3b\n"				\
 	"	.popsection"					\
 	_ASM_EXTABLE(0b, 4b)					\
 	_ASM_EXTABLE(1b, 4b)					\
 	ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,	\
 		CONFIG_ARM64_PAN)				\
-	: "=&r" (res), "+r" (data), "=&r" (temp)		\
-	: "r" (addr), "i" (-EAGAIN), "i" (-EFAULT)		\
+	: "=&r" (res), "+r" (data), "=&r" (temp), "=&r" (temp2)	\
+	: "r" (addr), "i" (-EAGAIN), "i" (-EFAULT),		\
+	  "i" (__SWP_LL_SC_LOOPS)				\
 	: "memory")
 
-#define __user_swp_asm(data, addr, res, temp) \
-	__user_swpX_asm(data, addr, res, temp, "")
-#define __user_swpb_asm(data, addr, res, temp) \
-	__user_swpX_asm(data, addr, res, temp, "b")
+#define __user_swp_asm(data, addr, res, temp, temp2) \
+	__user_swpX_asm(data, addr, res, temp, temp2, "")
+#define __user_swpb_asm(data, addr, res, temp, temp2) \
+	__user_swpX_asm(data, addr, res, temp, temp2, "b")
 
 /*
  * Bit 22 of the instruction encoding distinguishes between
@@ -328,12 +336,12 @@ static int emulate_swpX(unsigned int address, unsigned int *data,
 	}
 
 	while (1) {
-		unsigned long temp;
+		unsigned long temp, temp2;
 
 		if (type == TYPE_SWPB)
-			__user_swpb_asm(*data, address, res, temp);
+			__user_swpb_asm(*data, address, res, temp, temp2);
 		else
-			__user_swp_asm(*data, address, res, temp);
+			__user_swp_asm(*data, address, res, temp, temp2);
 
 		if (likely(res != -EAGAIN) || signal_pending(current))
 			break;

arch/arm64/kernel/cpu_errata.c

@@ -39,10 +39,11 @@ has_mismatched_cache_line_size(const struct arm64_cpu_capabilities *entry,
 		(arm64_ftr_reg_ctrel0.sys_val & arm64_ftr_reg_ctrel0.strict_mask);
 }
 
-static void cpu_enable_trap_ctr_access(void *__unused)
+static int cpu_enable_trap_ctr_access(void *__unused)
 {
 	/* Clear SCTLR_EL1.UCT */
 	config_sctlr_el1(SCTLR_EL1_UCT, 0);
+	return 0;
 }
 
 #define MIDR_RANGE(model, min, max) \

arch/arm64/kernel/cpufeature.c

@@ -19,7 +19,9 @@
 #define pr_fmt(fmt) "CPU features: " fmt
 
 #include <linux/bsearch.h>
+#include <linux/cpumask.h>
 #include <linux/sort.h>
+#include <linux/stop_machine.h>
 #include <linux/types.h>
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
@@ -941,7 +943,13 @@ void __init enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
 {
 	for (; caps->matches; caps++)
 		if (caps->enable && cpus_have_cap(caps->capability))
-			on_each_cpu(caps->enable, NULL, true);
+			/*
+			 * Use stop_machine() as it schedules the work allowing
+			 * us to modify PSTATE, instead of on_each_cpu() which
+			 * uses an IPI, giving us a PSTATE that disappears when
+			 * we return.
+			 */
+			stop_machine(caps->enable, NULL, cpu_online_mask);
 }
 
 /*

arch/arm64/kernel/head.S

@@ -586,8 +586,9 @@ CPU_LE(	movk	x0, #0x30d0, lsl #16	)	// Clear EE and E0E on LE systems
 	b.lt	4f				// Skip if no PMU present
 	mrs	x0, pmcr_el0			// Disable debug access traps
 	ubfx	x0, x0, #11, #5			// to EL2 and allow access to
-	msr	mdcr_el2, x0			// all PMU counters from EL1
 4:
+	csel	x0, xzr, x0, lt			// all PMU counters from EL1
+	msr	mdcr_el2, x0			// (if they exist)
 
 	/* Stage-2 translation */
 	msr	vttbr_el2, xzr

arch/arm64/kernel/process.c

@@ -49,6 +49,7 @@
 #include <asm/alternative.h>
 #include <asm/compat.h>
 #include <asm/cacheflush.h>
+#include <asm/exec.h>
 #include <asm/fpsimd.h>
 #include <asm/mmu_context.h>
 #include <asm/processor.h>
@@ -186,10 +187,19 @@ void __show_regs(struct pt_regs *regs)
 	printk("pc : [<%016llx>] lr : [<%016llx>] pstate: %08llx\n",
 	       regs->pc, lr, regs->pstate);
 	printk("sp : %016llx\n", sp);
-	for (i = top_reg; i >= 0; i--) {
+
+	i = top_reg;
+
+	while (i >= 0) {
 		printk("x%-2d: %016llx ", i, regs->regs[i]);
-		if (i % 2 == 0)
-			printk("\n");
+		i--;
+
+		if (i % 2 == 0) {
+			pr_cont("x%-2d: %016llx ", i, regs->regs[i]);
+			i--;
+		}
+
+		pr_cont("\n");
 	}
 	printk("\n");
 }
@@ -301,7 +311,7 @@ static void tls_thread_switch(struct task_struct *next)
 }
 
 /* Restore the UAO state depending on next's addr_limit */
-static void uao_thread_switch(struct task_struct *next)
+void uao_thread_switch(struct task_struct *next)
 {
 	if (IS_ENABLED(CONFIG_ARM64_UAO)) {
 		if (task_thread_info(next)->addr_limit == KERNEL_DS)

arch/arm64/kernel/sleep.S

@@ -135,7 +135,7 @@ ENTRY(_cpu_resume)
 
 #ifdef CONFIG_KASAN
 	mov	x0, sp
-	bl	kasan_unpoison_remaining_stack
+	bl	kasan_unpoison_task_stack_below
 #endif
 
 	ldp	x19, x20, [x29, #16]

arch/arm64/kernel/smp.c

@@ -544,6 +544,7 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
 			return;
 		}
 		bootcpu_valid = true;
+		early_map_cpu_to_node(0, acpi_numa_get_nid(0, hwid));
 		return;
 	}
 

arch/arm64/kernel/suspend.c

 #include <linux/ftrace.h>
 #include <linux/percpu.h>
 #include <linux/slab.h>
+#include <asm/alternative.h>
 #include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
 #include <asm/debug-monitors.h>
+#include <asm/exec.h>
 #include <asm/pgtable.h>
 #include <asm/memory.h>
 #include <asm/mmu_context.h>
@@ -49,6 +52,14 @@ void notrace __cpu_suspend_exit(void)
 	 */
 	set_my_cpu_offset(per_cpu_offset(cpu));
 
+	/*
+	 * PSTATE was not saved over suspend/resume, re-enable any detected
+	 * features that might not have been set correctly.
+	 */
+	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,
+			CONFIG_ARM64_PAN));
+	uao_thread_switch(current);
+
 	/*
 	 * Restore HW breakpoint registers to sane values
 	 * before debug exceptions are possibly reenabled

arch/arm64/kernel/traps.c

@@ -428,24 +428,28 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 	force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0);
 }
 
-void cpu_enable_cache_maint_trap(void *__unused)
+int cpu_enable_cache_maint_trap(void *__unused)
 {
 	config_sctlr_el1(SCTLR_EL1_UCI, 0);
+	return 0;
 }
 
 #define __user_cache_maint(insn, address, res)			\
-	asm volatile (						\
-		"1:	" insn ", %1\n"				\
-		"	mov	%w0, #0\n"			\
-		"2:\n"						\
-		"	.pushsection .fixup,\"ax\"\n"		\
-		"	.align	2\n"				\
-		"3:	mov	%w0, %w2\n"			\
-		"	b	2b\n"				\
-		"	.popsection\n"				\
-		_ASM_EXTABLE(1b, 3b)				\
-		: "=r" (res)					\
-		: "r" (address), "i" (-EFAULT) )
+	if (untagged_addr(address) >= user_addr_max())		\
+		res = -EFAULT;					\
+	else							\
+		asm volatile (					\
+			"1:	" insn ", %1\n"			\
+			"	mov	%w0, #0\n"		\
+			"2:\n"					\
+			"	.pushsection .fixup,\"ax\"\n"	\
+			"	.align	2\n"			\
+			"3:	mov	%w0, %w2\n"		\
+			"	b	2b\n"			\
+			"	.popsection\n"			\
+			_ASM_EXTABLE(1b, 3b)			\
+			: "=r" (res)				\
+			: "r" (address), "i" (-EFAULT) )
 
 static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
 {

arch/arm64/mm/fault.c

@@ -29,7 +29,9 @@
 #include <linux/sched.h>
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
+#include <linux/preempt.h>
 
+#include <asm/bug.h>
 #include <asm/cpufeature.h>
 #include <asm/exception.h>
 #include <asm/debug-monitors.h>
@@ -670,9 +672,17 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
 NOKPROBE_SYMBOL(do_debug_exception);
 
 #ifdef CONFIG_ARM64_PAN
-void cpu_enable_pan(void *__unused)
+int cpu_enable_pan(void *__unused)
 {
+	/*
+	 * We modify PSTATE. This won't work from irq context as the PSTATE
+	 * is discarded once we return from the exception.
+	 */
+	WARN_ON_ONCE(in_interrupt());
+
 	config_sctlr_el1(SCTLR_EL1_SPAN, 0);
+	asm(SET_PSTATE_PAN(1));
+	return 0;
 }
 #endif /* CONFIG_ARM64_PAN */
 
@@ -683,8 +693,9 @@ void cpu_enable_pan(void *__unused)
  * We need to enable the feature at runtime (instead of adding it to
  * PSR_MODE_EL1h) as the feature may not be implemented by the cpu.
  */
-void cpu_enable_uao(void *__unused)
+int cpu_enable_uao(void *__unused)
 {
 	asm(SET_PSTATE_UAO(1));
+	return 0;
 }
 #endif /* CONFIG_ARM64_UAO */

arch/arm64/mm/init.c

@@ -421,35 +421,35 @@ void __init mem_init(void)
 
 	pr_notice("Virtual kernel memory layout:\n");
 #ifdef CONFIG_KASAN
-	pr_cont("    kasan   : 0x%16lx - 0x%16lx   (%6ld GB)\n",
+	pr_notice("    kasan   : 0x%16lx - 0x%16lx   (%6ld GB)\n",
 		MLG(KASAN_SHADOW_START, KASAN_SHADOW_END));
 #endif
-	pr_cont("    modules : 0x%16lx - 0x%16lx   (%6ld MB)\n",
+	pr_notice("    modules : 0x%16lx - 0x%16lx   (%6ld MB)\n",
 		MLM(MODULES_VADDR, MODULES_END));
-	pr_cont("    vmalloc : 0x%16lx - 0x%16lx   (%6ld GB)\n",
+	pr_notice("    vmalloc : 0x%16lx - 0x%16lx   (%6ld GB)\n",
 		MLG(VMALLOC_START, VMALLOC_END));
-	pr_cont("      .text : 0x%p" " - 0x%p" "   (%6ld KB)\n",
+	pr_notice("      .text : 0x%p" " - 0x%p" "   (%6ld KB)\n",
 		MLK_ROUNDUP(_text, _etext));
-	pr_cont("    .rodata : 0x%p" " - 0x%p" "   (%6ld KB)\n",
+	pr_notice("    .rodata : 0x%p" " - 0x%p" "   (%6ld KB)\n",
 		MLK_ROUNDUP(__start_rodata, __init_begin));
-	pr_cont("      .init : 0x%p" " - 0x%p" "   (%6ld KB)\n",
+	pr_notice("      .init : 0x%p" " - 0x%p" "   (%6ld KB)\n",
 		MLK_ROUNDUP(__init_begin, __init_end));
-	pr_cont("      .data : 0x%p" " - 0x%p" "   (%6ld KB)\n",
+	pr_notice("      .data : 0x%p" " - 0x%p" "   (%6ld KB)\n",
 		MLK_ROUNDUP(_sdata, _edata));
-	pr_cont("       .bss : 0x%p" " - 0x%p" "   (%6ld KB)\n",
+	pr_notice("       .bss : 0x%p" " - 0x%p" "   (%6ld KB)\n",
 		MLK_ROUNDUP(__bss_start, __bss_stop));
-	pr_cont("    fixed   : 0x%16lx - 0x%16lx   (%6ld KB)\n",
+	pr_notice("    fixed   : 0x%16lx - 0x%16lx   (%6ld KB)\n",
 		MLK(FIXADDR_START, FIXADDR_TOP));
-	pr_cont("    PCI I/O : 0x%16lx - 0x%16lx   (%6ld MB)\n",
+	pr_notice("    PCI I/O : 0x%16lx - 0x%16lx   (%6ld MB)\n",
 		MLM(PCI_IO_START, PCI_IO_END));
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-	pr_cont("    vmemmap : 0x%16lx - 0x%16lx   (%6ld GB maximum)\n",
+	pr_notice("    vmemmap : 0x%16lx - 0x%16lx   (%6ld GB maximum)\n",
 		MLG(VMEMMAP_START, VMEMMAP_START + VMEMMAP_SIZE));
-	pr_cont("              0x%16lx - 0x%16lx   (%6ld MB actual)\n",
+	pr_notice("              0x%16lx - 0x%16lx   (%6ld MB actual)\n",
 		MLM((unsigned long)phys_to_page(memblock_start_of_DRAM()),
 		    (unsigned long)virt_to_page(high_memory)));
 #endif
-	pr_cont("    memory  : 0x%16lx - 0x%16lx   (%6ld MB)\n",
+	pr_notice("    memory  : 0x%16lx - 0x%16lx   (%6ld MB)\n",
 		MLM(__phys_to_virt(memblock_start_of_DRAM()),
 		    (unsigned long)high_memory));
 

arch/arm64/mm/numa.c

@@ -147,7 +147,7 @@ static int __init early_cpu_to_node(int cpu)
 
 static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
 {
-	return node_distance(from, to);
+	return node_distance(early_cpu_to_node(from), early_cpu_to_node(to));
 }
 
 static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size,
@@ -223,8 +223,11 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
 	void *nd;
 	int tnid;
 
-	pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
-		nid, start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);
+	if (start_pfn < end_pfn)
+		pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n", nid,
+			start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);
+	else
+		pr_info("Initmem setup node %d [<memory-less node>]\n", nid);
 
 	nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
 	nd = __va(nd_pa);

arch/blackfin/kernel/ptrace.c

@@ -271,7 +271,7 @@ long arch_ptrace(struct task_struct *child, long request,
 			case BFIN_MEM_ACCESS_CORE:
 			case BFIN_MEM_ACCESS_CORE_ONLY:
 				copied = access_process_vm(child, addr, &tmp,
-				                           to_copy, 0);
+							   to_copy, FOLL_FORCE);
 				if (copied)
 					break;
 
@@ -324,7 +324,8 @@ long arch_ptrace(struct task_struct *child, long request,
 			case BFIN_MEM_ACCESS_CORE:
 			case BFIN_MEM_ACCESS_CORE_ONLY:
 				copied = access_process_vm(child, addr, &data,
-				                           to_copy, 1);
+				                           to_copy,
+							   FOLL_FORCE | FOLL_WRITE);
 				break;
 			case BFIN_MEM_ACCESS_DMA:
 				if (safe_dma_memcpy(paddr, &data, to_copy))

arch/cris/arch-v32/drivers/cryptocop.c

@@ -2722,7 +2722,6 @@ static int cryptocop_ioctl_process(struct inode *inode, struct file *filp, unsig
 	err = get_user_pages((unsigned long int)(oper.indata + prev_ix),
 			     noinpages,
 			     0,  /* read access only for in data */
-			     0, /* no force */
 			     inpages,
 			     NULL);
 
@@ -2736,8 +2735,7 @@ static int cryptocop_ioctl_process(struct inode *inode, struct file *filp, unsig
 	if (oper.do_cipher){
 		err = get_user_pages((unsigned long int)oper.cipher_outdata,
 				     nooutpages,
-				     1, /* write access for out data */
-				     0, /* no force */
+				     FOLL_WRITE, /* write access for out data */
 				     outpages,
 				     NULL);
 		up_read(&current->mm->mmap_sem);
@@ -3151,7 +3149,7 @@ static void print_dma_descriptors(struct cryptocop_int_operation *iop)
 	printk("print_dma_descriptors start\n");
 
 	printk("iop:\n");
-	printk("\tsid: 0x%lld\n", iop->sid);
+	printk("\tsid: 0x%llx\n", iop->sid);
 
 	printk("\tcdesc_out: 0x%p\n", iop->cdesc_out);
 	printk("\tcdesc_in: 0x%p\n", iop->cdesc_in);

arch/cris/arch-v32/kernel/ptrace.c

@@ -147,7 +147,7 @@ long arch_ptrace(struct task_struct *child, long request,
 				/* The trampoline page is globally mapped, no page table to traverse.*/
 				tmp = *(unsigned long*)addr;
 			} else {
-				copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
+				copied = access_process_vm(child, addr, &tmp, sizeof(tmp), FOLL_FORCE);
 
 				if (copied != sizeof(tmp))
 					break;
@@ -279,7 +279,7 @@ static int insn_size(struct task_struct *child, unsigned long pc)
   int opsize = 0;
 
   /* Read the opcode at pc (do what PTRACE_PEEKTEXT would do). */
-  copied = access_process_vm(child, pc, &opcode, sizeof(opcode), 0);
+  copied = access_process_vm(child, pc, &opcode, sizeof(opcode), FOLL_FORCE);
   if (copied != sizeof(opcode))
     return 0;
 

arch/h8300/include/asm/thread_info.h

@@ -31,7 +31,6 @@ struct thread_info {
 	int		   cpu;			/* cpu we're on */
 	int		   preempt_count;	/* 0 => preemptable, <0 => BUG */
 	mm_segment_t		addr_limit;
-	struct restart_block restart_block;
 };
 
 /*
@@ -44,9 +43,6 @@ struct thread_info {
 	.cpu =		0,			\
 	.preempt_count = INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)

arch/h8300/kernel/signal.c

@@ -79,7 +79,7 @@ restore_sigcontext(struct sigcontext *usc, int *pd0)
 	unsigned int er0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/* restore passed registers */
 #define COPY(r)  do { err |= get_user(regs->r, &usc->sc_##r); } while (0)

arch/ia64/kernel/err_inject.c

@@ -142,7 +142,7 @@ store_virtual_to_phys(struct device *dev, struct device_attribute *attr,
 	u64 virt_addr=simple_strtoull(buf, NULL, 16);
 	int ret;
 
-	ret = get_user_pages(virt_addr, 1, VM_READ, 0, NULL, NULL);
+	ret = get_user_pages(virt_addr, 1, FOLL_WRITE, NULL, NULL);
 	if (ret<=0) {
 #ifdef ERR_INJ_DEBUG
 		printk("Virtual address %lx is not existing.\n",virt_addr);

arch/ia64/kernel/ptrace.c

@@ -453,7 +453,7 @@ ia64_peek (struct task_struct *child, struct switch_stack *child_stack,
 			return 0;
 		}
 	}
-	copied = access_process_vm(child, addr, &ret, sizeof(ret), 0);
+	copied = access_process_vm(child, addr, &ret, sizeof(ret), FOLL_FORCE);
 	if (copied != sizeof(ret))
 		return -EIO;
 	*val = ret;
@@ -489,7 +489,8 @@ ia64_poke (struct task_struct *child, struct switch_stack *child_stack,
 				*ia64_rse_skip_regs(krbs, regnum) = val;
 			}
 		}
-	} else if (access_process_vm(child, addr, &val, sizeof(val), 1)
+	} else if (access_process_vm(child, addr, &val, sizeof(val),
+				FOLL_FORCE | FOLL_WRITE)
 		   != sizeof(val))
 		return -EIO;
 	return 0;
@@ -543,7 +544,8 @@ ia64_sync_user_rbs (struct task_struct *child, struct switch_stack *sw,
 		ret = ia64_peek(child, sw, user_rbs_end, addr, &val);
 		if (ret < 0)
 			return ret;
-		if (access_process_vm(child, addr, &val, sizeof(val), 1)
+		if (access_process_vm(child, addr, &val, sizeof(val),
+				FOLL_FORCE | FOLL_WRITE)
 		    != sizeof(val))
 			return -EIO;
 	}
@@ -559,7 +561,8 @@ ia64_sync_kernel_rbs (struct task_struct *child, struct switch_stack *sw,
 
 	/* now copy word for word from user rbs to kernel rbs: */
 	for (addr = user_rbs_start; addr < user_rbs_end; addr += 8) {
-		if (access_process_vm(child, addr, &val, sizeof(val), 0)
+		if (access_process_vm(child, addr, &val, sizeof(val),
+				FOLL_FORCE)
 				!= sizeof(val))
 			return -EIO;
 
@@ -1156,7 +1159,8 @@ arch_ptrace (struct task_struct *child, long request,
 	case PTRACE_PEEKTEXT:
 	case PTRACE_PEEKDATA:
 		/* read word at location addr */
-		if (access_process_vm(child, addr, &data, sizeof(data), 0)
+		if (access_process_vm(child, addr, &data, sizeof(data),
+				FOLL_FORCE)
 		    != sizeof(data))
 			return -EIO;
 		/* ensure return value is not mistaken for error code */

arch/m32r/kernel/ptrace.c

@@ -493,7 +493,8 @@ unregister_all_debug_traps(struct task_struct *child)
 	int i;
 
 	for (i = 0; i < p->nr_trap; i++)
-		access_process_vm(child, p->addr[i], &p->insn[i], sizeof(p->insn[i]), 1);
+		access_process_vm(child, p->addr[i], &p->insn[i], sizeof(p->insn[i]),
+				FOLL_FORCE | FOLL_WRITE);
 	p->nr_trap = 0;
 }
 
@@ -537,7 +538,8 @@ embed_debug_trap(struct task_struct *child, unsigned long next_pc)
 	unsigned long next_insn, code;
 	unsigned long addr = next_pc & ~3;
 
-	if (access_process_vm(child, addr, &next_insn, sizeof(next_insn), 0)
+	if (access_process_vm(child, addr, &next_insn, sizeof(next_insn),
+			FOLL_FORCE)
 	    != sizeof(next_insn)) {
 		return -1; /* error */
 	}
@@ -546,7 +548,8 @@ embed_debug_trap(struct task_struct *child, unsigned long next_pc)
 	if (register_debug_trap(child, next_pc, next_insn, &code)) {
 		return -1; /* error */
 	}
-	if (access_process_vm(child, addr, &code, sizeof(code), 1)
+	if (access_process_vm(child, addr, &code, sizeof(code),
+			FOLL_FORCE | FOLL_WRITE)
 	    != sizeof(code)) {
 		return -1; /* error */
 	}
@@ -562,7 +565,8 @@ withdraw_debug_trap(struct pt_regs *regs)
  	addr = (regs->bpc - 2) & ~3;
 	regs->bpc -= 2;
 	if (unregister_debug_trap(current, addr, &code)) {
-	    access_process_vm(current, addr, &code, sizeof(code), 1);
+	    access_process_vm(current, addr, &code, sizeof(code),
+		    FOLL_FORCE | FOLL_WRITE);
 	    invalidate_cache();
 	}
 }
@@ -589,7 +593,8 @@ void user_enable_single_step(struct task_struct *child)
 	/* Compute next pc.  */
 	pc = get_stack_long(child, PT_BPC);
 
-	if (access_process_vm(child, pc&~3, &insn, sizeof(insn), 0)
+	if (access_process_vm(child, pc&~3, &insn, sizeof(insn),
+			FOLL_FORCE)
 	    != sizeof(insn))
 		return;
 

arch/mips/kernel/ptrace32.c

@@ -70,7 +70,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			break;
 
 		copied = access_process_vm(child, (u64)addrOthers, &tmp,
-				sizeof(tmp), 0);
+				sizeof(tmp), FOLL_FORCE);
 		if (copied != sizeof(tmp))
 			break;
 		ret = put_user(tmp, (u32 __user *) (unsigned long) data);
@@ -179,7 +179,8 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			break;
 		ret = 0;
 		if (access_process_vm(child, (u64)addrOthers, &data,
-					sizeof(data), 1) == sizeof(data))
+					sizeof(data),
+					FOLL_FORCE | FOLL_WRITE) == sizeof(data))
 			break;
 		ret = -EIO;
 		break;

arch/mips/kvm/mips.c

@@ -14,6 +14,7 @@
 #include <linux/err.h>
 #include <linux/kdebug.h>
 #include <linux/module.h>
+#include <linux/uaccess.h>
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
 #include <linux/bootmem.h>

arch/mips/mm/gup.c

@@ -287,7 +287,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	pages += nr;
 
 	ret = get_user_pages_unlocked(start, (end - start) >> PAGE_SHIFT,
-				      write, 0, pages);
+				      pages, write ? FOLL_WRITE : 0);
 
 	/* Have to be a bit careful with return values */
 	if (nr > 0) {

arch/powerpc/boot/main.c

@@ -32,9 +32,16 @@ static struct addr_range prep_kernel(void)
 	void *addr = 0;
 	struct elf_info ei;
 	long len;
+	int uncompressed_image = 0;
 
-	partial_decompress(vmlinuz_addr, vmlinuz_size,
+	len = partial_decompress(vmlinuz_addr, vmlinuz_size,
 		elfheader, sizeof(elfheader), 0);
+	/* assume uncompressed data if -1 is returned */
+	if (len == -1) {
+		uncompressed_image = 1;
+		memcpy(elfheader, vmlinuz_addr, sizeof(elfheader));
+		printf("No valid compressed data found, assume uncompressed data\n\r");
+	}
 
 	if (!parse_elf64(elfheader, &ei) && !parse_elf32(elfheader, &ei))
 		fatal("Error: not a valid PPC32 or PPC64 ELF file!\n\r");
@@ -67,6 +74,13 @@ static struct addr_range prep_kernel(void)
 					"device tree\n\r");
 	}
 
+	if (uncompressed_image) {
+		memcpy(addr, vmlinuz_addr + ei.elfoffset, ei.loadsize);
+		printf("0x%lx bytes of uncompressed data copied\n\r",
+		       ei.loadsize);
+		goto out;
+	}
+
 	/* Finally, decompress the kernel */
 	printf("Decompressing (0x%p <- 0x%p:0x%p)...\n\r", addr,
 	       vmlinuz_addr, vmlinuz_addr+vmlinuz_size);
@@ -82,7 +96,7 @@ static struct addr_range prep_kernel(void)
 			 len, ei.loadsize);
 
 	printf("Done! Decompressed 0x%lx bytes\n\r", len);
-
+out:
 	flush_cache(addr, ei.loadsize);
 
 	return (struct addr_range){addr, ei.memsize};

arch/powerpc/include/asm/cpuidle.h

@@ -26,7 +26,7 @@ extern u64 pnv_first_deep_stop_state;
 	std	r0,0(r1);					\
 	ptesync;						\
 	ld	r0,0(r1);					\
-1:	cmp	cr0,r0,r0;					\
+1:	cmpd	cr0,r0,r0;					\
 	bne	1b;						\
 	IDLE_INST;						\
 	b	.

arch/powerpc/include/asm/exception-64s.h

@@ -93,6 +93,10 @@
 	ld	reg,PACAKBASE(r13);	/* get high part of &label */	\
 	ori	reg,reg,(FIXED_SYMBOL_ABS_ADDR(label))@l;
 
+#define __LOAD_HANDLER(reg, label)					\
+	ld	reg,PACAKBASE(r13);					\
+	ori	reg,reg,(ABS_ADDR(label))@l;
+
 /* Exception register prefixes */
 #define EXC_HV	H
 #define EXC_STD
@@ -208,6 +212,18 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 #define kvmppc_interrupt kvmppc_interrupt_pr
 #endif
 
+#ifdef CONFIG_RELOCATABLE
+#define BRANCH_TO_COMMON(reg, label)					\
+	__LOAD_HANDLER(reg, label);					\
+	mtctr	reg;							\
+	bctr
+
+#else
+#define BRANCH_TO_COMMON(reg, label)					\
+	b	label
+
+#endif
+
 #define __KVM_HANDLER_PROLOG(area, n)					\
 	BEGIN_FTR_SECTION_NESTED(947)					\
 	ld	r10,area+EX_CFAR(r13);					\

arch/powerpc/include/asm/tlb.h

@@ -52,11 +52,23 @@ static inline int mm_is_core_local(struct mm_struct *mm)
 	return cpumask_subset(mm_cpumask(mm),
 			      topology_sibling_cpumask(smp_processor_id()));
 }
+
+static inline int mm_is_thread_local(struct mm_struct *mm)
+{
+	return cpumask_equal(mm_cpumask(mm),
+			      cpumask_of(smp_processor_id()));
+}
+
 #else
 static inline int mm_is_core_local(struct mm_struct *mm)
 {
 	return 1;
 }
+
+static inline int mm_is_thread_local(struct mm_struct *mm)
+{
+	return 1;
+}
 #endif
 
 #endif /* __KERNEL__ */

arch/powerpc/include/asm/unistd.h

@@ -16,6 +16,10 @@
 
 #define __NR__exit __NR_exit
 
+#define __IGNORE_pkey_mprotect
+#define __IGNORE_pkey_alloc
+#define __IGNORE_pkey_free
+
 #ifndef __ASSEMBLY__
 
 #include <linux/types.h>

arch/powerpc/kernel/exceptions-64s.S

@@ -95,19 +95,35 @@ __start_interrupts:
 /* No virt vectors corresponding with 0x0..0x100 */
 EXC_VIRT_NONE(0x4000, 0x4100)
 
-EXC_REAL_BEGIN(system_reset, 0x100, 0x200)
-	SET_SCRATCH0(r13)
+
 #ifdef CONFIG_PPC_P7_NAP
-BEGIN_FTR_SECTION
-	/* Running native on arch 2.06 or later, check if we are
-	 * waking up from nap/sleep/winkle.
+	/*
+	 * If running native on arch 2.06 or later, check if we are waking up
+	 * from nap/sleep/winkle, and branch to idle handler.
 	 */
-	mfspr	r13,SPRN_SRR1
-	rlwinm.	r13,r13,47-31,30,31
-	beq	9f
+#define IDLETEST(n)							\
+	BEGIN_FTR_SECTION ;						\
+	mfspr	r10,SPRN_SRR1 ;						\
+	rlwinm.	r10,r10,47-31,30,31 ;					\
+	beq-	1f ;							\
+	cmpwi	cr3,r10,2 ;						\
+	BRANCH_TO_COMMON(r10, system_reset_idle_common) ;		\
+1:									\
+	END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+#else
+#define IDLETEST NOTEST
+#endif
 
-	cmpwi	cr3,r13,2
-	GET_PACA(r13)
+EXC_REAL_BEGIN(system_reset, 0x100, 0x200)
+	SET_SCRATCH0(r13)
+	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD,
+				 IDLETEST, 0x100)
+
+EXC_REAL_END(system_reset, 0x100, 0x200)
+EXC_VIRT_NONE(0x4100, 0x4200)
+
+#ifdef CONFIG_PPC_P7_NAP
+EXC_COMMON_BEGIN(system_reset_idle_common)
 	bl	pnv_restore_hyp_resource
 
 	li	r0,PNV_THREAD_RUNNING
@@ -130,14 +146,8 @@ BEGIN_FTR_SECTION
 	blt	cr3,2f
 	b	pnv_wakeup_loss
 2:	b	pnv_wakeup_noloss
+#endif
 
-9:
-END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-#endif /* CONFIG_PPC_P7_NAP */
-	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD,
-				 NOTEST, 0x100)
-EXC_REAL_END(system_reset, 0x100, 0x200)
-EXC_VIRT_NONE(0x4100, 0x4200)
 EXC_COMMON(system_reset_common, 0x100, system_reset_exception)
 
 #ifdef CONFIG_PPC_PSERIES
@@ -817,10 +827,8 @@ EXC_VIRT(trap_0b, 0x4b00, 0x4c00, 0xb00)
 TRAMP_KVM(PACA_EXGEN, 0xb00)
 EXC_COMMON(trap_0b_common, 0xb00, unknown_exception)
 
-
-#define LOAD_SYSCALL_HANDLER(reg)				\
-	ld	reg,PACAKBASE(r13);				\
-	ori	reg,reg,(ABS_ADDR(system_call_common))@l;
+#define LOAD_SYSCALL_HANDLER(reg)					\
+	__LOAD_HANDLER(reg, system_call_common)
 
 /* Syscall routine is used twice, in reloc-off and reloc-on paths */
 #define SYSCALL_PSERIES_1 					\

arch/powerpc/kernel/hw_breakpoint.c

@@ -275,7 +275,7 @@ int hw_breakpoint_handler(struct die_args *args)
 	if (!stepped) {
 		WARN(1, "Unable to handle hardware breakpoint. Breakpoint at "
 			"0x%lx will be disabled.", info->address);
-		perf_event_disable(bp);
+		perf_event_disable_inatomic(bp);
 		goto out;
 	}
 	/*

arch/powerpc/kernel/idle_book3s.S

@@ -90,6 +90,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
  * Threads will spin in HMT_LOW until the lock bit is cleared.
  * r14 - pointer to core_idle_state
  * r15 - used to load contents of core_idle_state
+ * r9  - used as a temporary variable
  */
 
 core_idle_lock_held:
@@ -99,6 +100,8 @@ core_idle_lock_held:
 	bne	3b
 	HMT_MEDIUM
 	lwarx	r15,0,r14
+	andi.	r9,r15,PNV_CORE_IDLE_LOCK_BIT
+	bne	core_idle_lock_held
 	blr
 
 /*
@@ -163,12 +166,6 @@ _GLOBAL(pnv_powersave_common)
 	std	r9,_MSR(r1)
 	std	r1,PACAR1(r13)
 
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	/* Tell KVM we're entering idle */
-	li	r4,KVM_HWTHREAD_IN_IDLE
-	stb	r4,HSTATE_HWTHREAD_STATE(r13)
-#endif
-
 	/*
 	 * Go to real mode to do the nap, as required by the architecture.
 	 * Also, we need to be in real mode before setting hwthread_state,
@@ -185,6 +182,26 @@ _GLOBAL(pnv_powersave_common)
 
 	.globl pnv_enter_arch207_idle_mode
 pnv_enter_arch207_idle_mode:
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	/* Tell KVM we're entering idle */
+	li	r4,KVM_HWTHREAD_IN_IDLE
+	/******************************************************/
+	/*  N O T E   W E L L    ! ! !    N O T E   W E L L   */
+	/* The following store to HSTATE_HWTHREAD_STATE(r13)  */
+	/* MUST occur in real mode, i.e. with the MMU off,    */
+	/* and the MMU must stay off until we clear this flag */
+	/* and test HSTATE_HWTHREAD_REQ(r13) in the system    */
+	/* reset interrupt vector in exceptions-64s.S.        */
+	/* The reason is that another thread can switch the   */
+	/* MMU to a guest context whenever this flag is set   */
+	/* to KVM_HWTHREAD_IN_IDLE, and if the MMU was on,    */
+	/* that would potentially cause this thread to start  */
+	/* executing instructions from guest memory in        */
+	/* hypervisor mode, leading to a host crash or data   */
+	/* corruption, or worse.                              */
+	/******************************************************/
+	stb	r4,HSTATE_HWTHREAD_STATE(r13)
+#endif
 	stb	r3,PACA_THREAD_IDLE_STATE(r13)
 	cmpwi	cr3,r3,PNV_THREAD_SLEEP
 	bge	cr3,2f
@@ -250,6 +267,12 @@ enter_winkle:
  * r3 - requested stop state
  */
 power_enter_stop:
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	/* Tell KVM we're entering idle */
+	li	r4,KVM_HWTHREAD_IN_IDLE
+	/* DO THIS IN REAL MODE!  See comment above. */
+	stb	r4,HSTATE_HWTHREAD_STATE(r13)
+#endif
 /*
  * Check if the requested state is a deep idle state.
  */

arch/powerpc/kernel/process.c

@@ -1012,7 +1012,7 @@ void restore_tm_state(struct pt_regs *regs)
 	/* Ensure that restore_math() will restore */
 	if (msr_diff & MSR_FP)
 		current->thread.load_fp = 1;
-#ifdef CONFIG_ALIVEC
+#ifdef CONFIG_ALTIVEC
 	if (cpu_has_feature(CPU_FTR_ALTIVEC) && msr_diff & MSR_VEC)
 		current->thread.load_vec = 1;
 #endif

arch/powerpc/kernel/ptrace32.c

@@ -74,7 +74,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			break;
 
 		copied = access_process_vm(child, (u64)addrOthers, &tmp,
-				sizeof(tmp), 0);
+				sizeof(tmp), FOLL_FORCE);
 		if (copied != sizeof(tmp))
 			break;
 		ret = put_user(tmp, (u32 __user *)data);
@@ -179,7 +179,8 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			break;
 		ret = 0;
 		if (access_process_vm(child, (u64)addrOthers, &tmp,
-					sizeof(tmp), 1) == sizeof(tmp))
+					sizeof(tmp),
+					FOLL_FORCE | FOLL_WRITE) == sizeof(tmp))
 			break;
 		ret = -EIO;
 		break;

arch/powerpc/kvm/book3s_hv_rm_xics.c

@@ -23,6 +23,7 @@
 #include <asm/ppc-opcode.h>
 #include <asm/pnv-pci.h>
 #include <asm/opal.h>
+#include <asm/smp.h>
 
 #include "book3s_xics.h"