Merge branch 'for-linus' of git://git.linaro.org/people/rmk/linux-arm

Pull ARM updates from Russell King:
 "This set includes adding support for Neon acceleration of RAID6 XOR
  code from Ard Biesheuvel, cache flushing and barrier updates from Will
  Deacon, and a cleanup to the ARM debug code which reduces the amount
  of code by about 500 lines.

  A few other cleanups, such as constifying the machine descriptors
  which already shouldn't be written to, cleaning up the printing of the
  L2 cache size"

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (55 commits)
  ARM: 7826/1: debug: support debug ll on hisilicon soc
  ARM: 7830/1: delay: don't bother reporting bogomips in /proc/cpuinfo
  ARM: 7829/1: Add ".text.unlikely" and ".text.hot" to arm unwind tables
  ARM: 7828/1: ARMv7-M: implement restart routine common to all v7-M machines
  ARM: 7827/1: highbank: fix debug uart virtual address for LPAE
  ARM: 7823/1: errata: workaround Cortex-A15 erratum 773022
  ARM: 7806/1: allow DEBUG_UNCOMPRESS for Tegra
  ARM: 7793/1: debug: use generic option for ep93xx PL10x debug port
  ARM: debug: move SPEAr debug to generic PL01x code
  ARM: debug: move davinci debug to generic 8250 code
  ARM: debug: move keystone debug to generic 8250 code
  ARM: debug: remove DEBUG_ROCKCHIP_UART
  ARM: debug: provide generic option choices for 8250 and PL01x ports
  ARM: debug: move PL01X debug include into arch/arm/include/debug/
  ARM: debug: provide PL01x debug uart phys/virt address configuration options
  ARM: debug: add support for word accesses to debug/8250.S
  ARM: debug: move 8250 debug include into arch/arm/include/debug/
  ARM: debug: provide 8250 debug uart phys/virt address configuration options
  ARM: debug: provide 8250 debug uart register shift configuration option
  ARM: debug: provide 8250 debug uart flow control configuration option
  ...

Documentation/arm/Booting

@@ -18,7 +18,8 @@ following:
 2. Initialise one serial port.
 3. Detect the machine type.
 4. Setup the kernel tagged list.
-5. Call the kernel image.
+5. Load initramfs.
+6. Call the kernel image.
 
 
 1. Setup and initialise RAM
@@ -120,12 +121,27 @@ tagged list.
 The boot loader must pass at a minimum the size and location of the
 system memory, and the root filesystem location.  The dtb must be
 placed in a region of memory where the kernel decompressor will not
-overwrite it.  The recommended placement is in the first 16KiB of RAM
-with the caveat that it may not be located at physical address 0 since
-the kernel interprets a value of 0 in r2 to mean neither a tagged list
-nor a dtb were passed.
+overwrite it, whilst remaining within the region which will be covered
+by the kernel's low-memory mapping.
 
-5. Calling the kernel image
+A safe location is just above the 128MiB boundary from start of RAM.
+
+5. Load initramfs.
+------------------
+
+Existing boot loaders:		OPTIONAL
+New boot loaders:		OPTIONAL
+
+If an initramfs is in use then, as with the dtb, it must be placed in
+a region of memory where the kernel decompressor will not overwrite it
+while also with the region which will be covered by the kernel's
+low-memory mapping.
+
+A safe location is just above the device tree blob which itself will
+be loaded just above the 128MiB boundary from the start of RAM as
+recommended above.
+
+6. Calling the kernel image
 ---------------------------
 
 Existing boot loaders:		MANDATORY
@@ -136,11 +152,17 @@ is stored in flash, and is linked correctly to be run from flash,
 then it is legal for the boot loader to call the zImage in flash
 directly.
 
-The zImage may also be placed in system RAM (at any location) and
-called there.  Note that the kernel uses 16K of RAM below the image
-to store page tables.  The recommended placement is 32KiB into RAM.
+The zImage may also be placed in system RAM and called there.  The
+kernel should be placed in the first 128MiB of RAM.  It is recommended
+that it is loaded above 32MiB in order to avoid the need to relocate
+prior to decompression, which will make the boot process slightly
+faster.
+
+When booting a raw (non-zImage) kernel the constraints are tighter.
+In this case the kernel must be loaded at an offset into system equal
+to TEXT_OFFSET - PAGE_OFFSET.
 
-In either case, the following conditions must be met:
+In any case, the following conditions must be met:
 
 - Quiesce all DMA capable devices so that memory does not get
   corrupted by bogus network packets or disk data. This will save

Documentation/arm/kernel_mode_neon.txt

+Kernel mode NEON
+================
+
+TL;DR summary
+-------------
+* Use only NEON instructions, or VFP instructions that don't rely on support
+  code
+* Isolate your NEON code in a separate compilation unit, and compile it with
+  '-mfpu=neon -mfloat-abi=softfp'
+* Put kernel_neon_begin() and kernel_neon_end() calls around the calls into your
+  NEON code
+* Don't sleep in your NEON code, and be aware that it will be executed with
+  preemption disabled
+
+
+Introduction
+------------
+It is possible to use NEON instructions (and in some cases, VFP instructions) in
+code that runs in kernel mode. However, for performance reasons, the NEON/VFP
+register file is not preserved and restored at every context switch or taken
+exception like the normal register file is, so some manual intervention is
+required. Furthermore, special care is required for code that may sleep [i.e.,
+may call schedule()], as NEON or VFP instructions will be executed in a
+non-preemptible section for reasons outlined below.
+
+
+Lazy preserve and restore
+-------------------------
+The NEON/VFP register file is managed using lazy preserve (on UP systems) and
+lazy restore (on both SMP and UP systems). This means that the register file is
+kept 'live', and is only preserved and restored when multiple tasks are
+contending for the NEON/VFP unit (or, in the SMP case, when a task migrates to
+another core). Lazy restore is implemented by disabling the NEON/VFP unit after
+every context switch, resulting in a trap when subsequently a NEON/VFP
+instruction is issued, allowing the kernel to step in and perform the restore if
+necessary.
+
+Any use of the NEON/VFP unit in kernel mode should not interfere with this, so
+it is required to do an 'eager' preserve of the NEON/VFP register file, and
+enable the NEON/VFP unit explicitly so no exceptions are generated on first
+subsequent use. This is handled by the function kernel_neon_begin(), which
+should be called before any kernel mode NEON or VFP instructions are issued.
+Likewise, the NEON/VFP unit should be disabled again after use to make sure user
+mode will hit the lazy restore trap upon next use. This is handled by the
+function kernel_neon_end().
+
+
+Interruptions in kernel mode
+----------------------------
+For reasons of performance and simplicity, it was decided that there shall be no
+preserve/restore mechanism for the kernel mode NEON/VFP register contents. This
+implies that interruptions of a kernel mode NEON section can only be allowed if
+they are guaranteed not to touch the NEON/VFP registers. For this reason, the
+following rules and restrictions apply in the kernel:
+* NEON/VFP code is not allowed in interrupt context;
+* NEON/VFP code is not allowed to sleep;
+* NEON/VFP code is executed with preemption disabled.
+
+If latency is a concern, it is possible to put back to back calls to
+kernel_neon_end() and kernel_neon_begin() in places in your code where none of
+the NEON registers are live. (Additional calls to kernel_neon_begin() should be
+reasonably cheap if no context switch occurred in the meantime)
+
+
+VFP and support code
+--------------------
+Earlier versions of VFP (prior to version 3) rely on software support for things
+like IEEE-754 compliant underflow handling etc. When the VFP unit needs such
+software assistance, it signals the kernel by raising an undefined instruction
+exception. The kernel responds by inspecting the VFP control registers and the
+current instruction and arguments, and emulates the instruction in software.
+
+Such software assistance is currently not implemented for VFP instructions
+executed in kernel mode. If such a condition is encountered, the kernel will
+fail and generate an OOPS.
+
+
+Separating NEON code from ordinary code
+---------------------------------------
+The compiler is not aware of the special significance of kernel_neon_begin() and
+kernel_neon_end(), i.e., that it is only allowed to issue NEON/VFP instructions
+between calls to these respective functions. Furthermore, GCC may generate NEON
+instructions of its own at -O3 level if -mfpu=neon is selected, and even if the
+kernel is currently compiled at -O2, future changes may result in NEON/VFP
+instructions appearing in unexpected places if no special care is taken.
+
+Therefore, the recommended and only supported way of using NEON/VFP in the
+kernel is by adhering to the following rules:
+* isolate the NEON code in a separate compilation unit and compile it with
+  '-mfpu=neon -mfloat-abi=softfp';
+* issue the calls to kernel_neon_begin(), kernel_neon_end() as well as the calls
+  into the unit containing the NEON code from a compilation unit which is *not*
+  built with the GCC flag '-mfpu=neon' set.
+
+As the kernel is compiled with '-msoft-float', the above will guarantee that
+both NEON and VFP instructions will only ever appear in designated compilation
+units at any optimization level.
+
+
+NEON assembler
+--------------
+NEON assembler is supported with no additional caveats as long as the rules
+above are followed.
+
+
+NEON code generated by GCC
+--------------------------
+The GCC option -ftree-vectorize (implied by -O3) tries to exploit implicit
+parallelism, and generates NEON code from ordinary C source code. This is fully
+supported as long as the rules above are followed.
+
+
+NEON intrinsics
+---------------
+NEON intrinsics are also supported. However, as code using NEON intrinsics
+relies on the GCC header <arm_neon.h>, (which #includes <stdint.h>), you should
+observe the following in addition to the rules above:
+* Compile the unit containing the NEON intrinsics with '-ffreestanding' so GCC
+  uses its builtin version of <stdint.h> (this is a C99 header which the kernel
+  does not supply);
+* Include <arm_neon.h> last, or at least after <linux/types.h>

Documentation/devicetree/bindings/arm/l2cc.txt

@@ -16,9 +16,11 @@ Required properties:
      performs the same operation).
 	"marvell,"aurora-outer-cache: Marvell Controller designed to be
 	 compatible with the ARM one with outer cache mode.
-	"bcm,bcm11351-a2-pl310-cache": For Broadcom bcm11351 chipset where an
+	"brcm,bcm11351-a2-pl310-cache": For Broadcom bcm11351 chipset where an
 	offset needs to be added to the address before passing down to the L2
 	cache controller
+	"bcm,bcm11351-a2-pl310-cache": DEPRECATED by
+	                               "brcm,bcm11351-a2-pl310-cache"
 - cache-unified : Specifies the cache is a unified cache.
 - cache-level : Should be set to 2 for a level 2 cache.
 - reg : Physical base address and size of cache controller's memory mapped

arch/arm/Kconfig

@@ -52,6 +52,7 @@ config ARM
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_UID16
+	select IRQ_FORCED_THREADING
 	select KTIME_SCALAR
 	select PERF_USE_VMALLOC
 	select RTC_LIB
@@ -1372,6 +1373,15 @@ config ARM_ERRATA_798181
 	  which sends an IPI to the CPUs that are running the same ASID
 	  as the one being invalidated.
 
+config ARM_ERRATA_773022
+	bool "ARM errata: incorrect instructions may be executed from loop buffer"
+	depends on CPU_V7
+	help
+	  This option enables the workaround for the 773022 Cortex-A15
+	  (up to r0p4) erratum. In certain rare sequences of code, the
+	  loop buffer may deliver incorrect instructions. This
+	  workaround disables the loop buffer to avoid the erratum.
+
 endmenu
 
 source "arch/arm/common/Kconfig"
@@ -1613,13 +1623,49 @@ config ARCH_NR_GPIO
 
 source kernel/Kconfig.preempt
 
-config HZ
+config HZ_FIXED
 	int
 	default 200 if ARCH_EBSA110 || ARCH_S3C24XX || ARCH_S5P64X0 || \
 		ARCH_S5PV210 || ARCH_EXYNOS4
 	default AT91_TIMER_HZ if ARCH_AT91
 	default SHMOBILE_TIMER_HZ if ARCH_SHMOBILE
-	default 100
+
+choice
+	depends on !HZ_FIXED
+	prompt "Timer frequency"
+
+config HZ_100
+	bool "100 Hz"
+
+config HZ_200
+	bool "200 Hz"
+
+config HZ_250
+	bool "250 Hz"
+
+config HZ_300
+	bool "300 Hz"
+
+config HZ_500
+	bool "500 Hz"
+
+config HZ_1000
+	bool "1000 Hz"
+
+endchoice
+
+config HZ
+	int
+	default HZ_FIXED if HZ_FIXED
+	default 100 if HZ_100
+	default 200 if HZ_200
+	default 250 if HZ_250
+	default 300 if HZ_300
+	default 500 if HZ_500
+	default 1000
+
+config SCHED_HRTICK
+	def_bool HIGH_RES_TIMERS
 
 config SCHED_HRTICK
 	def_bool HIGH_RES_TIMERS
@@ -1756,6 +1802,9 @@ config HAVE_ARCH_TRANSPARENT_HUGEPAGE
        def_bool y
        depends on ARM_LPAE
 
+config ARCH_WANT_GENERAL_HUGETLB
+	def_bool y
+
 source "mm/Kconfig"
 
 config FORCE_MAX_ZONEORDER
@@ -2174,6 +2223,13 @@ config NEON
 	  Say Y to include support code for NEON, the ARMv7 Advanced SIMD
 	  Extension.
 
+config KERNEL_MODE_NEON
+	bool "Support for NEON in kernel mode"
+	default n
+	depends on NEON
+	help
+	  Say Y to include support for NEON in kernel mode.
+
 endmenu
 
 menu "Userspace binary formats"
@@ -2198,7 +2254,7 @@ source "kernel/power/Kconfig"
 
 config ARCH_SUSPEND_POSSIBLE
 	depends on !ARCH_S5PC100
-	depends on CPU_ARM920T || CPU_ARM926T || CPU_SA1100 || \
+	depends on CPU_ARM920T || CPU_ARM926T || CPU_FEROCEON || CPU_SA1100 || \
 		CPU_V6 || CPU_V6K || CPU_V7 || CPU_XSC3 || CPU_XSCALE || CPU_MOHAWK
 	def_bool y
 

arch/arm/Kconfig.debug

@@ -92,6 +92,7 @@ choice
 	config DEBUG_BCM2835
 		bool "Kernel low-level debugging on BCM2835 PL011 UART"
 		depends on ARCH_BCM2835
+		select DEBUG_UART_PL01X
 
 	config DEBUG_CLPS711X_UART1
 		bool "Kernel low-level debugging messages via UART1"
@@ -110,6 +111,7 @@ choice
 	config DEBUG_CNS3XXX
 		bool "Kernel Kernel low-level debugging on Cavium Networks CNS3xxx"
 		depends on ARCH_CNS3XXX
+		select DEBUG_UART_PL01X
 		help
 		  Say Y here if you want the debug print routines to direct
                   their output to the CNS3xxx UART0.
@@ -117,6 +119,7 @@ choice
 	config DEBUG_DAVINCI_DA8XX_UART1
 		bool "Kernel low-level debugging on DaVinci DA8XX using UART1"
 		depends on ARCH_DAVINCI_DA8XX
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to UART1 serial port on DaVinci DA8XX devices.
@@ -124,6 +127,7 @@ choice
 	config DEBUG_DAVINCI_DA8XX_UART2
 		bool "Kernel low-level debugging on DaVinci DA8XX using UART2"
 		depends on ARCH_DAVINCI_DA8XX
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to UART2 serial port on DaVinci DA8XX devices.
@@ -131,6 +135,7 @@ choice
 	config DEBUG_DAVINCI_DMx_UART0
 		bool "Kernel low-level debugging on DaVinci DMx using UART0"
 		depends on ARCH_DAVINCI_DMx
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to UART0 serial port on DaVinci DMx devices.
@@ -138,6 +143,7 @@ choice
 	config DEBUG_DAVINCI_TNETV107X_UART1
 		bool "Kernel low-level debugging on DaVinci TNETV107x using UART1"
 		depends on ARCH_DAVINCI_TNETV107X
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to UART1 serial port on DaVinci TNETV107X
@@ -174,9 +180,26 @@ choice
 		  Say Y here if you want the debug print routines to direct
 		  their output to the 8250 at PCI COM1.
 
+	config DEBUG_HI3620_UART
+		bool "Hisilicon HI3620 Debug UART"
+		depends on ARCH_HI3xxx
+		select DEBUG_UART_PL01X
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on HI3620 UART.
+
+	config DEBUG_HI3716_UART
+		bool "Hisilicon Hi3716 Debug UART"
+		depends on ARCH_HI3xxx
+		select DEBUG_UART_PL01X
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on HI3716 UART.
+
 	config DEBUG_HIGHBANK_UART
 		bool "Kernel low-level debugging messages via Highbank UART"
 		depends on ARCH_HIGHBANK
+		select DEBUG_UART_PL01X
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to the UART on Highbank based devices.
@@ -191,6 +214,7 @@ choice
 	config DEBUG_IMX23_UART
 		bool "i.MX23 Debug UART"
 		depends on SOC_IMX23
+		select DEBUG_UART_PL01X
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on i.MX23.
@@ -212,6 +236,7 @@ choice
 	config DEBUG_IMX28_UART
 		bool "i.MX28 Debug UART"
 		depends on SOC_IMX28
+		select DEBUG_UART_PL01X
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on i.MX28.
@@ -261,6 +286,7 @@ choice
 	config DEBUG_KEYSTONE_UART0
 		bool "Kernel low-level debugging on KEYSTONE2 using UART0"
 		depends on ARCH_KEYSTONE
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to UART0 serial port on KEYSTONE2 devices.
@@ -268,6 +294,7 @@ choice
 	config DEBUG_KEYSTONE_UART1
 		bool "Kernel low-level debugging on KEYSTONE2 using UART1"
 		depends on ARCH_KEYSTONE
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to UART1 serial port on KEYSTONE2 devices.
@@ -275,6 +302,7 @@ choice
 	config DEBUG_MMP_UART2
 		bool "Kernel low-level debugging message via MMP UART2"
 		depends on ARCH_MMP
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on MMP UART2.
@@ -282,6 +310,7 @@ choice
 	config DEBUG_MMP_UART3
 		bool "Kernel low-level debugging message via MMP UART3"
 		depends on ARCH_MMP
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on MMP UART3.
@@ -326,6 +355,7 @@ choice
 	config DEBUG_MVEBU_UART
 		bool "Kernel low-level debugging messages via MVEBU UART (old bootloaders)"
 		depends on ARCH_MVEBU
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on MVEBU based platforms.
@@ -344,6 +374,7 @@ choice
 	config DEBUG_MVEBU_UART_ALTERNATE
 		bool "Kernel low-level debugging messages via MVEBU UART (new bootloaders)"
 		depends on ARCH_MVEBU
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on MVEBU based platforms.
@@ -358,6 +389,7 @@ choice
 	config DEBUG_NOMADIK_UART
 		bool "Kernel low-level debugging messages via NOMADIK UART"
 		depends on ARCH_NOMADIK
+		select DEBUG_UART_PL01X
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on NOMADIK based platforms.
@@ -365,6 +397,7 @@ choice
 	config DEBUG_NSPIRE_CLASSIC_UART
 		bool "Kernel low-level debugging via TI-NSPIRE 8250 UART"
 		depends on ARCH_NSPIRE
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on TI-NSPIRE classic models.
@@ -372,20 +405,82 @@ choice
 	config DEBUG_NSPIRE_CX_UART
 		bool "Kernel low-level debugging via TI-NSPIRE PL011 UART"
 		depends on ARCH_NSPIRE
+		select DEBUG_UART_PL01X
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on TI-NSPIRE CX models.
 
-	config DEBUG_OMAP2PLUS_UART
-		bool "Kernel low-level debugging messages via OMAP2PLUS UART"
+	config DEBUG_OMAP2UART1
+		bool "OMAP2/3/4 UART1 (omap2/3 sdp boards and some omap3 boards)"
 		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
 		help
-		  Say Y here if you want kernel low-level debugging support
-		  on OMAP2PLUS based platforms.
+		  This covers at least h4, 2430sdp, 3430sdp, 3630sdp,
+		  omap3 torpedo and 3530 lv som.
+
+	config DEBUG_OMAP2UART2
+		bool "Kernel low-level debugging messages via OMAP2/3/4 UART2"
+		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
+
+	config DEBUG_OMAP2UART3
+		bool "Kernel low-level debugging messages via OMAP2 UART3 (n8x0)"
+		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
+
+	config DEBUG_OMAP3UART3
+		bool "Kernel low-level debugging messages via OMAP3 UART3 (most omap3 boards)"
+		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
+		help
+		  This covers at least cm_t3x, beagle, crane, devkit8000,
+		  igep00x0, ldp, n900, n9(50), pandora, overo, touchbook,
+		  and 3517evm.
+
+	config DEBUG_OMAP4UART3
+		bool "Kernel low-level debugging messages via OMAP4/5 UART3 (omap4 blaze, panda, omap5 sevm)"
+		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
+
+	config DEBUG_OMAP3UART4
+		bool "Kernel low-level debugging messages via OMAP36XX UART4"
+		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
+
+	config DEBUG_OMAP4UART4
+		bool "Kernel low-level debugging messages via OMAP4/5 UART4"
+		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
+
+	config DEBUG_TI81XXUART1
+		bool "Kernel low-level debugging messages via TI81XX UART1 (ti8148evm)"
+		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
+
+	config DEBUG_TI81XXUART2
+		bool "Kernel low-level debugging messages via TI81XX UART2"
+		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
+
+	config DEBUG_TI81XXUART3
+		bool "Kernel low-level debugging messages via TI81XX UART3 (ti8168evm)"
+		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
+
+	config DEBUG_AM33XXUART1
+		bool "Kernel low-level debugging messages via AM33XX UART1"
+		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
+
+	config DEBUG_ZOOM_UART
+		bool "Kernel low-level debugging messages via Zoom2/3 UART"
+		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
 
 	config DEBUG_PICOXCELL_UART
 		depends on ARCH_PICOXCELL
 		bool "Use PicoXcell UART for low-level debug"
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on PicoXcell based platforms.
@@ -393,6 +488,7 @@ choice
 	config DEBUG_PXA_UART1
 		depends on ARCH_PXA
 		bool "Use PXA UART1 for low-level debug"
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on PXA UART1.
@@ -400,6 +496,7 @@ choice
 	config DEBUG_REALVIEW_STD_PORT
 		bool "RealView Default UART"
 		depends on ARCH_REALVIEW
+		select DEBUG_UART_PL01X
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to the serial port on RealView EB, PB11MP, PBA8
@@ -408,14 +505,64 @@ choice
 	config DEBUG_REALVIEW_PB1176_PORT
 		bool "RealView PB1176 UART"
 		depends on MACH_REALVIEW_PB1176
+		select DEBUG_UART_PL01X
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to the standard serial port on the RealView
 		  PB1176 platform.
 
-	config DEBUG_ROCKCHIP_UART
-		bool "Kernel low-level debugging messages via Rockchip UART"
+	config DEBUG_RK29_UART0
+		bool "Kernel low-level debugging messages via Rockchip RK29 UART0"
+		depends on ARCH_ROCKCHIP
+		select DEBUG_UART_8250
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on Rockchip based platforms.
+
+	config DEBUG_RK29_UART1
+		bool "Kernel low-level debugging messages via Rockchip RK29 UART1"
+		depends on ARCH_ROCKCHIP
+		select DEBUG_UART_8250
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on Rockchip based platforms.
+
+	config DEBUG_RK29_UART2
+		bool "Kernel low-level debugging messages via Rockchip RK29 UART2"
 		depends on ARCH_ROCKCHIP
+		select DEBUG_UART_8250
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on Rockchip based platforms.
+
+	config DEBUG_RK3X_UART0
+		bool "Kernel low-level debugging messages via Rockchip RK3X UART0"
+		depends on ARCH_ROCKCHIP
+		select DEBUG_UART_8250
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on Rockchip based platforms.
+
+	config DEBUG_RK3X_UART1
+		bool "Kernel low-level debugging messages via Rockchip RK3X UART1"
+		depends on ARCH_ROCKCHIP
+		select DEBUG_UART_8250
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on Rockchip based platforms.
+
+	config DEBUG_RK3X_UART2
+		bool "Kernel low-level debugging messages via Rockchip RK3X UART2"
+		depends on ARCH_ROCKCHIP
+		select DEBUG_UART_8250
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on Rockchip based platforms.
+
+	config DEBUG_RK3X_UART3
+		bool "Kernel low-level debugging messages via Rockchip RK3X UART3"
+		depends on ARCH_ROCKCHIP
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on Rockchip based platforms.
@@ -471,6 +618,7 @@ choice
 	config DEBUG_SOCFPGA_UART
 		depends on ARCH_SOCFPGA
 		bool "Use SOCFPGA UART for low-level debug"
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on SOCFPGA based platforms.
@@ -478,6 +626,7 @@ choice
 	config DEBUG_SUNXI_UART0
 		bool "Kernel low-level debugging messages via sunXi UART0"
 		depends on ARCH_SUNXI
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on Allwinner A1X based platforms on the UART0.
@@ -485,13 +634,59 @@ choice
 	config DEBUG_SUNXI_UART1
 		bool "Kernel low-level debugging messages via sunXi UART1"
 		depends on ARCH_SUNXI
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on Allwinner A1X based platforms on the UART1.
 
-	config DEBUG_TEGRA_UART
+	config TEGRA_DEBUG_UART_AUTO_ODMDATA
+		bool "Kernel low-level debugging messages via Tegra UART via ODMDATA"
+		depends on ARCH_TEGRA
+		select DEBUG_TEGRA_UART
+		help
+		  Automatically determines which UART to use for low-level
+		  debug based on the ODMDATA value. This value is part of
+		  the BCT, and is written to the boot memory device using
+		  nvflash, or other flashing tool.  When bits 19:18 are 3,
+		  then bits 17:15 indicate which UART to use; 0/1/2/3/4
+		  are UART A/B/C/D/E.
+
+	config TEGRA_DEBUG_UARTA
+		bool "Kernel low-level debugging messages via Tegra UART A"
+		depends on ARCH_TEGRA
+		select DEBUG_TEGRA_UART
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on Tegra based platforms.
+
+	config TEGRA_DEBUG_UARTB
+		bool "Kernel low-level debugging messages via Tegra UART B"
+		depends on ARCH_TEGRA
+		select DEBUG_TEGRA_UART
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on Tegra based platforms.
+
+	config TEGRA_DEBUG_UARTC
+		bool "Kernel low-level debugging messages via Tegra UART C"
+		depends on ARCH_TEGRA
+		select DEBUG_TEGRA_UART
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on Tegra based platforms.
+
+	config TEGRA_DEBUG_UARTD
+		bool "Kernel low-level debugging messages via Tegra UART D"
+		depends on ARCH_TEGRA
+		select DEBUG_TEGRA_UART
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on Tegra based platforms.
+
+	config TEGRA_DEBUG_UARTE
+		bool "Kernel low-level debugging messages via Tegra UART E"
 		depends on ARCH_TEGRA
-		bool "Use Tegra UART for low-level debug"
+		select DEBUG_TEGRA_UART
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on Tegra based platforms.
@@ -510,19 +705,32 @@ choice
 		  Say Y here if you want the debug print routines to direct
 		  their output to the uart1 port on SiRFmarco devices.
 
-	config DEBUG_STI_UART
+	config STIH41X_DEBUG_ASC2
+		bool "Use StiH415/416 ASC2 UART for low-level debug"
 		depends on ARCH_STI
-		bool "Use StiH415/416 ASC for low-level debug"
+		select DEBUG_STI_UART
 		help
 		  Say Y here if you want kernel low-level debugging support
-		  on StiH415/416 based platforms like B2000, B2020.
-		  It support UART2 and SBC_UART1.
+		  on STiH415/416 based platforms like b2000, which has
+		  default UART wired up to ASC2.
+
+		  If unsure, say N.
+
+	config STIH41X_DEBUG_SBC_ASC1
+		bool "Use StiH415/416 SBC ASC1 UART for low-level debug"
+		depends on ARCH_STI
+		select DEBUG_STI_UART
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on STiH415/416 based platforms like b2020. which has
+		  default UART wired up to SBC ASC1.
 
 		  If unsure, say N.
 
 	config DEBUG_U300_UART
 		bool "Kernel low-level debugging messages via U300 UART0"
 		depends on ARCH_U300
+		select DEBUG_UART_PL01X
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to the uart port on U300 devices.
@@ -548,6 +756,7 @@ choice
 	config DEBUG_VEXPRESS_UART0_CA9
 		bool "Use PL011 UART0 at 0x10009000 (V2P-CA9 core tile)"
 		depends on ARCH_VEXPRESS
+		select DEBUG_UART_PL01X
 		help
 		  This option selects UART0 at 0x10009000. Except for custom models,
 		  this applies only to the V2P-CA9 tile.
@@ -555,6 +764,7 @@ choice
 	config DEBUG_VEXPRESS_UART0_RS1
 		bool "Use PL011 UART0 at 0x1c090000 (RS1 complaint tiles)"
 		depends on ARCH_VEXPRESS
+		select DEBUG_UART_PL01X
 		help
 		  This option selects UART0 at 0x1c090000. This applies to most
 		  of the tiles using the RS1 memory map, including all new A-class
@@ -563,6 +773,7 @@ choice
 	config DEBUG_VEXPRESS_UART0_CRX
 		bool "Use PL011 UART0 at 0xb0090000 (Cortex-R compliant tiles)"
 		depends on ARCH_VEXPRESS && !MMU
+		select DEBUG_UART_PL01X
 		help
 		  This option selects UART0 at 0xb0090000. This is appropriate for
 		  Cortex-R series tiles and SMMs, such as Cortex-R5 and Cortex-R7
@@ -579,7 +790,7 @@ choice
 		depends on !ARCH_MULTIPLATFORM
 		help
 		  Say Y here if your platform doesn't provide a UART option
-		  below. This relies on your platform choosing the right UART
+		  above. This relies on your platform choosing the right UART
 		  definition internally in order for low-level debugging to
 		  work.
 
@@ -610,11 +821,41 @@ choice
 		  For more details about semihosting, please see
 		  chapter 8 of DUI0203I_rvct_developer_guide.pdf from ARM Ltd.
 
+	config DEBUG_LL_UART_8250
+		bool "Kernel low-level debugging via 8250 UART"
+		help
+		  Say Y here if you wish the debug print routes to direct
+		  their output to an 8250 UART.  You can use this option
+		  to provide the parameters for the 8250 UART rather than
+		  selecting one of the platform specific options above if
+		  you know the parameters for the port.
+
+		  This option is preferred over the platform specific
+		  options; the platform specific options are deprecated
+		  and will be soon removed.
+
+	config DEBUG_LL_UART_PL01X
+		bool "Kernel low-level debugging via ARM Ltd PL01x Primecell UART"
+		help
+		  Say Y here if you wish the debug print routes to direct
+		  their output to a PL01x Primecell UART.  You can use
+		  this option to provide the parameters for the UART
+		  rather than selecting one of the platform specific
+		  options above if you know the parameters for the port.
+
+		  This option is preferred over the platform specific
+		  options; the platform specific options are deprecated
+		  and will be soon removed.
+
 endchoice
 
 config DEBUG_EXYNOS_UART
 	bool
 
+config DEBUG_OMAP2PLUS_UART
+	bool
+	depends on ARCH_OMAP2PLUS
+
 config DEBUG_IMX_UART_PORT
 	int "i.MX Debug UART Port Selection" if DEBUG_IMX1_UART || \
 						DEBUG_IMX25_UART || \
@@ -631,140 +872,19 @@ config DEBUG_IMX_UART_PORT
 	  Choose UART port on which kernel low-level debug messages
 	  should be output.
 
-choice
-	prompt "Low-level debug console UART"
-	depends on DEBUG_OMAP2PLUS_UART
-
-	config DEBUG_OMAP2UART1
-		bool "OMAP2/3/4 UART1 (omap2/3 sdp boards and some omap3 boards)"
-		help
-		  This covers at least h4, 2430sdp, 3430sdp, 3630sdp,
-		  omap3 torpedo and 3530 lv som.
-
-	config DEBUG_OMAP2UART2
-		bool "OMAP2/3/4 UART2"
-
-	config DEBUG_OMAP2UART3
-		bool "OMAP2 UART3 (n8x0)"
-
-	config DEBUG_OMAP3UART3
-		bool "OMAP3 UART3 (most omap3 boards)"
-		help
-		  This covers at least cm_t3x, beagle, crane, devkit8000,
-		  igep00x0, ldp, n900, n9(50), pandora, overo, touchbook,
-		  and 3517evm.
-
-	config DEBUG_OMAP4UART3
-		bool "OMAP4/5 UART3 (omap4 blaze, panda, omap5 sevm)"
-
-	config DEBUG_OMAP3UART4
-		bool "OMAP36XX UART4"
-
-	config DEBUG_OMAP4UART4
-		bool "OMAP4/5 UART4"
-
-	config DEBUG_TI81XXUART1
-		bool "TI81XX UART1 (ti8148evm)"
-
-	config DEBUG_TI81XXUART2
-		bool "TI81XX UART2"
-
-	config DEBUG_TI81XXUART3
-		bool "TI81XX UART3 (ti8168evm)"
-
-	config DEBUG_AM33XXUART1
-		bool "AM33XX UART1"
-
-	config DEBUG_ZOOM_UART
-		bool "Zoom2/3 UART"
-endchoice
-
-choice
-	prompt "Low-level debug console UART"
-	depends on DEBUG_ROCKCHIP_UART
-
-	config DEBUG_RK29_UART0
-		bool "RK29 UART0"
-
-	config DEBUG_RK29_UART1
-		bool "RK29 UART1"
-
-	config DEBUG_RK29_UART2
-		bool "RK29 UART2"
-
-	config DEBUG_RK3X_UART0
-		bool "RK3X UART0"
-
-	config DEBUG_RK3X_UART1
-		bool "RK3X UART1"
-
-	config DEBUG_RK3X_UART2
-		bool "RK3X UART2"
-
-	config DEBUG_RK3X_UART3
-		bool "RK3X UART3"
-endchoice
-
-choice
-	prompt "Low-level debug console UART"
-	depends on DEBUG_LL && DEBUG_TEGRA_UART
-
-	config TEGRA_DEBUG_UART_AUTO_ODMDATA
-	bool "Via ODMDATA"
-	help
-	  Automatically determines which UART to use for low-level debug based
-	  on the ODMDATA value. This value is part of the BCT, and is written
-	  to the boot memory device using nvflash, or other flashing tool.
-	  When bits 19:18 are 3, then bits 17:15 indicate which UART to use;
-	  0/1/2/3/4 are UART A/B/C/D/E.
-
-	config TEGRA_DEBUG_UARTA
-		bool "UART A"
-
-	config TEGRA_DEBUG_UARTB
-		bool "UART B"
-
-	config TEGRA_DEBUG_UARTC
-		bool "UART C"
-
-	config TEGRA_DEBUG_UARTD
-		bool "UART D"
-
-	config TEGRA_DEBUG_UARTE
-		bool "UART E"
-
-endchoice
-
-choice
-	prompt "Low-level debug console UART"
-	depends on DEBUG_LL && DEBUG_STI_UART
-
-	config STIH41X_DEBUG_ASC2
-		bool "ASC2 UART"
-		help
-		  Say Y here if you want kernel low-level debugging support
-		  on STiH415/416 based platforms like b2000, which has
-		  default UART wired up to ASC2.
-
-		  If unsure, say N.
-
-	config STIH41X_DEBUG_SBC_ASC1
-		bool "SBC ASC1 UART"
-		help
-		  Say Y here if you want kernel low-level debugging support
-		  on STiH415/416 based platforms like b2020. which has
-		  default UART wired up to SBC ASC1.
-
-		  If unsure, say N.
+config DEBUG_TEGRA_UART
+	bool
+	depends on ARCH_TEGRA
 
-endchoice
+config DEBUG_STI_UART
+	bool
+	depends on ARCH_STI
 
 config DEBUG_LL_INCLUDE
 	string
-	default "debug/bcm2835.S" if DEBUG_BCM2835
-	default "debug/cns3xxx.S" if DEBUG_CNS3XXX
+	default "debug/8250.S" if DEBUG_LL_UART_8250 || DEBUG_UART_8250
+	default "debug/pl01x.S" if DEBUG_LL_UART_PL01X || DEBUG_UART_PL01X
 	default "debug/exynos.S" if DEBUG_EXYNOS_UART
-	default "debug/highbank.S" if DEBUG_HIGHBANK_UART
 	default "debug/icedcc.S" if DEBUG_ICEDCC
 	default "debug/imx.S" if DEBUG_IMX1_UART || \
 				 DEBUG_IMX25_UART || \
@@ -775,38 +895,170 @@ config DEBUG_LL_INCLUDE
 				 DEBUG_IMX53_UART ||\
 				 DEBUG_IMX6Q_UART || \
 				 DEBUG_IMX6SL_UART
-	default "debug/keystone.S" if DEBUG_KEYSTONE_UART0 || \
-				      DEBUG_KEYSTONE_UART1
-	default "debug/mvebu.S" if DEBUG_MVEBU_UART || \
-				   DEBUG_MVEBU_UART_ALTERNATE
-	default "debug/mxs.S" if DEBUG_IMX23_UART || DEBUG_IMX28_UART
-	default "debug/nomadik.S" if DEBUG_NOMADIK_UART
-	default "debug/nspire.S" if 	DEBUG_NSPIRE_CX_UART || \
-					DEBUG_NSPIRE_CLASSIC_UART
 	default "debug/omap2plus.S" if DEBUG_OMAP2PLUS_UART
-	default "debug/picoxcell.S" if DEBUG_PICOXCELL_UART
-	default "debug/pxa.S" if DEBUG_PXA_UART1 || DEBUG_MMP_UART2 || \
-				 DEBUG_MMP_UART3
-	default "debug/rockchip.S" if DEBUG_ROCKCHIP_UART
 	default "debug/sirf.S" if DEBUG_SIRFPRIMA2_UART1 || DEBUG_SIRFMARCO_UART1
-	default "debug/socfpga.S" if DEBUG_SOCFPGA_UART
 	default "debug/sti.S" if DEBUG_STI_UART
-	default "debug/sunxi.S" if DEBUG_SUNXI_UART0 || DEBUG_SUNXI_UART1
 	default "debug/tegra.S" if DEBUG_TEGRA_UART
-	default "debug/u300.S" if DEBUG_U300_UART
 	default "debug/ux500.S" if DEBUG_UX500_UART
-	default "debug/vexpress.S" if DEBUG_VEXPRESS_UART0_DETECT || \
-		DEBUG_VEXPRESS_UART0_CA9 || DEBUG_VEXPRESS_UART0_RS1 || \
-		DEBUG_VEXPRESS_UART0_CRX
+	default "debug/vexpress.S" if DEBUG_VEXPRESS_UART0_DETECT
 	default "debug/vt8500.S" if DEBUG_VT8500_UART0
 	default "debug/zynq.S" if DEBUG_ZYNQ_UART0 || DEBUG_ZYNQ_UART1
 	default "mach/debug-macro.S"
 
+# Compatibility options for PL01x
+config DEBUG_UART_PL01X
+	def_bool ARCH_EP93XX || \
+		ARCH_INTEGRATOR || \
+		ARCH_SPEAR3XX || \
+		ARCH_SPEAR6XX || \
+		ARCH_SPEAR13XX || \
+		ARCH_VERSATILE
+
+# Compatibility options for 8250
+config DEBUG_UART_8250
+	def_bool ARCH_DOVE || ARCH_EBSA110 || \
+		(FOOTBRIDGE && !DEBUG_DC21285_PORT) || \
+		ARCH_GEMINI || ARCH_IOP13XX || ARCH_IOP32X || \
+		ARCH_IOP33X || ARCH_IXP4XX || ARCH_KIRKWOOD || \
+		ARCH_LPC32XX || ARCH_MV78XX0 || ARCH_ORION5X || ARCH_RPC
+
+config DEBUG_UART_PHYS
+	hex "Physical base address of debug UART"
+	default 0x01c20000 if DEBUG_DAVINCI_DMx_UART0
+	default 0x01c28000 if DEBUG_SUNXI_UART0
+	default 0x01c28400 if DEBUG_SUNXI_UART1
+	default 0x01d0c000 if DEBUG_DAVINCI_DA8XX_UART1
+	default 0x01d0d000 if DEBUG_DAVINCI_DA8XX_UART2
+	default 0x02530c00 if DEBUG_KEYSTONE_UART0
+	default 0x02531000 if DEBUG_KEYSTONE_UART1
+	default 0x03010fe0 if ARCH_RPC
+	default 0x08108300 if DEBUG_DAVINCI_TNETV107X_UART1
+	default 0x10009000 if DEBUG_REALVIEW_STD_PORT || DEBUG_CNS3XXX || \
+				DEBUG_VEXPRESS_UART0_CA9
+	default 0x1010c000 if DEBUG_REALVIEW_PB1176_PORT
+	default 0x10124000 if DEBUG_RK3X_UART0
+	default 0x10126000 if DEBUG_RK3X_UART1
+	default 0x101f1000 if ARCH_VERSATILE
+	default 0x101fb000 if DEBUG_NOMADIK_UART
+	default 0x16000000 if ARCH_INTEGRATOR
+	default 0x1c090000 if DEBUG_VEXPRESS_UART0_RS1
+	default 0x20060000 if DEBUG_RK29_UART0
+	default 0x20064000 if DEBUG_RK29_UART1 || DEBUG_RK3X_UART2
+	default 0x20068000 if DEBUG_RK29_UART2 || DEBUG_RK3X_UART3
+	default 0x20201000 if DEBUG_BCM2835
+	default 0x40090000 if ARCH_LPC32XX
+	default 0x40100000 if DEBUG_PXA_UART1
+	default 0x42000000 if ARCH_GEMINI
+	default 0x7c0003f8 if FOOTBRIDGE
+	default 0x80230000 if DEBUG_PICOXCELL_UART
+	default 0x80070000 if DEBUG_IMX23_UART
+	default 0x80074000 if DEBUG_IMX28_UART
+	default 0x808c0000 if ARCH_EP93XX
+	default 0x90020000 if DEBUG_NSPIRE_CLASSIC_UART || DEBUG_NSPIRE_CX_UART
+	default 0xb0090000 if DEBUG_VEXPRESS_UART0_CRX
+	default 0xc0013000 if DEBUG_U300_UART
+	default 0xc8000000 if ARCH_IXP4XX && !CPU_BIG_ENDIAN
+	default 0xc8000003 if ARCH_IXP4XX && CPU_BIG_ENDIAN
+	default 0xd0000000 if ARCH_SPEAR3XX || ARCH_SPEAR6XX
+	default 0xd0012000 if DEBUG_MVEBU_UART
+	default 0xd4017000 if DEBUG_MMP_UART2
+	default 0xd4018000 if DEBUG_MMP_UART3
+	default 0xe0000000 if ARCH_SPEAR13XX
+	default 0xf0000be0 if ARCH_EBSA110
+	default 0xf1012000 if DEBUG_MVEBU_UART_ALTERNATE
+	default 0xf1012000 if ARCH_DOVE || ARCH_KIRKWOOD || ARCH_MV78XX0 || \
+				ARCH_ORION5X
+	default 0xf8b00000 if DEBUG_HI3716_UART
+	default 0xfcb00000 if DEBUG_HI3620_UART
+	default 0xfe800000 if ARCH_IOP32X
+	default 0xffc02000 if DEBUG_SOCFPGA_UART
+	default 0xffd82340 if ARCH_IOP13XX
+	default 0xfff36000 if DEBUG_HIGHBANK_UART
+	default 0xfffff700 if ARCH_IOP33X
+	depends on DEBUG_LL_UART_8250 || DEBUG_LL_UART_PL01X || \
+		DEBUG_UART_8250 || DEBUG_UART_PL01X
+
+config DEBUG_UART_VIRT
+	hex "Virtual base address of debug UART"
+	default 0xe0010fe0 if ARCH_RPC
+	default 0xf0000be0 if ARCH_EBSA110
+	default 0xf0009000 if DEBUG_CNS3XXX
+	default 0xf01fb000 if DEBUG_NOMADIK_UART
+	default 0xf0201000 if DEBUG_BCM2835
+	default 0xf11f1000 if ARCH_VERSATILE
+	default 0xf1600000 if ARCH_INTEGRATOR
+	default 0xf1c28000 if DEBUG_SUNXI_UART0
+	default 0xf1c28400 if DEBUG_SUNXI_UART1
+	default 0xf2100000 if DEBUG_PXA_UART1
+	default 0xf4090000 if ARCH_LPC32XX
+	default 0xf4200000 if ARCH_GEMINI
+	default 0xf8009000 if DEBUG_VEXPRESS_UART0_CA9
+	default 0xf8090000 if DEBUG_VEXPRESS_UART0_RS1
+	default 0xfb009000 if DEBUG_REALVIEW_STD_PORT
+	default 0xfb10c000 if DEBUG_REALVIEW_PB1176_PORT
+	default 0xfd000000 if ARCH_SPEAR3XX || ARCH_SPEAR6XX
+	default 0xfd000000 if ARCH_SPEAR13XX
+	default 0xfd012000 if ARCH_MV78XX0
+	default 0xfde12000 if ARCH_DOVE
+	default 0xfe012000 if ARCH_ORION5X
+	default 0xfe017000 if DEBUG_MMP_UART2
+	default 0xfe018000 if DEBUG_MMP_UART3
+	default 0xfe100000 if DEBUG_IMX23_UART || DEBUG_IMX28_UART
+	default 0xfe230000 if DEBUG_PICOXCELL_UART
+	default 0xfe800000 if ARCH_IOP32X
+	default 0xfeb00000 if DEBUG_HI3620_UART || DEBUG_HI3716_UART
+	default 0xfeb24000 if DEBUG_RK3X_UART0
+	default 0xfeb26000 if DEBUG_RK3X_UART1
+	default 0xfeb30c00 if DEBUG_KEYSTONE_UART0
+	default 0xfeb31000 if DEBUG_KEYSTONE_UART1
+	default 0xfec12000 if DEBUG_MVEBU_UART || DEBUG_MVEBU_UART_ALTERNATE
+	default 0xfed60000 if DEBUG_RK29_UART0
+	default 0xfed64000 if DEBUG_RK29_UART1 || DEBUG_RK3X_UART2
+	default 0xfed68000 if DEBUG_RK29_UART2 || DEBUG_RK3X_UART3
+	default 0xfec02000 if DEBUG_SOCFPGA_UART
+	default 0xfec20000 if DEBUG_DAVINCI_DMx_UART0
+	default 0xfed0c000 if DEBUG_DAVINCI_DA8XX_UART1
+	default 0xfed0d000 if DEBUG_DAVINCI_DA8XX_UART2
+	default 0xfed12000 if ARCH_KIRKWOOD
+	default 0xfedc0000 if ARCH_EP93XX
+	default 0xfee003f8 if FOOTBRIDGE
+	default 0xfee08300 if DEBUG_DAVINCI_TNETV107X_UART1
+	default 0xfee20000 if DEBUG_NSPIRE_CLASSIC_UART || DEBUG_NSPIRE_CX_UART
+	default 0xfef36000 if DEBUG_HIGHBANK_UART
+	default 0xfee82340 if ARCH_IOP13XX
+	default 0xfef00000 if ARCH_IXP4XX && !CPU_BIG_ENDIAN
+	default 0xfef00003 if ARCH_IXP4XX && CPU_BIG_ENDIAN
+	default 0xfefff700 if ARCH_IOP33X
+	default 0xff003000 if DEBUG_U300_UART
+	default DEBUG_UART_PHYS if !MMU
+	depends on DEBUG_LL_UART_8250 || DEBUG_LL_UART_PL01X || \
+		DEBUG_UART_8250 || DEBUG_UART_PL01X
+
+config DEBUG_UART_8250_SHIFT
+	int "Register offset shift for the 8250 debug UART"
+	depends on DEBUG_LL_UART_8250 || DEBUG_UART_8250
+	default 0 if FOOTBRIDGE || ARCH_IOP32X
+	default 2
+
+config DEBUG_UART_8250_WORD
+	bool "Use 32-bit accesses for 8250 UART"
+	depends on DEBUG_LL_UART_8250 || DEBUG_UART_8250
+	depends on DEBUG_UART_8250_SHIFT >= 2
+	default y if DEBUG_PICOXCELL_UART || DEBUG_SOCFPGA_UART || \
+		ARCH_KEYSTONE || \
+		DEBUG_DAVINCI_DMx_UART0 || DEBUG_DAVINCI_DA8XX_UART1 || \
+		DEBUG_DAVINCI_DA8XX_UART2 || DEBUG_DAVINCI_TNETV107X_UART1
+
+config DEBUG_UART_8250_FLOW_CONTROL
+	bool "Enable flow control for 8250 UART"
+	depends on DEBUG_LL_UART_8250 || DEBUG_UART_8250
+	default y if ARCH_EBSA110 || FOOTBRIDGE || ARCH_GEMINI || ARCH_RPC
+
 config DEBUG_UNCOMPRESS
 	bool
 	depends on ARCH_MULTIPLATFORM
 	default y if DEBUG_LL && !DEBUG_OMAP2PLUS_UART && \
-		     !DEBUG_TEGRA_UART
+		     (!DEBUG_TEGRA_UART || !ZBOOT_ROM)
 	help
 	  This option influences the normal decompressor output for
 	  multiplatform kernels.  Normally, multiplatform kernels disable

arch/arm/common/mcpm_head.S

@@ -151,7 +151,7 @@ mcpm_setup_leave:
 
 	mov	r0, #INBOUND_NOT_COMING_UP
 	strb	r0, [r8, #MCPM_SYNC_CLUSTER_INBOUND]
-	dsb
+	dsb	st
 	sev
 
 	mov	r0, r11

arch/arm/common/vlock.S

@@ -42,7 +42,7 @@
 	dmb
 	mov	\rscratch, #0
 	strb	\rscratch, [\rbase, \rcpu]
-	dsb
+	dsb	st
 	sev
 .endm
 
@@ -102,7 +102,7 @@ ENTRY(vlock_unlock)
 	dmb
 	mov	r1, #VLOCK_OWNER_NONE
 	strb	r1, [r0, #VLOCK_OWNER_OFFSET]
-	dsb
+	dsb	st
 	sev
 	bx	lr
 ENDPROC(vlock_unlock)

arch/arm/include/asm/assembler.h

@@ -220,9 +220,9 @@
 #ifdef CONFIG_SMP
 #if __LINUX_ARM_ARCH__ >= 7
 	.ifeqs "\mode","arm"
-	ALT_SMP(dmb)
+	ALT_SMP(dmb	ish)
 	.else
-	ALT_SMP(W(dmb))
+	ALT_SMP(W(dmb)	ish)
 	.endif
 #elif __LINUX_ARM_ARCH__ == 6
 	ALT_SMP(mcr	p15, 0, r0, c7, c10, 5)	@ dmb

arch/arm/include/asm/barrier.h

@@ -14,27 +14,27 @@
 #endif
 
 #if __LINUX_ARM_ARCH__ >= 7
-#define isb() __asm__ __volatile__ ("isb" : : : "memory")
-#define dsb() __asm__ __volatile__ ("dsb" : : : "memory")
-#define dmb() __asm__ __volatile__ ("dmb" : : : "memory")
+#define isb(option) __asm__ __volatile__ ("isb " #option : : : "memory")
+#define dsb(option) __asm__ __volatile__ ("dsb " #option : : : "memory")
+#define dmb(option) __asm__ __volatile__ ("dmb " #option : : : "memory")
 #elif defined(CONFIG_CPU_XSC3) || __LINUX_ARM_ARCH__ == 6
-#define isb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
+#define isb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
 				    : : "r" (0) : "memory")
-#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
+#define dsb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
 				    : : "r" (0) : "memory")
-#define dmb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 5" \
+#define dmb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 5" \
 				    : : "r" (0) : "memory")
 #elif defined(CONFIG_CPU_FA526)
-#define isb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
+#define isb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
 				    : : "r" (0) : "memory")
-#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
+#define dsb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
 				    : : "r" (0) : "memory")
-#define dmb() __asm__ __volatile__ ("" : : : "memory")
+#define dmb(x) __asm__ __volatile__ ("" : : : "memory")
 #else
-#define isb() __asm__ __volatile__ ("" : : : "memory")
-#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
+#define isb(x) __asm__ __volatile__ ("" : : : "memory")
+#define dsb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
 				    : : "r" (0) : "memory")
-#define dmb() __asm__ __volatile__ ("" : : : "memory")
+#define dmb(x) __asm__ __volatile__ ("" : : : "memory")
 #endif
 
 #ifdef CONFIG_ARCH_HAS_BARRIERS
@@ -42,7 +42,7 @@
 #elif defined(CONFIG_ARM_DMA_MEM_BUFFERABLE) || defined(CONFIG_SMP)
 #define mb()		do { dsb(); outer_sync(); } while (0)
 #define rmb()		dsb()
-#define wmb()		mb()
+#define wmb()		do { dsb(st); outer_sync(); } while (0)
 #else
 #define mb()		barrier()
 #define rmb()		barrier()
@@ -54,9 +54,9 @@
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
 #else
-#define smp_mb()	dmb()
-#define smp_rmb()	dmb()
-#define smp_wmb()	dmb()
+#define smp_mb()	dmb(ish)
+#define smp_rmb()	smp_mb()
+#define smp_wmb()	dmb(ishst)
 #endif
 
 #define read_barrier_depends()		do { } while(0)

arch/arm/include/asm/cacheflush.h

@@ -268,8 +268,7 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr
  * Harvard caches are synchronised for the user space address range.
  * This is used for the ARM private sys_cacheflush system call.
  */
-#define flush_cache_user_range(start,end) \
-	__cpuc_coherent_user_range((start) & PAGE_MASK, PAGE_ALIGN(end))
+#define flush_cache_user_range(s,e)	__cpuc_coherent_user_range(s,e)
 
 /*
  * Perform necessary cache operations to ensure that data previously
@@ -352,7 +351,7 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 		 * set_pte_at() called from vmap_pte_range() does not
 		 * have a DSB after cleaning the cache line.
 		 */
-		dsb();
+		dsb(ishst);
 }
 
 static inline void flush_cache_vunmap(unsigned long start, unsigned long end)

arch/arm/include/asm/mach/arch.h

@@ -65,12 +65,12 @@ struct machine_desc {
 /*
  * Current machine - only accessible during boot.
  */
-extern struct machine_desc *machine_desc;
+extern const struct machine_desc *machine_desc;
 
 /*
  * Machine type table - also only accessible during boot
  */
-extern struct machine_desc __arch_info_begin[], __arch_info_end[];
+extern const struct machine_desc __arch_info_begin[], __arch_info_end[];
 #define for_each_machine_desc(p)			\
 	for (p = __arch_info_begin; p < __arch_info_end; p++)
 

arch/arm/include/asm/memblock.h

@@ -4,8 +4,7 @@
 struct meminfo;
 struct machine_desc;
 
-extern void arm_memblock_init(struct meminfo *, struct machine_desc *);
-
+void arm_memblock_init(struct meminfo *, const struct machine_desc *);
 phys_addr_t arm_memblock_steal(phys_addr_t size, phys_addr_t align);
 
 #endif

arch/arm/include/asm/module.h

@@ -12,6 +12,8 @@ enum {
 	ARM_SEC_CORE,
 	ARM_SEC_EXIT,
 	ARM_SEC_DEVEXIT,
+	ARM_SEC_HOT,
+	ARM_SEC_UNLIKELY,
 	ARM_SEC_MAX,
 };
 

arch/arm/include/asm/neon.h

+/*
+ * linux/arch/arm/include/asm/neon.h
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * 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 <asm/hwcap.h>
+
+#define cpu_has_neon()		(!!(elf_hwcap & HWCAP_NEON))
+
+#ifdef __ARM_NEON__
+
+/*
+ * If you are affected by the BUILD_BUG below, it probably means that you are
+ * using NEON code /and/ calling the kernel_neon_begin() function from the same
+ * compilation unit. To prevent issues that may arise from GCC reordering or
+ * generating(1) NEON instructions outside of these begin/end functions, the
+ * only supported way of using NEON code in the kernel is by isolating it in a
+ * separate compilation unit, and calling it from another unit from inside a
+ * kernel_neon_begin/kernel_neon_end pair.
+ *
+ * (1) Current GCC (4.7) might generate NEON instructions at O3 level if
+ *     -mpfu=neon is set.
+ */
+
+#define kernel_neon_begin() \
+	BUILD_BUG_ON_MSG(1, "kernel_neon_begin() called from NEON code")
+
+#else
+void kernel_neon_begin(void);
+#endif
+void kernel_neon_end(void);

arch/arm/include/asm/pgtable.h

@@ -100,7 +100,7 @@ extern pgprot_t		pgprot_s2_device;
 #define PAGE_HYP		_MOD_PROT(pgprot_kernel, L_PTE_HYP)
 #define PAGE_HYP_DEVICE		_MOD_PROT(pgprot_hyp_device, L_PTE_HYP)
 #define PAGE_S2			_MOD_PROT(pgprot_s2, L_PTE_S2_RDONLY)
-#define PAGE_S2_DEVICE		_MOD_PROT(pgprot_s2_device, L_PTE_USER | L_PTE_S2_RDONLY)
+#define PAGE_S2_DEVICE		_MOD_PROT(pgprot_s2_device, L_PTE_S2_RDWR)
 
 #define __PAGE_NONE		__pgprot(_L_PTE_DEFAULT | L_PTE_RDONLY | L_PTE_XN | L_PTE_NONE)
 #define __PAGE_SHARED		__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_XN)

arch/arm/include/asm/prom.h

@@ -15,13 +15,13 @@
 
 #ifdef CONFIG_OF
 
-extern struct machine_desc *setup_machine_fdt(unsigned int dt_phys);
+extern const struct machine_desc *setup_machine_fdt(unsigned int dt_phys);
 extern void arm_dt_memblock_reserve(void);
 extern void __init arm_dt_init_cpu_maps(void);
 
 #else /* CONFIG_OF */
 
-static inline struct machine_desc *setup_machine_fdt(unsigned int dt_phys)
+static inline const struct machine_desc *setup_machine_fdt(unsigned int dt_phys)
 {
 	return NULL;
 }

arch/arm/include/asm/spinlock.h

@@ -46,7 +46,7 @@ static inline void dsb_sev(void)
 {
 #if __LINUX_ARM_ARCH__ >= 7
 	__asm__ __volatile__ (
-		"dsb\n"
+		"dsb ishst\n"
 		SEV
 	);
 #else

arch/arm/include/asm/switch_to.h

@@ -3,6 +3,16 @@
 
 #include <linux/thread_info.h>
 
+/*
+ * For v7 SMP cores running a preemptible kernel we may be pre-empted
+ * during a TLB maintenance operation, so execute an inner-shareable dsb
+ * to ensure that the maintenance completes in case we migrate to another
+ * CPU.
+ */
+#if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP) && defined(CONFIG_CPU_V7)
+#define finish_arch_switch(prev)	dsb(ish)
+#endif
+
 /*
  * switch_to(prev, next) should switch from task `prev' to `next'
  * `prev' will never be the same as `next'.  schedule() itself

arch/arm/include/asm/thread_info.h

@@ -43,6 +43,16 @@ struct cpu_context_save {
 	__u32	extra[2];		/* Xscale 'acc' register, etc */
 };
 
+struct arm_restart_block {
+	union {
+		/* For user cache flushing */
+		struct {
+			unsigned long start;
+			unsigned long end;
+		} cache;
+	};
+};
+
 /*
  * low level task data that entry.S needs immediate access to.
  * __switch_to() assumes cpu_context follows immediately after cpu_domain.
@@ -68,6 +78,7 @@ struct thread_info {
 	unsigned long		thumbee_state;	/* ThumbEE Handler Base register */
 #endif
 	struct restart_block	restart_block;
+	struct arm_restart_block	arm_restart_block;
 };
 
 #define INIT_THREAD_INFO(tsk)						\

arch/arm/include/asm/tlbflush.h

@@ -319,67 +319,110 @@ extern struct cpu_tlb_fns cpu_tlb;
 #define tlb_op(f, regs, arg)	__tlb_op(f, "p15, 0, %0, " regs, arg)
 #define tlb_l2_op(f, regs, arg)	__tlb_op(f, "p15, 1, %0, " regs, arg)
 
-static inline void local_flush_tlb_all(void)
+static inline void __local_flush_tlb_all(void)
 {
 	const int zero = 0;
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
-	if (tlb_flag(TLB_WB))
-		dsb();
-
 	tlb_op(TLB_V4_U_FULL | TLB_V6_U_FULL, "c8, c7, 0", zero);
 	tlb_op(TLB_V4_D_FULL | TLB_V6_D_FULL, "c8, c6, 0", zero);
 	tlb_op(TLB_V4_I_FULL | TLB_V6_I_FULL, "c8, c5, 0", zero);
-	tlb_op(TLB_V7_UIS_FULL, "c8, c3, 0", zero);
+}
+
+static inline void local_flush_tlb_all(void)
+{
+	const int zero = 0;
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (tlb_flag(TLB_WB))
+		dsb(nshst);
+
+	__local_flush_tlb_all();
+	tlb_op(TLB_V7_UIS_FULL, "c8, c7, 0", zero);
 
 	if (tlb_flag(TLB_BARRIER)) {
-		dsb();
+		dsb(nsh);
 		isb();
 	}
 }
 
-static inline void local_flush_tlb_mm(struct mm_struct *mm)
+static inline void __flush_tlb_all(void)
 {
 	const int zero = 0;
-	const int asid = ASID(mm);
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
 	if (tlb_flag(TLB_WB))
-		dsb();
+		dsb(ishst);
+
+	__local_flush_tlb_all();
+	tlb_op(TLB_V7_UIS_FULL, "c8, c3, 0", zero);
+
+	if (tlb_flag(TLB_BARRIER)) {
+		dsb(ish);
+		isb();
+	}
+}
+
+static inline void __local_flush_tlb_mm(struct mm_struct *mm)
+{
+	const int zero = 0;
+	const int asid = ASID(mm);
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
 	if (possible_tlb_flags & (TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) {
-		if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) {
+		if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) {
 			tlb_op(TLB_V4_U_FULL, "c8, c7, 0", zero);
 			tlb_op(TLB_V4_D_FULL, "c8, c6, 0", zero);
 			tlb_op(TLB_V4_I_FULL, "c8, c5, 0", zero);
 		}
-		put_cpu();
 	}
 
 	tlb_op(TLB_V6_U_ASID, "c8, c7, 2", asid);
 	tlb_op(TLB_V6_D_ASID, "c8, c6, 2", asid);
 	tlb_op(TLB_V6_I_ASID, "c8, c5, 2", asid);
+}
+
+static inline void local_flush_tlb_mm(struct mm_struct *mm)
+{
+	const int asid = ASID(mm);
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (tlb_flag(TLB_WB))
+		dsb(nshst);
+
+	__local_flush_tlb_mm(mm);
+	tlb_op(TLB_V7_UIS_ASID, "c8, c7, 2", asid);
+
+	if (tlb_flag(TLB_BARRIER))
+		dsb(nsh);
+}
+
+static inline void __flush_tlb_mm(struct mm_struct *mm)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (tlb_flag(TLB_WB))
+		dsb(ishst);
+
+	__local_flush_tlb_mm(mm);
 #ifdef CONFIG_ARM_ERRATA_720789
-	tlb_op(TLB_V7_UIS_ASID, "c8, c3, 0", zero);
+	tlb_op(TLB_V7_UIS_ASID, "c8, c3, 0", 0);
 #else
-	tlb_op(TLB_V7_UIS_ASID, "c8, c3, 2", asid);
+	tlb_op(TLB_V7_UIS_ASID, "c8, c3, 2", ASID(mm));
 #endif
 
 	if (tlb_flag(TLB_BARRIER))
-		dsb();
+		dsb(ish);
 }
 
 static inline void
-local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
+__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 {
 	const int zero = 0;
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
 	uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm);
 
-	if (tlb_flag(TLB_WB))
-		dsb();
-
 	if (possible_tlb_flags & (TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) &&
 	    cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
 		tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", uaddr);
@@ -392,6 +435,36 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 	tlb_op(TLB_V6_U_PAGE, "c8, c7, 1", uaddr);
 	tlb_op(TLB_V6_D_PAGE, "c8, c6, 1", uaddr);
 	tlb_op(TLB_V6_I_PAGE, "c8, c5, 1", uaddr);
+}
+
+static inline void
+local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm);
+
+	if (tlb_flag(TLB_WB))
+		dsb(nshst);
+
+	__local_flush_tlb_page(vma, uaddr);
+	tlb_op(TLB_V7_UIS_PAGE, "c8, c7, 1", uaddr);
+
+	if (tlb_flag(TLB_BARRIER))
+		dsb(nsh);
+}
+
+static inline void
+__flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm);
+
+	if (tlb_flag(TLB_WB))
+		dsb(ishst);
+
+	__local_flush_tlb_page(vma, uaddr);
 #ifdef CONFIG_ARM_ERRATA_720789
 	tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 3", uaddr & PAGE_MASK);
 #else
@@ -399,19 +472,14 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 #endif
 
 	if (tlb_flag(TLB_BARRIER))
-		dsb();
+		dsb(ish);
 }
 
-static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
+static inline void __local_flush_tlb_kernel_page(unsigned long kaddr)
 {
 	const int zero = 0;
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
-	kaddr &= PAGE_MASK;
-
-	if (tlb_flag(TLB_WB))
-		dsb();
-
 	tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", kaddr);
 	tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", kaddr);
 	tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", kaddr);
@@ -421,26 +489,75 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
 	tlb_op(TLB_V6_U_PAGE, "c8, c7, 1", kaddr);
 	tlb_op(TLB_V6_D_PAGE, "c8, c6, 1", kaddr);
 	tlb_op(TLB_V6_I_PAGE, "c8, c5, 1", kaddr);
+}
+
+static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	kaddr &= PAGE_MASK;
+
+	if (tlb_flag(TLB_WB))
+		dsb(nshst);
+
+	__local_flush_tlb_kernel_page(kaddr);
+	tlb_op(TLB_V7_UIS_PAGE, "c8, c7, 1", kaddr);
+
+	if (tlb_flag(TLB_BARRIER)) {
+		dsb(nsh);
+		isb();
+	}
+}
+
+static inline void __flush_tlb_kernel_page(unsigned long kaddr)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	kaddr &= PAGE_MASK;
+
+	if (tlb_flag(TLB_WB))
+		dsb(ishst);
+
+	__local_flush_tlb_kernel_page(kaddr);
 	tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 1", kaddr);
 
 	if (tlb_flag(TLB_BARRIER)) {
-		dsb();
+		dsb(ish);
 		isb();
 	}
 }
 
+/*
+ * Branch predictor maintenance is paired with full TLB invalidation, so
+ * there is no need for any barriers here.
+ */
+static inline void __local_flush_bp_all(void)
+{
+	const int zero = 0;
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (tlb_flag(TLB_V6_BP))
+		asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero));
+}
+
 static inline void local_flush_bp_all(void)
 {
 	const int zero = 0;
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
+	__local_flush_bp_all();
 	if (tlb_flag(TLB_V7_UIS_BP))
-		asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero));
-	else if (tlb_flag(TLB_V6_BP))
 		asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero));
+}
 
-	if (tlb_flag(TLB_BARRIER))
-		isb();
+static inline void __flush_bp_all(void)
+{
+	const int zero = 0;
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	__local_flush_bp_all();
+	if (tlb_flag(TLB_V7_UIS_BP))
+		asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero));
 }
 
 #include <asm/cputype.h>
@@ -461,7 +578,7 @@ static inline void dummy_flush_tlb_a15_erratum(void)
 	 * Dummy TLBIMVAIS. Using the unmapped address 0 and ASID 0.
 	 */
 	asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0));
-	dsb();
+	dsb(ish);
 }
 #else
 static inline int erratum_a15_798181(void)
@@ -495,7 +612,7 @@ static inline void flush_pmd_entry(void *pmd)
 	tlb_l2_op(TLB_L2CLEAN_FR, "c15, c9, 1  @ L2 flush_pmd", pmd);
 
 	if (tlb_flag(TLB_WB))
-		dsb();
+		dsb(ishst);
 }
 
 static inline void clean_pmd_entry(void *pmd)

arch/arm/include/asm/types.h

+#ifndef _ASM_TYPES_H
+#define _ASM_TYPES_H
+
+#include <asm-generic/int-ll64.h>
+
+/*
+ * The C99 types uintXX_t that are usually defined in 'stdint.h' are not as
+ * unambiguous on ARM as you would expect. For the types below, there is a
+ * difference on ARM between GCC built for bare metal ARM, GCC built for glibc
+ * and the kernel itself, which results in build errors if you try to build with
+ * -ffreestanding and include 'stdint.h' (such as when you include 'arm_neon.h'
+ * in order to use NEON intrinsics)
+ *
+ * As the typedefs for these types in 'stdint.h' are based on builtin defines
+ * supplied by GCC, we can tweak these to align with the kernel's idea of those
+ * types, so 'linux/types.h' and 'stdint.h' can be safely included from the same
+ * source file (provided that -ffreestanding is used).
+ *
+ *                    int32_t         uint32_t               uintptr_t
+ * bare metal GCC     long            unsigned long          unsigned int
+ * glibc GCC          int             unsigned int           unsigned int
+ * kernel             int             unsigned int           unsigned long
+ */
+
+#ifdef __INT32_TYPE__
+#undef __INT32_TYPE__
+#define __INT32_TYPE__		int
+#endif
+
+#ifdef __UINT32_TYPE__
+#undef __UINT32_TYPE__
+#define __UINT32_TYPE__	unsigned int
+#endif
+
+#ifdef __UINTPTR_TYPE__
+#undef __UINTPTR_TYPE__
+#define __UINTPTR_TYPE__	unsigned long
+#endif
+
+#endif /* _ASM_TYPES_H */

arch/arm/include/asm/v7m.h

@@ -15,6 +15,10 @@
 
 #define V7M_SCB_VTOR			0x08
 
+#define V7M_SCB_AIRCR			0x0c
+#define V7M_SCB_AIRCR_VECTKEY			(0x05fa << 16)
+#define V7M_SCB_AIRCR_SYSRESETREQ		(1 << 2)
+
 #define V7M_SCB_SCR			0x10
 #define V7M_SCB_SCR_SLEEPDEEP			(1 << 2)
 
@@ -42,3 +46,11 @@
  */
 #define EXC_RET_STACK_MASK			0x00000004
 #define EXC_RET_THREADMODE_PROCESSSTACK		0xfffffffd
+
+#ifndef __ASSEMBLY__
+
+enum reboot_mode;
+
+void armv7m_restart(enum reboot_mode mode, const char *cmd);
+
+#endif /* __ASSEMBLY__ */

arch/arm/include/asm/xor.h

@@ -7,7 +7,10 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#include <linux/hardirq.h>
 #include <asm-generic/xor.h>
+#include <asm/hwcap.h>
+#include <asm/neon.h>
 
 #define __XOR(a1, a2) a1 ^= a2
 
@@ -138,4 +141,74 @@ static struct xor_block_template xor_block_arm4regs = {
 		xor_speed(&xor_block_arm4regs);	\
 		xor_speed(&xor_block_8regs);	\
 		xor_speed(&xor_block_32regs);	\
+		NEON_TEMPLATES;			\
 	} while (0)
+
+#ifdef CONFIG_KERNEL_MODE_NEON
+
+extern struct xor_block_template const xor_block_neon_inner;
+
+static void
+xor_neon_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+	if (in_interrupt()) {
+		xor_arm4regs_2(bytes, p1, p2);
+	} else {
+		kernel_neon_begin();
+		xor_block_neon_inner.do_2(bytes, p1, p2);
+		kernel_neon_end();
+	}
+}
+
+static void
+xor_neon_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+		unsigned long *p3)
+{
+	if (in_interrupt()) {
+		xor_arm4regs_3(bytes, p1, p2, p3);
+	} else {
+		kernel_neon_begin();
+		xor_block_neon_inner.do_3(bytes, p1, p2, p3);
+		kernel_neon_end();
+	}
+}
+
+static void
+xor_neon_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+		unsigned long *p3, unsigned long *p4)
+{
+	if (in_interrupt()) {
+		xor_arm4regs_4(bytes, p1, p2, p3, p4);
+	} else {
+		kernel_neon_begin();
+		xor_block_neon_inner.do_4(bytes, p1, p2, p3, p4);
+		kernel_neon_end();
+	}
+}
+
+static void
+xor_neon_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+		unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+	if (in_interrupt()) {
+		xor_arm4regs_5(bytes, p1, p2, p3, p4, p5);
+	} else {
+		kernel_neon_begin();
+		xor_block_neon_inner.do_5(bytes, p1, p2, p3, p4, p5);
+		kernel_neon_end();
+	}
+}
+
+static struct xor_block_template xor_block_neon = {
+	.name	= "neon",
+	.do_2	= xor_neon_2,
+	.do_3	= xor_neon_3,
+	.do_4	= xor_neon_4,
+	.do_5	= xor_neon_5
+};
+
+#define NEON_TEMPLATES	\
+	do { if (cpu_has_neon()) xor_speed(&xor_block_neon); } while (0)
+#else
+#define NEON_TEMPLATES
+#endif

arch/arm/include/asm/hardware/debug-8250.S → arch/arm/include/debug/8250.S

 /*
- * arch/arm/include/asm/hardware/debug-8250.S
+ * arch/arm/include/debug/8250.S
  *
- *  Copyright (C) 1994-1999 Russell King
+ *  Copyright (C) 1994-2013 Russell King
  *
  * 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
@@ -9,20 +9,45 @@
  */
 #include <linux/serial_reg.h>
 
+		.macro	addruart, rp, rv, tmp
+		ldr	\rp, =CONFIG_DEBUG_UART_PHYS
+		ldr	\rv, =CONFIG_DEBUG_UART_VIRT
+		.endm
+
+#ifdef CONFIG_DEBUG_UART_8250_WORD
+		.macro	store, rd, rx:vararg
+		str	\rd, \rx
+		.endm
+
+		.macro	load, rd, rx:vararg
+		ldr	\rd, \rx
+		.endm
+#else
+		.macro	store, rd, rx:vararg
+		strb	\rd, \rx
+		.endm
+
+		.macro	load, rd, rx:vararg
+		ldrb	\rd, \rx
+		.endm
+#endif
+
+#define UART_SHIFT CONFIG_DEBUG_UART_8250_SHIFT
+
 		.macro	senduart,rd,rx
-		strb	\rd, [\rx, #UART_TX << UART_SHIFT]
+		store	\rd, [\rx, #UART_TX << UART_SHIFT]
 		.endm
 
 		.macro	busyuart,rd,rx
-1002:		ldrb	\rd, [\rx, #UART_LSR << UART_SHIFT]
+1002:		load	\rd, [\rx, #UART_LSR << UART_SHIFT]
 		and	\rd, \rd, #UART_LSR_TEMT | UART_LSR_THRE
 		teq	\rd, #UART_LSR_TEMT | UART_LSR_THRE
 		bne	1002b
 		.endm
 
 		.macro	waituart,rd,rx
-#ifdef FLOW_CONTROL
-1001:		ldrb	\rd, [\rx, #UART_MSR << UART_SHIFT]
+#ifdef CONFIG_DEBUG_UART_8250_FLOW_CONTROL
+1001:		load	\rd, [\rx, #UART_MSR << UART_SHIFT]
 		tst	\rd, #UART_MSR_CTS
 		beq	1001b
 #endif

arch/arm/include/debug/8250_32.S

-/*
- * Copyright (c) 2011 Picochip Ltd., Jamie Iles
- *
- * 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.
- *
- * Derived from arch/arm/mach-davinci/include/mach/debug-macro.S to use 32-bit
- * accesses to the 8250.
- */
-
-#include <linux/serial_reg.h>
-
-		.macro	senduart,rd,rx
-		str	\rd, [\rx, #UART_TX << UART_SHIFT]
-		.endm
-
-		.macro	busyuart,rd,rx
-1002:		ldr	\rd, [\rx, #UART_LSR << UART_SHIFT]
-		and	\rd, \rd, #UART_LSR_TEMT | UART_LSR_THRE
-		teq	\rd, #UART_LSR_TEMT | UART_LSR_THRE
-		bne	1002b
-		.endm
-
-		/* The UART's don't have any flow control IO's wired up. */
-		.macro	waituart,rd,rx
-		.endm

arch/arm/include/debug/bcm2835.S

-/*
- * Debugging macro include header
- *
- * Copyright (C) 2010 Broadcom
- * Copyright (C) 1994-1999 Russell King
- * Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * 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.
- *
- */
-
-#define BCM2835_DEBUG_PHYS 0x20201000
-#define BCM2835_DEBUG_VIRT 0xf0201000
-
-	.macro	addruart, rp, rv, tmp
-	ldr	\rp, =BCM2835_DEBUG_PHYS
-	ldr	\rv, =BCM2835_DEBUG_VIRT
-	.endm
-
-#include <asm/hardware/debug-pl01x.S>

arch/arm/include/debug/cns3xxx.S

-/*
- * Debugging macro include header
- *
- * Copyright 1994-1999 Russell King
- * Copyright 2008 Cavium Networks
- * Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * This file 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.
- */
-
-		.macro	addruart,rp,rv,tmp
-		mov	\rp, #0x00009000
-		orr	\rv, \rp, #0xf0000000	@ virtual base
-		orr	\rp, \rp, #0x10000000
-		.endm
-
-#include <asm/hardware/debug-pl01x.S>

arch/arm/include/debug/highbank.S

-/*
- * Debugging macro include header
- *
- *  Copyright (C) 1994-1999 Russell King
- *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * 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.
- */
-
-		.macro	addruart,rp,rv,tmp
-		ldr	\rv, =0xfee36000
-		ldr	\rp, =0xfff36000
-		.endm
-
-#include <asm/hardware/debug-pl01x.S>

arch/arm/include/debug/keystone.S

-/*
- * Early serial debug output macro for Keystone SOCs
- *
- * Copyright 2013 Texas Instruments, Inc.
- *	Santosh Shilimkar <santosh.shilimkar@ti.com>
- *
- * Based on RMKs low level debug code.
- *  Copyright (C) 1994-1999 Russell King
- *
- * 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/serial_reg.h>
-
-#define UART_SHIFT 2
-#if defined(CONFIG_DEBUG_KEYSTONE_UART0)
-#define UART_PHYS		0x02530c00
-#define UART_VIRT		0xfeb30c00
-#elif defined(CONFIG_DEBUG_KEYSTONE_UART1)
-#define UART_PHYS		0x02531000
-#define UART_VIRT		0xfeb31000
-#endif
-
-	.macro	addruart, rp, rv, tmp
-	ldr	\rv, =UART_VIRT			@ physical base address
-	ldr	\rp, =UART_PHYS			@ virtual base address
-	.endm
-
-	.macro	senduart,rd,rx
-	str	\rd, [\rx, #UART_TX << UART_SHIFT]
-	.endm
-
-	.macro	busyuart,rd,rx
-1002:	ldr	\rd, [\rx, #UART_LSR << UART_SHIFT]
-	and	\rd, \rd, #UART_LSR_TEMT | UART_LSR_THRE
-	teq	\rd, #UART_LSR_TEMT | UART_LSR_THRE
-	bne	1002b
-	.endm
-
-	.macro	waituart,rd,rx
-	.endm

arch/arm/include/debug/mvebu.S

-/*
- * Early serial output macro for Marvell  SoC
- *
- * Copyright (C) 2012 Marvell
- *
- * Lior Amsalem <alior@marvell.com>
- * Gregory Clement <gregory.clement@free-electrons.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.
-*/
-
-#ifdef CONFIG_DEBUG_MVEBU_UART_ALTERNATE
-#define ARMADA_370_XP_REGS_PHYS_BASE	0xf1000000
-#else
-#define ARMADA_370_XP_REGS_PHYS_BASE	0xd0000000
-#endif
-
-#define ARMADA_370_XP_REGS_VIRT_BASE	0xfec00000
-
-	.macro	addruart, rp, rv, tmp
-	ldr	\rp, =ARMADA_370_XP_REGS_PHYS_BASE
-	ldr	\rv, =ARMADA_370_XP_REGS_VIRT_BASE
-	orr	\rp, \rp, #0x00012000
-	orr	\rv, \rv, #0x00012000
-	.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>

arch/arm/include/debug/mxs.S

-/* arch/arm/mach-mxs/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- *  Copyright (C) 1994-1999 Russell King
- *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * 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.
- *
- */
-
-#ifdef CONFIG_DEBUG_IMX23_UART
-#define UART_PADDR	0x80070000
-#elif defined (CONFIG_DEBUG_IMX28_UART)
-#define UART_PADDR	0x80074000
-#endif
-
-#define UART_VADDR	0xfe100000
-
-		.macro	addruart, rp, rv, tmp
-		ldr	\rp, =UART_PADDR	@ physical
-		ldr	\rv, =UART_VADDR	@ virtual
-		.endm
-
-#include <asm/hardware/debug-pl01x.S>

arch/arm/include/debug/nomadik.S

-/*
- * Debugging macro include header
- *
- *  Copyright (C) 1994-1999 Russell King
- *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * 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.
- *
-*/
-
-		.macro	addruart, rp, rv, tmp
-		mov	\rp, #0x00100000
-		add	\rp, \rp, #0x000fb000
-		add	\rv, \rp, #0xf0000000	@ virtual base
-		add	\rp, \rp, #0x10000000	@ physical base address
-		.endm
-
-#include <asm/hardware/debug-pl01x.S>

arch/arm/include/debug/nspire.S

-/*
- *	linux/arch/arm/include/debug/nspire.S
- *
- *	Copyright (C) 2013 Daniel Tang <tangrs@tangrs.id.au>
- *
- * 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.
- *
- */
-
-#define NSPIRE_EARLY_UART_PHYS_BASE	   0x90020000
-#define NSPIRE_EARLY_UART_VIRT_BASE	   0xfee20000
-
-.macro	addruart, rp, rv, tmp
-	ldr \rp, =(NSPIRE_EARLY_UART_PHYS_BASE)		@ physical base address
-	ldr \rv, =(NSPIRE_EARLY_UART_VIRT_BASE)		@ virtual base address
-.endm
-
-
-#ifdef CONFIG_DEBUG_NSPIRE_CX_UART
-#include <asm/hardware/debug-pl01x.S>
-#endif
-
-#ifdef CONFIG_DEBUG_NSPIRE_CLASSIC_UART
-#define UART_SHIFT 2
-#include <asm/hardware/debug-8250.S>
-#endif

arch/arm/include/debug/picoxcell.S

-/*
- * Copyright (c) 2011 Picochip Ltd., Jamie Iles
- *
- * 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.
- *
- */
-
-#define UART_SHIFT 2
-#define PICOXCELL_UART1_BASE		0x80230000
-#define PHYS_TO_IO(x)			(((x) & 0x00ffffff) | 0xfe000000)
-
-		.macro	addruart, rp, rv, tmp
-		ldr	\rv, =PHYS_TO_IO(PICOXCELL_UART1_BASE)
-		ldr	\rp, =PICOXCELL_UART1_BASE
-		.endm
-
-#include "8250_32.S"

arch/arm/include/asm/hardware/debug-pl01x.S → arch/arm/include/debug/pl01x.S

-/* arch/arm/include/asm/hardware/debug-pl01x.S
+/* arch/arm/include/debug/pl01x.S
  *
  * Debugging macro include header
  *
@@ -12,6 +12,13 @@
 */
 #include <linux/amba/serial.h>
 
+#ifdef CONFIG_DEBUG_UART_PHYS
+		.macro	addruart, rp, rv, tmp
+		ldr	\rp, =CONFIG_DEBUG_UART_PHYS
+		ldr	\rv, =CONFIG_DEBUG_UART_VIRT
+		.endm
+#endif
+
 		.macro	senduart,rd,rx
 		strb	\rd, [\rx, #UART01x_DR]
 		.endm

arch/arm/include/debug/pxa.S

-/*
- * Early serial output macro for Marvell PXA/MMP SoC
- *
- * Copyright (C) 1994-1999 Russell King
- * Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * Copyright (C) 2013 Haojian Zhuang
- *
- * 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.
-*/
-
-#if defined(CONFIG_DEBUG_PXA_UART1)
-#define PXA_UART_REG_PHYS_BASE	0x40100000
-#define PXA_UART_REG_VIRT_BASE	0xf2100000
-#elif defined(CONFIG_DEBUG_MMP_UART2)
-#define PXA_UART_REG_PHYS_BASE	0xd4017000
-#define PXA_UART_REG_VIRT_BASE	0xfe017000
-#elif defined(CONFIG_DEBUG_MMP_UART3)
-#define PXA_UART_REG_PHYS_BASE	0xd4018000
-#define PXA_UART_REG_VIRT_BASE	0xfe018000
-#else
-#error "Select uart for DEBUG_LL"
-#endif
-
-	.macro	addruart, rp, rv, tmp
-	ldr	\rp, =PXA_UART_REG_PHYS_BASE
-	ldr	\rv, =PXA_UART_REG_VIRT_BASE
-	.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>

arch/arm/include/debug/rockchip.S

-/*
- * Early serial output macro for Rockchip SoCs
- *
- * Copyright (C) 2012 Maxime Ripard
- *
- * Maxime Ripard <maxime.ripard@free-electrons.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.
-*/
-
-#if defined(CONFIG_DEBUG_RK29_UART0)
-#define ROCKCHIP_UART_DEBUG_PHYS_BASE 0x20060000
-#define ROCKCHIP_UART_DEBUG_VIRT_BASE 0xfed60000
-#elif defined(CONFIG_DEBUG_RK29_UART1)
-#define ROCKCHIP_UART_DEBUG_PHYS_BASE 0x20064000
-#define ROCKCHIP_UART_DEBUG_VIRT_BASE 0xfed64000
-#elif defined(CONFIG_DEBUG_RK29_UART2)
-#define ROCKCHIP_UART_DEBUG_PHYS_BASE 0x20068000
-#define ROCKCHIP_UART_DEBUG_VIRT_BASE 0xfed68000
-#elif defined(CONFIG_DEBUG_RK3X_UART0)
-#define ROCKCHIP_UART_DEBUG_PHYS_BASE 0x10124000
-#define ROCKCHIP_UART_DEBUG_VIRT_BASE 0xfeb24000
-#elif defined(CONFIG_DEBUG_RK3X_UART1)
-#define ROCKCHIP_UART_DEBUG_PHYS_BASE 0x10126000
-#define ROCKCHIP_UART_DEBUG_VIRT_BASE 0xfeb26000
-#elif defined(CONFIG_DEBUG_RK3X_UART2)
-#define ROCKCHIP_UART_DEBUG_PHYS_BASE 0x20064000
-#define ROCKCHIP_UART_DEBUG_VIRT_BASE 0xfed64000
-#elif defined(CONFIG_DEBUG_RK3X_UART3)
-#define ROCKCHIP_UART_DEBUG_PHYS_BASE 0x20068000
-#define ROCKCHIP_UART_DEBUG_VIRT_BASE 0xfed68000
-#endif
-
-	.macro	addruart, rp, rv, tmp
-	ldr	\rp, =ROCKCHIP_UART_DEBUG_PHYS_BASE
-	ldr	\rv, =ROCKCHIP_UART_DEBUG_VIRT_BASE
-	.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>

arch/arm/include/debug/socfpga.S

-/*
- *  Copyright (C) 1994-1999 Russell King
- *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * 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.
- */
-
-#define UART_SHIFT 2
-#define DEBUG_LL_UART_OFFSET	0x00002000
-
-		.macro	addruart, rp, rv, tmp
-		mov	\rp, #DEBUG_LL_UART_OFFSET
-		orr	\rp, \rp, #0x00c00000
-		orr	\rv, \rp, #0xfe000000	@ virtual base
-		orr	\rp, \rp, #0xff000000	@ physical base
-		.endm
-
-#include "8250_32.S"
-

arch/arm/include/debug/sunxi.S

-/*
- * Early serial output macro for Allwinner A1X SoCs
- *
- * Copyright (C) 2012 Maxime Ripard
- *
- * Maxime Ripard <maxime.ripard@free-electrons.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.
-*/
-
-#if defined(CONFIG_DEBUG_SUNXI_UART0)
-#define SUNXI_UART_DEBUG_PHYS_BASE 0x01c28000
-#define SUNXI_UART_DEBUG_VIRT_BASE 0xf1c28000
-#elif defined(CONFIG_DEBUG_SUNXI_UART1)
-#define SUNXI_UART_DEBUG_PHYS_BASE 0x01c28400
-#define SUNXI_UART_DEBUG_VIRT_BASE 0xf1c28400
-#endif
-
-	.macro	addruart, rp, rv, tmp
-	ldr	\rp, =SUNXI_UART_DEBUG_PHYS_BASE
-	ldr	\rv, =SUNXI_UART_DEBUG_VIRT_BASE
-	.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>

arch/arm/include/debug/tegra.S

@@ -221,3 +221,32 @@
 1002:
 #endif
 		.endm
+
+/*
+ * Storage for the state maintained by the macros above.
+ *
+ * In the kernel proper, this data is located in arch/arm/mach-tegra/common.c.
+ * That's because this header is included from multiple files, and we only
+ * want a single copy of the data. In particular, the UART probing code above
+ * assumes it's running using physical addresses. This is true when this file
+ * is included from head.o, but not when included from debug.o. So we need
+ * to share the probe results between the two copies, rather than having
+ * to re-run the probing again later.
+ *
+ * In the decompressor, we put the symbol/storage right here, since common.c
+ * isn't included in the decompressor build. This symbol gets put in .text
+ * even though it's really data, since .data is discarded from the
+ * decompressor. Luckily, .text is writeable in the decompressor, unless
+ * CONFIG_ZBOOT_ROM. That dependency is handled in arch/arm/Kconfig.debug.
+ */
+#if defined(ZIMAGE)
+tegra_uart_config:
+	/* Debug UART initialization required */
+	.word 1
+	/* Debug UART physical address */
+	.word 0
+	/* Debug UART virtual address */
+	.word 0
+	/* Scratch space for debug macro */
+	.word 0
+#endif

arch/arm/include/debug/u300.S

-/*
- * Copyright (C) 2006-2013 ST-Ericsson AB
- * License terms: GNU General Public License (GPL) version 2
- * Debugging macro include header.
- * Author: Linus Walleij <linus.walleij@stericsson.com>
- */
-#define U300_SLOW_PER_PHYS_BASE		0xc0010000
-#define U300_SLOW_PER_VIRT_BASE		0xff000000
-
-	.macro	addruart, rp, rv, tmp
-	/* If we move the address using MMU, use this. */
-	ldr	\rp,	  = U300_SLOW_PER_PHYS_BASE @ MMU off, physical address
-	ldr	\rv,	  = U300_SLOW_PER_VIRT_BASE @ MMU on, virtual address
-	orr	\rp, \rp, #0x00003000
-	orr	\rv, \rv, #0x00003000
-	.endm
-
-#include <asm/hardware/debug-pl01x.S>

arch/arm/include/debug/ux500.S

@@ -45,4 +45,4 @@
 	ldr	\rv, =UART_VIRT_BASE		@ yes, virtual address
 	.endm
 
-#include <asm/hardware/debug-pl01x.S>
+#include <debug/pl01x.S>

arch/arm/include/debug/vexpress.S

@@ -47,51 +47,5 @@
 
 		.endm
 
-#include <asm/hardware/debug-pl01x.S>
-
-#elif defined(CONFIG_DEBUG_VEXPRESS_UART0_CA9)
-
-		.macro	addruart,rp,rv,tmp
-		mov	\rp, #DEBUG_LL_UART_OFFSET
-		orr	\rv, \rp, #DEBUG_LL_VIRT_BASE
-		orr	\rp, \rp, #DEBUG_LL_PHYS_BASE
-		.endm
-
-#include <asm/hardware/debug-pl01x.S>
-
-#elif defined(CONFIG_DEBUG_VEXPRESS_UART0_RS1)
-
-		.macro	addruart,rp,rv,tmp
-		mov	\rp, #DEBUG_LL_UART_OFFSET_RS1
-		orr	\rv, \rp, #DEBUG_LL_VIRT_BASE
-		orr	\rp, \rp, #DEBUG_LL_PHYS_BASE_RS1
-		.endm
-
-#include <asm/hardware/debug-pl01x.S>
-
-#elif defined(CONFIG_DEBUG_VEXPRESS_UART0_CRX)
-
-		.macro	addruart,rp,tmp,tmp2
-		ldr	\rp, =DEBUG_LL_UART_PHYS_CRX
-		.endm
-
-#include <asm/hardware/debug-pl01x.S>
-
-#else /* CONFIG_DEBUG_LL_UART_NONE */
-
-		.macro	addruart, rp, rv, tmp
-		/* Safe dummy values */
-		mov	\rp, #0
-		mov	\rv, #DEBUG_LL_VIRT_BASE
-		.endm
-
-		.macro	senduart,rd,rx
-		.endm
-
-		.macro	waituart,rd,rx
-		.endm
-
-		.macro	busyuart,rd,rx
-		.endm
-
+#include <debug/pl01x.S>
 #endif

arch/arm/kernel/Makefile

@@ -24,7 +24,7 @@ obj-$(CONFIG_ATAGS_PROC)	+= atags_proc.o
 obj-$(CONFIG_DEPRECATED_PARAM_STRUCT) += atags_compat.o
 
 ifeq ($(CONFIG_CPU_V7M),y)
-obj-y		+= entry-v7m.o
+obj-y		+= entry-v7m.o v7m.o
 else
 obj-y		+= entry-armv.o
 endif

arch/arm/kernel/atags.h

@@ -7,9 +7,10 @@ static inline void save_atags(struct tag *tags) { }
 void convert_to_tag_list(struct tag *tags);
 
 #ifdef CONFIG_ATAGS
-struct machine_desc *setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr);
+const struct machine_desc *setup_machine_tags(phys_addr_t __atags_pointer,
+	unsigned int machine_nr);
 #else
-static inline struct machine_desc *
+static inline const struct machine_desc *
 setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr)
 {
 	early_print("no ATAGS support: can't continue\n");

arch/arm/kernel/atags_parse.c

@@ -178,11 +178,11 @@ static void __init squash_mem_tags(struct tag *tag)
 			tag->hdr.tag = ATAG_NONE;
 }
 
-struct machine_desc * __init setup_machine_tags(phys_addr_t __atags_pointer,
-						unsigned int machine_nr)
+const struct machine_desc * __init
+setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr)
 {
 	struct tag *tags = (struct tag *)&default_tags;
-	struct machine_desc *mdesc = NULL, *p;
+	const struct machine_desc *mdesc = NULL, *p;
 	char *from = default_command_line;
 
 	default_tags.mem.start = PHYS_OFFSET;

arch/arm/kernel/devtree.c

@@ -181,10 +181,10 @@ bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
  * If a dtb was passed to the kernel in r2, then use it to choose the
  * correct machine_desc and to setup the system.
  */
-struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
+const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
 {
 	struct boot_param_header *devtree;
-	struct machine_desc *mdesc, *mdesc_best = NULL;
+	const struct machine_desc *mdesc, *mdesc_best = NULL;
 	unsigned int score, mdesc_score = ~1;
 	unsigned long dt_root;
 	const char *model;
@@ -193,7 +193,7 @@ struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
 	DT_MACHINE_START(GENERIC_DT, "Generic DT based system")
 	MACHINE_END
 
-	mdesc_best = (struct machine_desc *)&__mach_desc_GENERIC_DT;
+	mdesc_best = &__mach_desc_GENERIC_DT;
 #endif
 
 	if (!dt_phys)

arch/arm/kernel/entry-common.S

@@ -442,10 +442,10 @@ local_restart:
 	ldrcc	pc, [tbl, scno, lsl #2]		@ call sys_* routine
 
 	add	r1, sp, #S_OFF
-2:	mov	why, #0				@ no longer a real syscall
 	cmp	scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE)
 	eor	r0, scno, #__NR_SYSCALL_BASE	@ put OS number back
 	bcs	arm_syscall
+2:	mov	why, #0				@ no longer a real syscall
 	b	sys_ni_syscall			@ not private func
 
 #if defined(CONFIG_OABI_COMPAT) || !defined(CONFIG_AEABI)

arch/arm/kernel/module.c

@@ -292,12 +292,20 @@ int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs,
 			maps[ARM_SEC_CORE].unw_sec = s;
 		else if (strcmp(".ARM.exidx.exit.text", secname) == 0)
 			maps[ARM_SEC_EXIT].unw_sec = s;
+		else if (strcmp(".ARM.exidx.text.unlikely", secname) == 0)
+			maps[ARM_SEC_UNLIKELY].unw_sec = s;
+		else if (strcmp(".ARM.exidx.text.hot", secname) == 0)
+			maps[ARM_SEC_HOT].unw_sec = s;
 		else if (strcmp(".init.text", secname) == 0)
 			maps[ARM_SEC_INIT].txt_sec = s;
 		else if (strcmp(".text", secname) == 0)
 			maps[ARM_SEC_CORE].txt_sec = s;
 		else if (strcmp(".exit.text", secname) == 0)
 			maps[ARM_SEC_EXIT].txt_sec = s;
+		else if (strcmp(".text.unlikely", secname) == 0)
+			maps[ARM_SEC_UNLIKELY].txt_sec = s;
+		else if (strcmp(".text.hot", secname) == 0)
+			maps[ARM_SEC_HOT].txt_sec = s;
 	}
 
 	for (i = 0; i < ARM_SEC_MAX; i++)

arch/arm/kernel/perf_event_cpu.c

@@ -118,7 +118,8 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 			continue;
 		}
 
-		err = request_irq(irq, handler, IRQF_NOBALANCING, "arm-pmu",
+		err = request_irq(irq, handler,
+				  IRQF_NOBALANCING | IRQF_NO_THREAD, "arm-pmu",
 				  cpu_pmu);
 		if (err) {
 			pr_err("unable to request IRQ%d for ARM PMU counters\n",

arch/arm/kernel/setup.c

@@ -72,10 +72,10 @@ static int __init fpe_setup(char *line)
 __setup("fpe=", fpe_setup);
 #endif
 
-extern void paging_init(struct machine_desc *desc);
+extern void paging_init(const struct machine_desc *desc);
 extern void sanity_check_meminfo(void);
 extern enum reboot_mode reboot_mode;
-extern void setup_dma_zone(struct machine_desc *desc);
+extern void setup_dma_zone(const struct machine_desc *desc);
 
 unsigned int processor_id;
 EXPORT_SYMBOL(processor_id);
@@ -139,7 +139,7 @@ EXPORT_SYMBOL(elf_platform);
 static const char *cpu_name;
 static const char *machine_name;
 static char __initdata cmd_line[COMMAND_LINE_SIZE];
-struct machine_desc *machine_desc __initdata;
+const struct machine_desc *machine_desc __initdata;
 
 static union { char c[4]; unsigned long l; } endian_test __initdata = { { 'l', '?', '?', 'b' } };
 #define ENDIANNESS ((char)endian_test.l)
@@ -607,7 +607,7 @@ static void __init setup_processor(void)
 
 void __init dump_machine_table(void)
 {
-	struct machine_desc *p;
+	const struct machine_desc *p;
 
 	early_print("Available machine support:\n\nID (hex)\tNAME\n");
 	for_each_machine_desc(p)
@@ -694,7 +694,7 @@ static int __init early_mem(char *p)
 }
 early_param("mem", early_mem);
 
-static void __init request_standard_resources(struct machine_desc *mdesc)
+static void __init request_standard_resources(const struct machine_desc *mdesc)
 {
 	struct memblock_region *region;
 	struct resource *res;
@@ -852,7 +852,7 @@ void __init hyp_mode_check(void)
 
 void __init setup_arch(char **cmdline_p)
 {
-	struct machine_desc *mdesc;
+	const struct machine_desc *mdesc;
 
 	setup_processor();
 	mdesc = setup_machine_fdt(__atags_pointer);
@@ -994,15 +994,6 @@ static int c_show(struct seq_file *m, void *v)
 		seq_printf(m, "model name\t: %s rev %d (%s)\n",
 			   cpu_name, cpuid & 15, elf_platform);
 
-#if defined(CONFIG_SMP)
-		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
-			   per_cpu(cpu_data, i).loops_per_jiffy / (500000UL/HZ),
-			   (per_cpu(cpu_data, i).loops_per_jiffy / (5000UL/HZ)) % 100);
-#else
-		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
-			   loops_per_jiffy / (500000/HZ),
-			   (loops_per_jiffy / (5000/HZ)) % 100);
-#endif
 		/* dump out the processor features */
 		seq_puts(m, "Features\t: ");
 

arch/arm/kernel/smp.c

@@ -398,17 +398,8 @@ asmlinkage void secondary_start_kernel(void)
 
 void __init smp_cpus_done(unsigned int max_cpus)
 {
-	int cpu;
-	unsigned long bogosum = 0;
-
-	for_each_online_cpu(cpu)
-		bogosum += per_cpu(cpu_data, cpu).loops_per_jiffy;
-
-	printk(KERN_INFO "SMP: Total of %d processors activated "
-	       "(%lu.%02lu BogoMIPS).\n",
-	       num_online_cpus(),
-	       bogosum / (500000/HZ),
-	       (bogosum / (5000/HZ)) % 100);
+	printk(KERN_INFO "SMP: Total of %d processors activated.\n",
+	       num_online_cpus());
 
 	hyp_mode_check();
 }

arch/arm/kernel/smp_tlb.c

@@ -104,7 +104,7 @@ void flush_tlb_all(void)
 	if (tlb_ops_need_broadcast())
 		on_each_cpu(ipi_flush_tlb_all, NULL, 1);
 	else
-		local_flush_tlb_all();
+		__flush_tlb_all();
 	broadcast_tlb_a15_erratum();
 }
 
@@ -113,7 +113,7 @@ void flush_tlb_mm(struct mm_struct *mm)
 	if (tlb_ops_need_broadcast())
 		on_each_cpu_mask(mm_cpumask(mm), ipi_flush_tlb_mm, mm, 1);
 	else
-		local_flush_tlb_mm(mm);
+		__flush_tlb_mm(mm);
 	broadcast_tlb_mm_a15_erratum(mm);
 }
 
@@ -126,7 +126,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 		on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_page,
 					&ta, 1);
 	} else
-		local_flush_tlb_page(vma, uaddr);
+		__flush_tlb_page(vma, uaddr);
 	broadcast_tlb_mm_a15_erratum(vma->vm_mm);
 }
 
@@ -137,7 +137,7 @@ void flush_tlb_kernel_page(unsigned long kaddr)
 		ta.ta_start = kaddr;
 		on_each_cpu(ipi_flush_tlb_kernel_page, &ta, 1);
 	} else
-		local_flush_tlb_kernel_page(kaddr);
+		__flush_tlb_kernel_page(kaddr);
 	broadcast_tlb_a15_erratum();
 }
 
@@ -173,5 +173,5 @@ void flush_bp_all(void)
 	if (tlb_ops_need_broadcast())
 		on_each_cpu(ipi_flush_bp_all, NULL, 1);
 	else
-		local_flush_bp_all();
+		__flush_bp_all();
 }

arch/arm/kernel/traps.c

@@ -497,28 +497,64 @@ static int bad_syscall(int n, struct pt_regs *regs)
 	return regs->ARM_r0;
 }
 
+static long do_cache_op_restart(struct restart_block *);
+
 static inline int
-do_cache_op(unsigned long start, unsigned long end, int flags)
+__do_cache_op(unsigned long start, unsigned long end)
+{
+	int ret;
+	unsigned long chunk = PAGE_SIZE;
+
+	do {
+		if (signal_pending(current)) {
+			struct thread_info *ti = current_thread_info();
+
+			ti->restart_block = (struct restart_block) {
+				.fn	= do_cache_op_restart,
+			};
+
+			ti->arm_restart_block = (struct arm_restart_block) {
+				{
+					.cache = {
+						.start	= start,
+						.end	= end,
+					},
+				},
+			};
+
+			return -ERESTART_RESTARTBLOCK;
+		}
+
+		ret = flush_cache_user_range(start, start + chunk);
+		if (ret)
+			return ret;
+
+		cond_resched();
+		start += chunk;
+	} while (start < end);
+
+	return 0;
+}
+
+static long do_cache_op_restart(struct restart_block *unused)
 {
-	struct mm_struct *mm = current->active_mm;
-	struct vm_area_struct *vma;
+	struct arm_restart_block *restart_block;
 
+	restart_block = &current_thread_info()->arm_restart_block;
+	return __do_cache_op(restart_block->cache.start,
+			     restart_block->cache.end);
+}
+
+static inline int
+do_cache_op(unsigned long start, unsigned long end, int flags)
+{
 	if (end < start || flags)
 		return -EINVAL;
 
-	down_read(&mm->mmap_sem);
-	vma = find_vma(mm, start);
-	if (vma && vma->vm_start < end) {
-		if (start < vma->vm_start)
-			start = vma->vm_start;
-		if (end > vma->vm_end)
-			end = vma->vm_end;
+	if (!access_ok(VERIFY_READ, start, end - start))
+		return -EFAULT;
 
-		up_read(&mm->mmap_sem);
-		return flush_cache_user_range(start, end);
-	}
-	up_read(&mm->mmap_sem);
-	return -EINVAL;
+	return __do_cache_op(start, end);
 }
 
 /*

arch/arm/kernel/v7m.c

+/*
+ * Copyright (C) 2013 Uwe Kleine-Koenig for Pengutronix
+ *
+ * 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/io.h>
+#include <linux/reboot.h>
+#include <asm/barrier.h>
+#include <asm/v7m.h>
+
+void armv7m_restart(enum reboot_mode mode, const char *cmd)
+{
+	dsb();
+	__raw_writel(V7M_SCB_AIRCR_VECTKEY | V7M_SCB_AIRCR_SYSRESETREQ,
+			BASEADDR_V7M_SCB + V7M_SCB_AIRCR);
+	dsb();
+}

arch/arm/kvm/init.S

@@ -142,7 +142,7 @@ target:	@ We're now in the trampoline code, switch page tables
 
 	@ Invalidate the old TLBs
 	mcr	p15, 4, r0, c8, c7, 0	@ TLBIALLH
-	dsb
+	dsb	ish
 
 	eret
 

arch/arm/kvm/interrupts.S

@@ -55,7 +55,7 @@ ENTRY(__kvm_tlb_flush_vmid_ipa)
 	mcrr	p15, 6, r2, r3, c2	@ Write VTTBR
 	isb
 	mcr     p15, 0, r0, c8, c3, 0	@ TLBIALLIS (rt ignored)
-	dsb
+	dsb	ish
 	isb
 	mov	r2, #0
 	mov	r3, #0
@@ -79,7 +79,7 @@ ENTRY(__kvm_flush_vm_context)
 	mcr     p15, 4, r0, c8, c3, 4
 	/* Invalidate instruction caches Inner Shareable (ICIALLUIS) */
 	mcr     p15, 0, r0, c7, c1, 0
-	dsb
+	dsb	ish
 	isb				@ Not necessary if followed by eret
 
 	bx	lr

arch/arm/kvm/mmu.c

@@ -489,7 +489,6 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 
 	for (addr = guest_ipa; addr < end; addr += PAGE_SIZE) {
 		pte_t pte = pfn_pte(pfn, PAGE_S2_DEVICE);
-		kvm_set_s2pte_writable(&pte);
 
 		ret = mmu_topup_memory_cache(&cache, 2, 2);
 		if (ret)

arch/arm/lib/Makefile

@@ -45,3 +45,9 @@ lib-$(CONFIG_ARCH_SHARK)	+= io-shark.o
 
 $(obj)/csumpartialcopy.o:	$(obj)/csumpartialcopygeneric.S
 $(obj)/csumpartialcopyuser.o:	$(obj)/csumpartialcopygeneric.S
+
+ifeq ($(CONFIG_KERNEL_MODE_NEON),y)
+  NEON_FLAGS			:= -mfloat-abi=softfp -mfpu=neon
+  CFLAGS_xor-neon.o		+= $(NEON_FLAGS)
+  lib-$(CONFIG_XOR_BLOCKS)	+= xor-neon.o
+endif

arch/arm/lib/xor-neon.c

+/*
+ * linux/arch/arm/lib/xor-neon.c
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * 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/raid/xor.h>
+
+#ifndef __ARM_NEON__
+#error You should compile this file with '-mfloat-abi=softfp -mfpu=neon'
+#endif
+
+/*
+ * Pull in the reference implementations while instructing GCC (through
+ * -ftree-vectorize) to attempt to exploit implicit parallelism and emit
+ * NEON instructions.
+ */
+#if __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 6)
+#pragma GCC optimize "tree-vectorize"
+#else
+/*
+ * While older versions of GCC do not generate incorrect code, they fail to
+ * recognize the parallel nature of these functions, and emit plain ARM code,
+ * which is known to be slower than the optimized ARM code in asm-arm/xor.h.
+ */
+#warning This code requires at least version 4.6 of GCC
+#endif
+
+#pragma GCC diagnostic ignored "-Wunused-variable"
+#include <asm-generic/xor.h>
+
+struct xor_block_template const xor_block_neon_inner = {
+	.name	= "__inner_neon__",
+	.do_2	= xor_8regs_2,
+	.do_3	= xor_8regs_3,
+	.do_4	= xor_8regs_4,
+	.do_5	= xor_8regs_5,
+};

arch/arm/mach-davinci/include/mach/debug-macro.S

-/*
- * Debugging macro for DaVinci
- *
- * Author: Kevin Hilman, MontaVista Software, Inc. <source@mvista.com>
- *
- * 2007 (c) MontaVista Software, Inc. 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.
- */
-
-/* Modifications
- * Jan 2009	Chaithrika U S	Added senduart, busyuart, waituart
- *				macros, based on debug-8250.S file
- *				but using 32-bit accesses required for
- *                              some davinci devices.
- */
-
-#include <linux/serial_reg.h>
-
-#include <mach/serial.h>
-
-#define UART_SHIFT	2
-
-#if defined(CONFIG_DEBUG_DAVINCI_DMx_UART0)
-#define UART_BASE	DAVINCI_UART0_BASE
-#elif defined(CONFIG_DEBUG_DAVINCI_DA8XX_UART1)
-#define UART_BASE	DA8XX_UART1_BASE
-#elif defined(CONFIG_DEBUG_DAVINCI_DA8XX_UART2)
-#define UART_BASE	DA8XX_UART2_BASE
-#elif defined(CONFIG_DEBUG_DAVINCI_TNETV107X_UART1)
-#define UART_BASE	TNETV107X_UART2_BASE
-#define UART_VIRTBASE	TNETV107X_UART2_VIRT
-#else
-#error "Select a specifc port for DEBUG_LL"
-#endif
-
-#ifndef UART_VIRTBASE
-#define UART_VIRTBASE	IO_ADDRESS(UART_BASE)
-#endif
-
-		.macro addruart, rp, rv, tmp
-		ldr	\rp, =UART_BASE
-		ldr	\rv, =UART_VIRTBASE
-		.endm
-
-		.macro	senduart,rd,rx
-		str	\rd, [\rx, #UART_TX << UART_SHIFT]
-		.endm
-
-		.macro	busyuart,rd,rx
-1002:		ldr	\rd, [\rx, #UART_LSR << UART_SHIFT]
-		and	\rd, \rd, #UART_LSR_TEMT | UART_LSR_THRE
-		teq	\rd, #UART_LSR_TEMT | UART_LSR_THRE
-		bne	1002b
-		.endm
-
-		.macro	waituart,rd,rx
-#ifdef FLOW_CONTROL
-1001:		ldr	\rd, [\rx, #UART_MSR << UART_SHIFT]
-		tst	\rd, #UART_MSR_CTS
-		beq	1001b
-#endif
-		.endm
-

arch/arm/mach-dove/include/mach/debug-macro.S

-/*
- * arch/arm/mach-dove/include/mach/debug-macro.S
- *
- * 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 <mach/bridge-regs.h>
-
-	.macro	addruart, rp, rv, tmp
-	ldr	\rp, =DOVE_SB_REGS_PHYS_BASE
-	ldr	\rv, =DOVE_SB_REGS_VIRT_BASE
-	orr	\rp, \rp, #0x00012000
-	orr	\rv, \rv, #0x00012000
-	.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>

arch/arm/mach-ebsa110/include/mach/debug-macro.S

-/* arch/arm/mach-ebsa110/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- *  Copyright (C) 1994-1999 Russell King
- *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * 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.
- *
-**/
-
-		.macro	addruart, rp, rv, tmp
-		mov	\rp, #0xf0000000
-		orr	\rp, \rp, #0x00000be0
-		mov	\rp, \rv
-		.endm
-
-#define UART_SHIFT	2
-#define FLOW_CONTROL
-#include <asm/hardware/debug-8250.S>

arch/arm/mach-ep93xx/Kconfig

@@ -194,20 +194,6 @@ config MACH_VISION_EP9307
 	  Say 'Y' here if you want your kernel to support the
 	  Vision Engraving Systems EP9307 SoM.
 
-choice
-	prompt "Select a UART for early kernel messages"
-
-config EP93XX_EARLY_UART1
-	bool "UART1"
-
-config EP93XX_EARLY_UART2
-	bool "UART2"
-
-config EP93XX_EARLY_UART3
-	bool "UART3"
-
-endchoice
-
 endmenu
 
 endif

arch/arm/mach-ep93xx/include/mach/debug-macro.S

-/*
- * arch/arm/mach-ep93xx/include/mach/debug-macro.S
- * Debugging macro include header
- *
- * Copyright (C) 2006 Lennert Buytenhek <buytenh@wantstofly.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 <mach/ep93xx-regs.h>
-
-		.macro	addruart, rp, rv, tmp
-		ldr	\rp, =EP93XX_APB_PHYS_BASE	@ Physical base
-		ldr	\rv, =EP93XX_APB_VIRT_BASE	@ virtual base
-		orr	\rp, \rp, #0x000c0000
-		orr	\rv, \rv, #0x000c0000
-		.endm
-
-#include <asm/hardware/debug-pl01x.S>

arch/arm/mach-ep93xx/include/mach/uncompress.h

@@ -31,18 +31,8 @@ static void __raw_writel(unsigned int value, unsigned int ptr)
 	*((volatile unsigned int *)ptr) = value;
 }
 
-#if defined(CONFIG_EP93XX_EARLY_UART1)
-#define UART_BASE		EP93XX_UART1_PHYS_BASE
-#elif defined(CONFIG_EP93XX_EARLY_UART2)
-#define UART_BASE		EP93XX_UART2_PHYS_BASE
-#elif defined(CONFIG_EP93XX_EARLY_UART3)
-#define UART_BASE		EP93XX_UART3_PHYS_BASE
-#else
-#define UART_BASE		EP93XX_UART1_PHYS_BASE
-#endif
-
-#define PHYS_UART_DATA		(UART_BASE + 0x00)
-#define PHYS_UART_FLAG		(UART_BASE + 0x18)
+#define PHYS_UART_DATA		(CONFIG_DEBUG_UART_PHYS + 0x00)
+#define PHYS_UART_FLAG		(CONFIG_DEBUG_UART_PHYS + 0x18)
 #define UART_FLAG_TXFF		0x20
 
 static inline void putc(int c)

arch/arm/mach-footbridge/include/mach/debug-macro.S

@@ -13,20 +13,6 @@
 
 #include <asm/hardware/dec21285.h>
 
-#ifndef CONFIG_DEBUG_DC21285_PORT
-	/* For NetWinder debugging */
-		.macro	addruart, rp, rv, tmp
-		mov	\rp, #0x000003f8
-		orr	\rv, \rp, #0xfe000000	@ virtual
-		orr	\rv, \rv, #0x00e00000	@ virtual
-		orr	\rp, \rp, #0x7c000000	@ physical
-		.endm
-
-#define UART_SHIFT	0
-#define FLOW_CONTROL
-#include <asm/hardware/debug-8250.S>
-
-#else
 #include <mach/hardware.h>
 	/* For EBSA285 debugging */
 		.equ	dc21285_high, ARMCSR_BASE & 0xff000000
@@ -54,4 +40,3 @@
 
 		.macro	waituart,rd,rx
 		.endm
-#endif

arch/arm/mach-gemini/include/mach/debug-macro.S

-/*
- * Debugging macro include header
- *
- *  Copyright (C) 1994-1999 Russell King
- *  Copyright (C) 2001-2006 Storlink, Corp.
- *  Copyright (C) 2008-2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt>
- *
- * 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 <mach/hardware.h>
-
-	.macro	addruart, rp, rv, tmp
-	ldr	\rp, =GEMINI_UART_BASE			@ physical
-	ldr	\rv, =IO_ADDRESS(GEMINI_UART_BASE)	@ virtual
-	.endm
-
-#define UART_SHIFT	2
-#define FLOW_CONTROL
-#include <asm/hardware/debug-8250.S>

arch/arm/mach-integrator/include/mach/debug-macro.S

-/* arch/arm/mach-integrator/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- *  Copyright (C) 1994-1999 Russell King
- *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * 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.
- *
-*/
-
-		.macro	addruart, rp, rv, tmp
-		mov	\rp, #0x16000000	@ physical base address
-		mov	\rv, #0xf0000000	@ virtual base
-		add	\rv, \rv, #0x16000000 >> 4
-		.endm
-
-#include <asm/hardware/debug-pl01x.S>

arch/arm/mach-iop13xx/include/mach/debug-macro.S

-/*
- * arch/arm/mach-iop13xx/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- * Copyright (C) 1994-1999 Russell King
- * Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * 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.
- */
-
-	.macro	addruart, rp, rv, tmp
-	mov	\rp, #0x00002300
-	orr	\rp, \rp, #0x00000040
-	orr	\rv, \rp, #0xfe000000	@ virtual
-	orr	\rv, \rv, #0x00e80000
-	orr	\rp, \rp, #0xff000000	@ physical
-	orr	\rp, \rp, #0x00d80000
-	.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>

arch/arm/mach-iop32x/include/mach/debug-macro.S

-/*
- * arch/arm/mach-iop32x/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- * Copyright (C) 1994-1999 Russell King
- * Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * 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.
- */
-
-		.macro	addruart, rp, rv, tmp
-		mov	\rp, #0xfe000000	@ physical as well as virtual
-		orr	\rp, \rp, #0x00800000	@ location of the UART
-		mov	\rv, \rp
-		.endm
-
-#define UART_SHIFT	0
-#include <asm/hardware/debug-8250.S>

arch/arm/mach-iop33x/include/mach/debug-macro.S

-/*
- * arch/arm/mach-iop33x/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- * Copyright (C) 1994-1999 Russell King
- * Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * 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.
- */
-
-		.macro	addruart, rp, rv, tmp
-		mov	\rp, #0x00ff0000
-		orr	\rp, \rp, #0x0000f700
-		orr	\rv, #0xfe000000	@ virtual
-		orr	\rp, #0xff000000	@ physical
-		.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>

arch/arm/mach-ixp4xx/include/mach/debug-macro.S

-/* arch/arm/mach-ixp4xx/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- *  Copyright (C) 1994-1999 Russell King
- *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * 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.
-*/
-
-                .macro  addruart, rp, rv, tmp
-#ifdef __ARMEB__
-                mov     \rp, #3         @ Uart regs are at off set of 3 if
-					@ byte writes used - Big Endian.
-#else
-		mov	\rp, #0
-#endif
-		orr	\rv, \rp, #0xfe000000	@ virtual
-		orr	\rv, \rv, #0x00f00000
-                orr     \rp, \rp, #0xc8000000	@ physical
-                .endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>

arch/arm/mach-kirkwood/include/mach/debug-macro.S

-/*
- * arch/arm/mach-kirkwood/include/mach/debug-macro.S
- *
- * 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 <mach/bridge-regs.h>
-
-	.macro	addruart, rp, rv, tmp
-	ldr	\rp, =KIRKWOOD_REGS_PHYS_BASE
-	ldr	\rv, =KIRKWOOD_REGS_VIRT_BASE
-	orr	\rp, \rp, #0x00012000
-	orr	\rv, \rv, #0x00012000
-	.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>

arch/arm/mach-lpc32xx/include/mach/debug-macro.S

-/*
- * arch/arm/mach-lpc32xx/include/mach/debug-macro.S
- *
- * Author: Kevin Wells <kevin.wells@nxp.com>
- *
- * Copyright (C) 2010 NXP Semiconductors
- *
- * 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.
- */
-
-/*
- * Debug output is hardcoded to standard UART 5
-*/
-
-	.macro	addruart, rp, rv, tmp
-	ldreq	\rp, =0x40090000
-	ldrne	\rv, =0xF4090000
-	.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>

arch/arm/mach-mv78xx0/include/mach/debug-macro.S

-/*
- * arch/arm/mach-mv78xx0/include/mach/debug-macro.S
- *
- * 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 <mach/mv78xx0.h>
-
-	.macro	addruart, rp, rv, tmp
-	ldr	\rp, =MV78XX0_REGS_PHYS_BASE
-	ldr	\rv, =MV78XX0_REGS_VIRT_BASE
-	orr	\rp, \rp, #0x00012000
-	orr	\rv, \rv, #0x00012000
-	.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>

arch/arm/mach-orion5x/include/mach/debug-macro.S

-/*
- * arch/arm/mach-orion5x/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- * 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 <mach/orion5x.h>
-
-	.macro  addruart, rp, rv, tmp
-	ldr	\rp, =ORION5X_REGS_PHYS_BASE
-	ldr	\rv, =ORION5X_REGS_VIRT_BASE
-	orr	\rp, \rp, #0x00012000
-	orr	\rv, \rv, #0x00012000
-	.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>

arch/arm/mach-realview/include/mach/debug-macro.S

-/* arch/arm/mach-realview/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- *  Copyright (C) 1994-1999 Russell King
- *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * 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.
- */
-
-#ifdef CONFIG_DEBUG_REALVIEW_STD_PORT
-#define DEBUG_LL_UART_OFFSET	0x00009000
-#elif defined(CONFIG_DEBUG_REALVIEW_PB1176_PORT)
-#define DEBUG_LL_UART_OFFSET	0x0010c000
-#endif
-
-#ifndef DEBUG_LL_UART_OFFSET
-#error "Unknown RealView platform"
-#endif
-
-		.macro	addruart, rp, rv, tmp
-		mov	\rp, #DEBUG_LL_UART_OFFSET
-		orr	\rv, \rp, #0xfb000000	@ virtual base
-		orr	\rp, \rp, #0x10000000	@ physical base
-		.endm
-
-#include <asm/hardware/debug-pl01x.S>

arch/arm/mach-rpc/include/mach/debug-macro.S

-/* arch/arm/mach-rpc/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- *  Copyright (C) 1994-1999 Russell King
- *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * 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.
- *
-*/
-
-		.macro	addruart, rp, rv, tmp
-		mov	\rp, #0x00010000
-		orr	\rp, \rp, #0x00000fe0
-		orr	\rv, \rp, #0xe0000000	@ virtual
-		orr	\rp, \rp, #0x03000000	@ physical
-		.endm
-
-#define UART_SHIFT	2
-#define FLOW_CONTROL
-#include <asm/hardware/debug-8250.S>

arch/arm/mach-spear/include/mach/debug-macro.S

-/*
- * arch/arm/plat-spear/include/plat/debug-macro.S
- *
- * Debugging macro include header for spear platform
- *
- * Copyright (C) 2009 ST Microelectronics
- * Viresh Kumar <viresh.linux@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/amba/serial.h>
-#include <mach/spear.h>
-
-		.macro	addruart, rp, rv, tmp
-		mov	\rp, #SPEAR_DBG_UART_BASE		@ Physical base
-		mov	\rv, #VA_SPEAR_DBG_UART_BASE		@ Virtual base
-		.endm
-
-		.macro	senduart, rd, rx
-		strb	\rd, [\rx, #UART01x_DR]			@ ASC_TX_BUFFER
-		.endm
-
-		.macro	waituart, rd, rx
-1001:		ldr	\rd, [\rx, #UART01x_FR]			@ FLAG REGISTER
-		tst	\rd, #UART01x_FR_TXFF			@ TX_FULL
-		bne	1001b
-		.endm
-
-		.macro	busyuart, rd, rx
-1002:		ldr	\rd, [\rx, #UART01x_FR]			@ FLAG REGISTER
-		tst	\rd, #UART011_FR_TXFE			@ TX_EMPTY
-		beq	1002b
-		.endm

arch/arm/mach-spear/include/mach/spear.h

@@ -39,7 +39,6 @@
 
 /* Debug uart for linux, will be used for debug and uncompress messages */
 #define SPEAR_DBG_UART_BASE		SPEAR_ICM1_UART_BASE
-#define VA_SPEAR_DBG_UART_BASE		VA_SPEAR_ICM1_UART_BASE
 
 /* Sysctl base for spear platform */
 #define SPEAR_SYS_CTRL_BASE		SPEAR_ICM3_SYS_CTRL_BASE
@@ -86,7 +85,6 @@
 
 /* Debug uart for linux, will be used for debug and uncompress messages */
 #define SPEAR_DBG_UART_BASE			UART_BASE
-#define VA_SPEAR_DBG_UART_BASE			VA_UART_BASE
 
 #endif /* SPEAR13XX */
 

arch/arm/mach-versatile/include/mach/debug-macro.S

-/* arch/arm/mach-versatile/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- *  Copyright (C) 1994-1999 Russell King
- *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * 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.
- *
-*/
-
-		.macro	addruart, rp, rv, tmp
-		mov	\rp,      #0x001F0000
-		orr	\rp, \rp, #0x00001000
-		orr	\rv, \rp, #0xf1000000	@ virtual base
-		orr	\rp, \rp,  #0x10000000	@ physical base
-		.endm
-
-#include <asm/hardware/debug-pl01x.S>

arch/arm/mm/cache-l2x0.c

@@ -290,7 +290,7 @@ static void l2x0_disable(void)
 	raw_spin_lock_irqsave(&l2x0_lock, flags);
 	__l2x0_flush_all();
 	writel_relaxed(0, l2x0_base + L2X0_CTRL);
-	dsb();
+	dsb(st);
 	raw_spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
@@ -417,9 +417,9 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 		outer_cache.disable = l2x0_disable;
 	}
 
-	printk(KERN_INFO "%s cache controller enabled\n", type);
-	printk(KERN_INFO "l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d B\n",
-			ways, cache_id, aux, l2x0_size);
+	pr_info("%s cache controller enabled\n", type);
+	pr_info("l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d kB\n",
+		ways, cache_id, aux, l2x0_size >> 10);
 }
 
 #ifdef CONFIG_OF
@@ -929,7 +929,9 @@ static const struct of_device_id l2x0_ids[] __initconst = {
 	  .data = (void *)&aurora_no_outer_data},
 	{ .compatible = "marvell,aurora-outer-cache",
 	  .data = (void *)&aurora_with_outer_data},
-	{ .compatible = "bcm,bcm11351-a2-pl310-cache",
+	{ .compatible = "brcm,bcm11351-a2-pl310-cache",
+	  .data = (void *)&bcm_l2x0_data},
+	{ .compatible = "bcm,bcm11351-a2-pl310-cache", /* deprecated name */
 	  .data = (void *)&bcm_l2x0_data},
 	{}
 };

arch/arm/mm/cache-v7.S

@@ -282,7 +282,7 @@ ENTRY(v7_coherent_user_range)
 	add	r12, r12, r2
 	cmp	r12, r1
 	blo	1b
-	dsb
+	dsb	ishst
 	icache_line_size r2, r3
 	sub	r3, r2, #1
 	bic	r12, r0, r3
@@ -294,7 +294,7 @@ ENTRY(v7_coherent_user_range)
 	mov	r0, #0
 	ALT_SMP(mcr	p15, 0, r0, c7, c1, 6)	@ invalidate BTB Inner Shareable
 	ALT_UP(mcr	p15, 0, r0, c7, c5, 6)	@ invalidate BTB
-	dsb
+	dsb	ishst
 	isb
 	mov	pc, lr
 

arch/arm/mm/context.c

@@ -162,9 +162,6 @@ static void flush_context(unsigned int cpu)
 	}
 
 	/* Queue a TLB invalidate and flush the I-cache if necessary. */
-	if (!tlb_ops_need_broadcast())
-		cpumask_set_cpu(cpu, &tlb_flush_pending);
-	else
 	cpumask_setall(&tlb_flush_pending);
 
 	if (icache_is_vivt_asid_tagged())
@@ -245,8 +242,6 @@ void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk)
 	if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending)) {
 		local_flush_bp_all();
 		local_flush_tlb_all();
-		if (erratum_a15_798181())
-			dummy_flush_tlb_a15_erratum();
 	}
 
 	atomic64_set(&per_cpu(active_asids, cpu), asid);

arch/arm/mm/dma-mapping.c

@@ -455,7 +455,6 @@ static void __dma_remap(struct page *page, size_t size, pgprot_t prot)
 	unsigned end = start + size;
 
 	apply_to_page_range(&init_mm, start, size, __dma_update_pte, &prot);
-	dsb();
 	flush_tlb_kernel_range(start, end);
 }
 

arch/arm/mm/hugetlbpage.c

@@ -36,22 +36,6 @@
  * of type casting from pmd_t * to pte_t *.
  */
 
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
-{
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd = NULL;
-
-	pgd = pgd_offset(mm, addr);
-	if (pgd_present(*pgd)) {
-		pud = pud_offset(pgd, addr);
-		if (pud_present(*pud))
-			pmd = pmd_offset(pud, addr);
-	}
-
-	return (pte_t *)pmd;
-}
-
 struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
 			      int write)
 {
@@ -68,33 +52,6 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 	return 0;
 }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm,
-			unsigned long addr, unsigned long sz)
-{
-	pgd_t *pgd;
-	pud_t *pud;
-	pte_t *pte = NULL;
-
-	pgd = pgd_offset(mm, addr);
-	pud = pud_alloc(mm, pgd, addr);
-	if (pud)
-		pte = (pte_t *)pmd_alloc(mm, pud, addr);
-
-	return pte;
-}
-
-struct page *
-follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-		pmd_t *pmd, int write)
-{
-	struct page *page;
-
-	page = pte_page(*(pte_t *)pmd);
-	if (page)
-		page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
-	return page;
-}
-
 int pmd_huge(pmd_t pmd)
 {
 	return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);

arch/arm/mm/init.c

@@ -231,7 +231,7 @@ static void __init arm_adjust_dma_zone(unsigned long *size, unsigned long *hole,
 }
 #endif
 
-void __init setup_dma_zone(struct machine_desc *mdesc)
+void __init setup_dma_zone(const struct machine_desc *mdesc)
 {
 #ifdef CONFIG_ZONE_DMA
 	if (mdesc->dma_zone_size) {
@@ -335,7 +335,8 @@ phys_addr_t __init arm_memblock_steal(phys_addr_t size, phys_addr_t align)
 	return phys;
 }
 
-void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc)
+void __init arm_memblock_init(struct meminfo *mi,
+	const struct machine_desc *mdesc)
 {
 	int i;
 

arch/arm/mm/mmu.c

@@ -1186,7 +1186,7 @@ void __init arm_mm_memblock_reserve(void)
  * called function.  This means you can't use any function or debugging
  * method which may touch any device, otherwise the kernel _will_ crash.
  */
-static void __init devicemaps_init(struct machine_desc *mdesc)
+static void __init devicemaps_init(const struct machine_desc *mdesc)
 {
 	struct map_desc map;
 	unsigned long addr;
@@ -1319,7 +1319,7 @@ static void __init map_lowmem(void)
  * paging_init() sets up the page tables, initialises the zone memory
  * maps, and sets up the zero page, bad page and bad page tables.
  */
-void __init paging_init(struct machine_desc *mdesc)
+void __init paging_init(const struct machine_desc *mdesc)
 {
 	void *zero_page;
 

arch/arm/mm/nommu.c

@@ -299,7 +299,7 @@ void __init sanity_check_meminfo(void)
  * paging_init() sets up the page tables, initialises the zone memory
  * maps, and sets up the zero page, bad page and bad page tables.
  */
-void __init paging_init(struct machine_desc *mdesc)
+void __init paging_init(const struct machine_desc *mdesc)
 {
 	early_trap_init((void *)CONFIG_VECTORS_BASE);
 	mpu_setup();

arch/arm/mm/proc-feroceon.S

@@ -514,6 +514,32 @@ ENTRY(cpu_feroceon_set_pte_ext)
 #endif
 	mov	pc, lr
 
+/* Suspend/resume support: taken from arch/arm/mm/proc-arm926.S */
+.globl	cpu_feroceon_suspend_size
+.equ	cpu_feroceon_suspend_size, 4 * 3
+#ifdef CONFIG_ARM_CPU_SUSPEND
+ENTRY(cpu_feroceon_do_suspend)
+	stmfd	sp!, {r4 - r6, lr}
+	mrc	p15, 0, r4, c13, c0, 0	@ PID
+	mrc	p15, 0, r5, c3, c0, 0	@ Domain ID
+	mrc	p15, 0, r6, c1, c0, 0	@ Control register
+	stmia	r0, {r4 - r6}
+	ldmfd	sp!, {r4 - r6, pc}
+ENDPROC(cpu_feroceon_do_suspend)
+
+ENTRY(cpu_feroceon_do_resume)
+	mov	ip, #0
+	mcr	p15, 0, ip, c8, c7, 0	@ invalidate I+D TLBs
+	mcr	p15, 0, ip, c7, c7, 0	@ invalidate I+D caches
+	ldmia	r0, {r4 - r6}
+	mcr	p15, 0, r4, c13, c0, 0	@ PID
+	mcr	p15, 0, r5, c3, c0, 0	@ Domain ID
+	mcr	p15, 0, r1, c2, c0, 0	@ TTB address
+	mov	r0, r6			@ control register
+	b	cpu_resume_mmu
+ENDPROC(cpu_feroceon_do_resume)
+#endif
+
 	.type	__feroceon_setup, #function
 __feroceon_setup:
 	mov	r0, #0

arch/arm/mm/proc-v7.S

@@ -83,7 +83,7 @@ ENTRY(cpu_v7_dcache_clean_area)
 	add	r0, r0, r2
 	subs	r1, r1, r2
 	bhi	2b
-	dsb
+	dsb	ishst
 	mov	pc, lr
 ENDPROC(cpu_v7_dcache_clean_area)
 
@@ -330,7 +330,19 @@ __v7_setup:
 1:
 #endif
 
-3:	mov	r10, #0
+	/* Cortex-A15 Errata */
+3:	ldr	r10, =0x00000c0f		@ Cortex-A15 primary part number
+	teq	r0, r10
+	bne	4f
+
+#ifdef CONFIG_ARM_ERRATA_773022
+	cmp	r6, #0x4			@ only present up to r0p4
+	mrcle	p15, 0, r10, c1, c0, 1		@ read aux control register
+	orrle	r10, r10, #1 << 1		@ disable loop buffer
+	mcrle	p15, 0, r10, c1, c0, 1		@ write aux control register
+#endif
+
+4:	mov	r10, #0
 	mcr	p15, 0, r10, c7, c5, 0		@ I+BTB cache invalidate
 	dsb
 #ifdef CONFIG_MMU

arch/arm/mm/tlb-v7.S

@@ -35,7 +35,7 @@
 ENTRY(v7wbi_flush_user_tlb_range)
 	vma_vm_mm r3, r2			@ get vma->vm_mm
 	mmid	r3, r3				@ get vm_mm->context.id
-	dsb
+	dsb	ish
 	mov	r0, r0, lsr #PAGE_SHIFT		@ align address
 	mov	r1, r1, lsr #PAGE_SHIFT
 	asid	r3, r3				@ mask ASID
@@ -56,7 +56,7 @@ ENTRY(v7wbi_flush_user_tlb_range)
 	add	r0, r0, #PAGE_SZ
 	cmp	r0, r1
 	blo	1b
-	dsb
+	dsb	ish
 	mov	pc, lr
 ENDPROC(v7wbi_flush_user_tlb_range)
 
@@ -69,7 +69,7 @@ ENDPROC(v7wbi_flush_user_tlb_range)
  *	- end   - end address (exclusive, may not be aligned)
  */
 ENTRY(v7wbi_flush_kern_tlb_range)
-	dsb
+	dsb	ish
 	mov	r0, r0, lsr #PAGE_SHIFT		@ align address
 	mov	r1, r1, lsr #PAGE_SHIFT
 	mov	r0, r0, lsl #PAGE_SHIFT
@@ -84,7 +84,7 @@ ENTRY(v7wbi_flush_kern_tlb_range)
 	add	r0, r0, #PAGE_SZ
 	cmp	r0, r1
 	blo	1b
-	dsb
+	dsb	ish
 	isb
 	mov	pc, lr
 ENDPROC(v7wbi_flush_kern_tlb_range)

arch/arm/vfp/vfphw.S

@@ -78,6 +78,11 @@
 ENTRY(vfp_support_entry)
 	DBGSTR3	"instr %08x pc %08x state %p", r0, r2, r10
 
+	ldr	r3, [sp, #S_PSR]	@ Neither lazy restore nor FP exceptions
+	and	r3, r3, #MODE_MASK	@ are supported in kernel mode
+	teq	r3, #USR_MODE
+	bne	vfp_kmode_exception	@ Returns through lr
+
 	VFPFMRX	r1, FPEXC		@ Is the VFP enabled?
 	DBGSTR1	"fpexc %08x", r1
 	tst	r1, #FPEXC_EN

arch/arm/vfp/vfpmodule.c

@@ -20,6 +20,7 @@
 #include <linux/init.h>
 #include <linux/uaccess.h>
 #include <linux/user.h>
+#include <linux/export.h>
 
 #include <asm/cp15.h>
 #include <asm/cputype.h>
@@ -648,6 +649,72 @@ static int vfp_hotplug(struct notifier_block *b, unsigned long action,
 	return NOTIFY_OK;
 }
 
+void vfp_kmode_exception(void)
+{
+	/*
+	 * If we reach this point, a floating point exception has been raised
+	 * while running in kernel mode. If the NEON/VFP unit was enabled at the
+	 * time, it means a VFP instruction has been issued that requires
+	 * software assistance to complete, something which is not currently
+	 * supported in kernel mode.
+	 * If the NEON/VFP unit was disabled, and the location pointed to below
+	 * is properly preceded by a call to kernel_neon_begin(), something has
+	 * caused the task to be scheduled out and back in again. In this case,
+	 * rebuilding and running with CONFIG_DEBUG_ATOMIC_SLEEP enabled should
+	 * be helpful in localizing the problem.
+	 */
+	if (fmrx(FPEXC) & FPEXC_EN)
+		pr_crit("BUG: unsupported FP instruction in kernel mode\n");
+	else
+		pr_crit("BUG: FP instruction issued in kernel mode with FP unit disabled\n");
+}
+
+#ifdef CONFIG_KERNEL_MODE_NEON
+
+/*
+ * Kernel-side NEON support functions
+ */
+void kernel_neon_begin(void)
+{
+	struct thread_info *thread = current_thread_info();
+	unsigned int cpu;
+	u32 fpexc;
+
+	/*
+	 * Kernel mode NEON is only allowed outside of interrupt context
+	 * with preemption disabled. This will make sure that the kernel
+	 * mode NEON register contents never need to be preserved.
+	 */
+	BUG_ON(in_interrupt());
+	cpu = get_cpu();
+
+	fpexc = fmrx(FPEXC) | FPEXC_EN;
+	fmxr(FPEXC, fpexc);
+
+	/*
+	 * Save the userland NEON/VFP state. Under UP,
+	 * the owner could be a task other than 'current'
+	 */
+	if (vfp_state_in_hw(cpu, thread))
+		vfp_save_state(&thread->vfpstate, fpexc);
+#ifndef CONFIG_SMP
+	else if (vfp_current_hw_state[cpu] != NULL)
+		vfp_save_state(vfp_current_hw_state[cpu], fpexc);
+#endif
+	vfp_current_hw_state[cpu] = NULL;
+}
+EXPORT_SYMBOL(kernel_neon_begin);
+
+void kernel_neon_end(void)
+{
+	/* Disable the NEON/VFP unit. */
+	fmxr(FPEXC, fmrx(FPEXC) & ~FPEXC_EN);
+	put_cpu();
+}
+EXPORT_SYMBOL(kernel_neon_end);
+
+#endif /* CONFIG_KERNEL_MODE_NEON */
+
 /*
  * VFP support code initialisation.
  */
@@ -731,4 +798,4 @@ static int __init vfp_init(void)
 	return 0;
 }
 
-late_initcall(vfp_init);
+core_initcall(vfp_init);

include/linux/raid/pq.h

@@ -114,6 +114,11 @@ extern const struct raid6_recov_calls raid6_recov_intx1;
 extern const struct raid6_recov_calls raid6_recov_ssse3;
 extern const struct raid6_recov_calls raid6_recov_avx2;
 
+extern const struct raid6_calls raid6_neonx1;
+extern const struct raid6_calls raid6_neonx2;
+extern const struct raid6_calls raid6_neonx4;
+extern const struct raid6_calls raid6_neonx8;
+
 /* Algorithm list */
 extern const struct raid6_calls * const raid6_algos[];
 extern const struct raid6_recov_calls *const raid6_recov_algos[];

lib/raid6/.gitignore

@@ -2,3 +2,4 @@ mktables
 altivec*.c
 int*.c
 tables.c
+neon?.c

lib/raid6/Makefile

@@ -5,6 +5,7 @@ raid6_pq-y	+= algos.o recov.o tables.o int1.o int2.o int4.o \
 
 raid6_pq-$(CONFIG_X86) += recov_ssse3.o recov_avx2.o mmx.o sse1.o sse2.o avx2.o
 raid6_pq-$(CONFIG_ALTIVEC) += altivec1.o altivec2.o altivec4.o altivec8.o
+raid6_pq-$(CONFIG_KERNEL_MODE_NEON) += neon.o neon1.o neon2.o neon4.o neon8.o
 
 hostprogs-y	+= mktables
 
@@ -16,6 +17,21 @@ ifeq ($(CONFIG_ALTIVEC),y)
 altivec_flags := -maltivec -mabi=altivec
 endif
 
+# The GCC option -ffreestanding is required in order to compile code containing
+# ARM/NEON intrinsics in a non C99-compliant environment (such as the kernel)
+ifeq ($(CONFIG_KERNEL_MODE_NEON),y)
+NEON_FLAGS := -ffreestanding
+ifeq ($(ARCH),arm)
+NEON_FLAGS += -mfloat-abi=softfp -mfpu=neon
+endif
+ifeq ($(ARCH),arm64)
+CFLAGS_REMOVE_neon1.o += -mgeneral-regs-only
+CFLAGS_REMOVE_neon2.o += -mgeneral-regs-only
+CFLAGS_REMOVE_neon4.o += -mgeneral-regs-only
+CFLAGS_REMOVE_neon8.o += -mgeneral-regs-only
+endif
+endif
+
 targets += int1.c
 $(obj)/int1.c:   UNROLL := 1
 $(obj)/int1.c:   $(src)/int.uc $(src)/unroll.awk FORCE
@@ -70,6 +86,30 @@ $(obj)/altivec8.c:   UNROLL := 8
 $(obj)/altivec8.c:   $(src)/altivec.uc $(src)/unroll.awk FORCE
 	$(call if_changed,unroll)
 
+CFLAGS_neon1.o += $(NEON_FLAGS)
+targets += neon1.c
+$(obj)/neon1.c:   UNROLL := 1
+$(obj)/neon1.c:   $(src)/neon.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+CFLAGS_neon2.o += $(NEON_FLAGS)
+targets += neon2.c
+$(obj)/neon2.c:   UNROLL := 2
+$(obj)/neon2.c:   $(src)/neon.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+CFLAGS_neon4.o += $(NEON_FLAGS)
+targets += neon4.c
+$(obj)/neon4.c:   UNROLL := 4
+$(obj)/neon4.c:   $(src)/neon.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+CFLAGS_neon8.o += $(NEON_FLAGS)
+targets += neon8.c
+$(obj)/neon8.c:   UNROLL := 8
+$(obj)/neon8.c:   $(src)/neon.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
 quiet_cmd_mktable = TABLE   $@
       cmd_mktable = $(obj)/mktables > $@ || ( rm -f $@ && exit 1 )
 

lib/raid6/algos.c

@@ -70,6 +70,12 @@ const struct raid6_calls * const raid6_algos[] = {
 	&raid6_intx2,
 	&raid6_intx4,
 	&raid6_intx8,
+#ifdef CONFIG_KERNEL_MODE_NEON
+	&raid6_neonx1,
+	&raid6_neonx2,
+	&raid6_neonx4,
+	&raid6_neonx8,
+#endif
 	NULL
 };
 

lib/raid6/neon.c

+/*
+ * linux/lib/raid6/neon.c - RAID6 syndrome calculation using ARM NEON intrinsics
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * 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/raid/pq.h>
+
+#ifdef __KERNEL__
+#include <asm/neon.h>
+#else
+#define kernel_neon_begin()
+#define kernel_neon_end()
+#define cpu_has_neon()		(1)
+#endif
+
+/*
+ * There are 2 reasons these wrappers are kept in a separate compilation unit
+ * from the actual implementations in neonN.c (generated from neon.uc by
+ * unroll.awk):
+ * - the actual implementations use NEON intrinsics, and the GCC support header
+ *   (arm_neon.h) is not fully compatible (type wise) with the kernel;
+ * - the neonN.c files are compiled with -mfpu=neon and optimization enabled,
+ *   and we have to make sure that we never use *any* NEON/VFP instructions
+ *   outside a kernel_neon_begin()/kernel_neon_end() pair.
+ */
+
+#define RAID6_NEON_WRAPPER(_n)						\
+	static void raid6_neon ## _n ## _gen_syndrome(int disks,	\
+					size_t bytes, void **ptrs)	\
+	{								\
+		void raid6_neon ## _n  ## _gen_syndrome_real(int,	\
+						unsigned long, void**);	\
+		kernel_neon_begin();					\
+		raid6_neon ## _n ## _gen_syndrome_real(disks,		\
+					(unsigned long)bytes, ptrs);	\
+		kernel_neon_end();					\
+	}								\
+	struct raid6_calls const raid6_neonx ## _n = {			\
+		raid6_neon ## _n ## _gen_syndrome,			\
+		raid6_have_neon,					\
+		"neonx" #_n,						\
+		0							\
+	}
+
+static int raid6_have_neon(void)
+{
+	return cpu_has_neon();
+}
+
+RAID6_NEON_WRAPPER(1);
+RAID6_NEON_WRAPPER(2);
+RAID6_NEON_WRAPPER(4);
+RAID6_NEON_WRAPPER(8);

lib/raid6/neon.uc

+/* -----------------------------------------------------------------------
+ *
+ *   neon.uc - RAID-6 syndrome calculation using ARM NEON instructions
+ *
+ *   Copyright (C) 2012 Rob Herring
+ *
+ *   Based on altivec.uc:
+ *     Copyright 2002-2004 H. Peter Anvin - All Rights Reserved
+ *
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of the GNU General Public License as published by
+ *   the Free Software Foundation, Inc., 53 Temple Place Ste 330,
+ *   Boston MA 02111-1307, USA; either version 2 of the License, or
+ *   (at your option) any later version; incorporated herein by reference.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * neon$#.c
+ *
+ * $#-way unrolled NEON intrinsics math RAID-6 instruction set
+ *
+ * This file is postprocessed using unroll.awk
+ */
+
+#include <arm_neon.h>
+
+typedef uint8x16_t unative_t;
+
+#define NBYTES(x) ((unative_t){x,x,x,x, x,x,x,x, x,x,x,x, x,x,x,x})
+#define NSIZE	sizeof(unative_t)
+
+/*
+ * The SHLBYTE() operation shifts each byte left by 1, *not*
+ * rolling over into the next byte
+ */
+static inline unative_t SHLBYTE(unative_t v)
+{
+	return vshlq_n_u8(v, 1);
+}
+
+/*
+ * The MASK() operation returns 0xFF in any byte for which the high
+ * bit is 1, 0x00 for any byte for which the high bit is 0.
+ */
+static inline unative_t MASK(unative_t v)
+{
+	const uint8x16_t temp = NBYTES(0);
+	return (unative_t)vcltq_s8((int8x16_t)v, (int8x16_t)temp);
+}
+
+void raid6_neon$#_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs)
+{
+	uint8_t **dptr = (uint8_t **)ptrs;
+	uint8_t *p, *q;
+	int d, z, z0;
+
+	register unative_t wd$$, wq$$, wp$$, w1$$, w2$$;
+	const unative_t x1d = NBYTES(0x1d);
+
+	z0 = disks - 3;		/* Highest data disk */
+	p = dptr[z0+1];		/* XOR parity */
+	q = dptr[z0+2];		/* RS syndrome */
+
+	for ( d = 0 ; d < bytes ; d += NSIZE*$# ) {
+		wq$$ = wp$$ = vld1q_u8(&dptr[z0][d+$$*NSIZE]);
+		for ( z = z0-1 ; z >= 0 ; z-- ) {
+			wd$$ = vld1q_u8(&dptr[z][d+$$*NSIZE]);
+			wp$$ = veorq_u8(wp$$, wd$$);
+			w2$$ = MASK(wq$$);
+			w1$$ = SHLBYTE(wq$$);
+
+			w2$$ = vandq_u8(w2$$, x1d);
+			w1$$ = veorq_u8(w1$$, w2$$);
+			wq$$ = veorq_u8(w1$$, wd$$);
+		}
+		vst1q_u8(&p[d+NSIZE*$$], wp$$);
+		vst1q_u8(&q[d+NSIZE*$$], wq$$);
+	}
+}

lib/raid6/test/Makefile

@@ -22,11 +22,23 @@ ifeq ($(ARCH),x86_64)
         IS_X86 = yes
 endif
 
+ifeq ($(ARCH),arm)
+        CFLAGS += -I../../../arch/arm/include -mfpu=neon
+        HAS_NEON = yes
+endif
+ifeq ($(ARCH),arm64)
+        CFLAGS += -I../../../arch/arm64/include
+        HAS_NEON = yes
+endif
+
 ifeq ($(IS_X86),yes)
         OBJS   += mmx.o sse1.o sse2.o avx2.o recov_ssse3.o recov_avx2.o
         CFLAGS += $(shell echo "vpbroadcastb %xmm0, %ymm1" |	\
                     gcc -c -x assembler - >&/dev/null &&	\
                     rm ./-.o && echo -DCONFIG_AS_AVX2=1)
+else ifeq ($(HAS_NEON),yes)
+        OBJS   += neon.o neon1.o neon2.o neon4.o neon8.o
+        CFLAGS += -DCONFIG_KERNEL_MODE_NEON=1
 else
         HAS_ALTIVEC := $(shell echo -e '\#include <altivec.h>\nvector int a;' |\
                          gcc -c -x c - >&/dev/null && \
@@ -55,6 +67,18 @@ raid6.a: $(OBJS)
 raid6test: test.c raid6.a
 	$(CC) $(CFLAGS) -o raid6test $^
 
+neon1.c: neon.uc ../unroll.awk
+	$(AWK) ../unroll.awk -vN=1 < neon.uc > $@
+
+neon2.c: neon.uc ../unroll.awk
+	$(AWK) ../unroll.awk -vN=2 < neon.uc > $@
+
+neon4.c: neon.uc ../unroll.awk
+	$(AWK) ../unroll.awk -vN=4 < neon.uc > $@
+
+neon8.c: neon.uc ../unroll.awk
+	$(AWK) ../unroll.awk -vN=8 < neon.uc > $@
+
 altivec1.c: altivec.uc ../unroll.awk
 	$(AWK) ../unroll.awk -vN=1 < altivec.uc > $@
 
@@ -89,7 +113,7 @@ tables.c: mktables
 	./mktables > tables.c
 
 clean:
-	rm -f *.o *.a mktables mktables.c *.uc int*.c altivec*.c tables.c raid6test
+	rm -f *.o *.a mktables mktables.c *.uc int*.c altivec*.c neon*.c tables.c raid6test
 
 spotless: clean
 	rm -f *~