Merge branch 'samsung/dt' into next/dt

* samsung/dt: (3 commit)
  Merge branch 'depends/rmk/for-linus' into samsung/dt
  Merge branch 'depends/rmk/restart' into next/cleanup
  Merge branch 'next/cleanup' into samsung/dt

Conflicts:
	arch/arm/mach-tegra/board-dt.c
	arch/arm/mach-tegra/include/mach/entry-macro.S

The latest version of the samsung/dt branch resolves
all sorts of conflicts with the latest upstream, no functional
changes that are not already there.
Signed-off-by: NArnd Bergmann <arnd@arndb.de>

Documentation/arm/memory.txt

@@ -51,15 +51,14 @@ ffc00000	ffefffff	DMA memory mapping region.  Memory returned
 ff000000	ffbfffff	Reserved for future expansion of DMA
 				mapping region.
 
-VMALLOC_END	feffffff	Free for platform use, recommended.
-				VMALLOC_END must be aligned to a 2MB
-				boundary.
-
 VMALLOC_START	VMALLOC_END-1	vmalloc() / ioremap() space.
 				Memory returned by vmalloc/ioremap will
 				be dynamically placed in this region.
-				VMALLOC_START may be based upon the value
-				of the high_memory variable.
+				Machine specific static mappings are also
+				located here through iotable_init().
+				VMALLOC_START is based upon the value
+				of the high_memory variable, and VMALLOC_END
+				is equal to 0xff000000.
 
 PAGE_OFFSET	high_memory-1	Kernel direct-mapped RAM region.
 				This maps the platforms RAM, and typically

Documentation/devicetree/bindings/arm/gic.txt

@@ -42,6 +42,10 @@ Optional
 - interrupts	: Interrupt source of the parent interrupt controller. Only
   present on secondary GICs.
 
+- cpu-offset	: per-cpu offset within the distributor and cpu interface
+  regions, used when the GIC doesn't have banked registers. The offset is
+  cpu-offset * cpu-nr.
+
 Example:
 
 	intc: interrupt-controller@fff11000 {

Documentation/devicetree/bindings/arm/vic.txt

+* ARM Vectored Interrupt Controller
+
+One or more Vectored Interrupt Controllers (VIC's) can be connected in an ARM
+system for interrupt routing.  For multiple controllers they can either be
+nested or have the outputs wire-OR'd together.
+
+Required properties:
+
+- compatible : should be one of
+	"arm,pl190-vic"
+	"arm,pl192-vic"
+- interrupt-controller : Identifies the node as an interrupt controller
+- #interrupt-cells : The number of cells to define the interrupts.  Must be 1 as
+  the VIC has no configuration options for interrupt sources.  The cell is a u32
+  and defines the interrupt number.
+- reg : The register bank for the VIC.
+
+Optional properties:
+
+- interrupts : Interrupt source for parent controllers if the VIC is nested.
+
+Example:
+
+	vic0: interrupt-controller@60000 {
+		compatible = "arm,pl192-vic";
+		interrupt-controller;
+		#interrupt-cells = <1>;
+		reg = <0x60000 0x1000>;
+	};

Documentation/virtual/kvm/api.txt

@@ -1100,6 +1100,15 @@ emulate them efficiently. The fields in each entry are defined as follows:
    eax, ebx, ecx, edx: the values returned by the cpuid instruction for
          this function/index combination
 
+The TSC deadline timer feature (CPUID leaf 1, ecx[24]) is always returned
+as false, since the feature depends on KVM_CREATE_IRQCHIP for local APIC
+support.  Instead it is reported via
+
+  ioctl(KVM_CHECK_EXTENSION, KVM_CAP_TSC_DEADLINE_TIMER)
+
+if that returns true and you use KVM_CREATE_IRQCHIP, or if you emulate the
+feature in userspace, then you can enable the feature for KVM_SET_CPUID2.
+
 4.47 KVM_PPC_GET_PVINFO
 
 Capability: KVM_CAP_PPC_GET_PVINFO
@@ -1151,6 +1160,13 @@ following flags are specified:
 /* Depends on KVM_CAP_IOMMU */
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
 
+The KVM_DEV_ASSIGN_ENABLE_IOMMU flag is a mandatory option to ensure
+isolation of the device.  Usages not specifying this flag are deprecated.
+
+Only PCI header type 0 devices with PCI BAR resources are supported by
+device assignment.  The user requesting this ioctl must have read/write
+access to the PCI sysfs resource files associated with the device.
+
 4.49 KVM_DEASSIGN_PCI_DEVICE
 
 Capability: KVM_CAP_DEVICE_DEASSIGNMENT

MAINTAINERS

@@ -1124,13 +1124,6 @@ S:	Supported
 F:	arch/arm/mach-shmobile/
 F:	drivers/sh/
 
-ARM/TELECHIPS ARM ARCHITECTURE
-M:	"Hans J. Koch" <hjk@hansjkoch.de>
-L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:	Maintained
-F:	arch/arm/plat-tcc/
-F:	arch/arm/mach-tcc8k/
-
 ARM/TECHNOLOGIC SYSTEMS TS7250 MACHINE SUPPORT
 M:	Lennert Buytenhek <kernel@wantstofly.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -2700,7 +2693,7 @@ FIREWIRE SUBSYSTEM
 M:	Stefan Richter <stefanr@s5r6.in-berlin.de>
 L:	linux1394-devel@lists.sourceforge.net
 W:	http://ieee1394.wiki.kernel.org/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ieee1394/linux1394-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ieee1394/linux1394.git
 S:	Maintained
 F:	drivers/firewire/
 F:	include/linux/firewire*.h
@@ -3101,6 +3094,7 @@ F:	include/linux/hid*
 
 HIGH-RESOLUTION TIMERS, CLOCKEVENTS, DYNTICKS
 M:	Thomas Gleixner <tglx@linutronix.de>
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core
 S:	Maintained
 F:	Documentation/timers/
 F:	kernel/hrtimer.c
@@ -3610,7 +3604,7 @@ F:	net/irda/
 IRQ SUBSYSTEM
 M:	Thomas Gleixner <tglx@linutronix.de>
 S:	Maintained
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git irq/core
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core
 F:	kernel/irq/
 
 ISAPNP
@@ -4098,7 +4092,7 @@ F:	drivers/hwmon/lm90.c
 LOCKDEP AND LOCKSTAT
 M:	Peter Zijlstra <peterz@infradead.org>
 M:	Ingo Molnar <mingo@redhat.com>
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/peterz/linux-2.6-lockdep.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core/locking
 S:	Maintained
 F:	Documentation/lockdep*.txt
 F:	Documentation/lockstat.txt
@@ -4280,7 +4274,9 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-2.6.git
 S:	Maintained
 F:	Documentation/dvb/
 F:	Documentation/video4linux/
+F:	Documentation/DocBook/media/
 F:	drivers/media/
+F:	drivers/staging/media/
 F:	include/media/
 F:	include/linux/dvb/
 F:	include/linux/videodev*.h
@@ -5086,6 +5082,7 @@ M:	Peter Zijlstra <a.p.zijlstra@chello.nl>
 M:	Paul Mackerras <paulus@samba.org>
 M:	Ingo Molnar <mingo@elte.hu>
 M:	Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf/core
 S:	Supported
 F:	kernel/events/*
 F:	include/linux/perf_event.h
@@ -5117,6 +5114,15 @@ L:	linux-mtd@lists.infradead.org
 S:	Maintained
 F:	drivers/mtd/devices/phram.c
 
+PICOXCELL SUPPORT
+M:	Jamie Iles <jamie@jamieiles.com>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+T:	git git://github.com/jamieiles/linux-2.6-ji.git
+S:	Supported
+F:	arch/arm/mach-picoxcell
+F:	drivers/*/picoxcell*
+F:	drivers/*/*/picoxcell*
+
 PIN CONTROL SUBSYSTEM
 M:	Linus Walleij <linus.walleij@linaro.org>
 S:	Maintained
@@ -5165,6 +5171,7 @@ F:	drivers/scsi/pm8001/
 
 POSIX CLOCKS and TIMERS
 M:	Thomas Gleixner <tglx@linutronix.de>
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core
 S:	Supported
 F:	fs/timerfd.c
 F:	include/linux/timer*
@@ -5680,6 +5687,7 @@ F:	drivers/dma/dw_dmac.c
 TIMEKEEPING, NTP
 M:	John Stultz <johnstul@us.ibm.com>
 M:	Thomas Gleixner <tglx@linutronix.de>
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core
 S:	Supported
 F:	include/linux/clocksource.h
 F:	include/linux/time.h
@@ -5704,6 +5712,7 @@ F:	drivers/watchdog/sc1200wdt.c
 SCHEDULER
 M:	Ingo Molnar <mingo@elte.hu>
 M:	Peter Zijlstra <peterz@infradead.org>
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched/core
 S:	Maintained
 F:	kernel/sched*
 F:	include/linux/sched.h
@@ -6631,7 +6640,7 @@ TRACING
 M:	Steven Rostedt <rostedt@goodmis.org>
 M:	Frederic Weisbecker <fweisbec@gmail.com>
 M:	Ingo Molnar <mingo@redhat.com>
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf/core
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf/core
 S:	Maintained
 F:	Documentation/trace/ftrace.txt
 F:	arch/*/*/*/ftrace.h
@@ -7381,7 +7390,7 @@ M:	Thomas Gleixner <tglx@linutronix.de>
 M:	Ingo Molnar <mingo@redhat.com>
 M:	"H. Peter Anvin" <hpa@zytor.com>
 M:	x86@kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/core
 S:	Maintained
 F:	Documentation/x86/
 F:	arch/x86/

Makefile

 VERSION = 3
 PATCHLEVEL = 2
 SUBLEVEL = 0
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc7
 NAME = Saber-toothed Squirrel
 
 # *DOCUMENTATION*

arch/arm/Kconfig

@@ -258,6 +258,7 @@ config ARCH_INTEGRATOR
 	select ARCH_HAS_CPUFREQ
 	select CLKDEV_LOOKUP
 	select HAVE_MACH_CLKDEV
+	select HAVE_TCM
 	select ICST
 	select GENERIC_CLOCKEVENTS
 	select PLAT_VERSATILE
@@ -341,10 +342,12 @@ config ARCH_HIGHBANK
 	select ARM_AMBA
 	select ARM_GIC
 	select ARM_TIMER_SP804
+	select CACHE_L2X0
 	select CLKDEV_LOOKUP
 	select CPU_V7
 	select GENERIC_CLOCKEVENTS
 	select HAVE_ARM_SCU
+	select HAVE_SMP
 	select USE_OF
 	help
 	  Support for the Calxeda Highbank SoC based boards.
@@ -362,6 +365,7 @@ config ARCH_CNS3XXX
 	select CPU_V6K
 	select GENERIC_CLOCKEVENTS
 	select ARM_GIC
+	select MIGHT_HAVE_CACHE_L2X0
 	select MIGHT_HAVE_PCI
 	select PCI_DOMAINS if PCI
 	help
@@ -382,6 +386,7 @@ config ARCH_PRIMA2
 	select GENERIC_CLOCKEVENTS
 	select CLKDEV_LOOKUP
 	select GENERIC_IRQ_CHIP
+	select MIGHT_HAVE_CACHE_L2X0
 	select USE_OF
 	select ZONE_DMA
 	help
@@ -634,6 +639,8 @@ config ARCH_TEGRA
 	select GENERIC_GPIO
 	select HAVE_CLK
 	select HAVE_SCHED_CLOCK
+	select HAVE_SMP
+	select MIGHT_HAVE_CACHE_L2X0
 	select ARCH_HAS_CPUFREQ
 	help
 	  This enables support for NVIDIA Tegra based systems (Tegra APX,
@@ -651,6 +658,7 @@ config ARCH_PICOXCELL
 	select HAVE_SCHED_CLOCK
 	select HAVE_TCM
 	select NO_IOPORT
+	select SPARSE_IRQ
 	select USE_OF
 	help
 	  This enables support for systems based on the Picochip picoXcell
@@ -703,7 +711,9 @@ config ARCH_SHMOBILE
 	select HAVE_CLK
 	select CLKDEV_LOOKUP
 	select HAVE_MACH_CLKDEV
+	select HAVE_SMP
 	select GENERIC_CLOCKEVENTS
+	select MIGHT_HAVE_CACHE_L2X0
 	select NO_IOPORT
 	select SPARSE_IRQ
 	select MULTI_IRQ_HANDLER
@@ -868,16 +878,6 @@ config ARCH_SHARK
 	  Support for the StrongARM based Digital DNARD machine, also known
 	  as "Shark" (<http://www.shark-linux.de/shark.html>).
 
-config ARCH_TCC_926
-	bool "Telechips TCC ARM926-based systems"
-	select CLKSRC_MMIO
-	select CPU_ARM926T
-	select HAVE_CLK
-	select CLKDEV_LOOKUP
-	select GENERIC_CLOCKEVENTS
-	help
-	  Support for Telechips TCC ARM926-based systems.
-
 config ARCH_U300
 	bool "ST-Ericsson U300 Series"
 	depends on MMU
@@ -893,7 +893,6 @@ config ARCH_U300
 	select HAVE_MACH_CLKDEV
 	select GENERIC_GPIO
 	select ARCH_REQUIRE_GPIOLIB
-	select NEED_MACH_MEMORY_H
 	help
 	  Support for ST-Ericsson U300 series mobile platforms.
 
@@ -905,6 +904,8 @@ config ARCH_U8500
 	select CLKDEV_LOOKUP
 	select ARCH_REQUIRE_GPIOLIB
 	select ARCH_HAS_CPUFREQ
+	select HAVE_SMP
+	select MIGHT_HAVE_CACHE_L2X0
 	help
 	  Support for ST-Ericsson's Ux500 architecture
 
@@ -915,6 +916,7 @@ config ARCH_NOMADIK
 	select CPU_ARM926T
 	select CLKDEV_LOOKUP
 	select GENERIC_CLOCKEVENTS
+	select MIGHT_HAVE_CACHE_L2X0
 	select ARCH_REQUIRE_GPIOLIB
 	help
 	  Support for the Nomadik platform by ST-Ericsson
@@ -974,6 +976,7 @@ config ARCH_ZYNQ
 	select ARM_GIC
 	select ARM_AMBA
 	select ICST
+	select MIGHT_HAVE_CACHE_L2X0
 	select USE_OF
 	help
 	  Support for Xilinx Zynq ARM Cortex A9 Platform
@@ -1060,8 +1063,6 @@ source "arch/arm/plat-s5p/Kconfig"
 
 source "arch/arm/plat-spear/Kconfig"
 
-source "arch/arm/plat-tcc/Kconfig"
-
 if ARCH_S3C2410
 source "arch/arm/mach-s3c2410/Kconfig"
 source "arch/arm/mach-s3c2412/Kconfig"
@@ -1126,6 +1127,11 @@ config ARM_TIMER_SP804
 
 source arch/arm/mm/Kconfig
 
+config ARM_NR_BANKS
+	int
+	default 16 if ARCH_EP93XX
+	default 8
+
 config IWMMXT
 	bool "Enable iWMMXt support"
 	depends on CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_PJ4
@@ -1246,7 +1252,7 @@ config PL310_ERRATA_588369
 
 config ARM_ERRATA_720789
 	bool "ARM errata: TLBIASIDIS and TLBIMVAIS operations can broadcast a faulty ASID"
-	depends on CPU_V7 && SMP
+	depends on CPU_V7
 	help
 	  This option enables the workaround for the 720789 Cortex-A9 (prior to
 	  r2p0) erratum. A faulty ASID can be sent to the other CPUs for the
@@ -1282,7 +1288,7 @@ config ARM_ERRATA_743622
 
 config ARM_ERRATA_751472
 	bool "ARM errata: Interrupted ICIALLUIS may prevent completion of broadcasted operation"
-	depends on CPU_V7 && SMP
+	depends on CPU_V7
 	help
 	  This option enables the workaround for the 751472 Cortex-A9 (prior
 	  to r3p0) erratum. An interrupted ICIALLUIS operation may prevent the
@@ -1435,14 +1441,20 @@ menu "Kernel Features"
 
 source "kernel/time/Kconfig"
 
+config HAVE_SMP
+	bool
+	help
+	  This option should be selected by machines which have an SMP-
+	  capable CPU.
+
+	  The only effect of this option is to make the SMP-related
+	  options available to the user for configuration.
+
 config SMP
 	bool "Symmetric Multi-Processing"
 	depends on CPU_V6K || CPU_V7
 	depends on GENERIC_CLOCKEVENTS
-	depends on REALVIEW_EB_ARM11MP || REALVIEW_EB_A9MP || \
-		 MACH_REALVIEW_PB11MP || MACH_REALVIEW_PBX || ARCH_OMAP4 || \
-		 ARCH_EXYNOS4 || ARCH_TEGRA || ARCH_U8500 || ARCH_VEXPRESS_CA9X4 || \
-		 ARCH_MSM_SCORPIONMP || ARCH_SHMOBILE || ARCH_HIGHBANK || SOC_IMX6Q
+	depends on HAVE_SMP
 	depends on MMU
 	select USE_GENERIC_SMP_HELPERS
 	select HAVE_ARM_SCU if !ARCH_MSM_SCORPIONMP
@@ -1560,6 +1572,16 @@ config LOCAL_TIMERS
 	  accounting to be spread across the timer interval, preventing a
 	  "thundering herd" at every timer tick.
 
+config ARCH_NR_GPIO
+	int
+	default 1024 if ARCH_SHMOBILE || ARCH_TEGRA
+	default 350 if ARCH_U8500
+	default 0
+	help
+	  Maximum number of GPIOs in the system.
+
+	  If unsure, leave the default value.
+
 source kernel/Kconfig.preempt
 
 config HZ
@@ -1972,7 +1994,7 @@ endchoice
 
 config XIP_KERNEL
 	bool "Kernel Execute-In-Place from ROM"
-	depends on !ZBOOT_ROM
+	depends on !ZBOOT_ROM && !ARM_LPAE
 	help
 	  Execute-In-Place allows the kernel to run from non-volatile storage
 	  directly addressable by the CPU, such as NOR flash. This saves RAM
@@ -2002,7 +2024,7 @@ config XIP_PHYS_ADDR
 
 config KEXEC
 	bool "Kexec system call (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	depends on EXPERIMENTAL && (!SMP || HOTPLUG_CPU)
 	help
 	  kexec is a system call that implements the ability to shutdown your
 	  current kernel, and to start another kernel.  It is like a reboot

arch/arm/Kconfig.debug

@@ -100,6 +100,14 @@ choice
 		  Note that the system will appear to hang during boot if there
 		  is nothing connected to read from the DCC.
 
+	config AT91_DEBUG_LL_DBGU0
+		bool "Kernel low-level debugging on rm9200, 9260/9g20, 9261/9g10 and 9rl"
+		depends on HAVE_AT91_DBGU0
+
+	config AT91_DEBUG_LL_DBGU1
+		bool "Kernel low-level debugging on 9263, 9g45 and cap9"
+		depends on HAVE_AT91_DBGU1
+
 	config DEBUG_FOOTBRIDGE_COM1
 		bool "Kernel low-level debugging messages via footbridge 8250 at PCI COM1"
 		depends on FOOTBRIDGE
@@ -247,6 +255,43 @@ choice
 		  their output to the standard serial port on the RealView
 		  PB1176 platform.
 
+	config DEBUG_MSM_UART1
+		bool "Kernel low-level debugging messages via MSM UART1"
+		depends on ARCH_MSM7X00A || ARCH_MSM7X30 || ARCH_QSD8X50
+		help
+		  Say Y here if you want the debug print routines to direct
+		  their output to the first serial port on MSM devices.
+
+	config DEBUG_MSM_UART2
+		bool "Kernel low-level debugging messages via MSM UART2"
+		depends on ARCH_MSM7X00A || ARCH_MSM7X30 || ARCH_QSD8X50
+		help
+		  Say Y here if you want the debug print routines to direct
+		  their output to the second serial port on MSM devices.
+
+	config DEBUG_MSM_UART3
+		bool "Kernel low-level debugging messages via MSM UART3"
+		depends on ARCH_MSM7X00A || ARCH_MSM7X30 || ARCH_QSD8X50
+		help
+		  Say Y here if you want the debug print routines to direct
+		  their output to the third serial port on MSM devices.
+
+	config DEBUG_MSM8660_UART
+		bool "Kernel low-level debugging messages via MSM 8660 UART"
+		depends on ARCH_MSM8X60
+		select MSM_HAS_DEBUG_UART_HS
+		help
+		  Say Y here if you want the debug print routines to direct
+		  their output to the serial port on MSM 8660 devices.
+
+	config DEBUG_MSM8960_UART
+		bool "Kernel low-level debugging messages via MSM 8960 UART"
+		depends on ARCH_MSM8960
+		select MSM_HAS_DEBUG_UART_HS
+		help
+		  Say Y here if you want the debug print routines to direct
+		  their output to the serial port on MSM 8960 devices.
+
 endchoice
 
 config EARLY_PRINTK

arch/arm/Makefile

@@ -184,7 +184,6 @@ machine-$(CONFIG_ARCH_EXYNOS4)		:= exynos
 machine-$(CONFIG_ARCH_SA1100)		:= sa1100
 machine-$(CONFIG_ARCH_SHARK)		:= shark
 machine-$(CONFIG_ARCH_SHMOBILE) 	:= shmobile
-machine-$(CONFIG_ARCH_TCC8K)		:= tcc8k
 machine-$(CONFIG_ARCH_TEGRA)		:= tegra
 machine-$(CONFIG_ARCH_U300)		:= u300
 machine-$(CONFIG_ARCH_U8500)		:= ux500
@@ -204,7 +203,6 @@ machine-$(CONFIG_ARCH_ZYNQ)		:= zynq
 plat-$(CONFIG_ARCH_MXC)		:= mxc
 plat-$(CONFIG_ARCH_OMAP)	:= omap
 plat-$(CONFIG_ARCH_S3C64XX)	:= samsung
-plat-$(CONFIG_ARCH_TCC_926)	:= tcc
 plat-$(CONFIG_ARCH_ZYNQ)	:= versatile
 plat-$(CONFIG_PLAT_IOP)		:= iop
 plat-$(CONFIG_PLAT_NOMADIK)	:= nomadik

arch/arm/boot/compressed/Makefile

@@ -126,7 +126,8 @@ ccflags-y := -fpic -fno-builtin -I$(obj)
 asflags-y := -Wa,-march=all
 
 # Supply kernel BSS size to the decompressor via a linker symbol.
-KBSS_SZ = $(shell size $(obj)/../../../../vmlinux | awk 'END{print $$3}')
+KBSS_SZ = $(shell $(CROSS_COMPILE)size $(obj)/../../../../vmlinux | \
+		awk 'END{print $$3}')
 LDFLAGS_vmlinux = --defsym _kernel_bss_size=$(KBSS_SZ)
 # Supply ZRELADDR to the decompressor via a linker symbol.
 ifneq ($(CONFIG_AUTO_ZRELADDR),y)

arch/arm/boot/compressed/head.S

@@ -659,6 +659,7 @@ __armv7_mmu_cache_on:
 		mcrne	p15, 0, r3, c2, c0, 0	@ load page table pointer
 		mcrne	p15, 0, r1, c3, c0, 0	@ load domain access control
 #endif
+		mcr	p15, 0, r0, c7, c5, 4	@ ISB
 		mcr	p15, 0, r0, c1, c0, 0	@ load control register
 		mrc	p15, 0, r0, c1, c0, 0	@ and read it back
 		mov	r0, #0

arch/arm/common/Kconfig

 config ARM_GIC
 	select IRQ_DOMAIN
+	select MULTI_IRQ_HANDLER
+	bool
+
+config GIC_NON_BANKED
 	bool
 
 config ARM_VIC
+	select IRQ_DOMAIN
+	select MULTI_IRQ_HANDLER
 	bool
 
 config ARM_VIC_NR

arch/arm/common/gic.c

@@ -40,13 +40,36 @@
 #include <linux/slab.h>
 
 #include <asm/irq.h>
+#include <asm/exception.h>
 #include <asm/mach/irq.h>
 #include <asm/hardware/gic.h>
 
-static DEFINE_RAW_SPINLOCK(irq_controller_lock);
+union gic_base {
+	void __iomem *common_base;
+	void __percpu __iomem **percpu_base;
+};
+
+struct gic_chip_data {
+	unsigned int irq_offset;
+	union gic_base dist_base;
+	union gic_base cpu_base;
+#ifdef CONFIG_CPU_PM
+	u32 saved_spi_enable[DIV_ROUND_UP(1020, 32)];
+	u32 saved_spi_conf[DIV_ROUND_UP(1020, 16)];
+	u32 saved_spi_target[DIV_ROUND_UP(1020, 4)];
+	u32 __percpu *saved_ppi_enable;
+	u32 __percpu *saved_ppi_conf;
+#endif
+#ifdef CONFIG_IRQ_DOMAIN
+	struct irq_domain domain;
+#endif
+	unsigned int gic_irqs;
+#ifdef CONFIG_GIC_NON_BANKED
+	void __iomem *(*get_base)(union gic_base *);
+#endif
+};
 
-/* Address of GIC 0 CPU interface */
-void __iomem *gic_cpu_base_addr __read_mostly;
+static DEFINE_RAW_SPINLOCK(irq_controller_lock);
 
 /*
  * Supported arch specific GIC irq extension.
@@ -67,16 +90,48 @@ struct irq_chip gic_arch_extn = {
 
 static struct gic_chip_data gic_data[MAX_GIC_NR] __read_mostly;
 
+#ifdef CONFIG_GIC_NON_BANKED
+static void __iomem *gic_get_percpu_base(union gic_base *base)
+{
+	return *__this_cpu_ptr(base->percpu_base);
+}
+
+static void __iomem *gic_get_common_base(union gic_base *base)
+{
+	return base->common_base;
+}
+
+static inline void __iomem *gic_data_dist_base(struct gic_chip_data *data)
+{
+	return data->get_base(&data->dist_base);
+}
+
+static inline void __iomem *gic_data_cpu_base(struct gic_chip_data *data)
+{
+	return data->get_base(&data->cpu_base);
+}
+
+static inline void gic_set_base_accessor(struct gic_chip_data *data,
+					 void __iomem *(*f)(union gic_base *))
+{
+	data->get_base = f;
+}
+#else
+#define gic_data_dist_base(d)	((d)->dist_base.common_base)
+#define gic_data_cpu_base(d)	((d)->cpu_base.common_base)
+#define gic_set_base_accessor(d,f)
+#endif
+
 static inline void __iomem *gic_dist_base(struct irq_data *d)
 {
 	struct gic_chip_data *gic_data = irq_data_get_irq_chip_data(d);
-	return gic_data->dist_base;
+	return gic_data_dist_base(gic_data);
 }
 
 static inline void __iomem *gic_cpu_base(struct irq_data *d)
 {
 	struct gic_chip_data *gic_data = irq_data_get_irq_chip_data(d);
-	return gic_data->cpu_base;
+	return gic_data_cpu_base(gic_data);
 }
 
 static inline unsigned int gic_irq(struct irq_data *d)
@@ -215,6 +270,32 @@ static int gic_set_wake(struct irq_data *d, unsigned int on)
 #define gic_set_wake	NULL
 #endif
 
+asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
+{
+	u32 irqstat, irqnr;
+	struct gic_chip_data *gic = &gic_data[0];
+	void __iomem *cpu_base = gic_data_cpu_base(gic);
+
+	do {
+		irqstat = readl_relaxed(cpu_base + GIC_CPU_INTACK);
+		irqnr = irqstat & ~0x1c00;
+
+		if (likely(irqnr > 15 && irqnr < 1021)) {
+			irqnr = irq_domain_to_irq(&gic->domain, irqnr);
+			handle_IRQ(irqnr, regs);
+			continue;
+		}
+		if (irqnr < 16) {
+			writel_relaxed(irqstat, cpu_base + GIC_CPU_EOI);
+#ifdef CONFIG_SMP
+			handle_IPI(irqnr, regs);
+#endif
+			continue;
+		}
+		break;
+	} while (1);
+}
+
 static void gic_handle_cascade_irq(unsigned int irq, struct irq_desc *desc)
 {
 	struct gic_chip_data *chip_data = irq_get_handler_data(irq);
@@ -225,7 +306,7 @@ static void gic_handle_cascade_irq(unsigned int irq, struct irq_desc *desc)
 	chained_irq_enter(chip, desc);
 
 	raw_spin_lock(&irq_controller_lock);
-	status = readl_relaxed(chip_data->cpu_base + GIC_CPU_INTACK);
+	status = readl_relaxed(gic_data_cpu_base(chip_data) + GIC_CPU_INTACK);
 	raw_spin_unlock(&irq_controller_lock);
 
 	gic_irq = (status & 0x3ff);
@@ -270,7 +351,7 @@ static void __init gic_dist_init(struct gic_chip_data *gic)
 	u32 cpumask;
 	unsigned int gic_irqs = gic->gic_irqs;
 	struct irq_domain *domain = &gic->domain;
-	void __iomem *base = gic->dist_base;
+	void __iomem *base = gic_data_dist_base(gic);
 	u32 cpu = 0;
 
 #ifdef CONFIG_SMP
@@ -330,8 +411,8 @@ static void __init gic_dist_init(struct gic_chip_data *gic)
 
 static void __cpuinit gic_cpu_init(struct gic_chip_data *gic)
 {
-	void __iomem *dist_base = gic->dist_base;
-	void __iomem *base = gic->cpu_base;
+	void __iomem *dist_base = gic_data_dist_base(gic);
+	void __iomem *base = gic_data_cpu_base(gic);
 	int i;
 
 	/*
@@ -368,7 +449,7 @@ static void gic_dist_save(unsigned int gic_nr)
 		BUG();
 
 	gic_irqs = gic_data[gic_nr].gic_irqs;
-	dist_base = gic_data[gic_nr].dist_base;
+	dist_base = gic_data_dist_base(&gic_data[gic_nr]);
 
 	if (!dist_base)
 		return;
@@ -403,7 +484,7 @@ static void gic_dist_restore(unsigned int gic_nr)
 		BUG();
 
 	gic_irqs = gic_data[gic_nr].gic_irqs;
-	dist_base = gic_data[gic_nr].dist_base;
+	dist_base = gic_data_dist_base(&gic_data[gic_nr]);
 
 	if (!dist_base)
 		return;
@@ -439,8 +520,8 @@ static void gic_cpu_save(unsigned int gic_nr)
 	if (gic_nr >= MAX_GIC_NR)
 		BUG();
 
-	dist_base = gic_data[gic_nr].dist_base;
-	cpu_base = gic_data[gic_nr].cpu_base;
+	dist_base = gic_data_dist_base(&gic_data[gic_nr]);
+	cpu_base = gic_data_cpu_base(&gic_data[gic_nr]);
 
 	if (!dist_base || !cpu_base)
 		return;
@@ -465,8 +546,8 @@ static void gic_cpu_restore(unsigned int gic_nr)
 	if (gic_nr >= MAX_GIC_NR)
 		BUG();
 
-	dist_base = gic_data[gic_nr].dist_base;
-	cpu_base = gic_data[gic_nr].cpu_base;
+	dist_base = gic_data_dist_base(&gic_data[gic_nr]);
+	cpu_base = gic_data_cpu_base(&gic_data[gic_nr]);
 
 	if (!dist_base || !cpu_base)
 		return;
@@ -491,6 +572,11 @@ static int gic_notifier(struct notifier_block *self, unsigned long cmd,	void *v)
 	int i;
 
 	for (i = 0; i < MAX_GIC_NR; i++) {
+#ifdef CONFIG_GIC_NON_BANKED
+		/* Skip over unused GICs */
+		if (!gic_data[i].get_base)
+			continue;
+#endif
 		switch (cmd) {
 		case CPU_PM_ENTER:
 			gic_cpu_save(i);
@@ -564,8 +650,9 @@ const struct irq_domain_ops gic_irq_domain_ops = {
 #endif
 };
 
-void __init gic_init(unsigned int gic_nr, int irq_start,
-	void __iomem *dist_base, void __iomem *cpu_base)
+void __init gic_init_bases(unsigned int gic_nr, int irq_start,
+			   void __iomem *dist_base, void __iomem *cpu_base,
+			   u32 percpu_offset)
 {
 	struct gic_chip_data *gic;
 	struct irq_domain *domain;
@@ -575,8 +662,36 @@ void __init gic_init(unsigned int gic_nr, int irq_start,
 
 	gic = &gic_data[gic_nr];
 	domain = &gic->domain;
-	gic->dist_base = dist_base;
-	gic->cpu_base = cpu_base;
+#ifdef CONFIG_GIC_NON_BANKED
+	if (percpu_offset) { /* Frankein-GIC without banked registers... */
+		unsigned int cpu;
+
+		gic->dist_base.percpu_base = alloc_percpu(void __iomem *);
+		gic->cpu_base.percpu_base = alloc_percpu(void __iomem *);
+		if (WARN_ON(!gic->dist_base.percpu_base ||
+			    !gic->cpu_base.percpu_base)) {
+			free_percpu(gic->dist_base.percpu_base);
+			free_percpu(gic->cpu_base.percpu_base);
+			return;
+		}
+
+		for_each_possible_cpu(cpu) {
+			unsigned long offset = percpu_offset * cpu_logical_map(cpu);
+			*per_cpu_ptr(gic->dist_base.percpu_base, cpu) = dist_base + offset;
+			*per_cpu_ptr(gic->cpu_base.percpu_base, cpu) = cpu_base + offset;
+		}
+
+		gic_set_base_accessor(gic, gic_get_percpu_base);
+	} else
+#endif
+	{			/* Normal, sane GIC... */
+		WARN(percpu_offset,
+		     "GIC_NON_BANKED not enabled, ignoring %08x offset!",
+		     percpu_offset);
+		gic->dist_base.common_base = dist_base;
+		gic->cpu_base.common_base = cpu_base;
+		gic_set_base_accessor(gic, gic_get_common_base);
+	}
 
 	/*
 	 * For primary GICs, skip over SGIs.
@@ -584,8 +699,6 @@ void __init gic_init(unsigned int gic_nr, int irq_start,
 	 */
 	domain->hwirq_base = 32;
 	if (gic_nr == 0) {
-		gic_cpu_base_addr = cpu_base;
-
 		if ((irq_start & 31) > 0) {
 			domain->hwirq_base = 16;
 			if (irq_start != -1)
@@ -597,7 +710,7 @@ void __init gic_init(unsigned int gic_nr, int irq_start,
 	 * Find out how many interrupts are supported.
 	 * The GIC only supports up to 1020 interrupt sources.
 	 */
-	gic_irqs = readl_relaxed(dist_base + GIC_DIST_CTR) & 0x1f;
+	gic_irqs = readl_relaxed(gic_data_dist_base(gic) + GIC_DIST_CTR) & 0x1f;
 	gic_irqs = (gic_irqs + 1) * 32;
 	if (gic_irqs > 1020)
 		gic_irqs = 1020;
@@ -645,7 +758,7 @@ void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 	dsb();
 
 	/* this always happens on GIC0 */
-	writel_relaxed(map << 16 | irq, gic_data[0].dist_base + GIC_DIST_SOFTINT);
+	writel_relaxed(map << 16 | irq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
 }
 #endif
 
@@ -656,6 +769,7 @@ int __init gic_of_init(struct device_node *node, struct device_node *parent)
 {
 	void __iomem *cpu_base;
 	void __iomem *dist_base;
+	u32 percpu_offset;
 	int irq;
 	struct irq_domain *domain = &gic_data[gic_cnt].domain;
 
@@ -668,9 +782,12 @@ int __init gic_of_init(struct device_node *node, struct device_node *parent)
 	cpu_base = of_iomap(node, 1);
 	WARN(!cpu_base, "unable to map gic cpu registers\n");
 
+	if (of_property_read_u32(node, "cpu-offset", &percpu_offset))
+		percpu_offset = 0;
+
 	domain->of_node = of_node_get(node);
 
-	gic_init(gic_cnt, -1, dist_base, cpu_base);
+	gic_init_bases(gic_cnt, -1, dist_base, cpu_base, percpu_offset);
 
 	if (parent) {
 		irq = irq_of_parse_and_map(node, 0);

arch/arm/common/pl330.c

@@ -221,17 +221,6 @@
  */
 #define MCODE_BUFF_PER_REQ	256
 
-/*
- * Mark a _pl330_req as free.
- * We do it by writing DMAEND as the first instruction
- * because no valid request is going to have DMAEND as
- * its first instruction to execute.
- */
-#define MARK_FREE(req)	do { \
-				_emit_END(0, (req)->mc_cpu); \
-				(req)->mc_len = 0; \
-			} while (0)
-
 /* If the _pl330_req is available to the client */
 #define IS_FREE(req)	(*((u8 *)((req)->mc_cpu)) == CMD_DMAEND)
 
@@ -301,8 +290,10 @@ struct pl330_thread {
 	struct pl330_dmac *dmac;
 	/* Only two at a time */
 	struct _pl330_req req[2];
-	/* Index of the last submitted request */
+	/* Index of the last enqueued request */
 	unsigned lstenq;
+	/* Index of the last submitted request or -1 if the DMA is stopped */
+	int req_running;
 };
 
 enum pl330_dmac_state {
@@ -778,6 +769,22 @@ static inline void _execute_DBGINSN(struct pl330_thread *thrd,
 	writel(0, regs + DBGCMD);
 }
 
+/*
+ * Mark a _pl330_req as free.
+ * We do it by writing DMAEND as the first instruction
+ * because no valid request is going to have DMAEND as
+ * its first instruction to execute.
+ */
+static void mark_free(struct pl330_thread *thrd, int idx)
+{
+	struct _pl330_req *req = &thrd->req[idx];
+
+	_emit_END(0, req->mc_cpu);
+	req->mc_len = 0;
+
+	thrd->req_running = -1;
+}
+
 static inline u32 _state(struct pl330_thread *thrd)
 {
 	void __iomem *regs = thrd->dmac->pinfo->base;
@@ -836,31 +843,6 @@ static inline u32 _state(struct pl330_thread *thrd)
 	}
 }
 
-/* If the request 'req' of thread 'thrd' is currently active */
-static inline bool _req_active(struct pl330_thread *thrd,
-		struct _pl330_req *req)
-{
-	void __iomem *regs = thrd->dmac->pinfo->base;
-	u32 buf = req->mc_bus, pc = readl(regs + CPC(thrd->id));
-
-	if (IS_FREE(req))
-		return false;
-
-	return (pc >= buf && pc <= buf + req->mc_len) ? true : false;
-}
-
-/* Returns 0 if the thread is inactive, ID of active req + 1 otherwise */
-static inline unsigned _thrd_active(struct pl330_thread *thrd)
-{
-	if (_req_active(thrd, &thrd->req[0]))
-		return 1; /* First req active */
-
-	if (_req_active(thrd, &thrd->req[1]))
-		return 2; /* Second req active */
-
-	return 0;
-}
-
 static void _stop(struct pl330_thread *thrd)
 {
 	void __iomem *regs = thrd->dmac->pinfo->base;
@@ -892,17 +874,22 @@ static bool _trigger(struct pl330_thread *thrd)
 	struct _arg_GO go;
 	unsigned ns;
 	u8 insn[6] = {0, 0, 0, 0, 0, 0};
+	int idx;
 
 	/* Return if already ACTIVE */
 	if (_state(thrd) != PL330_STATE_STOPPED)
 		return true;
 
-	if (!IS_FREE(&thrd->req[1 - thrd->lstenq]))
-		req = &thrd->req[1 - thrd->lstenq];
-	else if (!IS_FREE(&thrd->req[thrd->lstenq]))
-		req = &thrd->req[thrd->lstenq];
+	idx = 1 - thrd->lstenq;
+	if (!IS_FREE(&thrd->req[idx]))
+		req = &thrd->req[idx];
+	else {
+		idx = thrd->lstenq;
+		if (!IS_FREE(&thrd->req[idx]))
+			req = &thrd->req[idx];
 		else
 			req = NULL;
+	}
 
 	/* Return if no request */
 	if (!req || !req->r)
@@ -933,6 +920,8 @@ static bool _trigger(struct pl330_thread *thrd)
 	/* Only manager can execute GO */
 	_execute_DBGINSN(thrd, insn, true);
 
+	thrd->req_running = idx;
+
 	return true;
 }
 
@@ -1382,8 +1371,8 @@ static void pl330_dotask(unsigned long data)
 
 			thrd->req[0].r = NULL;
 			thrd->req[1].r = NULL;
-			MARK_FREE(&thrd->req[0]);
-			MARK_FREE(&thrd->req[1]);
+			mark_free(thrd, 0);
+			mark_free(thrd, 1);
 
 			/* Clear the reset flag */
 			pl330->dmac_tbd.reset_chan &= ~(1 << i);
@@ -1461,14 +1450,12 @@ int pl330_update(const struct pl330_info *pi)
 
 			thrd = &pl330->channels[id];
 
-			active = _thrd_active(thrd);
-			if (!active) /* Aborted */
+			active = thrd->req_running;
+			if (active == -1) /* Aborted */
 				continue;
 
-			active -= 1;
-
 			rqdone = &thrd->req[active];
-			MARK_FREE(rqdone);
+			mark_free(thrd, active);
 
 			/* Get going again ASAP */
 			_start(thrd);
@@ -1480,13 +1467,19 @@ int pl330_update(const struct pl330_info *pi)
 
 	/* Now that we are in no hurry, do the callbacks */
 	while (!list_empty(&pl330->req_done)) {
+		struct pl330_req *r;
+
 		rqdone = container_of(pl330->req_done.next,
 					struct _pl330_req, rqd);
 
 		list_del_init(&rqdone->rqd);
 
+		/* Detach the req */
+		r = rqdone->r;
+		rqdone->r = NULL;
+
 		spin_unlock_irqrestore(&pl330->lock, flags);
-		_callback(rqdone->r, PL330_ERR_NONE);
+		_callback(r, PL330_ERR_NONE);
 		spin_lock_irqsave(&pl330->lock, flags);
 	}
 
@@ -1509,7 +1502,7 @@ int pl330_chan_ctrl(void *ch_id, enum pl330_chan_op op)
 	struct pl330_thread *thrd = ch_id;
 	struct pl330_dmac *pl330;
 	unsigned long flags;
-	int ret = 0, active;
+	int ret = 0, active = thrd->req_running;
 
 	if (!thrd || thrd->free || thrd->dmac->state == DYING)
 		return -EINVAL;
@@ -1525,28 +1518,24 @@ int pl330_chan_ctrl(void *ch_id, enum pl330_chan_op op)
 
 		thrd->req[0].r = NULL;
 		thrd->req[1].r = NULL;
-		MARK_FREE(&thrd->req[0]);
-		MARK_FREE(&thrd->req[1]);
+		mark_free(thrd, 0);
+		mark_free(thrd, 1);
 		break;
 
 	case PL330_OP_ABORT:
-		active = _thrd_active(thrd);
-
 		/* Make sure the channel is stopped */
 		_stop(thrd);
 
 		/* ABORT is only for the active req */
-		if (!active)
+		if (active == -1)
 			break;
 
-		active--;
-
 		thrd->req[active].r = NULL;
-		MARK_FREE(&thrd->req[active]);
+		mark_free(thrd, active);
 
 		/* Start the next */
 	case PL330_OP_START:
-		if (!_thrd_active(thrd) && !_start(thrd))
+		if ((active == -1) && !_start(thrd))
 			ret = -EIO;
 		break;
 
@@ -1587,14 +1576,13 @@ int pl330_chan_status(void *ch_id, struct pl330_chanstatus *pstatus)
 	else
 		pstatus->faulting = false;
 
-	active = _thrd_active(thrd);
+	active = thrd->req_running;
 
-	if (!active) {
+	if (active == -1) {
 		/* Indicate that the thread is not running */
 		pstatus->top_req = NULL;
 		pstatus->wait_req = NULL;
 	} else {
-		active--;
 		pstatus->top_req = thrd->req[active].r;
 		pstatus->wait_req = !IS_FREE(&thrd->req[1 - active])
 					? thrd->req[1 - active].r : NULL;
@@ -1659,9 +1647,9 @@ void *pl330_request_channel(const struct pl330_info *pi)
 				thrd->free = false;
 				thrd->lstenq = 1;
 				thrd->req[0].r = NULL;
-				MARK_FREE(&thrd->req[0]);
+				mark_free(thrd, 0);
 				thrd->req[1].r = NULL;
-				MARK_FREE(&thrd->req[1]);
+				mark_free(thrd, 1);
 				break;
 			}
 		}
@@ -1767,14 +1755,14 @@ static inline void _reset_thread(struct pl330_thread *thrd)
 	thrd->req[0].mc_bus = pl330->mcode_bus
 				+ (thrd->id * pi->mcbufsz);
 	thrd->req[0].r = NULL;
-	MARK_FREE(&thrd->req[0]);
+	mark_free(thrd, 0);
 
 	thrd->req[1].mc_cpu = thrd->req[0].mc_cpu
 				+ pi->mcbufsz / 2;
 	thrd->req[1].mc_bus = thrd->req[0].mc_bus
 				+ pi->mcbufsz / 2;
 	thrd->req[1].r = NULL;
-	MARK_FREE(&thrd->req[1]);
+	mark_free(thrd, 1);
 }
 
 static int dmac_alloc_threads(struct pl330_dmac *pl330)

arch/arm/common/timer-sp.c

@@ -143,7 +143,6 @@ static int sp804_set_next_event(unsigned long next,
 }
 
 static struct clock_event_device sp804_clockevent = {
-	.shift		= 32,
 	.features       = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
 	.set_mode	= sp804_set_mode,
 	.set_next_event	= sp804_set_next_event,
@@ -169,13 +168,9 @@ void __init sp804_clockevents_init(void __iomem *base, unsigned int irq,
 
 	clkevt_base = base;
 	clkevt_reload = DIV_ROUND_CLOSEST(rate, HZ);
-
 	evt->name = name;
 	evt->irq = irq;
-	evt->mult = div_sc(rate, NSEC_PER_SEC, evt->shift);
-	evt->max_delta_ns = clockevent_delta2ns(0xffffffff, evt);
-	evt->min_delta_ns = clockevent_delta2ns(0xf, evt);
 
 	setup_irq(irq, &sp804_timer_irq);
-	clockevents_register_device(evt);
+	clockevents_config_and_register(evt, rate, 0xf, 0xffffffff);
 }

arch/arm/common/vic.c

@@ -19,17 +19,22 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/io.h>
+#include <linux/irqdomain.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
 #include <linux/syscore_ops.h>
 #include <linux/device.h>
 #include <linux/amba/bus.h>
 
+#include <asm/exception.h>
 #include <asm/mach/irq.h>
 #include <asm/hardware/vic.h>
 
-#ifdef CONFIG_PM
 /**
  * struct vic_device - VIC PM device
  * @irq: The IRQ number for the base of the VIC.
@@ -40,6 +45,7 @@
  * @int_enable: Save for VIC_INT_ENABLE.
  * @soft_int: Save for VIC_INT_SOFT.
  * @protect: Save for VIC_PROTECT.
+ * @domain: The IRQ domain for the VIC.
  */
 struct vic_device {
 	void __iomem	*base;
@@ -50,13 +56,13 @@ struct vic_device {
 	u32		int_enable;
 	u32		soft_int;
 	u32		protect;
+	struct irq_domain domain;
 };
 
 /* we cannot allocate memory when VICs are initially registered */
 static struct vic_device vic_devices[CONFIG_ARM_VIC_NR];
 
 static int vic_id;
-#endif /* CONFIG_PM */
 
 /**
  * vic_init2 - common initialisation code
@@ -156,39 +162,50 @@ static int __init vic_pm_init(void)
 	return 0;
 }
 late_initcall(vic_pm_init);
+#endif /* CONFIG_PM */
 
 /**
- * vic_pm_register - Register a VIC for later power management control
+ * vic_register() - Register a VIC.
  * @base: The base address of the VIC.
  * @irq: The base IRQ for the VIC.
  * @resume_sources: bitmask of interrupts allowed for resume sources.
+ * @node: The device tree node associated with the VIC.
  *
  * Register the VIC with the system device tree so that it can be notified
  * of suspend and resume requests and ensure that the correct actions are
  * taken to re-instate the settings on resume.
+ *
+ * This also configures the IRQ domain for the VIC.
  */
-static void __init vic_pm_register(void __iomem *base, unsigned int irq, u32 resume_sources)
+static void __init vic_register(void __iomem *base, unsigned int irq,
+				u32 resume_sources, struct device_node *node)
 {
 	struct vic_device *v;
 
-	if (vic_id >= ARRAY_SIZE(vic_devices))
+	if (vic_id >= ARRAY_SIZE(vic_devices)) {
 		printk(KERN_ERR "%s: too few VICs, increase CONFIG_ARM_VIC_NR\n", __func__);
-	else {
+		return;
+	}
+
 	v = &vic_devices[vic_id];
 	v->base = base;
 	v->resume_sources = resume_sources;
 	v->irq = irq;
 	vic_id++;
-	}
+
+	v->domain.irq_base = irq;
+	v->domain.nr_irq = 32;
+#ifdef CONFIG_OF_IRQ
+	v->domain.of_node = of_node_get(node);
+#endif /* CONFIG_OF */
+	v->domain.ops = &irq_domain_simple_ops;
+	irq_domain_add(&v->domain);
 }
-#else
-static inline void vic_pm_register(void __iomem *base, unsigned int irq, u32 arg1) { }
-#endif /* CONFIG_PM */
 
 static void vic_ack_irq(struct irq_data *d)
 {
 	void __iomem *base = irq_data_get_irq_chip_data(d);
-	unsigned int irq = d->irq & 31;
+	unsigned int irq = d->hwirq;
 	writel(1 << irq, base + VIC_INT_ENABLE_CLEAR);
 	/* moreover, clear the soft-triggered, in case it was the reason */
 	writel(1 << irq, base + VIC_INT_SOFT_CLEAR);
@@ -197,14 +214,14 @@ static void vic_ack_irq(struct irq_data *d)
 static void vic_mask_irq(struct irq_data *d)
 {
 	void __iomem *base = irq_data_get_irq_chip_data(d);
-	unsigned int irq = d->irq & 31;
+	unsigned int irq = d->hwirq;
 	writel(1 << irq, base + VIC_INT_ENABLE_CLEAR);
 }
 
 static void vic_unmask_irq(struct irq_data *d)
 {
 	void __iomem *base = irq_data_get_irq_chip_data(d);
-	unsigned int irq = d->irq & 31;
+	unsigned int irq = d->hwirq;
 	writel(1 << irq, base + VIC_INT_ENABLE);
 }
 
@@ -226,7 +243,7 @@ static struct vic_device *vic_from_irq(unsigned int irq)
 static int vic_set_wake(struct irq_data *d, unsigned int on)
 {
 	struct vic_device *v = vic_from_irq(d->irq);
-	unsigned int off = d->irq & 31;
+	unsigned int off = d->hwirq;
 	u32 bit = 1 << off;
 
 	if (!v)
@@ -301,7 +318,7 @@ static void __init vic_set_irq_sources(void __iomem *base,
  *  and 020 within the page. We call this "second block".
  */
 static void __init vic_init_st(void __iomem *base, unsigned int irq_start,
-				u32 vic_sources)
+			       u32 vic_sources, struct device_node *node)
 {
 	unsigned int i;
 	int vic_2nd_block = ((unsigned long)base & ~PAGE_MASK) != 0;
@@ -328,17 +345,12 @@ static void __init vic_init_st(void __iomem *base, unsigned int irq_start,
 	}
 
 	vic_set_irq_sources(base, irq_start, vic_sources);
+	vic_register(base, irq_start, 0, node);
 }
 
-/**
- * vic_init - initialise a vectored interrupt controller
- * @base: iomem base address
- * @irq_start: starting interrupt number, must be muliple of 32
- * @vic_sources: bitmask of interrupt sources to allow
- * @resume_sources: bitmask of interrupt sources to allow for resume
- */
-void __init vic_init(void __iomem *base, unsigned int irq_start,
-		     u32 vic_sources, u32 resume_sources)
+static void __init __vic_init(void __iomem *base, unsigned int irq_start,
+			      u32 vic_sources, u32 resume_sources,
+			      struct device_node *node)
 {
 	unsigned int i;
 	u32 cellid = 0;
@@ -356,7 +368,7 @@ void __init vic_init(void __iomem *base, unsigned int irq_start,
 
 	switch(vendor) {
 	case AMBA_VENDOR_ST:
-		vic_init_st(base, irq_start, vic_sources);
+		vic_init_st(base, irq_start, vic_sources, node);
 		return;
 	default:
 		printk(KERN_WARNING "VIC: unknown vendor, continuing anyways\n");
@@ -375,5 +387,81 @@ void __init vic_init(void __iomem *base, unsigned int irq_start,
 
 	vic_set_irq_sources(base, irq_start, vic_sources);
 
-	vic_pm_register(base, irq_start, resume_sources);
+	vic_register(base, irq_start, resume_sources, node);
+}
+
+/**
+ * vic_init() - initialise a vectored interrupt controller
+ * @base: iomem base address
+ * @irq_start: starting interrupt number, must be muliple of 32
+ * @vic_sources: bitmask of interrupt sources to allow
+ * @resume_sources: bitmask of interrupt sources to allow for resume
+ */
+void __init vic_init(void __iomem *base, unsigned int irq_start,
+		     u32 vic_sources, u32 resume_sources)
+{
+	__vic_init(base, irq_start, vic_sources, resume_sources, NULL);
+}
+
+#ifdef CONFIG_OF
+int __init vic_of_init(struct device_node *node, struct device_node *parent)
+{
+	void __iomem *regs;
+	int irq_base;
+
+	if (WARN(parent, "non-root VICs are not supported"))
+		return -EINVAL;
+
+	regs = of_iomap(node, 0);
+	if (WARN_ON(!regs))
+		return -EIO;
+
+	irq_base = irq_alloc_descs(-1, 0, 32, numa_node_id());
+	if (WARN_ON(irq_base < 0))
+		goto out_unmap;
+
+	__vic_init(regs, irq_base, ~0, ~0, node);
+
+	return 0;
+
+ out_unmap:
+	iounmap(regs);
+
+	return -EIO;
+}
+#endif /* CONFIG OF */
+
+/*
+ * Handle each interrupt in a single VIC.  Returns non-zero if we've
+ * handled at least one interrupt.  This does a single read of the
+ * status register and handles all interrupts in order from LSB first.
+ */
+static int handle_one_vic(struct vic_device *vic, struct pt_regs *regs)
+{
+	u32 stat, irq;
+	int handled = 0;
+
+	stat = readl_relaxed(vic->base + VIC_IRQ_STATUS);
+	while (stat) {
+		irq = ffs(stat) - 1;
+		handle_IRQ(irq_domain_to_irq(&vic->domain, irq), regs);
+		stat &= ~(1 << irq);
+		handled = 1;
+	}
+
+	return handled;
+}
+
+/*
+ * Keep iterating over all registered VIC's until there are no pending
+ * interrupts.
+ */
+asmlinkage void __exception_irq_entry vic_handle_irq(struct pt_regs *regs)
+{
+	int i, handled;
+
+	do {
+		for (i = 0, handled = 0; i < vic_id; ++i)
+			handled |= handle_one_vic(&vic_devices[i], regs);
+	} while (handled);
 }

arch/arm/configs/imx_v4_v5_defconfig

@@ -18,9 +18,10 @@ CONFIG_ARCH_MXC=y
 CONFIG_ARCH_IMX_V4_V5=y
 CONFIG_ARCH_MX1ADS=y
 CONFIG_MACH_SCB9328=y
+CONFIG_MACH_APF9328=y
 CONFIG_MACH_MX21ADS=y
 CONFIG_MACH_MX25_3DS=y
-CONFIG_MACH_EUKREA_CPUIMX25=y
+CONFIG_MACH_EUKREA_CPUIMX25SD=y
 CONFIG_MACH_MX27ADS=y
 CONFIG_MACH_PCM038=y
 CONFIG_MACH_CPUIMX27=y
@@ -72,17 +73,16 @@ CONFIG_MTD_CFI_GEOMETRY=y
 CONFIG_MTD_CFI_INTELEXT=y
 CONFIG_MTD_PHYSMAP=y
 CONFIG_MTD_NAND=y
+CONFIG_MTD_NAND_MXC=y
 CONFIG_MTD_UBI=y
 CONFIG_MISC_DEVICES=y
 CONFIG_EEPROM_AT24=y
 CONFIG_EEPROM_AT25=y
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_SMC91X=y
 CONFIG_DM9000=y
+CONFIG_SMC91X=y
 CONFIG_SMC911X=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
+CONFIG_SMSC_PHY=y
 # CONFIG_INPUT_MOUSEDEV is not set
 CONFIG_INPUT_EVDEV=y
 # CONFIG_INPUT_KEYBOARD is not set
@@ -100,6 +100,7 @@ CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_IMX=y
 CONFIG_SPI=y
 CONFIG_SPI_IMX=y
+CONFIG_SPI_SPIDEV=y
 CONFIG_W1=y
 CONFIG_W1_MASTER_MXC=y
 CONFIG_W1_SLAVE_THERM=y
@@ -139,6 +140,7 @@ CONFIG_MMC=y
 CONFIG_MMC_MXC=y
 CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_GPIO=y
 CONFIG_LEDS_MC13783=y
 CONFIG_LEDS_TRIGGERS=y
 CONFIG_LEDS_TRIGGER_TIMER=y

arch/arm/configs/pcontrol_g20_defconfig

-CONFIG_EXPERIMENTAL=y
-CONFIG_CROSS_COMPILE="/opt/arm-2010q1/bin/arm-none-linux-gnueabi-"
-# CONFIG_LOCALVERSION_AUTO is not set
-# CONFIG_SWAP is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_NAMESPACES=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-# CONFIG_SYSCTL_SYSCALL is not set
-# CONFIG_KALLSYMS is not set
-# CONFIG_VM_EVENT_COUNTERS is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_SLAB=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_LBDAF is not set
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_DEFAULT_DEADLINE=y
-CONFIG_ARCH_AT91=y
-CONFIG_ARCH_AT91SAM9G20=y
-CONFIG_MACH_PCONTROL_G20=y
-CONFIG_AT91_PROGRAMMABLE_CLOCKS=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_PREEMPT=y
-CONFIG_AEABI=y
-# CONFIG_OABI_COMPAT is not set
-CONFIG_ZBOOT_ROM_TEXT=0x0
-CONFIG_ZBOOT_ROM_BSS=0x0
-CONFIG_CMDLINE="console=ttyS0,115200 mem=128M mtdparts=atmel_nand:128k(bootstrap)ro,256k(uboot)ro,128k(env1)ro,128k(env2)ro,2M(linux),-(root) root=/dev/mmcblk0p1 rootwait rw"
-CONFIG_VFP=y
-CONFIG_BINFMT_MISC=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
-# CONFIG_IPV6 is not set
-CONFIG_VLAN_8021Q=y
-# CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_PARTITIONS=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_CHAR=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_COMPLEX_MAPPINGS=y
-CONFIG_MTD_PHRAM=m
-CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_ATMEL=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=8192
-CONFIG_ATMEL_TCLIB=y
-CONFIG_EEPROM_AT24=m
-CONFIG_SCSI=m
-# CONFIG_SCSI_PROC_FS is not set
-CONFIG_BLK_DEV_SD=m
-CONFIG_SCSI_MULTI_LUN=y
-# CONFIG_SCSI_LOWLEVEL is not set
-CONFIG_NETDEVICES=y
-CONFIG_MACVLAN=m
-CONFIG_TUN=m
-CONFIG_SMSC_PHY=m
-CONFIG_BROADCOM_PHY=m
-CONFIG_NET_ETHERNET=y
-CONFIG_MII=y
-CONFIG_MACB=y
-CONFIG_SMSC911X=m
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
-# CONFIG_WLAN is not set
-CONFIG_PPP=m
-CONFIG_PPP_ASYNC=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_MPPE=m
-CONFIG_INPUT_POLLDEV=y
-CONFIG_INPUT_SPARSEKMAP=y
-# CONFIG_INPUT_MOUSEDEV is not set
-CONFIG_INPUT_EVDEV=m
-CONFIG_INPUT_EVBUG=m
-# CONFIG_KEYBOARD_ATKBD is not set
-CONFIG_KEYBOARD_GPIO=m
-CONFIG_KEYBOARD_MATRIX=m
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_INPUT_TOUCHSCREEN=y
-CONFIG_INPUT_MISC=y
-CONFIG_INPUT_UINPUT=m
-CONFIG_INPUT_GPIO_ROTARY_ENCODER=m
-# CONFIG_SERIO is not set
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-CONFIG_SERIAL_MAX3100=m
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_HW_RANDOM is not set
-CONFIG_R3964=m
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-# CONFIG_I2C_HELPER_AUTO is not set
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=m
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-CONFIG_W1=m
-CONFIG_W1_MASTER_GPIO=m
-CONFIG_W1_SLAVE_DS2431=m
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT91SAM9X_WATCHDOG=y
-# CONFIG_MFD_SUPPORT is not set
-# CONFIG_HID_SUPPORT is not set
-CONFIG_USB=y
-# CONFIG_USB_DEVICE_CLASS is not set
-CONFIG_USB_OHCI_HCD=y
-CONFIG_USB_STORAGE=m
-CONFIG_USB_LIBUSUAL=y
-CONFIG_USB_SERIAL=m
-CONFIG_USB_SERIAL_GENERIC=y
-CONFIG_USB_SERIAL_FTDI_SIO=m
-CONFIG_USB_SERIAL_PL2303=m
-CONFIG_USB_GADGET=y
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_FILE_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_G_HID=m
-CONFIG_MMC=y
-CONFIG_MMC_UNSAFE_RESUME=y
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT91SAM9=y
-CONFIG_AUXDISPLAY=y
-CONFIG_UIO=y
-CONFIG_UIO_PDRV=y
-CONFIG_STAGING=y
-# CONFIG_STAGING_EXCLUDE_BUILD is not set
-CONFIG_IIO=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_VFAT_FS=y
-CONFIG_TMPFS=y
-CONFIG_JFFS2_FS=y
-CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
-CONFIG_NFS_V4=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_CODEPAGE_850=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_NLS_ISO8859_15=y
-CONFIG_NLS_UTF8=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_CRYPTO=y
-CONFIG_CRYPTO_ANSI_CPRNG=y
-# CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_CCITT=y

arch/arm/include/asm/assembler.h

@@ -186,6 +186,17 @@
 #define ALT_UP_B(label) b label
 #endif
 
+/*
+ * Instruction barrier
+ */
+	.macro	instr_sync
+#if __LINUX_ARM_ARCH__ >= 7
+	isb
+#elif __LINUX_ARM_ARCH__ == 6
+	mcr	p15, 0, r0, c7, c5, 4
+#endif
+	.endm
+
 /*
  * SMP data memory barrier
  */

arch/arm/include/asm/bug.h

@@ -32,7 +32,6 @@
 
 #define __BUG(__file, __line, __value)				\
 do {								\
-	BUILD_BUG_ON(sizeof(struct bug_entry) != 12);		\
 	asm volatile("1:\t" BUG_INSTR_TYPE #__value "\n"	\
 		".pushsection .rodata.str, \"aMS\", %progbits, 1\n" \
 		"2:\t.asciz " #__file "\n" 			\

arch/arm/include/asm/cti.h

+#ifndef __ASMARM_CTI_H
+#define __ASMARM_CTI_H
+
+#include	<asm/io.h>
+
+/* The registers' definition is from section 3.2 of
+ * Embedded Cross Trigger Revision: r0p0
+ */
+#define		CTICONTROL		0x000
+#define		CTISTATUS		0x004
+#define		CTILOCK			0x008
+#define		CTIPROTECTION		0x00C
+#define		CTIINTACK		0x010
+#define		CTIAPPSET		0x014
+#define		CTIAPPCLEAR		0x018
+#define		CTIAPPPULSE		0x01c
+#define		CTIINEN			0x020
+#define		CTIOUTEN		0x0A0
+#define		CTITRIGINSTATUS		0x130
+#define		CTITRIGOUTSTATUS	0x134
+#define		CTICHINSTATUS		0x138
+#define		CTICHOUTSTATUS		0x13c
+#define		CTIPERIPHID0		0xFE0
+#define		CTIPERIPHID1		0xFE4
+#define		CTIPERIPHID2		0xFE8
+#define		CTIPERIPHID3		0xFEC
+#define		CTIPCELLID0		0xFF0
+#define		CTIPCELLID1		0xFF4
+#define		CTIPCELLID2		0xFF8
+#define		CTIPCELLID3		0xFFC
+
+/* The below are from section 3.6.4 of
+ * CoreSight v1.0 Architecture Specification
+ */
+#define		LOCKACCESS		0xFB0
+#define		LOCKSTATUS		0xFB4
+
+/* write this value to LOCKACCESS will unlock the module, and
+ * other value will lock the module
+ */
+#define		LOCKCODE		0xC5ACCE55
+
+/**
+ * struct cti - cross trigger interface struct
+ * @base: mapped virtual address for the cti base
+ * @irq: irq number for the cti
+ * @trig_out_for_irq: triger out number which will cause
+ *	the @irq happen
+ *
+ * cti struct used to operate cti registers.
+ */
+struct cti {
+	void __iomem *base;
+	int irq;
+	int trig_out_for_irq;
+};
+
+/**
+ * cti_init - initialize the cti instance
+ * @cti: cti instance
+ * @base: mapped virtual address for the cti base
+ * @irq: irq number for the cti
+ * @trig_out: triger out number which will cause
+ *	the @irq happen
+ *
+ * called by machine code to pass the board dependent
+ * @base, @irq and @trig_out to cti.
+ */
+static inline void cti_init(struct cti *cti,
+	void __iomem *base, int irq, int trig_out)
+{
+	cti->base = base;
+	cti->irq  = irq;
+	cti->trig_out_for_irq = trig_out;
+}
+
+/**
+ * cti_map_trigger - use the @chan to map @trig_in to @trig_out
+ * @cti: cti instance
+ * @trig_in: trigger in number
+ * @trig_out: trigger out number
+ * @channel: channel number
+ *
+ * This function maps one trigger in of @trig_in to one trigger
+ * out of @trig_out using the channel @chan.
+ */
+static inline void cti_map_trigger(struct cti *cti,
+	int trig_in, int trig_out, int chan)
+{
+	void __iomem *base = cti->base;
+	unsigned long val;
+
+	val = __raw_readl(base + CTIINEN + trig_in * 4);
+	val |= BIT(chan);
+	__raw_writel(val, base + CTIINEN + trig_in * 4);
+
+	val = __raw_readl(base + CTIOUTEN + trig_out * 4);
+	val |= BIT(chan);
+	__raw_writel(val, base + CTIOUTEN + trig_out * 4);
+}
+
+/**
+ * cti_enable - enable the cti module
+ * @cti: cti instance
+ *
+ * enable the cti module
+ */
+static inline void cti_enable(struct cti *cti)
+{
+	__raw_writel(0x1, cti->base + CTICONTROL);
+}
+
+/**
+ * cti_disable - disable the cti module
+ * @cti: cti instance
+ *
+ * enable the cti module
+ */
+static inline void cti_disable(struct cti *cti)
+{
+	__raw_writel(0, cti->base + CTICONTROL);
+}
+
+/**
+ * cti_irq_ack - clear the cti irq
+ * @cti: cti instance
+ *
+ * clear the cti irq
+ */
+static inline void cti_irq_ack(struct cti *cti)
+{
+	void __iomem *base = cti->base;
+	unsigned long val;
+
+	val = __raw_readl(base + CTIINTACK);
+	val |= BIT(cti->trig_out_for_irq);
+	__raw_writel(val, base + CTIINTACK);
+}
+
+/**
+ * cti_unlock - unlock cti module
+ * @cti: cti instance
+ *
+ * unlock the cti module, or else any writes to the cti
+ * module is not allowed.
+ */
+static inline void cti_unlock(struct cti *cti)
+{
+	void __iomem *base = cti->base;
+	unsigned long val;
+
+	val = __raw_readl(base + LOCKSTATUS);
+
+	if (val & 1) {
+		val = LOCKCODE;
+		__raw_writel(val, base + LOCKACCESS);
+	}
+}
+
+/**
+ * cti_lock - lock cti module
+ * @cti: cti instance
+ *
+ * lock the cti module, so any writes to the cti
+ * module will be not allowed.
+ */
+static inline void cti_lock(struct cti *cti)
+{
+	void __iomem *base = cti->base;
+	unsigned long val;
+
+	val = __raw_readl(base + LOCKSTATUS);
+
+	if (!(val & 1)) {
+		val = ~LOCKCODE;
+		__raw_writel(val, base + LOCKACCESS);
+	}
+}
+#endif

arch/arm/plat-iop/io.c → arch/arm/include/asm/edac.h

 /*
- * iop3xx custom ioremap implementation
- * Copyright (c) 2006, Intel Corporation.
+ * Copyright 2011 Calxeda, Inc.
+ * Based on PPC version Copyright 2007 MontaVista Software, Inc.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -12,48 +12,37 @@
  * more details.
  *
  * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
- * Place - Suite 330, Boston, MA 02111-1307 USA.
- *
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/io.h>
-#include <mach/hardware.h>
-
-void * __iomem __iop3xx_ioremap(unsigned long cookie, size_t size,
-	unsigned int mtype)
+#ifndef ASM_EDAC_H
+#define ASM_EDAC_H
+/*
+ * ECC atomic, DMA, SMP and interrupt safe scrub function.
+ * Implements the per arch atomic_scrub() that EDAC use for software
+ * ECC scrubbing.  It reads memory and then writes back the original
+ * value, allowing the hardware to detect and correct memory errors.
+ */
+static inline void atomic_scrub(void *va, u32 size)
 {
-	void __iomem * retval;
+#if __LINUX_ARM_ARCH__ >= 6
+	unsigned int *virt_addr = va;
+	unsigned int temp, temp2;
+	unsigned int i;
 
-	switch (cookie) {
-	case IOP3XX_PCI_LOWER_IO_PA ... IOP3XX_PCI_UPPER_IO_PA:
-		retval = (void *) IOP3XX_PCI_IO_PHYS_TO_VIRT(cookie);
-		break;
-	case IOP3XX_PERIPHERAL_PHYS_BASE ... IOP3XX_PERIPHERAL_UPPER_PA:
-		retval = (void *) IOP3XX_PMMR_PHYS_TO_VIRT(cookie);
-		break;
-	default:
-		retval = __arm_ioremap_caller(cookie, size, mtype,
-				__builtin_return_address(0));
+	for (i = 0; i < size / sizeof(*virt_addr); i++, virt_addr++) {
+		/* Very carefully read and write to memory atomically
+		 * so we are interrupt, DMA and SMP safe.
+		 */
+		__asm__ __volatile__("\n"
+			"1:	ldrex	%0, [%2]\n"
+			"	strex	%1, %0, [%2]\n"
+			"	teq	%1, #0\n"
+			"	bne	1b\n"
+			: "=&r"(temp), "=&r"(temp2)
+			: "r"(virt_addr)
+			: "cc");
 	}
-
-	return retval;
+#endif
 }
-EXPORT_SYMBOL(__iop3xx_ioremap);
 
-void __iop3xx_iounmap(void __iomem *addr)
-{
-	extern void __iounmap(volatile void __iomem *addr);
-
-	switch ((u32) addr) {
-	case IOP3XX_PCI_LOWER_IO_VA ... IOP3XX_PCI_UPPER_IO_VA:
-	case IOP3XX_PERIPHERAL_VIRT_BASE ... IOP3XX_PERIPHERAL_UPPER_VA:
-		goto skip;
-	}
-	__iounmap(addr);
-
-skip:
-	return;
-}
-EXPORT_SYMBOL(__iop3xx_iounmap);
+#endif

arch/arm/include/asm/entry-macro-vic2.S

-/* arch/arm/include/asm/entry-macro-vic2.S
- *
- * Originally arch/arm/mach-s3c6400/include/mach/entry-macro.S
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- *	http://armlinux.simtec.co.uk/
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * Low-level IRQ helper macros for a device with two VICs
- *
- * 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.
-*/
-
-/* This should be included from <mach/entry-macro.S> with the necessary
- * defines for virtual addresses and IRQ bases for the two vics.
- *
- * The code needs the following defined:
- *	IRQ_VIC0_BASE	IRQ number of VIC0's first IRQ
- *	IRQ_VIC1_BASE	IRQ number of VIC1's first IRQ
- *	VA_VIC0		Virtual address of VIC0
- *	VA_VIC1		Virtual address of VIC1
- *
- * Note, code assumes VIC0's virtual address is an ARM immediate constant
- * away from VIC1.
-*/
-
-#include <asm/hardware/vic.h>
-
-	.macro	disable_fiq
-	.endm
-
-	.macro	get_irqnr_preamble, base, tmp
-	ldr	\base, =VA_VIC0
-	.endm
-
-	.macro	arch_ret_to_user, tmp1, tmp2
-	.endm
-
-	.macro	get_irqnr_and_base, irqnr, irqstat, base, tmp
-
-	@ check the vic0
-	mov	\irqnr, #IRQ_VIC0_BASE + 31
-	ldr	\irqstat, [ \base, # VIC_IRQ_STATUS ]
-	teq	\irqstat, #0
-
-	@ otherwise try vic1
-	addeq	\tmp, \base, #(VA_VIC1 - VA_VIC0)
-	addeq	\irqnr, \irqnr, #(IRQ_VIC1_BASE - IRQ_VIC0_BASE)
-	ldreq	\irqstat, [ \tmp, # VIC_IRQ_STATUS ]
-	teqeq	\irqstat, #0
-
-	clzne	\irqstat, \irqstat
-	subne	\irqnr, \irqnr, \irqstat
-	.endm

arch/arm/include/asm/gpio.h

 #ifndef _ARCH_ARM_GPIO_H
 #define _ARCH_ARM_GPIO_H
 
+#if CONFIG_ARCH_NR_GPIO > 0
+#define ARCH_NR_GPIO CONFIG_ARCH_NR_GPIO
+#endif
+
 /* not all ARM platforms necessarily support this API ... */
 #include <mach/gpio.h>
 

arch/arm/include/asm/hardirq.h

@@ -27,23 +27,6 @@ u64 smp_irq_stat_cpu(unsigned int cpu);
 
 #define arch_irq_stat_cpu	smp_irq_stat_cpu
 
-#if NR_IRQS > 512
-#define HARDIRQ_BITS	10
-#elif NR_IRQS > 256
-#define HARDIRQ_BITS	9
-#else
-#define HARDIRQ_BITS	8
-#endif
-
-/*
- * The hardirq mask has to be large enough to have space
- * for potentially all IRQ sources in the system nesting
- * on a single CPU:
- */
-#if (1 << HARDIRQ_BITS) < NR_IRQS
-# error HARDIRQ_BITS is too low!
-#endif
-
 #define __ARCH_IRQ_EXIT_IRQS_DISABLED	1
 
 #endif /* __ASM_HARDIRQ_H */

arch/arm/include/asm/hardware/entry-macro-gic.S

-/*
- * arch/arm/include/asm/hardware/entry-macro-gic.S
- *
- * Low-level IRQ helper macros for GIC
- *
- * 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 <asm/hardware/gic.h>
-
-#ifndef HAVE_GET_IRQNR_PREAMBLE
-	.macro	get_irqnr_preamble, base, tmp
-	ldr	\base, =gic_cpu_base_addr
-	ldr	\base, [\base]
-	.endm
-#endif
-
-/*
- * The interrupt numbering scheme is defined in the
- * interrupt controller spec.  To wit:
- *
- * Interrupts 0-15 are IPI
- * 16-31 are local.  We allow 30 to be used for the watchdog.
- * 32-1020 are global
- * 1021-1022 are reserved
- * 1023 is "spurious" (no interrupt)
- *
- * A simple read from the controller will tell us the number of the highest
- * priority enabled interrupt.  We then just need to check whether it is in the
- * valid range for an IRQ (30-1020 inclusive).
- */
-
-	.macro  get_irqnr_and_base, irqnr, irqstat, base, tmp
-
-	ldr     \irqstat, [\base, #GIC_CPU_INTACK]
-	/* bits 12-10 = src CPU, 9-0 = int # */
-
-	ldr	\tmp, =1021
-	bic     \irqnr, \irqstat, #0x1c00
-	cmp     \irqnr, #15
-	cmpcc	\irqnr, \irqnr
-	cmpne	\irqnr, \tmp
-	cmpcs	\irqnr, \irqnr
-	.endm
-
-/* We assume that irqstat (the raw value of the IRQ acknowledge
- * register) is preserved from the macro above.
- * If there is an IPI, we immediately signal end of interrupt on the
- * controller, since this requires the original irqstat value which
- * we won't easily be able to recreate later.
- */
-
-	.macro test_for_ipi, irqnr, irqstat, base, tmp
-	bic	\irqnr, \irqstat, #0x1c00
-	cmp	\irqnr, #16
-	strcc	\irqstat, [\base, #GIC_CPU_EOI]
-	cmpcs	\irqnr, \irqnr
-	.endm

arch/arm/include/asm/hardware/gic.h

@@ -36,30 +36,22 @@
 #include <linux/irqdomain.h>
 struct device_node;
 
-extern void __iomem *gic_cpu_base_addr;
 extern struct irq_chip gic_arch_extn;
 
-void gic_init(unsigned int, int, void __iomem *, void __iomem *);
+void gic_init_bases(unsigned int, int, void __iomem *, void __iomem *,
+		    u32 offset);
 int gic_of_init(struct device_node *node, struct device_node *parent);
 void gic_secondary_init(unsigned int);
+void gic_handle_irq(struct pt_regs *regs);
 void gic_cascade_irq(unsigned int gic_nr, unsigned int irq);
 void gic_raise_softirq(const struct cpumask *mask, unsigned int irq);
 
-struct gic_chip_data {
-	void __iomem *dist_base;
-	void __iomem *cpu_base;
-#ifdef CONFIG_CPU_PM
-	u32 saved_spi_enable[DIV_ROUND_UP(1020, 32)];
-	u32 saved_spi_conf[DIV_ROUND_UP(1020, 16)];
-	u32 saved_spi_target[DIV_ROUND_UP(1020, 4)];
-	u32 __percpu *saved_ppi_enable;
-	u32 __percpu *saved_ppi_conf;
-#endif
-#ifdef CONFIG_IRQ_DOMAIN
-	struct irq_domain domain;
-#endif
-	unsigned int gic_irqs;
-};
+static inline void gic_init(unsigned int nr, int start,
+			    void __iomem *dist , void __iomem *cpu)
+{
+	gic_init_bases(nr, start, dist, cpu, 0);
+}
+
 #endif
 
 #endif

arch/arm/include/asm/hardware/iop3xx.h

@@ -234,6 +234,7 @@ extern int iop3xx_get_init_atu(void);
 void iop3xx_map_io(void);
 void iop_init_cp6_handler(void);
 void iop_init_time(unsigned long tickrate);
+void iop3xx_restart(char, const char *);
 
 static inline u32 read_tmr0(void)
 {

arch/arm/include/asm/hardware/vic.h

@@ -41,7 +41,15 @@
 #define VIC_PL192_VECT_ADDR		0xF00
 
 #ifndef __ASSEMBLY__
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+struct device_node;
+struct pt_regs;
+
 void vic_init(void __iomem *base, unsigned int irq_start, u32 vic_sources, u32 resume_sources);
-#endif
+int vic_of_init(struct device_node *node, struct device_node *parent);
+void vic_handle_irq(struct pt_regs *regs);
 
+#endif /* __ASSEMBLY__ */
 #endif

arch/arm/include/asm/idmap.h

+#ifndef __ASM_IDMAP_H
+#define __ASM_IDMAP_H
+
+#include <linux/compiler.h>
+#include <asm/pgtable.h>
+
+/* Tag a function as requiring to be executed via an identity mapping. */
+#define __idmap __section(.idmap.text) noinline notrace
+
+extern pgd_t *idmap_pgd;
+
+void setup_mm_for_reboot(void);
+
+#endif	/* __ASM_IDMAP_H */

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

@@ -31,10 +31,10 @@ struct machine_desc {
 	unsigned int		video_start;	/* start of video RAM	*/
 	unsigned int		video_end;	/* end of video RAM	*/
 
-	unsigned int		reserve_lp0 :1;	/* never has lp0	*/
-	unsigned int		reserve_lp1 :1;	/* never has lp1	*/
-	unsigned int		reserve_lp2 :1;	/* never has lp2	*/
-	unsigned int		soft_reboot :1;	/* soft reboot		*/
+	unsigned char		reserve_lp0 :1;	/* never has lp0	*/
+	unsigned char		reserve_lp1 :1;	/* never has lp1	*/
+	unsigned char		reserve_lp2 :1;	/* never has lp2	*/
+	char			restart_mode;	/* default restart mode	*/
 	void			(*fixup)(struct tag *, char **,
 					 struct meminfo *);
 	void			(*reserve)(void);/* reserve mem blocks	*/
@@ -46,6 +46,7 @@ struct machine_desc {
 #ifdef CONFIG_MULTI_IRQ_HANDLER
 	void			(*handle_irq)(struct pt_regs *);
 #endif
+	void			(*restart)(char, const char *);
 };
 
 /*

arch/arm/mach-pxa/include/mach/vmalloc.h → arch/arm/include/asm/opcodes.h

 /*
- * arch/arm/mach-pxa/include/mach/vmalloc.h
- *
- * Author:	Nicolas Pitre
- * Copyright:	(C) 2001 MontaVista Software Inc.
+ *  arch/arm/include/asm/opcodes.h
  *
  * 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 VMALLOC_END       (0xe8000000UL)
+
+#ifndef __ASM_ARM_OPCODES_H
+#define __ASM_ARM_OPCODES_H
+
+#ifndef __ASSEMBLY__
+extern asmlinkage unsigned int arm_check_condition(u32 opcode, u32 psr);
+#endif
+
+#define ARM_OPCODE_CONDTEST_FAIL   0
+#define ARM_OPCODE_CONDTEST_PASS   1
+#define ARM_OPCODE_CONDTEST_UNCOND 2
+
+#endif /* __ASM_ARM_OPCODES_H */

arch/arm/include/asm/page.h

@@ -151,7 +151,11 @@ extern void __cpu_copy_user_highpage(struct page *to, struct page *from,
 #define clear_page(page)	memset((void *)(page), 0, PAGE_SIZE)
 extern void copy_page(void *to, const void *from);
 
+#ifdef CONFIG_ARM_LPAE
+#include <asm/pgtable-3level-types.h>
+#else
 #include <asm/pgtable-2level-types.h>
+#endif
 
 #endif /* CONFIG_MMU */
 

arch/arm/include/asm/perf_event.h

@@ -32,7 +32,4 @@ enum arm_perf_pmu_ids {
 extern enum arm_perf_pmu_ids
 armpmu_get_pmu_id(void);
 
-extern int
-armpmu_get_max_events(void);
-
 #endif /* __ARM_PERF_EVENT_H__ */

arch/arm/include/asm/pgalloc.h

@@ -25,12 +25,34 @@
 #define _PAGE_USER_TABLE	(PMD_TYPE_TABLE | PMD_BIT4 | PMD_DOMAIN(DOMAIN_USER))
 #define _PAGE_KERNEL_TABLE	(PMD_TYPE_TABLE | PMD_BIT4 | PMD_DOMAIN(DOMAIN_KERNEL))
 
+#ifdef CONFIG_ARM_LPAE
+
+static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	return (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_REPEAT);
+}
+
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+	BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
+	free_page((unsigned long)pmd);
+}
+
+static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
+{
+	set_pud(pud, __pud(__pa(pmd) | PMD_TYPE_TABLE));
+}
+
+#else	/* !CONFIG_ARM_LPAE */
+
 /*
  * Since we have only two-level page tables, these are trivial
  */
 #define pmd_alloc_one(mm,addr)		({ BUG(); ((pmd_t *)2); })
 #define pmd_free(mm, pmd)		do { } while (0)
-#define pgd_populate(mm,pmd,pte)	BUG()
+#define pud_populate(mm,pmd,pte)	BUG()
+
+#endif	/* CONFIG_ARM_LPAE */
 
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
 extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
@@ -109,7 +131,9 @@ static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte,
 {
 	pmdval_t pmdval = (pte + PTE_HWTABLE_OFF) | prot;
 	pmdp[0] = __pmd(pmdval);
+#ifndef CONFIG_ARM_LPAE
 	pmdp[1] = __pmd(pmdval + 256 * sizeof(pte_t));
+#endif
 	flush_pmd_entry(pmdp);
 }
 

arch/arm/include/asm/pgtable-2level.h

@@ -140,4 +140,45 @@
 #define L_PTE_MT_DEV_CACHED	(_AT(pteval_t, 0x0b) << 2)	/* 1011 */
 #define L_PTE_MT_MASK		(_AT(pteval_t, 0x0f) << 2)
 
+#ifndef __ASSEMBLY__
+
+/*
+ * The "pud_xxx()" functions here are trivial when the pmd is folded into
+ * the pud: the pud entry is never bad, always exists, and can't be set or
+ * cleared.
+ */
+#define pud_none(pud)		(0)
+#define pud_bad(pud)		(0)
+#define pud_present(pud)	(1)
+#define pud_clear(pudp)		do { } while (0)
+#define set_pud(pud,pudp)	do { } while (0)
+
+static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
+{
+	return (pmd_t *)pud;
+}
+
+#define pmd_bad(pmd)		(pmd_val(pmd) & 2)
+
+#define copy_pmd(pmdpd,pmdps)		\
+	do {				\
+		pmdpd[0] = pmdps[0];	\
+		pmdpd[1] = pmdps[1];	\
+		flush_pmd_entry(pmdpd);	\
+	} while (0)
+
+#define pmd_clear(pmdp)			\
+	do {				\
+		pmdp[0] = __pmd(0);	\
+		pmdp[1] = __pmd(0);	\
+		clean_pmd_entry(pmdp);	\
+	} while (0)
+
+/* we don't need complex calculations here as the pmd is folded into the pgd */
+#define pmd_addr_end(addr,end) (end)
+
+#define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
+
+#endif /* __ASSEMBLY__ */
+
 #endif /* _ASM_PGTABLE_2LEVEL_H */

arch/arm/include/asm/pgtable-3level-hwdef.h

+/*
+ * arch/arm/include/asm/pgtable-3level-hwdef.h
+ *
+ * Copyright (C) 2011 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+#ifndef _ASM_PGTABLE_3LEVEL_HWDEF_H
+#define _ASM_PGTABLE_3LEVEL_HWDEF_H
+
+/*
+ * Hardware page table definitions.
+ *
+ * + Level 1/2 descriptor
+ *   - common
+ */
+#define PMD_TYPE_MASK		(_AT(pmdval_t, 3) << 0)
+#define PMD_TYPE_FAULT		(_AT(pmdval_t, 0) << 0)
+#define PMD_TYPE_TABLE		(_AT(pmdval_t, 3) << 0)
+#define PMD_TYPE_SECT		(_AT(pmdval_t, 1) << 0)
+#define PMD_BIT4		(_AT(pmdval_t, 0))
+#define PMD_DOMAIN(x)		(_AT(pmdval_t, 0))
+
+/*
+ *   - section
+ */
+#define PMD_SECT_BUFFERABLE	(_AT(pmdval_t, 1) << 2)
+#define PMD_SECT_CACHEABLE	(_AT(pmdval_t, 1) << 3)
+#define PMD_SECT_S		(_AT(pmdval_t, 3) << 8)
+#define PMD_SECT_AF		(_AT(pmdval_t, 1) << 10)
+#define PMD_SECT_nG		(_AT(pmdval_t, 1) << 11)
+#define PMD_SECT_XN		(_AT(pmdval_t, 1) << 54)
+#define PMD_SECT_AP_WRITE	(_AT(pmdval_t, 0))
+#define PMD_SECT_AP_READ	(_AT(pmdval_t, 0))
+#define PMD_SECT_TEX(x)		(_AT(pmdval_t, 0))
+
+/*
+ * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
+ */
+#define PMD_SECT_UNCACHED	(_AT(pmdval_t, 0) << 2)	/* strongly ordered */
+#define PMD_SECT_BUFFERED	(_AT(pmdval_t, 1) << 2)	/* normal non-cacheable */
+#define PMD_SECT_WT		(_AT(pmdval_t, 2) << 2)	/* normal inner write-through */
+#define PMD_SECT_WB		(_AT(pmdval_t, 3) << 2)	/* normal inner write-back */
+#define PMD_SECT_WBWA		(_AT(pmdval_t, 7) << 2)	/* normal inner write-alloc */
+
+/*
+ * + Level 3 descriptor (PTE)
+ */
+#define PTE_TYPE_MASK		(_AT(pteval_t, 3) << 0)
+#define PTE_TYPE_FAULT		(_AT(pteval_t, 0) << 0)
+#define PTE_TYPE_PAGE		(_AT(pteval_t, 3) << 0)
+#define PTE_BUFFERABLE		(_AT(pteval_t, 1) << 2)		/* AttrIndx[0] */
+#define PTE_CACHEABLE		(_AT(pteval_t, 1) << 3)		/* AttrIndx[1] */
+#define PTE_EXT_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
+#define PTE_EXT_AF		(_AT(pteval_t, 1) << 10)	/* Access Flag */
+#define PTE_EXT_NG		(_AT(pteval_t, 1) << 11)	/* nG */
+#define PTE_EXT_XN		(_AT(pteval_t, 1) << 54)	/* XN */
+
+/*
+ * 40-bit physical address supported.
+ */
+#define PHYS_MASK_SHIFT		(40)
+#define PHYS_MASK		((1ULL << PHYS_MASK_SHIFT) - 1)
+
+#endif

arch/arm/include/asm/pgtable-3level-types.h

+/*
+ * arch/arm/include/asm/pgtable-3level-types.h
+ *
+ * Copyright (C) 2011 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+#ifndef _ASM_PGTABLE_3LEVEL_TYPES_H
+#define _ASM_PGTABLE_3LEVEL_TYPES_H
+
+#include <asm/types.h>
+
+typedef u64 pteval_t;
+typedef u64 pmdval_t;
+typedef u64 pgdval_t;
+
+#undef STRICT_MM_TYPECHECKS
+
+#ifdef STRICT_MM_TYPECHECKS
+
+/*
+ * These are used to make use of C type-checking..
+ */
+typedef struct { pteval_t pte; } pte_t;
+typedef struct { pmdval_t pmd; } pmd_t;
+typedef struct { pgdval_t pgd; } pgd_t;
+typedef struct { pteval_t pgprot; } pgprot_t;
+
+#define pte_val(x)      ((x).pte)
+#define pmd_val(x)      ((x).pmd)
+#define pgd_val(x)	((x).pgd)
+#define pgprot_val(x)   ((x).pgprot)
+
+#define __pte(x)        ((pte_t) { (x) } )
+#define __pmd(x)        ((pmd_t) { (x) } )
+#define __pgd(x)	((pgd_t) { (x) } )
+#define __pgprot(x)     ((pgprot_t) { (x) } )
+
+#else	/* !STRICT_MM_TYPECHECKS */
+
+typedef pteval_t pte_t;
+typedef pmdval_t pmd_t;
+typedef pgdval_t pgd_t;
+typedef pteval_t pgprot_t;
+
+#define pte_val(x)	(x)
+#define pmd_val(x)	(x)
+#define pgd_val(x)	(x)
+#define pgprot_val(x)	(x)
+
+#define __pte(x)	(x)
+#define __pmd(x)	(x)
+#define __pgd(x)	(x)
+#define __pgprot(x)	(x)
+
+#endif	/* STRICT_MM_TYPECHECKS */
+
+#endif	/* _ASM_PGTABLE_3LEVEL_TYPES_H */

arch/arm/include/asm/pgtable-3level.h

+/*
+ * arch/arm/include/asm/pgtable-3level.h
+ *
+ * Copyright (C) 2011 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+#ifndef _ASM_PGTABLE_3LEVEL_H
+#define _ASM_PGTABLE_3LEVEL_H
+
+/*
+ * With LPAE, there are 3 levels of page tables. Each level has 512 entries of
+ * 8 bytes each, occupying a 4K page. The first level table covers a range of
+ * 512GB, each entry representing 1GB. Since we are limited to 4GB input
+ * address range, only 4 entries in the PGD are used.
+ *
+ * There are enough spare bits in a page table entry for the kernel specific
+ * state.
+ */
+#define PTRS_PER_PTE		512
+#define PTRS_PER_PMD		512
+#define PTRS_PER_PGD		4
+
+#define PTE_HWTABLE_PTRS	(PTRS_PER_PTE)
+#define PTE_HWTABLE_OFF		(0)
+#define PTE_HWTABLE_SIZE	(PTRS_PER_PTE * sizeof(u64))
+
+/*
+ * PGDIR_SHIFT determines the size a top-level page table entry can map.
+ */
+#define PGDIR_SHIFT		30
+
+/*
+ * PMD_SHIFT determines the size a middle-level page table entry can map.
+ */
+#define PMD_SHIFT		21
+
+#define PMD_SIZE		(1UL << PMD_SHIFT)
+#define PMD_MASK		(~(PMD_SIZE-1))
+#define PGDIR_SIZE		(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK		(~(PGDIR_SIZE-1))
+
+/*
+ * section address mask and size definitions.
+ */
+#define SECTION_SHIFT		21
+#define SECTION_SIZE		(1UL << SECTION_SHIFT)
+#define SECTION_MASK		(~(SECTION_SIZE-1))
+
+#define USER_PTRS_PER_PGD	(PAGE_OFFSET / PGDIR_SIZE)
+
+/*
+ * "Linux" PTE definitions for LPAE.
+ *
+ * These bits overlap with the hardware bits but the naming is preserved for
+ * consistency with the classic page table format.
+ */
+#define L_PTE_PRESENT		(_AT(pteval_t, 3) << 0)		/* Valid */
+#define L_PTE_FILE		(_AT(pteval_t, 1) << 2)		/* only when !PRESENT */
+#define L_PTE_BUFFERABLE	(_AT(pteval_t, 1) << 2)		/* AttrIndx[0] */
+#define L_PTE_CACHEABLE		(_AT(pteval_t, 1) << 3)		/* AttrIndx[1] */
+#define L_PTE_USER		(_AT(pteval_t, 1) << 6)		/* AP[1] */
+#define L_PTE_RDONLY		(_AT(pteval_t, 1) << 7)		/* AP[2] */
+#define L_PTE_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
+#define L_PTE_YOUNG		(_AT(pteval_t, 1) << 10)	/* AF */
+#define L_PTE_XN		(_AT(pteval_t, 1) << 54)	/* XN */
+#define L_PTE_DIRTY		(_AT(pteval_t, 1) << 55)	/* unused */
+#define L_PTE_SPECIAL		(_AT(pteval_t, 1) << 56)	/* unused */
+
+/*
+ * To be used in assembly code with the upper page attributes.
+ */
+#define L_PTE_XN_HIGH		(1 << (54 - 32))
+#define L_PTE_DIRTY_HIGH	(1 << (55 - 32))
+
+/*
+ * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
+ */
+#define L_PTE_MT_UNCACHED	(_AT(pteval_t, 0) << 2)	/* strongly ordered */
+#define L_PTE_MT_BUFFERABLE	(_AT(pteval_t, 1) << 2)	/* normal non-cacheable */
+#define L_PTE_MT_WRITETHROUGH	(_AT(pteval_t, 2) << 2)	/* normal inner write-through */
+#define L_PTE_MT_WRITEBACK	(_AT(pteval_t, 3) << 2)	/* normal inner write-back */
+#define L_PTE_MT_WRITEALLOC	(_AT(pteval_t, 7) << 2)	/* normal inner write-alloc */
+#define L_PTE_MT_DEV_SHARED	(_AT(pteval_t, 4) << 2)	/* device */
+#define L_PTE_MT_DEV_NONSHARED	(_AT(pteval_t, 4) << 2)	/* device */
+#define L_PTE_MT_DEV_WC		(_AT(pteval_t, 1) << 2)	/* normal non-cacheable */
+#define L_PTE_MT_DEV_CACHED	(_AT(pteval_t, 3) << 2)	/* normal inner write-back */
+#define L_PTE_MT_MASK		(_AT(pteval_t, 7) << 2)
+
+/*
+ * Software PGD flags.
+ */
+#define L_PGD_SWAPPER		(_AT(pgdval_t, 1) << 55)	/* swapper_pg_dir entry */
+
+#ifndef __ASSEMBLY__
+
+#define pud_none(pud)		(!pud_val(pud))
+#define pud_bad(pud)		(!(pud_val(pud) & 2))
+#define pud_present(pud)	(pud_val(pud))
+
+#define pud_clear(pudp)			\
+	do {				\
+		*pudp = __pud(0);	\
+		clean_pmd_entry(pudp);	\
+	} while (0)
+
+#define set_pud(pudp, pud)		\
+	do {				\
+		*pudp = pud;		\
+		flush_pmd_entry(pudp);	\
+	} while (0)
+
+static inline pmd_t *pud_page_vaddr(pud_t pud)
+{
+	return __va(pud_val(pud) & PHYS_MASK & (s32)PAGE_MASK);
+}
+
+/* Find an entry in the second-level page table.. */
+#define pmd_index(addr)		(((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
+static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
+{
+	return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(addr);
+}
+
+#define pmd_bad(pmd)		(!(pmd_val(pmd) & 2))
+
+#define copy_pmd(pmdpd,pmdps)		\
+	do {				\
+		*pmdpd = *pmdps;	\
+		flush_pmd_entry(pmdpd);	\
+	} while (0)
+
+#define pmd_clear(pmdp)			\
+	do {				\
+		*pmdp = __pmd(0);	\
+		clean_pmd_entry(pmdp);	\
+	} while (0)
+
+#define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,__pte(pte_val(pte)|(ext)))
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_PGTABLE_3LEVEL_H */

arch/arm/include/asm/pgtable-hwdef.h

@@ -10,6 +10,10 @@
 #ifndef _ASMARM_PGTABLE_HWDEF_H
 #define _ASMARM_PGTABLE_HWDEF_H
 
+#ifdef CONFIG_ARM_LPAE
+#include <asm/pgtable-3level-hwdef.h>
+#else
 #include <asm/pgtable-2level-hwdef.h>
+#endif
 
 #endif

arch/arm/include/asm/pgtable.h

@@ -11,20 +11,24 @@
 #define _ASMARM_PGTABLE_H
 
 #include <linux/const.h>
-#include <asm-generic/4level-fixup.h>
 #include <asm/proc-fns.h>
 
 #ifndef CONFIG_MMU
 
+#include <asm-generic/4level-fixup.h>
 #include "pgtable-nommu.h"
 
 #else
 
+#include <asm-generic/pgtable-nopud.h>
 #include <asm/memory.h>
-#include <mach/vmalloc.h>
 #include <asm/pgtable-hwdef.h>
 
+#ifdef CONFIG_ARM_LPAE
+#include <asm/pgtable-3level.h>
+#else
 #include <asm/pgtable-2level.h>
+#endif
 
 /*
  * Just any arbitrary offset to the start of the vmalloc VM area: the
@@ -33,15 +37,10 @@
  * any out-of-bounds memory accesses will hopefully be caught.
  * The vmalloc() routines leaves a hole of 4kB between each vmalloced
  * area for the same reason. ;)
- *
- * Note that platforms may override VMALLOC_START, but they must provide
- * VMALLOC_END.  VMALLOC_END defines the (exclusive) limit of this space,
- * which may not overlap IO space.
  */
-#ifndef VMALLOC_START
 #define VMALLOC_OFFSET		(8*1024*1024)
 #define VMALLOC_START		(((unsigned long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))
-#endif
+#define VMALLOC_END		0xff000000UL
 
 #define LIBRARY_TEXT_START	0x0c000000
 
@@ -163,39 +162,8 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 /* to find an entry in a kernel page-table-directory */
 #define pgd_offset_k(addr)	pgd_offset(&init_mm, addr)
 
-/*
- * The "pgd_xxx()" functions here are trivial for a folded two-level
- * setup: the pgd is never bad, and a pmd always exists (as it's folded
- * into the pgd entry)
- */
-#define pgd_none(pgd)		(0)
-#define pgd_bad(pgd)		(0)
-#define pgd_present(pgd)	(1)
-#define pgd_clear(pgdp)		do { } while (0)
-#define set_pgd(pgd,pgdp)	do { } while (0)
-#define set_pud(pud,pudp)	do { } while (0)
-
-
-/* Find an entry in the second-level page table.. */
-#define pmd_offset(dir, addr)	((pmd_t *)(dir))
-
 #define pmd_none(pmd)		(!pmd_val(pmd))
 #define pmd_present(pmd)	(pmd_val(pmd))
-#define pmd_bad(pmd)		(pmd_val(pmd) & 2)
-
-#define copy_pmd(pmdpd,pmdps)		\
-	do {				\
-		pmdpd[0] = pmdps[0];	\
-		pmdpd[1] = pmdps[1];	\
-		flush_pmd_entry(pmdpd);	\
-	} while (0)
-
-#define pmd_clear(pmdp)			\
-	do {				\
-		pmdp[0] = __pmd(0);	\
-		pmdp[1] = __pmd(0);	\
-		clean_pmd_entry(pmdp);	\
-	} while (0)
 
 static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 {
@@ -204,10 +172,6 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 
 #define pmd_page(pmd)		pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
 
-/* we don't need complex calculations here as the pmd is folded into the pgd */
-#define pmd_addr_end(addr,end)	(end)
-
-
 #ifndef CONFIG_HIGHPTE
 #define __pte_map(pmd)		pmd_page_vaddr(*(pmd))
 #define __pte_unmap(pte)	do { } while (0)
@@ -229,7 +193,6 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 #define pte_page(pte)		pfn_to_page(pte_pfn(pte))
 #define mk_pte(page,prot)	pfn_pte(page_to_pfn(page), prot)
 
-#define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
 #define pte_clear(mm,addr,ptep)	set_pte_ext(ptep, __pte(0), 0)
 
 #if __LINUX_ARM_ARCH__ < 6
@@ -336,6 +299,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
  * We provide our own arch_get_unmapped_area to cope with VIPT caches.
  */
 #define HAVE_ARCH_UNMAPPED_AREA
+#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
 
 /*
  * remap a physical page `pfn' of size `size' with page protection `prot'
@@ -346,9 +310,6 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 
 #define pgtable_cache_init() do { } while (0)
 
-void identity_mapping_add(pgd_t *, unsigned long, unsigned long);
-void identity_mapping_del(pgd_t *, unsigned long, unsigned long);
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* CONFIG_MMU */

arch/arm/include/asm/pmu.h

@@ -27,13 +27,22 @@ enum arm_pmu_type {
 /*
  * struct arm_pmu_platdata - ARM PMU platform data
  *
- * @handle_irq: an optional handler which will be called from the interrupt and
- * passed the address of the low level handler, and can be used to implement
- * any platform specific handling before or after calling it.
+ * @handle_irq: an optional handler which will be called from the
+ *	interrupt and passed the address of the low level handler,
+ *	and can be used to implement any platform specific handling
+ *	before or after calling it.
+ * @enable_irq: an optional handler which will be called after
+ *	request_irq and be used to handle some platform specific
+ *	irq enablement
+ * @disable_irq: an optional handler which will be called before
+ *	free_irq and be used to handle some platform specific
+ *	irq disablement
  */
 struct arm_pmu_platdata {
 	irqreturn_t (*handle_irq)(int irq, void *dev,
 				  irq_handler_t pmu_handler);
+	void (*enable_irq)(int irq);
+	void (*disable_irq)(int irq);
 };
 
 #ifdef CONFIG_CPU_HAS_PMU

arch/arm/include/asm/proc-fns.h

@@ -65,7 +65,11 @@ extern struct processor {
 	 * Set a possibly extended PTE.  Non-extended PTEs should
 	 * ignore 'ext'.
 	 */
+#ifdef CONFIG_ARM_LPAE
+	void (*set_pte_ext)(pte_t *ptep, pte_t pte);
+#else
 	void (*set_pte_ext)(pte_t *ptep, pte_t pte, unsigned int ext);
+#endif
 
 	/* Suspend/resume */
 	unsigned int suspend_size;
@@ -79,7 +83,11 @@ extern void cpu_proc_fin(void);
 extern int cpu_do_idle(void);
 extern void cpu_dcache_clean_area(void *, int);
 extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
+#ifdef CONFIG_ARM_LPAE
+extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte);
+#else
 extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte, unsigned int ext);
+#endif
 extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
 
 /* These three are private to arch/arm/kernel/suspend.c */
@@ -107,6 +115,18 @@ extern void cpu_resume(void);
 
 #define cpu_switch_mm(pgd,mm) cpu_do_switch_mm(virt_to_phys(pgd),mm)
 
+#ifdef CONFIG_ARM_LPAE
+#define cpu_get_pgd()	\
+	({						\
+		unsigned long pg, pg2;			\
+		__asm__("mrrc	p15, 0, %0, %1, c2"	\
+			: "=r" (pg), "=r" (pg2)		\
+			:				\
+			: "cc");			\
+		pg &= ~(PTRS_PER_PGD*sizeof(pgd_t)-1);	\
+		(pgd_t *)phys_to_virt(pg);		\
+	})
+#else
 #define cpu_get_pgd()	\
 	({						\
 		unsigned long pg;			\
@@ -115,6 +135,7 @@ extern void cpu_resume(void);
 		pg &= ~0x3fff;				\
 		(pgd_t *)phys_to_virt(pg);		\
 	})
+#endif
 
 #endif
 

arch/arm/include/asm/processor.h

@@ -123,6 +123,8 @@ static inline void prefetch(const void *ptr)
 
 #endif
 
+#define HAVE_ARCH_PICK_MMAP_LAYOUT
+
 #endif
 
 #endif /* __ASM_ARM_PROCESSOR_H */

arch/arm/include/asm/sched_clock.h

@@ -8,113 +8,7 @@
 #ifndef ASM_SCHED_CLOCK
 #define ASM_SCHED_CLOCK
 
-#include <linux/kernel.h>
-#include <linux/types.h>
-
-struct clock_data {
-	u64 epoch_ns;
-	u32 epoch_cyc;
-	u32 epoch_cyc_copy;
-	u32 mult;
-	u32 shift;
-};
-
-#define DEFINE_CLOCK_DATA(name)	struct clock_data name
-
-static inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift)
-{
-	return (cyc * mult) >> shift;
-}
-
-/*
- * Atomically update the sched_clock epoch.  Your update callback will
- * be called from a timer before the counter wraps - read the current
- * counter value, and call this function to safely move the epochs
- * forward.  Only use this from the update callback.
- */
-static inline void update_sched_clock(struct clock_data *cd, u32 cyc, u32 mask)
-{
-	unsigned long flags;
-	u64 ns = cd->epoch_ns +
-		cyc_to_ns((cyc - cd->epoch_cyc) & mask, cd->mult, cd->shift);
-
-	/*
-	 * Write epoch_cyc and epoch_ns in a way that the update is
-	 * detectable in cyc_to_fixed_sched_clock().
-	 */
-	raw_local_irq_save(flags);
-	cd->epoch_cyc = cyc;
-	smp_wmb();
-	cd->epoch_ns = ns;
-	smp_wmb();
-	cd->epoch_cyc_copy = cyc;
-	raw_local_irq_restore(flags);
-}
-
-/*
- * If your clock rate is known at compile time, using this will allow
- * you to optimize the mult/shift loads away.  This is paired with
- * init_fixed_sched_clock() to ensure that your mult/shift are correct.
- */
-static inline unsigned long long cyc_to_fixed_sched_clock(struct clock_data *cd,
-	u32 cyc, u32 mask, u32 mult, u32 shift)
-{
-	u64 epoch_ns;
-	u32 epoch_cyc;
-
-	/*
-	 * Load the epoch_cyc and epoch_ns atomically.  We do this by
-	 * ensuring that we always write epoch_cyc, epoch_ns and
-	 * epoch_cyc_copy in strict order, and read them in strict order.
-	 * If epoch_cyc and epoch_cyc_copy are not equal, then we're in
-	 * the middle of an update, and we should repeat the load.
-	 */
-	do {
-		epoch_cyc = cd->epoch_cyc;
-		smp_rmb();
-		epoch_ns = cd->epoch_ns;
-		smp_rmb();
-	} while (epoch_cyc != cd->epoch_cyc_copy);
-
-	return epoch_ns + cyc_to_ns((cyc - epoch_cyc) & mask, mult, shift);
-}
-
-/*
- * Otherwise, you need to use this, which will obtain the mult/shift
- * from the clock_data structure.  Use init_sched_clock() with this.
- */
-static inline unsigned long long cyc_to_sched_clock(struct clock_data *cd,
-	u32 cyc, u32 mask)
-{
-	return cyc_to_fixed_sched_clock(cd, cyc, mask, cd->mult, cd->shift);
-}
-
-/*
- * Initialize the clock data - calculate the appropriate multiplier
- * and shift.  Also setup a timer to ensure that the epoch is refreshed
- * at the appropriate time interval, which will call your update
- * handler.
- */
-void init_sched_clock(struct clock_data *, void (*)(void),
-	unsigned int, unsigned long);
-
-/*
- * Use this initialization function rather than init_sched_clock() if
- * you're using cyc_to_fixed_sched_clock, which will warn if your
- * constants are incorrect.
- */
-static inline void init_fixed_sched_clock(struct clock_data *cd,
-	void (*update)(void), unsigned int bits, unsigned long rate,
-	u32 mult, u32 shift)
-{
-	init_sched_clock(cd, update, bits, rate);
-	if (cd->mult != mult || cd->shift != shift) {
-		pr_crit("sched_clock: wrong multiply/shift: %u>>%u vs calculated %u>>%u\n"
-			"sched_clock: fix multiply/shift to avoid scheduler hiccups\n",
-			mult, shift, cd->mult, cd->shift);
-	}
-}
-
 extern void sched_clock_postinit(void);
+extern void setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate);
 
 #endif

arch/arm/include/asm/setup.h

@@ -192,11 +192,7 @@ static const struct tagtable __tagtable_##fn __tag = { tag, fn }
 /*
  * Memory map description
  */
-#ifdef CONFIG_ARCH_EP93XX
-# define NR_BANKS 16
-#else
-# define NR_BANKS 8
-#endif
+#define NR_BANKS	CONFIG_ARM_NR_BANKS
 
 struct membank {
 	phys_addr_t start;

arch/arm/include/asm/swab.h

@@ -24,12 +24,13 @@
 
 #if defined(__KERNEL__) && __LINUX_ARM_ARCH__ >= 6
 
-static inline __attribute_const__ __u16 __arch_swab16(__u16 x)
+static inline __attribute_const__ __u32 __arch_swahb32(__u32 x)
 {
 	__asm__ ("rev16 %0, %1" : "=r" (x) : "r" (x));
 	return x;
 }
-#define __arch_swab16 __arch_swab16
+#define __arch_swahb32 __arch_swahb32
+#define __arch_swab16(x) ((__u16)__arch_swahb32(x))
 
 static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
 {

arch/arm/include/asm/system.h

@@ -80,6 +80,14 @@ struct siginfo;
 void arm_notify_die(const char *str, struct pt_regs *regs, struct siginfo *info,
 		unsigned long err, unsigned long trap);
 
+#ifdef CONFIG_ARM_LPAE
+#define FAULT_CODE_ALIGNMENT	33
+#define FAULT_CODE_DEBUG	34
+#else
+#define FAULT_CODE_ALIGNMENT	1
+#define FAULT_CODE_DEBUG	2
+#endif
+
 void hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int,
 				       struct pt_regs *),
 		     int sig, int code, const char *name);
@@ -100,7 +108,7 @@ extern void __show_regs(struct pt_regs *);
 extern int __pure cpu_architecture(void);
 extern void cpu_init(void);
 
-void arm_machine_restart(char mode, const char *cmd);
+void soft_restart(unsigned long);
 extern void (*arm_pm_restart)(char str, const char *cmd);
 
 #define UDBG_UNDEFINED	(1 << 0)

arch/arm/include/asm/tlb.h

@@ -202,8 +202,18 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 	tlb_remove_page(tlb, pte);
 }
 
+static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
+				  unsigned long addr)
+{
+#ifdef CONFIG_ARM_LPAE
+	tlb_add_flush(tlb, addr);
+	tlb_remove_page(tlb, virt_to_page(pmdp));
+#endif
+}
+
 #define pte_free_tlb(tlb, ptep, addr)	__pte_free_tlb(tlb, ptep, addr)
-#define pmd_free_tlb(tlb, pmdp, addr)	pmd_free((tlb)->mm, pmdp)
+#define pmd_free_tlb(tlb, pmdp, addr)	__pmd_free_tlb(tlb, pmdp, addr)
+#define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)
 
 #define tlb_migrate_finish(mm)		do { } while (0)
 

arch/arm/kernel/Makefile

@@ -13,7 +13,7 @@ CFLAGS_REMOVE_return_address.o = -pg
 
 # Object file lists.
 
-obj-y		:= elf.o entry-armv.o entry-common.o irq.o \
+obj-y		:= elf.o entry-armv.o entry-common.o irq.o opcodes.o \
 		   process.o ptrace.o return_address.o setup.o signal.o \
 		   sys_arm.o stacktrace.o time.o traps.o
 

arch/arm/kernel/entry-armv.S

@@ -36,12 +36,11 @@
 #ifdef CONFIG_MULTI_IRQ_HANDLER
 	ldr	r1, =handle_arch_irq
 	mov	r0, sp
-	ldr	r1, [r1]
 	adr	lr, BSYM(9997f)
-	teq	r1, #0
-	movne	pc, r1
-#endif
+	ldr	pc, [r1]
+#else
 	arch_irq_handler_default
+#endif
 9997:
 	.endm
 

arch/arm/kernel/head.S

@@ -39,8 +39,14 @@
 #error KERNEL_RAM_VADDR must start at 0xXXXX8000
 #endif
 
+#ifdef CONFIG_ARM_LPAE
+	/* LPAE requires an additional page for the PGD */
+#define PG_DIR_SIZE	0x5000
+#define PMD_ORDER	3
+#else
 #define PG_DIR_SIZE	0x4000
 #define PMD_ORDER	2
+#endif
 
 	.globl	swapper_pg_dir
 	.equ	swapper_pg_dir, KERNEL_RAM_VADDR - PG_DIR_SIZE
@@ -164,17 +170,36 @@ __create_page_tables:
 	teq	r0, r6
 	bne	1b
 
+#ifdef CONFIG_ARM_LPAE
+	/*
+	 * Build the PGD table (first level) to point to the PMD table. A PGD
+	 * entry is 64-bit wide.
+	 */
+	mov	r0, r4
+	add	r3, r4, #0x1000			@ first PMD table address
+	orr	r3, r3, #3			@ PGD block type
+	mov	r6, #4				@ PTRS_PER_PGD
+	mov	r7, #1 << (55 - 32)		@ L_PGD_SWAPPER
+1:	str	r3, [r0], #4			@ set bottom PGD entry bits
+	str	r7, [r0], #4			@ set top PGD entry bits
+	add	r3, r3, #0x1000			@ next PMD table
+	subs	r6, r6, #1
+	bne	1b
+
+	add	r4, r4, #0x1000			@ point to the PMD tables
+#endif
+
 	ldr	r7, [r10, #PROCINFO_MM_MMUFLAGS] @ mm_mmuflags
 
 	/*
 	 * Create identity mapping to cater for __enable_mmu.
 	 * This identity mapping will be removed by paging_init().
 	 */
-	adr	r0, __enable_mmu_loc
+	adr	r0, __turn_mmu_on_loc
 	ldmia	r0, {r3, r5, r6}
 	sub	r0, r0, r3			@ virt->phys offset
-	add	r5, r5, r0			@ phys __enable_mmu
-	add	r6, r6, r0			@ phys __enable_mmu_end
+	add	r5, r5, r0			@ phys __turn_mmu_on
+	add	r6, r6, r0			@ phys __turn_mmu_on_end
 	mov	r5, r5, lsr #SECTION_SHIFT
 	mov	r6, r6, lsr #SECTION_SHIFT
 
@@ -219,8 +244,8 @@ __create_page_tables:
 #endif
 
 	/*
-	 * Then map boot params address in r2 or
-	 * the first 1MB of ram if boot params address is not specified.
+	 * Then map boot params address in r2 or the first 1MB (2MB with LPAE)
+	 * of ram if boot params address is not specified.
 	 */
 	mov	r0, r2, lsr #SECTION_SHIFT
 	movs	r0, r0, lsl #SECTION_SHIFT
@@ -251,7 +276,15 @@ __create_page_tables:
 	mov	r3, r7, lsr #SECTION_SHIFT
 	ldr	r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags
 	orr	r3, r7, r3, lsl #SECTION_SHIFT
+#ifdef CONFIG_ARM_LPAE
+	mov	r7, #1 << (54 - 32)		@ XN
+#else
+	orr	r3, r3, #PMD_SECT_XN
+#endif
 1:	str	r3, [r0], #4
+#ifdef CONFIG_ARM_LPAE
+	str	r7, [r0], #4
+#endif
 	add	r3, r3, #1 << SECTION_SHIFT
 	cmp	r0, r6
 	blo	1b
@@ -282,15 +315,18 @@ __create_page_tables:
 	add	r0, r4, #0xd8000000 >> (SECTION_SHIFT - PMD_ORDER)
 	str	r3, [r0]
 #endif
+#endif
+#ifdef CONFIG_ARM_LPAE
+	sub	r4, r4, #0x1000		@ point to the PGD table
 #endif
 	mov	pc, lr
 ENDPROC(__create_page_tables)
 	.ltorg
 	.align
-__enable_mmu_loc:
+__turn_mmu_on_loc:
 	.long	.
-	.long	__enable_mmu
-	.long	__enable_mmu_end
+	.long	__turn_mmu_on
+	.long	__turn_mmu_on_end
 
 #if defined(CONFIG_SMP)
 	__CPUINIT
@@ -374,12 +410,17 @@ __enable_mmu:
 #ifdef CONFIG_CPU_ICACHE_DISABLE
 	bic	r0, r0, #CR_I
 #endif
+#ifdef CONFIG_ARM_LPAE
+	mov	r5, #0
+	mcrr	p15, 0, r4, r5, c2		@ load TTBR0
+#else
 	mov	r5, #(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \
 		      domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
 		      domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \
 		      domain_val(DOMAIN_IO, DOMAIN_CLIENT))
 	mcr	p15, 0, r5, c3, c0, 0		@ load domain access register
 	mcr	p15, 0, r4, c2, c0, 0		@ load page table pointer
+#endif
 	b	__turn_mmu_on
 ENDPROC(__enable_mmu)
 
@@ -398,15 +439,19 @@ ENDPROC(__enable_mmu)
  * other registers depend on the function called upon completion
  */
 	.align	5
-__turn_mmu_on:
+	.pushsection	.idmap.text, "ax"
+ENTRY(__turn_mmu_on)
 	mov	r0, r0
+	instr_sync
 	mcr	p15, 0, r0, c1, c0, 0		@ write control reg
 	mrc	p15, 0, r3, c0, c0, 0		@ read id reg
+	instr_sync
 	mov	r3, r3
 	mov	r3, r13
 	mov	pc, r3
-__enable_mmu_end:
+__turn_mmu_on_end:
 ENDPROC(__turn_mmu_on)
+	.popsection
 
 
 #ifdef CONFIG_SMP_ON_UP

arch/arm/kernel/hw_breakpoint.c

@@ -1016,10 +1016,10 @@ static int __init arch_hw_breakpoint_init(void)
 	}
 
 	/* Register debug fault handler. */
-	hook_fault_code(2, hw_breakpoint_pending, SIGTRAP, TRAP_HWBKPT,
-			"watchpoint debug exception");
-	hook_ifault_code(2, hw_breakpoint_pending, SIGTRAP, TRAP_HWBKPT,
-			"breakpoint debug exception");
+	hook_fault_code(FAULT_CODE_DEBUG, hw_breakpoint_pending, SIGTRAP,
+			TRAP_HWBKPT, "watchpoint debug exception");
+	hook_ifault_code(FAULT_CODE_DEBUG, hw_breakpoint_pending, SIGTRAP,
+			TRAP_HWBKPT, "breakpoint debug exception");
 
 	/* Register hotplug notifier. */
 	register_cpu_notifier(&dbg_reset_nb);

arch/arm/kernel/kprobes-test.c

@@ -202,6 +202,8 @@
 #include <linux/slab.h>
 #include <linux/kprobes.h>
 
+#include <asm/opcodes.h>
+
 #include "kprobes.h"
 #include "kprobes-test.h"
 
@@ -1050,65 +1052,9 @@ static int test_instance;
 
 static unsigned long test_check_cc(int cc, unsigned long cpsr)
 {
-	unsigned long temp;
-
-	switch (cc) {
-	case 0x0: /* eq */
-		return cpsr & PSR_Z_BIT;
-
-	case 0x1: /* ne */
-		return (~cpsr) & PSR_Z_BIT;
-
-	case 0x2: /* cs */
-		return cpsr & PSR_C_BIT;
-
-	case 0x3: /* cc */
-		return (~cpsr) & PSR_C_BIT;
-
-	case 0x4: /* mi */
-		return cpsr & PSR_N_BIT;
-
-	case 0x5: /* pl */
-		return (~cpsr) & PSR_N_BIT;
-
-	case 0x6: /* vs */
-		return cpsr & PSR_V_BIT;
-
-	case 0x7: /* vc */
-		return (~cpsr) & PSR_V_BIT;
-
-	case 0x8: /* hi */
-		cpsr &= ~(cpsr >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */
-		return cpsr & PSR_C_BIT;
-
-	case 0x9: /* ls */
-		cpsr &= ~(cpsr >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */
-		return (~cpsr) & PSR_C_BIT;
+	int ret = arm_check_condition(cc << 28, cpsr);
 
-	case 0xa: /* ge */
-		cpsr ^= (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */
-		return (~cpsr) & PSR_N_BIT;
-
-	case 0xb: /* lt */
-		cpsr ^= (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */
-		return cpsr & PSR_N_BIT;
-
-	case 0xc: /* gt */
-		temp = cpsr ^ (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */
-		temp |= (cpsr << 1);	   /* PSR_N_BIT |= PSR_Z_BIT */
-		return (~temp) & PSR_N_BIT;
-
-	case 0xd: /* le */
-		temp = cpsr ^ (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */
-		temp |= (cpsr << 1);	   /* PSR_N_BIT |= PSR_Z_BIT */
-		return temp & PSR_N_BIT;
-
-	case 0xe: /* al */
-	case 0xf: /* unconditional */
-		return true;
-	}
-	BUG();
-	return false;
+	return (ret != ARM_OPCODE_CONDTEST_FAIL);
 }
 
 static int is_last_scenario;
@@ -1128,7 +1074,9 @@ static unsigned long test_context_cpsr(int scenario)
 
 	if (!test_case_is_thumb) {
 		/* Testing ARM code */
-		probe_should_run = test_check_cc(current_instruction >> 28, cpsr) != 0;
+		int cc = current_instruction >> 28;
+
+		probe_should_run = test_check_cc(cc, cpsr) != 0;
 		if (scenario == 15)
 			is_last_scenario = true;
 

arch/arm/kernel/machine_kexec.c

@@ -12,12 +12,11 @@
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
 #include <asm/mach-types.h>
+#include <asm/system.h>
 
 extern const unsigned char relocate_new_kernel[];
 extern const unsigned int relocate_new_kernel_size;
 
-extern void setup_mm_for_reboot(char mode);
-
 extern unsigned long kexec_start_address;
 extern unsigned long kexec_indirection_page;
 extern unsigned long kexec_mach_type;
@@ -111,14 +110,6 @@ void machine_kexec(struct kimage *image)
 
 	if (kexec_reinit)
 		kexec_reinit();
-	local_irq_disable();
-	local_fiq_disable();
-	setup_mm_for_reboot(0); /* mode is not used, so just pass 0*/
-	flush_cache_all();
-	outer_flush_all();
-	outer_disable();
-	cpu_proc_fin();
-	outer_inv_all();
-	flush_cache_all();
-	cpu_reset(reboot_code_buffer_phys);
+
+	soft_restart(reboot_code_buffer_phys);
 }

arch/arm/kernel/opcodes.c

+/*
+ *  linux/arch/arm/kernel/opcodes.c
+ *
+ *  A32 condition code lookup feature moved from nwfpe/fpopcode.c
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <asm/opcodes.h>
+
+#define ARM_OPCODE_CONDITION_UNCOND 0xf
+
+/*
+ * condition code lookup table
+ * index into the table is test code: EQ, NE, ... LT, GT, AL, NV
+ *
+ * bit position in short is condition code: NZCV
+ */
+static const unsigned short cc_map[16] = {
+	0xF0F0,			/* EQ == Z set            */
+	0x0F0F,			/* NE                     */
+	0xCCCC,			/* CS == C set            */
+	0x3333,			/* CC                     */
+	0xFF00,			/* MI == N set            */
+	0x00FF,			/* PL                     */
+	0xAAAA,			/* VS == V set            */
+	0x5555,			/* VC                     */
+	0x0C0C,			/* HI == C set && Z clear */
+	0xF3F3,			/* LS == C clear || Z set */
+	0xAA55,			/* GE == (N==V)           */
+	0x55AA,			/* LT == (N!=V)           */
+	0x0A05,			/* GT == (!Z && (N==V))   */
+	0xF5FA,			/* LE == (Z || (N!=V))    */
+	0xFFFF,			/* AL always              */
+	0			/* NV                     */
+};
+
+/*
+ * Returns:
+ * ARM_OPCODE_CONDTEST_FAIL   - if condition fails
+ * ARM_OPCODE_CONDTEST_PASS   - if condition passes (including AL)
+ * ARM_OPCODE_CONDTEST_UNCOND - if NV condition, or separate unconditional
+ *                              opcode space from v5 onwards
+ *
+ * Code that tests whether a conditional instruction would pass its condition
+ * check should check that return value == ARM_OPCODE_CONDTEST_PASS.
+ *
+ * Code that tests if a condition means that the instruction would be executed
+ * (regardless of conditional or unconditional) should instead check that the
+ * return value != ARM_OPCODE_CONDTEST_FAIL.
+ */
+asmlinkage unsigned int arm_check_condition(u32 opcode, u32 psr)
+{
+	u32 cc_bits  = opcode >> 28;
+	u32 psr_cond = psr >> 28;
+	unsigned int ret;
+
+	if (cc_bits != ARM_OPCODE_CONDITION_UNCOND) {
+		if ((cc_map[cc_bits] >> (psr_cond)) & 1)
+			ret = ARM_OPCODE_CONDTEST_PASS;
+		else
+			ret = ARM_OPCODE_CONDTEST_FAIL;
+	} else {
+		ret = ARM_OPCODE_CONDTEST_UNCOND;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(arm_check_condition);

arch/arm/kernel/perf_event.c

@@ -59,8 +59,7 @@ armpmu_get_pmu_id(void)
 }
 EXPORT_SYMBOL_GPL(armpmu_get_pmu_id);
 
-int
-armpmu_get_max_events(void)
+int perf_num_counters(void)
 {
 	int max_events = 0;
 
@@ -69,12 +68,6 @@ armpmu_get_max_events(void)
 
 	return max_events;
 }
-EXPORT_SYMBOL_GPL(armpmu_get_max_events);
-
-int perf_num_counters(void)
-{
-	return armpmu_get_max_events();
-}
 EXPORT_SYMBOL_GPL(perf_num_counters);
 
 #define HW_OP_UNSUPPORTED		0xFFFF
@@ -380,6 +373,8 @@ armpmu_release_hardware(struct arm_pmu *armpmu)
 {
 	int i, irq, irqs;
 	struct platform_device *pmu_device = armpmu->plat_device;
+	struct arm_pmu_platdata *plat =
+		dev_get_platdata(&pmu_device->dev);
 
 	irqs = min(pmu_device->num_resources, num_possible_cpus());
 
@@ -387,9 +382,12 @@ armpmu_release_hardware(struct arm_pmu *armpmu)
 		if (!cpumask_test_and_clear_cpu(i, &armpmu->active_irqs))
 			continue;
 		irq = platform_get_irq(pmu_device, i);
-		if (irq >= 0)
+		if (irq >= 0) {
+			if (plat && plat->disable_irq)
+				plat->disable_irq(irq);
 			free_irq(irq, armpmu);
 		}
+	}
 
 	release_pmu(armpmu->type);
 }
@@ -448,7 +446,8 @@ armpmu_reserve_hardware(struct arm_pmu *armpmu)
 				irq);
 			armpmu_release_hardware(armpmu);
 			return err;
-		}
+		} else if (plat && plat->enable_irq)
+			plat->enable_irq(irq);
 
 		cpumask_set_cpu(i, &armpmu->active_irqs);
 	}

arch/arm/kernel/perf_event_v6.c

@@ -72,6 +72,8 @@ static const unsigned armv6_perf_map[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV6_PERFCTR_BR_EXEC,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV6_PERFCTR_BR_MISPREDICT,
 	[PERF_COUNT_HW_BUS_CYCLES]		= HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= ARMV6_PERFCTR_IBUF_STALL,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= ARMV6_PERFCTR_LSU_FULL_STALL,
 };
 
 static const unsigned armv6_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
@@ -225,6 +227,8 @@ static const unsigned armv6mpcore_perf_map[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV6MPCORE_PERFCTR_BR_EXEC,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV6MPCORE_PERFCTR_BR_MISPREDICT,
 	[PERF_COUNT_HW_BUS_CYCLES]		= HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= ARMV6MPCORE_PERFCTR_IBUF_STALL,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= ARMV6MPCORE_PERFCTR_LSU_FULL_STALL,
 };
 
 static const unsigned armv6mpcore_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]

arch/arm/kernel/perf_event_xscale.c

@@ -55,6 +55,8 @@ static const unsigned xscale_perf_map[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= XSCALE_PERFCTR_BRANCH,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= XSCALE_PERFCTR_BRANCH_MISS,
 	[PERF_COUNT_HW_BUS_CYCLES]		= HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= XSCALE_PERFCTR_ICACHE_NO_DELIVER,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
 };
 
 static const unsigned xscale_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]

arch/arm/kernel/process.c

@@ -57,7 +57,7 @@ static const char *isa_modes[] = {
   "ARM" , "Thumb" , "Jazelle", "ThumbEE"
 };
 
-extern void setup_mm_for_reboot(char mode);
+extern void setup_mm_for_reboot(void);
 
 static volatile int hlt_counter;
 
@@ -92,18 +92,24 @@ static int __init hlt_setup(char *__unused)
 __setup("nohlt", nohlt_setup);
 __setup("hlt", hlt_setup);
 
-void arm_machine_restart(char mode, const char *cmd)
-{
-	/* Disable interrupts first */
-	local_irq_disable();
-	local_fiq_disable();
+extern void call_with_stack(void (*fn)(void *), void *arg, void *sp);
+typedef void (*phys_reset_t)(unsigned long);
 
-	/*
-	 * Tell the mm system that we are going to reboot -
-	 * we may need it to insert some 1:1 mappings so that
-	 * soft boot works.
+/*
+ * A temporary stack to use for CPU reset. This is static so that we
+ * don't clobber it with the identity mapping. When running with this
+ * stack, any references to the current task *will not work* so you
+ * should really do as little as possible before jumping to your reset
+ * code.
  */
-	setup_mm_for_reboot(mode);
+static u64 soft_restart_stack[16];
+
+static void __soft_restart(void *addr)
+{
+	phys_reset_t phys_reset;
+
+	/* Take out a flat memory mapping. */
+	setup_mm_for_reboot();
 
 	/* Clean and invalidate caches */
 	flush_cache_all();
@@ -114,18 +120,35 @@ void arm_machine_restart(char mode, const char *cmd)
 	/* Push out any further dirty data, and ensure cache is empty */
 	flush_cache_all();
 
-	/*
-	 * Now call the architecture specific reboot code.
-	 */
-	arch_reset(mode, cmd);
+	/* Switch to the identity mapping. */
+	phys_reset = (phys_reset_t)(unsigned long)virt_to_phys(cpu_reset);
+	phys_reset((unsigned long)addr);
 
-	/*
-	 * Whoops - the architecture was unable to reboot.
-	 * Tell the user!
-	 */
-	mdelay(1000);
-	printk("Reboot failed -- System halted\n");
-	while (1);
+	/* Should never get here. */
+	BUG();
+}
+
+void soft_restart(unsigned long addr)
+{
+	u64 *stack = soft_restart_stack + ARRAY_SIZE(soft_restart_stack);
+
+	/* Disable interrupts first */
+	local_irq_disable();
+	local_fiq_disable();
+
+	/* Disable the L2 if we're the last man standing. */
+	if (num_online_cpus() == 1)
+		outer_disable();
+
+	/* Change to the new stack and continue with the reset. */
+	call_with_stack(__soft_restart, (void *)addr, (void *)stack);
+
+	/* Should never get here. */
+	BUG();
+}
+
+static void null_restart(char mode, const char *cmd)
+{
 }
 
 /*
@@ -134,7 +157,7 @@ void arm_machine_restart(char mode, const char *cmd)
 void (*pm_power_off)(void);
 EXPORT_SYMBOL(pm_power_off);
 
-void (*arm_pm_restart)(char str, const char *cmd) = arm_machine_restart;
+void (*arm_pm_restart)(char str, const char *cmd) = null_restart;
 EXPORT_SYMBOL_GPL(arm_pm_restart);
 
 static void do_nothing(void *unused)
@@ -253,7 +276,15 @@ void machine_power_off(void)
 void machine_restart(char *cmd)
 {
 	machine_shutdown();
+
 	arm_pm_restart(reboot_mode, cmd);
+
+	/* Give a grace period for failure to restart of 1s */
+	mdelay(1000);
+
+	/* Whoops - the platform was unable to reboot. Tell the user! */
+	printk("Reboot failed -- System halted\n");
+	while (1);
 }
 
 void __show_regs(struct pt_regs *regs)

arch/arm/kernel/sched_clock.c

@@ -14,61 +14,153 @@
 
 #include <asm/sched_clock.h>
 
+struct clock_data {
+	u64 epoch_ns;
+	u32 epoch_cyc;
+	u32 epoch_cyc_copy;
+	u32 mult;
+	u32 shift;
+};
+
 static void sched_clock_poll(unsigned long wrap_ticks);
 static DEFINE_TIMER(sched_clock_timer, sched_clock_poll, 0, 0);
-static void (*sched_clock_update_fn)(void);
+
+static struct clock_data cd = {
+	.mult	= NSEC_PER_SEC / HZ,
+};
+
+static u32 __read_mostly sched_clock_mask = 0xffffffff;
+
+static u32 notrace jiffy_sched_clock_read(void)
+{
+	return (u32)(jiffies - INITIAL_JIFFIES);
+}
+
+static u32 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read;
+
+static inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift)
+{
+	return (cyc * mult) >> shift;
+}
+
+static unsigned long long cyc_to_sched_clock(u32 cyc, u32 mask)
+{
+	u64 epoch_ns;
+	u32 epoch_cyc;
+
+	/*
+	 * Load the epoch_cyc and epoch_ns atomically.  We do this by
+	 * ensuring that we always write epoch_cyc, epoch_ns and
+	 * epoch_cyc_copy in strict order, and read them in strict order.
+	 * If epoch_cyc and epoch_cyc_copy are not equal, then we're in
+	 * the middle of an update, and we should repeat the load.
+	 */
+	do {
+		epoch_cyc = cd.epoch_cyc;
+		smp_rmb();
+		epoch_ns = cd.epoch_ns;
+		smp_rmb();
+	} while (epoch_cyc != cd.epoch_cyc_copy);
+
+	return epoch_ns + cyc_to_ns((cyc - epoch_cyc) & mask, cd.mult, cd.shift);
+}
+
+/*
+ * Atomically update the sched_clock epoch.
+ */
+static void notrace update_sched_clock(void)
+{
+	unsigned long flags;
+	u32 cyc;
+	u64 ns;
+
+	cyc = read_sched_clock();
+	ns = cd.epoch_ns +
+		cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask,
+			  cd.mult, cd.shift);
+	/*
+	 * Write epoch_cyc and epoch_ns in a way that the update is
+	 * detectable in cyc_to_fixed_sched_clock().
+	 */
+	raw_local_irq_save(flags);
+	cd.epoch_cyc = cyc;
+	smp_wmb();
+	cd.epoch_ns = ns;
+	smp_wmb();
+	cd.epoch_cyc_copy = cyc;
+	raw_local_irq_restore(flags);
+}
 
 static void sched_clock_poll(unsigned long wrap_ticks)
 {
 	mod_timer(&sched_clock_timer, round_jiffies(jiffies + wrap_ticks));
-	sched_clock_update_fn();
+	update_sched_clock();
 }
 
-void __init init_sched_clock(struct clock_data *cd, void (*update)(void),
-	unsigned int clock_bits, unsigned long rate)
+void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
 {
 	unsigned long r, w;
 	u64 res, wrap;
 	char r_unit;
 
-	sched_clock_update_fn = update;
+	BUG_ON(bits > 32);
+	WARN_ON(!irqs_disabled());
+	WARN_ON(read_sched_clock != jiffy_sched_clock_read);
+	read_sched_clock = read;
+	sched_clock_mask = (1 << bits) - 1;
 
 	/* calculate the mult/shift to convert counter ticks to ns. */
-	clocks_calc_mult_shift(&cd->mult, &cd->shift, rate, NSEC_PER_SEC, 0);
+	clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 0);
 
 	r = rate;
 	if (r >= 4000000) {
 		r /= 1000000;
 		r_unit = 'M';
-	} else {
+	} else if (r >= 1000) {
 		r /= 1000;
 		r_unit = 'k';
-	}
+	} else
+		r_unit = ' ';
 
 	/* calculate how many ns until we wrap */
-	wrap = cyc_to_ns((1ULL << clock_bits) - 1, cd->mult, cd->shift);
+	wrap = cyc_to_ns((1ULL << bits) - 1, cd.mult, cd.shift);
 	do_div(wrap, NSEC_PER_MSEC);
 	w = wrap;
 
 	/* calculate the ns resolution of this counter */
-	res = cyc_to_ns(1ULL, cd->mult, cd->shift);
+	res = cyc_to_ns(1ULL, cd.mult, cd.shift);
 	pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lums\n",
-		clock_bits, r, r_unit, res, w);
+		bits, r, r_unit, res, w);
 
 	/*
 	 * Start the timer to keep sched_clock() properly updated and
 	 * sets the initial epoch.
 	 */
 	sched_clock_timer.data = msecs_to_jiffies(w - (w / 10));
-	update();
+	update_sched_clock();
 
 	/*
 	 * Ensure that sched_clock() starts off at 0ns
 	 */
-	cd->epoch_ns = 0;
+	cd.epoch_ns = 0;
+
+	pr_debug("Registered %pF as sched_clock source\n", read);
+}
+
+unsigned long long notrace sched_clock(void)
+{
+	u32 cyc = read_sched_clock();
+	return cyc_to_sched_clock(cyc, sched_clock_mask);
 }
 
 void __init sched_clock_postinit(void)
 {
+	/*
+	 * If no sched_clock function has been provided at that point,
+	 * make it the final one one.
+	 */
+	if (read_sched_clock == jiffy_sched_clock_read)
+		setup_sched_clock(jiffy_sched_clock_read, 32, HZ);
+
 	sched_clock_poll(sched_clock_timer.data);
 }

arch/arm/kernel/setup.c

@@ -31,6 +31,7 @@
 #include <linux/memblock.h>
 #include <linux/bug.h>
 #include <linux/compiler.h>
+#include <linux/sort.h>
 
 #include <asm/unified.h>
 #include <asm/cpu.h>
@@ -890,6 +891,12 @@ static struct machine_desc * __init setup_machine_tags(unsigned int nr)
 	return mdesc;
 }
 
+static int __init meminfo_cmp(const void *_a, const void *_b)
+{
+	const struct membank *a = _a, *b = _b;
+	long cmp = bank_pfn_start(a) - bank_pfn_start(b);
+	return cmp < 0 ? -1 : cmp > 0 ? 1 : 0;
+}
 
 void __init setup_arch(char **cmdline_p)
 {
@@ -908,8 +915,8 @@ void __init setup_arch(char **cmdline_p)
 		arm_dma_zone_size = mdesc->dma_zone_size;
 	}
 #endif
-	if (mdesc->soft_reboot)
-		reboot_setup("s");
+	if (mdesc->restart_mode)
+		reboot_setup(&mdesc->restart_mode);
 
 	init_mm.start_code = (unsigned long) _text;
 	init_mm.end_code   = (unsigned long) _etext;
@@ -922,12 +929,16 @@ void __init setup_arch(char **cmdline_p)
 
 	parse_early_param();
 
+	sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL);
 	sanity_check_meminfo();
 	arm_memblock_init(&meminfo, mdesc);
 
 	paging_init(mdesc);
 	request_standard_resources(mdesc);
 
+	if (mdesc->restart)
+		arm_pm_restart = mdesc->restart;
+
 	unflatten_device_tree();
 
 #ifdef CONFIG_SMP

arch/arm/kernel/sleep.S

@@ -54,14 +54,18 @@ ENDPROC(cpu_suspend_abort)
  * r0 = control register value
  */
 	.align	5
+	.pushsection	.idmap.text,"ax"
 ENTRY(cpu_resume_mmu)
 	ldr	r3, =cpu_resume_after_mmu
+	instr_sync
 	mcr	p15, 0, r0, c1, c0, 0	@ turn on MMU, I-cache, etc
 	mrc	p15, 0, r0, c0, c0, 0	@ read id reg
+	instr_sync
 	mov	r0, r0
 	mov	r0, r0
 	mov	pc, r3			@ jump to virtual address
 ENDPROC(cpu_resume_mmu)
+	.popsection
 cpu_resume_after_mmu:
 	bl	cpu_init		@ restore the und/abt/irq banked regs
 	mov	r0, #0			@ return zero on success

arch/arm/kernel/smp.c

@@ -31,6 +31,7 @@
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/exception.h>
+#include <asm/idmap.h>
 #include <asm/topology.h>
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
@@ -61,7 +62,6 @@ int __cpuinit __cpu_up(unsigned int cpu)
 {
 	struct cpuinfo_arm *ci = &per_cpu(cpu_data, cpu);
 	struct task_struct *idle = ci->idle;
-	pgd_t *pgd;
 	int ret;
 
 	/*
@@ -83,30 +83,12 @@ int __cpuinit __cpu_up(unsigned int cpu)
 		init_idle(idle, cpu);
 	}
 
-	/*
-	 * Allocate initial page tables to allow the new CPU to
-	 * enable the MMU safely.  This essentially means a set
-	 * of our "standard" page tables, with the addition of
-	 * a 1:1 mapping for the physical address of the kernel.
-	 */
-	pgd = pgd_alloc(&init_mm);
-	if (!pgd)
-		return -ENOMEM;
-
-	if (PHYS_OFFSET != PAGE_OFFSET) {
-#ifndef CONFIG_HOTPLUG_CPU
-		identity_mapping_add(pgd, __pa(__init_begin), __pa(__init_end));
-#endif
-		identity_mapping_add(pgd, __pa(_stext), __pa(_etext));
-		identity_mapping_add(pgd, __pa(_sdata), __pa(_edata));
-	}
-
 	/*
 	 * We need to tell the secondary core where to find
 	 * its stack and the page tables.
 	 */
 	secondary_data.stack = task_stack_page(idle) + THREAD_START_SP;
-	secondary_data.pgdir = virt_to_phys(pgd);
+	secondary_data.pgdir = virt_to_phys(idmap_pgd);
 	secondary_data.swapper_pg_dir = virt_to_phys(swapper_pg_dir);
 	__cpuc_flush_dcache_area(&secondary_data, sizeof(secondary_data));
 	outer_clean_range(__pa(&secondary_data), __pa(&secondary_data + 1));
@@ -142,16 +124,6 @@ int __cpuinit __cpu_up(unsigned int cpu)
 	secondary_data.stack = NULL;
 	secondary_data.pgdir = 0;
 
-	if (PHYS_OFFSET != PAGE_OFFSET) {
-#ifndef CONFIG_HOTPLUG_CPU
-		identity_mapping_del(pgd, __pa(__init_begin), __pa(__init_end));
-#endif
-		identity_mapping_del(pgd, __pa(_stext), __pa(_etext));
-		identity_mapping_del(pgd, __pa(_sdata), __pa(_edata));
-	}
-
-	pgd_free(&init_mm, pgd);
-
 	return ret;
 }
 
@@ -550,6 +522,10 @@ static void ipi_cpu_stop(unsigned int cpu)
 	local_fiq_disable();
 	local_irq_disable();
 
+#ifdef CONFIG_HOTPLUG_CPU
+	platform_cpu_kill(cpu);
+#endif
+
 	while (1)
 		cpu_relax();
 }

arch/arm/kernel/smp_twd.c

@@ -10,8 +10,11 @@
  */
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/clk.h>
+#include <linux/cpufreq.h>
 #include <linux/delay.h>
 #include <linux/device.h>
+#include <linux/err.h>
 #include <linux/smp.h>
 #include <linux/jiffies.h>
 #include <linux/clockchips.h>
@@ -25,6 +28,7 @@
 /* set up by the platform code */
 void __iomem *twd_base;
 
+static struct clk *twd_clk;
 static unsigned long twd_timer_rate;
 
 static struct clock_event_device __percpu **twd_evt;
@@ -89,6 +93,52 @@ void twd_timer_stop(struct clock_event_device *clk)
 	disable_percpu_irq(clk->irq);
 }
 
+#ifdef CONFIG_CPU_FREQ
+
+/*
+ * Updates clockevent frequency when the cpu frequency changes.
+ * Called on the cpu that is changing frequency with interrupts disabled.
+ */
+static void twd_update_frequency(void *data)
+{
+	twd_timer_rate = clk_get_rate(twd_clk);
+
+	clockevents_update_freq(*__this_cpu_ptr(twd_evt), twd_timer_rate);
+}
+
+static int twd_cpufreq_transition(struct notifier_block *nb,
+	unsigned long state, void *data)
+{
+	struct cpufreq_freqs *freqs = data;
+
+	/*
+	 * The twd clock events must be reprogrammed to account for the new
+	 * frequency.  The timer is local to a cpu, so cross-call to the
+	 * changing cpu.
+	 */
+	if (state == CPUFREQ_POSTCHANGE || state == CPUFREQ_RESUMECHANGE)
+		smp_call_function_single(freqs->cpu, twd_update_frequency,
+			NULL, 1);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block twd_cpufreq_nb = {
+	.notifier_call = twd_cpufreq_transition,
+};
+
+static int twd_cpufreq_init(void)
+{
+	if (!IS_ERR(twd_clk))
+		return cpufreq_register_notifier(&twd_cpufreq_nb,
+			CPUFREQ_TRANSITION_NOTIFIER);
+
+	return 0;
+}
+core_initcall(twd_cpufreq_init);
+
+#endif
+
 static void __cpuinit twd_calibrate_rate(void)
 {
 	unsigned long count;
@@ -140,6 +190,35 @@ static irqreturn_t twd_handler(int irq, void *dev_id)
 	return IRQ_NONE;
 }
 
+static struct clk *twd_get_clock(void)
+{
+	struct clk *clk;
+	int err;
+
+	clk = clk_get_sys("smp_twd", NULL);
+	if (IS_ERR(clk)) {
+		pr_err("smp_twd: clock not found: %d\n", (int)PTR_ERR(clk));
+		return clk;
+	}
+
+	err = clk_prepare(clk);
+	if (err) {
+		pr_err("smp_twd: clock failed to prepare: %d\n", err);
+		clk_put(clk);
+		return ERR_PTR(err);
+	}
+
+	err = clk_enable(clk);
+	if (err) {
+		pr_err("smp_twd: clock failed to enable: %d\n", err);
+		clk_unprepare(clk);
+		clk_put(clk);
+		return ERR_PTR(err);
+	}
+
+	return clk;
+}
+
 /*
  * Setup the local clock events for a CPU.
  */
@@ -165,6 +244,12 @@ void __cpuinit twd_timer_setup(struct clock_event_device *clk)
 		}
 	}
 
+	if (!twd_clk)
+		twd_clk = twd_get_clock();
+
+	if (!IS_ERR_OR_NULL(twd_clk))
+		twd_timer_rate = clk_get_rate(twd_clk);
+	else
 		twd_calibrate_rate();
 
 	clk->name = "local_timer";
@@ -173,15 +258,11 @@ void __cpuinit twd_timer_setup(struct clock_event_device *clk)
 	clk->rating = 350;
 	clk->set_mode = twd_set_mode;
 	clk->set_next_event = twd_set_next_event;
-	clk->shift = 20;
-	clk->mult = div_sc(twd_timer_rate, NSEC_PER_SEC, clk->shift);
-	clk->max_delta_ns = clockevent_delta2ns(0xffffffff, clk);
-	clk->min_delta_ns = clockevent_delta2ns(0xf, clk);
 
 	this_cpu_clk = __this_cpu_ptr(twd_evt);
 	*this_cpu_clk = clk;
 
-	clockevents_register_device(clk);
-
+	clockevents_config_and_register(clk, twd_timer_rate,
+					0xf, 0xffffffff);
 	enable_percpu_irq(clk->irq, 0);
 }

arch/arm/kernel/suspend.c

 #include <linux/init.h>
 
+#include <asm/idmap.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/memory.h>
 #include <asm/suspend.h>
 #include <asm/tlbflush.h>
 
-static pgd_t *suspend_pgd;
-
 extern int __cpu_suspend(unsigned long, int (*)(unsigned long));
 extern void cpu_resume_mmu(void);
 
@@ -21,7 +20,7 @@ void __cpu_suspend_save(u32 *ptr, u32 ptrsz, u32 sp, u32 *save_ptr)
 	*save_ptr = virt_to_phys(ptr);
 
 	/* This must correspond to the LDM in cpu_resume() assembly */
-	*ptr++ = virt_to_phys(suspend_pgd);
+	*ptr++ = virt_to_phys(idmap_pgd);
 	*ptr++ = sp;
 	*ptr++ = virt_to_phys(cpu_do_resume);
 
@@ -42,7 +41,7 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	struct mm_struct *mm = current->active_mm;
 	int ret;
 
-	if (!suspend_pgd)
+	if (!idmap_pgd)
 		return -EINVAL;
 
 	/*
@@ -59,14 +58,3 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 
 	return ret;
 }
-
-static int __init cpu_suspend_init(void)
-{
-	suspend_pgd = pgd_alloc(&init_mm);
-	if (suspend_pgd) {
-		unsigned long addr = virt_to_phys(cpu_resume_mmu);
-		identity_mapping_add(suspend_pgd, addr, addr + SECTION_SIZE);
-	}
-	return suspend_pgd ? 0 : -ENOMEM;
-}
-core_initcall(cpu_suspend_init);

arch/arm/kernel/swp_emulate.c

@@ -25,6 +25,7 @@
 #include <linux/syscalls.h>
 #include <linux/perf_event.h>
 
+#include <asm/opcodes.h>
 #include <asm/traps.h>
 #include <asm/uaccess.h>
 
@@ -185,6 +186,21 @@ static int swp_handler(struct pt_regs *regs, unsigned int instr)
 
 	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, regs->ARM_pc);
 
+	res = arm_check_condition(instr, regs->ARM_cpsr);
+	switch (res) {
+	case ARM_OPCODE_CONDTEST_PASS:
+		break;
+	case ARM_OPCODE_CONDTEST_FAIL:
+		/* Condition failed - return to next instruction */
+		regs->ARM_pc += 4;
+		return 0;
+	case ARM_OPCODE_CONDTEST_UNCOND:
+		/* If unconditional encoding - not a SWP, undef */
+		return -EFAULT;
+	default:
+		return -EINVAL;
+	}
+
 	if (current->pid != previous_pid) {
 		pr_debug("\"%s\" (%ld) uses deprecated SWP{B} instruction\n",
 			 current->comm, (unsigned long)current->pid);

arch/arm/kernel/tcm.c

@@ -180,9 +180,9 @@ static int __init setup_tcm_bank(u8 type, u8 bank, u8 banks,
  */
 void __init tcm_init(void)
 {
-	u32 tcm_status = read_cpuid_tcmstatus();
-	u8 dtcm_banks = (tcm_status >> 16) & 0x03;
-	u8 itcm_banks = (tcm_status & 0x03);
+	u32 tcm_status;
+	u8 dtcm_banks;
+	u8 itcm_banks;
 	size_t dtcm_code_sz = &__edtcm_data - &__sdtcm_data;
 	size_t itcm_code_sz = &__eitcm_text - &__sitcm_text;
 	char *start;
@@ -191,6 +191,22 @@ void __init tcm_init(void)
 	int ret;
 	int i;
 
+	/*
+	 * Prior to ARMv5 there is no TCM, and trying to read the status
+	 * register will hang the processor.
+	 */
+	if (cpu_architecture() < CPU_ARCH_ARMv5) {
+		if (dtcm_code_sz || itcm_code_sz)
+			pr_info("CPU TCM: %u bytes of DTCM and %u bytes of "
+				"ITCM code compiled in, but no TCM present "
+				"in pre-v5 CPU\n", dtcm_code_sz, itcm_code_sz);
+		return;
+	}
+
+	tcm_status = read_cpuid_tcmstatus();
+	dtcm_banks = (tcm_status >> 16) & 0x03;
+	itcm_banks = (tcm_status & 0x03);
+
 	/* Values greater than 2 for D/ITCM banks are "reserved" */
 	if (dtcm_banks > 2)
 		dtcm_banks = 0;

arch/arm/kernel/vmlinux.lds.S

@@ -13,6 +13,12 @@
 	*(.proc.info.init)						\
 	VMLINUX_SYMBOL(__proc_info_end) = .;
 
+#define IDMAP_TEXT							\
+	ALIGN_FUNCTION();						\
+	VMLINUX_SYMBOL(__idmap_text_start) = .;				\
+	*(.idmap.text)							\
+	VMLINUX_SYMBOL(__idmap_text_end) = .;
+
 #ifdef CONFIG_HOTPLUG_CPU
 #define ARM_CPU_DISCARD(x)
 #define ARM_CPU_KEEP(x)		x
@@ -92,6 +98,7 @@ SECTIONS
 			SCHED_TEXT
 			LOCK_TEXT
 			KPROBES_TEXT
+			IDMAP_TEXT
 #ifdef CONFIG_MMU
 			*(.fixup)
 #endif

arch/arm/lib/Makefile

@@ -13,7 +13,8 @@ lib-y		:= backtrace.o changebit.o csumipv6.o csumpartial.o   \
 		   testchangebit.o testclearbit.o testsetbit.o        \
 		   ashldi3.o ashrdi3.o lshrdi3.o muldi3.o             \
 		   ucmpdi2.o lib1funcs.o div64.o                      \
-		   io-readsb.o io-writesb.o io-readsl.o io-writesl.o
+		   io-readsb.o io-writesb.o io-readsl.o io-writesl.o  \
+		   call_with_stack.o
 
 mmu-y	:= clear_user.o copy_page.o getuser.o putuser.o
 

arch/arm/mach-netx/include/mach/vmalloc.h → arch/arm/lib/call_with_stack.S

 /*
- *  arch/arm/mach-netx/include/mach/vmalloc.h
+ * arch/arm/lib/call_with_stack.S
  *
- * Copyright (C) 2005 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
+ * Copyright (C) 2011 ARM Ltd.
+ * Written by Will Deacon <will.deacon@arm.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.
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
  *
  * This program is distributed in the hope that it will be useful,
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
@@ -16,4 +17,28 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
-#define VMALLOC_END       0xd0000000UL
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+ * void call_with_stack(void (*fn)(void *), void *arg, void *sp)
+ *
+ * Change the stack to that pointed at by sp, then invoke fn(arg) with
+ * the new stack.
+ */
+ENTRY(call_with_stack)
+	str	sp, [r2, #-4]!
+	str	lr, [r2, #-4]!
+
+	mov	sp, r2
+	mov	r2, r0
+	mov	r0, r1
+
+	adr	lr, BSYM(1f)
+	mov	pc, r2
+
+1:	ldr	lr, [sp]
+	ldr	sp, [sp, #4]
+	mov	pc, lr
+ENDPROC(call_with_stack)

arch/arm/mach-at91/Kconfig

@@ -3,6 +3,12 @@ if ARCH_AT91
 config HAVE_AT91_DATAFLASH_CARD
 	bool
 
+config HAVE_AT91_DBGU0
+	bool
+
+config HAVE_AT91_DBGU1
+	bool
+
 config HAVE_AT91_USART3
 	bool
 
@@ -21,12 +27,14 @@ config ARCH_AT91RM9200
 	bool "AT91RM9200"
 	select CPU_ARM920T
 	select GENERIC_CLOCKEVENTS
+	select HAVE_AT91_DBGU0
 	select HAVE_AT91_USART3
 
 config ARCH_AT91SAM9260
 	bool "AT91SAM9260 or AT91SAM9XE"
 	select CPU_ARM926T
 	select GENERIC_CLOCKEVENTS
+	select HAVE_AT91_DBGU0
 	select HAVE_AT91_USART3
 	select HAVE_AT91_USART4
 	select HAVE_AT91_USART5
@@ -37,11 +45,13 @@ config ARCH_AT91SAM9261
 	select CPU_ARM926T
 	select GENERIC_CLOCKEVENTS
 	select HAVE_FB_ATMEL
+	select HAVE_AT91_DBGU0
 
 config ARCH_AT91SAM9G10
 	bool "AT91SAM9G10"
 	select CPU_ARM926T
 	select GENERIC_CLOCKEVENTS
+	select HAVE_AT91_DBGU0
 	select HAVE_FB_ATMEL
 
 config ARCH_AT91SAM9263
@@ -50,6 +60,7 @@ config ARCH_AT91SAM9263
 	select GENERIC_CLOCKEVENTS
 	select HAVE_FB_ATMEL
 	select HAVE_NET_MACB
+	select HAVE_AT91_DBGU1
 
 config ARCH_AT91SAM9RL
 	bool "AT91SAM9RL"
@@ -57,11 +68,13 @@ config ARCH_AT91SAM9RL
 	select GENERIC_CLOCKEVENTS
 	select HAVE_AT91_USART3
 	select HAVE_FB_ATMEL
+	select HAVE_AT91_DBGU0
 
 config ARCH_AT91SAM9G20
 	bool "AT91SAM9G20"
 	select CPU_ARM926T
 	select GENERIC_CLOCKEVENTS
+	select HAVE_AT91_DBGU0
 	select HAVE_AT91_USART3
 	select HAVE_AT91_USART4
 	select HAVE_AT91_USART5
@@ -74,6 +87,7 @@ config ARCH_AT91SAM9G45
 	select HAVE_AT91_USART3
 	select HAVE_FB_ATMEL
 	select HAVE_NET_MACB
+	select HAVE_AT91_DBGU1
 
 config ARCH_AT91CAP9
 	bool "AT91CAP9"
@@ -81,6 +95,7 @@ config ARCH_AT91CAP9
 	select GENERIC_CLOCKEVENTS
 	select HAVE_FB_ATMEL
 	select HAVE_NET_MACB
+	select HAVE_AT91_DBGU1
 
 config ARCH_AT91X40
 	bool "AT91x40"
@@ -510,8 +525,13 @@ config AT91_TIMER_HZ
 choice
 	prompt "Select a UART for early kernel messages"
 
-config AT91_EARLY_DBGU
-	bool "DBGU"
+config AT91_EARLY_DBGU0
+	bool "DBGU on rm9200, 9260/9g20, 9261/9g10 and 9rl"
+	depends on HAVE_AT91_DBGU0
+
+config AT91_EARLY_DBGU1
+	bool "DBGU on 9263, 9g45 and cap9"
+	depends on HAVE_AT91_DBGU1
 
 config AT91_EARLY_USART0
 	bool "USART0"

arch/arm/mach-at91/at91cap9.c

@@ -13,7 +13,6 @@
  */
 
 #include <linux/module.h>
-#include <linux/pm.h>
 
 #include <asm/irq.h>
 #include <asm/mach/arch.h>
@@ -23,11 +22,11 @@
 #include <mach/at91cap9.h>
 #include <mach/at91_pmc.h>
 #include <mach/at91_rstc.h>
-#include <mach/at91_shdwc.h>
 
 #include "soc.h"
 #include "generic.h"
 #include "clock.h"
+#include "sam9_smc.h"
 
 /* --------------------------------------------------------------------
  *  Clocks
@@ -137,7 +136,7 @@ static struct clk pwm_clk = {
 	.type		= CLK_TYPE_PERIPHERAL,
 };
 static struct clk macb_clk = {
-	.name		= "macb_clk",
+	.name		= "pclk",
 	.pmc_mask	= 1 << AT91CAP9_ID_EMAC,
 	.type		= CLK_TYPE_PERIPHERAL,
 };
@@ -210,6 +209,8 @@ static struct clk *periph_clocks[] __initdata = {
 };
 
 static struct clk_lookup periph_clocks_lookups[] = {
+	/* One additional fake clock for macb_hclk */
+	CLKDEV_CON_ID("hclk", &macb_clk),
 	CLKDEV_CON_DEV_ID("hclk", "atmel_usba_udc", &utmi_clk),
 	CLKDEV_CON_DEV_ID("pclk", "atmel_usba_udc", &udphs_clk),
 	CLKDEV_CON_DEV_ID("mci_clk", "at91_mci.0", &mmc0_clk),
@@ -221,6 +222,10 @@ static struct clk_lookup periph_clocks_lookups[] = {
 	CLKDEV_CON_DEV_ID("pclk", "ssc.1", &ssc1_clk),
 	/* fake hclk clock */
 	CLKDEV_CON_DEV_ID("hclk", "at91_ohci", &ohci_clk),
+	CLKDEV_CON_ID("pioA", &pioABCD_clk),
+	CLKDEV_CON_ID("pioB", &pioABCD_clk),
+	CLKDEV_CON_ID("pioC", &pioABCD_clk),
+	CLKDEV_CON_ID("pioD", &pioABCD_clk),
 };
 
 static struct clk_lookup usart_clocks_lookups[] = {
@@ -293,37 +298,27 @@ void __init at91cap9_set_console_clock(int id)
  *  GPIO
  * -------------------------------------------------------------------- */
 
-static struct at91_gpio_bank at91cap9_gpio[] = {
+static struct at91_gpio_bank at91cap9_gpio[] __initdata = {
 	{
 		.id		= AT91CAP9_ID_PIOABCD,
-		.offset		= AT91_PIOA,
-		.clock		= &pioABCD_clk,
+		.regbase	= AT91CAP9_BASE_PIOA,
 	}, {
 		.id		= AT91CAP9_ID_PIOABCD,
-		.offset		= AT91_PIOB,
-		.clock		= &pioABCD_clk,
+		.regbase	= AT91CAP9_BASE_PIOB,
 	}, {
 		.id		= AT91CAP9_ID_PIOABCD,
-		.offset		= AT91_PIOC,
-		.clock		= &pioABCD_clk,
+		.regbase	= AT91CAP9_BASE_PIOC,
 	}, {
 		.id		= AT91CAP9_ID_PIOABCD,
-		.offset		= AT91_PIOD,
-		.clock		= &pioABCD_clk,
+		.regbase	= AT91CAP9_BASE_PIOD,
 	}
 };
 
-static void at91cap9_reset(void)
+static void at91cap9_restart(char mode, const char *cmd)
 {
 	at91_sys_write(AT91_RSTC_CR, AT91_RSTC_KEY | AT91_RSTC_PROCRST | AT91_RSTC_PERRST);
 }
 
-static void at91cap9_poweroff(void)
-{
-	at91_sys_write(AT91_SHDW_CR, AT91_SHDW_KEY | AT91_SHDW_SHDW);
-}
-
-
 /* --------------------------------------------------------------------
  *  AT91CAP9 processor initialization
  * -------------------------------------------------------------------- */
@@ -333,10 +328,16 @@ static void __init at91cap9_map_io(void)
 	at91_init_sram(0, AT91CAP9_SRAM_BASE, AT91CAP9_SRAM_SIZE);
 }
 
+static void __init at91cap9_ioremap_registers(void)
+{
+	at91_ioremap_shdwc(AT91CAP9_BASE_SHDWC);
+	at91sam926x_ioremap_pit(AT91CAP9_BASE_PIT);
+	at91sam9_ioremap_smc(0, AT91CAP9_BASE_SMC);
+}
+
 static void __init at91cap9_initialize(void)
 {
-	at91_arch_reset = at91cap9_reset;
-	pm_power_off = at91cap9_poweroff;
+	arm_pm_restart = at91cap9_restart;
 	at91_extern_irq = (1 << AT91CAP9_ID_IRQ0) | (1 << AT91CAP9_ID_IRQ1);
 
 	/* Register GPIO subsystem */
@@ -394,6 +395,7 @@ static unsigned int at91cap9_default_irq_priority[NR_AIC_IRQS] __initdata = {
 struct at91_init_soc __initdata at91cap9_soc = {
 	.map_io = at91cap9_map_io,
 	.default_irq_priority = at91cap9_default_irq_priority,
+	.ioremap_registers = at91cap9_ioremap_registers,
 	.register_clocks = at91cap9_register_clocks,
 	.init = at91cap9_initialize,
 };

arch/arm/mach-at91/at91cap9_devices.c

@@ -76,7 +76,7 @@ void __init at91_add_device_usbh(struct at91_usbh_data *data)
 
 	/* Enable VBus control for UHP ports */
 	for (i = 0; i < data->ports; i++) {
-		if (data->vbus_pin[i])
+		if (gpio_is_valid(data->vbus_pin[i]))
 			at91_set_gpio_output(data->vbus_pin[i], 0);
 	}
 
@@ -179,7 +179,7 @@ void __init at91_add_device_usba(struct usba_platform_data *data)
 	usba_udc_data.pdata.num_ep = ARRAY_SIZE(usba_udc_ep);
 	memcpy(usba_udc_data.ep, usba_udc_ep, sizeof(usba_udc_ep));
 
-	if (data && data->vbus_pin > 0) {
+	if (data && gpio_is_valid(data->vbus_pin)) {
 		at91_set_gpio_input(data->vbus_pin, 0);
 		at91_set_deglitch(data->vbus_pin, 1);
 		usba_udc_data.pdata.vbus_pin = data->vbus_pin;
@@ -200,7 +200,7 @@ void __init at91_add_device_usba(struct usba_platform_data *data) {}
 
 #if defined(CONFIG_MACB) || defined(CONFIG_MACB_MODULE)
 static u64 eth_dmamask = DMA_BIT_MASK(32);
-static struct at91_eth_data eth_data;
+static struct macb_platform_data eth_data;
 
 static struct resource eth_resources[] = {
 	[0] = {
@@ -227,12 +227,12 @@ static struct platform_device at91cap9_eth_device = {
 	.num_resources	= ARRAY_SIZE(eth_resources),
 };
 
-void __init at91_add_device_eth(struct at91_eth_data *data)
+void __init at91_add_device_eth(struct macb_platform_data *data)
 {
 	if (!data)
 		return;
 
-	if (data->phy_irq_pin) {
+	if (gpio_is_valid(data->phy_irq_pin)) {
 		at91_set_gpio_input(data->phy_irq_pin, 0);
 		at91_set_deglitch(data->phy_irq_pin, 1);
 	}
@@ -264,7 +264,7 @@ void __init at91_add_device_eth(struct at91_eth_data *data)
 	platform_device_register(&at91cap9_eth_device);
 }
 #else
-void __init at91_add_device_eth(struct at91_eth_data *data) {}
+void __init at91_add_device_eth(struct macb_platform_data *data) {}
 #endif
 
 
@@ -332,13 +332,13 @@ void __init at91_add_device_mmc(short mmc_id, struct at91_mmc_data *data)
 		return;
 
 	/* input/irq */
-	if (data->det_pin) {
+	if (gpio_is_valid(data->det_pin)) {
 		at91_set_gpio_input(data->det_pin, 1);
 		at91_set_deglitch(data->det_pin, 1);
 	}
-	if (data->wp_pin)
+	if (gpio_is_valid(data->wp_pin))
 		at91_set_gpio_input(data->wp_pin, 1);
-	if (data->vcc_pin)
+	if (gpio_is_valid(data->vcc_pin))
 		at91_set_gpio_output(data->vcc_pin, 0);
 
 	if (mmc_id == 0) {		/* MCI0 */
@@ -398,8 +398,8 @@ static struct resource nand_resources[] = {
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
-		.start	= AT91_BASE_SYS + AT91_ECC,
-		.end	= AT91_BASE_SYS + AT91_ECC + SZ_512 - 1,
+		.start	= AT91CAP9_BASE_ECC,
+		.end	= AT91CAP9_BASE_ECC + SZ_512 - 1,
 		.flags	= IORESOURCE_MEM,
 	}
 };
@@ -425,15 +425,15 @@ void __init at91_add_device_nand(struct atmel_nand_data *data)
 	at91_sys_write(AT91_MATRIX_EBICSA, csa | AT91_MATRIX_EBI_CS3A_SMC_SMARTMEDIA);
 
 	/* enable pin */
-	if (data->enable_pin)
+	if (gpio_is_valid(data->enable_pin))
 		at91_set_gpio_output(data->enable_pin, 1);
 
 	/* ready/busy pin */
-	if (data->rdy_pin)
+	if (gpio_is_valid(data->rdy_pin))
 		at91_set_gpio_input(data->rdy_pin, 1);
 
 	/* card detect pin */
-	if (data->det_pin)
+	if (gpio_is_valid(data->det_pin))
 		at91_set_gpio_input(data->det_pin, 1);
 
 	nand_data = *data;
@@ -670,8 +670,8 @@ static void __init at91_add_device_tc(void) { }
 
 static struct resource rtt_resources[] = {
 	{
-		.start	= AT91_BASE_SYS + AT91_RTT,
-		.end	= AT91_BASE_SYS + AT91_RTT + SZ_16 - 1,
+		.start	= AT91CAP9_BASE_RTT,
+		.end	= AT91CAP9_BASE_RTT + SZ_16 - 1,
 		.flags	= IORESOURCE_MEM,
 	}
 };
@@ -694,10 +694,19 @@ static void __init at91_add_device_rtt(void)
  * -------------------------------------------------------------------- */
 
 #if defined(CONFIG_AT91SAM9X_WATCHDOG) || defined(CONFIG_AT91SAM9X_WATCHDOG_MODULE)
+static struct resource wdt_resources[] = {
+	{
+		.start	= AT91CAP9_BASE_WDT,
+		.end	= AT91CAP9_BASE_WDT + SZ_16 - 1,
+		.flags	= IORESOURCE_MEM,
+	}
+};
+
 static struct platform_device at91cap9_wdt_device = {
 	.name		= "at91_wdt",
 	.id		= -1,
-	.num_resources	= 0,
+	.resource	= wdt_resources,
+	.num_resources	= ARRAY_SIZE(wdt_resources),
 };
 
 static void __init at91_add_device_watchdog(void)
@@ -807,7 +816,7 @@ void __init at91_add_device_ac97(struct ac97c_platform_data *data)
 	at91_set_A_periph(AT91_PIN_PA9, 0);	/* AC97RX */
 
 	/* reset */
-	if (data->reset_pin)
+	if (gpio_is_valid(data->reset_pin))
 		at91_set_gpio_output(data->reset_pin, 0);
 
 	ac97_data = *data;
@@ -1021,8 +1030,8 @@ void __init at91_add_device_ssc(unsigned id, unsigned pins) {}
 #if defined(CONFIG_SERIAL_ATMEL)
 static struct resource dbgu_resources[] = {
 	[0] = {
-		.start	= AT91_BASE_SYS + AT91_DBGU,
-		.end	= AT91_BASE_SYS + AT91_DBGU + SZ_512 - 1,
+		.start	= AT91CAP9_BASE_DBGU,
+		.end	= AT91CAP9_BASE_DBGU + SZ_512 - 1,
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {

arch/arm/mach-at91/at91rm9200_time.c

@@ -32,6 +32,8 @@ static unsigned long last_crtr;
 static u32 irqmask;
 static struct clock_event_device clkevt;
 
+#define RM9200_TIMER_LATCH	((AT91_SLOW_CLOCK + HZ/2) / HZ)
+
 /*
  * The ST_CRTR is updated asynchronously to the master clock ... but
  * the updates as seen by the CPU don't seem to be strictly monotonic.
@@ -74,8 +76,8 @@ static irqreturn_t at91rm9200_timer_interrupt(int irq, void *dev_id)
 	if (sr & AT91_ST_PITS) {
 		u32	crtr = read_CRTR();
 
-		while (((crtr - last_crtr) & AT91_ST_CRTV) >= LATCH) {
-			last_crtr += LATCH;
+		while (((crtr - last_crtr) & AT91_ST_CRTV) >= RM9200_TIMER_LATCH) {
+			last_crtr += RM9200_TIMER_LATCH;
 			clkevt.event_handler(&clkevt);
 		}
 		return IRQ_HANDLED;
@@ -116,7 +118,7 @@ clkevt32k_mode(enum clock_event_mode mode, struct clock_event_device *dev)
 	case CLOCK_EVT_MODE_PERIODIC:
 		/* PIT for periodic irqs; fixed rate of 1/HZ */
 		irqmask = AT91_ST_PITS;
-		at91_sys_write(AT91_ST_PIMR, LATCH);
+		at91_sys_write(AT91_ST_PIMR, RM9200_TIMER_LATCH);
 		break;
 	case CLOCK_EVT_MODE_ONESHOT:
 		/* ALM for oneshot irqs, set by next_event()

arch/arm/mach-at91/at91sam9_alt_reset.S

@@ -14,20 +14,15 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/system.h>
 #include <mach/hardware.h>
 #include <mach/at91sam9_sdramc.h>
 #include <mach/at91_rstc.h>
 
 			.arm
 
-			.globl	at91sam9_alt_reset
+			.globl	at91sam9_alt_restart
 
-at91sam9_alt_reset:	mrc	p15, 0, r0, c1, c0, 0
-			orr	r0, r0, #CR_I
-			mcr	p15, 0, r0, c1, c0, 0		@ enable I-cache
-
-			ldr	r0, .at91_va_base_sdramc	@ preload constants
+at91sam9_alt_restart:	ldr	r0, .at91_va_base_sdramc	@ preload constants
 			ldr	r1, .at91_va_base_rstc_cr
 
 			mov	r2, #1