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

Pull more ARM updates from Russell King.

This got a fair number of conflicts with the <asm/system.h> split, but
also with some other sparse-irq and header file include cleanups. They
all looked pretty trivial, though.

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (59 commits)
ARM: fix Kconfig warning for HAVE_BPF_JIT
ARM: 7361/1: provide XIP_VIRT_ADDR for no-MMU builds
ARM: 7349/1: integrator: convert to sparse irqs
ARM: 7259/3: net: JIT compiler for packet filters
ARM: 7334/1: add jump label support
ARM: 7333/2: jump label: detect %c support for ARM
ARM: 7338/1: add support for early console output via semihosting
ARM: use set_current_blocked() and block_sigmask()
ARM: exec: remove redundant set_fs(USER_DS)
ARM: 7332/1: extract out code patch function from kprobes
ARM: 7331/1: extract out insn generation code from ftrace
ARM: 7330/1: ftrace: use canonical Thumb-2 wide instruction format
ARM: 7351/1: ftrace: remove useless memory checks
ARM: 7316/1: kexec: EOI active and mask all interrupts in kexec crash path
ARM: Versatile Express: add NO_IOPORT
ARM: get rid of asm/irq.h in asm/prom.h
ARM: 7319/1: Print debug info for SIGBUS in user faults
ARM: 7318/1: gic: refactor irq_start assignment
ARM: 7317/1: irq: avoid NULL check in for_each_irq_desc loop
ARM: 7315/1: perf: add support for the Cortex-A7 PMU
...

arch/arm/Kconfig

···
 	select SYS_SUPPORTS_APM_EMULATION
 	select GENERIC_ATOMIC64 if (CPU_V6 || !CPU_32v6K || !AEABI)
 	select HAVE_OPROFILE if (HAVE_PERF_EVENTS)
+	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
 	select HAVE_ARCH_KGDB
 	select HAVE_KPROBES if !XIP_KERNEL
 	select HAVE_KRETPROBES if (HAVE_KPROBES)
···
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZO
 	select HAVE_KERNEL_LZMA
+	select HAVE_KERNEL_XZ
 	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select PERF_USE_VMALLOC
···
 	select HAVE_HW_BREAKPOINT if (PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7))
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_GENERIC_HARDIRQS
-	select HAVE_SPARSE_IRQ
 	select GENERIC_IRQ_SHOW
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select GENERIC_PCI_IOMAP
+	select HAVE_BPF_JIT if NET
 	help
 	  The ARM series is a line of low-power-consumption RISC chip designs
 	  licensed by ARM Ltd and targeted at embedded applications and
···
 	bool
 
 config SYS_SUPPORTS_APM_EMULATION
-	bool
-
-config HAVE_SCHED_CLOCK
 	bool
 
 config GENERIC_GPIO
···
 	select PLAT_VERSATILE
 	select PLAT_VERSATILE_FPGA_IRQ
 	select NEED_MACH_MEMORY_H
+	select SPARSE_IRQ
 	help
 	  Support for ARM's Integrator platform.
 
···
 	select HAVE_CLK
 	select HAVE_PATA_PLATFORM
 	select ICST
+	select NO_IOPORT
 	select PLAT_VERSATILE
 	select PLAT_VERSATILE_CLCD
 	help
···
 	select GENERIC_CLOCKEVENTS
 	select HAVE_ARM_SCU
 	select HAVE_SMP
+	select SPARSE_IRQ
 	select USE_OF
 	help
 	  Support for the Calxeda Highbank SoC based boards.
···
 	select CLKDEV_LOOKUP
 	select CLKSRC_MMIO
 	select GENERIC_IRQ_CHIP
-	select HAVE_SCHED_CLOCK
 	select MULTI_IRQ_HANDLER
 	help
 	  Support for Freescale MXC/iMX-based family of processors
···
 	select CPU_XSCALE
 	select GENERIC_GPIO
 	select GENERIC_CLOCKEVENTS
-	select HAVE_SCHED_CLOCK
 	select MIGHT_HAVE_PCI
 	select DMABOUNCE if PCI
 	help
···
 	select CLKDEV_LOOKUP
 	select GENERIC_CLOCKEVENTS
 	select GPIO_PXA
-	select HAVE_SCHED_CLOCK
 	select TICK_ONESHOT
 	select PLAT_PXA
 	select SPARSE_IRQ
···
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_GPIO
 	select HAVE_CLK
-	select HAVE_SCHED_CLOCK
 	select HAVE_SMP
 	select MIGHT_HAVE_CACHE_L2X0
 	select ARCH_HAS_CPUFREQ
···
 	select DW_APB_TIMER
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_GPIO
-	select HAVE_SCHED_CLOCK
 	select HAVE_TCM
 	select NO_IOPORT
 	select SPARSE_IRQ
···
 	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_CLOCKEVENTS
 	select GPIO_PXA
-	select HAVE_SCHED_CLOCK
 	select TICK_ONESHOT
 	select PLAT_PXA
 	select SPARSE_IRQ
···
 	select CPU_FREQ
 	select GENERIC_CLOCKEVENTS
 	select CLKDEV_LOOKUP
-	select HAVE_SCHED_CLOCK
 	select TICK_ONESHOT
 	select ARCH_REQUIRE_GPIOLIB
 	select HAVE_IDE
···
 	select CLKSRC_MMIO
 	select HAVE_S3C2410_WATCHDOG if WATCHDOG
 	select GENERIC_CLOCKEVENTS
-	select HAVE_SCHED_CLOCK
 	select HAVE_S3C2410_I2C if I2C
 	select HAVE_S3C_RTC if RTC_CLASS
 	help
···
 	select CLKSRC_MMIO
 	select ARCH_HAS_CPUFREQ
 	select GENERIC_CLOCKEVENTS
-	select HAVE_SCHED_CLOCK
 	select HAVE_S3C2410_I2C if I2C
 	select HAVE_S3C_RTC if RTC_CLASS
 	select HAVE_S3C2410_WATCHDOG if WATCHDOG
···
 	depends on MMU
 	select CLKSRC_MMIO
 	select CPU_ARM926T
-	select HAVE_SCHED_CLOCK
 	select HAVE_TCM
 	select ARM_AMBA
 	select ARM_PATCH_PHYS_VIRT
···
 	select ARCH_HAS_CPUFREQ
 	select CLKSRC_MMIO
 	select GENERIC_CLOCKEVENTS
-	select HAVE_SCHED_CLOCK
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	help
 	  Support for TI's OMAP platform (OMAP1/2/3/4).
···
 config PLAT_IOP
 	bool
 	select GENERIC_CLOCKEVENTS
-	select HAVE_SCHED_CLOCK
 
 config PLAT_ORION
 	bool
 	select CLKSRC_MMIO
 	select GENERIC_IRQ_CHIP
-	select HAVE_SCHED_CLOCK
 
 config PLAT_PXA
 	bool

arch/arm/Kconfig.debug

···
 		  Note that the system will appear to hang during boot if there
 		  is nothing connected to read from the DCC.
 
+	config DEBUG_SEMIHOSTING
+		bool "Kernel low-level debug output via semihosting I"
+		help
+		  Semihosting enables code running on an ARM target to use
+		  the I/O facilities on a host debugger/emulator through a
+		  simple SVC calls. The host debugger or emulator must have
+		  semihosting enabled for the special svc call to be trapped
+		  otherwise the kernel will crash.
+
+		  This is known to work with OpenOCD, as wellas
+		  ARM's Fast Models, or any other controlling environment
+		  that implements semihosting.
+
+		  For more details about semihosting, please see
+		  chapter 8 of DUI0203I_rvct_developer_guide.pdf from ARM Ltd.
+
 endchoice
 
 config EARLY_PRINTK

arch/arm/Makefile

···
 
 # If we have a machine-specific directory, then include it in the build.
 core-y				+= arch/arm/kernel/ arch/arm/mm/ arch/arm/common/
+core-y				+= arch/arm/net/
 core-y				+= $(machdirs) $(platdirs)
 
 drivers-$(CONFIG_OPROFILE)      += arch/arm/oprofile/

arch/arm/boot/compressed/.gitignore

···
+ashldi3.S
 font.c
 lib1funcs.S
 piggy.gzip
 piggy.lzo
 piggy.lzma
+piggy.xzkern
 vmlinux
 vmlinux.lds
 

arch/arm/boot/compressed/Makefile

···
 suffix_$(CONFIG_KERNEL_GZIP) = gzip
 suffix_$(CONFIG_KERNEL_LZO)  = lzo
 suffix_$(CONFIG_KERNEL_LZMA) = lzma
+suffix_$(CONFIG_KERNEL_XZ)   = xzkern
 
 # Borrowed libfdt files for the ATAG compatibility mode
 
···
 
 targets       := vmlinux vmlinux.lds \
 		 piggy.$(suffix_y) piggy.$(suffix_y).o \
-		 lib1funcs.o lib1funcs.S font.o font.c head.o misc.o $(OBJS)
+		 lib1funcs.o lib1funcs.S ashldi3.o ashldi3.S \
+		 font.o font.c head.o misc.o $(OBJS)
 
 # Make sure files are removed during clean
-extra-y       += piggy.gzip piggy.lzo piggy.lzma lib1funcs.S $(libfdt) $(libfdt_hdrs)
+extra-y       += piggy.gzip piggy.lzo piggy.lzma piggy.xzkern \
+		 lib1funcs.S ashldi3.S $(libfdt) $(libfdt_hdrs)
 
 ifeq ($(CONFIG_FUNCTION_TRACER),y)
 ORIG_CFLAGS := $(KBUILD_CFLAGS)
···
 $(obj)/lib1funcs.S: $(srctree)/arch/$(SRCARCH)/lib/lib1funcs.S
 	$(call cmd,shipped)
 
+# For __aeabi_llsl
+ashldi3 = $(obj)/ashldi3.o
+
+$(obj)/ashldi3.S: $(srctree)/arch/$(SRCARCH)/lib/ashldi3.S
+	$(call cmd,shipped)
+
 # We need to prevent any GOTOFF relocs being used with references
 # to symbols in the .bss section since we cannot relocate them
 # independently from the rest at run time.  This can be achieved by
···
 fi
 
 $(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/$(HEAD) $(obj)/piggy.$(suffix_y).o \
-	 	$(addprefix $(obj)/, $(OBJS)) $(lib1funcs) FORCE
+		$(addprefix $(obj)/, $(OBJS)) $(lib1funcs) $(ashldi3) FORCE
 	@$(check_for_multiple_zreladdr)
 	$(call if_changed,ld)
 	@$(check_for_bad_syms)

arch/arm/boot/compressed/decompress.c

···
 #include "../../../../lib/decompress_unlzma.c"
 #endif
 
+#ifdef CONFIG_KERNEL_XZ
+#define memmove memmove
+#define memcpy memcpy
+#include "../../../../lib/decompress_unxz.c"
+#endif
+
 int do_decompress(u8 *input, int len, u8 *output, void (*error)(char *x))
 {
 	return decompress(input, len, NULL, NULL, output, NULL, error);

arch/arm/boot/compressed/piggy.xzkern.S

···
+	.section .piggydata,#alloc
+	.globl	input_data
+input_data:
+	.incbin	"arch/arm/boot/compressed/piggy.xzkern"
+	.globl	input_data_end
+input_data_end:

arch/arm/common/gic.c

···
 	 * For primary GICs, skip over SGIs.
 	 * For secondary GICs, skip over PPIs, too.
 	 */
-	hwirq_base = 32;
-	if (gic_nr == 0) {
-		if ((irq_start & 31) > 0) {
-			hwirq_base = 16;
-			if (irq_start != -1)
-				irq_start = (irq_start & ~31) + 16;
-		}
+	if (gic_nr == 0 && (irq_start & 31) > 0) {
+		hwirq_base = 16;
+		if (irq_start != -1)
+			irq_start = (irq_start & ~31) + 16;
+	} else {
+		hwirq_base = 32;
 	}
 
 	/*

arch/arm/configs/integrator_defconfig

···
 CONFIG_NET_ETHERNET=y
 CONFIG_NET_PCI=y
 CONFIG_E100=y
+CONFIG_SMC91X=y
 # CONFIG_KEYBOARD_ATKBD is not set
 # CONFIG_SERIO_SERPORT is not set
 CONFIG_SERIAL_AMBA_PL010=y
 CONFIG_SERIAL_AMBA_PL010_CONSOLE=y
 CONFIG_FB=y
 CONFIG_FB_MODE_HELPERS=y
+CONFIG_FB_ARMCLCD=y
 CONFIG_FB_MATROX=y
 CONFIG_FB_MATROX_MILLENIUM=y
 CONFIG_FB_MATROX_MYSTIQUE=y
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_MMC=y
+CONFIG_MMC_ARMMMCI=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_PL030=y
 CONFIG_EXT2_FS=y
+CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
 CONFIG_CRAMFS=y
···
 CONFIG_NFSD=y
 CONFIG_NFSD_V3=y
 CONFIG_PARTITION_ADVANCED=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y

arch/arm/include/asm/elf.h

···
 extern unsigned long arch_randomize_brk(struct mm_struct *mm);
 #define arch_randomize_brk arch_randomize_brk
 
-extern int vectors_user_mapping(void);
-#define arch_setup_additional_pages(bprm, uses_interp) vectors_user_mapping()
-#define ARCH_HAS_SETUP_ADDITIONAL_PAGES
-
 #endif

arch/arm/include/asm/hardware/cache-l2x0.h

···
 #define L2X0_ADDR_FILTER_EN		1
 
 #ifndef __ASSEMBLY__
-extern void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask);
+extern void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask);
 #if defined(CONFIG_CACHE_L2X0) && defined(CONFIG_OF)
-extern int l2x0_of_init(__u32 aux_val, __u32 aux_mask);
+extern int l2x0_of_init(u32 aux_val, u32 aux_mask);
 #else
-static inline int l2x0_of_init(__u32 aux_val, __u32 aux_mask)
+static inline int l2x0_of_init(u32 aux_val, u32 aux_mask)
 {
 	return -ENODEV;
 }

arch/arm/include/asm/hardware/it8152.h

···
 
 #ifndef __ASM_HARDWARE_IT8152_H
 #define __ASM_HARDWARE_IT8152_H
+
+#include <mach/irqs.h>
+
 extern void __iomem *it8152_base_address;
 
 #define IT8152_IO_BASE			(it8152_base_address + 0x03e00000)

arch/arm/include/asm/irq.h

···
 #ifndef __ASM_ARM_IRQ_H
 #define __ASM_ARM_IRQ_H
 
+#define NR_IRQS_LEGACY	16
+
+#ifndef CONFIG_SPARSE_IRQ
 #include <mach/irqs.h>
+#else
+#define NR_IRQS NR_IRQS_LEGACY
+#endif
 
 #ifndef irq_canonicalize
 #define irq_canonicalize(i)	(i)
 #endif
-
-#define NR_IRQS_LEGACY	16
 
 /*
  * Use this value to indicate lack of interrupt

arch/arm/include/asm/jump_label.h

···
+#ifndef _ASM_ARM_JUMP_LABEL_H
+#define _ASM_ARM_JUMP_LABEL_H
+
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <asm/system.h>
+
+#define JUMP_LABEL_NOP_SIZE 4
+
+#ifdef CONFIG_THUMB2_KERNEL
+#define JUMP_LABEL_NOP	"nop.w"
+#else
+#define JUMP_LABEL_NOP	"nop"
+#endif
+
+static __always_inline bool arch_static_branch(struct jump_label_key *key)
+{
+	asm goto("1:\n\t"
+		 JUMP_LABEL_NOP "\n\t"
+		 ".pushsection __jump_table,  \"aw\"\n\t"
+		 ".word 1b, %l[l_yes], %c0\n\t"
+		 ".popsection\n\t"
+		 : :  "i" (key) :  : l_yes);
+
+	return false;
+l_yes:
+	return true;
+}
+
+#endif /* __KERNEL__ */
+
+typedef u32 jump_label_t;
+
+struct jump_entry {
+	jump_label_t code;
+	jump_label_t target;
+	jump_label_t key;
+};
+
+#endif

arch/arm/include/asm/mc146818rtc.h

···
 #define _ASM_MC146818RTC_H
 
 #include <linux/io.h>
-#include <mach/irqs.h>
+#include <linux/kernel.h>
+
+#define RTC_IRQ BUILD_BUG_ON(1)
 
 #ifndef RTC_PORT
 #define RTC_PORT(x)	(0x70 + (x))

arch/arm/include/asm/memory.h

···
 #define MODULES_END		(END_MEM)
 #define MODULES_VADDR		(PHYS_OFFSET)
 
+#define XIP_VIRT_ADDR(physaddr)  (physaddr)
+
 #endif /* !CONFIG_MMU */
 
 /*

arch/arm/include/asm/mmu_context.h

···
 #include <asm/cacheflush.h>
 #include <asm/cachetype.h>
 #include <asm/proc-fns.h>
+#include <asm-generic/mm_hooks.h>
 
 void __check_kvm_seq(struct mm_struct *mm);
 
···
 
 #define deactivate_mm(tsk,mm)	do { } while (0)
 #define activate_mm(prev,next)	switch_mm(prev, next, NULL)
-
-/*
- * We are inserting a "fake" vma for the user-accessible vector page so
- * gdb and friends can get to it through ptrace and /proc/<pid>/mem.
- * But we also want to remove it before the generic code gets to see it
- * during process exit or the unmapping of it would  cause total havoc.
- * (the macro is used as remove_vma() is static to mm/mmap.c)
- */
-#define arch_exit_mmap(mm) \
-do { \
-	struct vm_area_struct *high_vma = find_vma(mm, 0xffff0000); \
-	if (high_vma) { \
-		BUG_ON(high_vma->vm_next);  /* it should be last */ \
-		if (high_vma->vm_prev) \
-			high_vma->vm_prev->vm_next = NULL; \
-		else \
-			mm->mmap = NULL; \
-		rb_erase(&high_vma->vm_rb, &mm->mm_rb); \
-		mm->mmap_cache = NULL; \
-		mm->map_count--; \
-		remove_vma(high_vma); \
-	} \
-} while (0)
-
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
-				 struct mm_struct *mm)
-{
-}
 
 #endif

arch/arm/include/asm/opcodes.h

···
 #define ARM_OPCODE_CONDTEST_PASS   1
 #define ARM_OPCODE_CONDTEST_UNCOND 2
 
+
+/*
+ * Opcode byteswap helpers
+ *
+ * These macros help with converting instructions between a canonical integer
+ * format and in-memory representation, in an endianness-agnostic manner.
+ *
+ * __mem_to_opcode_*() convert from in-memory representation to canonical form.
+ * __opcode_to_mem_*() convert from canonical form to in-memory representation.
+ *
+ *
+ * Canonical instruction representation:
+ *
+ *	ARM:		0xKKLLMMNN
+ *	Thumb 16-bit:	0x0000KKLL, where KK < 0xE8
+ *	Thumb 32-bit:	0xKKLLMMNN, where KK >= 0xE8
+ *
+ * There is no way to distinguish an ARM instruction in canonical representation
+ * from a Thumb instruction (just as these cannot be distinguished in memory).
+ * Where this distinction is important, it needs to be tracked separately.
+ *
+ * Note that values in the range 0x0000E800..0xE7FFFFFF intentionally do not
+ * represent any valid Thumb-2 instruction.  For this range,
+ * __opcode_is_thumb32() and __opcode_is_thumb16() will both be false.
+ */
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+#include <linux/swab.h>
+
+#ifdef CONFIG_CPU_ENDIAN_BE8
+#define __opcode_to_mem_arm(x) swab32(x)
+#define __opcode_to_mem_thumb16(x) swab16(x)
+#define __opcode_to_mem_thumb32(x) swahb32(x)
+#else
+#define __opcode_to_mem_arm(x) ((u32)(x))
+#define __opcode_to_mem_thumb16(x) ((u16)(x))
+#define __opcode_to_mem_thumb32(x) swahw32(x)
+#endif
+
+#define __mem_to_opcode_arm(x) __opcode_to_mem_arm(x)
+#define __mem_to_opcode_thumb16(x) __opcode_to_mem_thumb16(x)
+#define __mem_to_opcode_thumb32(x) __opcode_to_mem_thumb32(x)
+
+/* Operations specific to Thumb opcodes */
+
+/* Instruction size checks: */
+#define __opcode_is_thumb32(x) ((u32)(x) >= 0xE8000000UL)
+#define __opcode_is_thumb16(x) ((u32)(x) < 0xE800UL)
+
+/* Operations to construct or split 32-bit Thumb instructions: */
+#define __opcode_thumb32_first(x) ((u16)((x) >> 16))
+#define __opcode_thumb32_second(x) ((u16)(x))
+#define __opcode_thumb32_compose(first, second) \
+	(((u32)(u16)(first) << 16) | (u32)(u16)(second))
+
+#endif /* __ASSEMBLY__ */
+
 #endif /* __ASM_ARM_OPCODES_H */

arch/arm/include/asm/page.h

···
 #define clear_page(page)	memset((void *)(page), 0, PAGE_SIZE)
 extern void copy_page(void *to, const void *from);
 
+#define __HAVE_ARCH_GATE_AREA 1
+
 #ifdef CONFIG_ARM_LPAE
 #include <asm/pgtable-3level-types.h>
 #else

arch/arm/include/asm/perf_event.h

···
 	ARM_PERF_PMU_ID_CA9,
 	ARM_PERF_PMU_ID_CA5,
 	ARM_PERF_PMU_ID_CA15,
+	ARM_PERF_PMU_ID_CA7,
 	ARM_NUM_PMU_IDS,
 };
 

arch/arm/include/asm/processor.h

···
 #define start_thread(regs,pc,sp)					\
 ({									\
 	unsigned long *stack = (unsigned long *)sp;			\
-	set_fs(USER_DS);						\
 	memset(regs->uregs, 0, sizeof(regs->uregs));			\
 	if (current->personality & ADDR_LIMIT_32BIT)			\
 		regs->ARM_cpsr = USR_MODE;				\

arch/arm/include/asm/prom.h

···
 
 #ifdef CONFIG_OF
 
-#include <asm/irq.h>
-
 extern struct machine_desc *setup_machine_fdt(unsigned int dt_phys);
 extern void arm_dt_memblock_reserve(void);
 

arch/arm/include/asm/tlbflush.h

···
 
 #define tlb_flag(f)	((always_tlb_flags & (f)) || (__tlb_flag & possible_tlb_flags & (f)))
 
+#define __tlb_op(f, insnarg, arg)					\
+	do {								\
+		if (always_tlb_flags & (f))				\
+			asm("mcr " insnarg				\
+			    : : "r" (arg) : "cc");			\
+		else if (possible_tlb_flags & (f))			\
+			asm("tst %1, %2\n\t"				\
+			    "mcrne " insnarg				\
+			    : : "r" (arg), "r" (__tlb_flag), "Ir" (f)	\
+			    : "cc");					\
+	} while (0)
+
+#define tlb_op(f, regs, arg)	__tlb_op(f, "p15, 0, %0, " regs, arg)
+#define tlb_l2_op(f, regs, arg)	__tlb_op(f, "p15, 1, %0, " regs, arg)
+
 static inline void local_flush_tlb_all(void)
 {
 	const int zero = 0;
···
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	if (tlb_flag(TLB_V3_FULL))
-		asm("mcr p15, 0, %0, c6, c0, 0" : : "r" (zero) : "cc");
-	if (tlb_flag(TLB_V4_U_FULL | TLB_V6_U_FULL))
-		asm("mcr p15, 0, %0, c8, c7, 0" : : "r" (zero) : "cc");
-	if (tlb_flag(TLB_V4_D_FULL | TLB_V6_D_FULL))
-		asm("mcr p15, 0, %0, c8, c6, 0" : : "r" (zero) : "cc");
-	if (tlb_flag(TLB_V4_I_FULL | TLB_V6_I_FULL))
-		asm("mcr p15, 0, %0, c8, c5, 0" : : "r" (zero) : "cc");
-	if (tlb_flag(TLB_V7_UIS_FULL))
-		asm("mcr p15, 0, %0, c8, c3, 0" : : "r" (zero) : "cc");
+	tlb_op(TLB_V3_FULL, "c6, c0, 0", zero);
+	tlb_op(TLB_V4_U_FULL | TLB_V6_U_FULL, "c8, c7, 0", zero);
+	tlb_op(TLB_V4_D_FULL | TLB_V6_D_FULL, "c8, c6, 0", zero);
+	tlb_op(TLB_V4_I_FULL | TLB_V6_I_FULL, "c8, c5, 0", zero);
+	tlb_op(TLB_V7_UIS_FULL, "c8, c3, 0", zero);
 
 	if (tlb_flag(TLB_BARRIER)) {
 		dsb();
···
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) {
-		if (tlb_flag(TLB_V3_FULL))
-			asm("mcr p15, 0, %0, c6, c0, 0" : : "r" (zero) : "cc");
-		if (tlb_flag(TLB_V4_U_FULL))
-			asm("mcr p15, 0, %0, c8, c7, 0" : : "r" (zero) : "cc");
-		if (tlb_flag(TLB_V4_D_FULL))
-			asm("mcr p15, 0, %0, c8, c6, 0" : : "r" (zero) : "cc");
-		if (tlb_flag(TLB_V4_I_FULL))
-			asm("mcr p15, 0, %0, c8, c5, 0" : : "r" (zero) : "cc");
+	if (possible_tlb_flags & (TLB_V3_FULL|TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) {
+		if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) {
+			tlb_op(TLB_V3_FULL, "c6, c0, 0", zero);
+			tlb_op(TLB_V4_U_FULL, "c8, c7, 0", zero);
+			tlb_op(TLB_V4_D_FULL, "c8, c6, 0", zero);
+			tlb_op(TLB_V4_I_FULL, "c8, c5, 0", zero);
+		}
+		put_cpu();
 	}
-	put_cpu();
 
-	if (tlb_flag(TLB_V6_U_ASID))
-		asm("mcr p15, 0, %0, c8, c7, 2" : : "r" (asid) : "cc");
-	if (tlb_flag(TLB_V6_D_ASID))
-		asm("mcr p15, 0, %0, c8, c6, 2" : : "r" (asid) : "cc");
-	if (tlb_flag(TLB_V6_I_ASID))
-		asm("mcr p15, 0, %0, c8, c5, 2" : : "r" (asid) : "cc");
-	if (tlb_flag(TLB_V7_UIS_ASID))
+	tlb_op(TLB_V6_U_ASID, "c8, c7, 2", asid);
+	tlb_op(TLB_V6_D_ASID, "c8, c6, 2", asid);
+	tlb_op(TLB_V6_I_ASID, "c8, c5, 2", asid);
 #ifdef CONFIG_ARM_ERRATA_720789
-		asm("mcr p15, 0, %0, c8, c3, 0" : : "r" (zero) : "cc");
+	tlb_op(TLB_V7_UIS_ASID, "c8, c3, 0", zero);
 #else
-		asm("mcr p15, 0, %0, c8, c3, 2" : : "r" (asid) : "cc");
+	tlb_op(TLB_V7_UIS_ASID, "c8, c3, 2", asid);
 #endif
 
 	if (tlb_flag(TLB_BARRIER))
···
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
-		if (tlb_flag(TLB_V3_PAGE))
-			asm("mcr p15, 0, %0, c6, c0, 0" : : "r" (uaddr) : "cc");
-		if (tlb_flag(TLB_V4_U_PAGE))
-			asm("mcr p15, 0, %0, c8, c7, 1" : : "r" (uaddr) : "cc");
-		if (tlb_flag(TLB_V4_D_PAGE))
-			asm("mcr p15, 0, %0, c8, c6, 1" : : "r" (uaddr) : "cc");
-		if (tlb_flag(TLB_V4_I_PAGE))
-			asm("mcr p15, 0, %0, c8, c5, 1" : : "r" (uaddr) : "cc");
+	if (possible_tlb_flags & (TLB_V3_PAGE|TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) &&
+	    cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
+		tlb_op(TLB_V3_PAGE, "c6, c0, 0", uaddr);
+		tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", uaddr);
+		tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", uaddr);
+		tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", uaddr);
 		if (!tlb_flag(TLB_V4_I_PAGE) && tlb_flag(TLB_V4_I_FULL))
 			asm("mcr p15, 0, %0, c8, c5, 0" : : "r" (zero) : "cc");
 	}
 
-	if (tlb_flag(TLB_V6_U_PAGE))
-		asm("mcr p15, 0, %0, c8, c7, 1" : : "r" (uaddr) : "cc");
-	if (tlb_flag(TLB_V6_D_PAGE))
-		asm("mcr p15, 0, %0, c8, c6, 1" : : "r" (uaddr) : "cc");
-	if (tlb_flag(TLB_V6_I_PAGE))
-		asm("mcr p15, 0, %0, c8, c5, 1" : : "r" (uaddr) : "cc");
-	if (tlb_flag(TLB_V7_UIS_PAGE))
+	tlb_op(TLB_V6_U_PAGE, "c8, c7, 1", uaddr);
+	tlb_op(TLB_V6_D_PAGE, "c8, c6, 1", uaddr);
+	tlb_op(TLB_V6_I_PAGE, "c8, c5, 1", uaddr);
 #ifdef CONFIG_ARM_ERRATA_720789
-		asm("mcr p15, 0, %0, c8, c3, 3" : : "r" (uaddr & PAGE_MASK) : "cc");
+	tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 3", uaddr & PAGE_MASK);
 #else
-		asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (uaddr) : "cc");
+	tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 1", uaddr);
 #endif
 
 	if (tlb_flag(TLB_BARRIER))
···
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	if (tlb_flag(TLB_V3_PAGE))
-		asm("mcr p15, 0, %0, c6, c0, 0" : : "r" (kaddr) : "cc");
-	if (tlb_flag(TLB_V4_U_PAGE))
-		asm("mcr p15, 0, %0, c8, c7, 1" : : "r" (kaddr) : "cc");
-	if (tlb_flag(TLB_V4_D_PAGE))
-		asm("mcr p15, 0, %0, c8, c6, 1" : : "r" (kaddr) : "cc");
-	if (tlb_flag(TLB_V4_I_PAGE))
-		asm("mcr p15, 0, %0, c8, c5, 1" : : "r" (kaddr) : "cc");
+	tlb_op(TLB_V3_PAGE, "c6, c0, 0", kaddr);
+	tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", kaddr);
+	tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", kaddr);
+	tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", kaddr);
 	if (!tlb_flag(TLB_V4_I_PAGE) && tlb_flag(TLB_V4_I_FULL))
 		asm("mcr p15, 0, %0, c8, c5, 0" : : "r" (zero) : "cc");
 
-	if (tlb_flag(TLB_V6_U_PAGE))
-		asm("mcr p15, 0, %0, c8, c7, 1" : : "r" (kaddr) : "cc");
-	if (tlb_flag(TLB_V6_D_PAGE))
-		asm("mcr p15, 0, %0, c8, c6, 1" : : "r" (kaddr) : "cc");
-	if (tlb_flag(TLB_V6_I_PAGE))
-		asm("mcr p15, 0, %0, c8, c5, 1" : : "r" (kaddr) : "cc");
-	if (tlb_flag(TLB_V7_UIS_PAGE))
-		asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (kaddr) : "cc");
+	tlb_op(TLB_V6_U_PAGE, "c8, c7, 1", kaddr);
+	tlb_op(TLB_V6_D_PAGE, "c8, c6, 1", kaddr);
+	tlb_op(TLB_V6_I_PAGE, "c8, c5, 1", kaddr);
+	tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 1", kaddr);
 
 	if (tlb_flag(TLB_BARRIER)) {
 		dsb();
···
 {
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
-	if (tlb_flag(TLB_DCLEAN))
-		asm("mcr	p15, 0, %0, c7, c10, 1	@ flush_pmd"
-			: : "r" (pmd) : "cc");
-
-	if (tlb_flag(TLB_L2CLEAN_FR))
-		asm("mcr	p15, 1, %0, c15, c9, 1  @ L2 flush_pmd"
-			: : "r" (pmd) : "cc");
+	tlb_op(TLB_DCLEAN, "c7, c10, 1	@ flush_pmd", pmd);
+	tlb_l2_op(TLB_L2CLEAN_FR, "c15, c9, 1  @ L2 flush_pmd", pmd);
 
 	if (tlb_flag(TLB_WB))
 		dsb();
···
 {
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
-	if (tlb_flag(TLB_DCLEAN))
-		asm("mcr	p15, 0, %0, c7, c10, 1	@ flush_pmd"
-			: : "r" (pmd) : "cc");
-
-	if (tlb_flag(TLB_L2CLEAN_FR))
-		asm("mcr	p15, 1, %0, c15, c9, 1  @ L2 flush_pmd"
-			: : "r" (pmd) : "cc");
+	tlb_op(TLB_DCLEAN, "c7, c10, 1	@ flush_pmd", pmd);
+	tlb_l2_op(TLB_L2CLEAN_FR, "c15, c9, 1  @ L2 flush_pmd", pmd);
 }
 
+#undef tlb_op
 #undef tlb_flag
 #undef always_tlb_flags
 #undef possible_tlb_flags

arch/arm/include/asm/traps.h

···
 	return in ? : __in_irqentry_text(ptr);
 }
 
-extern void __init early_trap_init(void);
+extern void __init early_trap_init(void *);
 extern void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame);
 extern void ptrace_break(struct task_struct *tsk, struct pt_regs *regs);
 

arch/arm/kernel/Makefile

···
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_ftrace.o = -pg
+CFLAGS_REMOVE_insn.o = -pg
+CFLAGS_REMOVE_patch.o = -pg
 endif
 
 CFLAGS_REMOVE_return_address.o = -pg
···
 # Object file lists.
 
 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
+		   process.o ptrace.o return_address.o sched_clock.o \
+		   setup.o signal.o stacktrace.o sys_arm.o time.o traps.o
 
 obj-$(CONFIG_DEPRECATED_PARAM_STRUCT) += compat.o
 
···
 obj-$(CONFIG_ISA_DMA)		+= dma-isa.o
 obj-$(CONFIG_PCI)		+= bios32.o isa.o
 obj-$(CONFIG_ARM_CPU_SUSPEND)	+= sleep.o suspend.o
-obj-$(CONFIG_HAVE_SCHED_CLOCK)	+= sched_clock.o
 obj-$(CONFIG_SMP)		+= smp.o smp_tlb.o
 obj-$(CONFIG_HAVE_ARM_SCU)	+= smp_scu.o
 obj-$(CONFIG_HAVE_ARM_TWD)	+= smp_twd.o
-obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
-obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
+obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o insn.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o insn.o
+obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o insn.o patch.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
-obj-$(CONFIG_KPROBES)		+= kprobes.o kprobes-common.o
+obj-$(CONFIG_KPROBES)		+= kprobes.o kprobes-common.o patch.o
 ifdef CONFIG_THUMB2_KERNEL
 obj-$(CONFIG_KPROBES)		+= kprobes-thumb.o
 else

arch/arm/kernel/debug.S

···
 
 #endif	/* CONFIG_CPU_V6 */
 
-#else
+#elif !defined(CONFIG_DEBUG_SEMIHOSTING)
 #include <mach/debug-macro.S>
 #endif	/* CONFIG_DEBUG_ICEDCC */
 
···
 
 		.ltorg
 
+#ifndef CONFIG_DEBUG_SEMIHOSTING
+
 ENTRY(printascii)
 		addruart_current r3, r1, r2
 		b	2f
···
 		mov	r0, #0
 		b	1b
 ENDPROC(printch)
+
+#else
+
+ENTRY(printascii)
+		mov	r1, r0
+		mov	r0, #0x04		@ SYS_WRITE0
+	ARM(	svc	#0x123456	)
+	THUMB(	svc	#0xab		)
+		mov	pc, lr
+ENDPROC(printascii)
+
+ENTRY(printch)
+		adr	r1, hexbuf
+		strb	r0, [r1]
+		mov	r0, #0x03		@ SYS_WRITEC
+	ARM(	svc	#0x123456	)
+	THUMB(	svc	#0xab		)
+		mov	pc, lr
+ENDPROC(printch)
+
+#endif

arch/arm/kernel/ftrace.c

···
 #include <linux/uaccess.h>
 
 #include <asm/cacheflush.h>
+#include <asm/opcodes.h>
 #include <asm/ftrace.h>
 
+#include "insn.h"
+
 #ifdef CONFIG_THUMB2_KERNEL
-#define	NOP		0xeb04f85d	/* pop.w {lr} */
+#define	NOP		0xf85deb04	/* pop.w {lr} */
 #else
 #define	NOP		0xe8bd4000	/* pop {lr} */
 #endif
···
 }
 #endif
 
-#ifdef CONFIG_THUMB2_KERNEL
-static unsigned long ftrace_gen_branch(unsigned long pc, unsigned long addr,
-				       bool link)
-{
-	unsigned long s, j1, j2, i1, i2, imm10, imm11;
-	unsigned long first, second;
-	long offset;
-
-	offset = (long)addr - (long)(pc + 4);
-	if (offset < -16777216 || offset > 16777214) {
-		WARN_ON_ONCE(1);
-		return 0;
-	}
-
-	s	= (offset >> 24) & 0x1;
-	i1	= (offset >> 23) & 0x1;
-	i2	= (offset >> 22) & 0x1;
-	imm10	= (offset >> 12) & 0x3ff;
-	imm11	= (offset >>  1) & 0x7ff;
-
-	j1 = (!i1) ^ s;
-	j2 = (!i2) ^ s;
-
-	first = 0xf000 | (s << 10) | imm10;
-	second = 0x9000 | (j1 << 13) | (j2 << 11) | imm11;
-	if (link)
-		second |= 1 << 14;
-
-	return (second << 16) | first;
-}
-#else
-static unsigned long ftrace_gen_branch(unsigned long pc, unsigned long addr,
-				       bool link)
-{
-	unsigned long opcode = 0xea000000;
-	long offset;
-
-	if (link)
-		opcode |= 1 << 24;
-
-	offset = (long)addr - (long)(pc + 8);
-	if (unlikely(offset < -33554432 || offset > 33554428)) {
-		/* Can't generate branches that far (from ARM ARM). Ftrace
-		 * doesn't generate branches outside of kernel text.
-		 */
-		WARN_ON_ONCE(1);
-		return 0;
-	}
-
-	offset = (offset >> 2) & 0x00ffffff;
-
-	return opcode | offset;
-}
-#endif
-
 static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
 {
-	return ftrace_gen_branch(pc, addr, true);
+	return arm_gen_branch_link(pc, addr);
 }
 
 static int ftrace_modify_code(unsigned long pc, unsigned long old,
-			      unsigned long new)
+			      unsigned long new, bool validate)
 {
 	unsigned long replaced;
 
-	if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE))
-		return -EFAULT;
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
+		old = __opcode_to_mem_thumb32(old);
+		new = __opcode_to_mem_thumb32(new);
+	} else {
+		old = __opcode_to_mem_arm(old);
+		new = __opcode_to_mem_arm(new);
+	}
 
-	if (replaced != old)
-		return -EINVAL;
+	if (validate) {
+		if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE))
+			return -EFAULT;
+
+		if (replaced != old)
+			return -EINVAL;
+	}
 
 	if (probe_kernel_write((void *)pc, &new, MCOUNT_INSN_SIZE))
 		return -EPERM;
···
 
 int ftrace_update_ftrace_func(ftrace_func_t func)
 {
-	unsigned long pc, old;
+	unsigned long pc;
 	unsigned long new;
 	int ret;
 
 	pc = (unsigned long)&ftrace_call;
-	memcpy(&old, &ftrace_call, MCOUNT_INSN_SIZE);
 	new = ftrace_call_replace(pc, (unsigned long)func);
 
-	ret = ftrace_modify_code(pc, old, new);
+	ret = ftrace_modify_code(pc, 0, new, false);
 
 #ifdef CONFIG_OLD_MCOUNT
 	if (!ret) {
 		pc = (unsigned long)&ftrace_call_old;
-		memcpy(&old, &ftrace_call_old, MCOUNT_INSN_SIZE);
 		new = ftrace_call_replace(pc, (unsigned long)func);
 
-		ret = ftrace_modify_code(pc, old, new);
+		ret = ftrace_modify_code(pc, 0, new, false);
 	}
 #endif
 
···
 	old = ftrace_nop_replace(rec);
 	new = ftrace_call_replace(ip, adjust_address(rec, addr));
 
-	return ftrace_modify_code(rec->ip, old, new);
+	return ftrace_modify_code(rec->ip, old, new, true);
 }
 
 int ftrace_make_nop(struct module *mod,
···
 
 	old = ftrace_call_replace(ip, adjust_address(rec, addr));
 	new = ftrace_nop_replace(rec);
-	ret = ftrace_modify_code(ip, old, new);
+	ret = ftrace_modify_code(ip, old, new, true);
 
 #ifdef CONFIG_OLD_MCOUNT
 	if (ret == -EINVAL && addr == MCOUNT_ADDR) {
···
 
 		old = ftrace_call_replace(ip, adjust_address(rec, addr));
 		new = ftrace_nop_replace(rec);
-		ret = ftrace_modify_code(ip, old, new);
+		ret = ftrace_modify_code(ip, old, new, true);
 	}
 #endif
 
···
 {
 	unsigned long caller_fn = (unsigned long) func;
 	unsigned long pc = (unsigned long) callsite;
-	unsigned long branch = ftrace_gen_branch(pc, caller_fn, false);
+	unsigned long branch = arm_gen_branch(pc, caller_fn);
 	unsigned long nop = 0xe1a00000;	/* mov r0, r0 */
 	unsigned long old = enable ? nop : branch;
 	unsigned long new = enable ? branch : nop;
 
-	return ftrace_modify_code(pc, old, new);
+	return ftrace_modify_code(pc, old, new, true);
 }
 
 static int ftrace_modify_graph_caller(bool enable)

arch/arm/kernel/head.S

···
 	str	r6, [r3]
 
 #ifdef CONFIG_DEBUG_LL
-#ifndef CONFIG_DEBUG_ICEDCC
+#if !defined(CONFIG_DEBUG_ICEDCC) && !defined(CONFIG_DEBUG_SEMIHOSTING)
 	/*
 	 * Map in IO space for serial debugging.
 	 * This allows debug messages to be output
···
 	cmp	r0, r6
 	blo	1b
 
-#else /* CONFIG_DEBUG_ICEDCC */
-	/* we don't need any serial debugging mappings for ICEDCC */
+#else /* CONFIG_DEBUG_ICEDCC || CONFIG_DEBUG_SEMIHOSTING */
+	/* we don't need any serial debugging mappings */
 	ldr	r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags
-#endif /* !CONFIG_DEBUG_ICEDCC */
+#endif
 
 #if defined(CONFIG_ARCH_NETWINDER) || defined(CONFIG_ARCH_CATS)
 	/*

arch/arm/kernel/insn.c

···
+#include <linux/kernel.h>
+#include <asm/opcodes.h>
+
+static unsigned long
+__arm_gen_branch_thumb2(unsigned long pc, unsigned long addr, bool link)
+{
+	unsigned long s, j1, j2, i1, i2, imm10, imm11;
+	unsigned long first, second;
+	long offset;
+
+	offset = (long)addr - (long)(pc + 4);
+	if (offset < -16777216 || offset > 16777214) {
+		WARN_ON_ONCE(1);
+		return 0;
+	}
+
+	s	= (offset >> 24) & 0x1;
+	i1	= (offset >> 23) & 0x1;
+	i2	= (offset >> 22) & 0x1;
+	imm10	= (offset >> 12) & 0x3ff;
+	imm11	= (offset >>  1) & 0x7ff;
+
+	j1 = (!i1) ^ s;
+	j2 = (!i2) ^ s;
+
+	first = 0xf000 | (s << 10) | imm10;
+	second = 0x9000 | (j1 << 13) | (j2 << 11) | imm11;
+	if (link)
+		second |= 1 << 14;
+
+	return __opcode_thumb32_compose(first, second);
+}
+
+static unsigned long
+__arm_gen_branch_arm(unsigned long pc, unsigned long addr, bool link)
+{
+	unsigned long opcode = 0xea000000;
+	long offset;
+
+	if (link)
+		opcode |= 1 << 24;
+
+	offset = (long)addr - (long)(pc + 8);
+	if (unlikely(offset < -33554432 || offset > 33554428)) {
+		WARN_ON_ONCE(1);
+		return 0;
+	}
+
+	offset = (offset >> 2) & 0x00ffffff;
+
+	return opcode | offset;
+}
+
+unsigned long
+__arm_gen_branch(unsigned long pc, unsigned long addr, bool link)
+{
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL))
+		return __arm_gen_branch_thumb2(pc, addr, link);
+	else
+		return __arm_gen_branch_arm(pc, addr, link);
+}

arch/arm/kernel/insn.h

···
+#ifndef __ASM_ARM_INSN_H
+#define __ASM_ARM_INSN_H
+
+static inline unsigned long
+arm_gen_nop(void)
+{
+#ifdef CONFIG_THUMB2_KERNEL
+	return 0xf3af8000; /* nop.w */
+#else
+	return 0xe1a00000; /* mov r0, r0 */
+#endif
+}
+
+unsigned long
+__arm_gen_branch(unsigned long pc, unsigned long addr, bool link);
+
+static inline unsigned long
+arm_gen_branch(unsigned long pc, unsigned long addr)
+{
+	return __arm_gen_branch(pc, addr, false);
+}
+
+static inline unsigned long
+arm_gen_branch_link(unsigned long pc, unsigned long addr)
+{
+	return __arm_gen_branch(pc, addr, true);
+}
+
+#endif

arch/arm/kernel/irq.c

···
 	local_irq_save(flags);
 
 	for_each_irq_desc(i, desc) {
-		bool affinity_broken = false;
-
-		if (!desc)
-			continue;
+		bool affinity_broken;
 
 		raw_spin_lock(&desc->lock);
 		affinity_broken = migrate_one_irq(desc);

arch/arm/kernel/jump_label.c

···
+#include <linux/kernel.h>
+#include <linux/jump_label.h>
+
+#include "insn.h"
+#include "patch.h"
+
+#ifdef HAVE_JUMP_LABEL
+
+static void __arch_jump_label_transform(struct jump_entry *entry,
+					enum jump_label_type type,
+					bool is_static)
+{
+	void *addr = (void *)entry->code;
+	unsigned int insn;
+
+	if (type == JUMP_LABEL_ENABLE)
+		insn = arm_gen_branch(entry->code, entry->target);
+	else
+		insn = arm_gen_nop();
+
+	if (is_static)
+		__patch_text(addr, insn);
+	else
+		patch_text(addr, insn);
+}
+
+void arch_jump_label_transform(struct jump_entry *entry,
+			       enum jump_label_type type)
+{
+	__arch_jump_label_transform(entry, type, false);
+}
+
+void arch_jump_label_transform_static(struct jump_entry *entry,
+				      enum jump_label_type type)
+{
+	__arch_jump_label_transform(entry, type, true);
+}
+
+#endif

arch/arm/kernel/kprobes.c

···
 #include <asm/cacheflush.h>
 
 #include "kprobes.h"
+#include "patch.h"
 
 #define MIN_STACK_SIZE(addr) 				\
 	min((unsigned long)MAX_STACK_SIZE,		\
···
 	return 0;
 }
 
-#ifdef CONFIG_THUMB2_KERNEL
-
-/*
- * For a 32-bit Thumb breakpoint spanning two memory words we need to take
- * special precautions to insert the breakpoint atomically, especially on SMP
- * systems. This is achieved by calling this arming function using stop_machine.
- */
-static int __kprobes set_t32_breakpoint(void *addr)
-{
-	((u16 *)addr)[0] = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION >> 16;
-	((u16 *)addr)[1] = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION & 0xffff;
-	flush_insns(addr, 2*sizeof(u16));
-	return 0;
-}
-
 void __kprobes arch_arm_kprobe(struct kprobe *p)
 {
-	uintptr_t addr = (uintptr_t)p->addr & ~1; /* Remove any Thumb flag */
+	unsigned int brkp;
+	void *addr;
 
-	if (!is_wide_instruction(p->opcode)) {
-		*(u16 *)addr = KPROBE_THUMB16_BREAKPOINT_INSTRUCTION;
-		flush_insns(addr, sizeof(u16));
-	} else if (addr & 2) {
-		/* A 32-bit instruction spanning two words needs special care */
-		stop_machine(set_t32_breakpoint, (void *)addr, &cpu_online_map);
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
+		/* Remove any Thumb flag */
+		addr = (void *)((uintptr_t)p->addr & ~1);
+
+		if (is_wide_instruction(p->opcode))
+			brkp = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION;
+		else
+			brkp = KPROBE_THUMB16_BREAKPOINT_INSTRUCTION;
 	} else {
-		/* Word aligned 32-bit instruction can be written atomically */
-		u32 bkp = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION;
-#ifndef __ARMEB__ /* Swap halfwords for little-endian */
-		bkp = (bkp >> 16) | (bkp << 16);
-#endif
-		*(u32 *)addr = bkp;
-		flush_insns(addr, sizeof(u32));
+		kprobe_opcode_t insn = p->opcode;
+
+		addr = p->addr;
+		brkp = KPROBE_ARM_BREAKPOINT_INSTRUCTION;
+
+		if (insn >= 0xe0000000)
+			brkp |= 0xe0000000;  /* Unconditional instruction */
+		else
+			brkp |= insn & 0xf0000000;  /* Copy condition from insn */
 	}
+
+	patch_text(addr, brkp);
 }
-
-#else /* !CONFIG_THUMB2_KERNEL */
-
-void __kprobes arch_arm_kprobe(struct kprobe *p)
-{
-	kprobe_opcode_t insn = p->opcode;
-	kprobe_opcode_t brkp = KPROBE_ARM_BREAKPOINT_INSTRUCTION;
-	if (insn >= 0xe0000000)
-		brkp |= 0xe0000000;  /* Unconditional instruction */
-	else
-		brkp |= insn & 0xf0000000;  /* Copy condition from insn */
-	*p->addr = brkp;
-	flush_insns(p->addr, sizeof(p->addr[0]));
-}
-
-#endif /* !CONFIG_THUMB2_KERNEL */
 
 /*
  * The actual disarming is done here on each CPU and synchronized using
···
 int __kprobes __arch_disarm_kprobe(void *p)
 {
 	struct kprobe *kp = p;
-#ifdef CONFIG_THUMB2_KERNEL
-	u16 *addr = (u16 *)((uintptr_t)kp->addr & ~1);
-	kprobe_opcode_t insn = kp->opcode;
-	unsigned int len;
+	void *addr = (void *)((uintptr_t)kp->addr & ~1);
 
-	if (is_wide_instruction(insn)) {
-		((u16 *)addr)[0] = insn>>16;
-		((u16 *)addr)[1] = insn;
-		len = 2*sizeof(u16);
-	} else {
-		((u16 *)addr)[0] = insn;
-		len = sizeof(u16);
-	}
-	flush_insns(addr, len);
+	__patch_text(addr, kp->opcode);
 
-#else /* !CONFIG_THUMB2_KERNEL */
-	*kp->addr = kp->opcode;
-	flush_insns(kp->addr, sizeof(kp->addr[0]));
-#endif
 	return 0;
 }
 

arch/arm/kernel/machine_kexec.c

···
 #include <linux/delay.h>
 #include <linux/reboot.h>
 #include <linux/io.h>
+#include <linux/irq.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/mmu_context.h>
···
 		cpu_relax();
 }
 
+static void machine_kexec_mask_interrupts(void)
+{
+	unsigned int i;
+	struct irq_desc *desc;
+
+	for_each_irq_desc(i, desc) {
+		struct irq_chip *chip;
+
+		chip = irq_desc_get_chip(desc);
+		if (!chip)
+			continue;
+
+		if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data))
+			chip->irq_eoi(&desc->irq_data);
+
+		if (chip->irq_mask)
+			chip->irq_mask(&desc->irq_data);
+
+		if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data))
+			chip->irq_disable(&desc->irq_data);
+	}
+}
+
 void machine_crash_shutdown(struct pt_regs *regs)
 {
 	unsigned long msecs;
···
 		printk(KERN_WARNING "Non-crashing CPUs did not react to IPI\n");
 
 	crash_save_cpu(regs, smp_processor_id());
+	machine_kexec_mask_interrupts();
 
 	printk(KERN_INFO "Loading crashdump kernel...\n");
 }

arch/arm/kernel/patch.c

···
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+#include <linux/stop_machine.h>
+
+#include <asm/cacheflush.h>
+#include <asm/smp_plat.h>
+#include <asm/opcodes.h>
+
+#include "patch.h"
+
+struct patch {
+	void *addr;
+	unsigned int insn;
+};
+
+void __kprobes __patch_text(void *addr, unsigned int insn)
+{
+	bool thumb2 = IS_ENABLED(CONFIG_THUMB2_KERNEL);
+	int size;
+
+	if (thumb2 && __opcode_is_thumb16(insn)) {
+		*(u16 *)addr = __opcode_to_mem_thumb16(insn);
+		size = sizeof(u16);
+	} else if (thumb2 && ((uintptr_t)addr & 2)) {
+		u16 first = __opcode_thumb32_first(insn);
+		u16 second = __opcode_thumb32_second(insn);
+		u16 *addrh = addr;
+
+		addrh[0] = __opcode_to_mem_thumb16(first);
+		addrh[1] = __opcode_to_mem_thumb16(second);
+
+		size = sizeof(u32);
+	} else {
+		if (thumb2)
+			insn = __opcode_to_mem_thumb32(insn);
+		else
+			insn = __opcode_to_mem_arm(insn);
+
+		*(u32 *)addr = insn;
+		size = sizeof(u32);
+	}
+
+	flush_icache_range((uintptr_t)(addr),
+			   (uintptr_t)(addr) + size);
+}
+
+static int __kprobes patch_text_stop_machine(void *data)
+{
+	struct patch *patch = data;
+
+	__patch_text(patch->addr, patch->insn);
+
+	return 0;
+}
+
+void __kprobes patch_text(void *addr, unsigned int insn)
+{
+	struct patch patch = {
+		.addr = addr,
+		.insn = insn,
+	};
+
+	if (cache_ops_need_broadcast()) {
+		stop_machine(patch_text_stop_machine, &patch, cpu_online_mask);
+	} else {
+		bool straddles_word = IS_ENABLED(CONFIG_THUMB2_KERNEL)
+				      && __opcode_is_thumb32(insn)
+				      && ((uintptr_t)addr & 2);
+
+		if (straddles_word)
+			stop_machine(patch_text_stop_machine, &patch, NULL);
+		else
+			__patch_text(addr, insn);
+	}
+}

arch/arm/kernel/patch.h

···
+#ifndef _ARM_KERNEL_PATCH_H
+#define _ARM_KERNEL_PATCH_H
+
+void patch_text(void *addr, unsigned int insn);
+void __patch_text(void *addr, unsigned int insn);
+
+#endif

arch/arm/kernel/perf_event.c

···
 		case 0xC0F0:	/* Cortex-A15 */
 			cpu_pmu = armv7_a15_pmu_init();
 			break;
+		case 0xC070:	/* Cortex-A7 */
+			cpu_pmu = armv7_a7_pmu_init();
+			break;
 		}
 	/* Intel CPUs [xscale]. */
 	} else if (0x69 == implementor) {

arch/arm/kernel/perf_event_v7.c

···
 };
 
 /*
+ * Cortex-A7 HW events mapping
+ */
+static const unsigned armv7_a7_perf_map[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV7_PERFCTR_CPU_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV7_PERFCTR_INSTR_EXECUTED,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV7_PERFCTR_PC_WRITE,
+	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV7_PERFCTR_BUS_CYCLES,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
+};
+
+static const unsigned armv7_a7_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+					[PERF_COUNT_HW_CACHE_OP_MAX]
+					[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(L1D)] = {
+		/*
+		 * The performance counters don't differentiate between read
+		 * and write accesses/misses so this isn't strictly correct,
+		 * but it's the best we can do. Writes and reads get
+		 * combined.
+		 */
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(L1I)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L2_CACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L2_CACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(DTLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(ITLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(BPU)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(NODE)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+};
+
+/*
  * Perf Events' indices
  */
 #define	ARMV7_IDX_CYCLE_COUNTER	0
···
 				&armv7_a15_perf_cache_map, 0xFF);
 }
 
+static int armv7_a7_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv7_a7_perf_map,
+				&armv7_a7_perf_cache_map, 0xFF);
+}
+
 static struct arm_pmu armv7pmu = {
 	.handle_irq		= armv7pmu_handle_irq,
 	.enable			= armv7pmu_enable_event,
···
 	armv7pmu.set_event_filter = armv7pmu_set_event_filter;
 	return &armv7pmu;
 }
+
+static struct arm_pmu *__init armv7_a7_pmu_init(void)
+{
+	armv7pmu.id		= ARM_PERF_PMU_ID_CA7;
+	armv7pmu.name		= "ARMv7 Cortex-A7";
+	armv7pmu.map_event	= armv7_a7_map_event;
+	armv7pmu.num_events	= armv7_read_num_pmnc_events();
+	armv7pmu.set_event_filter = armv7pmu_set_event_filter;
+	return &armv7pmu;
+}
 #else
 static struct arm_pmu *__init armv7_a8_pmu_init(void)
 {
···
 }
 
 static struct arm_pmu *__init armv7_a15_pmu_init(void)
+{
+	return NULL;
+}
+
+static struct arm_pmu *__init armv7_a7_pmu_init(void)
 {
 	return NULL;
 }

arch/arm/kernel/process.c

···
 #ifdef CONFIG_MMU
 /*
  * The vectors page is always readable from user space for the
- * atomic helpers and the signal restart code.  Let's declare a mapping
- * for it so it is visible through ptrace and /proc/<pid>/mem.
+ * atomic helpers and the signal restart code. Insert it into the
+ * gate_vma so that it is visible through ptrace and /proc/<pid>/mem.
  */
+static struct vm_area_struct gate_vma;
 
-int vectors_user_mapping(void)
+static int __init gate_vma_init(void)
 {
-	struct mm_struct *mm = current->mm;
-	return install_special_mapping(mm, 0xffff0000, PAGE_SIZE,
-				       VM_READ | VM_EXEC |
-				       VM_MAYREAD | VM_MAYEXEC | VM_RESERVED,
-				       NULL);
+	gate_vma.vm_start	= 0xffff0000;
+	gate_vma.vm_end		= 0xffff0000 + PAGE_SIZE;
+	gate_vma.vm_page_prot	= PAGE_READONLY_EXEC;
+	gate_vma.vm_flags	= VM_READ | VM_EXEC |
+				  VM_MAYREAD | VM_MAYEXEC;
+	return 0;
+}
+arch_initcall(gate_vma_init);
+
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
+{
+	return &gate_vma;
+}
+
+int in_gate_area(struct mm_struct *mm, unsigned long addr)
+{
+	return (addr >= gate_vma.vm_start) && (addr < gate_vma.vm_end);
+}
+
+int in_gate_area_no_mm(unsigned long addr)
+{
+	return in_gate_area(NULL, addr);
 }
 
 const char *arch_vma_name(struct vm_area_struct *vma)
 {
-	return (vma->vm_start == 0xffff0000) ? "[vectors]" : NULL;
+	return (vma == &gate_vma) ? "[vectors]" : NULL;
 }
 #endif

arch/arm/kernel/sched_clock.c

···
 #include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/syscore_ops.h>
 #include <linux/timer.h>
 
 #include <asm/sched_clock.h>
···
 
 	sched_clock_poll(sched_clock_timer.data);
 }
+
+static int sched_clock_suspend(void)
+{
+	sched_clock_poll(sched_clock_timer.data);
+	return 0;
+}
+
+static struct syscore_ops sched_clock_ops = {
+	.suspend = sched_clock_suspend,
+};
+
+static int __init sched_clock_syscore_init(void)
+{
+	register_syscore_ops(&sched_clock_ops);
+	return 0;
+}
+device_initcall(sched_clock_syscore_init);

arch/arm/kernel/setup.c

···
 	conswitchp = &dummy_con;
 #endif
 #endif
-	early_trap_init();
 
 	if (mdesc->init_early)
 		mdesc->init_early();

arch/arm/kernel/signal.c

···
  */
 asmlinkage int sys_sigsuspend(int restart, unsigned long oldmask, old_sigset_t mask)
 {
-	mask &= _BLOCKABLE;
-	spin_lock_irq(&current->sighand->siglock);
+	sigset_t blocked;
+
 	current->saved_sigmask = current->blocked;
-	siginitset(&current->blocked, mask);
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+
+	mask &= _BLOCKABLE;
+	siginitset(&blocked, mask);
+	set_current_blocked(&blocked);
 
 	current->state = TASK_INTERRUPTIBLE;
 	schedule();
···
 	err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set));
 	if (err == 0) {
 		sigdelsetmask(&set, ~_BLOCKABLE);
-		spin_lock_irq(&current->sighand->siglock);
-		current->blocked = set;
-		recalc_sigpending();
-		spin_unlock_irq(&current->sighand->siglock);
+		set_current_blocked(&set);
 	}
 
 	__get_user_error(regs->ARM_r0, &sf->uc.uc_mcontext.arm_r0, err);
···
 	/*
 	 * Block the signal if we were successful.
 	 */
-	spin_lock_irq(&tsk->sighand->siglock);
-	sigorsets(&tsk->blocked, &tsk->blocked,
-		  &ka->sa.sa_mask);
-	if (!(ka->sa.sa_flags & SA_NODEFER))
-		sigaddset(&tsk->blocked, sig);
-	recalc_sigpending();
-	spin_unlock_irq(&tsk->sighand->siglock);
+	block_sigmask(ka, sig);
 
 	return 0;
 }

arch/arm/kernel/smp.c

···
 	IPI_CPU_STOP,
 };
 
+static DECLARE_COMPLETION(cpu_running);
+
 int __cpuinit __cpu_up(unsigned int cpu)
 {
 	struct cpuinfo_arm *ci = &per_cpu(cpu_data, cpu);
···
 	 */
 	ret = boot_secondary(cpu, idle);
 	if (ret == 0) {
-		unsigned long timeout;
-
 		/*
 		 * CPU was successfully started, wait for it
 		 * to come online or time out.
 		 */
-		timeout = jiffies + HZ;
-		while (time_before(jiffies, timeout)) {
-			if (cpu_online(cpu))
-				break;
-
-			udelay(10);
-			barrier();
-		}
+		wait_for_completion_timeout(&cpu_running,
+						 msecs_to_jiffies(1000));
 
 		if (!cpu_online(cpu)) {
 			pr_crit("CPU%u: failed to come online\n", cpu);
···
 	/*
 	 * OK, now it's safe to let the boot CPU continue.  Wait for
 	 * the CPU migration code to notice that the CPU is online
-	 * before we continue.
+	 * before we continue - which happens after __cpu_up returns.
 	 */
 	set_cpu_online(cpu, true);
+	complete(&cpu_running);
 
 	/*
 	 * Setup the percpu timer for this CPU.

arch/arm/kernel/time.c

···
 #include <linux/timer.h>
 #include <linux/irq.h>
 
-#include <linux/mc146818rtc.h>
-
 #include <asm/leds.h>
 #include <asm/thread_info.h>
 #include <asm/sched_clock.h>
···
 {
 	system_timer = machine_desc->timer;
 	system_timer->init();
-#ifdef CONFIG_HAVE_SCHED_CLOCK
 	sched_clock_postinit();
-#endif
 }
 

arch/arm/kernel/traps.c

···
 #else
 #define S_SMP ""
 #endif
+#ifdef CONFIG_THUMB2_KERNEL
+#define S_ISA " THUMB2"
+#else
+#define S_ISA " ARM"
+#endif
 
 static int __die(const char *str, int err, struct thread_info *thread, struct pt_regs *regs)
 {
···
 	static int die_counter;
 	int ret;
 
-	printk(KERN_EMERG "Internal error: %s: %x [#%d]" S_PREEMPT S_SMP "\n",
-	       str, err, ++die_counter);
+	printk(KERN_EMERG "Internal error: %s: %x [#%d]" S_PREEMPT S_SMP
+	       S_ISA "\n", str, err, ++die_counter);
 
 	/* trap and error numbers are mostly meaningless on ARM */
 	ret = notify_die(DIE_OOPS, str, regs, err, tsk->thread.trap_no, SIGSEGV);
···
 		memcpy((void *)vectors + 0xfe0, (void *)vectors + 0xfe8, 4);
 }
 
-void __init early_trap_init(void)
+void __init early_trap_init(void *vectors_base)
 {
-#if defined(CONFIG_CPU_USE_DOMAINS)
-	unsigned long vectors = CONFIG_VECTORS_BASE;
-#else
-	unsigned long vectors = (unsigned long)vectors_page;
-#endif
+	unsigned long vectors = (unsigned long)vectors_base;
 	extern char __stubs_start[], __stubs_end[];
 	extern char __vectors_start[], __vectors_end[];
 	extern char __kuser_helper_start[], __kuser_helper_end[];
 	int kuser_sz = __kuser_helper_end - __kuser_helper_start;
+
+	vectors_page = vectors_base;
 
 	/*
 	 * Copy the vectors, stubs and kuser helpers (in entry-armv.S)

arch/arm/mach-davinci/time.c

···
 #include <linux/err.h>
 #include <linux/platform_device.h>
 
-#include <mach/hardware.h>
+#include <asm/sched_clock.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
+
 #include <mach/cputype.h>
+#include <mach/hardware.h>
 #include <mach/time.h>
+
 #include "clock.h"
 
 static struct clock_event_device clockevent_davinci;
···
 	return (cycles_t)timer32_read(t);
 }
 
-/*
- * Kernel assumes that sched_clock can be called early but may not have
- * things ready yet.
- */
-static cycle_t read_dummy(struct clocksource *cs)
-{
-	return 0;
-}
-
-
 static struct clocksource clocksource_davinci = {
 	.rating		= 300,
-	.read		= read_dummy,
+	.read		= read_cycles,
 	.mask		= CLOCKSOURCE_MASK(32),
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
···
 /*
  * Overwrite weak default sched_clock with something more precise
  */
-unsigned long long notrace sched_clock(void)
+static u32 notrace davinci_read_sched_clock(void)
 {
-	const cycle_t cyc = clocksource_davinci.read(&clocksource_davinci);
-
-	return clocksource_cyc2ns(cyc, clocksource_davinci.mult,
-				clocksource_davinci.shift);
+	return timer32_read(&timers[TID_CLOCKSOURCE]);
 }
 
 /*
···
 	davinci_clock_tick_rate = clk_get_rate(timer_clk);
 
 	/* setup clocksource */
-	clocksource_davinci.read = read_cycles;
 	clocksource_davinci.name = id_to_name[clocksource_id];
 	if (clocksource_register_hz(&clocksource_davinci,
 				    davinci_clock_tick_rate))
 		printk(err, clocksource_davinci.name);
+
+	setup_sched_clock(davinci_read_sched_clock, 32,
+			  davinci_clock_tick_rate);
 
 	/* setup clockevent */
 	clockevent_davinci.name = id_to_name[timers[TID_CLOCKEVENT].id];

arch/arm/mach-highbank/highbank.c

···
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 #include <asm/mach/time.h>
-#include <mach/irqs.h>
 
 #include "core.h"
 #include "sysregs.h"

arch/arm/mach-highbank/include/mach/irqs.h

···
-#ifndef __MACH_IRQS_H
-#define __MACH_IRQS_H
-
-#define NR_IRQS			192
-
-#endif

arch/arm/mach-integrator/core.c

···
 
 #include <mach/hardware.h>
 #include <mach/platform.h>
-#include <asm/irq.h>
 #include <mach/cm.h>
+#include <mach/irqs.h>
+
 #include <asm/leds.h>
 #include <asm/mach-types.h>
 #include <asm/mach/time.h>

arch/arm/mach-integrator/include/mach/irqs.h

···
 #define IRQ_SIC_CP_LMINT7		46
 #define IRQ_SIC_END			46
 
-#define NR_IRQS                         47
+#define NR_IRQS_INTEGRATOR_AP		34
+#define NR_IRQS_INTEGRATOR_CP		47
 

arch/arm/mach-integrator/integrator_ap.c

···
 #include <mach/hardware.h>
 #include <mach/platform.h>
 #include <asm/hardware/arm_timer.h>
-#include <asm/irq.h>
 #include <asm/setup.h>
 #include <asm/param.h>		/* HZ */
 #include <asm/mach-types.h>
+#include <asm/sched_clock.h>
 
 #include <mach/lm.h>
+#include <mach/irqs.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
···
 
 static unsigned long timer_reload;
 
+static u32 notrace integrator_read_sched_clock(void)
+{
+	return -readl((void __iomem *) TIMER2_VA_BASE + TIMER_VALUE);
+}
+
 static void integrator_clocksource_init(unsigned long inrate)
 {
 	void __iomem *base = (void __iomem *)TIMER2_VA_BASE;
···
 
 	clocksource_mmio_init(base + TIMER_VALUE, "timer2",
 			rate, 200, 16, clocksource_mmio_readl_down);
+	setup_sched_clock(integrator_read_sched_clock, 16, rate);
 }
 
 static void __iomem * const clkevt_base = (void __iomem *)TIMER1_VA_BASE;
···
 	.atag_offset	= 0x100,
 	.reserve	= integrator_reserve,
 	.map_io		= ap_map_io,
+	.nr_irqs	= NR_IRQS_INTEGRATOR_AP,
 	.init_early	= integrator_init_early,
 	.init_irq	= ap_init_irq,
 	.timer		= &ap_timer,

arch/arm/mach-integrator/integrator_cp.c

···
 
 #include <mach/hardware.h>
 #include <mach/platform.h>
-#include <asm/irq.h>
 #include <asm/setup.h>
 #include <asm/mach-types.h>
 #include <asm/hardware/arm_timer.h>
···
 
 #include <mach/cm.h>
 #include <mach/lm.h>
+#include <mach/irqs.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
···
 	.atag_offset	= 0x100,
 	.reserve	= integrator_reserve,
 	.map_io		= intcp_map_io,
+	.nr_irqs	= NR_IRQS_INTEGRATOR_CP,
 	.init_early	= intcp_init_early,
 	.init_irq	= intcp_init_irq,
 	.timer		= &cp_timer,

arch/arm/mach-integrator/pci.c

···
 #include <linux/interrupt.h>
 #include <linux/init.h>
 
-#include <asm/irq.h>
 #include <asm/mach/pci.h>
 #include <asm/mach-types.h>
+
+#include <mach/irqs.h>
 
 /* 
  * A small note about bridges and interrupts.  The DECchip 21050 (and

arch/arm/mach-integrator/pci_v3.c

···
 
 #include <mach/hardware.h>
 #include <mach/platform.h>
-#include <asm/irq.h>
+#include <mach/irqs.h>
+
 #include <asm/signal.h>
 #include <asm/mach/pci.h>
 #include <asm/irq_regs.h>

arch/arm/mach-mmp/aspenite.c

···
 #include <mach/addr-map.h>
 #include <mach/mfp-pxa168.h>
 #include <mach/pxa168.h>
+#include <mach/irqs.h>
 #include <video/pxa168fb.h>
 #include <linux/input.h>
 #include <plat/pxa27x_keypad.h>
···
 
 MACHINE_START(ASPENITE, "PXA168-based Aspenite Development Platform")
 	.map_io		= mmp_map_io,
-	.nr_irqs	= IRQ_BOARD_START,
+	.nr_irqs	= MMP_NR_IRQS,
 	.init_irq       = pxa168_init_irq,
 	.timer          = &pxa168_timer,
 	.init_machine   = common_init,
···
 
 MACHINE_START(ZYLONITE2, "PXA168-based Zylonite2 Development Platform")
 	.map_io		= mmp_map_io,
-	.nr_irqs	= IRQ_BOARD_START,
+	.nr_irqs	= MMP_NR_IRQS,
 	.init_irq       = pxa168_init_irq,
 	.timer          = &pxa168_timer,
 	.init_machine   = common_init,

arch/arm/mach-mmp/avengers_lite.c

···
 
 MACHINE_START(AVENGERS_LITE, "PXA168 Avengers lite Development Platform")
 	.map_io		= mmp_map_io,
+	.nr_irqs	= MMP_NR_IRQS,
 	.init_irq       = pxa168_init_irq,
 	.timer          = &pxa168_timer,
 	.init_machine   = avengers_lite_init,

arch/arm/mach-mmp/brownstone.c

···
 
 #include "common.h"
 
-#define BROWNSTONE_NR_IRQS	(IRQ_BOARD_START + 40)
+#define BROWNSTONE_NR_IRQS	(MMP_NR_IRQS + 40)
 
 #define GPIO_5V_ENABLE		(89)
 
···
 };
 
 static struct max8925_platform_data brownstone_max8925_info = {
-	.irq_base		= IRQ_BOARD_START,
+	.irq_base		= MMP_NR_IRQS,
 };
 
 static struct i2c_board_info brownstone_twsi1_info[] = {

arch/arm/mach-mmp/flint.c

···
 #include <mach/addr-map.h>
 #include <mach/mfp-mmp2.h>
 #include <mach/mmp2.h>
+#include <mach/irqs.h>
 
 #include "common.h"
 
-#define FLINT_NR_IRQS	(IRQ_BOARD_START + 48)
+#define FLINT_NR_IRQS	(MMP_NR_IRQS + 48)
 
 static unsigned long flint_pin_config[] __initdata = {
 	/* UART1 */

arch/arm/mach-mmp/gplugd.c

···
 
 MACHINE_START(GPLUGD, "PXA168-based GuruPlug Display (gplugD) Platform")
 	.map_io		= mmp_map_io,
-	.nr_irqs	= IRQ_BOARD_START,
+	.nr_irqs	= MMP_NR_IRQS,
 	.init_irq       = pxa168_init_irq,
 	.timer          = &pxa168_timer,
 	.init_machine   = gplugd_init,

arch/arm/mach-mmp/include/mach/irqs.h

···
 #define MMP_GPIO_TO_IRQ(gpio)		(IRQ_GPIO_START + (gpio))
 
 #define IRQ_BOARD_START			(IRQ_GPIO_START + MMP_NR_BUILTIN_GPIO)
-
-#define NR_IRQS				(IRQ_BOARD_START)
+#define MMP_NR_IRQS			IRQ_BOARD_START
 
 #endif /* __ASM_MACH_IRQS_H */

arch/arm/mach-mmp/irq-mmp2.c

···
 #include <linux/irq.h>
 #include <linux/io.h>
 
+#include <mach/irqs.h>
 #include <mach/regs-icu.h>
 #include <mach/mmp2.h>
 

arch/arm/mach-mmp/jasper.c

···
 #include <linux/mfd/max8925.h>
 #include <linux/interrupt.h>
 
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <mach/addr-map.h>
···
 
 #include "common.h"
 
-#define JASPER_NR_IRQS		(IRQ_BOARD_START + 48)
+#define JASPER_NR_IRQS		(MMP_NR_IRQS + 48)
 
 static unsigned long jasper_pin_config[] __initdata = {
 	/* UART1 */
···
 static struct max8925_platform_data jasper_max8925_info = {
 	.backlight		= &jasper_backlight_data,
 	.power			= &jasper_power_data,
-	.irq_base		= IRQ_BOARD_START,
+	.irq_base		= MMP_NR_IRQS,
 };
 
 static struct i2c_board_info jasper_twsi1_info[] = {

arch/arm/mach-mmp/tavorevb.c

···
 
 MACHINE_START(TAVOREVB, "PXA910 Evaluation Board (aka TavorEVB)")
 	.map_io		= mmp_map_io,
+	.nr_irqs	= MMP_NR_IRQS,
 	.init_irq       = pxa910_init_irq,
 	.timer          = &pxa910_timer,
 	.init_machine   = tavorevb_init,

arch/arm/mach-mmp/teton_bga.c

···
 #include <mach/mfp-pxa168.h>
 #include <mach/pxa168.h>
 #include <mach/teton_bga.h>
+#include <mach/irqs.h>
 
 #include "common.h"
 
···
 
 MACHINE_START(TETON_BGA, "PXA168-based Teton BGA Development Platform")
 	.map_io		= mmp_map_io,
-	.nr_irqs	= IRQ_BOARD_START,
+	.nr_irqs	= MMP_NR_IRQS,
 	.init_irq       = pxa168_init_irq,
 	.timer          = &pxa168_timer,
 	.init_machine   = teton_bga_init,

arch/arm/mach-mmp/ttc_dkb.c

···
  * 16 board interrupts -- PCA9575 GPIO expander
  * 24 board interrupts -- 88PM860x PMIC
  */
-#define TTCDKB_NR_IRQS		(IRQ_BOARD_START + 16 + 16 + 24)
+#define TTCDKB_NR_IRQS		(MMP_NR_IRQS + 16 + 16 + 24)
 
 static unsigned long ttc_dkb_pin_config[] __initdata = {
 	/* UART2 */
···
 static struct pca953x_platform_data max7312_data[] = {
 	{
 		.gpio_base	= TTCDKB_GPIO_EXT0(0),
-		.irq_base	= IRQ_BOARD_START,
+		.irq_base	= MMP_NR_IRQS,
 	},
 };
 

arch/arm/mach-msm/timer.c

···
 #include <asm/mach/time.h>
 #include <asm/hardware/gic.h>
 #include <asm/localtimer.h>
+#include <asm/sched_clock.h>
 
 #include <mach/msm_iomap.h>
 #include <mach/cpu.h>
···
 
 static void __iomem *source_base;
 
-static cycle_t msm_read_timer_count(struct clocksource *cs)
+static notrace cycle_t msm_read_timer_count(struct clocksource *cs)
 {
 	return readl_relaxed(source_base + TIMER_COUNT_VAL);
 }
 
-static cycle_t msm_read_timer_count_shift(struct clocksource *cs)
+static notrace cycle_t msm_read_timer_count_shift(struct clocksource *cs)
 {
 	/*
 	 * Shift timer count down by a constant due to unreliable lower bits
···
 	.stop	= msm_local_timer_stop,
 };
 #endif /* CONFIG_LOCAL_TIMERS */
+
+static notrace u32 msm_sched_clock_read(void)
+{
+	return msm_clocksource.read(&msm_clocksource);
+}
 
 static void __init msm_timer_init(void)
 {
···
 	res = clocksource_register_hz(cs, dgt_hz);
 	if (res)
 		pr_err("clocksource_register failed\n");
+	setup_sched_clock(msm_sched_clock_read,
+			cpu_is_msm7x01() ? 32 - MSM_DGT_SHIFT : 32, dgt_hz);
 }
 
 struct sys_timer msm_timer = {

arch/arm/mach-picoxcell/include/mach/irqs.h

···
-/*
- * Copyright (c) 2011 Picochip Ltd., Jamie Iles
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-#ifndef __MACH_IRQS_H
-#define __MACH_IRQS_H
-
-/* We dynamically allocate our irq_desc's. */
-#define NR_IRQS				0
-
-#endif /* __MACH_IRQS_H */

arch/arm/mach-prima2/timer.c

···
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <mach/map.h>
+#include <asm/sched_clock.h>
 #include <asm/mach/time.h>
 
 #define SIRFSOC_TIMER_COUNTER_LO	0x0000
···
 };
 
 /* Overwrite weak default sched_clock with more precise one */
-unsigned long long notrace sched_clock(void)
+static u32 notrace sirfsoc_read_sched_clock(void)
 {
-	static int is_mapped;
-
-	/*
-	 * sched_clock is called earlier than .init of sys_timer
-	 * if we map timer memory in .init of sys_timer, system
-	 * will panic due to illegal memory access
-	 */
-	if (!is_mapped) {
-		sirfsoc_of_timer_map();
-		is_mapped = 1;
-	}
-
-	return sirfsoc_timer_read(NULL) * (NSEC_PER_SEC / CLOCK_TICK_RATE);
+	return (u32)(sirfsoc_timer_read(NULL) & 0xffffffff);
 }
 
 static void __init sirfsoc_clockevent_init(void)
···
 	BUG_ON(rate < CLOCK_TICK_RATE);
 	BUG_ON(rate % CLOCK_TICK_RATE);
 
+	sirfsoc_of_timer_map();
+
 	writel_relaxed(rate / CLOCK_TICK_RATE / 2 - 1, sirfsoc_timer_base + SIRFSOC_TIMER_DIV);
 	writel_relaxed(0, sirfsoc_timer_base + SIRFSOC_TIMER_COUNTER_LO);
 	writel_relaxed(0, sirfsoc_timer_base + SIRFSOC_TIMER_COUNTER_HI);
 	writel_relaxed(BIT(0), sirfsoc_timer_base + SIRFSOC_TIMER_STATUS);
 
 	BUG_ON(clocksource_register_hz(&sirfsoc_clocksource, CLOCK_TICK_RATE));
+
+	setup_sched_clock(sirfsoc_read_sched_clock, 32, CLOCK_TICK_RATE);
 
 	BUG_ON(setup_irq(sirfsoc_timer_irq.irq, &sirfsoc_timer_irq));
 

arch/arm/mach-pxa/capc7117.c

···
 	      "Embedian CAPC-7117 evaluation kit based on the MXM-8x10 CoM")
 	.atag_offset = 0x100,
 	.map_io = pxa3xx_map_io,
+	.nr_irqs = PXA_NR_IRQS,
 	.init_irq = pxa3xx_init_irq,
 	.handle_irq = pxa3xx_handle_irq,
 	.timer = &pxa_timer,

arch/arm/mach-pxa/cm-x300.c

···
 MACHINE_START(CM_X300, "CM-X300 module")
 	.atag_offset	= 0x100,
 	.map_io		= pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
 	.timer		= &pxa_timer,

arch/arm/mach-pxa/colibri-pxa270.c

···
 	.atag_offset	= 0x100,
 	.init_machine	= colibri_pxa270_init,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
···
 	.atag_offset	= 0x100,
 	.init_machine	= colibri_pxa270_income_init,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,

arch/arm/mach-pxa/colibri-pxa300.c

···
 	.atag_offset	= 0x100,
 	.init_machine	= colibri_pxa300_init,
 	.map_io		= pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
 	.timer		= &pxa_timer,

arch/arm/mach-pxa/colibri-pxa320.c

···
 	.atag_offset	= 0x100,
 	.init_machine	= colibri_pxa320_init,
 	.map_io		= pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
 	.timer		= &pxa_timer,

arch/arm/mach-pxa/corgi.c

···
 MACHINE_START(CORGI, "SHARP Corgi")
 	.fixup		= fixup_corgi,
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.init_machine	= corgi_init,
···
 MACHINE_START(SHEPHERD, "SHARP Shepherd")
 	.fixup		= fixup_corgi,
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.init_machine	= corgi_init,
···
 MACHINE_START(HUSKY, "SHARP Husky")
 	.fixup		= fixup_corgi,
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.init_machine	= corgi_init,

arch/arm/mach-pxa/csb726.c

···
 MACHINE_START(CSB726, "Cogent CSB726")
 	.atag_offset	= 0x100,
 	.map_io         = pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq       = pxa27x_init_irq,
 	.handle_irq       = pxa27x_handle_irq,
 	.init_machine   = csb726_init,

arch/arm/mach-pxa/devices.c

···
 #include <mach/pxafb.h>
 #include <mach/mmc.h>
 #include <mach/irda.h>
+#include <mach/irqs.h>
 #include <mach/ohci.h>
 #include <plat/pxa27x_keypad.h>
 #include <mach/camera.h>

arch/arm/mach-pxa/em-x270.c

···
 MACHINE_START(EM_X270, "Compulab EM-X270")
 	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
···
 MACHINE_START(EXEDA, "Compulab eXeda")
 	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,

arch/arm/mach-pxa/gumstix.c

···
 MACHINE_START(GUMSTIX, "Gumstix")
 	.atag_offset	= 0x100, /* match u-boot bi_boot_params */
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.timer		= &pxa_timer,

arch/arm/mach-pxa/h5000.c

···
 MACHINE_START(H5400, "HP iPAQ H5000")
 	.atag_offset = 0x100,
 	.map_io = pxa25x_map_io,
+	.nr_irqs = PXA_NR_IRQS,
 	.init_irq = pxa25x_init_irq,
 	.handle_irq = pxa25x_handle_irq,
 	.timer = &pxa_timer,

arch/arm/mach-pxa/himalaya.c

···
 MACHINE_START(HIMALAYA, "HTC Himalaya")
 	.atag_offset = 0x100,
 	.map_io = pxa25x_map_io,
+	.nr_irqs = PXA_NR_IRQS,
 	.init_irq = pxa25x_init_irq,
 	.handle_irq = pxa25x_handle_irq,
 	.init_machine = himalaya_init,

arch/arm/mach-pxa/icontrol.c

···
 MACHINE_START(ICONTROL, "iControl/SafeTcam boards using Embedian MXM-8x10 CoM")
 	.atag_offset	= 0x100,
 	.map_io		= pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
 	.timer		= &pxa_timer,

arch/arm/mach-pxa/idp.c

···
 MACHINE_START(PXA_IDP, "Vibren PXA255 IDP")
 	/* Maintainer: Vibren Technologies */
 	.map_io		= idp_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.timer		= &pxa_timer,

arch/arm/mach-pxa/include/mach/irqs.h

···
  */
 #define IRQ_BOARD_START		(PXA_GPIO_IRQ_BASE + PXA_NR_BUILTIN_GPIO)
 
-#define NR_IRQS			(IRQ_BOARD_START)
+#define PXA_NR_IRQS		(IRQ_BOARD_START)
 
 #ifndef __ASSEMBLY__
 struct irq_data;

arch/arm/mach-pxa/include/mach/mainstone.h

···
 #ifndef ASM_ARCH_MAINSTONE_H
 #define ASM_ARCH_MAINSTONE_H
 
+#include <mach/irqs.h>
+
 #define MST_ETH_PHYS		PXA_CS4_PHYS
 
 #define MST_FPGA_PHYS		PXA_CS2_PHYS

arch/arm/mach-pxa/mioa701.c

···
 	.atag_offset	= 0x100,
 	.restart_mode	= 's',
 	.map_io		= &pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= &pxa27x_init_irq,
 	.handle_irq	= &pxa27x_handle_irq,
 	.init_machine	= mioa701_machine_init,

arch/arm/mach-pxa/mp900.c

···
 	.atag_offset	= 0x220100,
 	.timer		= &pxa_timer,
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.init_machine	= mp900c_init,

arch/arm/mach-pxa/palmld.c

···
 MACHINE_START(PALMLD, "Palm LifeDrive")
 	.atag_offset	= 0x100,
 	.map_io		= palmld_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,

arch/arm/mach-pxa/palmt5.c

···
 	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
 	.reserve	= palmt5_reserve,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,

arch/arm/mach-pxa/palmtc.c

···
 MACHINE_START(PALMTC, "Palm Tungsten|C")
 	.atag_offset 	= 0x100,
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.timer		= &pxa_timer,

arch/arm/mach-pxa/palmte2.c

···
 MACHINE_START(PALMTE2, "Palm Tungsten|E2")
 	.atag_offset	= 0x100,
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.timer		= &pxa_timer,

arch/arm/mach-pxa/palmtreo.c

···
 	.atag_offset    = 0x100,
 	.map_io         = pxa27x_map_io,
 	.reserve	= treo_reserve,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq       = pxa27x_init_irq,
 	.handle_irq       = pxa27x_handle_irq,
 	.timer          = &pxa_timer,
···
 	.atag_offset    = 0x100,
 	.map_io         = pxa27x_map_io,
 	.reserve	= treo_reserve,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq       = pxa27x_init_irq,
 	.handle_irq       = pxa27x_handle_irq,
 	.timer          = &pxa_timer,

arch/arm/mach-pxa/palmtx.c

···
 MACHINE_START(PALMTX, "Palm T|X")
 	.atag_offset	= 0x100,
 	.map_io		= palmtx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,

arch/arm/mach-pxa/palmz72.c

···
 MACHINE_START(PALMZ72, "Palm Zire72")
 	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,

arch/arm/mach-pxa/pxa3xx.c

···
 #include <mach/pm.h>
 #include <mach/dma.h>
 #include <mach/smemc.h>
+#include <mach/irqs.h>
 
 #include "generic.h"
 #include "devices.h"

arch/arm/mach-pxa/raumfeld.c

···
 	.atag_offset	= 0x100,
 	.init_machine	= raumfeld_controller_init,
 	.map_io		= pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
 	.timer		= &pxa_timer,
···
 	.atag_offset	= 0x100,
 	.init_machine	= raumfeld_connector_init,
 	.map_io		= pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
 	.timer		= &pxa_timer,
···
 	.atag_offset	= 0x100,
 	.init_machine	= raumfeld_speaker_init,
 	.map_io		= pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.handle_irq	= pxa3xx_handle_irq,
 	.timer		= &pxa_timer,

arch/arm/mach-pxa/saar.c

···
 	/* Maintainer: Eric Miao <[e-mail]> */
 	.atag_offset    = 0x100,
 	.map_io         = pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq       = pxa3xx_init_irq,
 	.handle_irq       = pxa3xx_handle_irq,
 	.timer          = &pxa_timer,

arch/arm/mach-pxa/spitz.c

···
 	.restart_mode	= 'g',
 	.fixup		= spitz_fixup,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.init_machine	= spitz_init,
···
 	.restart_mode	= 'g',
 	.fixup		= spitz_fixup,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.init_machine	= spitz_init,
···
 	.restart_mode	= 'g',
 	.fixup		= spitz_fixup,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.init_machine	= spitz_init,

arch/arm/mach-pxa/stargate2.c

···
 #ifdef CONFIG_MACH_INTELMOTE2
 MACHINE_START(INTELMOTE2, "IMOTE 2")
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,

arch/arm/mach-pxa/tavorevb.c

···
 	/* Maintainer: Eric Miao <[e-mail]> */
 	.atag_offset    = 0x100,
 	.map_io         = pxa3xx_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq       = pxa3xx_init_irq,
 	.handle_irq       = pxa3xx_handle_irq,
 	.timer          = &pxa_timer,

arch/arm/mach-pxa/time.c

···
 #include <asm/mach/time.h>
 #include <asm/sched_clock.h>
 #include <mach/regs-ost.h>
+#include <mach/irqs.h>
 
 /*
  * This is PXA's sched_clock implementation. This has a resolution

arch/arm/mach-pxa/trizeps4.c

···
 	.atag_offset	= 0x100,
 	.init_machine	= trizeps4_init,
 	.map_io		= trizeps4_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,
···
 	.atag_offset	= 0x100,
 	.init_machine	= trizeps4_init,
 	.map_io		= trizeps4_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,

arch/arm/mach-pxa/viper.c

···
 	/* Maintainer: Marc Zyngier <[e-mail]> */
 	.atag_offset	= 0x100,
 	.map_io		= viper_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= viper_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.timer          = &pxa_timer,

arch/arm/mach-pxa/vpac270.c

···
 MACHINE_START(VPAC270, "Voipac PXA270")
 	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,

arch/arm/mach-pxa/xcep.c

···
 	.atag_offset	= 0x100,
 	.init_machine	= xcep_init,
 	.map_io		= pxa25x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.timer		= &pxa_timer,

arch/arm/mach-pxa/z2.c

···
 MACHINE_START(ZIPIT2, "Zipit Z2")
 	.atag_offset	= 0x100,
 	.map_io		= pxa27x_map_io,
+	.nr_irqs	= PXA_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.timer		= &pxa_timer,

arch/arm/mach-shmobile/Kconfig

···
 
 comment "SH-Mobile System Configuration"
 
+config CPU_HAS_INTEVT
+        bool
+	default y
+
 menu "Memory configuration"
 
 config MEMORY_START

arch/arm/mach-shmobile/board-ag5evm.c

···
 #include <video/sh_mipi_dsi.h>
 #include <sound/sh_fsi.h>
 #include <mach/hardware.h>
+#include <mach/irqs.h>
 #include <mach/sh73a0.h>
 #include <mach/common.h>
 #include <asm/mach-types.h>

arch/arm/mach-shmobile/board-bonito.c

···
 #include <asm/mach/time.h>
 #include <asm/hardware/cache-l2x0.h>
 #include <mach/r8a7740.h>
+#include <mach/irqs.h>
 #include <video/sh_mobile_lcdc.h>
 
 /*

arch/arm/mach-shmobile/board-g3evm.c

···
 #include <linux/input.h>
 #include <linux/input/sh_keysc.h>
 #include <linux/dma-mapping.h>
+#include <mach/irqs.h>
 #include <mach/sh7367.h>
 #include <mach/common.h>
 #include <asm/mach-types.h>

arch/arm/mach-shmobile/board-g4evm.c

···
 #include <linux/mmc/sh_mobile_sdhi.h>
 #include <linux/gpio.h>
 #include <linux/dma-mapping.h>
+#include <mach/irqs.h>
 #include <mach/sh7377.h>
 #include <mach/common.h>
 #include <asm/mach-types.h>

arch/arm/mach-shmobile/board-kota2.c

···
 #include <linux/mfd/tmio.h>
 #include <linux/mmc/sh_mobile_sdhi.h>
 #include <mach/hardware.h>
+#include <mach/irqs.h>
 #include <mach/sh73a0.h>
 #include <mach/common.h>
 #include <asm/mach-types.h>

arch/arm/mach-shmobile/board-mackerel.c

···
 #include <sound/sh_fsi.h>
 
 #include <mach/common.h>
+#include <mach/irqs.h>
 #include <mach/sh7372.h>
 
 #include <asm/mach/arch.h>

arch/arm/mach-shmobile/board-marzen.c

···
 #include <mach/hardware.h>
 #include <mach/r8a7779.h>
 #include <mach/common.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/hardware/gic.h>

arch/arm/mach-shmobile/include/mach/irqs.h

···
 #ifndef __ASM_MACH_IRQS_H
 #define __ASM_MACH_IRQS_H
 
-#define NR_IRQS         1024
+#include <linux/sh_intc.h>
 
 /* GIC */
 #define gic_spi(nr)		((nr) + 32)
-
-/* INTCA */
-#define evt2irq(evt)		(((evt) >> 5) - 16)
-#define irq2evt(irq)		(((irq) + 16) << 5)
 
 /* INTCS */
 #define INTCS_VECT_BASE		0x2200

arch/arm/mach-shmobile/intc-r8a7740.c

···
 #include <linux/io.h>
 #include <linux/sh_intc.h>
 #include <mach/intc.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 

arch/arm/mach-shmobile/intc-sh7367.c

···
 #include <linux/io.h>
 #include <linux/sh_intc.h>
 #include <mach/intc.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 

arch/arm/mach-shmobile/intc-sh7372.c

···
 #include <linux/io.h>
 #include <linux/sh_intc.h>
 #include <mach/intc.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 

arch/arm/mach-shmobile/intc-sh7377.c

···
 #include <linux/io.h>
 #include <linux/sh_intc.h>
 #include <mach/intc.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 

arch/arm/mach-shmobile/intc-sh73a0.c

···
 #include <linux/io.h>
 #include <linux/sh_intc.h>
 #include <mach/intc.h>
+#include <mach/irqs.h>
 #include <mach/sh73a0.h>
 #include <asm/hardware/gic.h>
 #include <asm/mach-types.h>

arch/arm/mach-shmobile/setup-r8a7740.c

···
 #include <linux/sh_timer.h>
 #include <mach/r8a7740.h>
 #include <mach/common.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/map.h>
 #include <asm/mach/arch.h>

arch/arm/mach-shmobile/setup-r8a7779.c

···
 #include <linux/sh_intc.h>
 #include <linux/sh_timer.h>
 #include <mach/hardware.h>
+#include <mach/irqs.h>
 #include <mach/r8a7779.h>
 #include <mach/common.h>
 #include <asm/mach-types.h>

arch/arm/mach-shmobile/setup-sh7367.c

···
 #include <linux/sh_timer.h>
 #include <mach/hardware.h>
 #include <mach/common.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>

arch/arm/mach-shmobile/setup-sh7372.c

···
 #include <linux/pm_domain.h>
 #include <linux/dma-mapping.h>
 #include <mach/hardware.h>
+#include <mach/irqs.h>
 #include <mach/sh7372.h>
 #include <mach/common.h>
 #include <asm/mach/map.h>

arch/arm/mach-shmobile/setup-sh7377.c

···
 #include <mach/hardware.h>
 #include <mach/common.h>
 #include <asm/mach/map.h>
+#include <mach/irqs.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>

arch/arm/mach-shmobile/setup-sh73a0.c

···
 #include <linux/sh_intc.h>
 #include <linux/sh_timer.h>
 #include <mach/hardware.h>
+#include <mach/irqs.h>
 #include <mach/sh73a0.h>
 #include <mach/common.h>
 #include <asm/mach-types.h>

arch/arm/mach-vexpress/include/mach/io.h

···
 #ifndef __ASM_ARM_ARCH_IO_H
 #define __ASM_ARM_ARCH_IO_H
 
-#define __io(a)		__typesafe_io(a)
 #define __mem_pci(a)	(a)
 
 #endif

arch/arm/mm/cache-l2x0.c

···
 
 static void __iomem *l2x0_base;
 static DEFINE_RAW_SPINLOCK(l2x0_lock);
-static uint32_t l2x0_way_mask;	/* Bitmask of active ways */
-static uint32_t l2x0_size;
+static u32 l2x0_way_mask;	/* Bitmask of active ways */
+static u32 l2x0_size;
 
 struct l2x0_regs l2x0_saved_regs;
 
 struct l2x0_of_data {
-	void (*setup)(const struct device_node *, __u32 *, __u32 *);
+	void (*setup)(const struct device_node *, u32 *, u32 *);
 	void (*save)(void);
 	void (*resume)(void);
 };
···
 	raw_spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
-static void l2x0_unlock(__u32 cache_id)
+static void l2x0_unlock(u32 cache_id)
 {
 	int lockregs;
 	int i;
···
 	}
 }
 
-void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
+void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 {
-	__u32 aux;
-	__u32 cache_id;
-	__u32 way_size = 0;
+	u32 aux;
+	u32 cache_id;
+	u32 way_size = 0;
 	int ways;
 	const char *type;
 
···
 
 #ifdef CONFIG_OF
 static void __init l2x0_of_setup(const struct device_node *np,
-				 __u32 *aux_val, __u32 *aux_mask)
+				 u32 *aux_val, u32 *aux_mask)
 {
 	u32 data[2] = { 0, 0 };
 	u32 tag = 0;
···
 }
 
 static void __init pl310_of_setup(const struct device_node *np,
-				  __u32 *aux_val, __u32 *aux_mask)
+				  u32 *aux_val, u32 *aux_mask)
 {
 	u32 data[3] = { 0, 0, 0 };
 	u32 tag[3] = { 0, 0, 0 };
···
 	{}
 };
 
-int __init l2x0_of_init(__u32 aux_val, __u32 aux_mask)
+int __init l2x0_of_init(u32 aux_val, u32 aux_mask)
 {
 	struct device_node *np;
 	struct l2x0_of_data *data;

arch/arm/mm/copypage-v4mc.c

···
 
 #include "mm.h"
 
-/*
- * 0xffff8000 to 0xffffffff is reserved for any ARM architecture
- * specific hacks for copying pages efficiently.
- */
 #define minicache_pgprot __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | \
 				  L_PTE_MT_MINICACHE)
 
···
 
 	raw_spin_lock(&minicache_lock);
 
-	set_pte_ext(TOP_PTE(0xffff8000), pfn_pte(page_to_pfn(from), minicache_pgprot), 0);
-	flush_tlb_kernel_page(0xffff8000);
+	set_top_pte(COPYPAGE_MINICACHE, mk_pte(from, minicache_pgprot));
 
-	mc_copy_user_page((void *)0xffff8000, kto);
+	mc_copy_user_page((void *)COPYPAGE_MINICACHE, kto);
 
 	raw_spin_unlock(&minicache_lock);
 

arch/arm/mm/copypage-v6.c

···
 #error FIX ME
 #endif
 
-#define from_address	(0xffff8000)
-#define to_address	(0xffffc000)
-
 static DEFINE_RAW_SPINLOCK(v6_lock);
 
 /*
···
 	 */
 	raw_spin_lock(&v6_lock);
 
-	set_pte_ext(TOP_PTE(from_address) + offset, pfn_pte(page_to_pfn(from), PAGE_KERNEL), 0);
-	set_pte_ext(TOP_PTE(to_address) + offset, pfn_pte(page_to_pfn(to), PAGE_KERNEL), 0);
+	kfrom = COPYPAGE_V6_FROM + (offset << PAGE_SHIFT);
+	kto   = COPYPAGE_V6_TO + (offset << PAGE_SHIFT);
 
-	kfrom = from_address + (offset << PAGE_SHIFT);
-	kto   = to_address + (offset << PAGE_SHIFT);
-
-	flush_tlb_kernel_page(kfrom);
-	flush_tlb_kernel_page(kto);
+	set_top_pte(kfrom, mk_pte(from, PAGE_KERNEL));
+	set_top_pte(kto, mk_pte(to, PAGE_KERNEL));
 
 	copy_page((void *)kto, (void *)kfrom);
 
···
  */
 static void v6_clear_user_highpage_aliasing(struct page *page, unsigned long vaddr)
 {
-	unsigned int offset = CACHE_COLOUR(vaddr);
-	unsigned long to = to_address + (offset << PAGE_SHIFT);
+	unsigned long to = COPYPAGE_V6_TO + (CACHE_COLOUR(vaddr) << PAGE_SHIFT);
 
 	/* FIXME: not highmem safe */
 	discard_old_kernel_data(page_address(page));
···
 	 */
 	raw_spin_lock(&v6_lock);
 
-	set_pte_ext(TOP_PTE(to_address) + offset, pfn_pte(page_to_pfn(page), PAGE_KERNEL), 0);
-	flush_tlb_kernel_page(to);
+	set_top_pte(to, mk_pte(page, PAGE_KERNEL));
 	clear_page((void *)to);
 
 	raw_spin_unlock(&v6_lock);

arch/arm/mm/copypage-xscale.c

···
 
 #include "mm.h"
 
-/*
- * 0xffff8000 to 0xffffffff is reserved for any ARM architecture
- * specific hacks for copying pages efficiently.
- */
-#define COPYPAGE_MINICACHE	0xffff8000
-
 #define minicache_pgprot __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | \
 				  L_PTE_MT_MINICACHE)
 
···
 
 	raw_spin_lock(&minicache_lock);
 
-	set_pte_ext(TOP_PTE(COPYPAGE_MINICACHE), pfn_pte(page_to_pfn(from), minicache_pgprot), 0);
-	flush_tlb_kernel_page(COPYPAGE_MINICACHE);
+	set_top_pte(COPYPAGE_MINICACHE, mk_pte(from, minicache_pgprot));
 
 	mc_copy_user_page((void *)COPYPAGE_MINICACHE, kto);
 

arch/arm/mm/dma-mapping.c

···
 core_initcall(consistent_init);
 
 static void *
-__dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot)
+__dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot,
+	const void *caller)
 {
 	struct arm_vmregion *c;
 	size_t align;
···
 	 * Allocate a virtual address in the consistent mapping region.
 	 */
 	c = arm_vmregion_alloc(&consistent_head, align, size,
-			    gfp & ~(__GFP_DMA | __GFP_HIGHMEM));
+			    gfp & ~(__GFP_DMA | __GFP_HIGHMEM), caller);
 	if (c) {
 		pte_t *pte;
 		int idx = CONSISTENT_PTE_INDEX(c->vm_start);
···
 
 #else	/* !CONFIG_MMU */
 
-#define __dma_alloc_remap(page, size, gfp, prot)	page_address(page)
+#define __dma_alloc_remap(page, size, gfp, prot, c)	page_address(page)
 #define __dma_free_remap(addr, size)			do { } while (0)
 
 #endif	/* CONFIG_MMU */
 
 static void *
 __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
-	    pgprot_t prot)
+	    pgprot_t prot, const void *caller)
 {
 	struct page *page;
 	void *addr;
···
 		return NULL;
 
 	if (!arch_is_coherent())
-		addr = __dma_alloc_remap(page, size, gfp, prot);
+		addr = __dma_alloc_remap(page, size, gfp, prot, caller);
 	else
 		addr = page_address(page);
 
···
 		return memory;
 
 	return __dma_alloc(dev, size, handle, gfp,
-			   pgprot_dmacoherent(pgprot_kernel));
+			   pgprot_dmacoherent(pgprot_kernel),
+			   __builtin_return_address(0));
 }
 EXPORT_SYMBOL(dma_alloc_coherent);
 
···
 dma_alloc_writecombine(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp)
 {
 	return __dma_alloc(dev, size, handle, gfp,
-			   pgprot_writecombine(pgprot_kernel));
+			   pgprot_writecombine(pgprot_kernel),
+			   __builtin_return_address(0));
 }
 EXPORT_SYMBOL(dma_alloc_writecombine);
 
···
 
 static int __init dma_debug_do_init(void)
 {
+#ifdef CONFIG_MMU
+	arm_vmregion_create_proc("dma-mappings", &consistent_head);
+#endif
 	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
 	return 0;
 }

arch/arm/mm/fault.c

···
 	struct siginfo si;
 
 #ifdef CONFIG_DEBUG_USER
-	if (user_debug & UDBG_SEGV) {
+	if (((user_debug & UDBG_SEGV) && (sig == SIGSEGV)) ||
+	    ((user_debug & UDBG_BUS)  && (sig == SIGBUS))) {
 		printk(KERN_DEBUG "%s: unhandled page fault (%d) at 0x%08lx, code 0x%03x\n",
 		       tsk->comm, sig, addr, fsr);
 		show_pte(tsk->mm, addr);

arch/arm/mm/flush.c

···
 
 #ifdef CONFIG_CPU_CACHE_VIPT
 
-#define ALIAS_FLUSH_START	0xffff4000
-
 static void flush_pfn_alias(unsigned long pfn, unsigned long vaddr)
 {
-	unsigned long to = ALIAS_FLUSH_START + (CACHE_COLOUR(vaddr) << PAGE_SHIFT);
+	unsigned long to = FLUSH_ALIAS_START + (CACHE_COLOUR(vaddr) << PAGE_SHIFT);
 	const int zero = 0;
 
-	set_pte_ext(TOP_PTE(to), pfn_pte(pfn, PAGE_KERNEL), 0);
-	flush_tlb_kernel_page(to);
+	set_top_pte(to, pfn_pte(pfn, PAGE_KERNEL));
 
 	asm(	"mcrr	p15, 0, %1, %0, c14\n"
 	"	mcr	p15, 0, %2, c7, c10, 4"
···
 
 static void flush_icache_alias(unsigned long pfn, unsigned long vaddr, unsigned long len)
 {
-	unsigned long colour = CACHE_COLOUR(vaddr);
+	unsigned long va = FLUSH_ALIAS_START + (CACHE_COLOUR(vaddr) << PAGE_SHIFT);
 	unsigned long offset = vaddr & (PAGE_SIZE - 1);
 	unsigned long to;
 
-	set_pte_ext(TOP_PTE(ALIAS_FLUSH_START) + colour, pfn_pte(pfn, PAGE_KERNEL), 0);
-	to = ALIAS_FLUSH_START + (colour << PAGE_SHIFT) + offset;
-	flush_tlb_kernel_page(to);
+	set_top_pte(va, pfn_pte(pfn, PAGE_KERNEL));
+	to = va + offset;
 	flush_icache_range(to, to + len);
 }
 

arch/arm/mm/highmem.c

···
 	 * With debugging enabled, kunmap_atomic forces that entry to 0.
 	 * Make sure it was indeed properly unmapped.
 	 */
-	BUG_ON(!pte_none(*(TOP_PTE(vaddr))));
+	BUG_ON(!pte_none(get_top_pte(vaddr)));
 #endif
-	set_pte_ext(TOP_PTE(vaddr), mk_pte(page, kmap_prot), 0);
 	/*
 	 * When debugging is off, kunmap_atomic leaves the previous mapping
-	 * in place, so this TLB flush ensures the TLB is updated with the
-	 * new mapping.
+	 * in place, so the contained TLB flush ensures the TLB is updated
+	 * with the new mapping.
 	 */
-	local_flush_tlb_kernel_page(vaddr);
+	set_top_pte(vaddr, mk_pte(page, kmap_prot));
 
 	return (void *)vaddr;
 }
···
 			__cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE);
 #ifdef CONFIG_DEBUG_HIGHMEM
 		BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
-		set_pte_ext(TOP_PTE(vaddr), __pte(0), 0);
-		local_flush_tlb_kernel_page(vaddr);
+		set_top_pte(vaddr, __pte(0));
 #else
 		(void) idx;  /* to kill a warning */
 #endif
···
 	idx = type + KM_TYPE_NR * smp_processor_id();
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
-	BUG_ON(!pte_none(*(TOP_PTE(vaddr))));
+	BUG_ON(!pte_none(get_top_pte(vaddr)));
 #endif
-	set_pte_ext(TOP_PTE(vaddr), pfn_pte(pfn, kmap_prot), 0);
-	local_flush_tlb_kernel_page(vaddr);
+	set_top_pte(vaddr, pfn_pte(pfn, kmap_prot));
 
 	return (void *)vaddr;
 }
···
 struct page *kmap_atomic_to_page(const void *ptr)
 {
 	unsigned long vaddr = (unsigned long)ptr;
-	pte_t *pte;
 
 	if (vaddr < FIXADDR_START)
 		return virt_to_page(ptr);
 
-	pte = TOP_PTE(vaddr);
-	return pte_page(*pte);
+	return pte_page(get_top_pte(vaddr));
 }

arch/arm/mm/init.c

···
 #ifdef CONFIG_HIGHMEM
 			"    pkmap   : 0x%08lx - 0x%08lx   (%4ld MB)\n"
 #endif
+#ifdef CONFIG_MODULES
 			"    modules : 0x%08lx - 0x%08lx   (%4ld MB)\n"
+#endif
 			"      .text : 0x%p" " - 0x%p" "   (%4d kB)\n"
 			"      .init : 0x%p" " - 0x%p" "   (%4d kB)\n"
 			"      .data : 0x%p" " - 0x%p" "   (%4d kB)\n"
···
 			MLM(PKMAP_BASE, (PKMAP_BASE) + (LAST_PKMAP) *
 				(PAGE_SIZE)),
 #endif
+#ifdef CONFIG_MODULES
 			MLM(MODULES_VADDR, MODULES_END),
+#endif
 
 			MLK_ROUNDUP(_text, _etext),
 			MLK_ROUNDUP(__init_begin, __init_end),

arch/arm/mm/mm.h

···
 /* the upper-most page table pointer */
 extern pmd_t *top_pmd;
 
-#define TOP_PTE(x)	pte_offset_kernel(top_pmd, x)
+/*
+ * 0xffff8000 to 0xffffffff is reserved for any ARM architecture
+ * specific hacks for copying pages efficiently, while 0xffff4000
+ * is reserved for VIPT aliasing flushing by generic code.
+ *
+ * Note that we don't allow VIPT aliasing caches with SMP.
+ */
+#define COPYPAGE_MINICACHE	0xffff8000
+#define COPYPAGE_V6_FROM	0xffff8000
+#define COPYPAGE_V6_TO		0xffffc000
+/* PFN alias flushing, for VIPT caches */
+#define FLUSH_ALIAS_START	0xffff4000
+
+static inline void set_top_pte(unsigned long va, pte_t pte)
+{
+	pte_t *ptep = pte_offset_kernel(top_pmd, va);
+	set_pte_ext(ptep, pte, 0);
+	local_flush_tlb_kernel_page(va);
+}
+
+static inline pte_t get_top_pte(unsigned long va)
+{
+	pte_t *ptep = pte_offset_kernel(top_pmd, va);
+	return *ptep;
+}
 
 static inline pmd_t *pmd_off_k(unsigned long virt)
 {

arch/arm/mm/mmu.c

···
 {
 	struct map_desc map;
 	unsigned long addr;
+	void *vectors;
 
 	/*
 	 * Allocate the vector page early.
 	 */
-	vectors_page = early_alloc(PAGE_SIZE);
+	vectors = early_alloc(PAGE_SIZE);
+
+	early_trap_init(vectors);
 
 	for (addr = VMALLOC_START; addr; addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
···
 	 * location (0xffff0000).  If we aren't using high-vectors, also
 	 * create a mapping at the low-vectors virtual address.
 	 */
-	map.pfn = __phys_to_pfn(virt_to_phys(vectors_page));
+	map.pfn = __phys_to_pfn(virt_to_phys(vectors));
 	map.virtual = 0xffff0000;
 	map.length = PAGE_SIZE;
 	map.type = MT_HIGH_VECTORS;

arch/arm/mm/vmregion.c

···
+#include <linux/fs.h>
 #include <linux/spinlock.h>
 #include <linux/list.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <linux/slab.h>
 
 #include "vmregion.h"
···
 
 struct arm_vmregion *
 arm_vmregion_alloc(struct arm_vmregion_head *head, size_t align,
-		   size_t size, gfp_t gfp)
+		   size_t size, gfp_t gfp, const void *caller)
 {
 	unsigned long start = head->vm_start, addr = head->vm_end;
 	unsigned long flags;
···
 	new = kmalloc(sizeof(struct arm_vmregion), gfp);
 	if (!new)
 		goto out;
+
+	new->caller = caller;
 
 	spin_lock_irqsave(&head->vm_lock, flags);
 
···
 
 	kfree(c);
 }
+
+#ifdef CONFIG_PROC_FS
+static int arm_vmregion_show(struct seq_file *m, void *p)
+{
+	struct arm_vmregion *c = list_entry(p, struct arm_vmregion, vm_list);
+
+	seq_printf(m, "0x%08lx-0x%08lx %7lu", c->vm_start, c->vm_end,
+		c->vm_end - c->vm_start);
+	if (c->caller)
+		seq_printf(m, " %pS", (void *)c->caller);
+	seq_putc(m, '\n');
+	return 0;
+}
+
+static void *arm_vmregion_start(struct seq_file *m, loff_t *pos)
+{
+	struct arm_vmregion_head *h = m->private;
+	spin_lock_irq(&h->vm_lock);
+	return seq_list_start(&h->vm_list, *pos);
+}
+
+static void *arm_vmregion_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	struct arm_vmregion_head *h = m->private;
+	return seq_list_next(p, &h->vm_list, pos);
+}
+
+static void arm_vmregion_stop(struct seq_file *m, void *p)
+{
+	struct arm_vmregion_head *h = m->private;
+	spin_unlock_irq(&h->vm_lock);
+}
+
+static const struct seq_operations arm_vmregion_ops = {
+	.start	= arm_vmregion_start,
+	.stop	= arm_vmregion_stop,
+	.next	= arm_vmregion_next,
+	.show	= arm_vmregion_show,
+};
+
+static int arm_vmregion_open(struct inode *inode, struct file *file)
+{
+	struct arm_vmregion_head *h = PDE(inode)->data;
+	int ret = seq_open(file, &arm_vmregion_ops);
+	if (!ret) {
+		struct seq_file *m = file->private_data;
+		m->private = h;
+	}
+	return ret;
+}
+
+static const struct file_operations arm_vmregion_fops = {
+	.open	= arm_vmregion_open,
+	.read	= seq_read,
+	.llseek	= seq_lseek,
+	.release = seq_release,
+};
+
+int arm_vmregion_create_proc(const char *path, struct arm_vmregion_head *h)
+{
+	proc_create_data(path, S_IRUSR, NULL, &arm_vmregion_fops, h);
+	return 0;
+}
+#else
+int arm_vmregion_create_proc(const char *path, struct arm_vmregion_head *h)
+{
+	return 0;
+}
+#endif

arch/arm/mm/vmregion.h

···
 	unsigned long		vm_end;
 	struct page		*vm_pages;
 	int			vm_active;
+	const void		*caller;
 };
 
-struct arm_vmregion *arm_vmregion_alloc(struct arm_vmregion_head *, size_t, size_t, gfp_t);
+struct arm_vmregion *arm_vmregion_alloc(struct arm_vmregion_head *, size_t, size_t, gfp_t, const void *);
 struct arm_vmregion *arm_vmregion_find(struct arm_vmregion_head *, unsigned long);
 struct arm_vmregion *arm_vmregion_find_remove(struct arm_vmregion_head *, unsigned long);
 void arm_vmregion_free(struct arm_vmregion_head *, struct arm_vmregion *);
+
+int arm_vmregion_create_proc(const char *, struct arm_vmregion_head *);
 
 #endif

arch/arm/net/Makefile

···
+# ARM-specific networking code
+
+obj-$(CONFIG_BPF_JIT) += bpf_jit_32.o

arch/arm/net/bpf_jit_32.c

···
+/*
+ * Just-In-Time compiler for BPF filters on 32bit ARM
+ *
+ * Copyright (c) 2011 Mircea Gherzan <[e-mail]>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; version 2 of the License.
+ */
+
+#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/filter.h>
+#include <linux/moduleloader.h>
+#include <linux/netdevice.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <asm/cacheflush.h>
+#include <asm/hwcap.h>
+
+#include "bpf_jit_32.h"
+
+/*
+ * ABI:
+ *
+ * r0	scratch register
+ * r4	BPF register A
+ * r5	BPF register X
+ * r6	pointer to the skb
+ * r7	skb->data
+ * r8	skb_headlen(skb)
+ */
+
+#define r_scratch	ARM_R0
+/* r1-r3 are (also) used for the unaligned loads on the non-ARMv7 slowpath */
+#define r_off		ARM_R1
+#define r_A		ARM_R4
+#define r_X		ARM_R5
+#define r_skb		ARM_R6
+#define r_skb_data	ARM_R7
+#define r_skb_hl	ARM_R8
+
+#define SCRATCH_SP_OFFSET	0
+#define SCRATCH_OFF(k)		(SCRATCH_SP_OFFSET + (k))
+
+#define SEEN_MEM		((1 << BPF_MEMWORDS) - 1)
+#define SEEN_MEM_WORD(k)	(1 << (k))
+#define SEEN_X			(1 << BPF_MEMWORDS)
+#define SEEN_CALL		(1 << (BPF_MEMWORDS + 1))
+#define SEEN_SKB		(1 << (BPF_MEMWORDS + 2))
+#define SEEN_DATA		(1 << (BPF_MEMWORDS + 3))
+
+#define FLAG_NEED_X_RESET	(1 << 0)
+
+struct jit_ctx {
+	const struct sk_filter *skf;
+	unsigned idx;
+	unsigned prologue_bytes;
+	int ret0_fp_idx;
+	u32 seen;
+	u32 flags;
+	u32 *offsets;
+	u32 *target;
+#if __LINUX_ARM_ARCH__ < 7
+	u16 epilogue_bytes;
+	u16 imm_count;
+	u32 *imms;
+#endif
+};
+
+int bpf_jit_enable __read_mostly;
+
+static u64 jit_get_skb_b(struct sk_buff *skb, unsigned offset)
+{
+	u8 ret;
+	int err;
+
+	err = skb_copy_bits(skb, offset, &ret, 1);
+
+	return (u64)err << 32 | ret;
+}
+
+static u64 jit_get_skb_h(struct sk_buff *skb, unsigned offset)
+{
+	u16 ret;
+	int err;
+
+	err = skb_copy_bits(skb, offset, &ret, 2);
+
+	return (u64)err << 32 | ntohs(ret);
+}
+
+static u64 jit_get_skb_w(struct sk_buff *skb, unsigned offset)
+{
+	u32 ret;
+	int err;
+
+	err = skb_copy_bits(skb, offset, &ret, 4);
+
+	return (u64)err << 32 | ntohl(ret);
+}
+
+/*
+ * Wrapper that handles both OABI and EABI and assures Thumb2 interworking
+ * (where the assembly routines like __aeabi_uidiv could cause problems).
+ */
+static u32 jit_udiv(u32 dividend, u32 divisor)
+{
+	return dividend / divisor;
+}
+
+static inline void _emit(int cond, u32 inst, struct jit_ctx *ctx)
+{
+	if (ctx->target != NULL)
+		ctx->target[ctx->idx] = inst | (cond << 28);
+
+	ctx->idx++;
+}
+
+/*
+ * Emit an instruction that will be executed unconditionally.
+ */
+static inline void emit(u32 inst, struct jit_ctx *ctx)
+{
+	_emit(ARM_COND_AL, inst, ctx);
+}
+
+static u16 saved_regs(struct jit_ctx *ctx)
+{
+	u16 ret = 0;
+
+	if ((ctx->skf->len > 1) ||
+	    (ctx->skf->insns[0].code == BPF_S_RET_A))
+		ret |= 1 << r_A;
+
+#ifdef CONFIG_FRAME_POINTER
+	ret |= (1 << ARM_FP) | (1 << ARM_IP) | (1 << ARM_LR) | (1 << ARM_PC);
+#else
+	if (ctx->seen & SEEN_CALL)
+		ret |= 1 << ARM_LR;
+#endif
+	if (ctx->seen & (SEEN_DATA | SEEN_SKB))
+		ret |= 1 << r_skb;
+	if (ctx->seen & SEEN_DATA)
+		ret |= (1 << r_skb_data) | (1 << r_skb_hl);
+	if (ctx->seen & SEEN_X)
+		ret |= 1 << r_X;
+
+	return ret;
+}
+
+static inline int mem_words_used(struct jit_ctx *ctx)
+{
+	/* yes, we do waste some stack space IF there are "holes" in the set" */
+	return fls(ctx->seen & SEEN_MEM);
+}
+
+static inline bool is_load_to_a(u16 inst)
+{
+	switch (inst) {
+	case BPF_S_LD_W_LEN:
+	case BPF_S_LD_W_ABS:
+	case BPF_S_LD_H_ABS:
+	case BPF_S_LD_B_ABS:
+	case BPF_S_ANC_CPU:
+	case BPF_S_ANC_IFINDEX:
+	case BPF_S_ANC_MARK:
+	case BPF_S_ANC_PROTOCOL:
+	case BPF_S_ANC_RXHASH:
+	case BPF_S_ANC_QUEUE:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static void build_prologue(struct jit_ctx *ctx)
+{
+	u16 reg_set = saved_regs(ctx);
+	u16 first_inst = ctx->skf->insns[0].code;
+	u16 off;
+
+#ifdef CONFIG_FRAME_POINTER
+	emit(ARM_MOV_R(ARM_IP, ARM_SP), ctx);
+	emit(ARM_PUSH(reg_set), ctx);
+	emit(ARM_SUB_I(ARM_FP, ARM_IP, 4), ctx);
+#else
+	if (reg_set)
+		emit(ARM_PUSH(reg_set), ctx);
+#endif
+
+	if (ctx->seen & (SEEN_DATA | SEEN_SKB))
+		emit(ARM_MOV_R(r_skb, ARM_R0), ctx);
+
+	if (ctx->seen & SEEN_DATA) {
+		off = offsetof(struct sk_buff, data);
+		emit(ARM_LDR_I(r_skb_data, r_skb, off), ctx);
+		/* headlen = len - data_len */
+		off = offsetof(struct sk_buff, len);
+		emit(ARM_LDR_I(r_skb_hl, r_skb, off), ctx);
+		off = offsetof(struct sk_buff, data_len);
+		emit(ARM_LDR_I(r_scratch, r_skb, off), ctx);
+		emit(ARM_SUB_R(r_skb_hl, r_skb_hl, r_scratch), ctx);
+	}
+
+	if (ctx->flags & FLAG_NEED_X_RESET)
+		emit(ARM_MOV_I(r_X, 0), ctx);
+
+	/* do not leak kernel data to userspace */
+	if ((first_inst != BPF_S_RET_K) && !(is_load_to_a(first_inst)))
+		emit(ARM_MOV_I(r_A, 0), ctx);
+
+	/* stack space for the BPF_MEM words */
+	if (ctx->seen & SEEN_MEM)
+		emit(ARM_SUB_I(ARM_SP, ARM_SP, mem_words_used(ctx) * 4), ctx);
+}
+
+static void build_epilogue(struct jit_ctx *ctx)
+{
+	u16 reg_set = saved_regs(ctx);
+
+	if (ctx->seen & SEEN_MEM)
+		emit(ARM_ADD_I(ARM_SP, ARM_SP, mem_words_used(ctx) * 4), ctx);
+
+	reg_set &= ~(1 << ARM_LR);
+
+#ifdef CONFIG_FRAME_POINTER
+	/* the first instruction of the prologue was: mov ip, sp */
+	reg_set &= ~(1 << ARM_IP);
+	reg_set |= (1 << ARM_SP);
+	emit(ARM_LDM(ARM_SP, reg_set), ctx);
+#else
+	if (reg_set) {
+		if (ctx->seen & SEEN_CALL)
+			reg_set |= 1 << ARM_PC;
+		emit(ARM_POP(reg_set), ctx);
+	}
+
+	if (!(ctx->seen & SEEN_CALL))
+		emit(ARM_BX(ARM_LR), ctx);
+#endif
+}
+
+static int16_t imm8m(u32 x)
+{
+	u32 rot;
+
+	for (rot = 0; rot < 16; rot++)
+		if ((x & ~ror32(0xff, 2 * rot)) == 0)
+			return rol32(x, 2 * rot) | (rot << 8);
+
+	return -1;
+}
+
+#if __LINUX_ARM_ARCH__ < 7
+
+static u16 imm_offset(u32 k, struct jit_ctx *ctx)
+{
+	unsigned i = 0, offset;
+	u16 imm;
+
+	/* on the "fake" run we just count them (duplicates included) */
+	if (ctx->target == NULL) {
+		ctx->imm_count++;
+		return 0;
+	}
+
+	while ((i < ctx->imm_count) && ctx->imms[i]) {
+		if (ctx->imms[i] == k)
+			break;
+		i++;
+	}
+
+	if (ctx->imms[i] == 0)
+		ctx->imms[i] = k;
+
+	/* constants go just after the epilogue */
+	offset =  ctx->offsets[ctx->skf->len];
+	offset += ctx->prologue_bytes;
+	offset += ctx->epilogue_bytes;
+	offset += i * 4;
+
+	ctx->target[offset / 4] = k;
+
+	/* PC in ARM mode == address of the instruction + 8 */
+	imm = offset - (8 + ctx->idx * 4);
+
+	return imm;
+}
+
+#endif /* __LINUX_ARM_ARCH__ */
+
+/*
+ * Move an immediate that's not an imm8m to a core register.
+ */
+static inline void emit_mov_i_no8m(int rd, u32 val, struct jit_ctx *ctx)
+{
+#if __LINUX_ARM_ARCH__ < 7
+	emit(ARM_LDR_I(rd, ARM_PC, imm_offset(val, ctx)), ctx);
+#else
+	emit(ARM_MOVW(rd, val & 0xffff), ctx);
+	if (val > 0xffff)
+		emit(ARM_MOVT(rd, val >> 16), ctx);
+#endif
+}
+
+static inline void emit_mov_i(int rd, u32 val, struct jit_ctx *ctx)
+{
+	int imm12 = imm8m(val);
+
+	if (imm12 >= 0)
+		emit(ARM_MOV_I(rd, imm12), ctx);
+	else
+		emit_mov_i_no8m(rd, val, ctx);
+}
+
+#if __LINUX_ARM_ARCH__ < 6
+
+static void emit_load_be32(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
+{
+	_emit(cond, ARM_LDRB_I(ARM_R3, r_addr, 1), ctx);
+	_emit(cond, ARM_LDRB_I(ARM_R1, r_addr, 0), ctx);
+	_emit(cond, ARM_LDRB_I(ARM_R2, r_addr, 3), ctx);
+	_emit(cond, ARM_LSL_I(ARM_R3, ARM_R3, 16), ctx);
+	_emit(cond, ARM_LDRB_I(ARM_R0, r_addr, 2), ctx);
+	_emit(cond, ARM_ORR_S(ARM_R3, ARM_R3, ARM_R1, SRTYPE_LSL, 24), ctx);
+	_emit(cond, ARM_ORR_R(ARM_R3, ARM_R3, ARM_R2), ctx);
+	_emit(cond, ARM_ORR_S(r_res, ARM_R3, ARM_R0, SRTYPE_LSL, 8), ctx);
+}
+
+static void emit_load_be16(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
+{
+	_emit(cond, ARM_LDRB_I(ARM_R1, r_addr, 0), ctx);
+	_emit(cond, ARM_LDRB_I(ARM_R2, r_addr, 1), ctx);
+	_emit(cond, ARM_ORR_S(r_res, ARM_R2, ARM_R1, SRTYPE_LSL, 8), ctx);
+}
+
+static inline void emit_swap16(u8 r_dst, u8 r_src, struct jit_ctx *ctx)
+{
+	emit(ARM_LSL_R(ARM_R1, r_src, 8), ctx);
+	emit(ARM_ORR_S(r_dst, ARM_R1, r_src, SRTYPE_LSL, 8), ctx);
+	emit(ARM_LSL_I(r_dst, r_dst, 8), ctx);
+	emit(ARM_LSL_R(r_dst, r_dst, 8), ctx);
+}
+
+#else  /* ARMv6+ */
+
+static void emit_load_be32(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
+{
+	_emit(cond, ARM_LDR_I(r_res, r_addr, 0), ctx);
+#ifdef __LITTLE_ENDIAN
+	_emit(cond, ARM_REV(r_res, r_res), ctx);
+#endif
+}
+
+static void emit_load_be16(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
+{
+	_emit(cond, ARM_LDRH_I(r_res, r_addr, 0), ctx);
+#ifdef __LITTLE_ENDIAN
+	_emit(cond, ARM_REV16(r_res, r_res), ctx);
+#endif
+}
+
+static inline void emit_swap16(u8 r_dst __maybe_unused,
+			       u8 r_src __maybe_unused,
+			       struct jit_ctx *ctx __maybe_unused)
+{
+#ifdef __LITTLE_ENDIAN
+	emit(ARM_REV16(r_dst, r_src), ctx);
+#endif
+}
+
+#endif /* __LINUX_ARM_ARCH__ < 6 */
+
+
+/* Compute the immediate value for a PC-relative branch. */
+static inline u32 b_imm(unsigned tgt, struct jit_ctx *ctx)
+{
+	u32 imm;
+
+	if (ctx->target == NULL)
+		return 0;
+	/*
+	 * BPF allows only forward jumps and the offset of the target is
+	 * still the one computed during the first pass.
+	 */
+	imm  = ctx->offsets[tgt] + ctx->prologue_bytes - (ctx->idx * 4 + 8);
+
+	return imm >> 2;
+}
+
+#define OP_IMM3(op, r1, r2, imm_val, ctx)				\
+	do {								\
+		imm12 = imm8m(imm_val);					\
+		if (imm12 < 0) {					\
+			emit_mov_i_no8m(r_scratch, imm_val, ctx);	\
+			emit(op ## _R((r1), (r2), r_scratch), ctx);	\
+		} else {						\
+			emit(op ## _I((r1), (r2), imm12), ctx);		\
+		}							\
+	} while (0)
+
+static inline void emit_err_ret(u8 cond, struct jit_ctx *ctx)
+{
+	if (ctx->ret0_fp_idx >= 0) {
+		_emit(cond, ARM_B(b_imm(ctx->ret0_fp_idx, ctx)), ctx);
+		/* NOP to keep the size constant between passes */
+		emit(ARM_MOV_R(ARM_R0, ARM_R0), ctx);
+	} else {
+		_emit(cond, ARM_MOV_I(ARM_R0, 0), ctx);
+		_emit(cond, ARM_B(b_imm(ctx->skf->len, ctx)), ctx);
+	}
+}
+
+static inline void emit_blx_r(u8 tgt_reg, struct jit_ctx *ctx)
+{
+#if __LINUX_ARM_ARCH__ < 5
+	emit(ARM_MOV_R(ARM_LR, ARM_PC), ctx);
+
+	if (elf_hwcap & HWCAP_THUMB)
+		emit(ARM_BX(tgt_reg), ctx);
+	else
+		emit(ARM_MOV_R(ARM_PC, tgt_reg), ctx);
+#else
+	emit(ARM_BLX_R(tgt_reg), ctx);
+#endif
+}
+
+static inline void emit_udiv(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx)
+{
+#if __LINUX_ARM_ARCH__ == 7
+	if (elf_hwcap & HWCAP_IDIVA) {
+		emit(ARM_UDIV(rd, rm, rn), ctx);
+		return;
+	}
+#endif
+	if (rm != ARM_R0)
+		emit(ARM_MOV_R(ARM_R0, rm), ctx);
+	if (rn != ARM_R1)
+		emit(ARM_MOV_R(ARM_R1, rn), ctx);
+
+	ctx->seen |= SEEN_CALL;
+	emit_mov_i(ARM_R3, (u32)jit_udiv, ctx);
+	emit_blx_r(ARM_R3, ctx);
+
+	if (rd != ARM_R0)
+		emit(ARM_MOV_R(rd, ARM_R0), ctx);
+}
+
+static inline void update_on_xread(struct jit_ctx *ctx)
+{
+	if (!(ctx->seen & SEEN_X))
+		ctx->flags |= FLAG_NEED_X_RESET;
+
+	ctx->seen |= SEEN_X;
+}
+
+static int build_body(struct jit_ctx *ctx)
+{
+	void *load_func[] = {jit_get_skb_b, jit_get_skb_h, jit_get_skb_w};
+	const struct sk_filter *prog = ctx->skf;
+	const struct sock_filter *inst;
+	unsigned i, load_order, off, condt;
+	int imm12;
+	u32 k;
+
+	for (i = 0; i < prog->len; i++) {
+		inst = &(prog->insns[i]);
+		/* K as an immediate value operand */
+		k = inst->k;
+
+		/* compute offsets only in the fake pass */
+		if (ctx->target == NULL)
+			ctx->offsets[i] = ctx->idx * 4;
+
+		switch (inst->code) {
+		case BPF_S_LD_IMM:
+			emit_mov_i(r_A, k, ctx);
+			break;
+		case BPF_S_LD_W_LEN:
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4);
+			emit(ARM_LDR_I(r_A, r_skb,
+				       offsetof(struct sk_buff, len)), ctx);
+			break;
+		case BPF_S_LD_MEM:
+			/* A = scratch[k] */
+			ctx->seen |= SEEN_MEM_WORD(k);
+			emit(ARM_LDR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx);
+			break;
+		case BPF_S_LD_W_ABS:
+			load_order = 2;
+			goto load;
+		case BPF_S_LD_H_ABS:
+			load_order = 1;
+			goto load;
+		case BPF_S_LD_B_ABS:
+			load_order = 0;
+load:
+			/* the interpreter will deal with the negative K */
+			if ((int)k < 0)
+				return -ENOTSUPP;
+			emit_mov_i(r_off, k, ctx);
+load_common:
+			ctx->seen |= SEEN_DATA | SEEN_CALL;
+
+			if (load_order > 0) {
+				emit(ARM_SUB_I(r_scratch, r_skb_hl,
+					       1 << load_order), ctx);
+				emit(ARM_CMP_R(r_scratch, r_off), ctx);
+				condt = ARM_COND_HS;
+			} else {
+				emit(ARM_CMP_R(r_skb_hl, r_off), ctx);
+				condt = ARM_COND_HI;
+			}
+
+			_emit(condt, ARM_ADD_R(r_scratch, r_off, r_skb_data),
+			      ctx);
+
+			if (load_order == 0)
+				_emit(condt, ARM_LDRB_I(r_A, r_scratch, 0),
+				      ctx);
+			else if (load_order == 1)
+				emit_load_be16(condt, r_A, r_scratch, ctx);
+			else if (load_order == 2)
+				emit_load_be32(condt, r_A, r_scratch, ctx);
+
+			_emit(condt, ARM_B(b_imm(i + 1, ctx)), ctx);
+
+			/* the slowpath */
+			emit_mov_i(ARM_R3, (u32)load_func[load_order], ctx);
+			emit(ARM_MOV_R(ARM_R0, r_skb), ctx);
+			/* the offset is already in R1 */
+			emit_blx_r(ARM_R3, ctx);
+			/* check the result of skb_copy_bits */
+			emit(ARM_CMP_I(ARM_R1, 0), ctx);
+			emit_err_ret(ARM_COND_NE, ctx);
+			emit(ARM_MOV_R(r_A, ARM_R0), ctx);
+			break;
+		case BPF_S_LD_W_IND:
+			load_order = 2;
+			goto load_ind;
+		case BPF_S_LD_H_IND:
+			load_order = 1;
+			goto load_ind;
+		case BPF_S_LD_B_IND:
+			load_order = 0;
+load_ind:
+			OP_IMM3(ARM_ADD, r_off, r_X, k, ctx);
+			goto load_common;
+		case BPF_S_LDX_IMM:
+			ctx->seen |= SEEN_X;
+			emit_mov_i(r_X, k, ctx);
+			break;
+		case BPF_S_LDX_W_LEN:
+			ctx->seen |= SEEN_X | SEEN_SKB;
+			emit(ARM_LDR_I(r_X, r_skb,
+				       offsetof(struct sk_buff, len)), ctx);
+			break;
+		case BPF_S_LDX_MEM:
+			ctx->seen |= SEEN_X | SEEN_MEM_WORD(k);
+			emit(ARM_LDR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx);
+			break;
+		case BPF_S_LDX_B_MSH:
+			/* x = ((*(frame + k)) & 0xf) << 2; */
+			ctx->seen |= SEEN_X | SEEN_DATA | SEEN_CALL;
+			/* the interpreter should deal with the negative K */
+			if (k < 0)
+				return -1;
+			/* offset in r1: we might have to take the slow path */
+			emit_mov_i(r_off, k, ctx);
+			emit(ARM_CMP_R(r_skb_hl, r_off), ctx);
+
+			/* load in r0: common with the slowpath */
+			_emit(ARM_COND_HI, ARM_LDRB_R(ARM_R0, r_skb_data,
+						      ARM_R1), ctx);
+			/*
+			 * emit_mov_i() might generate one or two instructions,
+			 * the same holds for emit_blx_r()
+			 */
+			_emit(ARM_COND_HI, ARM_B(b_imm(i + 1, ctx) - 2), ctx);
+
+			emit(ARM_MOV_R(ARM_R0, r_skb), ctx);
+			/* r_off is r1 */
+			emit_mov_i(ARM_R3, (u32)jit_get_skb_b, ctx);
+			emit_blx_r(ARM_R3, ctx);
+			/* check the return value of skb_copy_bits */
+			emit(ARM_CMP_I(ARM_R1, 0), ctx);
+			emit_err_ret(ARM_COND_NE, ctx);
+
+			emit(ARM_AND_I(r_X, ARM_R0, 0x00f), ctx);
+			emit(ARM_LSL_I(r_X, r_X, 2), ctx);
+			break;
+		case BPF_S_ST:
+			ctx->seen |= SEEN_MEM_WORD(k);
+			emit(ARM_STR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx);
+			break;
+		case BPF_S_STX:
+			update_on_xread(ctx);
+			ctx->seen |= SEEN_MEM_WORD(k);
+			emit(ARM_STR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx);
+			break;
+		case BPF_S_ALU_ADD_K:
+			/* A += K */
+			OP_IMM3(ARM_ADD, r_A, r_A, k, ctx);
+			break;
+		case BPF_S_ALU_ADD_X:
+			update_on_xread(ctx);
+			emit(ARM_ADD_R(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_SUB_K:
+			/* A -= K */
+			OP_IMM3(ARM_SUB, r_A, r_A, k, ctx);
+			break;
+		case BPF_S_ALU_SUB_X:
+			update_on_xread(ctx);
+			emit(ARM_SUB_R(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_MUL_K:
+			/* A *= K */
+			emit_mov_i(r_scratch, k, ctx);
+			emit(ARM_MUL(r_A, r_A, r_scratch), ctx);
+			break;
+		case BPF_S_ALU_MUL_X:
+			update_on_xread(ctx);
+			emit(ARM_MUL(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_DIV_K:
+			/* current k == reciprocal_value(userspace k) */
+			emit_mov_i(r_scratch, k, ctx);
+			/* A = top 32 bits of the product */
+			emit(ARM_UMULL(r_scratch, r_A, r_A, r_scratch), ctx);
+			break;
+		case BPF_S_ALU_DIV_X:
+			update_on_xread(ctx);
+			emit(ARM_CMP_I(r_X, 0), ctx);
+			emit_err_ret(ARM_COND_EQ, ctx);
+			emit_udiv(r_A, r_A, r_X, ctx);
+			break;
+		case BPF_S_ALU_OR_K:
+			/* A |= K */
+			OP_IMM3(ARM_ORR, r_A, r_A, k, ctx);
+			break;
+		case BPF_S_ALU_OR_X:
+			update_on_xread(ctx);
+			emit(ARM_ORR_R(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_AND_K:
+			/* A &= K */
+			OP_IMM3(ARM_AND, r_A, r_A, k, ctx);
+			break;
+		case BPF_S_ALU_AND_X:
+			update_on_xread(ctx);
+			emit(ARM_AND_R(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_LSH_K:
+			if (unlikely(k > 31))
+				return -1;
+			emit(ARM_LSL_I(r_A, r_A, k), ctx);
+			break;
+		case BPF_S_ALU_LSH_X:
+			update_on_xread(ctx);
+			emit(ARM_LSL_R(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_RSH_K:
+			if (unlikely(k > 31))
+				return -1;
+			emit(ARM_LSR_I(r_A, r_A, k), ctx);
+			break;
+		case BPF_S_ALU_RSH_X:
+			update_on_xread(ctx);
+			emit(ARM_LSR_R(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_NEG:
+			/* A = -A */
+			emit(ARM_RSB_I(r_A, r_A, 0), ctx);
+			break;
+		case BPF_S_JMP_JA:
+			/* pc += K */
+			emit(ARM_B(b_imm(i + k + 1, ctx)), ctx);
+			break;
+		case BPF_S_JMP_JEQ_K:
+			/* pc += (A == K) ? pc->jt : pc->jf */
+			condt  = ARM_COND_EQ;
+			goto cmp_imm;
+		case BPF_S_JMP_JGT_K:
+			/* pc += (A > K) ? pc->jt : pc->jf */
+			condt  = ARM_COND_HI;
+			goto cmp_imm;
+		case BPF_S_JMP_JGE_K:
+			/* pc += (A >= K) ? pc->jt : pc->jf */
+			condt  = ARM_COND_HS;
+cmp_imm:
+			imm12 = imm8m(k);
+			if (imm12 < 0) {
+				emit_mov_i_no8m(r_scratch, k, ctx);
+				emit(ARM_CMP_R(r_A, r_scratch), ctx);
+			} else {
+				emit(ARM_CMP_I(r_A, imm12), ctx);
+			}
+cond_jump:
+			if (inst->jt)
+				_emit(condt, ARM_B(b_imm(i + inst->jt + 1,
+						   ctx)), ctx);
+			if (inst->jf)
+				_emit(condt ^ 1, ARM_B(b_imm(i + inst->jf + 1,
+							     ctx)), ctx);
+			break;
+		case BPF_S_JMP_JEQ_X:
+			/* pc += (A == X) ? pc->jt : pc->jf */
+			condt   = ARM_COND_EQ;
+			goto cmp_x;
+		case BPF_S_JMP_JGT_X:
+			/* pc += (A > X) ? pc->jt : pc->jf */
+			condt   = ARM_COND_HI;
+			goto cmp_x;
+		case BPF_S_JMP_JGE_X:
+			/* pc += (A >= X) ? pc->jt : pc->jf */
+			condt   = ARM_COND_CS;
+cmp_x:
+			update_on_xread(ctx);
+			emit(ARM_CMP_R(r_A, r_X), ctx);
+			goto cond_jump;
+		case BPF_S_JMP_JSET_K:
+			/* pc += (A & K) ? pc->jt : pc->jf */
+			condt  = ARM_COND_NE;
+			/* not set iff all zeroes iff Z==1 iff EQ */
+
+			imm12 = imm8m(k);
+			if (imm12 < 0) {
+				emit_mov_i_no8m(r_scratch, k, ctx);
+				emit(ARM_TST_R(r_A, r_scratch), ctx);
+			} else {
+				emit(ARM_TST_I(r_A, imm12), ctx);
+			}
+			goto cond_jump;
+		case BPF_S_JMP_JSET_X:
+			/* pc += (A & X) ? pc->jt : pc->jf */
+			update_on_xread(ctx);
+			condt  = ARM_COND_NE;
+			emit(ARM_TST_R(r_A, r_X), ctx);
+			goto cond_jump;
+		case BPF_S_RET_A:
+			emit(ARM_MOV_R(ARM_R0, r_A), ctx);
+			goto b_epilogue;
+		case BPF_S_RET_K:
+			if ((k == 0) && (ctx->ret0_fp_idx < 0))
+				ctx->ret0_fp_idx = i;
+			emit_mov_i(ARM_R0, k, ctx);
+b_epilogue:
+			if (i != ctx->skf->len - 1)
+				emit(ARM_B(b_imm(prog->len, ctx)), ctx);
+			break;
+		case BPF_S_MISC_TAX:
+			/* X = A */
+			ctx->seen |= SEEN_X;
+			emit(ARM_MOV_R(r_X, r_A), ctx);
+			break;
+		case BPF_S_MISC_TXA:
+			/* A = X */
+			update_on_xread(ctx);
+			emit(ARM_MOV_R(r_A, r_X), ctx);
+			break;
+		case BPF_S_ANC_PROTOCOL:
+			/* A = ntohs(skb->protocol) */
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
+						  protocol) != 2);
+			off = offsetof(struct sk_buff, protocol);
+			emit(ARM_LDRH_I(r_scratch, r_skb, off), ctx);
+			emit_swap16(r_A, r_scratch, ctx);
+			break;
+		case BPF_S_ANC_CPU:
+			/* r_scratch = current_thread_info() */
+			OP_IMM3(ARM_BIC, r_scratch, ARM_SP, THREAD_SIZE - 1, ctx);
+			/* A = current_thread_info()->cpu */
+			BUILD_BUG_ON(FIELD_SIZEOF(struct thread_info, cpu) != 4);
+			off = offsetof(struct thread_info, cpu);
+			emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
+			break;
+		case BPF_S_ANC_IFINDEX:
+			/* A = skb->dev->ifindex */
+			ctx->seen |= SEEN_SKB;
+			off = offsetof(struct sk_buff, dev);
+			emit(ARM_LDR_I(r_scratch, r_skb, off), ctx);
+
+			emit(ARM_CMP_I(r_scratch, 0), ctx);
+			emit_err_ret(ARM_COND_EQ, ctx);
+
+			BUILD_BUG_ON(FIELD_SIZEOF(struct net_device,
+						  ifindex) != 4);
+			off = offsetof(struct net_device, ifindex);
+			emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
+			break;
+		case BPF_S_ANC_MARK:
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
+			off = offsetof(struct sk_buff, mark);
+			emit(ARM_LDR_I(r_A, r_skb, off), ctx);
+			break;
+		case BPF_S_ANC_RXHASH:
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, rxhash) != 4);
+			off = offsetof(struct sk_buff, rxhash);
+			emit(ARM_LDR_I(r_A, r_skb, off), ctx);
+			break;
+		case BPF_S_ANC_QUEUE:
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
+						  queue_mapping) != 2);
+			BUILD_BUG_ON(offsetof(struct sk_buff,
+					      queue_mapping) > 0xff);
+			off = offsetof(struct sk_buff, queue_mapping);
+			emit(ARM_LDRH_I(r_A, r_skb, off), ctx);
+			break;
+		default:
+			return -1;
+		}
+	}
+
+	/* compute offsets only during the first pass */
+	if (ctx->target == NULL)
+		ctx->offsets[i] = ctx->idx * 4;
+
+	return 0;
+}
+
+
+void bpf_jit_compile(struct sk_filter *fp)
+{
+	struct jit_ctx ctx;
+	unsigned tmp_idx;
+	unsigned alloc_size;
+
+	if (!bpf_jit_enable)
+		return;
+
+	memset(&ctx, 0, sizeof(ctx));
+	ctx.skf		= fp;
+	ctx.ret0_fp_idx = -1;
+
+	ctx.offsets = kzalloc(GFP_KERNEL, 4 * (ctx.skf->len + 1));
+	if (ctx.offsets == NULL)
+		return;
+
+	/* fake pass to fill in the ctx->seen */
+	if (unlikely(build_body(&ctx)))
+		goto out;
+
+	tmp_idx = ctx.idx;
+	build_prologue(&ctx);
+	ctx.prologue_bytes = (ctx.idx - tmp_idx) * 4;
+
+#if __LINUX_ARM_ARCH__ < 7
+	tmp_idx = ctx.idx;
+	build_epilogue(&ctx);
+	ctx.epilogue_bytes = (ctx.idx - tmp_idx) * 4;
+
+	ctx.idx += ctx.imm_count;
+	if (ctx.imm_count) {
+		ctx.imms = kzalloc(GFP_KERNEL, 4 * ctx.imm_count);
+		if (ctx.imms == NULL)
+			goto out;
+	}
+#else
+	/* there's nothing after the epilogue on ARMv7 */
+	build_epilogue(&ctx);
+#endif
+
+	alloc_size = 4 * ctx.idx;
+	ctx.target = module_alloc(max(sizeof(struct work_struct),
+				      alloc_size));
+	if (unlikely(ctx.target == NULL))
+		goto out;
+
+	ctx.idx = 0;
+	build_prologue(&ctx);
+	build_body(&ctx);
+	build_epilogue(&ctx);
+
+	flush_icache_range((u32)ctx.target, (u32)(ctx.target + ctx.idx));
+
+#if __LINUX_ARM_ARCH__ < 7
+	if (ctx.imm_count)
+		kfree(ctx.imms);
+#endif
+
+	if (bpf_jit_enable > 1)
+		print_hex_dump(KERN_INFO, "BPF JIT code: ",
+			       DUMP_PREFIX_ADDRESS, 16, 4, ctx.target,
+			       alloc_size, false);
+
+	fp->bpf_func = (void *)ctx.target;
+out:
+	kfree(ctx.offsets);
+	return;
+}
+
+static void bpf_jit_free_worker(struct work_struct *work)
+{
+	module_free(NULL, work);
+}
+
+void bpf_jit_free(struct sk_filter *fp)
+{
+	struct work_struct *work;
+
+	if (fp->bpf_func != sk_run_filter) {
+		work = (struct work_struct *)fp->bpf_func;
+
+		INIT_WORK(work, bpf_jit_free_worker);
+		schedule_work(work);
+	}
+}

arch/arm/net/bpf_jit_32.h

···
+/*
+ * Just-In-Time compiler for BPF filters on 32bit ARM
+ *
+ * Copyright (c) 2011 Mircea Gherzan <[e-mail]>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; version 2 of the License.
+ */
+
+#ifndef PFILTER_OPCODES_ARM_H
+#define PFILTER_OPCODES_ARM_H
+
+#define ARM_R0	0
+#define ARM_R1	1
+#define ARM_R2	2
+#define ARM_R3	3
+#define ARM_R4	4
+#define ARM_R5	5
+#define ARM_R6	6
+#define ARM_R7	7
+#define ARM_R8	8
+#define ARM_R9	9
+#define ARM_R10	10
+#define ARM_FP	11
+#define ARM_IP	12
+#define ARM_SP	13
+#define ARM_LR	14
+#define ARM_PC	15
+
+#define ARM_COND_EQ		0x0
+#define ARM_COND_NE		0x1
+#define ARM_COND_CS		0x2
+#define ARM_COND_HS		ARM_COND_CS
+#define ARM_COND_CC		0x3
+#define ARM_COND_LO		ARM_COND_CC
+#define ARM_COND_MI		0x4
+#define ARM_COND_PL		0x5
+#define ARM_COND_VS		0x6
+#define ARM_COND_VC		0x7
+#define ARM_COND_HI		0x8
+#define ARM_COND_LS		0x9
+#define ARM_COND_GE		0xa
+#define ARM_COND_LT		0xb
+#define ARM_COND_GT		0xc
+#define ARM_COND_LE		0xd
+#define ARM_COND_AL		0xe
+
+/* register shift types */
+#define SRTYPE_LSL		0
+#define SRTYPE_LSR		1
+#define SRTYPE_ASR		2
+#define SRTYPE_ROR		3
+
+#define ARM_INST_ADD_R		0x00800000
+#define ARM_INST_ADD_I		0x02800000
+
+#define ARM_INST_AND_R		0x00000000
+#define ARM_INST_AND_I		0x02000000
+
+#define ARM_INST_BIC_R		0x01c00000
+#define ARM_INST_BIC_I		0x03c00000
+
+#define ARM_INST_B		0x0a000000
+#define ARM_INST_BX		0x012FFF10
+#define ARM_INST_BLX_R		0x012fff30
+
+#define ARM_INST_CMP_R		0x01500000
+#define ARM_INST_CMP_I		0x03500000
+
+#define ARM_INST_LDRB_I		0x05d00000
+#define ARM_INST_LDRB_R		0x07d00000
+#define ARM_INST_LDRH_I		0x01d000b0
+#define ARM_INST_LDR_I		0x05900000
+
+#define ARM_INST_LDM		0x08900000
+
+#define ARM_INST_LSL_I		0x01a00000
+#define ARM_INST_LSL_R		0x01a00010
+
+#define ARM_INST_LSR_I		0x01a00020
+#define ARM_INST_LSR_R		0x01a00030
+
+#define ARM_INST_MOV_R		0x01a00000
+#define ARM_INST_MOV_I		0x03a00000
+#define ARM_INST_MOVW		0x03000000
+#define ARM_INST_MOVT		0x03400000
+
+#define ARM_INST_MUL		0x00000090
+
+#define ARM_INST_POP		0x08bd0000
+#define ARM_INST_PUSH		0x092d0000
+
+#define ARM_INST_ORR_R		0x01800000
+#define ARM_INST_ORR_I		0x03800000
+
+#define ARM_INST_REV		0x06bf0f30
+#define ARM_INST_REV16		0x06bf0fb0
+
+#define ARM_INST_RSB_I		0x02600000
+
+#define ARM_INST_SUB_R		0x00400000
+#define ARM_INST_SUB_I		0x02400000
+
+#define ARM_INST_STR_I		0x05800000
+
+#define ARM_INST_TST_R		0x01100000
+#define ARM_INST_TST_I		0x03100000
+
+#define ARM_INST_UDIV		0x0730f010
+
+#define ARM_INST_UMULL		0x00800090
+
+/* register */
+#define _AL3_R(op, rd, rn, rm)	((op ## _R) | (rd) << 12 | (rn) << 16 | (rm))
+/* immediate */
+#define _AL3_I(op, rd, rn, imm)	((op ## _I) | (rd) << 12 | (rn) << 16 | (imm))
+
+#define ARM_ADD_R(rd, rn, rm)	_AL3_R(ARM_INST_ADD, rd, rn, rm)
+#define ARM_ADD_I(rd, rn, imm)	_AL3_I(ARM_INST_ADD, rd, rn, imm)
+
+#define ARM_AND_R(rd, rn, rm)	_AL3_R(ARM_INST_AND, rd, rn, rm)
+#define ARM_AND_I(rd, rn, imm)	_AL3_I(ARM_INST_AND, rd, rn, imm)
+
+#define ARM_BIC_R(rd, rn, rm)	_AL3_R(ARM_INST_BIC, rd, rn, rm)
+#define ARM_BIC_I(rd, rn, imm)	_AL3_I(ARM_INST_BIC, rd, rn, imm)
+
+#define ARM_B(imm24)		(ARM_INST_B | ((imm24) & 0xffffff))
+#define ARM_BX(rm)		(ARM_INST_BX | (rm))
+#define ARM_BLX_R(rm)		(ARM_INST_BLX_R | (rm))
+
+#define ARM_CMP_R(rn, rm)	_AL3_R(ARM_INST_CMP, 0, rn, rm)
+#define ARM_CMP_I(rn, imm)	_AL3_I(ARM_INST_CMP, 0, rn, imm)
+
+#define ARM_LDR_I(rt, rn, off)	(ARM_INST_LDR_I | (rt) << 12 | (rn) << 16 \
+				 | (off))
+#define ARM_LDRB_I(rt, rn, off)	(ARM_INST_LDRB_I | (rt) << 12 | (rn) << 16 \
+				 | (off))
+#define ARM_LDRB_R(rt, rn, rm)	(ARM_INST_LDRB_R | (rt) << 12 | (rn) << 16 \
+				 | (rm))
+#define ARM_LDRH_I(rt, rn, off)	(ARM_INST_LDRH_I | (rt) << 12 | (rn) << 16 \
+				 | (((off) & 0xf0) << 4) | ((off) & 0xf))
+
+#define ARM_LDM(rn, regs)	(ARM_INST_LDM | (rn) << 16 | (regs))
+
+#define ARM_LSL_R(rd, rn, rm)	(_AL3_R(ARM_INST_LSL, rd, 0, rn) | (rm) << 8)
+#define ARM_LSL_I(rd, rn, imm)	(_AL3_I(ARM_INST_LSL, rd, 0, rn) | (imm) << 7)
+
+#define ARM_LSR_R(rd, rn, rm)	(_AL3_R(ARM_INST_LSR, rd, 0, rn) | (rm) << 8)
+#define ARM_LSR_I(rd, rn, imm)	(_AL3_I(ARM_INST_LSR, rd, 0, rn) | (imm) << 7)
+
+#define ARM_MOV_R(rd, rm)	_AL3_R(ARM_INST_MOV, rd, 0, rm)
+#define ARM_MOV_I(rd, imm)	_AL3_I(ARM_INST_MOV, rd, 0, imm)
+
+#define ARM_MOVW(rd, imm)	\
+	(ARM_INST_MOVW | ((imm) >> 12) << 16 | (rd) << 12 | ((imm) & 0x0fff))
+
+#define ARM_MOVT(rd, imm)	\
+	(ARM_INST_MOVT | ((imm) >> 12) << 16 | (rd) << 12 | ((imm) & 0x0fff))
+
+#define ARM_MUL(rd, rm, rn)	(ARM_INST_MUL | (rd) << 16 | (rm) << 8 | (rn))
+
+#define ARM_POP(regs)		(ARM_INST_POP | (regs))
+#define ARM_PUSH(regs)		(ARM_INST_PUSH | (regs))
+
+#define ARM_ORR_R(rd, rn, rm)	_AL3_R(ARM_INST_ORR, rd, rn, rm)
+#define ARM_ORR_I(rd, rn, imm)	_AL3_I(ARM_INST_ORR, rd, rn, imm)
+#define ARM_ORR_S(rd, rn, rm, type, rs)	\
+	(ARM_ORR_R(rd, rn, rm) | (type) << 5 | (rs) << 7)
+
+#define ARM_REV(rd, rm)		(ARM_INST_REV | (rd) << 12 | (rm))
+#define ARM_REV16(rd, rm)	(ARM_INST_REV16 | (rd) << 12 | (rm))
+
+#define ARM_RSB_I(rd, rn, imm)	_AL3_I(ARM_INST_RSB, rd, rn, imm)
+
+#define ARM_SUB_R(rd, rn, rm)	_AL3_R(ARM_INST_SUB, rd, rn, rm)
+#define ARM_SUB_I(rd, rn, imm)	_AL3_I(ARM_INST_SUB, rd, rn, imm)
+
+#define ARM_STR_I(rt, rn, off)	(ARM_INST_STR_I | (rt) << 12 | (rn) << 16 \
+				 | (off))
+
+#define ARM_TST_R(rn, rm)	_AL3_R(ARM_INST_TST, 0, rn, rm)
+#define ARM_TST_I(rn, imm)	_AL3_I(ARM_INST_TST, 0, rn, imm)
+
+#define ARM_UDIV(rd, rn, rm)	(ARM_INST_UDIV | (rd) << 16 | (rn) | (rm) << 8)
+
+#define ARM_UMULL(rd_lo, rd_hi, rn, rm)	(ARM_INST_UMULL | (rd_hi) << 16 \
+					 | (rd_lo) << 12 | (rm) << 8 | rn)
+
+#endif /* PFILTER_OPCODES_ARM_H */

arch/arm/plat-nomadik/Kconfig

···
 config NOMADIK_MTU_SCHED_CLOCK
 	bool
 	depends on HAS_MTU
-	select HAVE_SCHED_CLOCK
 	help
 	  Use the Multi Timer Unit as the sched_clock.
 

arch/arm/plat-versatile/Kconfig

···
 	depends on ARCH_REALVIEW || ARCH_VERSATILE
 
 config PLAT_VERSATILE_SCHED_CLOCK
-	def_bool y if !ARCH_INTEGRATOR_AP
-	select HAVE_SCHED_CLOCK
+	def_bool y
 
 endif

arch/c6x/Kconfig

···
 	select HAVE_DMA_API_DEBUG
 	select HAVE_GENERIC_HARDIRQS
 	select HAVE_MEMBLOCK
-	select HAVE_SPARSE_IRQ
+	select SPARSE_IRQ
 	select IRQ_DOMAIN
 	select OF
 	select OF_EARLY_FLATTREE

arch/powerpc/Kconfig

···
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS && PPC_BOOK3S_64
 	select HAVE_GENERIC_HARDIRQS
-	select HAVE_SPARSE_IRQ
 	select SPARSE_IRQ
 	select IRQ_PER_CPU
 	select IRQ_DOMAIN

arch/sh/Kconfig

···
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_GENERIC_HARDIRQS
-	select HAVE_SPARSE_IRQ
+	select MAY_HAVE_SPARSE_IRQ
 	select IRQ_FORCED_THREADING
 	select RTC_LIB
 	select GENERIC_ATOMIC64

arch/sh/include/asm/irq.h

···
 #define NO_IRQ_IGNORE		((unsigned int)-1)
 
 /*
- * Convert back and forth between INTEVT and IRQ values.
- */
-#ifdef CONFIG_CPU_HAS_INTEVT
-#define evt2irq(evt)		(((evt) >> 5) - 16)
-#define irq2evt(irq)		(((irq) + 16) << 5)
-#else
-#define evt2irq(evt)		(evt)
-#define irq2evt(irq)		(irq)
-#endif
-
-/*
  * Simple Mask Register Support
  */
 extern void make_maskreg_irq(unsigned int irq);

arch/x86/Kconfig

···
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_TEXT_POKE_SMP
 	select HAVE_GENERIC_HARDIRQS
-	select HAVE_SPARSE_IRQ
 	select SPARSE_IRQ
 	select GENERIC_FIND_FIRST_BIT
 	select GENERIC_IRQ_PROBE

drivers/clocksource/Kconfig

···
 config CLKSRC_DBX500_PRCMU_SCHED_CLOCK
 	bool "Clocksource PRCMU Timer sched_clock"
 	depends on (CLKSRC_DBX500_PRCMU && !NOMADIK_MTU_SCHED_CLOCK)
-	select HAVE_SCHED_CLOCK
 	default y
 	help
 	  Use the always on PRCMU Timer as sched_clock

drivers/gpio/gpio-pxa.c

···
 #include <linux/syscore_ops.h>
 #include <linux/slab.h>
 
+#include <mach/irqs.h>
+
 /*
  * We handle the GPIOs by banks, each bank covers up to 32 GPIOs with
  * one set of registers. The register offsets are organized below:

drivers/sh/intc/balancing.c

···
  */
 #include "internals.h"
 
-static unsigned long dist_handle[NR_IRQS];
+static unsigned long dist_handle[INTC_NR_IRQS];
 
 void intc_balancing_enable(unsigned int irq)
 {

drivers/sh/intc/core.c

···
  * - this needs to be at least 2 for 5-bit priorities on 7780
  */
 static unsigned int default_prio_level = 2;	/* 2 - 16 */
-static unsigned int intc_prio_level[NR_IRQS];	/* for now */
+static unsigned int intc_prio_level[INTC_NR_IRQS];	/* for now */
 
 unsigned int intc_get_dfl_prio_level(void)
 {

drivers/sh/intc/handle.c

···
 #include <linux/spinlock.h>
 #include "internals.h"
 
-static unsigned long ack_handle[NR_IRQS];
+static unsigned long ack_handle[INTC_NR_IRQS];
 
 static intc_enum __init intc_grp_id(struct intc_desc *desc,
 				    intc_enum enum_id)

drivers/sh/intc/virq.c

···
 #include <linux/export.h>
 #include "internals.h"
 
-static struct intc_map_entry intc_irq_xlate[NR_IRQS];
+static struct intc_map_entry intc_irq_xlate[INTC_NR_IRQS];
 
 struct intc_virq_list {
 	unsigned int irq;

include/linux/sh_intc.h

···
 
 #include <linux/ioport.h>
 
+#ifdef CONFIG_SUPERH
+#define INTC_NR_IRQS	512
+#else
+#define INTC_NR_IRQS	1024
+#endif
+
+/*
+ * Convert back and forth between INTEVT and IRQ values.
+ */
+#ifdef CONFIG_CPU_HAS_INTEVT
+#define evt2irq(evt)		(((evt) >> 5) - 16)
+#define irq2evt(irq)		(((irq) + 16) << 5)
+#else
+#define evt2irq(evt)		(evt)
+#define irq2evt(irq)		(irq)
+#endif
+
 typedef unsigned char intc_enum;
 
 struct intc_vect {

kernel/irq/Kconfig

···
 # Options selectable by the architecture code
 
 # Make sparse irq Kconfig switch below available
-config HAVE_SPARSE_IRQ
+config MAY_HAVE_SPARSE_IRQ
        bool
 
 # Enable the generic irq autoprobe mechanism
···
        bool
 
 config SPARSE_IRQ
-	bool "Support sparse irq numbering"
-	depends on HAVE_SPARSE_IRQ
+	bool "Support sparse irq numbering" if MAY_HAVE_SPARSE_IRQ
 	---help---
 
 	  Sparse irq numbering is useful for distro kernels that want

scripts/gcc-goto.sh

···
 # Test for gcc 'asm goto' support
 # Copyright (C) 2010, Jason Baron <[e-mail]>
 
-echo "int main(void) { entry: asm goto (\"\"::::entry); return 0; }" | $@ -x c - -c -o /dev/null >/dev/null 2>&1 && echo "y"
+cat << "END" | $@ -x c - -c -o /dev/null >/dev/null 2>&1 && echo "y"
+int main(void)
+{
+#ifdef __arm__
+	/*
+	 * Not related to asm goto, but used by jump label
+	 * and broken on some ARM GCC versions (see GCC Bug 48637).
+	 */
+	static struct { int dummy; int state; } tp;
+	asm (".long %c0" :: "i" (&tp.state));
+#endif
+
+entry:
+	asm goto ("" :::: entry);
+	return 0;
+}
+END

sound/arm/pxa2xx-ac97-lib.c

···
 #include <sound/ac97_codec.h>
 #include <sound/pxa2xx-lib.h>
 
-#include <asm/irq.h>
+#include <mach/irqs.h>
 #include <mach/regs-ac97.h>
 #include <mach/audio.h>