Merge branch 'clksrc' into devel

Conflicts:
	arch/arm/mach-vexpress/v2m.c
	arch/arm/plat-omap/counter_32k.c
	arch/arm/plat-versatile/Makefile

arch/arm/Kconfig

@@ -14,6 +14,7 @@ config ARM
 	select HAVE_FUNCTION_TRACER if (!XIP_KERNEL)
 	select HAVE_FTRACE_MCOUNT_RECORD if (!XIP_KERNEL)
 	select HAVE_DYNAMIC_FTRACE if (!XIP_KERNEL)
+	select HAVE_FUNCTION_GRAPH_TRACER if (!THUMB2_KERNEL)
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZO
@@ -38,6 +39,9 @@ config HAVE_PWM
 config SYS_SUPPORTS_APM_EMULATION
 	bool
 
+config HAVE_SCHED_CLOCK
+	bool
+
 config GENERIC_GPIO
 	bool
 
@@ -233,6 +237,7 @@ config ARCH_REALVIEW
 	bool "ARM Ltd. RealView family"
 	select ARM_AMBA
 	select COMMON_CLKDEV
+	select HAVE_SCHED_CLOCK
 	select ICST
 	select GENERIC_CLOCKEVENTS
 	select ARCH_WANT_OPTIONAL_GPIOLIB
@@ -247,6 +252,7 @@ config ARCH_VERSATILE
 	select ARM_AMBA
 	select ARM_VIC
 	select COMMON_CLKDEV
+	select HAVE_SCHED_CLOCK
 	select ICST
 	select GENERIC_CLOCKEVENTS
 	select ARCH_WANT_OPTIONAL_GPIOLIB
@@ -263,6 +269,7 @@ config ARCH_VEXPRESS
 	select COMMON_CLKDEV
 	select GENERIC_CLOCKEVENTS
 	select HAVE_CLK
+	select HAVE_SCHED_CLOCK
 	select ICST
 	select PLAT_VERSATILE
 	help
@@ -434,6 +441,7 @@ config ARCH_IXP4XX
 	select CPU_XSCALE
 	select GENERIC_GPIO
 	select GENERIC_CLOCKEVENTS
+	select HAVE_SCHED_CLOCK
 	select DMABOUNCE if PCI
 	help
 	  Support for Intel's IXP4XX (XScale) family of processors.
@@ -509,6 +517,7 @@ config ARCH_MMP
 	select ARCH_REQUIRE_GPIOLIB
 	select COMMON_CLKDEV
 	select GENERIC_CLOCKEVENTS
+	select HAVE_SCHED_CLOCK
 	select TICK_ONESHOT
 	select PLAT_PXA
 	select SPARSE_IRQ
@@ -565,6 +574,7 @@ config ARCH_TEGRA
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_GPIO
 	select HAVE_CLK
+	select HAVE_SCHED_CLOCK
 	select COMMON_CLKDEV
 	select ARCH_HAS_BARRIERS if CACHE_L2X0
 	select ARCH_HAS_CPUFREQ
@@ -588,6 +598,7 @@ config ARCH_PXA
 	select COMMON_CLKDEV
 	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_CLOCKEVENTS
+	select HAVE_SCHED_CLOCK
 	select TICK_ONESHOT
 	select PLAT_PXA
 	select SPARSE_IRQ
@@ -636,6 +647,7 @@ config ARCH_SA1100
 	select CPU_FREQ
 	select GENERIC_CLOCKEVENTS
 	select HAVE_CLK
+	select HAVE_SCHED_CLOCK
 	select TICK_ONESHOT
 	select ARCH_REQUIRE_GPIOLIB
 	help
@@ -782,6 +794,7 @@ config ARCH_U300
 	bool "ST-Ericsson U300 Series"
 	depends on MMU
 	select CPU_ARM926T
+	select HAVE_SCHED_CLOCK
 	select HAVE_TCM
 	select ARM_AMBA
 	select ARM_VIC
@@ -830,6 +843,7 @@ config ARCH_OMAP
 	select ARCH_REQUIRE_GPIOLIB
 	select ARCH_HAS_CPUFREQ
 	select GENERIC_CLOCKEVENTS
+	select HAVE_SCHED_CLOCK
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	help
 	  Support for TI's OMAP platform (OMAP1/2/3/4).
@@ -983,9 +997,11 @@ config ARCH_ACORN
 config PLAT_IOP
 	bool
 	select GENERIC_CLOCKEVENTS
+	select HAVE_SCHED_CLOCK
 
 config PLAT_ORION
 	bool
+	select HAVE_SCHED_CLOCK
 
 config PLAT_PXA
 	bool
@@ -1212,10 +1228,11 @@ config SMP
 	depends on EXPERIMENTAL
 	depends on GENERIC_CLOCKEVENTS
 	depends on REALVIEW_EB_ARM11MP || REALVIEW_EB_A9MP || \
-		 MACH_REALVIEW_PB11MP || MACH_REALVIEW_PBX || ARCH_OMAP4 ||\
-		 ARCH_S5PV310 || ARCH_TEGRA || ARCH_U8500 || ARCH_VEXPRESS_CA9X4
+		 MACH_REALVIEW_PB11MP || MACH_REALVIEW_PBX || ARCH_OMAP4 || \
+		 ARCH_S5PV310 || ARCH_TEGRA || ARCH_U8500 || ARCH_VEXPRESS_CA9X4 || \
+		 ARCH_MSM_SCORPIONMP
 	select USE_GENERIC_SMP_HELPERS
-	select HAVE_ARM_SCU
+	select HAVE_ARM_SCU if !ARCH_MSM_SCORPIONMP
 	help
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If
@@ -1290,6 +1307,7 @@ config NR_CPUS
 config HOTPLUG_CPU
 	bool "Support for hot-pluggable CPUs (EXPERIMENTAL)"
 	depends on SMP && HOTPLUG && EXPERIMENTAL
+	depends on !ARCH_MSM
 	help
 	  Say Y here to experiment with turning CPUs off and on.  CPUs
 	  can be controlled through /sys/devices/system/cpu.
@@ -1298,7 +1316,7 @@ config LOCAL_TIMERS
 	bool "Use local timer interrupts"
 	depends on SMP
 	default y
-	select HAVE_ARM_TWD
+	select HAVE_ARM_TWD if !ARCH_MSM_SCORPIONMP
 	help
 	  Enable support for local timers on SMP platforms, rather then the
 	  legacy IPI broadcast method.  Local timers allows the system

arch/arm/Kconfig.debug

@@ -23,7 +23,7 @@ config STRICT_DEVMEM
 config FRAME_POINTER
 	bool
 	depends on !THUMB2_KERNEL
-	default y if !ARM_UNWIND
+	default y if !ARM_UNWIND || FUNCTION_GRAPH_TRACER
 	help
 	  If you say N here, the resulting kernel will be slightly smaller and
 	  faster. However, if neither FRAME_POINTER nor ARM_UNWIND are enabled,

arch/arm/common/timer-sp.c

@@ -44,7 +44,6 @@ static struct clocksource clocksource_sp804 = {
 	.rating		= 200,
 	.read		= sp804_read,
 	.mask		= CLOCKSOURCE_MASK(32),
-	.shift		= 20,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
@@ -61,8 +60,7 @@ void __init sp804_clocksource_init(void __iomem *base)
 	writel(TIMER_CTRL_32BIT | TIMER_CTRL_ENABLE | TIMER_CTRL_PERIODIC,
 		clksrc_base + TIMER_CTRL);
 
-	cs->mult = clocksource_khz2mult(TIMER_FREQ_KHZ, cs->shift);
-	clocksource_register(cs);
+	clocksource_register_khz(cs, TIMER_FREQ_KHZ);
 }
 
 

arch/arm/include/asm/sched_clock.h

+/*
+ * sched_clock.h: support for extending counters to full 64-bit ns counter
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef ASM_SCHED_CLOCK
+#define ASM_SCHED_CLOCK
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+struct clock_data {
+	u64 epoch_ns;
+	u32 epoch_cyc;
+	u32 epoch_cyc_copy;
+	u32 mult;
+	u32 shift;
+};
+
+#define DEFINE_CLOCK_DATA(name)	struct clock_data name
+
+static inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift)
+{
+	return (cyc * mult) >> shift;
+}
+
+/*
+ * Atomically update the sched_clock epoch.  Your update callback will
+ * be called from a timer before the counter wraps - read the current
+ * counter value, and call this function to safely move the epochs
+ * forward.  Only use this from the update callback.
+ */
+static inline void update_sched_clock(struct clock_data *cd, u32 cyc, u32 mask)
+{
+	unsigned long flags;
+	u64 ns = cd->epoch_ns +
+		cyc_to_ns((cyc - cd->epoch_cyc) & mask, cd->mult, cd->shift);
+
+	/*
+	 * Write epoch_cyc and epoch_ns in a way that the update is
+	 * detectable in cyc_to_fixed_sched_clock().
+	 */
+	raw_local_irq_save(flags);
+	cd->epoch_cyc = cyc;
+	smp_wmb();
+	cd->epoch_ns = ns;
+	smp_wmb();
+	cd->epoch_cyc_copy = cyc;
+	raw_local_irq_restore(flags);
+}
+
+/*
+ * If your clock rate is known at compile time, using this will allow
+ * you to optimize the mult/shift loads away.  This is paired with
+ * init_fixed_sched_clock() to ensure that your mult/shift are correct.
+ */
+static inline unsigned long long cyc_to_fixed_sched_clock(struct clock_data *cd,
+	u32 cyc, u32 mask, u32 mult, u32 shift)
+{
+	u64 epoch_ns;
+	u32 epoch_cyc;
+
+	/*
+	 * Load the epoch_cyc and epoch_ns atomically.  We do this by
+	 * ensuring that we always write epoch_cyc, epoch_ns and
+	 * epoch_cyc_copy in strict order, and read them in strict order.
+	 * If epoch_cyc and epoch_cyc_copy are not equal, then we're in
+	 * the middle of an update, and we should repeat the load.
+	 */
+	do {
+		epoch_cyc = cd->epoch_cyc;
+		smp_rmb();
+		epoch_ns = cd->epoch_ns;
+		smp_rmb();
+	} while (epoch_cyc != cd->epoch_cyc_copy);
+
+	return epoch_ns + cyc_to_ns((cyc - epoch_cyc) & mask, mult, shift);
+}
+
+/*
+ * Otherwise, you need to use this, which will obtain the mult/shift
+ * from the clock_data structure.  Use init_sched_clock() with this.
+ */
+static inline unsigned long long cyc_to_sched_clock(struct clock_data *cd,
+	u32 cyc, u32 mask)
+{
+	return cyc_to_fixed_sched_clock(cd, cyc, mask, cd->mult, cd->shift);
+}
+
+/*
+ * Initialize the clock data - calculate the appropriate multiplier
+ * and shift.  Also setup a timer to ensure that the epoch is refreshed
+ * at the appropriate time interval, which will call your update
+ * handler.
+ */
+void init_sched_clock(struct clock_data *, void (*)(void),
+	unsigned int, unsigned long);
+
+/*
+ * Use this initialization function rather than init_sched_clock() if
+ * you're using cyc_to_fixed_sched_clock, which will warn if your
+ * constants are incorrect.
+ */
+static inline void init_fixed_sched_clock(struct clock_data *cd,
+	void (*update)(void), unsigned int bits, unsigned long rate,
+	u32 mult, u32 shift)
+{
+	init_sched_clock(cd, update, bits, rate);
+	if (cd->mult != mult || cd->shift != shift) {
+		pr_crit("sched_clock: wrong multiply/shift: %u>>%u vs calculated %u>>%u\n"
+			"sched_clock: fix multiply/shift to avoid scheduler hiccups\n",
+			mult, shift, cd->mult, cd->shift);
+	}
+}
+
+#endif

arch/arm/include/asm/system.h

@@ -63,6 +63,11 @@
 #include <asm/outercache.h>
 
 #define __exception	__attribute__((section(".exception.text")))
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#define __exception_irq_entry	__irq_entry
+#else
+#define __exception_irq_entry	__exception
+#endif
 
 struct thread_info;
 struct task_struct;

arch/arm/include/asm/traps.h

@@ -15,13 +15,32 @@ struct undef_hook {
 void register_undef_hook(struct undef_hook *hook);
 void unregister_undef_hook(struct undef_hook *hook);
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static inline int __in_irqentry_text(unsigned long ptr)
+{
+	extern char __irqentry_text_start[];
+	extern char __irqentry_text_end[];
+
+	return ptr >= (unsigned long)&__irqentry_text_start &&
+	       ptr < (unsigned long)&__irqentry_text_end;
+}
+#else
+static inline int __in_irqentry_text(unsigned long ptr)
+{
+	return 0;
+}
+#endif
+
 static inline int in_exception_text(unsigned long ptr)
 {
 	extern char __exception_text_start[];
 	extern char __exception_text_end[];
+	int in;
+
+	in = ptr >= (unsigned long)&__exception_text_start &&
+	     ptr < (unsigned long)&__exception_text_end;
 
-	return ptr >= (unsigned long)&__exception_text_start &&
-	       ptr < (unsigned long)&__exception_text_end;
+	return in ? : __in_irqentry_text(ptr);
 }
 
 extern void __init early_trap_init(void);

arch/arm/kernel/Makefile

@@ -5,7 +5,7 @@
 CPPFLAGS_vmlinux.lds := -DTEXT_OFFSET=$(TEXT_OFFSET)
 AFLAGS_head.o        := -DTEXT_OFFSET=$(TEXT_OFFSET)
 
-ifdef CONFIG_DYNAMIC_FTRACE
+ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_ftrace.o = -pg
 endif
 
@@ -29,10 +29,12 @@ obj-$(CONFIG_MODULES)		+= armksyms.o module.o
 obj-$(CONFIG_ARTHUR)		+= arthur.o
 obj-$(CONFIG_ISA_DMA)		+= dma-isa.o
 obj-$(CONFIG_PCI)		+= bios32.o isa.o
+obj-$(CONFIG_HAVE_SCHED_CLOCK)	+= sched_clock.o
 obj-$(CONFIG_SMP)		+= smp.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-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o kprobes-decode.o
 obj-$(CONFIG_ATAGS_PROC)	+= atags.o

arch/arm/kernel/entry-common.S

@@ -147,98 +147,170 @@ ENDPROC(ret_from_fork)
 #endif
 #endif
 
-#ifdef CONFIG_DYNAMIC_FTRACE
-ENTRY(__gnu_mcount_nc)
-	mov	ip, lr
-	ldmia	sp!, {lr}
-	mov	pc, ip
-ENDPROC(__gnu_mcount_nc)
+.macro __mcount suffix
+	mcount_enter
+	ldr	r0, =ftrace_trace_function
+	ldr	r2, [r0]
+	adr	r0, .Lftrace_stub
+	cmp	r0, r2
+	bne	1f
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	ldr     r1, =ftrace_graph_return
+	ldr     r2, [r1]
+	cmp     r0, r2
+	bne     ftrace_graph_caller\suffix
+
+	ldr     r1, =ftrace_graph_entry
+	ldr     r2, [r1]
+	ldr     r0, =ftrace_graph_entry_stub
+	cmp     r0, r2
+	bne     ftrace_graph_caller\suffix
+#endif
 
-ENTRY(ftrace_caller)
-	stmdb	sp!, {r0-r3, lr}
-	mov	r0, lr
+	mcount_exit
+
+1: 	mcount_get_lr	r1			@ lr of instrumented func
+	mov	r0, lr				@ instrumented function
+	sub	r0, r0, #MCOUNT_INSN_SIZE
+	adr	lr, BSYM(2f)
+	mov	pc, r2
+2:	mcount_exit
+.endm
+
+.macro __ftrace_caller suffix
+	mcount_enter
+
+	mcount_get_lr	r1			@ lr of instrumented func
+	mov	r0, lr				@ instrumented function
 	sub	r0, r0, #MCOUNT_INSN_SIZE
-	ldr	r1, [sp, #20]
 
-	.global	ftrace_call
-ftrace_call:
+	.globl ftrace_call\suffix
+ftrace_call\suffix:
 	bl	ftrace_stub
-	ldmia	sp!, {r0-r3, ip, lr}
-	mov	pc, ip
-ENDPROC(ftrace_caller)
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	.globl ftrace_graph_call\suffix
+ftrace_graph_call\suffix:
+	mov	r0, r0
+#endif
+
+	mcount_exit
+.endm
+
+.macro __ftrace_graph_caller
+	sub	r0, fp, #4		@ &lr of instrumented routine (&parent)
+#ifdef CONFIG_DYNAMIC_FTRACE
+	@ called from __ftrace_caller, saved in mcount_enter
+	ldr	r1, [sp, #16]		@ instrumented routine (func)
+#else
+	@ called from __mcount, untouched in lr
+	mov	r1, lr			@ instrumented routine (func)
+#endif
+	sub	r1, r1, #MCOUNT_INSN_SIZE
+	mov	r2, fp			@ frame pointer
+	bl	prepare_ftrace_return
+	mcount_exit
+.endm
 
 #ifdef CONFIG_OLD_MCOUNT
+/*
+ * mcount
+ */
+
+.macro mcount_enter
+	stmdb	sp!, {r0-r3, lr}
+.endm
+
+.macro mcount_get_lr reg
+	ldr	\reg, [fp, #-4]
+.endm
+
+.macro mcount_exit
+	ldr	lr, [fp, #-4]
+	ldmia	sp!, {r0-r3, pc}
+.endm
+
 ENTRY(mcount)
+#ifdef CONFIG_DYNAMIC_FTRACE
 	stmdb	sp!, {lr}
 	ldr	lr, [fp, #-4]
 	ldmia	sp!, {pc}
+#else
+	__mcount _old
+#endif
 ENDPROC(mcount)
 
+#ifdef CONFIG_DYNAMIC_FTRACE
 ENTRY(ftrace_caller_old)
-	stmdb	sp!, {r0-r3, lr}
-	ldr	r1, [fp, #-4]
-	mov	r0, lr
-	sub	r0, r0, #MCOUNT_INSN_SIZE
-
-	.globl ftrace_call_old
-ftrace_call_old:
-	bl	ftrace_stub
-	ldr	lr, [fp, #-4]			@ restore lr
-	ldmia	sp!, {r0-r3, pc}
+	__ftrace_caller _old
 ENDPROC(ftrace_caller_old)
 #endif
 
-#else
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(ftrace_graph_caller_old)
+	__ftrace_graph_caller
+ENDPROC(ftrace_graph_caller_old)
+#endif
 
-ENTRY(__gnu_mcount_nc)
+.purgem mcount_enter
+.purgem mcount_get_lr
+.purgem mcount_exit
+#endif
+
+/*
+ * __gnu_mcount_nc
+ */
+
+.macro mcount_enter
 	stmdb	sp!, {r0-r3, lr}
-	ldr	r0, =ftrace_trace_function
-	ldr	r2, [r0]
-	adr	r0, .Lftrace_stub
-	cmp	r0, r2
-	bne	gnu_trace
+.endm
+
+.macro mcount_get_lr reg
+	ldr	\reg, [sp, #20]
+.endm
+
+.macro mcount_exit
 	ldmia	sp!, {r0-r3, ip, lr}
 	mov	pc, ip
+.endm
 
-gnu_trace:
-	ldr	r1, [sp, #20]			@ lr of instrumented routine
-	mov	r0, lr
-	sub	r0, r0, #MCOUNT_INSN_SIZE
-	adr	lr, BSYM(1f)
-	mov	pc, r2
-1:
-	ldmia	sp!, {r0-r3, ip, lr}
+ENTRY(__gnu_mcount_nc)
+#ifdef CONFIG_DYNAMIC_FTRACE
+	mov	ip, lr
+	ldmia	sp!, {lr}
 	mov	pc, ip
+#else
+	__mcount
+#endif
 ENDPROC(__gnu_mcount_nc)
 
-#ifdef CONFIG_OLD_MCOUNT
-/*
- * This is under an ifdef in order to force link-time errors for people trying
- * to build with !FRAME_POINTER with a GCC which doesn't use the new-style
- * mcount.
- */
-ENTRY(mcount)
-	stmdb	sp!, {r0-r3, lr}
-	ldr	r0, =ftrace_trace_function
-	ldr	r2, [r0]
-	adr	r0, ftrace_stub
-	cmp	r0, r2
-	bne	trace
-	ldr	lr, [fp, #-4]			@ restore lr
-	ldmia	sp!, {r0-r3, pc}
+#ifdef CONFIG_DYNAMIC_FTRACE
+ENTRY(ftrace_caller)
+	__ftrace_caller
+ENDPROC(ftrace_caller)
+#endif
 
-trace:
-	ldr	r1, [fp, #-4]			@ lr of instrumented routine
-	mov	r0, lr
-	sub	r0, r0, #MCOUNT_INSN_SIZE
-	mov	lr, pc
-	mov	pc, r2
-	ldr	lr, [fp, #-4]			@ restore lr
-	ldmia	sp!, {r0-r3, pc}
-ENDPROC(mcount)
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(ftrace_graph_caller)
+	__ftrace_graph_caller
+ENDPROC(ftrace_graph_caller)
 #endif
 
-#endif /* CONFIG_DYNAMIC_FTRACE */
+.purgem mcount_enter
+.purgem mcount_get_lr
+.purgem mcount_exit
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	.globl return_to_handler
+return_to_handler:
+	stmdb	sp!, {r0-r3}
+	mov	r0, fp			@ frame pointer
+	bl	ftrace_return_to_handler
+	mov	lr, r0			@ r0 has real ret addr
+	ldmia	sp!, {r0-r3}
+	mov	pc, lr
+#endif
 
 ENTRY(ftrace_stub)
 .Lftrace_stub:

arch/arm/kernel/ftrace.c

@@ -24,6 +24,7 @@
 #define	NOP		0xe8bd4000	/* pop {lr} */
 #endif
 
+#ifdef CONFIG_DYNAMIC_FTRACE
 #ifdef CONFIG_OLD_MCOUNT
 #define OLD_MCOUNT_ADDR	((unsigned long) mcount)
 #define OLD_FTRACE_ADDR ((unsigned long) ftrace_caller_old)
@@ -59,9 +60,9 @@ static unsigned long adjust_address(struct dyn_ftrace *rec, unsigned long addr)
 }
 #endif
 
-/* construct a branch (BL) instruction to addr */
 #ifdef CONFIG_THUMB2_KERNEL
-static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
+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;
@@ -83,15 +84,22 @@ static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
 	j2 = (!i2) ^ s;
 
 	first = 0xf000 | (s << 10) | imm10;
-	second = 0xd000 | (j1 << 13) | (j2 << 11) | imm11;
+	second = 0x9000 | (j1 << 13) | (j2 << 11) | imm11;
+	if (link)
+		second |= 1 << 14;
 
 	return (second << 16) | first;
 }
 #else
-static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
+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
@@ -103,10 +111,15 @@ static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
 
 	offset = (offset >> 2) & 0x00ffffff;
 
-	return 0xeb000000 | offset;
+	return opcode | offset;
 }
 #endif
 
+static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
+{
+	return ftrace_gen_branch(pc, addr, true);
+}
+
 static int ftrace_modify_code(unsigned long pc, unsigned long old,
 			      unsigned long new)
 {
@@ -193,3 +206,83 @@ int __init ftrace_dyn_arch_init(void *data)
 
 	return 0;
 }
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+			   unsigned long frame_pointer)
+{
+	unsigned long return_hooker = (unsigned long) &return_to_handler;
+	struct ftrace_graph_ent trace;
+	unsigned long old;
+	int err;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		return;
+
+	old = *parent;
+	*parent = return_hooker;
+
+	err = ftrace_push_return_trace(old, self_addr, &trace.depth,
+				       frame_pointer);
+	if (err == -EBUSY) {
+		*parent = old;
+		return;
+	}
+
+	trace.func = self_addr;
+
+	/* Only trace if the calling function expects to */
+	if (!ftrace_graph_entry(&trace)) {
+		current->curr_ret_stack--;
+		*parent = old;
+	}
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+extern unsigned long ftrace_graph_call;
+extern unsigned long ftrace_graph_call_old;
+extern void ftrace_graph_caller_old(void);
+
+static int __ftrace_modify_caller(unsigned long *callsite,
+				  void (*func) (void), bool enable)
+{
+	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 nop = 0xe1a00000;	/* mov r0, r0 */
+	unsigned long old = enable ? nop : branch;
+	unsigned long new = enable ? branch : nop;
+
+	return ftrace_modify_code(pc, old, new);
+}
+
+static int ftrace_modify_graph_caller(bool enable)
+{
+	int ret;
+
+	ret = __ftrace_modify_caller(&ftrace_graph_call,
+				     ftrace_graph_caller,
+				     enable);
+
+#ifdef CONFIG_OLD_MCOUNT
+	if (!ret)
+		ret = __ftrace_modify_caller(&ftrace_graph_call_old,
+					     ftrace_graph_caller_old,
+					     enable);
+#endif
+
+	return ret;
+}
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+	return ftrace_modify_graph_caller(true);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+	return ftrace_modify_graph_caller(false);
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */

arch/arm/kernel/irq.c

@@ -35,6 +35,7 @@
 #include <linux/list.h>
 #include <linux/kallsyms.h>
 #include <linux/proc_fs.h>
+#include <linux/ftrace.h>
 
 #include <asm/system.h>
 #include <asm/mach/irq.h>
@@ -105,7 +106,8 @@ int show_interrupts(struct seq_file *p, void *v)
  * come via this function.  Instead, they should provide their
  * own 'handler'
  */
-asmlinkage void __exception asm_do_IRQ(unsigned int irq, struct pt_regs *regs)
+asmlinkage void __exception_irq_entry
+asm_do_IRQ(unsigned int irq, struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 

arch/arm/kernel/perf_event_v6.c

+/*
+ * ARMv6 Performance counter handling code.
+ *
+ * Copyright (C) 2009 picoChip Designs, Ltd., Jamie Iles
+ *
+ * ARMv6 has 2 configurable performance counters and a single cycle counter.
+ * They all share a single reset bit but can be written to zero so we can use
+ * that for a reset.
+ *
+ * The counters can't be individually enabled or disabled so when we remove
+ * one event and replace it with another we could get spurious counts from the
+ * wrong event. However, we can take advantage of the fact that the
+ * performance counters can export events to the event bus, and the event bus
+ * itself can be monitored. This requires that we *don't* export the events to
+ * the event bus. The procedure for disabling a configurable counter is:
+ *	- change the counter to count the ETMEXTOUT[0] signal (0x20). This
+ *	  effectively stops the counter from counting.
+ *	- disable the counter's interrupt generation (each counter has it's
+ *	  own interrupt enable bit).
+ * Once stopped, the counter value can be written as 0 to reset.
+ *
+ * To enable a counter:
+ *	- enable the counter's interrupt generation.
+ *	- set the new event type.
+ *
+ * Note: the dedicated cycle counter only counts cycles and can't be
+ * enabled/disabled independently of the others. When we want to disable the
+ * cycle counter, we have to just disable the interrupt reporting and start
+ * ignoring that counter. When re-enabling, we have to reset the value and
+ * enable the interrupt.
+ */
+
+#ifdef CONFIG_CPU_V6
+enum armv6_perf_types {
+	ARMV6_PERFCTR_ICACHE_MISS	    = 0x0,
+	ARMV6_PERFCTR_IBUF_STALL	    = 0x1,
+	ARMV6_PERFCTR_DDEP_STALL	    = 0x2,
+	ARMV6_PERFCTR_ITLB_MISS		    = 0x3,
+	ARMV6_PERFCTR_DTLB_MISS		    = 0x4,
+	ARMV6_PERFCTR_BR_EXEC		    = 0x5,
+	ARMV6_PERFCTR_BR_MISPREDICT	    = 0x6,
+	ARMV6_PERFCTR_INSTR_EXEC	    = 0x7,
+	ARMV6_PERFCTR_DCACHE_HIT	    = 0x9,
+	ARMV6_PERFCTR_DCACHE_ACCESS	    = 0xA,
+	ARMV6_PERFCTR_DCACHE_MISS	    = 0xB,
+	ARMV6_PERFCTR_DCACHE_WBACK	    = 0xC,
+	ARMV6_PERFCTR_SW_PC_CHANGE	    = 0xD,
+	ARMV6_PERFCTR_MAIN_TLB_MISS	    = 0xF,
+	ARMV6_PERFCTR_EXPL_D_ACCESS	    = 0x10,
+	ARMV6_PERFCTR_LSU_FULL_STALL	    = 0x11,
+	ARMV6_PERFCTR_WBUF_DRAINED	    = 0x12,
+	ARMV6_PERFCTR_CPU_CYCLES	    = 0xFF,
+	ARMV6_PERFCTR_NOP		    = 0x20,
+};
+
+enum armv6_counters {
+	ARMV6_CYCLE_COUNTER = 1,
+	ARMV6_COUNTER0,
+	ARMV6_COUNTER1,
+};
+
+/*
+ * The hardware events that we support. We do support cache operations but
+ * we have harvard caches and no way to combine instruction and data
+ * accesses/misses in hardware.
+ */
+static const unsigned armv6_perf_map[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES]	    = ARMV6_PERFCTR_CPU_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS]	    = ARMV6_PERFCTR_INSTR_EXEC,
+	[PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_CACHE_MISSES]	    = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6_PERFCTR_BR_EXEC,
+	[PERF_COUNT_HW_BRANCH_MISSES]	    = ARMV6_PERFCTR_BR_MISPREDICT,
+	[PERF_COUNT_HW_BUS_CYCLES]	    = HW_OP_UNSUPPORTED,
+};
+
+static const unsigned armv6_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)]	= ARMV6_PERFCTR_DCACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV6_PERFCTR_DCACHE_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV6_PERFCTR_DCACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV6_PERFCTR_DCACHE_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(L1I)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV6_PERFCTR_ICACHE_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV6_PERFCTR_ICACHE_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(LL)] = {
+		[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,
+		},
+	},
+	[C(DTLB)] = {
+		/*
+		 * The ARM performance counters can count micro DTLB misses,
+		 * micro ITLB misses and main TLB misses. There isn't an event
+		 * for TLB misses, so use the micro misses here and if users
+		 * want the main TLB misses they can use a raw counter.
+		 */
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV6_PERFCTR_DTLB_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV6_PERFCTR_DTLB_MISS,
+		},
+		[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)]	= ARMV6_PERFCTR_ITLB_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV6_PERFCTR_ITLB_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(BPU)] = {
+		[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,
+		},
+	},
+};
+
+enum armv6mpcore_perf_types {
+	ARMV6MPCORE_PERFCTR_ICACHE_MISS	    = 0x0,
+	ARMV6MPCORE_PERFCTR_IBUF_STALL	    = 0x1,
+	ARMV6MPCORE_PERFCTR_DDEP_STALL	    = 0x2,
+	ARMV6MPCORE_PERFCTR_ITLB_MISS	    = 0x3,
+	ARMV6MPCORE_PERFCTR_DTLB_MISS	    = 0x4,
+	ARMV6MPCORE_PERFCTR_BR_EXEC	    = 0x5,
+	ARMV6MPCORE_PERFCTR_BR_NOTPREDICT   = 0x6,
+	ARMV6MPCORE_PERFCTR_BR_MISPREDICT   = 0x7,
+	ARMV6MPCORE_PERFCTR_INSTR_EXEC	    = 0x8,
+	ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS = 0xA,
+	ARMV6MPCORE_PERFCTR_DCACHE_RDMISS   = 0xB,
+	ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS = 0xC,
+	ARMV6MPCORE_PERFCTR_DCACHE_WRMISS   = 0xD,
+	ARMV6MPCORE_PERFCTR_DCACHE_EVICTION = 0xE,
+	ARMV6MPCORE_PERFCTR_SW_PC_CHANGE    = 0xF,
+	ARMV6MPCORE_PERFCTR_MAIN_TLB_MISS   = 0x10,
+	ARMV6MPCORE_PERFCTR_EXPL_MEM_ACCESS = 0x11,
+	ARMV6MPCORE_PERFCTR_LSU_FULL_STALL  = 0x12,
+	ARMV6MPCORE_PERFCTR_WBUF_DRAINED    = 0x13,
+	ARMV6MPCORE_PERFCTR_CPU_CYCLES	    = 0xFF,
+};
+
+/*
+ * The hardware events that we support. We do support cache operations but
+ * we have harvard caches and no way to combine instruction and data
+ * accesses/misses in hardware.
+ */
+static const unsigned armv6mpcore_perf_map[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES]	    = ARMV6MPCORE_PERFCTR_CPU_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS]	    = ARMV6MPCORE_PERFCTR_INSTR_EXEC,
+	[PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_CACHE_MISSES]	    = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6MPCORE_PERFCTR_BR_EXEC,
+	[PERF_COUNT_HW_BRANCH_MISSES]	    = ARMV6MPCORE_PERFCTR_BR_MISPREDICT,
+	[PERF_COUNT_HW_BUS_CYCLES]	    = HW_OP_UNSUPPORTED,
+};
+
+static const unsigned armv6mpcore_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+					[PERF_COUNT_HW_CACHE_OP_MAX]
+					[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(L1D)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]  =
+				ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS,
+			[C(RESULT_MISS)]    =
+				ARMV6MPCORE_PERFCTR_DCACHE_RDMISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]  =
+				ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS,
+			[C(RESULT_MISS)]    =
+				ARMV6MPCORE_PERFCTR_DCACHE_WRMISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(L1I)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ICACHE_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ICACHE_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(LL)] = {
+		[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,
+		},
+	},
+	[C(DTLB)] = {
+		/*
+		 * The ARM performance counters can count micro DTLB misses,
+		 * micro ITLB misses and main TLB misses. There isn't an event
+		 * for TLB misses, so use the micro misses here and if users
+		 * want the main TLB misses they can use a raw counter.
+		 */
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_DTLB_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_DTLB_MISS,
+		},
+		[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)]    = ARMV6MPCORE_PERFCTR_ITLB_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ITLB_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(BPU)] = {
+		[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,
+		},
+	},
+};
+
+static inline unsigned long
+armv6_pmcr_read(void)
+{
+	u32 val;
+	asm volatile("mrc   p15, 0, %0, c15, c12, 0" : "=r"(val));
+	return val;
+}
+
+static inline void
+armv6_pmcr_write(unsigned long val)
+{
+	asm volatile("mcr   p15, 0, %0, c15, c12, 0" : : "r"(val));
+}
+
+#define ARMV6_PMCR_ENABLE		(1 << 0)
+#define ARMV6_PMCR_CTR01_RESET		(1 << 1)
+#define ARMV6_PMCR_CCOUNT_RESET		(1 << 2)
+#define ARMV6_PMCR_CCOUNT_DIV		(1 << 3)
+#define ARMV6_PMCR_COUNT0_IEN		(1 << 4)
+#define ARMV6_PMCR_COUNT1_IEN		(1 << 5)
+#define ARMV6_PMCR_CCOUNT_IEN		(1 << 6)
+#define ARMV6_PMCR_COUNT0_OVERFLOW	(1 << 8)
+#define ARMV6_PMCR_COUNT1_OVERFLOW	(1 << 9)
+#define ARMV6_PMCR_CCOUNT_OVERFLOW	(1 << 10)
+#define ARMV6_PMCR_EVT_COUNT0_SHIFT	20
+#define ARMV6_PMCR_EVT_COUNT0_MASK	(0xFF << ARMV6_PMCR_EVT_COUNT0_SHIFT)
+#define ARMV6_PMCR_EVT_COUNT1_SHIFT	12
+#define ARMV6_PMCR_EVT_COUNT1_MASK	(0xFF << ARMV6_PMCR_EVT_COUNT1_SHIFT)
+
+#define ARMV6_PMCR_OVERFLOWED_MASK \
+	(ARMV6_PMCR_COUNT0_OVERFLOW | ARMV6_PMCR_COUNT1_OVERFLOW | \
+	 ARMV6_PMCR_CCOUNT_OVERFLOW)
+
+static inline int
+armv6_pmcr_has_overflowed(unsigned long pmcr)
+{
+	return pmcr & ARMV6_PMCR_OVERFLOWED_MASK;
+}
+
+static inline int
+armv6_pmcr_counter_has_overflowed(unsigned long pmcr,
+				  enum armv6_counters counter)
+{
+	int ret = 0;
+
+	if (ARMV6_CYCLE_COUNTER == counter)
+		ret = pmcr & ARMV6_PMCR_CCOUNT_OVERFLOW;
+	else if (ARMV6_COUNTER0 == counter)
+		ret = pmcr & ARMV6_PMCR_COUNT0_OVERFLOW;
+	else if (ARMV6_COUNTER1 == counter)
+		ret = pmcr & ARMV6_PMCR_COUNT1_OVERFLOW;
+	else
+		WARN_ONCE(1, "invalid counter number (%d)\n", counter);
+
+	return ret;
+}
+
+static inline u32
+armv6pmu_read_counter(int counter)
+{
+	unsigned long value = 0;
+
+	if (ARMV6_CYCLE_COUNTER == counter)
+		asm volatile("mrc   p15, 0, %0, c15, c12, 1" : "=r"(value));
+	else if (ARMV6_COUNTER0 == counter)
+		asm volatile("mrc   p15, 0, %0, c15, c12, 2" : "=r"(value));
+	else if (ARMV6_COUNTER1 == counter)
+		asm volatile("mrc   p15, 0, %0, c15, c12, 3" : "=r"(value));
+	else
+		WARN_ONCE(1, "invalid counter number (%d)\n", counter);
+
+	return value;
+}
+
+static inline void
+armv6pmu_write_counter(int counter,
+		       u32 value)
+{
+	if (ARMV6_CYCLE_COUNTER == counter)
+		asm volatile("mcr   p15, 0, %0, c15, c12, 1" : : "r"(value));
+	else if (ARMV6_COUNTER0 == counter)
+		asm volatile("mcr   p15, 0, %0, c15, c12, 2" : : "r"(value));
+	else if (ARMV6_COUNTER1 == counter)
+		asm volatile("mcr   p15, 0, %0, c15, c12, 3" : : "r"(value));
+	else
+		WARN_ONCE(1, "invalid counter number (%d)\n", counter);
+}
+
+void
+armv6pmu_enable_event(struct hw_perf_event *hwc,
+		      int idx)
+{
+	unsigned long val, mask, evt, flags;
+
+	if (ARMV6_CYCLE_COUNTER == idx) {
+		mask	= 0;
+		evt	= ARMV6_PMCR_CCOUNT_IEN;
+	} else if (ARMV6_COUNTER0 == idx) {
+		mask	= ARMV6_PMCR_EVT_COUNT0_MASK;
+		evt	= (hwc->config_base << ARMV6_PMCR_EVT_COUNT0_SHIFT) |
+			  ARMV6_PMCR_COUNT0_IEN;
+	} else if (ARMV6_COUNTER1 == idx) {
+		mask	= ARMV6_PMCR_EVT_COUNT1_MASK;
+		evt	= (hwc->config_base << ARMV6_PMCR_EVT_COUNT1_SHIFT) |
+			  ARMV6_PMCR_COUNT1_IEN;
+	} else {
+		WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+		return;
+	}
+
+	/*
+	 * Mask out the current event and set the counter to count the event
+	 * that we're interested in.
+	 */
+	spin_lock_irqsave(&pmu_lock, flags);
+	val = armv6_pmcr_read();
+	val &= ~mask;
+	val |= evt;
+	armv6_pmcr_write(val);
+	spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static irqreturn_t
+armv6pmu_handle_irq(int irq_num,
+		    void *dev)
+{
+	unsigned long pmcr = armv6_pmcr_read();
+	struct perf_sample_data data;
+	struct cpu_hw_events *cpuc;
+	struct pt_regs *regs;
+	int idx;
+
+	if (!armv6_pmcr_has_overflowed(pmcr))
+		return IRQ_NONE;
+
+	regs = get_irq_regs();
+
+	/*
+	 * The interrupts are cleared by writing the overflow flags back to
+	 * the control register. All of the other bits don't have any effect
+	 * if they are rewritten, so write the whole value back.
+	 */
+	armv6_pmcr_write(pmcr);
+
+	perf_sample_data_init(&data, 0);
+
+	cpuc = &__get_cpu_var(cpu_hw_events);
+	for (idx = 0; idx <= armpmu->num_events; ++idx) {
+		struct perf_event *event = cpuc->events[idx];
+		struct hw_perf_event *hwc;
+
+		if (!test_bit(idx, cpuc->active_mask))
+			continue;
+
+		/*
+		 * We have a single interrupt for all counters. Check that
+		 * each counter has overflowed before we process it.
+		 */
+		if (!armv6_pmcr_counter_has_overflowed(pmcr, idx))
+			continue;
+
+		hwc = &event->hw;
+		armpmu_event_update(event, hwc, idx);
+		data.period = event->hw.last_period;
+		if (!armpmu_event_set_period(event, hwc, idx))
+			continue;
+
+		if (perf_event_overflow(event, 0, &data, regs))
+			armpmu->disable(hwc, idx);
+	}
+
+	/*
+	 * Handle the pending perf events.
+	 *
+	 * Note: this call *must* be run with interrupts disabled. For
+	 * platforms that can have the PMU interrupts raised as an NMI, this
+	 * will not work.
+	 */
+	irq_work_run();
+
+	return IRQ_HANDLED;
+}
+
+static void
+armv6pmu_start(void)
+{
+	unsigned long flags, val;
+
+	spin_lock_irqsave(&pmu_lock, flags);
+	val = armv6_pmcr_read();
+	val |= ARMV6_PMCR_ENABLE;
+	armv6_pmcr_write(val);
+	spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void
+armv6pmu_stop(void)
+{
+	unsigned long flags, val;
+
+	spin_lock_irqsave(&pmu_lock, flags);
+	val = armv6_pmcr_read();
+	val &= ~ARMV6_PMCR_ENABLE;
+	armv6_pmcr_write(val);
+	spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static int
+armv6pmu_get_event_idx(struct cpu_hw_events *cpuc,
+		       struct hw_perf_event *event)
+{
+	/* Always place a cycle counter into the cycle counter. */
+	if (ARMV6_PERFCTR_CPU_CYCLES == event->config_base) {
+		if (test_and_set_bit(ARMV6_CYCLE_COUNTER, cpuc->used_mask))
+			return -EAGAIN;
+
+		return ARMV6_CYCLE_COUNTER;
+	} else {
+		/*
+		 * For anything other than a cycle counter, try and use
+		 * counter0 and counter1.
+		 */
+		if (!test_and_set_bit(ARMV6_COUNTER1, cpuc->used_mask))
+			return ARMV6_COUNTER1;
+
+		if (!test_and_set_bit(ARMV6_COUNTER0, cpuc->used_mask))
+			return ARMV6_COUNTER0;
+
+		/* The counters are all in use. */
+		return -EAGAIN;
+	}
+}
+
+static void
+armv6pmu_disable_event(struct hw_perf_event *hwc,
+		       int idx)
+{
+	unsigned long val, mask, evt, flags;
+
+	if (ARMV6_CYCLE_COUNTER == idx) {
+		mask	= ARMV6_PMCR_CCOUNT_IEN;
+		evt	= 0;
+	} else if (ARMV6_COUNTER0 == idx) {
+		mask	= ARMV6_PMCR_COUNT0_IEN | ARMV6_PMCR_EVT_COUNT0_MASK;
+		evt	= ARMV6_PERFCTR_NOP << ARMV6_PMCR_EVT_COUNT0_SHIFT;
+	} else if (ARMV6_COUNTER1 == idx) {
+		mask	= ARMV6_PMCR_COUNT1_IEN | ARMV6_PMCR_EVT_COUNT1_MASK;
+		evt	= ARMV6_PERFCTR_NOP << ARMV6_PMCR_EVT_COUNT1_SHIFT;
+	} else {
+		WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+		return;
+	}
+
+	/*
+	 * Mask out the current event and set the counter to count the number
+	 * of ETM bus signal assertion cycles. The external reporting should
+	 * be disabled and so this should never increment.
+	 */
+	spin_lock_irqsave(&pmu_lock, flags);
+	val = armv6_pmcr_read();
+	val &= ~mask;
+	val |= evt;
+	armv6_pmcr_write(val);
+	spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void
+armv6mpcore_pmu_disable_event(struct hw_perf_event *hwc,
+			      int idx)
+{
+	unsigned long val, mask, flags, evt = 0;
+
+	if (ARMV6_CYCLE_COUNTER == idx) {
+		mask	= ARMV6_PMCR_CCOUNT_IEN;
+	} else if (ARMV6_COUNTER0 == idx) {
+		mask	= ARMV6_PMCR_COUNT0_IEN;
+	} else if (ARMV6_COUNTER1 == idx) {
+		mask	= ARMV6_PMCR_COUNT1_IEN;
+	} else {
+		WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+		return;
+	}
+
+	/*
+	 * Unlike UP ARMv6, we don't have a way of stopping the counters. We
+	 * simply disable the interrupt reporting.
+	 */
+	spin_lock_irqsave(&pmu_lock, flags);
+	val = armv6_pmcr_read();
+	val &= ~mask;
+	val |= evt;
+	armv6_pmcr_write(val);
+	spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static const struct arm_pmu armv6pmu = {
+	.id			= ARM_PERF_PMU_ID_V6,
+	.name			= "v6",
+	.handle_irq		= armv6pmu_handle_irq,
+	.enable			= armv6pmu_enable_event,
+	.disable		= armv6pmu_disable_event,
+	.read_counter		= armv6pmu_read_counter,
+	.write_counter		= armv6pmu_write_counter,
+	.get_event_idx		= armv6pmu_get_event_idx,
+	.start			= armv6pmu_start,
+	.stop			= armv6pmu_stop,
+	.cache_map		= &armv6_perf_cache_map,
+	.event_map		= &armv6_perf_map,
+	.raw_event_mask		= 0xFF,
+	.num_events		= 3,
+	.max_period		= (1LLU << 32) - 1,
+};
+
+const struct arm_pmu *__init armv6pmu_init(void)
+{
+	return &armv6pmu;
+}
+
+/*
+ * ARMv6mpcore is almost identical to single core ARMv6 with the exception
+ * that some of the events have different enumerations and that there is no
+ * *hack* to stop the programmable counters. To stop the counters we simply
+ * disable the interrupt reporting and update the event. When unthrottling we
+ * reset the period and enable the interrupt reporting.
+ */
+static const struct arm_pmu armv6mpcore_pmu = {
+	.id			= ARM_PERF_PMU_ID_V6MP,
+	.name			= "v6mpcore",
+	.handle_irq		= armv6pmu_handle_irq,
+	.enable			= armv6pmu_enable_event,
+	.disable		= armv6mpcore_pmu_disable_event,
+	.read_counter		= armv6pmu_read_counter,
+	.write_counter		= armv6pmu_write_counter,
+	.get_event_idx		= armv6pmu_get_event_idx,
+	.start			= armv6pmu_start,
+	.stop			= armv6pmu_stop,
+	.cache_map		= &armv6mpcore_perf_cache_map,
+	.event_map		= &armv6mpcore_perf_map,
+	.raw_event_mask		= 0xFF,
+	.num_events		= 3,
+	.max_period		= (1LLU << 32) - 1,
+};
+
+const struct arm_pmu *__init armv6mpcore_pmu_init(void)
+{
+	return &armv6mpcore_pmu;
+}
+#else
+const struct arm_pmu *__init armv6pmu_init(void)
+{
+	return NULL;
+}
+
+const struct arm_pmu *__init armv6mpcore_pmu_init(void)
+{
+	return NULL;
+}
+#endif	/* CONFIG_CPU_V6 */

arch/arm/kernel/sched_clock.c

+/*
+ * sched_clock.c: support for extending counters to full 64-bit ns counter
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/clocksource.h>
+#include <linux/init.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/timer.h>
+
+#include <asm/sched_clock.h>
+
+static void sched_clock_poll(unsigned long wrap_ticks);
+static DEFINE_TIMER(sched_clock_timer, sched_clock_poll, 0, 0);
+static void (*sched_clock_update_fn)(void);
+
+static void sched_clock_poll(unsigned long wrap_ticks)
+{
+	mod_timer(&sched_clock_timer, round_jiffies(jiffies + wrap_ticks));
+	sched_clock_update_fn();
+}
+
+void __init init_sched_clock(struct clock_data *cd, void (*update)(void),
+	unsigned int clock_bits, unsigned long rate)
+{
+	unsigned long r, w;
+	u64 res, wrap;
+	char r_unit;
+
+	sched_clock_update_fn = update;
+
+	/* calculate the mult/shift to convert counter ticks to ns. */
+	clocks_calc_mult_shift(&cd->mult, &cd->shift, rate, NSEC_PER_SEC, 60);
+
+	r = rate;
+	if (r >= 4000000) {
+		r /= 1000000;
+		r_unit = 'M';
+	} else {
+		r /= 1000;
+		r_unit = 'k';
+	}
+
+	/* calculate how many ns until we wrap */
+	wrap = cyc_to_ns((1ULL << clock_bits) - 1, cd->mult, cd->shift);
+	do_div(wrap, NSEC_PER_MSEC);
+	w = wrap;
+
+	/* calculate the ns resolution of this counter */
+	res = cyc_to_ns(1ULL, cd->mult, cd->shift);
+	pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lums\n",
+		clock_bits, r, r_unit, res, w);
+
+	/*
+	 * Start the timer to keep sched_clock() properly updated and
+	 * sets the initial epoch.
+	 */
+	sched_clock_timer.data = msecs_to_jiffies(w - (w / 10));
+	sched_clock_poll(sched_clock_timer.data);
+
+	/*
+	 * Ensure that sched_clock() starts off at 0ns
+	 */
+	cd->epoch_ns = 0;
+}

arch/arm/kernel/smp.c

@@ -16,6 +16,7 @@
 #include <linux/cache.h>
 #include <linux/profile.h>
 #include <linux/errno.h>
+#include <linux/ftrace.h>
 #include <linux/mm.h>
 #include <linux/err.h>
 #include <linux/cpu.h>
@@ -456,7 +457,7 @@ static void ipi_timer(void)
 }
 
 #ifdef CONFIG_LOCAL_TIMERS
-asmlinkage void __exception do_local_timer(struct pt_regs *regs)
+asmlinkage void __exception_irq_entry do_local_timer(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	int cpu = smp_processor_id();
@@ -543,7 +544,7 @@ static void ipi_cpu_stop(unsigned int cpu)
  *
  *  Bit 0 - Inter-processor function call
  */
-asmlinkage void __exception do_IPI(struct pt_regs *regs)
+asmlinkage void __exception_irq_entry do_IPI(struct pt_regs *regs)
 {
 	unsigned int cpu = smp_processor_id();
 	struct ipi_data *ipi = &per_cpu(ipi_data, cpu);

arch/arm/kernel/vmlinux.lds.S

@@ -101,6 +101,7 @@ SECTIONS
 			__exception_text_start = .;
 			*(.exception.text)
 			__exception_text_end = .;
+			IRQENTRY_TEXT
 			TEXT_TEXT
 			SCHED_TEXT
 			LOCK_TEXT

arch/arm/mach-at91/at91rm9200_time.c

@@ -101,7 +101,6 @@ static struct clocksource clk32k = {
 	.rating		= 150,
 	.read		= read_clk32k,
 	.mask		= CLOCKSOURCE_MASK(20),
-	.shift		= 10,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
@@ -201,8 +200,7 @@ void __init at91rm9200_timer_init(void)
 	clockevents_register_device(&clkevt);
 
 	/* register clocksource */
-	clk32k.mult = clocksource_hz2mult(AT91_SLOW_CLOCK, clk32k.shift);
-	clocksource_register(&clk32k);
+	clocksource_register_hz(&clk32k, AT91_SLOW_CLOCK);
 }
 
 struct sys_timer at91rm9200_timer = {

arch/arm/mach-at91/at91sam926x_time.c

@@ -51,7 +51,6 @@ static struct clocksource pit_clk = {
 	.name		= "pit",
 	.rating		= 175,
 	.read		= read_pit_clk,
-	.shift		= 20,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
@@ -163,10 +162,9 @@ static void __init at91sam926x_pit_init(void)
 	 * Register clocksource.  The high order bits of PIV are unused,
 	 * so this isn't a 32-bit counter unless we get clockevent irqs.
 	 */
-	pit_clk.mult = clocksource_hz2mult(pit_rate, pit_clk.shift);
 	bits = 12 /* PICNT */ + ilog2(pit_cycle) /* PIV */;
 	pit_clk.mask = CLOCKSOURCE_MASK(bits);
-	clocksource_register(&pit_clk);
+	clocksource_register_hz(&pit_clk, pit_rate);
 
 	/* Set up irq handler */
 	setup_irq(AT91_ID_SYS, &at91sam926x_pit_irq);

arch/arm/mach-davinci/time.c

@@ -276,7 +276,6 @@ static struct clocksource clocksource_davinci = {
 	.rating		= 300,
 	.read		= read_cycles,
 	.mask		= CLOCKSOURCE_MASK(32),
-	.shift		= 24,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
@@ -378,10 +377,8 @@ static void __init davinci_timer_init(void)
 
 	/* setup clocksource */
 	clocksource_davinci.name = id_to_name[clocksource_id];
-	clocksource_davinci.mult =
-		clocksource_khz2mult(davinci_clock_tick_rate/1000,
-				     clocksource_davinci.shift);
-	if (clocksource_register(&clocksource_davinci))
+	if (clocksource_register_hz(&clocksource_davinci,
+				    davinci_clock_tick_rate))
 		printk(err, clocksource_davinci.name);
 
 	/* setup clockevent */

arch/arm/mach-msm/Kconfig

@@ -49,6 +49,8 @@ endchoice
 
 config MSM_SOC_REV_A
 	bool
+config  ARCH_MSM_SCORPIONMP
+	bool
 
 config  ARCH_MSM_ARM11
 	bool

arch/arm/plat-nomadik/Kconfig

@@ -14,6 +14,7 @@ if PLAT_NOMADIK
 
 config HAS_MTU
 	bool
+	select HAVE_SCHED_CLOCK
 	help
 	  Support for Multi Timer Unit. MTU provides access
 	  to multiple interrupt generating programmable