Merge branch 'clksrc' into devel

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

55 files changed, 3173 insertions, 2844 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 9d2608363390..2e86b8f62104 100644
--- a/arch/arm/Kconfig
+++ b/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
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 2fd0b99afc4b..eac62085f5b2 100644
--- a/arch/arm/Kconfig.debug
+++ b/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,
diff --git a/arch/arm/common/timer-sp.c b/arch/arm/common/timer-sp.c
index 4740313daa5b..6ef3342153b9 100644
--- a/arch/arm/common/timer-sp.c
+++ b/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);
 }
 
 
diff --git a/arch/arm/include/asm/sched_clock.h b/arch/arm/include/asm/sched_clock.h
new file mode 100644
index 000000000000..a84628be1a7b
--- /dev/null
+++ b/arch/arm/include/asm/sched_clock.h
@@ -0,0 +1,118 @@
+/*
+ * 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
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index 80025948b8ad..3222ab8b3447 100644
--- a/arch/arm/include/asm/system.h
+++ b/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;
diff --git a/arch/arm/include/asm/traps.h b/arch/arm/include/asm/traps.h
index 491960bf4260..124475afb007 100644
--- a/arch/arm/include/asm/traps.h
+++ b/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);
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 5b9b268f4fbb..fd3ec49bfba6 100644
--- a/arch/arm/kernel/Makefile
+++ b/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
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 80bf8cd88d7c..1e7b04a40a31 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/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:
diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index 971ac8c36ea7..c0062ad1e847 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/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)) {
+		curren