3 files changed, 92 insertions, 54 deletions

diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 2c1db77d7848..f05a35a59694 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -92,75 +92,111 @@ ENDPROC(ret_from_fork)
 #define CALL(x) .long x
 
 #ifdef CONFIG_FUNCTION_TRACER
+/*
+ * When compiling with -pg, gcc inserts a call to the mcount routine at the
+ * start of every function.  In mcount, apart from the function's address (in
+ * lr), we need to get hold of the function's caller's address.
+ *
+ * Older GCCs (pre-4.4) inserted a call to a routine called mcount like this:
+ *
+ *	bl	mcount
+ *
+ * These versions have the limitation that in order for the mcount routine to
+ * be able to determine the function's caller's address, an APCS-style frame
+ * pointer (which is set up with something like the code below) is required.
+ *
+ *	mov     ip, sp
+ *	push    {fp, ip, lr, pc}
+ *	sub     fp, ip, #4
+ *
+ * With EABI, these frame pointers are not available unless -mapcs-frame is
+ * specified, and if building as Thumb-2, not even then.
+ *
+ * Newer GCCs (4.4+) solve this problem by introducing a new version of mcount,
+ * with call sites like:
+ *
+ *	push	{lr}
+ *	bl	__gnu_mcount_nc
+ *
+ * With these compilers, frame pointers are not necessary.
+ *
+ * mcount can be thought of as a function called in the middle of a subroutine
+ * call.  As such, it needs to be transparent for both the caller and the
+ * callee: the original lr needs to be restored when leaving mcount, and no
+ * registers should be clobbered.  (In the __gnu_mcount_nc implementation, we
+ * clobber the ip register.  This is OK because the ARM calling convention
+ * allows it to be clobbered in subroutines and doesn't use it to hold
+ * parameters.)
+ */
 #ifdef CONFIG_DYNAMIC_FTRACE
 ENTRY(mcount)
-	stmdb sp!, {r0-r3, lr}
-	mov r0, lr
-	sub r0, r0, #MCOUNT_INSN_SIZE
+	stmdb	sp!, {r0-r3, lr}
+	mov	r0, lr
+	sub	r0, r0, #MCOUNT_INSN_SIZE
 
 	.globl mcount_call
 mcount_call:
-	bl ftrace_stub
-	ldr lr, [fp, #-4]			@ restore lr
-	ldmia sp!, {r0-r3, pc}
+	bl	ftrace_stub
+	ldr	lr, [fp, #-4]			@ restore lr
+	ldmia	sp!, {r0-r3, pc}
 
 ENTRY(ftrace_caller)
-	stmdb sp!, {r0-r3, lr}
-	ldr r1, [fp, #-4]
-	mov r0, lr
-	sub r0, r0, #MCOUNT_INSN_SIZE
+	stmdb	sp!, {r0-r3, lr}
+	ldr	r1, [fp, #-4]
+	mov	r0, lr
+	sub	r0, r0, #MCOUNT_INSN_SIZE
 
 	.globl ftrace_call
 ftrace_call:
-	bl ftrace_stub
-	ldr lr, [fp, #-4]			@ restore lr
-	ldmia sp!, {r0-r3, pc}
+	bl	ftrace_stub
+	ldr	lr, [fp, #-4]			@ restore lr
+	ldmia	sp!, {r0-r3, pc}
 
 #else
 
 ENTRY(__gnu_mcount_nc)
-	stmdb sp!, {r0-r3, lr}
-	ldr r0, =ftrace_trace_function
-	ldr r2, [r0]
-	adr r0, ftrace_stub
-	cmp r0, r2
-	bne gnu_trace
-	ldmia sp!, {r0-r3, ip, lr}
-	mov pc, ip
+	stmdb	sp!, {r0-r3, lr}
+	ldr	r0, =ftrace_trace_function
+	ldr	r2, [r0]
+	adr	r0, ftrace_stub
+	cmp	r0, r2
+	bne	gnu_trace
+	ldmia	sp!, {r0-r3, ip, lr}
+	mov	pc, ip
 
 gnu_trace:
-	ldr r1, [sp, #20]			@ lr of instrumented routine
-	mov r0, lr
-	sub r0, r0, #MCOUNT_INSN_SIZE
-	mov lr, pc
-	mov pc, r2
-	ldmia sp!, {r0-r3, ip, lr}
-	mov pc, ip
+	ldr	r1, [sp, #20]			@ lr of instrumented routine
+	mov	r0, lr
+	sub	r0, r0, #MCOUNT_INSN_SIZE
+	mov	lr, pc
+	mov	pc, r2
+	ldmia	sp!, {r0-r3, ip, lr}
+	mov	pc, ip
 
 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}
+	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}
 
 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}
+	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}
 
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 	.globl ftrace_stub
 ftrace_stub:
-	mov pc, lr
+	mov	pc, lr
 
 #endif /* CONFIG_FUNCTION_TRACER */
 
diff --git a/arch/arm/kernel/etm.c b/arch/arm/kernel/etm.c
index 827753966301..56418f98cd01 100644
--- a/arch/arm/kernel/etm.c
+++ b/arch/arm/kernel/etm.c
@@ -543,7 +543,9 @@ static int __init etm_probe(struct amba_device *dev, struct amba_id *id)
 	t->etm_portsz = 1;
 
 	etm_unlock(t);
-	ret = etm_readl(t, CSCR_PRSR);
+	(void)etm_readl(t, ETMMR_PDSR);
+	/* dummy first read */
+	(void)etm_readl(&tracer, ETMMR_OSSRR);
 
 	t->ncmppairs = etm_readl(t, ETMR_CONFCODE) & 0xf;
 	etm_writel(t, 0x440, ETMR_CTRL);
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index de12536d687f..417c392ddf1c 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -164,20 +164,20 @@ armpmu_event_set_period(struct perf_event *event,
 			struct hw_perf_event *hwc,
 			int idx)
 {
-	s64 left = atomic64_read(&hwc->period_left);
+	s64 left = local64_read(&hwc->period_left);
 	s64 period = hwc->sample_period;
 	int ret = 0;
 
 	if (unlikely(left <= -period)) {
 		left = period;
-		atomic64_set(&hwc->period_left, left);
+		local64_set(&hwc->period_left, left);
 		hwc->last_period = period;
 		ret = 1;
 	}
 
 	if (unlikely(left <= 0)) {
 		left += period;
-		atomic64_set(&hwc->period_left, left);
+		local64_set(&hwc->period_left, left);
 		hwc->last_period = period;
 		ret = 1;
 	}
@@ -185,7 +185,7 @@ armpmu_event_set_period(struct perf_event *event,
 	if (left > (s64)armpmu->max_period)
 		left = armpmu->max_period;
 
-	atomic64_set(&hwc->prev_count, (u64)-left);
+	local64_set(&hwc->prev_count, (u64)-left);
 
 	armpmu->write_counter(idx, (u64)(-left) & 0xffffffff);
 
@@ -204,18 +204,18 @@ armpmu_event_update(struct perf_event *event,
 	u64 delta;
 
 again:
-	prev_raw_count = atomic64_read(&hwc->prev_count);
+	prev_raw_count = local64_read(&hwc->prev_count);
 	new_raw_count = armpmu->read_counter(idx);
 
-	if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count,
+	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
 			     new_raw_count) != prev_raw_count)
 		goto again;
 
 	delta = (new_raw_count << shift) - (prev_raw_count << shift);
 	delta >>= shift;
 
-	atomic64_add(delta, &event->count);
-	atomic64_sub(delta, &hwc->period_left);
+	local64_add(delta, &event->count);
+	local64_sub(delta, &hwc->period_left);
 
 	return new_raw_count;
 }
@@ -478,7 +478,7 @@ __hw_perf_event_init(struct perf_event *event)
 	if (!hwc->sample_period) {
 		hwc->sample_period  = armpmu->max_period;
 		hwc->last_period    = hwc->sample_period;
-		atomic64_set(&hwc->period_left, hwc->sample_period);
+		local64_set(&hwc->period_left, hwc->sample_period);
 	}
 
 	err = 0;