7 files changed, 38 insertions, 50 deletions
diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h
index e6d4ce69b12..5c16b891d50 100644
--- a/arch/powerpc/include/asm/perf_event.h
+++ b/arch/powerpc/include/asm/perf_event.h
@@ -21,3 +21,15 @@
 #ifdef CONFIG_FSL_EMB_PERF_EVENT
 #include <asm/perf_event_fsl_emb.h>
 #endif
+
+#ifdef CONFIG_PERF_EVENTS
+#include <asm/ptrace.h>
+#include <asm/reg.h>
+
+#define perf_arch_fetch_caller_regs(regs, __ip)			\
+	do {							\
+		(regs)->nip = __ip;				\
+		(regs)->gpr[1] = *(unsigned long *)__get_SP();	\
+		asm volatile("mfmsr %0" : "=r" ((regs)->msr));	\
+	} while (0)
+#endif
diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index 22e507c8a55..2d29752cbe1 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -127,29 +127,3 @@ _GLOBAL(__setup_cpu_power7)
 _GLOBAL(__restore_cpu_power7)
 	/* place holder */
 	blr
-
-/*
- * Get a minimal set of registers for our caller's nth caller.
- * r3 = regs pointer, r5 = n.
- *
- * We only get R1 (stack pointer), NIP (next instruction pointer)
- * and LR (link register).  These are all we can get in the
- * general case without doing complicated stack unwinding, but
- * fortunately they are enough to do a stack backtrace, which
- * is all we need them for.
- */
-_GLOBAL(perf_arch_fetch_caller_regs)
-	mr	r6,r1
-	cmpwi	r5,0
-	mflr	r4
-	ble	2f
-	mtctr	r5
-1:	PPC_LL	r6,0(r6)
-	bdnz	1b
-	PPC_LL	r4,PPC_LR_STKOFF(r6)
-2:	PPC_LL	r7,0(r6)
-	PPC_LL	r7,PPC_LR_STKOFF(r7)
-	PPC_STL	r6,GPR1-STACK_FRAME_OVERHEAD(r3)
-	PPC_STL	r4,_NIP-STACK_FRAME_OVERHEAD(r3)
-	PPC_STL	r7,_LINK-STACK_FRAME_OVERHEAD(r3)
-	blr
diff --git a/arch/sparc/include/asm/perf_event.h b/arch/sparc/include/asm/perf_event.h
index 7e2669894ce..74c4e0cd889 100644
--- a/arch/sparc/include/asm/perf_event.h
+++ b/arch/sparc/include/asm/perf_event.h
@@ -6,7 +6,15 @@ extern void set_perf_event_pending(void);
 #define	PERF_EVENT_INDEX_OFFSET	0
 
 #ifdef CONFIG_PERF_EVENTS
+#include <asm/ptrace.h>
+
 extern void init_hw_perf_events(void);
+
+extern void
+__perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip);
+
+#define perf_arch_fetch_caller_regs(pt_regs, ip)	\
+	__perf_arch_fetch_caller_regs(pt_regs, ip, 1);
 #else
 static inline void init_hw_perf_events(void)	{ }
 #endif
diff --git a/arch/sparc/kernel/helpers.S b/arch/sparc/kernel/helpers.S
index 92090cc9e82..682fee06a16 100644
--- a/arch/sparc/kernel/helpers.S
+++ b/arch/sparc/kernel/helpers.S
@@ -47,9 +47,9 @@ stack_trace_flush:
 	.size		stack_trace_flush,.-stack_trace_flush
 
 #ifdef CONFIG_PERF_EVENTS
-	.globl		perf_arch_fetch_caller_regs
-	.type		perf_arch_fetch_caller_regs,#function
-perf_arch_fetch_caller_regs:
+	.globl		__perf_arch_fetch_caller_regs
+	.type		__perf_arch_fetch_caller_regs,#function
+__perf_arch_fetch_caller_regs:
 	/* We always read the %pstate into %o5 since we will use
 	 * that to construct a fake %tstate to store into the regs.
 	 */
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 254883d0c7e..02de29830ff 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -140,6 +140,19 @@ extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 extern unsigned long perf_misc_flags(struct pt_regs *regs);
 #define perf_misc_flags(regs)	perf_misc_flags(regs)
 
+#include <asm/stacktrace.h>
+
+/*
+ * We abuse bit 3 from flags to pass exact information, see perf_misc_flags
+ * and the comment with PERF_EFLAGS_EXACT.
+ */
+#define perf_arch_fetch_caller_regs(regs, __ip)		{	\
+	(regs)->ip = (__ip);					\
+	(regs)->bp = caller_frame_pointer();			\
+	(regs)->cs = __KERNEL_CS;				\
+	regs->flags = 0;					\
+}
+
 #else
 static inline void init_hw_perf_events(void)		{ }
 static inline void perf_events_lapic_init(void)	{ }
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index a957463d3c7..2b16a2ad23d 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -78,17 +78,14 @@ struct stack_frame_ia32 {
     u32 return_address;
 };
 
-static inline unsigned long rewind_frame_pointer(int n)
+static inline unsigned long caller_frame_pointer(void)
 {
 	struct stack_frame *frame;
 
 	get_bp(frame);
 
 #ifdef CONFIG_FRAME_POINTER
-	while (n--) {
-		if (probe_kernel_address(&frame->next_frame, frame))
-			break;
-	}
+	frame = frame->next_frame;
 #endif
 
 	return (unsigned long)frame;
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 9632fb61e8f..2c075fe573d 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1706,22 +1706,6 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 	return entry;
 }
 
-void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
-{
-	regs->ip = ip;
-	/*
-	 * perf_arch_fetch_caller_regs adds another call, we need to increment
-	 * the skip level
-	 */
-	regs->bp = rewind_frame_pointer(skip + 1);
-	regs->cs = __KERNEL_CS;
-	/*
-	 * We abuse bit 3 to pass exact information, see perf_misc_flags
-	 * and the comment with PERF_EFLAGS_EXACT.
-	 */
-	regs->flags = 0;
-}
-
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
 	unsigned long ip;