perf: Drop the skip argument from perf_arch_fetch_regs_caller

Drop this argument now that we always want to rewind only to the
state of the first caller.
It means frame pointers are not necessary anymore to reliably get
the source of an event. But this also means we need this helper
to be a macro now, as an inline function is not an option since
we need to know when to provide a default implentation.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Cc: David Miller <davem@davemloft.net>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>

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

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

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

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.
 	 */

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)	{ }

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;

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;

include/linux/perf_event.h

@@ -905,8 +905,10 @@ extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
 
 extern void __perf_sw_event(u32, u64, int, struct pt_regs *, u64);
 
-extern void
-perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip);
+#ifndef perf_arch_fetch_caller_regs
+static inline void
+perf_arch_fetch_caller_regs(struct regs *regs, unsigned long ip) { }
+#endif
 
 /*
  * Take a snapshot of the regs. Skip ip and frame pointer to
@@ -916,31 +918,11 @@ perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip);
  * - bp for callchains
  * - eflags, for future purposes, just in case
  */
-static inline void perf_fetch_caller_regs(struct pt_regs *regs, int skip)
+static inline void perf_fetch_caller_regs(struct pt_regs *regs)
 {
-	unsigned long ip;
-
 	memset(regs, 0, sizeof(*regs));
 
-	switch (skip) {
-	case 1 :
-		ip = CALLER_ADDR0;
-		break;
-	case 2 :
-		ip = CALLER_ADDR1;
-		break;
-	case 3 :
-		ip = CALLER_ADDR2;
-		break;
-	case 4:
-		ip = CALLER_ADDR3;
-		break;
-	/* No need to support further for now */
-	default:
-		ip = 0;
-	}
-
-	return perf_arch_fetch_caller_regs(regs, ip, skip);
+	perf_arch_fetch_caller_regs(regs, CALLER_ADDR0);
 }
 
 static inline void
@@ -950,7 +932,7 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
 		struct pt_regs hot_regs;
 
 		if (!regs) {
-			perf_fetch_caller_regs(&hot_regs, 1);
+			perf_fetch_caller_regs(&hot_regs);
 			regs = &hot_regs;
 		}
 		__perf_sw_event(event_id, nr, nmi, regs, addr);

include/trace/ftrace.h

@@ -705,7 +705,7 @@ perf_trace_##call(void *__data, proto)					\
 	int __data_size;						\
 	int rctx;							\
 									\
-	perf_fetch_caller_regs(&__regs, 1);				\
+	perf_fetch_caller_regs(&__regs);				\
 									\
 	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
 	__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\

kernel/perf_event.c

@@ -2851,11 +2851,6 @@ __weak struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 	return NULL;
 }
 
-__weak
-void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
-{
-}
-
 
 /*
  * We assume there is only KVM supporting the callbacks.

kernel/trace/trace_event_perf.c

@@ -9,8 +9,6 @@
 #include <linux/kprobes.h>
 #include "trace.h"
 
-EXPORT_SYMBOL_GPL(perf_arch_fetch_caller_regs);
-
 static char *perf_trace_buf[4];
 
 /*