[GIT PULL] perf callchains updates

[GIT PULL] perf callchains updates

[Frederic Weisbecker]

Ingo,

Please pull the perf/core branch that can be found at:

git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing.git
	perf/core

Thanks,
	Frederic
---

Frederic Weisbecker (6):
      perf: Drop unappropriate tests on arch callchains
      perf: Generalize callchain_store()
      perf: Generalize some arch callchain code
      perf: Factorize callchain context handling
      perf: Fix race in callchains
      perf: Humanize the number of contexts

Namhyung Kim (1):
      perf, tracing: add missing __percpu markups


 arch/arm/kernel/perf_event.c         |   62 +--------
 arch/powerpc/kernel/perf_callchain.c |   86 ++++--------
 arch/sh/kernel/perf_callchain.c      |   50 +------
 arch/sparc/kernel/perf_event.c       |   69 +++------
 arch/x86/kernel/cpu/perf_event.c     |   82 +++--------
 include/linux/ftrace_event.h         |    4 +-
 include/linux/perf_event.h           |   30 +++-
 kernel/perf_event.c                  |  259 ++++++++++++++++++++++++++++++----
 kernel/trace/trace_event_perf.c      |   21 ++--
 kernel/trace/trace_functions_graph.c |    2 +-
 10 files changed, 342 insertions(+), 323 deletions(-)

[PATCH 1/7] perf: Drop unappropriate tests on arch callchains

[Frederic Weisbecker]

Drop the TASK_RUNNING test on user tasks for callchains as
this check doesn't seem to make any sense.

Also remove the tests for !current that is not supposed to
happen and current->pid as this should be handled at the
generic level, with exclude_idle attribute.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Tested-by: Will Deacon <will.deacon@arm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: David Miller <davem@davemloft.net>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Borislav Petkov <bp@amd64.org>
---
 arch/arm/kernel/perf_event.c     |    6 ------
 arch/sh/kernel/perf_callchain.c  |    3 ---
 arch/x86/kernel/cpu/perf_event.c |    3 ---
 3 files changed, 0 insertions(+), 12 deletions(-)

diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 417c392..fdcb0be 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -3107,12 +3107,6 @@ perf_do_callchain(struct pt_regs *regs,
 
 	is_user = user_mode(regs);
 
-	if (!current || !current->pid)
-		return;
-
-	if (is_user && current->state != TASK_RUNNING)
-		return;
-
 	if (!is_user)
 		perf_callchain_kernel(regs, entry);
 
diff --git a/arch/sh/kernel/perf_callchain.c b/arch/sh/kernel/perf_callchain.c
index a9dd3ab..1d6dbce 100644
--- a/arch/sh/kernel/perf_callchain.c
+++ b/arch/sh/kernel/perf_callchain.c
@@ -68,9 +68,6 @@ perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry)
 
 	is_user = user_mode(regs);
 
-	if (is_user && current->state != TASK_RUNNING)
-		return;
-
 	/*
 	 * Only the kernel side is implemented for now.
 	 */
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index f2da20f..4a4d191 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1703,9 +1703,6 @@ perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry)
 
 	is_user = user_mode(regs);
 
-	if (is_user && current->state != TASK_RUNNING)
-		return;
-
 	if (!is_user)
 		perf_callchain_kernel(regs, entry);
 
-- 
1.6.2.3

[PATCH 2/7] perf: Generalize callchain_store()

[Frederic Weisbecker]

callchain_store() is the same on every archs, inline it in
perf_event.h and rename it to perf_callchain_store() to avoid
any collision.

This removes repetitive code.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Tested-by: Will Deacon <will.deacon@arm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: David Miller <davem@davemloft.net>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Borislav Petkov <bp@amd64.org>
---
 arch/arm/kernel/perf_event.c         |   15 +++---------
 arch/powerpc/kernel/perf_callchain.c |   40 ++++++++++++----------------------
 arch/sh/kernel/perf_callchain.c      |   11 ++------
 arch/sparc/kernel/perf_event.c       |   26 ++++++++-------------
 arch/x86/kernel/cpu/perf_event.c     |   20 ++++++-----------
 include/linux/perf_event.h           |    7 ++++++
 6 files changed, 45 insertions(+), 74 deletions(-)

diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index fdcb0be..a07c3b1 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -3001,13 +3001,6 @@ arch_initcall(init_hw_perf_events);
 /*
  * Callchain handling code.
  */
-static inline void
-callchain_store(struct perf_callchain_entry *entry,
-		u64 ip)
-{
-	if (entry->nr < PERF_MAX_STACK_DEPTH)
-		entry->ip[entry->nr++] = ip;
-}
 
 /*
  * The registers we're interested in are at the end of the variable
@@ -3039,7 +3032,7 @@ user_backtrace(struct frame_tail *tail,
 	if (__copy_from_user_inatomic(&buftail, tail, sizeof(buftail)))
 		return NULL;
 
-	callchain_store(entry, buftail.lr);
+	perf_callchain_store(entry, buftail.lr);
 
 	/*
 	 * Frame pointers should strictly progress back up the stack
@@ -3057,7 +3050,7 @@ perf_callchain_user(struct pt_regs *regs,
 {
 	struct frame_tail *tail;
 
-	callchain_store(entry, PERF_CONTEXT_USER);
+	perf_callchain_store(entry, PERF_CONTEXT_USER);
 
 	if (!user_mode(regs))
 		regs = task_pt_regs(current);
@@ -3078,7 +3071,7 @@ callchain_trace(struct stackframe *fr,
 		void *data)
 {
 	struct perf_callchain_entry *entry = data;
-	callchain_store(entry, fr->pc);
+	perf_callchain_store(entry, fr->pc);
 	return 0;
 }
 
@@ -3088,7 +3081,7 @@ perf_callchain_kernel(struct pt_regs *regs,
 {
 	struct stackframe fr;
 
-	callchain_store(entry, PERF_CONTEXT_KERNEL);
+	perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
 	fr.fp = regs->ARM_fp;
 	fr.sp = regs->ARM_sp;
 	fr.lr = regs->ARM_lr;
diff --git a/arch/powerpc/kernel/perf_callchain.c b/arch/powerpc/kernel/perf_callchain.c
index 95ad9da..a286c2e 100644
--- a/arch/powerpc/kernel/perf_callchain.c
+++ b/arch/powerpc/kernel/perf_callchain.c
@@ -23,18 +23,6 @@
 #include "ppc32.h"
 #endif
 
-/*
- * Store another value in a callchain_entry.
- */
-static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip)
-{
-	unsigned int nr = entry->nr;
-
-	if (nr < PERF_MAX_STACK_DEPTH) {
-		entry->ip[nr] = ip;
-		entry->nr = nr + 1;
-	}
-}
 
 /*
  * Is sp valid as the address of the next kernel stack frame after prev_sp?
@@ -69,8 +57,8 @@ static void perf_callchain_kernel(struct pt_regs *regs,
 
 	lr = regs->link;
 	sp = regs->gpr[1];
-	callchain_store(entry, PERF_CONTEXT_KERNEL);
-	callchain_store(entry, regs->nip);
+	perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
+	perf_callchain_store(entry, regs->nip);
 
 	if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD))
 		return;
@@ -89,7 +77,7 @@ static void perf_callchain_kernel(struct pt_regs *regs,
 			next_ip = regs->nip;
 			lr = regs->link;
 			level = 0;
-			callchain_store(entry, PERF_CONTEXT_KERNEL);
+			perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
 
 		} else {
 			if (level == 0)
@@ -111,7 +99,7 @@ static void perf_callchain_kernel(struct pt_regs *regs,
 			++level;
 		}
 
-		callchain_store(entry, next_ip);
+		perf_callchain_store(entry, next_ip);
 		if (!valid_next_sp(next_sp, sp))
 			return;
 		sp = next_sp;
@@ -246,8 +234,8 @@ static void perf_callchain_user_64(struct pt_regs *regs,
 	next_ip = regs->nip;
 	lr = regs->link;
 	sp = regs->gpr[1];
-	callchain_store(entry, PERF_CONTEXT_USER);
-	callchain_store(entry, next_ip);
+	perf_callchain_store(entry, PERF_CONTEXT_USER);
+	perf_callchain_store(entry, next_ip);
 
 	for (;;) {
 		fp = (unsigned long __user *) sp;
@@ -276,14 +264,14 @@ static void perf_callchain_user_64(struct pt_regs *regs,
 			    read_user_stack_64(&uregs[PT_R1], &sp))
 				return;
 			level = 0;
-			callchain_store(entry, PERF_CONTEXT_USER);
-			callchain_store(entry, next_ip);
+			perf_callchain_store(entry, PERF_CONTEXT_USER);
+			perf_callchain_store(entry, next_ip);
 			continue;
 		}
 
 		if (level == 0)
 			next_ip = lr;
-		callchain_store(entry, next_ip);
+		perf_callchain_store(entry, next_ip);
 		++level;
 		sp = next_sp;
 	}
@@ -447,8 +435,8 @@ static void perf_callchain_user_32(struct pt_regs *regs,
 	next_ip = regs->nip;
 	lr = regs->link;
 	sp = regs->gpr[1];
-	callchain_store(entry, PERF_CONTEXT_USER);
-	callchain_store(entry, next_ip);
+	perf_callchain_store(entry, PERF_CONTEXT_USER);
+	perf_callchain_store(entry, next_ip);
 
 	while (entry->nr < PERF_MAX_STACK_DEPTH) {
 		fp = (unsigned int __user *) (unsigned long) sp;
@@ -470,14 +458,14 @@ static void perf_callchain_user_32(struct pt_regs *regs,
 			    read_user_stack_32(&uregs[PT_R1], &sp))
 				return;
 			level = 0;
-			callchain_store(entry, PERF_CONTEXT_USER);
-			callchain_store(entry, next_ip);
+			perf_callchain_store(entry, PERF_CONTEXT_USER);
+			perf_callchain_store(entry, next_ip);
 			continue;
 		}
 
 		if (level == 0)
 			next_ip = lr;
-		callchain_store(entry, next_ip);
+		perf_callchain_store(entry, next_ip);
 		++level;
 		sp = next_sp;
 	}
diff --git a/arch/sh/kernel/perf_callchain.c b/arch/sh/kernel/perf_callchain.c
index 1d6dbce..00143f3 100644
--- a/arch/sh/kernel/perf_callchain.c
+++ b/arch/sh/kernel/perf_callchain.c
@@ -14,11 +14,6 @@
 #include <asm/unwinder.h>
 #include <asm/ptrace.h>
 
-static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip)
-{
-	if (entry->nr < PERF_MAX_STACK_DEPTH)
-		entry->ip[entry->nr++] = ip;
-}
 
 static void callchain_warning(void *data, char *msg)
 {
@@ -39,7 +34,7 @@ static void callchain_address(void *data, unsigned long addr, int reliable)
 	struct perf_callchain_entry *entry = data;
 
 	if (reliable)
-		callchain_store(entry, addr);
+		perf_callchain_store(entry, addr);
 }
 
 static const struct stacktrace_ops callchain_ops = {
@@ -52,8 +47,8 @@ static const struct stacktrace_ops callchain_ops = {
 static void
 perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
 {
-	callchain_store(entry, PERF_CONTEXT_KERNEL);
-	callchain_store(entry, regs->pc);
+	perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
+	perf_callchain_store(entry, regs->pc);
 
 	unwind_stack(NULL, regs, NULL, &callchain_ops, entry);
 }
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 357ced3..2a95a90 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1283,12 +1283,6 @@ void __init init_hw_perf_events(void)
 	register_die_notifier(&perf_event_nmi_notifier);
 }
 
-static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip)
-{
-	if (entry->nr < PERF_MAX_STACK_DEPTH)
-		entry->ip[entry->nr++] = ip;
-}
-
 static void perf_callchain_kernel(struct pt_regs *regs,
 				  struct perf_callchain_entry *entry)
 {
@@ -1297,8 +1291,8 @@ static void perf_callchain_kernel(struct pt_regs *regs,
 	int graph = 0;
 #endif
 
-	callchain_store(entry, PERF_CONTEXT_KERNEL);
-	callchain_store(entry, regs->tpc);
+	perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
+	perf_callchain_store(entry, regs->tpc);
 
 	ksp = regs->u_regs[UREG_I6];
 	fp = ksp + STACK_BIAS;
@@ -1322,13 +1316,13 @@ static void perf_callchain_kernel(struct pt_regs *regs,
 			pc = sf->callers_pc;
 			fp = (unsigned long)sf->fp + STACK_BIAS;
 		}
-		callchain_store(entry, pc);
+		perf_callchain_store(entry, pc);
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 		if ((pc + 8UL) == (unsigned long) &return_to_handler) {
 			int index = current->curr_ret_stack;
 			if (current->ret_stack && index >= graph) {
 				pc = current->ret_stack[index - graph].ret;
-				callchain_store(entry, pc);
+				perf_callchain_store(entry, pc);
 				graph++;
 			}
 		}
@@ -1341,8 +1335,8 @@ static void perf_callchain_user_64(struct pt_regs *regs,
 {
 	unsigned long ufp;
 
-	callchain_store(entry, PERF_CONTEXT_USER);
-	callchain_store(entry, regs->tpc);
+	perf_callchain_store(entry, PERF_CONTEXT_USER);
+	perf_callchain_store(entry, regs->tpc);
 
 	ufp = regs->u_regs[UREG_I6] + STACK_BIAS;
 	do {
@@ -1355,7 +1349,7 @@ static void perf_callchain_user_64(struct pt_regs *regs,
 
 		pc = sf.callers_pc;
 		ufp = (unsigned long)sf.fp + STACK_BIAS;
-		callchain_store(entry, pc);
+		perf_callchain_store(entry, pc);
 	} while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
 
@@ -1364,8 +1358,8 @@ static void perf_callchain_user_32(struct pt_regs *regs,
 {
 	unsigned long ufp;
 
-	callchain_store(entry, PERF_CONTEXT_USER);
-	callchain_store(entry, regs->tpc);
+	perf_callchain_store(entry, PERF_CONTEXT_USER);
+	perf_callchain_store(entry, regs->tpc);
 
 	ufp = regs->u_regs[UREG_I6] & 0xffffffffUL;
 	do {
@@ -1378,7 +1372,7 @@ static void perf_callchain_user_32(struct pt_regs *regs,
 
 		pc = sf.callers_pc;
 		ufp = (unsigned long)sf.fp;
-		callchain_store(entry, pc);
+		perf_callchain_store(entry, pc);
 	} while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 4a4d191..8af28ca 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1571,12 +1571,6 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
  * callchain support
  */
 
-static inline
-void callchain_store(struct perf_callchain_entry *entry, u64 ip)
-{
-	if (entry->nr < PERF_MAX_STACK_DEPTH)
-		entry->ip[entry->nr++] = ip;
-}
 
 static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry);
 static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_nmi_entry);
@@ -1602,7 +1596,7 @@ static void backtrace_address(void *data, unsigned long addr, int reliable)
 {
 	struct perf_callchain_entry *entry = data;
 
-	callchain_store(entry, addr);
+	perf_callchain_store(entry, addr);
 }
 
 static const struct stacktrace_ops backtrace_ops = {
@@ -1616,8 +1610,8 @@ static const struct stacktrace_ops backtrace_ops = {
 static void
 perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
 {
-	callchain_store(entry, PERF_CONTEXT_KERNEL);
-	callchain_store(entry, regs->ip);
+	perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
+	perf_callchain_store(entry, regs->ip);
 
 	dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry);
 }
@@ -1646,7 +1640,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 		if (fp < compat_ptr(regs->sp))
 			break;
 
-		callchain_store(entry, frame.return_address);
+		perf_callchain_store(entry, frame.return_address);
 		fp = compat_ptr(frame.next_frame);
 	}
 	return 1;
@@ -1670,8 +1664,8 @@ perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
 
 	fp = (void __user *)regs->bp;
 
-	callchain_store(entry, PERF_CONTEXT_USER);
-	callchain_store(entry, regs->ip);
+	perf_callchain_store(entry, PERF_CONTEXT_USER);
+	perf_callchain_store(entry, regs->ip);
 
 	if (perf_callchain_user32(regs, entry))
 		return;
@@ -1688,7 +1682,7 @@ perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
 		if ((unsigned long)fp < regs->sp)
 			break;
 
-		callchain_store(entry, frame.return_address);
+		perf_callchain_store(entry, frame.return_address);
 		fp = frame.next_frame;
 	}
 }
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 937495c..3588804 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -978,6 +978,13 @@ extern void perf_event_fork(struct task_struct *tsk);
 
 extern struct perf_callchain_entry *perf_callchain(struct pt_regs *regs);
 
+static inline void
+perf_callchain_store(struct perf_callchain_entry *entry, u64 ip)
+{
+	if (entry->nr < PERF_MAX_STACK_DEPTH)
+		entry->ip[entry->nr++] = ip;
+}
+
 extern int sysctl_perf_event_paranoid;
 extern int sysctl_perf_event_mlock;
 extern int sysctl_perf_event_sample_rate;
-- 
1.6.2.3

[PATCH 3/7] perf: Generalize some arch callchain code

[Frederic Weisbecker]

- Most archs use one callchain buffer per cpu, except x86 that needs
  to deal with NMIs. Provide a default perf_callchain_buffer()
  implementation that x86 overrides.

- Centralize all the kernel/user regs handling and invoke new arch
  handlers from there: perf_callchain_user() / perf_callchain_kernel()
  That avoid all the user_mode(), current->mm checks and so...

- Invert some parameters in perf_callchain_*() helpers: entry to the
  left, regs to the right, following the traditional (dst, src).

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Tested-by: Will Deacon <will.deacon@arm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: David Miller <davem@davemloft.net>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Borislav Petkov <bp@amd64.org>
---
 arch/arm/kernel/perf_event.c         |   43 +++---------------------------
 arch/powerpc/kernel/perf_callchain.c |   49 +++++++++------------------------
 arch/sh/kernel/perf_callchain.c      |   37 +------------------------
 arch/sparc/kernel/perf_event.c       |   46 ++++++++++---------------------
 arch/x86/kernel/cpu/perf_event.c     |   45 +++++-------------------------
 include/linux/perf_event.h           |   10 ++++++-
 kernel/perf_event.c                  |   40 ++++++++++++++++++++++++++-
 7 files changed, 90 insertions(+), 180 deletions(-)

diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index a07c3b1..0e3bbdb 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -3044,17 +3044,13 @@ user_backtrace(struct frame_tail *tail,
 	return buftail.fp - 1;
 }
 
-static void
-perf_callchain_user(struct pt_regs *regs,
-		    struct perf_callchain_entry *entry)
+void
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
 	struct frame_tail *tail;
 
 	perf_callchain_store(entry, PERF_CONTEXT_USER);
 
-	if (!user_mode(regs))
-		regs = task_pt_regs(current);
-
 	tail = (struct frame_tail *)regs->ARM_fp - 1;
 
 	while (tail && !((unsigned long)tail & 0x3))
@@ -3075,9 +3071,8 @@ callchain_trace(struct stackframe *fr,
 	return 0;
 }
 
-static void
-perf_callchain_kernel(struct pt_regs *regs,
-		      struct perf_callchain_entry *entry)
+void
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
 	struct stackframe fr;
 
@@ -3088,33 +3083,3 @@ perf_callchain_kernel(struct pt_regs *regs,
 	fr.pc = regs->ARM_pc;
 	walk_stackframe(&fr, callchain_trace, entry);
 }
-
-static void
-perf_do_callchain(struct pt_regs *regs,
-		  struct perf_callchain_entry *entry)
-{
-	int is_user;
-
-	if (!regs)
-		return;
-
-	is_user = user_mode(regs);
-
-	if (!is_user)
-		perf_callchain_kernel(regs, entry);
-
-	if (current->mm)
-		perf_callchain_user(regs, entry);
-}
-
-static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry);
-
-struct perf_callchain_entry *
-perf_callchain(struct pt_regs *regs)
-{
-	struct perf_callchain_entry *entry = &__get_cpu_var(pmc_irq_entry);
-
-	entry->nr = 0;
-	perf_do_callchain(regs, entry);
-	return entry;
-}
diff --git a/arch/powerpc/kernel/perf_callchain.c b/arch/powerpc/kernel/perf_callchain.c
index a286c2e..f7a85ed 100644
--- a/arch/powerpc/kernel/perf_callchain.c
+++ b/arch/powerpc/kernel/perf_callchain.c
@@ -46,8 +46,8 @@ static int valid_next_sp(unsigned long sp, unsigned long prev_sp)
 	return 0;
 }
 
-static void perf_callchain_kernel(struct pt_regs *regs,
-				  struct perf_callchain_entry *entry)
+void
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
 	unsigned long sp, next_sp;
 	unsigned long next_ip;
@@ -221,8 +221,8 @@ static int sane_signal_64_frame(unsigned long sp)
 		puc == (unsigned long) &sf->uc;
 }
 
-static void perf_callchain_user_64(struct pt_regs *regs,
-				   struct perf_callchain_entry *entry)
+static void perf_callchain_user_64(struct perf_callchain_entry *entry,
+				   struct pt_regs *regs)
 {
 	unsigned long sp, next_sp;
 	unsigned long next_ip;
@@ -303,8 +303,8 @@ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
 	return __get_user_inatomic(*ret, ptr);
 }
 
-static inline void perf_callchain_user_64(struct pt_regs *regs,
-					  struct perf_callchain_entry *entry)
+static inline void perf_callchain_user_64(struct perf_callchain_entry *entry,
+					  struct pt_regs *regs)
 {
 }
 
@@ -423,8 +423,8 @@ static unsigned int __user *signal_frame_32_regs(unsigned int sp,
 	return mctx->mc_gregs;
 }
 
-static void perf_callchain_user_32(struct pt_regs *regs,
-				   struct perf_callchain_entry *entry)
+static void perf_callchain_user_32(struct perf_callchain_entry *entry,
+				   struct pt_regs *regs)
 {
 	unsigned int sp, next_sp;
 	unsigned int next_ip;
@@ -471,32 +471,11 @@ static void perf_callchain_user_32(struct pt_regs *regs,
 	}
 }
 
-/*
- * Since we can't get PMU interrupts inside a PMU interrupt handler,
- * we don't need separate irq and nmi entries here.
- */
-static DEFINE_PER_CPU(struct perf_callchain_entry, cpu_perf_callchain);
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+void
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
-	struct perf_callchain_entry *entry = &__get_cpu_var(cpu_perf_callchain);
-
-	entry->nr = 0;
-
-	if (!user_mode(regs)) {
-		perf_callchain_kernel(regs, entry);
-		if (current->mm)
-			regs = task_pt_regs(current);
-		else
-			regs = NULL;
-	}
-
-	if (regs) {
-		if (current_is_64bit())
-			perf_callchain_user_64(regs, entry);
-		else
-			perf_callchain_user_32(regs, entry);
-	}
-
-	return entry;
+	if (current_is_64bit())
+		perf_callchain_user_64(entry, regs);
+	else
+		perf_callchain_user_32(entry, regs);
 }
diff --git a/arch/sh/kernel/perf_callchain.c b/arch/sh/kernel/perf_callchain.c
index 00143f3..ef076a9 100644
--- a/arch/sh/kernel/perf_callchain.c
+++ b/arch/sh/kernel/perf_callchain.c
@@ -44,44 +44,11 @@ static const struct stacktrace_ops callchain_ops = {
 	.address	= callchain_address,
 };
 
-static void
-perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
+void
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
 	perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
 	perf_callchain_store(entry, regs->pc);
 
 	unwind_stack(NULL, regs, NULL, &callchain_ops, entry);
 }
-
-static void
-perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry)
-{
-	int is_user;
-
-	if (!regs)
-		return;
-
-	is_user = user_mode(regs);
-
-	/*
-	 * Only the kernel side is implemented for now.
-	 */
-	if (!is_user)
-		perf_callchain_kernel(regs, entry);
-}
-
-/*
- * No need for separate IRQ and NMI entries.
- */
-static DEFINE_PER_CPU(struct perf_callchain_entry, callchain);
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
-{
-	struct perf_callchain_entry *entry = &__get_cpu_var(callchain);
-
-	entry->nr = 0;
-
-	perf_do_callchain(regs, entry);
-
-	return entry;
-}
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 2a95a90..460162d 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1283,14 +1283,16 @@ void __init init_hw_perf_events(void)
 	register_die_notifier(&perf_event_nmi_notifier);
 }
 
-static void perf_callchain_kernel(struct pt_regs *regs,
-				  struct perf_callchain_entry *entry)
+void perf_callchain_kernel(struct perf_callchain_entry *entry,
+			   struct pt_regs *regs)
 {
 	unsigned long ksp, fp;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	int graph = 0;
 #endif
 
+	stack_trace_flush();
+
 	perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
 	perf_callchain_store(entry, regs->tpc);
 
@@ -1330,8 +1332,8 @@ static void perf_callchain_kernel(struct pt_regs *regs,
 	} while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
 
-static void perf_callchain_user_64(struct pt_regs *regs,
-				   struct perf_callchain_entry *entry)
+static void perf_callchain_user_64(struct perf_callchain_entry *entry,
+				   struct pt_regs *regs)
 {
 	unsigned long ufp;
 
@@ -1353,8 +1355,8 @@ static void perf_callchain_user_64(struct pt_regs *regs,
 	} while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
 
-static void perf_callchain_user_32(struct pt_regs *regs,
-				   struct perf_callchain_entry *entry)
+static void perf_callchain_user_32(struct perf_callchain_entry *entry,
+				   struct pt_regs *regs)
 {
 	unsigned long ufp;
 
@@ -1376,30 +1378,12 @@ static void perf_callchain_user_32(struct pt_regs *regs,
 	} while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
 
-/* Like powerpc we can't get PMU interrupts within the PMU handler,
- * so no need for separate NMI and IRQ chains as on x86.
- */
-static DEFINE_PER_CPU(struct perf_callchain_entry, callchain);
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+void
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
-	struct perf_callchain_entry *entry = &__get_cpu_var(callchain);
-
-	entry->nr = 0;
-	if (!user_mode(regs)) {
-		stack_trace_flush();
-		perf_callchain_kernel(regs, entry);
-		if (current->mm)
-			regs = task_pt_regs(current);
-		else
-			regs = NULL;
-	}
-	if (regs) {
-		flushw_user();
-		if (test_thread_flag(TIF_32BIT))
-			perf_callchain_user_32(regs, entry);
-		else
-			perf_callchain_user_64(regs, entry);
-	}
-	return entry;
+	flushw_user();
+	if (test_thread_flag(TIF_32BIT))
+		perf_callchain_user_32(entry, regs);
+	else
+		perf_callchain_user_64(entry, regs);
 }
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 8af28ca..39f8421 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1571,9 +1571,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
  * callchain support
  */
 
-
-static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry);
-static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_nmi_entry);
+static DEFINE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry_nmi);
 
 
 static void
@@ -1607,8 +1605,8 @@ static const struct stacktrace_ops backtrace_ops = {
 	.walk_stack		= print_context_stack_bp,
 };
 
-static void
-perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
+void
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
 	perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
 	perf_callchain_store(entry, regs->ip);
@@ -1653,14 +1651,12 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 }
 #endif
 
-static void
-perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
+void
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
 	struct stack_frame frame;
 	const void __user *fp;
 
-	if (!user_mode(regs))
-		regs = task_pt_regs(current);
 
 	fp = (void __user *)regs->bp;
 
@@ -1687,42 +1683,17 @@ perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
 	}
 }
 
-static void
-perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry)
-{
-	int is_user;
-
-	if (!regs)
-		return;
-
-	is_user = user_mode(regs);
-
-	if (!is_user)
-		perf_callchain_kernel(regs, entry);
-
-	if (current->mm)
-		perf_callchain_user(regs, entry);
-}
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+struct perf_callchain_entry *perf_callchain_buffer(void)
 {
-	struct perf_callchain_entry *entry;
-
 	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
 		/* TODO: We don't support guest os callchain now */
 		return NULL;
 	}
 
 	if (in_nmi())
-		entry = &__get_cpu_var(pmc_nmi_entry);
-	else
-		entry = &__get_cpu_var(pmc_irq_entry);
-
-	entry->nr = 0;
-
-	perf_do_callchain(regs, entry);
+		return &__get_cpu_var(perf_callchain_entry_nmi);
 
-	return entry;
+	return &__get_cpu_var(perf_callchain_entry);
 }
 
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 3588804..4db61dd 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -976,7 +976,15 @@ extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks
 extern void perf_event_comm(struct task_struct *tsk);
 extern void perf_event_fork(struct task_struct *tsk);
 
-extern struct perf_callchain_entry *perf_callchain(struct pt_regs *regs);
+/* Callchains */
+DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
+
+extern void perf_callchain_user(struct perf_callchain_entry *entry,
+				struct pt_regs *regs);
+extern void perf_callchain_kernel(struct perf_callchain_entry *entry,
+				  struct pt_regs *regs);
+extern struct perf_callchain_entry *perf_callchain_buffer(void);
+
 
 static inline void
 perf_callchain_store(struct perf_callchain_entry *entry, u64 ip)
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index c772a3d..02efde6 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -2937,13 +2937,49 @@ void perf_event_do_pending(void)
 	__perf_pending_run();
 }
 
+DEFINE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
+
 /*
  * Callchain support -- arch specific
  */
 
-__weak struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+__weak struct perf_callchain_entry *perf_callchain_buffer(void)
 {
-	return NULL;
+	return &__get_cpu_var(perf_callchain_entry);
+}
+
+__weak void perf_callchain_kernel(struct perf_callchain_entry *entry,
+				  struct pt_regs *regs)
+{
+}
+
+__weak void perf_callchain_user(struct perf_callchain_entry *entry,
+				struct pt_regs *regs)
+{
+}
+
+static struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+{
+	struct perf_callchain_entry *entry;
+
+	entry = perf_callchain_buffer();
+	if (!entry)
+		return NULL;
+
+	entry->nr = 0;
+
+	if (!user_mode(regs)) {
+		perf_callchain_kernel(entry, regs);
+		if (current->mm)
+			regs = task_pt_regs(current);
+		else
+			regs = NULL;
+	}
+
+	if (regs)
+		perf_callchain_user(entry, regs);
+
+	return entry;
 }
 
 
-- 
1.6.2.3

[PATCH 4/7] perf: Factorize callchain context handling

[Frederic Weisbecker]

Store the kernel and user contexts from the generic layer instead
of archs, this gathers some repetitive code.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Tested-by: Will Deacon <will.deacon@arm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: David Miller <davem@davemloft.net>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Borislav Petkov <bp@amd64.org>
---
 arch/arm/kernel/perf_event.c         |    2 --
 arch/powerpc/kernel/perf_callchain.c |    3 ---
 arch/sh/kernel/perf_callchain.c      |    1 -
 arch/sparc/kernel/perf_event.c       |    3 ---
 arch/x86/kernel/cpu/perf_event.c     |    2 --
 kernel/perf_event.c                  |    5 ++++-
 6 files changed, 4 insertions(+), 12 deletions(-)

diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 0e3bbdb..64ca8c3 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -3049,7 +3049,6 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
 	struct frame_tail *tail;
 
-	perf_callchain_store(entry, PERF_CONTEXT_USER);
 
 	tail = (struct frame_tail *)regs->ARM_fp - 1;
 
@@ -3076,7 +3075,6 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
 	struct stackframe fr;
 
-	perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
 	fr.fp = regs->ARM_fp;
 	fr.sp = regs->ARM_sp;
 	fr.lr = regs->ARM_lr;
diff --git a/arch/powerpc/kernel/perf_callchain.c b/arch/powerpc/kernel/perf_callchain.c
index f7a85ed..d05ae42 100644
--- a/arch/powerpc/kernel/perf_callchain.c
+++ b/arch/powerpc/kernel/perf_callchain.c
@@ -57,7 +57,6 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 
 	lr = regs->link;
 	sp = regs->gpr[1];
-	perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
 	perf_callchain_store(entry, regs->nip);
 
 	if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD))
@@ -234,7 +233,6 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry,
 	next_ip = regs->nip;
 	lr = regs->link;
 	sp = regs->gpr[1];
-	perf_callchain_store(entry, PERF_CONTEXT_USER);
 	perf_callchain_store(entry, next_ip);
 
 	for (;;) {
@@ -435,7 +433,6 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
 	next_ip = regs->nip;
 	lr = regs->link;
 	sp = regs->gpr[1];
-	perf_callchain_store(entry, PERF_CONTEXT_USER);
 	perf_callchain_store(entry, next_ip);
 
 	while (entry->nr < PERF_MAX_STACK_DEPTH) {
diff --git a/arch/sh/kernel/perf_callchain.c b/arch/sh/kernel/perf_callchain.c
index ef076a9..d5ca1ef 100644
--- a/arch/sh/kernel/perf_callchain.c
+++ b/arch/sh/kernel/perf_callchain.c
@@ -47,7 +47,6 @@ static const struct stacktrace_ops callchain_ops = {
 void
 perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
-	perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
 	perf_callchain_store(entry, regs->pc);
 
 	unwind_stack(NULL, regs, NULL, &callchain_ops, entry);
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 460162d..4bc4029 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1293,7 +1293,6 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry,
 
 	stack_trace_flush();
 
-	perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
 	perf_callchain_store(entry, regs->tpc);
 
 	ksp = regs->u_regs[UREG_I6];
@@ -1337,7 +1336,6 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry,
 {
 	unsigned long ufp;
 
-	perf_callchain_store(entry, PERF_CONTEXT_USER);
 	perf_callchain_store(entry, regs->tpc);
 
 	ufp = regs->u_regs[UREG_I6] + STACK_BIAS;
@@ -1360,7 +1358,6 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
 {
 	unsigned long ufp;
 
-	perf_callchain_store(entry, PERF_CONTEXT_USER);
 	perf_callchain_store(entry, regs->tpc);
 
 	ufp = regs->u_regs[UREG_I6] & 0xffffffffUL;
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 39f8421..a3c9222 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1608,7 +1608,6 @@ static const struct stacktrace_ops backtrace_ops = {
 void
 perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
-	perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
 	perf_callchain_store(entry, regs->ip);
 
 	dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry);
@@ -1660,7 +1659,6 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 
 	fp = (void __user *)regs->bp;
 
-	perf_callchain_store(entry, PERF_CONTEXT_USER);
 	perf_callchain_store(entry, regs->ip);
 
 	if (perf_callchain_user32(regs, entry))
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 02efde6..615d024 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -2969,6 +2969,7 @@ static struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 	entry->nr = 0;
 
 	if (!user_mode(regs)) {
+		perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
 		perf_callchain_kernel(entry, regs);
 		if (current->mm)
 			regs = task_pt_regs(current);
@@ -2976,8 +2977,10 @@ static struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 			regs = NULL;
 	}
 
-	if (regs)
+	if (regs) {
+		perf_callchain_store(entry, PERF_CONTEXT_USER);
 		perf_callchain_user(entry, regs);
+	}
 
 	return entry;
 }
-- 
1.6.2.3

[PATCH 5/7] perf: Fix race in callchains

[Frederic Weisbecker]

Now that software events don't have interrupt disabled anymore in
the event path, callchains can nest on any context. So seperating
nmi and others contexts in two buffers has become racy.

Fix this by providing one buffer per nesting level. Given the size
of the callchain entries (2040 bytes * 4), we now need to allocate
them dynamically.

v2: Fixed put_callchain_entry call after recursion.
    Fix the type of the recursion, it must be an array.

v3: Use a manual pr cpu allocation (temporary solution until NMIs
    can safely access vmalloc'ed memory).
    Do a better separation between callchain reference tracking and
    allocation. Make the "put" path lockless for non-release cases.

v4: Protect the callchain buffers with rcu.

v5: Do the cpu buffers allocations node affine.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Tested-by: Will Deacon <will.deacon@arm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: David Miller <davem@davemloft.net>
Cc: Borislav Petkov <bp@amd64.org>
---
 arch/x86/kernel/cpu/perf_event.c |   22 +--
 include/linux/perf_event.h       |    1 -
 kernel/perf_event.c              |  298 +++++++++++++++++++++++++++++---------
 3 files changed, 238 insertions(+), 83 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index a3c9222..8e91cf3 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1608,6 +1608,11 @@ static const struct stacktrace_ops backtrace_ops = {
 void
 perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+		/* TODO: We don't support guest os callchain now */
+		return NULL;
+	}
+
 	perf_callchain_store(entry, regs->ip);
 
 	dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry);
@@ -1656,6 +1661,10 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 	struct stack_frame frame;
 	const void __user *fp;
 
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+		/* TODO: We don't support guest os callchain now */
+		return NULL;
+	}
 
 	fp = (void __user *)regs->bp;
 
@@ -1681,19 +1690,6 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 	}
 }
 
-struct perf_callchain_entry *perf_callchain_buffer(void)
-{
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		/* TODO: We don't support guest os callchain now */
-		return NULL;
-	}
-
-	if (in_nmi())
-		return &__get_cpu_var(perf_callchain_entry_nmi);
-
-	return &__get_cpu_var(perf_callchain_entry);
-}
-
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
 	unsigned long ip;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 4db61dd..d7e8ea6 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -983,7 +983,6 @@ extern void perf_callchain_user(struct perf_callchain_entry *entry,
 				struct pt_regs *regs);
 extern void perf_callchain_kernel(struct perf_callchain_entry *entry,
 				  struct pt_regs *regs);
-extern struct perf_callchain_entry *perf_callchain_buffer(void);
 
 
 static inline void
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 615d024..75ab8a2 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -1764,6 +1764,216 @@ static u64 perf_event_read(struct perf_event *event)
 }
 
 /*
+ * Callchain support
+ */
+
+struct callchain_cpus_entries {
+	struct rcu_head			rcu_head;
+	struct perf_callchain_entry	*cpu_entries[0];
+};
+
+static DEFINE_PER_CPU(int, callchain_recursion[4]);
+static atomic_t nr_callchain_events;
+static DEFINE_MUTEX(callchain_mutex);
+struct callchain_cpus_entries *callchain_cpus_entries;
+
+
+__weak void perf_callchain_kernel(struct perf_callchain_entry *entry,
+				  struct pt_regs *regs)
+{
+}
+
+__weak void perf_callchain_user(struct perf_callchain_entry *entry,
+				struct pt_regs *regs)
+{
+}
+
+static void release_callchain_buffers_rcu(struct rcu_head *head)
+{
+	struct callchain_cpus_entries *entries;
+	int cpu;
+
+	entries = container_of(head, struct callchain_cpus_entries, rcu_head);
+
+	for_each_possible_cpu(cpu)
+		kfree(entries->cpu_entries[cpu]);
+
+	kfree(entries);
+}
+
+static void release_callchain_buffers(void)
+{
+	struct callchain_cpus_entries *entries;
+
+	entries = callchain_cpus_entries;
+	rcu_assign_pointer(callchain_cpus_entries, NULL);
+	call_rcu(&entries->rcu_head, release_callchain_buffers_rcu);
+}
+
+static int alloc_callchain_buffers(void)
+{
+	int cpu;
+	int size;
+	struct callchain_cpus_entries *entries;
+
+	/*
+	 * We can't use the percpu allocation API for data that can be
+	 * accessed from NMI. Use a temporary manual per cpu allocation
+	 * until that gets sorted out.
+	 */
+	size = sizeof(*entries) + sizeof(struct perf_callchain_entry *) *
+		num_possible_cpus();
+
+	entries = kzalloc(size, GFP_KERNEL);
+	if (!entries)
+		return -ENOMEM;
+
+	size = sizeof(struct perf_callchain_entry) * 4;
+
+	for_each_possible_cpu(cpu) {
+		entries->cpu_entries[cpu] = kmalloc_node(size, GFP_KERNEL,
+							 cpu_to_node(cpu));
+		if (!entries->cpu_entries[cpu])
+			goto fail;
+	}
+
+	rcu_assign_pointer(callchain_cpus_entries, entries);
+
+	return 0;
+
+fail:
+	for_each_possible_cpu(cpu)
+		kfree(entries->cpu_entries[cpu]);
+	kfree(entries);
+
+	return -ENOMEM;
+}
+
+static int get_callchain_buffers(void)
+{
+	int err = 0;
+	int count;
+
+	mutex_lock(&callchain_mutex);
+
+	count = atomic_inc_return(&nr_callchain_events);
+	if (WARN_ON_ONCE(count < 1)) {
+		err = -EINVAL;
+		goto exit;
+	}
+
+	if (count > 1) {
+		/* If the allocation failed, give up */
+		if (!callchain_cpus_entries)
+			err = -ENOMEM;
+		goto exit;
+	}
+
+	err = alloc_callchain_buffers();
+	if (err)
+		release_callchain_buffers();
+exit:
+	mutex_unlock(&callchain_mutex);
+
+	return err;
+}
+
+static void put_callchain_buffers(void)
+{
+	if (atomic_dec_and_mutex_lock(&nr_callchain_events, &callchain_mutex)) {
+		release_callchain_buffers();
+		mutex_unlock(&callchain_mutex);
+	}
+}
+
+static int get_recursion_context(int *recursion)
+{
+	int rctx;
+
+	if (in_nmi())
+		rctx = 3;
+	else if (in_irq())
+		rctx = 2;
+	else if (in_softirq())
+		rctx = 1;
+	else
+		rctx = 0;
+
+	if (recursion[rctx])
+		return -1;
+
+	recursion[rctx]++;
+	barrier();
+
+	return rctx;
+}
+
+static inline void put_recursion_context(int *recursion, int rctx)
+{
+	barrier();
+	recursion[rctx]--;
+}
+
+static struct perf_callchain_entry *get_callchain_entry(int *rctx)
+{
+	int cpu;
+	struct callchain_cpus_entries *entries;
+
+	*rctx = get_recursion_context(__get_cpu_var(callchain_recursion));
+	if (*rctx == -1)
+		return NULL;
+
+	entries = rcu_dereference(callchain_cpus_entries);
+	if (!entries)
+		return NULL;
+
+	cpu = smp_processor_id();
+
+	return &entries->cpu_entries[cpu][*rctx];
+}
+
+static void
+put_callchain_entry(int rctx)
+{
+	put_recursion_context(__get_cpu_var(callchain_recursion), rctx);
+}
+
+static struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+{
+	int rctx;
+	struct perf_callchain_entry *entry;
+
+
+	entry = get_callchain_entry(&rctx);
+	if (rctx == -1)
+		return NULL;
+
+	if (!entry)
+		goto exit_put;
+
+	entry->nr = 0;
+
+	if (!user_mode(regs)) {
+		perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
+		perf_callchain_kernel(entry, regs);
+		if (current->mm)
+			regs = task_pt_regs(current);
+		else
+			regs = NULL;
+	}
+
+	if (regs) {
+		perf_callchain_store(entry, PERF_CONTEXT_USER);
+		perf_callchain_user(entry, regs);
+	}
+
+exit_put:
+	put_callchain_entry(rctx);
+
+	return entry;
+}
+
+/*
  * Initialize the perf_event context in a task_struct:
  */
 static void
@@ -1895,6 +2105,8 @@ static void free_event(struct perf_event *event)
 			atomic_dec(&nr_comm_events);
 		if (event->attr.task)
 			atomic_dec(&nr_task_events);
+		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
+			put_callchain_buffers();
 	}
 
 	if (event->buffer) {
@@ -2937,55 +3149,6 @@ void perf_event_do_pending(void)
 	__perf_pending_run();
 }
 
-DEFINE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
-
-/*
- * Callchain support -- arch specific
- */
-
-__weak struct perf_callchain_entry *perf_callchain_buffer(void)
-{
-	return &__get_cpu_var(perf_callchain_entry);
-}
-
-__weak void perf_callchain_kernel(struct perf_callchain_entry *entry,
-				  struct pt_regs *regs)
-{
-}
-
-__weak void perf_callchain_user(struct perf_callchain_entry *entry,
-				struct pt_regs *regs)
-{
-}
-
-static struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
-{
-	struct perf_callchain_entry *entry;
-
-	entry = perf_callchain_buffer();
-	if (!entry)
-		return NULL;
-
-	entry->nr = 0;
-
-	if (!user_mode(regs)) {
-		perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
-		perf_callchain_kernel(entry, regs);
-		if (current->mm)
-			regs = task_pt_regs(current);
-		else
-			regs = NULL;
-	}
-
-	if (regs) {
-		perf_callchain_store(entry, PERF_CONTEXT_USER);
-		perf_callchain_user(entry, regs);
-	}
-
-	return entry;
-}
-
-
 /*
  * We assume there is only KVM supporting the callbacks.
  * Later on, we might change it to a list if there is
@@ -3480,14 +3643,20 @@ static void perf_event_output(struct perf_event *event, int nmi,
 	struct perf_output_handle handle;
 	struct perf_event_header header;
 
+	/* protect the callchain buffers */
+	rcu_read_lock();
+
 	perf_prepare_sample(&header, data, event, regs);
 
 	if (perf_output_begin(&handle, event, header.size, nmi, 1))
-		return;
+		goto exit;
 
 	perf_output_sample(&handle, &header, data, event);
 
 	perf_output_end(&handle);
+
+exit:
+	rcu_read_unlock();
 }
 
 /*
@@ -4243,32 +4412,16 @@ end:
 int perf_swevent_get_recursion_context(void)
 {
 	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-	int rctx;
 
-	if (in_nmi())
-		rctx = 3;
-	else if (in_irq())
-		rctx = 2;
-	else if (in_softirq())
-		rctx = 1;
-	else
-		rctx = 0;
-
-	if (cpuctx->recursion[rctx])
-		return -1;
-
-	cpuctx->recursion[rctx]++;
-	barrier();
-
-	return rctx;
+	return get_recursion_context(cpuctx->recursion);
 }
 EXPORT_SYMBOL_GPL(perf_swevent_get_recursion_context);
 
 void inline perf_swevent_put_recursion_context(int rctx)
 {
 	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-	barrier();
-	cpuctx->recursion[rctx]--;
+
+	put_recursion_context(cpuctx->recursion, rctx);
 }
 
 void __perf_sw_event(u32 event_id, u64 nr, int nmi,
@@ -4968,6 +5121,13 @@ done:
 			atomic_inc(&nr_comm_events);
 		if (event->attr.task)
 			atomic_inc(&nr_task_events);
+		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
+			err = get_callchain_buffers();
+			if (err) {
+				free_event(event);
+				return ERR_PTR(err);
+			}
+		}
 	}
 
 	return event;
-- 
1.6.2.3

[PATCH 6/7] perf: Humanize the number of contexts

[Frederic Weisbecker]

Instead of hardcoding the number of contexts for the recursions
barriers, define a cpp constant to make the code more
self-explanatory.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Stephane Eranian <eranian@google.com>
---
 include/linux/perf_event.h      |   14 ++++++++------
 kernel/perf_event.c             |    4 ++--
 kernel/trace/trace_event_perf.c |    8 ++++----
 3 files changed, 14 insertions(+), 12 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index d7e8ea6..ae6fa60 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -808,6 +808,12 @@ struct perf_event_context {
 	struct rcu_head			rcu_head;
 };
 
+/*
+ * Number of contexts where an event can trigger:
+ * 	task, softirq, hardirq, nmi.
+ */
+#define PERF_NR_CONTEXTS	4
+
 /**
  * struct perf_event_cpu_context - per cpu event context structure
  */
@@ -821,12 +827,8 @@ struct perf_cpu_context {
 	struct mutex			hlist_mutex;
 	int				hlist_refcount;
 
-	/*
-	 * Recursion avoidance:
-	 *
-	 * task, softirq, irq, nmi context
-	 */
-	int				recursion[4];
+	/* Recursion avoidance in each contexts */
+	int				recursion[PERF_NR_CONTEXTS];
 };
 
 struct perf_output_handle {
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 75ab8a2..f416aef 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -1772,7 +1772,7 @@ struct callchain_cpus_entries {
 	struct perf_callchain_entry	*cpu_entries[0];
 };
 
-static DEFINE_PER_CPU(int, callchain_recursion[4]);
+static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]);
 static atomic_t nr_callchain_events;
 static DEFINE_MUTEX(callchain_mutex);
 struct callchain_cpus_entries *callchain_cpus_entries;
@@ -1828,7 +1828,7 @@ static int alloc_callchain_buffers(void)
 	if (!entries)
 		return -ENOMEM;
 
-	size = sizeof(struct perf_callchain_entry) * 4;
+	size = sizeof(struct perf_callchain_entry) * PERF_NR_CONTEXTS;
 
 	for_each_possible_cpu(cpu) {
 		entries->cpu_entries[cpu] = kmalloc_node(size, GFP_KERNEL,
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 000e6e8..db2eae2 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -9,7 +9,7 @@
 #include <linux/kprobes.h>
 #include "trace.h"
 
-static char *perf_trace_buf[4];
+static char *perf_trace_buf[PERF_NR_CONTEXTS];
 
 /*
  * Force it to be aligned to unsigned long to avoid misaligned accesses
@@ -45,7 +45,7 @@ static int perf_trace_event_init(struct ftrace_event_call *tp_event,
 		char *buf;
 		int i;
 
-		for (i = 0; i < 4; i++) {
+		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
 			buf = (char *)alloc_percpu(perf_trace_t);
 			if (!buf)
 				goto fail;
@@ -65,7 +65,7 @@ fail:
 	if (!total_ref_count) {
 		int i;
 
-		for (i = 0; i < 4; i++) {
+		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
 			free_percpu(perf_trace_buf[i]);
 			perf_trace_buf[i] = NULL;
 		}
@@ -140,7 +140,7 @@ void perf_trace_destroy(struct perf_event *p_event)
 	tp_event->perf_events = NULL;
 
 	if (!--total_ref_count) {
-		for (i = 0; i < 4; i++) {
+		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
 			free_percpu(perf_trace_buf[i]);
 			perf_trace_buf[i] = NULL;
 		}
-- 
1.6.2.3

[PATCH 7/7] perf, tracing: add missing __percpu markups

[Frederic Weisbecker]

From: Namhyung Kim <namhyung@gmail.com>

ftrace_event_call->perf_events, perf_trace_buf,
fgraph_data->cpu_data and some local variables are percpu pointers
missing __percpu markups. Add them.

Signed-off-by: Namhyung Kim <namhyung@gmail.com>
Acked-by: Tejun Heo <tj@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Stephane Eranian <eranian@google.com>
LKML-Reference: <1281498479-28551-1-git-send-email-namhyung@gmail.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
---
 include/linux/ftrace_event.h         |    4 ++--
 kernel/trace/trace_event_perf.c      |   15 ++++++++-------
 kernel/trace/trace_functions_graph.c |    2 +-
 3 files changed, 11 insertions(+), 10 deletions(-)

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 02b8b24..5f8ad7b 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -191,8 +191,8 @@ struct ftrace_event_call {
 	unsigned int		flags;
 
 #ifdef CONFIG_PERF_EVENTS
-	int			perf_refcount;
-	struct hlist_head	*perf_events;
+	int				perf_refcount;
+	struct hlist_head __percpu	*perf_events;
 #endif
 };
 
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index db2eae2..92f5477 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -9,7 +9,7 @@
 #include <linux/kprobes.h>
 #include "trace.h"
 
-static char *perf_trace_buf[PERF_NR_CONTEXTS];
+static char __percpu *perf_trace_buf[PERF_NR_CONTEXTS];
 
 /*
  * Force it to be aligned to unsigned long to avoid misaligned accesses
@@ -24,7 +24,7 @@ static int	total_ref_count;
 static int perf_trace_event_init(struct ftrace_event_call *tp_event,
 				 struct perf_event *p_event)
 {
-	struct hlist_head *list;
+	struct hlist_head __percpu *list;
 	int ret = -ENOMEM;
 	int cpu;
 
@@ -42,11 +42,11 @@ static int perf_trace_event_init(struct ftrace_event_call *tp_event,
 	tp_event->perf_events = list;
 
 	if (!total_ref_count) {
-		char *buf;
+		char __percpu *buf;
 		int i;
 
 		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
-			buf = (char *)alloc_percpu(perf_trace_t);
+			buf = (char __percpu *)alloc_percpu(perf_trace_t);
 			if (!buf)
 				goto fail;
 
@@ -102,13 +102,14 @@ int perf_trace_init(struct perf_event *p_event)
 int perf_trace_enable(struct perf_event *p_event)
 {
 	struct ftrace_event_call *tp_event = p_event->tp_event;
+	struct hlist_head __percpu *pcpu_list;
 	struct hlist_head *list;
 
-	list = tp_event->perf_events;
-	if (WARN_ON_ONCE(!list))
+	pcpu_list = tp_event->perf_events;
+	if (WARN_ON_ONCE(!pcpu_list))
 		return -EINVAL;
 
-	list = this_cpu_ptr(list);
+	list = this_cpu_ptr(pcpu_list);
 	hlist_add_head_rcu(&p_event->hlist_entry, list);
 
 	return 0;
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 6bff236..fcb5a54 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -23,7 +23,7 @@ struct fgraph_cpu_data {
 };
 
 struct fgraph_data {
-	struct fgraph_cpu_data		*cpu_data;
+	struct fgraph_cpu_data __percpu *cpu_data;
 
 	/* Place to preserve last processed entry. */
 	struct ftrace_graph_ent_entry	ent;
-- 
1.6.2.3

Re: [GIT PULL] perf callchains updates

[Frederic Weisbecker]

On Thu, Aug 19, 2010 at 01:46:09AM +0200, Frederic Weisbecker wrote:
> Ingo,
> 
> Please pull the perf/core branch that can be found at:
> 
> git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing.git
> 	perf/core
> 
> Thanks,
> 	Frederic



BTW, I've built tested it on ARM, Sparc64 (thanks Borislav for the pointer),
PowerPC and SH.

And I've runtime tested it on x86-64, Will has runtime tested it on ARM.

Thanks.

Re: [GIT PULL] perf callchains updates

[Peter Zijlstra]

On Thu, 2010-08-19 at 01:46 +0200, Frederic Weisbecker wrote:

> Frederic Weisbecker (6):
>       perf: Drop unappropriate tests on arch callchains
>       perf: Generalize callchain_store()
>       perf: Generalize some arch callchain code
>       perf: Factorize callchain context handling
>       perf: Fix race in callchains
>       perf: Humanize the number of contexts
> 
> Namhyung Kim (1):
>       perf, tracing: add missing __percpu markups

Looks good, thanks Frederic!

Re: [GIT PULL] perf callchains updates

[Ingo Molnar]

* Frederic Weisbecker <fweisbec@gmail.com> wrote:

> Ingo,
> 
> Please pull the perf/core branch that can be found at:
> 
> git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing.git
> 	perf/core
> 
> Thanks,
> 	Frederic
> ---
> 
> Frederic Weisbecker (6):
>       perf: Drop unappropriate tests on arch callchains
>       perf: Generalize callchain_store()
>       perf: Generalize some arch callchain code
>       perf: Factorize callchain context handling
>       perf: Fix race in callchains
>       perf: Humanize the number of contexts
> 
> Namhyung Kim (1):
>       perf, tracing: add missing __percpu markups
> 
> 
>  arch/arm/kernel/perf_event.c         |   62 +--------
>  arch/powerpc/kernel/perf_callchain.c |   86 ++++--------
>  arch/sh/kernel/perf_callchain.c      |   50 +------
>  arch/sparc/kernel/perf_event.c       |   69 +++------
>  arch/x86/kernel/cpu/perf_event.c     |   82 +++--------
>  include/linux/ftrace_event.h         |    4 +-
>  include/linux/perf_event.h           |   30 +++-
>  kernel/perf_event.c                  |  259 ++++++++++++++++++++++++++++++----
>  kernel/trace/trace_event_perf.c      |   21 ++--
>  kernel/trace/trace_functions_graph.c |    2 +-
>  10 files changed, 342 insertions(+), 323 deletions(-)

Pulled, thanks a lot Frederic!

	Ingo

Re: [GIT PULL] perf callchains updates

[Peter Zijlstra]

On Thu, 2010-08-19 at 01:46 +0200, Frederic Weisbecker wrote:
> Ingo,
> 
> Please pull the perf/core branch that can be found at:
> 
> git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing.git
> 	perf/core
> 
> Thanks,
> 	Frederic
> ---
> 
> Frederic Weisbecker (6):
>       perf: Drop unappropriate tests on arch callchains
>       perf: Generalize callchain_store()
>       perf: Generalize some arch callchain code
>       perf: Factorize callchain context handling
>       perf: Fix race in callchains
>       perf: Humanize the number of contexts
> 
> Namhyung Kim (1):
>       perf, tracing: add missing __percpu markups
> 
> 
>  arch/arm/kernel/perf_event.c         |   62 +--------
>  arch/powerpc/kernel/perf_callchain.c |   86 ++++--------
>  arch/sh/kernel/perf_callchain.c      |   50 +------
>  arch/sparc/kernel/perf_event.c       |   69 +++------
>  arch/x86/kernel/cpu/perf_event.c     |   82 +++--------
>  include/linux/ftrace_event.h         |    4 +-
>  include/linux/perf_event.h           |   30 +++-
>  kernel/perf_event.c                  |  259 ++++++++++++++++++++++++++++++----
>  kernel/trace/trace_event_perf.c      |   21 ++--
>  kernel/trace/trace_functions_graph.c |    2 +-
>  10 files changed, 342 insertions(+), 323 deletions(-)

/usr/src/linux-2.6/arch/x86/kernel/cpu/perf_event.c: In function ‘perf_callchain_kernel’:
/usr/src/linux-2.6/arch/x86/kernel/cpu/perf_event.c:1645: warning: ‘return’ with a value, in function returning void
/usr/src/linux-2.6/arch/x86/kernel/cpu/perf_event.c: In function ‘perf_callchain_user’:
/usr/src/linux-2.6/arch/x86/kernel/cpu/perf_event.c:1698: warning: ‘return’ with a value, in function returning void


---
Index: linux-2.6/arch/x86/kernel/cpu/perf_event.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/cpu/perf_event.c
+++ linux-2.6/arch/x86/kernel/cpu/perf_event.c
@@ -1642,7 +1642,7 @@ perf_callchain_kernel(struct perf_callch
 {
 	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
 		/* TODO: We don't support guest os callchain now */
-		return NULL;
+		return;
 	}
 
 	perf_callchain_store(entry, regs->ip);
@@ -1695,7 +1695,7 @@ perf_callchain_user(struct perf_callchai
 
 	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
 		/* TODO: We don't support guest os callchain now */
-		return NULL;
+		return;
 	}
 
 	fp = (void __user *)regs->bp;

Re: [GIT PULL] perf callchains updates

[Frederic Weisbecker]

On Thu, Aug 19, 2010 at 02:09:38PM +0200, Peter Zijlstra wrote:
> On Thu, 2010-08-19 at 01:46 +0200, Frederic Weisbecker wrote:
> > Ingo,
> > 
> > Please pull the perf/core branch that can be found at:
> > 
> > git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing.git
> > 	perf/core
> > 
> > Thanks,
> > 	Frederic
> > ---
> > 
> > Frederic Weisbecker (6):
> >       perf: Drop unappropriate tests on arch callchains
> >       perf: Generalize callchain_store()
> >       perf: Generalize some arch callchain code
> >       perf: Factorize callchain context handling
> >       perf: Fix race in callchains
> >       perf: Humanize the number of contexts
> > 
> > Namhyung Kim (1):
> >       perf, tracing: add missing __percpu markups
> > 
> > 
> >  arch/arm/kernel/perf_event.c         |   62 +--------
> >  arch/powerpc/kernel/perf_callchain.c |   86 ++++--------
> >  arch/sh/kernel/perf_callchain.c      |   50 +------
> >  arch/sparc/kernel/perf_event.c       |   69 +++------
> >  arch/x86/kernel/cpu/perf_event.c     |   82 +++--------
> >  include/linux/ftrace_event.h         |    4 +-
> >  include/linux/perf_event.h           |   30 +++-
> >  kernel/perf_event.c                  |  259 ++++++++++++++++++++++++++++++----
> >  kernel/trace/trace_event_perf.c      |   21 ++--
> >  kernel/trace/trace_functions_graph.c |    2 +-
> >  10 files changed, 342 insertions(+), 323 deletions(-)
> 
> /usr/src/linux-2.6/arch/x86/kernel/cpu/perf_event.c: In function ‘perf_callchain_kernel’:
> /usr/src/linux-2.6/arch/x86/kernel/cpu/perf_event.c:1645: warning: ‘return’ with a value, in function returning void
> /usr/src/linux-2.6/arch/x86/kernel/cpu/perf_event.c: In function ‘perf_callchain_user’:
> /usr/src/linux-2.6/arch/x86/kernel/cpu/perf_event.c:1698: warning: ‘return’ with a value, in function returning void
> 



Ah sorry. Should I carry this patch (I'd need your Sob) or will you?

Thanks.


 
> ---
> Index: linux-2.6/arch/x86/kernel/cpu/perf_event.c
> ===================================================================
> --- linux-2.6.orig/arch/x86/kernel/cpu/perf_event.c
> +++ linux-2.6/arch/x86/kernel/cpu/perf_event.c
> @@ -1642,7 +1642,7 @@ perf_callchain_kernel(struct perf_callch
>  {
>  	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
>  		/* TODO: We don't support guest os callchain now */
> -		return NULL;
> +		return;
>  	}
>  
>  	perf_callchain_store(entry, regs->ip);
> @@ -1695,7 +1695,7 @@ perf_callchain_user(struct perf_callchai
>  
>  	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
>  		/* TODO: We don't support guest os callchain now */
> -		return NULL;
> +		return;
>  	}
>  
>  	fp = (void __user *)regs->bp;
>