Merge branch 'perfcounters-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perfcounters-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (50 commits)
  perf report: Add "Fractal" mode output - support callchains with relative overhead rate
  perf_counter tools: callchains: Manage the cumul hits on the fly
  perf report: Change default callchain parameters
  perf report: Use a modifiable string for default callchain options
  perf report: Warn on callchain output request from non-callchain file
  x86: atomic64: Inline atomic64_read() again
  x86: atomic64: Clean up atomic64_sub_and_test() and atomic64_add_negative()
  x86: atomic64: Improve atomic64_xchg()
  x86: atomic64: Export APIs to modules
  x86: atomic64: Improve atomic64_read()
  x86: atomic64: Code atomic(64)_read and atomic(64)_set in C not CPP
  x86: atomic64: Fix unclean type use in atomic64_xchg()
  x86: atomic64: Make atomic_read() type-safe
  x86: atomic64: Reduce size of functions
  x86: atomic64: Improve atomic64_add_return()
  x86: atomic64: Improve cmpxchg8b()
  x86: atomic64: Improve atomic64_read()
  x86: atomic64: Move the 32-bit atomic64_t implementation to a .c file
  x86: atomic64: The atomic64_t data type should be 8 bytes aligned on 32-bit too
  perf report: Annotate variable initialization
  ...

3 files changed, 28 insertions, 8 deletions

diff --git a/arch/x86/kernel/cpu/perf_counter.c b/arch/x86/kernel/cpu/perf_counter.c
index d4cf4ce..36c3dc7 100644
--- a/arch/x86/kernel/cpu/perf_counter.c
+++ b/arch/x86/kernel/cpu/perf_counter.c
@@ -1561,6 +1561,7 @@ void callchain_store(struct perf_callchain_entry *entry, u64 ip)
 
 static DEFINE_PER_CPU(struct perf_callchain_entry, irq_entry);
 static DEFINE_PER_CPU(struct perf_callchain_entry, nmi_entry);
+static DEFINE_PER_CPU(int, in_nmi_frame);
 
 
 static void
@@ -1576,7 +1577,9 @@ static void backtrace_warning(void *data, char *msg)
 
 static int backtrace_stack(void *data, char *name)
 {
-	/* Process all stacks: */
+	per_cpu(in_nmi_frame, smp_processor_id()) =
+			x86_is_stack_id(NMI_STACK, name);
+
 	return 0;
 }
 
@@ -1584,6 +1587,9 @@ static void backtrace_address(void *data, unsigned long addr, int reliable)
 {
 	struct perf_callchain_entry *entry = data;
 
+	if (per_cpu(in_nmi_frame, smp_processor_id()))
+		return;
+
 	if (reliable)
 		callchain_store(entry, addr);
 }
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index d593cd1..bca5fba 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -19,6 +19,12 @@
 
 #include "dumpstack.h"
 
+/* Just a stub for now */
+int x86_is_stack_id(int id, char *name)
+{
+	return 0;
+}
+
 void dump_trace(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *stack, unsigned long bp,
 		const struct stacktrace_ops *ops, void *data)
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index d35db59..54b0a32 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -19,10 +19,8 @@
 
 #include "dumpstack.h"
 
-static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
-					unsigned *usedp, char **idp)
-{
-	static char ids[][8] = {
+
+static char x86_stack_ids[][8] = {
 		[DEBUG_STACK - 1] = "#DB",
 		[NMI_STACK - 1] = "NMI",
 		[DOUBLEFAULT_STACK - 1] = "#DF",
@@ -33,6 +31,15 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
 			N_EXCEPTION_STACKS + DEBUG_STKSZ / EXCEPTION_STKSZ - 2] = "#DB[?]"
 #endif
 	};
+
+int x86_is_stack_id(int id, char *name)
+{
+	return x86_stack_ids[id - 1] == name;
+}
+
+static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
+					unsigned *usedp, char **idp)
+{
 	unsigned k;
 
 	/*
@@ -61,7 +68,7 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
 			if (*usedp & (1U << k))
 				break;
 			*usedp |= 1U << k;
-			*idp = ids[k];
+			*idp = x86_stack_ids[k];
 			return (unsigned long *)end;
 		}
 		/*
@@ -81,12 +88,13 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
 			do {
 				++j;
 				end -= EXCEPTION_STKSZ;
-				ids[j][4] = '1' + (j - N_EXCEPTION_STACKS);
+				x86_stack_ids[j][4] = '1' +
+						(j - N_EXCEPTION_STACKS);
 			} while (stack < end - EXCEPTION_STKSZ);
 			if (*usedp & (1U << j))
 				break;
 			*usedp |= 1U << j;
-			*idp = ids[j];
+			*idp = x86_stack_ids[j];
 			return (unsigned long *)end;
 		}
 #endif