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, 93 insertions, 136 deletions

diff --git a/arch/x86/include/asm/atomic_32.h b/arch/x86/include/asm/atomic_32.h
index 2503d4e64c2a..dc5a667ff791 100644
--- a/arch/x86/include/asm/atomic_32.h
+++ b/arch/x86/include/asm/atomic_32.h
@@ -19,7 +19,10 @@
  *
  * Atomically reads the value of @v.
  */
-#define atomic_read(v)		((v)->counter)
+static inline int atomic_read(const atomic_t *v)
+{
+	return v->counter;
+}
 
 /**
  * atomic_set - set atomic variable
@@ -28,7 +31,10 @@
  *
  * Atomically sets the value of @v to @i.
  */
-#define atomic_set(v, i)	(((v)->counter) = (i))
+static inline void atomic_set(atomic_t *v, int i)
+{
+	v->counter = i;
+}
 
 /**
  * atomic_add - add integer to atomic variable
@@ -200,8 +206,15 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 	return atomic_add_return(-i, v);
 }
 
-#define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new)))
-#define atomic_xchg(v, new) (xchg(&((v)->counter), (new)))
+static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+{
+	return cmpxchg(&v->counter, old, new);
+}
+
+static inline int atomic_xchg(atomic_t *v, int new)
+{
+	return xchg(&v->counter, new);
+}
 
 /**
  * atomic_add_unless - add unless the number is already a given value
@@ -250,45 +263,12 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
 /* An 64bit atomic type */
 
 typedef struct {
-	unsigned long long counter;
+	u64 __aligned(8) counter;
 } atomic64_t;
 
 #define ATOMIC64_INIT(val)	{ (val) }
 
-/**
- * atomic64_read - read atomic64 variable
- * @ptr: pointer of type atomic64_t
- *
- * Atomically reads the value of @v.
- * Doesn't imply a read memory barrier.
- */
-#define __atomic64_read(ptr)		((ptr)->counter)
-
-static inline unsigned long long
-cmpxchg8b(unsigned long long *ptr, unsigned long long old, unsigned long long new)
-{
-	asm volatile(
-
-		LOCK_PREFIX "cmpxchg8b (%[ptr])\n"
-
-		     :		"=A" (old)
-
-		     : [ptr]	"D" (ptr),
-				"A" (old),
-				"b" (ll_low(new)),
-				"c" (ll_high(new))
-
-		     : "memory");
-
-	return old;
-}
-
-static inline unsigned long long
-atomic64_cmpxchg(atomic64_t *ptr, unsigned long long old_val,
-		 unsigned long long new_val)
-{
-	return cmpxchg8b(&ptr->counter, old_val, new_val);
-}
+extern u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old_val, u64 new_val);
 
 /**
  * atomic64_xchg - xchg atomic64 variable
@@ -298,18 +278,7 @@ atomic64_cmpxchg(atomic64_t *ptr, unsigned long long old_val,
  * Atomically xchgs the value of @ptr to @new_val and returns
  * the old value.
  */
-
-static inline unsigned long long
-atomic64_xchg(atomic64_t *ptr, unsigned long long new_val)
-{
-	unsigned long long old_val;
-
-	do {
-		old_val = atomic_read(ptr);
-	} while (atomic64_cmpxchg(ptr, old_val, new_val) != old_val);
-
-	return old_val;
-}
+extern u64 atomic64_xchg(atomic64_t *ptr, u64 new_val);
 
 /**
  * atomic64_set - set atomic64 variable
@@ -318,10 +287,7 @@ atomic64_xchg(atomic64_t *ptr, unsigned long long new_val)
  *
  * Atomically sets the value of @ptr to @new_val.
  */
-static inline void atomic64_set(atomic64_t *ptr, unsigned long long new_val)
-{
-	atomic64_xchg(ptr, new_val);
-}
+extern void atomic64_set(atomic64_t *ptr, u64 new_val);
 
 /**
  * atomic64_read - read atomic64 variable
@@ -329,17 +295,30 @@ static inline void atomic64_set(atomic64_t *ptr, unsigned long long new_val)
  *
  * Atomically reads the value of @ptr and returns it.
  */
-static inline unsigned long long atomic64_read(atomic64_t *ptr)
+static inline u64 atomic64_read(atomic64_t *ptr)
 {
-	unsigned long long curr_val;
-
-	do {
-		curr_val = __atomic64_read(ptr);
-	} while (atomic64_cmpxchg(ptr, curr_val, curr_val) != curr_val);
-
-	return curr_val;
+	u64 res;
+
+	/*
+	 * Note, we inline this atomic64_t primitive because
+	 * it only clobbers EAX/EDX and leaves the others
+	 * untouched. We also (somewhat subtly) rely on the
+	 * fact that cmpxchg8b returns the current 64-bit value
+	 * of the memory location we are touching:
+	 */
+	asm volatile(
+		"mov %%ebx, %%eax\n\t"
+		"mov %%ecx, %%edx\n\t"
+		LOCK_PREFIX "cmpxchg8b %1\n"
+			: "=&A" (res)
+			: "m" (*ptr)
+		);
+
+	return res;
 }
 
+extern u64 atomic64_read(atomic64_t *ptr);
+
 /**
  * atomic64_add_return - add and return
  * @delta: integer value to add
@@ -347,34 +326,14 @@ static inline unsigned long long atomic64_read(atomic64_t *ptr)
  *
  * Atomically adds @delta to @ptr and returns @delta + *@ptr
  */
-static inline unsigned long long
-atomic64_add_return(unsigned long long delta, atomic64_t *ptr)
-{
-	unsigned long long old_val, new_val;
-
-	do {
-		old_val = atomic_read(ptr);
-		new_val = old_val + delta;
-
-	} while (atomic64_cmpxchg(ptr, old_val, new_val) != old_val);
-
-	return new_val;
-}
-
-static inline long atomic64_sub_return(unsigned long long delta, atomic64_t *ptr)
-{
-	return atomic64_add_return(-delta, ptr);
-}
+extern u64 atomic64_add_return(u64 delta, atomic64_t *ptr);
 
-static inline long atomic64_inc_return(atomic64_t *ptr)
-{
-	return atomic64_add_return(1, ptr);
-}
-
-static inline long atomic64_dec_return(atomic64_t *ptr)
-{
-	return atomic64_sub_return(1, ptr);
-}
+/*
+ * Other variants with different arithmetic operators:
+ */
+extern u64 atomic64_sub_return(u64 delta, atomic64_t *ptr);
+extern u64 atomic64_inc_return(atomic64_t *ptr);
+extern u64 atomic64_dec_return(atomic64_t *ptr);
 
 /**
  * atomic64_add - add integer to atomic64 variable
@@ -383,10 +342,7 @@ static inline long atomic64_dec_return(atomic64_t *ptr)
  *
  * Atomically adds @delta to @ptr.
  */
-static inline void atomic64_add(unsigned long long delta, atomic64_t *ptr)
-{
-	atomic64_add_return(delta, ptr);
-}
+extern void atomic64_add(u64 delta, atomic64_t *ptr);
 
 /**
  * atomic64_sub - subtract the atomic64 variable
@@ -395,10 +351,7 @@ static inline void atomic64_add(unsigned long long delta, atomic64_t *ptr)
  *
  * Atomically subtracts @delta from @ptr.
  */
-static inline void atomic64_sub(unsigned long long delta, atomic64_t *ptr)
-{
-	atomic64_add(-delta, ptr);
-}
+extern void atomic64_sub(u64 delta, atomic64_t *ptr);
 
 /**
  * atomic64_sub_and_test - subtract value from variable and test result
@@ -409,13 +362,7 @@ static inline void atomic64_sub(unsigned long long delta, atomic64_t *ptr)
  * true if the result is zero, or false for all
  * other cases.
  */
-static inline int
-atomic64_sub_and_test(unsigned long long delta, atomic64_t *ptr)
-{
-	unsigned long long old_val = atomic64_sub_return(delta, ptr);
-
-	return old_val == 0;
-}
+extern int atomic64_sub_and_test(u64 delta, atomic64_t *ptr);
 
 /**
  * atomic64_inc - increment atomic64 variable
@@ -423,10 +370,7 @@ atomic64_sub_and_test(unsigned long long delta, atomic64_t *ptr)
  *
  * Atomically increments @ptr by 1.
  */
-static inline void atomic64_inc(atomic64_t *ptr)
-{
-	atomic64_add(1, ptr);
-}
+extern void atomic64_inc(atomic64_t *ptr);
 
 /**
  * atomic64_dec - decrement atomic64 variable
@@ -434,10 +378,7 @@ static inline void atomic64_inc(atomic64_t *ptr)
  *
  * Atomically decrements @ptr by 1.
  */
-static inline void atomic64_dec(atomic64_t *ptr)
-{
-	atomic64_sub(1, ptr);
-}
+extern void atomic64_dec(atomic64_t *ptr);
 
 /**
  * atomic64_dec_and_test - decrement and test
@@ -447,10 +388,7 @@ static inline void atomic64_dec(atomic64_t *ptr)
  * returns true if the result is 0, or false for all other
  * cases.
  */
-static inline int atomic64_dec_and_test(atomic64_t *ptr)
-{
-	return atomic64_sub_and_test(1, ptr);
-}
+extern int atomic64_dec_and_test(atomic64_t *ptr);
 
 /**
  * atomic64_inc_and_test - increment and test
@@ -460,10 +398,7 @@ static inline int atomic64_dec_and_test(atomic64_t *ptr)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
-static inline int atomic64_inc_and_test(atomic64_t *ptr)
-{
-	return atomic64_sub_and_test(-1, ptr);
-}
+extern int atomic64_inc_and_test(atomic64_t *ptr);
 
 /**
  * atomic64_add_negative - add and test if negative
@@ -474,13 +409,7 @@ static inline int atomic64_inc_and_test(atomic64_t *ptr)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-static inline int
-atomic64_add_negative(unsigned long long delta, atomic64_t *ptr)
-{
-	long long old_val = atomic64_add_return(delta, ptr);
-
-	return old_val < 0;
-}
+extern int atomic64_add_negative(u64 delta, atomic64_t *ptr);
 
 #include <asm-generic/atomic-long.h>
 #endif /* _ASM_X86_ATOMIC_32_H */
diff --git a/arch/x86/include/asm/atomic_64.h b/arch/x86/include/asm/atomic_64.h
index 0d6360220007..d605dc268e79 100644
--- a/arch/x86/include/asm/atomic_64.h
+++ b/arch/x86/include/asm/atomic_64.h
@@ -18,7 +18,10 @@
  *
  * Atomically reads the value of @v.
  */
-#define atomic_read(v)		((v)->counter)
+static inline int atomic_read(const atomic_t *v)
+{
+	return v->counter;
+}
 
 /**
  * atomic_set - set atomic variable
@@ -27,7 +30,10 @@
  *
  * Atomically sets the value of @v to @i.
  */
-#define atomic_set(v, i)		(((v)->counter) = (i))
+static inline void atomic_set(atomic_t *v, int i)
+{
+	v->counter = i;
+}
 
 /**
  * atomic_add - add integer to atomic variable
@@ -192,7 +198,10 @@ static inline int atomic_sub_return(int i, atomic_t *v)
  * Atomically reads the value of @v.
  * Doesn't imply a read memory barrier.
  */
-#define atomic64_read(v)		((v)->counter)
+static inline long atomic64_read(const atomic64_t *v)
+{
+	return v->counter;
+}
 
 /**
  * atomic64_set - set atomic64 variable
@@ -201,7 +210,10 @@ static inline int atomic_sub_return(int i, atomic_t *v)
  *
  * Atomically sets the value of @v to @i.
  */
-#define atomic64_set(v, i)		(((v)->counter) = (i))
+static inline void atomic64_set(atomic64_t *v, long i)
+{
+	v->counter = i;
+}
 
 /**
  * atomic64_add - add integer to atomic64 variable
@@ -355,11 +367,25 @@ static inline long atomic64_sub_return(long i, atomic64_t *v)
 #define atomic64_inc_return(v)  (atomic64_add_return(1, (v)))
 #define atomic64_dec_return(v)  (atomic64_sub_return(1, (v)))
 
-#define atomic64_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new)))
-#define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
+static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new)
+{
+	return cmpxchg(&v->counter, old, new);
+}
+
+static inline long atomic64_xchg(atomic64_t *v, long new)
+{
+	return xchg(&v->counter, new);
+}
 
-#define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new)))
-#define atomic_xchg(v, new) (xchg(&((v)->counter), (new)))
+static inline long atomic_cmpxchg(atomic_t *v, int old, int new)
+{
+	return cmpxchg(&v->counter, old, new);
+}
+
+static inline long atomic_xchg(atomic_t *v, int new)
+{
+	return xchg(&v->counter, new);
+}
 
 /**
  * atomic_add_unless - add unless the number is a given value
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index f517944b2b17..cf86a5e73815 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -3,6 +3,8 @@
 
 extern int kstack_depth_to_print;
 
+int x86_is_stack_id(int id, char *name);
+
 /* Generic stack tracer with callbacks */
 
 struct stacktrace_ops {