x86: use s64* for old arg of atomic64_try_cmpxchg()

index 8db8879a6d8c..5d9de36a2f04 100644
@@ -177,7 +177,7 @@ static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new)
 }
 
 #define atomic64_try_cmpxchg atomic64_try_cmpxchg
-static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, long *old, long new)
+static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, long new)
 {
 	return try_cmpxchg(&v->counter, old, new);
 }

@@ -198,7 +198,7 @@ static inline long atomic64_xchg(atomic64_t *v, long new)
  */
 static inline bool atomic64_add_unless(atomic64_t *v, long a, long u)
 {
-	long c = atomic64_read(v);
+	s64 c = atomic64_read(v);
 	do {
 		if (unlikely(c == u))
 			return false;

@@ -217,7 +217,7 @@ static inline bool atomic64_add_unless(atomic64_t *v, long a, long u)
  */
 static inline long atomic64_dec_if_positive(atomic64_t *v)
 {
-	long dec, c = atomic64_read(v);
+	s64 dec, c = atomic64_read(v);
 	do {
 		dec = c - 1;
 		if (unlikely(dec < 0))

@@ -236,7 +236,7 @@ static inline void atomic64_and(long i, atomic64_t *v)
 
 static inline long atomic64_fetch_and(long i, atomic64_t *v)
 {
-	long val = atomic64_read(v);
+	s64 val = atomic64_read(v);
 
 	do {
 	} while (!atomic64_try_cmpxchg(v, &val, val & i));

@@ -253,7 +253,7 @@ static inline void atomic64_or(long i, atomic64_t *v)
 
 static inline long atomic64_fetch_or(long i, atomic64_t *v)
 {
-	long val = atomic64_read(v);
+	s64 val = atomic64_read(v);
 
 	do {
 	} while (!atomic64_try_cmpxchg(v, &val, val | i));

@@ -270,7 +270,7 @@ static inline void atomic64_xor(long i, atomic64_t *v)
 
 static inline long atomic64_fetch_xor(long i, atomic64_t *v)
 {
-	long val = atomic64_read(v);
+	s64 val = atomic64_read(v);
 
 	do {
 	} while (!atomic64_try_cmpxchg(v, &val, val ^ i));

index d90296d061e8..b5069e802d5c 100644
@@ -157,7 +157,7 @@ extern void __add_wrong_size(void)
 #define __raw_try_cmpxchg(_ptr, _pold, _new, size, lock)		\
 ({									\
 	bool success;							\
-	__typeof__(_ptr) _old = (_pold);				\
+	__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold);		\
 	__typeof__(*(_ptr)) __old = *_old;				\
 	__typeof__(*(_ptr)) __new = (_new);				\
 	switch (size) {							\

new file mode 100644
index 000000000000..50401d925290
@@ -0,0 +1,316 @@
+#ifndef _LINUX_ATOMIC_INSTRUMENTED_H
+#define _LINUX_ATOMIC_INSTRUMENTED_H
+
+static __always_inline int atomic_read(const atomic_t *v)
+{
+	return arch_atomic_read(v);
+}
+
+static __always_inline s64 atomic64_read(const atomic64_t *v)
+{
+	return arch_atomic64_read(v);
+}
+
+static __always_inline void atomic_set(atomic_t *v, int i)
+{
+	arch_atomic_set(v, i);
+}
+
+static __always_inline void atomic64_set(atomic64_t *v, s64 i)
+{
+	arch_atomic64_set(v, i);
+}
+
+static __always_inline int atomic_xchg(atomic_t *v, int i)
+{
+	return arch_atomic_xchg(v, i);
+}
+
+static __always_inline s64 atomic64_xchg(atomic64_t *v, s64 i)
+{
+	return arch_atomic64_xchg(v, i);
+}
+
+static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+{
+	return arch_atomic_cmpxchg(v, old, new);
+}
+
+static __always_inline s64 atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
+{
+	return arch_atomic64_cmpxchg(v, old, new);
+}
+
+#ifdef arch_atomic_try_cmpxchg
+#define atomic_try_cmpxchg atomic_try_cmpxchg
+static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new)
+{
+	return arch_atomic_try_cmpxchg(v, old, new);
+}
+#endif
+
+#ifdef arch_atomic64_try_cmpxchg
+#define atomic64_try_cmpxchg atomic64_try_cmpxchg
+static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
+{
+	return arch_atomic64_try_cmpxchg(v, old, new);
+}
+#endif
+
+static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
+{
+	return __arch_atomic_add_unless(v, a, u);
+}
+
+
+static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
+{
+	return arch_atomic64_add_unless(v, a, u);
+}
+
+static __always_inline void atomic_inc(atomic_t *v)
+{
+	arch_atomic_inc(v);
+}
+
+static __always_inline void atomic64_inc(atomic64_t *v)
+{
+	arch_atomic64_inc(v);
+}
+
+static __always_inline void atomic_dec(atomic_t *v)
+{
+	arch_atomic_dec(v);
+}
+
+static __always_inline void atomic64_dec(atomic64_t *v)
+{
+	arch_atomic64_dec(v);
+}
+
+static __always_inline void atomic_add(int i, atomic_t *v)
+{
+	arch_atomic_add(i, v);
+}
+
+static __always_inline void atomic64_add(s64 i, atomic64_t *v)
+{
+	arch_atomic64_add(i, v);
+}
+
+static __always_inline void atomic_sub(int i, atomic_t *v)
+{
+	arch_atomic_sub(i, v);
+}
+
+static __always_inline void atomic64_sub(s64 i, atomic64_t *v)
+{
+	arch_atomic64_sub(i, v);
+}
+
+static __always_inline void atomic_and(int i, atomic_t *v)
+{
+	arch_atomic_and(i, v);
+}
+
+static __always_inline void atomic64_and(s64 i, atomic64_t *v)
+{
+	arch_atomic64_and(i, v);
+}
+
+static __always_inline void atomic_or(int i, atomic_t *v)
+{
+	arch_atomic_or(i, v);
+}
+
+static __always_inline void atomic64_or(s64 i, atomic64_t *v)
+{
+	arch_atomic64_or(i, v);
+}
+
+static __always_inline void atomic_xor(int i, atomic_t *v)
+{
+	arch_atomic_xor(i, v);
+}
+
+static __always_inline void atomic64_xor(s64 i, atomic64_t *v)
+{
+	arch_atomic64_xor(i, v);
+}
+
+static __always_inline int atomic_inc_return(atomic_t *v)
+{
+	return arch_atomic_inc_return(v);
+}
+
+static __always_inline s64 atomic64_inc_return(atomic64_t *v)
+{
+	return arch_atomic64_inc_return(v);
+}
+
+static __always_inline int atomic_dec_return(atomic_t *v)
+{
+	return arch_atomic_dec_return(v);
+}
+
+static __always_inline s64 atomic64_dec_return(atomic64_t *v)
+{
+	return arch_atomic64_dec_return(v);
+}
+
+static __always_inline s64 atomic64_inc_not_zero(atomic64_t *v)
+{
+	return arch_atomic64_inc_not_zero(v);
+}
+
+static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v)
+{
+	return arch_atomic64_dec_if_positive(v);
+}
+
+static __always_inline bool atomic_dec_and_test(atomic_t *v)
+{
+	return arch_atomic_dec_and_test(v);
+}
+
+static __always_inline bool atomic64_dec_and_test(atomic64_t *v)
+{
+	return arch_atomic64_dec_and_test(v);
+}
+
+static __always_inline bool atomic_inc_and_test(atomic_t *v)
+{
+	return arch_atomic_inc_and_test(v);
+}
+
+static __always_inline bool atomic64_inc_and_test(atomic64_t *v)
+{
+	return arch_atomic64_inc_and_test(v);
+}
+
+static __always_inline int atomic_add_return(int i, atomic_t *v)
+{
+	return arch_atomic_add_return(i, v);
+}
+
+static __always_inline s64 atomic64_add_return(s64 i, atomic64_t *v)
+{
+	return arch_atomic64_add_return(i, v);
+}
+
+static __always_inline int atomic_sub_return(int i, atomic_t *v)
+{
+	return arch_atomic_sub_return(i, v);
+}
+
+static __always_inline s64 atomic64_sub_return(s64 i, atomic64_t *v)
+{
+	return arch_atomic64_sub_return(i, v);
+}
+
+static __always_inline int atomic_fetch_add(int i, atomic_t *v)
+{
+	return arch_atomic_fetch_add(i, v);
+}
+
+static __always_inline s64 atomic64_fetch_add(s64 i, atomic64_t *v)
+{
+	return arch_atomic64_fetch_add(i, v);
+}
+
+static __always_inline int atomic_fetch_sub(int i, atomic_t *v)
+{
+	return arch_atomic_fetch_sub(i, v);
+}
+
+static __always_inline s64 atomic64_fetch_sub(s64 i, atomic64_t *v)
+{
+	return arch_atomic64_fetch_sub(i, v);
+}
+
+static __always_inline int atomic_fetch_and(int i, atomic_t *v)
+{
+	return arch_atomic_fetch_and(i, v);
+}
+
+static __always_inline s64 atomic64_fetch_and(s64 i, atomic64_t *v)
+{
+	return arch_atomic64_fetch_and(i, v);
+}
+
+static __always_inline int atomic_fetch_or(int i, atomic_t *v)
+{
+	return arch_atomic_fetch_or(i, v);
+}
+
+static __always_inline s64 atomic64_fetch_or(s64 i, atomic64_t *v)
+{
+	return arch_atomic64_fetch_or(i, v);
+}
+
+static __always_inline int atomic_fetch_xor(int i, atomic_t *v)
+{
+	return arch_atomic_fetch_xor(i, v);
+}
+
+static __always_inline s64 atomic64_fetch_xor(s64 i, atomic64_t *v)
+{
+	return arch_atomic64_fetch_xor(i, v);
+}
+
+static __always_inline bool atomic_sub_and_test(int i, atomic_t *v)
+{
+	return arch_atomic_sub_and_test(i, v);
+}
+
+static __always_inline bool atomic64_sub_and_test(s64 i, atomic64_t *v)
+{
+	return arch_atomic64_sub_and_test(i, v);
+}
+
+static __always_inline bool atomic_add_negative(int i, atomic_t *v)
+{
+	return arch_atomic_add_negative(i, v);
+}
+
+static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v)
+{
+	return arch_atomic64_add_negative(i, v);
+}
+
+#define cmpxchg(ptr, old, new)				\
+({							\
+	arch_cmpxchg((ptr), (old), (new));		\
+})
+
+#define sync_cmpxchg(ptr, old, new)			\
+({							\
+	arch_sync_cmpxchg((ptr), (old), (new));		\
+})
+
+#define cmpxchg_local(ptr, old, new)			\
+({							\
+	arch_cmpxchg_local((ptr), (old), (new));	\
+})
+
+#define cmpxchg64(ptr, old, new)			\
+({							\
+	arch_cmpxchg64((ptr), (old), (new));		\
+})
+
+#define cmpxchg64_local(ptr, old, new)			\
+({							\
+	arch_cmpxchg64_local((ptr), (old), (new));	\
+})
+
+#define cmpxchg_double(p1, p2, o1, o2, n1, n2)				\
+({									\
+	arch_cmpxchg_double((p1), (p2), (o1), (o2), (n1), (n2));	\
+})
+
+#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2)			\
+({									\
+	arch_cmpxchg_double_local((p1), (p2), (o1), (o2), (n1), (n2));	\
+})
+
+#endif /* _LINUX_ATOMIC_INSTRUMENTED_H */

index 50401d925290..a0f5b7525bb2 100644
@@ -1,43 +1,53 @@
 #ifndef _LINUX_ATOMIC_INSTRUMENTED_H
 #define _LINUX_ATOMIC_INSTRUMENTED_H
 
+#include <linux/kasan-checks.h>
+
 static __always_inline int atomic_read(const atomic_t *v)
 {
+	kasan_check_read(v, sizeof(*v));
 	return arch_atomic_read(v);
 }
 
 static __always_inline s64 atomic64_read(const atomic64_t *v)
 {
+	kasan_check_read(v, sizeof(*v));
 	return arch_atomic64_read(v);
 }
 
 static __always_inline void atomic_set(atomic_t *v, int i)
 {
+	kasan_check_write(v, sizeof(*v));
 	arch_atomic_set(v, i);
 }
 
 static __always_inline void atomic64_set(atomic64_t *v, s64 i)
 {
+	kasan_check_write(v, sizeof(*v));
 	arch_atomic64_set(v, i);
 }
 
 static __always_inline int atomic_xchg(atomic_t *v, int i)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_xchg(v, i);
 }
 
 static __always_inline s64 atomic64_xchg(atomic64_t *v, s64 i)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_xchg(v, i);
 }
 
 static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_cmpxchg(v, old, new);
 }
 
 static __always_inline s64 atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_cmpxchg(v, old, new);
 }
 

@@ -45,6 +55,8 @@ static __always_inline s64 atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
 #define atomic_try_cmpxchg atomic_try_cmpxchg
 static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new)
 {
+	kasan_check_write(v, sizeof(*v));
+	kasan_check_read(old, sizeof(*old));
 	return arch_atomic_try_cmpxchg(v, old, new);
 }
 #endif

@@ -53,254 +65,310 @@ static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new)
 #define atomic64_try_cmpxchg atomic64_try_cmpxchg
 static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
 {
+	kasan_check_write(v, sizeof(*v));
+	kasan_check_read(old, sizeof(*old));
 	return arch_atomic64_try_cmpxchg(v, old, new);
 }
 #endif
 
 static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
 {
+	kasan_check_write(v, sizeof(*v));
 	return __arch_atomic_add_unless(v, a, u);
 }
 
 
 static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_add_unless(v, a, u);
 }
 
 static __always_inline void atomic_inc(atomic_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	arch_atomic_inc(v);
 }
 
 static __always_inline void atomic64_inc(atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	arch_atomic64_inc(v);
 }
 
 static __always_inline void atomic_dec(atomic_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	arch_atomic_dec(v);
 }
 
 static __always_inline void atomic64_dec(atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	arch_atomic64_dec(v);
 }
 
 static __always_inline void atomic_add(int i, atomic_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	arch_atomic_add(i, v);
 }
 
 static __always_inline void atomic64_add(s64 i, atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	arch_atomic64_add(i, v);
 }
 
 static __always_inline void atomic_sub(int i, atomic_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	arch_atomic_sub(i, v);
 }
 
 static __always_inline void atomic64_sub(s64 i, atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	arch_atomic64_sub(i, v);
 }
 
 static __always_inline void atomic_and(int i, atomic_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	arch_atomic_and(i, v);
 }
 
 static __always_inline void atomic64_and(s64 i, atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	arch_atomic64_and(i, v);
 }
 
 static __always_inline void atomic_or(int i, atomic_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	arch_atomic_or(i, v);
 }
 
 static __always_inline void atomic64_or(s64 i, atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	arch_atomic64_or(i, v);
 }
 
 static __always_inline void atomic_xor(int i, atomic_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	arch_atomic_xor(i, v);
 }
 
 static __always_inline void atomic64_xor(s64 i, atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	arch_atomic64_xor(i, v);
 }
 
 static __always_inline int atomic_inc_return(atomic_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_inc_return(v);
 }
 
 static __always_inline s64 atomic64_inc_return(atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_inc_return(v);
 }
 
 static __always_inline int atomic_dec_return(atomic_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_dec_return(v);
 }
 
 static __always_inline s64 atomic64_dec_return(atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_dec_return(v);
 }
 
 static __always_inline s64 atomic64_inc_not_zero(atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_inc_not_zero(v);
 }
 
 static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_dec_if_positive(v);
 }
 
 static __always_inline bool atomic_dec_and_test(atomic_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_dec_and_test(v);
 }
 
 static __always_inline bool atomic64_dec_and_test(atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_dec_and_test(v);
 }
 
 static __always_inline bool atomic_inc_and_test(atomic_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_inc_and_test(v);
 }
 
 static __always_inline bool atomic64_inc_and_test(atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_inc_and_test(v);
 }
 
 static __always_inline int atomic_add_return(int i, atomic_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_add_return(i, v);
 }
 
 static __always_inline s64 atomic64_add_return(s64 i, atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_add_return(i, v);
 }
 
 static __always_inline int atomic_sub_return(int i, atomic_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_sub_return(i, v);
 }
 
 static __always_inline s64 atomic64_sub_return(s64 i, atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_sub_return(i, v);
 }
 
 static __always_inline int atomic_fetch_add(int i, atomic_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_fetch_add(i, v);
 }
 
 static __always_inline s64 atomic64_fetch_add(s64 i, atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_fetch_add(i, v);
 }
 
 static __always_inline int atomic_fetch_sub(int i, atomic_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_fetch_sub(i, v);
 }
 
 static __always_inline s64 atomic64_fetch_sub(s64 i, atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_fetch_sub(i, v);
 }
 
 static __always_inline int atomic_fetch_and(int i, atomic_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_fetch_and(i, v);
 }
 
 static __always_inline s64 atomic64_fetch_and(s64 i, atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_fetch_and(i, v);
 }
 
 static __always_inline int atomic_fetch_or(int i, atomic_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_fetch_or(i, v);
 }
 
 static __always_inline s64 atomic64_fetch_or(s64 i, atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_fetch_or(i, v);
 }
 
 static __always_inline int atomic_fetch_xor(int i, atomic_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_fetch_xor(i, v);
 }
 
 static __always_inline s64 atomic64_fetch_xor(s64 i, atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_fetch_xor(i, v);
 }
 
 static __always_inline bool atomic_sub_and_test(int i, atomic_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_sub_and_test(i, v);
 }
 
 static __always_inline bool atomic64_sub_and_test(s64 i, atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_sub_and_test(i, v);
 }
 
 static __always_inline bool atomic_add_negative(int i, atomic_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_add_negative(i, v);
 }
 
 static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_add_negative(i, v);
 }
 
 #define cmpxchg(ptr, old, new)				\
 ({							\
+	__typeof__(ptr) ___ptr = (ptr);			\
+	kasan_check_write(___ptr, sizeof(*___ptr));	\
 	arch_cmpxchg((ptr), (old), (new));		\
 })
 
 #define sync_cmpxchg(ptr, old, new)			\
 ({							\
-	arch_sync_cmpxchg((ptr), (old), (new));		\
+	__typeof__(ptr) ___ptr = (ptr);			\
+	kasan_check_write(___ptr, sizeof(*___ptr));	\
+	arch_sync_cmpxchg(___ptr, (old), (new));	\
 })
 
 #define cmpxchg_local(ptr, old, new)			\
 ({							\
-	arch_cmpxchg_local((ptr), (old), (new));	\
+	__typeof__(ptr) ____ptr = (ptr);		\
+	kasan_check_write(____ptr, sizeof(*____ptr));	\
+	arch_cmpxchg_local(____ptr, (old), (new));	\
 })
 
 #define cmpxchg64(ptr, old, new)			\
 ({							\
-	arch_cmpxchg64((ptr), (old), (new));		\
+	__typeof__(ptr) ____ptr = (ptr);		\
+	kasan_check_write(____ptr, sizeof(*____ptr));	\
+	arch_cmpxchg64(____ptr, (old), (new));		\
 })
 
 #define cmpxchg64_local(ptr, old, new)			\
 ({							\
-	arch_cmpxchg64_local((ptr), (old), (new));	\
+	__typeof__(ptr) ____ptr = (ptr);		\
+	kasan_check_write(____ptr, sizeof(*____ptr));	\
+	arch_cmpxchg64_local(____ptr, (old), (new));	\
 })
 
 #define cmpxchg_double(p1, p2, o1, o2, n1, n2)				\

index b7900346c77e..8a9e65e585db 100644
@@ -23,6 +23,13 @@
  */
 static __always_inline int arch_atomic_read(const atomic_t *v)
 {
+	/*
+	 * Note: READ_ONCE() here leads to double instrumentation as
+	 * both READ_ONCE() and atomic_read() contain instrumentation.
+	 * This is a deliberate choice. READ_ONCE_NOCHECK() is compiled to a
+	 * non-inlined function call that considerably increases binary size
+	 * and stack usage under KASAN.
+	 */
 	return READ_ONCE((v)->counter);
 }
 

index a0f5b7525bb2..5771439e7a31 100644
@@ -1,3 +1,15 @@
+/*
+ * This file provides wrappers with KASAN instrumentation for atomic operations.
+ * To use this functionality an arch's atomic.h file needs to define all
+ * atomic operations with arch_ prefix (e.g. arch_atomic_read()) and include
+ * this file at the end. This file provides atomic_read() that forwards to
+ * arch_atomic_read() for actual atomic operation.
+ * Note: if an arch atomic operation is implemented by means of other atomic
+ * operations (e.g. atomic_read()/atomic_cmpxchg() loop), then it needs to use
+ * arch_ variants (i.e. arch_atomic_read()/arch_atomic_cmpxchg()) to avoid
+ * double instrumentation.
+ */
+
 #ifndef _LINUX_ATOMIC_INSTRUMENTED_H
 #define _LINUX_ATOMIC_INSTRUMENTED_H
 

@@ -336,6 +348,15 @@ static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v)
 	return arch_atomic64_add_negative(i, v);
 }
 
+/*
+ * In the following macros we need to be careful to not clash with arch_ macros.
+ * arch_xchg() can be defined as an extended statement expression as well,
+ * if we define a __ptr variable, and arch_xchg() also defines __ptr variable,
+ * and we pass __ptr as an argument to arch_xchg(), it will use own __ptr
+ * instead of ours. This leads to unpleasant crashes. To avoid the problem
+ * the following macros declare variables with lots of underscores.
+ */
+
 #define cmpxchg(ptr, old, new)				\
 ({							\
 	__typeof__(ptr) ___ptr = (ptr);			\

@@ -371,6 +392,15 @@ static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v)
 	arch_cmpxchg64_local(____ptr, (old), (new));	\
 })
 
+/*
+ * Originally we had the following code here:
+ *     __typeof__(p1) ____p1 = (p1);
+ *     kasan_check_write(____p1, 2 * sizeof(*____p1));
+ *     arch_cmpxchg_double(____p1, (p2), (o1), (o2), (n1), (n2));
+ * But it leads to compilation failures (see gcc issue 72873).
+ * So for now it's left non-instrumented.
+ * There are few callers of cmpxchg_double(), so it's not critical.
+ */
 #define cmpxchg_double(p1, p2, o1, o2, n1, n2)				\
 ({									\
 	arch_cmpxchg_double((p1), (p2), (o1), (o2), (n1), (n2));	\

index b7f8aced7870..41960fecf783 100644
@@ -2,11 +2,13 @@
 #define _LINUX_KASAN_CHECKS_H
 
 #ifdef CONFIG_KASAN
-void kasan_check_read(const void *p, unsigned int size);
-void kasan_check_write(const void *p, unsigned int size);
+void kasan_check_read(const volatile void *p, unsigned int size);
+void kasan_check_write(const volatile void *p, unsigned int size);
 #else
-static inline void kasan_check_read(const void *p, unsigned int size) { }
-static inline void kasan_check_write(const void *p, unsigned int size) { }
+static inline void kasan_check_read(const volatile void *p, unsigned int size)
+{ }
+static inline void kasan_check_write(const volatile void *p, unsigned int size)
+{ }
 #endif
 
 #endif

index c81549d5c833..edacd161c0e5 100644
@@ -333,13 +333,13 @@ static void check_memory_region(unsigned long addr,
 	check_memory_region_inline(addr, size, write, ret_ip);
 }
 
-void kasan_check_read(const void *p, unsigned int size)
+void kasan_check_read(const volatile void *p, unsigned int size)
 {
 	check_memory_region((unsigned long)p, size, false, _RET_IP_);
 }
 EXPORT_SYMBOL(kasan_check_read);
 
-void kasan_check_write(const void *p, unsigned int size)
+void kasan_check_write(const volatile void *p, unsigned int size)
 {
 	check_memory_region((unsigned long)p, size, true, _RET_IP_);
 }

index 1a4a6a99dcd8..b7900346c77e 100644
@@ -16,36 +16,42 @@
 #define ATOMIC_INIT(i)	{ (i) }
 
 /**
- * atomic_read - read atomic variable
+ * arch_atomic_read - read atomic variable
  * @v: pointer of type atomic_t
  *
  * Atomically reads the value of @v.
  */
-static __always_inline int atomic_read(const atomic_t *v)
+static __always_inline int arch_atomic_read(const atomic_t *v)
 {
 	return READ_ONCE((v)->counter);
 }
 
 /**
- * atomic_set - set atomic variable
+ * arch_atomic_set - set atomic variable
  * @v: pointer of type atomic_t
  * @i: required value
  *
  * Atomically sets the value of @v to @i.
  */
-static __always_inline void atomic_set(atomic_t *v, int i)
+static __always_inline void arch_atomic_set(atomic_t *v, int i)
 {
+	/*
+	 * We could use WRITE_ONCE_NOCHECK() if it exists, similar to
+	 * READ_ONCE_NOCHECK() in arch_atomic_read(). But there is no such
+	 * thing at the moment, and introducing it for this case does not
+	 * worth it.
+	 */
 	WRITE_ONCE(v->counter, i);
 }
 
 /**
- * atomic_add - add integer to atomic variable
+ * arch_atomic_add - add integer to atomic variable
  * @i: integer value to add
  * @v: pointer of type atomic_t
  *
  * Atomically adds @i to @v.
  */
-static __always_inline void atomic_add(int i, atomic_t *v)
+static __always_inline void arch_atomic_add(int i, atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "addl %1,%0"
 		     : "+m" (v->counter)

@@ -53,13 +59,13 @@ static __always_inline void atomic_add(int i, atomic_t *v)
 }
 
 /**
- * atomic_sub - subtract integer from atomic variable
+ * arch_atomic_sub - subtract integer from atomic variable
  * @i: integer value to subtract
  * @v: pointer of type atomic_t
  *
  * Atomically subtracts @i from @v.
  */
-static __always_inline void atomic_sub(int i, atomic_t *v)
+static __always_inline void arch_atomic_sub(int i, atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "subl %1,%0"
 		     : "+m" (v->counter)

@@ -67,7 +73,7 @@ static __always_inline void atomic_sub(int i, atomic_t *v)
 }
 
 /**
- * atomic_sub_and_test - subtract value from variable and test result
+ * arch_atomic_sub_and_test - subtract value from variable and test result
  * @i: integer value to subtract
  * @v: pointer of type atomic_t
  *

@@ -75,63 +81,63 @@ static __always_inline void atomic_sub(int i, atomic_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
-static __always_inline bool atomic_sub_and_test(int i, atomic_t *v)
+static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e);
 }
 
 /**
- * atomic_inc - increment atomic variable
+ * arch_atomic_inc - increment atomic variable
  * @v: pointer of type atomic_t
  *
  * Atomically increments @v by 1.
  */
-static __always_inline void atomic_inc(atomic_t *v)
+static __always_inline void arch_atomic_inc(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "incl %0"
 		     : "+m" (v->counter));
 }
 
 /**
- * atomic_dec - decrement atomic variable
+ * arch_atomic_dec - decrement atomic variable
  * @v: pointer of type atomic_t
  *
  * Atomically decrements @v by 1.
  */
-static __always_inline void atomic_dec(atomic_t *v)
+static __always_inline void arch_atomic_dec(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "decl %0"
 		     : "+m" (v->counter));
 }
 
 /**
- * atomic_dec_and_test - decrement and test
+ * arch_atomic_dec_and_test - decrement and test
  * @v: pointer of type atomic_t
  *
  * Atomically decrements @v by 1 and
  * returns true if the result is 0, or false for all other
  * cases.
  */
-static __always_inline bool atomic_dec_and_test(atomic_t *v)
+static __always_inline bool arch_atomic_dec_and_test(atomic_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e);
 }
 
 /**
- * atomic_inc_and_test - increment and test
+ * arch_atomic_inc_and_test - increment and test
  * @v: pointer of type atomic_t
  *
  * Atomically increments @v by 1
  * and returns true if the result is zero, or false for all
  * other cases.
  */
-static __always_inline bool atomic_inc_and_test(atomic_t *v)
+static __always_inline bool arch_atomic_inc_and_test(atomic_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e);
 }
 
 /**
- * atomic_add_negative - add and test if negative
+ * arch_atomic_add_negative - add and test if negative
  * @i: integer value to add
  * @v: pointer of type atomic_t
  *

@@ -139,65 +145,65 @@ static __always_inline bool atomic_inc_and_test(atomic_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-static __always_inline bool atomic_add_negative(int i, atomic_t *v)
+static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s);
 }
 
 /**
- * atomic_add_return - add integer and return
+ * arch_atomic_add_return - add integer and return
  * @i: integer value to add
  * @v: pointer of type atomic_t
  *
  * Atomically adds @i to @v and returns @i + @v
  */
-static __always_inline int atomic_add_return(int i, atomic_t *v)
+static __always_inline int arch_atomic_add_return(int i, atomic_t *v)
 {
 	return i + xadd(&v->counter, i);
 }
 
 /**
- * atomic_sub_return - subtract integer and return
+ * arch_atomic_sub_return - subtract integer and return
  * @v: pointer of type atomic_t
  * @i: integer value to subtract
  *
  * Atomically subtracts @i from @v and returns @v - @i
  */
-static __always_inline int atomic_sub_return(int i, atomic_t *v)
+static __always_inline int arch_atomic_sub_return(int i, atomic_t *v)
 {
-	return atomic_add_return(-i, v);
+	return arch_atomic_add_return(-i, v);
 }
 
-#define atomic_inc_return(v)  (atomic_add_return(1, v))
-#define atomic_dec_return(v)  (atomic_sub_return(1, v))
+#define arch_atomic_inc_return(v)  (arch_atomic_add_return(1, v))
+#define arch_atomic_dec_return(v)  (arch_atomic_sub_return(1, v))
 
-static __always_inline int atomic_fetch_add(int i, atomic_t *v)
+static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v)
 {
 	return xadd(&v->counter, i);
 }
 
-static __always_inline int atomic_fetch_sub(int i, atomic_t *v)
+static __always_inline int arch_atomic_fetch_sub(int i, atomic_t *v)
 {
 	return xadd(&v->counter, -i);
 }
 
-static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+static __always_inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new)
 {
-	return cmpxchg(&v->counter, old, new);
+	return arch_cmpxchg(&v->counter, old, new);
 }
 
-#define atomic_try_cmpxchg atomic_try_cmpxchg
-static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new)
+#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg
+static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new)
 {
 	return try_cmpxchg(&v->counter, old, new);
 }
 
-static inline int atomic_xchg(atomic_t *v, int new)
+static inline int arch_atomic_xchg(atomic_t *v, int new)
 {
 	return xchg(&v->counter, new);
 }
 
-static inline void atomic_and(int i, atomic_t *v)
+static inline void arch_atomic_and(int i, atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "andl %1,%0"
 			: "+m" (v->counter)

@@ -205,16 +211,16 @@ static inline void atomic_and(int i, atomic_t *v)
 			: "memory");
 }
 
-static inline int atomic_fetch_and(int i, atomic_t *v)
+static inline int arch_atomic_fetch_and(int i, atomic_t *v)
 {
-	int val = atomic_read(v);
+	int val = arch_atomic_read(v);
 
 	do {
-	} while (!atomic_try_cmpxchg(v, &val, val & i));
+	} while (!arch_atomic_try_cmpxchg(v, &val, val & i));
 	return val;
 }
 
-static inline void atomic_or(int i, atomic_t *v)
+static inline void arch_atomic_or(int i, atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "orl %1,%0"
 			: "+m" (v->counter)

@@ -222,17 +228,17 @@ static inline void atomic_or(int i, atomic_t *v)
 			: "memory");
 }
 
-static inline int atomic_fetch_or(int i, atomic_t *v)
+static inline int arch_atomic_fetch_or(int i, atomic_t *v)
 {
-	int val = atomic_read(v);
+	int val = arch_atomic_read(v);
 
 	do {
-	} while (!atomic_try_cmpxchg(v, &val, val | i));
+	} while (!arch_atomic_try_cmpxchg(v, &val, val | i));
 	return val;
 }
 
 
-static inline void atomic_xor(int i, atomic_t *v)
+static inline void arch_atomic_xor(int i, atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "xorl %1,%0"
 			: "+m" (v->counter)

@@ -240,17 +246,17 @@ static inline void atomic_xor(int i, atomic_t *v)
 			: "memory");
 }
 
-static inline int atomic_fetch_xor(int i, atomic_t *v)
+static inline int arch_atomic_fetch_xor(int i, atomic_t *v)
 {
-	int val = atomic_read(v);
+	int val = arch_atomic_read(v);
 
 	do {
-	} while (!atomic_try_cmpxchg(v, &val, val ^ i));
+	} while (!arch_atomic_try_cmpxchg(v, &val, val ^ i));
 	return val;
 }
 
 /**
- * __atomic_add_unless - add unless the number is already a given value
+ * __arch_atomic_add_unless - add unless the number is already a given value
  * @v: pointer of type atomic_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.

@@ -258,13 +264,13 @@ static inline int atomic_fetch_xor(int i, atomic_t *v)
  * Atomically adds @a to @v, so long as @v was not already @u.
  * Returns the old value of @v.
  */
-static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static __always_inline int __arch_atomic_add_unless(atomic_t *v, int a, int u)
 {
-	int c = atomic_read(v);
+	int c = arch_atomic_read(v);
 	do {
 		if (unlikely(c == u))
 			break;
-	} while (!atomic_try_cmpxchg(v, &c, c + a));
+	} while (!arch_atomic_try_cmpxchg(v, &c, c + a));
 	return c;
 }
 

@@ -287,4 +293,6 @@ static __always_inline short int atomic_inc_short(short int *v)
 # include <asm/atomic64_64.h>
 #endif
 
+#include <asm-generic/atomic-instrumented.h>
+
 #endif /* _ASM_X86_ATOMIC_H */

332 lines not on this page · raw message

314 lines not on this page · raw message

index b5069e802d5c..9e2faa85eb02 100644
@@ -144,13 +144,13 @@ extern void __add_wrong_size(void)
 # include <asm/cmpxchg_64.h>
 #endif
 
-#define cmpxchg(ptr, old, new)						\
+#define arch_cmpxchg(ptr, old, new)					\
 	__cmpxchg(ptr, old, new, sizeof(*(ptr)))
 
-#define sync_cmpxchg(ptr, old, new)					\
+#define arch_sync_cmpxchg(ptr, old, new)				\
 	__sync_cmpxchg(ptr, old, new, sizeof(*(ptr)))
 
-#define cmpxchg_local(ptr, old, new)					\
+#define arch_cmpxchg_local(ptr, old, new)				\
 	__cmpxchg_local(ptr, old, new, sizeof(*(ptr)))
 
 

@@ -220,7 +220,7 @@ extern void __add_wrong_size(void)
 #define __try_cmpxchg(ptr, pold, new, size)				\
 	__raw_try_cmpxchg((ptr), (pold), (new), (size), LOCK_PREFIX)
 
-#define try_cmpxchg(ptr, pold, new)					\
+#define try_cmpxchg(ptr, pold, new) 					\
 	__try_cmpxchg((ptr), (pold), (new), sizeof(*(ptr)))
 
 /*

@@ -249,10 +249,10 @@ extern void __add_wrong_size(void)
 	__ret;								\
 })
 
-#define cmpxchg_double(p1, p2, o1, o2, n1, n2) \
+#define arch_cmpxchg_double(p1, p2, o1, o2, n1, n2) \
 	__cmpxchg_double(LOCK_PREFIX, p1, p2, o1, o2, n1, n2)
 
-#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2) \
+#define arch_cmpxchg_double_local(p1, p2, o1, o2, n1, n2) \
 	__cmpxchg_double(, p1, p2, o1, o2, n1, n2)
 
 #endif	/* ASM_X86_CMPXCHG_H */

index e4959d023af8..d897291d2bf9 100644
@@ -35,10 +35,10 @@ static inline void set_64bit(volatile u64 *ptr, u64 value)
 }
 
 #ifdef CONFIG_X86_CMPXCHG64
-#define cmpxchg64(ptr, o, n)						\
+#define arch_cmpxchg64(ptr, o, n)					\
 	((__typeof__(*(ptr)))__cmpxchg64((ptr), (unsigned long long)(o), \
 					 (unsigned long long)(n)))
-#define cmpxchg64_local(ptr, o, n)					\
+#define arch_cmpxchg64_local(ptr, o, n)					\
 	((__typeof__(*(ptr)))__cmpxchg64_local((ptr), (unsigned long long)(o), \
 					       (unsigned long long)(n)))
 #endif

@@ -75,7 +75,7 @@ static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
  * to simulate the cmpxchg8b on the 80386 and 80486 CPU.
  */
 
-#define cmpxchg64(ptr, o, n)					\
+#define arch_cmpxchg64(ptr, o, n)				\
 ({								\
 	__typeof__(*(ptr)) __ret;				\
 	__typeof__(*(ptr)) __old = (o);				\

@@ -92,7 +92,7 @@ static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
 	__ret; })
 
 
-#define cmpxchg64_local(ptr, o, n)				\
+#define arch_cmpxchg64_local(ptr, o, n)				\
 ({								\
 	__typeof__(*(ptr)) __ret;				\
 	__typeof__(*(ptr)) __old = (o);				\

index caa23a34c963..fafaebacca2d 100644
@@ -6,13 +6,13 @@ static inline void set_64bit(volatile u64 *ptr, u64 val)
 	*ptr = val;
 }
 
-#define cmpxchg64(ptr, o, n)						\
+#define arch_cmpxchg64(ptr, o, n)					\
 ({									\
 	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
 	cmpxchg((ptr), (o), (n));					\
 })
 
-#define cmpxchg64_local(ptr, o, n)					\
+#define arch_cmpxchg64_local(ptr, o, n)					\
 ({									\
 	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
 	cmpxchg_local((ptr), (o), (n));					\

index caa5798c92f4..1a4a6a99dcd8 100644
@@ -197,35 +197,57 @@ static inline int atomic_xchg(atomic_t *v, int new)
 	return xchg(&v->counter, new);
 }
 
-#define ATOMIC_OP(op)							\
-static inline void atomic_##op(int i, atomic_t *v)			\
-{									\
-	asm volatile(LOCK_PREFIX #op"l %1,%0"				\
-			: "+m" (v->counter)				\
-			: "ir" (i)					\
-			: "memory");					\
+static inline void atomic_and(int i, atomic_t *v)
+{
+	asm volatile(LOCK_PREFIX "andl %1,%0"
+			: "+m" (v->counter)
+			: "ir" (i)
+			: "memory");
+}
+
+static inline int atomic_fetch_and(int i, atomic_t *v)
+{
+	int val = atomic_read(v);
+
+	do {
+	} while (!atomic_try_cmpxchg(v, &val, val & i));
+	return val;
+}
+
+static inline void atomic_or(int i, atomic_t *v)
+{
+	asm volatile(LOCK_PREFIX "orl %1,%0"
+			: "+m" (v->counter)
+			: "ir" (i)
+			: "memory");
 }
 
-#define ATOMIC_FETCH_OP(op, c_op)					\
-static inline int atomic_fetch_##op(int i, atomic_t *v)			\
-{									\
-	int val = atomic_read(v);					\
-	do {								\
-	} while (!atomic_try_cmpxchg(v, &val, val c_op i));		\
-	return val;							\
+static inline int atomic_fetch_or(int i, atomic_t *v)
+{
+	int val = atomic_read(v);
+
+	do {
+	} while (!atomic_try_cmpxchg(v, &val, val | i));
+	return val;
 }
 
-#define ATOMIC_OPS(op, c_op)						\
-	ATOMIC_OP(op)							\
-	ATOMIC_FETCH_OP(op, c_op)
 
-ATOMIC_OPS(and, &)
-ATOMIC_OPS(or , |)
-ATOMIC_OPS(xor, ^)
+static inline void atomic_xor(int i, atomic_t *v)
+{
+	asm volatile(LOCK_PREFIX "xorl %1,%0"
+			: "+m" (v->counter)
+			: "ir" (i)
+			: "memory");
+}
 
-#undef ATOMIC_OPS
-#undef ATOMIC_FETCH_OP
-#undef ATOMIC_OP
+static inline int atomic_fetch_xor(int i, atomic_t *v)
+{
+	int val = atomic_read(v);
+
+	do {
+	} while (!atomic_try_cmpxchg(v, &val, val ^ i));
+	return val;
+}
 
 /**
  * __atomic_add_unless - add unless the number is already a given value

90 lines not on this page · raw message

78 lines not on this page · raw message