[PATCH v2 2/7] x86: use long long for 64-bit atomic ops

[PATCH v2 2/7] x86: use long long for 64-bit atomic ops

[Dmitry Vyukov]

Some 64-bit atomic operations use 'long long' as operand/return type
(e.g. asm-generic/atomic64.h, arch/x86/include/asm/atomic64_32.h);
while others use 'long' (e.g. arch/x86/include/asm/atomic64_64.h).
This makes it impossible to write portable code.
For example, there is no format specifier that prints result of
atomic64_read() without warnings. atomic64_try_cmpxchg() is almost
impossible to use in portable fashion because it requires either
'long *' or 'long long *' as argument depending on arch.

Switch arch/x86/include/asm/atomic64_64.h to 'long long'.

Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: kasan-dev@googlegroups.com
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
Cc: x86@kernel.org

---
Changes since v1:
 - reverted stray s/long/long long/ replace in comment
 - added arch/s390 changes to fix build errors/warnings
---
 arch/s390/include/asm/atomic_ops.h | 14 +++++-----
 arch/s390/include/asm/bitops.h     | 12 ++++-----
 arch/x86/include/asm/atomic64_64.h | 52 +++++++++++++++++++-------------------
 include/linux/types.h              |  2 +-
 4 files changed, 40 insertions(+), 40 deletions(-)

diff --git a/arch/s390/include/asm/atomic_ops.h b/arch/s390/include/asm/atomic_ops.h
index ac9e2b939d04..055a9083e52d 100644
--- a/arch/s390/include/asm/atomic_ops.h
+++ b/arch/s390/include/asm/atomic_ops.h
@@ -31,10 +31,10 @@ __ATOMIC_OPS(__atomic_and, int, "lan")
 __ATOMIC_OPS(__atomic_or,  int, "lao")
 __ATOMIC_OPS(__atomic_xor, int, "lax")
 
-__ATOMIC_OPS(__atomic64_add, long, "laag")
-__ATOMIC_OPS(__atomic64_and, long, "lang")
-__ATOMIC_OPS(__atomic64_or,  long, "laog")
-__ATOMIC_OPS(__atomic64_xor, long, "laxg")
+__ATOMIC_OPS(__atomic64_add, long long, "laag")
+__ATOMIC_OPS(__atomic64_and, long long, "lang")
+__ATOMIC_OPS(__atomic64_or,  long long, "laog")
+__ATOMIC_OPS(__atomic64_xor, long long, "laxg")
 
 #undef __ATOMIC_OPS
 #undef __ATOMIC_OP
@@ -46,7 +46,7 @@ static inline void __atomic_add_const(int val, int *ptr)
 		: [ptr] "+Q" (*ptr) : [val] "i" (val) : "cc");
 }
 
-static inline void __atomic64_add_const(long val, long *ptr)
+static inline void __atomic64_add_const(long val, long long *ptr)
 {
 	asm volatile(
 		"	agsi	%[ptr],%[val]\n"
@@ -82,7 +82,7 @@ __ATOMIC_OPS(__atomic_xor, "xr")
 #undef __ATOMIC_OPS
 
 #define __ATOMIC64_OP(op_name, op_string)				\
-static inline long op_name(long val, long *ptr)				\
+static inline long op_name(long val, long long *ptr)			\
 {									\
 	long old, new;							\
 									\
@@ -118,7 +118,7 @@ static inline int __atomic_cmpxchg(int *ptr, int old, int new)
 	return old;
 }
 
-static inline long __atomic64_cmpxchg(long *ptr, long old, long new)
+static inline long __atomic64_cmpxchg(long long *ptr, long old, long new)
 {
 	asm volatile(
 		"	csg	%[old],%[new],%[ptr]"
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index d92047da5ccb..8912f52bca5d 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -80,7 +80,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *ptr)
 	}
 #endif
 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
-	__atomic64_or(mask, addr);
+	__atomic64_or(mask, (long long *)addr);
 }
 
 static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr)
@@ -101,7 +101,7 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr)
 	}
 #endif
 	mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
-	__atomic64_and(mask, addr);
+	__atomic64_and(mask, (long long *)addr);
 }
 
 static inline void change_bit(unsigned long nr, volatile unsigned long *ptr)
@@ -122,7 +122,7 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *ptr)
 	}
 #endif
 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
-	__atomic64_xor(mask, addr);
+	__atomic64_xor(mask, (long long *)addr);
 }
 
 static inline int
@@ -132,7 +132,7 @@ test_and_set_bit(unsigned long nr, volatile unsigned long *ptr)
 	unsigned long old, mask;
 
 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
-	old = __atomic64_or_barrier(mask, addr);
+	old = __atomic64_or_barrier(mask, (long long *)addr);
 	return (old & mask) != 0;
 }
 
@@ -143,7 +143,7 @@ test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr)
 	unsigned long old, mask;
 
 	mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
-	old = __atomic64_and_barrier(mask, addr);
+	old = __atomic64_and_barrier(mask, (long long *)addr);
 	return (old & ~mask) != 0;
 }
 
@@ -154,7 +154,7 @@ test_and_change_bit(unsigned long nr, volatile unsigned long *ptr)
 	unsigned long old, mask;
 
 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
-	old = __atomic64_xor_barrier(mask, addr);
+	old = __atomic64_xor_barrier(mask, (long long *)addr);
 	return (old & mask) != 0;
 }
 
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 8db8879a6d8c..8555cd19a916 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -16,7 +16,7 @@
  * Atomically reads the value of @v.
  * Doesn't imply a read memory barrier.
  */
-static inline long atomic64_read(const atomic64_t *v)
+static inline long long atomic64_read(const atomic64_t *v)
 {
 	return READ_ONCE((v)->counter);
 }
@@ -28,7 +28,7 @@ static inline long atomic64_read(const atomic64_t *v)
  *
  * Atomically sets the value of @v to @i.
  */
-static inline void atomic64_set(atomic64_t *v, long i)
+static inline void atomic64_set(atomic64_t *v, long long i)
 {
 	WRITE_ONCE(v->counter, i);
 }
@@ -40,7 +40,7 @@ static inline void atomic64_set(atomic64_t *v, long i)
  *
  * Atomically adds @i to @v.
  */
-static __always_inline void atomic64_add(long i, atomic64_t *v)
+static __always_inline void atomic64_add(long long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "addq %1,%0"
 		     : "=m" (v->counter)
@@ -54,7 +54,7 @@ static __always_inline void atomic64_add(long i, atomic64_t *v)
  *
  * Atomically subtracts @i from @v.
  */
-static inline void atomic64_sub(long i, atomic64_t *v)
+static inline void atomic64_sub(long long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "subq %1,%0"
 		     : "=m" (v->counter)
@@ -70,7 +70,7 @@ static inline void atomic64_sub(long i, atomic64_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
-static inline bool atomic64_sub_and_test(long i, atomic64_t *v)
+static inline bool atomic64_sub_and_test(long long i, atomic64_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e);
 }
@@ -136,7 +136,7 @@ static inline bool atomic64_inc_and_test(atomic64_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-static inline bool atomic64_add_negative(long i, atomic64_t *v)
+static inline bool atomic64_add_negative(long long i, atomic64_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s);
 }
@@ -148,22 +148,22 @@ static inline bool atomic64_add_negative(long i, atomic64_t *v)
  *
  * Atomically adds @i to @v and returns @i + @v
  */
-static __always_inline long atomic64_add_return(long i, atomic64_t *v)
+static __always_inline long long atomic64_add_return(long long i, atomic64_t *v)
 {
 	return i + xadd(&v->counter, i);
 }
 
-static inline long atomic64_sub_return(long i, atomic64_t *v)
+static inline long long atomic64_sub_return(long long i, atomic64_t *v)
 {
 	return atomic64_add_return(-i, v);
 }
 
-static inline long atomic64_fetch_add(long i, atomic64_t *v)
+static inline long long atomic64_fetch_add(long long i, atomic64_t *v)
 {
 	return xadd(&v->counter, i);
 }
 
-static inline long atomic64_fetch_sub(long i, atomic64_t *v)
+static inline long long atomic64_fetch_sub(long long i, atomic64_t *v)
 {
 	return xadd(&v->counter, -i);
 }
@@ -171,18 +171,18 @@ static inline long atomic64_fetch_sub(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)))
 
-static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new)
+static inline long long atomic64_cmpxchg(atomic64_t *v, long long old, long long new)
 {
 	return cmpxchg(&v->counter, old, 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, long long *old, long long new)
 {
 	return try_cmpxchg(&v->counter, old, new);
 }
 
-static inline long atomic64_xchg(atomic64_t *v, long new)
+static inline long long atomic64_xchg(atomic64_t *v, long long new)
 {
 	return xchg(&v->counter, new);
 }
@@ -196,9 +196,9 @@ static inline long atomic64_xchg(atomic64_t *v, long new)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static inline bool atomic64_add_unless(atomic64_t *v, long a, long u)
+static inline bool atomic64_add_unless(atomic64_t *v, long long a, long long u)
 {
-	long c = atomic64_read(v);
+	long long c = atomic64_read(v);
 	do {
 		if (unlikely(c == u))
 			return false;
@@ -215,9 +215,9 @@ static inline bool atomic64_add_unless(atomic64_t *v, long a, long u)
  * The function returns the old value of *v minus 1, even if
  * the atomic variable, v, was not decremented.
  */
-static inline long atomic64_dec_if_positive(atomic64_t *v)
+static inline long long atomic64_dec_if_positive(atomic64_t *v)
 {
-	long dec, c = atomic64_read(v);
+	long long dec, c = atomic64_read(v);
 	do {
 		dec = c - 1;
 		if (unlikely(dec < 0))
@@ -226,7 +226,7 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 	return dec;
 }
 
-static inline void atomic64_and(long i, atomic64_t *v)
+static inline void atomic64_and(long long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "andq %1,%0"
 			: "+m" (v->counter)
@@ -234,16 +234,16 @@ static inline void atomic64_and(long i, atomic64_t *v)
 			: "memory");
 }
 
-static inline long atomic64_fetch_and(long i, atomic64_t *v)
+static inline long long atomic64_fetch_and(long long i, atomic64_t *v)
 {
-	long val = atomic64_read(v);
+	long long val = atomic64_read(v);
 
 	do {
 	} while (!atomic64_try_cmpxchg(v, &val, val & i));
 	return val;
 }
 
-static inline void atomic64_or(long i, atomic64_t *v)
+static inline void atomic64_or(long long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "orq %1,%0"
 			: "+m" (v->counter)
@@ -251,16 +251,16 @@ static inline void atomic64_or(long i, atomic64_t *v)
 			: "memory");
 }
 
-static inline long atomic64_fetch_or(long i, atomic64_t *v)
+static inline long long atomic64_fetch_or(long long i, atomic64_t *v)
 {
-	long val = atomic64_read(v);
+	long long val = atomic64_read(v);
 
 	do {
 	} while (!atomic64_try_cmpxchg(v, &val, val | i));
 	return val;
 }
 
-static inline void atomic64_xor(long i, atomic64_t *v)
+static inline void atomic64_xor(long long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "xorq %1,%0"
 			: "+m" (v->counter)
@@ -268,9 +268,9 @@ static inline void atomic64_xor(long i, atomic64_t *v)
 			: "memory");
 }
 
-static inline long atomic64_fetch_xor(long i, atomic64_t *v)
+static inline long long atomic64_fetch_xor(long long i, atomic64_t *v)
 {
-	long val = atomic64_read(v);
+	long long val = atomic64_read(v);
 
 	do {
 	} while (!atomic64_try_cmpxchg(v, &val, val ^ i));
diff --git a/include/linux/types.h b/include/linux/types.h
index 1e7bd24848fc..569fc6db1bd5 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -177,7 +177,7 @@ typedef struct {
 
 #ifdef CONFIG_64BIT
 typedef struct {
-	long counter;
+	long long counter;
 } atomic64_t;
 #endif
 
-- 
2.13.0.219.gdb65acc882-goog

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH v2 2/7] x86: use long long for 64-bit atomic ops

[hpa]

On May 26, 2017 12:09:04 PM PDT, Dmitry Vyukov <dvyukov@google.com> wrote:
>Some 64-bit atomic operations use 'long long' as operand/return type
>(e.g. asm-generic/atomic64.h, arch/x86/include/asm/atomic64_32.h);
>while others use 'long' (e.g. arch/x86/include/asm/atomic64_64.h).
>This makes it impossible to write portable code.
>For example, there is no format specifier that prints result of
>atomic64_read() without warnings. atomic64_try_cmpxchg() is almost
>impossible to use in portable fashion because it requires either
>'long *' or 'long long *' as argument depending on arch.
>
>Switch arch/x86/include/asm/atomic64_64.h to 'long long'.
>
>Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
>Cc: Mark Rutland <mark.rutland@arm.com>
>Cc: Peter Zijlstra <peterz@infradead.org>
>Cc: Will Deacon <will.deacon@arm.com>
>Cc: Andrew Morton <akpm@linux-foundation.org>
>Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
>Cc: Ingo Molnar <mingo@redhat.com>
>Cc: kasan-dev@googlegroups.com
>Cc: linux-mm@kvack.org
>Cc: linux-kernel@vger.kernel.org
>Cc: x86@kernel.org
>
>---
>Changes since v1:
> - reverted stray s/long/long long/ replace in comment
> - added arch/s390 changes to fix build errors/warnings
>---
> arch/s390/include/asm/atomic_ops.h | 14 +++++-----
> arch/s390/include/asm/bitops.h     | 12 ++++-----
>arch/x86/include/asm/atomic64_64.h | 52
>+++++++++++++++++++-------------------
> include/linux/types.h              |  2 +-
> 4 files changed, 40 insertions(+), 40 deletions(-)
>
>diff --git a/arch/s390/include/asm/atomic_ops.h
>b/arch/s390/include/asm/atomic_ops.h
>index ac9e2b939d04..055a9083e52d 100644
>--- a/arch/s390/include/asm/atomic_ops.h
>+++ b/arch/s390/include/asm/atomic_ops.h
>@@ -31,10 +31,10 @@ __ATOMIC_OPS(__atomic_and, int, "lan")
> __ATOMIC_OPS(__atomic_or,  int, "lao")
> __ATOMIC_OPS(__atomic_xor, int, "lax")
> 
>-__ATOMIC_OPS(__atomic64_add, long, "laag")
>-__ATOMIC_OPS(__atomic64_and, long, "lang")
>-__ATOMIC_OPS(__atomic64_or,  long, "laog")
>-__ATOMIC_OPS(__atomic64_xor, long, "laxg")
>+__ATOMIC_OPS(__atomic64_add, long long, "laag")
>+__ATOMIC_OPS(__atomic64_and, long long, "lang")
>+__ATOMIC_OPS(__atomic64_or,  long long, "laog")
>+__ATOMIC_OPS(__atomic64_xor, long long, "laxg")
> 
> #undef __ATOMIC_OPS
> #undef __ATOMIC_OP
>@@ -46,7 +46,7 @@ static inline void __atomic_add_const(int val, int
>*ptr)
> 		: [ptr] "+Q" (*ptr) : [val] "i" (val) : "cc");
> }
> 
>-static inline void __atomic64_add_const(long val, long *ptr)
>+static inline void __atomic64_add_const(long val, long long *ptr)
> {
> 	asm volatile(
> 		"	agsi	%[ptr],%[val]\n"
>@@ -82,7 +82,7 @@ __ATOMIC_OPS(__atomic_xor, "xr")
> #undef __ATOMIC_OPS
> 
> #define __ATOMIC64_OP(op_name, op_string)				\
>-static inline long op_name(long val, long *ptr)				\
>+static inline long op_name(long val, long long *ptr)			\
> {									\
> 	long old, new;							\
> 									\
>@@ -118,7 +118,7 @@ static inline int __atomic_cmpxchg(int *ptr, int
>old, int new)
> 	return old;
> }
> 
>-static inline long __atomic64_cmpxchg(long *ptr, long old, long new)
>+static inline long __atomic64_cmpxchg(long long *ptr, long old, long
>new)
> {
> 	asm volatile(
> 		"	csg	%[old],%[new],%[ptr]"
>diff --git a/arch/s390/include/asm/bitops.h
>b/arch/s390/include/asm/bitops.h
>index d92047da5ccb..8912f52bca5d 100644
>--- a/arch/s390/include/asm/bitops.h
>+++ b/arch/s390/include/asm/bitops.h
>@@ -80,7 +80,7 @@ static inline void set_bit(unsigned long nr, volatile
>unsigned long *ptr)
> 	}
> #endif
> 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
>-	__atomic64_or(mask, addr);
>+	__atomic64_or(mask, (long long *)addr);
> }
> 
>static inline void clear_bit(unsigned long nr, volatile unsigned long
>*ptr)
>@@ -101,7 +101,7 @@ static inline void clear_bit(unsigned long nr,
>volatile unsigned long *ptr)
> 	}
> #endif
> 	mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
>-	__atomic64_and(mask, addr);
>+	__atomic64_and(mask, (long long *)addr);
> }
> 
>static inline void change_bit(unsigned long nr, volatile unsigned long
>*ptr)
>@@ -122,7 +122,7 @@ static inline void change_bit(unsigned long nr,
>volatile unsigned long *ptr)
> 	}
> #endif
> 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
>-	__atomic64_xor(mask, addr);
>+	__atomic64_xor(mask, (long long *)addr);
> }
> 
> static inline int
>@@ -132,7 +132,7 @@ test_and_set_bit(unsigned long nr, volatile
>unsigned long *ptr)
> 	unsigned long old, mask;
> 
> 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
>-	old = __atomic64_or_barrier(mask, addr);
>+	old = __atomic64_or_barrier(mask, (long long *)addr);
> 	return (old & mask) != 0;
> }
> 
>@@ -143,7 +143,7 @@ test_and_clear_bit(unsigned long nr, volatile
>unsigned long *ptr)
> 	unsigned long old, mask;
> 
> 	mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
>-	old = __atomic64_and_barrier(mask, addr);
>+	old = __atomic64_and_barrier(mask, (long long *)addr);
> 	return (old & ~mask) != 0;
> }
> 
>@@ -154,7 +154,7 @@ test_and_change_bit(unsigned long nr, volatile
>unsigned long *ptr)
> 	unsigned long old, mask;
> 
> 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
>-	old = __atomic64_xor_barrier(mask, addr);
>+	old = __atomic64_xor_barrier(mask, (long long *)addr);
> 	return (old & mask) != 0;
> }
> 
>diff --git a/arch/x86/include/asm/atomic64_64.h
>b/arch/x86/include/asm/atomic64_64.h
>index 8db8879a6d8c..8555cd19a916 100644
>--- a/arch/x86/include/asm/atomic64_64.h
>+++ b/arch/x86/include/asm/atomic64_64.h
>@@ -16,7 +16,7 @@
>  * Atomically reads the value of @v.
>  * Doesn't imply a read memory barrier.
>  */
>-static inline long atomic64_read(const atomic64_t *v)
>+static inline long long atomic64_read(const atomic64_t *v)
> {
> 	return READ_ONCE((v)->counter);
> }
>@@ -28,7 +28,7 @@ static inline long atomic64_read(const atomic64_t *v)
>  *
>  * Atomically sets the value of @v to @i.
>  */
>-static inline void atomic64_set(atomic64_t *v, long i)
>+static inline void atomic64_set(atomic64_t *v, long long i)
> {
> 	WRITE_ONCE(v->counter, i);
> }
>@@ -40,7 +40,7 @@ static inline void atomic64_set(atomic64_t *v, long
>i)
>  *
>  * Atomically adds @i to @v.
>  */
>-static __always_inline void atomic64_add(long i, atomic64_t *v)
>+static __always_inline void atomic64_add(long long i, atomic64_t *v)
> {
> 	asm volatile(LOCK_PREFIX "addq %1,%0"
> 		     : "=m" (v->counter)
>@@ -54,7 +54,7 @@ static __always_inline void atomic64_add(long i,
>atomic64_t *v)
>  *
>  * Atomically subtracts @i from @v.
>  */
>-static inline void atomic64_sub(long i, atomic64_t *v)
>+static inline void atomic64_sub(long long i, atomic64_t *v)
> {
> 	asm volatile(LOCK_PREFIX "subq %1,%0"
> 		     : "=m" (v->counter)
>@@ -70,7 +70,7 @@ static inline void atomic64_sub(long i, atomic64_t
>*v)
>  * true if the result is zero, or false for all
>  * other cases.
>  */
>-static inline bool atomic64_sub_and_test(long i, atomic64_t *v)
>+static inline bool atomic64_sub_and_test(long long i, atomic64_t *v)
> {
> 	GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e);
> }
>@@ -136,7 +136,7 @@ static inline bool atomic64_inc_and_test(atomic64_t
>*v)
>  * if the result is negative, or false when
>  * result is greater than or equal to zero.
>  */
>-static inline bool atomic64_add_negative(long i, atomic64_t *v)
>+static inline bool atomic64_add_negative(long long i, atomic64_t *v)
> {
> 	GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s);
> }
>@@ -148,22 +148,22 @@ static inline bool atomic64_add_negative(long i,
>atomic64_t *v)
>  *
>  * Atomically adds @i to @v and returns @i + @v
>  */
>-static __always_inline long atomic64_add_return(long i, atomic64_t *v)
>+static __always_inline long long atomic64_add_return(long long i,
>atomic64_t *v)
> {
> 	return i + xadd(&v->counter, i);
> }
> 
>-static inline long atomic64_sub_return(long i, atomic64_t *v)
>+static inline long long atomic64_sub_return(long long i, atomic64_t
>*v)
> {
> 	return atomic64_add_return(-i, v);
> }
> 
>-static inline long atomic64_fetch_add(long i, atomic64_t *v)
>+static inline long long atomic64_fetch_add(long long i, atomic64_t *v)
> {
> 	return xadd(&v->counter, i);
> }
> 
>-static inline long atomic64_fetch_sub(long i, atomic64_t *v)
>+static inline long long atomic64_fetch_sub(long long i, atomic64_t *v)
> {
> 	return xadd(&v->counter, -i);
> }
>@@ -171,18 +171,18 @@ static inline long atomic64_fetch_sub(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)))
> 
>-static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new)
>+static inline long long atomic64_cmpxchg(atomic64_t *v, long long old,
>long long new)
> {
> 	return cmpxchg(&v->counter, old, 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, long
>long *old, long long new)
> {
> 	return try_cmpxchg(&v->counter, old, new);
> }
> 
>-static inline long atomic64_xchg(atomic64_t *v, long new)
>+static inline long long atomic64_xchg(atomic64_t *v, long long new)
> {
> 	return xchg(&v->counter, new);
> }
>@@ -196,9 +196,9 @@ static inline long atomic64_xchg(atomic64_t *v,
>long new)
>  * Atomically adds @a to @v, so long as it was not @u.
>  * Returns the old value of @v.
>  */
>-static inline bool atomic64_add_unless(atomic64_t *v, long a, long u)
>+static inline bool atomic64_add_unless(atomic64_t *v, long long a,
>long long u)
> {
>-	long c = atomic64_read(v);
>+	long long c = atomic64_read(v);
> 	do {
> 		if (unlikely(c == u))
> 			return false;
>@@ -215,9 +215,9 @@ static inline bool atomic64_add_unless(atomic64_t
>*v, long a, long u)
>  * The function returns the old value of *v minus 1, even if
>  * the atomic variable, v, was not decremented.
>  */
>-static inline long atomic64_dec_if_positive(atomic64_t *v)
>+static inline long long atomic64_dec_if_positive(atomic64_t *v)
> {
>-	long dec, c = atomic64_read(v);
>+	long long dec, c = atomic64_read(v);
> 	do {
> 		dec = c - 1;
> 		if (unlikely(dec < 0))
>@@ -226,7 +226,7 @@ static inline long
>atomic64_dec_if_positive(atomic64_t *v)
> 	return dec;
> }
> 
>-static inline void atomic64_and(long i, atomic64_t *v)
>+static inline void atomic64_and(long long i, atomic64_t *v)
> {
> 	asm volatile(LOCK_PREFIX "andq %1,%0"
> 			: "+m" (v->counter)
>@@ -234,16 +234,16 @@ static inline void atomic64_and(long i,
>atomic64_t *v)
> 			: "memory");
> }
> 
>-static inline long atomic64_fetch_and(long i, atomic64_t *v)
>+static inline long long atomic64_fetch_and(long long i, atomic64_t *v)
> {
>-	long val = atomic64_read(v);
>+	long long val = atomic64_read(v);
> 
> 	do {
> 	} while (!atomic64_try_cmpxchg(v, &val, val & i));
> 	return val;
> }
> 
>-static inline void atomic64_or(long i, atomic64_t *v)
>+static inline void atomic64_or(long long i, atomic64_t *v)
> {
> 	asm volatile(LOCK_PREFIX "orq %1,%0"
> 			: "+m" (v->counter)
>@@ -251,16 +251,16 @@ static inline void atomic64_or(long i, atomic64_t
>*v)
> 			: "memory");
> }
> 
>-static inline long atomic64_fetch_or(long i, atomic64_t *v)
>+static inline long long atomic64_fetch_or(long long i, atomic64_t *v)
> {
>-	long val = atomic64_read(v);
>+	long long val = atomic64_read(v);
> 
> 	do {
> 	} while (!atomic64_try_cmpxchg(v, &val, val | i));
> 	return val;
> }
> 
>-static inline void atomic64_xor(long i, atomic64_t *v)
>+static inline void atomic64_xor(long long i, atomic64_t *v)
> {
> 	asm volatile(LOCK_PREFIX "xorq %1,%0"
> 			: "+m" (v->counter)
>@@ -268,9 +268,9 @@ static inline void atomic64_xor(long i, atomic64_t
>*v)
> 			: "memory");
> }
> 
>-static inline long atomic64_fetch_xor(long i, atomic64_t *v)
>+static inline long long atomic64_fetch_xor(long long i, atomic64_t *v)
> {
>-	long val = atomic64_read(v);
>+	long long val = atomic64_read(v);
> 
> 	do {
> 	} while (!atomic64_try_cmpxchg(v, &val, val ^ i));
>diff --git a/include/linux/types.h b/include/linux/types.h
>index 1e7bd24848fc..569fc6db1bd5 100644
>--- a/include/linux/types.h
>+++ b/include/linux/types.h
>@@ -177,7 +177,7 @@ typedef struct {
> 
> #ifdef CONFIG_64BIT
> typedef struct {
>-	long counter;
>+	long long counter;
> } atomic64_t;
> #endif
> 

NAK - this is what u64/s64 is for.
-- 
Sent from my Android device with K-9 Mail. Please excuse my brevity.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH v2 2/7] x86: use long long for 64-bit atomic ops

[Dmitry Vyukov]

On Sun, May 28, 2017 at 1:02 AM,  <hpa@zytor.com> wrote:
> On May 26, 2017 12:09:04 PM PDT, Dmitry Vyukov <dvyukov@google.com> wrote:
>>Some 64-bit atomic operations use 'long long' as operand/return type
>>(e.g. asm-generic/atomic64.h, arch/x86/include/asm/atomic64_32.h);
>>while others use 'long' (e.g. arch/x86/include/asm/atomic64_64.h).
>>This makes it impossible to write portable code.
>>For example, there is no format specifier that prints result of
>>atomic64_read() without warnings. atomic64_try_cmpxchg() is almost
>>impossible to use in portable fashion because it requires either
>>'long *' or 'long long *' as argument depending on arch.
>>
>>Switch arch/x86/include/asm/atomic64_64.h to 'long long'.
>>
>>Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
>>Cc: Mark Rutland <mark.rutland@arm.com>
>>Cc: Peter Zijlstra <peterz@infradead.org>
>>Cc: Will Deacon <will.deacon@arm.com>
>>Cc: Andrew Morton <akpm@linux-foundation.org>
>>Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
>>Cc: Ingo Molnar <mingo@redhat.com>
>>Cc: kasan-dev@googlegroups.com
>>Cc: linux-mm@kvack.org
>>Cc: linux-kernel@vger.kernel.org
>>Cc: x86@kernel.org
>>
>>---
>>Changes since v1:
>> - reverted stray s/long/long long/ replace in comment
>> - added arch/s390 changes to fix build errors/warnings
>>---
>> arch/s390/include/asm/atomic_ops.h | 14 +++++-----
>> arch/s390/include/asm/bitops.h     | 12 ++++-----
>>arch/x86/include/asm/atomic64_64.h | 52
>>+++++++++++++++++++-------------------
>> include/linux/types.h              |  2 +-
>> 4 files changed, 40 insertions(+), 40 deletions(-)
>>
>>diff --git a/arch/s390/include/asm/atomic_ops.h
>>b/arch/s390/include/asm/atomic_ops.h
>>index ac9e2b939d04..055a9083e52d 100644
>>--- a/arch/s390/include/asm/atomic_ops.h
>>+++ b/arch/s390/include/asm/atomic_ops.h
>>@@ -31,10 +31,10 @@ __ATOMIC_OPS(__atomic_and, int, "lan")
>> __ATOMIC_OPS(__atomic_or,  int, "lao")
>> __ATOMIC_OPS(__atomic_xor, int, "lax")
>>
>>-__ATOMIC_OPS(__atomic64_add, long, "laag")
>>-__ATOMIC_OPS(__atomic64_and, long, "lang")
>>-__ATOMIC_OPS(__atomic64_or,  long, "laog")
>>-__ATOMIC_OPS(__atomic64_xor, long, "laxg")
>>+__ATOMIC_OPS(__atomic64_add, long long, "laag")
>>+__ATOMIC_OPS(__atomic64_and, long long, "lang")
>>+__ATOMIC_OPS(__atomic64_or,  long long, "laog")
>>+__ATOMIC_OPS(__atomic64_xor, long long, "laxg")
>>
>> #undef __ATOMIC_OPS
>> #undef __ATOMIC_OP
>>@@ -46,7 +46,7 @@ static inline void __atomic_add_const(int val, int
>>*ptr)
>>               : [ptr] "+Q" (*ptr) : [val] "i" (val) : "cc");
>> }
>>
>>-static inline void __atomic64_add_const(long val, long *ptr)
>>+static inline void __atomic64_add_const(long val, long long *ptr)
>> {
>>       asm volatile(
>>               "       agsi    %[ptr],%[val]\n"
>>@@ -82,7 +82,7 @@ __ATOMIC_OPS(__atomic_xor, "xr")
>> #undef __ATOMIC_OPS
>>
>> #define __ATOMIC64_OP(op_name, op_string)                             \
>>-static inline long op_name(long val, long *ptr)                               \
>>+static inline long op_name(long val, long long *ptr)                  \
>> {                                                                     \
>>       long old, new;                                                  \
>>                                                                       \
>>@@ -118,7 +118,7 @@ static inline int __atomic_cmpxchg(int *ptr, int
>>old, int new)
>>       return old;
>> }
>>
>>-static inline long __atomic64_cmpxchg(long *ptr, long old, long new)
>>+static inline long __atomic64_cmpxchg(long long *ptr, long old, long
>>new)
>> {
>>       asm volatile(
>>               "       csg     %[old],%[new],%[ptr]"
>>diff --git a/arch/s390/include/asm/bitops.h
>>b/arch/s390/include/asm/bitops.h
>>index d92047da5ccb..8912f52bca5d 100644
>>--- a/arch/s390/include/asm/bitops.h
>>+++ b/arch/s390/include/asm/bitops.h
>>@@ -80,7 +80,7 @@ static inline void set_bit(unsigned long nr, volatile
>>unsigned long *ptr)
>>       }
>> #endif
>>       mask = 1UL << (nr & (BITS_PER_LONG - 1));
>>-      __atomic64_or(mask, addr);
>>+      __atomic64_or(mask, (long long *)addr);
>> }
>>
>>static inline void clear_bit(unsigned long nr, volatile unsigned long
>>*ptr)
>>@@ -101,7 +101,7 @@ static inline void clear_bit(unsigned long nr,
>>volatile unsigned long *ptr)
>>       }
>> #endif
>>       mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
>>-      __atomic64_and(mask, addr);
>>+      __atomic64_and(mask, (long long *)addr);
>> }
>>
>>static inline void change_bit(unsigned long nr, volatile unsigned long
>>*ptr)
>>@@ -122,7 +122,7 @@ static inline void change_bit(unsigned long nr,
>>volatile unsigned long *ptr)
>>       }
>> #endif
>>       mask = 1UL << (nr & (BITS_PER_LONG - 1));
>>-      __atomic64_xor(mask, addr);
>>+      __atomic64_xor(mask, (long long *)addr);
>> }
>>
>> static inline int
>>@@ -132,7 +132,7 @@ test_and_set_bit(unsigned long nr, volatile
>>unsigned long *ptr)
>>       unsigned long old, mask;
>>
>>       mask = 1UL << (nr & (BITS_PER_LONG - 1));
>>-      old = __atomic64_or_barrier(mask, addr);
>>+      old = __atomic64_or_barrier(mask, (long long *)addr);
>>       return (old & mask) != 0;
>> }
>>
>>@@ -143,7 +143,7 @@ test_and_clear_bit(unsigned long nr, volatile
>>unsigned long *ptr)
>>       unsigned long old, mask;
>>
>>       mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
>>-      old = __atomic64_and_barrier(mask, addr);
>>+      old = __atomic64_and_barrier(mask, (long long *)addr);
>>       return (old & ~mask) != 0;
>> }
>>
>>@@ -154,7 +154,7 @@ test_and_change_bit(unsigned long nr, volatile
>>unsigned long *ptr)
>>       unsigned long old, mask;
>>
>>       mask = 1UL << (nr & (BITS_PER_LONG - 1));
>>-      old = __atomic64_xor_barrier(mask, addr);
>>+      old = __atomic64_xor_barrier(mask, (long long *)addr);
>>       return (old & mask) != 0;
>> }
>>
>>diff --git a/arch/x86/include/asm/atomic64_64.h
>>b/arch/x86/include/asm/atomic64_64.h
>>index 8db8879a6d8c..8555cd19a916 100644
>>--- a/arch/x86/include/asm/atomic64_64.h
>>+++ b/arch/x86/include/asm/atomic64_64.h
>>@@ -16,7 +16,7 @@
>>  * Atomically reads the value of @v.
>>  * Doesn't imply a read memory barrier.
>>  */
>>-static inline long atomic64_read(const atomic64_t *v)
>>+static inline long long atomic64_read(const atomic64_t *v)
>> {
>>       return READ_ONCE((v)->counter);
>> }
>>@@ -28,7 +28,7 @@ static inline long atomic64_read(const atomic64_t *v)
>>  *
>>  * Atomically sets the value of @v to @i.
>>  */
>>-static inline void atomic64_set(atomic64_t *v, long i)
>>+static inline void atomic64_set(atomic64_t *v, long long i)
>> {
>>       WRITE_ONCE(v->counter, i);
>> }
>>@@ -40,7 +40,7 @@ static inline void atomic64_set(atomic64_t *v, long
>>i)
>>  *
>>  * Atomically adds @i to @v.
>>  */
>>-static __always_inline void atomic64_add(long i, atomic64_t *v)
>>+static __always_inline void atomic64_add(long long i, atomic64_t *v)
>> {
>>       asm volatile(LOCK_PREFIX "addq %1,%0"
>>                    : "=m" (v->counter)
>>@@ -54,7 +54,7 @@ static __always_inline void atomic64_add(long i,
>>atomic64_t *v)
>>  *
>>  * Atomically subtracts @i from @v.
>>  */
>>-static inline void atomic64_sub(long i, atomic64_t *v)
>>+static inline void atomic64_sub(long long i, atomic64_t *v)
>> {
>>       asm volatile(LOCK_PREFIX "subq %1,%0"
>>                    : "=m" (v->counter)
>>@@ -70,7 +70,7 @@ static inline void atomic64_sub(long i, atomic64_t
>>*v)
>>  * true if the result is zero, or false for all
>>  * other cases.
>>  */
>>-static inline bool atomic64_sub_and_test(long i, atomic64_t *v)
>>+static inline bool atomic64_sub_and_test(long long i, atomic64_t *v)
>> {
>>       GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e);
>> }
>>@@ -136,7 +136,7 @@ static inline bool atomic64_inc_and_test(atomic64_t
>>*v)
>>  * if the result is negative, or false when
>>  * result is greater than or equal to zero.
>>  */
>>-static inline bool atomic64_add_negative(long i, atomic64_t *v)
>>+static inline bool atomic64_add_negative(long long i, atomic64_t *v)
>> {
>>       GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s);
>> }
>>@@ -148,22 +148,22 @@ static inline bool atomic64_add_negative(long i,
>>atomic64_t *v)
>>  *
>>  * Atomically adds @i to @v and returns @i + @v
>>  */
>>-static __always_inline long atomic64_add_return(long i, atomic64_t *v)
>>+static __always_inline long long atomic64_add_return(long long i,
>>atomic64_t *v)
>> {
>>       return i + xadd(&v->counter, i);
>> }
>>
>>-static inline long atomic64_sub_return(long i, atomic64_t *v)
>>+static inline long long atomic64_sub_return(long long i, atomic64_t
>>*v)
>> {
>>       return atomic64_add_return(-i, v);
>> }
>>
>>-static inline long atomic64_fetch_add(long i, atomic64_t *v)
>>+static inline long long atomic64_fetch_add(long long i, atomic64_t *v)
>> {
>>       return xadd(&v->counter, i);
>> }
>>
>>-static inline long atomic64_fetch_sub(long i, atomic64_t *v)
>>+static inline long long atomic64_fetch_sub(long long i, atomic64_t *v)
>> {
>>       return xadd(&v->counter, -i);
>> }
>>@@ -171,18 +171,18 @@ static inline long atomic64_fetch_sub(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)))
>>
>>-static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new)
>>+static inline long long atomic64_cmpxchg(atomic64_t *v, long long old,
>>long long new)
>> {
>>       return cmpxchg(&v->counter, old, 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, long
>>long *old, long long new)
>> {
>>       return try_cmpxchg(&v->counter, old, new);
>> }
>>
>>-static inline long atomic64_xchg(atomic64_t *v, long new)
>>+static inline long long atomic64_xchg(atomic64_t *v, long long new)
>> {
>>       return xchg(&v->counter, new);
>> }
>>@@ -196,9 +196,9 @@ static inline long atomic64_xchg(atomic64_t *v,
>>long new)
>>  * Atomically adds @a to @v, so long as it was not @u.
>>  * Returns the old value of @v.
>>  */
>>-static inline bool atomic64_add_unless(atomic64_t *v, long a, long u)
>>+static inline bool atomic64_add_unless(atomic64_t *v, long long a,
>>long long u)
>> {
>>-      long c = atomic64_read(v);
>>+      long long c = atomic64_read(v);
>>       do {
>>               if (unlikely(c == u))
>>                       return false;
>>@@ -215,9 +215,9 @@ static inline bool atomic64_add_unless(atomic64_t
>>*v, long a, long u)
>>  * The function returns the old value of *v minus 1, even if
>>  * the atomic variable, v, was not decremented.
>>  */
>>-static inline long atomic64_dec_if_positive(atomic64_t *v)
>>+static inline long long atomic64_dec_if_positive(atomic64_t *v)
>> {
>>-      long dec, c = atomic64_read(v);
>>+      long long dec, c = atomic64_read(v);
>>       do {
>>               dec = c - 1;
>>               if (unlikely(dec < 0))
>>@@ -226,7 +226,7 @@ static inline long
>>atomic64_dec_if_positive(atomic64_t *v)
>>       return dec;
>> }
>>
>>-static inline void atomic64_and(long i, atomic64_t *v)
>>+static inline void atomic64_and(long long i, atomic64_t *v)
>> {
>>       asm volatile(LOCK_PREFIX "andq %1,%0"
>>                       : "+m" (v->counter)
>>@@ -234,16 +234,16 @@ static inline void atomic64_and(long i,
>>atomic64_t *v)
>>                       : "memory");
>> }
>>
>>-static inline long atomic64_fetch_and(long i, atomic64_t *v)
>>+static inline long long atomic64_fetch_and(long long i, atomic64_t *v)
>> {
>>-      long val = atomic64_read(v);
>>+      long long val = atomic64_read(v);
>>
>>       do {
>>       } while (!atomic64_try_cmpxchg(v, &val, val & i));
>>       return val;
>> }
>>
>>-static inline void atomic64_or(long i, atomic64_t *v)
>>+static inline void atomic64_or(long long i, atomic64_t *v)
>> {
>>       asm volatile(LOCK_PREFIX "orq %1,%0"
>>                       : "+m" (v->counter)
>>@@ -251,16 +251,16 @@ static inline void atomic64_or(long i, atomic64_t
>>*v)
>>                       : "memory");
>> }
>>
>>-static inline long atomic64_fetch_or(long i, atomic64_t *v)
>>+static inline long long atomic64_fetch_or(long long i, atomic64_t *v)
>> {
>>-      long val = atomic64_read(v);
>>+      long long val = atomic64_read(v);
>>
>>       do {
>>       } while (!atomic64_try_cmpxchg(v, &val, val | i));
>>       return val;
>> }
>>
>>-static inline void atomic64_xor(long i, atomic64_t *v)
>>+static inline void atomic64_xor(long long i, atomic64_t *v)
>> {
>>       asm volatile(LOCK_PREFIX "xorq %1,%0"
>>                       : "+m" (v->counter)
>>@@ -268,9 +268,9 @@ static inline void atomic64_xor(long i, atomic64_t
>>*v)
>>                       : "memory");
>> }
>>
>>-static inline long atomic64_fetch_xor(long i, atomic64_t *v)
>>+static inline long long atomic64_fetch_xor(long long i, atomic64_t *v)
>> {
>>-      long val = atomic64_read(v);
>>+      long long val = atomic64_read(v);
>>
>>       do {
>>       } while (!atomic64_try_cmpxchg(v, &val, val ^ i));
>>diff --git a/include/linux/types.h b/include/linux/types.h
>>index 1e7bd24848fc..569fc6db1bd5 100644
>>--- a/include/linux/types.h
>>+++ b/include/linux/types.h
>>@@ -177,7 +177,7 @@ typedef struct {
>>
>> #ifdef CONFIG_64BIT
>> typedef struct {
>>-      long counter;
>>+      long long counter;
>> } atomic64_t;
>> #endif
>>
>
> NAK - this is what u64/s64 is for.


Hi,

Patch 3 adds atomic-instrumented.h which now contains:

+static __always_inline long long atomic64_read(const atomic64_t *v)
+{
+       return arch_atomic64_read(v);
+}

without this patch that will become

+static __always_inline s64 atomic64_read(const atomic64_t *v)

Right?

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH v2 2/7] x86: use long long for 64-bit atomic ops

[hpa]

On May 28, 2017 2:29:32 AM PDT, Dmitry Vyukov <dvyukov@google.com> wrote:
>On Sun, May 28, 2017 at 1:02 AM,  <hpa@zytor.com> wrote:
>> On May 26, 2017 12:09:04 PM PDT, Dmitry Vyukov <dvyukov@google.com>
>wrote:
>>>Some 64-bit atomic operations use 'long long' as operand/return type
>>>(e.g. asm-generic/atomic64.h, arch/x86/include/asm/atomic64_32.h);
>>>while others use 'long' (e.g. arch/x86/include/asm/atomic64_64.h).
>>>This makes it impossible to write portable code.
>>>For example, there is no format specifier that prints result of
>>>atomic64_read() without warnings. atomic64_try_cmpxchg() is almost
>>>impossible to use in portable fashion because it requires either
>>>'long *' or 'long long *' as argument depending on arch.
>>>
>>>Switch arch/x86/include/asm/atomic64_64.h to 'long long'.
>>>
>>>Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
>>>Cc: Mark Rutland <mark.rutland@arm.com>
>>>Cc: Peter Zijlstra <peterz@infradead.org>
>>>Cc: Will Deacon <will.deacon@arm.com>
>>>Cc: Andrew Morton <akpm@linux-foundation.org>
>>>Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
>>>Cc: Ingo Molnar <mingo@redhat.com>
>>>Cc: kasan-dev@googlegroups.com
>>>Cc: linux-mm@kvack.org
>>>Cc: linux-kernel@vger.kernel.org
>>>Cc: x86@kernel.org
>>>
>>>---
>>>Changes since v1:
>>> - reverted stray s/long/long long/ replace in comment
>>> - added arch/s390 changes to fix build errors/warnings
>>>---
>>> arch/s390/include/asm/atomic_ops.h | 14 +++++-----
>>> arch/s390/include/asm/bitops.h     | 12 ++++-----
>>>arch/x86/include/asm/atomic64_64.h | 52
>>>+++++++++++++++++++-------------------
>>> include/linux/types.h              |  2 +-
>>> 4 files changed, 40 insertions(+), 40 deletions(-)
>>>
>>>diff --git a/arch/s390/include/asm/atomic_ops.h
>>>b/arch/s390/include/asm/atomic_ops.h
>>>index ac9e2b939d04..055a9083e52d 100644
>>>--- a/arch/s390/include/asm/atomic_ops.h
>>>+++ b/arch/s390/include/asm/atomic_ops.h
>>>@@ -31,10 +31,10 @@ __ATOMIC_OPS(__atomic_and, int, "lan")
>>> __ATOMIC_OPS(__atomic_or,  int, "lao")
>>> __ATOMIC_OPS(__atomic_xor, int, "lax")
>>>
>>>-__ATOMIC_OPS(__atomic64_add, long, "laag")
>>>-__ATOMIC_OPS(__atomic64_and, long, "lang")
>>>-__ATOMIC_OPS(__atomic64_or,  long, "laog")
>>>-__ATOMIC_OPS(__atomic64_xor, long, "laxg")
>>>+__ATOMIC_OPS(__atomic64_add, long long, "laag")
>>>+__ATOMIC_OPS(__atomic64_and, long long, "lang")
>>>+__ATOMIC_OPS(__atomic64_or,  long long, "laog")
>>>+__ATOMIC_OPS(__atomic64_xor, long long, "laxg")
>>>
>>> #undef __ATOMIC_OPS
>>> #undef __ATOMIC_OP
>>>@@ -46,7 +46,7 @@ static inline void __atomic_add_const(int val, int
>>>*ptr)
>>>               : [ptr] "+Q" (*ptr) : [val] "i" (val) : "cc");
>>> }
>>>
>>>-static inline void __atomic64_add_const(long val, long *ptr)
>>>+static inline void __atomic64_add_const(long val, long long *ptr)
>>> {
>>>       asm volatile(
>>>               "       agsi    %[ptr],%[val]\n"
>>>@@ -82,7 +82,7 @@ __ATOMIC_OPS(__atomic_xor, "xr")
>>> #undef __ATOMIC_OPS
>>>
>>> #define __ATOMIC64_OP(op_name, op_string)                           
> \
>>>-static inline long op_name(long val, long *ptr)                     
>         \
>>>+static inline long op_name(long val, long long *ptr)                
> \
>>> {                                                                   
> \
>>>       long old, new;                                                
> \
>>>                                                                     
> \
>>>@@ -118,7 +118,7 @@ static inline int __atomic_cmpxchg(int *ptr, int
>>>old, int new)
>>>       return old;
>>> }
>>>
>>>-static inline long __atomic64_cmpxchg(long *ptr, long old, long new)
>>>+static inline long __atomic64_cmpxchg(long long *ptr, long old, long
>>>new)
>>> {
>>>       asm volatile(
>>>               "       csg     %[old],%[new],%[ptr]"
>>>diff --git a/arch/s390/include/asm/bitops.h
>>>b/arch/s390/include/asm/bitops.h
>>>index d92047da5ccb..8912f52bca5d 100644
>>>--- a/arch/s390/include/asm/bitops.h
>>>+++ b/arch/s390/include/asm/bitops.h
>>>@@ -80,7 +80,7 @@ static inline void set_bit(unsigned long nr,
>volatile
>>>unsigned long *ptr)
>>>       }
>>> #endif
>>>       mask = 1UL << (nr & (BITS_PER_LONG - 1));
>>>-      __atomic64_or(mask, addr);
>>>+      __atomic64_or(mask, (long long *)addr);
>>> }
>>>
>>>static inline void clear_bit(unsigned long nr, volatile unsigned long
>>>*ptr)
>>>@@ -101,7 +101,7 @@ static inline void clear_bit(unsigned long nr,
>>>volatile unsigned long *ptr)
>>>       }
>>> #endif
>>>       mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
>>>-      __atomic64_and(mask, addr);
>>>+      __atomic64_and(mask, (long long *)addr);
>>> }
>>>
>>>static inline void change_bit(unsigned long nr, volatile unsigned
>long
>>>*ptr)
>>>@@ -122,7 +122,7 @@ static inline void change_bit(unsigned long nr,
>>>volatile unsigned long *ptr)
>>>       }
>>> #endif
>>>       mask = 1UL << (nr & (BITS_PER_LONG - 1));
>>>-      __atomic64_xor(mask, addr);
>>>+      __atomic64_xor(mask, (long long *)addr);
>>> }
>>>
>>> static inline int
>>>@@ -132,7 +132,7 @@ test_and_set_bit(unsigned long nr, volatile
>>>unsigned long *ptr)
>>>       unsigned long old, mask;
>>>
>>>       mask = 1UL << (nr & (BITS_PER_LONG - 1));
>>>-      old = __atomic64_or_barrier(mask, addr);
>>>+      old = __atomic64_or_barrier(mask, (long long *)addr);
>>>       return (old & mask) != 0;
>>> }
>>>
>>>@@ -143,7 +143,7 @@ test_and_clear_bit(unsigned long nr, volatile
>>>unsigned long *ptr)
>>>       unsigned long old, mask;
>>>
>>>       mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
>>>-      old = __atomic64_and_barrier(mask, addr);
>>>+      old = __atomic64_and_barrier(mask, (long long *)addr);
>>>       return (old & ~mask) != 0;
>>> }
>>>
>>>@@ -154,7 +154,7 @@ test_and_change_bit(unsigned long nr, volatile
>>>unsigned long *ptr)
>>>       unsigned long old, mask;
>>>
>>>       mask = 1UL << (nr & (BITS_PER_LONG - 1));
>>>-      old = __atomic64_xor_barrier(mask, addr);
>>>+      old = __atomic64_xor_barrier(mask, (long long *)addr);
>>>       return (old & mask) != 0;
>>> }
>>>
>>>diff --git a/arch/x86/include/asm/atomic64_64.h
>>>b/arch/x86/include/asm/atomic64_64.h
>>>index 8db8879a6d8c..8555cd19a916 100644
>>>--- a/arch/x86/include/asm/atomic64_64.h
>>>+++ b/arch/x86/include/asm/atomic64_64.h
>>>@@ -16,7 +16,7 @@
>>>  * Atomically reads the value of @v.
>>>  * Doesn't imply a read memory barrier.
>>>  */
>>>-static inline long atomic64_read(const atomic64_t *v)
>>>+static inline long long atomic64_read(const atomic64_t *v)
>>> {
>>>       return READ_ONCE((v)->counter);
>>> }
>>>@@ -28,7 +28,7 @@ static inline long atomic64_read(const atomic64_t
>*v)
>>>  *
>>>  * Atomically sets the value of @v to @i.
>>>  */
>>>-static inline void atomic64_set(atomic64_t *v, long i)
>>>+static inline void atomic64_set(atomic64_t *v, long long i)
>>> {
>>>       WRITE_ONCE(v->counter, i);
>>> }
>>>@@ -40,7 +40,7 @@ static inline void atomic64_set(atomic64_t *v, long
>>>i)
>>>  *
>>>  * Atomically adds @i to @v.
>>>  */
>>>-static __always_inline void atomic64_add(long i, atomic64_t *v)
>>>+static __always_inline void atomic64_add(long long i, atomic64_t *v)
>>> {
>>>       asm volatile(LOCK_PREFIX "addq %1,%0"
>>>                    : "=m" (v->counter)
>>>@@ -54,7 +54,7 @@ static __always_inline void atomic64_add(long i,
>>>atomic64_t *v)
>>>  *
>>>  * Atomically subtracts @i from @v.
>>>  */
>>>-static inline void atomic64_sub(long i, atomic64_t *v)
>>>+static inline void atomic64_sub(long long i, atomic64_t *v)
>>> {
>>>       asm volatile(LOCK_PREFIX "subq %1,%0"
>>>                    : "=m" (v->counter)
>>>@@ -70,7 +70,7 @@ static inline void atomic64_sub(long i, atomic64_t
>>>*v)
>>>  * true if the result is zero, or false for all
>>>  * other cases.
>>>  */
>>>-static inline bool atomic64_sub_and_test(long i, atomic64_t *v)
>>>+static inline bool atomic64_sub_and_test(long long i, atomic64_t *v)
>>> {
>>>       GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i,
>"%0", e);
>>> }
>>>@@ -136,7 +136,7 @@ static inline bool
>atomic64_inc_and_test(atomic64_t
>>>*v)
>>>  * if the result is negative, or false when
>>>  * result is greater than or equal to zero.
>>>  */
>>>-static inline bool atomic64_add_negative(long i, atomic64_t *v)
>>>+static inline bool atomic64_add_negative(long long i, atomic64_t *v)
>>> {
>>>       GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i,
>"%0", s);
>>> }
>>>@@ -148,22 +148,22 @@ static inline bool atomic64_add_negative(long
>i,
>>>atomic64_t *v)
>>>  *
>>>  * Atomically adds @i to @v and returns @i + @v
>>>  */
>>>-static __always_inline long atomic64_add_return(long i, atomic64_t
>*v)
>>>+static __always_inline long long atomic64_add_return(long long i,
>>>atomic64_t *v)
>>> {
>>>       return i + xadd(&v->counter, i);
>>> }
>>>
>>>-static inline long atomic64_sub_return(long i, atomic64_t *v)
>>>+static inline long long atomic64_sub_return(long long i, atomic64_t
>>>*v)
>>> {
>>>       return atomic64_add_return(-i, v);
>>> }
>>>
>>>-static inline long atomic64_fetch_add(long i, atomic64_t *v)
>>>+static inline long long atomic64_fetch_add(long long i, atomic64_t
>*v)
>>> {
>>>       return xadd(&v->counter, i);
>>> }
>>>
>>>-static inline long atomic64_fetch_sub(long i, atomic64_t *v)
>>>+static inline long long atomic64_fetch_sub(long long i, atomic64_t
>*v)
>>> {
>>>       return xadd(&v->counter, -i);
>>> }
>>>@@ -171,18 +171,18 @@ static inline long atomic64_fetch_sub(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)))
>>>
>>>-static inline long atomic64_cmpxchg(atomic64_t *v, long old, long
>new)
>>>+static inline long long atomic64_cmpxchg(atomic64_t *v, long long
>old,
>>>long long new)
>>> {
>>>       return cmpxchg(&v->counter, old, 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, long
>>>long *old, long long new)
>>> {
>>>       return try_cmpxchg(&v->counter, old, new);
>>> }
>>>
>>>-static inline long atomic64_xchg(atomic64_t *v, long new)
>>>+static inline long long atomic64_xchg(atomic64_t *v, long long new)
>>> {
>>>       return xchg(&v->counter, new);
>>> }
>>>@@ -196,9 +196,9 @@ static inline long atomic64_xchg(atomic64_t *v,
>>>long new)
>>>  * Atomically adds @a to @v, so long as it was not @u.
>>>  * Returns the old value of @v.
>>>  */
>>>-static inline bool atomic64_add_unless(atomic64_t *v, long a, long
>u)
>>>+static inline bool atomic64_add_unless(atomic64_t *v, long long a,
>>>long long u)
>>> {
>>>-      long c = atomic64_read(v);
>>>+      long long c = atomic64_read(v);
>>>       do {
>>>               if (unlikely(c == u))
>>>                       return false;
>>>@@ -215,9 +215,9 @@ static inline bool atomic64_add_unless(atomic64_t
>>>*v, long a, long u)
>>>  * The function returns the old value of *v minus 1, even if
>>>  * the atomic variable, v, was not decremented.
>>>  */
>>>-static inline long atomic64_dec_if_positive(atomic64_t *v)
>>>+static inline long long atomic64_dec_if_positive(atomic64_t *v)
>>> {
>>>-      long dec, c = atomic64_read(v);
>>>+      long long dec, c = atomic64_read(v);
>>>       do {
>>>               dec = c - 1;
>>>               if (unlikely(dec < 0))
>>>@@ -226,7 +226,7 @@ static inline long
>>>atomic64_dec_if_positive(atomic64_t *v)
>>>       return dec;
>>> }
>>>
>>>-static inline void atomic64_and(long i, atomic64_t *v)
>>>+static inline void atomic64_and(long long i, atomic64_t *v)
>>> {
>>>       asm volatile(LOCK_PREFIX "andq %1,%0"
>>>                       : "+m" (v->counter)
>>>@@ -234,16 +234,16 @@ static inline void atomic64_and(long i,
>>>atomic64_t *v)
>>>                       : "memory");
>>> }
>>>
>>>-static inline long atomic64_fetch_and(long i, atomic64_t *v)
>>>+static inline long long atomic64_fetch_and(long long i, atomic64_t
>*v)
>>> {
>>>-      long val = atomic64_read(v);
>>>+      long long val = atomic64_read(v);
>>>
>>>       do {
>>>       } while (!atomic64_try_cmpxchg(v, &val, val & i));
>>>       return val;
>>> }
>>>
>>>-static inline void atomic64_or(long i, atomic64_t *v)
>>>+static inline void atomic64_or(long long i, atomic64_t *v)
>>> {
>>>       asm volatile(LOCK_PREFIX "orq %1,%0"
>>>                       : "+m" (v->counter)
>>>@@ -251,16 +251,16 @@ static inline void atomic64_or(long i,
>atomic64_t
>>>*v)
>>>                       : "memory");
>>> }
>>>
>>>-static inline long atomic64_fetch_or(long i, atomic64_t *v)
>>>+static inline long long atomic64_fetch_or(long long i, atomic64_t
>*v)
>>> {
>>>-      long val = atomic64_read(v);
>>>+      long long val = atomic64_read(v);
>>>
>>>       do {
>>>       } while (!atomic64_try_cmpxchg(v, &val, val | i));
>>>       return val;
>>> }
>>>
>>>-static inline void atomic64_xor(long i, atomic64_t *v)
>>>+static inline void atomic64_xor(long long i, atomic64_t *v)
>>> {
>>>       asm volatile(LOCK_PREFIX "xorq %1,%0"
>>>                       : "+m" (v->counter)
>>>@@ -268,9 +268,9 @@ static inline void atomic64_xor(long i,
>atomic64_t
>>>*v)
>>>                       : "memory");
>>> }
>>>
>>>-static inline long atomic64_fetch_xor(long i, atomic64_t *v)
>>>+static inline long long atomic64_fetch_xor(long long i, atomic64_t
>*v)
>>> {
>>>-      long val = atomic64_read(v);
>>>+      long long val = atomic64_read(v);
>>>
>>>       do {
>>>       } while (!atomic64_try_cmpxchg(v, &val, val ^ i));
>>>diff --git a/include/linux/types.h b/include/linux/types.h
>>>index 1e7bd24848fc..569fc6db1bd5 100644
>>>--- a/include/linux/types.h
>>>+++ b/include/linux/types.h
>>>@@ -177,7 +177,7 @@ typedef struct {
>>>
>>> #ifdef CONFIG_64BIT
>>> typedef struct {
>>>-      long counter;
>>>+      long long counter;
>>> } atomic64_t;
>>> #endif
>>>
>>
>> NAK - this is what u64/s64 is for.
>
>
>Hi,
>
>Patch 3 adds atomic-instrumented.h which now contains:
>
>+static __always_inline long long atomic64_read(const atomic64_t *v)
>+{
>+       return arch_atomic64_read(v);
>+}
>
>without this patch that will become
>
>+static __always_inline s64 atomic64_read(const atomic64_t *v)
>
>Right?

Yes.
-- 
Sent from my Android device with K-9 Mail. Please excuse my brevity.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH v2 2/7] x86: use long long for 64-bit atomic ops

[Dmitry Vyukov]

On Sun, May 28, 2017 at 11:34 AM,  <hpa@zytor.com> wrote:
> On May 28, 2017 2:29:32 AM PDT, Dmitry Vyukov <dvyukov@google.com> wrote:
>>On Sun, May 28, 2017 at 1:02 AM,  <hpa@zytor.com> wrote:
>>> On May 26, 2017 12:09:04 PM PDT, Dmitry Vyukov <dvyukov@google.com>
>>wrote:
>>>>Some 64-bit atomic operations use 'long long' as operand/return type
>>>>(e.g. asm-generic/atomic64.h, arch/x86/include/asm/atomic64_32.h);
>>>>while others use 'long' (e.g. arch/x86/include/asm/atomic64_64.h).
>>>>This makes it impossible to write portable code.
>>>>For example, there is no format specifier that prints result of
>>>>atomic64_read() without warnings. atomic64_try_cmpxchg() is almost
>>>>impossible to use in portable fashion because it requires either
>>>>'long *' or 'long long *' as argument depending on arch.
>>>>
>>>>Switch arch/x86/include/asm/atomic64_64.h to 'long long'.
>>>>
>>>>Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
>>>>Cc: Mark Rutland <mark.rutland@arm.com>
>>>>Cc: Peter Zijlstra <peterz@infradead.org>
>>>>Cc: Will Deacon <will.deacon@arm.com>
>>>>Cc: Andrew Morton <akpm@linux-foundation.org>
>>>>Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
>>>>Cc: Ingo Molnar <mingo@redhat.com>
>>>>Cc: kasan-dev@googlegroups.com
>>>>Cc: linux-mm@kvack.org
>>>>Cc: linux-kernel@vger.kernel.org
>>>>Cc: x86@kernel.org
>>>>
>>>>---
>>>>Changes since v1:
>>>> - reverted stray s/long/long long/ replace in comment
>>>> - added arch/s390 changes to fix build errors/warnings
>>>>---

[snip]

>>> NAK - this is what u64/s64 is for.
>>
>>
>>Hi,
>>
>>Patch 3 adds atomic-instrumented.h which now contains:
>>
>>+static __always_inline long long atomic64_read(const atomic64_t *v)
>>+{
>>+       return arch_atomic64_read(v);
>>+}
>>
>>without this patch that will become
>>
>>+static __always_inline s64 atomic64_read(const atomic64_t *v)
>>
>>Right?
>
> Yes.


I see that s64 is not the same as long on x86_64 (long long vs long),
so it's still not possible to e.g. portably print a result of
atomic_read(). But it's a separate issue that we don't need to solve
now.

Also all wrappers like:

void atomic64_set(atomic64_t *v, s64 i)
{
    arch_atomic64_set(v, i);
}

lead to type conversions, but at least my compiler does not bark on it.

The only remaining problem is with atomic64_try_cmpxchg, which is
simply not possible to use now (not possible to declare the *old
type).
I will need something along the following lines to fix it (then
callers can use s64* for old).
Sounds good?


--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -177,7 +177,7 @@ static inline long
arch_atomic64_cmpxchg(atomic64_t *v, long old, long new)
 }

 #define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg
-static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v,
long *old, long new)
+static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v,
s64 *old, long new)
 {
        return try_cmpxchg(&v->counter, old, new);
 }
@@ -198,7 +198,7 @@ static inline long arch_atomic64_xchg(atomic64_t
*v, long new)
  */
 static inline bool arch_atomic64_add_unless(atomic64_t *v, long a, long u)
 {
-       long c = arch_atomic64_read(v);
+       s64 c = arch_atomic64_read(v);
        do {
                if (unlikely(c == u))
                        return false;
@@ -217,7 +217,7 @@ static inline bool
arch_atomic64_add_unless(atomic64_t *v, long a, long u)
  */
 static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
 {
-       long dec, c = arch_atomic64_read(v);
+       s64 dec, c = arch_atomic64_read(v);
        do {
                dec = c - 1;
                if (unlikely(dec < 0))
@@ -236,7 +236,7 @@ static inline void arch_atomic64_and(long i, atomic64_t *v)

 static inline long arch_atomic64_fetch_and(long i, atomic64_t *v)
 {
-       long val = arch_atomic64_read(v);
+       s64 val = arch_atomic64_read(v);

        do {
        } while (!arch_atomic64_try_cmpxchg(v, &val, val & i));
@@ -253,7 +253,7 @@ static inline void arch_atomic64_or(long i, atomic64_t *v)

 static inline long arch_atomic64_fetch_or(long i, atomic64_t *v)
 {
-       long val = arch_atomic64_read(v);
+       s64 val = arch_atomic64_read(v);

        do {
        } while (!arch_atomic64_try_cmpxchg(v, &val, val | i));
@@ -270,7 +270,7 @@ static inline void arch_atomic64_xor(long i, atomic64_t *v)

 static inline long arch_atomic64_fetch_xor(long i, atomic64_t *v)
 {
-       long val = arch_atomic64_read(v);
+       s64 val = arch_atomic64_read(v);

        do {
        } while (!arch_atomic64_try_cmpxchg(v, &val, val ^ i));
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index e8cf95908fe5..9e2faa85eb02 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -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) {                                                 \

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH v2 2/7] x86: use long long for 64-bit atomic ops

[Dmitry Vyukov]

On Mon, May 29, 2017 at 4:44 PM, Dmitry Vyukov <dvyukov@google.com> wrote:
> On Sun, May 28, 2017 at 11:34 AM,  <hpa@zytor.com> wrote:
>> On May 28, 2017 2:29:32 AM PDT, Dmitry Vyukov <dvyukov@google.com> wrote:
>>>On Sun, May 28, 2017 at 1:02 AM,  <hpa@zytor.com> wrote:
>>>> On May 26, 2017 12:09:04 PM PDT, Dmitry Vyukov <dvyukov@google.com>
>>>wrote:
>>>>>Some 64-bit atomic operations use 'long long' as operand/return type
>>>>>(e.g. asm-generic/atomic64.h, arch/x86/include/asm/atomic64_32.h);
>>>>>while others use 'long' (e.g. arch/x86/include/asm/atomic64_64.h).
>>>>>This makes it impossible to write portable code.
>>>>>For example, there is no format specifier that prints result of
>>>>>atomic64_read() without warnings. atomic64_try_cmpxchg() is almost
>>>>>impossible to use in portable fashion because it requires either
>>>>>'long *' or 'long long *' as argument depending on arch.
>>>>>
>>>>>Switch arch/x86/include/asm/atomic64_64.h to 'long long'.
>>>>>
>>>>>Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
>>>>>Cc: Mark Rutland <mark.rutland@arm.com>
>>>>>Cc: Peter Zijlstra <peterz@infradead.org>
>>>>>Cc: Will Deacon <will.deacon@arm.com>
>>>>>Cc: Andrew Morton <akpm@linux-foundation.org>
>>>>>Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
>>>>>Cc: Ingo Molnar <mingo@redhat.com>
>>>>>Cc: kasan-dev@googlegroups.com
>>>>>Cc: linux-mm@kvack.org
>>>>>Cc: linux-kernel@vger.kernel.org
>>>>>Cc: x86@kernel.org
>>>>>
>>>>>---
>>>>>Changes since v1:
>>>>> - reverted stray s/long/long long/ replace in comment
>>>>> - added arch/s390 changes to fix build errors/warnings
>>>>>---
>
> [snip]
>
>>>> NAK - this is what u64/s64 is for.

Mailed v3 with all requested changes.


>>>Hi,
>>>
>>>Patch 3 adds atomic-instrumented.h which now contains:
>>>
>>>+static __always_inline long long atomic64_read(const atomic64_t *v)
>>>+{
>>>+       return arch_atomic64_read(v);
>>>+}
>>>
>>>without this patch that will become
>>>
>>>+static __always_inline s64 atomic64_read(const atomic64_t *v)
>>>
>>>Right?
>>
>> Yes.
>
>
> I see that s64 is not the same as long on x86_64 (long long vs long),
> so it's still not possible to e.g. portably print a result of
> atomic_read(). But it's a separate issue that we don't need to solve
> now.
>
> Also all wrappers like:
>
> void atomic64_set(atomic64_t *v, s64 i)
> {
>     arch_atomic64_set(v, i);
> }
>
> lead to type conversions, but at least my compiler does not bark on it.
>
> The only remaining problem is with atomic64_try_cmpxchg, which is
> simply not possible to use now (not possible to declare the *old
> type).
> I will need something along the following lines to fix it (then
> callers can use s64* for old).
> Sounds good?
>
>
> --- a/arch/x86/include/asm/atomic64_64.h
> +++ b/arch/x86/include/asm/atomic64_64.h
> @@ -177,7 +177,7 @@ static inline long
> arch_atomic64_cmpxchg(atomic64_t *v, long old, long new)
>  }
>
>  #define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg
> -static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v,
> long *old, long new)
> +static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v,
> s64 *old, long new)
>  {
>         return try_cmpxchg(&v->counter, old, new);
>  }
> @@ -198,7 +198,7 @@ static inline long arch_atomic64_xchg(atomic64_t
> *v, long new)
>   */
>  static inline bool arch_atomic64_add_unless(atomic64_t *v, long a, long u)
>  {
> -       long c = arch_atomic64_read(v);
> +       s64 c = arch_atomic64_read(v);
>         do {
>                 if (unlikely(c == u))
>                         return false;
> @@ -217,7 +217,7 @@ static inline bool
> arch_atomic64_add_unless(atomic64_t *v, long a, long u)
>   */
>  static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
>  {
> -       long dec, c = arch_atomic64_read(v);
> +       s64 dec, c = arch_atomic64_read(v);
>         do {
>                 dec = c - 1;
>                 if (unlikely(dec < 0))
> @@ -236,7 +236,7 @@ static inline void arch_atomic64_and(long i, atomic64_t *v)
>
>  static inline long arch_atomic64_fetch_and(long i, atomic64_t *v)
>  {
> -       long val = arch_atomic64_read(v);
> +       s64 val = arch_atomic64_read(v);
>
>         do {
>         } while (!arch_atomic64_try_cmpxchg(v, &val, val & i));
> @@ -253,7 +253,7 @@ static inline void arch_atomic64_or(long i, atomic64_t *v)
>
>  static inline long arch_atomic64_fetch_or(long i, atomic64_t *v)
>  {
> -       long val = arch_atomic64_read(v);
> +       s64 val = arch_atomic64_read(v);
>
>         do {
>         } while (!arch_atomic64_try_cmpxchg(v, &val, val | i));
> @@ -270,7 +270,7 @@ static inline void arch_atomic64_xor(long i, atomic64_t *v)
>
>  static inline long arch_atomic64_fetch_xor(long i, atomic64_t *v)
>  {
> -       long val = arch_atomic64_read(v);
> +       s64 val = arch_atomic64_read(v);
>
>         do {
>         } while (!arch_atomic64_try_cmpxchg(v, &val, val ^ i));
> diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
> index e8cf95908fe5..9e2faa85eb02 100644
> --- a/arch/x86/include/asm/cmpxchg.h
> +++ b/arch/x86/include/asm/cmpxchg.h
> @@ -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) {                                                 \

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH v2 2/7] x86: use long long for 64-bit atomic ops

[Heiko Carstens]

On Fri, May 26, 2017 at 09:09:04PM +0200, Dmitry Vyukov wrote:
> Some 64-bit atomic operations use 'long long' as operand/return type
> (e.g. asm-generic/atomic64.h, arch/x86/include/asm/atomic64_32.h);
> while others use 'long' (e.g. arch/x86/include/asm/atomic64_64.h).
> This makes it impossible to write portable code.
> For example, there is no format specifier that prints result of
> atomic64_read() without warnings. atomic64_try_cmpxchg() is almost
> impossible to use in portable fashion because it requires either
> 'long *' or 'long long *' as argument depending on arch.
> 
> Switch arch/x86/include/asm/atomic64_64.h to 'long long'.
> 
> Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
> 
> ---
> Changes since v1:
>  - reverted stray s/long/long long/ replace in comment
>  - added arch/s390 changes to fix build errors/warnings

If you change s390 code, please add the relevant mailing list and/or
maintainers please.

> diff --git a/arch/s390/include/asm/atomic_ops.h b/arch/s390/include/asm/atomic_ops.h
> index ac9e2b939d04..055a9083e52d 100644
> --- a/arch/s390/include/asm/atomic_ops.h
> +++ b/arch/s390/include/asm/atomic_ops.h
> @@ -31,10 +31,10 @@ __ATOMIC_OPS(__atomic_and, int, "lan")
>  __ATOMIC_OPS(__atomic_or,  int, "lao")
>  __ATOMIC_OPS(__atomic_xor, int, "lax")
>  
> -__ATOMIC_OPS(__atomic64_add, long, "laag")
> -__ATOMIC_OPS(__atomic64_and, long, "lang")
> -__ATOMIC_OPS(__atomic64_or,  long, "laog")
> -__ATOMIC_OPS(__atomic64_xor, long, "laxg")
> +__ATOMIC_OPS(__atomic64_add, long long, "laag")
> +__ATOMIC_OPS(__atomic64_and, long long, "lang")
> +__ATOMIC_OPS(__atomic64_or,  long long, "laog")
> +__ATOMIC_OPS(__atomic64_xor, long long, "laxg")
>  
>  #undef __ATOMIC_OPS
>  #undef __ATOMIC_OP
> @@ -46,7 +46,7 @@ static inline void __atomic_add_const(int val, int *ptr)
>  		: [ptr] "+Q" (*ptr) : [val] "i" (val) : "cc");
>  }
>  
> -static inline void __atomic64_add_const(long val, long *ptr)
> +static inline void __atomic64_add_const(long val, long long *ptr)

If you change this then val should be long long (or s64) too.

> -static inline long op_name(long val, long *ptr)				\
> +static inline long op_name(long val, long long *ptr)			\
>  {									\
>  	long old, new;							\

Same here. You only changed the type of *ptr, but left the rest
alone. Everything should have the same type.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH v2 2/7] x86: use long long for 64-bit atomic ops

[Dmitry Vyukov]

On Mon, May 29, 2017 at 12:49 PM, Heiko Carstens
<heiko.carstens@de.ibm.com> wrote:
> On Fri, May 26, 2017 at 09:09:04PM +0200, Dmitry Vyukov wrote:
>> Some 64-bit atomic operations use 'long long' as operand/return type
>> (e.g. asm-generic/atomic64.h, arch/x86/include/asm/atomic64_32.h);
>> while others use 'long' (e.g. arch/x86/include/asm/atomic64_64.h).
>> This makes it impossible to write portable code.
>> For example, there is no format specifier that prints result of
>> atomic64_read() without warnings. atomic64_try_cmpxchg() is almost
>> impossible to use in portable fashion because it requires either
>> 'long *' or 'long long *' as argument depending on arch.
>>
>> Switch arch/x86/include/asm/atomic64_64.h to 'long long'.
>>
>> Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
>>
>> ---
>> Changes since v1:
>>  - reverted stray s/long/long long/ replace in comment
>>  - added arch/s390 changes to fix build errors/warnings
>
> If you change s390 code, please add the relevant mailing list and/or
> maintainers please.
>
>> diff --git a/arch/s390/include/asm/atomic_ops.h b/arch/s390/include/asm/atomic_ops.h
>> index ac9e2b939d04..055a9083e52d 100644
>> --- a/arch/s390/include/asm/atomic_ops.h
>> +++ b/arch/s390/include/asm/atomic_ops.h
>> @@ -31,10 +31,10 @@ __ATOMIC_OPS(__atomic_and, int, "lan")
>>  __ATOMIC_OPS(__atomic_or,  int, "lao")
>>  __ATOMIC_OPS(__atomic_xor, int, "lax")
>>
>> -__ATOMIC_OPS(__atomic64_add, long, "laag")
>> -__ATOMIC_OPS(__atomic64_and, long, "lang")
>> -__ATOMIC_OPS(__atomic64_or,  long, "laog")
>> -__ATOMIC_OPS(__atomic64_xor, long, "laxg")
>> +__ATOMIC_OPS(__atomic64_add, long long, "laag")
>> +__ATOMIC_OPS(__atomic64_and, long long, "lang")
>> +__ATOMIC_OPS(__atomic64_or,  long long, "laog")
>> +__ATOMIC_OPS(__atomic64_xor, long long, "laxg")
>>
>>  #undef __ATOMIC_OPS
>>  #undef __ATOMIC_OP
>> @@ -46,7 +46,7 @@ static inline void __atomic_add_const(int val, int *ptr)
>>               : [ptr] "+Q" (*ptr) : [val] "i" (val) : "cc");
>>  }
>>
>> -static inline void __atomic64_add_const(long val, long *ptr)
>> +static inline void __atomic64_add_const(long val, long long *ptr)
>
> If you change this then val should be long long (or s64) too.
>
>> -static inline long op_name(long val, long *ptr)                              \
>> +static inline long op_name(long val, long long *ptr)                 \
>>  {                                                                    \
>>       long old, new;                                                  \
>
> Same here. You only changed the type of *ptr, but left the rest
> alone. Everything should have the same type.

I will try to follow hpa's suggestion in the next version of the
patch. If it work out, I will not need to touch s390 code.

Still thanks for the review.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH v2 3/7] asm-generic: add atomic-instrumented.h

[Dmitry Vyukov]

The new header allows to wrap per-arch atomic operations
and add common functionality to all of them.

Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: kasan-dev@googlegroups.com
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
Cc: x86@kernel.org
---
 include/asm-generic/atomic-instrumented.h | 319 ++++++++++++++++++++++++++++++
 1 file changed, 319 insertions(+)

diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h
new file mode 100644
index 000000000000..fd483115d4c6
--- /dev/null
+++ b/include/asm-generic/atomic-instrumented.h
@@ -0,0 +1,319 @@
+#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 long long 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, long long 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 long long atomic64_xchg(atomic64_t *v, long long 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 long long atomic64_cmpxchg(atomic64_t *v, long long old,
+						  long long 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, long long *old,
+						 long long 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, long long a,
+						long long 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(long long 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(long long 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(long long 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(long long 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(long long 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 long long 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 long long atomic64_dec_return(atomic64_t *v)
+{
+	return arch_atomic64_dec_return(v);
+}
+
+static __always_inline long long atomic64_inc_not_zero(atomic64_t *v)
+{
+	return arch_atomic64_inc_not_zero(v);
+}
+
+static __always_inline long long 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 long long atomic64_add_return(long long 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 long long atomic64_sub_return(long long 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 long long atomic64_fetch_add(long long 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 long long atomic64_fetch_sub(long long 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 long long atomic64_fetch_and(long long 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 long long atomic64_fetch_or(long long 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 long long atomic64_fetch_xor(long long 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(long long 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(long long 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 */
-- 
2.13.0.219.gdb65acc882-goog

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH v2 4/7] x86: switch atomic.h to use atomic-instrumented.h

[Dmitry Vyukov]

Add arch_ prefix to all atomic operations and include
<asm-generic/atomic-instrumented.h>. This will allow
to add KASAN instrumentation to all atomic ops.

Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: kasan-dev@googlegroups.com
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
Cc: x86@kernel.org

---
Changes since v1:
 - reverted unnecessary change in __raw_try_cmpxchg()
 - reverted s/try_cmpxchg/arch_try_cmpxchg/ change
   try_cmpxchg is x86 implementation detail
---
 arch/x86/include/asm/atomic.h      | 108 ++++++++++++++++++++-----------------
 arch/x86/include/asm/atomic64_32.h | 106 ++++++++++++++++++------------------
 arch/x86/include/asm/atomic64_64.h | 108 ++++++++++++++++++-------------------
 arch/x86/include/asm/cmpxchg.h     |  12 ++---
 arch/x86/include/asm/cmpxchg_32.h  |   8 +--
 arch/x86/include/asm/cmpxchg_64.h  |   4 +-
 6 files changed, 178 insertions(+), 168 deletions(-)

diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 1a4a6a99dcd8..b7900346c77e 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -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 */
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index f107fef7bfcc..8501e4fc5054 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -61,7 +61,7 @@ ATOMIC64_DECL(add_unless);
 #undef ATOMIC64_EXPORT
 
 /**
- * atomic64_cmpxchg - cmpxchg atomic64 variable
+ * arch_atomic64_cmpxchg - cmpxchg atomic64 variable
  * @v: pointer to type atomic64_t
  * @o: expected value
  * @n: new value
@@ -70,20 +70,21 @@ ATOMIC64_DECL(add_unless);
  * the old value.
  */
 
-static inline long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n)
+static inline long long arch_atomic64_cmpxchg(atomic64_t *v, long long o,
+					      long long n)
 {
-	return cmpxchg64(&v->counter, o, n);
+	return arch_cmpxchg64(&v->counter, o, n);
 }
 
 /**
- * atomic64_xchg - xchg atomic64 variable
+ * arch_atomic64_xchg - xchg atomic64 variable
  * @v: pointer to type atomic64_t
  * @n: value to assign
  *
  * Atomically xchgs the value of @v to @n and returns
  * the old value.
  */
-static inline long long atomic64_xchg(atomic64_t *v, long long n)
+static inline long long arch_atomic64_xchg(atomic64_t *v, long long n)
 {
 	long long o;
 	unsigned high = (unsigned)(n >> 32);
@@ -95,13 +96,13 @@ static inline long long atomic64_xchg(atomic64_t *v, long long n)
 }
 
 /**
- * atomic64_set - set atomic64 variable
+ * arch_atomic64_set - set atomic64 variable
  * @v: pointer to type atomic64_t
  * @i: value to assign
  *
  * Atomically sets the value of @v to @n.
  */
-static inline void atomic64_set(atomic64_t *v, long long i)
+static inline void arch_atomic64_set(atomic64_t *v, long long i)
 {
 	unsigned high = (unsigned)(i >> 32);
 	unsigned low = (unsigned)i;
@@ -111,12 +112,12 @@ static inline void atomic64_set(atomic64_t *v, long long i)
 }
 
 /**
- * atomic64_read - read atomic64 variable
+ * arch_atomic64_read - read atomic64 variable
  * @v: pointer to type atomic64_t
  *
  * Atomically reads the value of @v and returns it.
  */
-static inline long long atomic64_read(const atomic64_t *v)
+static inline long long arch_atomic64_read(const atomic64_t *v)
 {
 	long long r;
 	alternative_atomic64(read, "=&A" (r), "c" (v) : "memory");
@@ -124,13 +125,13 @@ static inline long long atomic64_read(const atomic64_t *v)
  }
 
 /**
- * atomic64_add_return - add and return
+ * arch_atomic64_add_return - add and return
  * @i: integer value to add
  * @v: pointer to type atomic64_t
  *
  * Atomically adds @i to @v and returns @i + *@v
  */
-static inline long long atomic64_add_return(long long i, atomic64_t *v)
+static inline long long arch_atomic64_add_return(long long i, atomic64_t *v)
 {
 	alternative_atomic64(add_return,
 			     ASM_OUTPUT2("+A" (i), "+c" (v)),
@@ -141,7 +142,7 @@ static inline long long atomic64_add_return(long long i, atomic64_t *v)
 /*
  * Other variants with different arithmetic operators:
  */
-static inline long long atomic64_sub_return(long long i, atomic64_t *v)
+static inline long long arch_atomic64_sub_return(long long i, atomic64_t *v)
 {
 	alternative_atomic64(sub_return,
 			     ASM_OUTPUT2("+A" (i), "+c" (v)),
@@ -149,7 +150,7 @@ static inline long long atomic64_sub_return(long long i, atomic64_t *v)
 	return i;
 }
 
-static inline long long atomic64_inc_return(atomic64_t *v)
+static inline long long arch_atomic64_inc_return(atomic64_t *v)
 {
 	long long a;
 	alternative_atomic64(inc_return, "=&A" (a),
@@ -157,7 +158,7 @@ static inline long long atomic64_inc_return(atomic64_t *v)
 	return a;
 }
 
-static inline long long atomic64_dec_return(atomic64_t *v)
+static inline long long arch_atomic64_dec_return(atomic64_t *v)
 {
 	long long a;
 	alternative_atomic64(dec_return, "=&A" (a),
@@ -166,13 +167,13 @@ static inline long long atomic64_dec_return(atomic64_t *v)
 }
 
 /**
- * atomic64_add - add integer to atomic64 variable
+ * arch_atomic64_add - add integer to atomic64 variable
  * @i: integer value to add
  * @v: pointer to type atomic64_t
  *
  * Atomically adds @i to @v.
  */
-static inline long long atomic64_add(long long i, atomic64_t *v)
+static inline long long arch_atomic64_add(long long i, atomic64_t *v)
 {
 	__alternative_atomic64(add, add_return,
 			       ASM_OUTPUT2("+A" (i), "+c" (v)),
@@ -181,13 +182,13 @@ static inline long long atomic64_add(long long i, atomic64_t *v)
 }
 
 /**
- * atomic64_sub - subtract the atomic64 variable
+ * arch_atomic64_sub - subtract the atomic64 variable
  * @i: integer value to subtract
  * @v: pointer to type atomic64_t
  *
  * Atomically subtracts @i from @v.
  */
-static inline long long atomic64_sub(long long i, atomic64_t *v)
+static inline long long arch_atomic64_sub(long long i, atomic64_t *v)
 {
 	__alternative_atomic64(sub, sub_return,
 			       ASM_OUTPUT2("+A" (i), "+c" (v)),
@@ -196,7 +197,7 @@ static inline long long atomic64_sub(long long i, atomic64_t *v)
 }
 
 /**
- * atomic64_sub_and_test - subtract value from variable and test result
+ * arch_atomic64_sub_and_test - subtract value from variable and test result
  * @i: integer value to subtract
  * @v: pointer to type atomic64_t
  *
@@ -204,46 +205,46 @@ static inline long long atomic64_sub(long long i, atomic64_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
-static inline int atomic64_sub_and_test(long long i, atomic64_t *v)
+static inline int arch_atomic64_sub_and_test(long long i, atomic64_t *v)
 {
-	return atomic64_sub_return(i, v) == 0;
+	return arch_atomic64_sub_return(i, v) == 0;
 }
 
 /**
- * atomic64_inc - increment atomic64 variable
+ * arch_atomic64_inc - increment atomic64 variable
  * @v: pointer to type atomic64_t
  *
  * Atomically increments @v by 1.
  */
-static inline void atomic64_inc(atomic64_t *v)
+static inline void arch_atomic64_inc(atomic64_t *v)
 {
 	__alternative_atomic64(inc, inc_return, /* no output */,
 			       "S" (v) : "memory", "eax", "ecx", "edx");
 }
 
 /**
- * atomic64_dec - decrement atomic64 variable
+ * arch_atomic64_dec - decrement atomic64 variable
  * @v: pointer to type atomic64_t
  *
  * Atomically decrements @v by 1.
  */
-static inline void atomic64_dec(atomic64_t *v)
+static inline void arch_atomic64_dec(atomic64_t *v)
 {
 	__alternative_atomic64(dec, dec_return, /* no output */,
 			       "S" (v) : "memory", "eax", "ecx", "edx");
 }
 
 /**
- * atomic64_dec_and_test - decrement and test
+ * arch_atomic64_dec_and_test - decrement and test
  * @v: pointer to type atomic64_t
  *
  * Atomically decrements @v by 1 and
  * returns true if the result is 0, or false for all other
  * cases.
  */
-static inline int atomic64_dec_and_test(atomic64_t *v)
+static inline int arch_atomic64_dec_and_test(atomic64_t *v)
 {
-	return atomic64_dec_return(v) == 0;
+	return arch_atomic64_dec_return(v) == 0;
 }
 
 /**
@@ -254,13 +255,13 @@ static inline int atomic64_dec_and_test(atomic64_t *v)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
-static inline int atomic64_inc_and_test(atomic64_t *v)
+static inline int arch_atomic64_inc_and_test(atomic64_t *v)
 {
-	return atomic64_inc_return(v) == 0;
+	return arch_atomic64_inc_return(v) == 0;
 }
 
 /**
- * atomic64_add_negative - add and test if negative
+ * arch_atomic64_add_negative - add and test if negative
  * @i: integer value to add
  * @v: pointer to type atomic64_t
  *
@@ -268,13 +269,13 @@ static inline int atomic64_inc_and_test(atomic64_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-static inline int atomic64_add_negative(long long i, atomic64_t *v)
+static inline int arch_atomic64_add_negative(long long i, atomic64_t *v)
 {
-	return atomic64_add_return(i, v) < 0;
+	return arch_atomic64_add_return(i, v) < 0;
 }
 
 /**
- * atomic64_add_unless - add unless the number is a given value
+ * arch_atomic64_add_unless - add unless the number is a given value
  * @v: pointer of type atomic64_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
@@ -282,7 +283,8 @@ static inline int atomic64_add_negative(long long i, atomic64_t *v)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns non-zero if the add was done, zero otherwise.
  */
-static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+static inline int arch_atomic64_add_unless(atomic64_t *v, long long a,
+					   long long u)
 {
 	unsigned low = (unsigned)u;
 	unsigned high = (unsigned)(u >> 32);
@@ -293,7 +295,7 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
 }
 
 
-static inline int atomic64_inc_not_zero(atomic64_t *v)
+static inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 {
 	int r;
 	alternative_atomic64(inc_not_zero, "=&a" (r),
@@ -301,7 +303,7 @@ static inline int atomic64_inc_not_zero(atomic64_t *v)
 	return r;
 }
 
-static inline long long atomic64_dec_if_positive(atomic64_t *v)
+static inline long long arch_atomic64_dec_if_positive(atomic64_t *v)
 {
 	long long r;
 	alternative_atomic64(dec_if_positive, "=&A" (r),
@@ -312,66 +314,66 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
 #undef alternative_atomic64
 #undef __alternative_atomic64
 
-static inline void atomic64_and(long long i, atomic64_t *v)
+static inline void arch_atomic64_and(long long i, atomic64_t *v)
 {
 	long long old, c = 0;
 
-	while ((old = atomic64_cmpxchg(v, c, c & i)) != c)
+	while ((old = arch_atomic64_cmpxchg(v, c, c & i)) != c)
 		c = old;
 }
 
-static inline long long atomic64_fetch_and(long long i, atomic64_t *v)
+static inline long long arch_atomic64_fetch_and(long long i, atomic64_t *v)
 {
 	long long old, c = 0;
 
-	while ((old = atomic64_cmpxchg(v, c, c & i)) != c)
+	while ((old = arch_atomic64_cmpxchg(v, c, c & i)) != c)
 		c = old;
 	return old;
 }
 
-static inline void atomic64_or(long long i, atomic64_t *v)
+static inline void arch_atomic64_or(long long i, atomic64_t *v)
 {
 	long long old, c = 0;
 
-	while ((old = atomic64_cmpxchg(v, c, c | i)) != c)
+	while ((old = arch_atomic64_cmpxchg(v, c, c | i)) != c)
 		c = old;
 }
 
-static inline long long atomic64_fetch_or(long long i, atomic64_t *v)
+static inline long long arch_atomic64_fetch_or(long long i, atomic64_t *v)
 {
 	long long old, c = 0;
 
-	while ((old = atomic64_cmpxchg(v, c, c | i)) != c)
+	while ((old = arch_atomic64_cmpxchg(v, c, c | i)) != c)
 		c = old;
 	return old;
 }
 
-static inline void atomic64_xor(long long i, atomic64_t *v)
+static inline void arch_atomic64_xor(long long i, atomic64_t *v)
 {
 	long long old, c = 0;
 
-	while ((old = atomic64_cmpxchg(v, c, c ^ i)) != c)
+	while ((old = arch_atomic64_cmpxchg(v, c, c ^ i)) != c)
 		c = old;
 }
 
-static inline long long atomic64_fetch_xor(long long i, atomic64_t *v)
+static inline long long arch_atomic64_fetch_xor(long long i, atomic64_t *v)
 {
 	long long old, c = 0;
 
-	while ((old = atomic64_cmpxchg(v, c, c ^ i)) != c)
+	while ((old = arch_atomic64_cmpxchg(v, c, c ^ i)) != c)
 		c = old;
 	return old;
 }
 
-static inline long long atomic64_fetch_add(long long i, atomic64_t *v)
+static inline long long arch_atomic64_fetch_add(long long i, atomic64_t *v)
 {
 	long long old, c = 0;
 
-	while ((old = atomic64_cmpxchg(v, c, c + i)) != c)
+	while ((old = arch_atomic64_cmpxchg(v, c, c + i)) != c)
 		c = old;
 	return old;
 }
 
-#define atomic64_fetch_sub(i, v)	atomic64_fetch_add(-(i), (v))
+#define arch_atomic64_fetch_sub(i, v)	arch_atomic64_fetch_add(-(i), (v))
 
 #endif /* _ASM_X86_ATOMIC64_32_H */
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 8555cd19a916..001e648f2556 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -10,37 +10,37 @@
 #define ATOMIC64_INIT(i)	{ (i) }
 
 /**
- * atomic64_read - read atomic64 variable
+ * arch_atomic64_read - read atomic64 variable
  * @v: pointer of type atomic64_t
  *
  * Atomically reads the value of @v.
  * Doesn't imply a read memory barrier.
  */
-static inline long long atomic64_read(const atomic64_t *v)
+static inline long long arch_atomic64_read(const atomic64_t *v)
 {
 	return READ_ONCE((v)->counter);
 }
 
 /**
- * atomic64_set - set atomic64 variable
+ * arch_atomic64_set - set atomic64 variable
  * @v: pointer to type atomic64_t
  * @i: required value
  *
  * Atomically sets the value of @v to @i.
  */
-static inline void atomic64_set(atomic64_t *v, long long i)
+static inline void arch_atomic64_set(atomic64_t *v, long long i)
 {
 	WRITE_ONCE(v->counter, i);
 }
 
 /**
- * atomic64_add - add integer to atomic64 variable
+ * arch_atomic64_add - add integer to atomic64 variable
  * @i: integer value to add
  * @v: pointer to type atomic64_t
  *
  * Atomically adds @i to @v.
  */
-static __always_inline void atomic64_add(long long i, atomic64_t *v)
+static __always_inline void arch_atomic64_add(long long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "addq %1,%0"
 		     : "=m" (v->counter)
@@ -48,13 +48,13 @@ static __always_inline void atomic64_add(long long i, atomic64_t *v)
 }
 
 /**
- * atomic64_sub - subtract the atomic64 variable
+ * arch_atomic64_sub - subtract the atomic64 variable
  * @i: integer value to subtract
  * @v: pointer to type atomic64_t
  *
  * Atomically subtracts @i from @v.
  */
-static inline void atomic64_sub(long long i, atomic64_t *v)
+static inline void arch_atomic64_sub(long long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "subq %1,%0"
 		     : "=m" (v->counter)
@@ -62,7 +62,7 @@ static inline void atomic64_sub(long long i, atomic64_t *v)
 }
 
 /**
- * atomic64_sub_and_test - subtract value from variable and test result
+ * arch_atomic64_sub_and_test - subtract value from variable and test result
  * @i: integer value to subtract
  * @v: pointer to type atomic64_t
  *
@@ -70,18 +70,18 @@ static inline void atomic64_sub(long long i, atomic64_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
-static inline bool atomic64_sub_and_test(long long i, atomic64_t *v)
+static inline bool arch_atomic64_sub_and_test(long long i, atomic64_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e);
 }
 
 /**
- * atomic64_inc - increment atomic64 variable
+ * arch_atomic64_inc - increment atomic64 variable
  * @v: pointer to type atomic64_t
  *
  * Atomically increments @v by 1.
  */
-static __always_inline void atomic64_inc(atomic64_t *v)
+static __always_inline void arch_atomic64_inc(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "incq %0"
 		     : "=m" (v->counter)
@@ -89,12 +89,12 @@ static __always_inline void atomic64_inc(atomic64_t *v)
 }
 
 /**
- * atomic64_dec - decrement atomic64 variable
+ * arch_atomic64_dec - decrement atomic64 variable
  * @v: pointer to type atomic64_t
  *
  * Atomically decrements @v by 1.
  */
-static __always_inline void atomic64_dec(atomic64_t *v)
+static __always_inline void arch_atomic64_dec(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "decq %0"
 		     : "=m" (v->counter)
@@ -102,33 +102,33 @@ static __always_inline void atomic64_dec(atomic64_t *v)
 }
 
 /**
- * atomic64_dec_and_test - decrement and test
+ * arch_atomic64_dec_and_test - decrement and test
  * @v: pointer to type atomic64_t
  *
  * Atomically decrements @v by 1 and
  * returns true if the result is 0, or false for all other
  * cases.
  */
-static inline bool atomic64_dec_and_test(atomic64_t *v)
+static inline bool arch_atomic64_dec_and_test(atomic64_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e);
 }
 
 /**
- * atomic64_inc_and_test - increment and test
+ * arch_atomic64_inc_and_test - increment and test
  * @v: pointer to type atomic64_t
  *
  * Atomically increments @v by 1
  * and returns true if the result is zero, or false for all
  * other cases.
  */
-static inline bool atomic64_inc_and_test(atomic64_t *v)
+static inline bool arch_atomic64_inc_and_test(atomic64_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e);
 }
 
 /**
- * atomic64_add_negative - add and test if negative
+ * arch_atomic64_add_negative - add and test if negative
  * @i: integer value to add
  * @v: pointer to type atomic64_t
  *
@@ -136,59 +136,59 @@ static inline bool atomic64_inc_and_test(atomic64_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-static inline bool atomic64_add_negative(long long i, atomic64_t *v)
+static inline bool arch_atomic64_add_negative(long long i, atomic64_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s);
 }
 
 /**
- * atomic64_add_return - add and return
+ * arch_atomic64_add_return - add and return
  * @i: integer value to add
  * @v: pointer to type atomic64_t
  *
  * Atomically adds @i to @v and returns @i + @v
  */
-static __always_inline long long atomic64_add_return(long long i, atomic64_t *v)
+static __always_inline long long arch_atomic64_add_return(long long i, atomic64_t *v)
 {
 	return i + xadd(&v->counter, i);
 }
 
-static inline long long atomic64_sub_return(long long i, atomic64_t *v)
+static inline long long arch_atomic64_sub_return(long long i, atomic64_t *v)
 {
-	return atomic64_add_return(-i, v);
+	return arch_atomic64_add_return(-i, v);
 }
 
-static inline long long atomic64_fetch_add(long long i, atomic64_t *v)
+static inline long long arch_atomic64_fetch_add(long long i, atomic64_t *v)
 {
 	return xadd(&v->counter, i);
 }
 
-static inline long long atomic64_fetch_sub(long long i, atomic64_t *v)
+static inline long long arch_atomic64_fetch_sub(long long i, atomic64_t *v)
 {
 	return xadd(&v->counter, -i);
 }
 
-#define atomic64_inc_return(v)  (atomic64_add_return(1, (v)))
-#define atomic64_dec_return(v)  (atomic64_sub_return(1, (v)))
+#define arch_atomic64_inc_return(v)  (arch_atomic64_add_return(1, (v)))
+#define arch_atomic64_dec_return(v)  (arch_atomic64_sub_return(1, (v)))
 
-static inline long long atomic64_cmpxchg(atomic64_t *v, long long old, long long new)
+static inline long long arch_atomic64_cmpxchg(atomic64_t *v, long long old, long long new)
 {
-	return cmpxchg(&v->counter, old, new);
+	return arch_cmpxchg(&v->counter, old, new);
 }
 
-#define atomic64_try_cmpxchg atomic64_try_cmpxchg
-static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, long long *old, long long new)
+#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg
+static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, long long *old, long long new)
 {
 	return try_cmpxchg(&v->counter, old, new);
 }
 
-static inline long long atomic64_xchg(atomic64_t *v, long long new)
+static inline long long arch_atomic64_xchg(atomic64_t *v, long long new)
 {
 	return xchg(&v->counter, new);
 }
 
 /**
- * atomic64_add_unless - add unless the number is a given value
+ * arch_atomic64_add_unless - add unless the number is a given value
  * @v: pointer of type atomic64_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
@@ -196,37 +196,37 @@ static inline long long atomic64_xchg(atomic64_t *v, long long new)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static inline bool atomic64_add_unless(atomic64_t *v, long long a, long long u)
+static inline bool arch_atomic64_add_unless(atomic64_t *v, long long a, long long u)
 {
-	long long c = atomic64_read(v);
+	long long c = arch_atomic64_read(v);
 	do {
 		if (unlikely(c == u))
 			return false;
-	} while (!atomic64_try_cmpxchg(v, &c, c + a));
+	} while (!arch_atomic64_try_cmpxchg(v, &c, c + a));
 	return true;
 }
 
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
+#define arch_atomic64_inc_not_zero(v) arch_atomic64_add_unless((v), 1, 0)
 
 /*
- * atomic64_dec_if_positive - decrement by 1 if old value positive
+ * arch_atomic64_dec_if_positive - decrement by 1 if old value positive
  * @v: pointer of type atomic_t
  *
  * The function returns the old value of *v minus 1, even if
  * the atomic variable, v, was not decremented.
  */
-static inline long long atomic64_dec_if_positive(atomic64_t *v)
+static inline long long arch_atomic64_dec_if_positive(atomic64_t *v)
 {
-	long long dec, c = atomic64_read(v);
+	long long dec, c = arch_atomic64_read(v);
 	do {
 		dec = c - 1;
 		if (unlikely(dec < 0))
 			break;
-	} while (!atomic64_try_cmpxchg(v, &c, dec));
+	} while (!arch_atomic64_try_cmpxchg(v, &c, dec));
 	return dec;
 }
 
-static inline void atomic64_and(long long i, atomic64_t *v)
+static inline void arch_atomic64_and(long long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "andq %1,%0"
 			: "+m" (v->counter)
@@ -234,16 +234,16 @@ static inline void atomic64_and(long long i, atomic64_t *v)
 			: "memory");
 }
 
-static inline long long atomic64_fetch_and(long long i, atomic64_t *v)
+static inline long long arch_atomic64_fetch_and(long long i, atomic64_t *v)
 {
-	long long val = atomic64_read(v);
+	long long val = arch_atomic64_read(v);
 
 	do {
-	} while (!atomic64_try_cmpxchg(v, &val, val & i));
+	} while (!arch_atomic64_try_cmpxchg(v, &val, val & i));
 	return val;
 }
 
-static inline void atomic64_or(long long i, atomic64_t *v)
+static inline void arch_atomic64_or(long long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "orq %1,%0"
 			: "+m" (v->counter)
@@ -251,16 +251,16 @@ static inline void atomic64_or(long long i, atomic64_t *v)
 			: "memory");
 }
 
-static inline long long atomic64_fetch_or(long long i, atomic64_t *v)
+static inline long long arch_atomic64_fetch_or(long long i, atomic64_t *v)
 {
-	long long val = atomic64_read(v);
+	long long val = arch_atomic64_read(v);
 
 	do {
-	} while (!atomic64_try_cmpxchg(v, &val, val | i));
+	} while (!arch_atomic64_try_cmpxchg(v, &val, val | i));
 	return val;
 }
 
-static inline void atomic64_xor(long long i, atomic64_t *v)
+static inline void arch_atomic64_xor(long long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "xorq %1,%0"
 			: "+m" (v->counter)
@@ -268,12 +268,12 @@ static inline void atomic64_xor(long long i, atomic64_t *v)
 			: "memory");
 }
 
-static inline long long atomic64_fetch_xor(long long i, atomic64_t *v)
+static inline long long arch_atomic64_fetch_xor(long long i, atomic64_t *v)
 {
-	long long val = atomic64_read(v);
+	long long val = arch_atomic64_read(v);
 
 	do {
-	} while (!atomic64_try_cmpxchg(v, &val, val ^ i));
+	} while (!arch_atomic64_try_cmpxchg(v, &val, val ^ i));
 	return val;
 }
 
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index d90296d061e8..e8cf95908fe5 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -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 */
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index e4959d023af8..d897291d2bf9 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -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);				\
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index caa23a34c963..fafaebacca2d 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -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));					\
-- 
2.13.0.219.gdb65acc882-goog

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH v2 5/7] kasan: allow kasan_check_read/write() to accept pointers to volatiles

[Dmitry Vyukov]

Currently kasan_check_read/write() accept 'const void*', make them
accept 'const volatile void*'. This is required for instrumentation
of atomic operations and there is just no reason to not allow that.

Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-kernel@vger.kernel.org
Cc: x86@kernel.org
Cc: linux-mm@kvack.org
Cc: kasan-dev@googlegroups.com
---
 include/linux/kasan-checks.h | 10 ++++++----
 mm/kasan/kasan.c             |  4 ++--
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/include/linux/kasan-checks.h b/include/linux/kasan-checks.h
index b7f8aced7870..41960fecf783 100644
--- a/include/linux/kasan-checks.h
+++ b/include/linux/kasan-checks.h
@@ -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
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index 98b27195e38b..db46e66eb1d4 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -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_);
 }
-- 
2.13.0.219.gdb65acc882-goog

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH v2 6/7] asm-generic: add KASAN instrumentation to atomic operations

[Dmitry Vyukov]

KASAN uses compiler instrumentation to intercept all memory accesses.
But it does not see memory accesses done in assembly code.
One notable user of assembly code is atomic operations. Frequently,
for example, an atomic reference decrement is the last access to an
object and a good candidate for a racy use-after-free.

Add manual KASAN checks to atomic operations.

Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will.deacon@arm.com>,
Cc: Andrew Morton <akpm@linux-foundation.org>,
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>,
Cc: Ingo Molnar <mingo@redhat.com>,
Cc: kasan-dev@googlegroups.com
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
Cc: x86@kernel.org
---
 include/asm-generic/atomic-instrumented.h | 76 +++++++++++++++++++++++++++++--
 1 file changed, 72 insertions(+), 4 deletions(-)

diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h
index fd483115d4c6..7f8eb761f896 100644
--- a/include/asm-generic/atomic-instrumented.h
+++ b/include/asm-generic/atomic-instrumented.h
@@ -1,44 +1,54 @@
 #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 long long 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, long long 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 long long atomic64_xchg(atomic64_t *v, long long 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 long long atomic64_cmpxchg(atomic64_t *v, long long old,
 						  long long new)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_cmpxchg(v, old, new);
 }
 
@@ -46,6 +56,8 @@ static __always_inline long long atomic64_cmpxchg(atomic64_t *v, long long old,
 #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
@@ -55,12 +67,15 @@ static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new)
 static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, long long *old,
 						 long long 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);
 }
 
@@ -68,242 +83,295 @@ static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
 static __always_inline bool atomic64_add_unless(atomic64_t *v, long long a,
 						long long 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(long long 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(long long 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(long long 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(long long 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(long long 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 long long 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 long long atomic64_dec_return(atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_dec_return(v);
 }
 
 static __always_inline long long atomic64_inc_not_zero(atomic64_t *v)
 {
+	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_inc_not_zero(v);
 }
 
 static __always_inline long long 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 long long atomic64_add_return(long long 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 long long atomic64_sub_return(long long 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 long long atomic64_fetch_add(long long 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 long long atomic64_fetch_sub(long long 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 long long atomic64_fetch_and(long long 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 long long atomic64_fetch_or(long long 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 long long atomic64_fetch_xor(long long 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(long long 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(long long 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)				\
-- 
2.13.0.219.gdb65acc882-goog

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH v2 7/7] asm-generic, x86: add comments for atomic instrumentation

[Dmitry Vyukov]

The comments are factored out from the code changes to make them
easier to read. Add them separately to explain some non-obvious
aspects.

Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: kasan-dev@googlegroups.com
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
Cc: x86@kernel.org
---
 arch/x86/include/asm/atomic.h             |  7 +++++++
 include/asm-generic/atomic-instrumented.h | 30 ++++++++++++++++++++++++++++++
 2 files changed, 37 insertions(+)

diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index b7900346c77e..8a9e65e585db 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -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);
 }
 
diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h
index 7f8eb761f896..1134af090976 100644
--- a/include/asm-generic/atomic-instrumented.h
+++ b/include/asm-generic/atomic-instrumented.h
@@ -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
 
@@ -339,6 +351,15 @@ static __always_inline bool atomic64_add_negative(long long 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);			\
@@ -374,6 +395,15 @@ static __always_inline bool atomic64_add_negative(long long 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));	\
-- 
2.13.0.219.gdb65acc882-goog

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>