instrumentation: Wire up cmpxchg128()

Wire up the cmpxchg128 family in the atomic wrapper scripts.

These provide the generic cmpxchg128 family of functions from the
arch_ prefixed version, adding explicit instrumentation where needed.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/20230531132323.519237070@infradead.org

include/linux/atomic/atomic-arch-fallback.h

@@ -77,6 +77,29 @@
 
 #endif /* arch_cmpxchg64_relaxed */
 
+#ifndef arch_cmpxchg128_relaxed
+#define arch_cmpxchg128_acquire arch_cmpxchg128
+#define arch_cmpxchg128_release arch_cmpxchg128
+#define arch_cmpxchg128_relaxed arch_cmpxchg128
+#else /* arch_cmpxchg128_relaxed */
+
+#ifndef arch_cmpxchg128_acquire
+#define arch_cmpxchg128_acquire(...) \
+	__atomic_op_acquire(arch_cmpxchg128, __VA_ARGS__)
+#endif
+
+#ifndef arch_cmpxchg128_release
+#define arch_cmpxchg128_release(...) \
+	__atomic_op_release(arch_cmpxchg128, __VA_ARGS__)
+#endif
+
+#ifndef arch_cmpxchg128
+#define arch_cmpxchg128(...) \
+	__atomic_op_fence(arch_cmpxchg128, __VA_ARGS__)
+#endif
+
+#endif /* arch_cmpxchg128_relaxed */
+
 #ifndef arch_try_cmpxchg_relaxed
 #ifdef arch_try_cmpxchg
 #define arch_try_cmpxchg_acquire arch_try_cmpxchg
@@ -217,6 +240,76 @@
 
 #endif /* arch_try_cmpxchg64_relaxed */
 
+#ifndef arch_try_cmpxchg128_relaxed
+#ifdef arch_try_cmpxchg128
+#define arch_try_cmpxchg128_acquire arch_try_cmpxchg128
+#define arch_try_cmpxchg128_release arch_try_cmpxchg128
+#define arch_try_cmpxchg128_relaxed arch_try_cmpxchg128
+#endif /* arch_try_cmpxchg128 */
+
+#ifndef arch_try_cmpxchg128
+#define arch_try_cmpxchg128(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = arch_cmpxchg128((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
+#endif /* arch_try_cmpxchg128 */
+
+#ifndef arch_try_cmpxchg128_acquire
+#define arch_try_cmpxchg128_acquire(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = arch_cmpxchg128_acquire((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
+#endif /* arch_try_cmpxchg128_acquire */
+
+#ifndef arch_try_cmpxchg128_release
+#define arch_try_cmpxchg128_release(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = arch_cmpxchg128_release((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
+#endif /* arch_try_cmpxchg128_release */
+
+#ifndef arch_try_cmpxchg128_relaxed
+#define arch_try_cmpxchg128_relaxed(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = arch_cmpxchg128_relaxed((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
+#endif /* arch_try_cmpxchg128_relaxed */
+
+#else /* arch_try_cmpxchg128_relaxed */
+
+#ifndef arch_try_cmpxchg128_acquire
+#define arch_try_cmpxchg128_acquire(...) \
+	__atomic_op_acquire(arch_try_cmpxchg128, __VA_ARGS__)
+#endif
+
+#ifndef arch_try_cmpxchg128_release
+#define arch_try_cmpxchg128_release(...) \
+	__atomic_op_release(arch_try_cmpxchg128, __VA_ARGS__)
+#endif
+
+#ifndef arch_try_cmpxchg128
+#define arch_try_cmpxchg128(...) \
+	__atomic_op_fence(arch_try_cmpxchg128, __VA_ARGS__)
+#endif
+
+#endif /* arch_try_cmpxchg128_relaxed */
+
 #ifndef arch_try_cmpxchg_local
 #define arch_try_cmpxchg_local(_ptr, _oldp, _new) \
 ({ \
@@ -2668,4 +2761,4 @@ arch_atomic64_dec_if_positive(atomic64_t *v)
 #endif
 
 #endif /* _LINUX_ATOMIC_FALLBACK_H */
-// ad2e2b4d168dbc60a73922616047a9bfa446af36
+// 52dfc6fe4a2e7234bbd2aa3e16a377c1db793a53

include/linux/atomic/atomic-instrumented.h

@@ -2034,6 +2034,36 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	arch_cmpxchg64_relaxed(__ai_ptr, __VA_ARGS__); \
 })
 
+#define cmpxchg128(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	kcsan_mb(); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	arch_cmpxchg128(__ai_ptr, __VA_ARGS__); \
+})
+
+#define cmpxchg128_acquire(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	arch_cmpxchg128_acquire(__ai_ptr, __VA_ARGS__); \
+})
+
+#define cmpxchg128_release(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	kcsan_release(); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	arch_cmpxchg128_release(__ai_ptr, __VA_ARGS__); \
+})
+
+#define cmpxchg128_relaxed(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	arch_cmpxchg128_relaxed(__ai_ptr, __VA_ARGS__); \
+})
+
 #define try_cmpxchg(ptr, oldp, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
@@ -2110,6 +2140,44 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	arch_try_cmpxchg64_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \
 })
 
+#define try_cmpxchg128(ptr, oldp, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	typeof(oldp) __ai_oldp = (oldp); \
+	kcsan_mb(); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	arch_try_cmpxchg128(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+})
+
+#define try_cmpxchg128_acquire(ptr, oldp, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	typeof(oldp) __ai_oldp = (oldp); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	arch_try_cmpxchg128_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+})
+
+#define try_cmpxchg128_release(ptr, oldp, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	typeof(oldp) __ai_oldp = (oldp); \
+	kcsan_release(); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	arch_try_cmpxchg128_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+})
+
+#define try_cmpxchg128_relaxed(ptr, oldp, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	typeof(oldp) __ai_oldp = (oldp); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	arch_try_cmpxchg128_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+})
+
 #define cmpxchg_local(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
@@ -2124,6 +2192,13 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	arch_cmpxchg64_local(__ai_ptr, __VA_ARGS__); \
 })
 
+#define cmpxchg128_local(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	arch_cmpxchg128_local(__ai_ptr, __VA_ARGS__); \
+})
+
 #define sync_cmpxchg(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
@@ -2150,6 +2225,15 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	arch_try_cmpxchg64_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \
 })
 
+#define try_cmpxchg128_local(ptr, oldp, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	typeof(oldp) __ai_oldp = (oldp); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	arch_try_cmpxchg128_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+})
+
 #define cmpxchg_double(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
@@ -2167,4 +2251,4 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 })
 
 #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */
-// 6b513a42e1a1b5962532a019b7fc91eaa044ad5e
+// 82d1be694fab30414527d0877c29fa75ed5a0b74

scripts/atomic/gen-atomic-fallback.sh

@@ -217,11 +217,11 @@ cat << EOF
 
 EOF
 
-for xchg in "arch_xchg" "arch_cmpxchg" "arch_cmpxchg64"; do
+for xchg in "arch_xchg" "arch_cmpxchg" "arch_cmpxchg64" "arch_cmpxchg128"; do
 	gen_xchg_fallbacks "${xchg}"
 done
 
-for cmpxchg in "cmpxchg" "cmpxchg64"; do
+for cmpxchg in "cmpxchg" "cmpxchg64" "cmpxchg128"; do
 	gen_try_cmpxchg_fallbacks "${cmpxchg}"
 done
 

scripts/atomic/gen-atomic-instrumented.sh

@@ -166,14 +166,14 @@ grep '^[a-z]' "$1" | while read name meta args; do
 done
 
 
-for xchg in "xchg" "cmpxchg" "cmpxchg64" "try_cmpxchg" "try_cmpxchg64"; do
+for xchg in "xchg" "cmpxchg" "cmpxchg64" "cmpxchg128" "try_cmpxchg" "try_cmpxchg64" "try_cmpxchg128"; do
 	for order in "" "_acquire" "_release" "_relaxed"; do
 		gen_xchg "${xchg}" "${order}" ""
 		printf "\n"
 	done
 done
 
-for xchg in "cmpxchg_local" "cmpxchg64_local" "sync_cmpxchg" "try_cmpxchg_local" "try_cmpxchg64_local" ; do
+for xchg in "cmpxchg_local" "cmpxchg64_local" "cmpxchg128_local" "sync_cmpxchg" "try_cmpxchg_local" "try_cmpxchg64_local" "try_cmpxchg128_local"; do
 	gen_xchg "${xchg}" "" ""
 	printf "\n"
 done