Add CRYPTO_atomic_store api

Generally we can get away with just using CRYPTO_atomic_load to do
stores by reversing the source and target variables, but doing so
creates a problem for the thread sanitizer as CRYPTO_atomic_load hard
codes an __ATOMIC_ACQUIRE constraint, which confuses tsan into thinking
that loads and stores aren't properly ordered, leading to RAW/WAR
hazzards getting reported.  Instead create a CRYPTO_atomic_store api
that is identical to the load variant, save for the fact that the value
is a unit64_t rather than a pointer that gets stored using an
__ATOMIC_RELEASE constraint, satisfying tsan.

Reviewed-by: Tomas Mraz <tomas@openssl.org>
Reviewed-by: Paul Dale <pauli@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/23671)

3 files changed, 46 insertions, 0 deletions

diff --git a/crypto/threads_none.c b/crypto/threads_none.c
index 47a7c01f26..e0387650fe 100644
--- a/crypto/threads_none.c
+++ b/crypto/threads_none.c
@@ -226,6 +226,13 @@ int CRYPTO_atomic_load(uint64_t *val, uint64_t *ret, CRYPTO_RWLOCK *lock)
     return 1;
 }
 
+int CRYPTO_atomic_store(uint64_t *dst, uint64_t val, CRYPTO_RWLOCK *lock)
+{
+    *dst = val;
+
+    return 1;
+}
+
 int CRYPTO_atomic_load_int(int *val, int *ret, CRYPTO_RWLOCK *lock)
 {
     *ret = *val;
diff --git a/crypto/threads_pthread.c b/crypto/threads_pthread.c
index 69b68e5226..8e411671d9 100644
--- a/crypto/threads_pthread.c
+++ b/crypto/threads_pthread.c
@@ -919,6 +919,29 @@ int CRYPTO_atomic_load(uint64_t *val, uint64_t *ret, CRYPTO_RWLOCK *lock)
     return 1;
 }
 
+int CRYPTO_atomic_store(uint64_t *dst, uint64_t val, CRYPTO_RWLOCK *lock)
+{
+# if defined(__GNUC__) && defined(__ATOMIC_ACQUIRE) && !defined(BROKEN_CLANG_ATOMICS)
+    if (__atomic_is_lock_free(sizeof(*dst), dst)) {
+        __atomic_store(dst, &val, __ATOMIC_RELEASE);
+        return 1;
+    }
+# elif defined(__sun) && (defined(__SunOS_5_10) || defined(__SunOS_5_11))
+    /* This will work for all future Solaris versions. */
+    if (ret != NULL) {
+        atomic_swap_64(dst, val);
+        return 1;
+    }
+# endif
+    if (lock == NULL || !CRYPTO_THREAD_read_lock(lock))
+        return 0;
+    *dst  = val;
+    if (!CRYPTO_THREAD_unlock(lock))
+        return 0;
+
+    return 1;
+}
+
 int CRYPTO_atomic_load_int(int *val, int *ret, CRYPTO_RWLOCK *lock)
 {
 # if defined(__GNUC__) && defined(__ATOMIC_ACQUIRE) && !defined(BROKEN_CLANG_ATOMICS)
diff --git a/crypto/threads_win.c b/crypto/threads_win.c
index 6bcbaea10f..ea72670f22 100644
--- a/crypto/threads_win.c
+++ b/crypto/threads_win.c
@@ -593,6 +593,22 @@ int CRYPTO_atomic_load(uint64_t *val, uint64_t *ret, CRYPTO_RWLOCK *lock)
 #endif
 }
 
+int CRYPTO_atomic_store(uint64_t *dst, uint64_t val, CRYPTO_RWLOCK *lock)
+{
+#if (defined(NO_INTERLOCKEDOR64))
+    if (lock == NULL || !CRYPTO_THREAD_read_lock(lock))
+        return 0;
+    *dst = val;
+    if (!CRYPTO_THREAD_unlock(lock))
+        return 0;
+
+    return 1;
+#else
+    InterlockedExchange64(dst, val);
+    return 1;
+#endif
+}
+
 int CRYPTO_atomic_load_int(int *val, int *ret, CRYPTO_RWLOCK *lock)
 {
 #if (defined(NO_INTERLOCKEDOR64))