Use try_cmpxchg() instead of cmpxchg(*ptr, old, new) == old.

X86 CMPXCHG instruction returns success in ZF flag, so this change saves a
compare after CMPXCHG (and related move instruction in front of CMPXCHG).

Also, try_cmpxchg() implicitly assigns old *ptr value to "old" when CMPXCHG
fails. There is no need to re-read the value in the loop.

Note that the value from *ptr should be read using READ_ONCE to prevent
the compiler from merging, refetching or reordering the read.

No functional change intended.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Will Deacon <will@kernel.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
---
 kernel/locking/rtmutex.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 4a10e8c16fd2..88d08eeb8bc0 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -237,12 +237,13 @@ static __always_inline bool rt_mutex_cmpxchg_release(struct rt_mutex_base *lock,
  */
 static __always_inline void mark_rt_mutex_waiters(struct rt_mutex_base *lock)
 {
-	unsigned long owner, *p = (unsigned long *) &lock->owner;
+	unsigned long *p = (unsigned long *) &lock->owner;
+	unsigned long owner, new;
 
+	owner = READ_ONCE(*p);
 	do {
-		owner = *p;
-	} while (cmpxchg_relaxed(p, owner,
-				 owner | RT_MUTEX_HAS_WAITERS) != owner);
+		new = owner | RT_MUTEX_HAS_WAITERS;
+	} while (!try_cmpxchg_relaxed(p, &owner, new));
 
 	/*
 	 * The cmpxchg loop above is relaxed to avoid back-to-back ACQUIRE
-- 
2.31.1

The following commit has been merged into the locking/core branch of tip:

Commit-ID:     ce3576ebd62d99f79c1dc98824e2ef6d6ab68434
Gitweb:        https://git.kernel.org/tip/ce3576ebd62d99f79c1dc98824e2ef6d6ab68434
Author:        Uros Bizjak <ubizjak@gmail.com>
AuthorDate:    Wed, 24 Jan 2024 11:49:53 +01:00
Committer:     Ingo Molnar <mingo@kernel.org>
CommitterDate: Fri, 01 Mar 2024 13:02:05 +01:00

locking/rtmutex: Use try_cmpxchg_relaxed() in mark_rt_mutex_waiters()

Use try_cmpxchg() instead of cmpxchg(*ptr, old, new) == old.

The x86 CMPXCHG instruction returns success in the ZF flag, so this change
saves a compare after CMPXCHG (and related move instruction in front of CMPXCHG).

Also, try_cmpxchg() implicitly assigns old *ptr value to "old" when CMPXCHG
fails. There is no need to re-read the value in the loop.

Note that the value from *ptr should be read using READ_ONCE() to prevent
the compiler from merging, refetching or reordering the read.

No functional change intended.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@kernel.org>
Link: https://lore.kernel.org/r/20240124104953.612063-1-ubizjak@gmail.com
---
 kernel/locking/rtmutex.c |  9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 4a10e8c..88d08ee 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -237,12 +237,13 @@ static __always_inline bool rt_mutex_cmpxchg_release(struct rt_mutex_base *lock,
  */
 static __always_inline void mark_rt_mutex_waiters(struct rt_mutex_base *lock)
 {
-	unsigned long owner, *p = (unsigned long *) &lock->owner;
+	unsigned long *p = (unsigned long *) &lock->owner;
+	unsigned long owner, new;
 
+	owner = READ_ONCE(*p);
 	do {
-		owner = *p;
-	} while (cmpxchg_relaxed(p, owner,
-				 owner | RT_MUTEX_HAS_WAITERS) != owner);
+		new = owner | RT_MUTEX_HAS_WAITERS;
+	} while (!try_cmpxchg_relaxed(p, &owner, new));
 
 	/*
 	 * The cmpxchg loop above is relaxed to avoid back-to-back ACQUIRE