This is a note to let you know that I've just added the patch titled locking/qrwlock: Fix ordering in queued_write_lock_slowpath() to the 5.11-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: locking-qrwlock-fix-ordering-in-queued_write_lock_sl.patch and it can be found in the queue-5.11 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. commit b697b00a53c4cb3e2d32ca117167e23915e7552c Author: Ali Saidi <alisaidi@xxxxxxxxxx> Date: Thu Apr 15 17:27:11 2021 +0000 locking/qrwlock: Fix ordering in queued_write_lock_slowpath() [ Upstream commit 84a24bf8c52e66b7ac89ada5e3cfbe72d65c1896 ] While this code is executed with the wait_lock held, a reader can acquire the lock without holding wait_lock. The writer side loops checking the value with the atomic_cond_read_acquire(), but only truly acquires the lock when the compare-and-exchange is completed successfully which isnâ??t ordered. This exposes the window between the acquire and the cmpxchg to an A-B-A problem which allows reads following the lock acquisition to observe values speculatively before the write lock is truly acquired. We've seen a problem in epoll where the reader does a xchg while holding the read lock, but the writer can see a value change out from under it. Writer | Reader -------------------------------------------------------------------------------- ep_scan_ready_list() | |- write_lock_irq() | |- queued_write_lock_slowpath() | |- atomic_cond_read_acquire() | | read_lock_irqsave(&ep->lock, flags); --> (observes value before unlock) | chain_epi_lockless() | | epi->next = xchg(&ep->ovflist, epi); | | read_unlock_irqrestore(&ep->lock, flags); | | | atomic_cmpxchg_relaxed() | |-- READ_ONCE(ep->ovflist); | A core can order the read of the ovflist ahead of the atomic_cmpxchg_relaxed(). Switching the cmpxchg to use acquire semantics addresses this issue at which point the atomic_cond_read can be switched to use relaxed semantics. Fixes: b519b56e378ee ("locking/qrwlock: Use atomic_cond_read_acquire() when spinning in qrwlock") Signed-off-by: Ali Saidi <alisaidi@xxxxxxxxxx> [peterz: use try_cmpxchg()] Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx> Reviewed-by: Steve Capper <steve.capper@xxxxxxx> Acked-by: Will Deacon <will@xxxxxxxxxx> Acked-by: Waiman Long <longman@xxxxxxxxxx> Tested-by: Steve Capper <steve.capper@xxxxxxx> Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx> diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c index fe9ca92faa2a..909b0bf22a1e 100644 --- a/kernel/locking/qrwlock.c +++ b/kernel/locking/qrwlock.c @@ -61,6 +61,8 @@ EXPORT_SYMBOL(queued_read_lock_slowpath); */ void queued_write_lock_slowpath(struct qrwlock *lock) { + int cnts; + /* Put the writer into the wait queue */ arch_spin_lock(&lock->wait_lock); @@ -74,9 +76,8 @@ void queued_write_lock_slowpath(struct qrwlock *lock) /* When no more readers or writers, set the locked flag */ do { - atomic_cond_read_acquire(&lock->cnts, VAL == _QW_WAITING); - } while (atomic_cmpxchg_relaxed(&lock->cnts, _QW_WAITING, - _QW_LOCKED) != _QW_WAITING); + cnts = atomic_cond_read_relaxed(&lock->cnts, VAL == _QW_WAITING); + } while (!atomic_try_cmpxchg_acquire(&lock->cnts, &cnts, _QW_LOCKED)); unlock: arch_spin_unlock(&lock->wait_lock); }