From: Thomas Gleixner <tglx@xxxxxxxxxxxxx> [ Upstream commit 8d67743653dce5a0e7aa500fcccb237cde7ad88e ] The recent futex inode life time fix changed the ordering of the futex key union struct members, but forgot to adjust the hash function accordingly, As a result the hashing omits the leading 64bit and even hashes beyond the futex key causing a bad hash distribution which led to a ~100% performance regression. Hand in the futex key pointer instead of a random struct member and make the size calculation based of the struct offset. Fixes: 8019ad13ef7f ("futex: Fix inode life-time issue") Reported-by: Rong Chen <rong.a.chen@xxxxxxxxx> Decoded-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx> Tested-by: Rong Chen <rong.a.chen@xxxxxxxxx> Link: https://lkml.kernel.org/r/87h7yy90ve.fsf@xxxxxxxxxxxxxxxxxxxxxxx Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx> --- kernel/futex.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/futex.c b/kernel/futex.c index 07ab324885ac0..5660c02b01b05 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -385,9 +385,9 @@ static inline int hb_waiters_pending(struct futex_hash_bucket *hb) */ static struct futex_hash_bucket *hash_futex(union futex_key *key) { - u32 hash = jhash2((u32*)&key->both.word, - (sizeof(key->both.word)+sizeof(key->both.ptr))/4, + u32 hash = jhash2((u32 *)key, offsetof(typeof(*key), both.offset) / 4, key->both.offset); + return &futex_queues[hash & (futex_hashsize - 1)]; } -- 2.20.1