[PATCH 3.16 247/247] futex: Unbreak futex hashing

From: Ben Hutchings
Date: Fri Apr 24 2020 - 11:49:44 EST


3.16.83-rc2 review patch. If anyone has any objections, please let me know.

------------------

From: Thomas Gleixner <tglx@xxxxxxxxxxxxx>

commit 8d67743653dce5a0e7aa500fcccb237cde7ad88e upstream.

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: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
Cc: Jann Horn <jannh@xxxxxxxxxx>
---
kernel/futex.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)

--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -309,9 +309,9 @@ static inline int hb_waiters_pending(str
*/
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)];
}