From a89e9e234a84bf9a67586f57f4e027c880439383 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Sat, 31 Oct 2015 10:53:50 +1100 Subject: md/raid5: fix locking in handle_stripe_clean_event() commit b8a9d66d043ffac116100775a469f05f5158c16f upstream. After commit 566c09c53455 ("raid5: relieve lock contention in get_active_stripe()") __find_stripe() is called under conf->hash_locks + hash. But handle_stripe_clean_event() calls remove_hash() under conf->device_lock. Under some cirscumstances the hash chain can be circuited, and we get an infinite loop with disabled interrupts and locked hash lock in __find_stripe(). This leads to hard lockup on multiple CPUs and following system crash. I was able to reproduce this behavior on raid6 over 6 ssd disks. The devices_handle_discard_safely option should be set to enable trim support. The following script was used: for i in `seq 1 32`; do dd if=/dev/zero of=large$i bs=10M count=100 & done neilb: original was against a 3.x kernel. I forward-ported to 4.3-rc. This verison is suitable for any kernel since Commit: 59fc630b8b5f ("RAID5: batch adjacent full stripe write") (v4.1+). I'll post a version for earlier kernels to stable. Signed-off-by: Roman Gushchin Fixes: 566c09c53455 ("raid5: relieve lock contention in get_active_stripe()") Signed-off-by: NeilBrown Cc: Shaohua Li Signed-off-by: Greg Kroah-Hartman --- drivers/md/raid5.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'drivers/md/raid5.c') diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 23af6772f146..0d767e31f455 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -3494,6 +3494,7 @@ returnbi: } if (!discard_pending && test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)) { + int hash; clear_bit(R5_Discard, &sh->dev[sh->pd_idx].flags); clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags); if (sh->qd_idx >= 0) { @@ -3507,16 +3508,17 @@ returnbi: * no updated data, so remove it from hash list and the stripe * will be reinitialized */ - spin_lock_irq(&conf->device_lock); unhash: + hash = sh->hash_lock_index; + spin_lock_irq(conf->hash_locks + hash); remove_hash(sh); + spin_unlock_irq(conf->hash_locks + hash); if (head_sh->batch_head) { sh = list_first_entry(&sh->batch_list, struct stripe_head, batch_list); if (sh != head_sh) goto unhash; } - spin_unlock_irq(&conf->device_lock); sh = head_sh; if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state)) -- cgit v1.2.3