md/raid5: fix locking in handle_stripe_clean_event()

Roman Gushchin · NeilBrown · commit b8a9d66d043f · 2015-10-31T10:53:50.000+11:00
After commit 566c09c ("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: 59fc630 ("RAID5: batch adjacent full stripe write") (v4.1+). I'll post a version for earlier kernels to stable. Signed-off-by: Roman Gushchin <klamm@yandex-team.ru> Fixes: 566c09c ("raid5: relieve lock contention in get_active_stripe()") Signed-off-by: NeilBrown <neilb@suse.com> Cc: Shaohua Li <shli@kernel.org> Cc: <stable@vger.kernel.org> # 3.13 - 4.2
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
@@ -3499,6 +3499,7 @@ static void handle_stripe_clean_event(struct r5conf *conf,
 		}
 	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) {
@@ -3512,16 +3513,17 @@ static void handle_stripe_clean_event(struct r5conf *conf,
 		 * 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))
