On Wed, Oct 26, 2016 at 2:52 PM, Chris Mason <c...@fb.com> wrote: > > This one is special because CONFIG_VMAP_STACK is not set. Btrfs triggers in > < 10 minutes. > I've done 30 minutes each with XFS and Ext4 without luck.
Ok, see the email I wrote that crossed yours - if it's really some list corruption on ctx->rq_list due to some locking problem, I really would expect CONFIG_VMAP_STACK to be entirely irrelevant, except perhaps from a timing standpoint. > WARNING: CPU: 6 PID: 4481 at lib/list_debug.c:33 __list_add+0xbe/0xd0 > list_add corruption. prev->next should be next (ffffe8ffffd80b08), but was > ffff88012b65fb88. (prev=ffff880128c8d500). > Modules linked in: crc32c_intel aesni_intel aes_x86_64 glue_helper lrw > gf128mul ablk_helper i2c_piix4 cryptd i2c_core virtio_net serio_raw floppy > button pcspkr sch_fq_codel autofs4 virtio_blk > CPU: 6 PID: 4481 Comm: dbench Not tainted 4.9.0-rc2-15419-g811d54d #319 > Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.9.0-1.fc24 > 04/01/2014 > ffff880104eff868 ffffffff814fde0f ffffffff8151c46e ffff880104eff8c8 > ffff880104eff8c8 0000000000000000 ffff880104eff8b8 ffffffff810648cf > ffff880128cab2c0 000000213fc57c68 ffff8801384e8928 ffff880128cab180 > Call Trace: > [<ffffffff814fde0f>] dump_stack+0x53/0x74 > [<ffffffff8151c46e>] ? __list_add+0xbe/0xd0 > [<ffffffff810648cf>] __warn+0xff/0x120 > [<ffffffff810649a9>] warn_slowpath_fmt+0x49/0x50 > [<ffffffff8151c46e>] __list_add+0xbe/0xd0 > [<ffffffff814dec38>] blk_sq_make_request+0x388/0x580 > [<ffffffff814d5444>] generic_make_request+0x104/0x200 Well, it's very consistent, I have to say. So I really don't think this is random corruption. Could you try the attached patch? It adds a couple of sanity tests: - a number of tests to verify that 'rq->queuelist' isn't already on some queue when it is added to a queue - one test to verify that rq->mq_ctx is the same ctx that we have locked. I may be completely full of shit, and this patch may be pure garbage or "obviously will never trigger", but humor me. Linus
block/blk-mq.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/block/blk-mq.c b/block/blk-mq.c index ddc2eed64771..4f575de7fdd0 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -521,6 +521,8 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head) */ BUG_ON(rq->cmd_flags & REQ_SOFTBARRIER); +WARN_ON_ONCE(!list_empty(&rq->queuelist)); + spin_lock_irqsave(&q->requeue_lock, flags); if (at_head) { rq->cmd_flags |= REQ_SOFTBARRIER; @@ -838,6 +840,7 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx) queued++; break; case BLK_MQ_RQ_QUEUE_BUSY: +WARN_ON_ONCE(!list_empty(&rq->queuelist)); list_add(&rq->queuelist, &rq_list); __blk_mq_requeue_request(rq); break; @@ -1034,6 +1037,8 @@ static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx, trace_block_rq_insert(hctx->queue, rq); +WARN_ON_ONCE(!list_empty(&rq->queuelist)); + if (at_head) list_add(&rq->queuelist, &ctx->rq_list); else @@ -1137,6 +1142,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) depth = 0; } +WARN_ON_ONCE(!list_empty(&rq->queuelist)); depth++; list_add_tail(&rq->queuelist, &ctx_list); } @@ -1172,6 +1178,7 @@ static inline bool blk_mq_merge_queue_io(struct blk_mq_hw_ctx *hctx, blk_mq_bio_to_request(rq, bio); spin_lock(&ctx->lock); insert_rq: +WARN_ON_ONCE(rq->mq_ctx != ctx); __blk_mq_insert_request(hctx, rq, false); spin_unlock(&ctx->lock); return false; @@ -1326,6 +1333,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) old_rq = same_queue_rq; list_del_init(&old_rq->queuelist); } +WARN_ON_ONCE(!list_empty(&rq->queuelist)); list_add_tail(&rq->queuelist, &plug->mq_list); } else /* is_sync */ old_rq = rq; @@ -1412,6 +1420,7 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio) trace_block_plug(q); } +WARN_ON_ONCE(!list_empty(&rq->queuelist)); list_add_tail(&rq->queuelist, &plug->mq_list); return cookie; }