Commit f793fab4 authored Oct 21, 2024 by Tian Lan Committed by Zheng Qixing Oct 21, 2024

blk-mq: fix blk_mq_hw_ctx active request accounting

mainline inclusion
from mainline-v6.4-rc6
commit ddad5933
category: panic
bugzilla: https://gitee.com/openeuler/kernel/issues/IAWGLV

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=ddad59331a4e16088468ca0ad228a9fe32d7955a



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

The nr_active counter continues to increase over time which causes the
blk_mq_get_tag to hang until the thread is rescheduled to a different
core despite there are still tags available.

kernel-stack

  INFO: task inboundIOReacto:3014879 blocked for more than 2 seconds
  Not tainted 6.1.15-amd64 #1 Debian 6.1.15~debian11
  "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
  task:inboundIOReacto state:D stack:0  pid:3014879 ppid:4557 flags:0x00000000
    Call Trace:
    <TASK>
    __schedule+0x351/0xa20
    scheduler+0x5d/0xe0
    io_schedule+0x42/0x70
    blk_mq_get_tag+0x11a/0x2a0
    ? dequeue_task_stop+0x70/0x70
    __blk_mq_alloc_requests+0x191/0x2e0

kprobe output showing RQF_MQ_INFLIGHT bit is not cleared before
__blk_mq_free_request being called.

  320    320  kworker/29:1H __blk_mq_free_request rq_flags 0x220c0 in-flight 1
         b'__blk_mq_free_request+0x1 [kernel]'
         b'bt_iter+0x50 [kernel]'
         b'blk_mq_queue_tag_busy_iter+0x318 [kernel]'
         b'blk_mq_timeout_work+0x7c [kernel]'
         b'process_one_work+0x1c4 [kernel]'
         b'worker_thread+0x4d [kernel]'
         b'kthread+0xe6 [kernel]'
         b'ret_from_fork+0x1f [kernel]'

Signed-off-by: Tian Lan <tian.lan@twosigma.com>
Fixes: 2e315dc0 ("blk-mq: grab rq->refcount before calling ->fn in blk_mq_tagset_busy_iter")
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20230513221227.497327-1-tilan7663@gmail.com


Signed-off-by: Jens Axboe <axboe@kernel.dk>

Conflicts:
            block/blk-mq.c
[The conflict here is caused by the introduction of commit a668e8669590
("blk-mq: allow hardware queue to get more tag while sharing a tag set"),
which depends on this patch.]
Signed-off-by: Zheng Qixing <zhengqixing@huawei.com>

parent 49ac4302

block/blk-mq.c

+9 −8

Original line number	Diff line number	Diff line
		@@ -577,6 +577,15 @@ static void __blk_mq_free_request(struct request *rq)
		blk_crypto_free_request(rq);
		blk_pm_mark_last_busy(rq);
		rq->mq_hctx = NULL;

		if (rq->rq_flags & RQF_MQ_INFLIGHT) {
		__blk_mq_dec_active_requests(hctx);
		if (mq_unfair_dtag && !__blk_mq_active_requests(hctx)) {
		blk_mq_tag_idle(hctx);
		blk_mq_dtag_idle(hctx, true);
		}
		}

		if (rq->tag != BLK_MQ_NO_TAG)
		blk_mq_put_tag(hctx->tags, ctx, rq->tag);
		if (sched_tag != BLK_MQ_NO_TAG)
		@@ -590,7 +599,6 @@ void blk_mq_free_request(struct request *rq)
		struct request_queue *q = rq->q;
		struct elevator_queue *e = q->elevator;
		struct blk_mq_ctx *ctx = rq->mq_ctx;
		struct blk_mq_hw_ctx *hctx = rq->mq_hctx;

		if (rq->rq_flags & RQF_ELVPRIV) {
		if (e && e->type->ops.finish_request)
		@@ -602,13 +610,6 @@ void blk_mq_free_request(struct request *rq)
		}

		ctx->rq_completed[rq_is_sync(rq)]++;
		if (rq->rq_flags & RQF_MQ_INFLIGHT) {
		__blk_mq_dec_active_requests(hctx);
		if (mq_unfair_dtag && !__blk_mq_active_requests(hctx)) {
		blk_mq_tag_idle(hctx);
		blk_mq_dtag_idle(hctx, true);
		}
		}

		if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
		laptop_io_completion(q->backing_dev_info);