nvmet: loop: kill timeout handler
Subsystems (2)
PATCH 1/1 nvmet: loop: kill timeout handler
Firstly it doesn't make sense to handle timeout for loop: 1) for admin queue, the request is always completed in code path of queuing IO. 2) for normal IO request, the timeout on these IOs have been handled by underlying queue already.
Secondly nvme-loop's timeout handler is simply broken, and easy to cause issue: 1) no any sync/protection between timeout and normal completion, and now it is driver's responsibility to deal with that; 2) bad reset implementation, blk_mq_update_nr_hw_queues() is called after all NSs's queue is stopped(quiesced), and easy to trigger deadlock.
So kill the timeout handler.
--- drivers/nvme/target/loop.c | 16 ---------------- 1 file changed, 16 deletions(-)
drivers/nvme/target/loop.c +0 -16
@@ -129,20 +129,6 @@ static void nvme_loop_execute_work(struct work_struct *work)nvmet_req_execute (&iod->req); } -static enum blk_eh_timer_return -nvme_loop_timeout (struct request *rq,bool reserved) -{ -struct nvme_loop_iod *iod =blk_mq_rq_to_pdu (rq); - -/* queue error recovery */ -nvme_reset_ctrl (&iod->queue->ctrl->ctrl); - -/* fail with DNR on admin cmd timeout */ -nvme_req (rq)->status =NVME_SC_ABORT_REQ |NVME_SC_DNR ; - -return BLK_EH_DONE ; -} -static blk_status_t nvme_loop_queue_rq (struct blk_mq_hw_ctx *hctx,const struct blk_mq_queue_data *bd) {
@@ -253,7 +239,6 @@ static const struct blk_mq_ops nvme_loop_mq_ops = { .complete = nvme_loop_complete_rq, .init_request = nvme_loop_init_request, .init_hctx = nvme_loop_init_hctx, - .timeout = nvme_loop_timeout, };static const struct blk_mq_ops nvme_loop_admin_mq_ops = {
@@ -261,7 +246,6 @@ static const struct blk_mq_ops nvme_loop_admin_mq_ops = { .complete = nvme_loop_complete_rq, .init_request = nvme_loop_init_request, .init_hctx = nvme_loop_init_admin_hctx, - .timeout = nvme_loop_timeout, };static void nvme_loop_destroy_admin_queue (struct nvme_loop_ctrl *ctrl)
Signature · 1 line
2.9.5
PATCH 1/1 nvmet: loop: kill timeout handler
Quoted 69 lines · Ming Lei
Firstly it doesn't make sense to handle timeout for loop: 1) for admin queue, the request is always completed in code path of queuing IO. 2) for normal IO request, the timeout on these IOs have been handled by underlying queue already.
Secondly nvme-loop's timeout handler is simply broken, and easy to cause issue: 1) no any sync/protection between timeout and normal completion, and now it is driver's responsibility to deal with that; 2) bad reset implementation,
blk_mq_update_nr_hw_queues()is called after all NSs's queue is stopped(quiesced), and easy to trigger deadlock.So kill the timeout handler.
Cc Keith Busch <keith.busch at intel.com>Cc James Smart <jsmart2021 at gmail.com>Cc Hannes Reinecke <hare at suse.de>Cc Sagi Grimberg <sagi at grimberg.me>Signed-off-by Ming Lei <ming.lei at redhat.com>--- drivers/nvme/target/loop.c | 16 ---------------- 1 file changed, 16 deletions(-)drivers/nvme/target/loop.c +0
-17@@ -129,20 +129,6 @@ static void nvme_loop_execute_work(struct work_struct *work)nvmet_req_execute (&iod->req); } -static enum blk_eh_timer_return -nvme_loop_timeout (struct request *rq,bool reserved) -{ -struct nvme_loop_iod *iod =blk_mq_rq_to_pdu (rq); - -/* queue error recovery */ -nvme_reset_ctrl (&iod->queue->ctrl->ctrl); - -/* fail with DNR on admin cmd timeout */ -nvme_req (rq)->status =NVME_SC_ABORT_REQ |NVME_SC_DNR ; - -return BLK_EH_DONE ; -} -static blk_status_t nvme_loop_queue_rq (struct blk_mq_hw_ctx *hctx,const struct blk_mq_queue_data *bd) {@@ -253,7 +239,6 @@ static const struct blk_mq_ops nvme_loop_mq_ops = { .complete = nvme_loop_complete_rq, .init_request = nvme_loop_init_request, .init_hctx = nvme_loop_init_hctx, - .timeout = nvme_loop_timeout, };static const struct blk_mq_ops nvme_loop_admin_mq_ops = {@@ -261,7 +246,6 @@ static const struct blk_mq_ops nvme_loop_admin_mq_ops = { .complete = nvme_loop_complete_rq, .init_request = nvme_loop_init_request, .init_hctx = nvme_loop_init_admin_hctx, - .timeout = nvme_loop_timeout, };static void nvme_loop_destroy_admin_queue (struct nvme_loop_ctrl *ctrl) --2.9.5
Quoted 4 lines
_______________________________________________
Linux-nvme mailing list
Linux-nvme at lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme
Ping...
Thanks,
Ming Lei
Keith Busch
maintainerPATCH 1/1 nvmet: loop: kill timeout handler
In reply to Ming LeiQuoted 5 lines · Ming Lei
Firstly it doesn't make sense to handle timeout for loop: 1) for admin queue, the request is always completed in code path of queuing IO. 2) for normal IO request, the timeout on these IOs have been handled by underlying queue already.
Quoted 8 lines
Secondly nvme-loop's timeout handler is simply broken, and easy to cause issue: 1) no any sync/protection between timeout and normal completion, and now it is driver's responsibility to deal with that; 2) bad reset implementation,
blk_mq_update_nr_hw_queues()is called after all NSs's queue is stopped(quiesced), and easy to trigger deadlock.So kill the timeout handler.
Makes sense to me, looks good.
Reviewd-by: Keith Busch <keith.busch at intel.com>
Sagi Grimberg
maintainerPATCH 1/1 nvmet: loop: kill timeout handler
In reply to Ming LeiPATCH 1/1 nvmet: loop: kill timeout handler
In reply to Ming LeiThanks,
applied to nvme-5.2.