Commit de105068 authored by Chunguang Xu's avatar Chunguang Xu Committed by Keith Busch
Browse files

nvme: fix reconnection fail due to reserved tag allocation 



We found a issue on production environment while using NVMe over RDMA,
admin_q reconnect failed forever while remote target and network is ok.
After dig into it, we found it may caused by a ABBA deadlock due to tag
allocation. In my case, the tag was hold by a keep alive request
waiting inside admin_q, as we quiesced admin_q while reset ctrl, so the
request maked as idle and will not process before reset success. As
fabric_q shares tagset with admin_q, while reconnect remote target, we
need a tag for connect command, but the only one reserved tag was held
by keep alive command which waiting inside admin_q. As a result, we
failed to reconnect admin_q forever. In order to fix this issue, I
think we should keep two reserved tags for admin queue.

Fixes: ed01fee2 ("nvme-fabrics: only reserve a single tag")
Signed-off-by: default avatarChunguang Xu <chunguang.xu@shopee.com>
Reviewed-by: default avatarSagi Grimberg <sagi@grimberg.me>
Reviewed-by: default avatarChaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: default avatarChristoph Hellwig <hch@lst.de>
Signed-off-by: default avatarKeith Busch <kbusch@kernel.org>
parent 2bc91743

drivers/nvme/host/core.c

+4 −2
Original line number Diff line number Diff line
@@ -4385,7 +4385,8 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, 
	set->ops = ops;

	set->queue_depth = NVME_AQ_MQ_TAG_DEPTH;

	if (ctrl->ops->flags & NVME_F_FABRICS)

		set->reserved_tags = NVMF_RESERVED_TAGS;

		/* Reserved for fabric connect and keep alive */

		set->reserved_tags = 2;

	set->numa_node = ctrl->numa_node;

	set->flags = BLK_MQ_F_NO_SCHED;

	if (ctrl->ops->flags & NVME_F_BLOCKING)
@@ -4454,7 +4455,8 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, 
	if (ctrl->quirks & NVME_QUIRK_SHARED_TAGS)

		set->reserved_tags = NVME_AQ_DEPTH;

	else if (ctrl->ops->flags & NVME_F_FABRICS)

		set->reserved_tags = NVMF_RESERVED_TAGS;

		/* Reserved for fabric connect */

		set->reserved_tags = 1;

	set->numa_node = ctrl->numa_node;

	set->flags = BLK_MQ_F_SHOULD_MERGE;

	if (ctrl->ops->flags & NVME_F_BLOCKING)

drivers/nvme/host/fabrics.h

+0 −7
Original line number Diff line number Diff line
@@ -18,13 +18,6 @@ 
/* default is -1: the fail fast mechanism is disabled  */

#define NVMF_DEF_FAIL_FAST_TMO		-1



/*

 * Reserved one command for internal usage.  This command is used for sending

 * the connect command, as well as for the keep alive command on the admin

 * queue once live.

 */

#define NVMF_RESERVED_TAGS	1



/*

 * Define a host as seen by the target.  We allocate one at boot, but also

 * allow the override it when creating controllers.  This is both to provide