shinys000114/linux
1
0
Fork 0
mirror of https://github.com/hardkernel/linux.git synced 2026-06-05 10:31:46 +09:00
Code Issues Packages Projects Releases Wiki Activity

nvme: fix reconnection fail due to reserved tag allocation

Browse Source 
[ Upstream commit de105068fead55ed5c07ade75e9c8e7f86a00d1d ]

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: ed01fee283 ("nvme-fabrics: only reserve a single tag")
Signed-off-by: Chunguang Xu <chunguang.xu@shopee.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
This commit is contained in:
Chunguang Xu
2024-03-11 10:09:27 +08:00
committed by Sasha Levin
parent 1883ed12d7
commit 149afee5c7
2 changed files with 4 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
drivers/nvme/host/core.c
View File

@@ -4971,7 +4971,8 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
set->ops = ops; set->ops = ops;
set->queue_depth = NVME_AQ_MQ_TAG_DEPTH; set->queue_depth = NVME_AQ_MQ_TAG_DEPTH;
if (ctrl->ops->flags & NVME_F_FABRICS) 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->numa_node = ctrl->numa_node;
set->flags = BLK_MQ_F_NO_SCHED; set->flags = BLK_MQ_F_NO_SCHED;
if (ctrl->ops->flags & NVME_F_BLOCKING) if (ctrl->ops->flags & NVME_F_BLOCKING)
@@ -5036,7 +5037,8 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
if (ctrl->quirks & NVME_QUIRK_SHARED_TAGS) if (ctrl->quirks & NVME_QUIRK_SHARED_TAGS)
set->reserved_tags = NVME_AQ_DEPTH; set->reserved_tags = NVME_AQ_DEPTH;
else if (ctrl->ops->flags & NVME_F_FABRICS) 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->numa_node = ctrl->numa_node;
set->flags = BLK_MQ_F_SHOULD_MERGE; set->flags = BLK_MQ_F_SHOULD_MERGE;
if (ctrl->ops->flags & NVME_F_BLOCKING) if (ctrl->ops->flags & NVME_F_BLOCKING)

7
drivers/nvme/host/fabrics.h
View File

@@ -18,13 +18,6 @@
/* default is -1: the fail fast mechanism is disabled */ /* default is -1: the fail fast mechanism is disabled */
#define NVMF_DEF_FAIL_FAST_TMO -1 #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 * 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 * allow the override it when creating controllers. This is both to provide