diff options
| author | Keith Busch <kbusch@kernel.org> | 2023-10-27 10:58:12 -0700 |
|---|---|---|
| committer | Keith Busch <kbusch@kernel.org> | 2023-12-04 08:39:03 -0800 |
| commit | e6e7f7ac03e40795346f1b2994a05f507ad8d345 (patch) | |
| tree | 3e48f621f67d05ce07d4c6f71b6ac16a1f346206 /drivers/nvme/host/rdma.c | |
| parent | 5c687c287c46fadb14644091823298875a5216aa (diff) | |
nvme: ensure reset state check ordering
A different CPU may be setting the ctrl->state value, so ensure proper
barriers to prevent optimizing to a stale state. Normally it isn't a
problem to observe the wrong state as it is merely advisory to take a
quicker path during initialization and error recovery, but seeing an old
state can report unexpected ENETRESET errors when a reset request was in
fact successful.
Reported-by: Minh Hoang <mh2022@meta.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Diffstat (limited to 'drivers/nvme/host/rdma.c')
| -rw-r--r-- | drivers/nvme/host/rdma.c | 23 |
1 files changed, 14 insertions, 9 deletions
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 6d178d555920..81e2621169e5 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -984,10 +984,11 @@ free_ctrl: static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl) { + enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl); + /* If we are resetting/deleting then do nothing */ - if (ctrl->ctrl.state != NVME_CTRL_CONNECTING) { - WARN_ON_ONCE(ctrl->ctrl.state == NVME_CTRL_NEW || - ctrl->ctrl.state == NVME_CTRL_LIVE); + if (state != NVME_CTRL_CONNECTING) { + WARN_ON_ONCE(state == NVME_CTRL_NEW || state == NVME_CTRL_LIVE); return; } @@ -1059,8 +1060,10 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new) * unless we're during creation of a new controller to * avoid races with teardown flow. */ - WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING && - ctrl->ctrl.state != NVME_CTRL_DELETING_NOIO); + enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl); + + WARN_ON_ONCE(state != NVME_CTRL_DELETING && + state != NVME_CTRL_DELETING_NOIO); WARN_ON_ONCE(new); ret = -EINVAL; goto destroy_io; @@ -1129,8 +1132,10 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work) if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) { /* state change failure is ok if we started ctrl delete */ - WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING && - ctrl->ctrl.state != NVME_CTRL_DELETING_NOIO); + enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl); + + WARN_ON_ONCE(state != NVME_CTRL_DELETING && + state != NVME_CTRL_DELETING_NOIO); return; } @@ -1162,7 +1167,7 @@ static void nvme_rdma_wr_error(struct ib_cq *cq, struct ib_wc *wc, struct nvme_rdma_queue *queue = wc->qp->qp_context; struct nvme_rdma_ctrl *ctrl = queue->ctrl; - if (ctrl->ctrl.state == NVME_CTRL_LIVE) + if (nvme_ctrl_state(&ctrl->ctrl) == NVME_CTRL_LIVE) dev_info(ctrl->ctrl.device, "%s for CQE 0x%p failed with status %s (%d)\n", op, wc->wr_cqe, @@ -1945,7 +1950,7 @@ static enum blk_eh_timer_return nvme_rdma_timeout(struct request *rq) dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n", rq->tag, nvme_rdma_queue_idx(queue)); - if (ctrl->ctrl.state != NVME_CTRL_LIVE) { + if (nvme_ctrl_state(&ctrl->ctrl) != NVME_CTRL_LIVE) { /* * If we are resetting, connecting or deleting we should * complete immediately because we may block controller |