summaryrefslogtreecommitdiffstats
path: root/drivers/nvme
diff options
context:
space:
mode:
authorSagi Grimberg <sagi@grimberg.me>2017-12-21 14:54:15 +0200
committerChristoph Hellwig <hch@lst.de>2017-12-29 10:32:58 +0100
commitd5bf4b7f437c250821d40c3e32158729e6b484ce (patch)
treecacb24c397bed920f821fffa6a826e3517f54731 /drivers/nvme
parentcee160fd34b459ace029653436319557a643795a (diff)
downloadlinux-d5bf4b7f437c250821d40c3e32158729e6b484ce.tar.bz2
nvme-rdma: fix concurrent reset and reconnect
Now ctrl state machine allows to transition from RESETTING to RECONNECTING. In nvme-rdma when we receive a rdma cm DISONNECTED event, we trigger nvme_rdma_error_recovery. This happens also when we execute a controller reset, issue a cm diconnect request and receive a cm disconnect reply, as a result, the reset work and the error recovery work can run concurrently. Until now the state machine prevented from the error recovery work from running as a result of a controller reset (RESETTING -> RECONNECTING was not allowed). To fix this, we adopt the FC state machine approach, we always transition from LIVE to RESETTING and only then to RECONNECTING. We do this both for the error recovery work and the controller reset work: 1. transition to RESETTING 2. teardown the controller association 3. transition to RECONNECTING This will restore the protection against reset work and error recovery work from concurrently running together. Fixes: 3cec7f9de448 ("nvme: allow controller RESETTING to RECONNECTING transition") Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Christoph Hellwig <hch@lst.de>
Diffstat (limited to 'drivers/nvme')
-rw-r--r--drivers/nvme/host/rdma.c14
1 files changed, 13 insertions, 1 deletions
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 37af56596be6..2a0bba7f50cf 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -974,12 +974,18 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
nvme_start_queues(&ctrl->ctrl);
+ if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) {
+ /* state change failure should never happen */
+ WARN_ON_ONCE(1);
+ return;
+ }
+
nvme_rdma_reconnect_or_remove(ctrl);
}
static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl)
{
- if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING))
+ if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING))
return;
queue_work(nvme_wq, &ctrl->err_work);
@@ -1753,6 +1759,12 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
nvme_stop_ctrl(&ctrl->ctrl);
nvme_rdma_shutdown_ctrl(ctrl, false);
+ if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) {
+ /* state change failure should never happen */
+ WARN_ON_ONCE(1);
+ return;
+ }
+
ret = nvme_rdma_configure_admin_queue(ctrl, false);
if (ret)
goto out_fail;