When the controller is being removed, blk_cleanup_queue will try
to drain the queues. At the moment, if the controller no response,
because of DELETEING state, reset_work will not be able to be
scheduled, and completion of the expired request is deferred to
nvme_dev_disable, blk_cleanup_queue will hang forever. Add case
for DELETEING in nvme_timeout, when abort fails, disable the
controller and complete the request directly.
Signed-off-by: Jianchao Wang <jianchao.w.w...@oracle.com>
---
drivers/nvme/host/pci.c | 27 +++++++++++++++++++++++----
1 file changed, 23 insertions(+), 4 deletions(-)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 6c7c19cb..ac9efcd 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1261,11 +1261,30 @@ static enum blk_eh_timer_return nvme_timeout(struct
request *req, bool reserved)
}
if (nvmeq->qid) {
- if (dev->ctrl.state == NVME_CTRL_RESETTING ||
- iod->aborted)
+ switch (dev->ctrl.state) {
+ case NVME_CTRL_RESETTING:
action = RESET;
- else
- action = ABORT;
+ break;
+ case NVME_CTRL_DELETING:
+ /*
+ * When ctrl is being removed, we try to abort the
+ * expired request first, if success, it will be
+ * requeued, otherwise, disable the controller and
+ * complete it directly, because we cannot schedule
+ * the reset_work to do recovery in DELELTING state.
+ */
+ if (iod->aborted)
+ action = DISABLE;
+ else
+ action = ABORT;
+ break;
+ default:
+ if (iod->aborted)
+ action = RESET;
+ else
+ action = ABORT;
+ break;
+ }
} else {
/*
* Disable immediately if controller times out while disabling/
--
2.7.4
