This is a note to let you know that I've just added the patch titled
nvme: cancel pending I/O if nvme controller is in terminal state
to the 6.8-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
nvme-cancel-pending-i-o-if-nvme-controller-is-in-ter.patch
and it can be found in the queue-6.8 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 79f5dfbf40ab638d2acb11d815be819ac2c865d3
Author: Nilay Shroff <nilay@xxxxxxxxxxxxx>
Date: Thu Apr 25 19:33:00 2024 +0530
nvme: cancel pending I/O if nvme controller is in terminal state
[ Upstream commit 25bb3534ee21e39eb9301c4edd7182eb83cb0d07 ]
While I/O is running, if the pci bus error occurs then
in-flight I/O can not complete. Worst, if at this time,
user (logically) hot-unplug the nvme disk then the
nvme_remove() code path can't forward progress until
in-flight I/O is cancelled. So these sequence of events
may potentially hang hot-unplug code path indefinitely.
This patch helps cancel the pending/in-flight I/O from the
nvme request timeout handler in case the nvme controller
is in the terminal (DEAD/DELETING/DELETING_NOIO) state and
that helps nvme_remove() code path forward progress and
finish successfully.
Link: https://lore.kernel.org/all/199be893-5dfa-41e5-b6f2-40ac90ebccc4@xxxxxxxxxxxxx/
Signed-off-by: Nilay Shroff <nilay@xxxxxxxxxxxxx>
Reviewed-by: Sagi Grimberg <sagi@xxxxxxxxxxx>
Signed-off-by: Keith Busch <kbusch@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 26153cb7647d7..3cc79817e4d75 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -619,27 +619,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
}
EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);
-/*
- * Returns true for sink states that can't ever transition back to live.
- */
-static bool nvme_state_terminal(struct nvme_ctrl *ctrl)
-{
- switch (nvme_ctrl_state(ctrl)) {
- case NVME_CTRL_NEW:
- case NVME_CTRL_LIVE:
- case NVME_CTRL_RESETTING:
- case NVME_CTRL_CONNECTING:
- return false;
- case NVME_CTRL_DELETING:
- case NVME_CTRL_DELETING_NOIO:
- case NVME_CTRL_DEAD:
- return true;
- default:
- WARN_ONCE(1, "Unhandled ctrl state:%d", ctrl->state);
- return true;
- }
-}
-
/*
* Waits for the controller state to be resetting, or returns false if it is
* not possible to ever transition to that state.
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 738719085e054..2a7bf574284f6 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -745,6 +745,27 @@ static inline bool nvme_is_aen_req(u16 qid, __u16 command_id)
nvme_tag_from_cid(command_id) >= NVME_AQ_BLK_MQ_DEPTH;
}
+/*
+ * Returns true for sink states that can't ever transition back to live.
+ */
+static inline bool nvme_state_terminal(struct nvme_ctrl *ctrl)
+{
+ switch (nvme_ctrl_state(ctrl)) {
+ case NVME_CTRL_NEW:
+ case NVME_CTRL_LIVE:
+ case NVME_CTRL_RESETTING:
+ case NVME_CTRL_CONNECTING:
+ return false;
+ case NVME_CTRL_DELETING:
+ case NVME_CTRL_DELETING_NOIO:
+ case NVME_CTRL_DEAD:
+ return true;
+ default:
+ WARN_ONCE(1, "Unhandled ctrl state:%d", ctrl->state);
+ return true;
+ }
+}
+
void nvme_complete_rq(struct request *req);
void nvme_complete_batch_req(struct request *req);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 02565dc99ad85..710043086dffa 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1286,6 +1286,9 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
u32 csts = readl(dev->bar + NVME_REG_CSTS);
u8 opcode;
+ if (nvme_state_terminal(&dev->ctrl))
+ goto disable;
+
/* If PCI error recovery process is happening, we cannot reset or
* the recovery mechanism will surely fail.
*/
@@ -1390,8 +1393,11 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
return BLK_EH_RESET_TIMER;
disable:
- if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING))
+ if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING)) {
+ if (nvme_state_terminal(&dev->ctrl))
+ nvme_dev_disable(dev, true);
return BLK_EH_DONE;
+ }
nvme_dev_disable(dev, false);
if (nvme_try_sched_reset(&dev->ctrl))
