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/[email protected]/
Signed-off-by: Nilay Shroff <[email protected]>
Reviewed-by: Sagi Grimberg <[email protected]>
Signed-off-by: Keith Busch <[email protected]>
}
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.
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);
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.
*/
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))