From: Nilay Shroff nilay@linux.ibm.com
[ 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@linux.ibm.c... Signed-off-by: Nilay Shroff nilay@linux.ibm.com Reviewed-by: Sagi Grimberg sagi@grimberg.me Signed-off-by: Keith Busch kbusch@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/core.c | 21 --------------------- drivers/nvme/host/nvme.h | 21 +++++++++++++++++++++ drivers/nvme/host/pci.c | 8 +++++++- 3 files changed, 28 insertions(+), 22 deletions(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index fe3627c5bdc99..01702bc1baf1e 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 7b87763e2f8a6..5a09879cb1a5f 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -740,6 +740,27 @@ 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 8e0bb9692685d..e393f6947ce49 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))