iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

nvme: cancel pending I/O if nvme controller is in terminal state

Browse Source 
[ 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.com/
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>
This commit is contained in:
Nilay Shroff 2024-04-25 19:33:00 +05:30 committed by Greg Kroah-Hartman
parent 2ab74bf282
commit b6eaa53f95
3 changed files with 28 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
drivers/nvme/host/core.c
View File

@ -587,27 +587,6 @@ 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.

21
drivers/nvme/host/nvme.h
View File

@ -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);

8
drivers/nvme/host/pci.c
View File

@ -1286,6 +1286,9 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
struct nvme_command cmd = { };
u32 csts = readl(dev->bar + NVME_REG_CSTS);
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.
*/
@ -1388,8 +1391,11 @@ 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))