diff options
| author | Keith Busch <kbusch@kernel.org> | 2023-10-27 10:58:12 -0700 |
|---|---|---|
| committer | Keith Busch <kbusch@kernel.org> | 2023-12-04 08:39:03 -0800 |
| commit | e6e7f7ac03e40795346f1b2994a05f507ad8d345 (patch) | |
| tree | 3e48f621f67d05ce07d4c6f71b6ac16a1f346206 /drivers/nvme/host/pci.c | |
| parent | 5c687c287c46fadb14644091823298875a5216aa (diff) | |
nvme: ensure reset state check ordering
A different CPU may be setting the ctrl->state value, so ensure proper
barriers to prevent optimizing to a stale state. Normally it isn't a
problem to observe the wrong state as it is merely advisory to take a
quicker path during initialization and error recovery, but seeing an old
state can report unexpected ENETRESET errors when a reset request was in
fact successful.
Reported-by: Minh Hoang <mh2022@meta.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Diffstat (limited to 'drivers/nvme/host/pci.c')
| -rw-r--r-- | drivers/nvme/host/pci.c | 14 |
1 files changed, 7 insertions, 7 deletions
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 507bc149046d..fad4cccce745 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1233,7 +1233,7 @@ static bool nvme_should_reset(struct nvme_dev *dev, u32 csts) bool nssro = dev->subsystem && (csts & NVME_CSTS_NSSRO); /* If there is a reset/reinit ongoing, we shouldn't reset again. */ - switch (dev->ctrl.state) { + switch (nvme_ctrl_state(&dev->ctrl)) { case NVME_CTRL_RESETTING: case NVME_CTRL_CONNECTING: return false; @@ -1321,7 +1321,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) * cancellation error. All outstanding requests are completed on * shutdown, so we return BLK_EH_DONE. */ - switch (dev->ctrl.state) { + switch (nvme_ctrl_state(&dev->ctrl)) { case NVME_CTRL_CONNECTING: nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING); fallthrough; @@ -1593,7 +1593,7 @@ static int nvme_setup_io_queues_trylock(struct nvme_dev *dev) /* * Controller is in wrong state, fail early. */ - if (dev->ctrl.state != NVME_CTRL_CONNECTING) { + if (nvme_ctrl_state(&dev->ctrl) != NVME_CTRL_CONNECTING) { mutex_unlock(&dev->shutdown_lock); return -ENODEV; } @@ -2573,13 +2573,13 @@ static bool nvme_pci_ctrl_is_dead(struct nvme_dev *dev) static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) { + enum nvme_ctrl_state state = nvme_ctrl_state(&dev->ctrl); struct pci_dev *pdev = to_pci_dev(dev->dev); bool dead; mutex_lock(&dev->shutdown_lock); dead = nvme_pci_ctrl_is_dead(dev); - if (dev->ctrl.state == NVME_CTRL_LIVE || - dev->ctrl.state == NVME_CTRL_RESETTING) { + if (state == NVME_CTRL_LIVE || state == NVME_CTRL_RESETTING) { if (pci_is_enabled(pdev)) nvme_start_freeze(&dev->ctrl); /* @@ -2690,7 +2690,7 @@ static void nvme_reset_work(struct work_struct *work) bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL); int result; - if (dev->ctrl.state != NVME_CTRL_RESETTING) { + if (nvme_ctrl_state(&dev->ctrl) != NVME_CTRL_RESETTING) { dev_warn(dev->ctrl.device, "ctrl state %d is not RESETTING\n", dev->ctrl.state); result = -ENODEV; @@ -3192,7 +3192,7 @@ static int nvme_suspend(struct device *dev) nvme_wait_freeze(ctrl); nvme_sync_queues(ctrl); - if (ctrl->state != NVME_CTRL_LIVE) + if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE) goto unfreeze; /* |