diff options
| author | Keith Busch <kbusch@kernel.org> | 2019-09-06 11:23:08 -0600 |
|---|---|---|
| committer | Keith Busch <kbusch@kernel.org> | 2019-10-14 23:21:54 +0900 |
| commit | 4c75f877853cfa81b12374a07208e07b077f39b8 (patch) | |
| tree | dcac648e8a57d4661743094f6ec2c565d36132ee /drivers/nvme/host | |
| parent | 92b98e88d59ab17e65f261fbb5db272143ccf414 (diff) | |
nvme: Prevent resets during paused controller state
A paused controller is doing critical internal activation work in the
background. Prevent subsequent controller resets from occurring during
this period by setting the controller state to RESETTING first. A helper
function, nvme_try_sched_reset_work(), is introduced for these paths so
they may continue with scheduling the reset_work after they've completed
their uninterruptible critical section.
Tested-by: Edmund Nadolski <edmund.nadolski@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Diffstat (limited to 'drivers/nvme/host')
| -rw-r--r-- | drivers/nvme/host/core.c | 29 |
1 files changed, 25 insertions, 4 deletions
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index e451e77005dc..e94fa693dd4b 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -120,6 +120,21 @@ static void nvme_queue_scan(struct nvme_ctrl *ctrl) queue_work(nvme_wq, &ctrl->scan_work); } +/* + * Use this function to proceed with scheduling reset_work for a controller + * that had previously been set to the resetting state. This is intended for + * code paths that can't be interrupted by other reset attempts. A hot removal + * may prevent this from succeeding. + */ +static int nvme_try_sched_reset(struct nvme_ctrl *ctrl) +{ + if (ctrl->state != NVME_CTRL_RESETTING) + return -EBUSY; + if (!queue_work(nvme_reset_wq, &ctrl->reset_work)) + return -EBUSY; + return 0; +} + int nvme_reset_ctrl(struct nvme_ctrl *ctrl) { if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) @@ -3828,13 +3843,13 @@ static void nvme_fw_act_work(struct work_struct *work) if (time_after(jiffies, fw_act_timeout)) { dev_warn(ctrl->device, "Fw activation timeout, reset controller\n"); - nvme_reset_ctrl(ctrl); - break; + nvme_try_sched_reset(ctrl); + return; } msleep(100); } - if (ctrl->state != NVME_CTRL_LIVE) + if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE)) return; nvme_start_queues(ctrl); @@ -3854,7 +3869,13 @@ static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result) nvme_queue_scan(ctrl); break; case NVME_AER_NOTICE_FW_ACT_STARTING: - queue_work(nvme_wq, &ctrl->fw_act_work); + /* + * We are (ab)using the RESETTING state to prevent subsequent + * recovery actions from interfering with the controller's + * firmware activation. + */ + if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) + queue_work(nvme_wq, &ctrl->fw_act_work); break; #ifdef CONFIG_NVME_MULTIPATH case NVME_AER_NOTICE_ANA: |