This enables the nvme driver to trigger a device coredump when command timeout occurs, and it helps diagnose and debug issues.
This can be tested with fail_io_timeout fault injection. # echo 1 > /sys/kernel/debug/fail_io_timeout/probability # echo 1 > /sys/kernel/debug/fail_io_timeout/times # echo 1 > /sys/block/nvme0n1/io-timeout-fail # dd if=/dev/nvme0n1 of=/dev/null Cc: Johannes Berg <johan...@sipsolutions.net> Cc: Keith Busch <keith.bu...@intel.com> Cc: Jens Axboe <ax...@fb.com> Cc: Christoph Hellwig <h...@lst.de> Cc: Sagi Grimberg <s...@grimberg.me> Cc: Minwoo Im <minwoo.im....@gmail.com> Cc: Kenneth Heitke <kenneth.hei...@intel.com> Cc: Chaitanya Kulkarni <chaitanya.kulka...@wdc.com> Signed-off-by: Akinobu Mita <akinobu.m...@gmail.com> --- * v4 - Abandon the reset if nvme_coredump_logs() returns error code drivers/nvme/host/pci.c | 41 +++++++++++++++++++++++++---------------- 1 file changed, 25 insertions(+), 16 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 8a29c52..6436e72 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -87,12 +87,12 @@ MODULE_PARM_DESC(poll_queues, "Number of queues to use for polled IO."); struct nvme_dev; struct nvme_queue; -static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown); +static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown, bool dump); static bool __nvme_disable_io_queues(struct nvme_dev *dev, u8 opcode); -static void __maybe_unused nvme_coredump_init(struct nvme_dev *dev); -static int __maybe_unused nvme_coredump_logs(struct nvme_dev *dev); -static void __maybe_unused nvme_coredump_complete(struct nvme_dev *dev); +static void nvme_coredump_init(struct nvme_dev *dev); +static int nvme_coredump_logs(struct nvme_dev *dev); +static void nvme_coredump_complete(struct nvme_dev *dev); /* * Represents an NVM Express device. Each nvme_dev is a PCI function. @@ -1280,7 +1280,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) */ if (nvme_should_reset(dev, csts)) { nvme_warn_reset(dev, csts); - nvme_dev_disable(dev, false); + nvme_dev_disable(dev, false, true); nvme_reset_ctrl(&dev->ctrl); return BLK_EH_DONE; } @@ -1310,7 +1310,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) dev_warn_ratelimited(dev->ctrl.device, "I/O %d QID %d timeout, disable controller\n", req->tag, nvmeq->qid); - nvme_dev_disable(dev, shutdown); + nvme_dev_disable(dev, shutdown, true); nvme_req(req)->flags |= NVME_REQ_CANCELLED; return BLK_EH_DONE; default: @@ -1326,7 +1326,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) dev_warn(dev->ctrl.device, "I/O %d QID %d timeout, reset controller\n", req->tag, nvmeq->qid); - nvme_dev_disable(dev, false); + nvme_dev_disable(dev, false, true); nvme_reset_ctrl(&dev->ctrl); nvme_req(req)->flags |= NVME_REQ_CANCELLED; @@ -2382,7 +2382,7 @@ static void nvme_pci_disable(struct nvme_dev *dev) } } -static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) +static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown, bool dump) { bool dead = true; struct pci_dev *pdev = to_pci_dev(dev->dev); @@ -2407,6 +2407,9 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) nvme_wait_freeze_timeout(&dev->ctrl, NVME_IO_TIMEOUT); } + if (dump) + nvme_coredump_init(dev); + nvme_stop_queues(&dev->ctrl); if (!dead && dev->ctrl.queue_count > 0) { @@ -2477,7 +2480,7 @@ static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status) dev_warn(dev->ctrl.device, "Removing after probe failure status: %d\n", status); nvme_get_ctrl(&dev->ctrl); - nvme_dev_disable(dev, false); + nvme_dev_disable(dev, false, false); nvme_kill_queues(&dev->ctrl); if (!queue_work(nvme_wq, &dev->remove_work)) nvme_put_ctrl(&dev->ctrl); @@ -2499,7 +2502,7 @@ static void nvme_reset_work(struct work_struct *work) * moving on. */ if (dev->ctrl.ctrl_config & NVME_CC_ENABLE) - nvme_dev_disable(dev, false); + nvme_dev_disable(dev, false, false); mutex_lock(&dev->shutdown_lock); result = nvme_pci_enable(dev); @@ -2536,6 +2539,11 @@ static void nvme_reset_work(struct work_struct *work) if (result) goto out; + result = nvme_coredump_logs(dev); + if (result) + goto out; + nvme_coredump_complete(dev); + if (dev->ctrl.oacs & NVME_CTRL_OACS_SEC_SUPP) { if (!dev->ctrl.opal_dev) dev->ctrl.opal_dev = @@ -2598,6 +2606,7 @@ static void nvme_reset_work(struct work_struct *work) out_unlock: mutex_unlock(&dev->shutdown_lock); out: + nvme_coredump_complete(dev); nvme_remove_dead_ctrl(dev, result); } @@ -2788,7 +2797,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) static void nvme_reset_prepare(struct pci_dev *pdev) { struct nvme_dev *dev = pci_get_drvdata(pdev); - nvme_dev_disable(dev, false); + nvme_dev_disable(dev, false, false); } static void nvme_reset_done(struct pci_dev *pdev) @@ -2800,7 +2809,7 @@ static void nvme_reset_done(struct pci_dev *pdev) static void nvme_shutdown(struct pci_dev *pdev) { struct nvme_dev *dev = pci_get_drvdata(pdev); - nvme_dev_disable(dev, true); + nvme_dev_disable(dev, true, false); } /* @@ -2817,14 +2826,14 @@ static void nvme_remove(struct pci_dev *pdev) if (!pci_device_is_present(pdev)) { nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DEAD); - nvme_dev_disable(dev, true); + nvme_dev_disable(dev, true, false); nvme_dev_remove_admin(dev); } flush_work(&dev->ctrl.reset_work); nvme_stop_ctrl(&dev->ctrl); nvme_remove_namespaces(&dev->ctrl); - nvme_dev_disable(dev, true); + nvme_dev_disable(dev, true, false); nvme_release_cmb(dev); nvme_free_host_mem(dev); nvme_dev_remove_admin(dev); @@ -2841,7 +2850,7 @@ static int nvme_suspend(struct device *dev) struct pci_dev *pdev = to_pci_dev(dev); struct nvme_dev *ndev = pci_get_drvdata(pdev); - nvme_dev_disable(ndev, true); + nvme_dev_disable(ndev, true, false); return 0; } @@ -3290,7 +3299,7 @@ static pci_ers_result_t nvme_error_detected(struct pci_dev *pdev, case pci_channel_io_frozen: dev_warn(dev->ctrl.device, "frozen state error detected, reset controller\n"); - nvme_dev_disable(dev, false); + nvme_dev_disable(dev, false, false); return PCI_ERS_RESULT_NEED_RESET; case pci_channel_io_perm_failure: dev_warn(dev->ctrl.device, -- 2.7.4