[PATCH 4/4] nvme-pci: trigger device coredump before resetting controller

From: Akinobu Mita
Date: Thu May 02 2019 - 05:00:10 EST


This enables the nvme driver to trigger a device coredump before resetting
the controller caused by I/O timeout.

The device coredump helps diagnose and debug issues.

Cc: Johannes Berg <johannes@xxxxxxxxxxxxxxxx>
Cc: Keith Busch <keith.busch@xxxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Sagi Grimberg <sagi@xxxxxxxxxxx>
Signed-off-by: Akinobu Mita <akinobu.mita@xxxxxxxxx>
---
drivers/nvme/host/pci.c | 31 ++++++++++++++++++-------------
1 file changed, 18 insertions(+), 13 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 7f3077c..584c2aa 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -87,7 +87,7 @@ 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);

/*
@@ -1286,7 +1286,7 @@ 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;
}
@@ -1313,7 +1313,7 @@ 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, false);
+ nvme_dev_disable(dev, false, true);
nvme_req(req)->flags |= NVME_REQ_CANCELLED;
return BLK_EH_DONE;
default:
@@ -1329,7 +1329,7 @@ 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;
@@ -2396,7 +2396,9 @@ static void nvme_pci_disable(struct nvme_dev *dev)
}
}

-static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
+static void nvme_coredump(struct device *dev);
+
+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);
@@ -2421,6 +2423,9 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
nvme_wait_freeze_timeout(&dev->ctrl, NVME_IO_TIMEOUT);
}

+ if (dump)
+ nvme_coredump(dev->dev);
+
nvme_stop_queues(&dev->ctrl);

if (!dead && dev->ctrl.queue_count > 0) {
@@ -2488,7 +2493,7 @@ 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);
@@ -2510,7 +2515,7 @@ 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);
@@ -2799,7 +2804,7 @@ 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)
@@ -2811,7 +2816,7 @@ 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);
}

/*
@@ -2828,14 +2833,14 @@ 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);
@@ -2852,7 +2857,7 @@ 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;
}

@@ -3103,7 +3108,7 @@ 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