From: Akinobu Mita <akinobu.mita@gmail.com>
To: linux-nvme@lists.infradead.org, linux-kernel@vger.kernel.org
Cc: Akinobu Mita <akinobu.mita@gmail.com>,
Johannes Berg <johannes@sipsolutions.net>,
Keith Busch <keith.busch@intel.com>, Jens Axboe <axboe@fb.com>,
Christoph Hellwig <hch@lst.de>, Sagi Grimberg <sagi@grimberg.me>,
Minwoo Im <minwoo.im.dev@gmail.com>
Subject: [PATCH v2 7/7] nvme-pci: trigger device coredump on command timeout
Date: Wed, 8 May 2019 01:58:34 +0900 [thread overview]
Message-ID: <1557248314-4238-8-git-send-email-akinobu.mita@gmail.com> (raw)
In-Reply-To: <1557248314-4238-1-git-send-email-akinobu.mita@gmail.com>
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 <johannes@sipsolutions.net>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Jens Axboe <axboe@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: Minwoo Im <minwoo.im.dev@gmail.com>
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
---
- Make coredump procedure into two phases (before resetting controller and
after resetting as soon as admin queue is available).
drivers/nvme/host/pci.c | 35 ++++++++++++++++++++++-------------
1 file changed, 22 insertions(+), 13 deletions(-)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 4684a86..4ff918f 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -87,9 +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 int nvme_coredump_prologue(struct nvme_dev *dev);
+static void nvme_coredump_epilogue(struct nvme_dev *dev);
+
/*
* Represents an NVM Express device. Each nvme_dev is a PCI function.
*/
@@ -1289,7 +1292,7 @@ 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;
}
@@ -1316,7 +1319,7 @@ 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:
@@ -1332,7 +1335,7 @@ 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;
@@ -2399,7 +2402,7 @@ 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);
@@ -2424,6 +2427,9 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
nvme_wait_freeze_timeout(&dev->ctrl, NVME_IO_TIMEOUT);
}
+ if (dump)
+ nvme_coredump_prologue(dev);
+
nvme_stop_queues(&dev->ctrl);
if (!dead && dev->ctrl.queue_count > 0) {
@@ -2491,7 +2497,7 @@ 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);
@@ -2513,7 +2519,7 @@ 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);
@@ -2550,6 +2556,8 @@ static void nvme_reset_work(struct work_struct *work)
if (result)
goto out;
+ nvme_coredump_epilogue(dev);
+
if (dev->ctrl.oacs & NVME_CTRL_OACS_SEC_SUPP) {
if (!dev->ctrl.opal_dev)
dev->ctrl.opal_dev =
@@ -2612,6 +2620,7 @@ static void nvme_reset_work(struct work_struct *work)
out_unlock:
mutex_unlock(&dev->shutdown_lock);
out:
+ nvme_coredump_epilogue(dev);
nvme_remove_dead_ctrl(dev, result);
}
@@ -2802,7 +2811,7 @@ 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)
@@ -2814,7 +2823,7 @@ 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);
}
/*
@@ -2831,14 +2840,14 @@ 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);
@@ -2855,7 +2864,7 @@ 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;
}
@@ -3307,7 +3316,7 @@ 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
next prev parent reply other threads:[~2019-05-07 16:59 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-05-07 16:58 [PATCH v2 0/7] nvme-pci: support device coredump Akinobu Mita
2019-05-07 16:58 ` [PATCH v2 1/7] devcoredump: use memory_read_from_buffer Akinobu Mita
2019-05-07 16:58 ` [PATCH v2 2/7] devcoredump: fix typo in comment Akinobu Mita
2019-05-07 16:58 ` [PATCH v2 3/7] devcoredump: allow to create several coredump files in one device Akinobu Mita
2019-05-07 17:35 ` Heitke, Kenneth
2019-05-08 15:40 ` Akinobu Mita
2019-05-07 16:58 ` [PATCH v2 4/7] nvme.h: add telemetry log page definisions Akinobu Mita
2019-05-07 17:28 ` Heitke, Kenneth
2019-05-08 15:42 ` Akinobu Mita
2019-05-07 17:52 ` Heitke, Kenneth
2019-05-08 15:54 ` Akinobu Mita
2019-05-07 16:58 ` [PATCH v2 5/7] nvme: add facility to check log page attributes Akinobu Mita
2019-05-07 16:58 ` [PATCH v2 6/7] nvme-pci: add device coredump support Akinobu Mita
2019-05-07 17:07 ` Keith Busch
2019-05-07 17:44 ` Heitke, Kenneth
2019-05-07 20:31 ` Heitke, Kenneth
2019-05-07 21:22 ` Keith Busch
2019-05-08 15:56 ` Akinobu Mita
[not found] ` <CGME20190507171318epcas5p129bb73b39447d62a7d266ed461687488@epcms2p3>
2019-05-08 0:25 ` Minwoo Im
2019-05-08 16:02 ` Akinobu Mita
2019-05-07 16:58 ` Akinobu Mita [this message]
2019-05-07 17:43 ` [PATCH v2 0/7] nvme-pci: support device coredump Heitke, Kenneth
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1557248314-4238-8-git-send-email-akinobu.mita@gmail.com \
--to=akinobu.mita@gmail.com \
--cc=axboe@fb.com \
--cc=hch@lst.de \
--cc=johannes@sipsolutions.net \
--cc=keith.busch@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=minwoo.im.dev@gmail.com \
--cc=sagi@grimberg.me \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).