[PATCH v2 rfc 3/3] nvme-core: fix deadlock in disconnect during scan_work and/or ana_work
Sagi Grimberg
sagi at grimberg.me
Sun Jul 5 03:59:35 EDT 2020
A deadlock happens in the following scenario with multipath:
1) scan_work(nvme0) detects a new nsid while nvme0
is an optimized path to it, path nvme1 happens to be
inaccessible.
2) Before scan_work is complete nvme0 disconnect is initiated
nvme_delete_ctrl_sync() sets nvme0 state to NVME_CTRL_DELETING
3) scan_work(1) attempts to submit IO,
but nvme_path_is_optimized() observes nvme0 is not LIVE.
Since nvme1 is a possible path IO is requeued and scan_work hangs.
--
Workqueue: nvme-wq nvme_scan_work [nvme_core]
kernel: Call Trace:
kernel: __schedule+0x2b9/0x6c0
kernel: schedule+0x42/0xb0
kernel: io_schedule+0x16/0x40
kernel: do_read_cache_page+0x438/0x830
kernel: read_cache_page+0x12/0x20
kernel: read_dev_sector+0x27/0xc0
kernel: read_lba+0xc1/0x220
kernel: efi_partition+0x1e6/0x708
kernel: check_partition+0x154/0x244
kernel: rescan_partitions+0xae/0x280
kernel: __blkdev_get+0x40f/0x560
kernel: blkdev_get+0x3d/0x140
kernel: __device_add_disk+0x388/0x480
kernel: device_add_disk+0x13/0x20
kernel: nvme_mpath_set_live+0x119/0x140 [nvme_core]
kernel: nvme_update_ns_ana_state+0x5c/0x60 [nvme_core]
kernel: nvme_set_ns_ana_state+0x1e/0x30 [nvme_core]
kernel: nvme_parse_ana_log+0xa1/0x180 [nvme_core]
kernel: nvme_mpath_add_disk+0x47/0x90 [nvme_core]
kernel: nvme_validate_ns+0x396/0x940 [nvme_core]
kernel: nvme_scan_work+0x24f/0x380 [nvme_core]
kernel: process_one_work+0x1db/0x380
kernel: worker_thread+0x249/0x400
kernel: kthread+0x104/0x140
--
4) Delete also hangs in flush_work(ctrl->scan_work)
from nvme_remove_namespaces().
Similiarly a deadlock with ana_work may happen: if ana_work has started
and calls nvme_mpath_set_live and device_add_disk, it will
trigger I/O. When we trigger disconnect I/O will block because
our accessible (optimized) path is disconnecting, but the alternate
path is inaccessible, so I/O blocks. Then disconnect tries to flush
the ana_work and hangs.
[ 605.550896] Workqueue: nvme-wq nvme_ana_work [nvme_core]
[ 605.552087] Call Trace:
[ 605.552683] __schedule+0x2b9/0x6c0
[ 605.553507] schedule+0x42/0xb0
[ 605.554201] io_schedule+0x16/0x40
[ 605.555012] do_read_cache_page+0x438/0x830
[ 605.556925] read_cache_page+0x12/0x20
[ 605.557757] read_dev_sector+0x27/0xc0
[ 605.558587] amiga_partition+0x4d/0x4c5
[ 605.561278] check_partition+0x154/0x244
[ 605.562138] rescan_partitions+0xae/0x280
[ 605.563076] __blkdev_get+0x40f/0x560
[ 605.563830] blkdev_get+0x3d/0x140
[ 605.564500] __device_add_disk+0x388/0x480
[ 605.565316] device_add_disk+0x13/0x20
[ 605.566070] nvme_mpath_set_live+0x5e/0x130 [nvme_core]
[ 605.567114] nvme_update_ns_ana_state+0x2c/0x30 [nvme_core]
[ 605.568197] nvme_update_ana_state+0xca/0xe0 [nvme_core]
[ 605.569360] nvme_parse_ana_log+0xa1/0x180 [nvme_core]
[ 605.571385] nvme_read_ana_log+0x76/0x100 [nvme_core]
[ 605.572376] nvme_ana_work+0x15/0x20 [nvme_core]
[ 605.573330] process_one_work+0x1db/0x380
[ 605.574144] worker_thread+0x4d/0x400
[ 605.574896] kthread+0x104/0x140
[ 605.577205] ret_from_fork+0x35/0x40
[ 605.577955] INFO: task nvme:14044 blocked for more than 120 seconds.
[ 605.579239] Tainted: G OE 5.3.5-050305-generic #201910071830
[ 605.580712] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 605.582320] nvme D 0 14044 14043 0x00000000
[ 605.583424] Call Trace:
[ 605.583935] __schedule+0x2b9/0x6c0
[ 605.584625] schedule+0x42/0xb0
[ 605.585290] schedule_timeout+0x203/0x2f0
[ 605.588493] wait_for_completion+0xb1/0x120
[ 605.590066] __flush_work+0x123/0x1d0
[ 605.591758] __cancel_work_timer+0x10e/0x190
[ 605.593542] cancel_work_sync+0x10/0x20
[ 605.594347] nvme_mpath_stop+0x2f/0x40 [nvme_core]
[ 605.595328] nvme_stop_ctrl+0x12/0x50 [nvme_core]
[ 605.596262] nvme_do_delete_ctrl+0x3f/0x90 [nvme_core]
[ 605.597333] nvme_sysfs_delete+0x5c/0x70 [nvme_core]
[ 605.598320] dev_attr_store+0x17/0x30
Fix this by introducing a new state: NVME_CTRL_DELETE_NOIO, which will
indicate the phase of controller deletion where I/O cannot be allowed
to access the namespace. NVME_CTRL_DELETING still allows mpath I/O to
be issued to the bottom device, and only after we flush the ana_work
and scan_work (after nvme_stop_ctrl and nvme_prep_remove_namespaces)
we change the state to NVME_CTRL_DELETING_NOIO. Also we prevent ana_work
from re-firing by aborting early if we are not LIVE, so we should be safe
here.
In addition, change the transport drivers to follow the updated state
machine.
Fixes: 0d0b660f214d ("nvme: add ANA support")
Reported-by: Anton Eidelman <anton at lightbitslabs.com>
Signed-off-by: Sagi Grimberg <sagi at grimberg.me>
---
drivers/nvme/host/core.c | 16 +++++++++++++++-
drivers/nvme/host/fc.c | 1 +
drivers/nvme/host/multipath.c | 13 ++++++++++++-
drivers/nvme/host/nvme.h | 6 ++++++
drivers/nvme/host/pci.c | 4 +++-
drivers/nvme/host/rdma.c | 10 ++++++----
drivers/nvme/host/tcp.c | 15 +++++++++------
7 files changed, 52 insertions(+), 13 deletions(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index f1bb2a522cf0..c2f0e6cfea28 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -168,7 +168,9 @@ static void nvme_do_delete_ctrl(struct nvme_ctrl *ctrl)
flush_work(&ctrl->reset_work);
nvme_stop_ctrl(ctrl);
- nvme_remove_namespaces(ctrl);
+ nvme_prep_remove_namespaces(ctrl);
+ nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING_NOIO);
+ nvme_do_remove_namespaces(ctrl);
ctrl->ops->delete_ctrl(ctrl);
nvme_uninit_ctrl(ctrl);
}
@@ -366,6 +368,16 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
break;
}
break;
+ case NVME_CTRL_DELETING_NOIO:
+ switch (old_state) {
+ case NVME_CTRL_DELETING:
+ case NVME_CTRL_DEAD:
+ changed = true;
+ /* FALLTHRU */
+ default:
+ break;
+ }
+ break;
case NVME_CTRL_DEAD:
switch (old_state) {
case NVME_CTRL_DELETING:
@@ -403,6 +415,7 @@ static bool nvme_state_terminal(struct nvme_ctrl *ctrl)
case NVME_CTRL_CONNECTING:
return false;
case NVME_CTRL_DELETING:
+ case NVME_CTRL_DELETING_NOIO:
case NVME_CTRL_DEAD:
return true;
default:
@@ -3482,6 +3495,7 @@ static ssize_t nvme_sysfs_show_state(struct device *dev,
[NVME_CTRL_RESETTING] = "resetting",
[NVME_CTRL_CONNECTING] = "connecting",
[NVME_CTRL_DELETING] = "deleting",
+ [NVME_CTRL_DELETING_NOIO]= "deleting (no IO)",
[NVME_CTRL_DEAD] = "dead",
};
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index e999a8c4b7e8..549f5b0fb0b4 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -825,6 +825,7 @@ nvme_fc_ctrl_connectivity_loss(struct nvme_fc_ctrl *ctrl)
break;
case NVME_CTRL_DELETING:
+ case NVME_CTRL_DELETING_NOIO:
default:
/* no action to take - let it delete */
break;
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 6cf80f7cf6be..395f7d1d5c54 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -167,7 +167,15 @@ void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
static bool nvme_path_is_disabled(struct nvme_ns *ns)
{
- return ns->ctrl->state != NVME_CTRL_LIVE ||
+ /*
+ * We don't treat NVME_CTRL_DELETING as a disabled path
+ * as I/O should still be able to complete assuming that
+ * the controller is connected, otherwise it'll fail
+ * immediately and return to the requeue list. only fail
+ * for NVME_CTRL_DELETING_NOIO
+ */
+ return (ns->ctrl->state != NVME_CTRL_LIVE &&
+ ns->ctrl->state != NVME_CTRL_DELETING) ||
test_bit(NVME_NS_ANA_PENDING, &ns->flags) ||
test_bit(NVME_NS_REMOVING, &ns->flags);
}
@@ -565,6 +573,9 @@ static void nvme_ana_work(struct work_struct *work)
{
struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, ana_work);
+ if (ctrl->state != NVME_CTRL_LIVE)
+ return;
+
nvme_read_ana_log(ctrl);
}
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 0bffa0435e24..7762ce24df77 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -182,6 +182,11 @@ static inline u16 nvme_req_qid(struct request *req)
* @NVME_CTRL_CONNECTING: Controller is disconnected, now connecting the
* transport
* @NVME_CTRL_DELETING: Controller is deleting (or scheduled deletion)
+ * @NVME_CTRL_DELETING_NOIO: Controller is deleting and I/O is not
+ * disabled/failed immediately. This state comes
+ * after all async event processing took place and
+ * before ns removal and the controller deletion
+ * progress
* @NVME_CTRL_DEAD: Controller is non-present/unresponsive during
* shutdown or removal. In this case we forcibly
* kill all inflight I/O as they have no chance to
@@ -193,6 +198,7 @@ enum nvme_ctrl_state {
NVME_CTRL_RESETTING,
NVME_CTRL_CONNECTING,
NVME_CTRL_DELETING,
+ NVME_CTRL_DELETING_NOIO,
NVME_CTRL_DEAD,
};
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index c283e8dbfb86..e9d57682d021 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2898,7 +2898,9 @@ static void nvme_remove(struct pci_dev *pdev)
flush_work(&dev->ctrl.reset_work);
nvme_stop_ctrl(&dev->ctrl);
- nvme_remove_namespaces(&dev->ctrl);
+ nvme_prep_remove_namespaces(&dev->ctrl);
+ nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING_NOIO);
+ nvme_do_remove_namespaces(&dev->ctrl);
nvme_dev_disable(dev, true);
nvme_release_cmb(dev);
nvme_free_host_mem(dev);
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 13506a87a444..1900ae99ca7b 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1076,11 +1076,12 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
if (!changed) {
/*
- * state change failure is ok if we're in DELETING state,
+ * state change failure is ok if we started ctrl delete,
* unless we're during creation of a new controller to
* avoid races with teardown flow.
*/
- WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING);
+ WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING &&
+ ctrl->ctrl.state != NVME_CTRL_DELETING_NOIO);
WARN_ON_ONCE(new);
ret = -EINVAL;
goto destroy_io;
@@ -1133,8 +1134,9 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
- /* state change failure is ok if we're in DELETING state */
- WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING);
+ /* state change failure is ok if we started ctrl delete */
+ WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING &&
+ ctrl->ctrl.state != NVME_CTRL_DELETING_NOIO);
return;
}
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 860d7ddc2eee..14b6594b418a 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1948,11 +1948,12 @@ static int nvme_tcp_setup_ctrl(struct nvme_ctrl *ctrl, bool new)
if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE)) {
/*
- * state change failure is ok if we're in DELETING state,
+ * state change failure is ok if we started ctrl delete,
* unless we're during creation of a new controller to
* avoid races with teardown flow.
*/
- WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING);
+ WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING &&
+ ctrl->state != NVME_CTRL_DELETING_NOIO);
WARN_ON_ONCE(new);
ret = -EINVAL;
goto destroy_io;
@@ -2008,8 +2009,9 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work)
blk_mq_unquiesce_queue(ctrl->admin_q);
if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING)) {
- /* state change failure is ok if we're in DELETING state */
- WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING);
+ /* state change failure is ok if we started ctrl delete */
+ WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING &&
+ ctrl->state != NVME_CTRL_DELETING_NOIO);
return;
}
@@ -2044,8 +2046,9 @@ static void nvme_reset_ctrl_work(struct work_struct *work)
nvme_tcp_teardown_ctrl(ctrl, false);
if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING)) {
- /* state change failure is ok if we're in DELETING state */
- WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING);
+ /* state change failure is ok if we started ctrl delete */
+ WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING &&
+ ctrl->state != NVME_CTRL_DELETING_NOIO);
return;
}
--
2.25.1
More information about the Linux-nvme
mailing list