Blob Blame History Raw
From: Anton Eidelman <anton@lightbitslabs.com>
Date: Wed, 24 Jun 2020 01:53:11 -0700
Subject: [PATCH] nvme-multipath: fix deadlock due to head->lock
Git-commit: d8a22f85609fadb46ba699e0136cc3ebdeebff79
Patch-mainline: v5.8-rc3
References: git-fixes

In the following scenario scan_work and ana_work will deadlock:

When scan_work calls nvme_mpath_add_disk() this holds ana_lock
and invokes nvme_parse_ana_log(), which may issue IO
in device_add_disk() and hang waiting for an accessible path.

While nvme_mpath_set_live() only called when nvme_state_is_live(),
a transition may cause NVME_SC_ANA_TRANSITION and requeue the IO.

Since nvme_mpath_set_live() holds ns->head->lock, an ana_work on
ANY ctrl will not be able to complete nvme_mpath_set_live()
on the same ns->head, which is required in order to update
the new accessible path and remove NVME_NS_ANA_PENDING..
Therefore IO never completes: deadlock [1].

Fix:
Move device_add_disk out of the head->lock and protect it with an
atomic test_and_set for a new NVME_NS_HEAD_HAS_DISK bit.

[1]:
kernel: INFO: task kworker/u8:2:160 blocked for more than 120 seconds.
kernel:       Tainted: G           OE     5.3.5-050305-generic #201910071830
kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
kernel: kworker/u8:2    D    0   160      2 0x80004000
kernel: Workqueue: nvme-wq nvme_ana_work [nvme_core]
kernel: Call Trace:
kernel:  __schedule+0x2b9/0x6c0
kernel:  schedule+0x42/0xb0
kernel:  schedule_preempt_disabled+0xe/0x10
kernel:  __mutex_lock.isra.0+0x182/0x4f0
kernel:  __mutex_lock_slowpath+0x13/0x20
kernel:  mutex_lock+0x2e/0x40
kernel:  nvme_update_ns_ana_state+0x22/0x60 [nvme_core]
kernel:  nvme_update_ana_state+0xca/0xe0 [nvme_core]
kernel:  nvme_parse_ana_log+0xa1/0x180 [nvme_core]
kernel:  nvme_read_ana_log+0x76/0x100 [nvme_core]
kernel:  nvme_ana_work+0x15/0x20 [nvme_core]
kernel:  process_one_work+0x1db/0x380
kernel:  worker_thread+0x4d/0x400
kernel:  kthread+0x104/0x140
kernel:  ret_from_fork+0x35/0x40
kernel: INFO: task kworker/u8:4:439 blocked for more than 120 seconds.
kernel:       Tainted: G           OE     5.3.5-050305-generic #201910071830
kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
kernel: kworker/u8:4    D    0   439      2 0x80004000
kernel: 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_mpath_add_disk+0xbe/0x100 [nvme_core]
kernel:  nvme_validate_ns+0x396/0x940 [nvme_core]
kernel:  nvme_scan_work+0x256/0x390 [nvme_core]
kernel:  process_one_work+0x1db/0x380
kernel:  worker_thread+0x4d/0x400
kernel:  kthread+0x104/0x140
kernel:  ret_from_fork+0x35/0x40

Fixes: 0d0b660f214d ("nvme: add ANA support")
Signed-off-by: Anton Eidelman <anton@lightbitslabs.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Hannes Reinecke <hare@suse.com>
---
 drivers/nvme/host/multipath.c | 4 ++--
 drivers/nvme/host/nvme.h      | 2 ++
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 5c48a38aebf8..79c8caced81f 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -412,11 +412,11 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 	if (!head->disk)
 		return;
 
-	mutex_lock(&head->lock);
-	if (!(head->disk->flags & GENHD_FL_UP))
+	if (!test_and_set_bit(NVME_NSHEAD_DISK_LIVE, &head->flags))
 		device_add_disk(&head->subsys->dev, head->disk,
 				nvme_ns_id_attr_groups);
 
+	mutex_lock(&head->lock);
 	if (nvme_path_is_optimized(ns)) {
 		int node, srcu_idx;
 
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index c0f4226d3299..2ef8d501e2a8 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -364,6 +364,8 @@ struct nvme_ns_head {
 	spinlock_t		requeue_lock;
 	struct work_struct	requeue_work;
 	struct mutex		lock;
+	unsigned long		flags;
+#define NVME_NSHEAD_DISK_LIVE	0
 	struct nvme_ns __rcu	*current_path[];
 #endif
 };
-- 
2.16.4