nvme: fix deadlock between reset and scan

[ Upstream commit 839a40d1e730977d4448d141fa653517c2959a88 ]

If controller reset occurs when allocating namespace, both
nvme_reset_work and nvme_scan_work will hang, as shown below.

Test Scripts:

    for ((t=1;t<=128;t++))
    do
    nsid=`nvme create-ns /dev/nvme1 -s 14537724 -c 14537724 -f 0 -m 0 \
    -d 0 | awk -F: '{print($NF);}'`
    nvme attach-ns /dev/nvme1 -n $nsid -c 0
    done
    nvme reset /dev/nvme1

We will find that both nvme_reset_work and nvme_scan_work hung:

    INFO: task kworker/u249:4:17848 blocked for more than 120 seconds.
    "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this
    message.
    task:kworker/u249:4  state:D stack:    0 pid:17848 ppid:     2
    flags:0x00000028
    Workqueue: nvme-reset-wq nvme_reset_work [nvme]
    Call trace:
    __switch_to+0xb4/0xfc
    __schedule+0x22c/0x670
    schedule+0x4c/0xd0
    blk_mq_freeze_queue_wait+0x84/0xc0
    nvme_wait_freeze+0x40/0x64 [nvme_core]
    nvme_reset_work+0x1c0/0x5cc [nvme]
    process_one_work+0x1d8/0x4b0
    worker_thread+0x230/0x440
    kthread+0x114/0x120
    INFO: task kworker/u249:3:22404 blocked for more than 120 seconds.
    "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this
    message.
    task:kworker/u249:3  state:D stack:    0 pid:22404 ppid:     2
    flags:0x00000028
    Workqueue: nvme-wq nvme_scan_work [nvme_core]
    Call trace:
    __switch_to+0xb4/0xfc
    __schedule+0x22c/0x670
    schedule+0x4c/0xd0
    rwsem_down_write_slowpath+0x32c/0x98c
    down_write+0x70/0x80
    nvme_alloc_ns+0x1ac/0x38c [nvme_core]
    nvme_validate_or_alloc_ns+0xbc/0x150 [nvme_core]
    nvme_scan_ns_list+0xe8/0x2e4 [nvme_core]
    nvme_scan_work+0x60/0x500 [nvme_core]
    process_one_work+0x1d8/0x4b0
    worker_thread+0x260/0x440
    kthread+0x114/0x120
    INFO: task nvme:28428 blocked for more than 120 seconds.
    "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this
    message.
    task:nvme            state:D stack:    0 pid:28428 ppid: 27119
    flags:0x00000000
    Call trace:
    __switch_to+0xb4/0xfc
    __schedule+0x22c/0x670
    schedule+0x4c/0xd0
    schedule_timeout+0x160/0x194
    do_wait_for_common+0xac/0x1d0
    __wait_for_common+0x78/0x100
    wait_for_completion+0x24/0x30
    __flush_work.isra.0+0x74/0x90
    flush_work+0x14/0x20
    nvme_reset_ctrl_sync+0x50/0x74 [nvme_core]
    nvme_dev_ioctl+0x1b0/0x250 [nvme_core]
    __arm64_sys_ioctl+0xa8/0xf0
    el0_svc_common+0x88/0x234
    do_el0_svc+0x7c/0x90
    el0_svc+0x1c/0x30
    el0_sync_handler+0xa8/0xb0
    el0_sync+0x148/0x180

The reason for the hang is that nvme_reset_work occurs while nvme_scan_work
is still running. nvme_scan_work may add new ns into ctrl->namespaces
list after nvme_reset_work frozen all ns->q in ctrl->namespaces list.
The newly added ns is not frozen, so nvme_wait_freeze will wait forever.
Unfortunately, ctrl->namespaces_rwsem is held by nvme_reset_work, so
nvme_scan_work will also wait forever. Now we are deadlocked!

PROCESS1                         PROCESS2
==============                   ==============
nvme_scan_work
  ...                            nvme_reset_work
  nvme_validate_or_alloc_ns        nvme_dev_disable
    nvme_alloc_ns                    nvme_start_freeze
     down_write                      ...
     nvme_ns_add_to_ctrl_list        ...
     up_write                      nvme_wait_freeze
    ...                              down_read
    nvme_alloc_ns                    blk_mq_freeze_queue_wait
     down_write

Fix by marking the ctrl with say NVME_CTRL_FROZEN flag set in
nvme_start_freeze and cleared in nvme_unfreeze. Then the scan can check
it before adding the new namespace (under the namespaces_rwsem).

Signed-off-by: Bitao Hu <yaoma@linux.alibaba.com>
Reviewed-by: Guixin Liu <kanie@linux.alibaba.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>

2 files changed, 11 insertions, 0 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index c38e234723ec..d4564a2517eb 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3652,6 +3652,14 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 		goto out_unlink_ns;
 
 	down_write(&ctrl->namespaces_rwsem);
+	/*
+	 * Ensure that no namespaces are added to the ctrl list after the queues
+	 * are frozen, thereby avoiding a deadlock between scan and reset.
+	 */
+	if (test_bit(NVME_CTRL_FROZEN, &ctrl->flags)) {
+		up_write(&ctrl->namespaces_rwsem);
+		goto out_unlink_ns;
+	}
 	nvme_ns_add_to_ctrl_list(ns);
 	up_write(&ctrl->namespaces_rwsem);
 	nvme_get_ctrl(ctrl);
@@ -4562,6 +4570,7 @@ void nvme_unfreeze(struct nvme_ctrl *ctrl)
 	list_for_each_entry(ns, &ctrl->namespaces, list)
 		blk_mq_unfreeze_queue(ns->queue);
 	up_read(&ctrl->namespaces_rwsem);
+	clear_bit(NVME_CTRL_FROZEN, &ctrl->flags);
 }
 EXPORT_SYMBOL_GPL(nvme_unfreeze);
 
@@ -4595,6 +4604,7 @@ void nvme_start_freeze(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
 
+	set_bit(NVME_CTRL_FROZEN, &ctrl->flags);
 	down_read(&ctrl->namespaces_rwsem);
 	list_for_each_entry(ns, &ctrl->namespaces, list)
 		blk_freeze_queue_start(ns->queue);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 13f71461f5f1..ba62d42d2a8b 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -256,6 +256,7 @@ enum nvme_ctrl_flags {
 	NVME_CTRL_STOPPED		= 3,
 	NVME_CTRL_SKIP_ID_CNS_CS	= 4,
 	NVME_CTRL_DIRTY_CAPABILITY	= 5,
+	NVME_CTRL_FROZEN		= 6,
 };
 
 struct nvme_ctrl {