[PATCH 5.15 129/167] nvme: fix regression when disconnect a recovering ctrl

From: Greg Kroah-Hartman
Date: Tue Jul 19 2022 - 08:42:16 EST


From: Ruozhu Li <liruozhu@xxxxxxxxxx>

[ Upstream commit f7f70f4aa09dc43d7455c060143e86a017c30548 ]

We encountered a problem that the disconnect command hangs.
After analyzing the log and stack, we found that the triggering
process is as follows:
CPU0 CPU1
nvme_rdma_error_recovery_work
nvme_rdma_teardown_io_queues
nvme_do_delete_ctrl nvme_stop_queues
nvme_remove_namespaces
--clear ctrl->namespaces
nvme_start_queues
--no ns in ctrl->namespaces
nvme_ns_remove return(because ctrl is deleting)
blk_freeze_queue
blk_mq_freeze_queue_wait
--wait for ns to unquiesce to clean infligt IO, hang forever

This problem was not found in older kernels because we will flush
err work in nvme_stop_ctrl before nvme_remove_namespaces.It does not
seem to be modified for functional reasons, the patch can be revert
to solve the problem.

Revert commit 794a4cb3d2f7 ("nvme: remove the .stop_ctrl callout")

Signed-off-by: Ruozhu Li <liruozhu@xxxxxxxxxx>
Reviewed-by: Sagi Grimberg <sagi@xxxxxxxxxxx>
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
drivers/nvme/host/core.c | 2 ++
drivers/nvme/host/nvme.h | 1 +
drivers/nvme/host/rdma.c | 12 +++++++++---
drivers/nvme/host/tcp.c | 10 +++++++---
4 files changed, 19 insertions(+), 6 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 19054b791c67..29b56ea01132 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4385,6 +4385,8 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl)
nvme_stop_failfast_work(ctrl);
flush_work(&ctrl->async_event_work);
cancel_work_sync(&ctrl->fw_act_work);
+ if (ctrl->ops->stop_ctrl)
+ ctrl->ops->stop_ctrl(ctrl);
}
EXPORT_SYMBOL_GPL(nvme_stop_ctrl);

diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 72bcd7e5716e..75a7e7baa1fc 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -495,6 +495,7 @@ struct nvme_ctrl_ops {
void (*free_ctrl)(struct nvme_ctrl *ctrl);
void (*submit_async_event)(struct nvme_ctrl *ctrl);
void (*delete_ctrl)(struct nvme_ctrl *ctrl);
+ void (*stop_ctrl)(struct nvme_ctrl *ctrl);
int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size);
};

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index d51f52e296f5..2db9c166a1b7 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1049,6 +1049,14 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
}
}

+static void nvme_rdma_stop_ctrl(struct nvme_ctrl *nctrl)
+{
+ struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
+
+ cancel_work_sync(&ctrl->err_work);
+ cancel_delayed_work_sync(&ctrl->reconnect_work);
+}
+
static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl)
{
struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
@@ -2230,9 +2238,6 @@ static const struct blk_mq_ops nvme_rdma_admin_mq_ops = {

static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown)
{
- cancel_work_sync(&ctrl->err_work);
- cancel_delayed_work_sync(&ctrl->reconnect_work);
-
nvme_rdma_teardown_io_queues(ctrl, shutdown);
blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
if (shutdown)
@@ -2282,6 +2287,7 @@ static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = {
.submit_async_event = nvme_rdma_submit_async_event,
.delete_ctrl = nvme_rdma_delete_ctrl,
.get_address = nvmf_get_address,
+ .stop_ctrl = nvme_rdma_stop_ctrl,
};

/*
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 1821d38e620e..20138e132558 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -2163,9 +2163,6 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work)

static void nvme_tcp_teardown_ctrl(struct nvme_ctrl *ctrl, bool shutdown)
{
- cancel_work_sync(&to_tcp_ctrl(ctrl)->err_work);
- cancel_delayed_work_sync(&to_tcp_ctrl(ctrl)->connect_work);
-
nvme_tcp_teardown_io_queues(ctrl, shutdown);
blk_mq_quiesce_queue(ctrl->admin_q);
if (shutdown)
@@ -2205,6 +2202,12 @@ static void nvme_reset_ctrl_work(struct work_struct *work)
nvme_tcp_reconnect_or_remove(ctrl);
}

+static void nvme_tcp_stop_ctrl(struct nvme_ctrl *ctrl)
+{
+ cancel_work_sync(&to_tcp_ctrl(ctrl)->err_work);
+ cancel_delayed_work_sync(&to_tcp_ctrl(ctrl)->connect_work);
+}
+
static void nvme_tcp_free_ctrl(struct nvme_ctrl *nctrl)
{
struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
@@ -2528,6 +2531,7 @@ static const struct nvme_ctrl_ops nvme_tcp_ctrl_ops = {
.submit_async_event = nvme_tcp_submit_async_event,
.delete_ctrl = nvme_tcp_delete_ctrl,
.get_address = nvmf_get_address,
+ .stop_ctrl = nvme_tcp_stop_ctrl,
};

static bool
--
2.35.1