[PATCH V2 4/5] nvme: fix race between freeze queues and unfreeze queues

[Ming Lei]

nvme_dev_disable() and resetting controller are required for recovering
controller, but the two are run from different contexts.

nvme_start_freeze() is run from nvme_dev_disable(), and nvme_unfreeze()
is run from resetting context. Unfortunatley timeout may be triggered
when draining IO from resetting controller, so nvme_start_freeze() may
be run several times.

This patch fixes the race between nvme_start_freeze() and
nvme_unfreeze() by introducing flags of 'queues_freezed' and the lock
of 'freeze_mutex'.

Cc: Jianchao Wang <jianchao.w.wang at oracle.com>
Cc: Christoph Hellwig <hch at lst.de>
Cc: Sagi Grimberg <sagi at grimberg.me>
Cc: linux-nvme at lists.infradead.org
Signed-off-by: Ming Lei <ming.lei at redhat.com>
---
 drivers/nvme/host/core.c | 29 +++++++++++++++++++++--------
 drivers/nvme/host/nvme.h |  3 +++
 2 files changed, 24 insertions(+), 8 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 9df4f71e58ca..f9028873298e 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3447,6 +3447,9 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	INIT_WORK(&ctrl->fw_act_work, nvme_fw_act_work);
 	INIT_WORK(&ctrl->delete_work, nvme_delete_ctrl_work);
 
+	ctrl->queues_freezed = false;
+	mutex_init(&ctrl->freeze_mutex);
+
 	ret = ida_simple_get(&nvme_instance_ida, 0, 0, GFP_KERNEL);
 	if (ret < 0)
 		goto out;
@@ -3526,10 +3529,15 @@ void nvme_unfreeze(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list)
-		blk_mq_unfreeze_queue(ns->queue);
-	up_read(&ctrl->namespaces_rwsem);
+	mutex_lock(&ctrl->freeze_mutex);
+	if (ctrl->queues_freezed) {
+		down_read(&ctrl->namespaces_rwsem);
+		list_for_each_entry(ns, &ctrl->namespaces, list)
+			blk_mq_unfreeze_queue(ns->queue);
+		up_read(&ctrl->namespaces_rwsem);
+		ctrl->queues_freezed = false;
+	}
+	mutex_unlock(&ctrl->freeze_mutex);
 }
 EXPORT_SYMBOL_GPL(nvme_unfreeze);
 
@@ -3562,10 +3570,15 @@ void nvme_start_freeze(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list)
-		blk_freeze_queue_start(ns->queue);
-	up_read(&ctrl->namespaces_rwsem);
+	mutex_lock(&ctrl->freeze_mutex);
+	if (!ctrl->queues_freezed) {
+		down_read(&ctrl->namespaces_rwsem);
+		list_for_each_entry(ns, &ctrl->namespaces, list)
+			blk_freeze_queue_start(ns->queue);
+		up_read(&ctrl->namespaces_rwsem);
+		ctrl->queues_freezed = true;
+	}
+	mutex_unlock(&ctrl->freeze_mutex);
 }
 EXPORT_SYMBOL_GPL(nvme_start_freeze);
 
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 061fecfd44f5..a19b7f04ac24 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -149,6 +149,9 @@ struct nvme_ctrl {
 	struct work_struct reset_work;
 	struct work_struct delete_work;
 
+	bool queues_freezed;
+	struct mutex freeze_mutex;
+
 	struct nvme_subsystem *subsys;
 	struct list_head subsys_entry;
 
-- 
2.9.5