nvme: use srcu for iterating namespace list

The nvme pci driver synchronizes with all the namespace queues during a
reset to ensure that there's no pending timeout work.

Meanwhile the timeout work potentially iterates those same namespaces to
freeze their queues.

Each of those namespace iterations use the same read lock. If a write
lock should somehow get between the synchronize and freeze steps, then
forward progress is deadlocked.

We had been relying on the nvme controller state machine to ensure the
reset work wouldn't conflict with timeout work. That guarantee may be a
bit fragile to rely on, so iterate the namespace lists without taking
potentially circular locks, as reported by lockdep.

Link: https://lore.kernel.org/all/20220930001943.zdbvolc3gkekfmcv@shindev/
Reported-by: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Tested-by: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>

1 files changed, 9 insertions, 6 deletions

diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 499a8bb7cac7..9d9d2a127c4e 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -789,15 +789,15 @@ static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp,
 		bool open_for_write)
 {
 	struct nvme_ns *ns;
-	int ret;
+	int ret, srcu_idx;
 
-	down_read(&ctrl->namespaces_rwsem);
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
 	if (list_empty(&ctrl->namespaces)) {
 		ret = -ENOTTY;
 		goto out_unlock;
 	}
 
-	ns = list_first_entry(&ctrl->namespaces, struct nvme_ns, list);
+	ns = list_first_or_null_rcu(&ctrl->namespaces, struct nvme_ns, list);
 	if (ns != list_last_entry(&ctrl->namespaces, struct nvme_ns, list)) {
 		dev_warn(ctrl->device,
 			"NVME_IOCTL_IO_CMD not supported when multiple namespaces present!\n");
@@ -807,15 +807,18 @@ static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp,
 
 	dev_warn(ctrl->device,
 		"using deprecated NVME_IOCTL_IO_CMD ioctl on the char device!\n");
-	kref_get(&ns->kref);
-	up_read(&ctrl->namespaces_rwsem);
+	if (!nvme_get_ns(ns)) {
+		ret = -ENXIO;
+		goto out_unlock;
+	}
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 
 	ret = nvme_user_cmd(ctrl, ns, argp, 0, open_for_write);
 	nvme_put_ns(ns);
 	return ret;
 
 out_unlock:
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 	return ret;
 }