[PATCH v1 3/7] ublk: move device reset into ublk_ch_release()

[Jared Holzman <jholzman@nvidia.com>]

From: Ming Lei <ming.lei@redhat.com>

ublk_ch_release() is called after ublk char device is closed, when all
uring_cmd are done, so it is perfect fine to move ublk device reset to
ublk_ch_release() from ublk_ctrl_start_recovery().

This way can avoid to grab the exiting daemon task_struct too long.

However, reset of the following ublk IO flags has to be moved until ublk
io_uring queues are ready:

- ubq->canceling

For requeuing IO in case of ublk_nosrv_dev_should_queue_io() before device
is recovered

- ubq->fail_io

For failing IO in case of UBLK_F_USER_RECOVERY_FAIL_IO before device is
recovered

- ublk_io->flags

For preventing using io->cmd

With this way, recovery is simplified a lot.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250416035444.99569-5-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/ublk_drv.c | 121 +++++++++++++++++++++++----------------
 1 file changed, 72 insertions(+), 49 deletions(-)

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 9345a6d8dbd8..c619df880c72 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -1043,7 +1043,7 @@ static inline struct ublk_uring_cmd_pdu *ublk_get_uring_cmd_pdu(
 
 static inline bool ubq_daemon_is_dying(struct ublk_queue *ubq)
 {
-	return ubq->ubq_daemon->flags & PF_EXITING;
+	return !ubq->ubq_daemon || ubq->ubq_daemon->flags & PF_EXITING;
 }
 
 /* todo: handle partial completion */
@@ -1440,6 +1440,37 @@ static const struct blk_mq_ops ublk_mq_ops = {
 	.timeout	= ublk_timeout,
 };
 
+static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq)
+{
+	int i;
+
+	/* All old ioucmds have to be completed */
+	ubq->nr_io_ready = 0;
+
+	/*
+	 * old daemon is PF_EXITING, put it now
+	 *
+	 * It could be NULL in case of closing one quisced device.
+	 */
+	if (ubq->ubq_daemon)
+		put_task_struct(ubq->ubq_daemon);
+	/* We have to reset it to NULL, otherwise ub won't accept new FETCH_REQ */
+	ubq->ubq_daemon = NULL;
+	ubq->timeout = false;
+
+	for (i = 0; i < ubq->q_depth; i++) {
+		struct ublk_io *io = &ubq->ios[i];
+
+		/*
+		 * UBLK_IO_FLAG_CANCELED is kept for avoiding to touch
+		 * io->cmd
+		 */
+		io->flags &= UBLK_IO_FLAG_CANCELED;
+		io->cmd = NULL;
+		io->addr = 0;
+	}
+}
+
 static int ublk_ch_open(struct inode *inode, struct file *filp)
 {
 	struct ublk_device *ub = container_of(inode->i_cdev,
@@ -1451,10 +1482,26 @@ static int ublk_ch_open(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+static void ublk_reset_ch_dev(struct ublk_device *ub)
+{
+	int i;
+
+	for (i = 0; i < ub->dev_info.nr_hw_queues; i++)
+		ublk_queue_reinit(ub, ublk_get_queue(ub, i));
+
+	/* set to NULL, otherwise new ubq_daemon cannot mmap the io_cmd_buf */
+	ub->mm = NULL;
+	ub->nr_queues_ready = 0;
+	ub->nr_privileged_daemon = 0;
+}
+
 static int ublk_ch_release(struct inode *inode, struct file *filp)
 {
 	struct ublk_device *ub = filp->private_data;
 
+	/* all uring_cmd has been done now, reset device & ubq */
+	ublk_reset_ch_dev(ub);
+
 	clear_bit(UB_STATE_OPEN, &ub->state);
 	return 0;
 }
@@ -1801,6 +1848,24 @@ static void ublk_nosrv_work(struct work_struct *work)
 	ublk_cancel_dev(ub);
 }
 
+/* reset ublk io_uring queue & io flags */
+static void ublk_reset_io_flags(struct ublk_device *ub)
+{
+	int i, j;
+
+	for (i = 0; i < ub->dev_info.nr_hw_queues; i++) {
+		struct ublk_queue *ubq = ublk_get_queue(ub, i);
+
+		/* UBLK_IO_FLAG_CANCELED can be cleared now */
+		spin_lock(&ubq->cancel_lock);
+		for (j = 0; j < ubq->q_depth; j++)
+			ubq->ios[j].flags &= ~UBLK_IO_FLAG_CANCELED;
+		spin_unlock(&ubq->cancel_lock);
+		ubq->canceling = false;
+		ubq->fail_io = false;
+	}
+}
+
 /* device can only be started after all IOs are ready */
 static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq)
 	__must_hold(&ub->mutex)
@@ -1814,8 +1879,12 @@ static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq)
 		if (capable(CAP_SYS_ADMIN))
 			ub->nr_privileged_daemon++;
 	}
-	if (ub->nr_queues_ready == ub->dev_info.nr_hw_queues)
+
+	if (ub->nr_queues_ready == ub->dev_info.nr_hw_queues) {
+		/* now we are ready for handling ublk io request */
+		ublk_reset_io_flags(ub);
 		complete_all(&ub->completion);
+	}
 }
 
 static inline int ublk_check_cmd_op(u32 cmd_op)
@@ -2866,42 +2935,15 @@ static int ublk_ctrl_set_params(struct ublk_device *ub,
 	return ret;
 }
 
-static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq)
-{
-	int i;
-
-	WARN_ON_ONCE(!(ubq->ubq_daemon && ubq_daemon_is_dying(ubq)));
-
-	/* All old ioucmds have to be completed */
-	ubq->nr_io_ready = 0;
-	/* old daemon is PF_EXITING, put it now */
-	put_task_struct(ubq->ubq_daemon);
-	/* We have to reset it to NULL, otherwise ub won't accept new FETCH_REQ */
-	ubq->ubq_daemon = NULL;
-	ubq->timeout = false;
-
-	for (i = 0; i < ubq->q_depth; i++) {
-		struct ublk_io *io = &ubq->ios[i];
-
-		/* forget everything now and be ready for new FETCH_REQ */
-		io->flags = 0;
-		io->cmd = NULL;
-		io->addr = 0;
-	}
-}
-
 static int ublk_ctrl_start_recovery(struct ublk_device *ub,
 		struct io_uring_cmd *cmd)
 {
 	const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
 	int ret = -EINVAL;
-	int i;
 
 	mutex_lock(&ub->mutex);
 	if (ublk_nosrv_should_stop_dev(ub))
 		goto out_unlock;
-	if (!ub->nr_queues_ready)
-		goto out_unlock;
 	/*
 	 * START_RECOVERY is only allowd after:
 	 *
@@ -2925,12 +2967,6 @@ static int ublk_ctrl_start_recovery(struct ublk_device *ub,
 		goto out_unlock;
 	}
 	pr_devel("%s: start recovery for dev id %d.\n", __func__, header->dev_id);
-	for (i = 0; i < ub->dev_info.nr_hw_queues; i++)
-		ublk_queue_reinit(ub, ublk_get_queue(ub, i));
-	/* set to NULL, otherwise new ubq_daemon cannot mmap the io_cmd_buf */
-	ub->mm = NULL;
-	ub->nr_queues_ready = 0;
-	ub->nr_privileged_daemon = 0;
 	init_completion(&ub->completion);
 	ret = 0;
  out_unlock:
@@ -2944,7 +2980,6 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub,
 	const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
 	int ublksrv_pid = (int)header->data[0];
 	int ret = -EINVAL;
-	int i;
 
 	pr_devel("%s: Waiting for new ubq_daemons(nr: %d) are ready, dev id %d...\n",
 			__func__, ub->dev_info.nr_hw_queues, header->dev_id);
@@ -2964,22 +2999,10 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub,
 		goto out_unlock;
 	}
 	ub->dev_info.ublksrv_pid = ublksrv_pid;
+	ub->dev_info.state = UBLK_S_DEV_LIVE;
 	pr_devel("%s: new ublksrv_pid %d, dev id %d\n",
 			__func__, ublksrv_pid, header->dev_id);
-
-	blk_mq_quiesce_queue(ub->ub_disk->queue);
-	ub->dev_info.state = UBLK_S_DEV_LIVE;
-	for (i = 0; i < ub->dev_info.nr_hw_queues; i++) {
-		struct ublk_queue *ubq = ublk_get_queue(ub, i);
-
-		ubq->canceling = false;
-		ubq->fail_io = false;
-	}
-	blk_mq_unquiesce_queue(ub->ub_disk->queue);
-	pr_devel("%s: queue unquiesced, dev id %d.\n",
-			__func__, header->dev_id);
 	blk_mq_kick_requeue_list(ub->ub_disk->queue);
-
 	ret = 0;
  out_unlock:
 	mutex_unlock(&ub->mutex);
-- 
2.43.0