START_USER_RECOVERY and END_USER_RECOVERY are two new control commands
to support user recovery feature.

After a crash, user should send START_USER_RECOVERY, it will:
(1) check if (a)current ublk_device is UBLK_S_DEV_QUIESCED which was
    set by quiesce_work and (b)the file struct is released.
(2) reinit all ubqs, including:
    (a) put the task_struct and reset ->ubq_daemon to NULL.
    (b) reset all ublk_io.
(3) reset ub->mm to NULL.

Then, user should start a new process and send FETCH_REQ on each
ubq_daemon.

Finally, user should send END_USER_RECOVERY, it will:
(1) wait for all new ubq_daemons getting ready.
(2) update ublksrv_pid
(3) unquiesce the request queue and expect incoming ublk_queue_rq()
(4) convert ub's state to UBLK_S_DEV_LIVE

Note: we can handle STOP_DEV between START_USER_RECOVERY and
END_USER_RECOVERY. This is helpful to users who cannot start new process
after sending START_USER_RECOVERY ctrl-cmd.

Signed-off-by: ZiyangZhang <ZiyangZhang@linux.alibaba.com>
---
 drivers/block/ublk_drv.c | 116 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 116 insertions(+)

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 4409a130d0b6..3a3af80ee938 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -1961,6 +1961,116 @@ static int ublk_ctrl_set_params(struct io_uring_cmd *cmd)
 	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 */
+	WARN_ON_ONCE(ubq->nr_io_ready);
+	pr_devel("%s: prepare for recovering qid %d\n", __func__, ubq->q_id);
+	/* 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;
+
+	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 io_uring_cmd *cmd)
+{
+	struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd;
+	struct ublk_device *ub;
+	int ret = -EINVAL;
+	int i;
+
+	ub = ublk_get_device_from_id(header->dev_id);
+	if (!ub)
+		return ret;
+
+	mutex_lock(&ub->mutex);
+	if (!ublk_can_use_recovery(ub))
+		goto out_unlock;
+	/*
+	 * START_RECOVERY is only allowd after:
+	 *
+	 * (1) UB_STATE_OPEN is not set, which means the dying process is exited
+	 *     and related io_uring ctx is freed so file struct of /dev/ublkcX is
+	 *     released.
+	 *
+	 * (2) UBLK_S_DEV_QUIESCED is set, which means the quiesce_work:
+	 *     (a)has quiesced request queue
+	 *     (b)has requeued every inflight rqs whose io_flags is ACTIVE
+	 *     (c)has requeued/aborted every inflight rqs whose io_flags is NOT ACTIVE
+	 *     (d)has completed/camceled all ioucmds owned by ther dying process
+	 */
+	if (test_bit(UB_STATE_OPEN, &ub->state) ||
+			ub->dev_info.state != UBLK_S_DEV_QUIESCED) {
+		ret = -EBUSY;
+		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;
+	init_completion(&ub->completion);
+	ret = 0;
+ out_unlock:
+	mutex_unlock(&ub->mutex);
+	ublk_put_device(ub);
+	return ret;
+}
+
+static int ublk_ctrl_end_recovery(struct io_uring_cmd *cmd)
+{
+	struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd;
+	int ublksrv_pid = (int)header->data[0];
+	struct ublk_device *ub;
+	int ret = -EINVAL;
+
+	ub = ublk_get_device_from_id(header->dev_id);
+	if (!ub)
+		return ret;
+
+	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);
+	/* wait until new ubq_daemon sending all FETCH_REQ */
+	wait_for_completion_interruptible(&ub->completion);
+	pr_devel("%s: All new ubq_daemons(nr: %d) are ready, dev id %d\n",
+			__func__, ub->dev_info.nr_hw_queues, header->dev_id);
+
+	mutex_lock(&ub->mutex);
+	if (!ublk_can_use_recovery(ub))
+		goto out_unlock;
+
+	if (ub->dev_info.state != UBLK_S_DEV_QUIESCED) {
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+	ub->dev_info.ublksrv_pid = ublksrv_pid;
+	pr_devel("%s: new ublksrv_pid %d, dev id %d\n",
+			__func__, ublksrv_pid, header->dev_id);
+	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);
+	ub->dev_info.state = UBLK_S_DEV_LIVE;
+	ret = 0;
+ out_unlock:
+	mutex_unlock(&ub->mutex);
+	ublk_put_device(ub);
+	return ret;
+}
+
 static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
 		unsigned int issue_flags)
 {
@@ -2002,6 +2112,12 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
 	case UBLK_CMD_SET_PARAMS:
 		ret = ublk_ctrl_set_params(cmd);
 		break;
+	case UBLK_CMD_START_USER_RECOVERY:
+		ret = ublk_ctrl_start_recovery(cmd);
+		break;
+	case UBLK_CMD_END_USER_RECOVERY:
+		ret = ublk_ctrl_end_recovery(cmd);
+		break;
 	default:
 		break;
 	}
-- 
2.27.0

On Tue, Sep 13, 2022 at 12:17:06PM +0800, ZiyangZhang wrote:
> START_USER_RECOVERY and END_USER_RECOVERY are two new control commands
> to support user recovery feature.
> 
> After a crash, user should send START_USER_RECOVERY, it will:
> (1) check if (a)current ublk_device is UBLK_S_DEV_QUIESCED which was
>     set by quiesce_work and (b)the file struct is released.
> (2) reinit all ubqs, including:
>     (a) put the task_struct and reset ->ubq_daemon to NULL.
>     (b) reset all ublk_io.
> (3) reset ub->mm to NULL.
> 
> Then, user should start a new process and send FETCH_REQ on each
> ubq_daemon.
> 
> Finally, user should send END_USER_RECOVERY, it will:
> (1) wait for all new ubq_daemons getting ready.
> (2) update ublksrv_pid
> (3) unquiesce the request queue and expect incoming ublk_queue_rq()
> (4) convert ub's state to UBLK_S_DEV_LIVE
> 
> Note: we can handle STOP_DEV between START_USER_RECOVERY and
> END_USER_RECOVERY. This is helpful to users who cannot start new process
> after sending START_USER_RECOVERY ctrl-cmd.
> 
> Signed-off-by: ZiyangZhang <ZiyangZhang@linux.alibaba.com>
> ---
>  drivers/block/ublk_drv.c | 116 +++++++++++++++++++++++++++++++++++++++
>  1 file changed, 116 insertions(+)
> 
> diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
> index 4409a130d0b6..3a3af80ee938 100644
> --- a/drivers/block/ublk_drv.c
> +++ b/drivers/block/ublk_drv.c
> @@ -1961,6 +1961,116 @@ static int ublk_ctrl_set_params(struct io_uring_cmd *cmd)
>  	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 */
> +	WARN_ON_ONCE(ubq->nr_io_ready);
> +	pr_devel("%s: prepare for recovering qid %d\n", __func__, ubq->q_id);
> +	/* 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;
> +
> +	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 io_uring_cmd *cmd)
> +{
> +	struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd;
> +	struct ublk_device *ub;
> +	int ret = -EINVAL;
> +	int i;
> +
> +	ub = ublk_get_device_from_id(header->dev_id);
> +	if (!ub)
> +		return ret;
> +
> +	mutex_lock(&ub->mutex);
> +	if (!ublk_can_use_recovery(ub))
> +		goto out_unlock;
> +	/*
> +	 * START_RECOVERY is only allowd after:
> +	 *
> +	 * (1) UB_STATE_OPEN is not set, which means the dying process is exited
> +	 *     and related io_uring ctx is freed so file struct of /dev/ublkcX is
> +	 *     released.
> +	 *
> +	 * (2) UBLK_S_DEV_QUIESCED is set, which means the quiesce_work:
> +	 *     (a)has quiesced request queue
> +	 *     (b)has requeued every inflight rqs whose io_flags is ACTIVE
> +	 *     (c)has requeued/aborted every inflight rqs whose io_flags is NOT ACTIVE
> +	 *     (d)has completed/camceled all ioucmds owned by ther dying process
> +	 */
> +	if (test_bit(UB_STATE_OPEN, &ub->state) ||
> +			ub->dev_info.state != UBLK_S_DEV_QUIESCED) {
> +		ret = -EBUSY;
> +		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;

I am wondering why you don't move the above(queue reinit, clearing ub->mm)
into ublk_ch_release(), and looks it is more clean to clear this stuff
there. Meantime I guess one control command might be enough for user
recovery.


Thanks, 
Ming

On 2022/9/19 21:03, Ming Lei wrote:
> On Tue, Sep 13, 2022 at 12:17:06PM +0800, ZiyangZhang wrote:
>> START_USER_RECOVERY and END_USER_RECOVERY are two new control commands
>> to support user recovery feature.
>>
>> After a crash, user should send START_USER_RECOVERY, it will:
>> (1) check if (a)current ublk_device is UBLK_S_DEV_QUIESCED which was
>>     set by quiesce_work and (b)the file struct is released.
>> (2) reinit all ubqs, including:
>>     (a) put the task_struct and reset ->ubq_daemon to NULL.
>>     (b) reset all ublk_io.
>> (3) reset ub->mm to NULL.
>>
>> Then, user should start a new process and send FETCH_REQ on each
>> ubq_daemon.
>>
>> Finally, user should send END_USER_RECOVERY, it will:
>> (1) wait for all new ubq_daemons getting ready.
>> (2) update ublksrv_pid
>> (3) unquiesce the request queue and expect incoming ublk_queue_rq()
>> (4) convert ub's state to UBLK_S_DEV_LIVE
>>
>> Note: we can handle STOP_DEV between START_USER_RECOVERY and
>> END_USER_RECOVERY. This is helpful to users who cannot start new process
>> after sending START_USER_RECOVERY ctrl-cmd.
>>
>> Signed-off-by: ZiyangZhang <ZiyangZhang@linux.alibaba.com>
>> ---
>>  drivers/block/ublk_drv.c | 116 +++++++++++++++++++++++++++++++++++++++
>>  1 file changed, 116 insertions(+)
>>
>> diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
>> index 4409a130d0b6..3a3af80ee938 100644
>> --- a/drivers/block/ublk_drv.c
>> +++ b/drivers/block/ublk_drv.c
>> @@ -1961,6 +1961,116 @@ static int ublk_ctrl_set_params(struct io_uring_cmd *cmd)
>>  	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 */
>> +	WARN_ON_ONCE(ubq->nr_io_ready);
>> +	pr_devel("%s: prepare for recovering qid %d\n", __func__, ubq->q_id);
>> +	/* 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;
>> +
>> +	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 io_uring_cmd *cmd)
>> +{
>> +	struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd;
>> +	struct ublk_device *ub;
>> +	int ret = -EINVAL;
>> +	int i;
>> +
>> +	ub = ublk_get_device_from_id(header->dev_id);
>> +	if (!ub)
>> +		return ret;
>> +
>> +	mutex_lock(&ub->mutex);
>> +	if (!ublk_can_use_recovery(ub))
>> +		goto out_unlock;
>> +	/*
>> +	 * START_RECOVERY is only allowd after:
>> +	 *
>> +	 * (1) UB_STATE_OPEN is not set, which means the dying process is exited
>> +	 *     and related io_uring ctx is freed so file struct of /dev/ublkcX is
>> +	 *     released.
>> +	 *
>> +	 * (2) UBLK_S_DEV_QUIESCED is set, which means the quiesce_work:
>> +	 *     (a)has quiesced request queue
>> +	 *     (b)has requeued every inflight rqs whose io_flags is ACTIVE
>> +	 *     (c)has requeued/aborted every inflight rqs whose io_flags is NOT ACTIVE
>> +	 *     (d)has completed/camceled all ioucmds owned by ther dying process
>> +	 */
>> +	if (test_bit(UB_STATE_OPEN, &ub->state) ||
>> +			ub->dev_info.state != UBLK_S_DEV_QUIESCED) {
>> +		ret = -EBUSY;
>> +		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;
> 
> I am wondering why you don't move the above(queue reinit, clearing ub->mm)
> into ublk_ch_release(), and looks it is more clean to clear this stuff
> there. Meantime I guess one control command might be enough for user
> recovery.


OK, START_USER_RECOVERY just does cleanup stuff for a new process and
ublk_ch_release() does the similar thing since it is always called when chardev
is released. And our new process must open the chardev after it is released.

So (queue reinit, clearing ub->mm) can be done in ublk_ch_release().

Regards,
Zhang.