diff mbox series

[v2,2/4] ublk: refactor recovery configuration flag helpers

Message ID 20240917002155.2044225-3-ushankar@purestorage.com (mailing list archive)
State New, archived
Headers show
Series ublk: support device recovery without I/O queueing | expand

Commit Message

Uday Shankar Sept. 17, 2024, 12:21 a.m. UTC
ublk currently supports the following behaviors on ublk server exit:

A: outstanding I/Os get errors, subsequently issued I/Os get errors
B: outstanding I/Os get errors, subsequently issued I/Os queue
C: outstanding I/Os get reissued, subsequently issued I/Os queue

and the following behaviors for recovery of preexisting block devices by
a future incarnation of the ublk server:

1: ublk devices stopped on ublk server exit (no recovery possible)
2: ublk devices are recoverable using start/end_recovery commands

The userspace interface allows selection of combinations of these
behaviors using flags specified at device creation time, namely:

default behavior: A + 1
UBLK_F_USER_RECOVERY: B + 2
UBLK_F_USER_RECOVERY|UBLK_F_USER_RECOVERY_REISSUE: C + 2

We can't easily change the userspace interface to allow independent
selection of one of {A, B, C} and one of {1, 2}, but we can refactor the
internal helpers which test for the flags. Replace the existing helpers
with the following set:

ublk_nosrv_should_reissue_outstanding: tests for behavior C
ublk_nosrv_[dev_]should_queue_io: tests for behavior B
ublk_nosrv_should_stop_dev: tests for behavior 1

Signed-off-by: Uday Shankar <ushankar@purestorage.com>
---
Changes since v1 (https://lore.kernel.org/linux-block/20240617194451.435445-3-ushankar@purestorage.com/):
- Make the fast-path test in ublk_queue_rq access the queue-local copy
  of the device flags.

 drivers/block/ublk_drv.c | 63 +++++++++++++++++++++++++++-------------
 1 file changed, 43 insertions(+), 20 deletions(-)

Comments

Ming Lei Sept. 25, 2024, 3:54 a.m. UTC | #1
On Mon, Sep 16, 2024 at 06:21:53PM -0600, Uday Shankar wrote:
> ublk currently supports the following behaviors on ublk server exit:
> 
> A: outstanding I/Os get errors, subsequently issued I/Os get errors
> B: outstanding I/Os get errors, subsequently issued I/Os queue
> C: outstanding I/Os get reissued, subsequently issued I/Os queue
> 
> and the following behaviors for recovery of preexisting block devices by
> a future incarnation of the ublk server:
> 
> 1: ublk devices stopped on ublk server exit (no recovery possible)
> 2: ublk devices are recoverable using start/end_recovery commands
> 
> The userspace interface allows selection of combinations of these
> behaviors using flags specified at device creation time, namely:
> 
> default behavior: A + 1
> UBLK_F_USER_RECOVERY: B + 2
> UBLK_F_USER_RECOVERY|UBLK_F_USER_RECOVERY_REISSUE: C + 2
> 
> We can't easily change the userspace interface to allow independent
> selection of one of {A, B, C} and one of {1, 2}, but we can refactor the
> internal helpers which test for the flags. Replace the existing helpers
> with the following set:
> 
> ublk_nosrv_should_reissue_outstanding: tests for behavior C
> ublk_nosrv_[dev_]should_queue_io: tests for behavior B
> ublk_nosrv_should_stop_dev: tests for behavior 1
> 
> Signed-off-by: Uday Shankar <ushankar@purestorage.com>
> ---
> Changes since v1 (https://lore.kernel.org/linux-block/20240617194451.435445-3-ushankar@purestorage.com/):
> - Make the fast-path test in ublk_queue_rq access the queue-local copy
>   of the device flags.
> 
>  drivers/block/ublk_drv.c | 63 +++++++++++++++++++++++++++-------------
>  1 file changed, 43 insertions(+), 20 deletions(-)
> 
> diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
> index 5e04a0fcd0b7..b069f4d2b9d2 100644
> --- a/drivers/block/ublk_drv.c
> +++ b/drivers/block/ublk_drv.c
> @@ -675,22 +675,45 @@ static inline int ublk_queue_cmd_buf_size(struct ublk_device *ub, int q_id)
>  			PAGE_SIZE);
>  }
>  
> -static inline bool ublk_queue_can_use_recovery_reissue(
> -		struct ublk_queue *ubq)
> +/*
> + * Should I/O outstanding to the ublk server when it exits be reissued?
> + * If not, outstanding I/O will get errors.
> + */
> +static inline bool ublk_nosrv_should_reissue_outstanding(struct ublk_device *ub)
>  {
> -	return (ubq->flags & UBLK_F_USER_RECOVERY) &&
> -			(ubq->flags & UBLK_F_USER_RECOVERY_REISSUE);
> +	return (ub->dev_info.flags & UBLK_F_USER_RECOVERY) &&
> +	       (ub->dev_info.flags & UBLK_F_USER_RECOVERY_REISSUE);
>  }
>  
> -static inline bool ublk_queue_can_use_recovery(
> -		struct ublk_queue *ubq)
> +/*
> + * Should I/O issued while there is no ublk server queue? If not, I/O
> + * issued while there is no ublk server will get errors.
> + */
> +static inline bool ublk_nosrv_dev_should_queue_io(struct ublk_device *ub)
> +{
> +	return ub->dev_info.flags & UBLK_F_USER_RECOVERY;
> +}
> +
> +/*
> + * Same as ublk_nosrv_dev_should_queue_io, but uses a queue-local copy
> + * of the device flags for smaller cache footprint - better for fast
> + * paths.
> + */
> +static inline bool ublk_nosrv_should_queue_io(struct ublk_queue *ubq)
>  {
>  	return ubq->flags & UBLK_F_USER_RECOVERY;
>  }
>  
> -static inline bool ublk_can_use_recovery(struct ublk_device *ub)
> +/*
> + * Should ublk devices be stopped (i.e. no recovery possible) when the
> + * ublk server exits? If not, devices can be used again by a future
> + * incarnation of a ublk server via the start_recovery/end_recovery
> + * commands.
> + */
> +static inline bool ublk_nosrv_should_stop_dev(struct ublk_device *ub)
>  {
> -	return ub->dev_info.flags & UBLK_F_USER_RECOVERY;
> +	return (!(ub->dev_info.flags & UBLK_F_USER_RECOVERY)) &&
> +	       (!(ub->dev_info.flags & UBLK_F_USER_RECOVERY_REISSUE));
>  }

It should be enough to check UBLK_F_USER_RECOVERY only since
UBLK_F_USER_RECOVERY_REISSUE implies UBLK_F_USER_RECOVERY.

Otherwise, this patch looks fine.


Thanks, 
Ming
diff mbox series

Patch

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 5e04a0fcd0b7..b069f4d2b9d2 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -675,22 +675,45 @@  static inline int ublk_queue_cmd_buf_size(struct ublk_device *ub, int q_id)
 			PAGE_SIZE);
 }
 
-static inline bool ublk_queue_can_use_recovery_reissue(
-		struct ublk_queue *ubq)
+/*
+ * Should I/O outstanding to the ublk server when it exits be reissued?
+ * If not, outstanding I/O will get errors.
+ */
+static inline bool ublk_nosrv_should_reissue_outstanding(struct ublk_device *ub)
 {
-	return (ubq->flags & UBLK_F_USER_RECOVERY) &&
-			(ubq->flags & UBLK_F_USER_RECOVERY_REISSUE);
+	return (ub->dev_info.flags & UBLK_F_USER_RECOVERY) &&
+	       (ub->dev_info.flags & UBLK_F_USER_RECOVERY_REISSUE);
 }
 
-static inline bool ublk_queue_can_use_recovery(
-		struct ublk_queue *ubq)
+/*
+ * Should I/O issued while there is no ublk server queue? If not, I/O
+ * issued while there is no ublk server will get errors.
+ */
+static inline bool ublk_nosrv_dev_should_queue_io(struct ublk_device *ub)
+{
+	return ub->dev_info.flags & UBLK_F_USER_RECOVERY;
+}
+
+/*
+ * Same as ublk_nosrv_dev_should_queue_io, but uses a queue-local copy
+ * of the device flags for smaller cache footprint - better for fast
+ * paths.
+ */
+static inline bool ublk_nosrv_should_queue_io(struct ublk_queue *ubq)
 {
 	return ubq->flags & UBLK_F_USER_RECOVERY;
 }
 
-static inline bool ublk_can_use_recovery(struct ublk_device *ub)
+/*
+ * Should ublk devices be stopped (i.e. no recovery possible) when the
+ * ublk server exits? If not, devices can be used again by a future
+ * incarnation of a ublk server via the start_recovery/end_recovery
+ * commands.
+ */
+static inline bool ublk_nosrv_should_stop_dev(struct ublk_device *ub)
 {
-	return ub->dev_info.flags & UBLK_F_USER_RECOVERY;
+	return (!(ub->dev_info.flags & UBLK_F_USER_RECOVERY)) &&
+	       (!(ub->dev_info.flags & UBLK_F_USER_RECOVERY_REISSUE));
 }
 
 static void ublk_free_disk(struct gendisk *disk)
@@ -1066,7 +1089,7 @@  static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io,
 {
 	WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE);
 
-	if (ublk_queue_can_use_recovery_reissue(ubq))
+	if (ublk_nosrv_should_reissue_outstanding(ubq->dev))
 		blk_mq_requeue_request(req, false);
 	else
 		ublk_put_req_ref(ubq, req);
@@ -1094,7 +1117,7 @@  static inline void __ublk_abort_rq(struct ublk_queue *ubq,
 		struct request *rq)
 {
 	/* We cannot process this rq so just requeue it. */
-	if (ublk_queue_can_use_recovery(ubq))
+	if (ublk_nosrv_dev_should_queue_io(ubq->dev))
 		blk_mq_requeue_request(rq, false);
 	else
 		blk_mq_end_request(rq, BLK_STS_IOERR);
@@ -1239,10 +1262,10 @@  static enum blk_eh_timer_return ublk_timeout(struct request *rq)
 		struct ublk_device *ub = ubq->dev;
 
 		if (ublk_abort_requests(ub, ubq)) {
-			if (ublk_can_use_recovery(ub))
-				schedule_work(&ub->quiesce_work);
-			else
+			if (ublk_nosrv_should_stop_dev(ub))
 				schedule_work(&ub->stop_work);
+			else
+				schedule_work(&ub->quiesce_work);
 		}
 		return BLK_EH_DONE;
 	}
@@ -1271,7 +1294,7 @@  static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx,
 	 * Note: force_abort is guaranteed to be seen because it is set
 	 * before request queue is unqiuesced.
 	 */
-	if (ublk_queue_can_use_recovery(ubq) && unlikely(ubq->force_abort))
+	if (ublk_nosrv_should_queue_io(ubq) && unlikely(ubq->force_abort))
 		return BLK_STS_IOERR;
 
 	if (unlikely(ubq->canceling)) {
@@ -1492,10 +1515,10 @@  static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd,
 	ublk_cancel_cmd(ubq, io, issue_flags);
 
 	if (need_schedule) {
-		if (ublk_can_use_recovery(ub))
-			schedule_work(&ub->quiesce_work);
-		else
+		if (ublk_nosrv_should_stop_dev(ub))
 			schedule_work(&ub->stop_work);
+		else
+			schedule_work(&ub->quiesce_work);
 	}
 }
 
@@ -1600,7 +1623,7 @@  static void ublk_stop_dev(struct ublk_device *ub)
 	mutex_lock(&ub->mutex);
 	if (ub->dev_info.state == UBLK_S_DEV_DEAD)
 		goto unlock;
-	if (ublk_can_use_recovery(ub)) {
+	if (ublk_nosrv_dev_should_queue_io(ub)) {
 		if (ub->dev_info.state == UBLK_S_DEV_LIVE)
 			__ublk_quiesce_dev(ub);
 		ublk_unquiesce_dev(ub);
@@ -2702,7 +2725,7 @@  static int ublk_ctrl_start_recovery(struct ublk_device *ub,
 	int i;
 
 	mutex_lock(&ub->mutex);
-	if (!ublk_can_use_recovery(ub))
+	if (ublk_nosrv_should_stop_dev(ub))
 		goto out_unlock;
 	if (!ub->nr_queues_ready)
 		goto out_unlock;
@@ -2755,7 +2778,7 @@  static int ublk_ctrl_end_recovery(struct ublk_device *ub,
 			__func__, ub->dev_info.nr_hw_queues, header->dev_id);
 
 	mutex_lock(&ub->mutex);
-	if (!ublk_can_use_recovery(ub))
+	if (ublk_nosrv_should_stop_dev(ub))
 		goto out_unlock;
 
 	if (ub->dev_info.state != UBLK_S_DEV_QUIESCED) {