[PATCH v1 6/7] ublk: simplify aborting ublk request

[PATCH v1 6/7] ublk: simplify aborting ublk request

[Jared Holzman]

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

Now ublk_abort_queue() is moved to ublk char device release handler,
meantime our request queue is "quiesced" because either ->canceling was
set from uring_cmd cancel function or all IOs are inflight and can't be
completed by ublk server, things becomes easy much:

- all uring_cmd are done, so we needn't to mark io as UBLK_IO_FLAG_ABORTED
for handling completion from uring_cmd

- ublk char device is closed, no one can hold IO request reference any more,
so we can simply complete this request or requeue it for ublk_nosrv_should_reissue_outstanding.

Reviewed-by: Uday Shankar <ushankar@purestorage.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250416035444.99569-8-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/ublk_drv.c | 82 ++++++++++------------------------------
 1 file changed, 20 insertions(+), 62 deletions(-)

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index c3f576a9dbf2..6000147ac2a5 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -115,15 +115,6 @@ struct ublk_uring_cmd_pdu {
  */
 #define UBLK_IO_FLAG_OWNED_BY_SRV 0x02
 
-/*
- * IO command is aborted, so this flag is set in case of
- * !UBLK_IO_FLAG_ACTIVE.
- *
- * After this flag is observed, any pending or new incoming request
- * associated with this io command will be failed immediately
- */
-#define UBLK_IO_FLAG_ABORTED 0x04
-
 /*
  * UBLK_IO_FLAG_NEED_GET_DATA is set because IO command requires
  * get data buffer address from ublksrv.
@@ -1054,12 +1045,6 @@ static inline void __ublk_complete_rq(struct request *req)
 	unsigned int unmapped_bytes;
 	blk_status_t res = BLK_STS_OK;
 
-	/* called from ublk_abort_queue() code path */
-	if (io->flags & UBLK_IO_FLAG_ABORTED) {
-		res = BLK_STS_IOERR;
-		goto exit;
-	}
-
 	/* failed read IO if nothing is read */
 	if (!io->res && req_op(req) == REQ_OP_READ)
 		io->res = -EIO;
@@ -1109,47 +1094,6 @@ static void ublk_complete_rq(struct kref *ref)
 	__ublk_complete_rq(req);
 }
 
-static void ublk_do_fail_rq(struct request *req)
-{
-	struct ublk_queue *ubq = req->mq_hctx->driver_data;
-
-	if (ublk_nosrv_should_reissue_outstanding(ubq->dev))
-		blk_mq_requeue_request(req, false);
-	else
-		__ublk_complete_rq(req);
-}
-
-static void ublk_fail_rq_fn(struct kref *ref)
-{
-	struct ublk_rq_data *data = container_of(ref, struct ublk_rq_data,
-			ref);
-	struct request *req = blk_mq_rq_from_pdu(data);
-
-	ublk_do_fail_rq(req);
-}
-
-/*
- * Since ublk_rq_task_work_cb always fails requests immediately during
- * exiting, __ublk_fail_req() is only called from abort context during
- * exiting. So lock is unnecessary.
- *
- * Also aborting may not be started yet, keep in mind that one failed
- * request may be issued by block layer again.
- */
-static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io,
-		struct request *req)
-{
-	WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE);
-
-	if (ublk_need_req_ref(ubq)) {
-		struct ublk_rq_data *data = blk_mq_rq_to_pdu(req);
-
-		kref_put(&data->ref, ublk_fail_rq_fn);
-	} else {
-		ublk_do_fail_rq(req);
-	}
-}
-
 static void ubq_complete_io_cmd(struct ublk_io *io, int res,
 				unsigned issue_flags)
 {
@@ -1639,10 +1583,26 @@ static void ublk_commit_completion(struct ublk_device *ub,
 		ublk_put_req_ref(ubq, req);
 }
 
+static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io,
+		struct request *req)
+{
+	WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE);
+
+	if (ublk_nosrv_should_reissue_outstanding(ubq->dev))
+		blk_mq_requeue_request(req, false);
+	else {
+		io->res = -EIO;
+		__ublk_complete_rq(req);
+	}
+}
+
 /*
- * Called from ubq_daemon context via cancel fn, meantime quiesce ublk
- * blk-mq queue, so we are called exclusively with blk-mq and ubq_daemon
- * context, so everything is serialized.
+ * Called from ublk char device release handler, when any uring_cmd is
+ * done, meantime request queue is "quiesced" since all inflight requests
+ * can't be completed because ublk server is dead.
+ *
+ * So no one can hold our request IO reference any more, simply ignore the
+ * reference, and complete the request immediately
  */
 static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq)
 {
@@ -1659,10 +1619,8 @@ static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq)
 			 * will do it
 			 */
 			rq = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], i);
-			if (rq && blk_mq_request_started(rq)) {
-				io->flags |= UBLK_IO_FLAG_ABORTED;
+			if (rq && blk_mq_request_started(rq))
 				__ublk_fail_req(ubq, io, rq);
-			}
 		}
 	}
 }
-- 
2.43.0

[PATCH v1 0/7] ublk: Backport to 6.14-stable: fix race between io_uring_cmd_complete_in_task and ublk_cancel_cmd

[Jared Holzman]

This patchset backports a series of ublk fixes from upstream to 6.14-stable.

Patch 7 fixes the race that can cause kernel panic when ublk server daemon is exiting.

It depends on patches 1-6 which simplifies & improves IO canceling when ublk server daemon
is exiting as described here:

https://lore.kernel.org/linux-block/20250416035444.99569-1-ming.lei@redhat.com/

Ming Lei (5):
  ublk: add helper of ublk_need_map_io()
  ublk: move device reset into ublk_ch_release()
  ublk: remove __ublk_quiesce_dev()
  ublk: simplify aborting ublk request
  ublk: fix race between io_uring_cmd_complete_in_task and
    ublk_cancel_cmd

Uday Shankar (2):
  ublk: properly serialize all FETCH_REQs
  ublk: improve detection and handling of ublk server exit

 drivers/block/ublk_drv.c | 550 +++++++++++++++++++++------------------
 1 file changed, 291 insertions(+), 259 deletions(-)

-- 
2.43.0

[PATCH v1 6/7] ublk: simplify aborting ublk request

[Jared Holzman]

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

Now ublk_abort_queue() is moved to ublk char device release handler,
meantime our request queue is "quiesced" because either ->canceling was
set from uring_cmd cancel function or all IOs are inflight and can't be
completed by ublk server, things becomes easy much:

- all uring_cmd are done, so we needn't to mark io as UBLK_IO_FLAG_ABORTED
for handling completion from uring_cmd

- ublk char device is closed, no one can hold IO request reference any more,
so we can simply complete this request or requeue it for ublk_nosrv_should_reissue_outstanding.

Reviewed-by: Uday Shankar <ushankar@purestorage.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250416035444.99569-8-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/ublk_drv.c | 82 ++++++++++------------------------------
 1 file changed, 20 insertions(+), 62 deletions(-)

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index c3f576a9dbf2..6000147ac2a5 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -115,15 +115,6 @@ struct ublk_uring_cmd_pdu {
  */
 #define UBLK_IO_FLAG_OWNED_BY_SRV 0x02
 
-/*
- * IO command is aborted, so this flag is set in case of
- * !UBLK_IO_FLAG_ACTIVE.
- *
- * After this flag is observed, any pending or new incoming request
- * associated with this io command will be failed immediately
- */
-#define UBLK_IO_FLAG_ABORTED 0x04
-
 /*
  * UBLK_IO_FLAG_NEED_GET_DATA is set because IO command requires
  * get data buffer address from ublksrv.
@@ -1054,12 +1045,6 @@ static inline void __ublk_complete_rq(struct request *req)
 	unsigned int unmapped_bytes;
 	blk_status_t res = BLK_STS_OK;
 
-	/* called from ublk_abort_queue() code path */
-	if (io->flags & UBLK_IO_FLAG_ABORTED) {
-		res = BLK_STS_IOERR;
-		goto exit;
-	}
-
 	/* failed read IO if nothing is read */
 	if (!io->res && req_op(req) == REQ_OP_READ)
 		io->res = -EIO;
@@ -1109,47 +1094,6 @@ static void ublk_complete_rq(struct kref *ref)
 	__ublk_complete_rq(req);
 }
 
-static void ublk_do_fail_rq(struct request *req)
-{
-	struct ublk_queue *ubq = req->mq_hctx->driver_data;
-
-	if (ublk_nosrv_should_reissue_outstanding(ubq->dev))
-		blk_mq_requeue_request(req, false);
-	else
-		__ublk_complete_rq(req);
-}
-
-static void ublk_fail_rq_fn(struct kref *ref)
-{
-	struct ublk_rq_data *data = container_of(ref, struct ublk_rq_data,
-			ref);
-	struct request *req = blk_mq_rq_from_pdu(data);
-
-	ublk_do_fail_rq(req);
-}
-
-/*
- * Since ublk_rq_task_work_cb always fails requests immediately during
- * exiting, __ublk_fail_req() is only called from abort context during
- * exiting. So lock is unnecessary.
- *
- * Also aborting may not be started yet, keep in mind that one failed
- * request may be issued by block layer again.
- */
-static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io,
-		struct request *req)
-{
-	WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE);
-
-	if (ublk_need_req_ref(ubq)) {
-		struct ublk_rq_data *data = blk_mq_rq_to_pdu(req);
-
-		kref_put(&data->ref, ublk_fail_rq_fn);
-	} else {
-		ublk_do_fail_rq(req);
-	}
-}
-
 static void ubq_complete_io_cmd(struct ublk_io *io, int res,
 				unsigned issue_flags)
 {
@@ -1639,10 +1583,26 @@ static void ublk_commit_completion(struct ublk_device *ub,
 		ublk_put_req_ref(ubq, req);
 }
 
+static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io,
+		struct request *req)
+{
+	WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE);
+
+	if (ublk_nosrv_should_reissue_outstanding(ubq->dev))
+		blk_mq_requeue_request(req, false);
+	else {
+		io->res = -EIO;
+		__ublk_complete_rq(req);
+	}
+}
+
 /*
- * Called from ubq_daemon context via cancel fn, meantime quiesce ublk
- * blk-mq queue, so we are called exclusively with blk-mq and ubq_daemon
- * context, so everything is serialized.
+ * Called from ublk char device release handler, when any uring_cmd is
+ * done, meantime request queue is "quiesced" since all inflight requests
+ * can't be completed because ublk server is dead.
+ *
+ * So no one can hold our request IO reference any more, simply ignore the
+ * reference, and complete the request immediately
  */
 static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq)
 {
@@ -1659,10 +1619,8 @@ static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq)
 			 * will do it
 			 */
 			rq = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], i);
-			if (rq && blk_mq_request_started(rq)) {
-				io->flags |= UBLK_IO_FLAG_ABORTED;
+			if (rq && blk_mq_request_started(rq))
 				__ublk_fail_req(ubq, io, rq);
-			}
 		}
 	}
 }
-- 
2.43.0