Linux io-uring development
 help / color / mirror / Atom feed
From: Qiliang Yuan <qiliang.yuan@linux.dev>
To: "Martin K. Petersen" <mkp@kernel.org>,
	Shuah Khan <shuah@kernel.org>,  Jonathan Corbet <corbet@lwn.net>,
	Shuah Khan <skhan@linuxfoundation.org>,
	 Randy Dunlap <rdunlap@infradead.org>
Cc: linux-kernel@vger.kernel.org, linux-scsi@vger.kernel.org,
	 target-devel@vger.kernel.org, linux-kselftest@vger.kernel.org,
	 linux-doc@vger.kernel.org, Jens Axboe <axboe@kernel.dk>,
	 io-uring@vger.kernel.org,
	Mike Christie <michael.christie@oracle.com>,
	 Bodo Stroesser <bostroesser@gmail.com>,
	Ming Lei <tom.leiming@gmail.com>,
	 Qiliang Yuan <qiliang.yuan@linux.dev>
Subject: [PATCH RFC 10/18] scsi: target: uring: Time out commands the server does not complete
Date: Sun, 15 Nov 2026 19:18:03 -0500	[thread overview]
Message-ID: <20261115-feat-target-core-uring-v1-10-28cdc137eac6@linux.dev> (raw)
In-Reply-To: <20261115-feat-target-core-uring-v1-0-28cdc137eac6@linux.dev>

Commands of a target_core_uring device wait on a pending list until a
server fetches them, and then for the server to commit them.

Without a server, or with one that hangs, they wait forever, and so
does everything that waits for them, such as removing the LUN.

Add the cmd_time_out parameter, 30 seconds by default, and fail the
commands that are older. A delayed work scans the queues when the oldest
command is due. A timed out command that the server works on is
completed, but the server keeps the tag until it commits it.

Signed-off-by: Qiliang Yuan <qiliang.yuan@linux.dev>
---
 drivers/target/target_core_uring.c | 80 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 78 insertions(+), 2 deletions(-)

diff --git a/drivers/target/target_core_uring.c b/drivers/target/target_core_uring.c
index 2978dd08c99cf..0f83bdc55e06a 100644
--- a/drivers/target/target_core_uring.c
+++ b/drivers/target/target_core_uring.c
@@ -21,6 +21,7 @@
 #include <linux/slab.h>
 #include <linux/uio.h>
 #include <linux/vmalloc.h>
+#include <linux/workqueue.h>
 #include <scsi/scsi_proto.h>
 #include <target/target_core_base.h>
 #include <target/target_core_backend.h>
@@ -31,6 +32,7 @@
 #define TCMUR_MAX_IO_SIZE	(4U << 20)
 #define TCMUR_DEF_QUEUE_DEPTH	128
 #define TCMUR_DEF_BLOCK_SIZE	512
+#define TCMUR_DEF_CMD_TIMEOUT	30
 
 /* Set while the file is open, to allow one server at a time */
 #define TCMUR_DEV_OPEN		0
@@ -46,6 +48,7 @@ struct tcmur_dev;
  * @desc:	What the server is asked to do
  * @ref:	Held by the tag or the pending list and by data copies in
  *		progress
+ * @deadline:	When to give up waiting for the server
  * @status:	SAM status to complete @se_cmd with
  */
 struct tcmur_cmd {
@@ -55,6 +58,7 @@ struct tcmur_cmd {
 	u32			sgl_nents;
 	struct tcmur_io_desc	desc;
 	refcount_t		ref;
+	unsigned long		deadline;
 	u8			status;
 };
 
@@ -102,8 +106,10 @@ struct tcmur_dev {
 	u32			block_size;
 	u16			nr_queues;
 	u16			queue_depth;
+	unsigned int		cmd_timeout;
 
 	struct tcmur_queue	*queues;
+	struct delayed_work	timeout_work;
 };
 
 /**
@@ -190,6 +196,8 @@ static void tcmur_queue_cmd(struct tcmur_dev *udev, struct tcmur_cmd *tcmd)
 	struct tcmur_io *io;
 
 	refcount_set(&tcmd->ref, 1);
+	if (udev->cmd_timeout)
+		tcmd->deadline = jiffies + udev->cmd_timeout * HZ;
 
 	spin_lock(&q->lock);
 	io = list_first_entry_or_null(&q->idle, struct tcmur_io, node);
@@ -205,6 +213,9 @@ static void tcmur_queue_cmd(struct tcmur_dev *udev, struct tcmur_cmd *tcmd)
 
 	if (ucmd)
 		io_uring_cmd_complete_in_task(ucmd, tcmur_fetch_tw_cb);
+	if (udev->cmd_timeout)
+		schedule_delayed_work(&udev->timeout_work,
+				      udev->cmd_timeout * HZ);
 }
 
 static sense_reason_t tcmur_submit(struct se_cmd *se_cmd, u32 op, u64 offset,
@@ -244,6 +255,58 @@ static sense_reason_t tcmur_execute_rw(struct se_cmd *se_cmd,
 			    se_cmd->data_length, sgl, sgl_nents);
 }
 
+static void tcmur_timeout_work(struct work_struct *work)
+{
+	struct tcmur_dev *udev = container_of(work, struct tcmur_dev,
+					      timeout_work.work);
+	unsigned long now = jiffies, next = 0;
+	struct tcmur_cmd *tcmd, *tmp;
+	struct tcmur_queue *q;
+	struct tcmur_io *io;
+	bool rearm = false;
+	LIST_HEAD(expired);
+	unsigned int i, j;
+
+	for (i = 0; i < udev->nr_queues; i++) {
+		q = &udev->queues[i];
+
+		spin_lock(&q->lock);
+		list_for_each_entry_safe(tcmd, tmp, &q->pending, node) {
+			if (time_after(tcmd->deadline, now)) {
+				if (!rearm || time_before(tcmd->deadline, next))
+					next = tcmd->deadline;
+				rearm = true;
+				break;
+			}
+			list_move_tail(&tcmd->node, &expired);
+		}
+		for (j = 0; j < udev->queue_depth; j++) {
+			io = &q->ios[j];
+			tcmd = io->cmd;
+			if (!tcmd)
+				continue;
+			if (time_after(tcmd->deadline, now)) {
+				if (!rearm || time_before(tcmd->deadline, next))
+					next = tcmd->deadline;
+				rearm = true;
+				continue;
+			}
+			/* Leave the tag to the server until it commits it */
+			io->cmd = NULL;
+			list_add_tail(&tcmd->node, &expired);
+		}
+		spin_unlock(&q->lock);
+	}
+
+	if (!list_empty(&expired))
+		pr_warn_ratelimited("tcmur%d: command timed out\n",
+				    udev->dev_id);
+	tcmur_end_cmds(&expired, SAM_STAT_CHECK_CONDITION);
+
+	if (rearm)
+		schedule_delayed_work(&udev->timeout_work, next - now);
+}
+
 /* Take a reference on the command the server works on in (@q_id, @tag) */
 static struct tcmur_cmd *tcmur_get_cmd(struct tcmur_dev *udev, u16 q_id,
 				       u16 tag)
@@ -331,7 +394,10 @@ static int tcmur_commit(struct tcmur_queue *q, struct tcmur_io *io, int result)
 	io->owned = false;
 	spin_unlock(&q->lock);
 
-	tcmur_cmd_end(tcmd, result ? SAM_STAT_CHECK_CONDITION : SAM_STAT_GOOD);
+	/* Skip a command that timed out already */
+	if (tcmd)
+		tcmur_cmd_end(tcmd, result ? SAM_STAT_CHECK_CONDITION :
+					     SAM_STAT_GOOD);
 	return 0;
 }
 
@@ -639,6 +705,8 @@ static struct se_device *tcmur_alloc_device(struct se_hba *hba,
 	udev->nr_queues = 1;
 	udev->queue_depth = TCMUR_DEF_QUEUE_DEPTH;
 	udev->block_size = TCMUR_DEF_BLOCK_SIZE;
+	udev->cmd_timeout = TCMUR_DEF_CMD_TIMEOUT;
+	INIT_DELAYED_WORK(&udev->timeout_work, tcmur_timeout_work);
 
 	device_initialize(&udev->cdev_dev);
 	udev->cdev_dev.class = &tcmur_class;
@@ -723,6 +791,8 @@ static void tcmur_destroy_device(struct se_device *dev)
 		}
 		spin_unlock(&q->lock);
 	}
+
+	cancel_delayed_work_sync(&udev->timeout_work);
 }
 
 static void tcmur_free_device(struct se_device *dev)
@@ -731,7 +801,8 @@ static void tcmur_free_device(struct se_device *dev)
 }
 
 enum {
-	Opt_dev_size, Opt_block_size, Opt_nr_queues, Opt_queue_depth, Opt_err,
+	Opt_dev_size, Opt_block_size, Opt_nr_queues, Opt_queue_depth,
+	Opt_cmd_time_out, Opt_err,
 };
 
 static const match_table_t tcmur_tokens = {
@@ -739,6 +810,7 @@ static const match_table_t tcmur_tokens = {
 	{ Opt_block_size,	"block_size=%u" },
 	{ Opt_nr_queues,	"nr_queues=%u" },
 	{ Opt_queue_depth,	"queue_depth=%u" },
+	{ Opt_cmd_time_out,	"cmd_time_out=%u" },
 	{ Opt_err,		NULL }
 };
 
@@ -794,6 +866,9 @@ static ssize_t tcmur_set_configfs_dev_params(struct se_device *dev,
 			else
 				udev->queue_depth = val;
 			break;
+		case Opt_cmd_time_out:
+			udev->cmd_timeout = val;
+			break;
 		}
 	}
 
@@ -812,6 +887,7 @@ static ssize_t tcmur_show_configfs_dev_params(struct se_device *dev, char *b)
 		      udev->block_size);
 	bl += sprintf(b + bl, " Queues: %u Queue depth: %u", udev->nr_queues,
 		      udev->queue_depth);
+	bl += sprintf(b + bl, " Command timeout: %u", udev->cmd_timeout);
 	bl += sprintf(b + bl, "\n");
 	return bl;
 }

-- 
2.43.0


  parent reply	other threads:[~2026-11-16  0:19 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-16  0:17 [PATCH RFC 00/18] scsi: target: Add target_core_uring, an io_uring based user backstore Qiliang Yuan
2026-11-16  0:17 ` [PATCH RFC 01/18] scsi: target: uring: Introduce " Qiliang Yuan
2026-11-16  0:17 ` [PATCH RFC 02/18] scsi: target: uring: Allocate per-queue command descriptors Qiliang Yuan
2026-11-16  0:17 ` [PATCH RFC 03/18] scsi: target: uring: Create a character device per backstore device Qiliang Yuan
2026-11-16  0:17 ` [PATCH RFC 04/18] scsi: target: uring: Map the command descriptors into the server Qiliang Yuan
2026-11-16  0:17 ` [PATCH RFC 05/18] scsi: target: uring: Queue commands until a server fetches them Qiliang Yuan
2026-11-16  0:17 ` [PATCH RFC 06/18] scsi: target: uring: Hand commands out through TCMUR_IO_FETCH Qiliang Yuan
2026-11-16  0:18 ` [PATCH RFC 07/18] scsi: target: uring: Complete commands with TCMUR_IO_COMMIT_AND_FETCH Qiliang Yuan
2026-11-16  0:18 ` [PATCH RFC 08/18] scsi: target: uring: Copy command data with pread() and pwrite() Qiliang Yuan
2026-11-16  0:18 ` [PATCH RFC 09/18] scsi: target: uring: Fail in-flight commands when the server exits Qiliang Yuan
2026-11-16  0:18 ` Qiliang Yuan [this message]
2026-11-16  0:18 ` [PATCH RFC 11/18] scsi: target: uring: Drop aborted commands that are still queued Qiliang Yuan
2026-11-16  0:18 ` [PATCH RFC 12/18] scsi: target: uring: Support SYNCHRONIZE CACHE Qiliang Yuan
2026-11-16  0:18 ` [PATCH RFC 13/18] scsi: target: uring: Implement UNMAP Qiliang Yuan
2026-11-16  0:18 ` [PATCH RFC 14/18] scsi: target: uring: Handle WRITE SAME Qiliang Yuan
2026-11-16  0:18 ` [PATCH RFC 15/18] scsi: target: uring: Register command data as io_uring fixed buffers Qiliang Yuan
2026-11-16  0:18 ` [PATCH RFC 16/18] selftests: target_core_uring: Add a minimal server Qiliang Yuan
2026-11-16  0:18 ` [PATCH RFC 17/18] selftests: target_core_uring: Test a device exported through tcm_loop Qiliang Yuan
2026-11-16  0:18 ` [PATCH RFC 18/18] Documentation: target: Describe the uring backstore Qiliang Yuan

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20261115-feat-target-core-uring-v1-10-28cdc137eac6@linux.dev \
    --to=qiliang.yuan@linux.dev \
    --cc=axboe@kernel.dk \
    --cc=bostroesser@gmail.com \
    --cc=corbet@lwn.net \
    --cc=io-uring@vger.kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=michael.christie@oracle.com \
    --cc=mkp@kernel.org \
    --cc=rdunlap@infradead.org \
    --cc=shuah@kernel.org \
    --cc=skhan@linuxfoundation.org \
    --cc=target-devel@vger.kernel.org \
    --cc=tom.leiming@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox