diff mbox series

[4/8] vhost scsi: fix cmd completion race

Message ID 1600712588-9514-5-git-send-email-michael.christie@oracle.com (mailing list archive)
State New, archived
Headers show
Series vhost scsi: fixes and cleanups | expand

Commit Message

Mike Christie Sept. 21, 2020, 6:23 p.m. UTC 
We might not do the final se_cmd put from vhost_scsi_complete_cmd_work.
If the last put happens a little later then we could race where
vhost_scsi_complete_cmd_work does vhost_signal, the guest runs and sends
more IO, and vhost_scsi_handle_vq runs but does not find any free cmds.

This patch has us delay completing the cmd until the last lio core ref
is dropped. We then know that once we signal to the guest that the cmd
is completed that if it queues a new command it will find a free cmd.

Signed-off-by: Mike Christie <michael.christie@oracle.com>
---
 drivers/vhost/scsi.c | 42 +++++++++++++++---------------------------
 1 file changed, 15 insertions(+), 27 deletions(-)

Comments

Bart Van Assche Sept. 22, 2020, 2:48 a.m. UTC | #1 
On 2020-09-21 11:23, Mike Christie wrote:
> We might not do the final se_cmd put from vhost_scsi_complete_cmd_work.
> If the last put happens a little later then we could race where
> vhost_scsi_complete_cmd_work does vhost_signal, the guest runs and sends
> more IO, and vhost_scsi_handle_vq runs but does not find any free cmds.
> 
> This patch has us delay completing the cmd until the last lio core ref
> is dropped. We then know that once we signal to the guest that the cmd
> is completed that if it queues a new command it will find a free cmd.

It seems weird to me to see a reference to LIO in the description of a
vhost patch? Since this driver supports more backends than LIO, shouldn't
the patch description be made more generic?

Thanks,

Bart.
Bart Van Assche Sept. 22, 2020, 2:51 a.m. UTC | #2 
On 2020-09-21 19:48, Bart Van Assche wrote:
> On 2020-09-21 11:23, Mike Christie wrote:
>> We might not do the final se_cmd put from vhost_scsi_complete_cmd_work.
>> If the last put happens a little later then we could race where
>> vhost_scsi_complete_cmd_work does vhost_signal, the guest runs and sends
>> more IO, and vhost_scsi_handle_vq runs but does not find any free cmds.
>>
>> This patch has us delay completing the cmd until the last lio core ref
>> is dropped. We then know that once we signal to the guest that the cmd
>> is completed that if it queues a new command it will find a free cmd.
> 
> It seems weird to me to see a reference to LIO in the description of a
> vhost patch? Since this driver supports more backends than LIO, shouldn't
> the patch description be made more generic?

Please ignore the above comment.

Bart.
diff mbox series

Patch

diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 13311b8..26d0f75 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -322,7 +322,7 @@  static u32 vhost_scsi_tpg_get_inst_index(struct se_portal_group *se_tpg)
 	return 1;
 }
 
-static void vhost_scsi_release_cmd(struct se_cmd *se_cmd)
+static void vhost_scsi_release_cmd_res(struct se_cmd *se_cmd)
 {
 	struct vhost_scsi_cmd *tv_cmd = container_of(se_cmd,
 				struct vhost_scsi_cmd, tvc_se_cmd);
@@ -344,6 +344,16 @@  static void vhost_scsi_release_cmd(struct se_cmd *se_cmd)
 	vhost_scsi_put_inflight(inflight);
 }
 
+static void vhost_scsi_release_cmd(struct se_cmd *se_cmd)
+{
+	struct vhost_scsi_cmd *cmd = container_of(se_cmd,
+					struct vhost_scsi_cmd, tvc_se_cmd);
+	struct vhost_scsi *vs = cmd->tvc_vhost;
+
+	llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list);
+	vhost_work_queue(&vs->dev, &vs->vs_completion_work);
+}
+
 static u32 vhost_scsi_sess_get_index(struct se_session *se_sess)
 {
 	return 0;
@@ -366,28 +376,15 @@  static int vhost_scsi_get_cmd_state(struct se_cmd *se_cmd)
 	return 0;
 }
 
-static void vhost_scsi_complete_cmd(struct vhost_scsi_cmd *cmd)
-{
-	struct vhost_scsi *vs = cmd->tvc_vhost;
-
-	llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list);
-
-	vhost_work_queue(&vs->dev, &vs->vs_completion_work);
-}
-
 static int vhost_scsi_queue_data_in(struct se_cmd *se_cmd)
 {
-	struct vhost_scsi_cmd *cmd = container_of(se_cmd,
-				struct vhost_scsi_cmd, tvc_se_cmd);
-	vhost_scsi_complete_cmd(cmd);
+	transport_generic_free_cmd(se_cmd, 0);
 	return 0;
 }
 
 static int vhost_scsi_queue_status(struct se_cmd *se_cmd)
 {
-	struct vhost_scsi_cmd *cmd = container_of(se_cmd,
-				struct vhost_scsi_cmd, tvc_se_cmd);
-	vhost_scsi_complete_cmd(cmd);
+	transport_generic_free_cmd(se_cmd, 0);
 	return 0;
 }
 
@@ -433,15 +430,6 @@  static void vhost_scsi_free_evt(struct vhost_scsi *vs, struct vhost_scsi_evt *ev
 	return evt;
 }
 
-static void vhost_scsi_free_cmd(struct vhost_scsi_cmd *cmd)
-{
-	struct se_cmd *se_cmd = &cmd->tvc_se_cmd;
-
-	/* TODO locking against target/backend threads? */
-	transport_generic_free_cmd(se_cmd, 0);
-
-}
-
 static int vhost_scsi_check_stop_free(struct se_cmd *se_cmd)
 {
 	return target_put_sess_cmd(se_cmd);
@@ -560,7 +548,7 @@  static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
 		} else
 			pr_err("Faulted on virtio_scsi_cmd_resp\n");
 
-		vhost_scsi_free_cmd(cmd);
+		vhost_scsi_release_cmd_res(se_cmd);
 	}
 
 	vq = -1;
@@ -1092,7 +1080,7 @@  static void vhost_scsi_submission_work(struct work_struct *work)
 						      &prot_iter, exp_data_len,
 						      &data_iter))) {
 				vq_err(vq, "Failed to map iov to sgl\n");
-				vhost_scsi_release_cmd(&cmd->tvc_se_cmd);
+				vhost_scsi_release_cmd_res(&cmd->tvc_se_cmd);
 				goto err;
 			}
 		}