| Message ID | 1603326903-27052-10-git-send-email-michael.christie@oracle.com |
|---|---|
| State | Superseded |
| Headers | show |
| Series | vhost: fix scsi cmd handling and cgroup support | expand |
Dne 22. 10. 20 v 2:34 Mike Christie napsal(a): > We might not do the final se_cmd put from vhost_scsi_complete_cmd_work. > When 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(-) > > diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c > index f6b9010..2fa48dd 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; > @@ -1096,7 +1084,7 @@ static u16 vhost_buf_to_lun(u8 *lun_buf) > &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; > } > } > Looks ok to me. Reviewed-by: Maurizio Lombardi <mlombard@redhat.com>
On Wed, Oct 21, 2020 at 07:34:55PM -0500, Mike Christie wrote: > We might not do the final se_cmd put from vhost_scsi_complete_cmd_work. > When 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> Paolo, could you review this one? > --- > drivers/vhost/scsi.c | 42 +++++++++++++++--------------------------- > 1 file changed, 15 insertions(+), 27 deletions(-) > > diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c > index f6b9010..2fa48dd 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; > @@ -1096,7 +1084,7 @@ static u16 vhost_buf_to_lun(u8 *lun_buf) > &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; > } > } > -- > 1.8.3.1
On 30/10/20 09:51, Michael S. Tsirkin wrote: > On Wed, Oct 21, 2020 at 07:34:55PM -0500, Mike Christie wrote: >> We might not do the final se_cmd put from vhost_scsi_complete_cmd_work. >> When 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> > > Paolo, could you review this one? I don't know how LIO does all the callbacks, honestly (I have only ever worked on the virtio-scsi driver, not vhost-scsi, and I have only ever reviewed some virtio-scsi spec bits of vhost-scsi). The vhost_scsi_complete_cmd_work parts look fine, but I have no idea why vhost_scsi_queue_data_in and vhost_scsi_queue_status call. Paolo
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index f6b9010..2fa48dd 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; @@ -1096,7 +1084,7 @@ static u16 vhost_buf_to_lun(u8 *lun_buf) &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; } }
We might not do the final se_cmd put from vhost_scsi_complete_cmd_work. When 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(-)