From: ZiyangZhang <ZiyangZhang@linux.alibaba.com>
To: ming.lei@redhat.com
Cc: axboe@kernel.dk, xiaoguang.wang@linux.alibaba.com,
linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
joseph.qi@linux.alibaba.com,
ZiyangZhang <ZiyangZhang@linux.alibaba.com>
Subject: [RESEND PATCH V5 6/7] ublk_drv: add START_USER_RECOVERY and END_USER_RECOVERY support
Date: Fri, 23 Sep 2022 14:15:04 +0800 [thread overview]
Message-ID: <20220923061505.52007-7-ZiyangZhang@linux.alibaba.com> (raw)
In-Reply-To: <20220923061505.52007-1-ZiyangZhang@linux.alibaba.com>
START_USER_RECOVERY and END_USER_RECOVERY are two new control commands
to support user recovery feature.
After a crash, user should send START_USER_RECOVERY, it will:
(1) check if (a)current ublk_device is UBLK_S_DEV_QUIESCED which was
set by quiesce_work and (b)chardev is released
(2) reinit all ubqs, including:
(a) put the task_struct and reset ->ubq_daemon to NULL.
(b) reset all ublk_io.
(3) reset ub->mm to NULL.
Then, user should start a new process and send FETCH_REQ on each
ubq_daemon.
Finally, user should send END_USER_RECOVERY, it will:
(1) wait for all new ubq_daemons getting ready.
(2) update ublksrv_pid
(3) unquiesce the request queue and expect incoming ublk_queue_rq()
(4) convert ub's state to UBLK_S_DEV_LIVE
Note: we can handle STOP_DEV between START_USER_RECOVERY and
END_USER_RECOVERY. This is helpful to users who cannot start new process
after sending START_USER_RECOVERY ctrl-cmd.
Signed-off-by: ZiyangZhang <ZiyangZhang@linux.alibaba.com>
---
drivers/block/ublk_drv.c | 116 ++++++++++++++++++++++++++++++++++
include/uapi/linux/ublk_cmd.h | 3 +-
2 files changed, 118 insertions(+), 1 deletion(-)
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 3d7b067e0b99..f31d80f66fd6 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -1862,6 +1862,116 @@ static int ublk_ctrl_set_params(struct io_uring_cmd *cmd)
return ret;
}
+static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq)
+{
+ int i;
+
+ WARN_ON_ONCE(!(ubq->ubq_daemon && ubq_daemon_is_dying(ubq)));
+ /* All old ioucmds have to be completed */
+ WARN_ON_ONCE(ubq->nr_io_ready);
+ /* old daemon is PF_EXITING, put it now */
+ put_task_struct(ubq->ubq_daemon);
+ /* We have to reset it to NULL, otherwise ub won't accept new FETCH_REQ */
+ ubq->ubq_daemon = NULL;
+
+ for (i = 0; i < ubq->q_depth; i++) {
+ struct ublk_io *io = &ubq->ios[i];
+
+ /* forget everything now and be ready for new FETCH_REQ */
+ io->flags = 0;
+ io->cmd = NULL;
+ io->addr = 0;
+ }
+}
+
+static int ublk_ctrl_start_recovery(struct io_uring_cmd *cmd)
+{
+ struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd;
+ struct ublk_device *ub;
+ int ret = -EINVAL;
+ int i;
+
+ ub = ublk_get_device_from_id(header->dev_id);
+ if (!ub)
+ return ret;
+
+ mutex_lock(&ub->mutex);
+ if (!ublk_can_use_recovery(ub))
+ goto out_unlock;
+ /*
+ * START_RECOVERY is only allowd after:
+ *
+ * (1) UB_STATE_OPEN is not set, which means the dying process is exited
+ * and related io_uring ctx is freed so file struct of /dev/ublkcX is
+ * released.
+ *
+ * (2) UBLK_S_DEV_QUIESCED is set, which means the quiesce_work:
+ * (a)has quiesced request queue
+ * (b)has requeued every inflight rqs whose io_flags is ACTIVE
+ * (c)has requeued/aborted every inflight rqs whose io_flags is NOT ACTIVE
+ * (d)has completed/camceled all ioucmds owned by ther dying process
+ */
+ if (test_bit(UB_STATE_OPEN, &ub->state) ||
+ ub->dev_info.state != UBLK_S_DEV_QUIESCED) {
+ ret = -EBUSY;
+ goto out_unlock;
+ }
+ pr_devel("%s: start recovery for dev id %d.\n", __func__, header->dev_id);
+ for (i = 0; i < ub->dev_info.nr_hw_queues; i++)
+ ublk_queue_reinit(ub, ublk_get_queue(ub, i));
+ /* set to NULL, otherwise new ubq_daemon cannot mmap the io_cmd_buf */
+ ub->mm = NULL;
+ ub->nr_queues_ready = 0;
+ init_completion(&ub->completion);
+ ret = 0;
+ out_unlock:
+ mutex_unlock(&ub->mutex);
+ ublk_put_device(ub);
+ return ret;
+}
+
+static int ublk_ctrl_end_recovery(struct io_uring_cmd *cmd)
+{
+ struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd;
+ int ublksrv_pid = (int)header->data[0];
+ struct ublk_device *ub;
+ int ret = -EINVAL;
+
+ ub = ublk_get_device_from_id(header->dev_id);
+ if (!ub)
+ return ret;
+
+ pr_devel("%s: Waiting for new ubq_daemons(nr: %d) are ready, dev id %d...\n",
+ __func__, ub->dev_info.nr_hw_queues, header->dev_id);
+ /* wait until new ubq_daemon sending all FETCH_REQ */
+ wait_for_completion_interruptible(&ub->completion);
+ pr_devel("%s: All new ubq_daemons(nr: %d) are ready, dev id %d\n",
+ __func__, ub->dev_info.nr_hw_queues, header->dev_id);
+
+ mutex_lock(&ub->mutex);
+ if (!ublk_can_use_recovery(ub))
+ goto out_unlock;
+
+ if (ub->dev_info.state != UBLK_S_DEV_QUIESCED) {
+ ret = -EBUSY;
+ goto out_unlock;
+ }
+ ub->dev_info.ublksrv_pid = ublksrv_pid;
+ pr_devel("%s: new ublksrv_pid %d, dev id %d\n",
+ __func__, ublksrv_pid, header->dev_id);
+ blk_mq_unquiesce_queue(ub->ub_disk->queue);
+ pr_devel("%s: queue unquiesced, dev id %d.\n",
+ __func__, header->dev_id);
+ blk_mq_kick_requeue_list(ub->ub_disk->queue);
+ ub->dev_info.state = UBLK_S_DEV_LIVE;
+ schedule_delayed_work(&ub->monitor_work, UBLK_DAEMON_MONITOR_PERIOD);
+ ret = 0;
+ out_unlock:
+ mutex_unlock(&ub->mutex);
+ ublk_put_device(ub);
+ return ret;
+}
+
static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
unsigned int issue_flags)
{
@@ -1903,6 +2013,12 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
case UBLK_CMD_SET_PARAMS:
ret = ublk_ctrl_set_params(cmd);
break;
+ case UBLK_CMD_START_USER_RECOVERY:
+ ret = ublk_ctrl_start_recovery(cmd);
+ break;
+ case UBLK_CMD_END_USER_RECOVERY:
+ ret = ublk_ctrl_end_recovery(cmd);
+ break;
default:
break;
}
diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h
index 332370628757..8f88e3a29998 100644
--- a/include/uapi/linux/ublk_cmd.h
+++ b/include/uapi/linux/ublk_cmd.h
@@ -17,7 +17,8 @@
#define UBLK_CMD_STOP_DEV 0x07
#define UBLK_CMD_SET_PARAMS 0x08
#define UBLK_CMD_GET_PARAMS 0x09
-
+#define UBLK_CMD_START_USER_RECOVERY 0x10
+#define UBLK_CMD_END_USER_RECOVERY 0x11
/*
* IO commands, issued by ublk server, and handled by ublk driver.
*
--
2.27.0
next prev parent reply other threads:[~2022-09-23 6:17 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-23 6:14 [RESEND PATCH V5 0/7] ublk_drv: add USER_RECOVERY support ZiyangZhang
2022-09-23 6:14 ` [RESEND PATCH V5 1/7] ublk_drv: check 'current' instead of 'ubq_daemon' ZiyangZhang
2022-09-23 6:15 ` [RESEND PATCH V5 2/7] ublk_drv: define macros for recovery feature and check them ZiyangZhang
2022-09-23 6:15 ` [RESEND PATCH V5 3/7] ublk_drv: requeue rqs with recovery feature enabled ZiyangZhang
2022-09-23 13:47 ` Ming Lei
2022-09-23 6:15 ` [RESEND PATCH V5 4/7] ublk_drv: consider recovery feature in aborting mechanism ZiyangZhang
2022-09-23 13:48 ` Ming Lei
2022-09-23 6:15 ` [RESEND PATCH V5 5/7] ublk_drv: support UBLK_F_USER_RECOVERY_REISSUE ZiyangZhang
2022-09-23 6:15 ` ZiyangZhang [this message]
2022-09-23 6:34 ` [RESEND PATCH V5 6/7] ublk_drv: add START_USER_RECOVERY and END_USER_RECOVERY support Ziyang Zhang
2022-09-23 13:50 ` Ming Lei
2022-09-23 6:15 ` [RESEND PATCH V5 7/7] Documentation: document ublk user recovery feature ZiyangZhang
2022-09-23 13:58 ` Ming Lei
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=20220923061505.52007-7-ZiyangZhang@linux.alibaba.com \
--to=ziyangzhang@linux.alibaba.com \
--cc=axboe@kernel.dk \
--cc=joseph.qi@linux.alibaba.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=ming.lei@redhat.com \
--cc=xiaoguang.wang@linux.alibaba.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;
as well as URLs for NNTP newsgroup(s).