selftests: ublk: kublk: lift queue initialization out of thread

Currently, each ublk server I/O handler thread initializes its own
queue. However, as we move towards decoupled ublk_queues and ublk server
threads, this model does not make sense anymore, as there will no longer
be a concept of a thread having "its own" queue. So lift queue
initialization out of the per-thread ublk_io_handler_fn and into a loop
in ublk_start_daemon (which runs once for each device).

There is a part of ublk_queue_init (ring initialization) which does
actually need to happen on the thread that will use the ring; that is
separated into a separate ublk_thread_init which is still called by each
I/O handler thread.

Signed-off-by: Uday Shankar <ushankar@purestorage.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250529-ublk_task_per_io-v8-4-e9d3b119336a@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Author: ps-ushankar

tools/testing/selftests/ublk/kublk.c

@@ -412,6 +412,17 @@ static void ublk_queue_deinit(struct ublk_queue *q)
 	int i;
 	int nr_ios = q->q_depth;
 
+	if (q->io_cmd_buf)
+		munmap(q->io_cmd_buf, ublk_queue_cmd_buf_sz(q));
+
+	for (i = 0; i < nr_ios; i++)
+		free(q->ios[i].buf_addr);
+}
+
+static void ublk_thread_deinit(struct ublk_queue *q)
+{
+	q->tid = 0;
+
 	io_uring_unregister_buffers(&q->ring);
 
 	io_uring_unregister_ring_fd(&q->ring);
@@ -421,28 +432,20 @@ static void ublk_queue_deinit(struct ublk_queue *q)
 		close(q->ring.ring_fd);
 		q->ring.ring_fd = -1;
 	}
-
-	if (q->io_cmd_buf)
-		munmap(q->io_cmd_buf, ublk_queue_cmd_buf_sz(q));
-
-	for (i = 0; i < nr_ios; i++)
-		free(q->ios[i].buf_addr);
 }
 
 static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags)
 {
 	struct ublk_dev *dev = q->dev;
 	int depth = dev->dev_info.queue_depth;
-	int i, ret = -1;
+	int i;
 	int cmd_buf_size, io_buf_size;
 	unsigned long off;
-	int ring_depth = dev->tgt.sq_depth, cq_depth = dev->tgt.cq_depth;
 
 	q->tgt_ops = dev->tgt.ops;
 	q->state = 0;
 	q->q_depth = depth;
 	q->cmd_inflight = 0;
-	q->tid = gettid();
 
 	if (dev->dev_info.flags & (UBLK_F_SUPPORT_ZERO_COPY | UBLK_F_AUTO_BUF_REG)) {
 		q->state |= UBLKSRV_NO_BUF;
@@ -479,6 +482,22 @@ static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags)
 		}
 	}
 
+	return 0;
+ fail:
+	ublk_queue_deinit(q);
+	ublk_err("ublk dev %d queue %d failed\n",
+			dev->dev_info.dev_id, q->q_id);
+	return -ENOMEM;
+}
+
+static int ublk_thread_init(struct ublk_queue *q)
+{
+	struct ublk_dev *dev = q->dev;
+	int ring_depth = dev->tgt.sq_depth, cq_depth = dev->tgt.cq_depth;
+	int ret;
+
+	q->tid = gettid();
+
 	ret = ublk_setup_ring(&q->ring, ring_depth, cq_depth,
 			IORING_SETUP_COOP_TASKRUN |
 			IORING_SETUP_SINGLE_ISSUER |
@@ -508,9 +527,9 @@ static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags)
 	}
 
 	return 0;
- fail:
-	ublk_queue_deinit(q);
-	ublk_err("ublk dev %d queue %d failed\n",
+fail:
+	ublk_thread_deinit(q);
+	ublk_err("ublk dev %d queue %d thread init failed\n",
 			dev->dev_info.dev_id, q->q_id);
 	return -ENOMEM;
 }
@@ -778,23 +797,18 @@ struct ublk_queue_info {
 	struct ublk_queue 	*q;
 	sem_t 			*queue_sem;
 	cpu_set_t 		*affinity;
-	unsigned char 		auto_zc_fallback;
 };
 
 static void *ublk_io_handler_fn(void *data)
 {
 	struct ublk_queue_info *info = data;
 	struct ublk_queue *q = info->q;
 	int dev_id = q->dev->dev_info.dev_id;
-	unsigned extra_flags = 0;
 	int ret;
 
-	if (info->auto_zc_fallback)
-		extra_flags = UBLKSRV_AUTO_BUF_REG_FALLBACK;
-
-	ret = ublk_queue_init(q, extra_flags);
+	ret = ublk_thread_init(q);
 	if (ret) {
-		ublk_err("ublk dev %d queue %d init queue failed\n",
+		ublk_err("ublk dev %d queue %d thread init failed\n",
 				dev_id, q->q_id);
 		return NULL;
 	}
@@ -813,7 +827,7 @@ static void *ublk_io_handler_fn(void *data)
 	} while (1);
 
 	ublk_dbg(UBLK_DBG_QUEUE, "ublk dev %d queue %d exited\n", dev_id, q->q_id);
-	ublk_queue_deinit(q);
+	ublk_thread_deinit(q);
 	return NULL;
 }
 
@@ -857,6 +871,7 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev)
 {
 	const struct ublksrv_ctrl_dev_info *dinfo = &dev->dev_info;
 	struct ublk_queue_info *qinfo;
+	unsigned extra_flags = 0;
 	cpu_set_t *affinity_buf;
 	void *thread_ret;
 	sem_t queue_sem;
@@ -878,14 +893,23 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev)
 	if (ret)
 		return ret;
 
+	if (ctx->auto_zc_fallback)
+		extra_flags = UBLKSRV_AUTO_BUF_REG_FALLBACK;
+
 	for (i = 0; i < dinfo->nr_hw_queues; i++) {
 		dev->q[i].dev = dev;
 		dev->q[i].q_id = i;
 
+		ret = ublk_queue_init(&dev->q[i], extra_flags);
+		if (ret) {
+			ublk_err("ublk dev %d queue %d init queue failed\n",
+				 dinfo->dev_id, i);
+			goto fail;
+		}
+
 		qinfo[i].q = &dev->q[i];
 		qinfo[i].queue_sem = &queue_sem;
 		qinfo[i].affinity = &affinity_buf[i];
-		qinfo[i].auto_zc_fallback = ctx->auto_zc_fallback;
 		pthread_create(&dev->q[i].thread, NULL,
 				ublk_io_handler_fn,
 				&qinfo[i]);
@@ -918,6 +942,8 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev)
 	for (i = 0; i < dinfo->nr_hw_queues; i++)
 		pthread_join(dev->q[i].thread, &thread_ret);
  fail:
+	for (i = 0; i < dinfo->nr_hw_queues; i++)
+		ublk_queue_deinit(&dev->q[i]);
 	ublk_dev_unprep(dev);
 	ublk_dbg(UBLK_DBG_DEV, "%s exit\n", __func__);