Merge tag 'block-6.16-20250606' of git://git.kernel.dk/linux

Pull more block updates from Jens Axboe:

 - NVMe pull request via Christoph:
      - TCP error handling fix (Shin'ichiro Kawasaki)
      - TCP I/O stall handling fixes (Hannes Reinecke)
      - fix command limits status code (Keith Busch)
      - support vectored buffers also for passthrough (Pavel Begunkov)
      - spelling fixes (Yi Zhang)

 - MD pull request via Yu:
      - fix REQ_RAHEAD and REQ_NOWAIT IO err handling for raid1/10
      - fix max_write_behind setting for dm-raid
      - some minor cleanups

 - Integrity data direction fix and cleanup

 - bcache NULL pointer fix

 - Fix for loop missing write start/end handling

 - Decouple hardware queues and IO threads in ublk

 - Slew of ublk selftests additions and updates

* tag 'block-6.16-20250606' of git://git.kernel.dk/linux: (29 commits)
  nvme: spelling fixes
  nvme-tcp: fix I/O stalls on congested sockets
  nvme-tcp: sanitize request list handling
  nvme-tcp: remove tag set when second admin queue config fails
  nvme: enable vectored registered bufs for passthrough cmds
  nvme: fix implicit bool to flags conversion
  nvme: fix command limits status code
  selftests: ublk: kublk: improve behavior on init failure
  block: flip iter directions in blk_rq_integrity_map_user()
  block: drop direction param from bio_integrity_copy_user()
  selftests: ublk: cover PER_IO_DAEMON in more stress tests
  Documentation: ublk: document UBLK_F_PER_IO_DAEMON
  selftests: ublk: add stress test for per io daemons
  selftests: ublk: add functional test for per io daemons
  selftests: ublk: kublk: decouple ublk_queues from ublk server threads
  selftests: ublk: kublk: move per-thread data out of ublk_queue
  selftests: ublk: kublk: lift queue initialization out of thread
  selftests: ublk: kublk: tie sqe allocation to io instead of queue
  selftests: ublk: kublk: plumb q_id in io_uring user_data
  ublk: have a per-io daemon instead of a per-queue daemon
  ...

13 files changed, 429 insertions, 175 deletions

diff --git a/tools/testing/selftests/ublk/Makefile b/tools/testing/selftests/ublk/Makefile
index 4dde8838261d..5d7f4ecfb816 100644
--- a/tools/testing/selftests/ublk/Makefile
+++ b/tools/testing/selftests/ublk/Makefile
@@ -19,6 +19,7 @@ TEST_PROGS += test_generic_08.sh
 TEST_PROGS += test_generic_09.sh
 TEST_PROGS += test_generic_10.sh
 TEST_PROGS += test_generic_11.sh
+TEST_PROGS += test_generic_12.sh
 
 TEST_PROGS += test_null_01.sh
 TEST_PROGS += test_null_02.sh
diff --git a/tools/testing/selftests/ublk/fault_inject.c b/tools/testing/selftests/ublk/fault_inject.c
index 5421774d7867..6e60f7d97125 100644
--- a/tools/testing/selftests/ublk/fault_inject.c
+++ b/tools/testing/selftests/ublk/fault_inject.c
@@ -46,9 +46,9 @@ static int ublk_fault_inject_queue_io(struct ublk_queue *q, int tag)
 		.tv_nsec = (long long)q->dev->private_data,
 	};
 
-	ublk_queue_alloc_sqes(q, &sqe, 1);
+	ublk_io_alloc_sqes(ublk_get_io(q, tag), &sqe, 1);
 	io_uring_prep_timeout(sqe, &ts, 1, 0);
-	sqe->user_data = build_user_data(tag, ublksrv_get_op(iod), 0, 1);
+	sqe->user_data = build_user_data(tag, ublksrv_get_op(iod), 0, q->q_id, 1);
 
 	ublk_queued_tgt_io(q, tag, 1);
 
diff --git a/tools/testing/selftests/ublk/file_backed.c b/tools/testing/selftests/ublk/file_backed.c
index 509842df9bee..cfa59b631693 100644
--- a/tools/testing/selftests/ublk/file_backed.c
+++ b/tools/testing/selftests/ublk/file_backed.c
@@ -18,11 +18,11 @@ static int loop_queue_flush_io(struct ublk_queue *q, const struct ublksrv_io_des
 	unsigned ublk_op = ublksrv_get_op(iod);
 	struct io_uring_sqe *sqe[1];
 
-	ublk_queue_alloc_sqes(q, sqe, 1);
+	ublk_io_alloc_sqes(ublk_get_io(q, tag), sqe, 1);
 	io_uring_prep_fsync(sqe[0], 1 /*fds[1]*/, IORING_FSYNC_DATASYNC);
 	io_uring_sqe_set_flags(sqe[0], IOSQE_FIXED_FILE);
 	/* bit63 marks us as tgt io */
-	sqe[0]->user_data = build_user_data(tag, ublk_op, 0, 1);
+	sqe[0]->user_data = build_user_data(tag, ublk_op, 0, q->q_id, 1);
 	return 1;
 }
 
@@ -36,7 +36,7 @@ static int loop_queue_tgt_rw_io(struct ublk_queue *q, const struct ublksrv_io_de
 	void *addr = (zc | auto_zc) ? NULL : (void *)iod->addr;
 
 	if (!zc || auto_zc) {
-		ublk_queue_alloc_sqes(q, sqe, 1);
+		ublk_io_alloc_sqes(ublk_get_io(q, tag), sqe, 1);
 		if (!sqe[0])
 			return -ENOMEM;
 
@@ -48,26 +48,26 @@ static int loop_queue_tgt_rw_io(struct ublk_queue *q, const struct ublksrv_io_de
 			sqe[0]->buf_index = tag;
 		io_uring_sqe_set_flags(sqe[0], IOSQE_FIXED_FILE);
 		/* bit63 marks us as tgt io */
-		sqe[0]->user_data = build_user_data(tag, ublk_op, 0, 1);
+		sqe[0]->user_data = build_user_data(tag, ublk_op, 0, q->q_id, 1);
 		return 1;
 	}
 
-	ublk_queue_alloc_sqes(q, sqe, 3);
+	ublk_io_alloc_sqes(ublk_get_io(q, tag), sqe, 3);
 
-	io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, tag);
+	io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
 	sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK;
 	sqe[0]->user_data = build_user_data(tag,
-			ublk_cmd_op_nr(sqe[0]->cmd_op), 0, 1);
+			ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1);
 
 	io_uring_prep_rw(op, sqe[1], 1 /*fds[1]*/, 0,
 		iod->nr_sectors << 9,
 		iod->start_sector << 9);
 	sqe[1]->buf_index = tag;
 	sqe[1]->flags |= IOSQE_FIXED_FILE | IOSQE_IO_HARDLINK;
-	sqe[1]->user_data = build_user_data(tag, ublk_op, 0, 1);
+	sqe[1]->user_data = build_user_data(tag, ublk_op, 0, q->q_id, 1);
 
-	io_uring_prep_buf_unregister(sqe[2], 0, tag, q->q_id, tag);
-	sqe[2]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[2]->cmd_op), 0, 1);
+	io_uring_prep_buf_unregister(sqe[2], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
+	sqe[2]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[2]->cmd_op), 0, q->q_id, 1);
 
 	return 2;
 }
diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c
index b5131a000795..e2d2042810d4 100644
--- a/tools/testing/selftests/ublk/kublk.c
+++ b/tools/testing/selftests/ublk/kublk.c
@@ -348,8 +348,8 @@ static void ublk_ctrl_dump(struct ublk_dev *dev)
 
 		for (i = 0; i < info->nr_hw_queues; i++) {
 			ublk_print_cpu_set(&affinity[i], buf, sizeof(buf));
-			printf("\tqueue %u: tid %d affinity(%s)\n",
-					i, dev->q[i].tid, buf);
+			printf("\tqueue %u: affinity(%s)\n",
+					i, buf);
 		}
 		free(affinity);
 	}
@@ -412,16 +412,6 @@ static void ublk_queue_deinit(struct ublk_queue *q)
 	int i;
 	int nr_ios = q->q_depth;
 
-	io_uring_unregister_buffers(&q->ring);
-
-	io_uring_unregister_ring_fd(&q->ring);
-
-	if (q->ring.ring_fd > 0) {
-		io_uring_unregister_files(&q->ring);
-		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));
 
@@ -429,20 +419,30 @@ static void ublk_queue_deinit(struct ublk_queue *q)
 		free(q->ios[i].buf_addr);
 }
 
+static void ublk_thread_deinit(struct ublk_thread *t)
+{
+	io_uring_unregister_buffers(&t->ring);
+
+	io_uring_unregister_ring_fd(&t->ring);
+
+	if (t->ring.ring_fd > 0) {
+		io_uring_unregister_files(&t->ring);
+		close(t->ring.ring_fd);
+		t->ring.ring_fd = -1;
+	}
+}
+
 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;
@@ -467,6 +467,7 @@ static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags)
 	for (i = 0; i < q->q_depth; i++) {
 		q->ios[i].buf_addr = NULL;
 		q->ios[i].flags = UBLKSRV_NEED_FETCH_RQ | UBLKSRV_IO_FREE;
+		q->ios[i].tag = i;
 
 		if (q->state & UBLKSRV_NO_BUF)
 			continue;
@@ -479,39 +480,57 @@ static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags)
 		}
 	}
 
-	ret = ublk_setup_ring(&q->ring, ring_depth, cq_depth,
+	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_thread *t)
+{
+	struct ublk_dev *dev = t->dev;
+	int ring_depth = dev->tgt.sq_depth, cq_depth = dev->tgt.cq_depth;
+	int ret;
+
+	ret = ublk_setup_ring(&t->ring, ring_depth, cq_depth,
 			IORING_SETUP_COOP_TASKRUN |
 			IORING_SETUP_SINGLE_ISSUER |
 			IORING_SETUP_DEFER_TASKRUN);
 	if (ret < 0) {
-		ublk_err("ublk dev %d queue %d setup io_uring failed %d\n",
-				q->dev->dev_info.dev_id, q->q_id, ret);
+		ublk_err("ublk dev %d thread %d setup io_uring failed %d\n",
+				dev->dev_info.dev_id, t->idx, ret);
 		goto fail;
 	}
 
 	if (dev->dev_info.flags & (UBLK_F_SUPPORT_ZERO_COPY | UBLK_F_AUTO_BUF_REG)) {
-		ret = io_uring_register_buffers_sparse(&q->ring, q->q_depth);
+		unsigned nr_ios = dev->dev_info.queue_depth * dev->dev_info.nr_hw_queues;
+		unsigned max_nr_ios_per_thread = nr_ios / dev->nthreads;
+		max_nr_ios_per_thread += !!(nr_ios % dev->nthreads);
+		ret = io_uring_register_buffers_sparse(
+			&t->ring, max_nr_ios_per_thread);
 		if (ret) {
-			ublk_err("ublk dev %d queue %d register spare buffers failed %d",
-					dev->dev_info.dev_id, q->q_id, ret);
+			ublk_err("ublk dev %d thread %d register spare buffers failed %d",
+					dev->dev_info.dev_id, t->idx, ret);
 			goto fail;
 		}
 	}
 
-	io_uring_register_ring_fd(&q->ring);
+	io_uring_register_ring_fd(&t->ring);
 
-	ret = io_uring_register_files(&q->ring, dev->fds, dev->nr_fds);
+	ret = io_uring_register_files(&t->ring, dev->fds, dev->nr_fds);
 	if (ret) {
-		ublk_err("ublk dev %d queue %d register files failed %d\n",
-				q->dev->dev_info.dev_id, q->q_id, ret);
+		ublk_err("ublk dev %d thread %d register files failed %d\n",
+				t->dev->dev_info.dev_id, t->idx, ret);
 		goto fail;
 	}
 
 	return 0;
- fail:
-	ublk_queue_deinit(q);
-	ublk_err("ublk dev %d queue %d failed\n",
-			dev->dev_info.dev_id, q->q_id);
+fail:
+	ublk_thread_deinit(t);
+	ublk_err("ublk dev %d thread %d init failed\n",
+			dev->dev_info.dev_id, t->idx);
 	return -ENOMEM;
 }
 
@@ -562,7 +581,7 @@ static void ublk_set_auto_buf_reg(const struct ublk_queue *q,
 	if (q->tgt_ops->buf_index)
 		buf.index = q->tgt_ops->buf_index(q, tag);
 	else
-		buf.index = tag;
+		buf.index = q->ios[tag].buf_index;
 
 	if (q->state & UBLKSRV_AUTO_BUF_REG_FALLBACK)
 		buf.flags = UBLK_AUTO_BUF_REG_FALLBACK;
@@ -570,8 +589,10 @@ static void ublk_set_auto_buf_reg(const struct ublk_queue *q,
 	sqe->addr = ublk_auto_buf_reg_to_sqe_addr(&buf);
 }
 
-int ublk_queue_io_cmd(struct ublk_queue *q, struct ublk_io *io, unsigned tag)
+int ublk_queue_io_cmd(struct ublk_io *io)
 {
+	struct ublk_thread *t = io->t;
+	struct ublk_queue *q = ublk_io_to_queue(io);
 	struct ublksrv_io_cmd *cmd;
 	struct io_uring_sqe *sqe[1];
 	unsigned int cmd_op = 0;
@@ -596,13 +617,13 @@ int ublk_queue_io_cmd(struct ublk_queue *q, struct ublk_io *io, unsigned tag)
 	else if (io->flags & UBLKSRV_NEED_FETCH_RQ)
 		cmd_op = UBLK_U_IO_FETCH_REQ;
 
-	if (io_uring_sq_space_left(&q->ring) < 1)
-		io_uring_submit(&q->ring);
+	if (io_uring_sq_space_left(&t->ring) < 1)
+		io_uring_submit(&t->ring);
 
-	ublk_queue_alloc_sqes(q, sqe, 1);
+	ublk_io_alloc_sqes(io, sqe, 1);
 	if (!sqe[0]) {
-		ublk_err("%s: run out of sqe %d, tag %d\n",
-				__func__, q->q_id, tag);
+		ublk_err("%s: run out of sqe. thread %u, tag %d\n",
+				__func__, t->idx, io->tag);
 		return -1;
 	}
 
@@ -617,7 +638,7 @@ int ublk_queue_io_cmd(struct ublk_queue *q, struct ublk_io *io, unsigned tag)
 	sqe[0]->opcode	= IORING_OP_URING_CMD;
 	sqe[0]->flags	= IOSQE_FIXED_FILE;
 	sqe[0]->rw_flags	= 0;
-	cmd->tag	= tag;
+	cmd->tag	= io->tag;
 	cmd->q_id	= q->q_id;
 	if (!(q->state & UBLKSRV_NO_BUF))
 		cmd->addr	= (__u64) (uintptr_t) io->buf_addr;
@@ -625,37 +646,72 @@ int ublk_queue_io_cmd(struct ublk_queue *q, struct ublk_io *io, unsigned tag)
 		cmd->addr	= 0;
 
 	if (q->state & UBLKSRV_AUTO_BUF_REG)
-		ublk_set_auto_buf_reg(q, sqe[0], tag);
+		ublk_set_auto_buf_reg(q, sqe[0], io->tag);
 
-	user_data = build_user_data(tag, _IOC_NR(cmd_op), 0, 0);
+	user_data = build_user_data(io->tag, _IOC_NR(cmd_op), 0, q->q_id, 0);
 	io_uring_sqe_set_data64(sqe[0], user_data);
 
 	io->flags = 0;
 
-	q->cmd_inflight += 1;
+	t->cmd_inflight += 1;
 
-	ublk_dbg(UBLK_DBG_IO_CMD, "%s: (qid %d tag %u cmd_op %u) iof %x stopping %d\n",
-			__func__, q->q_id, tag, cmd_op,
-			io->flags, !!(q->state & UBLKSRV_QUEUE_STOPPING));
+	ublk_dbg(UBLK_DBG_IO_CMD, "%s: (thread %u qid %d tag %u cmd_op %u) iof %x stopping %d\n",
+			__func__, t->idx, q->q_id, io->tag, cmd_op,
+			io->flags, !!(t->state & UBLKSRV_THREAD_STOPPING));
 	return 1;
 }
 
-static void ublk_submit_fetch_commands(struct ublk_queue *q)
+static void ublk_submit_fetch_commands(struct ublk_thread *t)
 {
-	int i = 0;
+	struct ublk_queue *q;
+	struct ublk_io *io;
+	int i = 0, j = 0;
 
-	for (i = 0; i < q->q_depth; i++)
-		ublk_queue_io_cmd(q, &q->ios[i], i);
+	if (t->dev->per_io_tasks) {
+		/*
+		 * Lexicographically order all the (qid,tag) pairs, with
+		 * qid taking priority (so (1,0) > (0,1)). Then make
+		 * this thread the daemon for every Nth entry in this
+		 * list (N is the number of threads), starting at this
+		 * thread's index. This ensures that each queue is
+		 * handled by as many ublk server threads as possible,
+		 * so that load that is concentrated on one or a few
+		 * queues can make use of all ublk server threads.
+		 */
+		const struct ublksrv_ctrl_dev_info *dinfo = &t->dev->dev_info;
+		int nr_ios = dinfo->nr_hw_queues * dinfo->queue_depth;
+		for (i = t->idx; i < nr_ios; i += t->dev->nthreads) {
+			int q_id = i / dinfo->queue_depth;
+			int tag = i % dinfo->queue_depth;
+			q = &t->dev->q[q_id];
+			io = &q->ios[tag];
+			io->t = t;
+			io->buf_index = j++;
+			ublk_queue_io_cmd(io);
+		}
+	} else {
+		/*
+		 * Service exclusively the queue whose q_id matches our
+		 * thread index.
+		 */
+		struct ublk_queue *q = &t->dev->q[t->idx];
+		for (i = 0; i < q->q_depth; i++) {
+			io = &q->ios[i];
+			io->t = t;
+			io->buf_index = i;
+			ublk_queue_io_cmd(io);
+		}
+	}
 }
 
-static int ublk_queue_is_idle(struct ublk_queue *q)
+static int ublk_thread_is_idle(struct ublk_thread *t)
 {
-	return !io_uring_sq_ready(&q->ring) && !q->io_inflight;
+	return !io_uring_sq_ready(&t->ring) && !t->io_inflight;
 }
 
-static int ublk_queue_is_done(struct ublk_queue *q)
+static int ublk_thread_is_done(struct ublk_thread *t)
 {
-	return (q->state & UBLKSRV_QUEUE_STOPPING) && ublk_queue_is_idle(q);
+	return (t->state & UBLKSRV_THREAD_STOPPING) && ublk_thread_is_idle(t);
 }
 
 static inline void ublksrv_handle_tgt_cqe(struct ublk_queue *q,
@@ -673,14 +729,16 @@ static inline void ublksrv_handle_tgt_cqe(struct ublk_queue *q,
 		q->tgt_ops->tgt_io_done(q, tag, cqe);
 }
 
-static void ublk_handle_cqe(struct io_uring *r,
+static void ublk_handle_cqe(struct ublk_thread *t,
 		struct io_uring_cqe *cqe, void *data)
 {
-	struct ublk_queue *q = container_of(r, struct ublk_queue, ring);
+	struct ublk_dev *dev = t->dev;
+	unsigned q_id = user_data_to_q_id(cqe->user_data);
+	struct ublk_queue *q = &dev->q[q_id];
 	unsigned tag = user_data_to_tag(cqe->user_data);
 	unsigned cmd_op = user_data_to_op(cqe->user_data);
 	int fetch = (cqe->res != UBLK_IO_RES_ABORT) &&
-		!(q->state & UBLKSRV_QUEUE_STOPPING);
+		!(t->state & UBLKSRV_THREAD_STOPPING);
 	struct ublk_io *io;
 
 	if (cqe->res < 0 && cqe->res != -ENODEV)
@@ -691,7 +749,7 @@ static void ublk_handle_cqe(struct io_uring *r,
 			__func__, cqe->res, q->q_id, tag, cmd_op,
 			is_target_io(cqe->user_data),
 			user_data_to_tgt_data(cqe->user_data),
-			(q->state & UBLKSRV_QUEUE_STOPPING));
+			(t->state & UBLKSRV_THREAD_STOPPING));
 
 	/* Don't retrieve io in case of target io */
 	if (is_target_io(cqe->user_data)) {
@@ -700,10 +758,10 @@ static void ublk_handle_cqe(struct io_uring *r,
 	}
 
 	io = &q->ios[tag];
-	q->cmd_inflight--;
+	t->cmd_inflight--;
 
 	if (!fetch) {
-		q->state |= UBLKSRV_QUEUE_STOPPING;
+		t->state |= UBLKSRV_THREAD_STOPPING;
 		io->flags &= ~UBLKSRV_NEED_FETCH_RQ;
 	}
 
@@ -713,7 +771,7 @@ static void ublk_handle_cqe(struct io_uring *r,
 			q->tgt_ops->queue_io(q, tag);
 	} else if (cqe->res == UBLK_IO_RES_NEED_GET_DATA) {
 		io->flags |= UBLKSRV_NEED_GET_DATA | UBLKSRV_IO_FREE;
-		ublk_queue_io_cmd(q, io, tag);
+		ublk_queue_io_cmd(io);
 	} else {
 		/*
 		 * COMMIT_REQ will be completed immediately since no fetching
@@ -727,92 +785,93 @@ static void ublk_handle_cqe(struct io_uring *r,
 	}
 }
 
-static int ublk_reap_events_uring(struct io_uring *r)
+static int ublk_reap_events_uring(struct ublk_thread *t)
 {
 	struct io_uring_cqe *cqe;
 	unsigned head;
 	int count = 0;
 
-	io_uring_for_each_cqe(r, head, cqe) {
-		ublk_handle_cqe(r, cqe, NULL);
+	io_uring_for_each_cqe(&t->ring, head, cqe) {
+		ublk_handle_cqe(t, cqe, NULL);
 		count += 1;
 	}
-	io_uring_cq_advance(r, count);
+	io_uring_cq_advance(&t->ring, count);
 
 	return count;
 }
 
-static int ublk_process_io(struct ublk_queue *q)
+static int ublk_process_io(struct ublk_thread *t)
 {
 	int ret, reapped;
 
-	ublk_dbg(UBLK_DBG_QUEUE, "dev%d-q%d: to_submit %d inflight cmd %u stopping %d\n",
-				q->dev->dev_info.dev_id,
-				q->q_id, io_uring_sq_ready(&q->ring),
-				q->cmd_inflight,
-				(q->state & UBLKSRV_QUEUE_STOPPING));
+	ublk_dbg(UBLK_DBG_THREAD, "dev%d-t%u: to_submit %d inflight cmd %u stopping %d\n",
+				t->dev->dev_info.dev_id,
+				t->idx, io_uring_sq_ready(&t->ring),
+				t->cmd_inflight,
+				(t->state & UBLKSRV_THREAD_STOPPING));
 
-	if (ublk_queue_is_done(q))
+	if (ublk_thread_is_done(t))
 		return -ENODEV;
 
-	ret = io_uring_submit_and_wait(&q->ring, 1);
-	reapped = ublk_reap_events_uring(&q->ring);
+	ret = io_uring_submit_and_wait(&t->ring, 1);
+	reapped = ublk_reap_events_uring(t);
 
-	ublk_dbg(UBLK_DBG_QUEUE, "submit result %d, reapped %d stop %d idle %d\n",
-			ret, reapped, (q->state & UBLKSRV_QUEUE_STOPPING),
-			(q->state & UBLKSRV_QUEUE_IDLE));
+	ublk_dbg(UBLK_DBG_THREAD, "submit result %d, reapped %d stop %d idle %d\n",
+			ret, reapped, (t->state & UBLKSRV_THREAD_STOPPING),
+			(t->state & UBLKSRV_THREAD_IDLE));
 
 	return reapped;
 }
 
-static void ublk_queue_set_sched_affinity(const struct ublk_queue *q,
+static void ublk_thread_set_sched_affinity(const struct ublk_thread *t,
 		cpu_set_t *cpuset)
 {
         if (sched_setaffinity(0, sizeof(*cpuset), cpuset) < 0)
-                ublk_err("ublk dev %u queue %u set affinity failed",
-                                q->dev->dev_info.dev_id, q->q_id);
+		ublk_err("ublk dev %u thread %u set affinity failed",
+				t->dev->dev_info.dev_id, t->idx);
 }
 
-struct ublk_queue_info {
-	struct ublk_queue 	*q;
-	sem_t 			*queue_sem;
+struct ublk_thread_info {
+	struct ublk_dev 	*dev;
+	unsigned		idx;
+	sem_t 			*ready;
 	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;
+	struct ublk_thread_info *info = data;
+	struct ublk_thread *t = &info->dev->threads[info->idx];
+	int dev_id = info->dev->dev_info.dev_id;
 	int ret;
 
-	if (info->auto_zc_fallback)
-		extra_flags = UBLKSRV_AUTO_BUF_REG_FALLBACK;
+	t->dev = info->dev;
+	t->idx = info->idx;
 
-	ret = ublk_queue_init(q, extra_flags);
+	ret = ublk_thread_init(t);
 	if (ret) {
-		ublk_err("ublk dev %d queue %d init queue failed\n",
-				dev_id, q->q_id);
+		ublk_err("ublk dev %d thread %u init failed\n",
+				dev_id, t->idx);
 		return NULL;
 	}
 	/* IO perf is sensitive with queue pthread affinity on NUMA machine*/
-	ublk_queue_set_sched_affinity(q, info->affinity);
-	sem_post(info->queue_sem);
+	if (info->affinity)
+		ublk_thread_set_sched_affinity(t, info->affinity);
+	sem_post(info->ready);
 
-	ublk_dbg(UBLK_DBG_QUEUE, "tid %d: ublk dev %d queue %d started\n",
-			q->tid, dev_id, q->q_id);
+	ublk_dbg(UBLK_DBG_THREAD, "tid %d: ublk dev %d thread %u started\n",
+			gettid(), dev_id, t->idx);
 
 	/* submit all io commands to ublk driver */
-	ublk_submit_fetch_commands(q);
+	ublk_submit_fetch_commands(t);
 	do {
-		if (ublk_process_io(q) < 0)
+		if (ublk_process_io(t) < 0)
 			break;
 	} while (1);
 
-	ublk_dbg(UBLK_DBG_QUEUE, "ublk dev %d queue %d exited\n", dev_id, q->q_id);
-	ublk_queue_deinit(q);
+	ublk_dbg(UBLK_DBG_THREAD, "tid %d: ublk dev %d thread %d exiting\n",
+		 gettid(), dev_id, t->idx);
+	ublk_thread_deinit(t);
 	return NULL;
 }
 
@@ -855,20 +914,20 @@ static int ublk_send_dev_event(const struct dev_ctx *ctx, struct ublk_dev *dev,
 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;
+	struct ublk_thread_info *tinfo;
+	unsigned extra_flags = 0;
 	cpu_set_t *affinity_buf;
 	void *thread_ret;
-	sem_t queue_sem;
+	sem_t ready;
 	int ret, i;
 
 	ublk_dbg(UBLK_DBG_DEV, "%s enter\n", __func__);
 
-	qinfo = (struct ublk_queue_info *)calloc(sizeof(struct ublk_queue_info),
-			dinfo->nr_hw_queues);
-	if (!qinfo)
+	tinfo = calloc(sizeof(struct ublk_thread_info), dev->nthreads);
+	if (!tinfo)
 		return -ENOMEM;
 
-	sem_init(&queue_sem, 0, 0);
+	sem_init(&ready, 0, 0);
 	ret = ublk_dev_prep(ctx, dev);
 	if (ret)
 		return ret;
@@ -877,22 +936,44 @@ 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;
 
-		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,
+		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;
+		}
+	}
+
+	for (i = 0; i < dev->nthreads; i++) {
+		tinfo[i].dev = dev;
+		tinfo[i].idx = i;
+		tinfo[i].ready = &ready;
+
+		/*
+		 * If threads are not tied 1:1 to queues, setting thread
+		 * affinity based on queue affinity makes little sense.
+		 * However, thread CPU affinity has significant impact
+		 * on performance, so to compare fairly, we'll still set
+		 * thread CPU affinity based on queue affinity where
+		 * possible.
+		 */
+		if (dev->nthreads == dinfo->nr_hw_queues)
+			tinfo[i].affinity = &affinity_buf[i];
+		pthread_create(&dev->threads[i].thread, NULL,
 				ublk_io_handler_fn,
-				&qinfo[i]);
+				&tinfo[i]);
 	}
 
-	for (i = 0; i < dinfo->nr_hw_queues; i++)
-		sem_wait(&queue_sem);
-	free(qinfo);
+	for (i = 0; i < dev->nthreads; i++)
+		sem_wait(&ready);
+	free(tinfo);
 	free(affinity_buf);
 
 	/* everything is fine now, start us */
@@ -914,9 +995,11 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev)
 		ublk_send_dev_event(ctx, dev, dev->dev_info.dev_id);
 
 	/* wait until we are terminated */
-	for (i = 0; i < dinfo->nr_hw_queues; i++)
-		pthread_join(dev->q[i].thread, &thread_ret);
+	for (i = 0; i < dev->nthreads; i++)
+		pthread_join(dev->threads[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__);
 
@@ -1022,13 +1105,14 @@ wait:
 
 static int __cmd_dev_add(const struct dev_ctx *ctx)
 {
+	unsigned nthreads = ctx->nthreads;
 	unsigned nr_queues = ctx->nr_hw_queues;
 	const char *tgt_type = ctx->tgt_type;
 	unsigned depth = ctx->queue_depth;
 	__u64 features;
 	const struct ublk_tgt_ops *ops;
 	struct ublksrv_ctrl_dev_info *info;
-	struct ublk_dev *dev;
+	struct ublk_dev *dev = NULL;
 	int dev_id = ctx->dev_id;
 	int ret, i;
 
@@ -1036,29 +1120,55 @@ static int __cmd_dev_add(const struct dev_ctx *ctx)
 	if (!ops) {
 		ublk_err("%s: no such tgt type, type %s\n",
 				__func__, tgt_type);
-		return -ENODEV;
+		ret = -ENODEV;
+		goto fail;
 	}
 
 	if (nr_queues > UBLK_MAX_QUEUES || depth > UBLK_QUEUE_DEPTH) {
 		ublk_err("%s: invalid nr_queues or depth queues %u depth %u\n",
 				__func__, nr_queues, depth);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	/* default to 1:1 threads:queues if nthreads is unspecified */
+	if (!nthreads)
+		nthreads = nr_queues;
+
+	if (nthreads > UBLK_MAX_THREADS) {
+		ublk_err("%s: %u is too many threads (max %u)\n",
+				__func__, nthreads, UBLK_MAX_THREADS);
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	if (nthreads != nr_queues && !ctx->per_io_tasks) {
+		ublk_err("%s: threads %u must be same as queues %u if "
+			"not using per_io_tasks\n",
+			__func__, nthreads, nr_queues);
+		ret = -EINVAL;
+		goto fail;
 	}
 
 	dev = ublk_ctrl_init();
 	if (!dev) {
 		ublk_err("%s: can't alloc dev id %d, type %s\n",
 				__func__, dev_id, tgt_type);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto fail;
 	}
 
 	/* kernel doesn't support get_features */
 	ret = ublk_ctrl_get_features(dev, &features);
-	if (ret < 0)
-		return -EINVAL;
+	if (ret < 0) {
+		ret = -EINVAL;
+		goto fail;
+	}
 
-	if (!(features & UBLK_F_CMD_IOCTL_ENCODE))
-		return -ENOTSUP;
+	if (!(features & UBLK_F_CMD_IOCTL_ENCODE)) {
+		ret = -ENOTSUP;
+		goto fail;
+	}
 
 	info = &dev->dev_info;
 	info->dev_id = ctx->dev_id;
@@ -1068,6 +1178,8 @@ static int __cmd_dev_add(const struct dev_ctx *ctx)
 	if ((features & UBLK_F_QUIESCE) &&
 			(info->flags & UBLK_F_USER_RECOVERY))
 		info->flags |= UBLK_F_QUIESCE;
+	dev->nthreads = nthreads;
+	dev->per_io_tasks = ctx->per_io_tasks;
 	dev->tgt.ops = ops;
 	dev->tgt.sq_depth = depth;
 	dev->tgt.cq_depth = depth;
@@ -1097,7 +1209,8 @@ static int __cmd_dev_add(const struct dev_ctx *ctx)
 fail:
 	if (ret < 0)
 		ublk_send_dev_event(ctx, dev, -1);
-	ublk_ctrl_deinit(dev);
+	if (dev)
+		ublk_ctrl_deinit(dev);
 	return ret;
 }
 
@@ -1159,6 +1272,8 @@ run:
 		shmctl(ctx->_shmid, IPC_RMID, NULL);
 		/* wait for child and detach from it */
 		wait(NULL);
+		if (exit_code == EXIT_FAILURE)
+			ublk_err("%s: command failed\n", __func__);
 		exit(exit_code);
 	} else {
 		exit(EXIT_FAILURE);
@@ -1266,6 +1381,7 @@ static int cmd_dev_get_features(void)
 		[const_ilog2(UBLK_F_UPDATE_SIZE)] = "UPDATE_SIZE",
 		[const_ilog2(UBLK_F_AUTO_BUF_REG)] = "AUTO_BUF_REG",
 		[const_ilog2(UBLK_F_QUIESCE)] = "QUIESCE",
+		[const_ilog2(UBLK_F_PER_IO_DAEMON)] = "PER_IO_DAEMON",
 	};
 	struct ublk_dev *dev;
 	__u64 features = 0;
@@ -1360,8 +1476,10 @@ static void __cmd_create_help(char *exe, bool recovery)
 			exe, recovery ? "recover" : "add");
 	printf("\t[--foreground] [--quiet] [-z] [--auto_zc] [--auto_zc_fallback] [--debug_mask mask] [-r 0|1 ] [-g]\n");
 	printf("\t[-e 0|1 ] [-i 0|1]\n");
+	printf("\t[--nthreads threads] [--per_io_tasks]\n");
 	printf("\t[target options] [backfile1] [backfile2] ...\n");
 	printf("\tdefault: nr_queues=2(max 32), depth=128(max 1024), dev_id=-1(auto allocation)\n");
+	printf("\tdefault: nthreads=nr_queues");
 
 	for (i = 0; i < sizeof(tgt_ops_list) / sizeof(tgt_ops_list[0]); i++) {
 		const struct ublk_tgt_ops *ops = tgt_ops_list[i];
@@ -1418,6 +1536,8 @@ int main(int argc, char *argv[])
 		{ "auto_zc",		0,	NULL,  0 },
 		{ "auto_zc_fallback", 	0,	NULL,  0 },
 		{ "size",		1,	NULL, 's'},
+		{ "nthreads",		1,	NULL,  0 },
+		{ "per_io_tasks",	0,	NULL,  0 },
 		{ 0, 0, 0, 0 }
 	};
 	const struct ublk_tgt_ops *ops = NULL;
@@ -1493,6 +1613,10 @@ int main(int argc, char *argv[])
 				ctx.flags |= UBLK_F_AUTO_BUF_REG;
 			if (!strcmp(longopts[option_idx].name, "auto_zc_fallback"))
 				ctx.auto_zc_fallback = 1;
+			if (!strcmp(longopts[option_idx].name, "nthreads"))
+				ctx.nthreads = strtol(optarg, NULL, 10);
+			if (!strcmp(longopts[option_idx].name, "per_io_tasks"))
+				ctx.per_io_tasks = 1;
 			break;
 		case '?':
 			/*
diff --git a/tools/testing/selftests/ublk/kublk.h b/tools/testing/selftests/ublk/kublk.h
index e34508bf5798..6be601536b3d 100644
--- a/tools/testing/selftests/ublk/kublk.h
+++ b/tools/testing/selftests/ublk/kublk.h
@@ -49,11 +49,14 @@
 #define UBLKSRV_IO_IDLE_SECS		20
 
 #define UBLK_IO_MAX_BYTES               (1 << 20)
-#define UBLK_MAX_QUEUES                 32
+#define UBLK_MAX_QUEUES_SHIFT		5
+#define UBLK_MAX_QUEUES                 (1 << UBLK_MAX_QUEUES_SHIFT)
+#define UBLK_MAX_THREADS_SHIFT		5
+#define UBLK_MAX_THREADS		(1 << UBLK_MAX_THREADS_SHIFT)
 #define UBLK_QUEUE_DEPTH                1024
 
 #define UBLK_DBG_DEV            (1U << 0)
-#define UBLK_DBG_QUEUE          (1U << 1)
+#define UBLK_DBG_THREAD         (1U << 1)
 #define UBLK_DBG_IO_CMD         (1U << 2)
 #define UBLK_DBG_IO             (1U << 3)
 #define UBLK_DBG_CTRL_CMD       (1U << 4)
@@ -61,6 +64,7 @@
 
 struct ublk_dev;
 struct ublk_queue;
+struct ublk_thread;
 
 struct stripe_ctx {
 	/* stripe */
@@ -76,6 +80,7 @@ struct dev_ctx {
 	char tgt_type[16];
 	unsigned long flags;
 	unsigned nr_hw_queues;
+	unsigned short nthreads;
 	unsigned queue_depth;
 	int dev_id;
 	int nr_files;
@@ -85,6 +90,7 @@ struct dev_ctx {
 	unsigned int	fg:1;
 	unsigned int	recovery:1;
 	unsigned int	auto_zc_fallback:1;
+	unsigned int	per_io_tasks:1;
 
 	int _evtfd;
 	int _shmid;
@@ -123,10 +129,14 @@ struct ublk_io {
 	unsigned short flags;
 	unsigned short refs;		/* used by target code only */
 
+	int tag;
+
 	int result;
 
+	unsigned short buf_index;
 	unsigned short tgt_ios;
 	void *private_data;
+	struct ublk_thread *t;
 };
 
 struct ublk_tgt_ops {
@@ -165,28 +175,39 @@ struct ublk_tgt {
 struct ublk_queue {
 	int q_id;
 	int q_depth;
-	unsigned int cmd_inflight;
-	unsigned int io_inflight;
 	struct ublk_dev *dev;