Merge tag 'for-6.15/io_uring-20250322' of git://git.kernel.dk/linux

Pull io_uring updates from Jens Axboe:
 "This is the first of the io_uring pull requests for the 6.15 merge
  window, there will be others once the net tree has gone in. This
  contains:

   - Cleanup and unification of cancelation handling across various
     request types.

   - Improvement for bundles, supporting them both for incrementally
     consumed buffers, and for non-multishot requests.

   - Enable toggling of using iowait while waiting on io_uring events or
     not. Unfortunately this is still tied with CPU frequency boosting
     on short waits, as the scheduler side has not been very receptive
     to splitting the (useless) iowait stat from the cpufreq implied
     boost.

   - Add support for kbuf nodes, enabling zero-copy support for the ublk
     block driver.

   - Various cleanups for resource node handling.

   - Series greatly cleaning up the legacy provided (non-ring based)
     buffers. For years, we've been pushing the ring provided buffers as
     the way to go, and that is what people have been using. Reduce the
     complexity and code associated with legacy provided buffers.

   - Series cleaning up the compat handling.

   - Series improving and cleaning up the recvmsg/sendmsg iovec and msg
     handling.

   - Series of cleanups for io-wq.

   - Start adding a bunch of selftests. The liburing repository
     generally carries feature and regression tests for everything, but
     at least for ublk initially, we'll try and go the route of having
     it in selftests as well. We'll see how this goes, might decide to
     migrate more tests this way in the future.

   - Various little cleanups and fixes"

* tag 'for-6.15/io_uring-20250322' of git://git.kernel.dk/linux: (108 commits)
  selftests: ublk: add stripe target
  selftests: ublk: simplify loop io completion
  selftests: ublk: enable zero copy for null target
  selftests: ublk: prepare for supporting stripe target
  selftests: ublk: move common code into common.c
  selftests: ublk: increase max buffer size to 1MB
  selftests: ublk: add single sqe allocator helper
  selftests: ublk: add generic_01 for verifying sequential IO order
  selftests: ublk: fix starting ublk device
  io_uring: enable toggle of iowait usage when waiting on CQEs
  selftests: ublk: fix write cache implementation
  selftests: ublk: add variable for user to not show test result
  selftests: ublk: don't show `modprobe` failure
  selftests: ublk: add one dependency header
  io_uring/kbuf: enable bundles for incrementally consumed buffers
  Revert "io_uring/rsrc: simplify the bvec iter count calculation"
  selftests: ublk: improve test usability
  selftests: ublk: add stress test for covering IO vs. killing ublk server
  selftests: ublk: add one stress test for covering IO vs. removing device
  selftests: ublk: load/unload ublk_drv when preparing & cleaning up tests
  ...

24 files changed, 2820 insertions, 0 deletions

diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 2ebaf5e6942e..2694344274bf 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -114,6 +114,7 @@ endif
 TARGETS += tmpfs
 TARGETS += tpm2
 TARGETS += tty
+TARGETS += ublk
 TARGETS += uevent
 TARGETS += user_events
 TARGETS += vDSO
diff --git a/tools/testing/selftests/ublk/.gitignore b/tools/testing/selftests/ublk/.gitignore
new file mode 100644
index 000000000000..8b2871ea7751
--- /dev/null
+++ b/tools/testing/selftests/ublk/.gitignore
@@ -0,0 +1,3 @@
+kublk
+/tools
+*-verify.state
diff --git a/tools/testing/selftests/ublk/Makefile b/tools/testing/selftests/ublk/Makefile
new file mode 100644
index 000000000000..7817afe29005
--- /dev/null
+++ b/tools/testing/selftests/ublk/Makefile
@@ -0,0 +1,27 @@
+# SPDX-License-Identifier: GPL-2.0
+
+CFLAGS += -O3 -Wl,-no-as-needed -Wall -I $(top_srcdir)
+LDLIBS += -lpthread -lm -luring
+
+TEST_PROGS := test_generic_01.sh
+
+TEST_PROGS += test_null_01.sh
+TEST_PROGS += test_null_02.sh
+TEST_PROGS += test_loop_01.sh
+TEST_PROGS += test_loop_02.sh
+TEST_PROGS += test_loop_03.sh
+TEST_PROGS += test_loop_04.sh
+TEST_PROGS += test_stripe_01.sh
+TEST_PROGS += test_stripe_02.sh
+
+TEST_PROGS += test_stress_01.sh
+TEST_PROGS += test_stress_02.sh
+
+TEST_GEN_PROGS_EXTENDED = kublk
+
+include ../lib.mk
+
+$(TEST_GEN_PROGS_EXTENDED): kublk.c null.c file_backed.c common.c stripe.c
+
+check:
+	shellcheck -x -f gcc *.sh
diff --git a/tools/testing/selftests/ublk/common.c b/tools/testing/selftests/ublk/common.c
new file mode 100644
index 000000000000..01580a6f8519
--- /dev/null
+++ b/tools/testing/selftests/ublk/common.c
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "kublk.h"
+
+void backing_file_tgt_deinit(struct ublk_dev *dev)
+{
+	int i;
+
+	for (i = 1; i < dev->nr_fds; i++) {
+		fsync(dev->fds[i]);
+		close(dev->fds[i]);
+	}
+}
+
+int backing_file_tgt_init(struct ublk_dev *dev)
+{
+	int fd, i;
+
+	assert(dev->nr_fds == 1);
+
+	for (i = 0; i < dev->tgt.nr_backing_files; i++) {
+		char *file = dev->tgt.backing_file[i];
+		unsigned long bytes;
+		struct stat st;
+
+		ublk_dbg(UBLK_DBG_DEV, "%s: file %d: %s\n", __func__, i, file);
+
+		fd = open(file, O_RDWR | O_DIRECT);
+		if (fd < 0) {
+			ublk_err("%s: backing file %s can't be opened: %s\n",
+					__func__, file, strerror(errno));
+			return -EBADF;
+		}
+
+		if (fstat(fd, &st) < 0) {
+			close(fd);
+			return -EBADF;
+		}
+
+		if (S_ISREG(st.st_mode))
+			bytes = st.st_size;
+		else if (S_ISBLK(st.st_mode)) {
+			if (ioctl(fd, BLKGETSIZE64, &bytes) != 0)
+				return -1;
+		} else {
+			return -EINVAL;
+		}
+
+		dev->tgt.backing_file_size[i] = bytes;
+		dev->fds[dev->nr_fds] = fd;
+		dev->nr_fds += 1;
+	}
+
+	return 0;
+}
diff --git a/tools/testing/selftests/ublk/config b/tools/testing/selftests/ublk/config
new file mode 100644
index 000000000000..592b0ba4d661
--- /dev/null
+++ b/tools/testing/selftests/ublk/config
@@ -0,0 +1 @@
+CONFIG_BLK_DEV_UBLK=m
diff --git a/tools/testing/selftests/ublk/file_backed.c b/tools/testing/selftests/ublk/file_backed.c
new file mode 100644
index 000000000000..6f34eabfae97
--- /dev/null
+++ b/tools/testing/selftests/ublk/file_backed.c
@@ -0,0 +1,169 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "kublk.h"
+
+static enum io_uring_op ublk_to_uring_op(const struct ublksrv_io_desc *iod, int zc)
+{
+	unsigned ublk_op = ublksrv_get_op(iod);
+
+	if (ublk_op == UBLK_IO_OP_READ)
+		return zc ? IORING_OP_READ_FIXED : IORING_OP_READ;
+	else if (ublk_op == UBLK_IO_OP_WRITE)
+		return zc ? IORING_OP_WRITE_FIXED : IORING_OP_WRITE;
+	assert(0);
+}
+
+static int loop_queue_flush_io(struct ublk_queue *q, const struct ublksrv_io_desc *iod, int tag)
+{
+	unsigned ublk_op = ublksrv_get_op(iod);
+	struct io_uring_sqe *sqe[1];
+
+	ublk_queue_alloc_sqes(q, 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);
+	return 1;
+}
+
+static int loop_queue_tgt_rw_io(struct ublk_queue *q, const struct ublksrv_io_desc *iod, int tag)
+{
+	unsigned ublk_op = ublksrv_get_op(iod);
+	int zc = ublk_queue_use_zc(q);
+	enum io_uring_op op = ublk_to_uring_op(iod, zc);
+	struct io_uring_sqe *sqe[3];
+
+	if (!zc) {
+		ublk_queue_alloc_sqes(q, sqe, 1);
+		if (!sqe[0])
+			return -ENOMEM;
+
+		io_uring_prep_rw(op, sqe[0], 1 /*fds[1]*/,
+				(void *)iod->addr,
+				iod->nr_sectors << 9,
+				iod->start_sector << 9);
+		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);
+		return 1;
+	}
+
+	ublk_queue_alloc_sqes(q, sqe, 3);
+
+	io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, tag);
+	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);
+
+	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);
+
+	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);
+
+	return 2;
+}
+
+static int loop_queue_tgt_io(struct ublk_queue *q, int tag)
+{
+	const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag);
+	unsigned ublk_op = ublksrv_get_op(iod);
+	int ret;
+
+	switch (ublk_op) {
+	case UBLK_IO_OP_FLUSH:
+		ret = loop_queue_flush_io(q, iod, tag);
+		break;
+	case UBLK_IO_OP_WRITE_ZEROES:
+	case UBLK_IO_OP_DISCARD:
+		ret = -ENOTSUP;
+		break;
+	case UBLK_IO_OP_READ:
+	case UBLK_IO_OP_WRITE:
+		ret = loop_queue_tgt_rw_io(q, iod, tag);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	ublk_dbg(UBLK_DBG_IO, "%s: tag %d ublk io %x %llx %u\n", __func__, tag,
+			iod->op_flags, iod->start_sector, iod->nr_sectors << 9);
+	return ret;
+}
+
+static int ublk_loop_queue_io(struct ublk_queue *q, int tag)
+{
+	int queued = loop_queue_tgt_io(q, tag);
+
+	ublk_queued_tgt_io(q, tag, queued);
+	return 0;
+}
+
+static void ublk_loop_io_done(struct ublk_queue *q, int tag,
+		const struct io_uring_cqe *cqe)
+{
+	unsigned op = user_data_to_op(cqe->user_data);
+	struct ublk_io *io = ublk_get_io(q, tag);
+
+	if (cqe->res < 0 || op != ublk_cmd_op_nr(UBLK_U_IO_UNREGISTER_IO_BUF)) {
+		if (!io->result)
+			io->result = cqe->res;
+		if (cqe->res < 0)
+			ublk_err("%s: io failed op %x user_data %lx\n",
+					__func__, op, cqe->user_data);
+	}
+
+	/* buffer register op is IOSQE_CQE_SKIP_SUCCESS */
+	if (op == ublk_cmd_op_nr(UBLK_U_IO_REGISTER_IO_BUF))
+		io->tgt_ios += 1;
+
+	if (ublk_completed_tgt_io(q, tag))
+		ublk_complete_io(q, tag, io->result);
+}
+
+static int ublk_loop_tgt_init(const struct dev_ctx *ctx, struct ublk_dev *dev)
+{
+	unsigned long long bytes;
+	int ret;
+	struct ublk_params p = {
+		.types = UBLK_PARAM_TYPE_BASIC | UBLK_PARAM_TYPE_DMA_ALIGN,
+		.basic = {
+			.attrs = UBLK_ATTR_VOLATILE_CACHE,
+			.logical_bs_shift	= 9,
+			.physical_bs_shift	= 12,
+			.io_opt_shift	= 12,
+			.io_min_shift	= 9,
+			.max_sectors = dev->dev_info.max_io_buf_bytes >> 9,
+		},
+		.dma = {
+			.alignment = 511,
+		},
+	};
+
+	ret = backing_file_tgt_init(dev);
+	if (ret)
+		return ret;
+
+	if (dev->tgt.nr_backing_files != 1)
+		return -EINVAL;
+
+	bytes = dev->tgt.backing_file_size[0];
+	dev->tgt.dev_size = bytes;
+	p.basic.dev_sectors = bytes >> 9;
+	dev->tgt.params = p;
+
+	return 0;
+}
+
+const struct ublk_tgt_ops loop_tgt_ops = {
+	.name = "loop",
+	.init_tgt = ublk_loop_tgt_init,
+	.deinit_tgt = backing_file_tgt_deinit,
+	.queue_io = ublk_loop_queue_io,
+	.tgt_io_done = ublk_loop_io_done,
+};
diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c
new file mode 100644
index 000000000000..05147b53c361
--- /dev/null
+++ b/tools/testing/selftests/ublk/kublk.c
@@ -0,0 +1,1138 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Description: uring_cmd based ublk
+ */
+
+#include "kublk.h"
+
+unsigned int ublk_dbg_mask = UBLK_LOG;
+static const struct ublk_tgt_ops *tgt_ops_list[] = {
+	&null_tgt_ops,
+	&loop_tgt_ops,
+	&stripe_tgt_ops,
+};
+
+static const struct ublk_tgt_ops *ublk_find_tgt(const char *name)
+{
+	const struct ublk_tgt_ops *ops;
+	int i;
+
+	if (name == NULL)
+		return NULL;
+
+	for (i = 0; sizeof(tgt_ops_list) / sizeof(ops); i++)
+		if (strcmp(tgt_ops_list[i]->name, name) == 0)
+			return tgt_ops_list[i];
+	return NULL;
+}
+
+static inline int ublk_setup_ring(struct io_uring *r, int depth,
+		int cq_depth, unsigned flags)
+{
+	struct io_uring_params p;
+
+	memset(&p, 0, sizeof(p));
+	p.flags = flags | IORING_SETUP_CQSIZE;
+	p.cq_entries = cq_depth;
+
+	return io_uring_queue_init_params(depth, r, &p);
+}
+
+static void ublk_ctrl_init_cmd(struct ublk_dev *dev,
+		struct io_uring_sqe *sqe,
+		struct ublk_ctrl_cmd_data *data)
+{
+	struct ublksrv_ctrl_dev_info *info = &dev->dev_info;
+	struct ublksrv_ctrl_cmd *cmd = (struct ublksrv_ctrl_cmd *)ublk_get_sqe_cmd(sqe);
+
+	sqe->fd = dev->ctrl_fd;
+	sqe->opcode = IORING_OP_URING_CMD;
+	sqe->ioprio = 0;
+
+	if (data->flags & CTRL_CMD_HAS_BUF) {
+		cmd->addr = data->addr;
+		cmd->len = data->len;
+	}
+
+	if (data->flags & CTRL_CMD_HAS_DATA)
+		cmd->data[0] = data->data[0];
+
+	cmd->dev_id = info->dev_id;
+	cmd->queue_id = -1;
+
+	ublk_set_sqe_cmd_op(sqe, data->cmd_op);
+
+	io_uring_sqe_set_data(sqe, cmd);
+}
+
+static int __ublk_ctrl_cmd(struct ublk_dev *dev,
+		struct ublk_ctrl_cmd_data *data)
+{
+	struct io_uring_sqe *sqe;
+	struct io_uring_cqe *cqe;
+	int ret = -EINVAL;
+
+	sqe = io_uring_get_sqe(&dev->ring);
+	if (!sqe) {
+		ublk_err("%s: can't get sqe ret %d\n", __func__, ret);
+		return ret;
+	}
+
+	ublk_ctrl_init_cmd(dev, sqe, data);
+
+	ret = io_uring_submit(&dev->ring);
+	if (ret < 0) {
+		ublk_err("uring submit ret %d\n", ret);
+		return ret;
+	}
+
+	ret = io_uring_wait_cqe(&dev->ring, &cqe);
+	if (ret < 0) {
+		ublk_err("wait cqe: %s\n", strerror(-ret));
+		return ret;
+	}
+	io_uring_cqe_seen(&dev->ring, cqe);
+
+	return cqe->res;
+}
+
+static int ublk_ctrl_stop_dev(struct ublk_dev *dev)
+{
+	struct ublk_ctrl_cmd_data data = {
+		.cmd_op	= UBLK_CMD_STOP_DEV,
+	};
+
+	return __ublk_ctrl_cmd(dev, &data);
+}
+
+static int ublk_ctrl_start_dev(struct ublk_dev *dev,
+		int daemon_pid)
+{
+	struct ublk_ctrl_cmd_data data = {
+		.cmd_op	= UBLK_U_CMD_START_DEV,
+		.flags	= CTRL_CMD_HAS_DATA,
+	};
+
+	dev->dev_info.ublksrv_pid = data.data[0] = daemon_pid;
+
+	return __ublk_ctrl_cmd(dev, &data);
+}
+
+static int ublk_ctrl_add_dev(struct ublk_dev *dev)
+{
+	struct ublk_ctrl_cmd_data data = {
+		.cmd_op	= UBLK_U_CMD_ADD_DEV,
+		.flags	= CTRL_CMD_HAS_BUF,
+		.addr = (__u64) (uintptr_t) &dev->dev_info,
+		.len = sizeof(struct ublksrv_ctrl_dev_info),
+	};
+
+	return __ublk_ctrl_cmd(dev, &data);
+}
+
+static int ublk_ctrl_del_dev(struct ublk_dev *dev)
+{
+	struct ublk_ctrl_cmd_data data = {
+		.cmd_op = UBLK_U_CMD_DEL_DEV,
+		.flags = 0,
+	};
+
+	return __ublk_ctrl_cmd(dev, &data);
+}
+
+static int ublk_ctrl_get_info(struct ublk_dev *dev)
+{
+	struct ublk_ctrl_cmd_data data = {
+		.cmd_op	= UBLK_U_CMD_GET_DEV_INFO,
+		.flags	= CTRL_CMD_HAS_BUF,
+		.addr = (__u64) (uintptr_t) &dev->dev_info,
+		.len = sizeof(struct ublksrv_ctrl_dev_info),
+	};
+
+	return __ublk_ctrl_cmd(dev, &data);
+}
+
+static int ublk_ctrl_set_params(struct ublk_dev *dev,
+		struct ublk_params *params)
+{
+	struct ublk_ctrl_cmd_data data = {
+		.cmd_op	= UBLK_U_CMD_SET_PARAMS,
+		.flags	= CTRL_CMD_HAS_BUF,
+		.addr = (__u64) (uintptr_t) params,
+		.len = sizeof(*params),
+	};
+	params->len = sizeof(*params);
+	return __ublk_ctrl_cmd(dev, &data);
+}
+
+static int ublk_ctrl_get_params(struct ublk_dev *dev,
+		struct ublk_params *params)
+{
+	struct ublk_ctrl_cmd_data data = {
+		.cmd_op	= UBLK_CMD_GET_PARAMS,
+		.flags	= CTRL_CMD_HAS_BUF,
+		.addr = (__u64)params,
+		.len = sizeof(*params),
+	};
+
+	params->len = sizeof(*params);
+
+	return __ublk_ctrl_cmd(dev, &data);
+}
+
+static int ublk_ctrl_get_features(struct ublk_dev *dev,
+		__u64 *features)
+{
+	struct ublk_ctrl_cmd_data data = {
+		.cmd_op	= UBLK_U_CMD_GET_FEATURES,
+		.flags	= CTRL_CMD_HAS_BUF,
+		.addr = (__u64) (uintptr_t) features,
+		.len = sizeof(*features),
+	};
+
+	return __ublk_ctrl_cmd(dev, &data);
+}
+
+static const char *ublk_dev_state_desc(struct ublk_dev *dev)
+{
+	switch (dev->dev_info.state) {
+	case UBLK_S_DEV_DEAD:
+		return "DEAD";
+	case UBLK_S_DEV_LIVE:
+		return "LIVE";
+	case UBLK_S_DEV_QUIESCED:
+		return "QUIESCED";
+	default:
+		return "UNKNOWN";
+	};
+}
+
+static void ublk_ctrl_dump(struct ublk_dev *dev)
+{
+	struct ublksrv_ctrl_dev_info *info = &dev->dev_info;
+	struct ublk_params p;
+	int ret;
+
+	ret = ublk_ctrl_get_params(dev, &p);
+	if (ret < 0) {
+		ublk_err("failed to get params %m\n");
+		return;
+	}
+
+	ublk_log("dev id %d: nr_hw_queues %d queue_depth %d block size %d dev_capacity %lld\n",
+			info->dev_id, info->nr_hw_queues, info->queue_depth,
+			1 << p.basic.logical_bs_shift, p.basic.dev_sectors);
+	ublk_log("\tmax rq size %d daemon pid %d flags 0x%llx state %s\n",
+			info->max_io_buf_bytes, info->ublksrv_pid, info->flags,
+			ublk_dev_state_desc(dev));
+	fflush(stdout);
+}
+
+static void ublk_ctrl_deinit(struct ublk_dev *dev)
+{
+	close(dev->ctrl_fd);
+	free(dev);
+}
+
+static struct ublk_dev *ublk_ctrl_init(void)
+{
+	struct ublk_dev *dev = (struct ublk_dev *)calloc(1, sizeof(*dev));
+	struct ublksrv_ctrl_dev_info *info = &dev->dev_info;
+	int ret;
+
+	dev->ctrl_fd = open(CTRL_DEV, O_RDWR);
+	if (dev->ctrl_fd < 0) {
+		free(dev);
+		return NULL;
+	}
+
+	info->max_io_buf_bytes = UBLK_IO_MAX_BYTES;
+
+	ret = ublk_setup_ring(&dev->ring, UBLK_CTRL_RING_DEPTH,
+			UBLK_CTRL_RING_DEPTH, IORING_SETUP_SQE128);
+	if (ret < 0) {
+		ublk_err("queue_init: %s\n", strerror(-ret));
+		free(dev);
+		return NULL;
+	}
+	dev->nr_fds = 1;
+
+	return dev;
+}
+
+static int __ublk_queue_cmd_buf_sz(unsigned depth)
+{
+	int size =  depth * sizeof(struct ublksrv_io_desc);
+	unsigned int page_sz = getpagesize();
+
+	return round_up(size, page_sz);
+}
+
+static int ublk_queue_max_cmd_buf_sz(void)
+{
+	return __ublk_queue_cmd_buf_sz(UBLK_MAX_QUEUE_DEPTH);
+}
+
+static int ublk_queue_cmd_buf_sz(struct ublk_queue *q)
+{
+	return __ublk_queue_cmd_buf_sz(q->q_depth);
+}
+
+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));
+
+	for (i = 0; i < nr_ios; i++)
+		free(q->ios[i].buf_addr);
+}
+
+static int ublk_queue_init(struct ublk_queue *q)
+{
+	struct ublk_dev *dev = q->dev;
+	int depth = dev->dev_info.queue_depth;
+	int i, ret = -1;
+	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) {
+		q->state |= UBLKSRV_NO_BUF;
+		q->state |= UBLKSRV_ZC;
+	}
+
+	cmd_buf_size = ublk_queue_cmd_buf_sz(q);
+	off = UBLKSRV_CMD_BUF_OFFSET + q->q_id * ublk_queue_max_cmd_buf_sz();
+	q->io_cmd_buf = (char *)mmap(0, cmd_buf_size, PROT_READ,
+			MAP_SHARED | MAP_POPULATE, dev->fds[0], off);
+	if (q->io_cmd_buf == MAP_FAILED) {
+		ublk_err("ublk dev %d queue %d map io_cmd_buf failed %m\n",
+				q->dev->dev_info.dev_id, q->q_id);
+		goto fail;
+	}
+
+	io_buf_size = dev->dev_info.max_io_buf_bytes;
+	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;
+
+		if (q->state & UBLKSRV_NO_BUF)
+			continue;
+
+		if (posix_memalign((void **)&q->ios[i].buf_addr,
+					getpagesize(), io_buf_size)) {
+			ublk_err("ublk dev %d queue %d io %d posix_memalign failed %m\n",
+					dev->dev_info.dev_id, q->q_id, i);
+			goto fail;
+		}
+	}
+
+	ret = ublk_setup_ring(&q->ring, ring_depth, cq_depth,
+			IORING_SETUP_COOP_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);
+		goto fail;
+	}
+
+	if (dev->dev_info.flags & UBLK_F_SUPPORT_ZERO_COPY) {
+		ret = io_uring_register_buffers_sparse(&q->ring, q->q_depth);
+		if (ret) {
+			ublk_err("ublk dev %d queue %d register spare buffers failed %d",
+					dev->dev_info.dev_id, q->q_id, ret);
+			goto fail;
+		}
+	}
+
+	io_uring_register_ring_fd(&q->ring);
+
+	ret = io_uring_register_files(&q->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);
+		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);
+	return -ENOMEM;
+}
+
+#define WAIT_USEC 	100000
+#define MAX_WAIT_USEC 	(3 * 1000000)
+static int ublk_dev_prep(const struct dev_ctx *ctx, struct ublk_dev *dev)
+{
+	int dev_id = dev->dev_info.dev_id;
+	unsigned int wait_usec = 0;
+	int ret = 0, fd = -1;
+	char buf[64];
+
+	snprintf(buf, 64, "%s%d", UBLKC_DEV, dev_id);
+
+	while (wait_usec < MAX_WAIT_USEC) {
+		fd = open(buf, O_RDWR);
+		if (fd >= 0)
+			break;
+		usleep(WAIT_USEC);
+		wait_usec += WAIT_USEC;
+	}
+	if (fd < 0) {
+		ublk_err("can't open %s %s\n", buf, strerror(errno));
+		return -1;
+	}
+
+	dev->fds[0] = fd;
+	if (dev->tgt.ops->init_tgt)
+		ret = dev->tgt.ops->init_tgt(ctx, dev);
+	if (ret)
+		close(dev->fds[0]);
+	return ret;
+}
+
+static void ublk_dev_unprep(struct ublk_dev *dev)
+{
+	if (dev->tgt.ops->deinit_tgt)
+		dev->tgt.ops->deinit_tgt(dev);
+	close(dev->fds[0]);
+}
+
+int ublk_queue_io_cmd(struct ublk_queue *q, struct ublk_io *io, unsigned tag)
+{
+	struct ublksrv_io_cmd *cmd;
+	struct io_uring_sqe *sqe[1];
+	unsigned int cmd_op = 0;
+	__u64 user_data;
+
+	/* only freed io can be issued */
+	if (!(io->flags & UBLKSRV_IO_FREE))
+		return 0;
+
+	/* we issue because we need either fetching or committing */
+	if (!(io->flags &
+		(UBLKSRV_NEED_FETCH_RQ | UBLKSRV_NEED_COMMIT_RQ_COMP)))
+		return 0;
+
+	if (io->flags & UBLKSRV_NEED_COMMIT_RQ_COMP)
+		cmd_op = UBLK_U_IO_COMMIT_AND_FETCH_REQ;
+	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);
+
+	ublk_queue_alloc_sqes(q, sqe, 1);
+	if (!sqe[0]) {
+		ublk_err("%s: run out of sqe %d, tag %d\n",
+				__func__, q->q_id, tag);
+		return -1;
+	}
+
+	cmd = (struct ublksrv_io_cmd *)ublk_get_sqe_cmd(sqe[0]);
+
+	if (cmd_op == UBLK_U_IO_COMMIT_AND_FETCH_REQ)
+		cmd->result = io->result;
+
+	/* These fields should be written once, never change */
+	ublk_set_sqe_cmd_op(sqe[0], cmd_op);
+	sqe[0]->fd		= 0;	/* dev->fds[0] */
+	sqe[0]->opcode	= IORING_OP_URING_CMD;
+	sqe[0]->flags	= IOSQE_FIXED_FILE;
+	sqe[0]->rw_flags	= 0;
+	cmd->tag	= tag;
+	cmd->q_id	= q->q_id;
+	if (!(q->state & UBLKSRV_NO_BUF))
+		cmd->addr	= (__u64) (uintptr_t) io->buf_addr;
+	else
+		cmd->addr	= 0;
+
+	user_data = build_user_data(tag, _IOC_NR(cmd_op), 0, 0);
+	io_uring_sqe_set_data64(sqe[0], user_data);
+
+	io->flags = 0;
+
+	q->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));
+	return 1;
+}
+
+static void ublk_submit_fetch_commands(struct ublk_queue *q)
+{
+	int i = 0;
+
+	for (i = 0; i < q->q_depth; i++)
+		ublk_queue_io_cmd(q, &q->ios[i], i);
+}
+
+static int ublk_queue_is_idle(struct ublk_queue *q)
+{
+	return !io_uring_sq_ready(&q->ring) && !q->io_inflight;
+}
+
+static int ublk_queue_is_done(struct ublk_queue *q)
+{
+	return (q->state & UBLKSRV_QUEUE_STOPPING) && ublk_queue_is_idle(q);
+}
+
+static inline void ublksrv_handle_tgt_cqe(struct ublk_queue *q,
+		struct io_uring_cqe *cqe)
+{
+	unsigned tag = user_data_to_tag(cqe->user_data);
+
+	if (cqe->res < 0 && cqe->res != -EAGAIN)
+		ublk_err("%s: failed tgt io: res %d qid %u tag %u, cmd_op %u\n",
+			__func__, cqe->res, q->q_id,
+			user_data_to_tag(cqe->user_data),
+			user_data_to_op(cqe->user_data));
+
+	if (q->tgt_ops->tgt_io_done)
+		q->tgt_ops->tgt_io_done(q, tag, cqe);
+}
+
+static void ublk_handle_cqe(struct io_uring *r,
+		struct io_uring_cqe *cqe, void *data)
+{
+	struct ublk_queue *q = container_of(r, struct ublk_queue, ring);
+	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);
+	struct ublk_io *io;
+
+	if (cqe->res < 0 && cqe->res != -ENODEV)
+		ublk_err("%s: res %d userdata %llx queue state %x\n", __func__,
+				cqe->res, cqe->user_data, q->state);
+
+	ublk_dbg(UBLK_DBG_IO_CMD, "%s: res %d (qid %d tag %u cmd_op %u target %d/%d) stopping %d\n",
+			__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));
+
+	/* Don't retrieve io in case of target io */
+	if (is_target_io(cqe->user_data)) {
+		ublksrv_handle_tgt_cqe(q, cqe);
+		return;
+	}
+
+	io = &q->ios[tag];
+	q->cmd_inflight--;
+
+	if (!fetch) {
+		q->state |= UBLKSRV_QUEUE_STOPPING;
+		io->flags &= ~UBLKSRV_NEED_FETCH_RQ;
+	}
+
+	if (cqe->res == UBLK_IO_RES_OK) {
+		assert(tag < q->q_depth);
+		if (q->tgt_ops->queue_io)
+			q->tgt_ops->queue_io(q, tag);
+	} else {
+		/*
+		 * COMMIT_REQ will be completed immediately since no fetching
+		 * piggyback is required.
+		 *
+		 * Marking IO_FREE only, then this io won't be issued since
+		 * we only issue io with (UBLKSRV_IO_FREE | UBLKSRV_NEED_*)
+		 *
+		 * */
+		io->flags = UBLKSRV_IO_FREE;
+	}
+}
+
+static int ublk_reap_events_uring(struct io_uring *r)
+{
+	struct io_uring_cqe *cqe;
+	unsigned head;
+	int count = 0;
+
+	io_uring_for_each_cqe(r, head, cqe) {
+		ublk_handle_cqe(r, cqe, NULL);
+		count += 1;
+	}
+	io_uring_cq_advance(r, count);
+
+	return count;
+}
+
+static int ublk_process_io(struct ublk_queue *q)
+{
+	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));
+
+	if (ublk_queue_is_done(q))
+		return -ENODEV;
+
+	ret = io_uring_submit_and_wait(&q->ring, 1);
+	reapped = ublk_reap_events_uring(&q->ring);
+
+	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));
+
+	return reapped;
+}
+
+static void *ublk_io_handler_fn(void *data)
+{
+	struct ublk_queue *q = data;
+	int dev_id = q->dev->dev_info.dev_id;
+	int ret;
+
+	ret = ublk_queue_init(q);
+	if (ret) {
+		ublk_err("ublk dev %d queue %d init queue failed\n",
+				dev_id, q->q_id);
+		return NULL;
+	}
+	ublk_dbg(UBLK_DBG_QUEUE, "tid %d: ublk dev %d queue %d started\n",
+			q->tid, dev_id, q->q_id);
+
+	/* submit all io commands to ublk driver */
+	ublk_submit_fetch_commands(q);
+	do {
+		if (ublk_process_io(q) < 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);
+	return NULL;
+}
+
+static void ublk_set_parameters(struct ublk_dev *dev)
+{
+	int ret;
+
+	ret = ublk_ctrl_set_params(dev, &dev->tgt.params);
+	if (ret)
+		ublk_err("dev %d set basic parameter failed %d\n",
+				dev->dev_info.dev_id, ret);
+}
+
+static int ublk_send_dev_event(const struct dev_ctx *ctx, int dev_id)
+{
+	uint64_t id;
+	int evtfd = ctx->_evtfd;
+
+	if (evtfd < 0)
+		return -EBADF;
+
+	if (dev_id >= 0)
+		id = dev_id + 1;
+	else
+		id = ERROR_EVTFD_DEVID;
+
+	if (write(evtfd, &id, sizeof(id)) != sizeof(id))
+		return -EINVAL;
+
+	return 0;
+}
+
+
+static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev)
+{
+	int ret, i;
+	void *thread_ret;
+	const struct ublksrv_ctrl_dev_info *dinfo = &dev->dev_info;
+
+	ublk_dbg(UBLK_DBG_DEV, "%s enter\n", __func__);
+
+	ret = ublk_dev_prep(ctx, dev);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < dinfo->nr_hw_queues; i++) {
+		dev->q[i].dev = dev;
+		dev->q[i].q_id = i;
+		pthread_create(&dev->q[i].thread, NULL,
+				ublk_io_handler_fn,
+				&dev->q[i]);
+	}
+
+	/* everything is fine now, start us */
+	ublk_set_parameters(dev);
+	ret = ublk_ctrl_start_dev(dev, getpid());
+	if (ret < 0) {
+		ublk_err("%s: ublk_ctrl_start_dev failed: %d\n", __func__, ret);
+		goto fail;
+	}
+
+	ublk_ctrl_get_info(dev);
+	if (ctx->fg)
+		ublk_ctrl_dump(dev);
+	else
+		ublk_send_dev_event(ctx, 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);
+ fail:
+	ublk_dev_unprep(dev);
+	ublk_dbg(UBLK_DBG_DEV, "%s exit\n", __func__);
+
+	return ret;
+}
+
+static int wait_ublk_dev(const char *path, int evt_mask, unsigned timeout)
+{
+#define EV_SIZE (sizeof(struct inotify_event))
+#define EV_BUF_LEN (128 * (EV_SIZE + 16))
+	struct pollfd pfd;
+	int fd, wd;
+	int ret = -EINVAL;
+	const char *dev_name = basename(path);
+
+	fd = inotify_init();
+	if (fd < 0) {
+		ublk_dbg(UBLK_DBG_DEV, "%s: inotify init failed\n", __func__);
+		return fd;
+	}
+
+	wd = inotify_add_watch(fd, "/dev", evt_mask);
+	if (wd == -1) {
+		ublk_dbg(UBLK_DBG_DEV, "%s: add watch for /dev failed\n", __func__);
+		goto fail;
+	}
+
+	pfd.fd = fd;
+	pfd.events = POLL_IN;
+	while (1) {
+		int i = 0;
+		char buffer[EV_BUF_LEN];
+		ret = poll(&pfd, 1, 1000 * timeout);
+
+		if (ret == -1) {
+			ublk_err("%s: poll inotify failed: %d\n", __func__, ret);
+			goto rm_watch;
+		} else if (ret == 0) {
+			ublk_err("%s: poll inotify timeout\n", __func__);
+			ret = -ETIMEDOUT;
+			goto rm_watch;
+		}
+
+		ret = read(fd, buffer, EV_BUF_LEN);
+		if (ret < 0) {
+			ublk_err("%s: read inotify fd failed\n", __func__);
+			goto rm_watch;
+		}
+
+		while (i < ret) {
+			struct inotify_event *event = (struct inotify_event *)&buffer[i];
+
+			ublk_dbg(UBLK_DBG_DEV, "%s: inotify event %x %s\n",
+					__func__, event->mask, event->name);
+			if (event->mask & evt_mask) {
+				if (!strcmp(event->name, dev_name)) {
+					ret = 0;
+					goto rm_watch;
+				}
+			}
+			i += EV_SIZE + event->len;
+		}
+	}
+rm_watch:
+	inotify_rm_watch(fd, wd);
+fail:
+	close(fd);
+	return ret;
+}
+
+static int ublk_stop_io_daemon(const struct ublk_dev *dev)
+{
+	int daemon_pid = dev->dev_info.ublksrv_pid;
+	int dev_id = dev->dev_info.dev_id;
+	char ublkc[64];
+	int ret = 0;
+
+	if (daemon_pid < 0)
+		return 0;
+
+	/* daemon may be dead already */
+	if (kill(daemon_pid, 0) < 0)
+		goto wait;
+
+	snprintf(ublkc, sizeof(ublkc), "/dev/%s%d", "ublkc", dev_id);
+
+	/* ublk char device may be gone already */
+	if (access(ublkc, F_OK) != 0)
+		goto wait;
+
+	/* Wait until ublk char device is closed, when the daemon is shutdown */
+	ret = wait_ublk_dev(ublkc, IN_CLOSE, 10);
+	/* double check and since it may be closed before starting inotify */
+	if (ret == -ETIMEDOUT)
+		ret = kill(daemon_pid, 0) < 0;
+wait:
+	waitpid(daemon_pid, NULL, 0);
+	ublk_dbg(UBLK_DBG_DEV, "%s: pid %d dev_id %d ret %d\n",
+			__func__, daemon_pid, dev_id, ret);
+
+	return ret;
+}
+
+static int __cmd_dev_add(const struct dev_ctx *ctx)
+{
+	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;
+	int dev_id = ctx->dev_id;
+	int ret, i;
+
+	ops = ublk_find_tgt(tgt_type);
+	if (!ops) {
+		ublk_err("%s: no such tgt type, type %s\n",
+				__func__, tgt_type);
+		return -ENODEV;
+	}
+
+	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;
+	}
+
+	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;
+	}
+
+	/* kernel doesn't support get_features */
+	ret = ublk_ctrl_get_features(dev, &features);
+	if (ret < 0)
+		return -EINVAL;
+
+	if (!(features & UBLK_F_CMD_IOCTL_ENCODE))
+		return -ENOTSUP;
+
+	info = &dev->dev_info;
+	info->dev_id = ctx->dev_id;
+	info->nr_hw_queues = nr_queues;
+	info->queue_depth = depth;
+	info->flags = ctx->flags;
+	dev->tgt.ops = ops;
+	dev->tgt.sq_depth = depth;
+	dev->tgt.cq_depth = depth;
+
+	for (i = 0; i < MAX_BACK_FILES; i++) {
+		if (ctx->files[i]) {
+			strcpy(dev->tgt.backing_file[i], ctx->files[i]);
+			dev->tgt.nr_backing_files++;
+		}
+	}
+
+	ret = ublk_ctrl_add_dev(dev);
+	if (ret < 0) {
+		ublk_err("%s: can't add dev id %d, type %s ret %d\n",
+				__func__, dev_id, tgt_type, ret);
+		goto fail;
+	}
+
+	ret = ublk_start_daemon(ctx, dev);
+	ublk_dbg(UBLK_DBG_DEV, "%s: daemon exit %d\b", ret);
+	if (ret < 0)
+		ublk_ctrl_del_dev(dev);
+
+fail:
+	if (ret < 0)
+		ublk_send_dev_event(ctx, -1);
+	ublk_ctrl_deinit(dev);
+	return ret;
+}
+
+static int __cmd_dev_list(struct dev_ctx *ctx);
+
+static int cmd_dev_add(struct dev_ctx *ctx)
+{
+	int res;
+
+	if (ctx->fg)
+		goto run;
+
+	ctx->_evtfd = eventfd(0, 0);
+	if (ctx->_evtfd < 0) {
+		ublk_err("%s: failed to create eventfd %s\n", __func__, strerror(errno));
+		exit(-1);
+	}
+
+	setsid();
+	res = fork();
+	if (res == 0) {
+run:
+		res = __cmd_dev_add(ctx);
+		return res;
+	} else if (res > 0) {
+		uint64_t id;
+
+		res = read(ctx->_evtfd, &id, sizeof(id));
+		close(ctx->_evtfd);
+		if (res == sizeof(id) && id != ERROR_EVTFD_DEVID) {
+			ctx->dev_id = id - 1;
+			return __cmd_dev_list(ctx);
+		}
+		exit(EXIT_FAILURE);
+	} else {
+		return res;
+	}
+}
+
+static int __cmd_dev_del(struct dev_ctx *ctx)
+{
+	int number = ctx->dev_id;
+	struct ublk_dev *dev;
+	int ret;
+
+	dev = ublk_ctrl_init();
+	dev->dev_info.dev_id = number;
+
+	ret = ublk_ctrl_get_info(dev);
+	if (ret < 0)
+		goto fail;
+
+	ret = ublk_ctrl_stop_dev(dev);
+	if (ret < 0)
+		ublk_err("%s: stop dev %d failed ret %d\n", __func__, number, ret);
+
+	ret = ublk_stop_io_daemon(dev);
+	if (ret < 0)
+		ublk_err("%s: stop daemon id %d dev %d, ret %d\n",
+				__func__, dev->dev_info.ublksrv_pid, number, ret);
+	ublk_ctrl_del_dev(dev);
+fail:
+	ublk_ctrl_deinit(dev);
+
+	return (ret >= 0) ? 0 : ret;
+}
+
+static int cmd_dev_del(struct dev_ctx *ctx)
+{
+	int i;
+
+	if (ctx->dev_id >= 0 || !ctx->all)
+		return __cmd_dev_del(ctx);
+
+	for (i = 0; i < 255; i++) {
+		ctx->dev_id = i;
+		__cmd_dev_del(ctx);
+	}
+	return 0;
+}
+
+static int __cmd_dev_list(struct dev_ctx *ctx)
+{
+	struct ublk_dev *dev = ublk_ctrl_init();
+	int ret;
+
+	if (!dev)
+		return -ENODEV;
+
+	dev->dev_info.dev_id = ctx->dev_id;
+
+	ret = ublk_ctrl_get_info(dev);
+	if (ret < 0) {
+		if (ctx->logging)
+			ublk_err("%s: can't get dev info from %d: %d\n",
+					__func__, ctx->dev_id, ret);
+	} else {
+		ublk_ctrl_dump(dev);
+	}
+
+	ublk_ctrl_deinit(dev);
+
+	return ret;
+}
+
+static int cmd_dev_list(struct dev_ctx *ctx)
+{
+	int i;
+
+	if (ctx->dev_id >= 0 || !ctx->all)
+		return __cmd_dev_list(ctx);
+
+	ctx->logging = false;
+	for (i = 0; i < 255; i++) {
+		ctx->dev_id = i;
+		__cmd_dev_list(ctx);
+	}
+	return 0;
+}
+
+static int cmd_dev_get_features(void)
+{
+#define const_ilog2(x) (63 - __builtin_clzll(x))
+	static const char *feat_map[] = {
+		[const_ilog2(UBLK_F_SUPPORT_ZERO_COPY)] = "ZERO_COPY",
+		[const_ilog2(UBLK_F_URING_CMD_COMP_IN_TASK)] = "COMP_IN_TASK",
+		[const_ilog2(UBLK_F_NEED_GET_DATA)] = "GET_DATA",
+		[const_ilog2(UBLK_F_USER_RECOVERY)] = "USER_RECOVERY",
+		[const_ilog2(UBLK_F_USER_RECOVERY_REISSUE)] = "RECOVERY_REISSUE",
+		[const_ilog2(UBLK_F_UNPRIVILEGED_DEV)] = "UNPRIVILEGED_DEV",
+		[const_ilog2(UBLK_F_CMD_IOCTL_ENCODE)] = "CMD_IOCTL_ENCODE",
+		[const_ilog2(UBLK_F_USER_COPY)] = "USER_COPY",
+		[const_ilog2(UBLK_F_ZONED)] = "ZONED",
+		[const_ilog2(UBLK_F_USER_RECOVERY_FAIL_IO)] = "RECOVERY_FAIL_IO",
+	};
+	struct ublk_dev *dev;
+	__u64 features = 0;
+	int ret;
+
+	dev = ublk_ctrl_init();
+	if (!dev) {
+		fprintf(stderr, "ublksrv_ctrl_init failed id\n");
+		return -EOPNOTSUPP;
+	}
+
+	ret = ublk_ctrl_get_features(dev, &features);
+	if (!ret) {
+		int i;
+
+		printf("ublk_drv features: 0x%llx\n", features);
+
+		for (i = 0; i < sizeof(features) * 8; i++) {
+			const char *feat;
+
+			if (!((1ULL << i)  & features))
+				continue;
+			if (i < sizeof(feat_map) / sizeof(feat_map[0]))
+				feat = feat_map[i];
+			else
+				feat = "unknown";
+			printf("\t%-20s: 0x%llx\n", feat, 1ULL << i);
+		}
+	}
+
+	return ret;
+}
+
+static int cmd_dev_help(char *exe)
+{
+	printf("%s add -t [null|loop] [-q nr_queues] [-d depth] [-n dev_id] [backfile1] [backfile2] ...\n", exe);
+	printf("\t default: nr_queues=2(max 4), depth=128(max 128), dev_id=-1(auto allocation)\n");
+	printf("%s del [-n dev_id] -a \n", exe);
+	printf("\t -a delete all devices -n delete specified device\n");
+	printf("%s list [-n dev_id] -a \n", exe);
+	printf("\t -a list all devices, -n list specified device, default -a \n");
+	printf("%s features\n", exe);
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	static const struct option longopts[] = {
+		{ "all",		0,	NULL, 'a' },
+		{ "type",		1,	NULL, 't' },
+		{ "number",		1,	NULL, 'n' },
+		{ "queues",		1,	NULL, 'q' },
+		{ "depth",		1,	NULL, 'd' },
+		{ "debug_mask",		1,	NULL,  0  },
+		{ "quiet",		0,	NULL,  0  },
+		{ "zero_copy",          0,      NULL, 'z' },
+		{ "foreground",		0,	NULL,  0  },
+		{ "chunk_size", 	1,	NULL,  0  },
+		{ 0, 0, 0, 0 }
+	};
+	int option_idx, opt;
+	const char *cmd = argv[1];
+	struct dev_ctx ctx = {
+		.queue_depth	=	128,
+		.nr_hw_queues	=	2,
+		.dev_id		=	-1,
+		.tgt_type	=	"unknown",
+		.chunk_size 	= 	65536, 	/* def chunk size is 64K */
+	};
+	int ret = -EINVAL, i;
+
+	if (argc == 1)
+		return ret;
+
+	optind = 2;
+	while ((opt = getopt_long(argc, argv, "t:n:d:q:az",
+				  longopts, &option_idx)) != -1) {
+		switch (opt) {
+		case 'a':
+			ctx.all = 1;
+			break;
+		case 'n':
+			ctx.dev_id = strtol(optarg, NULL, 10);
+			break;
+		case 't':
+			if (strlen(optarg) < sizeof(ctx.tgt_type))
+				strcpy(ctx.tgt_type, optarg);
+			break;
+		case 'q':
+			ctx.nr_hw_queues = strtol(optarg, NULL, 10);
+			break;
+		case 'd':
+			ctx.queue_depth = strtol(optarg, NULL, 10);
+			break;
+		case 'z':
+			ctx.flags |= UBLK_F_SUPPORT_ZERO_COPY | UBLK_F_USER_COPY;
+			break;
+		case 0:
+			if (!strcmp(longopts[option_idx].name, "debug_mask"))
+				ublk_dbg_mask = strtol(optarg, NULL, 16);
+			if (!strcmp(longopts[option_idx].name, "quiet"))
+				ublk_dbg_mask = 0;
+			if (!strcmp(longopts[option_idx].name, "foreground"))
+				ctx.fg = 1;
+			if (!strcmp(longopts[option_idx].name, "chunk_size"))
+				ctx.chunk_size = strtol(optarg, NULL, 10);
+		}
+	}
+
+	i = optind;
+	while (i < argc && ctx.nr_files < MAX_BACK_FILES) {
+		ctx.files[ctx.nr_files++] = argv[i++];
+	}
+
+	if (!strcmp(cmd, "add"))
+		ret = cmd_dev_add(&ctx);
+	else if (!strcmp(cmd, "del"))
+		ret = cmd_dev_del(&ctx);
+	else if (!strcmp(cmd, "list")) {
+		ctx.all = 1;
+		ret = cmd_dev_list(&ctx);
+	} else if (!strcmp(cmd, "help"))
+		ret = cmd_dev_help(argv[0]);
+	else if (!strcmp(cmd, "features"))
+		ret = cmd_dev_get_features();
+	else
+		cmd_dev_help(argv[0]);
+
+	return ret;
+}
diff --git a/tools/testing/selftests/ublk/kublk.h b/tools/testing/selftests/ublk/kublk.h
new file mode 100644
index 000000000000..f31a5c4d4143
--- /dev/null
+++ b/tools/testing/selftests/ublk/kublk.h
@@ -0,0 +1,370 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef KUBLK_INTERNAL_H
+#define KUBLK_INTERNAL_H
+
+#include <unistd.h>
+#include <stdlib.h>
+#include <assert.h>
+#include <stdio.h>
+#include <stdarg.h>
+#include <string.h>
+#include <pthread.h>
+#include <getopt.h>
+#include <limits.h>
+#include <poll.h>
+#include <fcntl.h>
+#include <sys/syscall.h>
+#include <sys/mman.h>
+#include <sys/ioctl.h>
+#include <sys/inotify.h>
+#include <sys/wait.h>
+#include <sys/eventfd.h>
+#include <sys/uio.h>
+#include <liburing.h>
+#include <linux/ublk_cmd.h>
+#include "ublk_dep.h"
+
+#define __maybe_unused __attribute__((unused))
+#define MAX_BACK_FILES   4
+#ifndef min
+#define min(a, b) ((a) < (b) ? (a) : (b))
+#endif
+
+/****************** part 1: libublk ********************/
+
+#define CTRL_DEV		"/dev/ublk-control"
+#define UBLKC_DEV		"/dev/ublkc"
+#define UBLKB_DEV		"/dev/ublkb"
+#define UBLK_CTRL_RING_DEPTH            32
+#define ERROR_EVTFD_DEVID 	-2
+
+/* queue idle timeout */
+#define UBLKSRV_IO_IDLE_SECS		20
+
+#define UBLK_IO_MAX_BYTES               (1 << 20)
+#define UBLK_MAX_QUEUES                 4
+#define UBLK_QUEUE_DEPTH                128
+
+#define UBLK_DBG_DEV            (1U << 0)
+#define UBLK_DBG_QUEUE          (1U << 1)
+#define UBLK_DBG_IO_CMD         (1U << 2)
+#define UBLK_DBG_IO             (1U << 3)
+#define UBLK_DBG_CTRL_CMD       (1U << 4)
+#define UBLK_LOG                (1U << 5)
+
+struct ublk_dev;
+struct ublk_queue;
+
+struct dev_ctx {
+	char tgt_type[16];
+	unsigned long flags;
+	unsigned nr_hw_queues;
+	unsigned queue_depth;
+	int dev_id;
+	int nr_files;
+	char *files[MAX_BACK_FILES];
+	unsigned int	logging:1;
+	unsigned int	all:1;
+	unsigned int	fg:1;
+
+	/* stripe */
+	unsigned int    chunk_size;
+
+	int _evtfd;
+};
+
+struct ublk_ctrl_cmd_data {
+	__u32 cmd_op;
+#define CTRL_CMD_HAS_DATA	1
+#define CTRL_CMD_HAS_BUF	2
+	__u32 flags;
+
+	__u64 data[2];
+	__u64 addr;
+	__u32 len;
+};
+
+struct ublk_io {
+	char *buf_addr;
+
+#define UBLKSRV_NEED_FETCH_RQ		(1UL << 0)
+#define UBLKSRV_NEED_COMMIT_RQ_COMP	(1UL << 1)
+#define UBLKSRV_IO_FREE			(1UL << 2)
+	unsigned short flags;
+	unsigned short refs;		/* used by target code only */
+
+	int result;
+
+	unsigned short tgt_ios;
+	void *private_data;
+};
+
+struct ublk_tgt_ops {
+	const char *name;
+	int (*init_tgt)(const struct dev_ctx *ctx, struct ublk_dev *);
+	void (*deinit_tgt)(struct ublk_dev *);
+
+	int (*queue_io)(struct ublk_queue *, int tag);
+	void (*tgt_io_done)(struct ublk_queue *,
+			int tag, const struct io_uring_cqe *);
+};
+
+struct ublk_tgt {
+	unsigned long dev_size;
+	unsigned int  sq_depth;
+	unsigned int  cq_depth;
+	const struct ublk_tgt_ops *ops;
+	struct ublk_params params;
+
+	int nr_backing_files;
+	unsigned long backing_file_size[MAX_BACK_FILES];
+	char backing_file[MAX_BACK_FILES][PATH_MAX];
+};
+
+struct ublk_queue {
+	int q_id;
+	int q_depth;
+	unsigned int cmd_inflight;
+	unsigned int io_inflight;
+	struct ublk_dev *dev;
+	const struct ublk_tgt_ops *tgt_ops;
+	char *io_cmd_buf;
+	struct io_uring ring;
+	struct ublk_io ios[UBLK_QUEUE_DEPTH];
+#define UBLKSRV_QUEUE_STOPPING	(1U << 0)
+#define UBLKSRV_QUEUE_IDLE	(1U << 1)
+#define UBLKSRV_NO_BUF		(1U << 2)
+#define UBLKSRV_ZC		(1U << 3)
+	unsigned state;
+	pid_t tid;
+	pthread_t thread;
+};
+
+struct ublk_dev {
+	struct ublk_tgt tgt;
+	struct ublksrv_ctrl_dev_info  dev_info;
+	struct ublk_queue q[UBLK_MAX_QUEUES];
+
+	int fds[MAX_BACK_FILES + 1];	/* fds[0] points to /dev/ublkcN */
+	int nr_fds;
+	int ctrl_fd;
+	struct io_uring ring;
+
+	void *private_data;
+};
+
+#ifndef offsetof
+#define offsetof(TYPE, MEMBER)  ((size_t)&((TYPE *)0)->MEMBER)
+#endif
+
+#ifndef container_of
+#define container_of(ptr, type, member) ({                              \
+	unsigned long __mptr = (unsigned long)(ptr);                    \
+	((type *)(__mptr - offsetof(type, member))); })
+#endif
+
+#define round_up(val, rnd) \
+	(((val) + ((rnd) - 1)) & ~((rnd) - 1))
+
+
+extern unsigned int ublk_dbg_mask;
+extern int ublk_queue_io_cmd(struct ublk_queue *q, struct ublk_io *io, unsigned tag);
+
+static inline int is_target_io(__u64 user_data)
+{
+	return (user_data & (1ULL << 63)) != 0;
+}
+
+static inline __u64 build_user_data(unsigned tag, unsigned op,
+		unsigned tgt_data, unsigned is_target_io)
+{
+	assert(!(tag >> 16) && !(op >> 8) && !(tgt_data >> 16));
+
+	return tag | (op << 16) | (tgt_data << 24) | (__u64)is_target_io << 63;
+}
+
+static inline unsigned int user_data_to_tag(__u64 user_data)
+{
+	return user_data & 0xffff;
+}
+
+static inline unsigned int user_data_to_op(__u64 user_data)
+{
+	return (user_data >> 16) & 0xff;
+}
+
+static inline unsigned int user_data_to_tgt_data(__u64 user_data)
+{
+	return (user_data >> 24) & 0xffff;
+}
+
+static inline unsigned short ublk_cmd_op_nr(unsigned int op)
+{
+	return _IOC_NR(op);
+}
+
+static inline void ublk_err(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vfprintf(stderr, fmt, ap);
+}
+
+static inline void ublk_log(const char *fmt, ...)
+{
+	if (ublk_dbg_mask & UBLK_LOG) {
+		va_list ap;
+
+		va_start(ap, fmt);
+		vfprintf(stdout, fmt, ap);
+	}
+}
+
+static inline void ublk_dbg(int level, const char *fmt, ...)
+{
+	if (level & ublk_dbg_mask) {
+		va_list ap;
+
+		va_start(ap, fmt);
+		vfprintf(stdout, fmt, ap);
+	}
+}
+
+static inline int ublk_queue_alloc_sqes(struct ublk_queue *q,
+		struct io_uring_sqe *sqes[], int nr_sqes)
+{
+	unsigned left = io_uring_sq_space_left(&q->ring);
+	int i;
+
+	if (left < nr_sqes)
+		io_uring_submit(&q->ring);
+
+	for (i = 0; i < nr_sqes; i++) {
+		sqes[i] = io_uring_get_sqe(&q->ring);
+		if (!sqes[i])
+			return i;
+	}
+
+	return nr_sqes;
+}
+
+static inline void io_uring_prep_buf_register(struct io_uring_sqe *sqe,
+		int dev_fd, int tag, int q_id, __u64 index)
+{
+	struct ublksrv_io_cmd *cmd = (struct ublksrv_io_cmd *)sqe->cmd;
+
+	io_uring_prep_read(sqe, dev_fd, 0, 0, 0);
+	sqe->opcode		= IORING_OP_URING_CMD;
+	sqe->flags		|= IOSQE_FIXED_FILE;
+	sqe->cmd_op		= UBLK_U_IO_REGISTER_IO_BUF;
+
+	cmd->tag		= tag;
+	cmd->addr		= index;
+	cmd->q_id		= q_id;
+}
+
+static inline void io_uring_prep_buf_unregister(struct io_uring_sqe *sqe,
+		int dev_fd, int tag, int q_id, __u64 index)
+{
+	struct ublksrv_io_cmd *cmd = (struct ublksrv_io_cmd *)sqe->cmd;
+
+	io_uring_prep_read(sqe, dev_fd, 0, 0, 0);
+	sqe->opcode		= IORING_OP_URING_CMD;
+	sqe->flags		|= IOSQE_FIXED_FILE;
+	sqe->cmd_op		= UBLK_U_IO_UNREGISTER_IO_BUF;
+
+	cmd->tag		= tag;
+	cmd->addr		= index;
+	cmd->q_id		= q_id;
+}
+
+static inline void *ublk_get_sqe_cmd(const struct io_uring_sqe *sqe)
+{
+	return (void *)&sqe->cmd;
+}
+
+static inline void ublk_set_io_res(struct ublk_queue *q, int tag, int res)
+{
+	q->ios[tag].result = res;
+}
+
+static inline int ublk_get_io_res(const struct ublk_queue *q, unsigned tag)
+{
+	return q->ios[tag].result;
+}
+
+static inline void ublk_mark_io_done(struct ublk_io *io, int res)
+{
+	io->flags |= (UBLKSRV_NEED_COMMIT_RQ_COMP | UBLKSRV_IO_FREE);
+	io->result = res;
+}
+
+static inline const struct ublksrv_io_desc *ublk_get_iod(const struct ublk_queue *q, int tag)
+{
+	return (struct ublksrv_io_desc *)&(q->io_cmd_buf[tag * sizeof(struct ublksrv_io_desc)]);
+}
+
+static inline void ublk_set_sqe_cmd_op(struct io_uring_sqe *sqe, __u32 cmd_op)
+{
+	__u32 *addr = (__u32 *)&sqe->off;
+
+	addr[0] = cmd_op;
+	addr[1] = 0;
+}
+
+static inline struct ublk_io *ublk_get_io(struct ublk_queue *q, unsigned tag)
+{
+	return &q->ios[tag];
+}
+
+static inline int ublk_complete_io(struct ublk_queue *q, unsigned tag, int res)
+{
+	struct ublk_io *io = &q->ios[tag];
+
+	ublk_mark_io_done(io, res);
+
+	return ublk_queue_io_cmd(q, io, tag);
+}
+
+static inline void ublk_queued_tgt_io(struct ublk_queue *q, unsigned tag, int queued)
+{
+	if (queued < 0)
+		ublk_complete_io(q, tag, queued);
+	else {
+		struct ublk_io *io = ublk_get_io(q, tag);
+
+		q->io_inflight += queued;
+		io->tgt_ios = queued;
+		io->result = 0;
+	}
+}
+
+static inline int ublk_completed_tgt_io(struct ublk_queue *q, unsigned tag)
+{
+	struct ublk_io *io = ublk_get_io(q, tag);
+
+	q->io_inflight--;
+
+	return --io->tgt_ios == 0;
+}
+
+static inline int ublk_queue_use_zc(const struct ublk_queue *q)
+{
+	return q->state & UBLKSRV_ZC;
+}
+
+extern const struct ublk_tgt_ops null_tgt_ops;
+extern const struct ublk_tgt_ops loop_tgt_ops;
+extern const struct ublk_tgt_ops stripe_tgt_ops;
+
+void backing_file_tgt_deinit(struct ublk_dev *dev);
+int backing_file_tgt_init(struct ublk_dev *dev);
+
+static inline unsigned int ilog2(unsigned int x)
+{
+	if (x == 0)
+		return 0;
+	return (sizeof(x) * 8 - 1) - __builtin_clz(x);
+}
+#endif
diff --git a/tools/testing/selftests/ublk/null.c b/tools/testing/selftests/ublk/null.c
new file mode 100644
index 000000000000..899875ff50fe
--- /dev/null
+++ b/tools/testing/selftests/ublk/null.c
@@ -0,0 +1,106 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include "kublk.h"
+
+#ifndef IORING_NOP_INJECT_RESULT
+#define IORING_NOP_INJECT_RESULT        (1U << 0)
+#endif
+
+#ifndef IORING_NOP_FIXED_BUFFER
+#define IORING_NOP_FIXED_BUFFER         (1U << 3)
+#endif
+
+static int ublk_null_tgt_init(const struct dev_ctx *ctx, struct ublk_dev *dev)
+{
+	const struct ublksrv_ctrl_dev_info *info = &dev->dev_info;
+	unsigned long dev_size = 250UL << 30;
+
+	dev->tgt.dev_size = dev_size;
+	dev->tgt.params = (struct ublk_params) {
+		.types = UBLK_PARAM_TYPE_BASIC,
+		.basic = {
+			.logical_bs_shift	= 9,
+			.physical_bs_shift	= 12,
+			.io_opt_shift		= 12,
+			.io_min_shift		= 9,
+			.max_sectors		= info->max_io_buf_bytes >> 9,
+			.dev_sectors		= dev_size >> 9,
+		},
+	};
+
+	if (info->flags & UBLK_F_SUPPORT_ZERO_COPY)
+		dev->tgt.sq_depth = dev->tgt.cq_depth = 2 * info->queue_depth;
+	return 0;
+}
+
+static int null_queue_zc_io(struct ublk_queue *q, int tag)
+{
+	const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag);
+	unsigned ublk_op = ublksrv_get_op(iod);
+	struct io_uring_sqe *sqe[3];
+
+	ublk_queue_alloc_sqes(q, sqe, 3);
+
+	io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, tag);
+	sqe[0]->user_data = build_user_data(tag,
+			ublk_cmd_op_nr(sqe[0]->cmd_op), 0, 1);
+	sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK;
+
+	io_uring_prep_nop(sqe[1]);
+	sqe[1]->buf_index = tag;
+	sqe[1]->flags |= IOSQE_FIXED_FILE | IOSQE_IO_HARDLINK;
+	sqe[1]->rw_flags = IORING_NOP_FIXED_BUFFER | IORING_NOP_INJECT_RESULT;
+	sqe[1]->len = iod->nr_sectors << 9; 	/* injected result */
+	sqe[1]->user_data = build_user_data(tag, ublk_op, 0, 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);
+
+	// buf register is marked as IOSQE_CQE_SKIP_SUCCESS
+	return 2;
+}
+
+static void ublk_null_io_done(struct ublk_queue *q, int tag,
+		const struct io_uring_cqe *cqe)
+{
+	unsigned op = user_data_to_op(cqe->user_data);
+	struct ublk_io *io = ublk_get_io(q, tag);
+
+	if (cqe->res < 0 || op != ublk_cmd_op_nr(UBLK_U_IO_UNREGISTER_IO_BUF)) {
+		if (!io->result)
+			io->result = cqe->res;
+		if (cqe->res < 0)
+			ublk_err("%s: io failed op %x user_data %lx\n",
+					__func__, op, cqe->user_data);
+	}
+
+	/* buffer register op is IOSQE_CQE_SKIP_SUCCESS */
+	if (op == ublk_cmd_op_nr(UBLK_U_IO_REGISTER_IO_BUF))
+		io->tgt_ios += 1;
+
+	if (ublk_completed_tgt_io(q, tag))
+		ublk_complete_io(q, tag, io->result);
+}
+
+static int ublk_null_queue_io(struct ublk_queue *q, int tag)
+{
+	const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag);
+	int zc = ublk_queue_use_zc(q);
+	int queued;
+
+	if (!zc) {
+		ublk_complete_io(q, tag, iod->nr_sectors << 9);
+		return 0;
+	}
+
+	queued = null_queue_zc_io(q, tag);
+	ublk_queued_tgt_io(q, tag, queued);
+	return 0;
+}
+
+const struct ublk_tgt_ops null_tgt_ops = {
+	.name = "null",
+	.init_tgt = ublk_null_tgt_init,
+	.queue_io = ublk_null_queue_io,
+	.tgt_io_done = ublk_null_io_done,
+};
diff --git a/tools/testing/selftests/ublk/stripe.c b/tools/testing/selftests/ublk/stripe.c
new file mode 100644
index 000000000000..98c564b12f3c
--- /dev/null
+++ b/tools/testing/selftests/ublk/stripe.c
@@ -0,0 +1,318 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "kublk.h"
+
+#define NR_STRIPE  MAX_BACK_FILES
+
+struct stripe_conf {
+	unsigned nr_files;
+	unsigned shift;
+};
+
+struct stripe {
+	loff_t 		start;
+	unsigned 	nr_sects;
+	int 		seq;
+
+	struct iovec 	*vec;
+	unsigned 	nr_vec;
+	unsigned 	cap;
+};
+
+struct stripe_array {
+	struct stripe 	s[NR_STRIPE];
+	unsigned 	nr;
+	struct iovec 	_vec[];
+};
+
+static inline const struct stripe_conf *get_chunk_shift(const struct ublk_queue *q)
+{
+	return (struct stripe_conf *)q->dev->private_data;
+}
+
+static inline unsigned calculate_nr_vec(const struct stripe_conf *conf,
+		const struct ublksrv_io_desc *iod)
+{
+	const unsigned shift = conf->shift - 9;
+	const unsigned unit_sects = conf->nr_files << shift;
+	loff_t start = iod->start_sector;
+	loff_t end = start + iod->nr_sectors;
+
+	return (end / unit_sects) - (start / unit_sects) + 1;
+}
+
+static struct stripe_array *alloc_stripe_array(const struct stripe_conf *conf,
+		const struct ublksrv_io_desc *iod)
+{
+	unsigned nr_vecs = calculate_nr_vec(conf, iod);
+	unsigned total = nr_vecs * conf->nr_files;
+	struct stripe_array *s;
+	int i;
+
+	s = malloc(sizeof(*s) + total * sizeof(struct iovec));
+
+	s->nr = 0;
+	for (i = 0; i < conf->nr_files; i++) {
+		struct stripe *t = &s->s[i];
+
+		t->nr_vec = 0;
+		t->vec = &s->_vec[i * nr_vecs];
+		t->nr_sects = 0;
+		t->cap = nr_vecs;
+	}
+
+	return s;
+}
+
+static void free_stripe_array(struct stripe_array *s)
+{
+	free(s);
+}
+
+static void calculate_stripe_array(const struct stripe_conf *conf,
+		const struct ublksrv_io_desc *iod, struct stripe_array *s)
+{
+	const unsigned shift = conf->shift - 9;
+	const unsigned chunk_sects = 1 << shift;
+	const unsigned unit_sects = conf->nr_files << shift;
+	off64_t start = iod->start_sector;
+	off64_t end = start + iod->nr_sectors;
+	unsigned long done = 0;
+	unsigned idx = 0;
+
+	while (start < end) {
+		unsigned nr_sects = chunk_sects - (start & (chunk_sects - 1));
+		loff_t unit_off = (start / unit_sects) * unit_sects;
+		unsigned seq = (start - unit_off) >> shift;
+		struct stripe *this = &s->s[idx];
+		loff_t stripe_off = (unit_off / conf->nr_files) +
+			(start & (chunk_sects - 1));
+
+		if (nr_sects > end - start)
+			nr_sects = end - start;
+		if (this->nr_sects == 0) {
+			this->nr_sects = nr_sects;
+			this->start = stripe_off;
+			this->seq = seq;
+			s->nr += 1;
+		} else {
+			assert(seq == this->seq);
+			assert(this->start + this->nr_sects == stripe_off);
+			this->nr_sects += nr_sects;
+		}
+
+		assert(this->nr_vec < this->cap);
+		this->vec[this->nr_vec].iov_base = (void *)(iod->addr + done);
+		this->vec[this->nr_vec++].iov_len = nr_sects << 9;
+
+		start += nr_sects;
+		done += nr_sects << 9;
+		idx = (idx + 1) % conf->nr_files;
+	}
+}
+
+static inline enum io_uring_op stripe_to_uring_op(const struct ublksrv_io_desc *iod)
+{
+	unsigned ublk_op = ublksrv_get_op(iod);
+
+	if (ublk_op == UBLK_IO_OP_READ)
+		return IORING_OP_READV;
+	else if (ublk_op == UBLK_IO_OP_WRITE)
+		return IORING_OP_WRITEV;
+	assert(0);
+}
+
+static int stripe_queue_tgt_rw_io(struct ublk_queue *q, const struct ublksrv_io_desc *iod, int tag)
+{
+	const struct stripe_conf *conf = get_chunk_shift(q);
+	enum io_uring_op op = stripe_to_uring_op(iod);
+	struct io_uring_sqe *sqe[NR_STRIPE];
+	struct stripe_array *s = alloc_stripe_array(conf, iod);
+	struct ublk_io *io = ublk_get_io(q, tag);
+	int i;
+
+	io->private_data = s;
+	calculate_stripe_array(conf, iod, s);
+
+	ublk_queue_alloc_sqes(q, sqe, s->nr);
+	for (i = 0; i < s->nr; i++) {
+		struct stripe *t = &s->s[i];
+
+		io_uring_prep_rw(op, sqe[i],
+				t->seq + 1,
+				(void *)t->vec,
+				t->nr_vec,
+				t->start << 9);
+		io_uring_sqe_set_flags(sqe[i], IOSQE_FIXED_FILE);
+		/* bit63 marks us as tgt io */
+		sqe[i]->user_data = build_user_data(tag, ublksrv_get_op(iod), i, 1);
+	}
+	return s->nr;
+}
+
+static int handle_flush(struct ublk_queue *q, const struct ublksrv_io_desc *iod, int tag)
+{
+	const struct stripe_conf *conf = get_chunk_shift(q);
+	struct io_uring_sqe *sqe[NR_STRIPE];
+	int i;
+
+	ublk_queue_alloc_sqes(q, sqe, conf->nr_files);
+	for (i = 0; i < conf->nr_files; i++) {
+		io_uring_prep_fsync(sqe[i], i + 1, IORING_FSYNC_DATASYNC);
+		io_uring_sqe_set_flags(sqe[i], IOSQE_FIXED_FILE);
+		sqe[i]->user_data = build_user_data(tag, UBLK_IO_OP_FLUSH, 0, 1);
+	}
+	return conf->nr_files;
+}
+
+static int stripe_queue_tgt_io(struct ublk_queue *q, int tag)
+{
+	const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag);
+	unsigned ublk_op = ublksrv_get_op(iod);
+	int ret = 0;
+
+	switch (ublk_op) {
+	case UBLK_IO_OP_FLUSH:
+		ret = handle_flush(q, iod, tag);
+		break;
+	case UBLK_IO_OP_WRITE_ZEROES:
+	case UBLK_IO_OP_DISCARD:
+		ret = -ENOTSUP;
+		break;
+	case UBLK_IO_OP_READ:
+	case UBLK_IO_OP_WRITE:
+		ret = stripe_queue_tgt_rw_io(q, iod, tag);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+	ublk_dbg(UBLK_DBG_IO, "%s: tag %d ublk io %x %llx %u ret %d\n", __func__, tag,
+			iod->op_flags, iod->start_sector, iod->nr_sectors << 9, ret);
+	return ret;
+}
+
+static int ublk_stripe_queue_io(struct ublk_queue *q, int tag)
+{
+	int queued = stripe_queue_tgt_io(q, tag);
+
+	ublk_queued_tgt_io(q, tag, queued);
+	return 0;
+}
+
+static void ublk_stripe_io_done(struct ublk_queue *q, int tag,
+		const struct io_uring_cqe *cqe)
+{
+	const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag);
+	unsigned op = user_data_to_op(cqe->user_data);
+	struct ublk_io *io = ublk_get_io(q, tag);
+	int res = cqe->res;
+
+	if (res < 0) {
+		if (!io->result)
+			io->result = res;
+		ublk_err("%s: io failure %d tag %u\n", __func__, res, tag);
+	}
+
+	/* fail short READ/WRITE simply */
+	if (op == UBLK_IO_OP_READ || op == UBLK_IO_OP_WRITE) {
+		unsigned seq = user_data_to_tgt_data(cqe->user_data);
+		struct stripe_array *s = io->private_data;
+
+		if (res < s->s[seq].vec->iov_len)
+			io->result = -EIO;
+	}
+
+	if (ublk_completed_tgt_io(q, tag)) {
+		int res = io->result;
+
+		if (!res)
+			res = iod->nr_sectors << 9;
+
+		ublk_complete_io(q, tag, res);
+
+		free_stripe_array(io->private_data);
+		io->private_data = NULL;
+	}
+}
+
+static int ublk_stripe_tgt_init(const struct dev_ctx *ctx, struct ublk_dev *dev)
+{
+	struct ublk_params p = {
+		.types = UBLK_PARAM_TYPE_BASIC,
+		.basic = {
+			.attrs = UBLK_ATTR_VOLATILE_CACHE,
+			.logical_bs_shift	= 9,
+			.physical_bs_shift	= 12,
+			.io_opt_shift	= 12,
+			.io_min_shift	= 9,
+			.max_sectors = dev->dev_info.max_io_buf_bytes >> 9,
+		},
+	};
+	unsigned chunk_size = ctx->chunk_size;
+	struct stripe_conf *conf;
+	unsigned chunk_shift;
+	loff_t bytes = 0;
+	int ret, i;
+
+	if ((chunk_size & (chunk_size - 1)) || !chunk_size) {
+		ublk_err("invalid chunk size %u\n", chunk_size);
+		return -EINVAL;
+	}
+
+	if (chunk_size < 4096 || chunk_size > 512 * 1024) {
+		ublk_err("invalid chunk size %u\n", chunk_size);
+		return -EINVAL;
+	}
+
+	chunk_shift = ilog2(chunk_size);
+
+	ret = backing_file_tgt_init(dev);
+	if (ret)
+		return ret;
+
+	if (!dev->tgt.nr_backing_files || dev->tgt.nr_backing_files > NR_STRIPE)
+		return -EINVAL;
+
+	assert(dev->nr_fds == dev->tgt.nr_backing_files + 1);
+
+	for (i = 0; i < dev->tgt.nr_backing_files; i++)
+		dev->tgt.backing_file_size[i] &= ~((1 << chunk_shift) - 1);
+
+	for (i = 0; i < dev->tgt.nr_backing_files; i++) {
+		unsigned long size = dev->tgt.backing_file_size[i];
+
+		if (size != dev->tgt.backing_file_size[0])
+			return -EINVAL;
+		bytes += size;
+	}
+
+	conf = malloc(sizeof(*conf));
+	conf->shift = chunk_shift;
+	conf->nr_files = dev->tgt.nr_backing_files;
+
+	dev->private_data = conf;
+	dev->tgt.dev_size = bytes;
+	p.basic.dev_sectors = bytes >> 9;
+	dev->tgt.params = p;
+	dev->tgt.sq_depth = dev->dev_info.queue_depth * conf->nr_files;
+	dev->tgt.cq_depth = dev->dev_info.queue_depth * conf->nr_files;
+
+	printf("%s: shift %u files %u\n", __func__, conf->shift, conf->nr_files);
+
+	return 0;
+}
+
+static void ublk_stripe_tgt_deinit(struct ublk_dev *dev)
+{
+	free(dev->private_data);
+	backing_file_tgt_deinit(dev);
+}
+
+const struct ublk_tgt_ops stripe_tgt_ops = {
+	.name = "stripe",
+	.init_tgt = ublk_stripe_tgt_init,
+	.deinit_tgt = ublk_stripe_tgt_deinit,
+	.queue_io = ublk_stripe_queue_io,
+	.tgt_io_done = ublk_stripe_io_done,
+};
diff --git a/tools/testing/selftests/ublk/test_common.sh b/tools/testing/selftests/ublk/test_common.sh
new file mode 100755
index 000000000000..75f54ac6b1c4
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_common.sh
@@ -0,0 +1,246 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+UBLK_SKIP_CODE=4
+
+_have_program() {
+	if command -v "$1" >/dev/null 2>&1; then
+		return 0
+	fi
+	return 1
+}
+
+_get_disk_dev_t() {
+	local dev_id=$1
+	local dev
+	local major
+	local minor
+
+	dev=/dev/ublkb"${dev_id}"
+	major=$(stat -c '%Hr' "$dev")
+	minor=$(stat -c '%Lr' "$dev")
+
+	echo $(( (major & 0xfff) << 20 | (minor & 0xfffff) ))
+}
+
+_create_backfile() {
+	local my_size=$1
+	local my_file
+
+	my_file=$(mktemp ublk_file_"${my_size}"_XXXXX)
+	truncate -s "${my_size}" "${my_file}"
+	echo "$my_file"
+}
+
+_remove_backfile() {
+	local file=$1
+
+	[ -f "$file" ] && rm -f "$file"
+}
+
+_create_tmp_dir() {
+	local my_file;
+
+	my_file=$(mktemp -d ublk_dir_XXXXX)
+	echo "$my_file"
+}
+
+_remove_tmp_dir() {
+	local dir=$1
+
+	[ -d "$dir" ] && rmdir "$dir"
+}
+
+_mkfs_mount_test()
+{
+	local dev=$1
+	local err_code=0
+	local mnt_dir;
+
+	mnt_dir=$(_create_tmp_dir)
+	mkfs.ext4 -F "$dev" > /dev/null 2>&1
+	err_code=$?
+	if [ $err_code -ne 0 ]; then
+		return $err_code
+	fi
+
+	mount -t ext4 "$dev" "$mnt_dir" > /dev/null 2>&1
+	umount "$dev"
+	err_code=$?
+	_remove_tmp_dir "$mnt_dir"
+	if [ $err_code -ne 0 ]; then
+		return $err_code
+	fi
+}
+
+_check_root() {
+	local ksft_skip=4
+
+	if [ $UID != 0 ]; then
+		echo please run this as root >&2
+		exit $ksft_skip
+	fi
+}
+
+_remove_ublk_devices() {
+	${UBLK_PROG} del -a
+	modprobe -r ublk_drv > /dev/null 2>&1
+}
+
+_get_ublk_dev_state() {
+	${UBLK_PROG} list -n "$1" | grep "state" | awk '{print $11}'
+}
+
+_get_ublk_daemon_pid() {
+	${UBLK_PROG} list -n "$1" | grep "pid" | awk '{print $7}'
+}
+
+_prep_test() {
+	_check_root
+	local type=$1
+	shift 1
+	modprobe ublk_drv > /dev/null 2>&1
+	[ "$UBLK_TEST_QUIET" -eq 0 ] && echo "ublk $type: $*"
+}
+
+_remove_test_files()
+{
+	local files=$*
+
+	for file in ${files}; do
+		[ -f "${file}" ] && rm -f "${file}"
+	done
+}
+
+_show_result()
+{
+	if [ "$UBLK_TEST_SHOW_RESULT" -ne 0 ]; then
+		if [ "$2" -eq 0 ]; then
+			echo "$1 : [PASS]"
+		elif [ "$2" -eq 4 ]; then
+			echo "$1 : [SKIP]"
+		else
+			echo "$1 : [FAIL]"
+		fi
+	fi
+	[ "$2" -ne 0 ] && exit "$2"
+	return 0
+}
+
+# don't call from sub-shell, otherwise can't exit
+_check_add_dev()
+{
+	local tid=$1
+	local code=$2
+	shift 2
+	if [ "${code}" -ne 0 ]; then
+		_remove_test_files "$@"
+		_show_result "${tid}" "${code}"
+	fi
+}
+
+_cleanup_test() {
+	"${UBLK_PROG}" del -a
+	rm -f "$UBLK_TMP"
+}
+
+_have_feature()
+{
+	if  $UBLK_PROG "features" | grep "$1" > /dev/null 2>&1; then
+		return 0
+	fi
+	return 1
+}
+
+_add_ublk_dev() {
+	local kublk_temp;
+	local dev_id;
+
+	if [ ! -c /dev/ublk-control ]; then
+		return ${UBLK_SKIP_CODE}
+	fi
+	if echo "$@" | grep -q "\-z"; then
+		if ! _have_feature "ZERO_COPY"; then
+			return ${UBLK_SKIP_CODE}
+		fi
+	fi
+
+	kublk_temp=$(mktemp /tmp/kublk-XXXXXX)
+	if ! "${UBLK_PROG}" add "$@" > "${kublk_temp}" 2>&1; then
+		echo "fail to add ublk dev $*"
+		rm -f "${kublk_temp}"
+		return 255
+	fi
+
+	dev_id=$(grep "dev id" "${kublk_temp}" | awk -F '[ :]' '{print $3}')
+	udevadm settle
+	rm -f "${kublk_temp}"
+	echo "${dev_id}"
+}
+
+# kill the ublk daemon and return ublk device state
+__ublk_kill_daemon()
+{
+	local dev_id=$1
+	local exp_state=$2
+	local daemon_pid
+	local state
+
+	daemon_pid=$(_get_ublk_daemon_pid "${dev_id}")
+	state=$(_get_ublk_dev_state "${dev_id}")
+
+	for ((j=0;j<50;j++)); do
+		[ "$state" == "$exp_state" ] && break
+		kill -9 "$daemon_pid" > /dev/null 2>&1
+		sleep 1
+		state=$(_get_ublk_dev_state "${dev_id}")
+	done
+	echo "$state"
+}
+
+__remove_ublk_dev_return() {
+	local dev_id=$1
+
+	${UBLK_PROG} del -n "${dev_id}"
+	local res=$?
+	udevadm settle
+	return ${res}
+}
+
+__run_io_and_remove()
+{
+	local dev_id=$1
+	local size=$2
+	local kill_server=$3
+
+	fio --name=job1 --filename=/dev/ublkb"${dev_id}" --ioengine=libaio \
+		--rw=readwrite --iodepth=64 --size="${size}" --numjobs=4 \
+		--runtime=20 --time_based > /dev/null 2>&1 &
+	sleep 2
+	if [ "${kill_server}" = "yes" ]; then
+		local state
+		state=$(__ublk_kill_daemon "${dev_id}" "DEAD")
+		if [ "$state" != "DEAD" ]; then
+			echo "device isn't dead($state) after killing daemon"
+			return 255
+		fi
+	fi
+	if ! __remove_ublk_dev_return "${dev_id}"; then
+		echo "delete dev ${dev_id} failed"
+		return 255
+	fi
+	wait
+}
+
+_ublk_test_top_dir()
+{
+	cd "$(dirname "$0")" && pwd
+}
+
+UBLK_TMP=$(mktemp ublk_test_XXXXX)
+UBLK_PROG=$(_ublk_test_top_dir)/kublk
+UBLK_TEST_QUIET=1
+UBLK_TEST_SHOW_RESULT=1
+export UBLK_PROG
+export UBLK_TEST_QUIET
+export UBLK_TEST_SHOW_RESULT
diff --git a/tools/testing/selftests/ublk/test_generic_01.sh b/tools/testing/selftests/ublk/test_generic_01.sh
new file mode 100755
index 000000000000..9227a208ba53
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_01.sh
@@ -0,0 +1,44 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_01"
+ERR_CODE=0
+
+if ! _have_program bpftrace; then
+	exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "null" "sequential io order"
+
+dev_id=$(_add_ublk_dev -t null)
+_check_add_dev $TID $?
+
+dev_t=$(_get_disk_dev_t "$dev_id")
+bpftrace trace/seq_io.bt "$dev_t" "W" 1 > "$UBLK_TMP" 2>&1 &
+btrace_pid=$!
+sleep 2
+
+if ! kill -0 "$btrace_pid" > /dev/null 2>&1; then
+	_cleanup_test "null"
+	exit "$UBLK_SKIP_CODE"
+fi
+
+# run fio over this ublk disk
+fio --name=write_seq \
+    --filename=/dev/ublkb"${dev_id}" \
+    --ioengine=libaio --iodepth=16 \
+    --rw=write \
+    --size=512M \
+    --direct=1 \
+    --bs=4k > /dev/null 2>&1
+ERR_CODE=$?
+kill "$btrace_pid"
+wait
+if grep -q "io_out_of_order" "$UBLK_TMP"; then
+	cat "$UBLK_TMP"
+	ERR_CODE=255
+fi
+_cleanup_test "null"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_01.sh b/tools/testing/selftests/ublk/test_loop_01.sh
new file mode 100755
index 000000000000..c882d2a08e13
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_loop_01.sh
@@ -0,0 +1,32 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="loop_01"
+ERR_CODE=0
+
+_prep_test "loop" "write and verify test"
+
+backfile_0=$(_create_backfile 256M)
+
+dev_id=$(_add_ublk_dev -t loop "$backfile_0")
+_check_add_dev $TID $? "${backfile_0}"
+
+# run fio over the ublk disk
+fio --name=write_and_verify \
+    --filename=/dev/ublkb"${dev_id}" \
+    --ioengine=libaio --iodepth=16 \
+    --rw=write \
+    --size=256M \
+    --direct=1 \
+    --verify=crc32c \
+    --do_verify=1 \
+    --bs=4k > /dev/null 2>&1
+ERR_CODE=$?
+
+_cleanup_test "loop"
+
+_remove_backfile "$backfile_0"
+
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_02.sh b/tools/testing/selftests/ublk/test_loop_02.sh
new file mode 100755
index 000000000000..03863d825e07
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_loop_02.sh
@@ -0,0 +1,22 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="loop_02"
+ERR_CODE=0
+
+_prep_test "loop" "mkfs & mount & umount"
+
+backfile_0=$(_create_backfile 256M)
+dev_id=$(_add_ublk_dev -t loop "$backfile_0")
+_check_add_dev $TID $? "$backfile_0"
+
+_mkfs_mount_test /dev/ublkb"${dev_id}"
+ERR_CODE=$?
+
+_cleanup_test "loop"
+
+_remove_backfile "$backfile_0"
+
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_03.sh b/tools/testing/selftests/ublk/test_loop_03.sh
new file mode 100755
index 000000000000..269c96787d7d
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_loop_03.sh
@@ -0,0 +1,31 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="loop_03"
+ERR_CODE=0
+
+_prep_test "loop" "write and verify over zero copy"
+
+backfile_0=$(_create_backfile 256M)
+dev_id=$(_add_ublk_dev -t loop -z "$backfile_0")
+_check_add_dev $TID $? "$backfile_0"
+
+# run fio over the ublk disk
+fio --name=write_and_verify \
+    --filename=/dev/ublkb"${dev_id}" \
+    --ioengine=libaio --iodepth=64 \
+    --rw=write \
+    --size=256M \
+    --direct=1 \
+    --verify=crc32c \
+    --do_verify=1 \
+    --bs=4k > /dev/null 2>&1
+ERR_CODE=$?
+
+_cleanup_test "loop"
+
+_remove_backfile "$backfile_0"
+
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_04.sh b/tools/testing/selftests/ublk/test_loop_04.sh
new file mode 100755
index 000000000000..1435422c38ec
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_loop_04.sh
@@ -0,0 +1,22 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="loop_04"
+ERR_CODE=0
+
+_prep_test "loop" "mkfs & mount & umount with zero copy"
+
+backfile_0=$(_create_backfile 256M)
+dev_id=$(_add_ublk_dev -t loop -z "$backfile_0")
+_check_add_dev $TID $? "$backfile_0"
+
+_mkfs_mount_test /dev/ublkb"${dev_id}"
+ERR_CODE=$?
+
+_cleanup_test "loop"
+
+_remove_backfile "$backfile_0"
+
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_null_01.sh b/tools/testing/selftests/ublk/test_null_01.sh
new file mode 100755
index 000000000000..a34203f72668
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_null_01.sh
@@ -0,0 +1,20 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="null_01"
+ERR_CODE=0
+
+_prep_test "null" "basic IO test"
+
+dev_id=$(_add_ublk_dev -t null)
+_check_add_dev $TID $?
+
+# run fio over the two disks
+fio --name=job1 --filename=/dev/ublkb"${dev_id}" --ioengine=libaio --rw=readwrite --iodepth=32 --size=256M > /dev/null 2>&1
+ERR_CODE=$?
+
+_cleanup_test "null"
+
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_null_02.sh b/tools/testing/selftests/ublk/test_null_02.sh
new file mode 100755
index 000000000000..5633ca876655
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_null_02.sh
@@ -0,0 +1,20 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="null_02"
+ERR_CODE=0
+
+_prep_test "null" "basic IO test with zero copy"
+
+dev_id=$(_add_ublk_dev -t null -z)
+_check_add_dev $TID $?
+
+# run fio over the two disks
+fio --name=job1 --filename=/dev/ublkb"${dev_id}" --ioengine=libaio --rw=readwrite --iodepth=32 --size=256M > /dev/null 2>&1
+ERR_CODE=$?
+
+_cleanup_test "null"
+
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_01.sh b/tools/testing/selftests/ublk/test_stress_01.sh
new file mode 100755
index 000000000000..7177f6c57bc5
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_stress_01.sh
@@ -0,0 +1,47 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+TID="stress_01"
+ERR_CODE=0
+DEV_ID=-1
+
+ublk_io_and_remove()
+{
+	local size=$1
+	shift 1
+	local backfile=""
+	if echo "$@" | grep -q "loop"; then
+		backfile=${*: -1}
+	fi
+	DEV_ID=$(_add_ublk_dev "$@")
+	_check_add_dev $TID $? "${backfile}"
+
+	[ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs. remove device(ublk add $*)"
+	if ! __run_io_and_remove "${DEV_ID}" "${size}" "no"; then
+		echo "/dev/ublkc${DEV_ID} isn't removed"
+		_remove_backfile "${backfile}"
+		exit 255
+	fi
+}
+
+_prep_test "stress" "run IO and remove device"
+
+ublk_io_and_remove 8G -t null
+ERR_CODE=$?
+if [ ${ERR_CODE} -ne 0 ]; then
+	_show_result $TID $ERR_CODE
+fi
+
+BACK_FILE=$(_create_backfile 256M)
+ublk_io_and_remove 256M -t loop "${BACK_FILE}"
+ERR_CODE=$?
+if [ ${ERR_CODE} -ne 0 ]; then
+	_show_result $TID $ERR_CODE
+fi
+
+ublk_io_and_remove 256M -t loop -z "${BACK_FILE}"
+ERR_CODE=$?
+_cleanup_test "stress"
+_remove_backfile "${BACK_FILE}"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_02.sh b/tools/testing/selftests/ublk/test_stress_02.sh
new file mode 100755
index 000000000000..2a8e60579a06
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_stress_02.sh
@@ -0,0 +1,47 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+TID="stress_02"
+ERR_CODE=0
+DEV_ID=-1
+
+ublk_io_and_kill_daemon()
+{
+	local size=$1
+	shift 1
+	local backfile=""
+	if echo "$@" | grep -q "loop"; then
+		backfile=${*: -1}
+	fi
+	DEV_ID=$(_add_ublk_dev "$@")
+	_check_add_dev $TID $? "${backfile}"
+
+	[ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs kill ublk server(ublk add $*)"
+	if ! __run_io_and_remove "${DEV_ID}" "${size}" "yes"; then
+		echo "/dev/ublkc${DEV_ID} isn't removed res ${res}"
+		_remove_backfile "${backfile}"
+		exit 255
+	fi
+}
+
+_prep_test "stress" "run IO and kill ublk server"
+
+ublk_io_and_kill_daemon 8G -t null
+ERR_CODE=$?
+if [ ${ERR_CODE} -ne 0 ]; then
+	_show_result $TID $ERR_CODE
+fi
+
+BACK_FILE=$(_create_backfile 256M)
+ublk_io_and_kill_daemon 256M -t loop "${BACK_FILE}"
+ERR_CODE=$?
+if [ ${ERR_CODE} -ne 0 ]; then
+	_show_result $TID $ERR_CODE
+fi
+
+ublk_io_and_kill_daemon 256M -t loop -z "${BACK_FILE}"
+ERR_CODE=$?
+_cleanup_test "stress"
+_remove_backfile "${BACK_FILE}"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stripe_01.sh b/tools/testing/selftests/ublk/test_stripe_01.sh
new file mode 100755
index 000000000000..c01f3dc325ab
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_stripe_01.sh
@@ -0,0 +1,34 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="stripe_01"
+ERR_CODE=0
+
+_prep_test "stripe" "write and verify test"
+
+backfile_0=$(_create_backfile 256M)
+backfile_1=$(_create_backfile 256M)
+
+dev_id=$(_add_ublk_dev -t stripe "$backfile_0" "$backfile_1")
+_check_add_dev $TID $? "${backfile_0}"
+
+# run fio over the ublk disk
+fio --name=write_and_verify \
+    --filename=/dev/ublkb"${dev_id}" \
+    --ioengine=libaio --iodepth=32 \
+    --rw=write \
+    --size=512M \
+    --direct=1 \
+    --verify=crc32c \
+    --do_verify=1 \
+    --bs=4k > /dev/null 2>&1
+ERR_CODE=$?
+
+_cleanup_test "stripe"
+
+_remove_backfile "$backfile_0"
+_remove_backfile "$backfile_1"
+
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stripe_02.sh b/tools/testing/selftests/ublk/test_stripe_02.sh
new file mode 100755
index 000000000000..e8a45fa82dde
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_stripe_02.sh
@@ -0,0 +1,24 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="stripe_02"
+ERR_CODE=0
+
+_prep_test "stripe" "mkfs & mount & umount"
+
+backfile_0=$(_create_backfile 256M)
+backfile_1=$(_create_backfile 256M)
+dev_id=$(_add_ublk_dev -t stripe "$backfile_0" "$backfile_1")
+_check_add_dev $TID $? "$backfile_0" "$backfile_1"
+
+_mkfs_mount_test /dev/ublkb"${dev_id}"
+ERR_CODE=$?
+
+_cleanup_test "stripe"
+
+_remove_backfile "$backfile_0"
+_remove_backfile "$backfile_1"
+
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/trace/seq_io.bt b/tools/testing/selftests/ublk/trace/seq_io.bt
new file mode 100644
index 000000000000..272ac54c9d5f
--- /dev/null
+++ b/tools/testing/selftests/ublk/trace/seq_io.bt
@@ -0,0 +1,25 @@
+/*
+	$1: 	dev_t
+	$2: 	RWBS
+	$3:     strlen($2)
+*/
+BEGIN {
+	@last_rw[$1, str($2)] = 0;
+}
+tracepoint:block:block_rq_complete
+{
+	$dev = $1;
+	if ((int64)args.dev == $1 && !strncmp(args.rwbs, str($2), $3)) {
+		$last = @last_rw[$dev, str($2)];
+		if ((uint64)args.sector != $last) {
+			printf("io_out_of_order: exp %llu actual %llu\n",
+				args.sector, $last);
+		}
+		@last_rw[$dev, str($2)] = (args.sector + args.nr_sector);
+	}
+	@ios = count();
+}
+
+END {
+	clear(@last_rw);
+}
diff --git a/tools/testing/selftests/ublk/ublk_dep.h b/tools/testing/selftests/ublk/ublk_dep.h
new file mode 100644
index 000000000000..f68fa7eac939
--- /dev/null
+++ b/tools/testing/selftests/ublk/ublk_dep.h
@@ -0,0 +1,18 @@
+#ifndef UBLK_DEP_H
+#define UBLK_DEP_H
+
+#ifndef UBLK_U_IO_REGISTER_IO_BUF
+#define	UBLK_U_IO_REGISTER_IO_BUF	\
+	_IOWR('u', 0x23, struct ublksrv_io_cmd)
+#define	UBLK_U_IO_UNREGISTER_IO_BUF	\
+	_IOWR('u', 0x24, struct ublksrv_io_cmd)
+#endif
+
+#ifndef UBLK_F_USER_RECOVERY_FAIL_IO
+#define UBLK_F_USER_RECOVERY_FAIL_IO (1ULL << 9)
+#endif
+
+#ifndef UBLK_F_ZONED
+#define UBLK_F_ZONED (1ULL << 8)
+#endif
+#endif