1 files changed, 369 insertions, 129 deletions

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 33d3298a0da1..1c823750c95a 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -43,6 +43,7 @@
 #include <asm/page.h>
 #include <linux/task_work.h>
 #include <linux/namei.h>
+#include <linux/kref.h>
 #include <uapi/linux/ublk_cmd.h>
 
 #define UBLK_MINORS		(1U << MINORBITS)
@@ -54,7 +55,8 @@
 		| UBLK_F_USER_RECOVERY \
 		| UBLK_F_USER_RECOVERY_REISSUE \
 		| UBLK_F_UNPRIVILEGED_DEV \
-		| UBLK_F_CMD_IOCTL_ENCODE)
+		| UBLK_F_CMD_IOCTL_ENCODE \
+		| UBLK_F_USER_COPY)
 
 /* All UBLK_PARAM_TYPE_* should be included here */
 #define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | \
@@ -62,7 +64,8 @@
 
 struct ublk_rq_data {
 	struct llist_node node;
-	struct callback_head work;
+
+	struct kref ref;
 };
 
 struct ublk_uring_cmd_pdu {
@@ -182,8 +185,13 @@ struct ublk_params_header {
 	__u32	types;
 };
 
+static inline void __ublk_complete_rq(struct request *req);
+static void ublk_complete_rq(struct kref *ref);
+
 static dev_t ublk_chr_devt;
-static struct class *ublk_chr_class;
+static const struct class ublk_chr_class = {
+	.name = "ublk-char",
+};
 
 static DEFINE_IDR(ublk_index_idr);
 static DEFINE_SPINLOCK(ublk_idr_lock);
@@ -202,6 +210,23 @@ static unsigned int ublks_added;	/* protected by ublk_ctl_mutex */
 
 static struct miscdevice ublk_misc;
 
+static inline unsigned ublk_pos_to_hwq(loff_t pos)
+{
+	return ((pos - UBLKSRV_IO_BUF_OFFSET) >> UBLK_QID_OFF) &
+		UBLK_QID_BITS_MASK;
+}
+
+static inline unsigned ublk_pos_to_buf_off(loff_t pos)
+{
+	return (pos - UBLKSRV_IO_BUF_OFFSET) & UBLK_IO_BUF_BITS_MASK;
+}
+
+static inline unsigned ublk_pos_to_tag(loff_t pos)
+{
+	return ((pos - UBLKSRV_IO_BUF_OFFSET) >> UBLK_TAG_OFF) &
+		UBLK_TAG_BITS_MASK;
+}
+
 static void ublk_dev_param_basic_apply(struct ublk_device *ub)
 {
 	struct request_queue *q = ub->ub_disk->queue;
@@ -290,12 +315,52 @@ static int ublk_apply_params(struct ublk_device *ub)
 	return 0;
 }
 
-static inline bool ublk_can_use_task_work(const struct ublk_queue *ubq)
+static inline bool ublk_support_user_copy(const struct ublk_queue *ubq)
 {
-	if (IS_BUILTIN(CONFIG_BLK_DEV_UBLK) &&
-			!(ubq->flags & UBLK_F_URING_CMD_COMP_IN_TASK))
-		return true;
-	return false;
+	return ubq->flags & UBLK_F_USER_COPY;
+}
+
+static inline bool ublk_need_req_ref(const struct ublk_queue *ubq)
+{
+	/*
+	 * read()/write() is involved in user copy, so request reference
+	 * has to be grabbed
+	 */
+	return ublk_support_user_copy(ubq);
+}
+
+static inline void ublk_init_req_ref(const struct ublk_queue *ubq,
+		struct request *req)
+{
+	if (ublk_need_req_ref(ubq)) {
+		struct ublk_rq_data *data = blk_mq_rq_to_pdu(req);
+
+		kref_init(&data->ref);
+	}
+}
+
+static inline bool ublk_get_req_ref(const struct ublk_queue *ubq,
+		struct request *req)
+{
+	if (ublk_need_req_ref(ubq)) {
+		struct ublk_rq_data *data = blk_mq_rq_to_pdu(req);
+
+		return kref_get_unless_zero(&data->ref);
+	}
+
+	return true;
+}
+
+static inline void ublk_put_req_ref(const struct ublk_queue *ubq,
+		struct request *req)
+{
+	if (ublk_need_req_ref(ubq)) {
+		struct ublk_rq_data *data = blk_mq_rq_to_pdu(req);
+
+		kref_put(&data->ref, ublk_complete_rq);
+	} else {
+		__ublk_complete_rq(req);
+	}
 }
 
 static inline bool ublk_need_get_data(const struct ublk_queue *ubq)
@@ -384,9 +449,9 @@ static void ublk_store_owner_uid_gid(unsigned int *owner_uid,
 	*owner_gid = from_kgid(&init_user_ns, gid);
 }
 
-static int ublk_open(struct block_device *bdev, fmode_t mode)
+static int ublk_open(struct gendisk *disk, blk_mode_t mode)
 {
-	struct ublk_device *ub = bdev->bd_disk->private_data;
+	struct ublk_device *ub = disk->private_data;
 
 	if (capable(CAP_SYS_ADMIN))
 		return 0;
@@ -421,49 +486,39 @@ static const struct block_device_operations ub_fops = {
 
 #define UBLK_MAX_PIN_PAGES	32
 
-struct ublk_map_data {
-	const struct request *rq;
-	unsigned long	ubuf;
-	unsigned int	len;
-};
-
 struct ublk_io_iter {
 	struct page *pages[UBLK_MAX_PIN_PAGES];
-	unsigned pg_off;	/* offset in the 1st page in pages */
-	int nr_pages;		/* how many page pointers in pages */
 	struct bio *bio;
 	struct bvec_iter iter;
 };
 
-static inline unsigned ublk_copy_io_pages(struct ublk_io_iter *data,
-		unsigned max_bytes, bool to_vm)
+/* return how many pages are copied */
+static void ublk_copy_io_pages(struct ublk_io_iter *data,
+		size_t total, size_t pg_off, int dir)
 {
-	const unsigned total = min_t(unsigned, max_bytes,
-			PAGE_SIZE - data->pg_off +
-			((data->nr_pages - 1) << PAGE_SHIFT));
 	unsigned done = 0;
 	unsigned pg_idx = 0;
 
 	while (done < total) {
 		struct bio_vec bv = bio_iter_iovec(data->bio, data->iter);
-		const unsigned int bytes = min3(bv.bv_len, total - done,
-				(unsigned)(PAGE_SIZE - data->pg_off));
+		unsigned int bytes = min3(bv.bv_len, (unsigned)total - done,
+				(unsigned)(PAGE_SIZE - pg_off));
 		void *bv_buf = bvec_kmap_local(&bv);
 		void *pg_buf = kmap_local_page(data->pages[pg_idx]);
 
-		if (to_vm)
-			memcpy(pg_buf + data->pg_off, bv_buf, bytes);
+		if (dir == ITER_DEST)
+			memcpy(pg_buf + pg_off, bv_buf, bytes);
 		else
-			memcpy(bv_buf, pg_buf + data->pg_off, bytes);
+			memcpy(bv_buf, pg_buf + pg_off, bytes);
 
 		kunmap_local(pg_buf);
 		kunmap_local(bv_buf);
 
 		/* advance page array */
-		data->pg_off += bytes;
-		if (data->pg_off == PAGE_SIZE) {
+		pg_off += bytes;
+		if (pg_off == PAGE_SIZE) {
 			pg_idx += 1;
-			data->pg_off = 0;
+			pg_off = 0;
 		}
 
 		done += bytes;
@@ -477,41 +532,58 @@ static inline unsigned ublk_copy_io_pages(struct ublk_io_iter *data,
 			data->iter = data->bio->bi_iter;
 		}
 	}
+}
 
-	return done;
+static bool ublk_advance_io_iter(const struct request *req,
+		struct ublk_io_iter *iter, unsigned int offset)
+{
+	struct bio *bio = req->bio;
+
+	for_each_bio(bio) {
+		if (bio->bi_iter.bi_size > offset) {
+			iter->bio = bio;
+			iter->iter = bio->bi_iter;
+			bio_advance_iter(iter->bio, &iter->iter, offset);
+			return true;
+		}
+		offset -= bio->bi_iter.bi_size;
+	}
+	return false;
 }
 
-static int ublk_copy_user_pages(struct ublk_map_data *data, bool to_vm)
+/*
+ * Copy data between request pages and io_iter, and 'offset'
+ * is the start point of linear offset of request.
+ */
+static size_t ublk_copy_user_pages(const struct request *req,
+		unsigned offset, struct iov_iter *uiter, int dir)
 {
-	const unsigned int gup_flags = to_vm ? FOLL_WRITE : 0;
-	const unsigned long start_vm = data->ubuf;
-	unsigned int done = 0;
-	struct ublk_io_iter iter = {
-		.pg_off	= start_vm & (PAGE_SIZE - 1),
-		.bio	= data->rq->bio,
-		.iter	= data->rq->bio->bi_iter,
-	};
-	const unsigned int nr_pages = round_up(data->len +
-			(start_vm & (PAGE_SIZE - 1)), PAGE_SIZE) >> PAGE_SHIFT;
-
-	while (done < nr_pages) {
-		const unsigned to_pin = min_t(unsigned, UBLK_MAX_PIN_PAGES,
-				nr_pages - done);
-		unsigned i, len;
-
-		iter.nr_pages = get_user_pages_fast(start_vm +
-				(done << PAGE_SHIFT), to_pin, gup_flags,
-				iter.pages);
-		if (iter.nr_pages <= 0)
-			return done == 0 ? iter.nr_pages : done;
-		len = ublk_copy_io_pages(&iter, data->len, to_vm);
-		for (i = 0; i < iter.nr_pages; i++) {
-			if (to_vm)
+	struct ublk_io_iter iter;
+	size_t done = 0;
+
+	if (!ublk_advance_io_iter(req, &iter, offset))
+		return 0;
+
+	while (iov_iter_count(uiter) && iter.bio) {
+		unsigned nr_pages;
+		ssize_t len;
+		size_t off;
+		int i;
+
+		len = iov_iter_get_pages2(uiter, iter.pages,
+				iov_iter_count(uiter),
+				UBLK_MAX_PIN_PAGES, &off);
+		if (len <= 0)
+			return done;
+
+		ublk_copy_io_pages(&iter, len, off, dir);
+		nr_pages = DIV_ROUND_UP(len + off, PAGE_SIZE);
+		for (i = 0; i < nr_pages; i++) {
+			if (dir == ITER_DEST)
 				set_page_dirty(iter.pages[i]);
 			put_page(iter.pages[i]);
 		}
-		data->len -= len;
-		done += iter.nr_pages;
+		done += len;
 	}
 
 	return done;
@@ -532,21 +604,23 @@ static int ublk_map_io(const struct ublk_queue *ubq, const struct request *req,
 {
 	const unsigned int rq_bytes = blk_rq_bytes(req);
 
+	if (ublk_support_user_copy(ubq))
+		return rq_bytes;
+
 	/*
 	 * no zero copy, we delay copy WRITE request data into ublksrv
 	 * context and the big benefit is that pinning pages in current
 	 * context is pretty fast, see ublk_pin_user_pages
 	 */
 	if (ublk_need_map_req(req)) {
-		struct ublk_map_data data = {
-			.rq	=	req,
-			.ubuf	=	io->addr,
-			.len	=	rq_bytes,
-		};
+		struct iov_iter iter;
+		struct iovec iov;
+		const int dir = ITER_DEST;
 
-		ublk_copy_user_pages(&data, true);
+		import_single_range(dir, u64_to_user_ptr(io->addr), rq_bytes,
+				&iov, &iter);
 
-		return rq_bytes - data.len;
+		return ublk_copy_user_pages(req, 0, &iter, dir);
 	}
 	return rq_bytes;
 }
@@ -557,18 +631,19 @@ static int ublk_unmap_io(const struct ublk_queue *ubq,
 {
 	const unsigned int rq_bytes = blk_rq_bytes(req);
 
+	if (ublk_support_user_copy(ubq))
+		return rq_bytes;
+
 	if (ublk_need_unmap_req(req)) {
-		struct ublk_map_data data = {
-			.rq	=	req,
-			.ubuf	=	io->addr,
-			.len	=	io->res,
-		};
+		struct iov_iter iter;
+		struct iovec iov;
+		const int dir = ITER_SOURCE;
 
 		WARN_ON_ONCE(io->res > rq_bytes);
 
-		ublk_copy_user_pages(&data, false);
-
-		return io->res - data.len;
+		import_single_range(dir, u64_to_user_ptr(io->addr), io->res,
+				&iov, &iter);
+		return ublk_copy_user_pages(req, 0, &iter, dir);
 	}
 	return rq_bytes;
 }
@@ -648,13 +723,19 @@ static inline bool ubq_daemon_is_dying(struct ublk_queue *ubq)
 }
 
 /* todo: handle partial completion */
-static void ublk_complete_rq(struct request *req)
+static inline void __ublk_complete_rq(struct request *req)
 {
 	struct ublk_queue *ubq = req->mq_hctx->driver_data;
 	struct ublk_io *io = &ubq->ios[req->tag];
 	unsigned int unmapped_bytes;
 	blk_status_t res = BLK_STS_OK;
 
+	/* called from ublk_abort_queue() code path */
+	if (io->flags & UBLK_IO_FLAG_ABORTED) {
+		res = BLK_STS_IOERR;
+		goto exit;
+	}
+
 	/* failed read IO if nothing is read */
 	if (!io->res && req_op(req) == REQ_OP_READ)
 		io->res = -EIO;
@@ -694,6 +775,15 @@ exit:
 	blk_mq_end_request(req, res);
 }
 
+static void ublk_complete_rq(struct kref *ref)
+{
+	struct ublk_rq_data *data = container_of(ref, struct ublk_rq_data,
+			ref);
+	struct request *req = blk_mq_rq_from_pdu(data);
+
+	__ublk_complete_rq(req);
+}
+
 /*
  * Since __ublk_rq_task_work always fails requests immediately during
  * exiting, __ublk_fail_req() is only called from abort context during
@@ -712,7 +802,7 @@ static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io,
 		if (ublk_queue_can_use_recovery_reissue(ubq))
 			blk_mq_requeue_request(req, false);
 		else
-			blk_mq_end_request(req, BLK_STS_IOERR);
+			ublk_put_req_ref(ubq, req);
 	}
 }
 
@@ -821,6 +911,7 @@ static inline void __ublk_rq_task_work(struct request *req,
 			mapped_bytes >> 9;
 	}
 
+	ublk_init_req_ref(ubq, req);
 	ubq_complete_io_cmd(io, UBLK_IO_RES_OK, issue_flags);
 }
 
@@ -852,17 +943,6 @@ static void ublk_rq_task_work_cb(struct io_uring_cmd *cmd, unsigned issue_flags)
 	ublk_forward_io_cmds(ubq, issue_flags);
 }
 
-static void ublk_rq_task_work_fn(struct callback_head *work)
-{
-	struct ublk_rq_data *data = container_of(work,
-			struct ublk_rq_data, work);
-	struct request *req = blk_mq_rq_from_pdu(data);
-	struct ublk_queue *ubq = req->mq_hctx->driver_data;
-	unsigned issue_flags = IO_URING_F_UNLOCKED;
-
-	ublk_forward_io_cmds(ubq, issue_flags);
-}
-
 static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq)
 {
 	struct ublk_rq_data *data = blk_mq_rq_to_pdu(rq);
@@ -886,10 +966,6 @@ static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq)
 	 */
 	if (unlikely(io->flags & UBLK_IO_FLAG_ABORTED)) {
 		ublk_abort_io_cmds(ubq);
-	} else if (ublk_can_use_task_work(ubq)) {
-		if (task_work_add(ubq->ubq_daemon, &data->work,
-					TWA_SIGNAL_NO_IPI))
-			ublk_abort_io_cmds(ubq);
 	} else {
 		struct io_uring_cmd *cmd = io->cmd;
 		struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);
@@ -961,19 +1037,9 @@ static int ublk_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data,
 	return 0;
 }
 
-static int ublk_init_rq(struct blk_mq_tag_set *set, struct request *req,
-		unsigned int hctx_idx, unsigned int numa_node)
-{
-	struct ublk_rq_data *data = blk_mq_rq_to_pdu(req);
-
-	init_task_work(&data->work, ublk_rq_task_work_fn);
-	return 0;
-}
-
 static const struct blk_mq_ops ublk_mq_ops = {
 	.queue_rq       = ublk_queue_rq,
 	.init_hctx	= ublk_init_hctx,
-	.init_request   = ublk_init_rq,
 	.timeout	= ublk_timeout,
 };
 
@@ -1050,7 +1116,7 @@ static void ublk_commit_completion(struct ublk_device *ub,
 	req = blk_mq_tag_to_rq(ub->tag_set.tags[qid], tag);
 
 	if (req && likely(!blk_should_fake_timeout(req->q)))
-		ublk_complete_rq(req);
+		ublk_put_req_ref(ubq, req);
 }
 
 /*
@@ -1295,6 +1361,14 @@ static inline int ublk_check_cmd_op(u32 cmd_op)
 	return 0;
 }
 
+static inline void ublk_fill_io_cmd(struct ublk_io *io,
+		struct io_uring_cmd *cmd, unsigned long buf_addr)
+{
+	io->cmd = cmd;
+	io->flags |= UBLK_IO_FLAG_ACTIVE;
+	io->addr = buf_addr;
+}
+
 static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 			       unsigned int issue_flags,
 			       const struct ublksrv_io_cmd *ub_cmd)
@@ -1340,6 +1414,11 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 			^ (_IOC_NR(cmd_op) == UBLK_IO_NEED_GET_DATA))
 		goto out;
 
+	if (ublk_support_user_copy(ubq) && ub_cmd->addr) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	ret = ublk_check_cmd_op(cmd_op);
 	if (ret)
 		goto out;
@@ -1358,36 +1437,41 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 		 */
 		if (io->flags & UBLK_IO_FLAG_OWNED_BY_SRV)
 			goto out;
-		/* FETCH_RQ has to provide IO buffer if NEED GET DATA is not enabled */
-		if (!ub_cmd->addr && !ublk_need_get_data(ubq))
-			goto out;
-		io->cmd = cmd;
-		io->flags |= UBLK_IO_FLAG_ACTIVE;
-		io->addr = ub_cmd->addr;
 
+		if (!ublk_support_user_copy(ubq)) {
+			/*
+			 * FETCH_RQ has to provide IO buffer if NEED GET
+			 * DATA is not enabled
+			 */
+			if (!ub_cmd->addr && !ublk_need_get_data(ubq))
+				goto out;
+		}
+
+		ublk_fill_io_cmd(io, cmd, ub_cmd->addr);
 		ublk_mark_io_ready(ub, ubq);
 		break;
 	case UBLK_IO_COMMIT_AND_FETCH_REQ:
 		req = blk_mq_tag_to_rq(ub->tag_set.tags[ub_cmd->q_id], tag);
-		/*
-		 * COMMIT_AND_FETCH_REQ has to provide IO buffer if NEED GET DATA is
-		 * not enabled or it is Read IO.
-		 */
-		if (!ub_cmd->addr && (!ublk_need_get_data(ubq) || req_op(req) == REQ_OP_READ))
-			goto out;
+
 		if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV))
 			goto out;
-		io->addr = ub_cmd->addr;
-		io->flags |= UBLK_IO_FLAG_ACTIVE;
-		io->cmd = cmd;
+
+		if (!ublk_support_user_copy(ubq)) {
+			/*
+			 * COMMIT_AND_FETCH_REQ has to provide IO buffer if
+			 * NEED GET DATA is not enabled or it is Read IO.
+			 */
+			if (!ub_cmd->addr && (!ublk_need_get_data(ubq) ||
+						req_op(req) == REQ_OP_READ))
+				goto out;
+		}
+		ublk_fill_io_cmd(io, cmd, ub_cmd->addr);
 		ublk_commit_completion(ub, ub_cmd);
 		break;
 	case UBLK_IO_NEED_GET_DATA:
 		if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV))
 			goto out;
-		io->addr = ub_cmd->addr;
-		io->cmd = cmd;
-		io->flags |= UBLK_IO_FLAG_ACTIVE;
+		ublk_fill_io_cmd(io, cmd, ub_cmd->addr);
 		ublk_handle_need_get_data(ub, ub_cmd->q_id, ub_cmd->tag);
 		break;
 	default:
@@ -1402,6 +1486,36 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 	return -EIOCBQUEUED;
 }
 
+static inline struct request *__ublk_check_and_get_req(struct ublk_device *ub,
+		struct ublk_queue *ubq, int tag, size_t offset)
+{
+	struct request *req;
+
+	if (!ublk_need_req_ref(ubq))
+		return NULL;
+
+	req = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], tag);
+	if (!req)
+		return NULL;
+
+	if (!ublk_get_req_ref(ubq, req))
+		return NULL;
+
+	if (unlikely(!blk_mq_request_started(req) || req->tag != tag))
+		goto fail_put;
+
+	if (!ublk_rq_has_data(req))
+		goto fail_put;
+
+	if (offset > blk_rq_bytes(req))
+		goto fail_put;
+
+	return req;
+fail_put:
+	ublk_put_req_ref(ubq, req);
+	return NULL;
+}
+
 static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)
 {
 	/*
@@ -1419,11 +1533,112 @@ static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)
 	return __ublk_ch_uring_cmd(cmd, issue_flags, &ub_cmd);
 }
 
+static inline bool ublk_check_ubuf_dir(const struct request *req,
+		int ubuf_dir)
+{
+	/* copy ubuf to request pages */
+	if (req_op(req) == REQ_OP_READ && ubuf_dir == ITER_SOURCE)
+		return true;
+
+	/* copy request pages to ubuf */
+	if (req_op(req) == REQ_OP_WRITE && ubuf_dir == ITER_DEST)
+		return true;
+
+	return false;
+}
+
+static struct request *ublk_check_and_get_req(struct kiocb *iocb,
+		struct iov_iter *iter, size_t *off, int dir)
+{
+	struct ublk_device *ub = iocb->ki_filp->private_data;
+	struct ublk_queue *ubq;
+	struct request *req;
+	size_t buf_off;
+	u16 tag, q_id;
+
+	if (!ub)
+		return ERR_PTR(-EACCES);
+
+	if (!user_backed_iter(iter))
+		return ERR_PTR(-EACCES);
+
+	if (ub->dev_info.state == UBLK_S_DEV_DEAD)
+		return ERR_PTR(-EACCES);
+
+	tag = ublk_pos_to_tag(iocb->ki_pos);
+	q_id = ublk_pos_to_hwq(iocb->ki_pos);
+	buf_off = ublk_pos_to_buf_off(iocb->ki_pos);
+
+	if (q_id >= ub->dev_info.nr_hw_queues)
+		return ERR_PTR(-EINVAL);
+
+	ubq = ublk_get_queue(ub, q_id);
+	if (!ubq)
+		return ERR_PTR(-EINVAL);
+
+	if (tag >= ubq->q_depth)
+		return ERR_PTR(-EINVAL);
+
+	req = __ublk_check_and_get_req(ub, ubq, tag, buf_off);
+	if (!req)
+		return ERR_PTR(-EINVAL);
+
+	if (!req->mq_hctx || !req->mq_hctx->driver_data)
+		goto fail;
+
+	if (!ublk_check_ubuf_dir(req, dir))
+		goto fail;
+
+	*off = buf_off;
+	return req;
+fail:
+	ublk_put_req_ref(ubq, req);
+	return ERR_PTR(-EACCES);
+}
+
+static ssize_t ublk_ch_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct ublk_queue *ubq;
+	struct request *req;
+	size_t buf_off;
+	size_t ret;
+
+	req = ublk_check_and_get_req(iocb, to, &buf_off, ITER_DEST);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	ret = ublk_copy_user_pages(req, buf_off, to, ITER_DEST);
+	ubq = req->mq_hctx->driver_data;
+	ublk_put_req_ref(ubq, req);
+
+	return ret;
+}
+
+static ssize_t ublk_ch_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct ublk_queue *ubq;
+	struct request *req;
+	size_t buf_off;
+	size_t ret;
+
+	req = ublk_check_and_get_req(iocb, from, &buf_off, ITER_SOURCE);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	ret = ublk_copy_user_pages(req, buf_off, from, ITER_SOURCE);
+	ubq = req->mq_hctx->driver_data;
+	ublk_put_req_ref(ubq, req);
+
+	return ret;
+}
+
 static const struct file_operations ublk_ch_fops = {
 	.owner = THIS_MODULE,
 	.open = ublk_ch_open,
 	.release = ublk_ch_release,
 	.llseek = no_llseek,
+	.read_iter = ublk_ch_read_iter,
+	.write_iter = ublk_ch_write_iter,
 	.uring_cmd = ublk_ch_uring_cmd,
 	.mmap = ublk_ch_mmap,
 };
@@ -1547,7 +1762,7 @@ static int ublk_add_chdev(struct ublk_device *ub)
 
 	dev->parent = ublk_misc.this_device;
 	dev->devt = MKDEV(MAJOR(ublk_chr_devt), minor);
-	dev->class = ublk_chr_class;
+	dev->class = &ublk_chr_class;
 	dev->release = ublk_cdev_rel;
 	device_initialize(dev);
 
@@ -1818,10 +2033,12 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd)
 	 */
 	ub->dev_info.flags &= UBLK_F_ALL;
 
-	if (!IS_BUILTIN(CONFIG_BLK_DEV_UBLK))
-		ub->dev_info.flags |= UBLK_F_URING_CMD_COMP_IN_TASK;
+	ub->dev_info.flags |= UBLK_F_CMD_IOCTL_ENCODE |
+		UBLK_F_URING_CMD_COMP_IN_TASK;
 
-	ub->dev_info.flags |= UBLK_F_CMD_IOCTL_ENCODE;
+	/* GET_DATA isn't needed any more with USER_COPY */
+	if (ub->dev_info.flags & UBLK_F_USER_COPY)
+		ub->dev_info.flags &= ~UBLK_F_NEED_GET_DATA;
 
 	/* We are not ready to support zero copy */
 	ub->dev_info.flags &= ~UBLK_F_SUPPORT_ZERO_COPY;
@@ -2133,6 +2350,21 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub,
 	return ret;
 }
 
+static int ublk_ctrl_get_features(struct io_uring_cmd *cmd)
+{
+	const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
+	void __user *argp = (void __user *)(unsigned long)header->addr;
+	u64 features = UBLK_F_ALL & ~UBLK_F_SUPPORT_ZERO_COPY;
+
+	if (header->len != UBLK_FEATURES_LEN || !header->addr)
+		return -EINVAL;
+
+	if (copy_to_user(argp, &features, UBLK_FEATURES_LEN))
+		return -EFAULT;
+
+	return 0;
+}
+
 /*
  * All control commands are sent via /dev/ublk-control, so we have to check
  * the destination device's permission
@@ -2213,6 +2445,7 @@ static int ublk_ctrl_uring_cmd_permission(struct ublk_device *ub,
 	case UBLK_CMD_GET_DEV_INFO2:
 	case UBLK_CMD_GET_QUEUE_AFFINITY:
 	case UBLK_CMD_GET_PARAMS:
+	case (_IOC_NR(UBLK_U_CMD_GET_FEATURES)):
 		mask = MAY_READ;
 		break;
 	case UBLK_CMD_START_DEV:
@@ -2262,6 +2495,11 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
 	if (ret)
 		goto out;
 
+	if (cmd_op == UBLK_U_CMD_GET_FEATURES) {
+		ret = ublk_ctrl_get_features(cmd);
+		goto out;
+	}
+
 	if (_IOC_NR(cmd_op) != UBLK_CMD_ADD_DEV) {
 		ret = -ENODEV;
 		ub = ublk_get_device_from_id(header->dev_id);
@@ -2337,6 +2575,9 @@ static int __init ublk_init(void)
 {
 	int ret;
 
+	BUILD_BUG_ON((u64)UBLKSRV_IO_BUF_OFFSET +
+			UBLKSRV_IO_BUF_TOTAL_SIZE < UBLKSRV_IO_BUF_OFFSET);
+
 	init_waitqueue_head(&ublk_idr_wq);
 
 	ret = misc_register(&ublk_misc);
@@ -2347,11 +2588,10 @@ static int __init ublk_init(void)
 	if (ret)
 		goto unregister_mis;
 
-	ublk_chr_class = class_create("ublk-char");
-	if (IS_ERR(ublk_chr_class)) {
-		ret = PTR_ERR(ublk_chr_class);
+	ret = class_register(&ublk_chr_class);
+	if (ret)
 		goto free_chrdev_region;
-	}
+
 	return 0;
 
 free_chrdev_region:
@@ -2369,7 +2609,7 @@ static void __exit ublk_exit(void)
 	idr_for_each_entry(&ublk_index_idr, ub, id)
 		ublk_remove(ub);
 
-	class_destroy(ublk_chr_class);
+	class_unregister(&ublk_chr_class);
 	misc_deregister(&ublk_misc);
 
 	idr_destroy(&ublk_index_idr);