[PATCH 4/6] ublk: zc register/unregister bvec

[Keith Busch <kbusch@meta.com>]

From: Keith Busch <kbusch@kernel.org>

Provide new operations for the user to request mapping an active request
to an io uring instance's buf_table. The user has to provide the index
it wants to install the buffer.

A reference count is taken on the request to ensure it can't be
completed while it is active in a ring's buf_table.

Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/block/ublk_drv.c      | 139 +++++++++++++++++++++++++---------
 include/uapi/linux/ublk_cmd.h |   4 +
 2 files changed, 107 insertions(+), 36 deletions(-)

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 529085181f355..58f224b5687b9 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -51,6 +51,9 @@
 /* private ioctl command mirror */
 #define UBLK_CMD_DEL_DEV_ASYNC	_IOC_NR(UBLK_U_CMD_DEL_DEV_ASYNC)
 
+#define UBLK_IO_REGISTER_IO_BUF		_IOC_NR(UBLK_U_IO_REGISTER_IO_BUF)
+#define UBLK_IO_UNREGISTER_IO_BUF	_IOC_NR(UBLK_U_IO_UNREGISTER_IO_BUF)
+
 /* All UBLK_F_* have to be included into UBLK_F_ALL */
 #define UBLK_F_ALL (UBLK_F_SUPPORT_ZERO_COPY \
 		| UBLK_F_URING_CMD_COMP_IN_TASK \
@@ -76,6 +79,9 @@ struct ublk_rq_data {
 	struct llist_node node;
 
 	struct kref ref;
+
+#define UBLK_ZC_REGISTERED 0
+	unsigned long flags;
 };
 
 struct ublk_uring_cmd_pdu {
@@ -201,7 +207,7 @@ static inline struct ublksrv_io_desc *ublk_get_iod(struct ublk_queue *ubq,
 						   int tag);
 static inline bool ublk_dev_is_user_copy(const struct ublk_device *ub)
 {
-	return ub->dev_info.flags & UBLK_F_USER_COPY;
+	return ub->dev_info.flags & (UBLK_F_USER_COPY | UBLK_F_SUPPORT_ZERO_COPY);
 }
 
 static inline bool ublk_dev_is_zoned(const struct ublk_device *ub)
@@ -581,7 +587,7 @@ static void ublk_apply_params(struct ublk_device *ub)
 
 static inline bool ublk_support_user_copy(const struct ublk_queue *ubq)
 {
-	return ubq->flags & UBLK_F_USER_COPY;
+	return ubq->flags & (UBLK_F_USER_COPY | UBLK_F_SUPPORT_ZERO_COPY);
 }
 
 static inline bool ublk_need_req_ref(const struct ublk_queue *ubq)
@@ -1747,6 +1753,96 @@ static inline void ublk_prep_cancel(struct io_uring_cmd *cmd,
 	io_uring_cmd_mark_cancelable(cmd, issue_flags);
 }
 
+
+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_register_io_buf(struct io_uring_cmd *cmd,
+				struct ublk_queue *ubq, int tag,
+				const struct ublksrv_io_cmd *ub_cmd)
+{
+	struct io_ring_ctx *ctx = cmd_to_io_kiocb(cmd)->ctx;
+	struct ublk_device *ub = cmd->file->private_data;
+	int index = (int)ub_cmd->addr, ret;
+	struct ublk_rq_data *data;
+	struct request *req;
+
+	if (!ub)
+		return -EPERM;
+
+	req = __ublk_check_and_get_req(ub, ubq, tag, 0);
+	if (!req)
+		return -EINVAL;
+
+	data = blk_mq_rq_to_pdu(req);
+	if (test_and_set_bit(UBLK_ZC_REGISTERED, &data->flags)) {
+		ublk_put_req_ref(ubq, req);
+		return -EBUSY;
+	}
+
+	ret = io_buffer_register_bvec(ctx, req, index);
+	if (ret) {
+		clear_bit(UBLK_ZC_REGISTERED, &data->flags);
+		ublk_put_req_ref(ubq, req);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int ublk_unregister_io_buf(struct io_uring_cmd *cmd,
+				  struct ublk_queue *ubq, int tag,
+				  const struct ublksrv_io_cmd *ub_cmd)
+{
+	struct io_ring_ctx *ctx = cmd_to_io_kiocb(cmd)->ctx;
+	struct ublk_device *ub = cmd->file->private_data;
+	int index = (int)ub_cmd->addr;
+	struct ublk_rq_data *data;
+	struct request *req;
+
+	if (!ub)
+		return -EPERM;
+
+	req = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], tag);
+	if (!req)
+		return -EINVAL;
+
+	data = blk_mq_rq_to_pdu(req);
+	if (!test_and_clear_bit(UBLK_ZC_REGISTERED, &data->flags))
+		return -EINVAL;
+
+	ublk_put_req_ref(ubq, req);
+	io_buffer_unregister_bvec(ctx, index);
+	return 0;
+}
+
 static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 			       unsigned int issue_flags,
 			       const struct ublksrv_io_cmd *ub_cmd)
@@ -1798,6 +1894,10 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 
 	ret = -EINVAL;
 	switch (_IOC_NR(cmd_op)) {
+	case UBLK_IO_REGISTER_IO_BUF:
+		return ublk_register_io_buf(cmd, ubq, tag, ub_cmd);
+	case UBLK_IO_UNREGISTER_IO_BUF:
+		return ublk_unregister_io_buf(cmd, ubq, tag, ub_cmd);
 	case UBLK_IO_FETCH_REQ:
 		/* UBLK_IO_FETCH_REQ is only allowed before queue is setup */
 		if (ublk_queue_ready(ubq)) {
@@ -1872,36 +1972,6 @@ 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 inline int ublk_ch_uring_cmd_local(struct io_uring_cmd *cmd,
 		unsigned int issue_flags)
 {
@@ -2527,9 +2597,6 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd)
 		goto out_free_dev_number;
 	}
 
-	/* We are not ready to support zero copy */
-	ub->dev_info.flags &= ~UBLK_F_SUPPORT_ZERO_COPY;
-
 	ub->dev_info.nr_hw_queues = min_t(unsigned int,
 			ub->dev_info.nr_hw_queues, nr_cpu_ids);
 	ublk_align_max_io_size(ub);
@@ -2860,7 +2927,7 @@ 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;
+	u64 features = UBLK_F_ALL;
 
 	if (header->len != UBLK_FEATURES_LEN || !header->addr)
 		return -EINVAL;
diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h
index a8bc98bb69fce..74246c926b55f 100644
--- a/include/uapi/linux/ublk_cmd.h
+++ b/include/uapi/linux/ublk_cmd.h
@@ -94,6 +94,10 @@
 	_IOWR('u', UBLK_IO_COMMIT_AND_FETCH_REQ, struct ublksrv_io_cmd)
 #define	UBLK_U_IO_NEED_GET_DATA		\
 	_IOWR('u', UBLK_IO_NEED_GET_DATA, struct ublksrv_io_cmd)
+#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)
 
 /* only ABORT means that no re-fetch */
 #define UBLK_IO_RES_OK			0
-- 
2.43.5