[PATCH 6/6] nvme/ioctl: support fixed buffer for metadata

[Caleb Sander Mateos]

io_uring NVMe passthrough supports using a "fixed" (registered) buffer
for data, but not metadata. On high-IOPS workloads, the pinning and
unpinning overhead for the metadata pages is significant and could be
avoided if fixed metadata buffers were supported.

Define a NVME_URING_CMD_FIXED_METADATA bit for the nvme_uring_cmd's
flags field (which is currently required to be 0) to indicate that the
metadata buffer belongs to a fixed buffer registered with the io_uring.
The metadata fixed buffer index is specified in a metadata_buf_index
field replacing the existing rsvd1 in nvme_uring_cmd.

If NVME_URING_CMD_FIXED_METADATA is set, the metadata iov_iter is
obtained from io_uring_cmd_import_fixed_metadata() instead of
iov_iter_ubuf().

Signed-off-by: Caleb Sander Mateos <csander@xxxxxxxxxxxxxxx>
---
 drivers/nvme/host/ioctl.c       | 21 ++++++++++++++++-----
 include/uapi/linux/nvme_ioctl.h |  5 ++++-
 2 files changed, 20 insertions(+), 6 deletions(-)

diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 8e722184ecf1..4da8cf92c2e0 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -488,21 +488,22 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	struct iov_iter iter, meta_iter;
 	struct iov_iter *map_iter = NULL, *map_meta_iter = NULL;
 	struct request *req;
 	blk_opf_t rq_flags = 0;
 	blk_mq_req_flags_t blk_flags = 0;
+	u8 flags = READ_ONCE(cmd->flags);
 	u32 metadata_len, data_len;
 	u64 metadata, addr;
 	u32 timeout_ms;
 	int ddir;
 	int ret;
 
-	c.common.opcode = READ_ONCE(cmd->opcode);
-	c.common.flags = READ_ONCE(cmd->flags);
-	if (c.common.flags)
+	if (flags & ~NVME_URING_CMD_FIXED_METADATA)
 		return -EINVAL;
 
+	c.common.opcode = READ_ONCE(cmd->opcode);
+	c.common.flags = 0;
 	c.common.command_id = 0;
 	c.common.nsid = cpu_to_le32(cmd->nsid);
 	if (!nvme_validate_passthru_nsid(ctrl, ns, le32_to_cpu(c.common.nsid)))
 		return -EINVAL;
 
@@ -539,12 +540,22 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 			return ret;
 
 		map_iter = &iter;
 	}
 	if (data_len && metadata && metadata_len) {
-		iov_iter_ubuf(&meta_iter, ddir, nvme_to_user_ptr(metadata),
-			      metadata_len);
+		if (flags & NVME_URING_CMD_FIXED_METADATA) {
+			u16 buf_index = READ_ONCE(cmd->metadata_buf_index);
+
+			ret = io_uring_cmd_import_fixed_metadata(
+				ioucmd, buf_index, metadata, metadata_len, ddir,
+				&meta_iter, issue_flags);
+			if (ret < 0)
+				return ret;
+		} else {
+			iov_iter_ubuf(&meta_iter, ddir, nvme_to_user_ptr(metadata),
+				      metadata_len);
+		}
 		map_meta_iter = &meta_iter;
 	}
 
 	if (issue_flags & IO_URING_F_NONBLOCK) {
 		rq_flags |= REQ_NOWAIT;
diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h
index 2f76cba67166..93973f636b48 100644
--- a/include/uapi/linux/nvme_ioctl.h
+++ b/include/uapi/linux/nvme_ioctl.h
@@ -68,15 +68,18 @@ struct nvme_passthru_cmd64 {
 	__u32	timeout_ms;
 	__u32   rsvd2;
 	__u64	result;
 };
 
+/* struct nvme_uring_cmd flags field bits */
+#define NVME_URING_CMD_FIXED_METADATA (1U << 0)
+
 /* same as struct nvme_passthru_cmd64, minus the 8b result field */
 struct nvme_uring_cmd {
 	__u8	opcode;
 	__u8	flags;
-	__u16	rsvd1;
+	__u16	metadata_buf_index;
 	__u32	nsid;
 	__u32	cdw2;
 	__u32	cdw3;
 	__u64	metadata;
 	__u64	addr;
-- 
2.55.0