Merge tag 'for-6.1/passthrough-2022-10-04' of git://git.kernel.dk/linux

Pull passthrough updates from Jens Axboe:
 "With these changes, passthrough NVMe support over io_uring now
  performs at the same level as block device O_DIRECT, and in many cases
  6-8% better.

  This contains:

   - Add support for fixed buffers for passthrough (Anuj, Kanchan)

   - Enable batched allocations and freeing on passthrough, similarly to
     what we support on the normal storage path (me)

   - Fix from Geert fixing an issue with !CONFIG_IO_URING"

* tag 'for-6.1/passthrough-2022-10-04' of git://git.kernel.dk/linux:
  io_uring: Add missing inline to io_uring_cmd_import_fixed() dummy
  nvme: wire up fixed buffer support for nvme passthrough
  nvme: pass ubuffer as an integer
  block: extend functionality to map bvec iterator
  block: factor out blk_rq_map_bio_alloc helper
  block: rename bio_map_put to blk_mq_map_bio_put
  nvme: refactor nvme_alloc_request
  nvme: refactor nvme_add_user_metadata
  nvme: Use blk_rq_map_user_io helper
  scsi: Use blk_rq_map_user_io helper
  block: add blk_rq_map_user_io
  io_uring: introduce fixed buffer support for io_uring_cmd
  io_uring: add io_uring_cmd_import_fixed
  nvme: enable batched completions of passthrough IO
  nvme: split out metadata vs non metadata end_io uring_cmd completions
  block: allow end_io based requests in the completion batch handling
  block: change request end_io handler to pass back a return value
  block: enable batched allocation for blk_mq_alloc_request()
  block: kill deprecated BUG_ON() in the flush handling

3 files changed, 28 insertions, 3 deletions

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 00a15808c137..ba18e9bdb799 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -14,7 +14,12 @@ struct blk_flush_queue;
 #define BLKDEV_MIN_RQ	4
 #define BLKDEV_DEFAULT_RQ	128
 
-typedef void (rq_end_io_fn)(struct request *, blk_status_t);
+enum rq_end_io_ret {
+	RQ_END_IO_NONE,
+	RQ_END_IO_FREE,
+};
+
+typedef enum rq_end_io_ret (rq_end_io_fn)(struct request *, blk_status_t);
 
 /*
  * request flags */
@@ -848,8 +853,9 @@ static inline bool blk_mq_add_to_batch(struct request *req,
 				       struct io_comp_batch *iob, int ioerror,
 				       void (*complete)(struct io_comp_batch *))
 {
-	if (!iob || (req->rq_flags & RQF_ELV) || req->end_io || ioerror)
+	if (!iob || (req->rq_flags & RQF_ELV) || ioerror)
 		return false;
+
 	if (!iob->complete)
 		iob->complete = complete;
 	else if (iob->complete != complete)
@@ -979,6 +985,8 @@ struct rq_map_data {
 
 int blk_rq_map_user(struct request_queue *, struct request *,
 		struct rq_map_data *, void __user *, unsigned long, gfp_t);
+int blk_rq_map_user_io(struct request *, struct rq_map_data *,
+		void __user *, unsigned long, gfp_t, bool, int, bool, int);
 int blk_rq_map_user_iov(struct request_queue *, struct request *,
 		struct rq_map_data *, const struct iov_iter *, gfp_t);
 int blk_rq_unmap_user(struct bio *);
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 58676c0a398f..43bc8a2edccf 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -4,6 +4,7 @@
 
 #include <linux/sched.h>
 #include <linux/xarray.h>
+#include <uapi/linux/io_uring.h>
 
 enum io_uring_cmd_flags {
 	IO_URING_F_COMPLETE_DEFER	= 1,
@@ -27,11 +28,13 @@ struct io_uring_cmd {
 		void *cookie;
 	};
 	u32		cmd_op;
-	u32		pad;
+	u32		flags;
 	u8		pdu[32]; /* available inline for free use */
 };
 
 #if defined(CONFIG_IO_URING)
+int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
+			      struct iov_iter *iter, void *ioucmd);
 void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2);
 void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
 			void (*task_work_cb)(struct io_uring_cmd *));
@@ -59,6 +62,11 @@ static inline void io_uring_free(struct task_struct *tsk)
 		__io_uring_free(tsk);
 }
 #else
+static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
+			      struct iov_iter *iter, void *ioucmd)
+{
+	return -EOPNOTSUPP;
+}
 static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret,
 		ssize_t ret2)
 {
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 92f29d9505a6..ab7458033ee3 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -56,6 +56,7 @@ struct io_uring_sqe {
 		__u32		hardlink_flags;
 		__u32		xattr_flags;
 		__u32		msg_ring_flags;
+		__u32		uring_cmd_flags;
 	};
 	__u64	user_data;	/* data to be passed back at completion time */
 	/* pack this to avoid bogus arm OABI complaints */
@@ -220,6 +221,14 @@ enum io_uring_op {
 };
 
 /*
+ * sqe->uring_cmd_flags
+ * IORING_URING_CMD_FIXED	use registered buffer; pass thig flag
+ *				along with setting sqe->buf_index.
+ */
+#define IORING_URING_CMD_FIXED	(1U << 0)
+
+
+/*
  * sqe->fsync_flags
  */
 #define IORING_FSYNC_DATASYNC	(1U << 0)