Add ->uring_cmd callback for block device files and use it to implement
asynchronous discard. Normally, it first tries to execute the command
from non-blocking context, which we limit to a single bio because
otherwise one of sub-bios may need to wait for other bios, and we don't
want to deal with partial IO. If non-blocking attempt fails, we'll retry
it in a blocking context.

Suggested-by: Conrad Meyer <redacted>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 block/blk.h             |  1 +
 block/fops.c            |  2 +
 block/ioctl.c           | 94 +++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/fs.h |  2 +
 4 files changed, 99 insertions(+)

diff --git a/block/blk.h b/block/blk.h
index e180863f918b..5178c5ba6852 100644
--- a/block/blk.h
+++ b/block/blk.h

@@ -571,6 +571,7 @@ blk_mode_t file_to_blk_mode(struct file *file);
 int truncate_bdev_range(struct block_device *bdev, blk_mode_t mode,
                loff_t lstart, loff_t lend);
 long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg);
+int blkdev_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags);
 long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg);

 extern const struct address_space_operations def_blk_aops;

diff --git a/block/fops.c b/block/fops.c
index 9825c1713a49..8154b10b5abf 100644
--- a/block/fops.c
+++ b/block/fops.c

@@ -17,6 +17,7 @@
 #include <linux/fs.h>
 #include <linux/iomap.h>
 #include <linux/module.h>
+#include <linux/io_uring/cmd.h>
 #include "blk.h"

 static inline struct inode *bdev_file_inode(struct file *file)

@@ -873,6 +874,7 @@ const struct file_operations def_blk_fops = {
        .splice_read    = filemap_splice_read,
        .splice_write   = iter_file_splice_write,
        .fallocate      = blkdev_fallocate,
+       .uring_cmd      = blkdev_uring_cmd,