[PATCH v3 6/8] block: implement async write zeroes command

[Pavel Begunkov <asml.silence@xxxxxxxxx>]

Add another io_uring cmd for block layer implementing asynchronous write
zeroes. It reuses helpers we've added for async discards, and inherits
the code structure as well as all considerations in regards to page
cache races.

Suggested-by: Conrad Meyer <conradmeyer@xxxxxxxx>
Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
---
 block/ioctl.c           | 64 +++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/fs.h |  1 +
 2 files changed, 65 insertions(+)

diff --git a/block/ioctl.c b/block/ioctl.c
index 19fba8332eee..ef4b2a90ad79 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -772,6 +772,67 @@ static void bio_cmd_bio_end_io(struct bio *bio)
 	bio_put(bio);
 }
 
+static int blkdev_cmd_write_zeroes(struct io_uring_cmd *cmd,
+				   struct block_device *bdev,
+				   uint64_t start, uint64_t len, bool nowait)
+{
+
+	sector_t bs_mask = (bdev_logical_block_size(bdev) >> SECTOR_SHIFT) - 1;
+	sector_t limit = bdev_write_zeroes_sectors(bdev);
+	sector_t sector = start >> SECTOR_SHIFT;
+	sector_t nr_sects = len >> SECTOR_SHIFT;
+	struct bio *prev = NULL, *bio;
+	gfp_t gfp = nowait ? GFP_NOWAIT : GFP_KERNEL;
+	int err;
+
+	if (!(file_to_blk_mode(cmd->file) & BLK_OPEN_WRITE))
+		return -EBADF;
+	if (bdev_read_only(bdev))
+		return -EPERM;
+	err = blk_validate_byte_range(bdev, start, len);
+	if (err)
+		return err;
+
+	if (!limit)
+		return -EOPNOTSUPP;
+	/*
+	 * Don't allow multi-bio non-blocking submissions as subsequent bios
+	 * may fail but we won't get a direct indication of that. Normally,
+	 * the caller should retry from a blocking context.
+	 */
+	if (nowait && nr_sects > limit)
+		return -EAGAIN;
+
+	err = filemap_invalidate_pages(bdev->bd_mapping, start,
+					start + len - 1, nowait);
+	if (err)
+		return err;
+
+	limit = min(limit, (UINT_MAX >> SECTOR_SHIFT) & ~bs_mask);
+	while (nr_sects) {
+		sector_t bio_sects = min(nr_sects, limit);
+
+		bio = bio_alloc(bdev, 0, REQ_OP_WRITE_ZEROES|REQ_NOUNMAP, gfp);
+		if (!bio)
+			break;
+		if (nowait)
+			bio->bi_opf |= REQ_NOWAIT;
+		bio->bi_iter.bi_sector = sector;
+		bio->bi_iter.bi_size = bio_sects << SECTOR_SHIFT;
+		sector += bio_sects;
+		nr_sects -= bio_sects;
+
+		prev = bio_chain_and_submit(prev, bio);
+	}
+	if (!prev)
+		return -EAGAIN;
+
+	prev->bi_private = cmd;
+	prev->bi_end_io = bio_cmd_bio_end_io;
+	submit_bio(prev);
+	return -EIOCBQUEUED;
+}
+
 static int blkdev_cmd_discard(struct io_uring_cmd *cmd,
 			      struct block_device *bdev,
 			      uint64_t start, uint64_t len, bool nowait)
@@ -841,6 +902,9 @@ int blkdev_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)
 	switch (cmd_op) {
 	case BLOCK_URING_CMD_DISCARD:
 		return blkdev_cmd_discard(cmd, bdev, start, len, bic->nowait);
+	case BLOCK_URING_CMD_WRITE_ZEROES:
+		return blkdev_cmd_write_zeroes(cmd, bdev, start, len,
+					       bic->nowait);
 	}
 	return -EINVAL;
 }
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 7ea41ca97158..68b0fccebf92 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -209,6 +209,7 @@ struct fsxattr {
  */
 
 #define BLOCK_URING_CMD_DISCARD			_IO(0x12,137)
+#define BLOCK_URING_CMD_WRITE_ZEROES		_IO(0x12,138)
 
 #define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
 #define FIBMAP	   _IO(0x00,1)	/* bmap access */
-- 
2.45.2