[PATCH v5 6/8] block: implement write zeroes io_uring cmd

[Pavel Begunkov <asml.silence@gmail.com>]

Add a second 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. It has to be supported by underlying hardware to be
used, otherwise the request will fail. A fallback version is implemented
separately in a later patch.

Suggested-by: Conrad Meyer <conradmeyer@meta.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 block/ioctl.c               | 66 +++++++++++++++++++++++++++++++++++++
 include/uapi/linux/blkdev.h |  1 +
 2 files changed, 67 insertions(+)

diff --git a/block/ioctl.c b/block/ioctl.c
index 007f6399de66..f8f6d6a71ff0 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -778,6 +778,69 @@ 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)
+{
+	struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd);
+	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 (unlikely(!prev))
+		return -EAGAIN;
+	if (unlikely(nr_sects))
+		bic->res = -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)
@@ -856,6 +919,9 @@ 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/blkdev.h b/include/uapi/linux/blkdev.h
index 66373cd1a83a..b4664139a82a 100644
--- a/include/uapi/linux/blkdev.h
+++ b/include/uapi/linux/blkdev.h
@@ -10,5 +10,6 @@
  * It's a different number space from ioctl(), reuse the block's code 0x12.
  */
 #define BLOCK_URING_CMD_DISCARD			_IO(0x12, 0)
+#define BLOCK_URING_CMD_WRITE_ZEROES		_IO(0x12, 1)
 
 #endif
-- 
2.45.2