[PATCH v2 5/7] block: implement async discard as io_uring cmd

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

io_uring allows to implement custom file specific operations via
fops->uring_cmd callback. Use it to wire up asynchronous discard
commands. Normally, first it tries to do a non-blocking issue, and if
fails we'd retry from a blocking context by returning -EAGAIN to
core io_uring.

Note, unlike ioctl(BLKDISCARD) with stronger guarantees against races,
we only do a best effort attempt to invalidate page cache, and it can
race with any writes and reads and leave page cache stale. It's the
same kind of races we allow to direct writes.

Suggested-by: Conrad Meyer <conradmeyer@meta.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 block/blk.h             |   1 +
 block/fops.c            |   2 +
 block/ioctl.c           | 101 ++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/fs.h |   2 +
 4 files changed, 106 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,
 	.fop_flags	= FOP_BUFFER_RASYNC,
 };
 
diff --git a/block/ioctl.c b/block/ioctl.c
index 8df0bc8002f5..a9aaa7cb7f73 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -11,6 +11,8 @@
 #include <linux/blktrace_api.h>
 #include <linux/pr.h>
 #include <linux/uaccess.h>
+#include <linux/pagemap.h>
+#include <linux/io_uring/cmd.h>
 #include "blk.h"
 
 static int blkpg_do_ioctl(struct block_device *bdev,
@@ -745,3 +747,102 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	return ret;
 }
 #endif
+
+struct blk_cmd {
+	blk_status_t status;
+	bool nowait;
+};
+
+static void blk_cmd_complete(struct io_uring_cmd *cmd, unsigned int issue_flags)
+{
+	struct blk_cmd *bc = io_uring_cmd_to_pdu(cmd, struct blk_cmd);
+	int res = blk_status_to_errno(bc->status);
+
+	if (res == -EAGAIN && bc->nowait)
+		io_uring_cmd_issue_blocking(cmd);
+	else
+		io_uring_cmd_done(cmd, res, 0, issue_flags);
+}
+
+static void bio_cmd_end(struct bio *bio)
+{
+	struct io_uring_cmd *cmd = bio->bi_private;
+	struct blk_cmd *bc = io_uring_cmd_to_pdu(cmd, struct blk_cmd);
+
+	if (unlikely(bio->bi_status) && !bc->status)
+		bc->status = bio->bi_status;
+
+	io_uring_cmd_do_in_task_lazy(cmd, blk_cmd_complete);
+	bio_put(bio);
+}
+
+static int blkdev_cmd_discard(struct io_uring_cmd *cmd,
+			      struct block_device *bdev,
+			      uint64_t start, uint64_t len, bool nowait)
+{
+	sector_t sector = start >> SECTOR_SHIFT;
+	sector_t nr_sects = len >> SECTOR_SHIFT;
+	struct bio *prev = NULL, *bio;
+	int err;
+
+	if (!bdev_max_discard_sectors(bdev))
+		return -EOPNOTSUPP;
+
+	err = blk_validate_write(bdev, file_to_blk_mode(cmd->file), start, len);
+	if (err)
+		return err;
+	err = filemap_invalidate_pages(bdev->bd_mapping, start,
+					start + len - 1, nowait);
+	if (err)
+		return err;
+
+	while ((bio = blk_alloc_discard_bio(bdev, &sector, &nr_sects,
+					    GFP_KERNEL))) {
+		if (nowait) {
+			/*
+			 * Don't allow multi-bio non-blocking submissions as
+			 * subsequent bios may fail but we won't get direct
+			 * feedback about that. Normally, the caller should
+			 * retry from a blocking context.
+			 */
+			if (unlikely(nr_sects)) {
+				bio_put(bio);
+				return -EAGAIN;
+			}
+			bio->bi_opf |= REQ_NOWAIT;
+		}
+		prev = bio_chain_and_submit(prev, bio);
+	}
+	if (!prev)
+		return -EFAULT;
+
+	prev->bi_private = cmd;
+	prev->bi_end_io = bio_cmd_end;
+	submit_bio(prev);
+	return -EIOCBQUEUED;
+}
+
+int blkdev_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)
+{
+	struct block_device *bdev = I_BDEV(cmd->file->f_mapping->host);
+	struct blk_cmd *bc = io_uring_cmd_to_pdu(cmd, struct blk_cmd);
+	const struct io_uring_sqe *sqe = cmd->sqe;
+	u32 cmd_op = cmd->cmd_op;
+	uint64_t start, len;
+
+	if (unlikely(sqe->ioprio || sqe->__pad1 || sqe->len ||
+		     sqe->rw_flags || sqe->file_index))
+		return -EINVAL;
+
+	bc->status = BLK_STS_OK;
+	bc->nowait = issue_flags & IO_URING_F_NONBLOCK;
+
+	start = READ_ONCE(sqe->addr);
+	len = READ_ONCE(sqe->addr3);
+
+	switch (cmd_op) {
+	case BLOCK_URING_CMD_DISCARD:
+		return blkdev_cmd_discard(cmd, bdev, start, len, bc->nowait);
+	}
+	return -EINVAL;
+}
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 753971770733..0016e38ed33c 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -208,6 +208,8 @@ struct fsxattr {
  * (see uapi/linux/blkzoned.h)
  */
 
+#define BLOCK_URING_CMD_DISCARD			0
+
 #define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
 #define FIBMAP	   _IO(0x00,1)	/* bmap access */
 #define FIGETBSZ   _IO(0x00,2)	/* get the block size used for bmap */
-- 
2.45.2