Merge tag 'for-6.12/io_uring-discard-20240913' of git://git.kernel.dk/linux

Pull io_uring async discard support from Jens Axboe:
 "Sitting on top of both the 6.12 block and io_uring core branches,
  here's support for async discard through io_uring.

  This allows applications to issue async discards, rather than rely on
  the blocking sync ioctl discards we already have. The sync support is
  difficult to use outside of idle/cleanup periods.

  On a real (but slow) device, testing shows the following results when
  compared to sync discard:

	qd64 sync discard: 21K IOPS, lat avg 3 msec (max 21 msec)
	qd64 async discard: 76K IOPS, lat avg 845 usec (max 2.2 msec)

	qd64 sync discard: 14K IOPS, lat avg 5 msec (max 25 msec)
	qd64 async discard: 56K IOPS, lat avg 1153 usec (max 3.6 msec)

  and synthetic null_blk testing with the same queue depth and block
  size settings as above shows:

	Type    Trim size       IOPS    Lat avg (usec)  Lat Max (usec)
	==============================================================
	sync    4k               144K       444            20314
	async   4k              1353K        47              595
	sync    1M                56K      1136            21031
	async   1M                94K       680              760"

* tag 'for-6.12/io_uring-discard-20240913' of git://git.kernel.dk/linux:
  block: implement async io_uring discard cmd
  block: introduce blk_validate_byte_range()
  filemap: introduce filemap_invalidate_pages
  io_uring/cmd: give inline space in request to cmds
  io_uring/cmd: expose iowq to cmds

3 files changed, 147 insertions, 19 deletions

diff --git a/block/blk.h b/block/blk.h
index 86affb583eb6..c718e4291db0 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -609,6 +609,7 @@ 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 35c47a304727..e69deb6d8635 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)
@@ -865,6 +866,7 @@ 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 44257bdfeacb..6554b728bae6 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -11,6 +11,9 @@
 #include <linux/blktrace_api.h>
 #include <linux/pr.h>
 #include <linux/uaccess.h>
+#include <linux/pagemap.h>
+#include <linux/io_uring/cmd.h>
+#include <uapi/linux/blkdev.h>
 #include "blk.h"
 
 static int blkpg_do_ioctl(struct block_device *bdev,
@@ -92,41 +95,54 @@ static int compat_blkpg_ioctl(struct block_device *bdev,
 }
 #endif
 
+/*
+ * Check that [start, start + len) is a valid range from the block device's
+ * perspective, including verifying that it can be correctly translated into
+ * logical block addresses.
+ */
+static int blk_validate_byte_range(struct block_device *bdev,
+				   uint64_t start, uint64_t len)
+{
+	unsigned int bs_mask = bdev_logical_block_size(bdev) - 1;
+	uint64_t end;
+
+	if ((start | len) & bs_mask)
+		return -EINVAL;
+	if (!len)
+		return -EINVAL;
+	if (check_add_overflow(start, len, &end) || end > bdev_nr_bytes(bdev))
+		return -EINVAL;
+
+	return 0;
+}
+
 static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode,
 		unsigned long arg)
 {
-	unsigned int bs_mask = bdev_logical_block_size(bdev) - 1;
-	uint64_t range[2], start, len, end;
+	uint64_t range[2], start, len;
 	struct bio *prev = NULL, *bio;
 	sector_t sector, nr_sects;
 	struct blk_plug plug;
 	int err;
 
-	if (!(mode & BLK_OPEN_WRITE))
-		return -EBADF;
-
-	if (!bdev_max_discard_sectors(bdev))
-		return -EOPNOTSUPP;
-	if (bdev_read_only(bdev))
-		return -EPERM;
-
 	if (copy_from_user(range, (void __user *)arg, sizeof(range)))
 		return -EFAULT;
-
 	start = range[0];
 	len = range[1];
 
-	if (!len)
-		return -EINVAL;
-	if ((start | len) & bs_mask)
-		return -EINVAL;
+	if (!bdev_max_discard_sectors(bdev))
+		return -EOPNOTSUPP;
 
-	if (check_add_overflow(start, len, &end) ||
-	    end > bdev_nr_bytes(bdev))
-		return -EINVAL;
+	if (!(mode & BLK_OPEN_WRITE))
+		return -EBADF;
+	if (bdev_read_only(bdev))
+		return -EPERM;
+	err = blk_validate_byte_range(bdev, start, len);
+	if (err)
+		return err;
 
 	filemap_invalidate_lock(bdev->bd_mapping);
-	err = truncate_bdev_range(bdev, mode, start, end - 1);
+	err = truncate_bdev_range(bdev, mode, start, start + len - 1);
 	if (err)
 		goto fail;
 
@@ -735,3 +751,112 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	return ret;
 }
 #endif
+
+struct blk_iou_cmd {
+	int res;
+	bool nowait;
+};
+
+static void blk_cmd_complete(struct io_uring_cmd *cmd, unsigned int issue_flags)
+{
+	struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd);
+
+	if (bic->res == -EAGAIN && bic->nowait)
+		io_uring_cmd_issue_blocking(cmd);
+	else
+		io_uring_cmd_done(cmd, bic->res, 0, issue_flags);
+}
+
+static void bio_cmd_bio_end_io(struct bio *bio)
+{
+	struct io_uring_cmd *cmd = bio->bi_private;
+	struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd);
+
+	if (unlikely(bio->bi_status) && !bic->res)
+		bic->res = blk_status_to_errno(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)
+{
+	struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd);
+	gfp_t gfp = nowait ? GFP_NOWAIT : GFP_KERNEL;
+	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;
+	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;
+
+	err = filemap_invalidate_pages(bdev->bd_mapping, start,
+					start + len - 1, nowait);
+	if (err)
+		return err;
+
+	while (true) {
+		bio = blk_alloc_discard_bio(bdev, &sector, &nr_sects, gfp);
+		if (!bio)
+			break;
+		if (nowait) {
+			/*
+			 * 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 (unlikely(nr_sects)) {
+				bio_put(bio);
+				return -EAGAIN;
+			}
+			bio->bi_opf |= REQ_NOWAIT;
+		}
+
+		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;
+}
+
+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_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_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;
+
+	bic->res = 0;
+	bic->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, bic->nowait);
+	}
+	return -EINVAL;
+}