When BLKZEROOUT ioctl and data read race, the data read leaves stale
page cache. To avoid the stale page cache, hold invalidate_lock of the
block device file mapping. The stale page cache is observed when
blktests test case block/009 is modified to call "blkdiscard -z" command
and repeated hundreds of times.
This patch can be applied back to the stable kernel version v5.15.y.
Rework is required for older stable kernels.
Fixes: 22dd6d356628 ("block: invalidate the page cache when issuing BLKZEROOUT")
Signed-off-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@xxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx # v5.15
---
block/ioctl.c | 12 +++++++++---
1 file changed, 9 insertions(+), 3 deletions(-)
diff --git a/block/ioctl.c b/block/ioctl.c
index 9fa87f64f703..0a1d10ac2e1a 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -154,6 +154,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
{
uint64_t range[2];
uint64_t start, end, len;
+ struct inode *inode = bdev->bd_inode;
int err;
if (!(mode & FMODE_WRITE))
@@ -176,12 +177,17 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
return -EINVAL;
/* Invalidate the page cache, including dirty pages */
+ filemap_invalidate_lock(inode->i_mapping);
err = truncate_bdev_range(bdev, mode, start, end);
if (err)
- return err;
+ goto fail;
+
+ err = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL,
+ BLKDEV_ZERO_NOUNMAP);
- return blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL,
- BLKDEV_ZERO_NOUNMAP);
+fail:
+ filemap_invalidate_unlock(inode->i_mapping);
+ return err;
}
static int put_ushort(unsigned short __user *argp, unsigned short val)
--
2.33.1
