From: OGAWA Hirofumi <hirofumi@xxxxxxxxxxxxxxxxxx>
[ Upstream commit 07bfa4415ab607e459b69bd86aa7e7602ce10b4f ]
If userspace reads the buffer via blockdev while mounting,
sb_getblk()+modify can race with buffer read via blockdev.
For example,
FS userspace
bh = sb_getblk()
modify bh->b_data
read
ll_rw_block(bh)
fill bh->b_data by on-disk data
/* lost modified data by FS */
set_buffer_uptodate(bh)
set_buffer_uptodate(bh)
Userspace should not use the blockdev while mounting though, the udev
seems to be already doing this. Although I think the udev should try to
avoid this, workaround the race by small overhead.
Link: http://lkml.kernel.org/r/87pnk7l3sw.fsf_-_@xxxxxxxxxxxxxxxxxx
Signed-off-by: OGAWA Hirofumi <hirofumi@xxxxxxxxxxxxxxxxxx>
Reported-by: Jan Stancek <jstancek@xxxxxxxxxx>
Tested-by: Jan Stancek <jstancek@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
fs/fat/dir.c | 13 +++++++++++--
fs/fat/fatent.c | 3 +++
2 files changed, 14 insertions(+), 2 deletions(-)
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 81cecbe6d7cf6..971e369517a73 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -1097,8 +1097,11 @@ static int fat_zeroed_cluster(struct inode *dir, sector_t blknr, int nr_used,
err = -ENOMEM;
goto error;
}
+ /* Avoid race with userspace read via bdev */
+ lock_buffer(bhs[n]);
memset(bhs[n]->b_data, 0, sb->s_blocksize);
set_buffer_uptodate(bhs[n]);
+ unlock_buffer(bhs[n]);
mark_buffer_dirty_inode(bhs[n], dir);
n++;
@@ -1155,6 +1158,8 @@ int fat_alloc_new_dir(struct inode *dir, struct timespec *ts)
fat_time_unix2fat(sbi, ts, &time, &date, &time_cs);
de = (struct msdos_dir_entry *)bhs[0]->b_data;
+ /* Avoid race with userspace read via bdev */
+ lock_buffer(bhs[0]);
/* filling the new directory slots ("." and ".." entries) */
memcpy(de[0].name, MSDOS_DOT, MSDOS_NAME);
memcpy(de[1].name, MSDOS_DOTDOT, MSDOS_NAME);
@@ -1177,6 +1182,7 @@ int fat_alloc_new_dir(struct inode *dir, struct timespec *ts)
de[0].size = de[1].size = 0;
memset(de + 2, 0, sb->s_blocksize - 2 * sizeof(*de));
set_buffer_uptodate(bhs[0]);
+ unlock_buffer(bhs[0]);
mark_buffer_dirty_inode(bhs[0], dir);
err = fat_zeroed_cluster(dir, blknr, 1, bhs, MAX_BUF_PER_PAGE);
@@ -1234,11 +1240,14 @@ static int fat_add_new_entries(struct inode *dir, void *slots, int nr_slots,
/* fill the directory entry */
copy = min(size, sb->s_blocksize);
+ /* Avoid race with userspace read via bdev */
+ lock_buffer(bhs[n]);
memcpy(bhs[n]->b_data, slots, copy);
- slots += copy;
- size -= copy;
set_buffer_uptodate(bhs[n]);
+ unlock_buffer(bhs[n]);
mark_buffer_dirty_inode(bhs[n], dir);
+ slots += copy;
+ size -= copy;
if (!size)
break;
n++;
diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c
index 9635df94db7d9..24ed1f4e48ae2 100644
--- a/fs/fat/fatent.c
+++ b/fs/fat/fatent.c
@@ -389,8 +389,11 @@ static int fat_mirror_bhs(struct super_block *sb, struct buffer_head **bhs,
err = -ENOMEM;
goto error;
}
+ /* Avoid race with userspace read via bdev */
+ lock_buffer(c_bh);
memcpy(c_bh->b_data, bhs[n]->b_data, sb->s_blocksize);
set_buffer_uptodate(c_bh);
+ unlock_buffer(c_bh);
mark_buffer_dirty_inode(c_bh, sbi->fat_inode);
if (sb->s_flags & MS_SYNCHRONOUS)
err = sync_dirty_buffer(c_bh);
--
2.20.1
