block: Do not discard buffers under a mounted filesystem
Discarding blocks and buffers under a mounted filesystem is hardly
anything admin wants to do. Usually it will confuse the filesystem and
sometimes the loss of buffer_head state (including b_private field) can
even cause crashes like:
BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
PGD 0 P4D 0
Oops: 0002 [#1] SMP PTI
CPU: 4 PID: 203778 Comm: jbd2/dm-3-8 Kdump: loaded Tainted: G O --------- - - 4.18.0-147.5.0.5.h126.eulerosv2r9.x86_64 #1
Hardware name: Huawei RH2288H V3/BC11HGSA0, BIOS 1.57 08/11/2015
RIP: 0010:jbd2_journal_grab_journal_head+0x1b/0x40 [jbd2]
...
Call Trace:
__jbd2_journal_insert_checkpoint+0x23/0x70 [jbd2]
jbd2_journal_commit_transaction+0x155f/0x1b60 [jbd2]
kjournald2+0xbd/0x270 [jbd2]
So if we don't have block device open with O_EXCL already, claim the
block device while we truncate buffer cache. This makes sure any
exclusive block device user (such as filesystem) cannot operate on the
device while we are discarding buffer cache.
Reported-by: Ye Bin <yebin10@huawei.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Christoph Hellwig <hch@lst.de>
[axboe: fix !CONFIG_BLOCK error in truncate_bdev_range()]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 9cb2054..c70c41ec 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -103,6 +103,35 @@ void invalidate_bdev(struct block_device *bdev)
}
EXPORT_SYMBOL(invalidate_bdev);
+/*
+ * Drop all buffers & page cache for given bdev range. This function bails
+ * with error if bdev has other exclusive owner (such as filesystem).
+ */
+int truncate_bdev_range(struct block_device *bdev, fmode_t mode,
+ loff_t lstart, loff_t lend)
+{
+ struct block_device *claimed_bdev = NULL;
+ int err;
+
+ /*
+ * If we don't hold exclusive handle for the device, upgrade to it
+ * while we discard the buffer cache to avoid discarding buffers
+ * under live filesystem.
+ */
+ if (!(mode & FMODE_EXCL)) {
+ claimed_bdev = bdev->bd_contains;
+ err = bd_prepare_to_claim(bdev, claimed_bdev,
+ truncate_bdev_range);
+ if (err)
+ return err;
+ }
+ truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend);
+ if (claimed_bdev)
+ bd_abort_claiming(bdev, claimed_bdev, truncate_bdev_range);
+ return 0;
+}
+EXPORT_SYMBOL(truncate_bdev_range);
+
static void set_init_blocksize(struct block_device *bdev)
{
bdev->bd_inode->i_blkbits = blksize_bits(bdev_logical_block_size(bdev));
@@ -1968,7 +1997,6 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
loff_t len)
{
struct block_device *bdev = I_BDEV(bdev_file_inode(file));
- struct address_space *mapping;
loff_t end = start + len - 1;
loff_t isize;
int error;
@@ -1996,8 +2024,9 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
return -EINVAL;
/* Invalidate the page cache, including dirty pages. */
- mapping = bdev->bd_inode->i_mapping;
- truncate_inode_pages_range(mapping, start, end);
+ error = truncate_bdev_range(bdev, file->f_mode, start, end);
+ if (error)
+ return error;
switch (mode) {
case FALLOC_FL_ZERO_RANGE:
@@ -2024,7 +2053,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
* the caller will be given -EBUSY. The third argument is
* inclusive, so the rounding here is safe.
*/
- return invalidate_inode_pages2_range(mapping,
+ return invalidate_inode_pages2_range(bdev->bd_inode->i_mapping,
start >> PAGE_SHIFT,
end >> PAGE_SHIFT);
}