On Tue, Aug 27, 2024 at 07:09:51AM +0200, Christoph Hellwig wrote:
> All callers of iomap_zero_range already hold invalidate_lock, so we can't
> take it again in iomap_file_buffered_write_punch_delalloc.
What about the xfs_zero_range call in xfs_file_write_checks? AFAICT we
don't hold the invalidate lock there. Did I misread that?
Also, would nested takings of the invalidate lock cause a livelock? Or
is this actually quite broken now?
--D
> Use the passed in flags argument to detect if we're called from a zeroing
> operation and don't take the lock again in this case.
>
> Signed-off-by: Christoph Hellwig <hch@xxxxxx>
> ---
> fs/iomap/buffered-io.c | 16 +++++++++++-----
> 1 file changed, 11 insertions(+), 5 deletions(-)
>
> diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
> index 34de9f58794ad5..574ca413516443 100644
> --- a/fs/iomap/buffered-io.c
> +++ b/fs/iomap/buffered-io.c
> @@ -1198,8 +1198,8 @@ static int iomap_write_delalloc_scan(struct inode *inode,
> * require sprinkling this code with magic "+ 1" and "- 1" arithmetic and expose
> * the code to subtle off-by-one bugs....
> */
> -static int iomap_write_delalloc_release(struct inode *inode,
> - loff_t start_byte, loff_t end_byte, iomap_punch_t punch)
> +static int iomap_write_delalloc_release(struct inode *inode, loff_t start_byte,
> + loff_t end_byte, unsigned flags, iomap_punch_t punch)
> {
> loff_t punch_start_byte = start_byte;
> loff_t scan_end_byte = min(i_size_read(inode), end_byte);
> @@ -1210,8 +1210,13 @@ static int iomap_write_delalloc_release(struct inode *inode,
> * folios and dirtying them via ->page_mkwrite whilst we walk the
> * cache and perform delalloc extent removal. Failing to do this can
> * leave dirty pages with no space reservation in the cache.
> + *
> + * For zeroing operations the callers already hold invalidate_lock.
> */
> - filemap_invalidate_lock(inode->i_mapping);
> + if (flags & IOMAP_ZERO)
> + rwsem_assert_held_write(&inode->i_mapping->invalidate_lock);
> + else
> + filemap_invalidate_lock(inode->i_mapping);
> while (start_byte < scan_end_byte) {
> loff_t data_end;
>
> @@ -1264,7 +1269,8 @@ static int iomap_write_delalloc_release(struct inode *inode,
> error = punch(inode, punch_start_byte,
> end_byte - punch_start_byte);
> out_unlock:
> - filemap_invalidate_unlock(inode->i_mapping);
> + if (!(flags & IOMAP_ZERO))
> + filemap_invalidate_unlock(inode->i_mapping);
> return error;
> }
>
> @@ -1328,7 +1334,7 @@ int iomap_file_buffered_write_punch_delalloc(struct inode *inode,
> if (start_byte >= end_byte)
> return 0;
>
> - return iomap_write_delalloc_release(inode, start_byte, end_byte,
> + return iomap_write_delalloc_release(inode, start_byte, end_byte, flags,
> punch);
> }
> EXPORT_SYMBOL_GPL(iomap_file_buffered_write_punch_delalloc);
> --
> 2.43.0
>
>
