@@ -1170,6 +1170,7 @@ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode,
u64 delalloc_end = page_end;
u64 delalloc_to_write = 0;
int ret = 0;
+ int bit;
/* Save the dirty bitmap as our submission bitmap will be a subset of it. */
if (btrfs_is_subpage(fs_info, inode->vfs_inode.i_mapping)) {
@@ -1179,6 +1180,12 @@ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode,
bio_ctrl->submit_bitmap = 1;
}
+ for_each_set_bit(bit, &bio_ctrl->submit_bitmap, fs_info->sectors_per_page) {
+ u64 start = page_start + (bit << fs_info->sectorsize_bits);
+
+ btrfs_folio_set_writer_lock(fs_info, folio, start, fs_info->sectorsize);
+ }
+
/* Lock all (subpage) delalloc ranges inside the folio first. */
while (delalloc_start < page_end) {
delalloc_end = page_end;
@@ -1189,9 +1196,6 @@ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode,
}
set_delalloc_bitmap(folio, &delalloc_bitmap, delalloc_start,
min(delalloc_end, page_end) + 1 - delalloc_start);
- btrfs_folio_set_writer_lock(fs_info, folio, delalloc_start,
- min(delalloc_end, page_end) + 1 -
- delalloc_start);
last_delalloc_end = delalloc_end;
delalloc_start = delalloc_end + 1;
}
Currently we only mark sectors as locked if there is a *NEW* delalloc range for it. But NEW delalloc range is not the same as dirty sectors we want to submit, e.g: 0 32K 64K 96K 128K | |////////||///////| |////| 120K For above 64K page size case, writepage_delalloc() for page 0 will find and lock the delalloc range [32K, 96K), which is beyond the page boundary. Then when writepage_delalloc() is called for the page 64K, since [64K, 96K) is already locked, only [120K, 128K) will be locked. This means, although range [64K, 96K) is dirty and will be submitted later by extent_writepage_io(), it will not be marked as locked. This is fine for now, as we call btrfs_folio_end_writer_lock_bitmap() to free every non-compressed sector, and compression is only allowed for full page range. But this is not safe for future sector perfect compression support, as this can lead to double folio unlock: Thread A | Thread B ---------------------------------------+-------------------------------- | submit_one_async_extent() | |- extent_clear_unlock_delalloc() extent_writepage() | |- btrfs_folio_end_writer_lock() |- btrfs_folio_edn_writer_lock_bitmap()| |- btrfs_subpage_end_and_test_writer() | | | |- atomic_sub_and_test() | | | /* Now the atomic value is 0 */ |- if (atomic_read() == 0) | | |- folio_unlock() | |- folio_unlock() The root cause is the above range [64K, 96K) is dirtied and should also be locked but it isn't. So to make everything more consistent and prepare for the incoming sector perfect compression, mark all dirty sectors as locked. Signed-off-by: Qu Wenruo <wqu@suse.com> --- fs/btrfs/extent_io.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)