@@ -3909,6 +3909,16 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
if (cur >= i_size) {
btrfs_writepage_endio_finish_ordered(inode, page, cur,
end, 1);
+ /*
+ * This range is beyond isize, thus we don't need to
+ * bother writing back.
+ * But we still need to clear the dirty subpage bit, or
+ * the next time the page get dirtied, we will try to
+ * writeback the sectors with subpage diryt bits,
+ * causing writeback without ordered extent.
+ */
+ btrfs_page_clear_dirty(fs_info, page, cur,
+ end + 1 - cur);
break;
}
@@ -3959,6 +3969,7 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
else
btrfs_writepage_endio_finish_ordered(inode,
page, cur, cur + iosize - 1, 1);
+ btrfs_page_clear_dirty(fs_info, page, cur, iosize);
cur += iosize;
continue;
}
@@ -3994,6 +4005,12 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
cur += iosize;
nr++;
}
+ /*
+ * If we finishes without problem, we should not only clear page dirty,
+ * but also emptied subpage dirty bits
+ */
+ if (!ret)
+ btrfs_page_assert_not_dirty(fs_info, page);
*nr_ret = nr;
return ret;
}
@@ -548,3 +548,19 @@ IMPLEMENT_BTRFS_PAGE_OPS(writeback, set_page_writeback, end_page_writeback,
PageWriteback);
IMPLEMENT_BTRFS_PAGE_OPS(ordered, SetPageOrdered, ClearPageOrdered,
PageOrdered);
+
+void btrfs_page_assert_not_dirty(const struct btrfs_fs_info *fs_info,
+ struct page *page)
+{
+ struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
+
+ if (!IS_ENABLED(CONFIG_BTRFS_ASSERT))
+ return;
+
+ ASSERT(!PageDirty(page));
+ if (fs_info->sectorsize == PAGE_SIZE)
+ return;
+
+ ASSERT(PagePrivate(page) && page->private);
+ ASSERT(subpage->dirty_bitmap == 0);
+}
@@ -119,4 +119,11 @@ DECLARE_BTRFS_SUBPAGE_OPS(ordered);
bool btrfs_subpage_clear_and_test_dirty(const struct btrfs_fs_info *fs_info,
struct page *page, u64 start, u32 len);
+/*
+ * Extra assert to make sure not only the page dirty bit is cleared, but also
+ * subpage dirty bit is cleared.
+ */
+void btrfs_page_assert_not_dirty(const struct btrfs_fs_info *fs_info,
+ struct page *page);
+
#endif
[BUG] When running fsstress with subpage RW support, there are random BUG_ON()s triggered with the following trace: kernel BUG at fs/btrfs/file-item.c:667! Internal error: Oops - BUG: 0 [#1] SMP CPU: 1 PID: 3486 Comm: kworker/u13:2 Tainted: G WC O 5.11.0-rc4-custom+ #43 Hardware name: Radxa ROCK Pi 4B (DT) Workqueue: btrfs-worker-high btrfs_work_helper [btrfs] pstate: 60000005 (nZCv daif -PAN -UAO -TCO BTYPE=--) pc : btrfs_csum_one_bio+0x420/0x4e0 [btrfs] lr : btrfs_csum_one_bio+0x400/0x4e0 [btrfs] Call trace: btrfs_csum_one_bio+0x420/0x4e0 [btrfs] btrfs_submit_bio_start+0x20/0x30 [btrfs] run_one_async_start+0x28/0x44 [btrfs] btrfs_work_helper+0x128/0x1b4 [btrfs] process_one_work+0x22c/0x430 worker_thread+0x70/0x3a0 kthread+0x13c/0x140 ret_from_fork+0x10/0x30 [CAUSE] Above BUG_ON() means there are some bio range which doesn't have ordered extent, which indeed is worthy a BUG_ON(). Unlike regular sectorsize == PAGE_SIZE case, in subpage we have extra subpage dirty bitmap to record which range is dirty and should be written back. This means, if we submit bio for a subpage range, we do not only need to clear page dirty, but also need to clear subpage dirty bits. In __extent_writepage_io(), we will call btrfs_page_clear_dirty() for any range we submit a bio. But there is loophole, if we hit a range which is beyond isize, we just call btrfs_writepage_endio_finish_ordered() to finish the ordered io, then break out, without clearing the subpage dirty. This means, if we hit above branch, the subpage dirty bits are still there, if other range of the page get dirtied and we need to writeback that page again, we will submit bio for the old range, leaving a wild bio range which doesn't have ordered extent. [FIX] Fix it by always calling btrfs_page_clear_dirty() in __extent_writepage_io(). Also to avoid such problem from happening again, add a new assert, btrfs_page_assert_not_dirty(), to make sure both page dirty and subpage dirty bits are cleared before exiting __extent_writepage_io(). Signed-off-by: Qu Wenruo <wqu@suse.com> --- fs/btrfs/extent_io.c | 17 +++++++++++++++++ fs/btrfs/subpage.c | 16 ++++++++++++++++ fs/btrfs/subpage.h | 7 +++++++ 3 files changed, 40 insertions(+)