From 3b8358407aac088564f7db35ea842376686d0c92 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 6 Apr 2021 19:54:53 +0800 Subject: [PATCH] btrfs: refactor btrfs_invalidatepage() for subpage support This patch will refactor btrfs_invalidatepage() for the incoming subpage support. The involved modifications are: - Use while() loop instead of "goto again;" - Use single variable to determine whether to delete extent states Each branch will also have comments why we can or cannot delete the extent states - Do qgroup free and extent states deletion per-loop Current code can only work for PAGE_SIZE == sectorsize case. This refactor also makes it clear what we do for different sectors: - Sectors without ordered extent We're completely safe to remove all extent states for the sector(s) - Sectors with ordered extent, but no Private2 bit This means the endio has already been executed, we can't remove all extent states for the sector(s). - Sectors with ordere extent, still has Private2 bit This means we need to decrease the ordered extent accounting. And then it comes to two different variants: * We have finished and removed the ordered extent Then it's the same as "sectors without ordered extent" * We didn't finished the ordered extent We can remove some extent states, but not all. Signed-off-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/inode.c | 175 +++++++++++++++++++++++++++-------------------- 1 file changed, 99 insertions(+), 76 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index e86a6113e149..f036b6e992df 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8318,15 +8318,11 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset, { struct btrfs_inode *inode = BTRFS_I(page->mapping->host); struct extent_io_tree *tree = &inode->io_tree; - struct btrfs_ordered_extent *ordered; struct extent_state *cached_state = NULL; u64 page_start = page_offset(page); u64 page_end = page_start + PAGE_SIZE - 1; - u64 start; - u64 end; + u64 cur; int inode_evicting = inode->vfs_inode.i_state & I_FREEING; - bool found_ordered = false; - bool completed_ordered = false; /* * We have page locked so no new ordered extent can be created on this @@ -8350,93 +8346,120 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset, if (!inode_evicting) lock_extent_bits(tree, page_start, page_end, &cached_state); - start = page_start; -again: - ordered = btrfs_lookup_ordered_range(inode, start, page_end - start + 1); - if (ordered) { - found_ordered = true; - end = min(page_end, - ordered->file_offset + ordered->num_bytes - 1); + cur = page_start; + while (cur < page_end) { + struct btrfs_ordered_extent *ordered; + bool delete_states; + u64 range_end; + + ordered = btrfs_lookup_first_ordered_range(inode, cur, + page_end + 1 - cur); + if (!ordered) { + range_end = page_end; + /* + * No ordered extent covering this range, we are safe + * to delete all extent states in the range. + */ + delete_states = true; + goto next; + } + if (ordered->file_offset > cur) { + /* + * There is a range between [cur, oe->file_offset) not + * covered by any ordered extent. + * We are safe to delete all extent states, and handle + * the ordered extent in the next iteration. + */ + range_end = ordered->file_offset - 1; + delete_states = true; + goto next; + } + + range_end = min(ordered->file_offset + ordered->num_bytes - 1, + page_end); + if (!PagePrivate2(page)) { + /* + * If Private2 is cleared, it means endio has already + * been executed for the range. + * We can't delete the extent states as + * btrfs_finish_ordered_io() may still use some of them. + */ + delete_states = false; + goto next; + } + ClearPagePrivate2(page); + /* * IO on this page will never be started, so we need to account * for any ordered extents now. Don't clear EXTENT_DELALLOC_NEW * here, must leave that up for the ordered extent completion. + * + * This will also unlock the range for incoming + * btrfs_finish_ordered_io(). */ if (!inode_evicting) - clear_extent_bit(tree, start, end, + clear_extent_bit(tree, cur, range_end, EXTENT_DELALLOC | EXTENT_LOCKED | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 1, 0, &cached_state); + + spin_lock_irq(&inode->ordered_tree.lock); + set_bit(BTRFS_ORDERED_TRUNCATED, &ordered->flags); + ordered->truncated_len = min(ordered->truncated_len, + cur - ordered->file_offset); + spin_unlock_irq(&inode->ordered_tree.lock); + + if (btrfs_dec_test_ordered_pending(inode, &ordered, + cur, range_end + 1 - cur, 1)) { + btrfs_finish_ordered_io(ordered); + /* + * The ordered extent has finished, now we're again + * safe to delete all extent states of the range. + */ + delete_states = true; + } else { + /* + * btrfs_finish_ordered_io() will get executed by endio + * of other pages, thus we can't delete extent states + * anymore + */ + delete_states = false; + } +next: + if (ordered) + btrfs_put_ordered_extent(ordered); /* - * A page with Private2 bit means no bio has been submitted - * covering the page, thus we have to manually do the ordered - * extent accounting. + * Qgroup reserved space handler + * Sector(s) here will be either: * - * For page without Private2, the ordered extent accounting is - * done in its endio function of the submitted bio. + * 1) Already written to disk or bio already finished + * Then its QGROUP_RESERVED bit in io_tree is already cleared. + * Qgroup will be handled by its qgroup_record then. + * btrfs_qgroup_free_data() call will do nothing here. + * + * 2) Not written to disk yet + * Then btrfs_qgroup_free_data() call will clear the + * QGROUP_RESERVED bit of its io_tree, and free the qgroup + * reserved data space. + * Since the IO will never happen for this page. */ - if (TestClearPagePrivate2(page)) { - spin_lock_irq(&inode->ordered_tree.lock); - set_bit(BTRFS_ORDERED_TRUNCATED, &ordered->flags); - ordered->truncated_len = min(ordered->truncated_len, - start - ordered->file_offset); - spin_unlock_irq(&inode->ordered_tree.lock); - - if (btrfs_dec_test_ordered_pending(inode, &ordered, - start, - end - start + 1, 1)) { - btrfs_finish_ordered_io(ordered); - completed_ordered = true; - } - } - btrfs_put_ordered_extent(ordered); + btrfs_qgroup_free_data(inode, NULL, cur, range_end + 1 - cur); if (!inode_evicting) { - cached_state = NULL; - lock_extent_bits(tree, start, end, - &cached_state); - } - - start = end + 1; - if (start < page_end) - goto again; - } - - /* - * Qgroup reserved space handler - * Page here will be either - * 1) Already written to disk or ordered extent already submitted - * Then its QGROUP_RESERVED bit in io_tree is already cleaned. - * Qgroup will be handled by its qgroup_record then. - * btrfs_qgroup_free_data() call will do nothing here. - * - * 2) Not written to disk yet - * Then btrfs_qgroup_free_data() call will clear the QGROUP_RESERVED - * bit of its io_tree, and free the qgroup reserved data space. - * Since the IO will never happen for this page. - */ - btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE); - if (!inode_evicting) { - bool delete = true; - - /* - * If there's an ordered extent for this range and we have not - * finished it ourselves, we must leave EXTENT_DELALLOC_NEW set - * in the range for the ordered extent completion. We must also - * not delete the range, otherwise we would lose that bit (and - * any other bits set in the range). Make sure EXTENT_UPTODATE - * is cleared if we don't delete, otherwise it can lead to - * corruptions if the i_size is extented later. - */ - if (found_ordered && !completed_ordered) - delete = false; - clear_extent_bit(tree, page_start, page_end, EXTENT_LOCKED | + clear_extent_bit(tree, cur, range_end, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_UPTODATE | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 1, - delete, &cached_state); - - __btrfs_releasepage(page, GFP_NOFS); + delete_states, &cached_state); + } + cur = range_end + 1; } - + /* + * We have iterated through all ordered extents of the page, the page + * should not have Private2 anymore, or the above iteration does + * something wrong. + */ + ASSERT(!PagePrivate2(page)); + if (!inode_evicting) + __btrfs_releasepage(page, GFP_NOFS); ClearPageChecked(page); clear_page_extent_mapped(page); }