diff options
| -rw-r--r-- | fs/btrfs/extent_io.c | 80 |
1 files changed, 75 insertions, 5 deletions
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 2fb26193b795..1acbb7f1e6e3 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3784,6 +3784,54 @@ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode, } /* + * Find the first byte we need to write. + * + * For subpage, one page can contain several sectors, and + * __extent_writepage_io() will just grab all extent maps in the page + * range and try to submit all non-inline/non-compressed extents. + * + * This is a big problem for subpage, we shouldn't re-submit already written + * data at all. + * This function will lookup subpage dirty bit to find which range we really + * need to submit. + * + * Return the next dirty range in [@start, @end). + * If no dirty range is found, @start will be page_offset(page) + PAGE_SIZE. + */ +static void find_next_dirty_byte(struct btrfs_fs_info *fs_info, + struct page *page, u64 *start, u64 *end) +{ + struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; + u64 orig_start = *start; + /* Declare as unsigned long so we can use bitmap ops */ + unsigned long dirty_bitmap; + unsigned long flags; + int nbits = (orig_start - page_offset(page)) >> fs_info->sectorsize_bits; + int range_start_bit = nbits; + int range_end_bit; + + /* + * For regular sector size == page size case, since one page only + * contains one sector, we return the page offset directly. + */ + if (fs_info->sectorsize == PAGE_SIZE) { + *start = page_offset(page); + *end = page_offset(page) + PAGE_SIZE; + return; + } + + /* We should have the page locked, but just in case */ + spin_lock_irqsave(&subpage->lock, flags); + dirty_bitmap = subpage->dirty_bitmap; + spin_unlock_irqrestore(&subpage->lock, flags); + + bitmap_next_set_region(&dirty_bitmap, &range_start_bit, &range_end_bit, + BTRFS_SUBPAGE_BITMAP_SIZE); + *start = page_offset(page) + range_start_bit * fs_info->sectorsize; + *end = page_offset(page) + range_end_bit * fs_info->sectorsize; +} + +/* * helper for __extent_writepage. This calls the writepage start hooks, * and does the loop to map the page into extents and bios. * @@ -3830,6 +3878,8 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, while (cur <= end) { u64 disk_bytenr; u64 em_end; + u64 dirty_range_start = cur; + u64 dirty_range_end; u32 iosize; if (cur >= i_size) { @@ -3837,9 +3887,17 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, end, 1); break; } + + find_next_dirty_byte(fs_info, page, &dirty_range_start, + &dirty_range_end); + if (cur < dirty_range_start) { + cur = dirty_range_start; + continue; + } + em = btrfs_get_extent(inode, NULL, 0, cur, end - cur + 1); if (IS_ERR_OR_NULL(em)) { - SetPageError(page); + btrfs_page_set_error(fs_info, page, cur, end - cur + 1); ret = PTR_ERR_OR_ZERO(em); break; } @@ -3854,8 +3912,11 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, compressed = test_bit(EXTENT_FLAG_COMPRESSED, &em->flags); disk_bytenr = em->block_start + extent_offset; - /* Note that em_end from extent_map_end() is exclusive */ - iosize = min(em_end, end + 1) - cur; + /* + * Note that em_end from extent_map_end() and dirty_range_end from + * find_next_dirty_byte() are all exclusive + */ + iosize = min(min(em_end, end + 1), dirty_range_end) - cur; if (btrfs_use_zone_append(inode, em->block_start)) opf = REQ_OP_ZONE_APPEND; @@ -3885,6 +3946,14 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, page->index, cur, end); } + /* + * Although the PageDirty bit is cleared before entering this + * function, subpage dirty bit is not cleared. + * So clear subpage dirty bit here so next time we won't submit + * page for range already written to disk. + */ + btrfs_page_clear_dirty(fs_info, page, cur, iosize); + ret = submit_extent_page(opf | write_flags, wbc, &epd->bio_ctrl, page, disk_bytenr, iosize, @@ -3892,9 +3961,10 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, end_bio_extent_writepage, 0, 0, false); if (ret) { - SetPageError(page); + btrfs_page_set_error(fs_info, page, cur, iosize); if (PageWriteback(page)) - end_page_writeback(page); + btrfs_page_clear_writeback(fs_info, page, cur, + iosize); } cur += iosize; |