From 863981e96738983919de841ec669e157e6bdaeb0 Mon Sep 17 00:00:00 2001 From: André Fabian Silva Delgado Date: Sun, 11 Sep 2016 04:34:46 -0300 Subject: Linux-libre 4.7.1-gnu --- fs/btrfs/extent_io.c | 218 ++++++++++++++++++++++++++++++--------------------- 1 file changed, 128 insertions(+), 90 deletions(-) (limited to 'fs/btrfs/extent_io.c') diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index d247fc0ee..75533adef 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -726,14 +726,6 @@ next: start = last_end + 1; if (start <= end && state && !need_resched()) goto hit_next; - goto search_again; - -out: - spin_unlock(&tree->lock); - if (prealloc) - free_extent_state(prealloc); - - return 0; search_again: if (start > end) @@ -742,6 +734,14 @@ search_again: if (gfpflags_allow_blocking(mask)) cond_resched(); goto again; + +out: + spin_unlock(&tree->lock); + if (prealloc) + free_extent_state(prealloc); + + return 0; + } static void wait_on_state(struct extent_io_tree *tree, @@ -873,8 +873,14 @@ __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, bits |= EXTENT_FIRST_DELALLOC; again: if (!prealloc && gfpflags_allow_blocking(mask)) { + /* + * Don't care for allocation failure here because we might end + * up not needing the pre-allocated extent state at all, which + * is the case if we only have in the tree extent states that + * cover our input range and don't cover too any other range. + * If we end up needing a new extent state we allocate it later. + */ prealloc = alloc_extent_state(mask); - BUG_ON(!prealloc); } spin_lock(&tree->lock); @@ -1037,7 +1043,13 @@ hit_next: goto out; } - goto search_again; +search_again: + if (start > end) + goto out; + spin_unlock(&tree->lock); + if (gfpflags_allow_blocking(mask)) + cond_resched(); + goto again; out: spin_unlock(&tree->lock); @@ -1046,13 +1058,6 @@ out: return err; -search_again: - if (start > end) - goto out; - spin_unlock(&tree->lock); - if (gfpflags_allow_blocking(mask)) - cond_resched(); - goto again; } int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, @@ -1073,17 +1078,18 @@ int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, * @bits: the bits to set in this range * @clear_bits: the bits to clear in this range * @cached_state: state that we're going to cache - * @mask: the allocation mask * * This will go through and set bits for the given range. If any states exist * already in this range they are set with the given bit and cleared of the * clear_bits. This is only meant to be used by things that are mergeable, ie * converting from say DELALLOC to DIRTY. This is not meant to be used with * boundary bits like LOCK. + * + * All allocations are done with GFP_NOFS. */ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, unsigned bits, unsigned clear_bits, - struct extent_state **cached_state, gfp_t mask) + struct extent_state **cached_state) { struct extent_state *state; struct extent_state *prealloc = NULL; @@ -1098,7 +1104,7 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, btrfs_debug_check_extent_io_range(tree, start, end); again: - if (!prealloc && gfpflags_allow_blocking(mask)) { + if (!prealloc) { /* * Best effort, don't worry if extent state allocation fails * here for the first iteration. We might have a cached state @@ -1106,7 +1112,7 @@ again: * extent state allocations are needed. We'll only know this * after locking the tree. */ - prealloc = alloc_extent_state(mask); + prealloc = alloc_extent_state(GFP_NOFS); if (!prealloc && !first_iteration) return -ENOMEM; } @@ -1263,7 +1269,13 @@ hit_next: goto out; } - goto search_again; +search_again: + if (start > end) + goto out; + spin_unlock(&tree->lock); + cond_resched(); + first_iteration = false; + goto again; out: spin_unlock(&tree->lock); @@ -1271,21 +1283,11 @@ out: free_extent_state(prealloc); return err; - -search_again: - if (start > end) - goto out; - spin_unlock(&tree->lock); - if (gfpflags_allow_blocking(mask)) - cond_resched(); - first_iteration = false; - goto again; } /* wrappers around set/clear extent bit */ int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, gfp_t mask, - struct extent_changeset *changeset) + unsigned bits, struct extent_changeset *changeset) { /* * We don't support EXTENT_LOCKED yet, as current changeset will @@ -1295,7 +1297,7 @@ int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, */ BUG_ON(bits & EXTENT_LOCKED); - return __set_extent_bit(tree, start, end, bits, 0, NULL, NULL, mask, + return __set_extent_bit(tree, start, end, bits, 0, NULL, NULL, GFP_NOFS, changeset); } @@ -1308,8 +1310,7 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, } int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, gfp_t mask, - struct extent_changeset *changeset) + unsigned bits, struct extent_changeset *changeset) { /* * Don't support EXTENT_LOCKED case, same reason as @@ -1317,7 +1318,7 @@ int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, */ BUG_ON(bits & EXTENT_LOCKED); - return __clear_extent_bit(tree, start, end, bits, 0, 0, NULL, mask, + return __clear_extent_bit(tree, start, end, bits, 0, 0, NULL, GFP_NOFS, changeset); } @@ -1975,13 +1976,13 @@ int free_io_failure(struct inode *inode, struct io_failure_record *rec) set_state_failrec(failure_tree, rec->start, NULL); ret = clear_extent_bits(failure_tree, rec->start, rec->start + rec->len - 1, - EXTENT_LOCKED | EXTENT_DIRTY, GFP_NOFS); + EXTENT_LOCKED | EXTENT_DIRTY); if (ret) err = ret; ret = clear_extent_bits(&BTRFS_I(inode)->io_tree, rec->start, rec->start + rec->len - 1, - EXTENT_DAMAGED, GFP_NOFS); + EXTENT_DAMAGED); if (ret && !err) err = ret; @@ -2024,9 +2025,16 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical, bio->bi_iter.bi_size = 0; map_length = length; + /* + * Avoid races with device replace and make sure our bbio has devices + * associated to its stripes that don't go away while we are doing the + * read repair operation. + */ + btrfs_bio_counter_inc_blocked(fs_info); ret = btrfs_map_block(fs_info, WRITE, logical, &map_length, &bbio, mirror_num); if (ret) { + btrfs_bio_counter_dec(fs_info); bio_put(bio); return -EIO; } @@ -2036,6 +2044,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical, dev = bbio->stripes[mirror_num-1].dev; btrfs_put_bbio(bbio); if (!dev || !dev->bdev || !dev->writeable) { + btrfs_bio_counter_dec(fs_info); bio_put(bio); return -EIO; } @@ -2044,6 +2053,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical, if (btrfsic_submit_bio_wait(WRITE_SYNC, bio)) { /* try to remap that extent elsewhere? */ + btrfs_bio_counter_dec(fs_info); bio_put(bio); btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS); return -EIO; @@ -2053,6 +2063,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical, "read error corrected: ino %llu off %llu (dev %s sector %llu)", btrfs_ino(inode), start, rcu_str_deref(dev->name), sector); + btrfs_bio_counter_dec(fs_info); bio_put(bio); return 0; } @@ -2232,13 +2243,12 @@ int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end, /* set the bits in the private failure tree */ ret = set_extent_bits(failure_tree, start, end, - EXTENT_LOCKED | EXTENT_DIRTY, GFP_NOFS); + EXTENT_LOCKED | EXTENT_DIRTY); if (ret >= 0) ret = set_state_failrec(failure_tree, start, failrec); /* set the bits in the inode's tree */ if (ret >= 0) - ret = set_extent_bits(tree, start, end, EXTENT_DAMAGED, - GFP_NOFS); + ret = set_extent_bits(tree, start, end, EXTENT_DAMAGED); if (ret < 0) { kfree(failrec); return ret; @@ -3200,14 +3210,10 @@ int extent_read_full_page(struct extent_io_tree *tree, struct page *page, return ret; } -static noinline void update_nr_written(struct page *page, - struct writeback_control *wbc, - unsigned long nr_written) +static void update_nr_written(struct page *page, struct writeback_control *wbc, + unsigned long nr_written) { wbc->nr_to_write -= nr_written; - if (wbc->range_cyclic || (wbc->nr_to_write > 0 && - wbc->range_start == 0 && wbc->range_end == LLONG_MAX)) - page->mapping->writeback_index = page->index + nr_written; } /* @@ -3368,6 +3374,8 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, while (cur <= end) { u64 em_end; + unsigned long max_nr; + if (cur >= i_size) { if (tree->ops && tree->ops->writepage_end_io_hook) tree->ops->writepage_end_io_hook(page, cur, @@ -3423,32 +3431,23 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, continue; } - if (tree->ops && tree->ops->writepage_io_hook) { - ret = tree->ops->writepage_io_hook(page, cur, - cur + iosize - 1); - } else { - ret = 0; + max_nr = (i_size >> PAGE_SHIFT) + 1; + + set_range_writeback(tree, cur, cur + iosize - 1); + if (!PageWriteback(page)) { + btrfs_err(BTRFS_I(inode)->root->fs_info, + "page %lu not writeback, cur %llu end %llu", + page->index, cur, end); } - if (ret) { - SetPageError(page); - } else { - unsigned long max_nr = (i_size >> PAGE_SHIFT) + 1; - set_range_writeback(tree, cur, cur + iosize - 1); - if (!PageWriteback(page)) { - btrfs_err(BTRFS_I(inode)->root->fs_info, - "page %lu not writeback, cur %llu end %llu", - page->index, cur, end); - } + ret = submit_extent_page(write_flags, tree, wbc, page, + sector, iosize, pg_offset, + bdev, &epd->bio, max_nr, + end_bio_extent_writepage, + 0, 0, 0, false); + if (ret) + SetPageError(page); - ret = submit_extent_page(write_flags, tree, wbc, page, - sector, iosize, pg_offset, - bdev, &epd->bio, max_nr, - end_bio_extent_writepage, - 0, 0, 0, false); - if (ret) - SetPageError(page); - } cur = cur + iosize; pg_offset += iosize; nr++; @@ -3920,12 +3919,13 @@ static int extent_write_cache_pages(struct extent_io_tree *tree, struct inode *inode = mapping->host; int ret = 0; int done = 0; - int err = 0; int nr_to_write_done = 0; struct pagevec pvec; int nr_pages; pgoff_t index; pgoff_t end; /* Inclusive */ + pgoff_t done_index; + int range_whole = 0; int scanned = 0; int tag; @@ -3948,6 +3948,8 @@ static int extent_write_cache_pages(struct extent_io_tree *tree, } else { index = wbc->range_start >> PAGE_SHIFT; end = wbc->range_end >> PAGE_SHIFT; + if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) + range_whole = 1; scanned = 1; } if (wbc->sync_mode == WB_SYNC_ALL) @@ -3957,6 +3959,7 @@ static int extent_write_cache_pages(struct extent_io_tree *tree, retry: if (wbc->sync_mode == WB_SYNC_ALL) tag_pages_for_writeback(mapping, index, end); + done_index = index; while (!done && !nr_to_write_done && (index <= end) && (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag, min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) { @@ -3966,6 +3969,7 @@ retry: for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; + done_index = page->index; /* * At this point we hold neither mapping->tree_lock nor * lock on the page itself: the page may be truncated or @@ -4007,8 +4011,20 @@ retry: unlock_page(page); ret = 0; } - if (!err && ret < 0) - err = ret; + if (ret < 0) { + /* + * done_index is set past this page, + * so media errors will not choke + * background writeout for the entire + * file. This has consequences for + * range_cyclic semantics (ie. it may + * not be suitable for data integrity + * writeout). + */ + done_index = page->index + 1; + done = 1; + break; + } /* * the filesystem may choose to bump up nr_to_write. @@ -4020,7 +4036,7 @@ retry: pagevec_release(&pvec); cond_resched(); } - if (!scanned && !done && !err) { + if (!scanned && !done) { /* * We hit the last page and there is more work to be done: wrap * back to the start of the file @@ -4029,8 +4045,12 @@ retry: index = 0; goto retry; } + + if (wbc->range_cyclic || (wbc->nr_to_write > 0 && range_whole)) + mapping->writeback_index = done_index; + btrfs_add_delayed_iput(inode); - return err; + return ret; } static void flush_epd_write_bio(struct extent_page_data *epd) @@ -4379,8 +4399,12 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, if (ret < 0) { btrfs_free_path(path); return ret; + } else { + WARN_ON(!ret); + if (ret == 1) + ret = 0; } - WARN_ON(!ret); + path->slots[0]--; btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); found_type = found_key.type; @@ -4591,7 +4615,7 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb) if (mapped) spin_unlock(&page->mapping->private_lock); - /* One for when we alloced the page */ + /* One for when we allocated the page */ put_page(page); } while (index != 0); } @@ -4704,16 +4728,16 @@ err: } struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info, - u64 start) + u64 start, u32 nodesize) { unsigned long len; if (!fs_info) { /* * Called only from tests that don't always have a fs_info - * available, but we know that nodesize is 4096 + * available */ - len = 4096; + len = nodesize; } else { len = fs_info->tree_root->nodesize; } @@ -4809,7 +4833,7 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info, #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info, - u64 start) + u64 start, u32 nodesize) { struct extent_buffer *eb, *exists = NULL; int ret; @@ -4817,12 +4841,12 @@ struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info, eb = find_extent_buffer(fs_info, start); if (eb) return eb; - eb = alloc_dummy_extent_buffer(fs_info, start); + eb = alloc_dummy_extent_buffer(fs_info, start, nodesize); if (!eb) return NULL; eb->fs_info = fs_info; again: - ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM); + ret = radix_tree_preload(GFP_NOFS); if (ret) goto free_eb; spin_lock(&fs_info->buffer_lock); @@ -4868,18 +4892,25 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, int uptodate = 1; int ret; + if (!IS_ALIGNED(start, fs_info->tree_root->sectorsize)) { + btrfs_err(fs_info, "bad tree block start %llu", start); + return ERR_PTR(-EINVAL); + } + eb = find_extent_buffer(fs_info, start); if (eb) return eb; eb = __alloc_extent_buffer(fs_info, start, len); if (!eb) - return NULL; + return ERR_PTR(-ENOMEM); for (i = 0; i < num_pages; i++, index++) { p = find_or_create_page(mapping, index, GFP_NOFS|__GFP_NOFAIL); - if (!p) + if (!p) { + exists = ERR_PTR(-ENOMEM); goto free_eb; + } spin_lock(&mapping->private_lock); if (PagePrivate(p)) { @@ -4923,9 +4954,11 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, if (uptodate) set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); again: - ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM); - if (ret) + ret = radix_tree_preload(GFP_NOFS); + if (ret) { + exists = ERR_PTR(ret); goto free_eb; + } spin_lock(&fs_info->buffer_lock); ret = radix_tree_insert(&fs_info->buffer_radix, @@ -5309,6 +5342,11 @@ int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dstv, return ret; } +/* + * return 0 if the item is found within a page. + * return 1 if the item spans two pages. + * return -EINVAL otherwise. + */ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start, unsigned long min_len, char **map, unsigned long *map_start, @@ -5323,7 +5361,7 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start, PAGE_SHIFT; if (i != end_i) - return -EINVAL; + return 1; if (i == 0) { offset = start_offset; @@ -5751,7 +5789,7 @@ int try_release_extent_buffer(struct page *page) struct extent_buffer *eb; /* - * We need to make sure noboody is attaching this page to an eb right + * We need to make sure nobody is attaching this page to an eb right * now. */ spin_lock(&page->mapping->private_lock); -- cgit v1.2.3-54-g00ecf