diff options
Diffstat (limited to 'fs')
50 files changed, 708 insertions, 553 deletions
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 8f7d1237b7a0..a383c18e74e8 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -179,61 +179,74 @@ static int __add_prelim_ref(struct list_head *head, u64 root_id, static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, struct ulist *parents, int level, - struct btrfs_key *key, u64 time_seq, + struct btrfs_key *key_for_search, u64 time_seq, u64 wanted_disk_byte, const u64 *extent_item_pos) { - int ret; - int slot = path->slots[level]; - struct extent_buffer *eb = path->nodes[level]; + int ret = 0; + int slot; + struct extent_buffer *eb; + struct btrfs_key key; struct btrfs_file_extent_item *fi; struct extent_inode_elem *eie = NULL; u64 disk_byte; - u64 wanted_objectid = key->objectid; -add_parent: - if (level == 0 && extent_item_pos) { - fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item); - ret = check_extent_in_eb(key, eb, fi, *extent_item_pos, &eie); + if (level != 0) { + eb = path->nodes[level]; + ret = ulist_add(parents, eb->start, 0, GFP_NOFS); if (ret < 0) return ret; - } - ret = ulist_add(parents, eb->start, (unsigned long)eie, GFP_NOFS); - if (ret < 0) - return ret; - - if (level != 0) return 0; + } /* - * if the current leaf is full with EXTENT_DATA items, we must - * check the next one if that holds a reference as well. - * ref->count cannot be used to skip this check. - * repeat this until we don't find any additional EXTENT_DATA items. + * We normally enter this function with the path already pointing to + * the first item to check. But sometimes, we may enter it with + * slot==nritems. In that case, go to the next leaf before we continue. */ - while (1) { - eie = NULL; + if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) ret = btrfs_next_old_leaf(root, path, time_seq); - if (ret < 0) - return ret; - if (ret) - return 0; + while (!ret) { eb = path->nodes[0]; - for (slot = 0; slot < btrfs_header_nritems(eb); ++slot) { - btrfs_item_key_to_cpu(eb, key, slot); - if (key->objectid != wanted_objectid || - key->type != BTRFS_EXTENT_DATA_KEY) - return 0; - fi = btrfs_item_ptr(eb, slot, - struct btrfs_file_extent_item); - disk_byte = btrfs_file_extent_disk_bytenr(eb, fi); - if (disk_byte == wanted_disk_byte) - goto add_parent; + slot = path->slots[0]; + + btrfs_item_key_to_cpu(eb, &key, slot); + + if (key.objectid != key_for_search->objectid || + key.type != BTRFS_EXTENT_DATA_KEY) + break; + + fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item); + disk_byte = btrfs_file_extent_disk_bytenr(eb, fi); + + if (disk_byte == wanted_disk_byte) { + eie = NULL; + if (extent_item_pos) { + ret = check_extent_in_eb(&key, eb, fi, + *extent_item_pos, + &eie); + if (ret < 0) + break; + } + if (!ret) { + ret = ulist_add(parents, eb->start, + (unsigned long)eie, GFP_NOFS); + if (ret < 0) + break; + if (!extent_item_pos) { + ret = btrfs_next_old_leaf(root, path, + time_seq); + continue; + } + } } + ret = btrfs_next_old_item(root, path, time_seq); } - return 0; + if (ret > 0) + ret = 0; + return ret; } /* @@ -250,7 +263,6 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info, struct btrfs_path *path; struct btrfs_root *root; struct btrfs_key root_key; - struct btrfs_key key = {0}; struct extent_buffer *eb; int ret = 0; int root_level; @@ -289,17 +301,19 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info, goto out; eb = path->nodes[level]; - if (!eb) { - WARN_ON(1); - ret = 1; - goto out; + while (!eb) { + if (!level) { + WARN_ON(1); + ret = 1; + goto out; + } + level--; + eb = path->nodes[level]; } - if (level == 0) - btrfs_item_key_to_cpu(eb, &key, path->slots[0]); - - ret = add_all_parents(root, path, parents, level, &key, time_seq, - ref->wanted_disk_byte, extent_item_pos); + ret = add_all_parents(root, path, parents, level, &ref->key_for_search, + time_seq, ref->wanted_disk_byte, + extent_item_pos); out: btrfs_free_path(path); return ret; @@ -825,6 +839,7 @@ again: } ret = __add_delayed_refs(head, delayed_ref_seq, &prefs_delayed); + mutex_unlock(&head->mutex); if (ret) { spin_unlock(&delayed_refs->lock); goto out; @@ -918,8 +933,6 @@ again: } out: - if (head) - mutex_unlock(&head->mutex); btrfs_free_path(path); while (!list_empty(&prefs)) { ref = list_first_entry(&prefs, struct __prelim_ref, list); diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 15cbc2bf4ff0..8206b3900587 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1024,11 +1024,18 @@ __tree_mod_log_oldest_root(struct btrfs_fs_info *fs_info, if (!looped && !tm) return 0; /* - * we must have key remove operations in the log before the - * replace operation. + * if there are no tree operation for the oldest root, we simply + * return it. this should only happen if that (old) root is at + * level 0. */ - BUG_ON(!tm); + if (!tm) + break; + /* + * if there's an operation that's not a root replacement, we + * found the oldest version of our root. normally, we'll find a + * MOD_LOG_KEY_REMOVE_WHILE_FREEING operation here. + */ if (tm->op != MOD_LOG_ROOT_REPLACE) break; @@ -1087,11 +1094,7 @@ __tree_mod_log_rewind(struct extent_buffer *eb, u64 time_seq, tm->generation); break; case MOD_LOG_KEY_ADD: - if (tm->slot != n - 1) { - o_dst = btrfs_node_key_ptr_offset(tm->slot); - o_src = btrfs_node_key_ptr_offset(tm->slot + 1); - memmove_extent_buffer(eb, o_dst, o_src, p_size); - } + /* if a move operation is needed it's in the log */ n--; break; case MOD_LOG_MOVE_KEYS: @@ -1192,16 +1195,8 @@ get_old_root(struct btrfs_root *root, u64 time_seq) } tm = tree_mod_log_search(root->fs_info, logical, time_seq); - /* - * there was an item in the log when __tree_mod_log_oldest_root - * returned. this one must not go away, because the time_seq passed to - * us must be blocking its removal. - */ - BUG_ON(!tm); - if (old_root) - eb = alloc_dummy_extent_buffer(tm->index << PAGE_CACHE_SHIFT, - root->nodesize); + eb = alloc_dummy_extent_buffer(logical, root->nodesize); else eb = btrfs_clone_extent_buffer(root->node); btrfs_tree_read_unlock(root->node); @@ -1216,7 +1211,10 @@ get_old_root(struct btrfs_root *root, u64 time_seq) btrfs_set_header_level(eb, old_root->level); btrfs_set_header_generation(eb, old_generation); } - __tree_mod_log_rewind(eb, time_seq, tm); + if (tm) + __tree_mod_log_rewind(eb, time_seq, tm); + else + WARN_ON(btrfs_header_level(eb) != 0); extent_buffer_get(eb); return eb; @@ -2995,7 +2993,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans, static void insert_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct btrfs_disk_key *key, u64 bytenr, - int slot, int level, int tree_mod_log) + int slot, int level) { struct extent_buffer *lower; int nritems; @@ -3008,7 +3006,7 @@ static void insert_ptr(struct btrfs_trans_handle *trans, BUG_ON(slot > nritems); BUG_ON(nritems == BTRFS_NODEPTRS_PER_BLOCK(root)); if (slot != nritems) { - if (tree_mod_log && level) + if (level) tree_mod_log_eb_move(root->fs_info, lower, slot + 1, slot, nritems - slot); memmove_extent_buffer(lower, @@ -3016,7 +3014,7 @@ static void insert_ptr(struct btrfs_trans_handle *trans, btrfs_node_key_ptr_offset(slot), (nritems - slot) * sizeof(struct btrfs_key_ptr)); } - if (tree_mod_log && level) { + if (level) { ret = tree_mod_log_insert_key(root->fs_info, lower, slot, MOD_LOG_KEY_ADD); BUG_ON(ret < 0); @@ -3104,7 +3102,7 @@ static noinline int split_node(struct btrfs_trans_handle *trans, btrfs_mark_buffer_dirty(split); insert_ptr(trans, root, path, &disk_key, split->start, - path->slots[level + 1] + 1, level + 1, 1); + path->slots[level + 1] + 1, level + 1); if (path->slots[level] >= mid) { path->slots[level] -= mid; @@ -3641,7 +3639,7 @@ static noinline void copy_for_split(struct btrfs_trans_handle *trans, btrfs_set_header_nritems(l, mid); btrfs_item_key(right, &disk_key, 0); insert_ptr(trans, root, path, &disk_key, right->start, - path->slots[1] + 1, 1, 0); + path->slots[1] + 1, 1); btrfs_mark_buffer_dirty(right); btrfs_mark_buffer_dirty(l); @@ -3848,7 +3846,7 @@ again: if (mid <= slot) { btrfs_set_header_nritems(right, 0); insert_ptr(trans, root, path, &disk_key, right->start, - path->slots[1] + 1, 1, 0); + path->slots[1] + 1, 1); btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); path->nodes[0] = right; @@ -3857,7 +3855,7 @@ again: } else { btrfs_set_header_nritems(right, 0); insert_ptr(trans, root, path, &disk_key, right->start, - path->slots[1], 1, 0); + path->slots[1], 1); btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); path->nodes[0] = right; @@ -5121,6 +5119,18 @@ again: if (!path->skip_locking) { ret = btrfs_try_tree_read_lock(next); + if (!ret && time_seq) { + /* + * If we don't get the lock, we may be racing + * with push_leaf_left, holding that lock while + * itself waiting for the leaf we've currently + * locked. To solve this situation, we give up + * on our lock and cycle. + */ + btrfs_release_path(path); + cond_resched(); + goto again; + } if (!ret) { btrfs_set_path_blocking(path); btrfs_tree_read_lock(next); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 8b73b2d4deb7..fa5c45b39075 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2755,13 +2755,18 @@ static inline int btrfs_insert_empty_item(struct btrfs_trans_handle *trans, int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path); int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path, u64 time_seq); -static inline int btrfs_next_item(struct btrfs_root *root, struct btrfs_path *p) +static inline int btrfs_next_old_item(struct btrfs_root *root, + struct btrfs_path *p, u64 time_seq) { ++p->slots[0]; if (p->slots[0] >= btrfs_header_nritems(p->nodes[0])) - return btrfs_next_leaf(root, p); + return btrfs_next_old_leaf(root, p, time_seq); return 0; } +static inline int btrfs_next_item(struct btrfs_root *root, struct btrfs_path *p) +{ + return btrfs_next_old_item(root, p, 0); +} int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path); int btrfs_leaf_free_space(struct btrfs_root *root, struct extent_buffer *leaf); int __must_check btrfs_drop_snapshot(struct btrfs_root *root, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index e1890b1d3075..2936ca49b3b4 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2354,12 +2354,17 @@ retry_root_backup: BTRFS_CSUM_TREE_OBJECTID, csum_root); if (ret) goto recovery_tree_root; - csum_root->track_dirty = 1; fs_info->generation = generation; fs_info->last_trans_committed = generation; + ret = btrfs_recover_balance(fs_info); + if (ret) { + printk(KERN_WARNING "btrfs: failed to recover balance\n"); + goto fail_block_groups; + } + ret = btrfs_init_dev_stats(fs_info); if (ret) { printk(KERN_ERR "btrfs: failed to init dev_stats: %d\n", @@ -2485,20 +2490,23 @@ retry_root_backup: goto fail_trans_kthread; } - if (!(sb->s_flags & MS_RDONLY)) { - down_read(&fs_info->cleanup_work_sem); - err = btrfs_orphan_cleanup(fs_info->fs_root); - if (!err) - err = btrfs_orphan_cleanup(fs_info->tree_root); - up_read(&fs_info->cleanup_work_sem); + if (sb->s_flags & MS_RDONLY) + return 0; - if (!err) - err = btrfs_recover_balance(fs_info->tree_root); + down_read(&fs_info->cleanup_work_sem); + if ((ret = btrfs_orphan_cleanup(fs_info->fs_root)) || + (ret = btrfs_orphan_cleanup(fs_info->tree_root))) { + up_read(&fs_info->cleanup_work_sem); + close_ctree(tree_root); + return ret; + } + up_read(&fs_info->cleanup_work_sem); - if (err) { - close_ctree(tree_root); - return err; - } + ret = btrfs_resume_balance_async(fs_info); + if (ret) { + printk(KERN_WARNING "btrfs: failed to resume balance\n"); + close_ctree(tree_root); + return ret; } return 0; @@ -3426,6 +3434,7 @@ int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, mutex_unlock(&head->mutex); btrfs_put_delayed_ref(ref); + spin_lock(&delayed_refs->lock); continue; } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 4b5a1e1bdefb..6e1d36702ff7 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2347,12 +2347,10 @@ next: return count; } - static void wait_for_more_refs(struct btrfs_delayed_ref_root *delayed_refs, - unsigned long num_refs) + unsigned long num_refs, + struct list_head *first_seq) { - struct list_head *first_seq = delayed_refs->seq_head.next; - spin_unlock(&delayed_refs->lock); pr_debug("waiting for more refs (num %ld, first %p)\n", num_refs, first_seq); @@ -2381,6 +2379,7 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_delayed_ref_node *ref; struct list_head cluster; + struct list_head *first_seq = NULL; int ret; u64 delayed_start; int run_all = count == (unsigned long)-1; @@ -2436,8 +2435,10 @@ again: */ consider_waiting = 1; num_refs = delayed_refs->num_entries; + first_seq = root->fs_info->tree_mod_seq_list.next; } else { - wait_for_more_refs(delayed_refs, num_refs); + wait_for_more_refs(delayed_refs, + num_refs, first_seq); /* * after waiting, things have changed. we * dropped the lock and someone else might have diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index aaa12c1eb348..01c21b6c6d43 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3324,6 +3324,7 @@ static int extent_write_cache_pages(struct extent_io_tree *tree, writepage_t writepage, void *data, void (*flush_fn)(void *)) { + struct inode *inode = mapping->host; int ret = 0; int done = 0; int nr_to_write_done = 0; @@ -3334,6 +3335,18 @@ static int extent_write_cache_pages(struct extent_io_tree *tree, int scanned = 0; int tag; + /* + * We have to hold onto the inode so that ordered extents can do their + * work when the IO finishes. The alternative to this is failing to add + * an ordered extent if the igrab() fails there and that is a huge pain + * to deal with, so instead just hold onto the inode throughout the + * writepages operation. If it fails here we are freeing up the inode + * anyway and we'd rather not waste our time writing out stuff that is + * going to be truncated anyway. + */ + if (!igrab(inode)) + return 0; + pagevec_init(&pvec, 0); if (wbc->range_cyclic) { index = mapping->writeback_index; /* Start from prev offset */ @@ -3428,6 +3441,7 @@ retry: index = 0; goto retry; } + btrfs_add_delayed_iput(inode); return ret; } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 70dc8ca73e25..9aa01ec2138d 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1334,7 +1334,6 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, loff_t *ppos, size_t count, size_t ocount) { struct file *file = iocb->ki_filp; - struct inode *inode = fdentry(file)->d_inode; struct iov_iter i; ssize_t written; ssize_t written_buffered; @@ -1344,18 +1343,6 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, written = generic_file_direct_write(iocb, iov, &nr_segs, pos, ppos, count, ocount); - /* - * the generic O_DIRECT will update in-memory i_size after the - * DIOs are done. But our endio handlers that update the on - * disk i_size never update past the in memory i_size. So we - * need one more update here to catch any additions to the - * file - */ - if (inode->i_size != BTRFS_I(inode)->disk_i_size) { - btrfs_ordered_update_i_size(inode, inode->i_size, NULL); - mark_inode_dirty(inode); - } - if (written < 0 || written == count) return written; diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 81296c57405a..6c4e2baa9290 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -1543,29 +1543,26 @@ again: end = bitmap_info->offset + (u64)(BITS_PER_BITMAP * ctl->unit) - 1; /* - * XXX - this can go away after a few releases. - * - * since the only user of btrfs_remove_free_space is the tree logging - * stuff, and the only way to test that is under crash conditions, we - * want to have this debug stuff here just in case somethings not - * working. Search the bitmap for the space we are trying to use to - * make sure its actually there. If its not there then we need to stop - * because something has gone wrong. + * We need to search for bits in this bitmap. We could only cover some + * of the extent in this bitmap thanks to how we add space, so we need + * to search for as much as it as we can and clear that amount, and then + * go searching for the next bit. */ search_start = *offset; - search_bytes = *bytes; + search_bytes = ctl->unit; search_bytes = min(search_bytes, end - search_start + 1); ret = search_bitmap(ctl, bitmap_info, &search_start, &search_bytes); BUG_ON(ret < 0 || search_start != *offset); - if (*offset > bitmap_info->offset && *offset + *bytes > end) { - bitmap_clear_bits(ctl, bitmap_info, *offset, end - *offset + 1); - *bytes -= end - *offset + 1; - *offset = end + 1; - } else if (*offset >= bitmap_info->offset && *offset + *bytes <= end) { - bitmap_clear_bits(ctl, bitmap_info, *offset, *bytes); - *bytes = 0; - } + /* We may have found more bits than what we need */ + search_bytes = min(search_bytes, *bytes); + + /* Cannot clear past the end of the bitmap */ + search_bytes = min(search_bytes, end - search_start + 1); + + bitmap_clear_bits(ctl, bitmap_info, search_start, search_bytes); + *offset += search_bytes; + *bytes -= search_bytes; if (*bytes) { struct rb_node *next = rb_next(&bitmap_info->offset_index); @@ -1596,7 +1593,7 @@ again: * everything over again. */ search_start = *offset; - search_bytes = *bytes; + search_bytes = ctl->unit; ret = search_bitmap(ctl, bitmap_info, &search_start, &search_bytes); if (ret < 0 || search_start != *offset) @@ -1879,12 +1876,14 @@ int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group, { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_space *info; - struct btrfs_free_space *next_info = NULL; int ret = 0; spin_lock(&ctl->tree_lock); again: + if (!bytes) + goto out_lock; + info = tree_search_offset(ctl, offset, 0, 0); if (!info) { /* @@ -1905,88 +1904,48 @@ again: } } - if (info->bytes < bytes && rb_next(&info->offset_index)) { - u64 end; - next_info = rb_entry(rb_next(&info->offset_index), - struct btrfs_free_space, - offset_index); - - if (next_info->bitmap) - end = next_info->offset + - BITS_PER_BITMAP * ctl->unit - 1; - else - end = next_info->offset + next_info->bytes; - - if (next_info->bytes < bytes || - next_info->offset > offset || offset > end) { - printk(KERN_CRIT "Found free space at %llu, size %llu," - " trying to use %llu\n", - (unsigned long long)info->offset, - (unsigned long long)info->bytes, - (unsigned long long)bytes); - WARN_ON(1); - ret = -EINVAL; - goto out_lock; - } - - info = next_info; - } - - if (info->bytes == bytes) { + if (!info->bitmap) { unlink_free_space(ctl, info); - if (info->bitmap) { - kfree(info->bitmap); - ctl->total_bitmaps--; - } - kmem_cache_free(btrfs_free_space_cachep, info); - ret = 0; - goto out_lock; - } - - if (!info->bitmap && info->offset == offset) { - unlink_free_space(ctl, info); - info->offset += bytes; - info->bytes -= bytes; - ret = link_free_space(ctl, info); - WARN_ON(ret); - goto out_lock; - } + if (offset == info->offset) { + u64 to_free = min(bytes, info->bytes); + + info->bytes -= to_free; + info->offset += to_free; + if (info->bytes) { + ret = link_free_space(ctl, info); + WARN_ON(ret); + } else { + kmem_cache_free(btrfs_free_space_cachep, info); + } - if (!info->bitmap && info->offset <= offset && - info->offset + info->bytes >= offset + bytes) { - u64 old_start = info->offset; - /* - * we're freeing space in the middle of the info, - * this can happen during tree log replay - * - * first unlink the old info and then - * insert it again after the hole we're creating - */ - unlink_free_space(ctl, info); - if (offset + bytes < info->offset + info->bytes) { - u64 old_end = info->offset + info->bytes; + offset += to_free; + bytes -= to_free; + goto again; + } else { + u64 old_end = info->bytes + info->offset; - info->offset = offset + bytes; - info->bytes = old_end - info->offset; + info->bytes = offset - info->offset; ret = link_free_space(ctl, info); WARN_ON(ret); if (ret) goto out_lock; - } else { - /* the hole we're creating ends at the end - * of the info struct, just free the info - */ - kmem_cache_free(btrfs_free_space_cachep, info); - } - spin_unlock(&ctl->tree_lock); - /* step two, insert a new info struct to cover - * anything before the hole - */ - ret = btrfs_add_free_space(block_group, old_start, - offset - old_start); - WARN_ON(ret); /* -ENOMEM */ - goto out; + /* Not enough bytes in this entry to satisfy us */ + if (old_end < offset + bytes) { + bytes -= old_end - offset; + offset = old_end; + goto again; + } else if (old_end == offset + bytes) { + /* all done */ + goto out_lock; + } + spin_unlock(&ctl->tree_lock); + + ret = btrfs_add_free_space(block_group, offset + bytes, + old_end - (offset + bytes)); + WARN_ON(ret); + goto out; + } } ret = remove_from_bitmap(ctl, info, &offset, &bytes); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a4f02501da40..a7d1921ac76b 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -987,7 +987,7 @@ static noinline void async_cow_start(struct btrfs_work *work) async_cow->start, async_cow->end, async_cow, &num_added); if (num_added == 0) { - iput(async_cow->inode); + btrfs_add_delayed_iput(async_cow->inode); async_cow->inode = NULL; } } @@ -1023,7 +1023,7 @@ static noinline void async_cow_free(struct btrfs_work *work) struct async_cow *async_cow; async_cow = container_of(work, struct async_cow, work); if (async_cow->inode) - iput(async_cow->inode); + btrfs_add_delayed_iput(async_cow->inode); kfree(async_cow); } @@ -3754,7 +3754,7 @@ void btrfs_evict_inode(struct inode *inode) btrfs_wait_ordered_range(inode, 0, (u64)-1); if (root->fs_info->log_root_recovering) { - BUG_ON(!test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, + BUG_ON(test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, &BTRFS_I(inode)->runtime_flags)); goto no_delete; } @@ -5876,8 +5876,17 @@ map: bh_result->b_size = len; bh_result->b_bdev = em->bdev; set_buffer_mapped(bh_result); - if (create && !test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) - set_buffer_new(bh_result); + if (create) { + if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) + set_buffer_new(bh_result); + + /* + * Need to update the i_size under the extent lock so buffered + * readers will get the updated i_size when we unlock. + */ + if (start + len > i_size_read(inode)) + i_size_write(inode, start + len); + } free_extent_map(em); @@ -6360,12 +6369,48 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, */ ordered = btrfs_lookup_ordered_range(inode, lockstart, lockend - lockstart + 1); - if (!ordered) + + /* + * We need to make sure there are no buffered pages in this + * range either, we could have raced between the invalidate in + * generic_file_direct_write and locking the extent. The + * invalidate needs to happen so that reads after a write do not + * get stale data. + */ + if (!ordered && (!writing || + !test_range_bit(&BTRFS_I(inode)->io_tree, + lockstart, lockend, EXTENT_UPTODATE, 0, + cached_state))) break; + unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend, &cached_state, GFP_NOFS); - btrfs_start_ordered_extent(inode, ordered, 1); - btrfs_put_ordered_extent(ordered); + + if (ordered) { + btrfs_start_ordered_extent(inode, ordered, 1); + btrfs_put_ordered_extent(ordered); + } else { + /* Screw you mmap */ + ret = filemap_write_and_wait_range(file->f_mapping, + lockstart, + lockend); + if (ret) + goto out; + + /* + * If we found a page that couldn't be invalidated just + * fall back to buffered. + */ + ret = invalidate_inode_pages2_range(file->f_mapping, + lockstart >> PAGE_CACHE_SHIFT, + lockend >> PAGE_CACHE_SHIFT); + if (ret) { + if (ret == -EBUSY) + ret = 0; + goto out; + } + } + cond_resched(); } diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h index 497c530724cf..e440aa653c30 100644 --- a/fs/btrfs/ioctl.h +++ b/fs/btrfs/ioctl.h @@ -339,7 +339,7 @@ struct btrfs_ioctl_get_dev_stats { #define BTRFS_IOC_WAIT_SYNC _IOW(BTRFS_IOCTL_MAGIC, 22, __u64) #define BTRFS_IOC_SNAP_CREATE_V2 _IOW(BTRFS_IOCTL_MAGIC, 23, \ struct btrfs_ioctl_vol_args_v2) -#define BTRFS_IOC_SUBVOL_GETFLAGS _IOW(BTRFS_IOCTL_MAGIC, 25, __u64) +#define BTRFS_IOC_SUBVOL_GETFLAGS _IOR(BTRFS_IOCTL_MAGIC, 25, __u64) #define BTRFS_IOC_SUBVOL_SETFLAGS _IOW(BTRFS_IOCTL_MAGIC, 26, __u64) #define BTRFS_IOC_SCRUB _IOWR(BTRFS_IOCTL_MAGIC, 27, \ struct btrfs_ioctl_scrub_args) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 0eb9a4da069e..e23991574fdf 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1187,6 +1187,10 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) if (ret) goto restore; + ret = btrfs_resume_balance_async(fs_info); + if (ret) + goto restore; + sb->s_flags &= ~MS_RDONLY; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 2017d0ff511c..8abeae4224f9 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -690,6 +690,8 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans, kfree(name); iput(inode); + + btrfs_run_delayed_items(trans, root); return ret; } @@ -895,6 +897,7 @@ again: ret = btrfs_unlink_inode(trans, root, dir, inode, victim_name, victim_name_len); + btrfs_run_delayed_items(trans, root); } kfree(victim_name); ptr = (unsigned long)(victim_ref + 1) + victim_name_len; @@ -1475,6 +1478,9 @@ again: ret = btrfs_unlink_inode(trans, root, dir, inode, name, name_len); BUG_ON(ret); + + btrfs_run_delayed_items(trans, root); + kfree(name); iput(inode); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 8a3d2594b807..ecaad40e7ef4 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2845,31 +2845,48 @@ out: static int balance_kthread(void *data) { - struct btrfs_balance_control *bctl = - (struct btrfs_balance_control *)data; - struct btrfs_fs_info *fs_info = bctl->fs_info; + struct btrfs_fs_info *fs_info = data; int ret = 0; mutex_lock(&fs_info->volume_mutex); mutex_lock(&fs_info->balance_mutex); - set_balance_control(bctl); - - if (btrfs_test_opt(fs_info->tree_root, SKIP_BALANCE)) { - printk(KERN_INFO "btrfs: force skipping balance\n"); - } else { + if (fs_info->balance_ctl) { printk(KERN_INFO "btrfs: continuing balance\n"); - ret = btrfs_balance(bctl, NULL); + ret = btrfs_balance(fs_info->balance_ctl, NULL); } mutex_unlock(&fs_info->balance_mutex); mutex_unlock(&fs_info->volume_mutex); + return ret; } -int btrfs_recover_balance(struct btrfs_root *tree_root) +int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info) { struct task_struct *tsk; + + spin_lock(&fs_info->balance_lock); + if (!fs_info->balance_ctl) { + spin_unlock(&fs_info->balance_lock); + return 0; + } + spin_unlock(&fs_info->balance_lock); + + if (btrfs_test_opt(fs_info->tree_root, SKIP_BALANCE)) { + printk(KERN_INFO "btrfs: force skipping balance\n"); + return 0; + } + + tsk = kthread_run(balance_kthread, fs_info, "btrfs-balance"); + if (IS_ERR(tsk)) + return PTR_ERR(tsk); + + return 0; +} + +int btrfs_recover_balance(struct btrfs_fs_info *fs_info) +{ struct btrfs_balance_control *bctl; struct btrfs_balance_item *item; struct btrfs_disk_balance_args disk_bargs; @@ -2882,29 +2899,30 @@ int btrfs_recover_balance(struct btrfs_root *tree_root) if (!path) return -ENOMEM; - bctl = kzalloc(sizeof(*bctl), GFP_NOFS); - if (!bctl) { - ret = -ENOMEM; - goto out; - } - key.objectid = BTRFS_BALANCE_OBJECTID; key.type = BTRFS_BALANCE_ITEM_KEY; key.offset = 0; - ret = btrfs_search_slot(NULL, tree_root, &key, path, 0, 0); + ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0); if (ret < 0) - goto out_bctl; + goto out; if (ret > 0) { /* ret = -ENOENT; */ ret = 0; - goto out_bctl; + goto out; + } + + bctl = kzalloc(sizeof(*bctl), GFP_NOFS); + if (!bctl) { + ret = -ENOMEM; + goto out; } leaf = path->nodes[0]; item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_balance_item); - bctl->fs_info = tree_root->fs_info; - bctl->flags = btrfs_balance_flags(leaf, item) | BTRFS_BALANCE_RESUME; + bctl->fs_info = fs_info; + bctl->flags = btrfs_balance_flags(leaf, item); + bctl->flags |= BTRFS_BALANCE_RESUME; btrfs_balance_data(leaf, item, &disk_bargs); btrfs_disk_balance_args_to_cpu(&bctl->data, &disk_bargs); @@ -2913,14 +2931,13 @@ int btrfs_recover_balance(struct btrfs_root *tree_root) btrfs_balance_sys(leaf, item, &disk_bargs); btrfs_disk_balance_args_to_cpu(&bctl->sys, &disk_bargs); - tsk = kthread_run(balance_kthread, bctl, "btrfs-balance"); - if (IS_ERR(tsk)) - ret = PTR_ERR(tsk); - else - goto out; + mutex_lock(&fs_info->volume_mutex); + mutex_lock(&fs_info->balance_mutex); -out_bctl: - kfree(bctl); + set_balance_control(bctl); + + mutex_unlock(&fs_info->balance_mutex); + mutex_unlock(&fs_info->volume_mutex); out: btrfs_free_path(path); return ret; @@ -4061,16 +4078,18 @@ static void btrfs_end_bio(struct bio *bio, int err) BUG_ON(stripe_index >= bbio->num_stripes); dev = bbio->stripes[stripe_index].dev; - if (bio->bi_rw & WRITE) - btrfs_dev_stat_inc(dev, - BTRFS_DEV_STAT_WRITE_ERRS); - else - btrfs_dev_stat_inc(dev, - BTRFS_DEV_STAT_READ_ERRS); - if ((bio->bi_rw & WRITE_FLUSH) == WRITE_FLUSH) - btrfs_dev_stat_inc(dev, - BTRFS_DEV_STAT_FLUSH_ERRS); - btrfs_dev_stat_print_on_error(dev); + if (dev->bdev) { + if (bio->bi_rw & WRITE) + btrfs_dev_stat_inc(dev, + BTRFS_DEV_STAT_WRITE_ERRS); + else + btrfs_dev_stat_inc(dev, + BTRFS_DEV_STAT_READ_ERRS); + if ((bio->bi_rw & WRITE_FLUSH) == WRITE_FLUSH) + btrfs_dev_stat_inc(dev, + BTRFS_DEV_STAT_FLUSH_ERRS); + btrfs_dev_stat_print_on_error(dev); + } } } diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 74366f27a76b..95f6637614db 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -281,7 +281,8 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size); int btrfs_init_new_device(struct btrfs_root *root, char *path); int btrfs_balance(struct btrfs_balance_control *bctl, struct btrfs_ioctl_balance_args *bargs); -int btrfs_recover_balance(struct btrfs_root *tree_root); +int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info); +int btrfs_recover_balance(struct btrfs_fs_info *fs_info); int btrfs_pause_balance(struct btrfs_fs_info *fs_info); int btrfs_cancel_balance(struct btrfs_fs_info *fs_info); int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 173b1d22e59b..8b67304e4b80 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -54,7 +54,12 @@ (CONGESTION_ON_THRESH(congestion_kb) - \ (CONGESTION_ON_THRESH(congestion_kb) >> 2)) - +static inline struct ceph_snap_context *page_snap_context(struct page *page) +{ + if (PagePrivate(page)) + return (void *)page->private; + return NULL; +} /* * Dirty a page. Optimistically adjust accounting, on the assumption @@ -142,10 +147,9 @@ static void ceph_invalidatepage(struct page *page, unsigned long offset) { struct inode *inode; struct ceph_inode_info *ci; - struct ceph_snap_context *snapc = (void *)page->private; + struct ceph_snap_context *snapc = page_snap_context(page); BUG_ON(!PageLocked(page)); - BUG_ON(!page->private); BUG_ON(!PagePrivate(page)); BUG_ON(!page->mapping); @@ -182,7 +186,6 @@ static int ceph_releasepage(struct page *page, gfp_t g) struct inode *inode = page->mapping ? page->mapping->host : NULL; dout("%p releasepage %p idx %lu\n", inode, page, page->index); WARN_ON(PageDirty(page)); - WARN_ON(page->private); WARN_ON(PagePrivate(page)); return 0; } @@ -443,7 +446,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) osdc = &fsc->client->osdc; /* verify this is a writeable snap context */ - snapc = (void *)page->private; + snapc = page_snap_context(page); if (snapc == NULL) { dout("writepage %p page %p not dirty?\n", inode, page); goto out; @@ -451,7 +454,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) oldest = get_oldest_context(inode, &snap_size); if (snapc->seq > oldest->seq) { dout("writepage %p page %p snapc %p not writeable - noop\n", - inode, page, (void *)page->private); + inode, page, snapc); /* we should only noop if called by kswapd */ WARN_ON((current->flags & PF_MEMALLOC) == 0); ceph_put_snap_context(oldest); @@ -591,7 +594,7 @@ static void writepages_finish(struct ceph_osd_request *req, clear_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC); - ceph_put_snap_context((void *)page->private); + ceph_put_snap_context(page_snap_context(page)); page->private = 0; ClearPagePrivate(page); dout("unlocking %d %p\n", i, page); @@ -795,7 +798,7 @@ get_more_pages: } /* only if matching snap context */ - pgsnapc = (void *)page->private; + pgsnapc = page_snap_context(page); if (pgsnapc->seq > snapc->seq) { dout("page snapc %p %lld > oldest %p %lld\n", pgsnapc, pgsnapc->seq, snapc, snapc->seq); @@ -984,7 +987,7 @@ retry_locked: BUG_ON(!ci->i_snap_realm); down_read(&mdsc->snap_rwsem); BUG_ON(!ci->i_snap_realm->cached_context); - snapc = (void *)page->private; + snapc = page_snap_context(page); if (snapc && snapc != ci->i_head_snapc) { /* * this page is already dirty in another (older) snap diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 78db68a5cf44..0ae86ddf2213 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1653,24 +1653,26 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, * If yes, we have encountered a double deliminator * reset the NULL character to the deliminator */ - if (tmp_end < end && tmp_end[1] == delim) + if (tmp_end < end && tmp_end[1] == delim) { tmp_end[0] = delim; - /* Keep iterating until we get to a single deliminator - * OR the end - */ - while ((tmp_end = strchr(tmp_end, delim)) != NULL && - (tmp_end[1] == delim)) { - tmp_end = (char *) &tmp_end[2]; - } + /* Keep iterating until we get to a single + * deliminator OR the end + */ + while ((tmp_end = strchr(tmp_end, delim)) + != NULL && (tmp_end[1] == delim)) { + tmp_end = (char *) &tmp_end[2]; + } - /* Reset var options to point to next element */ - if (tmp_end) { - tmp_end[0] = '\0'; - options = (char *) &tmp_end[1]; - } else - /* Reached the end of the mount option string */ - options = end; + /* Reset var options to point to next element */ + if (tmp_end) { + tmp_end[0] = '\0'; + options = (char *) &tmp_end[1]; + } else + /* Reached the end of the mount option + * string */ + options = end; + } /* Now build new password string */ temp_len = strlen(value); @@ -3493,18 +3495,15 @@ cifs_negotiate_rsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info) * MS-CIFS indicates that servers are only limited by the client's * bufsize for reads, testing against win98se shows that it throws * INVALID_PARAMETER errors if you try to request too large a read. + * OS/2 just sends back short reads. * - * If the server advertises a MaxBufferSize of less than one page, - * assume that it also can't satisfy reads larger than that either. - * - * FIXME: Is there a better heuristic for this? + * If the server doesn't advertise CAP_LARGE_READ_X, then assume that + * it can't handle a read request larger than its MaxBufferSize either. */ if (tcon->unix_ext && (unix_cap & CIFS_UNIX_LARGE_READ_CAP)) defsize = CIFS_DEFAULT_IOSIZE; else if (server->capabilities & CAP_LARGE_READ_X) defsize = CIFS_DEFAULT_NON_POSIX_RSIZE; - else if (server->maxBuf >= PAGE_CACHE_SIZE) - defsize = CIFSMaxBufSize; else defsize = server->maxBuf - sizeof(READ_RSP); diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c index 69f994a7d524..0dbe58a8b172 100644 --- a/fs/ecryptfs/kthread.c +++ b/fs/ecryptfs/kthread.c @@ -149,7 +149,7 @@ int ecryptfs_privileged_open(struct file **lower_file, (*lower_file) = dentry_open(lower_dentry, lower_mnt, flags, cred); if (!IS_ERR(*lower_file)) goto out; - if (flags & O_RDONLY) { + if ((flags & O_ACCMODE) == O_RDONLY) { rc = PTR_ERR((*lower_file)); goto out; } diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c index 3a06f4043df4..c0038f6566d4 100644 --- a/fs/ecryptfs/miscdev.c +++ b/fs/ecryptfs/miscdev.c @@ -49,7 +49,10 @@ ecryptfs_miscdev_poll(struct file *file, poll_table *pt) mutex_lock(&ecryptfs_daemon_hash_mux); /* TODO: Just use file->private_data? */ rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns()); - BUG_ON(rc || !daemon); + if (rc || !daemon) { + mutex_unlock(&ecryptfs_daemon_hash_mux); + return -EINVAL; + } mutex_lock(&daemon->mux); mutex_unlock(&ecryptfs_daemon_hash_mux); if (daemon->flags & ECRYPTFS_DAEMON_ZOMBIE) { @@ -122,6 +125,7 @@ ecryptfs_miscdev_open(struct inode *inode, struct file *file) goto out_unlock_daemon; } daemon->flags |= ECRYPTFS_DAEMON_MISCDEV_OPEN; + file->private_data = daemon; atomic_inc(&ecryptfs_num_miscdev_opens); out_unlock_daemon: mutex_unlock(&daemon->mux); @@ -152,9 +156,9 @@ ecryptfs_miscdev_release(struct inode *inode, struct file *file) mutex_lock(&ecryptfs_daemon_hash_mux); rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns()); - BUG_ON(rc || !daemon); + if (rc || !daemon) + daemon = file->private_data; mutex_lock(&daemon->mux); - BUG_ON(daemon->pid != task_pid(current)); BUG_ON(!(daemon->flags & ECRYPTFS_DAEMON_MISCDEV_OPEN)); daemon->flags &= ~ECRYPTFS_DAEMON_MISCDEV_OPEN; atomic_dec(&ecryptfs_num_miscdev_opens); @@ -191,31 +195,32 @@ int ecryptfs_send_miscdev(char *data, size_t data_size, struct ecryptfs_msg_ctx *msg_ctx, u8 msg_type, u16 msg_flags, struct ecryptfs_daemon *daemon) { - int rc = 0; + struct ecryptfs_message *msg; - mutex_lock(&msg_ctx->mux); - msg_ctx->msg = kmalloc((sizeof(*msg_ctx->msg) + data_size), - GFP_KERNEL); - if (!msg_ctx->msg) { - rc = -ENOMEM; + msg = kmalloc((sizeof(*msg) + data_size), GFP_KERNEL); + if (!msg) { printk(KERN_ERR "%s: Out of memory whilst attempting " "to kmalloc(%zd, GFP_KERNEL)\n", __func__, - (sizeof(*msg_ctx->msg) + data_size)); - goto out_unlock; + (sizeof(*msg) + data_size)); + return -ENOMEM; } + + mutex_lock(&msg_ctx->mux); + msg_ctx->msg = msg; msg_ctx->msg->index = msg_ctx->index; msg_ctx->msg->data_len = data_size; msg_ctx->type = msg_type; memcpy(msg_ctx->msg->data, data, data_size); msg_ctx->msg_size = (sizeof(*msg_ctx->msg) + data_size); - mutex_lock(&daemon->mux); list_add_tail(&msg_ctx->daemon_out_list, &daemon->msg_ctx_out_queue); + mutex_unlock(&msg_ctx->mux); + + mutex_lock(&daemon->mux); daemon->num_queued_msg_ctx++; wake_up_interruptible(&daemon->wait); mutex_unlock(&daemon->mux); -out_unlock: - mutex_unlock(&msg_ctx->mux); - return rc; + + return 0; } /* @@ -269,8 +274,16 @@ ecryptfs_miscdev_read(struct file *file, char __user *buf, size_t count, mutex_lock(&ecryptfs_daemon_hash_mux); /* TODO: Just use file->private_data? */ rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns()); - BUG_ON(rc || !daemon); + if (rc || !daemon) { + mutex_unlock(&ecryptfs_daemon_hash_mux); + return -EINVAL; + } mutex_lock(&daemon->mux); + if (task_pid(current) != daemon->pid) { + mutex_unlock(&daemon->mux); + mutex_unlock(&ecryptfs_daemon_hash_mux); + return -EPERM; + } if (daemon->flags & ECRYPTFS_DAEMON_ZOMBIE) { rc = 0; mutex_unlock(&ecryptfs_daemon_hash_mux); @@ -307,9 +320,6 @@ check_list: * message from the queue; try again */ goto check_list; } - BUG_ON(euid != daemon->euid); - BUG_ON(current_user_ns() != daemon->user_ns); - BUG_ON(task_pid(current) != daemon->pid); msg_ctx = list_first_entry(&daemon->msg_ctx_out_queue, struct ecryptfs_msg_ctx, daemon_out_list); BUG_ON(!msg_ctx); diff --git a/fs/exec.c b/fs/exec.c index a79786a8d2c8..da27b91ff1e8 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -819,10 +819,10 @@ static int exec_mmap(struct mm_struct *mm) /* Notify parent that we're no longer interested in the old VM */ tsk = current; old_mm = current->mm; - sync_mm_rss(old_mm); mm_release(tsk, old_mm); if (old_mm) { + sync_mm_rss(old_mm); /* * Make sure that if there is a core dump in progress * for the old mm, we get out and die instead of going diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 17ba6b995659..f005b5bebdc7 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -207,7 +207,6 @@ error_0: static void nfs4_shutdown_session(struct nfs_client *clp) { if (nfs4_has_session(clp)) { - nfs4_deviceid_purge_client(clp); nfs4_destroy_session(clp->cl_session); nfs4_destroy_clientid(clp); } diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 3168f6e3d4d4..9a4cbfc85d81 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -490,6 +490,7 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) dreq->error = -EIO; spin_unlock(cinfo.lock); } + nfs_release_request(req); } nfs_pageio_complete(&desc); diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index b5b86a05059c..864c51e4b400 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -57,6 +57,11 @@ unsigned int nfs_idmap_cache_timeout = 600; static const struct cred *id_resolver_cache; static struct key_type key_type_id_resolver_legacy; +struct idmap { + struct rpc_pipe *idmap_pipe; + struct key_construction *idmap_key_cons; + struct mutex idmap_mutex; +}; /** * nfs_fattr_init_names - initialise the nfs_fattr owner_name/group_name fields @@ -310,9 +315,11 @@ static ssize_t nfs_idmap_get_key(const char *name, size_t namelen, name, namelen, type, data, data_size, NULL); if (ret < 0) { + mutex_lock(&idmap->idmap_mutex); ret = nfs_idmap_request_key(&key_type_id_resolver_legacy, name, namelen, type, data, data_size, idmap); + mutex_unlock(&idmap->idmap_mutex); } return ret; } @@ -354,11 +361,6 @@ static int nfs_idmap_lookup_id(const char *name, size_t namelen, const char *typ /* idmap classic begins here */ module_param(nfs_idmap_cache_timeout, int, 0644); -struct idmap { - struct rpc_pipe *idmap_pipe; - struct key_construction *idmap_key_cons; -}; - enum { Opt_find_uid, Opt_find_gid, Opt_find_user, Opt_find_group, Opt_find_err }; @@ -469,6 +471,7 @@ nfs_idmap_new(struct nfs_client *clp) return error; } idmap->idmap_pipe = pipe; + mutex_init(&idmap->idmap_mutex); clp->cl_idmap = idmap; return 0; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index e605d695dbcb..f7296983eba6 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1530,7 +1530,6 @@ static inline void nfs4_init_once(struct nfs_inode *nfsi) nfsi->delegation_state = 0; init_rwsem(&nfsi->rwsem); nfsi->layout = NULL; - atomic_set(&nfsi->commit_info.rpcs_out, 0); #endif } @@ -1545,6 +1544,7 @@ static void init_once(void *foo) INIT_LIST_HEAD(&nfsi->commit_info.list); nfsi->npages = 0; nfsi->commit_info.ncommit = 0; + atomic_set(&nfsi->commit_info.rpcs_out, 0); atomic_set(&nfsi->silly_count, 1); INIT_HLIST_HEAD(&nfsi->silly_list); init_waitqueue_head(&nfsi->waitqueue); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index b8323aa7b543..bbc49caa7a82 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -70,6 +70,10 @@ find_pnfs_driver(u32 id) spin_lock(&pnfs_spinlock); local = find_pnfs_driver_locked(id); + if (local != NULL && !try_module_get(local->owner)) { + dprintk("%s: Could not grab reference on module\n", __func__); + local = NULL; + } spin_unlock(&pnfs_spinlock); return local; } @@ -80,6 +84,9 @@ unset_pnfs_layoutdriver(struct nfs_server *nfss) if (nfss->pnfs_curr_ld) { if (nfss->pnfs_curr_ld->clear_layoutdriver) nfss->pnfs_curr_ld->clear_layoutdriver(nfss); + /* Decrement the MDS count. Purge the deviceid cache if zero */ + if (atomic_dec_and_test(&nfss->nfs_client->cl_mds_count)) + nfs4_deviceid_purge_client(nfss->nfs_client); module_put(nfss->pnfs_curr_ld->owner); } nfss->pnfs_curr_ld = NULL; @@ -115,10 +122,6 @@ set_pnfs_layoutdriver(struct nfs_server *server, const struct nfs_fh *mntfh, goto out_no_driver; } } - if (!try_module_get(ld_type->owner)) { - dprintk("%s: Could not grab reference on module\n", __func__); - goto out_no_driver; - } server->pnfs_curr_ld = ld_type; if (ld_type->set_layoutdriver && ld_type->set_layoutdriver(server, mntfh)) { @@ -127,6 +130,8 @@ set_pnfs_layoutdriver(struct nfs_server *server, const struct nfs_fh *mntfh, module_put(ld_type->owner); goto out_no_driver; } + /* Bump the MDS count */ + atomic_inc(&server->nfs_client->cl_mds_count); dprintk("%s: pNFS module for %u set\n", __func__, id); return; diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index 08a07a218d26..57ceaf33d177 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -191,6 +191,8 @@ void nilfs_remove_all_gcinodes(struct the_nilfs *nilfs) while (!list_empty(head)) { ii = list_first_entry(head, struct nilfs_inode_info, i_dirty); list_del_init(&ii->i_dirty); + truncate_inode_pages(&ii->vfs_inode.i_data, 0); + nilfs_btnode_cache_clear(&ii->i_btnode_cache); iput(&ii->vfs_inode); } } diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 0e72ad6f22aa..88e11fb346b6 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2309,6 +2309,8 @@ nilfs_remove_written_gcinodes(struct the_nilfs *nilfs, struct list_head *head) if (!test_bit(NILFS_I_UPDATED, &ii->i_state)) continue; list_del_init(&ii->i_dirty); + truncate_inode_pages(&ii->vfs_inode.i_data, 0); + nilfs_btnode_cache_clear(&ii->i_btnode_cache); iput(&ii->vfs_inode); } } diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 81a4cd22f80b..4f7795fb5fc0 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -456,7 +456,7 @@ static void ocfs2_update_lock_stats(struct ocfs2_lock_res *res, int level, stats->ls_gets++; stats->ls_total += ktime_to_ns(kt); /* overflow */ - if (unlikely(stats->ls_gets) == 0) { + if (unlikely(stats->ls_gets == 0)) { stats->ls_gets++; stats->ls_total = ktime_to_ns(kt); } @@ -3932,6 +3932,8 @@ unqueue: static void ocfs2_schedule_blocked_lock(struct ocfs2_super *osb, struct ocfs2_lock_res *lockres) { + unsigned long flags; + assert_spin_locked(&lockres->l_lock); if (lockres->l_flags & OCFS2_LOCK_FREEING) { @@ -3945,21 +3947,22 @@ static void ocfs2_schedule_blocked_lock(struct ocfs2_super *osb, lockres_or_flags(lockres, OCFS2_LOCK_QUEUED); - spin_lock(&osb->dc_task_lock); + spin_lock_irqsave(&osb->dc_task_lock, flags); if (list_empty(&lockres->l_blocked_list)) { list_add_tail(&lockres->l_blocked_list, &osb->blocked_lock_list); osb->blocked_lock_count++; } - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); } static void ocfs2_downconvert_thread_do_work(struct ocfs2_super *osb) { unsigned long processed; + unsigned long flags; struct ocfs2_lock_res *lockres; - spin_lock(&osb->dc_task_lock); + spin_lock_irqsave(&osb->dc_task_lock, flags); /* grab this early so we know to try again if a state change and * wake happens part-way through our work */ osb->dc_work_sequence = osb->dc_wake_sequence; @@ -3972,38 +3975,40 @@ static void ocfs2_downconvert_thread_do_work(struct ocfs2_super *osb) struct ocfs2_lock_res, l_blocked_list); list_del_init(&lockres->l_blocked_list); osb->blocked_lock_count--; - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); BUG_ON(!processed); processed--; ocfs2_process_blocked_lock(osb, lockres); - spin_lock(&osb->dc_task_lock); + spin_lock_irqsave(&osb->dc_task_lock, flags); } - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); } static int ocfs2_downconvert_thread_lists_empty(struct ocfs2_super *osb) { int empty = 0; + unsigned long flags; - spin_lock(&osb->dc_task_lock); + spin_lock_irqsave(&osb->dc_task_lock, flags); if (list_empty(&osb->blocked_lock_list)) empty = 1; - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); return empty; } static int ocfs2_downconvert_thread_should_wake(struct ocfs2_super *osb) { int should_wake = 0; + unsigned long flags; - spin_lock(&osb->dc_task_lock); + spin_lock_irqsave(&osb->dc_task_lock, flags); if (osb->dc_work_sequence != osb->dc_wake_sequence) should_wake = 1; - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); return should_wake; } @@ -4033,10 +4038,12 @@ static int ocfs2_downconvert_thread(void *arg) void ocfs2_wake_downconvert_thread(struct ocfs2_super *osb) { - spin_lock(&osb->dc_task_lock); + unsigned long flags; + + spin_lock_irqsave(&osb->dc_task_lock, flags); /* make sure the voting thread gets a swipe at whatever changes * the caller may have made to the voting state */ osb->dc_wake_sequence++; - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); wake_up(&osb->dc_event); } diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c index 2f5b92ef0e53..70b5863a2d64 100644 --- a/fs/ocfs2/extent_map.c +++ b/fs/ocfs2/extent_map.c @@ -923,8 +923,6 @@ out_unlock: ocfs2_inode_unlock(inode, 0); out: - if (ret && ret != -ENXIO) - ret = -ENXIO; return ret; } diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 061591a3ab08..98513c8ed589 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2422,8 +2422,10 @@ out_dio: unaligned_dio = 0; } - if (unaligned_dio) + if (unaligned_dio) { + ocfs2_iocb_clear_unaligned_aio(iocb); atomic_dec(&OCFS2_I(inode)->ip_unaligned_aio); + } out: if (rw_level != -1) diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index 92fcd575775a..0a86e302655f 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -399,8 +399,6 @@ int ocfs2_global_read_info(struct super_block *sb, int type) msecs_to_jiffies(oinfo->dqi_syncms)); out_err: - if (status) - mlog_errno(status); return status; out_unlock: ocfs2_unlock_global_qf(oinfo, 0); diff --git a/fs/open.c b/fs/open.c index d6c79a0dffc7..1540632d8387 100644 --- a/fs/open.c +++ b/fs/open.c @@ -397,10 +397,10 @@ SYSCALL_DEFINE1(fchdir, unsigned int, fd) { struct file *file; struct inode *inode; - int error; + int error, fput_needed; error = -EBADF; - file = fget(fd); + file = fget_raw_light(fd, &fput_needed); if (!file) goto out; @@ -414,7 +414,7 @@ SYSCALL_DEFINE1(fchdir, unsigned int, fd) if (!error) set_fs_pwd(current->fs, &file->f_path); out_putf: - fput(file); + fput_light(file, fput_needed); out: return error; } diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index aeb19e68e086..11a2aa2a56c4 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -258,7 +258,7 @@ fail: return rc; } -int pstore_fill_super(struct super_block *sb, void *data, int silent) +static int pstore_fill_super(struct super_block *sb, void *data, int silent) { struct inode *inode; diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 82c585f715e3..03ce7a9b81cc 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -94,20 +94,15 @@ static const char *get_reason_str(enum kmsg_dump_reason reason) * as we can from the end of the buffer. */ static void pstore_dump(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason, - const char *s1, unsigned long l1, - const char *s2, unsigned long l2) + enum kmsg_dump_reason reason) { - unsigned long s1_start, s2_start; - unsigned long l1_cpy, l2_cpy; - unsigned long size, total = 0; - char *dst; + unsigned long total = 0; const char *why; u64 id; - int hsize, ret; unsigned int part = 1; unsigned long flags = 0; int is_locked = 0; + int ret; why = get_reason_str(reason); @@ -119,30 +114,25 @@ static void pstore_dump(struct kmsg_dumper *dumper, spin_lock_irqsave(&psinfo->buf_lock, flags); oopscount++; while (total < kmsg_bytes) { + char *dst; + unsigned long size; + int hsize; + size_t len; + dst = psinfo->buf; hsize = sprintf(dst, "%s#%d Part%d\n", why, oopscount, part); size = psinfo->bufsize - hsize; dst += hsize; - l2_cpy = min(l2, size); - l1_cpy = min(l1, size - l2_cpy); - - if (l1_cpy + l2_cpy == 0) + if (!kmsg_dump_get_buffer(dumper, true, dst, size, &len)) break; - s2_start = l2 - l2_cpy; - s1_start = l1 - l1_cpy; - - memcpy(dst, s1 + s1_start, l1_cpy); - memcpy(dst + l1_cpy, s2 + s2_start, l2_cpy); - ret = psinfo->write(PSTORE_TYPE_DMESG, reason, &id, part, - hsize + l1_cpy + l2_cpy, psinfo); + hsize + len, psinfo); if (ret == 0 && reason == KMSG_DUMP_OOPS && pstore_is_mounted()) pstore_new_entry = 1; - l1 -= l1_cpy; - l2 -= l2_cpy; - total += l1_cpy + l2_cpy; + + total += hsize + len; part++; } if (in_nmi()) { diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 9123cce28c1e..453030f9c5bc 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -106,6 +106,8 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, time->tv_sec = 0; time->tv_nsec = 0; + /* Update old/shadowed buffer. */ + persistent_ram_save_old(prz); size = persistent_ram_old_size(prz); *buf = kmalloc(size, GFP_KERNEL); if (*buf == NULL) @@ -184,6 +186,7 @@ static int ramoops_pstore_erase(enum pstore_type_id type, u64 id, return -EINVAL; persistent_ram_free_old(cxt->przs[id]); + persistent_ram_zap(cxt->przs[id]); return 0; } diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index 31f8d184f3a0..c5fbdbbf81ac 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -250,23 +250,24 @@ static void notrace persistent_ram_update(struct persistent_ram_zone *prz, persistent_ram_update_ecc(prz, start, count); } -static void __init -persistent_ram_save_old(struct persistent_ram_zone *prz) +void persistent_ram_save_old(struct persistent_ram_zone *prz) { struct persistent_ram_buffer *buffer = prz->buffer; size_t size = buffer_size(prz); size_t start = buffer_start(prz); - char *dest; - persistent_ram_ecc_old(prz); + if (!size) + return; - dest = kmalloc(size, GFP_KERNEL); - if (dest == NULL) { + if (!prz->old_log) { + persistent_ram_ecc_old(prz); + prz->old_log = kmalloc(size, GFP_KERNEL); + } + if (!prz->old_log) { pr_err("persistent_ram: failed to allocate buffer\n"); return; } - prz->old_log = dest; prz->old_log_size = size; memcpy(prz->old_log, &buffer->data[start], size - start); memcpy(prz->old_log + size - start, &buffer->data[0], start); @@ -319,6 +320,13 @@ void persistent_ram_free_old(struct persistent_ram_zone *prz) prz->old_log_size = 0; } +void persistent_ram_zap(struct persistent_ram_zone *prz) +{ + atomic_set(&prz->buffer->start, 0); + atomic_set(&prz->buffer->size, 0); + persistent_ram_update_header_ecc(prz); +} + static void *persistent_ram_vmap(phys_addr_t start, size_t size) { struct page **pages; @@ -405,6 +413,7 @@ static int __init persistent_ram_post_init(struct persistent_ram_zone *prz, bool " size %zu, start %zu\n", buffer_size(prz), buffer_start(prz)); persistent_ram_save_old(prz); + return 0; } } else { pr_info("persistent_ram: no valid data in buffer" @@ -412,8 +421,7 @@ static int __init persistent_ram_post_init(struct persistent_ram_zone *prz, bool } prz->buffer->sig = PERSISTENT_RAM_SIG; - atomic_set(&prz->buffer->start, 0); - atomic_set(&prz->buffer->size, 0); + persistent_ram_zap(prz); return 0; } @@ -448,7 +456,6 @@ struct persistent_ram_zone * __init persistent_ram_new(phys_addr_t start, goto err; persistent_ram_post_init(prz, ecc); - persistent_ram_update_header_ecc(prz); return prz; err: diff --git a/fs/splice.c b/fs/splice.c index c9f1318a3b82..7bf08fa22ec9 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -273,13 +273,16 @@ void spd_release_page(struct splice_pipe_desc *spd, unsigned int i) * Check if we need to grow the arrays holding pages and partial page * descriptions. */ -int splice_grow_spd(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) +int splice_grow_spd(const struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) { - if (pipe->buffers <= PIPE_DEF_BUFFERS) + unsigned int buffers = ACCESS_ONCE(pipe->buffers); + + spd->nr_pages_max = buffers; + if (buffers <= PIPE_DEF_BUFFERS) return 0; - spd->pages = kmalloc(pipe->buffers * sizeof(struct page *), GFP_KERNEL); - spd->partial = kmalloc(pipe->buffers * sizeof(struct partial_page), GFP_KERNEL); + spd->pages = kmalloc(buffers * sizeof(struct page *), GFP_KERNEL); + spd->partial = kmalloc(buffers * sizeof(struct partial_page), GFP_KERNEL); if (spd->pages && spd->partial) return 0; @@ -289,10 +292,9 @@ int splice_grow_spd(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) return -ENOMEM; } -void splice_shrink_spd(struct pipe_inode_info *pipe, - struct splice_pipe_desc *spd) +void splice_shrink_spd(struct splice_pipe_desc *spd) { - if (pipe->buffers <= PIPE_DEF_BUFFERS) + if (spd->nr_pages_max <= PIPE_DEF_BUFFERS) return; kfree(spd->pages); @@ -315,6 +317,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &page_cache_pipe_buf_ops, .spd_release = spd_release_page, @@ -326,7 +329,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, index = *ppos >> PAGE_CACHE_SHIFT; loff = *ppos & ~PAGE_CACHE_MASK; req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - nr_pages = min(req_pages, pipe->buffers); + nr_pages = min(req_pages, spd.nr_pages_max); /* * Lookup the (hopefully) full range of pages we need. @@ -497,7 +500,7 @@ fill_it: if (spd.nr_pages) error = splice_to_pipe(pipe, &spd); - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); return error; } @@ -598,6 +601,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos, struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &default_pipe_buf_ops, .spd_release = spd_release_page, @@ -608,8 +612,8 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos, res = -ENOMEM; vec = __vec; - if (pipe->buffers > PIPE_DEF_BUFFERS) { - vec = kmalloc(pipe->buffers * sizeof(struct iovec), GFP_KERNEL); + if (spd.nr_pages_max > PIPE_DEF_BUFFERS) { + vec = kmalloc(spd.nr_pages_max * sizeof(struct iovec), GFP_KERNEL); if (!vec) goto shrink_ret; } @@ -617,7 +621,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos, offset = *ppos & ~PAGE_CACHE_MASK; nr_pages = (len + offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - for (i = 0; i < nr_pages && i < pipe->buffers && len; i++) { + for (i = 0; i < nr_pages && i < spd.nr_pages_max && len; i++) { struct page *page; page = alloc_page(GFP_USER); @@ -665,7 +669,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos, shrink_ret: if (vec != __vec) kfree(vec); - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); return res; err: @@ -1614,6 +1618,7 @@ static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov, struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &user_page_pipe_buf_ops, .spd_release = spd_release_page, @@ -1629,13 +1634,13 @@ static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov, spd.nr_pages = get_iovec_page_array(iov, nr_segs, spd.pages, spd.partial, false, - pipe->buffers); + spd.nr_pages_max); if (spd.nr_pages <= 0) ret = spd.nr_pages; else ret = splice_to_pipe(pipe, &spd); - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); return ret; } diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index 84a7e6f3c046..92df3b081539 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -2918,7 +2918,7 @@ int dbg_debugfs_init_fs(struct ubifs_info *c) struct dentry *dent; struct ubifs_debug_info *d = c->dbg; - if (!IS_ENABLED(DEBUG_FS)) + if (!IS_ENABLED(CONFIG_DEBUG_FS)) return 0; n = snprintf(d->dfs_dir_name, UBIFS_DFS_DIR_LEN + 1, UBIFS_DFS_DIR_NAME, @@ -3013,7 +3013,7 @@ out: */ void dbg_debugfs_exit_fs(struct ubifs_info *c) { - if (IS_ENABLED(DEBUG_FS)) + if (IS_ENABLED(CONFIG_DEBUG_FS)) debugfs_remove_recursive(c->dbg->dfs_dir); } @@ -3099,7 +3099,7 @@ int dbg_debugfs_init(void) const char *fname; struct dentry *dent; - if (!IS_ENABLED(DEBUG_FS)) + if (!IS_ENABLED(CONFIG_DEBUG_FS)) return 0; fname = "ubifs"; @@ -3166,7 +3166,7 @@ out: */ void dbg_debugfs_exit(void) { - if (IS_ENABLED(DEBUG_FS)) + if (IS_ENABLED(CONFIG_DEBUG_FS)) debugfs_remove_recursive(dfs_rootdir); } diff --git a/fs/ubifs/find.c b/fs/ubifs/find.c index 2559d174e004..28ec13af28d9 100644 --- a/fs/ubifs/find.c +++ b/fs/ubifs/find.c @@ -939,8 +939,8 @@ static int find_dirtiest_idx_leb(struct ubifs_info *c) } dbg_find("LEB %d, dirty %d and free %d flags %#x", lp->lnum, lp->dirty, lp->free, lp->flags); - ubifs_assert(lp->flags | LPROPS_TAKEN); - ubifs_assert(lp->flags | LPROPS_INDEX); + ubifs_assert(lp->flags & LPROPS_TAKEN); + ubifs_assert(lp->flags & LPROPS_INDEX); return lnum; } diff --git a/fs/udf/super.c b/fs/udf/super.c index ac8a348dcb69..8d86a8706c0e 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -56,6 +56,7 @@ #include <linux/seq_file.h> #include <linux/bitmap.h> #include <linux/crc-itu-t.h> +#include <linux/log2.h> #include <asm/byteorder.h> #include "udf_sb.h" @@ -1215,16 +1216,65 @@ out_bh: return ret; } +static int udf_load_sparable_map(struct super_block *sb, + struct udf_part_map *map, + struct sparablePartitionMap *spm) +{ + uint32_t loc; + uint16_t ident; + struct sparingTable *st; + struct udf_sparing_data *sdata = &map->s_type_specific.s_sparing; + int i; + struct buffer_head *bh; + + map->s_partition_type = UDF_SPARABLE_MAP15; + sdata->s_packet_len = le16_to_cpu(spm->packetLength); + if (!is_power_of_2(sdata->s_packet_len)) { + udf_err(sb, "error loading logical volume descriptor: " + "Invalid packet length %u\n", + (unsigned)sdata->s_packet_len); + return -EIO; + } + if (spm->numSparingTables > 4) { + udf_err(sb, "error loading logical volume descriptor: " + "Too many sparing tables (%d)\n", + (int)spm->numSparingTables); + return -EIO; + } + + for (i = 0; i < spm->numSparingTables; i++) { + loc = le32_to_cpu(spm->locSparingTable[i]); + bh = udf_read_tagged(sb, loc, loc, &ident); + if (!bh) + continue; + + st = (struct sparingTable *)bh->b_data; + if (ident != 0 || + strncmp(st->sparingIdent.ident, UDF_ID_SPARING, + strlen(UDF_ID_SPARING)) || + sizeof(*st) + le16_to_cpu(st->reallocationTableLen) > + sb->s_blocksize) { + brelse(bh); + continue; + } + + sdata->s_spar_map[i] = bh; + } + map->s_partition_func = udf_get_pblock_spar15; + return 0; +} + static int udf_load_logicalvol(struct super_block *sb, sector_t block, struct kernel_lb_addr *fileset) { struct logicalVolDesc *lvd; - int i, j, offset; + int i, offset; uint8_t type; struct udf_sb_info *sbi = UDF_SB(sb); struct genericPartitionMap *gpm; uint16_t ident; struct buffer_head *bh; + unsigned int table_len; int ret = 0; bh = udf_read_tagged(sb, block, block, &ident); @@ -1232,15 +1282,20 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block, return 1; BUG_ON(ident != TAG_IDENT_LVD); lvd = (struct logicalVolDesc *)bh->b_data; - - i = udf_sb_alloc_partition_maps(sb, le32_to_cpu(lvd->numPartitionMaps)); - if (i != 0) { - ret = i; + table_len = le32_to_cpu(lvd->mapTableLength); + if (sizeof(*lvd) + table_len > sb->s_blocksize) { + udf_err(sb, "error loading logical volume descriptor: " + "Partition table too long (%u > %lu)\n", table_len, + sb->s_blocksize - sizeof(*lvd)); goto out_bh; } + ret = udf_sb_alloc_partition_maps(sb, le32_to_cpu(lvd->numPartitionMaps)); + if (ret) + goto out_bh; + for (i = 0, offset = 0; - i < sbi->s_partitions && offset < le32_to_cpu(lvd->mapTableLength); + i < sbi->s_partitions && offset < table_len; i++, offset += gpm->partitionMapLength) { struct udf_part_map *map = &sbi->s_partmaps[i]; gpm = (struct genericPartitionMap *) @@ -1275,38 +1330,9 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block, } else if (!strncmp(upm2->partIdent.ident, UDF_ID_SPARABLE, strlen(UDF_ID_SPARABLE))) { - uint32_t loc; - struct sparingTable *st; - struct sparablePartitionMap *spm = - (struct sparablePartitionMap *)gpm; - - map->s_partition_type = UDF_SPARABLE_MAP15; - map->s_type_specific.s_sparing.s_packet_len = - le16_to_cpu(spm->packetLength); - for (j = 0; j < spm->numSparingTables; j++) { - struct buffer_head *bh2; - - loc = le32_to_cpu( - spm->locSparingTable[j]); - bh2 = udf_read_tagged(sb, loc, loc, - &ident); - map->s_type_specific.s_sparing. - s_spar_map[j] = bh2; - - if (bh2 == NULL) - continue; - - st = (struct sparingTable *)bh2->b_data; - if (ident != 0 || strncmp( - st->sparingIdent.ident, - UDF_ID_SPARING, - strlen(UDF_ID_SPARING))) { - brelse(bh2); - map->s_type_specific.s_sparing. - s_spar_map[j] = NULL; - } - } - map->s_partition_func = udf_get_pblock_spar15; + if (udf_load_sparable_map(sb, map, + (struct sparablePartitionMap *)gpm) < 0) + goto out_bh; } else if (!strncmp(upm2->partIdent.ident, UDF_ID_METADATA, strlen(UDF_ID_METADATA))) { diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c index 229641fb8e67..9d1aeb7e2734 100644 --- a/fs/xfs/xfs_alloc.c +++ b/fs/xfs/xfs_alloc.c @@ -1080,6 +1080,7 @@ restart: goto restart; } + xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); trace_xfs_alloc_size_neither(args); args->agbno = NULLAGBLOCK; return 0; @@ -2441,7 +2442,7 @@ xfs_alloc_vextent( DECLARE_COMPLETION_ONSTACK(done); args->done = &done; - INIT_WORK(&args->work, xfs_alloc_vextent_worker); + INIT_WORK_ONSTACK(&args->work, xfs_alloc_vextent_worker); queue_work(xfs_alloc_wq, &args->work); wait_for_completion(&done); return args->result; diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index ae31c313a79e..8dad722c0041 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -981,10 +981,15 @@ xfs_vm_writepage( imap_valid = 0; } } else { - if (PageUptodate(page)) { + if (PageUptodate(page)) ASSERT(buffer_mapped(bh)); - imap_valid = 0; - } + /* + * This buffer is not uptodate and will not be + * written to disk. Ensure that we will put any + * subsequent writeable buffers into a new + * ioend. + */ + imap_valid = 0; continue; } diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 172d3cc8f8cb..a4beb421018a 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -201,14 +201,7 @@ xfs_buf_alloc( bp->b_length = numblks; bp->b_io_length = numblks; bp->b_flags = flags; - - /* - * We do not set the block number here in the buffer because we have not - * finished initialising the buffer. We insert the buffer into the cache - * in this state, so this ensures that we are unable to do IO on a - * buffer that hasn't been fully initialised. - */ - bp->b_bn = XFS_BUF_DADDR_NULL; + bp->b_bn = blkno; atomic_set(&bp->b_pin_count, 0); init_waitqueue_head(&bp->b_waiters); @@ -567,11 +560,6 @@ xfs_buf_get( if (bp != new_bp) xfs_buf_free(new_bp); - /* - * Now we have a workable buffer, fill in the block number so - * that we can do IO on it. - */ - bp->b_bn = blkno; bp->b_io_length = bp->b_length; found: @@ -772,7 +760,7 @@ xfs_buf_get_uncached( int error, i; xfs_buf_t *bp; - bp = xfs_buf_alloc(target, 0, numblks, 0); + bp = xfs_buf_alloc(target, XFS_BUF_DADDR_NULL, numblks, 0); if (unlikely(bp == NULL)) goto fail; diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 6cdbf90c6f7b..d041d47d9d86 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -505,6 +505,14 @@ xfs_inode_item_push( } /* + * Stale inode items should force out the iclog. + */ + if (ip->i_flags & XFS_ISTALE) { + rval = XFS_ITEM_PINNED; + goto out_unlock; + } + + /* * Someone else is already flushing the inode. Nothing we can do * here but wait for the flush to finish and remove the item from * the AIL. @@ -514,15 +522,6 @@ xfs_inode_item_push( goto out_unlock; } - /* - * Stale inode items should force out the iclog. - */ - if (ip->i_flags & XFS_ISTALE) { - xfs_ifunlock(ip); - xfs_iunlock(ip, XFS_ILOCK_SHARED); - return XFS_ITEM_PINNED; - } - ASSERT(iip->ili_fields != 0 || XFS_FORCED_SHUTDOWN(ip->i_mount)); ASSERT(iip->ili_logged == 0 || XFS_FORCED_SHUTDOWN(ip->i_mount)); diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index f30d9807dc48..d90d4a388609 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -38,13 +38,21 @@ kmem_zone_t *xfs_log_ticket_zone; /* Local miscellaneous function prototypes */ -STATIC int xlog_commit_record(struct log *log, struct xlog_ticket *ticket, - xlog_in_core_t **, xfs_lsn_t *); +STATIC int +xlog_commit_record( + struct xlog *log, + struct xlog_ticket *ticket, + struct xlog_in_core **iclog, + xfs_lsn_t *commitlsnp); + STATIC xlog_t * xlog_alloc_log(xfs_mount_t *mp, xfs_buftarg_t *log_target, xfs_daddr_t blk_offset, int num_bblks); -STATIC int xlog_space_left(struct log *log, atomic64_t *head); +STATIC int +xlog_space_left( + struct xlog *log, + atomic64_t *head); STATIC int xlog_sync(xlog_t *log, xlog_in_core_t *iclog); STATIC void xlog_dealloc_log(xlog_t *log); @@ -64,8 +72,10 @@ STATIC void xlog_state_switch_iclogs(xlog_t *log, int eventual_size); STATIC void xlog_state_want_sync(xlog_t *log, xlog_in_core_t *iclog); -STATIC void xlog_grant_push_ail(struct log *log, - int need_bytes); +STATIC void +xlog_grant_push_ail( + struct xlog *log, + int need_bytes); STATIC void xlog_regrant_reserve_log_space(xlog_t *log, xlog_ticket_t *ticket); STATIC void xlog_ungrant_log_space(xlog_t *log, @@ -73,7 +83,9 @@ STATIC void xlog_ungrant_log_space(xlog_t *log, #if defined(DEBUG) STATIC void xlog_verify_dest_ptr(xlog_t *log, char *ptr); -STATIC void xlog_verify_grant_tail(struct log *log); +STATIC void +xlog_verify_grant_tail( + struct xlog *log); STATIC void xlog_verify_iclog(xlog_t *log, xlog_in_core_t *iclog, int count, boolean_t syncing); STATIC void xlog_verify_tail_lsn(xlog_t *log, xlog_in_core_t *iclog, @@ -89,9 +101,9 @@ STATIC int xlog_iclogs_empty(xlog_t *log); static void xlog_grant_sub_space( - struct log *log, - atomic64_t *head, - int bytes) + struct xlog *log, + atomic64_t *head, + int bytes) { int64_t head_val = atomic64_read(head); int64_t new, old; @@ -115,9 +127,9 @@ xlog_grant_sub_space( static void xlog_grant_add_space( - struct log *log, - atomic64_t *head, - int bytes) + struct xlog *log, + atomic64_t *head, + int bytes) { int64_t head_val = atomic64_read(head); int64_t new, old; @@ -165,7 +177,7 @@ xlog_grant_head_wake_all( static inline int xlog_ticket_reservation( - struct log *log, + struct xlog *log, struct xlog_grant_head *head, struct xlog_ticket *tic) { @@ -182,7 +194,7 @@ xlog_ticket_reservation( STATIC bool xlog_grant_head_wake( - struct log *log, + struct xlog *log, struct xlog_grant_head *head, int *free_bytes) { @@ -204,7 +216,7 @@ xlog_grant_head_wake( STATIC int xlog_grant_head_wait( - struct log *log, + struct xlog *log, struct xlog_grant_head *head, struct xlog_ticket *tic, int need_bytes) @@ -256,7 +268,7 @@ shutdown: */ STATIC int xlog_grant_head_check( - struct log *log, + struct xlog *log, struct xlog_grant_head *head, struct xlog_ticket *tic, int *need_bytes) @@ -323,7 +335,7 @@ xfs_log_regrant( struct xfs_mount *mp, struct xlog_ticket *tic) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; int need_bytes; int error = 0; @@ -389,7 +401,7 @@ xfs_log_reserve( bool permanent, uint t_type) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; struct xlog_ticket *tic; int need_bytes; int error = 0; @@ -465,7 +477,7 @@ xfs_log_done( struct xlog_in_core **iclog, uint flags) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; xfs_lsn_t lsn = 0; if (XLOG_FORCED_SHUTDOWN(log) || @@ -810,6 +822,7 @@ xfs_log_unmount_write(xfs_mount_t *mp) void xfs_log_unmount(xfs_mount_t *mp) { + cancel_delayed_work_sync(&mp->m_sync_work); xfs_trans_ail_destroy(mp); xlog_dealloc_log(mp->m_log); } @@ -838,7 +851,7 @@ void xfs_log_space_wake( struct xfs_mount *mp) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; int free_bytes; if (XLOG_FORCED_SHUTDOWN(log)) @@ -916,7 +929,7 @@ xfs_lsn_t xlog_assign_tail_lsn_locked( struct xfs_mount *mp) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; struct xfs_log_item *lip; xfs_lsn_t tail_lsn; @@ -965,7 +978,7 @@ xlog_assign_tail_lsn( */ STATIC int xlog_space_left( - struct log *log, + struct xlog *log, atomic64_t *head) { int free_bytes; @@ -1277,7 +1290,7 @@ out: */ STATIC int xlog_commit_record( - struct log *log, + struct xlog *log, struct xlog_ticket *ticket, struct xlog_in_core **iclog, xfs_lsn_t *commitlsnp) @@ -1311,7 +1324,7 @@ xlog_commit_record( */ STATIC void xlog_grant_push_ail( - struct log *log, + struct xlog *log, int need_bytes) { xfs_lsn_t threshold_lsn = 0; @@ -1790,7 +1803,7 @@ xlog_write_start_rec( static xlog_op_header_t * xlog_write_setup_ophdr( - struct log *log, + struct xlog *log, struct xlog_op_header *ophdr, struct xlog_ticket *ticket, uint flags) @@ -1873,7 +1886,7 @@ xlog_write_setup_copy( static int xlog_write_copy_finish( - struct log *log, + struct xlog *log, struct xlog_in_core *iclog, uint flags, int *record_cnt, @@ -1958,7 +1971,7 @@ xlog_write_copy_finish( */ int xlog_write( - struct log *log, + struct xlog *log, struct xfs_log_vec *log_vector, struct xlog_ticket *ticket, xfs_lsn_t *start_lsn, @@ -2821,7 +2834,7 @@ _xfs_log_force( uint flags, int *log_flushed) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; struct xlog_in_core *iclog; xfs_lsn_t lsn; @@ -2969,7 +2982,7 @@ _xfs_log_force_lsn( uint flags, int *log_flushed) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; struct xlog_in_core *iclog; int already_slept = 0; @@ -3147,7 +3160,7 @@ xfs_log_ticket_get( */ xlog_ticket_t * xlog_ticket_alloc( - struct log *log, + struct xlog *log, int unit_bytes, int cnt, char client, @@ -3278,7 +3291,7 @@ xlog_ticket_alloc( */ void xlog_verify_dest_ptr( - struct log *log, + struct xlog *log, char *ptr) { int i; @@ -3307,7 +3320,7 @@ xlog_verify_dest_ptr( */ STATIC void xlog_verify_grant_tail( - struct log *log) + struct xlog *log) { int tail_cycle, tail_blocks; int cycle, space; diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index 7d6197c58493..ddc4529d07d3 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -44,7 +44,7 @@ */ static struct xlog_ticket * xlog_cil_ticket_alloc( - struct log *log) + struct xlog *log) { struct xlog_ticket *tic; @@ -72,7 +72,7 @@ xlog_cil_ticket_alloc( */ void xlog_cil_init_post_recovery( - struct log *log) + struct xlog *log) { log->l_cilp->xc_ctx->ticket = xlog_cil_ticket_alloc(log); log->l_cilp->xc_ctx->sequence = 1; @@ -182,7 +182,7 @@ xlog_cil_prepare_log_vecs( */ STATIC void xfs_cil_prepare_item( - struct log *log, + struct xlog *log, struct xfs_log_vec *lv, int *len, int *diff_iovecs) @@ -231,7 +231,7 @@ xfs_cil_prepare_item( */ static void xlog_cil_insert_items( - struct log *log, + struct xlog *log, struct xfs_log_vec *log_vector, struct xlog_ticket *ticket) { @@ -373,7 +373,7 @@ xlog_cil_committed( */ STATIC int xlog_cil_push( - struct log *log) + struct xlog *log) { struct xfs_cil *cil = log->l_cilp; struct xfs_log_vec *lv; @@ -601,7 +601,7 @@ xlog_cil_push_work( */ static void xlog_cil_push_background( - struct log *log) + struct xlog *log) { struct xfs_cil *cil = log->l_cilp; @@ -629,7 +629,7 @@ xlog_cil_push_background( static void xlog_cil_push_foreground( - struct log *log, + struct xlog *log, xfs_lsn_t push_seq) { struct xfs_cil *cil = log->l_cilp; @@ -683,7 +683,7 @@ xfs_log_commit_cil( xfs_lsn_t *commit_lsn, int flags) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; int log_flags = 0; struct xfs_log_vec *log_vector; @@ -754,7 +754,7 @@ xfs_log_commit_cil( */ xfs_lsn_t xlog_cil_force_lsn( - struct log *log, + struct xlog *log, xfs_lsn_t sequence) { struct xfs_cil *cil = log->l_cilp; @@ -833,7 +833,7 @@ xfs_log_item_in_current_chkpt( */ int xlog_cil_init( - struct log *log) + struct xlog *log) { struct xfs_cil *cil; struct xfs_cil_ctx *ctx; @@ -869,7 +869,7 @@ xlog_cil_init( void xlog_cil_destroy( - struct log *log) + struct xlog *log) { if (log->l_cilp->xc_ctx) { if (log->l_cilp->xc_ctx->ticket) diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index 5bc33261f5be..72eba2201b14 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -19,7 +19,7 @@ #define __XFS_LOG_PRIV_H__ struct xfs_buf; -struct log; +struct xlog; struct xlog_ticket; struct xfs_mount; @@ -352,7 +352,7 @@ typedef struct xlog_in_core { struct xlog_in_core *ic_next; struct xlog_in_core *ic_prev; struct xfs_buf *ic_bp; - struct log *ic_log; + struct xlog *ic_log; int ic_size; int ic_offset; int ic_bwritecnt; @@ -409,7 +409,7 @@ struct xfs_cil_ctx { * operations almost as efficient as the old logging methods. */ struct xfs_cil { - struct log *xc_log; + struct xlog *xc_log; struct list_head xc_cil; spinlock_t xc_cil_lock; struct xfs_cil_ctx *xc_ctx; @@ -487,7 +487,7 @@ struct xlog_grant_head { * overflow 31 bits worth of byte offset, so using a byte number will mean * that round off problems won't occur when releasing partial reservations. */ -typedef struct log { +typedef struct xlog { /* The following fields don't need locking */ struct xfs_mount *l_mp; /* mount point */ struct xfs_ail *l_ailp; /* AIL log is working with */ @@ -553,9 +553,14 @@ extern int xlog_recover_finish(xlog_t *log); extern void xlog_pack_data(xlog_t *log, xlog_in_core_t *iclog, int); extern kmem_zone_t *xfs_log_ticket_zone; -struct xlog_ticket *xlog_ticket_alloc(struct log *log, int unit_bytes, - int count, char client, bool permanent, - xfs_km_flags_t alloc_flags); +struct xlog_ticket * +xlog_ticket_alloc( + struct xlog *log, + int unit_bytes, + int count, + char client, + bool permanent, + xfs_km_flags_t alloc_flags); static inline void @@ -567,9 +572,14 @@ xlog_write_adv_cnt(void **ptr, int *len, int *off, size_t bytes) } void xlog_print_tic_res(struct xfs_mount *mp, struct xlog_ticket *ticket); -int xlog_write(struct log *log, struct xfs_log_vec *log_vector, - struct xlog_ticket *tic, xfs_lsn_t *start_lsn, - xlog_in_core_t **commit_iclog, uint flags); +int +xlog_write( + struct xlog *log, + struct xfs_log_vec *log_vector, + struct xlog_ticket *tic, + xfs_lsn_t *start_lsn, + struct xlog_in_core **commit_iclog, + uint flags); /* * When we crack an atomic LSN, we sample it first so that the value will not @@ -629,17 +639,23 @@ xlog_assign_grant_head(atomic64_t *head, int cycle, int space) /* * Committed Item List interfaces */ -int xlog_cil_init(struct log *log); -void xlog_cil_init_post_recovery(struct log *log); -void xlog_cil_destroy(struct log *log); +int +xlog_cil_init(struct xlog *log); +void +xlog_cil_init_post_recovery(struct xlog *log); +void +xlog_cil_destroy(struct xlog *log); /* * CIL force routines */ -xfs_lsn_t xlog_cil_force_lsn(struct log *log, xfs_lsn_t sequence); +xfs_lsn_t +xlog_cil_force_lsn( + struct xlog *log, + xfs_lsn_t sequence); static inline void -xlog_cil_force(struct log *log) +xlog_cil_force(struct xlog *log) { xlog_cil_force_lsn(log, log->l_cilp->xc_current_sequence); } diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index ca386909131a..a7be98abd6a9 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1471,8 +1471,8 @@ xlog_recover_add_item( STATIC int xlog_recover_add_to_cont_trans( - struct log *log, - xlog_recover_t *trans, + struct xlog *log, + struct xlog_recover *trans, xfs_caddr_t dp, int len) { @@ -1517,8 +1517,8 @@ xlog_recover_add_to_cont_trans( */ STATIC int xlog_recover_add_to_trans( - struct log *log, - xlog_recover_t *trans, + struct xlog *log, + struct xlog_recover *trans, xfs_caddr_t dp, int len) { @@ -1588,8 +1588,8 @@ xlog_recover_add_to_trans( */ STATIC int xlog_recover_reorder_trans( - struct log *log, - xlog_recover_t *trans, + struct xlog *log, + struct xlog_recover *trans, int pass) { xlog_recover_item_t *item, *n; @@ -1642,8 +1642,8 @@ xlog_recover_reorder_trans( */ STATIC int xlog_recover_buffer_pass1( - struct log *log, - xlog_recover_item_t *item) + struct xlog *log, + struct xlog_recover_item *item) { xfs_buf_log_format_t *buf_f = item->ri_buf[0].i_addr; struct list_head *bucket; @@ -1696,7 +1696,7 @@ xlog_recover_buffer_pass1( */ STATIC int xlog_check_buffer_cancelled( - struct log *log, + struct xlog *log, xfs_daddr_t blkno, uint len, ushort flags) @@ -2689,9 +2689,9 @@ xlog_recover_free_trans( STATIC int xlog_recover_commit_pass1( - struct log *log, - struct xlog_recover *trans, - xlog_recover_item_t *item) + struct xlog *log, + struct xlog_recover *trans, + struct xlog_recover_item *item) { trace_xfs_log_recover_item_recover(log, trans, item, XLOG_RECOVER_PASS1); @@ -2716,10 +2716,10 @@ xlog_recover_commit_pass1( STATIC int xlog_recover_commit_pass2( - struct log *log, - struct xlog_recover *trans, - struct list_head *buffer_list, - xlog_recover_item_t *item) + struct xlog *log, + struct xlog_recover *trans, + struct list_head *buffer_list, + struct xlog_recover_item *item) { trace_xfs_log_recover_item_recover(log, trans, item, XLOG_RECOVER_PASS2); @@ -2753,7 +2753,7 @@ xlog_recover_commit_pass2( */ STATIC int xlog_recover_commit_trans( - struct log *log, + struct xlog *log, struct xlog_recover *trans, int pass) { @@ -2793,8 +2793,8 @@ out: STATIC int xlog_recover_unmount_trans( - struct log *log, - xlog_recover_t *trans) + struct xlog *log, + struct xlog_recover *trans) { /* Do nothing now */ xfs_warn(log->l_mp, "%s: Unmount LR", __func__); diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 8b89c5ac72d9..90c1fc9eaea4 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -53,7 +53,7 @@ typedef struct xfs_trans_reservations { #include "xfs_sync.h" -struct log; +struct xlog; struct xfs_mount_args; struct xfs_inode; struct xfs_bmbt_irec; @@ -133,7 +133,7 @@ typedef struct xfs_mount { uint m_readio_blocks; /* min read size blocks */ uint m_writeio_log; /* min write size log bytes */ uint m_writeio_blocks; /* min write size blocks */ - struct log *m_log; /* log specific stuff */ + struct xlog *m_log; /* log specific stuff */ int m_logbufs; /* number of log buffers */ int m_logbsize; /* size of each log buffer */ uint m_rsumlevels; /* rt summary levels */ diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c index c9d3409c5ca3..1e9ee064dbb2 100644 --- a/fs/xfs/xfs_sync.c +++ b/fs/xfs/xfs_sync.c @@ -386,23 +386,23 @@ xfs_sync_worker( * We shouldn't write/force the log if we are in the mount/unmount * process or on a read only filesystem. The workqueue still needs to be * active in both cases, however, because it is used for inode reclaim - * during these times. Use the s_umount semaphore to provide exclusion - * with unmount. + * during these times. Use the MS_ACTIVE flag to avoid doing anything + * during mount. Doing work during unmount is avoided by calling + * cancel_delayed_work_sync on this work queue before tearing down + * the ail and the log in xfs_log_unmount. */ - if (down_read_trylock(&mp->m_super->s_umount)) { - if (!(mp->m_flags & XFS_MOUNT_RDONLY)) { - /* dgc: errors ignored here */ - if (mp->m_super->s_frozen == SB_UNFROZEN && - xfs_log_need_covered(mp)) - error = xfs_fs_log_dummy(mp); - else - xfs_log_force(mp, 0); - - /* start pushing all the metadata that is currently - * dirty */ - xfs_ail_push_all(mp->m_ail); - } - up_read(&mp->m_super->s_umount); + if (!(mp->m_super->s_flags & MS_ACTIVE) && + !(mp->m_flags & XFS_MOUNT_RDONLY)) { + /* dgc: errors ignored here */ + if (mp->m_super->s_frozen == SB_UNFROZEN && + xfs_log_need_covered(mp)) + error = xfs_fs_log_dummy(mp); + else + xfs_log_force(mp, 0); + + /* start pushing all the metadata that is currently + * dirty */ + xfs_ail_push_all(mp->m_ail); } /* queue us up again */ diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 7cf9d3529e51..caf5dabfd553 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -32,7 +32,7 @@ struct xfs_da_node_entry; struct xfs_dquot; struct xfs_log_item; struct xlog_ticket; -struct log; +struct xlog; struct xlog_recover; struct xlog_recover_item; struct xfs_buf_log_format; @@ -762,7 +762,7 @@ DEFINE_DQUOT_EVENT(xfs_dqflush_force); DEFINE_DQUOT_EVENT(xfs_dqflush_done); DECLARE_EVENT_CLASS(xfs_loggrant_class, - TP_PROTO(struct log *log, struct xlog_ticket *tic), + TP_PROTO(struct xlog *log, struct xlog_ticket *tic), TP_ARGS(log, tic), TP_STRUCT__entry( __field(dev_t, dev) @@ -830,7 +830,7 @@ DECLARE_EVENT_CLASS(xfs_loggrant_class, #define DEFINE_LOGGRANT_EVENT(name) \ DEFINE_EVENT(xfs_loggrant_class, name, \ - TP_PROTO(struct log *log, struct xlog_ticket *tic), \ + TP_PROTO(struct xlog *log, struct xlog_ticket *tic), \ TP_ARGS(log, tic)) DEFINE_LOGGRANT_EVENT(xfs_log_done_nonperm); DEFINE_LOGGRANT_EVENT(xfs_log_done_perm); @@ -1664,7 +1664,7 @@ DEFINE_SWAPEXT_EVENT(xfs_swap_extent_before); DEFINE_SWAPEXT_EVENT(xfs_swap_extent_after); DECLARE_EVENT_CLASS(xfs_log_recover_item_class, - TP_PROTO(struct log *log, struct xlog_recover *trans, + TP_PROTO(struct xlog *log, struct xlog_recover *trans, struct xlog_recover_item *item, int pass), TP_ARGS(log, trans, item, pass), TP_STRUCT__entry( @@ -1698,7 +1698,7 @@ DECLARE_EVENT_CLASS(xfs_log_recover_item_class, #define DEFINE_LOG_RECOVER_ITEM(name) \ DEFINE_EVENT(xfs_log_recover_item_class, name, \ - TP_PROTO(struct log *log, struct xlog_recover *trans, \ + TP_PROTO(struct xlog *log, struct xlog_recover *trans, \ struct xlog_recover_item *item, int pass), \ TP_ARGS(log, trans, item, pass)) @@ -1709,7 +1709,7 @@ DEFINE_LOG_RECOVER_ITEM(xfs_log_recover_item_reorder_tail); DEFINE_LOG_RECOVER_ITEM(xfs_log_recover_item_recover); DECLARE_EVENT_CLASS(xfs_log_recover_buf_item_class, - TP_PROTO(struct log *log, struct xfs_buf_log_format *buf_f), + TP_PROTO(struct xlog *log, struct xfs_buf_log_format *buf_f), TP_ARGS(log, buf_f), TP_STRUCT__entry( __field(dev_t, dev) @@ -1739,7 +1739,7 @@ DECLARE_EVENT_CLASS(xfs_log_recover_buf_item_class, #define DEFINE_LOG_RECOVER_BUF_ITEM(name) \ DEFINE_EVENT(xfs_log_recover_buf_item_class, name, \ - TP_PROTO(struct log *log, struct xfs_buf_log_format *buf_f), \ + TP_PROTO(struct xlog *log, struct xfs_buf_log_format *buf_f), \ TP_ARGS(log, buf_f)) DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_not_cancel); @@ -1752,7 +1752,7 @@ DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_reg_buf); DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_dquot_buf); DECLARE_EVENT_CLASS(xfs_log_recover_ino_item_class, - TP_PROTO(struct log *log, struct xfs_inode_log_format *in_f), + TP_PROTO(struct xlog *log, struct xfs_inode_log_format *in_f), TP_ARGS(log, in_f), TP_STRUCT__entry( __field(dev_t, dev) @@ -1790,7 +1790,7 @@ DECLARE_EVENT_CLASS(xfs_log_recover_ino_item_class, ) #define DEFINE_LOG_RECOVER_INO_ITEM(name) \ DEFINE_EVENT(xfs_log_recover_ino_item_class, name, \ - TP_PROTO(struct log *log, struct xfs_inode_log_format *in_f), \ + TP_PROTO(struct xlog *log, struct xfs_inode_log_format *in_f), \ TP_ARGS(log, in_f)) DEFINE_LOG_RECOVER_INO_ITEM(xfs_log_recover_inode_recover); |