diff options
Diffstat (limited to 'fs')
173 files changed, 3056 insertions, 1266 deletions
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 296482fc77a9..a2f6e9ae1a98 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -540,8 +540,7 @@ static struct inode *v9fs_qid_iget(struct super_block *sb, unlock_new_inode(inode); return inode; error: - unlock_new_inode(inode); - iput(inode); + iget_failed(inode); return ERR_PTR(retval); } diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 02b64f4e576a..092d20c643e5 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -149,8 +149,7 @@ static struct inode *v9fs_qid_iget_dotl(struct super_block *sb, unlock_new_inode(inode); return inode; error: - unlock_new_inode(inode); - iput(inode); + iget_failed(inode); return ERR_PTR(retval); } diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 3dd249787b11..e39fe28f1ea0 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -816,7 +816,7 @@ static int load_elf_binary(struct linux_binprm *bprm) total_size = total_mapping_size(elf_phdata, loc->elf_ex.e_phnum); if (!total_size) { - error = -EINVAL; + retval = -EINVAL; goto out_free_dentry; } } diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index 4dabeb893b7c..dcc1aae4c951 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -316,8 +316,8 @@ static inline void __btrfs_queue_work(struct __btrfs_workqueue *wq, list_add_tail(&work->ordered_list, &wq->ordered_list); spin_unlock_irqrestore(&wq->list_lock, flags); } - queue_work(wq->normal_wq, &work->normal_work); trace_btrfs_work_queued(work); + queue_work(wq->normal_wq, &work->normal_work); } void btrfs_queue_work(struct btrfs_workqueue *wq, diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 2d3e32ebfd15..69e596b1f95b 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1371,7 +1371,8 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, read_extent_buffer(eb, dest + bytes_left, name_off, name_len); if (eb != eb_in) { - btrfs_tree_read_unlock_blocking(eb); + if (!path->skip_locking) + btrfs_tree_read_unlock_blocking(eb); free_extent_buffer(eb); } ret = inode_ref_info(parent, 0, fs_root, path, &found_key); @@ -1390,9 +1391,10 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, eb = path->nodes[0]; /* make sure we can use eb after releasing the path */ if (eb != eb_in) { - atomic_inc(&eb->refs); - btrfs_tree_read_lock(eb); - btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + if (!path->skip_locking) + btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + path->nodes[0] = NULL; + path->locks[0] = 0; } btrfs_release_path(path); iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref); @@ -1778,7 +1780,6 @@ static int iterate_inode_extrefs(u64 inum, struct btrfs_root *fs_root, int found = 0; struct extent_buffer *eb; struct btrfs_inode_extref *extref; - struct extent_buffer *leaf; u32 item_size; u32 cur_offset; unsigned long ptr; @@ -1806,9 +1807,8 @@ static int iterate_inode_extrefs(u64 inum, struct btrfs_root *fs_root, btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); btrfs_release_path(path); - leaf = path->nodes[0]; - item_size = btrfs_item_size_nr(leaf, slot); - ptr = btrfs_item_ptr_offset(leaf, slot); + item_size = btrfs_item_size_nr(eb, slot); + ptr = btrfs_item_ptr_offset(eb, slot); cur_offset = 0; while (cur_offset < item_size) { @@ -1822,7 +1822,7 @@ static int iterate_inode_extrefs(u64 inum, struct btrfs_root *fs_root, if (ret) break; - cur_offset += btrfs_inode_extref_name_len(leaf, extref); + cur_offset += btrfs_inode_extref_name_len(eb, extref); cur_offset += sizeof(*extref); } btrfs_tree_read_unlock_blocking(eb); diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index c81ce0c7c1a9..39c68ef10808 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1542,6 +1542,7 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans, trans->transid, root->fs_info->generation); if (!should_cow_block(trans, root, buf)) { + trans->dirty = true; *cow_ret = buf; return 0; } @@ -2762,8 +2763,10 @@ again: * then we don't want to set the path blocking, * so we test it here */ - if (!should_cow_block(trans, root, b)) + if (!should_cow_block(trans, root, b)) { + trans->dirty = true; goto cow_done; + } /* * must have write locks on this node and the @@ -2920,7 +2923,7 @@ done: */ if (!p->leave_spinning) btrfs_set_path_blocking(p); - if (ret < 0) + if (ret < 0 && !p->skip_release_on_error) btrfs_release_path(p); return ret; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index fe69edda11fb..42d11e7cf7fe 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -607,6 +607,7 @@ struct btrfs_path { unsigned int leave_spinning:1; unsigned int search_commit_root:1; unsigned int need_commit_sem:1; + unsigned int skip_release_on_error:1; }; /* @@ -3686,6 +3687,10 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans, int verify_dir_item(struct btrfs_root *root, struct extent_buffer *leaf, struct btrfs_dir_item *dir_item); +struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root, + struct btrfs_path *path, + const char *name, + int name_len); /* orphan.c */ int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans, @@ -3861,6 +3866,7 @@ extern const struct dentry_operations btrfs_dentry_operations; /* ioctl.c */ long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); +long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg); void btrfs_update_iflags(struct inode *inode); void btrfs_inherit_iflags(struct inode *inode, struct inode *dir); int btrfs_is_empty_uuid(u8 *uuid); diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index de4e70fb3cbb..37848167c4b8 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1689,7 +1689,7 @@ int btrfs_should_delete_dir_index(struct list_head *del_list, * */ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, - struct list_head *ins_list) + struct list_head *ins_list, bool *emitted) { struct btrfs_dir_item *di; struct btrfs_delayed_item *curr, *next; @@ -1733,6 +1733,7 @@ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, if (over) return 1; + *emitted = true; } return 0; } diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h index f70119f25421..0167853c84ae 100644 --- a/fs/btrfs/delayed-inode.h +++ b/fs/btrfs/delayed-inode.h @@ -144,7 +144,7 @@ void btrfs_put_delayed_items(struct list_head *ins_list, int btrfs_should_delete_dir_index(struct list_head *del_list, u64 index); int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, - struct list_head *ins_list); + struct list_head *ins_list, bool *emitted); /* for init */ int __init btrfs_delayed_inode_init(void); diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index fc8df866e919..1752625fb4dd 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -21,10 +21,6 @@ #include "hash.h" #include "transaction.h" -static struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root, - struct btrfs_path *path, - const char *name, int name_len); - /* * insert a name into a directory, doing overflow properly if there is a hash * collision. data_size indicates how big the item inserted should be. On @@ -383,9 +379,9 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans, * this walks through all the entries in a dir item and finds one * for a specific name. */ -static struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root, - struct btrfs_path *path, - const char *name, int name_len) +struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root, + struct btrfs_path *path, + const char *name, int name_len) { struct btrfs_dir_item *dir_item; unsigned long name_ptr; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b1709831b1a1..5177954e1a2c 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2418,6 +2418,7 @@ int open_ctree(struct super_block *sb, if (btrfs_check_super_csum(bh->b_data)) { printk(KERN_ERR "BTRFS: superblock checksum mismatch\n"); err = -EINVAL; + brelse(bh); goto fail_alloc; } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 950479f2d337..a067065efa6b 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -7237,7 +7237,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, set_extent_dirty(&trans->transaction->dirty_pages, buf->start, buf->start + buf->len - 1, GFP_NOFS); } - trans->blocks_used++; + trans->dirty = true; /* this returns a buffer locked for blocking */ return buf; } @@ -9196,9 +9196,8 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans, int ret = 0; list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) { - list_del_init(&block_group->bg_list); if (ret) - continue; + goto next; spin_lock(&block_group->lock); memcpy(&item, &block_group->item, sizeof(item)); @@ -9213,6 +9212,8 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans, key.objectid, key.offset); if (ret) btrfs_abort_transaction(trans, extent_root, ret); +next: + list_del_init(&block_group->bg_list); } } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index bf3f424e0013..cb239ddae5c9 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2767,7 +2767,8 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree, bio_end_io_t end_io_func, int mirror_num, unsigned long prev_bio_flags, - unsigned long bio_flags) + unsigned long bio_flags, + bool force_bio_submit) { int ret = 0; struct bio *bio; @@ -2785,6 +2786,7 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree, contig = bio_end_sector(bio) == sector; if (prev_bio_flags != bio_flags || !contig || + force_bio_submit || merge_bio(rw, tree, page, offset, page_size, bio, bio_flags) || bio_add_page(bio, page, page_size, offset) < page_size) { ret = submit_one_bio(rw, bio, mirror_num, @@ -2876,7 +2878,8 @@ static int __do_readpage(struct extent_io_tree *tree, get_extent_t *get_extent, struct extent_map **em_cached, struct bio **bio, int mirror_num, - unsigned long *bio_flags, int rw) + unsigned long *bio_flags, int rw, + u64 *prev_em_start) { struct inode *inode = page->mapping->host; u64 start = page_offset(page); @@ -2924,6 +2927,7 @@ static int __do_readpage(struct extent_io_tree *tree, } while (cur <= end) { unsigned long pnr = (last_byte >> PAGE_CACHE_SHIFT) + 1; + bool force_bio_submit = false; if (cur >= last_byte) { char *userpage; @@ -2974,6 +2978,49 @@ static int __do_readpage(struct extent_io_tree *tree, block_start = em->block_start; if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) block_start = EXTENT_MAP_HOLE; + + /* + * If we have a file range that points to a compressed extent + * and it's followed by a consecutive file range that points to + * to the same compressed extent (possibly with a different + * offset and/or length, so it either points to the whole extent + * or only part of it), we must make sure we do not submit a + * single bio to populate the pages for the 2 ranges because + * this makes the compressed extent read zero out the pages + * belonging to the 2nd range. Imagine the following scenario: + * + * File layout + * [0 - 8K] [8K - 24K] + * | | + * | | + * points to extent X, points to extent X, + * offset 4K, length of 8K offset 0, length 16K + * + * [extent X, compressed length = 4K uncompressed length = 16K] + * + * If the bio to read the compressed extent covers both ranges, + * it will decompress extent X into the pages belonging to the + * first range and then it will stop, zeroing out the remaining + * pages that belong to the other range that points to extent X. + * So here we make sure we submit 2 bios, one for the first + * range and another one for the third range. Both will target + * the same physical extent from disk, but we can't currently + * make the compressed bio endio callback populate the pages + * for both ranges because each compressed bio is tightly + * coupled with a single extent map, and each range can have + * an extent map with a different offset value relative to the + * uncompressed data of our extent and different lengths. This + * is a corner case so we prioritize correctness over + * non-optimal behavior (submitting 2 bios for the same extent). + */ + if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) && + prev_em_start && *prev_em_start != (u64)-1 && + *prev_em_start != em->orig_start) + force_bio_submit = true; + + if (prev_em_start) + *prev_em_start = em->orig_start; + free_extent_map(em); em = NULL; @@ -3023,7 +3070,8 @@ static int __do_readpage(struct extent_io_tree *tree, bdev, bio, pnr, end_bio_extent_readpage, mirror_num, *bio_flags, - this_bio_flag); + this_bio_flag, + force_bio_submit); if (!ret) { nr++; *bio_flags = this_bio_flag; @@ -3050,7 +3098,8 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree, get_extent_t *get_extent, struct extent_map **em_cached, struct bio **bio, int mirror_num, - unsigned long *bio_flags, int rw) + unsigned long *bio_flags, int rw, + u64 *prev_em_start) { struct inode *inode; struct btrfs_ordered_extent *ordered; @@ -3070,7 +3119,7 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree, for (index = 0; index < nr_pages; index++) { __do_readpage(tree, pages[index], get_extent, em_cached, bio, - mirror_num, bio_flags, rw); + mirror_num, bio_flags, rw, prev_em_start); page_cache_release(pages[index]); } } @@ -3080,7 +3129,8 @@ static void __extent_readpages(struct extent_io_tree *tree, int nr_pages, get_extent_t *get_extent, struct extent_map **em_cached, struct bio **bio, int mirror_num, - unsigned long *bio_flags, int rw) + unsigned long *bio_flags, int rw, + u64 *prev_em_start) { u64 start = 0; u64 end = 0; @@ -3101,7 +3151,7 @@ static void __extent_readpages(struct extent_io_tree *tree, index - first_index, start, end, get_extent, em_cached, bio, mirror_num, bio_flags, - rw); + rw, prev_em_start); start = page_start; end = start + PAGE_CACHE_SIZE - 1; first_index = index; @@ -3112,7 +3162,8 @@ static void __extent_readpages(struct extent_io_tree *tree, __do_contiguous_readpages(tree, &pages[first_index], index - first_index, start, end, get_extent, em_cached, bio, - mirror_num, bio_flags, rw); + mirror_num, bio_flags, rw, + prev_em_start); } static int __extent_read_full_page(struct extent_io_tree *tree, @@ -3138,7 +3189,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree, } ret = __do_readpage(tree, page, get_extent, NULL, bio, mirror_num, - bio_flags, rw); + bio_flags, rw, NULL); return ret; } @@ -3164,7 +3215,7 @@ int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page, int ret; ret = __do_readpage(tree, page, get_extent, NULL, &bio, mirror_num, - &bio_flags, READ); + &bio_flags, READ, NULL); if (bio) ret = submit_one_bio(READ, bio, mirror_num, bio_flags); return ret; @@ -3417,7 +3468,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, sector, iosize, pg_offset, bdev, &epd->bio, max_nr, end_bio_extent_writepage, - 0, 0, 0); + 0, 0, 0, false); if (ret) SetPageError(page); } @@ -3719,7 +3770,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, ret = submit_extent_page(rw, tree, p, offset >> 9, PAGE_CACHE_SIZE, 0, bdev, &epd->bio, -1, end_bio_extent_buffer_writepage, - 0, epd->bio_flags, bio_flags); + 0, epd->bio_flags, bio_flags, false); epd->bio_flags = bio_flags; if (ret) { set_btree_ioerr(p); @@ -4123,6 +4174,7 @@ int extent_readpages(struct extent_io_tree *tree, struct page *page; struct extent_map *em_cached = NULL; int nr = 0; + u64 prev_em_start = (u64)-1; for (page_idx = 0; page_idx < nr_pages; page_idx++) { page = list_entry(pages->prev, struct page, lru); @@ -4139,12 +4191,12 @@ int extent_readpages(struct extent_io_tree *tree, if (nr < ARRAY_SIZE(pagepool)) continue; __extent_readpages(tree, pagepool, nr, get_extent, &em_cached, - &bio, 0, &bio_flags, READ); + &bio, 0, &bio_flags, READ, &prev_em_start); nr = 0; } if (nr) __extent_readpages(tree, pagepool, nr, get_extent, &em_cached, - &bio, 0, &bio_flags, READ); + &bio, 0, &bio_flags, READ, &prev_em_start); if (em_cached) free_extent_map(em_cached); @@ -4484,8 +4536,11 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, } ret = fiemap_fill_next_extent(fieinfo, em_start, disko, em_len, flags); - if (ret) + if (ret) { + if (ret == 1) + ret = 0; goto out_free; + } } out_free: free_extent_map(em); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 5193c7844315..2ad4cb3da8f6 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -760,8 +760,16 @@ next_slot: } btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); - if (key.objectid > ino || - key.type > BTRFS_EXTENT_DATA_KEY || key.offset >= end) + + if (key.objectid > ino) + break; + if (WARN_ON_ONCE(key.objectid < ino) || + key.type < BTRFS_EXTENT_DATA_KEY) { + ASSERT(del_nr == 0); + path->slots[0]++; + goto next_slot; + } + if (key.type > BTRFS_EXTENT_DATA_KEY || key.offset >= end) break; fi = btrfs_item_ptr(leaf, path->slots[0], @@ -780,8 +788,8 @@ next_slot: btrfs_file_extent_inline_len(leaf, path->slots[0], fi); } else { - WARN_ON(1); - extent_end = search_start; + /* can't happen */ + BUG(); } /* @@ -2789,7 +2797,7 @@ const struct file_operations btrfs_file_operations = { .fallocate = btrfs_fallocate, .unlocked_ioctl = btrfs_ioctl, #ifdef CONFIG_COMPAT - .compat_ioctl = btrfs_ioctl, + .compat_ioctl = btrfs_compat_ioctl, #endif }; diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index 83d646bd2e4b..ed2de833dd18 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -271,7 +271,7 @@ void btrfs_unpin_free_ino(struct btrfs_root *root) __btrfs_add_free_space(ctl, info->offset, count); free: rb_erase(&info->offset_index, rbroot); - kfree(info); + kmem_cache_free(btrfs_free_space_cachep, info); } } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index edaa6178b4ec..ef677cdf777f 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1268,8 +1268,14 @@ next_slot: num_bytes = 0; btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); - if (found_key.objectid > ino || - found_key.type > BTRFS_EXTENT_DATA_KEY || + if (found_key.objectid > ino) + break; + if (WARN_ON_ONCE(found_key.objectid < ino) || + found_key.type < BTRFS_EXTENT_DATA_KEY) { + path->slots[0]++; + goto next_slot; + } + if (found_key.type > BTRFS_EXTENT_DATA_KEY || found_key.offset > end) break; @@ -4802,7 +4808,8 @@ void btrfs_evict_inode(struct inode *inode) goto no_delete; } /* do we really want it for ->i_nlink > 0 and zero btrfs_root_refs? */ - btrfs_wait_ordered_range(inode, 0, (u64)-1); + if (!special_file(inode->i_mode)) + btrfs_wait_ordered_range(inode, 0, (u64)-1); btrfs_free_io_failure_record(inode, 0, (u64)-1); @@ -5334,6 +5341,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) char *name_ptr; int name_len; int is_curr = 0; /* ctx->pos points to the current index? */ + bool emitted; /* FIXME, use a real flag for deciding about the key type */ if (root->fs_info->tree_root == root) @@ -5362,6 +5370,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) if (ret < 0) goto err; + emitted = false; while (1) { leaf = path->nodes[0]; slot = path->slots[0]; @@ -5441,6 +5450,7 @@ skip: if (over) goto nopos; + emitted = true; di_len = btrfs_dir_name_len(leaf, di) + btrfs_dir_data_len(leaf, di) + sizeof(*di); di_cur += di_len; @@ -5453,11 +5463,20 @@ next: if (key_type == BTRFS_DIR_INDEX_KEY) { if (is_curr) ctx->pos++; - ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list); + ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list, &emitted); if (ret) goto nopos; } + /* + * If we haven't emitted any dir entry, we must not touch ctx->pos as + * it was was set to the termination value in previous call. We assume + * that "." and ".." were emitted if we reach this point and set the + * termination value as well for an empty directory. + */ + if (ctx->pos > 2 && !emitted) + goto nopos; + /* Reached end of directory/root. Bump pos past the last item. */ ctx->pos++; @@ -6073,7 +6092,7 @@ out_unlock_inode: static int btrfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { - struct btrfs_trans_handle *trans; + struct btrfs_trans_handle *trans = NULL; struct btrfs_root *root = BTRFS_I(dir)->root; struct inode *inode = old_dentry->d_inode; u64 index; @@ -6099,6 +6118,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, trans = btrfs_start_transaction(root, 5); if (IS_ERR(trans)) { err = PTR_ERR(trans); + trans = NULL; goto fail; } @@ -6132,9 +6152,10 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, btrfs_log_new_name(trans, inode, NULL, parent); } - btrfs_end_transaction(trans, root); btrfs_balance_delayed_items(root); fail: + if (trans) + btrfs_end_transaction(trans, root); if (drop_inode) { inode_dec_link_count(inode); iput(inode); @@ -8034,15 +8055,28 @@ int btrfs_readpage(struct file *file, struct page *page) static int btrfs_writepage(struct page *page, struct writeback_control *wbc) { struct extent_io_tree *tree; - + struct inode *inode = page->mapping->host; + int ret; if (current->flags & PF_MEMALLOC) { redirty_page_for_writepage(wbc, page); unlock_page(page); return 0; } + + /* + * If we are under memory pressure we will call this directly from the + * VM, we need to make sure we have the inode referenced for the ordered + * extent. If not just return like we didn't do anything. + */ + if (!igrab(inode)) { + redirty_page_for_writepage(wbc, page); + return AOP_WRITEPAGE_ACTIVATE; + } tree = &BTRFS_I(page->mapping->host)->io_tree; - return extent_write_full_page(tree, page, btrfs_get_extent, wbc); + ret = extent_write_full_page(tree, page, btrfs_get_extent, wbc); + btrfs_add_delayed_iput(inode); + return ret; } static int btrfs_writepages(struct address_space *mapping, @@ -9118,9 +9152,11 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, /* * 2 items for inode item and ref * 2 items for dir items + * 1 item for updating parent inode item + * 1 item for the inline extent item * 1 item for xattr if selinux is on */ - trans = btrfs_start_transaction(root, 5); + trans = btrfs_start_transaction(root, 7); if (IS_ERR(trans)) return PTR_ERR(trans); @@ -9477,7 +9513,7 @@ static const struct file_operations btrfs_dir_file_operations = { .iterate = btrfs_real_readdir, .unlocked_ioctl = btrfs_ioctl, #ifdef CONFIG_COMPAT - .compat_ioctl = btrfs_ioctl, + .compat_ioctl = btrfs_compat_ioctl, #endif .release = btrfs_release_file, .fsync = btrfs_sync_file, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index fce3b5b9a2bb..d96b2bc444c8 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1656,7 +1656,7 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file, src_inode = file_inode(src.file); if (src_inode->i_sb != file_inode(file)->i_sb) { - btrfs_info(BTRFS_I(src_inode)->root->fs_info, + btrfs_info(BTRFS_I(file_inode(file))->root->fs_info, "Snapshot src from another FS"); ret = -EXDEV; } else if (!inode_owner_or_capable(src_inode)) { @@ -2434,8 +2434,6 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, goto out_unlock_inode; } - d_invalidate(dentry); - down_write(&root->fs_info->subvol_sem); err = may_destroy_subvol(dest); @@ -2529,7 +2527,7 @@ out_up_write: out_unlock_inode: mutex_unlock(&inode->i_mutex); if (!err) { - shrink_dcache_sb(root->fs_info->sb); + d_invalidate(dentry); btrfs_invalidate_inodes(dest); d_delete(dentry); ASSERT(dest->send_in_progress == 0); @@ -2961,7 +2959,7 @@ out_unlock: static long btrfs_ioctl_file_extent_same(struct file *file, struct btrfs_ioctl_same_args __user *argp) { - struct btrfs_ioctl_same_args *same; + struct btrfs_ioctl_same_args *same = NULL; struct btrfs_ioctl_same_extent_info *info; struct inode *src = file_inode(file); u64 off; @@ -2991,6 +2989,7 @@ static long btrfs_ioctl_file_extent_same(struct file *file, if (IS_ERR(same)) { ret = PTR_ERR(same); + same = NULL; goto out; } @@ -3061,6 +3060,7 @@ static long btrfs_ioctl_file_extent_same(struct file *file, out: mnt_drop_write_file(file); + kfree(same); return ret; } @@ -3187,6 +3187,150 @@ static void clone_update_extent_map(struct inode *inode, &BTRFS_I(inode)->runtime_flags); } +/* + * Make sure we do not end up inserting an inline extent into a file that has + * already other (non-inline) extents. If a file has an inline extent it can + * not have any other extents and the (single) inline extent must start at the + * file offset 0. Failing to respect these rules will lead to file corruption, + * resulting in EIO errors on read/write operations, hitting BUG_ON's in mm, etc + * + * We can have extents that have been already written to disk or we can have + * dirty ranges still in delalloc, in which case the extent maps and items are + * created only when we run delalloc, and the delalloc ranges might fall outside + * the range we are currently locking in the inode's io tree. So we check the + * inode's i_size because of that (i_size updates are done while holding the + * i_mutex, which we are holding here). + * We also check to see if the inode has a size not greater than "datal" but has + * extents beyond it, due to an fallocate with FALLOC_FL_KEEP_SIZE (and we are + * protected against such concurrent fallocate calls by the i_mutex). + * + * If the file has no extents but a size greater than datal, do not allow the + * copy because we would need turn the inline extent into a non-inline one (even + * with NO_HOLES enabled). If we find our destination inode only has one inline + * extent, just overwrite it with the source inline extent if its size is less + * than the source extent's size, or we could copy the source inline extent's + * data into the destination inode's inline extent if the later is greater then + * the former. + */ +static int clone_copy_inline_extent(struct inode *src, + struct inode *dst, + struct btrfs_trans_handle *trans, + struct btrfs_path *path, + struct btrfs_key *new_key, + const u64 drop_start, + const u64 datal, + const u64 skip, + const u64 size, + char *inline_data) +{ + struct btrfs_root *root = BTRFS_I(dst)->root; + const u64 aligned_end = ALIGN(new_key->offset + datal, + root->sectorsize); + int ret; + struct btrfs_key key; + + if (new_key->offset > 0) + return -EOPNOTSUPP; + + key.objectid = btrfs_ino(dst); + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = 0; + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) { + return ret; + } else if (ret > 0) { + if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { + ret = btrfs_next_leaf(root, path); + if (ret < 0) + return ret; + else if (ret > 0) + goto copy_inline_extent; + } + btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); + if (key.objectid == btrfs_ino(dst) && + key.type == BTRFS_EXTENT_DATA_KEY) { + ASSERT(key.offset > 0); + return -EOPNOTSUPP; + } + } else if (i_size_read(dst) <= datal) { + struct btrfs_file_extent_item *ei; + u64 ext_len; + + /* + * If the file size is <= datal, make sure there are no other + * extents following (can happen do to an fallocate call with + * the flag FALLOC_FL_KEEP_SIZE). + */ + ei = btrfs_item_ptr(path->nodes[0], path->slots[0], + struct btrfs_file_extent_item); + /* + * If it's an inline extent, it can not have other extents + * following it. + */ + if (btrfs_file_extent_type(path->nodes[0], ei) == + BTRFS_FILE_EXTENT_INLINE) + goto copy_inline_extent; + + ext_len = btrfs_file_extent_num_bytes(path->nodes[0], ei); + if (ext_len > aligned_end) + return -EOPNOTSUPP; + + ret = btrfs_next_item(root, path); + if (ret < 0) { + return ret; + } else if (ret == 0) { + btrfs_item_key_to_cpu(path->nodes[0], &key, + path->slots[0]); + if (key.objectid == btrfs_ino(dst) && + key.type == BTRFS_EXTENT_DATA_KEY) + return -EOPNOTSUPP; + } + } + +copy_inline_extent: + /* + * We have no extent items, or we have an extent at offset 0 which may + * or may not be inlined. All these cases are dealt the same way. + */ + if (i_size_read(dst) > datal) { + /* + * If the destination inode has an inline extent... + * This would require copying the data from the source inline + * extent into the beginning of the destination's inline extent. + * But this is really complex, both extents can be compressed + * or just one of them, which would require decompressing and + * re-compressing data (which could increase the new compressed + * size, not allowing the compressed data to fit anymore in an + * inline extent). + * So just don't support this case for now (it should be rare, + * we are not really saving space when cloning inline extents). + */ + return -EOPNOTSUPP; + } + + btrfs_release_path(path); + ret = btrfs_drop_extents(trans, root, dst, drop_start, aligned_end, 1); + if (ret) + return ret; + ret = btrfs_insert_empty_item(trans, root, path, new_key, size); + if (ret) + return ret; + + if (skip) { + const u32 start = btrfs_file_extent_calc_inline_size(0); + + memmove(inline_data + start, inline_data + start + skip, datal); + } + + write_extent_buffer(path->nodes[0], inline_data, + btrfs_item_ptr_offset(path->nodes[0], + path->slots[0]), + size); + inode_add_bytes(dst, datal); + + return 0; +} + /** * btrfs_clone() - clone a range from inode file to another * @@ -3451,7 +3595,6 @@ process_slot: } else if (type == BTRFS_FILE_EXTENT_INLINE) { u64 skip = 0; u64 trim = 0; - u64 aligned_end = 0; if (off > key.offset) { skip = off - key.offset; @@ -3469,42 +3612,22 @@ process_slot: size -= skip + trim; datal -= skip + trim; - aligned_end = ALIGN(new_key.offset + datal, - root->sectorsize); - ret = btrfs_drop_extents(trans, root, inode, - drop_start, - aligned_end, - 1); + ret = clone_copy_inline_extent(src, inode, + trans, path, + &new_key, + drop_start, + datal, + skip, size, buf); if (ret) { if (ret != -EOPNOTSUPP) btrfs_abort_transaction(trans, - root, ret); - btrfs_end_transaction(trans, root); - goto out; - } - - ret = btrfs_insert_empty_item(trans, root, path, - &new_key, size); - if (ret) { - btrfs_abort_transaction(trans, root, - ret); + root, + ret); btrfs_end_transaction(trans, root); goto out; } - - if (skip) { - u32 start = - btrfs_file_extent_calc_inline_size(0); - memmove(buf+start, buf+start+skip, - datal); - } - leaf = path->nodes[0]; slot = path->slots[0]; - write_extent_buffer(leaf, buf, - btrfs_item_ptr_offset(leaf, slot), - size); - inode_add_bytes(inode, datal); } /* If we have an implicit hole (NO_HOLES feature). */ @@ -5372,3 +5495,24 @@ long btrfs_ioctl(struct file *file, unsigned int return -ENOTTY; } + +#ifdef CONFIG_COMPAT +long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + switch (cmd) { + case FS_IOC32_GETFLAGS: + cmd = FS_IOC_GETFLAGS; + break; + case FS_IOC32_SETFLAGS: + cmd = FS_IOC_SETFLAGS; + break; + case FS_IOC32_GETVERSION: + cmd = FS_IOC_GETVERSION; + break; + default: + return -ENOIOCTLCMD; + } + + return btrfs_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); +} +#endif diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 874828dd0a86..3cc2d1dfd7bf 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1461,7 +1461,21 @@ static int read_symlink(struct btrfs_root *root, ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto out; - BUG_ON(ret); + if (ret) { + /* + * An empty symlink inode. Can happen in rare error paths when + * creating a symlink (transaction committed before the inode + * eviction handler removed the symlink inode items and a crash + * happened in between or the subvol was snapshoted in between). + * Print an informative message to dmesg/syslog so that the user + * can delete the symlink. + */ + btrfs_err(root->fs_info, + "Found empty symlink inode %llu at root %llu", + ino, root->root_key.objectid); + ret = -EIO; + goto out; + } ei = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_file_extent_item); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index cde9c03e3913..cf6d11bb8dcb 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -262,7 +262,7 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans, trans->aborted = errno; /* Nothing used. The other threads that have joined this * transaction may be able to continue. */ - if (!trans->blocks_used) { + if (!trans->dirty && list_empty(&trans->new_bgs)) { const char *errstr; errstr = btrfs_decode_error(errno); @@ -901,6 +901,15 @@ find_root: if (IS_ERR(new_root)) return ERR_CAST(new_root); + if (!(sb->s_flags & MS_RDONLY)) { + int ret; + down_read(&fs_info->cleanup_work_sem); + ret = btrfs_orphan_cleanup(new_root); + up_read(&fs_info->cleanup_work_sem); + if (ret) + return ERR_PTR(ret); + } + dir_id = btrfs_root_dirid(&new_root->root_item); setup_root: location.objectid = dir_id; @@ -1766,6 +1775,8 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes) * there are other factors that may change the result (like a new metadata * chunk). * + * If metadata is exhausted, f_bavail will be 0. + * * FIXME: not accurate for mixed block groups, total and free/used are ok, * available appears slightly larger. */ @@ -1777,11 +1788,13 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) struct btrfs_space_info *found; u64 total_used = 0; u64 total_free_data = 0; + u64 total_free_meta = 0; int bits = dentry->d_sb->s_blocksize_bits; __be32 *fsid = (__be32 *)fs_info->fsid; unsigned factor = 1; struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv; int ret; + u64 thresh = 0; /* * holding chunk_muext to avoid allocating new chunks, holding @@ -1809,6 +1822,8 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) } } } + if (found->flags & BTRFS_BLOCK_GROUP_METADATA) + total_free_meta += found->disk_total - found->disk_used; total_used += found->disk_used; } @@ -1836,6 +1851,24 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) mutex_unlock(&fs_info->chunk_mutex); mutex_unlock(&fs_info->fs_devices->device_list_mutex); + /* + * We calculate the remaining metadata space minus global reserve. If + * this is (supposedly) smaller than zero, there's no space. But this + * does not hold in practice, the exhausted state happens where's still + * some positive delta. So we apply some guesswork and compare the + * delta to a 4M threshold. (Practically observed delta was ~2M.) + * + * We probably cannot calculate the exact threshold value because this + * depends on the internal reservations requested by various + * operations, so some operations that consume a few metadata will + * succeed even if the Avail is zero. But this is better than the other + * way around. + */ + thresh = 4 * 1024 * 1024; + + if (total_free_meta - thresh < block_rsv->size) + buf->f_bavail = 0; + buf->f_type = BTRFS_SUPER_MAGIC; buf->f_bsize = dentry->d_sb->s_blocksize; buf->f_namelen = BTRFS_NAME_LEN; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 63c6d05950f2..30dbf315c2d6 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -472,7 +472,6 @@ again: h->transid = cur_trans->transid; h->transaction = cur_trans; - h->blocks_used = 0; h->bytes_reserved = 0; h->root = root; h->delayed_ref_updates = 0; @@ -723,7 +722,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, if (!list_empty(&trans->ordered)) { spin_lock(&info->trans_lock); - list_splice(&trans->ordered, &cur_trans->pending_ordered); + list_splice_init(&trans->ordered, &cur_trans->pending_ordered); spin_unlock(&info->trans_lock); } @@ -1732,7 +1731,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, } spin_lock(&root->fs_info->trans_lock); - list_splice(&trans->ordered, &cur_trans->pending_ordered); + list_splice_init(&trans->ordered, &cur_trans->pending_ordered); if (cur_trans->state >= TRANS_STATE_COMMIT_START) { spin_unlock(&root->fs_info->trans_lock); atomic_inc(&cur_trans->use_count); @@ -1756,8 +1755,11 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, spin_unlock(&root->fs_info->trans_lock); wait_for_commit(root, prev_trans); + ret = prev_trans->aborted; btrfs_put_transaction(prev_trans); + if (ret) + goto cleanup_transaction; } else { spin_unlock(&root->fs_info->trans_lock); } diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 1ba9c3e04191..1cf5de30368a 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -88,7 +88,6 @@ struct btrfs_trans_handle { u64 qgroup_reserved; unsigned long use_count; unsigned long blocks_reserved; - unsigned long blocks_used; unsigned long delayed_ref_updates; struct btrfs_transaction *transaction; struct btrfs_block_rsv *block_rsv; @@ -98,6 +97,7 @@ struct btrfs_trans_handle { bool allocating_chunk; bool reloc_reserved; bool sync; + bool dirty; unsigned int type; /* * this root is only needed to validate that the root passed to diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 3b68c75eccea..f6c20cf6090e 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3929,6 +3929,308 @@ static int logged_inode_size(struct btrfs_root *log, struct inode *inode, return 0; } +/* + * At the moment we always log all xattrs. This is to figure out at log replay + * time which xattrs must have their deletion replayed. If a xattr is missing + * in the log tree and exists in the fs/subvol tree, we delete it. This is + * because if a xattr is deleted, the inode is fsynced and a power failure + * happens, causing the log to be replayed the next time the fs is mounted, + * we want the xattr to not exist anymore (same behaviour as other filesystems + * with a journal, ext3/4, xfs, f2fs, etc). + */ +static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + struct inode *inode, + struct btrfs_path *path, + struct btrfs_path *dst_path) +{ + int ret; + struct btrfs_key key; + const u64 ino = btrfs_ino(inode); + int ins_nr = 0; + int start_slot = 0; + + key.objectid = ino; + key.type = BTRFS_XATTR_ITEM_KEY; + key.offset = 0; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) + return ret; + + while (true) { + int slot = path->slots[0]; + struct extent_buffer *leaf = path->nodes[0]; + int nritems = btrfs_header_nritems(leaf); + + if (slot >= nritems) { + if (ins_nr > 0) { + u64 last_extent = 0; + + ret = copy_items(trans, inode, dst_path, path, + &last_extent, start_slot, + ins_nr, 1, 0); + /* can't be 1, extent items aren't processed */ + ASSERT(ret <= 0); + if (ret < 0) + return ret; + ins_nr = 0; + } + ret = btrfs_next_leaf(root, path); + if (ret < 0) + return ret; + else if (ret > 0) + break; + continue; + } + + btrfs_item_key_to_cpu(leaf, &key, slot); + if (key.objectid != ino || key.type != BTRFS_XATTR_ITEM_KEY) + break; + + if (ins_nr == 0) + start_slot = slot; + ins_nr++; + path->slots[0]++; + cond_resched(); + } + if (ins_nr > 0) { + u64 last_extent = 0; + + ret = copy_items(trans, inode, dst_path, path, + &last_extent, start_slot, + ins_nr, 1, 0); + /* can't be 1, extent items aren't processed */ + ASSERT(ret <= 0); + if (ret < 0) + return ret; + } + + return 0; +} + +/* + * If the no holes feature is enabled we need to make sure any hole between the + * last extent and the i_size of our inode is explicitly marked in the log. This + * is to make sure that doing something like: + * + * 1) create file with 128Kb of data + * 2) truncate file to 64Kb + * 3) truncate file to 256Kb + * 4) fsync file + * 5) <crash/power failure> + * 6) mount fs and trigger log replay + * + * Will give us a file with a size of 256Kb, the first 64Kb of data match what + * the file had in its first 64Kb of data at step 1 and the last 192Kb of the + * file correspond to a hole. The presence of explicit holes in a log tree is + * what guarantees that log replay will remove/adjust file extent items in the + * fs/subvol tree. + * + * Here we do not need to care about holes between extents, that is already done + * by copy_items(). We also only need to do this in the full sync path, where we + * lookup for extents from the fs/subvol tree only. In the fast path case, we + * lookup the list of modified extent maps and if any represents a hole, we + * insert a corresponding extent representing a hole in the log tree. + */ +static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + struct inode *inode, + struct btrfs_path *path) +{ + int ret; + struct btrfs_key key; + u64 hole_start; + u64 hole_size; + struct extent_buffer *leaf; + struct btrfs_root *log = root->log_root; + const u64 ino = btrfs_ino(inode); + const u64 i_size = i_size_read(inode); + + if (!btrfs_fs_incompat(root->fs_info, NO_HOLES)) + return 0; + + key.objectid = ino; + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = (u64)-1; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + ASSERT(ret != 0); + if (ret < 0) + return ret; + + ASSERT(path->slots[0] > 0); + path->slots[0]--; + leaf = path->nodes[0]; + btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); + + if (key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY) { + /* inode does not have any extents */ + hole_start = 0; + hole_size = i_size; + } else { + struct btrfs_file_extent_item *extent; + u64 len; + + /* + * If there's an extent beyond i_size, an explicit hole was + * already inserted by copy_items(). + */ + if (key.offset >= i_size) + return 0; + + extent = btrfs_item_ptr(leaf, path->slots[0], + struct btrfs_file_extent_item); + + if (btrfs_file_extent_type(leaf, extent) == + BTRFS_FILE_EXTENT_INLINE) { + len = btrfs_file_extent_inline_len(leaf, + path->slots[0], + extent); + ASSERT(len == i_size); + return 0; + } + + len = btrfs_file_extent_num_bytes(leaf, extent); + /* Last extent goes beyond i_size, no need to log a hole. */ + if (key.offset + len > i_size) + return 0; + hole_start = key.offset + len; + hole_size = i_size - hole_start; + } + btrfs_release_path(path); + + /* Last extent ends at i_size. */ + if (hole_size == 0) + return 0; + + hole_size = ALIGN(hole_size, root->sectorsize); + ret = btrfs_insert_file_extent(trans, log, ino, hole_start, 0, 0, + hole_size, 0, hole_size, 0, 0, 0); + return ret; +} + +/* + * When we are logging a new inode X, check if it doesn't have a reference that + * matches the reference from some other inode Y created in a past transaction + * and that was renamed in the current transaction. If we don't do this, then at + * log replay time we can lose inode Y (and all its files if it's a directory): + * + * mkdir /mnt/x + * echo "hello world" > /mnt/x/foobar + * sync + * mv /mnt/x /mnt/y + * mkdir /mnt/x # or touch /mnt/x + * xfs_io -c fsync /mnt/x + * <power fail> + * mount fs, trigger log replay + * + * After the log replay procedure, we would lose the first directory and all its + * files (file foobar). + * For the case where inode Y is not a directory we simply end up losing it: + * + * echo "123" > /mnt/foo + * sync + * mv /mnt/foo /mnt/bar + * echo "abc" > /mnt/foo + * xfs_io -c fsync /mnt/foo + * <power fail> + * + * We also need this for cases where a snapshot entry is replaced by some other + * entry (file or directory) otherwise we end up with an unreplayable log due to + * attempts to delete the snapshot entry (entry of type BTRFS_ROOT_ITEM_KEY) as + * if it were a regular entry: + * + * mkdir /mnt/x + * btrfs subvolume snapshot /mnt /mnt/x/snap + * btrfs subvolume delete /mnt/x/snap + * rmdir /mnt/x + * mkdir /mnt/x + * fsync /mnt/x or fsync some new file inside it + * <power fail> + * + * The snapshot delete, rmdir of x, mkdir of a new x and the fsync all happen in + * the same transaction. + */ +static int btrfs_check_ref_name_override(struct extent_buffer *eb, + const int slot, + const struct btrfs_key *key, + struct inode *inode) +{ + int ret; + struct btrfs_path *search_path; + char *name = NULL; + u32 name_len = 0; + u32 item_size = btrfs_item_size_nr(eb, slot); + u32 cur_offset = 0; + unsigned long ptr = btrfs_item_ptr_offset(eb, slot); + + search_path = btrfs_alloc_path(); + if (!search_path) + return -ENOMEM; + search_path->search_commit_root = 1; + search_path->skip_locking = 1; + + while (cur_offset < item_size) { + u64 parent; + u32 this_name_len; + u32 this_len; + unsigned long name_ptr; + struct btrfs_dir_item *di; + + if (key->type == BTRFS_INODE_REF_KEY) { + struct btrfs_inode_ref *iref; + + iref = (struct btrfs_inode_ref *)(ptr + cur_offset); + parent = key->offset; + this_name_len = btrfs_inode_ref_name_len(eb, iref); + name_ptr = (unsigned long)(iref + 1); + this_len = sizeof(*iref) + this_name_len; + } else { + struct btrfs_inode_extref *extref; + + extref = (struct btrfs_inode_extref *)(ptr + + cur_offset); + parent = btrfs_inode_extref_parent(eb, extref); + this_name_len = btrfs_inode_extref_name_len(eb, extref); + name_ptr = (unsigned long)&extref->name; + this_len = sizeof(*extref) + this_name_len; + } + + if (this_name_len > name_len) { + char *new_name; + + new_name = krealloc(name, this_name_len, GFP_NOFS); + if (!new_name) { + ret = -ENOMEM; + goto out; + } + name_len = this_name_len; + name = new_name; + } + + read_extent_buffer(eb, name, name_ptr, this_name_len); + di = btrfs_lookup_dir_item(NULL, BTRFS_I(inode)->root, + search_path, parent, + name, this_name_len, 0); + if (di && !IS_ERR(di)) { + ret = 1; + goto out; + } else if (IS_ERR(di)) { + ret = PTR_ERR(di); + goto out; + } + btrfs_release_path(search_path); + + cur_offset += this_len; + } + ret = 0; +out: + btrfs_free_path(search_path); + kfree(name); + return ret; +} + /* log a single inode in the tree log. * At least one parent directory for this inode must exist in the tree * or be logged already. @@ -3967,6 +4269,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, u64 ino = btrfs_ino(inode); struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; u64 logged_isize = 0; + bool need_log_inode_item = true; path = btrfs_alloc_path(); if (!path) @@ -4056,11 +4359,6 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, } else { if (inode_only == LOG_INODE_ALL) fast_search = true; - ret = log_inode_item(trans, log, dst_path, inode); - if (ret) { - err = ret; - goto out_unlock; - } goto log_extents; } @@ -4083,6 +4381,44 @@ again: if (min_key.type > max_key.type) break; + if (min_key.type == BTRFS_INODE_ITEM_KEY) + need_log_inode_item = false; + + if ((min_key.type == BTRFS_INODE_REF_KEY || + min_key.type == BTRFS_INODE_EXTREF_KEY) && + BTRFS_I(inode)->generation == trans->transid) { + ret = btrfs_check_ref_name_override(path->nodes[0], + path->slots[0], + &min_key, inode); + if (ret < 0) { + err = ret; + goto out_unlock; + } else if (ret > 0) { + err = 1; + btrfs_set_log_full_commit(root->fs_info, trans); + goto out_unlock; + } + } + + /* Skip xattrs, we log them later with btrfs_log_all_xattrs() */ + if (min_key.type == BTRFS_XATTR_ITEM_KEY) { + if (ins_nr == 0) + goto next_slot; + ret = copy_items(trans, inode, dst_path, path, + &last_extent, ins_start_slot, + ins_nr, inode_only, logged_isize); + if (ret < 0) { + err = ret; + goto out_unlock; + } + ins_nr = 0; + if (ret) { + btrfs_release_path(path); + continue; + } + goto next_slot; + } + src = path->nodes[0]; if (ins_nr && ins_start_slot + ins_nr == path->slots[0]) { ins_nr++; @@ -4150,9 +4486,26 @@ next_slot: ins_nr = 0; } + btrfs_release_path(path); + btrfs_release_path(dst_path); + err = btrfs_log_all_xattrs(trans, root, inode, path, dst_path); + if (err) + goto out_unlock; + if (max_key.type >= BTRFS_EXTENT_DATA_KEY && !fast_search) { + btrfs_release_path(path); + btrfs_release_path(dst_path); + err = btrfs_log_trailing_hole(trans, root, inode, path); + if (err) + goto out_unlock; + } log_extents: btrfs_release_path(path); btrfs_release_path(dst_path); + if (need_log_inode_item) { + err = log_inode_item(trans, log, dst_path, inode); + if (err) + goto out_unlock; + } if (fast_search) { ret = btrfs_log_changed_extents(trans, root, inode, dst_path, &logged_list, ctx); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index d47289c715c8..25df49239ceb 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -162,6 +162,7 @@ static struct btrfs_device *__alloc_device(void) spin_lock_init(&dev->reada_lock); atomic_set(&dev->reada_in_flight, 0); atomic_set(&dev->dev_stats_ccnt, 0); + btrfs_device_data_ordered_init(dev); INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_WAIT); INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_WAIT); diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 00eacd83ce3d..fbb0533e977f 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -29,6 +29,7 @@ #include "xattr.h" #include "disk-io.h" #include "props.h" +#include "locking.h" ssize_t __btrfs_getxattr(struct inode *inode, const char *name, @@ -91,7 +92,7 @@ static int do_setxattr(struct btrfs_trans_handle *trans, struct inode *inode, const char *name, const void *value, size_t size, int flags) { - struct btrfs_dir_item *di; + struct btrfs_dir_item *di = NULL; struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_path *path; size_t name_len = strlen(name); @@ -103,84 +104,119 @@ static int do_setxattr(struct btrfs_trans_handle *trans, path = btrfs_alloc_path(); if (!path) return -ENOMEM; + path->skip_release_on_error = 1; + + if (!value) { + di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode), + name, name_len, -1); + if (!di && (flags & XATTR_REPLACE)) + ret = -ENODATA; + else if (di) + ret = btrfs_delete_one_dir_name(trans, root, path, di); + goto out; + } + /* + * For a replace we can't just do the insert blindly. + * Do a lookup first (read-only btrfs_search_slot), and return if xattr + * doesn't exist. If it exists, fall down below to the insert/replace + * path - we can't race with a concurrent xattr delete, because the VFS + * locks the inode's i_mutex before calling setxattr or removexattr. + */ if (flags & XATTR_REPLACE) { - di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode), name, - name_len, -1); - if (IS_ERR(di)) { - ret = PTR_ERR(di); - goto out; - } else if (!di) { + ASSERT(mutex_is_locked(&inode->i_mutex)); + di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode), + name, name_len, 0); + if (!di) { ret = -ENODATA; goto out; } - ret = btrfs_delete_one_dir_name(trans, root, path, di); - if (ret) - goto out; btrfs_release_path(path); + di = NULL; + } + ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(inode), + name, name_len, value, size); + if (ret == -EOVERFLOW) { /* - * remove the attribute + * We have an existing item in a leaf, split_leaf couldn't + * expand it. That item might have or not a dir_item that + * matches our target xattr, so lets check. */ - if (!value) - goto out; - } else { - di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode), - name, name_len, 0); - if (IS_ERR(di)) { - ret = PTR_ERR(di); + ret = 0; + btrfs_assert_tree_locked(path->nodes[0]); + di = btrfs_match_dir_item_name(root, path, name, name_len); + if (!di && !(flags & XATTR_REPLACE)) { + ret = -ENOSPC; goto out; } - if (!di && !value) - goto out; - btrfs_release_path(path); + } else if (ret == -EEXIST) { + ret = 0; + di = btrfs_match_dir_item_name(root, path, name, name_len); + ASSERT(di); /* logic error */ + } else if (ret) { + goto out; } -again: - ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(inode), - name, name_len, value, size); - /* - * If we're setting an xattr to a new value but the new value is say - * exactly BTRFS_MAX_XATTR_SIZE, we could end up with EOVERFLOW getting - * back from split_leaf. This is because it thinks we'll be extending - * the existing item size, but we're asking for enough space to add the - * item itself. So if we get EOVERFLOW just set ret to EEXIST and let - * the rest of the function figure it out. - */ - if (ret == -EOVERFLOW) + if (di && (flags & XATTR_CREATE)) { ret = -EEXIST; + goto out; + } - if (ret == -EEXIST) { - if (flags & XATTR_CREATE) - goto out; + if (di) { /* - * We can't use the path we already have since we won't have the - * proper locking for a delete, so release the path and - * re-lookup to delete the thing. + * We're doing a replace, and it must be atomic, that is, at + * any point in time we have either the old or the new xattr + * value in the tree. We don't want readers (getxattr and + * listxattrs) to miss a value, this is specially important + * for ACLs. */ - btrfs_release_path(path); - di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode), - name, name_len, -1); - if (IS_ERR(di)) { - ret = PTR_ERR(di); - goto out; - } else if (!di) { - /* Shouldn't happen but just in case... */ - btrfs_release_path(path); - goto again; + const int slot = path->slots[0]; + struct extent_buffer *leaf = path->nodes[0]; + const u16 old_data_len = btrfs_dir_data_len(leaf, di); + const u32 item_size = btrfs_item_size_nr(leaf, slot); + const u32 data_size = sizeof(*di) + name_len + size; + struct btrfs_item *item; + unsigned long data_ptr; + char *ptr; + + if (size > old_data_len) { + if (btrfs_leaf_free_space(root, leaf) < + (size - old_data_len)) { + ret = -ENOSPC; + goto out; + } } - ret = btrfs_delete_one_dir_name(trans, root, path, di); - if (ret) - goto out; + if (old_data_len + name_len + sizeof(*di) == item_size) { + /* No other xattrs packed in the same leaf item. */ + if (size > old_data_len) + btrfs_extend_item(root, path, + size - old_data_len); + else if (size < old_data_len) + btrfs_truncate_item(root, path, data_size, 1); + } else { + /* There are other xattrs packed in the same item. */ + ret = btrfs_delete_one_dir_name(trans, root, path, di); + if (ret) + goto out; + btrfs_extend_item(root, path, data_size); + } + item = btrfs_item_nr(slot); + ptr = btrfs_item_ptr(leaf, slot, char); + ptr += btrfs_item_size(leaf, item) - data_size; + di = (struct btrfs_dir_item *)ptr; + btrfs_set_dir_data_len(leaf, di, size); + data_ptr = ((unsigned long)(di + 1)) + name_len; + write_extent_buffer(leaf, value, data_ptr, size); + btrfs_mark_buffer_dirty(leaf); + } else { /* - * We have a value to set, so go back and try to insert it now. + * Insert, and we had space for the xattr, so path->slots[0] is + * where our xattr dir_item is and btrfs_insert_xattr_item() + * filled it. */ - if (value) { - btrfs_release_path(path); - goto again; - } } out: btrfs_free_path(path); @@ -273,8 +309,10 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size) /* check to make sure this item is what we want */ if (found_key.objectid != key.objectid) break; - if (found_key.type != BTRFS_XATTR_ITEM_KEY) + if (found_key.type > BTRFS_XATTR_ITEM_KEY) break; + if (found_key.type < BTRFS_XATTR_ITEM_KEY) + goto next; di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item); if (verify_dir_item(root, leaf, di)) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index a92d3f5c6c12..6f29455c03fe 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1857,7 +1857,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, len = sizeof(*head) + pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64)) + - sizeof(struct timespec); + sizeof(struct ceph_timespec); /* calculate (max) length for cap releases */ len += sizeof(struct ceph_mds_request_release) * diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 44ec72684df5..dab67ad53a1a 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -34,27 +34,9 @@ void cifs_dump_mem(char *label, void *data, int length) { - int i, j; - int *intptr = data; - char *charptr = data; - char buf[10], line[80]; - - printk(KERN_DEBUG "%s: dump of %d bytes of data at 0x%p\n", - label, length, data); - for (i = 0; i < length; i += 16) { - line[0] = 0; - for (j = 0; (j < 4) && (i + j * 4 < length); j++) { - sprintf(buf, " %08x", intptr[i / 4 + j]); - strcat(line, buf); - } - buf[0] = ' '; - buf[2] = 0; - for (j = 0; (j < 16) && (i + j < length); j++) { - buf[1] = isprint(charptr[i + j]) ? charptr[i + j] : '.'; - strcat(line, buf); - } - printk(KERN_DEBUG "%s\n", line); - } + pr_debug("%s: dump of %d bytes of data at 0x%p\n", label, length, data); + print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_OFFSET, 16, 4, + data, length, true); } #ifdef CONFIG_CIFS_DEBUG @@ -68,7 +50,7 @@ void cifs_vfs_err(const char *fmt, ...) vaf.fmt = fmt; vaf.va = &args; - printk(KERN_ERR "CIFS VFS: %pV", &vaf); + pr_err_ratelimited("CIFS VFS: %pV", &vaf); va_end(args); } diff --git a/fs/cifs/cifs_debug.h b/fs/cifs/cifs_debug.h index c99b40fb609b..66cf0f9fff89 100644 --- a/fs/cifs/cifs_debug.h +++ b/fs/cifs/cifs_debug.h @@ -51,15 +51,13 @@ __printf(1, 2) void cifs_vfs_err(const char *fmt, ...); /* information message: e.g., configuration, major event */ #define cifs_dbg(type, fmt, ...) \ do { \ - if (type == FYI) { \ - if (cifsFYI & CIFS_INFO) { \ - printk(KERN_DEBUG "%s: " fmt, \ - __FILE__, ##__VA_ARGS__); \ - } \ + if (type == FYI && cifsFYI & CIFS_INFO) { \ + pr_debug_ratelimited("%s: " \ + fmt, __FILE__, ##__VA_ARGS__); \ } else if (type == VFS) { \ cifs_vfs_err(fmt, ##__VA_ARGS__); \ } else if (type == NOISY && type != 0) { \ - printk(KERN_DEBUG fmt, ##__VA_ARGS__); \ + pr_debug_ratelimited(fmt, ##__VA_ARGS__); \ } \ } while (0) @@ -71,7 +69,7 @@ do { \ #define cifs_dbg(type, fmt, ...) \ do { \ if (0) \ - printk(KERN_DEBUG fmt, ##__VA_ARGS__); \ + pr_debug(fmt, ##__VA_ARGS__); \ } while (0) #endif diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c index f4cf200b3c76..79450fa66d16 100644 --- a/fs/cifs/cifs_spnego.c +++ b/fs/cifs/cifs_spnego.c @@ -24,10 +24,13 @@ #include <linux/string.h> #include <keys/user-type.h> #include <linux/key-type.h> +#include <linux/keyctl.h> #include <linux/inet.h> #include "cifsglob.h" #include "cifs_spnego.h" #include "cifs_debug.h" +#include "cifsproto.h" +static const struct cred *spnego_cred; /* create a new cifs key */ static int @@ -102,6 +105,7 @@ cifs_get_spnego_key(struct cifs_ses *sesInfo) size_t desc_len; struct key *spnego_key; const char *hostname = server->hostname; + const struct cred *saved_cred; /* length of fields (with semicolons): ver=0xyz ip4=ipaddress host=hostname sec=mechanism uid=0xFF user=username */ @@ -163,7 +167,9 @@ cifs_get_spnego_key(struct cifs_ses *sesInfo) sprintf(dp, ";pid=0x%x", current->pid); cifs_dbg(FYI, "key description = %s\n", description); + saved_cred = override_creds(spnego_cred); spnego_key = request_key(&cifs_spnego_key_type, description, ""); + revert_creds(saved_cred); #ifdef CONFIG_CIFS_DEBUG2 if (cifsFYI && !IS_ERR(spnego_key)) { @@ -177,3 +183,64 @@ out: kfree(description); return spnego_key; } + +int +init_cifs_spnego(void) +{ + struct cred *cred; + struct key *keyring; + int ret; + + cifs_dbg(FYI, "Registering the %s key type\n", + cifs_spnego_key_type.name); + + /* + * Create an override credential set with special thread keyring for + * spnego upcalls. + */ + + cred = prepare_kernel_cred(NULL); + if (!cred) + return -ENOMEM; + + keyring = keyring_alloc(".cifs_spnego", + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, cred, + (KEY_POS_ALL & ~KEY_POS_SETATTR) | + KEY_USR_VIEW | KEY_USR_READ, + KEY_ALLOC_NOT_IN_QUOTA, NULL); + if (IS_ERR(keyring)) { + ret = PTR_ERR(keyring); + goto failed_put_cred; + } + + ret = register_key_type(&cifs_spnego_key_type); + if (ret < 0) + goto failed_put_key; + + /* + * instruct request_key() to use this special keyring as a cache for + * the results it looks up + */ + set_bit(KEY_FLAG_ROOT_CAN_CLEAR, &keyring->flags); + cred->thread_keyring = keyring; + cred->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING; + spnego_cred = cred; + + cifs_dbg(FYI, "cifs spnego keyring: %d\n", key_serial(keyring)); + return 0; + +failed_put_key: + key_put(keyring); +failed_put_cred: + put_cred(cred); + return ret; +} + +void +exit_cifs_spnego(void) +{ + key_revoke(spnego_cred->thread_keyring); + unregister_key_type(&cifs_spnego_key_type); + put_cred(spnego_cred); + cifs_dbg(FYI, "Unregistered %s key type\n", cifs_spnego_key_type.name); +} diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index 0303c6793d90..f7fb4b8658ba 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -136,6 +136,12 @@ convert_sfm_char(const __u16 src_char, char *target) case SFM_SLASH: *target = '\\'; break; + case SFM_SPACE: + *target = ' '; + break; + case SFM_PERIOD: + *target = '.'; + break; default: return false; } @@ -364,7 +370,7 @@ static __le16 convert_to_sfu_char(char src_char) return dest_char; } -static __le16 convert_to_sfm_char(char src_char) +static __le16 convert_to_sfm_char(char src_char, bool end_of_string) { __le16 dest_char; @@ -387,6 +393,18 @@ static __le16 convert_to_sfm_char(char src_char) case '|': dest_char = cpu_to_le16(SFM_PIPE); break; + case '.': + if (end_of_string) + dest_char = cpu_to_le16(SFM_PERIOD); + else + dest_char = 0; + break; + case ' ': + if (end_of_string) + dest_char = cpu_to_le16(SFM_SPACE); + else + dest_char = 0; + break; default: dest_char = 0; } @@ -424,9 +442,16 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen, /* see if we must remap this char */ if (map_chars == SFU_MAP_UNI_RSVD) dst_char = convert_to_sfu_char(src_char); - else if (map_chars == SFM_MAP_UNI_RSVD) - dst_char = convert_to_sfm_char(src_char); - else + else if (map_chars == SFM_MAP_UNI_RSVD) { + bool end_of_string; + + if (i == srclen - 1) + end_of_string = true; + else + end_of_string = false; + + dst_char = convert_to_sfm_char(src_char, end_of_string); + } else dst_char = 0; /* * FIXME: We can not handle remapping backslash (UNI_SLASH) diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h index bdc52cb9a676..479bc0a941f3 100644 --- a/fs/cifs/cifs_unicode.h +++ b/fs/cifs/cifs_unicode.h @@ -64,6 +64,8 @@ #define SFM_LESSTHAN ((__u16) 0xF023) #define SFM_PIPE ((__u16) 0xF027) #define SFM_SLASH ((__u16) 0xF026) +#define SFM_PERIOD ((__u16) 0xF028) +#define SFM_SPACE ((__u16) 0xF029) /* * Mapping mechanism to use when one of the seven reserved characters is diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 4ac7445e6ec7..cee9889a6612 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -441,6 +441,48 @@ find_domain_name(struct cifs_ses *ses, const struct nls_table *nls_cp) return 0; } +/* Server has provided av pairs/target info in the type 2 challenge + * packet and we have plucked it and stored within smb session. + * We parse that blob here to find the server given timestamp + * as part of ntlmv2 authentication (or local current time as + * default in case of failure) + */ +static __le64 +find_timestamp(struct cifs_ses *ses) +{ + unsigned int attrsize; + unsigned int type; + unsigned int onesize = sizeof(struct ntlmssp2_name); + unsigned char *blobptr; + unsigned char *blobend; + struct ntlmssp2_name *attrptr; + + if (!ses->auth_key.len || !ses->auth_key.response) + return 0; + + blobptr = ses->auth_key.response; + blobend = blobptr + ses->auth_key.len; + + while (blobptr + onesize < blobend) { + attrptr = (struct ntlmssp2_name *) blobptr; + type = le16_to_cpu(attrptr->type); + if (type == NTLMSSP_AV_EOL) + break; + blobptr += 2; /* advance attr type */ + attrsize = le16_to_cpu(attrptr->length); + blobptr += 2; /* advance attr size */ + if (blobptr + attrsize > blobend) + break; + if (type == NTLMSSP_AV_TIMESTAMP) { + if (attrsize == sizeof(u64)) + return *((__le64 *)blobptr); + } + blobptr += attrsize; /* advance attr value */ + } + + return cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME)); +} + static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash, const struct nls_table *nls_cp) { @@ -637,6 +679,7 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) struct ntlmv2_resp *ntlmv2; char ntlmv2_hash[16]; unsigned char *tiblob = NULL; /* target info blob */ + __le64 rsp_timestamp; if (ses->server->negflavor == CIFS_NEGFLAVOR_EXTENDED) { if (!ses->domainName) { @@ -655,13 +698,19 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) } } + /* Must be within 5 minutes of the server (or in range +/-2h + * in case of Mac OS X), so simply carry over server timestamp + * (as Windows 7 does) + */ + rsp_timestamp = find_timestamp(ses); + baselen = CIFS_SESS_KEY_SIZE + sizeof(struct ntlmv2_resp); tilen = ses->auth_key.len; tiblob = ses->auth_key.response; ses->auth_key.response = kmalloc(baselen + tilen, GFP_KERNEL); if (!ses->auth_key.response) { - rc = ENOMEM; + rc = -ENOMEM; ses->auth_key.len = 0; goto setup_ntlmv2_rsp_ret; } @@ -671,8 +720,8 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) (ses->auth_key.response + CIFS_SESS_KEY_SIZE); ntlmv2->blob_signature = cpu_to_le32(0x00000101); ntlmv2->reserved = 0; - /* Must be within 5 minutes of the server */ - ntlmv2->time = cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME)); + ntlmv2->time = rsp_timestamp; + get_random_bytes(&ntlmv2->client_chal, sizeof(ntlmv2->client_chal)); ntlmv2->reserved2 = 0; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 9d7996e8e793..3e924abdd969 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1249,7 +1249,7 @@ init_cifs(void) goto out_destroy_mids; #ifdef CONFIG_CIFS_UPCALL - rc = register_key_type(&cifs_spnego_key_type); + rc = init_cifs_spnego(); if (rc) goto out_destroy_request_bufs; #endif /* CONFIG_CIFS_UPCALL */ @@ -1272,7 +1272,7 @@ out_init_cifs_idmap: out_register_key_type: #endif #ifdef CONFIG_CIFS_UPCALL - unregister_key_type(&cifs_spnego_key_type); + exit_cifs_spnego(); out_destroy_request_bufs: #endif cifs_destroy_request_bufs(); diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 002e0c173939..15da9e346f60 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -31,19 +31,15 @@ * so that it will fit. We use hash_64 to convert the value to 31 bits, and * then add 1, to ensure that we don't end up with a 0 as the value. */ -#if BITS_PER_LONG == 64 static inline ino_t cifs_uniqueid_to_ino_t(u64 fileid) { + if ((sizeof(ino_t)) < (sizeof(u64))) + return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1; + return (ino_t)fileid; + } -#else -static inline ino_t -cifs_uniqueid_to_ino_t(u64 fileid) -{ - return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1; -} -#endif extern struct file_system_type cifs_fs_type; extern const struct address_space_operations cifs_addr_ops; diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index c31ce98c1704..5b868060eab8 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -60,6 +60,8 @@ do { \ } while (0) extern int init_cifs_idmap(void); extern void exit_cifs_idmap(void); +extern int init_cifs_spnego(void); +extern void exit_cifs_spnego(void); extern char *build_path_from_dentry(struct dentry *); extern char *cifs_build_path_to_root(struct smb_vol *vol, struct cifs_sb_info *cifs_sb, diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 61d00a6e398f..9924c8cbe70f 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -625,9 +625,8 @@ CIFSSMBNegotiate(const unsigned int xid, struct cifs_ses *ses) server->negflavor = CIFS_NEGFLAVOR_UNENCAP; memcpy(ses->server->cryptkey, pSMBr->u.EncryptionKey, CIFS_CRYPTO_KEY_SIZE); - } else if ((pSMBr->hdr.Flags2 & SMBFLG2_EXT_SEC || - server->capabilities & CAP_EXTENDED_SECURITY) && - (pSMBr->EncryptionKeyLength == 0)) { + } else if (pSMBr->hdr.Flags2 & SMBFLG2_EXT_SEC || + server->capabilities & CAP_EXTENDED_SECURITY) { server->negflavor = CIFS_NEGFLAVOR_EXTENDED; rc = decode_ext_sec_blob(ses, pSMBr); } else if (server->sec_mode & SECMODE_PW_ENCRYPT) { @@ -1395,11 +1394,10 @@ openRetry: * current bigbuf. */ static int -cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) +discard_remaining_data(struct TCP_Server_Info *server) { unsigned int rfclen = get_rfc1002_length(server->smallbuf); int remaining = rfclen + 4 - server->total_read; - struct cifs_readdata *rdata = mid->callback_data; while (remaining > 0) { int length; @@ -1413,10 +1411,20 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) remaining -= length; } - dequeue_mid(mid, rdata->result); return 0; } +static int +cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) +{ + int length; + struct cifs_readdata *rdata = mid->callback_data; + + length = discard_remaining_data(server); + dequeue_mid(mid, rdata->result); + return length; +} + int cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) { @@ -1445,6 +1453,12 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) return length; server->total_read += length; + if (server->ops->is_status_pending && + server->ops->is_status_pending(buf, server, 0)) { + discard_remaining_data(server); + return -1; + } + /* Was the SMB read successful? */ rdata->result = server->ops->map_error(buf, false); if (rdata->result != 0) { diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 24fa08d261fb..34ea0a19a669 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -357,7 +357,6 @@ cifs_reconnect(struct TCP_Server_Info *server) server->session_key.response = NULL; server->session_key.len = 0; server->lstrp = jiffies; - mutex_unlock(&server->srv_mutex); /* mark submitted MIDs for retry and issue callback */ INIT_LIST_HEAD(&retry_list); @@ -370,6 +369,7 @@ cifs_reconnect(struct TCP_Server_Info *server) list_move(&mid_entry->qhead, &retry_list); } spin_unlock(&GlobalMid_Lock); + mutex_unlock(&server->srv_mutex); cifs_dbg(FYI, "%s: issuing mid callbacks\n", __func__); list_for_each_safe(tmp, tmp2, &retry_list) { @@ -413,7 +413,9 @@ cifs_echo_request(struct work_struct *work) * server->ops->need_neg() == true. Also, no need to ping if * we got a response recently. */ - if (!server->ops->need_neg || server->ops->need_neg(server) || + + if (server->tcpStatus == CifsNeedReconnect || + server->tcpStatus == CifsExiting || server->tcpStatus == CifsNew || (server->ops->can_echo && !server->ops->can_echo(server)) || time_before(jiffies, server->lstrp + SMB_ECHO_INTERVAL - HZ)) goto requeue_echo; @@ -773,8 +775,7 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) length = atomic_dec_return(&tcpSesAllocCount); if (length > 0) - mempool_resize(cifs_req_poolp, length + cifs_min_rcv, - GFP_KERNEL); + mempool_resize(cifs_req_poolp, length + cifs_min_rcv); } static int @@ -848,8 +849,7 @@ cifs_demultiplex_thread(void *p) length = atomic_inc_return(&tcpSesAllocCount); if (length > 1) - mempool_resize(cifs_req_poolp, length + cifs_min_rcv, - GFP_KERNEL); + mempool_resize(cifs_req_poolp, length + cifs_min_rcv); set_freezable(); while (server->tcpStatus != CifsExiting) { @@ -1466,9 +1466,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, vol->seal = 1; break; case Opt_noac: - printk(KERN_WARNING "CIFS: Mount option noac not " - "supported. Instead set " - "/proc/fs/cifs/LookupCacheEnabled to 0\n"); + pr_warn("CIFS: Mount option noac not supported. Instead set /proc/fs/cifs/LookupCacheEnabled to 0\n"); break; case Opt_fsc: #ifndef CONFIG_CIFS_FSCACHE @@ -1598,7 +1596,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, if (strnlen(string, CIFS_MAX_USERNAME_LEN) > CIFS_MAX_USERNAME_LEN) { - printk(KERN_WARNING "CIFS: username too long\n"); + pr_warn("CIFS: username too long\n"); goto cifs_parse_mount_err; } vol->username = kstrdup(string, GFP_KERNEL); @@ -1662,8 +1660,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, temp_len = strlen(value); vol->password = kzalloc(temp_len+1, GFP_KERNEL); if (vol->password == NULL) { - printk(KERN_WARNING "CIFS: no memory " - "for password\n"); + pr_warn("CIFS: no memory for password\n"); goto cifs_parse_mount_err; } @@ -1687,8 +1684,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, if (!cifs_convert_address(dstaddr, string, strlen(string))) { - printk(KERN_ERR "CIFS: bad ip= option (%s).\n", - string); + pr_err("CIFS: bad ip= option (%s).\n", string); goto cifs_parse_mount_err; } got_ip = true; @@ -1700,15 +1696,13 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, if (strnlen(string, CIFS_MAX_DOMAINNAME_LEN) == CIFS_MAX_DOMAINNAME_LEN) { - printk(KERN_WARNING "CIFS: domain name too" - " long\n"); + pr_warn("CIFS: domain name too long\n"); goto cifs_parse_mount_err; } vol->domainname = kstrdup(string, GFP_KERNEL); if (!vol->domainname) { - printk(KERN_WARNING "CIFS: no memory " - "for domainname\n"); + pr_warn("CIFS: no memory for domainname\n"); goto cifs_parse_mount_err; } cifs_dbg(FYI, "Domain name set\n"); @@ -1721,8 +1715,8 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, if (!cifs_convert_address( (struct sockaddr *)&vol->srcaddr, string, strlen(string))) { - printk(KERN_WARNING "CIFS: Could not parse" - " srcaddr: %s\n", string); + pr_warn("CIFS: Could not parse srcaddr: %s\n", + string); goto cifs_parse_mount_err; } break; @@ -1732,8 +1726,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, goto out_nomem; if (strnlen(string, 1024) >= 65) { - printk(KERN_WARNING "CIFS: iocharset name " - "too long.\n"); + pr_warn("CIFS: iocharset name too long.\n"); goto cifs_parse_mount_err; } @@ -1741,8 +1734,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, vol->iocharset = kstrdup(string, GFP_KERNEL); if (!vol->iocharset) { - printk(KERN_WARNING "CIFS: no memory" - "for charset\n"); + pr_warn("CIFS: no memory for charset\n"); goto cifs_parse_mount_err; } } @@ -1773,9 +1765,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, * set at top of the function */ if (i == RFC1001_NAME_LEN && string[i] != 0) - printk(KERN_WARNING "CIFS: netbiosname" - " longer than 15 truncated.\n"); - + pr_warn("CIFS: netbiosname longer than 15 truncated.\n"); break; case Opt_servern: /* servernetbiosname specified override *SMBSERVER */ @@ -1801,8 +1791,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, /* The string has 16th byte zero still from set at top of the function */ if (i == RFC1001_NAME_LEN && string[i] != 0) - printk(KERN_WARNING "CIFS: server net" - "biosname longer than 15 truncated.\n"); + pr_warn("CIFS: server netbiosname longer than 15 truncated.\n"); break; case Opt_ver: string = match_strdup(args); @@ -1814,8 +1803,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, break; } /* For all other value, error */ - printk(KERN_WARNING "CIFS: Invalid version" - " specified\n"); + pr_warn("CIFS: Invalid version specified\n"); goto cifs_parse_mount_err; case Opt_vers: string = match_strdup(args); @@ -1856,7 +1844,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, } if (!sloppy && invalid) { - printk(KERN_ERR "CIFS: Unknown mount option \"%s\"\n", invalid); + pr_err("CIFS: Unknown mount option \"%s\"\n", invalid); goto cifs_parse_mount_err; } @@ -1882,8 +1870,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, /* No ip= option specified? Try to get it from UNC */ if (!cifs_convert_address(dstaddr, &vol->UNC[2], strlen(&vol->UNC[2]))) { - printk(KERN_ERR "Unable to determine destination " - "address.\n"); + pr_err("Unable to determine destination address.\n"); goto cifs_parse_mount_err; } } @@ -1894,20 +1881,18 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, if (uid_specified) vol->override_uid = override_uid; else if (override_uid == 1) - printk(KERN_NOTICE "CIFS: ignoring forceuid mount option " - "specified with no uid= option.\n"); + pr_notice("CIFS: ignoring forceuid mount option specified with no uid= option.\n"); if (gid_specified) vol->override_gid = override_gid; else if (override_gid == 1) - printk(KERN_NOTICE "CIFS: ignoring forcegid mount option " - "specified with no gid= option.\n"); + pr_notice("CIFS: ignoring forcegid mount option specified with no gid= option.\n"); kfree(mountdata_copy); return 0; out_nomem: - printk(KERN_WARNING "Could not allocate temporary buffer\n"); + pr_warn("Could not allocate temporary buffer\n"); cifs_parse_mount_err: kfree(string); kfree(mountdata_copy); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 0c3ce464cae4..c88a8279e532 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -2010,7 +2010,6 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs, struct tcon_link *tlink = NULL; struct cifs_tcon *tcon = NULL; struct TCP_Server_Info *server; - struct cifs_io_parms io_parms; /* * To avoid spurious oplock breaks from server, in the case of @@ -2032,18 +2031,6 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs, rc = -ENOSYS; cifsFileInfo_put(open_file); cifs_dbg(FYI, "SetFSize for attrs rc = %d\n", rc); - if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) { - unsigned int bytes_written; - - io_parms.netfid = open_file->fid.netfid; - io_parms.pid = open_file->pid; - io_parms.tcon = tcon; - io_parms.offset = 0; - io_parms.length = attrs->ia_size; - rc = CIFSSMBWrite(xid, &io_parms, &bytes_written, - NULL, NULL, 1); - cifs_dbg(FYI, "Wrt seteof rc %d\n", rc); - } } else rc = -EINVAL; @@ -2069,28 +2056,7 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs, else rc = -ENOSYS; cifs_dbg(FYI, "SetEOF by path (setattrs) rc = %d\n", rc); - if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) { - __u16 netfid; - int oplock = 0; - rc = SMBLegacyOpen(xid, tcon, full_path, FILE_OPEN, - GENERIC_WRITE, CREATE_NOT_DIR, &netfid, - &oplock, NULL, cifs_sb->local_nls, - cifs_remap(cifs_sb)); - if (rc == 0) { - unsigned int bytes_written; - - io_parms.netfid = netfid; - io_parms.pid = current->tgid; - io_parms.tcon = tcon; - io_parms.offset = 0; - io_parms.length = attrs->ia_size; - rc = CIFSSMBWrite(xid, &io_parms, &bytes_written, NULL, - NULL, 1); - cifs_dbg(FYI, "wrt seteof rc %d\n", rc); - CIFSSMBClose(xid, tcon, netfid); - } - } if (tlink) cifs_put_tlink(tlink); diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 8b7898b7670f..64a9bca976d0 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -67,6 +67,12 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, goto out_drop_write; } + if (src_file.file->f_op->unlocked_ioctl != cifs_ioctl) { + rc = -EBADF; + cifs_dbg(VFS, "src file seems to be from a different filesystem type\n"); + goto out_fput; + } + if ((!src_file.file->private_data) || (!dst_file->private_data)) { rc = -EBADF; cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n"); diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index b7415d596dbd..337946355b29 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -513,39 +513,11 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) void dump_smb(void *buf, int smb_buf_length) { - int i, j; - char debug_line[17]; - unsigned char *buffer = buf; - if (traceSMB == 0) return; - for (i = 0, j = 0; i < smb_buf_length; i++, j++) { - if (i % 8 == 0) { - /* have reached the beginning of line */ - printk(KERN_DEBUG "| "); - j = 0; - } - printk("%0#4x ", buffer[i]); - debug_line[2 * j] = ' '; - if (isprint(buffer[i])) - debug_line[1 + (2 * j)] = buffer[i]; - else - debug_line[1 + (2 * j)] = '_'; - - if (i % 8 == 7) { - /* reached end of line, time to print ascii */ - debug_line[16] = 0; - printk(" | %s\n", debug_line); - } - } - for (; j < 8; j++) { - printk(" "); - debug_line[2 * j] = ' '; - debug_line[1 + (2 * j)] = ' '; - } - printk(" | %s\n", debug_line); - return; + print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_NONE, 8, 2, buf, + smb_buf_length, true); } void diff --git a/fs/cifs/ntlmssp.h b/fs/cifs/ntlmssp.h index 848249fa120f..3079b38f0afb 100644 --- a/fs/cifs/ntlmssp.h +++ b/fs/cifs/ntlmssp.h @@ -133,6 +133,6 @@ typedef struct _AUTHENTICATE_MESSAGE { int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, struct cifs_ses *ses); void build_ntlmssp_negotiate_blob(unsigned char *pbuffer, struct cifs_ses *ses); -int build_ntlmssp_auth_blob(unsigned char *pbuffer, u16 *buflen, +int build_ntlmssp_auth_blob(unsigned char **pbuffer, u16 *buflen, struct cifs_ses *ses, const struct nls_table *nls_cp); diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 8fd2a95860ba..404b084614aa 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -845,6 +845,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx) * if buggy server returns . and .. late do we want to * check for that here? */ + *tmp_buf = 0; rc = cifs_filldir(current_entry, file, ctx, tmp_buf, max_len); if (rc) { diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 57db63ff88da..693da83a65f0 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -364,19 +364,43 @@ void build_ntlmssp_negotiate_blob(unsigned char *pbuffer, sec_blob->DomainName.MaximumLength = 0; } -/* We do not malloc the blob, it is passed in pbuffer, because its - maximum possible size is fixed and small, making this approach cleaner. - This function returns the length of the data in the blob */ -int build_ntlmssp_auth_blob(unsigned char *pbuffer, +static int size_of_ntlmssp_blob(struct cifs_ses *ses) +{ + int sz = sizeof(AUTHENTICATE_MESSAGE) + ses->auth_key.len + - CIFS_SESS_KEY_SIZE + CIFS_CPHTXT_SIZE + 2; + + if (ses->domainName) + sz += 2 * strnlen(ses->domainName, CIFS_MAX_DOMAINNAME_LEN); + else + sz += 2; + + if (ses->user_name) + sz += 2 * strnlen(ses->user_name, CIFS_MAX_USERNAME_LEN); + else + sz += 2; + + return sz; +} + +int build_ntlmssp_auth_blob(unsigned char **pbuffer, u16 *buflen, struct cifs_ses *ses, const struct nls_table *nls_cp) { int rc; - AUTHENTICATE_MESSAGE *sec_blob = (AUTHENTICATE_MESSAGE *)pbuffer; + AUTHENTICATE_MESSAGE *sec_blob; __u32 flags; unsigned char *tmp; + rc = setup_ntlmv2_rsp(ses, nls_cp); + if (rc) { + cifs_dbg(VFS, "Error %d during NTLMSSP authentication\n", rc); + *buflen = 0; + goto setup_ntlmv2_ret; + } + *pbuffer = kmalloc(size_of_ntlmssp_blob(ses), GFP_KERNEL); + sec_blob = (AUTHENTICATE_MESSAGE *)*pbuffer; + memcpy(sec_blob->Signature, NTLMSSP_SIGNATURE, 8); sec_blob->MessageType = NtLmAuthenticate; @@ -391,7 +415,7 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer, flags |= NTLMSSP_NEGOTIATE_KEY_XCH; } - tmp = pbuffer + sizeof(AUTHENTICATE_MESSAGE); + tmp = *pbuffer + sizeof(AUTHENTICATE_MESSAGE); sec_blob->NegotiateFlags = cpu_to_le32(flags); sec_blob->LmChallengeResponse.BufferOffset = @@ -399,23 +423,27 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer, sec_blob->LmChallengeResponse.Length = 0; sec_blob->LmChallengeResponse.MaximumLength = 0; - sec_blob->NtChallengeResponse.BufferOffset = cpu_to_le32(tmp - pbuffer); - rc = setup_ntlmv2_rsp(ses, nls_cp); - if (rc) { - cifs_dbg(VFS, "Error %d during NTLMSSP authentication\n", rc); - goto setup_ntlmv2_ret; + sec_blob->NtChallengeResponse.BufferOffset = + cpu_to_le32(tmp - *pbuffer); + if (ses->user_name != NULL) { + memcpy(tmp, ses->auth_key.response + CIFS_SESS_KEY_SIZE, + ses->auth_key.len - CIFS_SESS_KEY_SIZE); + tmp += ses->auth_key.len - CIFS_SESS_KEY_SIZE; + + sec_blob->NtChallengeResponse.Length = + cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE); + sec_blob->NtChallengeResponse.MaximumLength = + cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE); + } else { + /* + * don't send an NT Response for anonymous access + */ + sec_blob->NtChallengeResponse.Length = 0; + sec_blob->NtChallengeResponse.MaximumLength = 0; } - memcpy(tmp, ses->auth_key.response + CIFS_SESS_KEY_SIZE, - ses->auth_key.len - CIFS_SESS_KEY_SIZE); - tmp += ses->auth_key.len - CIFS_SESS_KEY_SIZE; - - sec_blob->NtChallengeResponse.Length = - cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE); - sec_blob->NtChallengeResponse.MaximumLength = - cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE); if (ses->domainName == NULL) { - sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - pbuffer); + sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - *pbuffer); sec_blob->DomainName.Length = 0; sec_blob->DomainName.MaximumLength = 0; tmp += 2; @@ -424,14 +452,14 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer, len = cifs_strtoUTF16((__le16 *)tmp, ses->domainName, CIFS_MAX_USERNAME_LEN, nls_cp); len *= 2; /* unicode is 2 bytes each */ - sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - pbuffer); + sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - *pbuffer); sec_blob->DomainName.Length = cpu_to_le16(len); sec_blob->DomainName.MaximumLength = cpu_to_le16(len); tmp += len; } if (ses->user_name == NULL) { - sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - pbuffer); + sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - *pbuffer); sec_blob->UserName.Length = 0; sec_blob->UserName.MaximumLength = 0; tmp += 2; @@ -440,13 +468,13 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer, len = cifs_strtoUTF16((__le16 *)tmp, ses->user_name, CIFS_MAX_USERNAME_LEN, nls_cp); len *= 2; /* unicode is 2 bytes each */ - sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - pbuffer); + sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - *pbuffer); sec_blob->UserName.Length = cpu_to_le16(len); sec_blob->UserName.MaximumLength = cpu_to_le16(len); tmp += len; } - sec_blob->WorkstationName.BufferOffset = cpu_to_le32(tmp - pbuffer); + sec_blob->WorkstationName.BufferOffset = cpu_to_le32(tmp - *pbuffer); sec_blob->WorkstationName.Length = 0; sec_blob->WorkstationName.MaximumLength = 0; tmp += 2; @@ -455,19 +483,19 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer, (ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_EXTENDED_SEC)) && !calc_seckey(ses)) { memcpy(tmp, ses->ntlmssp->ciphertext, CIFS_CPHTXT_SIZE); - sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - pbuffer); + sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - *pbuffer); sec_blob->SessionKey.Length = cpu_to_le16(CIFS_CPHTXT_SIZE); sec_blob->SessionKey.MaximumLength = cpu_to_le16(CIFS_CPHTXT_SIZE); tmp += CIFS_CPHTXT_SIZE; } else { - sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - pbuffer); + sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - *pbuffer); sec_blob->SessionKey.Length = 0; sec_blob->SessionKey.MaximumLength = 0; } + *buflen = tmp - *pbuffer; setup_ntlmv2_ret: - *buflen = tmp - pbuffer; return rc; } @@ -670,20 +698,24 @@ sess_auth_lanman(struct sess_data *sess_data) pSMB->req.hdr.Flags2 &= ~SMBFLG2_UNICODE; - /* no capabilities flags in old lanman negotiation */ - pSMB->old_req.PasswordLength = cpu_to_le16(CIFS_AUTH_RESP_SIZE); - - /* Calculate hash with password and copy into bcc_ptr. - * Encryption Key (stored as in cryptkey) gets used if the - * security mode bit in Negottiate Protocol response states - * to use challenge/response method (i.e. Password bit is 1). - */ - rc = calc_lanman_hash(ses->password, ses->server->cryptkey, - ses->server->sec_mode & SECMODE_PW_ENCRYPT ? - true : false, lnm_session_key); - - memcpy(bcc_ptr, (char *)lnm_session_key, CIFS_AUTH_RESP_SIZE); - bcc_ptr += CIFS_AUTH_RESP_SIZE; + if (ses->user_name != NULL) { + /* no capabilities flags in old lanman negotiation */ + pSMB->old_req.PasswordLength = cpu_to_le16(CIFS_AUTH_RESP_SIZE); + + /* Calculate hash with password and copy into bcc_ptr. + * Encryption Key (stored as in cryptkey) gets used if the + * security mode bit in Negottiate Protocol response states + * to use challenge/response method (i.e. Password bit is 1). + */ + rc = calc_lanman_hash(ses->password, ses->server->cryptkey, + ses->server->sec_mode & SECMODE_PW_ENCRYPT ? + true : false, lnm_session_key); + + memcpy(bcc_ptr, (char *)lnm_session_key, CIFS_AUTH_RESP_SIZE); + bcc_ptr += CIFS_AUTH_RESP_SIZE; + } else { + pSMB->old_req.PasswordLength = 0; + } /* * can not sign if LANMAN negotiated so no need @@ -769,27 +801,32 @@ sess_auth_ntlm(struct sess_data *sess_data) capabilities = cifs_ssetup_hdr(ses, pSMB); pSMB->req_no_secext.Capabilities = cpu_to_le32(capabilities); - pSMB->req_no_secext.CaseInsensitivePasswordLength = - cpu_to_le16(CIFS_AUTH_RESP_SIZE); - pSMB->req_no_secext.CaseSensitivePasswordLength = - cpu_to_le16(CIFS_AUTH_RESP_SIZE); + if (ses->user_name != NULL) { + pSMB->req_no_secext.CaseInsensitivePasswordLength = + cpu_to_le16(CIFS_AUTH_RESP_SIZE); + pSMB->req_no_secext.CaseSensitivePasswordLength = + cpu_to_le16(CIFS_AUTH_RESP_SIZE); + + /* calculate ntlm response and session key */ + rc = setup_ntlm_response(ses, sess_data->nls_cp); + if (rc) { + cifs_dbg(VFS, "Error %d during NTLM authentication\n", + rc); + goto out; + } - /* calculate ntlm response and session key */ - rc = setup_ntlm_response(ses, sess_data->nls_cp); - if (rc) { - cifs_dbg(VFS, "Error %d during NTLM authentication\n", - rc); - goto out; + /* copy ntlm response */ + memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE, + CIFS_AUTH_RESP_SIZE); + bcc_ptr += CIFS_AUTH_RESP_SIZE; + memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE, + CIFS_AUTH_RESP_SIZE); + bcc_ptr += CIFS_AUTH_RESP_SIZE; + } else { + pSMB->req_no_secext.CaseInsensitivePasswordLength = 0; + pSMB->req_no_secext.CaseSensitivePasswordLength = 0; } - /* copy ntlm response */ - memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE, - CIFS_AUTH_RESP_SIZE); - bcc_ptr += CIFS_AUTH_RESP_SIZE; - memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE, - CIFS_AUTH_RESP_SIZE); - bcc_ptr += CIFS_AUTH_RESP_SIZE; - if (ses->capabilities & CAP_UNICODE) { /* unicode strings must be word aligned */ if (sess_data->iov[0].iov_len % 2) { @@ -878,22 +915,26 @@ sess_auth_ntlmv2(struct sess_data *sess_data) /* LM2 password would be here if we supported it */ pSMB->req_no_secext.CaseInsensitivePasswordLength = 0; - /* calculate nlmv2 response and session key */ - rc = setup_ntlmv2_rsp(ses, sess_data->nls_cp); - if (rc) { - cifs_dbg(VFS, "Error %d during NTLMv2 authentication\n", rc); - goto out; - } + if (ses->user_name != NULL) { + /* calculate nlmv2 response and session key */ + rc = setup_ntlmv2_rsp(ses, sess_data->nls_cp); + if (rc) { + cifs_dbg(VFS, "Error %d during NTLMv2 authentication\n", rc); + goto out; + } - memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE, - ses->auth_key.len - CIFS_SESS_KEY_SIZE); - bcc_ptr += ses->auth_key.len - CIFS_SESS_KEY_SIZE; + memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE, + ses->auth_key.len - CIFS_SESS_KEY_SIZE); + bcc_ptr += ses->auth_key.len - CIFS_SESS_KEY_SIZE; - /* set case sensitive password length after tilen may get - * assigned, tilen is 0 otherwise. - */ - pSMB->req_no_secext.CaseSensitivePasswordLength = - cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE); + /* set case sensitive password length after tilen may get + * assigned, tilen is 0 otherwise. + */ + pSMB->req_no_secext.CaseSensitivePasswordLength = + cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE); + } else { + pSMB->req_no_secext.CaseSensitivePasswordLength = 0; + } if (ses->capabilities & CAP_UNICODE) { if (sess_data->iov[0].iov_len % 2) { @@ -1245,7 +1286,7 @@ sess_auth_rawntlmssp_authenticate(struct sess_data *sess_data) struct cifs_ses *ses = sess_data->ses; __u16 bytes_remaining; char *bcc_ptr; - char *ntlmsspblob = NULL; + unsigned char *ntlmsspblob = NULL; u16 blob_len; cifs_dbg(FYI, "rawntlmssp session setup authenticate phase\n"); @@ -1258,19 +1299,7 @@ sess_auth_rawntlmssp_authenticate(struct sess_data *sess_data) /* Build security blob before we assemble the request */ pSMB = (SESSION_SETUP_ANDX *)sess_data->iov[0].iov_base; smb_buf = (struct smb_hdr *)pSMB; - /* - * 5 is an empirical value, large enough to hold - * authenticate message plus max 10 of av paris, - * domain, user, workstation names, flags, etc. - */ - ntlmsspblob = kzalloc(5*sizeof(struct _AUTHENTICATE_MESSAGE), - GFP_KERNEL); - if (!ntlmsspblob) { - rc = -ENOMEM; - goto out; - } - - rc = build_ntlmssp_auth_blob(ntlmsspblob, + rc = build_ntlmssp_auth_blob(&ntlmsspblob, &blob_len, ses, sess_data->nls_cp); if (rc) goto out_free_ntlmsspblob; diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h index bc0bb9c34f72..0ffa18094335 100644 --- a/fs/cifs/smb2glob.h +++ b/fs/cifs/smb2glob.h @@ -44,6 +44,7 @@ #define SMB2_OP_DELETE 7 #define SMB2_OP_HARDLINK 8 #define SMB2_OP_SET_EOF 9 +#define SMB2_OP_RMDIR 10 /* Used when constructing chained read requests. */ #define CHAINED_REQUEST 1 diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index 899bbc86f73e..4f0231e685a9 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -80,6 +80,10 @@ smb2_open_op_close(const unsigned int xid, struct cifs_tcon *tcon, * SMB2_open() call. */ break; + case SMB2_OP_RMDIR: + tmprc = SMB2_rmdir(xid, tcon, fid.persistent_fid, + fid.volatile_fid); + break; case SMB2_OP_RENAME: tmprc = SMB2_rename(xid, tcon, fid.persistent_fid, fid.volatile_fid, (__le16 *)data); @@ -191,8 +195,8 @@ smb2_rmdir(const unsigned int xid, struct cifs_tcon *tcon, const char *name, struct cifs_sb_info *cifs_sb) { return smb2_open_op_close(xid, tcon, cifs_sb, name, DELETE, FILE_OPEN, - CREATE_NOT_FILE | CREATE_DELETE_ON_CLOSE, - NULL, SMB2_OP_DELETE); + CREATE_NOT_FILE, + NULL, SMB2_OP_RMDIR); } int diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index cc93a7ffe8e4..51f5251d7db5 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -50,9 +50,13 @@ change_conf(struct TCP_Server_Info *server) break; default: server->echoes = true; - server->oplocks = true; + if (enable_oplocks) { + server->oplocks = true; + server->oplock_credits = 1; + } else + server->oplocks = false; + server->echo_credits = 1; - server->oplock_credits = 1; } server->credits -= server->echo_credits + server->oplock_credits; return 0; diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 8f1672bb82d5..d759ecdfa9d6 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -46,6 +46,7 @@ #include "smb2status.h" #include "smb2glob.h" #include "cifspdu.h" +#include "cifs_spnego.h" /* * The following table defines the expected "StructureSize" of SMB2 requests @@ -427,20 +428,15 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) cifs_dbg(FYI, "missing security blob on negprot\n"); rc = cifs_enable_signing(server, ses->sign); -#ifdef CONFIG_SMB2_ASN1 /* BB REMOVEME when updated asn1.c ready */ if (rc) goto neg_exit; - if (blob_length) - rc = decode_neg_token_init(security_blob, blob_length, - &server->sec_type); - if (rc == 1) - rc = 0; - else if (rc == 0) { - rc = -EIO; - goto neg_exit; + if (blob_length) { + rc = decode_negTokenInit(security_blob, blob_length, server); + if (rc == 1) + rc = 0; + else if (rc == 0) + rc = -EIO; } -#endif - neg_exit: free_rsp_buf(resp_buftype, rsp); return rc; @@ -534,8 +530,9 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses, __le32 phase = NtLmNegotiate; /* NTLMSSP, if needed, is multistage */ struct TCP_Server_Info *server = ses->server; u16 blob_length = 0; - char *security_blob; - char *ntlmssp_blob = NULL; + struct key *spnego_key = NULL; + char *security_blob = NULL; + unsigned char *ntlmssp_blob = NULL; bool use_spnego = false; /* else use raw ntlmssp */ cifs_dbg(FYI, "Session Setup\n"); @@ -562,7 +559,8 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses, ses->ntlmssp->sesskey_per_smbsess = true; /* FIXME: allow for other auth types besides NTLMSSP (e.g. krb5) */ - ses->sectype = RawNTLMSSP; + if (ses->sectype != Kerberos && ses->sectype != RawNTLMSSP) + ses->sectype = RawNTLMSSP; ssetup_ntlmssp_authenticate: if (phase == NtLmChallenge) @@ -591,7 +589,48 @@ ssetup_ntlmssp_authenticate: iov[0].iov_base = (char *)req; /* 4 for rfc1002 length field and 1 for pad */ iov[0].iov_len = get_rfc1002_length(req) + 4 - 1; - if (phase == NtLmNegotiate) { + + if (ses->sectype == Kerberos) { +#ifdef CONFIG_CIFS_UPCALL + struct cifs_spnego_msg *msg; + + spnego_key = cifs_get_spnego_key(ses); + if (IS_ERR(spnego_key)) { + rc = PTR_ERR(spnego_key); + spnego_key = NULL; + goto ssetup_exit; + } + + msg = spnego_key->payload.data; + /* + * check version field to make sure that cifs.upcall is + * sending us a response in an expected form + */ + if (msg->version != CIFS_SPNEGO_UPCALL_VERSION) { + cifs_dbg(VFS, + "bad cifs.upcall version. Expected %d got %d", + CIFS_SPNEGO_UPCALL_VERSION, msg->version); + rc = -EKEYREJECTED; + goto ssetup_exit; + } + ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len, + GFP_KERNEL); + if (!ses->auth_key.response) { + cifs_dbg(VFS, + "Kerberos can't allocate (%u bytes) memory", + msg->sesskey_len); + rc = -ENOMEM; + goto ssetup_exit; + } + ses->auth_key.len = msg->sesskey_len; + blob_length = msg->secblob_len; + iov[1].iov_base = msg->data + msg->sesskey_len; + iov[1].iov_len = blob_length; +#else + rc = -EOPNOTSUPP; + goto ssetup_exit; +#endif /* CONFIG_CIFS_UPCALL */ + } else if (phase == NtLmNegotiate) { /* if not krb5 must be ntlmssp */ ntlmssp_blob = kmalloc(sizeof(struct _NEGOTIATE_MESSAGE), GFP_KERNEL); if (ntlmssp_blob == NULL) { @@ -614,15 +653,11 @@ ssetup_ntlmssp_authenticate: /* with raw NTLMSSP we don't encapsulate in SPNEGO */ security_blob = ntlmssp_blob; } + iov[1].iov_base = security_blob; + iov[1].iov_len = blob_length; } else if (phase == NtLmAuthenticate) { req->hdr.SessionId = ses->Suid; - ntlmssp_blob = kzalloc(sizeof(struct _NEGOTIATE_MESSAGE) + 500, - GFP_KERNEL); - if (ntlmssp_blob == NULL) { - rc = -ENOMEM; - goto ssetup_exit; - } - rc = build_ntlmssp_auth_blob(ntlmssp_blob, &blob_length, ses, + rc = build_ntlmssp_auth_blob(&ntlmssp_blob, &blob_length, ses, nls_cp); if (rc) { cifs_dbg(FYI, "build_ntlmssp_auth_blob failed %d\n", @@ -641,6 +676,8 @@ ssetup_ntlmssp_authenticate: } else { security_blob = ntlmssp_blob; } + iov[1].iov_base = security_blob; + iov[1].iov_len = blob_length; } else { cifs_dbg(VFS, "illegal ntlmssp phase\n"); rc = -EIO; @@ -652,8 +689,6 @@ ssetup_ntlmssp_authenticate: cpu_to_le16(sizeof(struct smb2_sess_setup_req) - 1 /* pad */ - 4 /* rfc1001 len */); req->SecurityBufferLength = cpu_to_le16(blob_length); - iov[1].iov_base = security_blob; - iov[1].iov_len = blob_length; inc_rfc1001_len(req, blob_length - 1 /* pad */); @@ -664,6 +699,7 @@ ssetup_ntlmssp_authenticate: kfree(security_blob); rsp = (struct smb2_sess_setup_rsp *)iov[0].iov_base; + ses->Suid = rsp->hdr.SessionId; if (resp_buftype != CIFS_NO_BUFFER && rsp->hdr.Status == STATUS_MORE_PROCESSING_REQUIRED) { if (phase != NtLmNegotiate) { @@ -681,7 +717,6 @@ ssetup_ntlmssp_authenticate: /* NTLMSSP Negotiate sent now processing challenge (response) */ phase = NtLmChallenge; /* process ntlmssp challenge */ rc = 0; /* MORE_PROCESSING is not an error here but expected */ - ses->Suid = rsp->hdr.SessionId; rc = decode_ntlmssp_challenge(rsp->Buffer, le16_to_cpu(rsp->SecurityBufferLength), ses); } @@ -738,6 +773,10 @@ keygen_exit: kfree(ses->auth_key.response); ses->auth_key.response = NULL; } + if (spnego_key) { + key_invalidate(spnego_key); + key_put(spnego_key); + } kfree(ses->ntlmssp); return rc; @@ -997,21 +1036,25 @@ parse_lease_state(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp, { char *data_offset; struct create_context *cc; - unsigned int next = 0; + unsigned int next; + unsigned int remaining; char *name; data_offset = (char *)rsp + 4 + le32_to_cpu(rsp->CreateContextsOffset); + remaining = le32_to_cpu(rsp->CreateContextsLength); cc = (struct create_context *)data_offset; - do { - cc = (struct create_context *)((char *)cc + next); + while (remaining >= sizeof(struct create_context)) { name = le16_to_cpu(cc->NameOffset) + (char *)cc; - if (le16_to_cpu(cc->NameLength) != 4 || - strncmp(name, "RqLs", 4)) { - next = le32_to_cpu(cc->Next); - continue; - } - return server->ops->parse_lease_buf(cc, epoch); - } while (next != 0); + if (le16_to_cpu(cc->NameLength) == 4 && + strncmp(name, "RqLs", 4) == 0) + return server->ops->parse_lease_buf(cc, epoch); + + next = le32_to_cpu(cc->Next); + if (!next) + break; + remaining -= next; + cc = (struct create_context *)((char *)cc + next); + } return 0; } @@ -1580,6 +1623,33 @@ SMB2_echo(struct TCP_Server_Info *server) cifs_dbg(FYI, "In echo request\n"); + if (server->tcpStatus == CifsNeedNegotiate) { + struct list_head *tmp, *tmp2; + struct cifs_ses *ses; + struct cifs_tcon *tcon; + + cifs_dbg(FYI, "Need negotiate, reconnecting tcons\n"); + spin_lock(&cifs_tcp_ses_lock); + list_for_each(tmp, &server->smb_ses_list) { + ses = list_entry(tmp, struct cifs_ses, smb_ses_list); + list_for_each(tmp2, &ses->tcon_list) { + tcon = list_entry(tmp2, struct cifs_tcon, + tcon_list); + /* add check for persistent handle reconnect */ + if (tcon && tcon->need_reconnect) { + spin_unlock(&cifs_tcp_ses_lock); + rc = smb2_reconnect(SMB2_ECHO, tcon); + spin_lock(&cifs_tcp_ses_lock); + } + } + } + spin_unlock(&cifs_tcp_ses_lock); + } + + /* if no session, renegotiate failed above */ + if (server->tcpStatus == CifsNeedNegotiate) + return -EIO; + rc = small_smb2_init(SMB2_ECHO, NULL, (void **)&req); if (rc) return rc; @@ -2332,6 +2402,22 @@ SMB2_rename(const unsigned int xid, struct cifs_tcon *tcon, } int +SMB2_rmdir(const unsigned int xid, struct cifs_tcon *tcon, + u64 persistent_fid, u64 volatile_fid) +{ + __u8 delete_pending = 1; + void *data; + unsigned int size; + + data = &delete_pending; + size = 1; /* sizeof __u8 */ + + return send_set_info(xid, tcon, persistent_fid, volatile_fid, + current->tgid, FILE_DISPOSITION_INFORMATION, 1, &data, + &size); +} + +int SMB2_set_hardlink(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, __le16 *target_file) { diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 79dc650c18b2..9bc59f9c12fb 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -140,6 +140,8 @@ extern int SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon, extern int SMB2_rename(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, __le16 *target_file); +extern int SMB2_rmdir(const unsigned int xid, struct cifs_tcon *tcon, + u64 persistent_fid, u64 volatile_fid); extern int SMB2_set_hardlink(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, __le16 *target_file); diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 9d087f4e7d4e..66106f6ed7b4 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -99,9 +99,9 @@ DeleteMidQEntry(struct mid_q_entry *midEntry) something is wrong, unless it is quite a slow link or server */ if ((now - midEntry->when_alloc) > HZ) { if ((cifsFYI & CIFS_TIMER) && (midEntry->command != command)) { - printk(KERN_DEBUG " CIFS slow rsp: cmd %d mid %llu", + pr_debug(" CIFS slow rsp: cmd %d mid %llu", midEntry->command, midEntry->mid); - printk(" A: 0x%lx S: 0x%lx R: 0x%lx\n", + pr_info(" A: 0x%lx S: 0x%lx R: 0x%lx\n", now - midEntry->when_alloc, now - midEntry->when_sent, now - midEntry->when_received); @@ -576,14 +576,16 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst, cifs_in_send_dec(server); cifs_save_when_sent(mid); - if (rc < 0) + if (rc < 0) { server->sequence_number -= 2; + cifs_delete_mid(mid); + } + mutex_unlock(&server->srv_mutex); if (rc == 0) return 0; - cifs_delete_mid(mid); add_credits_and_wake_if(server, credits, optype); return rc; } diff --git a/fs/coredump.c b/fs/coredump.c index 4c5866b948e7..7eb6181184ea 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -32,6 +32,9 @@ #include <linux/pipe_fs_i.h> #include <linux/oom.h> #include <linux/compat.h> +#include <linux/sched.h> +#include <linux/fs.h> +#include <linux/path.h> #include <asm/uaccess.h> #include <asm/mmu_context.h> @@ -506,10 +509,10 @@ void do_coredump(const siginfo_t *siginfo) const struct cred *old_cred; struct cred *cred; int retval = 0; - int flag = 0; int ispipe; struct files_struct *displaced; - bool need_nonrelative = false; + /* require nonrelative corefile path and be extra careful */ + bool need_suid_safe = false; bool core_dumped = false; static atomic_t core_dump_count = ATOMIC_INIT(0); struct coredump_params cprm = { @@ -543,9 +546,8 @@ void do_coredump(const siginfo_t *siginfo) */ if (__get_dumpable(cprm.mm_flags) == SUID_DUMP_ROOT) { /* Setuid core dump mode */ - flag = O_EXCL; /* Stop rewrite attacks */ cred->fsuid = GLOBAL_ROOT_UID; /* Dump root private */ - need_nonrelative = true; + need_suid_safe = true; } retval = coredump_wait(siginfo->si_signo, &core_state); @@ -622,11 +624,13 @@ void do_coredump(const siginfo_t *siginfo) } } else { struct inode *inode; + int open_flags = O_CREAT | O_RDWR | O_NOFOLLOW | + O_LARGEFILE | O_EXCL; if (cprm.limit < binfmt->min_coredump) goto fail_unlock; - if (need_nonrelative && cn.corename[0] != '/') { + if (need_suid_safe && cn.corename[0] != '/') { printk(KERN_WARNING "Pid %d(%s) can only dump core "\ "to fully qualified path!\n", task_tgid_vnr(current), current->comm); @@ -634,9 +638,53 @@ void do_coredump(const siginfo_t *siginfo) goto fail_unlock; } - cprm.file = filp_open(cn.corename, - O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag, - 0600); + /* + * Unlink the file if it exists unless this is a SUID + * binary - in that case, we're running around with root + * privs and don't want to unlink another user's coredump. + */ + if (!need_suid_safe) { + mm_segment_t old_fs; + + old_fs = get_fs(); + set_fs(KERNEL_DS); + /* + * If it doesn't exist, that's fine. If there's some + * other problem, we'll catch it at the filp_open(). + */ + (void) sys_unlink((const char __user *)cn.corename); + set_fs(old_fs); + } + + /* + * There is a race between unlinking and creating the + * file, but if that causes an EEXIST here, that's + * fine - another process raced with us while creating + * the corefile, and the other process won. To userspace, + * what matters is that at least one of the two processes + * writes its coredump successfully, not which one. + */ + if (need_suid_safe) { + /* + * Using user namespaces, normal user tasks can change + * their current->fs->root to point to arbitrary + * directories. Since the intention of the "only dump + * with a fully qualified path" rule is to control where + * coredumps may be placed using root privileges, + * current->fs->root must not be used. Instead, use the + * root directory of init_task. + */ + struct path root; + + task_lock(&init_task); + get_fs_root(init_task.fs, &root); + task_unlock(&init_task); + cprm.file = file_open_root(root.dentry, root.mnt, + cn.corename, open_flags, 0600); + path_put(&root); + } else { + cprm.file = filp_open(cn.corename, open_flags, 0600); + } if (IS_ERR(cprm.file)) goto fail_unlock; diff --git a/fs/dcache.c b/fs/dcache.c index b20c267fdd6d..bf9feb2a960c 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -39,6 +39,8 @@ #include <linux/prefetch.h> #include <linux/ratelimit.h> #include <linux/list_lru.h> +#include <linux/kasan.h> + #include "internal.h" #include "mount.h" @@ -630,6 +632,9 @@ repeat: if (unlikely(d_unhashed(dentry))) goto kill_it; + if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED)) + goto kill_it; + if (unlikely(dentry->d_flags & DCACHE_OP_DELETE)) { if (dentry->d_op->d_delete(dentry)) goto kill_it; @@ -1431,6 +1436,9 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) } atomic_set(&p->u.count, 1); dname = p->name; + if (IS_ENABLED(CONFIG_DCACHE_WORD_ACCESS)) + kasan_unpoison_shadow(dname, + round_up(name->len + 1, sizeof(unsigned long))); } else { dname = dentry->d_iname; } @@ -1479,7 +1487,7 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) struct dentry *dentry = __d_alloc(parent->d_sb, name); if (!dentry) return NULL; - + dentry->d_flags |= DCACHE_RCUACCESS; spin_lock(&parent->d_lock); /* * don't need child lock because it is not subject @@ -1526,7 +1534,8 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op) DCACHE_OP_COMPARE | DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE | - DCACHE_OP_DELETE )); + DCACHE_OP_DELETE | + DCACHE_OP_SELECT_INODE)); dentry->d_op = op; if (!op) return; @@ -1542,6 +1551,8 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op) dentry->d_flags |= DCACHE_OP_DELETE; if (op->d_prune) dentry->d_flags |= DCACHE_OP_PRUNE; + if (op->d_select_inode) + dentry->d_flags |= DCACHE_OP_SELECT_INODE; } EXPORT_SYMBOL(d_set_d_op); @@ -2308,7 +2319,6 @@ static void __d_rehash(struct dentry * entry, struct hlist_bl_head *b) { BUG_ON(!d_unhashed(entry)); hlist_bl_lock(b); - entry->d_flags |= DCACHE_RCUACCESS; hlist_bl_add_head_rcu(&entry->d_hash, b); hlist_bl_unlock(b); } @@ -2527,6 +2537,7 @@ static void __d_move(struct dentry *dentry, struct dentry *target, /* ... and switch them in the tree */ if (IS_ROOT(dentry)) { /* splicing a tree */ + dentry->d_flags |= DCACHE_RCUACCESS; dentry->d_parent = target->d_parent; target->d_parent = target; list_del_init(&target->d_child); @@ -2887,6 +2898,13 @@ restart: if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) { struct mount *parent = ACCESS_ONCE(mnt->mnt_parent); + /* Escaped? */ + if (dentry != vfsmnt->mnt_root) { + bptr = *buffer; + blen = *buflen; + error = 3; + break; + } /* Global root? */ if (mnt != parent) { dentry = ACCESS_ONCE(mnt->mnt_mountpoint); @@ -2894,17 +2912,6 @@ restart: vfsmnt = &mnt->mnt; continue; } - /* - * Filesystems needing to implement special "root names" - * should do so with ->d_dname() - */ - if (IS_ROOT(dentry) && - (dentry->d_name.len != 1 || - dentry->d_name.name[0] != '/')) { - WARN(1, "Root dentry has weird name <%.*s>\n", - (int) dentry->d_name.len, - dentry->d_name.name); - } if (!error) error = is_mounted(vfsmnt) ? 1 : 2; break; diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index cfe8466f7fef..f13aa00ed1d6 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -569,6 +569,26 @@ void devpts_kill_index(struct inode *ptmx_inode, int idx) mutex_unlock(&allocated_ptys_lock); } +/* + * pty code needs to hold extra references in case of last /dev/tty close + */ + +void devpts_add_ref(struct inode *ptmx_inode) +{ + struct super_block *sb = pts_sb_from_inode(ptmx_inode); + + atomic_inc(&sb->s_active); + ihold(ptmx_inode); +} + +void devpts_del_ref(struct inode *ptmx_inode) +{ + struct super_block *sb = pts_sb_from_inode(ptmx_inode); + + iput(ptmx_inode); + deactivate_super(sb); +} + /** * devpts_pty_new -- create a new inode in /dev/pts/ * @ptmx_inode: inode of the master diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index 77a3db3791c7..c02f52cfe64a 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -177,6 +177,19 @@ out: return rc; } +static int ecryptfs_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct file *lower_file = ecryptfs_file_to_lower(file); + /* + * Don't allow mmap on top of file systems that don't support it + * natively. If FILESYSTEM_MAX_STACK_DEPTH > 2 or ecryptfs + * allows recursive mounting, this will need to be extended. + */ + if (!lower_file->f_op->mmap) + return -ENODEV; + return generic_file_mmap(file, vma); +} + /** * ecryptfs_open * @inode: inode speciying file to open @@ -374,7 +387,7 @@ const struct file_operations ecryptfs_main_fops = { #ifdef CONFIG_COMPAT .compat_ioctl = ecryptfs_compat_ioctl, #endif - .mmap = generic_file_mmap, + .mmap = ecryptfs_mmap, .open = ecryptfs_open, .flush = ecryptfs_flush, .release = ecryptfs_release, diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c index cdb2971192a5..174bb20042b3 100644 --- a/fs/efivarfs/file.c +++ b/fs/efivarfs/file.c @@ -10,6 +10,7 @@ #include <linux/efi.h> #include <linux/fs.h> #include <linux/slab.h> +#include <linux/mount.h> #include "internal.h" @@ -103,9 +104,79 @@ out_free: return size; } +static int +efivarfs_ioc_getxflags(struct file *file, void __user *arg) +{ + struct inode *inode = file->f_mapping->host; + unsigned int i_flags; + unsigned int flags = 0; + + i_flags = inode->i_flags; + if (i_flags & S_IMMUTABLE) + flags |= FS_IMMUTABLE_FL; + + if (copy_to_user(arg, &flags, sizeof(flags))) + return -EFAULT; + return 0; +} + +static int +efivarfs_ioc_setxflags(struct file *file, void __user *arg) +{ + struct inode *inode = file->f_mapping->host; + unsigned int flags; + unsigned int i_flags = 0; + int error; + + if (!inode_owner_or_capable(inode)) + return -EACCES; + + if (copy_from_user(&flags, arg, sizeof(flags))) + return -EFAULT; + + if (flags & ~FS_IMMUTABLE_FL) + return -EOPNOTSUPP; + + if (!capable(CAP_LINUX_IMMUTABLE)) + return -EPERM; + + if (flags & FS_IMMUTABLE_FL) + i_flags |= S_IMMUTABLE; + + + error = mnt_want_write_file(file); + if (error) + return error; + + mutex_lock(&inode->i_mutex); + inode->i_flags &= ~S_IMMUTABLE; + inode->i_flags |= i_flags; + mutex_unlock(&inode->i_mutex); + + mnt_drop_write_file(file); + + return 0; +} + +long +efivarfs_file_ioctl(struct file *file, unsigned int cmd, unsigned long p) +{ + void __user *arg = (void __user *)p; + + switch (cmd) { + case FS_IOC_GETFLAGS: + return efivarfs_ioc_getxflags(file, arg); + case FS_IOC_SETFLAGS: + return efivarfs_ioc_setxflags(file, arg); + } + + return -ENOTTY; +} + const struct file_operations efivarfs_file_operations = { .open = simple_open, .read = efivarfs_file_read, .write = efivarfs_file_write, .llseek = no_llseek, + .unlocked_ioctl = efivarfs_file_ioctl, }; diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index 07ab49745e31..7e7318f10575 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -15,7 +15,8 @@ #include "internal.h" struct inode *efivarfs_get_inode(struct super_block *sb, - const struct inode *dir, int mode, dev_t dev) + const struct inode *dir, int mode, + dev_t dev, bool is_removable) { struct inode *inode = new_inode(sb); @@ -23,6 +24,7 @@ struct inode *efivarfs_get_inode(struct super_block *sb, inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; + inode->i_flags = is_removable ? 0 : S_IMMUTABLE; switch (mode & S_IFMT) { case S_IFREG: inode->i_fop = &efivarfs_file_operations; @@ -102,22 +104,17 @@ static void efivarfs_hex_to_guid(const char *str, efi_guid_t *guid) static int efivarfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { - struct inode *inode; + struct inode *inode = NULL; struct efivar_entry *var; int namelen, i = 0, err = 0; + bool is_removable = false; if (!efivarfs_valid_name(dentry->d_name.name, dentry->d_name.len)) return -EINVAL; - inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0); - if (!inode) - return -ENOMEM; - var = kzalloc(sizeof(struct efivar_entry), GFP_KERNEL); - if (!var) { - err = -ENOMEM; - goto out; - } + if (!var) + return -ENOMEM; /* length of the variable name itself: remove GUID and separator */ namelen = dentry->d_name.len - EFI_VARIABLE_GUID_LEN - 1; @@ -125,6 +122,16 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry, efivarfs_hex_to_guid(dentry->d_name.name + namelen + 1, &var->var.VendorGuid); + if (efivar_variable_is_removable(var->var.VendorGuid, + dentry->d_name.name, namelen)) + is_removable = true; + + inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0, is_removable); + if (!inode) { + err = -ENOMEM; + goto out; + } + for (i = 0; i < namelen; i++) var->var.VariableName[i] = dentry->d_name.name[i]; @@ -138,7 +145,8 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry, out: if (err) { kfree(var); - iput(inode); + if (inode) + iput(inode); } return err; } diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h index b5ff16addb7c..b4505188e799 100644 --- a/fs/efivarfs/internal.h +++ b/fs/efivarfs/internal.h @@ -15,7 +15,8 @@ extern const struct file_operations efivarfs_file_operations; extern const struct inode_operations efivarfs_dir_inode_operations; extern bool efivarfs_valid_name(const char *str, int len); extern struct inode *efivarfs_get_inode(struct super_block *sb, - const struct inode *dir, int mode, dev_t dev); + const struct inode *dir, int mode, dev_t dev, + bool is_removable); extern struct list_head efivarfs_list; diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 0a48886e069c..b57db0c6c2af 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -118,25 +118,28 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, struct dentry *dentry, *root = sb->s_root; unsigned long size = 0; char *name; - int len, i; + int len; int err = -ENOMEM; + bool is_removable = false; - entry = kmalloc(sizeof(*entry), GFP_KERNEL); + entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return err; memcpy(entry->var.VariableName, name16, name_size); memcpy(&(entry->var.VendorGuid), &vendor, sizeof(efi_guid_t)); - len = ucs2_strlen(entry->var.VariableName); + len = ucs2_utf8size(entry->var.VariableName); /* name, plus '-', plus GUID, plus NUL*/ name = kmalloc(len + 1 + EFI_VARIABLE_GUID_LEN + 1, GFP_KERNEL); if (!name) goto fail; - for (i = 0; i < len; i++) - name[i] = entry->var.VariableName[i] & 0xFF; + ucs2_as_utf8(name, entry->var.VariableName, len); + + if (efivar_variable_is_removable(entry->var.VendorGuid, name, len)) + is_removable = true; name[len] = '-'; @@ -144,7 +147,8 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, name[len + EFI_VARIABLE_GUID_LEN+1] = '\0'; - inode = efivarfs_get_inode(sb, root->d_inode, S_IFREG | 0644, 0); + inode = efivarfs_get_inode(sb, root->d_inode, S_IFREG | 0644, 0, + is_removable); if (!inode) goto fail_name; @@ -200,7 +204,7 @@ static int efivarfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_d_op = &efivarfs_d_ops; sb->s_time_gran = 1; - inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0); + inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0, true); if (!inode) return -ENOMEM; inode->i_op = &efivarfs_dir_inode_operations; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index c55a1faaed58..6ce71e4e82e5 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -811,6 +811,29 @@ do { \ #include "extents_status.h" /* + * Lock subclasses for i_data_sem in the ext4_inode_info structure. + * + * These are needed to avoid lockdep false positives when we need to + * allocate blocks to the quota inode during ext4_map_blocks(), while + * holding i_data_sem for a normal (non-quota) inode. Since we don't + * do quota tracking for the quota inode, this avoids deadlock (as + * well as infinite recursion, since it isn't turtles all the way + * down...) + * + * I_DATA_SEM_NORMAL - Used for most inodes + * I_DATA_SEM_OTHER - Used by move_inode.c for the second normal inode + * where the second inode has larger inode number + * than the first + * I_DATA_SEM_QUOTA - Used for quota inodes only + */ +enum { + I_DATA_SEM_NORMAL = 0, + I_DATA_SEM_OTHER, + I_DATA_SEM_QUOTA, +}; + + +/* * fourth extended file system inode data in memory */ struct ext4_inode_info { diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index b5fcb1ac0dd7..b95c32096a68 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4792,12 +4792,6 @@ static long ext4_zero_range(struct file *file, loff_t offset, else max_blocks -= lblk; - flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT | - EXT4_GET_BLOCKS_CONVERT_UNWRITTEN | - EXT4_EX_NOCACHE; - if (mode & FALLOC_FL_KEEP_SIZE) - flags |= EXT4_GET_BLOCKS_KEEP_SIZE; - mutex_lock(&inode->i_mutex); /* @@ -4814,15 +4808,28 @@ static long ext4_zero_range(struct file *file, loff_t offset, ret = inode_newsize_ok(inode, new_size); if (ret) goto out_mutex; - /* - * If we have a partial block after EOF we have to allocate - * the entire block. - */ - if (partial_end) - max_blocks += 1; } + flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT; + if (mode & FALLOC_FL_KEEP_SIZE) + flags |= EXT4_GET_BLOCKS_KEEP_SIZE; + + /* Preallocate the range including the unaligned edges */ + if (partial_begin || partial_end) { + ret = ext4_alloc_file_blocks(file, + round_down(offset, 1 << blkbits) >> blkbits, + (round_up((offset + len), 1 << blkbits) - + round_down(offset, 1 << blkbits)) >> blkbits, + new_size, flags, mode); + if (ret) + goto out_mutex; + + } + + /* Zero range excluding the unaligned edges */ if (max_blocks > 0) { + flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN | + EXT4_EX_NOCACHE); /* Now release the pages and zero block aligned part of pages*/ truncate_pagecache_range(inode, start, end - 1); @@ -4836,19 +4843,6 @@ static long ext4_zero_range(struct file *file, loff_t offset, flags, mode); if (ret) goto out_dio; - /* - * Remove entire range from the extent status tree. - * - * ext4_es_remove_extent(inode, lblk, max_blocks) is - * NOT sufficient. I'm not sure why this is the case, - * but let's be conservative and remove the extent - * status tree for the entire inode. There should be - * no outstanding delalloc extents thanks to the - * filemap_write_and_wait_range() call above. - */ - ret = ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); - if (ret) - goto out_dio; } if (!partial_begin && !partial_end) goto out_dio; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index ac644c31ca67..9f230e589ecc 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -1090,22 +1090,20 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino) unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count); ext4_group_t block_group; int bit; - struct buffer_head *bitmap_bh; + struct buffer_head *bitmap_bh = NULL; struct inode *inode = NULL; - long err = -EIO; + int err = -EIO; - /* Error cases - e2fsck has already cleaned up for us */ - if (ino > max_ino) { - ext4_warning(sb, "bad orphan ino %lu! e2fsck was run?", ino); - goto error; - } + if (ino < EXT4_FIRST_INO(sb) || ino > max_ino) + goto bad_orphan; block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb); bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb); bitmap_bh = ext4_read_inode_bitmap(sb, block_group); if (!bitmap_bh) { - ext4_warning(sb, "inode bitmap error for orphan %lu", ino); - goto error; + ext4_error(sb, "inode bitmap error %ld for orphan %lu", + ino, PTR_ERR(bitmap_bh)); + return (struct inode *) bitmap_bh; } /* Having the inode bit set should be a 100% indicator that this @@ -1116,15 +1114,21 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino) goto bad_orphan; inode = ext4_iget(sb, ino); - if (IS_ERR(inode)) - goto iget_failed; + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + ext4_error(sb, "couldn't read orphan inode %lu (err %d)", + ino, err); + return inode; + } /* - * If the orphans has i_nlinks > 0 then it should be able to be - * truncated, otherwise it won't be removed from the orphan list - * during processing and an infinite loop will result. + * If the orphans has i_nlinks > 0 then it should be able to + * be truncated, otherwise it won't be removed from the orphan + * list during processing and an infinite loop will result. + * Similarly, it must not be a bad inode. */ - if (inode->i_nlink && !ext4_can_truncate(inode)) + if ((inode->i_nlink && !ext4_can_truncate(inode)) || + is_bad_inode(inode)) goto bad_orphan; if (NEXT_ORPHAN(inode) > max_ino) @@ -1132,29 +1136,25 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino) brelse(bitmap_bh); return inode; -iget_failed: - err = PTR_ERR(inode); - inode = NULL; bad_orphan: - ext4_warning(sb, "bad orphan inode %lu! e2fsck was run?", ino); - printk(KERN_WARNING "ext4_test_bit(bit=%d, block=%llu) = %d\n", - bit, (unsigned long long)bitmap_bh->b_blocknr, - ext4_test_bit(bit, bitmap_bh->b_data)); - printk(KERN_WARNING "inode=%p\n", inode); + ext4_error(sb, "bad orphan inode %lu", ino); + if (bitmap_bh) + printk(KERN_ERR "ext4_test_bit(bit=%d, block=%llu) = %d\n", + bit, (unsigned long long)bitmap_bh->b_blocknr, + ext4_test_bit(bit, bitmap_bh->b_data)); if (inode) { - printk(KERN_WARNING "is_bad_inode(inode)=%d\n", + printk(KERN_ERR "is_bad_inode(inode)=%d\n", is_bad_inode(inode)); - printk(KERN_WARNING "NEXT_ORPHAN(inode)=%u\n", + printk(KERN_ERR "NEXT_ORPHAN(inode)=%u\n", NEXT_ORPHAN(inode)); - printk(KERN_WARNING "max_ino=%lu\n", max_ino); - printk(KERN_WARNING "i_nlink=%u\n", inode->i_nlink); + printk(KERN_ERR "max_ino=%lu\n", max_ino); + printk(KERN_ERR "i_nlink=%u\n", inode->i_nlink); /* Avoid freeing blocks if we got a bad deleted inode */ if (inode->i_nlink == 0) inode->i_blocks = 0; iput(inode); } brelse(bitmap_bh); -error: return ERR_PTR(err); } diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 5e7af1c69577..11368881477c 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -565,7 +565,7 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, EXT4_FEATURE_RO_COMPAT_BIGALLOC)) { EXT4_ERROR_INODE(inode, "Can't allocate blocks for " "non-extent mapped inodes with bigalloc"); - return -ENOSPC; + return -EUCLEAN; } /* Set up for the direct block allocation */ diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 842cdd153c20..6d7293082086 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1230,7 +1230,7 @@ static void ext4_da_page_release_reservation(struct page *page, unsigned int offset, unsigned int length) { - int to_release = 0; + int to_release = 0, contiguous_blks = 0; struct buffer_head *head, *bh; unsigned int curr_off = 0; struct inode *inode = page->mapping->host; @@ -1251,14 +1251,23 @@ static void ext4_da_page_release_reservation(struct page *page, if ((offset <= curr_off) && (buffer_delay(bh))) { to_release++; + contiguous_blks++; clear_buffer_delay(bh); + } else if (contiguous_blks) { + lblk = page->index << + (PAGE_CACHE_SHIFT - inode->i_blkbits); + lblk += (curr_off >> inode->i_blkbits) - + contiguous_blks; + ext4_es_remove_extent(inode, lblk, contiguous_blks); + contiguous_blks = 0; } curr_off = next_off; } while ((bh = bh->b_this_page) != head); - if (to_release) { + if (contiguous_blks) { lblk = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits); - ext4_es_remove_extent(inode, lblk, to_release); + lblk += (curr_off >> inode->i_blkbits) - contiguous_blks; + ext4_es_remove_extent(inode, lblk, contiguous_blks); } /* If we have released all the blocks belonging to a cluster, then we @@ -1606,19 +1615,32 @@ static int __ext4_journalled_writepage(struct page *page, ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL, bget_one); } - /* As soon as we unlock the page, it can go away, but we have - * references to buffers so we are safe */ + /* + * We need to release the page lock before we start the + * journal, so grab a reference so the page won't disappear + * out from under us. + */ + get_page(page); unlock_page(page); handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, ext4_writepage_trans_blocks(inode)); if (IS_ERR(handle)) { ret = PTR_ERR(handle); - goto out; + put_page(page); + goto out_no_pagelock; } - BUG_ON(!ext4_handle_valid(handle)); + lock_page(page); + put_page(page); + if (page->mapping != mapping) { + /* The page got truncated from under us */ + ext4_journal_stop(handle); + ret = 0; + goto out; + } + if (inline_data) { BUFFER_TRACE(inode_bh, "get write access"); ret = ext4_journal_get_write_access(handle, inode_bh); @@ -1644,6 +1666,8 @@ static int __ext4_journalled_writepage(struct page *page, NULL, bput_one); ext4_set_inode_state(inode, EXT4_STATE_JDATA); out: + unlock_page(page); +out_no_pagelock: brelse(inode_bh); return ret; } @@ -3009,29 +3033,29 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, * case, we allocate an io_end structure to hook to the iocb. */ iocb->private = NULL; - ext4_inode_aio_set(inode, NULL); - if (!is_sync_kiocb(iocb)) { - io_end = ext4_init_io_end(inode, GFP_NOFS); - if (!io_end) { - ret = -ENOMEM; - goto retake_lock; - } - /* - * Grab reference for DIO. Will be dropped in ext4_end_io_dio() - */ - iocb->private = ext4_get_io_end(io_end); - /* - * we save the io structure for current async direct - * IO, so that later ext4_map_blocks() could flag the - * io structure whether there is a unwritten extents - * needs to be converted when IO is completed. - */ - ext4_inode_aio_set(inode, io_end); - } - if (overwrite) { get_block_func = ext4_get_block_write_nolock; } else { + ext4_inode_aio_set(inode, NULL); + if (!is_sync_kiocb(iocb)) { + io_end = ext4_init_io_end(inode, GFP_NOFS); + if (!io_end) { + ret = -ENOMEM; + goto retake_lock; + } + /* + * Grab reference for DIO. Will be dropped in + * ext4_end_io_dio() + */ + iocb->private = ext4_get_io_end(io_end); + /* + * we save the io structure for current async direct + * IO, so that later ext4_map_blocks() could flag the + * io structure whether there is a unwritten extents + * needs to be converted when IO is completed. + */ + ext4_inode_aio_set(inode, io_end); + } get_block_func = ext4_get_block_write; dio_flags = DIO_LOCKING; } @@ -4817,6 +4841,8 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) might_sleep(); trace_ext4_mark_inode_dirty(inode, _RET_IP_); err = ext4_reserve_inode_write(handle, inode, &iloc); + if (err) + return err; if (ext4_handle_valid(handle) && EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize && !ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) { @@ -4847,9 +4873,7 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) } } } - if (!err) - err = ext4_mark_iloc_dirty(handle, inode, &iloc); - return err; + return ext4_mark_iloc_dirty(handle, inode, &iloc); } /* diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index dbfe15c2533c..dee06cd428eb 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1248,6 +1248,7 @@ static void ext4_mb_unload_buddy(struct ext4_buddy *e4b) static int mb_find_order_for_block(struct ext4_buddy *e4b, int block) { int order = 1; + int bb_incr = 1 << (e4b->bd_blkbits - 1); void *bb; BUG_ON(e4b->bd_bitmap == e4b->bd_buddy); @@ -1260,7 +1261,8 @@ static int mb_find_order_for_block(struct ext4_buddy *e4b, int block) /* this block is part of buddy of order 'order' */ return order; } - bb += 1 << (e4b->bd_blkbits - order); + bb += bb_incr; + bb_incr >>= 1; order++; } return 0; @@ -2553,7 +2555,7 @@ int ext4_mb_init(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned i, j; - unsigned offset; + unsigned offset, offset_incr; unsigned max; int ret; @@ -2582,11 +2584,13 @@ int ext4_mb_init(struct super_block *sb) i = 1; offset = 0; + offset_incr = 1 << (sb->s_blocksize_bits - 1); max = sb->s_blocksize << 2; do { sbi->s_mb_offsets[i] = offset; sbi->s_mb_maxs[i] = max; - offset += 1 << (sb->s_blocksize_bits - i); + offset += offset_incr; + offset_incr = offset_incr >> 1; max = max >> 1; i++; } while (i <= sb->s_blocksize_bits + 1); @@ -4801,18 +4805,12 @@ do_more: /* * blocks being freed are metadata. these blocks shouldn't * be used until this transaction is committed + * + * We use __GFP_NOFAIL because ext4_free_blocks() is not allowed + * to fail. */ - retry: - new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS); - if (!new_entry) { - /* - * We use a retry loop because - * ext4_free_blocks() is not allowed to fail. - */ - cond_resched(); - congestion_wait(BLK_RW_ASYNC, HZ/50); - goto retry; - } + new_entry = kmem_cache_alloc(ext4_free_data_cachep, + GFP_NOFS|__GFP_NOFAIL); new_entry->efd_start_cluster = bit; new_entry->efd_group = block_group; new_entry->efd_count = count_clusters; diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index a432634f2e6a..876b984f1a75 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -620,6 +620,7 @@ int ext4_ind_migrate(struct inode *inode) struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_extent *ex; unsigned int i, len; + ext4_lblk_t start, end; ext4_fsblk_t blk; handle_t *handle; int ret; @@ -633,6 +634,14 @@ int ext4_ind_migrate(struct inode *inode) EXT4_FEATURE_RO_COMPAT_BIGALLOC)) return -EOPNOTSUPP; + /* + * In order to get correct extent info, force all delayed allocation + * blocks to be allocated, otherwise delayed allocation blocks may not + * be reflected and bypass the checks on extent header. + */ + if (test_opt(inode->i_sb, DELALLOC)) + ext4_alloc_da_blocks(inode); + handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1); if (IS_ERR(handle)) return PTR_ERR(handle); @@ -650,11 +659,13 @@ int ext4_ind_migrate(struct inode *inode) goto errout; } if (eh->eh_entries == 0) - blk = len = 0; + blk = len = start = end = 0; else { len = le16_to_cpu(ex->ee_len); blk = ext4_ext_pblock(ex); - if (len > EXT4_NDIR_BLOCKS) { + start = le32_to_cpu(ex->ee_block); + end = start + len - 1; + if (end >= EXT4_NDIR_BLOCKS) { ret = -EOPNOTSUPP; goto errout; } @@ -662,7 +673,7 @@ int ext4_ind_migrate(struct inode *inode) ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS); memset(ei->i_data, 0, sizeof(ei->i_data)); - for (i=0; i < len; i++) + for (i = start; i <= end; i++) ei->i_data[i] = cpu_to_le32(blk++); ext4_mark_inode_dirty(handle, inode); errout: diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 9f2311bc9c4f..4d1049517e4a 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -60,10 +60,10 @@ ext4_double_down_write_data_sem(struct inode *first, struct inode *second) { if (first < second) { down_write(&EXT4_I(first)->i_data_sem); - down_write_nested(&EXT4_I(second)->i_data_sem, SINGLE_DEPTH_NESTING); + down_write_nested(&EXT4_I(second)->i_data_sem, I_DATA_SEM_OTHER); } else { down_write(&EXT4_I(second)->i_data_sem); - down_write_nested(&EXT4_I(first)->i_data_sem, SINGLE_DEPTH_NESTING); + down_write_nested(&EXT4_I(first)->i_data_sem, I_DATA_SEM_OTHER); } } @@ -269,10 +269,12 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode, unsigned long blocksize = orig_inode->i_sb->s_blocksize; unsigned int w_flags = 0; unsigned int tmp_data_size, data_size, replaced_size; - int err2, jblocks, retries = 0; + int i, err2, jblocks, retries = 0; int replaced_count = 0; int from = data_offset_in_page << orig_inode->i_blkbits; int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits; + struct super_block *sb = orig_inode->i_sb; + struct buffer_head *bh = NULL; /* * It needs twice the amount of ordinary journal buffers because @@ -386,8 +388,17 @@ data_copy: } /* Perform all necessary steps similar write_begin()/write_end() * but keeping in mind that i_size will not change */ - *err = __block_write_begin(pagep[0], from, replaced_size, - ext4_get_block); + if (!page_has_buffers(pagep[0])) + create_empty_buffers(pagep[0], 1 << orig_inode->i_blkbits, 0); + bh = page_buffers(pagep[0]); + for (i = 0; i < data_offset_in_page; i++) + bh = bh->b_this_page; + for (i = 0; i < block_len_in_page; i++) { + *err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0); + if (*err < 0) + break; + bh = bh->b_this_page; + } if (!*err) *err = block_commit_write(pagep[0], from, from + replaced_size); @@ -405,10 +416,13 @@ unlock_pages: page_cache_release(pagep[1]); stop_journal: ext4_journal_stop(handle); + if (*err == -ENOSPC && + ext4_should_retry_alloc(sb, &retries)) + goto again; /* Buffer was busy because probably is pinned to journal transaction, * force transaction commit may help to free it. */ - if (*err == -EBUSY && ext4_should_retry_alloc(orig_inode->i_sb, - &retries)) + if (*err == -EBUSY && retries++ < 4 && EXT4_SB(sb)->s_journal && + jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal)) goto again; return replaced_count; @@ -477,6 +491,13 @@ mext_check_arguments(struct inode *orig_inode, return -EBUSY; } + if (IS_NOQUOTA(orig_inode) || IS_NOQUOTA(donor_inode)) { + ext4_debug("ext4 move extent: The argument files should " + "not be quota files [ino:orig %lu, donor %lu]\n", + orig_inode->i_ino, donor_inode->i_ino); + return -EBUSY; + } + /* Ext4 move extent supports only extent based file */ if (!(ext4_test_inode_flag(orig_inode, EXT4_INODE_EXTENTS))) { ext4_debug("ext4 move extent: orig file is not extents " diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index bada5a1fb695..d3a22a11ac76 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2598,7 +2598,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) * list entries can cause panics at unmount time. */ mutex_lock(&sbi->s_orphan_lock); - list_del(&EXT4_I(inode)->i_orphan); + list_del_init(&EXT4_I(inode)->i_orphan); mutex_unlock(&sbi->s_orphan_lock); } } @@ -3261,12 +3261,18 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2); if (!(flags & RENAME_WHITEOUT)) { handle = ext4_journal_start(old.dir, EXT4_HT_DIR, credits); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + retval = PTR_ERR(handle); + handle = NULL; + goto end_rename; + } } else { whiteout = ext4_whiteout_for_rename(&old, credits, &handle); - if (IS_ERR(whiteout)) - return PTR_ERR(whiteout); + if (IS_ERR(whiteout)) { + retval = PTR_ERR(whiteout); + whiteout = NULL; + goto end_rename; + } } if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir)) @@ -3430,8 +3436,11 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry, handle = ext4_journal_start(old.dir, EXT4_HT_DIR, (2 * EXT4_DATA_TRANS_BLOCKS(old.dir->i_sb) + 2 * EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2)); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + retval = PTR_ERR(handle); + handle = NULL; + goto end_rename; + } if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir)) ext4_handle_sync(handle); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index ca4588388fc3..77c81c64a47e 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -186,7 +186,7 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size) if (flex_gd == NULL) goto out3; - if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_flex_group_data)) + if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data)) goto out2; flex_gd->count = flexbg_size; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index fc7391e14c2a..a5d94f263870 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -404,9 +404,13 @@ static void ext4_handle_error(struct super_block *sb) smp_wmb(); sb->s_flags |= MS_RDONLY; } - if (test_opt(sb, ERRORS_PANIC)) + if (test_opt(sb, ERRORS_PANIC)) { + if (EXT4_SB(sb)->s_journal && + !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR)) + return; panic("EXT4-fs (device %s): panic forced after error\n", sb->s_id); + } } #define ext4_error_ratelimit(sb) \ @@ -595,8 +599,12 @@ void __ext4_abort(struct super_block *sb, const char *function, jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO); save_error_info(sb, function, line); } - if (test_opt(sb, ERRORS_PANIC)) + if (test_opt(sb, ERRORS_PANIC)) { + if (EXT4_SB(sb)->s_journal && + !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR)) + return; panic("EXT4-fs panic from previous error\n"); + } } void __ext4_msg(struct super_block *sb, @@ -831,6 +839,7 @@ static void ext4_put_super(struct super_block *sb) dump_orphan_list(sb, sbi); J_ASSERT(list_empty(&sbi->s_orphan)); + sync_blockdev(sb->s_bdev); invalidate_bdev(sb->s_bdev); if (sbi->journal_bdev && sbi->journal_bdev != sb->s_bdev) { /* @@ -1272,9 +1281,9 @@ static int set_qf_name(struct super_block *sb, int qtype, substring_t *args) return -1; } if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) { - ext4_msg(sb, KERN_ERR, "Cannot set journaled quota options " - "when QUOTA feature is enabled"); - return -1; + ext4_msg(sb, KERN_INFO, "Journaled quota options " + "ignored when QUOTA feature is enabled"); + return 1; } qname = match_strdup(args); if (!qname) { @@ -1613,10 +1622,10 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, } if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) { - ext4_msg(sb, KERN_ERR, - "Cannot set journaled quota options " + ext4_msg(sb, KERN_INFO, + "Quota format mount options ignored " "when QUOTA feature is enabled"); - return -1; + return 1; } sbi->s_jquota_fmt = m->mount_opt; #endif @@ -1668,11 +1677,11 @@ static int parse_options(char *options, struct super_block *sb, #ifdef CONFIG_QUOTA if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) && (test_opt(sb, USRQUOTA) || test_opt(sb, GRPQUOTA))) { - ext4_msg(sb, KERN_ERR, "Cannot set quota options when QUOTA " - "feature is enabled"); - return 0; - } - if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) { + ext4_msg(sb, KERN_INFO, "Quota feature enabled, usrquota and grpquota " + "mount options ignored."); + clear_opt(sb, USRQUOTA); + clear_opt(sb, GRPQUOTA); + } else if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) { if (test_opt(sb, USRQUOTA) && sbi->s_qf_names[USRQUOTA]) clear_opt(sb, USRQUOTA); @@ -4753,10 +4762,11 @@ static int ext4_freeze(struct super_block *sb) error = jbd2_journal_flush(journal); if (error < 0) goto out; + + /* Journal blocked and flushed, clear needs_recovery flag. */ + EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); } - /* Journal blocked and flushed, clear needs_recovery flag. */ - EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); error = ext4_commit_super(sb, 1); out: if (journal) @@ -4774,8 +4784,11 @@ static int ext4_unfreeze(struct super_block *sb) if (sb->s_flags & MS_RDONLY) return 0; - /* Reset the needs_recovery flag before the fs is unlocked. */ - EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); + if (EXT4_SB(sb)->s_journal) { + /* Reset the needs_recovery flag before the fs is unlocked. */ + EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); + } + ext4_commit_super(sb, 1); return 0; } @@ -5174,6 +5187,20 @@ static int ext4_quota_on_mount(struct super_block *sb, int type) EXT4_SB(sb)->s_jquota_fmt, type); } +static void lockdep_set_quota_inode(struct inode *inode, int subclass) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + + /* The first argument of lockdep_set_subclass has to be + * *exactly* the same as the argument to init_rwsem() --- in + * this case, in init_once() --- or lockdep gets unhappy + * because the name of the lock is set using the + * stringification of the argument to init_rwsem(). + */ + (void) ei; /* shut up clang warning if !CONFIG_LOCKDEP */ + lockdep_set_subclass(&ei->i_data_sem, subclass); +} + /* * Standard function to be called on quota_on */ @@ -5213,8 +5240,12 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, if (err) return err; } - - return dquot_quota_on(sb, type, format_id, path); + lockdep_set_quota_inode(path->dentry->d_inode, I_DATA_SEM_QUOTA); + err = dquot_quota_on(sb, type, format_id, path); + if (err) + lockdep_set_quota_inode(path->dentry->d_inode, + I_DATA_SEM_NORMAL); + return err; } static int ext4_quota_enable(struct super_block *sb, int type, int format_id, @@ -5240,8 +5271,11 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id, /* Don't account quota for quota files to avoid recursion */ qf_inode->i_flags |= S_NOQUOTA; + lockdep_set_quota_inode(qf_inode, I_DATA_SEM_QUOTA); err = dquot_enable(qf_inode, type, format_id, flags); iput(qf_inode); + if (err) + lockdep_set_quota_inode(qf_inode, I_DATA_SEM_NORMAL); return err; } diff --git a/fs/fhandle.c b/fs/fhandle.c index d59712dfa3e7..ca3c3dd01789 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -228,7 +228,7 @@ long do_handle_open(int mountdirfd, path_put(&path); return fd; } - file = file_open_root(path.dentry, path.mnt, "", open_flag); + file = file_open_root(path.dentry, path.mnt, "", open_flag, 0); if (IS_ERR(file)) { put_unused_fd(fd); retval = PTR_ERR(file); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 2d609a5fbfea..a07634599cd7 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -705,6 +705,21 @@ static long writeback_sb_inodes(struct super_block *sb, work->nr_pages -= write_chunk - wbc.nr_to_write; wrote += write_chunk - wbc.nr_to_write; + + if (need_resched()) { + /* + * We're trying to balance between building up a nice + * long list of IOs to improve our merge rate, and + * getting those IOs out quickly for anyone throttling + * in balance_dirty_pages(). cond_resched() doesn't + * unplug, so get our IOs out the door before we + * give up the CPU. + */ + blk_flush_plug(current); + cond_resched(); + } + + spin_lock(&wb->list_lock); spin_lock(&inode->i_lock); if (!(inode->i_state & I_DIRTY)) @@ -712,7 +727,7 @@ static long writeback_sb_inodes(struct super_block *sb, requeue_inode(inode, wb, &wbc); inode_sync_complete(inode); spin_unlock(&inode->i_lock); - cond_resched_lock(&wb->list_lock); + /* * bail out to wb_writeback() often enough to check * background threshold and other termination conditions. diff --git a/fs/fuse/file.c b/fs/fuse/file.c index caa8d95b24e8..e2a2c14a90ee 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1088,6 +1088,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req, tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes); flush_dcache_page(page); + iov_iter_advance(ii, tmp); if (!tmp) { unlock_page(page); page_cache_release(page); @@ -1100,7 +1101,6 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req, req->page_descs[req->num_pages].length = tmp; req->num_pages++; - iov_iter_advance(ii, tmp); count += tmp; pos += tmp; offset += tmp; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 03246cd9d47a..9e3f6cfee2fb 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1049,6 +1049,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) goto err_fput; fuse_conn_init(fc); + fc->release = fuse_free_conn; fc->dev = sb->s_dev; fc->sb = sb; @@ -1063,7 +1064,6 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) fc->dont_mask = 1; sb->s_flags |= MS_POSIXACL; - fc->release = fuse_free_conn; fc->flags = d.flags; fc->user_id = d.user_id; fc->group_id = d.group_id; diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c index d3fa6bd9503e..221719eac5de 100644 --- a/fs/hfs/bnode.c +++ b/fs/hfs/bnode.c @@ -288,7 +288,6 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) page_cache_release(page); goto fail; } - page_cache_release(page); node->page[i] = page; } @@ -398,11 +397,11 @@ node_error: void hfs_bnode_free(struct hfs_bnode *node) { - //int i; + int i; - //for (i = 0; i < node->tree->pages_per_bnode; i++) - // if (node->page[i]) - // page_cache_release(node->page[i]); + for (i = 0; i < node->tree->pages_per_bnode; i++) + if (node->page[i]) + page_cache_release(node->page[i]); kfree(node); } diff --git a/fs/hfs/brec.c b/fs/hfs/brec.c index 9f4ee7f52026..6fc766df0461 100644 --- a/fs/hfs/brec.c +++ b/fs/hfs/brec.c @@ -131,13 +131,16 @@ skip: hfs_bnode_write(node, entry, data_off + key_len, entry_len); hfs_bnode_dump(node); - if (new_node) { - /* update parent key if we inserted a key - * at the start of the first node - */ - if (!rec && new_node != node) - hfs_brec_update_parent(fd); + /* + * update parent key if we inserted a key + * at the start of the node and it is not the new node + */ + if (!rec && new_node != node) { + hfs_bnode_read_key(node, fd->search_key, data_off + size); + hfs_brec_update_parent(fd); + } + if (new_node) { hfs_bnode_put(fd->bnode); if (!new_node->parent) { hfs_btree_inc_height(tree); @@ -166,9 +169,6 @@ skip: goto again; } - if (!rec) - hfs_brec_update_parent(fd); - return 0; } @@ -366,6 +366,8 @@ again: if (IS_ERR(parent)) return PTR_ERR(parent); __hfs_brec_find(parent, fd); + if (fd->record < 0) + return -ENOENT; hfs_bnode_dump(parent); rec = fd->record; diff --git a/fs/hfsplus/bnode.c b/fs/hfsplus/bnode.c index 759708fd9331..63924662aaf3 100644 --- a/fs/hfsplus/bnode.c +++ b/fs/hfsplus/bnode.c @@ -454,7 +454,6 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) page_cache_release(page); goto fail; } - page_cache_release(page); node->page[i] = page; } @@ -566,13 +565,11 @@ node_error: void hfs_bnode_free(struct hfs_bnode *node) { -#if 0 int i; for (i = 0; i < node->tree->pages_per_bnode; i++) if (node->page[i]) page_cache_release(node->page[i]); -#endif kfree(node); } diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index fd62cae0fdcb..6e4a3f1b9ce2 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -720,15 +720,13 @@ static int hostfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, init_special_inode(inode, mode, dev); err = do_mknod(name, mode, MAJOR(dev), MINOR(dev)); - if (!err) + if (err) goto out_free; err = read_name(inode, name); __putname(name); if (err) goto out_put; - if (err) - goto out_put; d_instantiate(dentry, inode); return 0; diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index bdbc2c3080a4..12da295759f7 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -8,6 +8,17 @@ #include <linux/sched.h> #include "hpfs_fn.h" +static void hpfs_update_directory_times(struct inode *dir) +{ + time_t t = get_seconds(); + if (t == dir->i_mtime.tv_sec && + t == dir->i_ctime.tv_sec) + return; + dir->i_mtime.tv_sec = dir->i_ctime.tv_sec = t; + dir->i_mtime.tv_nsec = dir->i_ctime.tv_nsec = 0; + hpfs_write_inode_nolock(dir); +} + static int hpfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { const unsigned char *name = dentry->d_name.name; @@ -99,6 +110,7 @@ static int hpfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) result->i_mode = mode | S_IFDIR; hpfs_write_inode_nolock(result); } + hpfs_update_directory_times(dir); d_instantiate(dentry, result); hpfs_unlock(dir->i_sb); return 0; @@ -187,6 +199,7 @@ static int hpfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, b result->i_mode = mode | S_IFREG; hpfs_write_inode_nolock(result); } + hpfs_update_directory_times(dir); d_instantiate(dentry, result); hpfs_unlock(dir->i_sb); return 0; @@ -262,6 +275,7 @@ static int hpfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, de insert_inode_hash(result); hpfs_write_inode_nolock(result); + hpfs_update_directory_times(dir); d_instantiate(dentry, result); brelse(bh); hpfs_unlock(dir->i_sb); @@ -340,6 +354,7 @@ static int hpfs_symlink(struct inode *dir, struct dentry *dentry, const char *sy insert_inode_hash(result); hpfs_write_inode_nolock(result); + hpfs_update_directory_times(dir); d_instantiate(dentry, result); hpfs_unlock(dir->i_sb); return 0; @@ -362,12 +377,11 @@ static int hpfs_unlink(struct inode *dir, struct dentry *dentry) struct inode *inode = dentry->d_inode; dnode_secno dno; int r; - int rep = 0; int err; hpfs_lock(dir->i_sb); hpfs_adjust_length(name, &len); -again: + err = -ENOENT; de = map_dirent(dir, hpfs_i(dir)->i_dno, name, len, &dno, &qbh); if (!de) @@ -387,33 +401,9 @@ again: hpfs_error(dir->i_sb, "there was error when removing dirent"); err = -EFSERROR; break; - case 2: /* no space for deleting, try to truncate file */ - + case 2: /* no space for deleting */ err = -ENOSPC; - if (rep++) - break; - - dentry_unhash(dentry); - if (!d_unhashed(dentry)) { - hpfs_unlock(dir->i_sb); - return -ENOSPC; - } - if (generic_permission(inode, MAY_WRITE) || - !S_ISREG(inode->i_mode) || - get_write_access(inode)) { - d_rehash(dentry); - } else { - struct iattr newattrs; - /*pr_info("truncating file before delete.\n");*/ - newattrs.ia_size = 0; - newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME; - err = notify_change(dentry, &newattrs, NULL); - put_write_access(inode); - if (!err) - goto again; - } - hpfs_unlock(dir->i_sb); - return -ENOSPC; + break; default: drop_nlink(inode); err = 0; @@ -423,6 +413,8 @@ again: out1: hpfs_brelse4(&qbh); out: + if (!err) + hpfs_update_directory_times(dir); hpfs_unlock(dir->i_sb); return err; } @@ -477,6 +469,8 @@ static int hpfs_rmdir(struct inode *dir, struct dentry *dentry) out1: hpfs_brelse4(&qbh); out: + if (!err) + hpfs_update_directory_times(dir); hpfs_unlock(dir->i_sb); return err; } @@ -595,7 +589,7 @@ static int hpfs_rename(struct inode *old_dir, struct dentry *old_dentry, goto end1; } - end: +end: hpfs_i(i)->i_parent_dir = new_dir->i_ino; if (S_ISDIR(i->i_mode)) { inc_nlink(new_dir); @@ -610,6 +604,10 @@ static int hpfs_rename(struct inode *old_dir, struct dentry *old_dentry, brelse(bh); } end1: + if (!err) { + hpfs_update_directory_times(old_dir); + hpfs_update_directory_times(new_dir); + } hpfs_unlock(i->i_sb); return err; } diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index 7cd00d3a7c9b..f445d155dfae 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -52,17 +52,20 @@ static void unmark_dirty(struct super_block *s) } /* Filesystem error... */ -static char err_buf[1024]; - void hpfs_error(struct super_block *s, const char *fmt, ...) { + struct va_format vaf; va_list args; va_start(args, fmt); - vsnprintf(err_buf, sizeof(err_buf), fmt, args); + + vaf.fmt = fmt; + vaf.va = &args; + + pr_err("filesystem error: %pV", &vaf); + va_end(args); - pr_err("filesystem error: %s", err_buf); if (!hpfs_sb(s)->sb_was_error) { if (hpfs_sb(s)->sb_err == 2) { pr_cont("; crashing the system because you wanted it\n"); diff --git a/fs/inode.c b/fs/inode.c index 26753ba7b6d6..56d1d2b4bf31 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1631,8 +1631,8 @@ int file_remove_suid(struct file *file) error = security_inode_killpriv(dentry); if (!error && killsuid) error = __remove_suid(dentry, killsuid); - if (!error && (inode->i_sb->s_flags & MS_NOSEC)) - inode->i_flags |= S_NOSEC; + if (!error) + inode_has_no_xattr(inode); return error; } diff --git a/fs/internal.h b/fs/internal.h index 757ba2abf21e..53279bd90b72 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -106,6 +106,7 @@ extern struct file *do_file_open_root(struct dentry *, struct vfsmount *, extern long do_handle_open(int mountdirfd, struct file_handle __user *ufh, int open_flag); extern int open_check_o_direct(struct file *f); +extern int vfs_open(const struct path *, struct file *, const struct cred *); /* * inode.c diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c index 735d7522a3a9..204659a5f6db 100644 --- a/fs/isofs/rock.c +++ b/fs/isofs/rock.c @@ -203,6 +203,8 @@ int get_rock_ridge_filename(struct iso_directory_record *de, int retnamlen = 0; int truncate = 0; int ret = 0; + char *p; + int len; if (!ISOFS_SB(inode->i_sb)->s_rock) return 0; @@ -267,12 +269,17 @@ repeat: rr->u.NM.flags); break; } - if ((strlen(retname) + rr->len - 5) >= 254) { + len = rr->len - 5; + if (retnamlen + len >= 254) { truncate = 1; break; } - strncat(retname, rr->u.NM.name, rr->len - 5); - retnamlen += rr->len - 5; + p = memchr(rr->u.NM.name, '\0', len); + if (unlikely(p)) + len = p - rr->u.NM.name; + memcpy(retname + retnamlen, rr->u.NM.name, len); + retnamlen += len; + retname[retnamlen] = '\0'; break; case SIG('R', 'E'): kfree(rs.buffer); diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 6f691c289c71..78c1545a3fab 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -392,7 +392,7 @@ int jbd2_cleanup_journal_tail(journal_t *journal) unsigned long blocknr; if (is_journal_aborted(journal)) - return 1; + return -EIO; if (!jbd2_journal_get_log_tail(journal, &first_tid, &blocknr)) return 1; @@ -407,10 +407,9 @@ int jbd2_cleanup_journal_tail(journal_t *journal) * jbd2_cleanup_journal_tail() doesn't get called all that often. */ if (journal->j_flags & JBD2_BARRIER) - blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL); + blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS, NULL); - __jbd2_update_log_tail(journal, first_tid, blocknr); - return 0; + return __jbd2_update_log_tail(journal, first_tid, blocknr); } @@ -420,12 +419,12 @@ int jbd2_cleanup_journal_tail(journal_t *journal) * journal_clean_one_cp_list * * Find all the written-back checkpoint buffers in the given list and - * release them. + * release them. If 'destroy' is set, clean all buffers unconditionally. * * Called with j_list_lock held. * Returns 1 if we freed the transaction, 0 otherwise. */ -static int journal_clean_one_cp_list(struct journal_head *jh) +static int journal_clean_one_cp_list(struct journal_head *jh, bool destroy) { struct journal_head *last_jh; struct journal_head *next_jh = jh; @@ -439,7 +438,10 @@ static int journal_clean_one_cp_list(struct journal_head *jh) do { jh = next_jh; next_jh = jh->b_cpnext; - ret = __try_to_free_cp_buf(jh); + if (!destroy) + ret = __try_to_free_cp_buf(jh); + else + ret = __jbd2_journal_remove_checkpoint(jh) + 1; if (!ret) return freed; if (ret == 2) @@ -462,10 +464,11 @@ static int journal_clean_one_cp_list(struct journal_head *jh) * journal_clean_checkpoint_list * * Find all the written-back checkpoint buffers in the journal and release them. + * If 'destroy' is set, release all buffers unconditionally. * * Called with j_list_lock held. */ -void __jbd2_journal_clean_checkpoint_list(journal_t *journal) +void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy) { transaction_t *transaction, *last_transaction, *next_transaction; int ret; @@ -479,7 +482,8 @@ void __jbd2_journal_clean_checkpoint_list(journal_t *journal) do { transaction = next_transaction; next_transaction = transaction->t_cpnext; - ret = journal_clean_one_cp_list(transaction->t_checkpoint_list); + ret = journal_clean_one_cp_list(transaction->t_checkpoint_list, + destroy); /* * This function only frees up some memory if possible so we * dont have an obligation to finish processing. Bail out if @@ -495,7 +499,7 @@ void __jbd2_journal_clean_checkpoint_list(journal_t *journal) * we can possibly see not yet submitted buffers on io_list */ ret = journal_clean_one_cp_list(transaction-> - t_checkpoint_io_list); + t_checkpoint_io_list, destroy); if (need_resched()) return; /* @@ -509,6 +513,28 @@ void __jbd2_journal_clean_checkpoint_list(journal_t *journal) } /* + * Remove buffers from all checkpoint lists as journal is aborted and we just + * need to free memory + */ +void jbd2_journal_destroy_checkpoint(journal_t *journal) +{ + /* + * We loop because __jbd2_journal_clean_checkpoint_list() may abort + * early due to a need of rescheduling. + */ + while (1) { + spin_lock(&journal->j_list_lock); + if (!journal->j_checkpoint_transactions) { + spin_unlock(&journal->j_list_lock); + break; + } + __jbd2_journal_clean_checkpoint_list(journal, true); + spin_unlock(&journal->j_list_lock); + cond_resched(); + } +} + +/* * journal_remove_checkpoint: called after a buffer has been committed * to disk (either by being write-back flushed to disk, or being * committed to the log). diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index b73e0215baa7..362e5f614450 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -510,7 +510,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) * frees some memory */ spin_lock(&journal->j_list_lock); - __jbd2_journal_clean_checkpoint_list(journal); + __jbd2_journal_clean_checkpoint_list(journal, false); spin_unlock(&journal->j_list_lock); jbd_debug(3, "JBD2: commit phase 1\n"); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 1df94fabe4eb..985e95b9b4ef 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -885,9 +885,10 @@ int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid, * * Requires j_checkpoint_mutex */ -void __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) +int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) { unsigned long freed; + int ret; BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); @@ -897,7 +898,10 @@ void __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) * space and if we lose sb update during power failure we'd replay * old transaction with possibly newly overwritten data. */ - jbd2_journal_update_sb_log_tail(journal, tid, block, WRITE_FUA); + ret = jbd2_journal_update_sb_log_tail(journal, tid, block, WRITE_FUA); + if (ret) + goto out; + write_lock(&journal->j_state_lock); freed = block - journal->j_tail; if (block < journal->j_tail) @@ -913,6 +917,9 @@ void __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) journal->j_tail_sequence = tid; journal->j_tail = block; write_unlock(&journal->j_state_lock); + +out: + return ret; } /* @@ -1331,7 +1338,7 @@ static int journal_reset(journal_t *journal) return jbd2_journal_start_thread(journal); } -static void jbd2_write_superblock(journal_t *journal, int write_op) +static int jbd2_write_superblock(journal_t *journal, int write_op) { struct buffer_head *bh = journal->j_sb_buffer; journal_superblock_t *sb = journal->j_superblock; @@ -1370,7 +1377,10 @@ static void jbd2_write_superblock(journal_t *journal, int write_op) printk(KERN_ERR "JBD2: Error %d detected when updating " "journal superblock for %s.\n", ret, journal->j_devname); + jbd2_journal_abort(journal, ret); } + + return ret; } /** @@ -1383,10 +1393,11 @@ static void jbd2_write_superblock(journal_t *journal, int write_op) * Update a journal's superblock information about log tail and write it to * disk, waiting for the IO to complete. */ -void jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid, +int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid, unsigned long tail_block, int write_op) { journal_superblock_t *sb = journal->j_superblock; + int ret; BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); jbd_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n", @@ -1395,23 +1406,29 @@ void jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid, sb->s_sequence = cpu_to_be32(tail_tid); sb->s_start = cpu_to_be32(tail_block); - jbd2_write_superblock(journal, write_op); + ret = jbd2_write_superblock(journal, write_op); + if (ret) + goto out; /* Log is no longer empty */ write_lock(&journal->j_state_lock); WARN_ON(!sb->s_sequence); journal->j_flags &= ~JBD2_FLUSHED; write_unlock(&journal->j_state_lock); + +out: + return ret; } /** * jbd2_mark_journal_empty() - Mark on disk journal as empty. * @journal: The journal to update. + * @write_op: With which operation should we write the journal sb * * Update a journal's dynamic superblock fields to show that journal is empty. * Write updated superblock to disk waiting for IO to complete. */ -static void jbd2_mark_journal_empty(journal_t *journal) +static void jbd2_mark_journal_empty(journal_t *journal, int write_op) { journal_superblock_t *sb = journal->j_superblock; @@ -1429,7 +1446,7 @@ static void jbd2_mark_journal_empty(journal_t *journal) sb->s_start = cpu_to_be32(0); read_unlock(&journal->j_state_lock); - jbd2_write_superblock(journal, WRITE_FUA); + jbd2_write_superblock(journal, write_op); /* Log is no longer empty */ write_lock(&journal->j_state_lock); @@ -1692,8 +1709,17 @@ int jbd2_journal_destroy(journal_t *journal) while (journal->j_checkpoint_transactions != NULL) { spin_unlock(&journal->j_list_lock); mutex_lock(&journal->j_checkpoint_mutex); - jbd2_log_do_checkpoint(journal); + err = jbd2_log_do_checkpoint(journal); mutex_unlock(&journal->j_checkpoint_mutex); + /* + * If checkpointing failed, just free the buffers to avoid + * looping forever + */ + if (err) { + jbd2_journal_destroy_checkpoint(journal); + spin_lock(&journal->j_list_lock); + break; + } spin_lock(&journal->j_list_lock); } @@ -1705,7 +1731,13 @@ int jbd2_journal_destroy(journal_t *journal) if (journal->j_sb_buffer) { if (!is_journal_aborted(journal)) { mutex_lock(&journal->j_checkpoint_mutex); - jbd2_mark_journal_empty(journal); + + write_lock(&journal->j_state_lock); + journal->j_tail_sequence = + ++journal->j_transaction_sequence; + write_unlock(&journal->j_state_lock); + + jbd2_mark_journal_empty(journal, WRITE_FLUSH_FUA); mutex_unlock(&journal->j_checkpoint_mutex); } else err = -EIO; @@ -1951,14 +1983,21 @@ int jbd2_journal_flush(journal_t *journal) return -EIO; mutex_lock(&journal->j_checkpoint_mutex); - jbd2_cleanup_journal_tail(journal); + if (!err) { + err = jbd2_cleanup_journal_tail(journal); + if (err < 0) { + mutex_unlock(&journal->j_checkpoint_mutex); + goto out; + } + err = 0; + } /* Finally, mark the journal as really needing no recovery. * This sets s_start==0 in the underlying superblock, which is * the magic code for a fully-recovered superblock. Any future * commits of data to the journal will restore the current * s_start value. */ - jbd2_mark_journal_empty(journal); + jbd2_mark_journal_empty(journal, WRITE_FUA); mutex_unlock(&journal->j_checkpoint_mutex); write_lock(&journal->j_state_lock); J_ASSERT(!journal->j_running_transaction); @@ -1967,7 +2006,8 @@ int jbd2_journal_flush(journal_t *journal) J_ASSERT(journal->j_head == journal->j_tail); J_ASSERT(journal->j_tail_sequence == journal->j_transaction_sequence); write_unlock(&journal->j_state_lock); - return 0; +out: + return err; } /** @@ -2003,7 +2043,7 @@ int jbd2_journal_wipe(journal_t *journal, int write) if (write) { /* Lock to make assertions happy... */ mutex_lock(&journal->j_checkpoint_mutex); - jbd2_mark_journal_empty(journal); + jbd2_mark_journal_empty(journal, WRITE_FUA); mutex_unlock(&journal->j_checkpoint_mutex); } @@ -2054,8 +2094,12 @@ static void __journal_abort_soft (journal_t *journal, int errno) __jbd2_journal_abort_hard(journal); - if (errno) + if (errno) { jbd2_journal_update_sb_errno(journal); + write_lock(&journal->j_state_lock); + journal->j_flags |= JBD2_REC_ERR; + write_unlock(&journal->j_state_lock); + } } /** diff --git a/fs/jffs2/README.Locking b/fs/jffs2/README.Locking index 3ea36554107f..8918ac905a3b 100644 --- a/fs/jffs2/README.Locking +++ b/fs/jffs2/README.Locking @@ -2,10 +2,6 @@ JFFS2 LOCKING DOCUMENTATION --------------------------- -At least theoretically, JFFS2 does not require the Big Kernel Lock -(BKL), which was always helpfully obtained for it by Linux 2.4 VFS -code. It has its own locking, as described below. - This document attempts to describe the existing locking rules for JFFS2. It is not expected to remain perfectly up to date, but ought to be fairly close. @@ -69,6 +65,7 @@ Ordering constraints: any f->sem held. 2. Never attempt to lock two file mutexes in one thread. No ordering rules have been made for doing so. + 3. Never lock a page cache page with f->sem held. erase_completion_lock spinlock diff --git a/fs/jffs2/build.c b/fs/jffs2/build.c index a3750f902adc..c1f04947d7dc 100644 --- a/fs/jffs2/build.c +++ b/fs/jffs2/build.c @@ -49,7 +49,8 @@ next_inode(int *i, struct jffs2_inode_cache *ic, struct jffs2_sb_info *c) static void jffs2_build_inode_pass1(struct jffs2_sb_info *c, - struct jffs2_inode_cache *ic) + struct jffs2_inode_cache *ic, + int *dir_hardlinks) { struct jffs2_full_dirent *fd; @@ -68,19 +69,21 @@ static void jffs2_build_inode_pass1(struct jffs2_sb_info *c, dbg_fsbuild("child \"%s\" (ino #%u) of dir ino #%u doesn't exist!\n", fd->name, fd->ino, ic->ino); jffs2_mark_node_obsolete(c, fd->raw); + /* Clear the ic/raw union so it doesn't cause problems later. */ + fd->ic = NULL; continue; } + /* From this point, fd->raw is no longer used so we can set fd->ic */ + fd->ic = child_ic; + child_ic->pino_nlink++; + /* If we appear (at this stage) to have hard-linked directories, + * set a flag to trigger a scan later */ if (fd->type == DT_DIR) { - if (child_ic->pino_nlink) { - JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u appears to be a hard link\n", - fd->name, fd->ino, ic->ino); - /* TODO: What do we do about it? */ - } else { - child_ic->pino_nlink = ic->ino; - } - } else - child_ic->pino_nlink++; + child_ic->flags |= INO_FLAGS_IS_DIR; + if (child_ic->pino_nlink > 1) + *dir_hardlinks = 1; + } dbg_fsbuild("increased nlink for child \"%s\" (ino #%u)\n", fd->name, fd->ino); /* Can't free scan_dents so far. We might need them in pass 2 */ @@ -94,8 +97,7 @@ static void jffs2_build_inode_pass1(struct jffs2_sb_info *c, */ static int jffs2_build_filesystem(struct jffs2_sb_info *c) { - int ret; - int i; + int ret, i, dir_hardlinks = 0; struct jffs2_inode_cache *ic; struct jffs2_full_dirent *fd; struct jffs2_full_dirent *dead_fds = NULL; @@ -119,7 +121,7 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c) /* Now scan the directory tree, increasing nlink according to every dirent found. */ for_each_inode(i, c, ic) { if (ic->scan_dents) { - jffs2_build_inode_pass1(c, ic); + jffs2_build_inode_pass1(c, ic, &dir_hardlinks); cond_resched(); } } @@ -155,6 +157,20 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c) } dbg_fsbuild("pass 2a complete\n"); + + if (dir_hardlinks) { + /* If we detected directory hardlinks earlier, *hopefully* + * they are gone now because some of the links were from + * dead directories which still had some old dirents lying + * around and not yet garbage-collected, but which have + * been discarded above. So clear the pino_nlink field + * in each directory, so that the final scan below can + * print appropriate warnings. */ + for_each_inode(i, c, ic) { + if (ic->flags & INO_FLAGS_IS_DIR) + ic->pino_nlink = 0; + } + } dbg_fsbuild("freeing temporary data structures\n"); /* Finally, we can scan again and free the dirent structs */ @@ -162,6 +178,33 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c) while(ic->scan_dents) { fd = ic->scan_dents; ic->scan_dents = fd->next; + /* We do use the pino_nlink field to count nlink of + * directories during fs build, so set it to the + * parent ino# now. Now that there's hopefully only + * one. */ + if (fd->type == DT_DIR) { + if (!fd->ic) { + /* We'll have complained about it and marked the coresponding + raw node obsolete already. Just skip it. */ + continue; + } + + /* We *have* to have set this in jffs2_build_inode_pass1() */ + BUG_ON(!(fd->ic->flags & INO_FLAGS_IS_DIR)); + + /* We clear ic->pino_nlink ∀ directories' ic *only* if dir_hardlinks + * is set. Otherwise, we know this should never trigger anyway, so + * we don't do the check. And ic->pino_nlink still contains the nlink + * value (which is 1). */ + if (dir_hardlinks && fd->ic->pino_nlink) { + JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u is also hard linked from dir ino #%u\n", + fd->name, fd->ino, ic->ino, fd->ic->pino_nlink); + /* Should we unlink it from its previous parent? */ + } + + /* For directories, ic->pino_nlink holds that parent inode # */ + fd->ic->pino_nlink = ic->ino; + } jffs2_free_full_dirent(fd); } ic->scan_dents = NULL; @@ -240,11 +283,7 @@ static void jffs2_build_remove_unlinked_inode(struct jffs2_sb_info *c, /* Reduce nlink of the child. If it's now zero, stick it on the dead_fds list to be cleaned up later. Else just free the fd */ - - if (fd->type == DT_DIR) - child_ic->pino_nlink = 0; - else - child_ic->pino_nlink--; + child_ic->pino_nlink--; if (!child_ic->pino_nlink) { dbg_fsbuild("inode #%u (\"%s\") now has no links; adding to dead_fds list.\n", diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index 64989ca9ba90..129eccb4c5a8 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -139,39 +139,33 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, struct page *pg; struct inode *inode = mapping->host; struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); - struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); - struct jffs2_raw_inode ri; - uint32_t alloc_len = 0; pgoff_t index = pos >> PAGE_CACHE_SHIFT; uint32_t pageofs = index << PAGE_CACHE_SHIFT; int ret = 0; - jffs2_dbg(1, "%s()\n", __func__); - - if (pageofs > inode->i_size) { - ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len, - ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE); - if (ret) - return ret; - } - - mutex_lock(&f->sem); pg = grab_cache_page_write_begin(mapping, index, flags); - if (!pg) { - if (alloc_len) - jffs2_complete_reservation(c); - mutex_unlock(&f->sem); + if (!pg) return -ENOMEM; - } *pagep = pg; - if (alloc_len) { + jffs2_dbg(1, "%s()\n", __func__); + + if (pageofs > inode->i_size) { /* Make new hole frag from old EOF to new page */ + struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); + struct jffs2_raw_inode ri; struct jffs2_full_dnode *fn; + uint32_t alloc_len; jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new page\n", (unsigned int)inode->i_size, pageofs); + ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len, + ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE); + if (ret) + goto out_page; + + mutex_lock(&f->sem); memset(&ri, 0, sizeof(ri)); ri.magic = cpu_to_je16(JFFS2_MAGIC_BITMASK); @@ -198,6 +192,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, if (IS_ERR(fn)) { ret = PTR_ERR(fn); jffs2_complete_reservation(c); + mutex_unlock(&f->sem); goto out_page; } ret = jffs2_add_full_dnode_to_inode(c, f, fn); @@ -212,10 +207,12 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, jffs2_mark_node_obsolete(c, fn->raw); jffs2_free_full_dnode(fn); jffs2_complete_reservation(c); + mutex_unlock(&f->sem); goto out_page; } jffs2_complete_reservation(c); inode->i_size = pageofs; + mutex_unlock(&f->sem); } /* @@ -224,18 +221,18 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, * case of a short-copy. */ if (!PageUptodate(pg)) { + mutex_lock(&f->sem); ret = jffs2_do_readpage_nolock(inode, pg); + mutex_unlock(&f->sem); if (ret) goto out_page; } - mutex_unlock(&f->sem); jffs2_dbg(1, "end write_begin(). pg->flags %lx\n", pg->flags); return ret; out_page: unlock_page(pg); page_cache_release(pg); - mutex_unlock(&f->sem); return ret; } diff --git a/fs/jffs2/gc.c b/fs/jffs2/gc.c index 5a2dec2b064c..95d5880a63ee 100644 --- a/fs/jffs2/gc.c +++ b/fs/jffs2/gc.c @@ -1296,14 +1296,17 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era BUG_ON(start > orig_start); } - /* First, use readpage() to read the appropriate page into the page cache */ - /* Q: What happens if we actually try to GC the _same_ page for which commit_write() - * triggered garbage collection in the first place? - * A: I _think_ it's OK. read_cache_page shouldn't deadlock, we'll write out the - * page OK. We'll actually write it out again in commit_write, which is a little - * suboptimal, but at least we're correct. - */ + /* The rules state that we must obtain the page lock *before* f->sem, so + * drop f->sem temporarily. Since we also hold c->alloc_sem, nothing's + * actually going to *change* so we're safe; we only allow reading. + * + * It is important to note that jffs2_write_begin() will ensure that its + * page is marked Uptodate before allocating space. That means that if we + * end up here trying to GC the *same* page that jffs2_write_begin() is + * trying to write out, read_cache_page() will not deadlock. */ + mutex_unlock(&f->sem); pg_ptr = jffs2_gc_fetch_page(c, f, start, &pg); + mutex_lock(&f->sem); if (IS_ERR(pg_ptr)) { pr_warn("read_cache_page() returned error: %ld\n", diff --git a/fs/jffs2/nodelist.h b/fs/jffs2/nodelist.h index fa35ff79ab35..0637271f3770 100644 --- a/fs/jffs2/nodelist.h +++ b/fs/jffs2/nodelist.h @@ -194,6 +194,7 @@ struct jffs2_inode_cache { #define INO_STATE_CLEARING 6 /* In clear_inode() */ #define INO_FLAGS_XATTR_CHECKED 0x01 /* has no duplicate xattr_ref */ +#define INO_FLAGS_IS_DIR 0x02 /* is a directory */ #define RAWNODE_CLASS_INODE_CACHE 0 #define RAWNODE_CLASS_XATTR_DATUM 1 @@ -249,7 +250,10 @@ struct jffs2_readinode_info struct jffs2_full_dirent { - struct jffs2_raw_node_ref *raw; + union { + struct jffs2_raw_node_ref *raw; + struct jffs2_inode_cache *ic; /* Just during part of build */ + }; struct jffs2_full_dirent *next; uint32_t version; uint32_t ino; /* == zero for unlink */ diff --git a/fs/locks.c b/fs/locks.c index 59e2f905e4ff..253ca5c2b9c7 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1580,7 +1580,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr { struct file_lock *fl, **before, **my_before = NULL, *lease; struct dentry *dentry = filp->f_path.dentry; - struct inode *inode = dentry->d_inode; + struct inode *inode = file_inode(filp); bool is_deleg = (*flp)->fl_flags & FL_DELEG; int error; LIST_HEAD(dispose); @@ -2127,7 +2127,6 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, goto out; } -again: error = flock_to_posix_lock(filp, file_lock, &flock); if (error) goto out; @@ -2169,19 +2168,22 @@ again: * Attempt to detect a close/fcntl race and recover by * releasing the lock that was just acquired. */ - /* - * we need that spin_lock here - it prevents reordering between - * update of inode->i_flock and check for it done in close(). - * rcu_read_lock() wouldn't do. - */ - spin_lock(¤t->files->file_lock); - f = fcheck(fd); - spin_unlock(¤t->files->file_lock); - if (!error && f != filp && flock.l_type != F_UNLCK) { - flock.l_type = F_UNLCK; - goto again; + if (!error && file_lock->fl_type != F_UNLCK) { + /* + * We need that spin_lock here - it prevents reordering between + * update of i_flctx->flc_posix and check for it done in + * close(). rcu_read_lock() wouldn't do. + */ + spin_lock(¤t->files->file_lock); + f = fcheck(fd); + spin_unlock(¤t->files->file_lock); + if (f != filp) { + file_lock->fl_type = F_UNLCK; + error = do_lock_file_wait(filp, cmd, file_lock); + WARN_ON_ONCE(error); + error = -EBADF; + } } - out: locks_free_lock(file_lock); return error; @@ -2267,7 +2269,6 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, goto out; } -again: error = flock64_to_posix_lock(filp, file_lock, &flock); if (error) goto out; @@ -2309,14 +2310,22 @@ again: * Attempt to detect a close/fcntl race and recover by * releasing the lock that was just acquired. */ - spin_lock(¤t->files->file_lock); - f = fcheck(fd); - spin_unlock(¤t->files->file_lock); - if (!error && f != filp && flock.l_type != F_UNLCK) { - flock.l_type = F_UNLCK; - goto again; + if (!error && file_lock->fl_type != F_UNLCK) { + /* + * We need that spin_lock here - it prevents reordering between + * update of i_flctx->flc_posix and check for it done in + * close(). rcu_read_lock() wouldn't do. + */ + spin_lock(¤t->files->file_lock); + f = fcheck(fd); + spin_unlock(¤t->files->file_lock); + if (f != filp) { + file_lock->fl_type = F_UNLCK; + error = do_lock_file_wait(filp, cmd, file_lock); + WARN_ON_ONCE(error); + error = -EBADF; + } } - out: locks_free_lock(file_lock); return error; diff --git a/fs/namei.c b/fs/namei.c index d20f061cddd3..e1976450a1e2 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -487,6 +487,24 @@ void path_put(const struct path *path) } EXPORT_SYMBOL(path_put); +/** + * path_connected - Verify that a path->dentry is below path->mnt.mnt_root + * @path: nameidate to verify + * + * Rename can sometimes move a file or directory outside of a bind + * mount, path_connected allows those cases to be detected. + */ +static bool path_connected(const struct path *path) +{ + struct vfsmount *mnt = path->mnt; + + /* Only bind mounts can have disconnected paths */ + if (mnt->mnt_root == mnt->mnt_sb->s_root) + return true; + + return is_subdir(path->dentry, mnt->mnt_root); +} + /* * Path walking has 2 modes, rcu-walk and ref-walk (see * Documentation/filesystems/path-lookup.txt). In situations when we can't @@ -1164,6 +1182,8 @@ static int follow_dotdot_rcu(struct nameidata *nd) goto failed; nd->path.dentry = parent; nd->seq = seq; + if (unlikely(!path_connected(&nd->path))) + goto failed; break; } if (!follow_up_rcu(&nd->path)) @@ -1260,7 +1280,7 @@ static void follow_mount(struct path *path) } } -static void follow_dotdot(struct nameidata *nd) +static int follow_dotdot(struct nameidata *nd) { if (!nd->root.mnt) set_root(nd); @@ -1276,6 +1296,10 @@ static void follow_dotdot(struct nameidata *nd) /* rare case of legitimate dget_parent()... */ nd->path.dentry = dget_parent(nd->path.dentry); dput(old); + if (unlikely(!path_connected(&nd->path))) { + path_put(&nd->path); + return -ENOENT; + } break; } if (!follow_up(&nd->path)) @@ -1283,6 +1307,7 @@ static void follow_dotdot(struct nameidata *nd) } follow_mount(&nd->path); nd->inode = nd->path.dentry->d_inode; + return 0; } /* @@ -1503,7 +1528,7 @@ static inline int handle_dots(struct nameidata *nd, int type) if (follow_dotdot_rcu(nd)) return -ECHILD; } else - follow_dotdot(nd); + return follow_dotdot(nd); } return 0; } @@ -2239,7 +2264,7 @@ mountpoint_last(struct nameidata *nd, struct path *path) if (unlikely(nd->last_type != LAST_NORM)) { error = handle_dots(nd, nd->last_type); if (error) - goto out; + return error; dentry = dget(nd->path.dentry); goto done; } @@ -2772,22 +2797,10 @@ no_open: dentry = lookup_real(dir, dentry, nd->flags); if (IS_ERR(dentry)) return PTR_ERR(dentry); - - if (create_error) { - int open_flag = op->open_flag; - - error = create_error; - if ((open_flag & O_EXCL)) { - if (!dentry->d_inode) - goto out; - } else if (!dentry->d_inode) { - goto out; - } else if ((open_flag & O_TRUNC) && - S_ISREG(dentry->d_inode->i_mode)) { - goto out; - } - /* will fail later, go on to get the right error */ - } + } + if (create_error && !dentry->d_inode) { + error = create_error; + goto out; } looked_up: path->dentry = dentry; @@ -3086,6 +3099,10 @@ opened: goto exit_fput; } out: + if (unlikely(error > 0)) { + WARN_ON(1); + error = -EINVAL; + } if (got_write) mnt_drop_write(nd->path.mnt); path_put(&save_parent); diff --git a/fs/namespace.c b/fs/namespace.c index 9f184628105d..5a27e2edbb75 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1494,10 +1494,11 @@ void __detach_mounts(struct dentry *dentry) namespace_lock(); mp = lookup_mountpoint(dentry); - if (!mp) + if (IS_ERR_OR_NULL(mp)) goto out_unlock; lock_mount_hash(); + event++; while (!hlist_empty(&mp->m_list)) { mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list); umount_tree(mnt, 0); @@ -2301,6 +2302,8 @@ unlock: return err; } +static bool fs_fully_visible(struct file_system_type *fs_type, int *new_mnt_flags); + /* * create a new mount for userspace and request it to be added into the * namespace's tree @@ -2332,6 +2335,12 @@ static int do_new_mount(struct path *path, const char *fstype, int flags, flags |= MS_NODEV; mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV; } + if (type->fs_flags & FS_USERNS_VISIBLE) { + if (!fs_fully_visible(type, &mnt_flags)) { + put_filesystem(type); + return -EPERM; + } + } } mnt = vfs_kern_mount(type, flags, name, data); @@ -3129,9 +3138,10 @@ bool current_chrooted(void) return chrooted; } -bool fs_fully_visible(struct file_system_type *type) +static bool fs_fully_visible(struct file_system_type *type, int *new_mnt_flags) { struct mnt_namespace *ns = current->nsproxy->mnt_ns; + int new_flags = *new_mnt_flags; struct mount *mnt; bool visible = false; @@ -3150,16 +3160,37 @@ bool fs_fully_visible(struct file_system_type *type) if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root) continue; - /* This mount is not fully visible if there are any child mounts - * that cover anything except for empty directories. + /* Verify the mount flags are equal to or more permissive + * than the proposed new mount. + */ + if ((mnt->mnt.mnt_flags & MNT_LOCK_READONLY) && + !(new_flags & MNT_READONLY)) + continue; + if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) && + !(new_flags & MNT_NODEV)) + continue; + if ((mnt->mnt.mnt_flags & MNT_LOCK_ATIME) && + ((mnt->mnt.mnt_flags & MNT_ATIME_MASK) != (new_flags & MNT_ATIME_MASK))) + continue; + + /* This mount is not fully visible if there are any + * locked child mounts that cover anything except for + * empty directories. */ list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { struct inode *inode = child->mnt_mountpoint->d_inode; + /* Only worry about locked mounts */ + if (!(child->mnt.mnt_flags & MNT_LOCKED)) + continue; if (!S_ISDIR(inode->i_mode)) goto next; if (inode->i_nlink > 2) goto next; } + /* Preserve the locked attributes */ + *new_mnt_flags |= mnt->mnt.mnt_flags & (MNT_LOCK_READONLY | \ + MNT_LOCK_NODEV | \ + MNT_LOCK_ATIME); visible = true; goto found; next: ; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index f9f4845db989..33a8f50fe738 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -776,7 +776,7 @@ static int nfs_init_server(struct nfs_server *server, server->options = data->options; server->caps |= NFS_CAP_HARDLINKS|NFS_CAP_SYMLINKS|NFS_CAP_FILEID| NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|NFS_CAP_OWNER_GROUP| - NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME|NFS_CAP_CHANGE_ATTR; + NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME; if (data->rsize) server->rsize = nfs_block_size(data->rsize, NULL); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 7a8d67cd823d..29b7a75064af 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1529,9 +1529,9 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, err = PTR_ERR(inode); trace_nfs_atomic_open_exit(dir, ctx, open_flags, err); put_nfs_open_context(ctx); + d_drop(dentry); switch (err) { case -ENOENT: - d_drop(dentry); d_add(dentry, NULL); nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); break; diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 7afb52f6a25a..32879965b255 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -682,23 +682,18 @@ out_put: goto out; } -static void filelayout_free_fh_array(struct nfs4_filelayout_segment *fl) +static void _filelayout_free_lseg(struct nfs4_filelayout_segment *fl) { int i; - for (i = 0; i < fl->num_fh; i++) { - if (!fl->fh_array[i]) - break; - kfree(fl->fh_array[i]); + if (fl->fh_array) { + for (i = 0; i < fl->num_fh; i++) { + if (!fl->fh_array[i]) + break; + kfree(fl->fh_array[i]); + } + kfree(fl->fh_array); } - kfree(fl->fh_array); - fl->fh_array = NULL; -} - -static void -_filelayout_free_lseg(struct nfs4_filelayout_segment *fl) -{ - filelayout_free_fh_array(fl); kfree(fl); } @@ -769,21 +764,21 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo, /* Do we want to use a mempool here? */ fl->fh_array[i] = kmalloc(sizeof(struct nfs_fh), gfp_flags); if (!fl->fh_array[i]) - goto out_err_free; + goto out_err; p = xdr_inline_decode(&stream, 4); if (unlikely(!p)) - goto out_err_free; + goto out_err; fl->fh_array[i]->size = be32_to_cpup(p++); if (sizeof(struct nfs_fh) < fl->fh_array[i]->size) { printk(KERN_ERR "NFS: Too big fh %d received %d\n", i, fl->fh_array[i]->size); - goto out_err_free; + goto out_err; } p = xdr_inline_decode(&stream, fl->fh_array[i]->size); if (unlikely(!p)) - goto out_err_free; + goto out_err; memcpy(fl->fh_array[i]->data, p, fl->fh_array[i]->size); dprintk("DEBUG: %s: fh len %d\n", __func__, fl->fh_array[i]->size); @@ -792,8 +787,6 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo, __free_page(scratch); return 0; -out_err_free: - filelayout_free_fh_array(fl); out_err: __free_page(scratch); return -EIO; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 00689a8a85e4..aa9eadc55834 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -435,7 +435,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); if (fattr->valid & NFS_ATTR_FATTR_CHANGE) inode->i_version = fattr->change_attr; - else if (nfs_server_capable(inode, NFS_CAP_CHANGE_ATTR)) + else nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); if (fattr->valid & NFS_ATTR_FATTR_SIZE) inode->i_size = nfs_size_to_loff_t(fattr->size); @@ -1533,6 +1533,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) unsigned long invalid = 0; unsigned long now = jiffies; unsigned long save_cache_validity; + bool cache_revalidated = true; dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%x)\n", __func__, inode->i_sb->s_id, inode->i_ino, @@ -1595,22 +1596,28 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfs_force_lookup_revalidate(inode); inode->i_version = fattr->change_attr; } - } else if (server->caps & NFS_CAP_CHANGE_ATTR) + } else { nfsi->cache_validity |= save_cache_validity; + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_MTIME) { memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime)); - } else if (server->caps & NFS_CAP_MTIME) + } else if (server->caps & NFS_CAP_MTIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_CTIME) { memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime)); - } else if (server->caps & NFS_CAP_CTIME) + } else if (server->caps & NFS_CAP_CTIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } /* Check if our cached file size is stale */ if (fattr->valid & NFS_ATTR_FATTR_SIZE) { @@ -1631,19 +1638,23 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) (long long)cur_isize, (long long)new_isize); } - } else + } else { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_ATIME) memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime)); - else if (server->caps & NFS_CAP_ATIME) + else if (server->caps & NFS_CAP_ATIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATIME | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_MODE) { if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) { @@ -1652,36 +1663,42 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) inode->i_mode = newmode; invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; } - } else if (server->caps & NFS_CAP_MODE) + } else if (server->caps & NFS_CAP_MODE) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_OWNER) { if (!uid_eq(inode->i_uid, fattr->uid)) { invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; inode->i_uid = fattr->uid; } - } else if (server->caps & NFS_CAP_OWNER) + } else if (server->caps & NFS_CAP_OWNER) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_GROUP) { if (!gid_eq(inode->i_gid, fattr->gid)) { invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; inode->i_gid = fattr->gid; } - } else if (server->caps & NFS_CAP_OWNER_GROUP) + } else if (server->caps & NFS_CAP_OWNER_GROUP) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_NLINK) { if (inode->i_nlink != fattr->nlink) { @@ -1690,19 +1707,22 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) invalid |= NFS_INO_INVALID_DATA; set_nlink(inode, fattr->nlink); } - } else if (server->caps & NFS_CAP_NLINK) + } else if (server->caps & NFS_CAP_NLINK) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { /* * report the blocks in 512byte units */ inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); - } - if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) + } else if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; + else + cache_revalidated = false; /* Update attrtimeo value if we're out of the unstable period */ if (invalid & NFS_INO_INVALID_ATTR) { @@ -1711,13 +1731,21 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfsi->attrtimeo_timestamp = now; nfsi->attr_gencount = nfs_inc_attr_generation_counter(); } else { - if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) { - if ((nfsi->attrtimeo <<= 1) > NFS_MAXATTRTIMEO(inode)) - nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode); + if (cache_revalidated) { + if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, + nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) { + nfsi->attrtimeo <<= 1; + if (nfsi->attrtimeo > NFS_MAXATTRTIMEO(inode)) + nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode); + } nfsi->attrtimeo_timestamp = now; } } - invalid &= ~NFS_INO_INVALID_ATTR; + + /* Don't declare attrcache up to date if there were no attrs! */ + if (cache_revalidated) + invalid &= ~NFS_INO_INVALID_ATTR; + /* Don't invalidate the data if we were to blame */ if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 8f4cbe7f4aa8..53853ca134e5 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -1342,7 +1342,7 @@ static void nfs3_xdr_enc_setacl3args(struct rpc_rqst *req, if (args->npages != 0) xdr_write_pages(xdr, args->pages, 0, args->len); else - xdr_reserve_space(xdr, NFS_ACL_INLINE_BUFSIZE); + xdr_reserve_space(xdr, args->len); error = nfsacl_encode(xdr->buf, base, args->inode, (args->mask & NFS_ACL) ? diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 368a6b72290c..0e11fe80e5b9 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -33,7 +33,7 @@ static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion) return ret; idr_preload(GFP_KERNEL); spin_lock(&nn->nfs_client_lock); - ret = idr_alloc(&nn->cb_ident_idr, clp, 0, 0, GFP_NOWAIT); + ret = idr_alloc(&nn->cb_ident_idr, clp, 1, 0, GFP_NOWAIT); if (ret >= 0) clp->cl_cb_ident = ret; spin_unlock(&nn->nfs_client_lock); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index cd617076aeca..43fb57831567 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -38,6 +38,7 @@ #include <linux/mm.h> #include <linux/delay.h> #include <linux/errno.h> +#include <linux/file.h> #include <linux/string.h> #include <linux/ratelimit.h> #include <linux/printk.h> @@ -1230,6 +1231,7 @@ static void __update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_s * Protect the call to nfs4_state_set_mode_locked and * serialise the stateid update */ + spin_lock(&state->owner->so_lock); write_seqlock(&state->seqlock); if (deleg_stateid != NULL) { nfs4_stateid_copy(&state->stateid, deleg_stateid); @@ -1238,7 +1240,6 @@ static void __update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_s if (open_stateid != NULL) nfs_set_open_stateid_locked(state, open_stateid, fmode); write_sequnlock(&state->seqlock); - spin_lock(&state->owner->so_lock); update_open_stateflags(state, fmode); spin_unlock(&state->owner->so_lock); } @@ -2257,9 +2258,9 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, dentry = d_add_unique(dentry, igrab(state->inode)); if (dentry == NULL) { dentry = opendata->dentry; - } else if (dentry != ctx->dentry) { + } else { dput(ctx->dentry); - ctx->dentry = dget(dentry); + ctx->dentry = dentry; } nfs_set_verifier(dentry, nfs_save_change_attribute(opendata->dir->d_inode)); @@ -2345,7 +2346,7 @@ static int _nfs4_do_open(struct inode *dir, goto err_free_label; state = ctx->state; - if ((opendata->o_arg.open_flags & O_EXCL) && + if ((opendata->o_arg.open_flags & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL) && (opendata->o_arg.createmode != NFS4_CREATE_GUARDED)) { nfs4_exclusive_attrset(opendata, sattr); @@ -2634,12 +2635,11 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) call_close |= is_wronly; else if (is_wronly) calldata->arg.fmode |= FMODE_WRITE; + if (calldata->arg.fmode != (FMODE_READ|FMODE_WRITE)) + call_close |= is_rdwr; } else if (is_rdwr) calldata->arg.fmode |= FMODE_READ|FMODE_WRITE; - if (calldata->arg.fmode == 0) - call_close |= is_rdwr; - if (!nfs4_valid_open_stateid(state)) call_close = 0; spin_unlock(&state->owner->so_lock); @@ -5550,6 +5550,7 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl, p->server = server; atomic_inc(&lsp->ls_count); p->ctx = get_nfs_open_context(ctx); + get_file(fl->fl_file); memcpy(&p->fl, fl, sizeof(p->fl)); return p; out_free_seqid: @@ -5639,6 +5640,7 @@ static void nfs4_lock_release(void *calldata) nfs_free_seqid(data->arg.lock_seqid); nfs4_put_lock_state(data->lsp); put_nfs_open_context(data->ctx); + fput(data->fl.fl_file); kfree(data); dprintk("%s: done!\n", __func__); } @@ -8385,7 +8387,6 @@ static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = { .minor_version = 0, .init_caps = NFS_CAP_READDIRPLUS | NFS_CAP_ATOMIC_OPEN - | NFS_CAP_CHANGE_ATTR | NFS_CAP_POSIX_LOCK, .init_client = nfs40_init_client, .shutdown_client = nfs40_shutdown_client, @@ -8404,7 +8405,6 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = { .minor_version = 1, .init_caps = NFS_CAP_READDIRPLUS | NFS_CAP_ATOMIC_OPEN - | NFS_CAP_CHANGE_ATTR | NFS_CAP_POSIX_LOCK | NFS_CAP_STATEID_NFSV41 | NFS_CAP_ATOMIC_OPEN_V1, @@ -8426,7 +8426,6 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = { .minor_version = 2, .init_caps = NFS_CAP_READDIRPLUS | NFS_CAP_ATOMIC_OPEN - | NFS_CAP_CHANGE_ATTR | NFS_CAP_POSIX_LOCK | NFS_CAP_STATEID_NFSV41 | NFS_CAP_ATOMIC_OPEN_V1 @@ -8440,6 +8439,7 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = { .reboot_recovery_ops = &nfs41_reboot_recovery_ops, .nograce_recovery_ops = &nfs41_nograce_recovery_ops, .state_renewal_ops = &nfs41_state_renewal_ops, + .mig_recovery_ops = &nfs41_mig_recovery_ops, }; #endif diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 5194933ed419..1f9d57ab8df4 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1455,6 +1455,8 @@ restart: spin_unlock(&state->state_lock); } nfs4_put_open_state(state); + clear_bit(NFS4CLNT_RECLAIM_NOGRACE, + &state->flags); spin_lock(&sp->so_lock); goto restart; } diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index ed0db61f8543..54631609d601 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -63,8 +63,8 @@ EXPORT_SYMBOL_GPL(nfs_pgheader_init); void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos) { spin_lock(&hdr->lock); - if (pos < hdr->io_start + hdr->good_bytes) { - set_bit(NFS_IOHDR_ERROR, &hdr->flags); + if (!test_and_set_bit(NFS_IOHDR_ERROR, &hdr->flags) + || pos < hdr->io_start + hdr->good_bytes) { clear_bit(NFS_IOHDR_EOF, &hdr->flags); hdr->good_bytes = pos - hdr->io_start; hdr->error = error; @@ -486,7 +486,7 @@ size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, * for it without upsetting the slab allocator. */ if (((desc->pg_count + req->wb_bytes) >> PAGE_SHIFT) * - sizeof(struct page) > PAGE_SIZE) + sizeof(struct page *) > PAGE_SIZE) return 0; return min(desc->pg_bsize - desc->pg_count, (size_t)req->wb_bytes); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 883ee88e5f5e..354f66609316 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1535,6 +1535,7 @@ int pnfs_write_done_resend_to_mds(struct nfs_pgio_header *hdr) /* Resend all requests through the MDS */ nfs_pageio_init_write(&pgio, hdr->inode, FLUSH_STABLE, true, hdr->completion_ops); + set_bit(NFS_CONTEXT_RESEND_WRITES, &hdr->args.context->flags); return nfs_pageio_resend(&pgio, hdr); } EXPORT_SYMBOL_GPL(pnfs_write_done_resend_to_mds); @@ -1576,6 +1577,7 @@ pnfs_write_through_mds(struct nfs_pageio_descriptor *desc, desc->pg_recoalesce = 1; } nfs_pgio_data_destroy(hdr); + hdr->release(hdr); } static enum pnfs_try_status @@ -1692,6 +1694,7 @@ pnfs_read_through_mds(struct nfs_pageio_descriptor *desc, desc->pg_recoalesce = 1; } nfs_pgio_data_destroy(hdr); + hdr->release(hdr); } /* diff --git a/fs/nfs/write.c b/fs/nfs/write.c index f83b02dc9166..6067f2a0b493 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1252,6 +1252,7 @@ static void nfs_initiate_write(struct nfs_pgio_header *hdr, static void nfs_redirty_request(struct nfs_page *req) { nfs_mark_request_dirty(req); + set_bit(NFS_CONTEXT_RESEND_WRITES, &req->wb_context->flags); nfs_unlock_request(req); nfs_end_page_writeback(req); nfs_release_request(req); diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 7cbdf1b2e4ab..9701a76f562e 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -630,22 +630,6 @@ static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc } } -static struct rpc_clnt *create_backchannel_client(struct rpc_create_args *args) -{ - struct rpc_xprt *xprt; - - if (args->protocol != XPRT_TRANSPORT_BC_TCP) - return rpc_create(args); - - xprt = args->bc_xprt->xpt_bc_xprt; - if (xprt) { - xprt_get(xprt); - return rpc_create_xprt(args, xprt); - } - - return rpc_create(args); -} - static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn, struct nfsd4_session *ses) { int maxtime = max_cb_time(clp->net); @@ -688,7 +672,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c args.authflavor = ses->se_cb_sec.flavor; } /* Create RPC client */ - client = create_backchannel_client(&args); + client = rpc_create(&args); if (IS_ERR(client)) { dprintk("NFSD: couldn't create callback client: %ld\n", PTR_ERR(client)); diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 6ed585935d5e..606d5aa33d76 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -878,6 +878,7 @@ nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, &exp, &dentry); if (err) return err; + fh_unlock(&cstate->current_fh); if (dentry->d_inode == NULL) { exp_put(exp); err = nfserr_noent; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 58f98ad93828..b6c3a8792358 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -3241,6 +3241,7 @@ static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, stp->st_access_bmap = 0; stp->st_deny_bmap = 0; stp->st_openstp = NULL; + init_rwsem(&stp->st_rwsem); spin_lock(&oo->oo_owner.so_client->cl_lock); list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids); spin_lock(&fp->fi_lock); @@ -4057,21 +4058,27 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf */ if (stp) { /* Stateid was found, this is an OPEN upgrade */ + down_read(&stp->st_rwsem); status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open); - if (status) + if (status) { + up_read(&stp->st_rwsem); goto out; + } } else { stp = open->op_stp; open->op_stp = NULL; init_open_stateid(stp, fp, open); + down_read(&stp->st_rwsem); status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open); if (status) { + up_read(&stp->st_rwsem); release_open_stateid(stp); goto out; } } update_stateid(&stp->st_stid.sc_stateid); memcpy(&open->op_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); + up_read(&stp->st_rwsem); if (nfsd4_has_session(&resp->cstate)) { if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) { @@ -4285,9 +4292,9 @@ laundromat_main(struct work_struct *laundry) queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ); } -static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_ol_stateid *stp) +static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp) { - if (!nfsd_fh_match(&fhp->fh_handle, &stp->st_stid.sc_file->fi_fhandle)) + if (!nfsd_fh_match(&fhp->fh_handle, &stp->sc_file->fi_fhandle)) return nfserr_bad_stateid; return nfs_ok; } @@ -4462,20 +4469,49 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, return nfs_ok; } +static struct file * +nfs4_find_file(struct nfs4_stid *s, int flags) +{ + switch (s->sc_type) { + case NFS4_DELEG_STID: + if (WARN_ON_ONCE(!s->sc_file->fi_deleg_file)) + return NULL; + return get_file(s->sc_file->fi_deleg_file); + case NFS4_OPEN_STID: + case NFS4_LOCK_STID: + if (flags & RD_STATE) + return find_readable_file(s->sc_file); + else + return find_writeable_file(s->sc_file); + break; + } + + return NULL; +} + +static __be32 +nfs4_check_olstateid(struct svc_fh *fhp, struct nfs4_ol_stateid *ols, int flags) +{ + __be32 status; + + status = nfsd4_check_openowner_confirmed(ols); + if (status) + return status; + return nfs4_check_openmode(ols, flags); +} + /* -* Checks for stateid operations -*/ + * Checks for stateid operations + */ __be32 nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate, stateid_t *stateid, int flags, struct file **filpp) { - struct nfs4_stid *s; - struct nfs4_ol_stateid *stp = NULL; - struct nfs4_delegation *dp = NULL; - struct svc_fh *current_fh = &cstate->current_fh; - struct inode *ino = current_fh->fh_dentry->d_inode; + struct svc_fh *fhp = &cstate->current_fh; + struct inode *ino = fhp->fh_dentry->d_inode; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); - struct file *file = NULL; + struct nfs4_stid *s; __be32 status; if (filpp) @@ -4485,60 +4521,39 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate, return nfserr_grace; if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) - return check_special_stateids(net, current_fh, stateid, flags); + return check_special_stateids(net, fhp, stateid, flags); status = nfsd4_lookup_stateid(cstate, stateid, NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID, &s, nn); if (status) return status; - status = check_stateid_generation(stateid, &s->sc_stateid, nfsd4_has_session(cstate)); + status = check_stateid_generation(stateid, &s->sc_stateid, + nfsd4_has_session(cstate)); if (status) goto out; + switch (s->sc_type) { case NFS4_DELEG_STID: - dp = delegstateid(s); - status = nfs4_check_delegmode(dp, flags); - if (status) - goto out; - if (filpp) { - file = dp->dl_stid.sc_file->fi_deleg_file; - if (!file) { - WARN_ON_ONCE(1); - status = nfserr_serverfault; - goto out; - } - get_file(file); - } + status = nfs4_check_delegmode(delegstateid(s), flags); break; case NFS4_OPEN_STID: case NFS4_LOCK_STID: - stp = openlockstateid(s); - status = nfs4_check_fh(current_fh, stp); - if (status) - goto out; - status = nfsd4_check_openowner_confirmed(stp); - if (status) - goto out; - status = nfs4_check_openmode(stp, flags); - if (status) - goto out; - if (filpp) { - struct nfs4_file *fp = stp->st_stid.sc_file; - - if (flags & RD_STATE) - file = find_readable_file(fp); - else - file = find_writeable_file(fp); - } + status = nfs4_check_olstateid(fhp, openlockstateid(s), flags); break; default: status = nfserr_bad_stateid; + break; + } + if (status) goto out; + status = nfs4_check_fh(fhp, s); + + if (!status && filpp) { + *filpp = nfs4_find_file(s, flags); + if (!*filpp) + status = nfserr_serverfault; } - status = nfs_ok; - if (file) - *filpp = file; out: nfs4_put_stid(s); return status; @@ -4639,10 +4654,13 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_ * revoked delegations are kept only for free_stateid. */ return nfserr_bad_stateid; + down_write(&stp->st_rwsem); status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate)); - if (status) - return status; - return nfs4_check_fh(current_fh, stp); + if (status == nfs_ok) + status = nfs4_check_fh(current_fh, &stp->st_stid); + if (status != nfs_ok) + up_write(&stp->st_rwsem); + return status; } /* @@ -4689,6 +4707,7 @@ static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cs return status; oo = openowner(stp->st_stateowner); if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) { + up_write(&stp->st_rwsem); nfs4_put_stid(&stp->st_stid); return nfserr_bad_stateid; } @@ -4719,11 +4738,14 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; oo = openowner(stp->st_stateowner); status = nfserr_bad_stateid; - if (oo->oo_flags & NFS4_OO_CONFIRMED) + if (oo->oo_flags & NFS4_OO_CONFIRMED) { + up_write(&stp->st_rwsem); goto put_stateid; + } oo->oo_flags |= NFS4_OO_CONFIRMED; update_stateid(&stp->st_stid.sc_stateid); memcpy(&oc->oc_resp_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); + up_write(&stp->st_rwsem); dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n", __func__, oc->oc_seqid, STATEID_VAL(&stp->st_stid.sc_stateid)); @@ -4802,6 +4824,7 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp, memcpy(&od->od_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); status = nfs_ok; put_stateid: + up_write(&stp->st_rwsem); nfs4_put_stid(&stp->st_stid); out: nfsd4_bump_seqid(cstate, status); @@ -4852,6 +4875,7 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; update_stateid(&stp->st_stid.sc_stateid); memcpy(&close->cl_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); + up_write(&stp->st_rwsem); nfsd4_close_open_stateid(stp); @@ -5080,6 +5104,7 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo, stp->st_access_bmap = 0; stp->st_deny_bmap = open_stp->st_deny_bmap; stp->st_openstp = open_stp; + init_rwsem(&stp->st_rwsem); list_add(&stp->st_locks, &open_stp->st_locks); list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids); spin_lock(&fp->fi_lock); @@ -5248,6 +5273,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, &open_stp, nn); if (status) goto out; + up_write(&open_stp->st_rwsem); open_sop = openowner(open_stp->st_stateowner); status = nfserr_bad_stateid; if (!same_clid(&open_sop->oo_owner.so_client->cl_clientid, @@ -5255,6 +5281,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; status = lookup_or_create_lock_state(cstate, open_stp, lock, &lock_stp, &new); + if (status == nfs_ok) + down_write(&lock_stp->st_rwsem); } else { status = nfs4_preprocess_seqid_op(cstate, lock->lk_old_lock_seqid, @@ -5360,6 +5388,8 @@ out: seqid_mutating_err(ntohl(status))) lock_sop->lo_owner.so_seqid++; + up_write(&lock_stp->st_rwsem); + /* * If this is a new, never-before-used stateid, and we are * returning an error, then just go ahead and release it. @@ -5530,6 +5560,7 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, fput: fput(filp); put_stateid: + up_write(&stp->st_rwsem); nfs4_put_stid(&stp->st_stid); out: nfsd4_bump_seqid(cstate, status); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 6abe96593225..dc7fd83409da 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1061,8 +1061,9 @@ nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename READ_BUF(4); rename->rn_snamelen = be32_to_cpup(p++); - READ_BUF(rename->rn_snamelen + 4); + READ_BUF(rename->rn_snamelen); SAVEMEM(rename->rn_sname, rename->rn_snamelen); + READ_BUF(4); rename->rn_tnamelen = be32_to_cpup(p++); READ_BUF(rename->rn_tnamelen); SAVEMEM(rename->rn_tname, rename->rn_tnamelen); @@ -1144,13 +1145,14 @@ nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclient READ_BUF(8); setclientid->se_callback_prog = be32_to_cpup(p++); setclientid->se_callback_netid_len = be32_to_cpup(p++); - - READ_BUF(setclientid->se_callback_netid_len + 4); + READ_BUF(setclientid->se_callback_netid_len); SAVEMEM(setclientid->se_callback_netid_val, setclientid->se_callback_netid_len); + READ_BUF(4); setclientid->se_callback_addr_len = be32_to_cpup(p++); - READ_BUF(setclientid->se_callback_addr_len + 4); + READ_BUF(setclientid->se_callback_addr_len); SAVEMEM(setclientid->se_callback_addr_val, setclientid->se_callback_addr_len); + READ_BUF(4); setclientid->se_callback_ident = be32_to_cpup(p++); DECODE_TAIL; @@ -1646,8 +1648,9 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) READ_BUF(4); argp->taglen = be32_to_cpup(p++); - READ_BUF(argp->taglen + 8); + READ_BUF(argp->taglen); SAVEMEM(argp->tag, argp->taglen); + READ_BUF(8); argp->minorversion = be32_to_cpup(p++); argp->opcnt = be32_to_cpup(p++); max_reply += 4 + (XDR_QUADLEN(argp->taglen) << 2); @@ -1974,6 +1977,7 @@ nfsd4_encode_aclname(struct xdr_stream *xdr, struct svc_rqst *rqstp, #define WORD0_ABSENT_FS_ATTRS (FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_FSID | \ FATTR4_WORD0_RDATTR_ERROR) #define WORD1_ABSENT_FS_ATTRS FATTR4_WORD1_MOUNTED_ON_FILEID +#define WORD2_ABSENT_FS_ATTRS 0 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL static inline __be32 @@ -2002,7 +2006,7 @@ nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp, { return 0; } #endif -static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *rdattr_err) +static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *bmval2, u32 *rdattr_err) { /* As per referral draft: */ if (*bmval0 & ~WORD0_ABSENT_FS_ATTRS || @@ -2015,6 +2019,7 @@ static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *rdattr_err) } *bmval0 &= WORD0_ABSENT_FS_ATTRS; *bmval1 &= WORD1_ABSENT_FS_ATTRS; + *bmval2 &= WORD2_ABSENT_FS_ATTRS; return 0; } @@ -2078,8 +2083,7 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, BUG_ON(bmval2 & ~nfsd_suppattrs2(minorversion)); if (exp->ex_fslocs.migrated) { - BUG_ON(bmval[2]); - status = fattr_handle_absent_fs(&bmval0, &bmval1, &rdattr_err); + status = fattr_handle_absent_fs(&bmval0, &bmval1, &bmval2, &rdattr_err); if (status) goto out; } @@ -2122,8 +2126,8 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, } #ifdef CONFIG_NFSD_V4_SECURITY_LABEL - if ((bmval[2] & FATTR4_WORD2_SECURITY_LABEL) || - bmval[0] & FATTR4_WORD0_SUPPORTED_ATTRS) { + if ((bmval2 & FATTR4_WORD2_SECURITY_LABEL) || + bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) { err = security_inode_getsecctx(dentry->d_inode, &context, &contextlen); contextsupport = (err == 0); diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 2712042a66b1..3ccb1046a2f9 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -506,14 +506,15 @@ struct nfs4_file { * Better suggestions welcome. */ struct nfs4_ol_stateid { - struct nfs4_stid st_stid; /* must be first field */ - struct list_head st_perfile; - struct list_head st_perstateowner; - struct list_head st_locks; - struct nfs4_stateowner * st_stateowner; - unsigned char st_access_bmap; - unsigned char st_deny_bmap; - struct nfs4_ol_stateid * st_openstp; + struct nfs4_stid st_stid; + struct list_head st_perfile; + struct list_head st_perstateowner; + struct list_head st_locks; + struct nfs4_stateowner *st_stateowner; + unsigned char st_access_bmap; + unsigned char st_deny_bmap; + struct nfs4_ol_stateid *st_openstp; + struct rw_semaphore st_rwsem; }; static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s) diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 9da25fe9ea61..ed3a2d9ec5f7 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -443,7 +443,7 @@ static int nilfs_valid_sb(struct nilfs_super_block *sbp) if (!sbp || le16_to_cpu(sbp->s_magic) != NILFS_SUPER_MAGIC) return 0; bytes = le16_to_cpu(sbp->s_bytes); - if (bytes > BLOCK_SIZE) + if (bytes < sumoff + 4 || bytes > BLOCK_SIZE) return 0; crc = crc32_le(le32_to_cpu(sbp->s_crc_seed), (unsigned char *)sbp, sumoff); diff --git a/fs/notify/mark.c b/fs/notify/mark.c index 34c38fabf514..28c90a6fcd6c 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -329,16 +329,36 @@ void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group, unsigned int flags) { struct fsnotify_mark *lmark, *mark; + LIST_HEAD(to_free); + /* + * We have to be really careful here. Anytime we drop mark_mutex, e.g. + * fsnotify_clear_marks_by_inode() can come and free marks. Even in our + * to_free list so we have to use mark_mutex even when accessing that + * list. And freeing mark requires us to drop mark_mutex. So we can + * reliably free only the first mark in the list. That's why we first + * move marks to free to to_free list in one go and then free marks in + * to_free list one by one. + */ mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING); list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) { - if (mark->flags & flags) { - fsnotify_get_mark(mark); - fsnotify_destroy_mark_locked(mark, group); - fsnotify_put_mark(mark); - } + if (mark->flags & flags) + list_move(&mark->g_list, &to_free); } mutex_unlock(&group->mark_mutex); + + while (1) { + mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING); + if (list_empty(&to_free)) { + mutex_unlock(&group->mark_mutex); + break; + } + mark = list_first_entry(&to_free, struct fsnotify_mark, g_list); + fsnotify_get_mark(mark); + fsnotify_destroy_mark_locked(mark, group); + mutex_unlock(&group->mark_mutex); + fsnotify_put_mark(mark); + } } /* diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 7e8282dcea2a..8a7d2f812b5b 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -310,3 +310,90 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type) return acl; } + +int ocfs2_acl_chmod(struct inode *inode, struct buffer_head *bh) +{ + struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); + struct posix_acl *acl; + int ret; + + if (S_ISLNK(inode->i_mode)) + return -EOPNOTSUPP; + + if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL)) + return 0; + + acl = ocfs2_get_acl_nolock(inode, ACL_TYPE_ACCESS, bh); + if (IS_ERR(acl) || !acl) + return PTR_ERR(acl); + ret = __posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode); + if (ret) + return ret; + ret = ocfs2_set_acl(NULL, inode, NULL, ACL_TYPE_ACCESS, + acl, NULL, NULL); + posix_acl_release(acl); + return ret; +} + +/* + * Initialize the ACLs of a new inode. If parent directory has default ACL, + * then clone to new inode. Called from ocfs2_mknod. + */ +int ocfs2_init_acl(handle_t *handle, + struct inode *inode, + struct inode *dir, + struct buffer_head *di_bh, + struct buffer_head *dir_bh, + struct ocfs2_alloc_context *meta_ac, + struct ocfs2_alloc_context *data_ac) +{ + struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); + struct posix_acl *acl = NULL; + int ret = 0, ret2; + umode_t mode; + + if (!S_ISLNK(inode->i_mode)) { + if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) { + acl = ocfs2_get_acl_nolock(dir, ACL_TYPE_DEFAULT, + dir_bh); + if (IS_ERR(acl)) + return PTR_ERR(acl); + } + if (!acl) { + mode = inode->i_mode & ~current_umask(); + ret = ocfs2_acl_set_mode(inode, di_bh, handle, mode); + if (ret) { + mlog_errno(ret); + goto cleanup; + } + } + } + if ((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) && acl) { + if (S_ISDIR(inode->i_mode)) { + ret = ocfs2_set_acl(handle, inode, di_bh, + ACL_TYPE_DEFAULT, acl, + meta_ac, data_ac); + if (ret) + goto cleanup; + } + mode = inode->i_mode; + ret = __posix_acl_create(&acl, GFP_NOFS, &mode); + if (ret < 0) + return ret; + + ret2 = ocfs2_acl_set_mode(inode, di_bh, handle, mode); + if (ret2) { + mlog_errno(ret2); + ret = ret2; + goto cleanup; + } + if (ret > 0) { + ret = ocfs2_set_acl(handle, inode, + di_bh, ACL_TYPE_ACCESS, + acl, meta_ac, data_ac); + } + } +cleanup: + posix_acl_release(acl); + return ret; +} diff --git a/fs/ocfs2/acl.h b/fs/ocfs2/acl.h index 3fce68d08625..2783a75b3999 100644 --- a/fs/ocfs2/acl.h +++ b/fs/ocfs2/acl.h @@ -35,5 +35,10 @@ int ocfs2_set_acl(handle_t *handle, struct posix_acl *acl, struct ocfs2_alloc_context *meta_ac, struct ocfs2_alloc_context *data_ac); +extern int ocfs2_acl_chmod(struct inode *, struct buffer_head *); +extern int ocfs2_init_acl(handle_t *, struct inode *, struct inode *, + struct buffer_head *, struct buffer_head *, + struct ocfs2_alloc_context *, + struct ocfs2_alloc_context *); #endif /* OCFS2_ACL_H */ diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c index e36d63ff1783..f90931335c6b 100644 --- a/fs/ocfs2/dlm/dlmconvert.c +++ b/fs/ocfs2/dlm/dlmconvert.c @@ -262,6 +262,7 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm, struct dlm_lock *lock, int flags, int type) { enum dlm_status status; + u8 old_owner = res->owner; mlog(0, "type=%d, convert_type=%d, busy=%d\n", lock->ml.type, lock->ml.convert_type, res->state & DLM_LOCK_RES_IN_PROGRESS); @@ -287,6 +288,19 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm, status = DLM_DENIED; goto bail; } + + if (lock->ml.type == type && lock->ml.convert_type == LKM_IVMODE) { + mlog(0, "last convert request returned DLM_RECOVERING, but " + "owner has already queued and sent ast to me. res %.*s, " + "(cookie=%u:%llu, type=%d, conv=%d)\n", + res->lockname.len, res->lockname.name, + dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)), + dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)), + lock->ml.type, lock->ml.convert_type); + status = DLM_NORMAL; + goto bail; + } + res->state |= DLM_LOCK_RES_IN_PROGRESS; /* move lock to local convert queue */ /* do not alter lock refcount. switching lists. */ @@ -316,11 +330,19 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm, spin_lock(&res->spinlock); res->state &= ~DLM_LOCK_RES_IN_PROGRESS; lock->convert_pending = 0; - /* if it failed, move it back to granted queue */ + /* if it failed, move it back to granted queue. + * if master returns DLM_NORMAL and then down before sending ast, + * it may have already been moved to granted queue, reset to + * DLM_RECOVERING and retry convert */ if (status != DLM_NORMAL) { if (status != DLM_NOTQUEUED) dlm_error(status); dlm_revert_pending_convert(res, lock); + } else if ((res->state & DLM_LOCK_RES_RECOVERING) || + (old_owner != res->owner)) { + mlog(0, "res %.*s is in recovering or has been recovered.\n", + res->lockname.len, res->lockname.name); + status = DLM_RECOVERING; } bail: spin_unlock(&res->spinlock); diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 9ec1eea7c3a3..d14b28e832a7 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -1447,6 +1447,7 @@ int dlm_master_request_handler(struct o2net_msg *msg, u32 len, void *data, int found, ret; int set_maybe; int dispatch_assert = 0; + int dispatched = 0; if (!dlm_grab(dlm)) return DLM_MASTER_RESP_NO; @@ -1653,14 +1654,17 @@ send_response: mlog(ML_ERROR, "failed to dispatch assert master work\n"); response = DLM_MASTER_RESP_ERROR; dlm_lockres_put(res); - } else + } else { + dispatched = 1; dlm_lockres_grab_inflight_worker(dlm, res); + } } else { if (res) dlm_lockres_put(res); } - dlm_put(dlm); + if (!dispatched) + dlm_put(dlm); return response; } @@ -2084,7 +2088,6 @@ int dlm_dispatch_assert_master(struct dlm_ctxt *dlm, /* queue up work for dlm_assert_master_worker */ - dlm_grab(dlm); /* get an extra ref for the work item */ dlm_init_work_item(dlm, item, dlm_assert_master_worker, NULL); item->u.am.lockres = res; /* already have a ref */ /* can optionally ignore node numbers higher than this node */ @@ -2509,6 +2512,11 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm, spin_lock(&dlm->master_lock); ret = dlm_add_migration_mle(dlm, res, mle, &oldmle, name, namelen, target, dlm->node_num); + /* get an extra reference on the mle. + * otherwise the assert_master from the new + * master will destroy this. + */ + dlm_get_mle_inuse(mle); spin_unlock(&dlm->master_lock); spin_unlock(&dlm->spinlock); @@ -2544,6 +2552,7 @@ fail: if (mle_added) { dlm_mle_detach_hb_events(dlm, mle); dlm_put_mle(mle); + dlm_put_mle_inuse(mle); } else if (mle) { kmem_cache_free(dlm_mle_cache, mle); mle = NULL; @@ -2561,17 +2570,6 @@ fail: * ensure that all assert_master work is flushed. */ flush_workqueue(dlm->dlm_worker); - /* get an extra reference on the mle. - * otherwise the assert_master from the new - * master will destroy this. - * also, make sure that all callers of dlm_get_mle - * take both dlm->spinlock and dlm->master_lock */ - spin_lock(&dlm->spinlock); - spin_lock(&dlm->master_lock); - dlm_get_mle_inuse(mle); - spin_unlock(&dlm->master_lock); - spin_unlock(&dlm->spinlock); - /* notify new node and send all lock state */ /* call send_one_lockres with migration flag. * this serves as notice to the target node that a @@ -3300,6 +3298,15 @@ top: mle->new_master != dead_node) continue; + if (mle->new_master == dead_node && mle->inuse) { + mlog(ML_NOTICE, "%s: target %u died during " + "migration from %u, the MLE is " + "still keep used, ignore it!\n", + dlm->name, dead_node, + mle->master); + continue; + } + /* If we have reached this point, this mle needs to be * removed from the list and freed. */ dlm_clean_migration_mle(dlm, mle); diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 3365839d2971..3a78afb14b16 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -1687,6 +1687,7 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data, unsigned int hash; int master = DLM_LOCK_RES_OWNER_UNKNOWN; u32 flags = DLM_ASSERT_MASTER_REQUERY; + int dispatched = 0; if (!dlm_grab(dlm)) { /* since the domain has gone away on this @@ -1708,8 +1709,10 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data, mlog_errno(-ENOMEM); /* retry!? */ BUG(); - } else + } else { + dispatched = 1; __dlm_lockres_grab_inflight_worker(dlm, res); + } spin_unlock(&res->spinlock); } else { /* put.. incase we are not the master */ @@ -1719,7 +1722,8 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data, } spin_unlock(&dlm->spinlock); - dlm_put(dlm); + if (!dispatched) + dlm_put(dlm); return master; } @@ -2052,7 +2056,6 @@ void dlm_move_lockres_to_recovery_list(struct dlm_ctxt *dlm, dlm_lock_get(lock); if (lock->convert_pending) { /* move converting lock back to granted */ - BUG_ON(i != DLM_CONVERTING_LIST); mlog(0, "node died with convert pending " "on %.*s. move back to granted list.\n", res->lockname.len, res->lockname.name); @@ -2344,6 +2347,8 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node) break; } } + dlm_lockres_clear_refmap_bit(dlm, res, + dead_node); spin_unlock(&res->spinlock); continue; } diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 21262f2b1654..12fe56b2e870 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -1373,6 +1373,7 @@ static int __ocfs2_cluster_lock(struct ocfs2_super *osb, unsigned long flags; unsigned int gen; int noqueue_attempted = 0; + int kick_dc = 0; ocfs2_init_mask_waiter(&mw); @@ -1501,7 +1502,12 @@ update_holders: unlock: lockres_clear_flags(lockres, OCFS2_LOCK_UPCONVERT_FINISHING); + /* ocfs2_unblock_lock reques on seeing OCFS2_LOCK_UPCONVERT_FINISHING */ + kick_dc = (lockres->l_flags & OCFS2_LOCK_BLOCKED); + spin_unlock_irqrestore(&lockres->l_lock, flags); + if (kick_dc) + ocfs2_wake_downconvert_thread(osb); out: /* * This is helping work around a lock inversion between the page lock @@ -3993,9 +3999,13 @@ static void ocfs2_downconvert_thread_do_work(struct ocfs2_super *osb) osb->dc_work_sequence = osb->dc_wake_sequence; processed = osb->blocked_lock_count; - while (processed) { - BUG_ON(list_empty(&osb->blocked_lock_list)); - + /* + * blocked lock processing in this loop might call iput which can + * remove items off osb->blocked_lock_list. Downconvert up to + * 'processed' number of locks, but stop short if we had some + * removed in ocfs2_mark_lockres_freeing when downconverting. + */ + while (processed && !list_empty(&osb->blocked_lock_list)) { lockres = list_entry(osb->blocked_lock_list.next, struct ocfs2_lock_res, l_blocked_list); list_del_init(&lockres->l_blocked_list); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index e6e8d6449b47..9d5adfd6b326 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1249,18 +1249,18 @@ bail_unlock_rw: if (size_change) ocfs2_rw_unlock(inode, 1); bail: - brelse(bh); /* Release quota pointers in case we acquired them */ for (qtype = 0; qtype < OCFS2_MAXQUOTAS; qtype++) dqput(transfer_to[qtype]); if (!status && attr->ia_valid & ATTR_MODE) { - status = posix_acl_chmod(inode, inode->i_mode); + status = ocfs2_acl_chmod(inode, bh); if (status < 0) mlog_errno(status); } + brelse(bh); return status; } diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 914c121ec890..8f7f5de38e91 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -253,7 +253,6 @@ static int ocfs2_mknod(struct inode *dir, struct ocfs2_dir_lookup_result lookup = { NULL, }; sigset_t oldset; int did_block_signals = 0; - struct posix_acl *default_acl = NULL, *acl = NULL; struct ocfs2_dentry_lock *dl = NULL; trace_ocfs2_mknod(dir, dentry, dentry->d_name.len, dentry->d_name.name, @@ -356,12 +355,6 @@ static int ocfs2_mknod(struct inode *dir, goto leave; } - status = posix_acl_create(dir, &mode, &default_acl, &acl); - if (status) { - mlog_errno(status); - goto leave; - } - handle = ocfs2_start_trans(osb, ocfs2_mknod_credits(osb->sb, S_ISDIR(mode), xattr_credits)); @@ -410,16 +403,8 @@ static int ocfs2_mknod(struct inode *dir, inc_nlink(dir); } - if (default_acl) { - status = ocfs2_set_acl(handle, inode, new_fe_bh, - ACL_TYPE_DEFAULT, default_acl, - meta_ac, data_ac); - } - if (!status && acl) { - status = ocfs2_set_acl(handle, inode, new_fe_bh, - ACL_TYPE_ACCESS, acl, - meta_ac, data_ac); - } + status = ocfs2_init_acl(handle, inode, dir, new_fe_bh, parent_fe_bh, + meta_ac, data_ac); if (status < 0) { mlog_errno(status); @@ -461,10 +446,6 @@ static int ocfs2_mknod(struct inode *dir, d_instantiate(dentry, inode); status = 0; leave: - if (default_acl) - posix_acl_release(default_acl); - if (acl) - posix_acl_release(acl); if (status < 0 && did_quota_inode) dquot_free_inode(inode); if (handle) diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index d81f6e2a97f5..18e8b4d8447a 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4268,20 +4268,12 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir, struct inode *inode = old_dentry->d_inode; struct buffer_head *old_bh = NULL; struct inode *new_orphan_inode = NULL; - struct posix_acl *default_acl, *acl; - umode_t mode; if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb))) return -EOPNOTSUPP; - mode = inode->i_mode; - error = posix_acl_create(dir, &mode, &default_acl, &acl); - if (error) { - mlog_errno(error); - goto out; - } - error = ocfs2_create_inode_in_orphan(dir, mode, + error = ocfs2_create_inode_in_orphan(dir, inode->i_mode, &new_orphan_inode); if (error) { mlog_errno(error); @@ -4320,16 +4312,11 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir, /* If the security isn't preserved, we need to re-initialize them. */ if (!preserve) { error = ocfs2_init_security_and_acl(dir, new_orphan_inode, - &new_dentry->d_name, - default_acl, acl); + &new_dentry->d_name); if (error) mlog_errno(error); } out: - if (default_acl) - posix_acl_release(default_acl); - if (acl) - posix_acl_release(acl); if (!error) { error = ocfs2_mv_orphaned_inode_to_new(dir, new_orphan_inode, new_dentry); diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 016f01df3825..c237008c010d 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -7207,12 +7207,10 @@ out: */ int ocfs2_init_security_and_acl(struct inode *dir, struct inode *inode, - const struct qstr *qstr, - struct posix_acl *default_acl, - struct posix_acl *acl) + const struct qstr *qstr) { - struct buffer_head *dir_bh = NULL; int ret = 0; + struct buffer_head *dir_bh = NULL; ret = ocfs2_init_security_get(inode, dir, qstr, NULL); if (ret) { @@ -7225,11 +7223,9 @@ int ocfs2_init_security_and_acl(struct inode *dir, mlog_errno(ret); goto leave; } - - if (!ret && default_acl) - ret = ocfs2_iop_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); - if (!ret && acl) - ret = ocfs2_iop_set_acl(inode, acl, ACL_TYPE_ACCESS); + ret = ocfs2_init_acl(NULL, inode, dir, NULL, dir_bh, NULL, NULL); + if (ret) + mlog_errno(ret); ocfs2_inode_unlock(dir, 0); brelse(dir_bh); diff --git a/fs/ocfs2/xattr.h b/fs/ocfs2/xattr.h index f10d5b93c366..1633cc15ea1f 100644 --- a/fs/ocfs2/xattr.h +++ b/fs/ocfs2/xattr.h @@ -94,7 +94,5 @@ int ocfs2_reflink_xattrs(struct inode *old_inode, bool preserve_security); int ocfs2_init_security_and_acl(struct inode *dir, struct inode *inode, - const struct qstr *qstr, - struct posix_acl *default_acl, - struct posix_acl *acl); + const struct qstr *qstr); #endif /* OCFS2_XATTR_H */ diff --git a/fs/open.c b/fs/open.c index 4a8a355ffab8..1651f35d50f5 100644 --- a/fs/open.c +++ b/fs/open.c @@ -665,18 +665,18 @@ int open_check_o_direct(struct file *f) } static int do_dentry_open(struct file *f, + struct inode *inode, int (*open)(struct inode *, struct file *), const struct cred *cred) { static const struct file_operations empty_fops = {}; - struct inode *inode; int error; f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; path_get(&f->f_path); - inode = f->f_inode = f->f_path.dentry->d_inode; + f->f_inode = inode; f->f_mapping = inode->i_mapping; if (unlikely(f->f_flags & O_PATH)) { @@ -780,7 +780,8 @@ int finish_open(struct file *file, struct dentry *dentry, BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */ file->f_path.dentry = dentry; - error = do_dentry_open(file, open, current_cred()); + error = do_dentry_open(file, d_backing_inode(dentry), open, + current_cred()); if (!error) *opened |= FILE_OPENED; @@ -809,6 +810,28 @@ int finish_no_open(struct file *file, struct dentry *dentry) } EXPORT_SYMBOL(finish_no_open); +/** + * vfs_open - open the file at the given path + * @path: path to open + * @file: newly allocated file with f_flag initialized + * @cred: credentials to use + */ +int vfs_open(const struct path *path, struct file *file, + const struct cred *cred) +{ + struct dentry *dentry = path->dentry; + struct inode *inode = dentry->d_inode; + + file->f_path = *path; + if (dentry->d_flags & DCACHE_OP_SELECT_INODE) { + inode = dentry->d_op->d_select_inode(dentry, file->f_flags); + if (IS_ERR(inode)) + return PTR_ERR(inode); + } + + return do_dentry_open(file, inode, NULL, cred); +} + struct file *dentry_open(const struct path *path, int flags, const struct cred *cred) { @@ -840,26 +863,6 @@ struct file *dentry_open(const struct path *path, int flags, } EXPORT_SYMBOL(dentry_open); -/** - * vfs_open - open the file at the given path - * @path: path to open - * @filp: newly allocated file with f_flag initialized - * @cred: credentials to use - */ -int vfs_open(const struct path *path, struct file *filp, - const struct cred *cred) -{ - struct inode *inode = path->dentry->d_inode; - - if (inode->i_op->dentry_open) - return inode->i_op->dentry_open(path->dentry, filp, cred); - else { - filp->f_path = *path; - return do_dentry_open(filp, NULL, cred); - } -} -EXPORT_SYMBOL(vfs_open); - static inline int build_open_flags(int flags, umode_t mode, struct open_flags *op) { int lookup_flags = 0; @@ -965,14 +968,12 @@ struct file *filp_open(const char *filename, int flags, umode_t mode) EXPORT_SYMBOL(filp_open); struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt, - const char *filename, int flags) + const char *filename, int flags, umode_t mode) { struct open_flags op; - int err = build_open_flags(flags, 0, &op); + int err = build_open_flags(flags, mode, &op); if (err) return ERR_PTR(err); - if (flags & O_CREAT) - return ERR_PTR(-EINVAL); if (!filename && (flags & O_DIRECTORY)) if (!dentry->d_inode->i_op->lookup) return ERR_PTR(-ENOTDIR); diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index ea10a8719107..54d62bd95e92 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -22,9 +22,9 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new) { - ssize_t list_size, size; - char *buf, *name, *value; - int error; + ssize_t list_size, size, value_size = 0; + char *buf, *name, *value = NULL; + int uninitialized_var(error); if (!old->d_inode->i_op->getxattr || !new->d_inode->i_op->getxattr) @@ -41,29 +41,40 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new) if (!buf) return -ENOMEM; - error = -ENOMEM; - value = kmalloc(XATTR_SIZE_MAX, GFP_KERNEL); - if (!value) - goto out; - list_size = vfs_listxattr(old, buf, list_size); if (list_size <= 0) { error = list_size; - goto out_free_value; + goto out; } for (name = buf; name < (buf + list_size); name += strlen(name) + 1) { - size = vfs_getxattr(old, name, value, XATTR_SIZE_MAX); - if (size <= 0) { +retry: + size = vfs_getxattr(old, name, value, value_size); + if (size == -ERANGE) + size = vfs_getxattr(old, name, NULL, 0); + + if (size < 0) { error = size; - goto out_free_value; + break; + } + + if (size > value_size) { + void *new; + + new = krealloc(value, size, GFP_KERNEL); + if (!new) { + error = -ENOMEM; + break; + } + value = new; + value_size = size; + goto retry; } + error = vfs_setxattr(new, name, value, size, 0); if (error) - goto out_free_value; + break; } - -out_free_value: kfree(value); out: kfree(buf); diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 8ffc4b980f1b..d124faf087f9 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -505,6 +505,7 @@ static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir) struct dentry *upper; struct dentry *opaquedir = NULL; int err; + int flags = 0; if (is_dir) { opaquedir = ovl_check_empty_and_clear(dentry); @@ -517,46 +518,39 @@ static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir) if (err) goto out_dput; - whiteout = ovl_whiteout(workdir, dentry); - err = PTR_ERR(whiteout); - if (IS_ERR(whiteout)) + upper = lookup_one_len(dentry->d_name.name, upperdir, + dentry->d_name.len); + err = PTR_ERR(upper); + if (IS_ERR(upper)) goto out_unlock; - upper = ovl_dentry_upper(dentry); - if (!upper) { - upper = lookup_one_len(dentry->d_name.name, upperdir, - dentry->d_name.len); - err = PTR_ERR(upper); - if (IS_ERR(upper)) - goto kill_whiteout; - - err = ovl_do_rename(wdir, whiteout, udir, upper, 0); - dput(upper); - if (err) - goto kill_whiteout; - } else { - int flags = 0; + err = -ESTALE; + if ((opaquedir && upper != opaquedir) || + (!opaquedir && ovl_dentry_upper(dentry) && + upper != ovl_dentry_upper(dentry))) { + goto out_dput_upper; + } - if (opaquedir) - upper = opaquedir; - err = -ESTALE; - if (upper->d_parent != upperdir) - goto kill_whiteout; + whiteout = ovl_whiteout(workdir, dentry); + err = PTR_ERR(whiteout); + if (IS_ERR(whiteout)) + goto out_dput_upper; - if (is_dir) - flags |= RENAME_EXCHANGE; + if (d_is_dir(upper)) + flags = RENAME_EXCHANGE; - err = ovl_do_rename(wdir, whiteout, udir, upper, flags); - if (err) - goto kill_whiteout; + err = ovl_do_rename(wdir, whiteout, udir, upper, flags); + if (err) + goto kill_whiteout; + if (flags) + ovl_cleanup(wdir, upper); - if (is_dir) - ovl_cleanup(wdir, upper); - } ovl_dentry_version_inc(dentry->d_parent); out_d_drop: d_drop(dentry); dput(whiteout); +out_dput_upper: + dput(upper); out_unlock: unlock_rename(workdir, upperdir); out_dput: @@ -595,7 +589,8 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir) * sole user of this dentry. Too tricky... Just unhash for * now. */ - d_drop(dentry); + if (!err) + d_drop(dentry); mutex_unlock(&dir->i_mutex); return err; diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 07d74b24913b..fefce48e0f31 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -49,13 +49,19 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr) if (err) goto out; - upperdentry = ovl_dentry_upper(dentry); - if (upperdentry) { + err = ovl_copy_up(dentry); + if (!err) { + upperdentry = ovl_dentry_upper(dentry); + mutex_lock(&upperdentry->d_inode->i_mutex); + + if (attr->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) + attr->ia_valid &= ~ATTR_MODE; + err = notify_change(upperdentry, attr, NULL); + if (!err) + ovl_copyattr(upperdentry->d_inode, dentry->d_inode); mutex_unlock(&upperdentry->d_inode->i_mutex); - } else { - err = ovl_copy_up_last(dentry, attr, false); } ovl_drop_write(dentry); out: @@ -333,37 +339,33 @@ static bool ovl_open_need_copy_up(int flags, enum ovl_path_type type, return true; } -static int ovl_dentry_open(struct dentry *dentry, struct file *file, - const struct cred *cred) +struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags) { int err; struct path realpath; enum ovl_path_type type; - bool want_write = false; + + if (d_is_dir(dentry)) + return d_backing_inode(dentry); type = ovl_path_real(dentry, &realpath); - if (ovl_open_need_copy_up(file->f_flags, type, realpath.dentry)) { - want_write = true; + if (ovl_open_need_copy_up(file_flags, type, realpath.dentry)) { err = ovl_want_write(dentry); if (err) - goto out; + return ERR_PTR(err); - if (file->f_flags & O_TRUNC) + if (file_flags & O_TRUNC) err = ovl_copy_up_last(dentry, NULL, true); else err = ovl_copy_up(dentry); + ovl_drop_write(dentry); if (err) - goto out_drop_write; + return ERR_PTR(err); ovl_path_upper(dentry, &realpath); } - err = vfs_open(&realpath, file, cred); -out_drop_write: - if (want_write) - ovl_drop_write(dentry); -out: - return err; + return d_backing_inode(realpath.dentry); } static const struct inode_operations ovl_file_inode_operations = { @@ -374,7 +376,6 @@ static const struct inode_operations ovl_file_inode_operations = { .getxattr = ovl_getxattr, .listxattr = ovl_listxattr, .removexattr = ovl_removexattr, - .dentry_open = ovl_dentry_open, }; static const struct inode_operations ovl_symlink_inode_operations = { @@ -398,12 +399,11 @@ struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, if (!inode) return NULL; - mode &= S_IFMT; - inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_flags |= S_NOATIME | S_NOCMTIME; + mode &= S_IFMT; switch (mode) { case S_IFDIR: inode->i_private = oe; diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 814bed33dd07..00eb848faad8 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -165,6 +165,7 @@ ssize_t ovl_getxattr(struct dentry *dentry, const char *name, void *value, size_t size); ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size); int ovl_removexattr(struct dentry *dentry, const char *name); +struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags); struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, struct ovl_entry *oe); @@ -172,6 +173,7 @@ static inline void ovl_copyattr(struct inode *from, struct inode *to) { to->i_uid = from->i_uid; to->i_gid = from->i_gid; + to->i_mode = from->i_mode; } /* dir.c */ diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index ab1e3dcbed95..c55dc5588b17 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -579,7 +579,8 @@ void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list) (int) PTR_ERR(dentry)); continue; } - ovl_cleanup(upper->d_inode, dentry); + if (dentry->d_inode) + ovl_cleanup(upper->d_inode, dentry); dput(dentry); } mutex_unlock(&upper->d_inode->i_mutex); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index f16d318b71f8..b2361a1b50f2 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -269,6 +269,7 @@ static void ovl_dentry_release(struct dentry *dentry) static const struct dentry_operations ovl_dentry_operations = { .d_release = ovl_dentry_release, + .d_select_inode = ovl_d_select_inode, }; static struct ovl_entry *ovl_alloc_entry(void) @@ -775,6 +776,9 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) root_dentry->d_fsdata = oe; + ovl_copyattr(ovl_dentry_real(root_dentry)->d_inode, + root_dentry->d_inode); + sb->s_magic = OVERLAYFS_SUPER_MAGIC; sb->s_op = &ovl_super_operations; sb->s_root = root_dentry; diff --git a/fs/pipe.c b/fs/pipe.c index 21981e58e2a6..e3ba6c3a1743 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -39,6 +39,12 @@ unsigned int pipe_max_size = 1048576; */ unsigned int pipe_min_size = PAGE_SIZE; +/* Maximum allocatable pages per user. Hard limit is unset by default, soft + * matches default values. + */ +unsigned long pipe_user_pages_hard; +unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR; + /* * We use a start+len construction, which provides full use of the * allocated memory. @@ -585,20 +591,49 @@ pipe_fasync(int fd, struct file *filp, int on) return retval; } +static void account_pipe_buffers(struct pipe_inode_info *pipe, + unsigned long old, unsigned long new) +{ + atomic_long_add(new - old, &pipe->user->pipe_bufs); +} + +static bool too_many_pipe_buffers_soft(struct user_struct *user) +{ + return pipe_user_pages_soft && + atomic_long_read(&user->pipe_bufs) >= pipe_user_pages_soft; +} + +static bool too_many_pipe_buffers_hard(struct user_struct *user) +{ + return pipe_user_pages_hard && + atomic_long_read(&user->pipe_bufs) >= pipe_user_pages_hard; +} + struct pipe_inode_info *alloc_pipe_info(void) { struct pipe_inode_info *pipe; pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL); if (pipe) { - pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * PIPE_DEF_BUFFERS, GFP_KERNEL); + unsigned long pipe_bufs = PIPE_DEF_BUFFERS; + struct user_struct *user = get_current_user(); + + if (!too_many_pipe_buffers_hard(user)) { + if (too_many_pipe_buffers_soft(user)) + pipe_bufs = 1; + pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * pipe_bufs, GFP_KERNEL); + } + if (pipe->bufs) { init_waitqueue_head(&pipe->wait); pipe->r_counter = pipe->w_counter = 1; - pipe->buffers = PIPE_DEF_BUFFERS; + pipe->buffers = pipe_bufs; + pipe->user = user; + account_pipe_buffers(pipe, 0, pipe_bufs); mutex_init(&pipe->mutex); return pipe; } + free_uid(user); kfree(pipe); } @@ -609,6 +644,8 @@ void free_pipe_info(struct pipe_inode_info *pipe) { int i; + account_pipe_buffers(pipe, pipe->buffers, 0); + free_uid(pipe->user); for (i = 0; i < pipe->buffers; i++) { struct pipe_buffer *buf = pipe->bufs + i; if (buf->ops) @@ -999,6 +1036,7 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long nr_pages) memcpy(bufs + head, pipe->bufs, tail * sizeof(struct pipe_buffer)); } + account_pipe_buffers(pipe, pipe->buffers, nr_pages); pipe->curbuf = 0; kfree(pipe->bufs); pipe->bufs = bufs; @@ -1070,6 +1108,11 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg) if (!capable(CAP_SYS_RESOURCE) && size > pipe_max_size) { ret = -EPERM; goto out; + } else if ((too_many_pipe_buffers_hard(pipe->user) || + too_many_pipe_buffers_soft(pipe->user)) && + !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) { + ret = -EPERM; + goto out; } ret = pipe_set_size(pipe, nr_pages); break; diff --git a/fs/pnode.c b/fs/pnode.c index aae331a5d03b..18e56fc4a88c 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -198,10 +198,15 @@ static struct mount *next_group(struct mount *m, struct mount *origin) /* all accesses are serialized by namespace_sem */ static struct user_namespace *user_ns; -static struct mount *last_dest, *last_source, *dest_master; +static struct mount *last_dest, *first_source, *last_source, *dest_master; static struct mountpoint *mp; static struct hlist_head *list; +static inline bool peers(struct mount *m1, struct mount *m2) +{ + return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id; +} + static int propagate_one(struct mount *m) { struct mount *child; @@ -212,24 +217,26 @@ static int propagate_one(struct mount *m) /* skip if mountpoint isn't covered by it */ if (!is_subdir(mp->m_dentry, m->mnt.mnt_root)) return 0; - if (m->mnt_group_id == last_dest->mnt_group_id) { + if (peers(m, last_dest)) { type = CL_MAKE_SHARED; } else { struct mount *n, *p; + bool done; for (n = m; ; n = p) { p = n->mnt_master; - if (p == dest_master || IS_MNT_MARKED(p)) { - while (last_dest->mnt_master != p) { - last_source = last_source->mnt_master; - last_dest = last_source->mnt_parent; - } - if (n->mnt_group_id != last_dest->mnt_group_id) { - last_source = last_source->mnt_master; - last_dest = last_source->mnt_parent; - } + if (p == dest_master || IS_MNT_MARKED(p)) break; - } } + do { + struct mount *parent = last_source->mnt_parent; + if (last_source == first_source) + break; + done = parent->mnt_master == p; + if (done && peers(n, parent)) + break; + last_source = last_source->mnt_master; + } while (!done); + type = CL_SLAVE; /* beginning of peer group among the slaves? */ if (IS_MNT_SHARED(m)) @@ -280,6 +287,7 @@ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp, */ user_ns = current->nsproxy->mnt_ns->user_ns; last_dest = dest_mnt; + first_source = source_mnt; last_source = source_mnt; mp = dest_mp; list = tree_list; diff --git a/fs/proc/array.c b/fs/proc/array.c index cd3653e4f35c..16226e24ec48 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -391,7 +391,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, state = *get_task_state(task); vsize = eip = esp = 0; - permitted = ptrace_may_access(task, PTRACE_MODE_READ | PTRACE_MODE_NOAUDIT); + permitted = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS | PTRACE_MODE_NOAUDIT); mm = get_task_mm(task); if (mm) { vsize = task_vsize(mm); diff --git a/fs/proc/base.c b/fs/proc/base.c index 7dc3ea89ef1a..dc98620634a3 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -211,7 +211,7 @@ static int proc_pid_cmdline(struct seq_file *m, struct pid_namespace *ns, static int proc_pid_auxv(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { - struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ); + struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); if (mm && !IS_ERR(mm)) { unsigned int nwords = 0; do { @@ -239,7 +239,7 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, wchan = get_wchan(task); if (lookup_symbol_name(wchan, symname) < 0) - if (!ptrace_may_access(task, PTRACE_MODE_READ)) + if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) return 0; else return seq_printf(m, "%lu", wchan); @@ -253,7 +253,7 @@ static int lock_trace(struct task_struct *task) int err = mutex_lock_killable(&task->signal->cred_guard_mutex); if (err) return err; - if (!ptrace_may_access(task, PTRACE_MODE_ATTACH)) { + if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) { mutex_unlock(&task->signal->cred_guard_mutex); return -EPERM; } @@ -496,7 +496,7 @@ static int proc_fd_access_allowed(struct inode *inode) */ task = get_proc_task(inode); if (task) { - allowed = ptrace_may_access(task, PTRACE_MODE_READ); + allowed = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); put_task_struct(task); } return allowed; @@ -531,7 +531,7 @@ static bool has_pid_permissions(struct pid_namespace *pid, return true; if (in_group_p(pid->pid_gid)) return true; - return ptrace_may_access(task, PTRACE_MODE_READ); + return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); } @@ -608,7 +608,7 @@ struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode) struct mm_struct *mm = ERR_PTR(-ESRCH); if (task) { - mm = mm_access(task, mode); + mm = mm_access(task, mode | PTRACE_MODE_FSCREDS); put_task_struct(task); if (!IS_ERR_OR_NULL(mm)) { @@ -752,7 +752,8 @@ static ssize_t environ_read(struct file *file, char __user *buf, int ret = 0; struct mm_struct *mm = file->private_data; - if (!mm) + /* Ensure the process spawned far enough to have an environment. */ + if (!mm || !mm->env_end) return 0; page = (char *)__get_free_page(GFP_TEMPORARY); @@ -1670,7 +1671,7 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags) if (!task) goto out_notask; - mm = mm_access(task, PTRACE_MODE_READ); + mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); if (IS_ERR_OR_NULL(mm)) goto out; @@ -1802,7 +1803,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir, goto out; result = -EACCES; - if (!ptrace_may_access(task, PTRACE_MODE_READ)) + if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto out_put_task; result = -ENOENT; @@ -1859,7 +1860,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx) goto out; ret = -EACCES; - if (!ptrace_may_access(task, PTRACE_MODE_READ)) + if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto out_put_task; ret = 0; @@ -2338,7 +2339,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh if (result) return result; - if (!ptrace_may_access(task, PTRACE_MODE_READ)) { + if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) { result = -EACCES; goto out_unlock; } diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c index 89026095f2b5..0bdad6b11a16 100644 --- a/fs/proc/namespaces.c +++ b/fs/proc/namespaces.c @@ -119,7 +119,7 @@ static void *proc_ns_follow_link(struct dentry *dentry, struct nameidata *nd) if (!task) goto out; - if (!ptrace_may_access(task, PTRACE_MODE_READ)) + if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto out_put_task; ns_path.dentry = proc_ns_get_dentry(sb, task, ei->ns.ns_ops); @@ -152,7 +152,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl if (!task) goto out; - if (!ptrace_may_access(task, PTRACE_MODE_READ)) + if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto out_put_task; res = -ENOENT; diff --git a/fs/proc/root.c b/fs/proc/root.c index 094e44d4a6be..7863ed5a6a88 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -112,9 +112,6 @@ static struct dentry *proc_mount(struct file_system_type *fs_type, ns = task_active_pid_ns(current); options = data; - if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type)) - return ERR_PTR(-EPERM); - /* Does the mounter have privilege over the pid namespace? */ if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); @@ -124,6 +121,13 @@ static struct dentry *proc_mount(struct file_system_type *fs_type, if (IS_ERR(sb)) return ERR_CAST(sb); + /* + * procfs isn't actually a stacking filesystem; however, there is + * too much magic going on inside it to permit stacking things on + * top of it + */ + sb->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH; + if (!proc_parse_options(options, ns)) { deactivate_locked_super(sb); return ERR_PTR(-EINVAL); @@ -159,7 +163,7 @@ static struct file_system_type proc_fs_type = { .name = "proc", .mount = proc_mount, .kill_sb = proc_kill_sb, - .fs_flags = FS_USERNS_MOUNT, + .fs_flags = FS_USERNS_VISIBLE | FS_USERNS_MOUNT, }; void __init proc_root_init(void) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 69aa378e60d9..af33fb77196f 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -447,58 +447,91 @@ struct mem_size_stats { u64 pss; }; +static void smaps_account(struct mem_size_stats *mss, struct page *page, + unsigned long size, bool young, bool dirty) +{ + int mapcount; + + if (PageAnon(page)) + mss->anonymous += size; -static void smaps_pte_entry(pte_t ptent, unsigned long addr, - unsigned long ptent_size, struct mm_walk *walk) + mss->resident += size; + /* Accumulate the size in pages that have been accessed. */ + if (young || PageReferenced(page)) + mss->referenced += size; + mapcount = page_mapcount(page); + if (mapcount >= 2) { + u64 pss_delta; + + if (dirty || PageDirty(page)) + mss->shared_dirty += size; + else + mss->shared_clean += size; + pss_delta = (u64)size << PSS_SHIFT; + do_div(pss_delta, mapcount); + mss->pss += pss_delta; + } else { + if (dirty || PageDirty(page)) + mss->private_dirty += size; + else + mss->private_clean += size; + mss->pss += (u64)size << PSS_SHIFT; + } +} + +static void smaps_pte_entry(pte_t *pte, unsigned long addr, + struct mm_walk *walk) { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = mss->vma; pgoff_t pgoff = linear_page_index(vma, addr); struct page *page = NULL; - int mapcount; - if (pte_present(ptent)) { - page = vm_normal_page(vma, addr, ptent); - } else if (is_swap_pte(ptent)) { - swp_entry_t swpent = pte_to_swp_entry(ptent); + if (pte_present(*pte)) { + page = vm_normal_page(vma, addr, *pte); + } else if (is_swap_pte(*pte)) { + swp_entry_t swpent = pte_to_swp_entry(*pte); if (!non_swap_entry(swpent)) - mss->swap += ptent_size; + mss->swap += PAGE_SIZE; else if (is_migration_entry(swpent)) page = migration_entry_to_page(swpent); - } else if (pte_file(ptent)) { - if (pte_to_pgoff(ptent) != pgoff) - mss->nonlinear += ptent_size; + } else if (pte_file(*pte)) { + if (pte_to_pgoff(*pte) != pgoff) + mss->nonlinear += PAGE_SIZE; } if (!page) return; - if (PageAnon(page)) - mss->anonymous += ptent_size; - if (page->index != pgoff) - mss->nonlinear += ptent_size; + mss->nonlinear += PAGE_SIZE; - mss->resident += ptent_size; - /* Accumulate the size in pages that have been accessed. */ - if (pte_young(ptent) || PageReferenced(page)) - mss->referenced += ptent_size; - mapcount = page_mapcount(page); - if (mapcount >= 2) { - if (pte_dirty(ptent) || PageDirty(page)) - mss->shared_dirty += ptent_size; - else - mss->shared_clean += ptent_size; - mss->pss += (ptent_size << PSS_SHIFT) / mapcount; - } else { - if (pte_dirty(ptent) || PageDirty(page)) - mss->private_dirty += ptent_size; - else - mss->private_clean += ptent_size; - mss->pss += (ptent_size << PSS_SHIFT); - } + smaps_account(mss, page, PAGE_SIZE, pte_young(*pte), pte_dirty(*pte)); +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, + struct mm_walk *walk) +{ + struct mem_size_stats *mss = walk->private; + struct vm_area_struct *vma = mss->vma; + struct page *page; + + /* FOLL_DUMP will return -EFAULT on huge zero page */ + page = follow_trans_huge_pmd(vma, addr, pmd, FOLL_DUMP); + if (IS_ERR_OR_NULL(page)) + return; + mss->anonymous_thp += HPAGE_PMD_SIZE; + smaps_account(mss, page, HPAGE_PMD_SIZE, + pmd_young(*pmd), pmd_dirty(*pmd)); } +#else +static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, + struct mm_walk *walk) +{ +} +#endif static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -509,9 +542,8 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, spinlock_t *ptl; if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { - smaps_pte_entry(*(pte_t *)pmd, addr, HPAGE_PMD_SIZE, walk); + smaps_pmd_entry(pmd, addr, walk); spin_unlock(ptl); - mss->anonymous_thp += HPAGE_PMD_SIZE; return 0; } @@ -524,7 +556,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, */ pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); for (; addr != end; pte++, addr += PAGE_SIZE) - smaps_pte_entry(*pte, addr, PAGE_SIZE, walk); + smaps_pte_entry(pte, addr, walk); pte_unmap_unlock(pte - 1, ptl); cond_resched(); return 0; diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 05fea2ac116c..18aaccb290c2 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1384,7 +1384,7 @@ static int dquot_active(const struct inode *inode) static void __dquot_initialize(struct inode *inode, int type) { int cnt, init_needed = 0; - struct dquot *got[MAXQUOTAS]; + struct dquot *got[MAXQUOTAS] = {}; struct super_block *sb = inode->i_sb; qsize_t rsv; @@ -1394,7 +1394,6 @@ static void __dquot_initialize(struct inode *inode, int type) /* First get references to structures we might need. */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { struct kqid qid; - got[cnt] = NULL; if (type != -1 && cnt != type) continue; /* diff --git a/fs/signalfd.c b/fs/signalfd.c index 424b7b65321f..148f8e7af882 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -121,8 +121,9 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, * Other callers might not initialize the si_lsb field, * so check explicitly for the right codes here. */ - if (kinfo->si_code == BUS_MCEERR_AR || - kinfo->si_code == BUS_MCEERR_AO) + if (kinfo->si_signo == SIGBUS && + (kinfo->si_code == BUS_MCEERR_AR || + kinfo->si_code == BUS_MCEERR_AO)) err |= __put_user((short) kinfo->si_addr_lsb, &uinfo->ssi_addr_lsb); #endif diff --git a/fs/splice.c b/fs/splice.c index 75c6058eabf2..cf0cb768a1a7 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -186,6 +186,9 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe, unsigned int spd_pages = spd->nr_pages; int ret, do_wakeup, page_nr; + if (!spd_pages) + return 0; + ret = 0; do_wakeup = 0; page_nr = 0; diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index 8a49486bf30c..1c6ac6fcee9f 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -31,9 +31,6 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type, bool new_sb; if (!(flags & MS_KERNMOUNT)) { - if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type)) - return ERR_PTR(-EPERM); - if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET)) return ERR_PTR(-EPERM); } @@ -58,7 +55,7 @@ static struct file_system_type sysfs_fs_type = { .name = "sysfs", .mount = sysfs_mount, .kill_sb = sysfs_kill_sb, - .fs_flags = FS_USERNS_MOUNT, + .fs_flags = FS_USERNS_VISIBLE | FS_USERNS_MOUNT, }; int __init sysfs_init(void) diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index b5b593c45270..d37140e5b722 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -54,6 +54,7 @@ #include <linux/mount.h> #include <linux/namei.h> #include <linux/slab.h> +#include <linux/migrate.h> static int read_block(struct inode *inode, void *addr, unsigned int block, struct ubifs_data_node *dn) @@ -1419,6 +1420,26 @@ static int ubifs_set_page_dirty(struct page *page) return ret; } +#ifdef CONFIG_MIGRATION +static int ubifs_migrate_page(struct address_space *mapping, + struct page *newpage, struct page *page, enum migrate_mode mode) +{ + int rc; + + rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, 0); + if (rc != MIGRATEPAGE_SUCCESS) + return rc; + + if (PagePrivate(page)) { + ClearPagePrivate(page); + SetPagePrivate(newpage); + } + + migrate_page_copy(newpage, page); + return MIGRATEPAGE_SUCCESS; +} +#endif + static int ubifs_releasepage(struct page *page, gfp_t unused_gfp_flags) { /* @@ -1556,6 +1577,9 @@ const struct address_space_operations ubifs_file_address_operations = { .write_end = ubifs_write_end, .invalidatepage = ubifs_invalidatepage, .set_page_dirty = ubifs_set_page_dirty, +#ifdef CONFIG_MIGRATION + .migratepage = ubifs_migrate_page, +#endif .releasepage = ubifs_releasepage, }; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 7b72b7dd8906..9ae690d4cfeb 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -2054,14 +2054,29 @@ void udf_write_aext(struct inode *inode, struct extent_position *epos, epos->offset += adsize; } +/* + * Only 1 indirect extent in a row really makes sense but allow upto 16 in case + * someone does some weird stuff. + */ +#define UDF_MAX_INDIR_EXTS 16 + int8_t udf_next_aext(struct inode *inode, struct extent_position *epos, struct kernel_lb_addr *eloc, uint32_t *elen, int inc) { int8_t etype; + unsigned int indirections = 0; while ((etype = udf_current_aext(inode, epos, eloc, elen, inc)) == (EXT_NEXT_EXTENT_ALLOCDECS >> 30)) { int block; + + if (++indirections > UDF_MAX_INDIR_EXTS) { + udf_err(inode->i_sb, + "too many indirect extents in inode %lu\n", + inode->i_ino); + return -1; + } + epos->block = *eloc; epos->offset = sizeof(struct allocExtDesc); brelse(epos->bh); diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c index b84fee372734..2eafe2c4d239 100644 --- a/fs/udf/unicode.c +++ b/fs/udf/unicode.c @@ -133,11 +133,15 @@ int udf_CS0toUTF8(struct ustr *utf_o, const struct ustr *ocu_i) if (c < 0x80U) utf_o->u_name[utf_o->u_len++] = (uint8_t)c; else if (c < 0x800U) { + if (utf_o->u_len > (UDF_NAME_LEN - 4)) + break; utf_o->u_name[utf_o->u_len++] = (uint8_t)(0xc0 | (c >> 6)); utf_o->u_name[utf_o->u_len++] = (uint8_t)(0x80 | (c & 0x3f)); } else { + if (utf_o->u_len > (UDF_NAME_LEN - 5)) + break; utf_o->u_name[utf_o->u_len++] = (uint8_t)(0xe0 | (c >> 12)); utf_o->u_name[utf_o->u_len++] = @@ -178,17 +182,22 @@ int udf_CS0toUTF8(struct ustr *utf_o, const struct ustr *ocu_i) static int udf_UTF8toCS0(dstring *ocu, struct ustr *utf, int length) { unsigned c, i, max_val, utf_char; - int utf_cnt, u_len; + int utf_cnt, u_len, u_ch; memset(ocu, 0, sizeof(dstring) * length); ocu[0] = 8; max_val = 0xffU; + u_ch = 1; try_again: u_len = 0U; utf_char = 0U; utf_cnt = 0U; for (i = 0U; i < utf->u_len; i++) { + /* Name didn't fit? */ + if (u_len + 1 + u_ch >= length) + return 0; + c = (uint8_t)utf->u_name[i]; /* Complete a multi-byte UTF-8 character */ @@ -230,6 +239,7 @@ try_again: if (max_val == 0xffU) { max_val = 0xffffU; ocu[0] = (uint8_t)0x10U; + u_ch = 2; goto try_again; } goto error_out; @@ -282,7 +292,7 @@ static int udf_CS0toNLS(struct nls_table *nls, struct ustr *utf_o, c = (c << 8) | ocu[i++]; len = nls->uni2char(c, &utf_o->u_name[utf_o->u_len], - UDF_NAME_LEN - utf_o->u_len); + UDF_NAME_LEN - 2 - utf_o->u_len); /* Valid character? */ if (len >= 0) utf_o->u_len += len; @@ -300,15 +310,19 @@ static int udf_NLStoCS0(struct nls_table *nls, dstring *ocu, struct ustr *uni, int len; unsigned i, max_val; uint16_t uni_char; - int u_len; + int u_len, u_ch; memset(ocu, 0, sizeof(dstring) * length); ocu[0] = 8; max_val = 0xffU; + u_ch = 1; try_again: u_len = 0U; for (i = 0U; i < uni->u_len; i++) { + /* Name didn't fit? */ + if (u_len + 1 + u_ch >= length) + return 0; len = nls->char2uni(&uni->u_name[i], uni->u_len - i, &uni_char); if (!len) continue; @@ -321,6 +335,7 @@ try_again: if (uni_char > max_val) { max_val = 0xffffU; ocu[0] = (uint8_t)0x10U; + u_ch = 2; goto try_again; } diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c index 2c1036080d52..a7106eda5024 100644 --- a/fs/ufs/balloc.c +++ b/fs/ufs/balloc.c @@ -51,8 +51,8 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count) if (ufs_fragnum(fragment) + count > uspi->s_fpg) ufs_error (sb, "ufs_free_fragments", "internal error"); - - lock_ufs(sb); + + mutex_lock(&UFS_SB(sb)->s_lock); cgno = ufs_dtog(uspi, fragment); bit = ufs_dtogd(uspi, fragment); @@ -115,13 +115,13 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count) if (sb->s_flags & MS_SYNCHRONOUS) ubh_sync_block(UCPI_UBH(ucpi)); ufs_mark_sb_dirty(sb); - - unlock_ufs(sb); + + mutex_unlock(&UFS_SB(sb)->s_lock); UFSD("EXIT\n"); return; failed: - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); UFSD("EXIT (FAILED)\n"); return; } @@ -151,7 +151,7 @@ void ufs_free_blocks(struct inode *inode, u64 fragment, unsigned count) goto failed; } - lock_ufs(sb); + mutex_lock(&UFS_SB(sb)->s_lock); do_more: overflow = 0; @@ -211,12 +211,12 @@ do_more: } ufs_mark_sb_dirty(sb); - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); UFSD("EXIT\n"); return; failed_unlock: - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); failed: UFSD("EXIT (FAILED)\n"); return; @@ -357,7 +357,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, usb1 = ubh_get_usb_first(uspi); *err = -ENOSPC; - lock_ufs(sb); + mutex_lock(&UFS_SB(sb)->s_lock); tmp = ufs_data_ptr_to_cpu(sb, p); if (count + ufs_fragnum(fragment) > uspi->s_fpb) { @@ -378,19 +378,19 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, "fragment %llu, tmp %llu\n", (unsigned long long)fragment, (unsigned long long)tmp); - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); return INVBLOCK; } if (fragment < UFS_I(inode)->i_lastfrag) { UFSD("EXIT (ALREADY ALLOCATED)\n"); - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); return 0; } } else { if (tmp) { UFSD("EXIT (ALREADY ALLOCATED)\n"); - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); return 0; } } @@ -399,7 +399,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, * There is not enough space for user on the device */ if (!capable(CAP_SYS_RESOURCE) && ufs_freespace(uspi, UFS_MINFREE) <= 0) { - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); UFSD("EXIT (FAILED)\n"); return 0; } @@ -424,7 +424,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, ufs_clear_frags(inode, result + oldcount, newcount - oldcount, locked_page != NULL); } - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); UFSD("EXIT, result %llu\n", (unsigned long long)result); return result; } @@ -439,7 +439,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, fragment + count); ufs_clear_frags(inode, result + oldcount, newcount - oldcount, locked_page != NULL); - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); UFSD("EXIT, result %llu\n", (unsigned long long)result); return result; } @@ -477,7 +477,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, *err = 0; UFS_I(inode)->i_lastfrag = max(UFS_I(inode)->i_lastfrag, fragment + count); - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); if (newcount < request) ufs_free_fragments (inode, result + newcount, request - newcount); ufs_free_fragments (inode, tmp, oldcount); @@ -485,7 +485,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, return result; } - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); UFSD("EXIT (FAILED)\n"); return 0; } diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c index 7caa01652888..fd0203ce1f7f 100644 --- a/fs/ufs/ialloc.c +++ b/fs/ufs/ialloc.c @@ -69,11 +69,11 @@ void ufs_free_inode (struct inode * inode) ino = inode->i_ino; - lock_ufs(sb); + mutex_lock(&UFS_SB(sb)->s_lock); if (!((ino > 1) && (ino < (uspi->s_ncg * uspi->s_ipg )))) { ufs_warning(sb, "ufs_free_inode", "reserved inode or nonexistent inode %u\n", ino); - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); return; } @@ -81,7 +81,7 @@ void ufs_free_inode (struct inode * inode) bit = ufs_inotocgoff (ino); ucpi = ufs_load_cylinder (sb, cg); if (!ucpi) { - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); return; } ucg = ubh_get_ucg(UCPI_UBH(ucpi)); @@ -115,7 +115,7 @@ void ufs_free_inode (struct inode * inode) ubh_sync_block(UCPI_UBH(ucpi)); ufs_mark_sb_dirty(sb); - unlock_ufs(sb); + mutex_unlock(&UFS_SB(sb)->s_lock); UFSD("EXIT\n"); } @@ -193,7 +193,7 @@ struct inode *ufs_new_inode(struct inode *dir, umode_t mode) sbi = UFS_SB(sb); uspi = sbi->s_uspi; - lock_ufs(sb); + mutex_lock(&sbi->s_lock); /* * Try to place the inode in its parent directory @@ -331,21 +331,21 @@ cg_found: sync_dirty_buffer(bh); brelse(bh); } - unlock_ufs(sb); + mutex_unlock(&sbi->s_lock); UFSD("allocating inode %lu\n", inode->i_ino); UFSD("EXIT\n"); return inode; fail_remove_inode: - unlock_ufs(sb); + mutex_unlock(&sbi->s_lock); clear_nlink(inode); unlock_new_inode(inode); iput(inode); UFSD("EXIT (FAILED): err %d\n", err); return ERR_PTR(err); failed: - unlock_ufs(sb); + mutex_unlock(&sbi->s_lock); make_bad_inode(inode); iput (inode); UFSD("EXIT (FAILED): err %d\n", err); diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index be7d42c7d938..2d93ab07da8a 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -902,6 +902,9 @@ void ufs_evict_inode(struct inode * inode) invalidate_inode_buffers(inode); clear_inode(inode); - if (want_delete) + if (want_delete) { + lock_ufs(inode->i_sb); ufs_free_inode(inode); + unlock_ufs(inode->i_sb); + } } diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c index fd65deb4b5f0..e8ee2985b068 100644 --- a/fs/ufs/namei.c +++ b/fs/ufs/namei.c @@ -128,12 +128,12 @@ static int ufs_symlink (struct inode * dir, struct dentry * dentry, if (l > sb->s_blocksize) goto out_notlocked; + lock_ufs(dir->i_sb); inode = ufs_new_inode(dir, S_IFLNK | S_IRWXUGO); err = PTR_ERR(inode); if (IS_ERR(inode)) - goto out_notlocked; + goto out; - lock_ufs(dir->i_sb); if (l > UFS_SB(sb)->s_uspi->s_maxsymlinklen) { /* slow symlink */ inode->i_op = &ufs_symlink_inode_operations; @@ -174,7 +174,12 @@ static int ufs_link (struct dentry * old_dentry, struct inode * dir, inode_inc_link_count(inode); ihold(inode); - error = ufs_add_nondir(dentry, inode); + error = ufs_add_link(dentry, inode); + if (error) { + inode_dec_link_count(inode); + iput(inode); + } else + d_instantiate(dentry, inode); unlock_ufs(dir->i_sb); return error; } @@ -184,9 +189,13 @@ static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode) struct inode * inode; int err; + lock_ufs(dir->i_sb); + inode_inc_link_count(dir); + inode = ufs_new_inode(dir, S_IFDIR|mode); + err = PTR_ERR(inode); if (IS_ERR(inode)) - return PTR_ERR(inode); + goto out_dir; inode->i_op = &ufs_dir_inode_operations; inode->i_fop = &ufs_dir_operations; @@ -194,9 +203,6 @@ static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode) inode_inc_link_count(inode); - lock_ufs(dir->i_sb); - inode_inc_link_count(dir); - err = ufs_make_empty(inode, dir); if (err) goto out_fail; @@ -206,6 +212,7 @@ static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode) goto out_fail; unlock_ufs(dir->i_sb); + unlock_new_inode(inode); d_instantiate(dentry, inode); out: return err; @@ -215,6 +222,7 @@ out_fail: inode_dec_link_count(inode); unlock_new_inode(inode); iput (inode); +out_dir: inode_dec_link_count(dir); unlock_ufs(dir->i_sb); goto out; diff --git a/fs/ufs/super.c b/fs/ufs/super.c index da73801301d5..ce02dff5572f 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -698,6 +698,7 @@ static int ufs_sync_fs(struct super_block *sb, int wait) unsigned flags; lock_ufs(sb); + mutex_lock(&UFS_SB(sb)->s_lock); UFSD("ENTER\n"); @@ -715,6 +716,7 @@ static int ufs_sync_fs(struct super_block *sb, int wait) ufs_put_cstotal(sb); UFSD("EXIT\n"); + mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return 0; @@ -803,6 +805,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) UFSD("flag %u\n", (int)(sb->s_flags & MS_RDONLY)); mutex_init(&sbi->mutex); + mutex_init(&sbi->s_lock); spin_lock_init(&sbi->work_lock); INIT_DELAYED_WORK(&sbi->sync_work, delayed_sync_fs); /* @@ -1281,6 +1284,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) sync_filesystem(sb); lock_ufs(sb); + mutex_lock(&UFS_SB(sb)->s_lock); uspi = UFS_SB(sb)->s_uspi; flags = UFS_SB(sb)->s_flags; usb1 = ubh_get_usb_first(uspi); @@ -1294,6 +1298,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) new_mount_opt = 0; ufs_set_opt (new_mount_opt, ONERROR_LOCK); if (!ufs_parse_options (data, &new_mount_opt)) { + mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return -EINVAL; } @@ -1301,12 +1306,14 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) new_mount_opt |= ufstype; } else if ((new_mount_opt & UFS_MOUNT_UFSTYPE) != ufstype) { pr_err("ufstype can't be changed during remount\n"); + mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return -EINVAL; } if ((*mount_flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) { UFS_SB(sb)->s_mount_opt = new_mount_opt; + mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return 0; } @@ -1330,6 +1337,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) */ #ifndef CONFIG_UFS_FS_WRITE pr_err("ufs was compiled with read-only support, can't be mounted as read-write\n"); + mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return -EINVAL; #else @@ -1339,11 +1347,13 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) ufstype != UFS_MOUNT_UFSTYPE_SUNx86 && ufstype != UFS_MOUNT_UFSTYPE_UFS2) { pr_err("this ufstype is read-only supported\n"); + mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return -EINVAL; } if (!ufs_read_cylinder_structures(sb)) { pr_err("failed during remounting\n"); + mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return -EPERM; } @@ -1351,6 +1361,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) #endif } UFS_SB(sb)->s_mount_opt = new_mount_opt; + mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return 0; } diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h index 2a07396d5f9e..cf6368d42d4a 100644 --- a/fs/ufs/ufs.h +++ b/fs/ufs/ufs.h @@ -30,6 +30,7 @@ struct ufs_sb_info { int work_queued; /* non-zero if the delayed work is queued */ struct delayed_work sync_work; /* FS sync delayed work */ spinlock_t work_lock; /* protects sync_work and work_queued */ + struct mutex s_lock; }; struct ufs_inode_info { diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index eff34218f405..2300743e701e 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -515,6 +515,7 @@ xfs_agfl_write_verify( } const struct xfs_buf_ops xfs_agfl_buf_ops = { + .name = "xfs_agfl", .verify_read = xfs_agfl_read_verify, .verify_write = xfs_agfl_write_verify, }; @@ -2271,6 +2272,7 @@ xfs_agf_write_verify( } const struct xfs_buf_ops xfs_agf_buf_ops = { + .name = "xfs_agf", .verify_read = xfs_agf_read_verify, .verify_write = xfs_agf_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c index e0e83e24d3ef..3bd94d5a5068 100644 --- a/fs/xfs/libxfs/xfs_alloc_btree.c +++ b/fs/xfs/libxfs/xfs_alloc_btree.c @@ -380,6 +380,7 @@ xfs_allocbt_write_verify( } const struct xfs_buf_ops xfs_allocbt_buf_ops = { + .name = "xfs_allocbt", .verify_read = xfs_allocbt_read_verify, .verify_write = xfs_allocbt_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index b7cd0a0541af..905b0cdb0107 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -251,6 +251,7 @@ xfs_attr3_leaf_read_verify( } const struct xfs_buf_ops xfs_attr3_leaf_buf_ops = { + .name = "xfs_attr3_leaf", .verify_read = xfs_attr3_leaf_read_verify, .verify_write = xfs_attr3_leaf_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c index 7510ab8058a4..fda9c2aad37c 100644 --- a/fs/xfs/libxfs/xfs_attr_remote.c +++ b/fs/xfs/libxfs/xfs_attr_remote.c @@ -198,6 +198,7 @@ xfs_attr3_rmt_write_verify( } const struct xfs_buf_ops xfs_attr3_rmt_buf_ops = { + .name = "xfs_attr3_rmt", .verify_read = xfs_attr3_rmt_read_verify, .verify_write = xfs_attr3_rmt_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index fba753308f31..e6bde91a7d0c 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -722,6 +722,7 @@ xfs_bmbt_write_verify( } const struct xfs_buf_ops xfs_bmbt_buf_ops = { + .name = "xfs_bmbt", .verify_read = xfs_bmbt_read_verify, .verify_write = xfs_bmbt_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index fd827530afec..837b366c3fcf 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -243,6 +243,7 @@ xfs_da3_node_read_verify( } const struct xfs_buf_ops xfs_da3_node_buf_ops = { + .name = "xfs_da3_node", .verify_read = xfs_da3_node_read_verify, .verify_write = xfs_da3_node_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c index 9628ceccfa02..11a3beed2e57 100644 --- a/fs/xfs/libxfs/xfs_dir2_block.c +++ b/fs/xfs/libxfs/xfs_dir2_block.c @@ -123,6 +123,7 @@ xfs_dir3_block_write_verify( } const struct xfs_buf_ops xfs_dir3_block_buf_ops = { + .name = "xfs_dir3_block", .verify_read = xfs_dir3_block_read_verify, .verify_write = xfs_dir3_block_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c index fdd803fecb8e..47504a191bb3 100644 --- a/fs/xfs/libxfs/xfs_dir2_data.c +++ b/fs/xfs/libxfs/xfs_dir2_data.c @@ -302,11 +302,13 @@ xfs_dir3_data_write_verify( } const struct xfs_buf_ops xfs_dir3_data_buf_ops = { + .name = "xfs_dir3_data", .verify_read = xfs_dir3_data_read_verify, .verify_write = xfs_dir3_data_write_verify, }; static const struct xfs_buf_ops xfs_dir3_data_reada_buf_ops = { + .name = "xfs_dir3_data_reada", .verify_read = xfs_dir3_data_reada_verify, .verify_write = xfs_dir3_data_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c index a19174eb3cb2..a03f595674bf 100644 --- a/fs/xfs/libxfs/xfs_dir2_leaf.c +++ b/fs/xfs/libxfs/xfs_dir2_leaf.c @@ -244,11 +244,13 @@ xfs_dir3_leafn_write_verify( } const struct xfs_buf_ops xfs_dir3_leaf1_buf_ops = { + .name = "xfs_dir3_leaf1", .verify_read = xfs_dir3_leaf1_read_verify, .verify_write = xfs_dir3_leaf1_write_verify, }; const struct xfs_buf_ops xfs_dir3_leafn_buf_ops = { + .name = "xfs_dir3_leafn", .verify_read = xfs_dir3_leafn_read_verify, .verify_write = xfs_dir3_leafn_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c index 2ae6ac2c11ae..75431b220174 100644 --- a/fs/xfs/libxfs/xfs_dir2_node.c +++ b/fs/xfs/libxfs/xfs_dir2_node.c @@ -149,6 +149,7 @@ xfs_dir3_free_write_verify( } const struct xfs_buf_ops xfs_dir3_free_buf_ops = { + .name = "xfs_dir3_free", .verify_read = xfs_dir3_free_read_verify, .verify_write = xfs_dir3_free_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c index bb969337efc8..c6fba7314e8f 100644 --- a/fs/xfs/libxfs/xfs_dquot_buf.c +++ b/fs/xfs/libxfs/xfs_dquot_buf.c @@ -56,7 +56,7 @@ xfs_dqcheck( xfs_dqid_t id, uint type, /* used only when IO_dorepair is true */ uint flags, - char *str) + const char *str) { xfs_dqblk_t *d = (xfs_dqblk_t *)ddq; int errs = 0; @@ -209,7 +209,8 @@ xfs_dquot_buf_verify_crc( STATIC bool xfs_dquot_buf_verify( struct xfs_mount *mp, - struct xfs_buf *bp) + struct xfs_buf *bp, + int warn) { struct xfs_dqblk *d = (struct xfs_dqblk *)bp->b_addr; xfs_dqid_t id = 0; @@ -242,8 +243,7 @@ xfs_dquot_buf_verify( if (i == 0) id = be32_to_cpu(ddq->d_id); - error = xfs_dqcheck(mp, ddq, id + i, 0, XFS_QMOPT_DOWARN, - "xfs_dquot_buf_verify"); + error = xfs_dqcheck(mp, ddq, id + i, 0, warn, __func__); if (error) return false; } @@ -258,7 +258,7 @@ xfs_dquot_buf_read_verify( if (!xfs_dquot_buf_verify_crc(mp, bp)) xfs_buf_ioerror(bp, -EFSBADCRC); - else if (!xfs_dquot_buf_verify(mp, bp)) + else if (!xfs_dquot_buf_verify(mp, bp, XFS_QMOPT_DOWARN)) xfs_buf_ioerror(bp, -EFSCORRUPTED); if (bp->b_error) @@ -266,6 +266,25 @@ xfs_dquot_buf_read_verify( } /* + * readahead errors are silent and simply leave the buffer as !done so a real + * read will then be run with the xfs_dquot_buf_ops verifier. See + * xfs_inode_buf_verify() for why we use EIO and ~XBF_DONE here rather than + * reporting the failure. + */ +static void +xfs_dquot_buf_readahead_verify( + struct xfs_buf *bp) +{ + struct xfs_mount *mp = bp->b_target->bt_mount; + + if (!xfs_dquot_buf_verify_crc(mp, bp) || + !xfs_dquot_buf_verify(mp, bp, 0)) { + xfs_buf_ioerror(bp, -EIO); + bp->b_flags &= ~XBF_DONE; + } +} + +/* * we don't calculate the CRC here as that is done when the dquot is flushed to * the buffer after the update is done. This ensures that the dquot in the * buffer always has an up-to-date CRC value. @@ -276,7 +295,7 @@ xfs_dquot_buf_write_verify( { struct xfs_mount *mp = bp->b_target->bt_mount; - if (!xfs_dquot_buf_verify(mp, bp)) { + if (!xfs_dquot_buf_verify(mp, bp, XFS_QMOPT_DOWARN)) { xfs_buf_ioerror(bp, -EFSCORRUPTED); xfs_verifier_error(bp); return; @@ -284,7 +303,12 @@ xfs_dquot_buf_write_verify( } const struct xfs_buf_ops xfs_dquot_buf_ops = { + .name = "xfs_dquot", .verify_read = xfs_dquot_buf_read_verify, .verify_write = xfs_dquot_buf_write_verify, }; +const struct xfs_buf_ops xfs_dquot_buf_ra_ops = { + .verify_read = xfs_dquot_buf_readahead_verify, + .verify_write = xfs_dquot_buf_write_verify, +}; diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 23dcb72fc5e6..196f29690484 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -2105,6 +2105,7 @@ xfs_agi_write_verify( } const struct xfs_buf_ops xfs_agi_buf_ops = { + .name = "xfs_agi", .verify_read = xfs_agi_read_verify, .verify_write = xfs_agi_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index c9b06f30fe86..14ae3e295e7c 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -297,6 +297,7 @@ xfs_inobt_write_verify( } const struct xfs_buf_ops xfs_inobt_buf_ops = { + .name = "xfs_inobt", .verify_read = xfs_inobt_read_verify, .verify_write = xfs_inobt_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index f18fd2da49f7..1bf2f1ccd957 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -66,11 +66,14 @@ xfs_inobp_check( * has not had the inode cores stamped into it. Hence for readahead, the buffer * may be potentially invalid. * - * If the readahead buffer is invalid, we don't want to mark it with an error, - * but we do want to clear the DONE status of the buffer so that a followup read - * will re-read it from disk. This will ensure that we don't get an unnecessary - * warnings during log recovery and we don't get unnecssary panics on debug - * kernels. + * If the readahead buffer is invalid, we need to mark it with an error and + * clear the DONE status of the buffer so that a followup read will re-read it + * from disk. We don't report the error otherwise to avoid warnings during log + * recovery and we don't get unnecssary panics on debug kernels. We use EIO here + * because all we want to do is say readahead failed; there is no-one to report + * the error to, so this will distinguish it from a non-ra verifier failure. + * Changes to this readahead error behavour also need to be reflected in + * xfs_dquot_buf_readahead_verify(). */ static void xfs_inode_buf_verify( @@ -98,6 +101,7 @@ xfs_inode_buf_verify( XFS_RANDOM_ITOBP_INOTOBP))) { if (readahead) { bp->b_flags &= ~XBF_DONE; + xfs_buf_ioerror(bp, -EIO); return; } @@ -137,11 +141,13 @@ xfs_inode_buf_write_verify( } const struct xfs_buf_ops xfs_inode_buf_ops = { + .name = "xfs_inode", .verify_read = xfs_inode_buf_read_verify, .verify_write = xfs_inode_buf_write_verify, }; const struct xfs_buf_ops xfs_inode_buf_ra_ops = { + .name = "xxfs_inode_ra", .verify_read = xfs_inode_buf_readahead_verify, .verify_write = xfs_inode_buf_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h index 1b0a08379759..f51078f1e92a 100644 --- a/fs/xfs/libxfs/xfs_quota_defs.h +++ b/fs/xfs/libxfs/xfs_quota_defs.h @@ -153,7 +153,7 @@ typedef __uint16_t xfs_qwarncnt_t; #define XFS_QMOPT_RESBLK_MASK (XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_RES_RTBLKS) extern int xfs_dqcheck(struct xfs_mount *mp, xfs_disk_dquot_t *ddq, - xfs_dqid_t id, uint type, uint flags, char *str); + xfs_dqid_t id, uint type, uint flags, const char *str); extern int xfs_calc_dquots_per_chunk(unsigned int nbblks); #endif /* __XFS_QUOTA_H__ */ diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 5f902fa7913f..acfcdc625aca 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -704,11 +704,13 @@ xfs_sb_write_verify( } const struct xfs_buf_ops xfs_sb_buf_ops = { + .name = "xfs_sb", .verify_read = xfs_sb_read_verify, .verify_write = xfs_sb_write_verify, }; const struct xfs_buf_ops xfs_sb_quiet_buf_ops = { + .name = "xfs_sb_quiet", .verify_read = xfs_sb_quiet_read_verify, .verify_write = xfs_sb_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h index 82404da2ca67..41b510c11e2c 100644 --- a/fs/xfs/libxfs/xfs_shared.h +++ b/fs/xfs/libxfs/xfs_shared.h @@ -49,6 +49,7 @@ extern const struct xfs_buf_ops xfs_inobt_buf_ops; extern const struct xfs_buf_ops xfs_inode_buf_ops; extern const struct xfs_buf_ops xfs_inode_buf_ra_ops; extern const struct xfs_buf_ops xfs_dquot_buf_ops; +extern const struct xfs_buf_ops xfs_dquot_buf_ra_ops; extern const struct xfs_buf_ops xfs_sb_buf_ops; extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops; extern const struct xfs_buf_ops xfs_symlink_buf_ops; diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c index a7dce9aea5b5..ccbbbbc7f25a 100644 --- a/fs/xfs/libxfs/xfs_symlink_remote.c +++ b/fs/xfs/libxfs/xfs_symlink_remote.c @@ -166,6 +166,7 @@ xfs_symlink_write_verify( } const struct xfs_buf_ops xfs_symlink_buf_ops = { + .name = "xfs_symlink", .verify_read = xfs_symlink_read_verify, .verify_write = xfs_symlink_write_verify, }; diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c index 62db83ab6cbc..ae64625937e5 100644 --- a/fs/xfs/xfs_attr_list.c +++ b/fs/xfs/xfs_attr_list.c @@ -205,8 +205,10 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context) sbp->namelen, sbp->valuelen, &sbp->name[sbp->namelen]); - if (error) + if (error) { + kmem_free(sbuf); return error; + } if (context->seen_enough) break; cursor->offset++; @@ -454,14 +456,13 @@ xfs_attr3_leaf_list_int( args.rmtblkcnt = xfs_attr3_rmt_blocks( args.dp->i_mount, valuelen); retval = xfs_attr_rmtval_get(&args); - if (retval) - return retval; - retval = context->put_listent(context, - entry->flags, - name_rmt->name, - (int)name_rmt->namelen, - valuelen, - args.value); + if (!retval) + retval = context->put_listent(context, + entry->flags, + name_rmt->name, + (int)name_rmt->namelen, + valuelen, + args.value); kmem_free(args.value); } else { retval = context->put_listent(context, diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 24b4ebea0d4d..284c2b2cf810 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -607,6 +607,13 @@ found: } } + /* + * Clear b_error if this is a lookup from a caller that doesn't expect + * valid data to be found in the buffer. + */ + if (!(flags & XBF_READ)) + xfs_buf_ioerror(bp, 0); + XFS_STATS_INC(xb_get); trace_xfs_buf_get(bp, flags, _RET_IP_); return bp; diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 82002c00af90..136319ccabf5 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -131,6 +131,7 @@ struct xfs_buf_map { struct xfs_buf_map (map) = { .bm_bn = (blkno), .bm_len = (numblk) }; struct xfs_buf_ops { + char *name; void (*verify_read)(struct xfs_buf *); void (*verify_write)(struct xfs_buf *); }; diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index b92fd7bc49e3..d55a1ce6d880 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -166,9 +166,9 @@ xfs_verifier_error( { struct xfs_mount *mp = bp->b_target->bt_mount; - xfs_alert(mp, "Metadata %s detected at %pF, block 0x%llx", + xfs_alert(mp, "Metadata %s detected at %pF, %s block 0x%llx", bp->b_error == -EFSBADCRC ? "CRC error" : "corruption", - __return_address, bp->b_bn); + __return_address, bp->b_ops->name, bp->b_bn); xfs_alert(mp, "Unmount and run xfs_repair"); diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 32e95c76cbd0..44e5598744b1 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2969,13 +2969,14 @@ xfs_iflush_cluster( * We need to check under the i_flags_lock for a valid inode * here. Skip it if it is not valid or the wrong inode. */ - spin_lock(&ip->i_flags_lock); - if (!ip->i_ino || + spin_lock(&iq->i_flags_lock); + if (!iq->i_ino || + __xfs_iflags_test(iq, XFS_ISTALE) || (XFS_INO_TO_AGINO(mp, iq->i_ino) & mask) != first_index) { - spin_unlock(&ip->i_flags_lock); + spin_unlock(&iq->i_flags_lock); continue; } - spin_unlock(&ip->i_flags_lock); + spin_unlock(&iq->i_flags_lock); /* * Do an un-protected check to see if the inode is dirty and @@ -3091,7 +3092,7 @@ xfs_iflush( struct xfs_buf **bpp) { struct xfs_mount *mp = ip->i_mount; - struct xfs_buf *bp; + struct xfs_buf *bp = NULL; struct xfs_dinode *dip; int error; @@ -3133,14 +3134,22 @@ xfs_iflush( } /* - * Get the buffer containing the on-disk inode. + * Get the buffer containing the on-disk inode. We are doing a try-lock + * operation here, so we may get an EAGAIN error. In that case, we + * simply want to return with the inode still dirty. + * + * If we get any other error, we effectively have a corruption situation + * and we cannot flush the inode, so we treat it the same as failing + * xfs_iflush_int(). */ error = xfs_imap_to_bp(mp, NULL, &ip->i_imap, &dip, &bp, XBF_TRYLOCK, 0); - if (error || !bp) { + if (error == -EAGAIN) { xfs_ifunlock(ip); return error; } + if (error) + goto corrupt_out; /* * First flush out the inode that xfs_iflush was called with. @@ -3168,7 +3177,8 @@ xfs_iflush( return 0; corrupt_out: - xfs_buf_relse(bp); + if (bp) + xfs_buf_relse(bp); xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); cluster_corrupt_out: error = -EFSCORRUPTED; diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 00cd7f3a8f59..5942b9fa5681 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -3151,6 +3151,7 @@ xlog_recover_dquot_ra_pass2( struct xfs_disk_dquot *recddq; struct xfs_dq_logformat *dq_f; uint type; + int len; if (mp->m_qflags == 0) @@ -3171,8 +3172,12 @@ xlog_recover_dquot_ra_pass2( ASSERT(dq_f); ASSERT(dq_f->qlf_len == 1); - xfs_buf_readahead(mp->m_ddev_targp, dq_f->qlf_blkno, - XFS_FSB_TO_BB(mp, dq_f->qlf_len), NULL); + len = XFS_FSB_TO_BB(mp, dq_f->qlf_len); + if (xlog_peek_buffer_cancelled(log, dq_f->qlf_blkno, len, 0)) + return; + + xfs_buf_readahead(mp->m_ddev_targp, dq_f->qlf_blkno, len, + &xfs_dquot_buf_ra_ops); } STATIC void diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 9f622feda6a4..73b6c8fca308 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1248,6 +1248,22 @@ xfs_fs_remount( /* ro -> rw */ if ((mp->m_flags & XFS_MOUNT_RDONLY) && !(*flags & MS_RDONLY)) { + if (mp->m_flags & XFS_MOUNT_NORECOVERY) { + xfs_warn(mp, + "ro->rw transition prohibited on norecovery mount"); + return -EINVAL; + } + + if (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 && + xfs_sb_has_ro_compat_feature(sbp, + XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) { + xfs_warn(mp, +"ro->rw transition prohibited on unknown (0x%x) ro-compat filesystem", + (sbp->sb_features_ro_compat & + XFS_SB_FEAT_RO_COMPAT_UNKNOWN)); + return -EINVAL; + } + mp->m_flags &= ~XFS_MOUNT_RDONLY; /* diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index 02ae62a998e0..6a93fd583ec0 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -107,7 +107,7 @@ xfs_readlink_bmap( cur_chunk += sizeof(struct xfs_dsymlink_hdr); } - memcpy(link + offset, bp->b_addr, byte_cnt); + memcpy(link + offset, cur_chunk, byte_cnt); pathlen -= byte_cnt; offset += byte_cnt; |