diff options
Diffstat (limited to 'fs')
51 files changed, 463 insertions, 302 deletions
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 030ab44fce18..82324c327a50 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -441,13 +441,23 @@ void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache, u64 num_bytes) { struct btrfs_caching_control *caching_ctl; + int progress; caching_ctl = btrfs_get_caching_control(cache); if (!caching_ctl) return; + /* + * We've already failed to allocate from this block group, so even if + * there's enough space in the block group it isn't contiguous enough to + * allow for an allocation, so wait for at least the next wakeup tick, + * or for the thing to be done. + */ + progress = atomic_read(&caching_ctl->progress); + wait_event(caching_ctl->wait, btrfs_block_group_done(cache) || - (cache->free_space_ctl->free_space >= num_bytes)); + (progress != atomic_read(&caching_ctl->progress) && + (cache->free_space_ctl->free_space >= num_bytes))); btrfs_put_caching_control(caching_ctl); } @@ -802,8 +812,10 @@ next: if (total_found > CACHING_CTL_WAKE_UP) { total_found = 0; - if (wakeup) + if (wakeup) { + atomic_inc(&caching_ctl->progress); wake_up(&caching_ctl->wait); + } } } path->slots[0]++; @@ -910,6 +922,7 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait) init_waitqueue_head(&caching_ctl->wait); caching_ctl->block_group = cache; refcount_set(&caching_ctl->count, 2); + atomic_set(&caching_ctl->progress, 0); btrfs_init_work(&caching_ctl->work, caching_thread, NULL, NULL); spin_lock(&cache->lock); diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index aba5dff66c19..74b61e663028 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -90,6 +90,8 @@ struct btrfs_caching_control { wait_queue_head_t wait; struct btrfs_work work; struct btrfs_block_group *block_group; + /* Track progress of caching during allocation. */ + atomic_t progress; refcount_t count; }; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index f2d2b313bde5..9419f4e37a58 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -443,6 +443,7 @@ struct btrfs_drop_extents_args { struct btrfs_file_private { void *filldir_buf; + u64 last_index; struct extent_state *llseek_cached_state; }; diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 6b457b010cbc..6d51db066503 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1632,6 +1632,7 @@ int btrfs_inode_delayed_dir_index_count(struct btrfs_inode *inode) } bool btrfs_readdir_get_delayed_items(struct inode *inode, + u64 last_index, struct list_head *ins_list, struct list_head *del_list) { @@ -1651,14 +1652,14 @@ bool btrfs_readdir_get_delayed_items(struct inode *inode, mutex_lock(&delayed_node->mutex); item = __btrfs_first_delayed_insertion_item(delayed_node); - while (item) { + while (item && item->index <= last_index) { refcount_inc(&item->refs); list_add_tail(&item->readdir_list, ins_list); item = __btrfs_next_delayed_item(item); } item = __btrfs_first_delayed_deletion_item(delayed_node); - while (item) { + while (item && item->index <= last_index) { refcount_inc(&item->refs); list_add_tail(&item->readdir_list, del_list); item = __btrfs_next_delayed_item(item); diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h index 4f21daa3dbc7..dc1085b2a397 100644 --- a/fs/btrfs/delayed-inode.h +++ b/fs/btrfs/delayed-inode.h @@ -148,6 +148,7 @@ void btrfs_destroy_delayed_inodes(struct btrfs_fs_info *fs_info); /* Used for readdir() */ bool btrfs_readdir_get_delayed_items(struct inode *inode, + u64 last_index, struct list_head *ins_list, struct list_head *del_list); void btrfs_readdir_put_delayed_items(struct inode *inode, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 9b9914e5f03d..a9a2c5446c18 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1103,7 +1103,8 @@ static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev) btrfs_drew_lock_init(&root->snapshot_lock); if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID && - !btrfs_is_data_reloc_root(root)) { + !btrfs_is_data_reloc_root(root) && + is_fstree(root->root_key.objectid)) { set_bit(BTRFS_ROOT_SHAREABLE, &root->state); btrfs_check_and_init_root_item(&root->root_item); } @@ -1300,6 +1301,16 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, root = btrfs_get_global_root(fs_info, objectid); if (root) return root; + + /* + * If we're called for non-subvolume trees, and above function didn't + * find one, do not try to read it from disk. + * + * This is namely for free-space-tree and quota tree, which can change + * at runtime and should only be grabbed from fs_info. + */ + if (!is_fstree(objectid) && objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) + return ERR_PTR(-ENOENT); again: root = btrfs_lookup_fs_root(fs_info, objectid); if (root) { diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 911908ea5f6f..f396a9afa403 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4310,8 +4310,11 @@ have_block_group: ret = 0; } - if (unlikely(block_group->cached == BTRFS_CACHE_ERROR)) + if (unlikely(block_group->cached == BTRFS_CACHE_ERROR)) { + if (!cache_block_group_error) + cache_block_group_error = -EIO; goto loop; + } if (!find_free_extent_check_size_class(ffe_ctl, block_group)) goto loop; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index a91d5ad27984..90ad3006ef3a 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -902,7 +902,30 @@ static void submit_extent_page(struct btrfs_bio_ctrl *bio_ctrl, size -= len; pg_offset += len; disk_bytenr += len; - bio_ctrl->len_to_oe_boundary -= len; + + /* + * len_to_oe_boundary defaults to U32_MAX, which isn't page or + * sector aligned. alloc_new_bio() then sets it to the end of + * our ordered extent for writes into zoned devices. + * + * When len_to_oe_boundary is tracking an ordered extent, we + * trust the ordered extent code to align things properly, and + * the check above to cap our write to the ordered extent + * boundary is correct. + * + * When len_to_oe_boundary is U32_MAX, the cap above would + * result in a 4095 byte IO for the last page right before + * we hit the bio limit of UINT_MAX. bio_add_page() has all + * the checks required to make sure we don't overflow the bio, + * and we should just ignore len_to_oe_boundary completely + * unless we're using it to track an ordered extent. + * + * It's pretty hard to make a bio sized U32_MAX, but it can + * happen when the page cache is able to feed us contiguous + * pages for large extents. + */ + if (bio_ctrl->len_to_oe_boundary != U32_MAX) + bio_ctrl->len_to_oe_boundary -= len; /* Ordered extent boundary: move on to a new bio. */ if (bio_ctrl->len_to_oe_boundary == 0) @@ -2145,6 +2168,12 @@ retry: continue; } + if (!folio_test_dirty(folio)) { + /* Someone wrote it for us. */ + folio_unlock(folio); + continue; + } + if (wbc->sync_mode != WB_SYNC_NONE) { if (folio_test_writeback(folio)) submit_write_bio(bio_ctrl, 0); @@ -2164,11 +2193,12 @@ retry: } /* - * the filesystem may choose to bump up nr_to_write. + * The filesystem may choose to bump up nr_to_write. * We have to make sure to honor the new nr_to_write - * at any time + * at any time. */ - nr_to_write_done = wbc->nr_to_write <= 0; + nr_to_write_done = (wbc->sync_mode == WB_SYNC_NONE && + wbc->nr_to_write <= 0); } folio_batch_release(&fbatch); cond_resched(); diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 0cdb3e86f29b..a6d8368ed0ed 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -760,8 +760,6 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end, if (skip_pinned && test_bit(EXTENT_FLAG_PINNED, &em->flags)) { start = em_end; - if (end != (u64)-1) - len = start + len - em_end; goto next; } @@ -829,8 +827,8 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end, if (!split) goto remove_em; } - split->start = start + len; - split->len = em_end - (start + len); + split->start = end; + split->len = em_end - end; split->block_start = em->block_start; split->flags = flags; split->compress_type = em->compress_type; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 49cef61f6a39..aa090b0b5d29 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1654,8 +1654,6 @@ out_unlock: clear_bits, page_ops); start += cur_alloc_size; - if (start >= end) - return ret; } /* @@ -1664,9 +1662,11 @@ out_unlock: * space_info's bytes_may_use counter, reserved in * btrfs_check_data_free_space(). */ - extent_clear_unlock_delalloc(inode, start, end, locked_page, - clear_bits | EXTENT_CLEAR_DATA_RESV, - page_ops); + if (start < end) { + clear_bits |= EXTENT_CLEAR_DATA_RESV; + extent_clear_unlock_delalloc(inode, start, end, locked_page, + clear_bits, page_ops); + } return ret; } @@ -5873,6 +5873,74 @@ static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry, } /* + * Find the highest existing sequence number in a directory and then set the + * in-memory index_cnt variable to the first free sequence number. + */ +static int btrfs_set_inode_index_count(struct btrfs_inode *inode) +{ + struct btrfs_root *root = inode->root; + struct btrfs_key key, found_key; + struct btrfs_path *path; + struct extent_buffer *leaf; + int ret; + + key.objectid = btrfs_ino(inode); + key.type = BTRFS_DIR_INDEX_KEY; + key.offset = (u64)-1; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) + goto out; + /* FIXME: we should be able to handle this */ + if (ret == 0) + goto out; + ret = 0; + + if (path->slots[0] == 0) { + inode->index_cnt = BTRFS_DIR_START_INDEX; + goto out; + } + + path->slots[0]--; + + leaf = path->nodes[0]; + btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); + + if (found_key.objectid != btrfs_ino(inode) || + found_key.type != BTRFS_DIR_INDEX_KEY) { + inode->index_cnt = BTRFS_DIR_START_INDEX; + goto out; + } + + inode->index_cnt = found_key.offset + 1; +out: + btrfs_free_path(path); + return ret; +} + +static int btrfs_get_dir_last_index(struct btrfs_inode *dir, u64 *index) +{ + if (dir->index_cnt == (u64)-1) { + int ret; + + ret = btrfs_inode_delayed_dir_index_count(dir); + if (ret) { + ret = btrfs_set_inode_index_count(dir); + if (ret) + return ret; + } + } + + *index = dir->index_cnt; + + return 0; +} + +/* * All this infrastructure exists because dir_emit can fault, and we are holding * the tree lock when doing readdir. For now just allocate a buffer and copy * our information into that, and then dir_emit from the buffer. This is @@ -5884,10 +5952,17 @@ static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry, static int btrfs_opendir(struct inode *inode, struct file *file) { struct btrfs_file_private *private; + u64 last_index; + int ret; + + ret = btrfs_get_dir_last_index(BTRFS_I(inode), &last_index); + if (ret) + return ret; private = kzalloc(sizeof(struct btrfs_file_private), GFP_KERNEL); if (!private) return -ENOMEM; + private->last_index = last_index; private->filldir_buf = kzalloc(PAGE_SIZE, GFP_KERNEL); if (!private->filldir_buf) { kfree(private); @@ -5954,7 +6029,8 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) INIT_LIST_HEAD(&ins_list); INIT_LIST_HEAD(&del_list); - put = btrfs_readdir_get_delayed_items(inode, &ins_list, &del_list); + put = btrfs_readdir_get_delayed_items(inode, private->last_index, + &ins_list, &del_list); again: key.type = BTRFS_DIR_INDEX_KEY; @@ -5972,6 +6048,8 @@ again: break; if (found_key.offset < ctx->pos) continue; + if (found_key.offset > private->last_index) + break; if (btrfs_should_delete_dir_index(&del_list, found_key.offset)) continue; di = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dir_item); @@ -6108,57 +6186,6 @@ static int btrfs_update_time(struct inode *inode, struct timespec64 *now, } /* - * find the highest existing sequence number in a directory - * and then set the in-memory index_cnt variable to reflect - * free sequence numbers - */ -static int btrfs_set_inode_index_count(struct btrfs_inode *inode) -{ - struct btrfs_root *root = inode->root; - struct btrfs_key key, found_key; - struct btrfs_path *path; - struct extent_buffer *leaf; - int ret; - - key.objectid = btrfs_ino(inode); - key.type = BTRFS_DIR_INDEX_KEY; - key.offset = (u64)-1; - - path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; - - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) - goto out; - /* FIXME: we should be able to handle this */ - if (ret == 0) - goto out; - ret = 0; - - if (path->slots[0] == 0) { - inode->index_cnt = BTRFS_DIR_START_INDEX; - goto out; - } - - path->slots[0]--; - - leaf = path->nodes[0]; - btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); - - if (found_key.objectid != btrfs_ino(inode) || - found_key.type != BTRFS_DIR_INDEX_KEY) { - inode->index_cnt = BTRFS_DIR_START_INDEX; - goto out; - } - - inode->index_cnt = found_key.offset + 1; -out: - btrfs_free_path(path); - return ret; -} - -/* * helper to find a free sequence number in a given directory. This current * code is very simple, later versions will do smarter things in the btree */ diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 25a3361caedc..46c3c1d57266 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1916,7 +1916,39 @@ again: err = PTR_ERR(root); break; } - ASSERT(root->reloc_root == reloc_root); + + if (unlikely(root->reloc_root != reloc_root)) { + if (root->reloc_root) { + btrfs_err(fs_info, +"reloc tree mismatch, root %lld has reloc root key (%lld %u %llu) gen %llu, expect reloc root key (%lld %u %llu) gen %llu", + root->root_key.objectid, + root->reloc_root->root_key.objectid, + root->reloc_root->root_key.type, + root->reloc_root->root_key.offset, + btrfs_root_generation( + &root->reloc_root->root_item), + reloc_root->root_key.objectid, + reloc_root->root_key.type, + reloc_root->root_key.offset, + btrfs_root_generation( + &reloc_root->root_item)); + } else { + btrfs_err(fs_info, +"reloc tree mismatch, root %lld has no reloc root, expect reloc root key (%lld %u %llu) gen %llu", + root->root_key.objectid, + reloc_root->root_key.objectid, + reloc_root->root_key.type, + reloc_root->root_key.offset, + btrfs_root_generation( + &reloc_root->root_item)); + } + list_add(&reloc_root->root_list, &reloc_roots); + btrfs_put_root(root); + btrfs_abort_transaction(trans, -EUCLEAN); + if (!err) + err = -EUCLEAN; + break; + } /* * set reference count to 1, so btrfs_recover_relocation @@ -1989,7 +2021,7 @@ again: root = btrfs_get_fs_root(fs_info, reloc_root->root_key.offset, false); if (btrfs_root_refs(&reloc_root->root_item) > 0) { - if (IS_ERR(root)) { + if (WARN_ON(IS_ERR(root))) { /* * For recovery we read the fs roots on mount, * and if we didn't find the root then we marked @@ -1998,17 +2030,14 @@ again: * memory. However there's no reason we can't * handle the error properly here just in case. */ - ASSERT(0); ret = PTR_ERR(root); goto out; } - if (root->reloc_root != reloc_root) { + if (WARN_ON(root->reloc_root != reloc_root)) { /* - * This is actually impossible without something - * going really wrong (like weird race condition - * or cosmic rays). + * This can happen if on-disk metadata has some + * corruption, e.g. bad reloc tree key offset. */ - ASSERT(0); ret = -EINVAL; goto out; } diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 4cae41bd6de0..7289f5bff397 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -605,7 +605,8 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr btrfs_stack_header_bytenr(header), logical); return; } - if (memcmp(header->fsid, fs_info->fs_devices->fsid, BTRFS_FSID_SIZE) != 0) { + if (memcmp(header->fsid, fs_info->fs_devices->metadata_uuid, + BTRFS_FSID_SIZE) != 0) { bitmap_set(&stripe->meta_error_bitmap, sector_nr, sectors_per_tree); bitmap_set(&stripe->error_bitmap, sector_nr, sectors_per_tree); btrfs_warn_rl(fs_info, diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 038dfa8f1788..ab08a0b01311 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -446,6 +446,20 @@ static int check_root_key(struct extent_buffer *leaf, struct btrfs_key *key, btrfs_item_key_to_cpu(leaf, &item_key, slot); is_root_item = (item_key.type == BTRFS_ROOT_ITEM_KEY); + /* + * Bad rootid for reloc trees. + * + * Reloc trees are only for subvolume trees, other trees only need + * to be COWed to be relocated. + */ + if (unlikely(is_root_item && key->objectid == BTRFS_TREE_RELOC_OBJECTID && + !is_fstree(key->offset))) { + generic_err(leaf, slot, + "invalid reloc tree for root %lld, root id is not a subvolume tree", + key->offset); + return -EUCLEAN; + } + /* No such tree id */ if (unlikely(key->objectid == 0)) { if (is_root_item) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 2ecb76cf3d91..6aa9bf3661ac 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4638,8 +4638,7 @@ int btrfs_cancel_balance(struct btrfs_fs_info *fs_info) } } - BUG_ON(fs_info->balance_ctl || - test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)); + ASSERT(!test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)); atomic_dec(&fs_info->balance_cancel_req); mutex_unlock(&fs_info->balance_mutex); return 0; diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 4a2b39d9a61a..bdcffb04513f 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -2019,9 +2019,10 @@ unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn) } } +WRAP_DIR_ITER(ceph_readdir) // FIXME! const struct file_operations ceph_dir_fops = { .read = ceph_read_dir, - .iterate = ceph_readdir, + .iterate_shared = shared_ceph_readdir, .llseek = ceph_dir_llseek, .open = ceph_open, .release = ceph_release, @@ -2033,7 +2034,7 @@ const struct file_operations ceph_dir_fops = { }; const struct file_operations ceph_snapdir_fops = { - .iterate = ceph_readdir, + .iterate_shared = shared_ceph_readdir, .llseek = ceph_dir_llseek, .open = ceph_open, .release = ceph_release, diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 66048a86c480..5fb367b1d4b0 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -4764,7 +4764,7 @@ static void delayed_work(struct work_struct *work) dout("mdsc delayed_work\n"); - if (mdsc->stopping) + if (mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHED) return; mutex_lock(&mdsc->mutex); @@ -4943,7 +4943,7 @@ void send_flush_mdlog(struct ceph_mds_session *s) void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc) { dout("pre_umount\n"); - mdsc->stopping = 1; + mdsc->stopping = CEPH_MDSC_STOPPING_BEGIN; ceph_mdsc_iterate_sessions(mdsc, send_flush_mdlog, true); ceph_mdsc_iterate_sessions(mdsc, lock_unlock_session, false); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 724307ff89cd..86d2965e68a1 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -380,6 +380,11 @@ struct cap_wait { int want; }; +enum { + CEPH_MDSC_STOPPING_BEGIN = 1, + CEPH_MDSC_STOPPING_FLUSHED = 2, +}; + /* * mds client state */ diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 3fc48b43cab0..a5f52013314d 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -1374,6 +1374,16 @@ static void ceph_kill_sb(struct super_block *s) ceph_mdsc_pre_umount(fsc->mdsc); flush_fs_workqueues(fsc); + /* + * Though the kill_anon_super() will finally trigger the + * sync_filesystem() anyway, we still need to do it here + * and then bump the stage of shutdown to stop the work + * queue as earlier as possible. + */ + sync_filesystem(s); + + fsc->mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHED; + kill_anon_super(s); fsc->client->extra_mon_dispatch = NULL; diff --git a/fs/coda/dir.c b/fs/coda/dir.c index 8450b1bd354b..1b960de2bf39 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -429,21 +429,14 @@ static int coda_readdir(struct file *coda_file, struct dir_context *ctx) cfi = coda_ftoc(coda_file); host_file = cfi->cfi_container; - if (host_file->f_op->iterate || host_file->f_op->iterate_shared) { + if (host_file->f_op->iterate_shared) { struct inode *host_inode = file_inode(host_file); ret = -ENOENT; if (!IS_DEADDIR(host_inode)) { - if (host_file->f_op->iterate_shared) { - inode_lock_shared(host_inode); - ret = host_file->f_op->iterate_shared(host_file, ctx); - file_accessed(host_file); - inode_unlock_shared(host_inode); - } else { - inode_lock(host_inode); - ret = host_file->f_op->iterate(host_file, ctx); - file_accessed(host_file); - inode_unlock(host_inode); - } + inode_lock_shared(host_inode); + ret = host_file->f_op->iterate_shared(host_file, ctx); + file_accessed(host_file); + inode_unlock_shared(host_inode); } return ret; } @@ -585,10 +578,11 @@ const struct inode_operations coda_dir_inode_operations = { .setattr = coda_setattr, }; +WRAP_DIR_ITER(coda_readdir) // FIXME! const struct file_operations coda_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = coda_readdir, + .iterate_shared = shared_coda_readdir, .open = coda_open, .release = coda_release, .fsync = coda_fsync, diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 9d6a3c6158bd..566f68ddfa36 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -889,8 +889,6 @@ static void erofs_kill_sb(struct super_block *sb) { struct erofs_sb_info *sbi; - WARN_ON(sb->s_magic != EROFS_SUPER_MAGIC); - /* pseudo mount for anon inodes */ if (sb->s_flags & SB_KERNMOUNT) { kill_anon_super(sb); diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index b69d89a11dd0..de4f12152b62 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1144,10 +1144,11 @@ static void z_erofs_do_decompressed_bvec(struct z_erofs_decompress_backend *be, struct z_erofs_bvec *bvec) { struct z_erofs_bvec_item *item; + unsigned int pgnr; - if (!((bvec->offset + be->pcl->pageofs_out) & ~PAGE_MASK)) { - unsigned int pgnr; - + if (!((bvec->offset + be->pcl->pageofs_out) & ~PAGE_MASK) && + (bvec->end == PAGE_SIZE || + bvec->offset + bvec->end == be->pcl->length)) { pgnr = (bvec->offset + be->pcl->pageofs_out) >> PAGE_SHIFT; DBG_BUGON(pgnr >= be->nr_pages); if (!be->decompressed_pages[pgnr]) { diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c index 9f42f25fab92..e918decb3735 100644 --- a/fs/exfat/balloc.c +++ b/fs/exfat/balloc.c @@ -69,7 +69,7 @@ static int exfat_allocate_bitmap(struct super_block *sb, } sbi->map_sectors = ((need_map_size - 1) >> (sb->s_blocksize_bits)) + 1; - sbi->vol_amap = kmalloc_array(sbi->map_sectors, + sbi->vol_amap = kvmalloc_array(sbi->map_sectors, sizeof(struct buffer_head *), GFP_KERNEL); if (!sbi->vol_amap) return -ENOMEM; @@ -84,7 +84,7 @@ static int exfat_allocate_bitmap(struct super_block *sb, while (j < i) brelse(sbi->vol_amap[j++]); - kfree(sbi->vol_amap); + kvfree(sbi->vol_amap); sbi->vol_amap = NULL; return -EIO; } @@ -138,7 +138,7 @@ void exfat_free_bitmap(struct exfat_sb_info *sbi) for (i = 0; i < sbi->map_sectors; i++) __brelse(sbi->vol_amap[i]); - kfree(sbi->vol_amap); + kvfree(sbi->vol_amap); } int exfat_set_bitmap(struct inode *inode, unsigned int clu, bool sync) diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c index 957574180a5e..e1586bba6d86 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -34,6 +34,7 @@ static int exfat_get_uniname_from_ext_entry(struct super_block *sb, { int i, err; struct exfat_entry_set_cache es; + unsigned int uni_len = 0, len; err = exfat_get_dentry_set(&es, sb, p_dir, entry, ES_ALL_ENTRIES); if (err) @@ -52,7 +53,10 @@ static int exfat_get_uniname_from_ext_entry(struct super_block *sb, if (exfat_get_entry_type(ep) != TYPE_EXTEND) break; - exfat_extract_uni_name(ep, uniname); + len = exfat_extract_uni_name(ep, uniname); + uni_len += len; + if (len != EXFAT_FILE_NAME_LEN || uni_len >= MAX_NAME_LENGTH) + break; uniname += EXFAT_FILE_NAME_LEN; } @@ -214,7 +218,10 @@ static void exfat_free_namebuf(struct exfat_dentry_namebuf *nb) exfat_init_namebuf(nb); } -/* skip iterating emit_dots when dir is empty */ +/* + * Before calling dir_emit*(), sbi->s_lock should be released + * because page fault can occur in dir_emit*(). + */ #define ITER_POS_FILLED_DOTS (2) static int exfat_iterate(struct file *file, struct dir_context *ctx) { @@ -229,11 +236,10 @@ static int exfat_iterate(struct file *file, struct dir_context *ctx) int err = 0, fake_offset = 0; exfat_init_namebuf(nb); - mutex_lock(&EXFAT_SB(sb)->s_lock); cpos = ctx->pos; if (!dir_emit_dots(file, ctx)) - goto unlock; + goto out; if (ctx->pos == ITER_POS_FILLED_DOTS) { cpos = 0; @@ -245,16 +251,18 @@ static int exfat_iterate(struct file *file, struct dir_context *ctx) /* name buffer should be allocated before use */ err = exfat_alloc_namebuf(nb); if (err) - goto unlock; + goto out; get_new: + mutex_lock(&EXFAT_SB(sb)->s_lock); + if (ei->flags == ALLOC_NO_FAT_CHAIN && cpos >= i_size_read(inode)) goto end_of_dir; err = exfat_readdir(inode, &cpos, &de); if (err) { /* - * At least we tried to read a sector. Move cpos to next sector - * position (should be aligned). + * At least we tried to read a sector. + * Move cpos to next sector position (should be aligned). */ if (err == -EIO) { cpos += 1 << (sb->s_blocksize_bits); @@ -277,16 +285,10 @@ get_new: inum = iunique(sb, EXFAT_ROOT_INO); } - /* - * Before calling dir_emit(), sb_lock should be released. - * Because page fault can occur in dir_emit() when the size - * of buffer given from user is larger than one page size. - */ mutex_unlock(&EXFAT_SB(sb)->s_lock); if (!dir_emit(ctx, nb->lfn, strlen(nb->lfn), inum, (de.attr & ATTR_SUBDIR) ? DT_DIR : DT_REG)) - goto out_unlocked; - mutex_lock(&EXFAT_SB(sb)->s_lock); + goto out; ctx->pos = cpos; goto get_new; @@ -294,9 +296,8 @@ end_of_dir: if (!cpos && fake_offset) cpos = ITER_POS_FILLED_DOTS; ctx->pos = cpos; -unlock: mutex_unlock(&EXFAT_SB(sb)->s_lock); -out_unlocked: +out: /* * To improve performance, free namebuf after unlock sb_lock. * If namebuf is not allocated, this function do nothing @@ -305,10 +306,11 @@ out_unlocked: return err; } +WRAP_DIR_ITER(exfat_iterate) // FIXME! const struct file_operations exfat_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = exfat_iterate, + .iterate_shared = shared_exfat_iterate, .unlocked_ioctl = exfat_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = exfat_compat_ioctl, @@ -1079,7 +1081,8 @@ rewind: if (entry_type == TYPE_EXTEND) { unsigned short entry_uniname[16], unichar; - if (step != DIRENT_STEP_NAME) { + if (step != DIRENT_STEP_NAME || + name_len >= MAX_NAME_LENGTH) { step = DIRENT_STEP_FILE; continue; } diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 40e624cf7e92..d1dbe47c7975 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -315,7 +315,7 @@ static int get_name(const struct path *path, char *name, struct dentry *child) goto out; error = -EINVAL; - if (!file->f_op->iterate && !file->f_op->iterate_shared) + if (!file->f_op->iterate_shared) goto out_close; buffer.sequence = 0; diff --git a/fs/file.c b/fs/file.c index 35c62b54c9d6..3fd003a8604f 100644 --- a/fs/file.c +++ b/fs/file.c @@ -1036,12 +1036,28 @@ unsigned long __fdget_raw(unsigned int fd) return __fget_light(fd, 0); } +/* + * Try to avoid f_pos locking. We only need it if the + * file is marked for FMODE_ATOMIC_POS, and it can be + * accessed multiple ways. + * + * Always do it for directories, because pidfd_getfd() + * can make a file accessible even if it otherwise would + * not be, and for directories this is a correctness + * issue, not a "POSIX requirement". + */ +static inline bool file_needs_f_pos_lock(struct file *file) +{ + return (file->f_mode & FMODE_ATOMIC_POS) && + (file_count(file) > 1 || file->f_op->iterate_shared); +} + unsigned long __fdget_pos(unsigned int fd) { unsigned long v = __fdget(fd); struct file *file = (struct file *)(v & ~3); - if (file && (file->f_mode & FMODE_ATOMIC_POS)) { + if (file && file_needs_f_pos_lock(file)) { v |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); } diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 1bf3c4453516..b43fa8b8fc05 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -1578,7 +1578,7 @@ const struct file_operations gfs2_file_fops = { .fsync = gfs2_fsync, .lock = gfs2_lock, .flock = gfs2_flock, - .splice_read = filemap_splice_read, + .splice_read = copy_splice_read, .splice_write = gfs2_file_splice_write, .setlease = simple_nosetlease, .fallocate = gfs2_fallocate, @@ -1609,7 +1609,7 @@ const struct file_operations gfs2_file_fops_nolock = { .open = gfs2_open, .release = gfs2_release, .fsync = gfs2_fsync, - .splice_read = filemap_splice_read, + .splice_read = copy_splice_read, .splice_write = gfs2_file_splice_write, .setlease = generic_setlease, .fallocate = gfs2_fallocate, diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index ec1631257978..7e835be7032d 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -230,9 +230,11 @@ void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + struct super_block *sb = sdp->sd_vfs; struct gfs2_bufdata *bd; struct gfs2_meta_header *mh; struct gfs2_trans *tr = current->journal_info; + bool withdraw = false; lock_buffer(bh); if (buffer_pinned(bh)) { @@ -266,13 +268,15 @@ void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh) (unsigned long long)bd->bd_bh->b_blocknr); BUG(); } - if (unlikely(test_bit(SDF_FROZEN, &sdp->sd_flags))) { - fs_info(sdp, "GFS2:adding buf while frozen\n"); - gfs2_assert_withdraw(sdp, 0); - } if (unlikely(gfs2_withdrawn(sdp))) { fs_info(sdp, "GFS2:adding buf while withdrawn! 0x%llx\n", (unsigned long long)bd->bd_bh->b_blocknr); + goto out_unlock; + } + if (unlikely(sb->s_writers.frozen == SB_FREEZE_COMPLETE)) { + fs_info(sdp, "GFS2:adding buf while frozen\n"); + withdraw = true; + goto out_unlock; } gfs2_pin(sdp, bd->bd_bh); mh->__pad0 = cpu_to_be64(0); @@ -281,6 +285,8 @@ void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh) tr->tr_num_buf_new++; out_unlock: gfs2_log_unlock(sdp); + if (withdraw) + gfs2_assert_withdraw(sdp, 0); out: unlock_buffer(bh); } diff --git a/fs/inode.c b/fs/inode.c index 8fefb69e1f84..67611a360031 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -16,7 +16,6 @@ #include <linux/fsnotify.h> #include <linux/mount.h> #include <linux/posix_acl.h> -#include <linux/prefetch.h> #include <linux/buffer_head.h> /* for inode_has_buffers */ #include <linux/ratelimit.h> #include <linux/list_lru.h> @@ -1041,8 +1040,6 @@ struct inode *new_inode(struct super_block *sb) { struct inode *inode; - spin_lock_prefetch(&sb->s_inode_list_lock); - inode = new_inode_pseudo(sb); if (inode) inode_sb_list_add(inode); diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 9b030297aa64..e98ddb2b1cf2 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -1535,9 +1535,10 @@ const struct inode_operations jfs_dir_inode_operations = { #endif }; +WRAP_DIR_ITER(jfs_readdir) // FIXME! const struct file_operations jfs_dir_operations = { .read = generic_read_dir, - .iterate = jfs_readdir, + .iterate_shared = shared_jfs_readdir, .fsync = jfs_fsync, .unlocked_ioctl = jfs_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 8a2321d19194..2c9074ab2315 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -956,10 +956,13 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf, last_page = page + (offset + sd->len - 1) / PAGE_SIZE; for (page += offset / PAGE_SIZE; page <= last_page; page++) { /* - * Skip page replacement when extending the contents - * of the current page. + * Skip page replacement when extending the contents of the + * current page. But note that we may get two zero_pages in a + * row from shmem. */ - if (page == *(rqstp->rq_next_page - 1)) + if (page == *(rqstp->rq_next_page - 1) && + offset_in_page(rqstp->rq_res.page_base + + rqstp->rq_res.page_len)) continue; if (unlikely(!svc_rqst_replace_page(rqstp, page))) return -EIO; diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index a8ce522ac747..35bc79305318 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -1101,9 +1101,17 @@ int nilfs_set_file_dirty(struct inode *inode, unsigned int nr_dirty) int __nilfs_mark_inode_dirty(struct inode *inode, int flags) { + struct the_nilfs *nilfs = inode->i_sb->s_fs_info; struct buffer_head *ibh; int err; + /* + * Do not dirty inodes after the log writer has been detached + * and its nilfs_root struct has been freed. + */ + if (unlikely(nilfs_purging(nilfs))) + return 0; + err = nilfs_load_inode_block(inode, &ibh); if (unlikely(err)) { nilfs_warn(inode->i_sb, diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index c2553024bd25..581691e4be49 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2845,6 +2845,7 @@ void nilfs_detach_log_writer(struct super_block *sb) nilfs_segctor_destroy(nilfs->ns_writer); nilfs->ns_writer = NULL; } + set_nilfs_purging(nilfs); /* Force to free the list of dirty files */ spin_lock(&nilfs->ns_inode_lock); @@ -2857,4 +2858,5 @@ void nilfs_detach_log_writer(struct super_block *sb) up_write(&nilfs->ns_segctor_sem); nilfs_dispose_list(nilfs, &garbage_list, 1); + clear_nilfs_purging(nilfs); } diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h index 47c7dfbb7ea5..cd4ae1b8ae16 100644 --- a/fs/nilfs2/the_nilfs.h +++ b/fs/nilfs2/the_nilfs.h @@ -29,6 +29,7 @@ enum { THE_NILFS_DISCONTINUED, /* 'next' pointer chain has broken */ THE_NILFS_GC_RUNNING, /* gc process is running */ THE_NILFS_SB_DIRTY, /* super block is dirty */ + THE_NILFS_PURGING, /* disposing dirty files for cleanup */ }; /** @@ -208,6 +209,7 @@ THE_NILFS_FNS(INIT, init) THE_NILFS_FNS(DISCONTINUED, discontinued) THE_NILFS_FNS(GC_RUNNING, gc_running) THE_NILFS_FNS(SB_DIRTY, sb_dirty) +THE_NILFS_FNS(PURGING, purging) /* * Mount option operations diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c index 518c3a21a556..4596c90e7b7c 100644 --- a/fs/ntfs/dir.c +++ b/fs/ntfs/dir.c @@ -1525,10 +1525,11 @@ static int ntfs_dir_fsync(struct file *filp, loff_t start, loff_t end, #endif /* NTFS_RW */ +WRAP_DIR_ITER(ntfs_readdir) // FIXME! const struct file_operations ntfs_dir_ops = { .llseek = generic_file_llseek, /* Seek inside directory. */ .read = generic_read_dir, /* Return -EISDIR. */ - .iterate = ntfs_readdir, /* Read directory contents. */ + .iterate_shared = shared_ntfs_readdir, /* Read directory contents. */ #ifdef NTFS_RW .fsync = ntfs_dir_fsync, /* Sync a directory to disk. */ #endif /* NTFS_RW */ diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 91a194596552..bf2c17ea96a0 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2793,10 +2793,11 @@ const struct file_operations ocfs2_fops = { .remap_file_range = ocfs2_remap_file_range, }; +WRAP_DIR_ITER(ocfs2_readdir) // FIXME! const struct file_operations ocfs2_dops = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = ocfs2_readdir, + .iterate_shared = shared_ocfs2_readdir, .fsync = ocfs2_sync_file, .release = ocfs2_dir_release, .open = ocfs2_dir_open, @@ -2842,7 +2843,7 @@ const struct file_operations ocfs2_fops_no_plocks = { const struct file_operations ocfs2_dops_no_plocks = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = ocfs2_readdir, + .iterate_shared = shared_ocfs2_readdir, .fsync = ocfs2_sync_file, .release = ocfs2_dir_release, .open = ocfs2_dir_open, diff --git a/fs/open.c b/fs/open.c index 0c55c8e7f837..e6ead0f19964 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1322,7 +1322,7 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op) lookup_flags |= LOOKUP_IN_ROOT; if (how->resolve & RESOLVE_CACHED) { /* Don't bother even trying for create/truncate/tmpfile open */ - if (flags & (O_TRUNC | O_CREAT | O_TMPFILE)) + if (flags & (O_TRUNC | O_CREAT | __O_TMPFILE)) return -EAGAIN; lookup_flags |= LOOKUP_CACHED; } diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index ee5c4736480f..de39e067ae65 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -954,10 +954,11 @@ static int ovl_dir_open(struct inode *inode, struct file *file) return 0; } +WRAP_DIR_ITER(ovl_iterate) // FIXME! const struct file_operations ovl_dir_operations = { .read = generic_read_dir, .open = ovl_dir_open, - .iterate = ovl_iterate, + .iterate_shared = shared_ovl_iterate, .llseek = ovl_dir_llseek, .fsync = ovl_dir_fsync, .release = ovl_dir_release, diff --git a/fs/proc/base.c b/fs/proc/base.c index 05452c3b9872..9df3f4839662 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2817,7 +2817,7 @@ static int proc_##LSM##_attr_dir_iterate(struct file *filp, \ \ static const struct file_operations proc_##LSM##_attr_dir_ops = { \ .read = generic_read_dir, \ - .iterate = proc_##LSM##_attr_dir_iterate, \ + .iterate_shared = proc_##LSM##_attr_dir_iterate, \ .llseek = default_llseek, \ }; \ \ diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 9cb32e1a78a0..23fc24d16b31 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -309,6 +309,8 @@ static void append_kcore_note(char *notes, size_t *i, const char *name, static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) { + struct file *file = iocb->ki_filp; + char *buf = file->private_data; loff_t *fpos = &iocb->ki_pos; size_t phdrs_offset, notes_offset, data_offset; size_t page_offline_frozen = 1; @@ -555,10 +557,21 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) case KCORE_VMEMMAP: case KCORE_TEXT: /* - * We use _copy_to_iter() to bypass usermode hardening - * which would otherwise prevent this operation. + * Sadly we must use a bounce buffer here to be able to + * make use of copy_from_kernel_nofault(), as these + * memory regions might not always be mapped on all + * architectures. */ - if (_copy_to_iter((char *)start, tsz, iter) != tsz) { + if (copy_from_kernel_nofault(buf, (void *)start, tsz)) { + if (iov_iter_zero(tsz, iter) != tsz) { + ret = -EFAULT; + goto out; + } + /* + * We know the bounce buffer is safe to copy from, so + * use _copy_to_iter() directly. + */ + } else if (_copy_to_iter(buf, tsz, iter) != tsz) { ret = -EFAULT; goto out; } @@ -595,6 +608,10 @@ static int open_kcore(struct inode *inode, struct file *filp) if (ret) return ret; + filp->private_data = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!filp->private_data) + return -ENOMEM; + if (kcore_need_update) kcore_update_ram(); if (i_size_read(inode) != proc_root_kcore->size) { @@ -605,9 +622,16 @@ static int open_kcore(struct inode *inode, struct file *filp) return 0; } +static int release_kcore(struct inode *inode, struct file *file) +{ + kfree(file->private_data); + return 0; +} + static const struct proc_ops kcore_proc_ops = { .proc_read_iter = read_kcore_iter, .proc_open = open_kcore, + .proc_release = release_kcore, .proc_lseek = default_llseek, }; diff --git a/fs/readdir.c b/fs/readdir.c index b264ce60114d..c8c46e294431 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -25,6 +25,53 @@ #include <asm/unaligned.h> /* + * Some filesystems were never converted to '->iterate_shared()' + * and their directory iterators want the inode lock held for + * writing. This wrapper allows for converting from the shared + * semantics to the exclusive inode use. + */ +int wrap_directory_iterator(struct file *file, + struct dir_context *ctx, + int (*iter)(struct file *, struct dir_context *)) +{ + struct inode *inode = file_inode(file); + int ret; + + /* + * We'd love to have an 'inode_upgrade_trylock()' operation, + * see the comment in mmap_upgrade_trylock() in mm/memory.c. + * + * But considering this is for "filesystems that never got + * converted", it really doesn't matter. + * + * Also note that since we have to return with the lock held + * for reading, we can't use the "killable()" locking here, + * since we do need to get the lock even if we're dying. + * + * We could do the write part killably and then get the read + * lock unconditionally if it mattered, but see above on why + * this does the very simplistic conversion. + */ + up_read(&inode->i_rwsem); + down_write(&inode->i_rwsem); + + /* + * Since we dropped the inode lock, we should do the + * DEADDIR test again. See 'iterate_dir()' below. + * + * Note that we don't need to re-do the f_pos games, + * since the file must be locked wrt f_pos anyway. + */ + ret = -ENOENT; + if (!IS_DEADDIR(inode)) + ret = iter(file, ctx); + + downgrade_write(&inode->i_rwsem); + return ret; +} +EXPORT_SYMBOL(wrap_directory_iterator); + +/* * Note the "unsafe_put_user() semantics: we goto a * label for errors. */ @@ -40,39 +87,28 @@ int iterate_dir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); - bool shared = false; int res = -ENOTDIR; - if (file->f_op->iterate_shared) - shared = true; - else if (!file->f_op->iterate) + + if (!file->f_op->iterate_shared) goto out; res = security_file_permission(file, MAY_READ); if (res) goto out; - if (shared) - res = down_read_killable(&inode->i_rwsem); - else - res = down_write_killable(&inode->i_rwsem); + res = down_read_killable(&inode->i_rwsem); if (res) goto out; res = -ENOENT; if (!IS_DEADDIR(inode)) { ctx->pos = file->f_pos; - if (shared) - res = file->f_op->iterate_shared(file, ctx); - else - res = file->f_op->iterate(file, ctx); + res = file->f_op->iterate_shared(file, ctx); file->f_pos = ctx->pos; fsnotify_access(file); file_accessed(file); } - if (shared) - inode_unlock_shared(inode); - else - inode_unlock(inode); + inode_unlock_shared(inode); out: return res; } diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c index fb4162a52844..aec6e9137474 100644 --- a/fs/smb/client/cifs_debug.c +++ b/fs/smb/client/cifs_debug.c @@ -153,6 +153,11 @@ cifs_dump_channel(struct seq_file *m, int i, struct cifs_chan *chan) in_flight(server), atomic_read(&server->in_send), atomic_read(&server->num_waiters)); +#ifdef CONFIG_NET_NS + if (server->net) + seq_printf(m, " Net namespace: %u ", server->net->ns.inum); +#endif /* NET_NS */ + } static inline const char *smb_speed_to_str(size_t bps) @@ -430,10 +435,15 @@ skip_rdma: server->reconnect_instance, server->srv_count, server->sec_mode, in_flight(server)); +#ifdef CONFIG_NET_NS + if (server->net) + seq_printf(m, " Net namespace: %u ", server->net->ns.inum); +#endif /* NET_NS */ seq_printf(m, "\nIn Send: %d In MaxReq Wait: %d", atomic_read(&server->in_send), atomic_read(&server->num_waiters)); + if (server->leaf_fullpath) { seq_printf(m, "\nDFS leaf full path: %s", server->leaf_fullpath); diff --git a/fs/smb/client/dfs.c b/fs/smb/client/dfs.c index df3fd3b720da..ee772c3d9f00 100644 --- a/fs/smb/client/dfs.c +++ b/fs/smb/client/dfs.c @@ -177,8 +177,12 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) struct dfs_cache_tgt_list tl = DFS_CACHE_TGT_LIST_INIT(tl); rc = dfs_get_referral(mnt_ctx, ref_path + 1, NULL, &tl); - if (rc) + if (rc) { + rc = cifs_mount_get_tcon(mnt_ctx); + if (!rc) + rc = cifs_is_path_remote(mnt_ctx); break; + } tit = dfs_cache_get_tgt_iterator(&tl); if (!tit) { diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index fc5acc95cd13..6bc44f79d2e9 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -4681,9 +4681,9 @@ static int cifs_readpage_worker(struct file *file, struct page *page, io_error: kunmap(page); - unlock_page(page); read_complete: + unlock_page(page); return rc; } @@ -4878,9 +4878,11 @@ void cifs_oplock_break(struct work_struct *work) struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo, oplock_break); struct inode *inode = d_inode(cfile->dentry); + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifsInodeInfo *cinode = CIFS_I(inode); - struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); - struct TCP_Server_Info *server = tcon->ses->server; + struct cifs_tcon *tcon; + struct TCP_Server_Info *server; + struct tcon_link *tlink; int rc = 0; bool purge_cache = false, oplock_break_cancelled; __u64 persistent_fid, volatile_fid; @@ -4889,6 +4891,12 @@ void cifs_oplock_break(struct work_struct *work) wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, TASK_UNINTERRUPTIBLE); + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + goto out; + tcon = tlink_tcon(tlink); + server = tcon->ses->server; + server->ops->downgrade_oplock(server, cinode, cfile->oplock_level, cfile->oplock_epoch, &purge_cache); @@ -4938,18 +4946,19 @@ oplock_break_ack: /* * MS-SMB2 3.2.5.19.1 and 3.2.5.19.2 (and MS-CIFS 3.2.5.42) do not require * an acknowledgment to be sent when the file has already been closed. - * check for server null, since can race with kill_sb calling tree disconnect. */ spin_lock(&cinode->open_file_lock); - if (tcon->ses && tcon->ses->server && !oplock_break_cancelled && - !list_empty(&cinode->openFileList)) { + /* check list empty since can race with kill_sb calling tree disconnect */ + if (!oplock_break_cancelled && !list_empty(&cinode->openFileList)) { spin_unlock(&cinode->open_file_lock); - rc = tcon->ses->server->ops->oplock_response(tcon, persistent_fid, - volatile_fid, net_fid, cinode); + rc = server->ops->oplock_response(tcon, persistent_fid, + volatile_fid, net_fid, cinode); cifs_dbg(FYI, "Oplock release rc = %d\n", rc); } else spin_unlock(&cinode->open_file_lock); + cifs_put_tlink(tlink); +out: cifs_done_oplock_break(cinode); } diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index 4946a0c59600..67e16c2ac90e 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -231,6 +231,8 @@ cifs_parse_security_flavors(struct fs_context *fc, char *value, struct smb3_fs_c break; case Opt_sec_none: ctx->nullauth = 1; + kfree(ctx->username); + ctx->username = NULL; break; default: cifs_errorf(fc, "bad security option: %s\n", value); @@ -1201,6 +1203,8 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, case Opt_user: kfree(ctx->username); ctx->username = NULL; + if (ctx->nullauth) + break; if (strlen(param->string) == 0) { /* null user, ie. anonymous authentication */ ctx->nullauth = 1; diff --git a/fs/smb/server/smb2misc.c b/fs/smb/server/smb2misc.c index 33b7e6c4ceff..e881df1d10cb 100644 --- a/fs/smb/server/smb2misc.c +++ b/fs/smb/server/smb2misc.c @@ -380,13 +380,13 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) } if (smb2_req_struct_sizes[command] != pdu->StructureSize2) { - if (command == SMB2_OPLOCK_BREAK_HE && - le16_to_cpu(pdu->StructureSize2) != OP_BREAK_STRUCT_SIZE_20 && - le16_to_cpu(pdu->StructureSize2) != OP_BREAK_STRUCT_SIZE_21) { + if (!(command == SMB2_OPLOCK_BREAK_HE && + (le16_to_cpu(pdu->StructureSize2) == OP_BREAK_STRUCT_SIZE_20 || + le16_to_cpu(pdu->StructureSize2) == OP_BREAK_STRUCT_SIZE_21))) { /* special case for SMB2.1 lease break message */ ksmbd_debug(SMB, - "Illegal request size %d for oplock break\n", - le16_to_cpu(pdu->StructureSize2)); + "Illegal request size %u for command %d\n", + le16_to_cpu(pdu->StructureSize2), command); return 1; } } diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 9849d7489345..7cc1b0c47d0a 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -2324,9 +2324,16 @@ next: break; buf_len -= next; eabuf = (struct smb2_ea_info *)((char *)eabuf + next); - if (next < (u32)eabuf->EaNameLength + le16_to_cpu(eabuf->EaValueLength)) + if (buf_len < sizeof(struct smb2_ea_info)) { + rc = -EINVAL; break; + } + if (buf_len < sizeof(struct smb2_ea_info) + eabuf->EaNameLength + + le16_to_cpu(eabuf->EaValueLength)) { + rc = -EINVAL; + break; + } } while (next != 0); kfree(attr_name); diff --git a/fs/vboxsf/dir.c b/fs/vboxsf/dir.c index 075f15c43c78..5f1a14d5b927 100644 --- a/fs/vboxsf/dir.c +++ b/fs/vboxsf/dir.c @@ -179,9 +179,10 @@ static int vboxsf_dir_iterate(struct file *dir, struct dir_context *ctx) return 0; } +WRAP_DIR_ITER(vboxsf_dir_iterate) // FIXME! const struct file_operations vboxsf_dir_fops = { .open = vboxsf_dir_open, - .iterate = vboxsf_dir_iterate, + .iterate_shared = shared_vboxsf_dir_iterate, .release = vboxsf_dir_release, .read = generic_read_dir, .llseek = generic_file_llseek, diff --git a/fs/vboxsf/shfl_hostintf.h b/fs/vboxsf/shfl_hostintf.h index aca829062c12..069a019c9247 100644 --- a/fs/vboxsf/shfl_hostintf.h +++ b/fs/vboxsf/shfl_hostintf.h @@ -68,9 +68,9 @@ struct shfl_string { /** UTF-8 or UTF-16 string. Nul terminated. */ union { - u8 utf8[2]; - u16 utf16[1]; - u16 ucs2[1]; /* misnomer, use utf16. */ + u8 legacy_padding[2]; + DECLARE_FLEX_ARRAY(u8, utf8); + DECLARE_FLEX_ARRAY(u16, utf16); } string; }; VMMDEV_ASSERT_SIZE(shfl_string, 6); diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c index 92c9aaae3663..789cfb74c146 100644 --- a/fs/zonefs/file.c +++ b/fs/zonefs/file.c @@ -341,77 +341,6 @@ static loff_t zonefs_file_llseek(struct file *file, loff_t offset, int whence) return generic_file_llseek_size(file, offset, whence, isize, isize); } -struct zonefs_zone_append_bio { - /* The target inode of the BIO */ - struct inode *inode; - - /* For sync writes, the target append write offset */ - u64 append_offset; - - /* - * This member must come last, bio_alloc_bioset will allocate enough - * bytes for entire zonefs_bio but relies on bio being last. - */ - struct bio bio; -}; - -static inline struct zonefs_zone_append_bio * -zonefs_zone_append_bio(struct bio *bio) -{ - return container_of(bio, struct zonefs_zone_append_bio, bio); -} - -static void zonefs_file_zone_append_dio_bio_end_io(struct bio *bio) -{ - struct zonefs_zone_append_bio *za_bio = zonefs_zone_append_bio(bio); - struct zonefs_zone *z = zonefs_inode_zone(za_bio->inode); - sector_t za_sector; - - if (bio->bi_status != BLK_STS_OK) - goto bio_end; - - /* - * If the file zone was written underneath the file system, the zone - * append operation can still succedd (if the zone is not full) but - * the write append location will not be where we expect it to be. - * Check that we wrote where we intended to, that is, at z->z_wpoffset. - */ - za_sector = z->z_sector + (za_bio->append_offset >> SECTOR_SHIFT); - if (bio->bi_iter.bi_sector != za_sector) { - zonefs_warn(za_bio->inode->i_sb, - "Invalid write sector %llu for zone at %llu\n", - bio->bi_iter.bi_sector, z->z_sector); - bio->bi_status = BLK_STS_IOERR; - } - -bio_end: - iomap_dio_bio_end_io(bio); -} - -static void zonefs_file_zone_append_dio_submit_io(const struct iomap_iter *iter, - struct bio *bio, - loff_t file_offset) -{ - struct zonefs_zone_append_bio *za_bio = zonefs_zone_append_bio(bio); - struct inode *inode = iter->inode; - struct zonefs_zone *z = zonefs_inode_zone(inode); - - /* - * Issue a zone append BIO to process sync dio writes. The append - * file offset is saved to check the zone append write location - * on completion of the BIO. - */ - za_bio->inode = inode; - za_bio->append_offset = file_offset; - - bio->bi_opf &= ~REQ_OP_WRITE; - bio->bi_opf |= REQ_OP_ZONE_APPEND; - bio->bi_iter.bi_sector = z->z_sector; - bio->bi_end_io = zonefs_file_zone_append_dio_bio_end_io; - - submit_bio(bio); -} - static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size, int error, unsigned int flags) { @@ -442,14 +371,6 @@ static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size, return 0; } -static struct bio_set zonefs_zone_append_bio_set; - -static const struct iomap_dio_ops zonefs_zone_append_dio_ops = { - .submit_io = zonefs_file_zone_append_dio_submit_io, - .end_io = zonefs_file_write_dio_end_io, - .bio_set = &zonefs_zone_append_bio_set, -}; - static const struct iomap_dio_ops zonefs_write_dio_ops = { .end_io = zonefs_file_write_dio_end_io, }; @@ -533,9 +454,6 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) struct zonefs_inode_info *zi = ZONEFS_I(inode); struct zonefs_zone *z = zonefs_inode_zone(inode); struct super_block *sb = inode->i_sb; - const struct iomap_dio_ops *dio_ops; - bool sync = is_sync_kiocb(iocb); - bool append = false; ssize_t ret, count; /* @@ -543,7 +461,8 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) * as this can cause write reordering (e.g. the first aio gets EAGAIN * on the inode lock but the second goes through but is now unaligned). */ - if (zonefs_zone_is_seq(z) && !sync && (iocb->ki_flags & IOCB_NOWAIT)) + if (zonefs_zone_is_seq(z) && !is_sync_kiocb(iocb) && + (iocb->ki_flags & IOCB_NOWAIT)) return -EOPNOTSUPP; if (iocb->ki_flags & IOCB_NOWAIT) { @@ -573,18 +492,6 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) goto inode_unlock; } mutex_unlock(&zi->i_truncate_mutex); - append = sync; - } - - if (append) { - unsigned int max = bdev_max_zone_append_sectors(sb->s_bdev); - - max = ALIGN_DOWN(max << SECTOR_SHIFT, sb->s_blocksize); - iov_iter_truncate(from, max); - - dio_ops = &zonefs_zone_append_dio_ops; - } else { - dio_ops = &zonefs_write_dio_ops; } /* @@ -593,7 +500,7 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) * the user can make sense of the error. */ ret = iomap_dio_rw(iocb, from, &zonefs_write_iomap_ops, - dio_ops, 0, NULL, 0); + &zonefs_write_dio_ops, 0, NULL, 0); if (ret == -ENOTBLK) ret = -EBUSY; @@ -938,15 +845,3 @@ const struct file_operations zonefs_file_operations = { .splice_write = iter_file_splice_write, .iopoll = iocb_bio_iopoll, }; - -int zonefs_file_bioset_init(void) -{ - return bioset_init(&zonefs_zone_append_bio_set, BIO_POOL_SIZE, - offsetof(struct zonefs_zone_append_bio, bio), - BIOSET_NEED_BVECS); -} - -void zonefs_file_bioset_exit(void) -{ - bioset_exit(&zonefs_zone_append_bio_set); -} diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index bbe44a26a8e5..9350221abfc5 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -1412,13 +1412,9 @@ static int __init zonefs_init(void) BUILD_BUG_ON(sizeof(struct zonefs_super) != ZONEFS_SUPER_SIZE); - ret = zonefs_file_bioset_init(); - if (ret) - return ret; - ret = zonefs_init_inodecache(); if (ret) - goto destroy_bioset; + return ret; ret = zonefs_sysfs_init(); if (ret) @@ -1434,8 +1430,6 @@ sysfs_exit: zonefs_sysfs_exit(); destroy_inodecache: zonefs_destroy_inodecache(); -destroy_bioset: - zonefs_file_bioset_exit(); return ret; } @@ -1445,7 +1439,6 @@ static void __exit zonefs_exit(void) unregister_filesystem(&zonefs_type); zonefs_sysfs_exit(); zonefs_destroy_inodecache(); - zonefs_file_bioset_exit(); } MODULE_AUTHOR("Damien Le Moal"); diff --git a/fs/zonefs/zonefs.h b/fs/zonefs/zonefs.h index f663b8ebc2cb..8175652241b5 100644 --- a/fs/zonefs/zonefs.h +++ b/fs/zonefs/zonefs.h @@ -279,8 +279,6 @@ extern const struct file_operations zonefs_dir_operations; extern const struct address_space_operations zonefs_file_aops; extern const struct file_operations zonefs_file_operations; int zonefs_file_truncate(struct inode *inode, loff_t isize); -int zonefs_file_bioset_init(void); -void zonefs_file_bioset_exit(void); /* In sysfs.c */ int zonefs_sysfs_register(struct super_block *sb); |