diff options
Diffstat (limited to 'fs')
114 files changed, 939 insertions, 604 deletions
diff --git a/fs/affs/file.c b/fs/affs/file.c index a5a861dd5223..7a71018e3f67 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -596,7 +596,7 @@ affs_extent_file_ofs(struct inode *inode, u32 newsize) BUG_ON(tmp > bsize); AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA); AFFS_DATA_HEAD(bh)->key = cpu_to_be32(inode->i_ino); - AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx); + AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx + 1); AFFS_DATA_HEAD(bh)->size = cpu_to_be32(tmp); affs_fix_checksum(sb, bh); bh->b_state &= ~(1UL << BH_New); @@ -724,7 +724,8 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping, tmp = min(bsize - boff, to - from); BUG_ON(boff + tmp > bsize || tmp > bsize); memcpy(AFFS_DATA(bh) + boff, data + from, tmp); - be32_add_cpu(&AFFS_DATA_HEAD(bh)->size, tmp); + AFFS_DATA_HEAD(bh)->size = cpu_to_be32( + max(boff + tmp, be32_to_cpu(AFFS_DATA_HEAD(bh)->size))); affs_fix_checksum(sb, bh); mark_buffer_dirty_inode(bh, inode); written += tmp; @@ -746,7 +747,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping, if (buffer_new(bh)) { AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA); AFFS_DATA_HEAD(bh)->key = cpu_to_be32(inode->i_ino); - AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx); + AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx + 1); AFFS_DATA_HEAD(bh)->size = cpu_to_be32(bsize); AFFS_DATA_HEAD(bh)->next = 0; bh->b_state &= ~(1UL << BH_New); @@ -780,7 +781,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping, if (buffer_new(bh)) { AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA); AFFS_DATA_HEAD(bh)->key = cpu_to_be32(inode->i_ino); - AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx); + AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx + 1); AFFS_DATA_HEAD(bh)->size = cpu_to_be32(tmp); AFFS_DATA_HEAD(bh)->next = 0; bh->b_state &= ~(1UL << BH_New); diff --git a/fs/afs/cell.c b/fs/afs/cell.c index cee42646736c..96a6781f3653 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -64,7 +64,8 @@ static struct afs_cell *afs_find_cell_locked(struct afs_net *net, return ERR_PTR(-ENAMETOOLONG); if (!name) { - cell = net->ws_cell; + cell = rcu_dereference_protected(net->ws_cell, + lockdep_is_held(&net->cells_lock)); if (!cell) return ERR_PTR(-EDESTADDRREQ); goto found; @@ -388,8 +389,8 @@ int afs_cell_init(struct afs_net *net, const char *rootcell) /* install the new cell */ down_write(&net->cells_lock); afs_see_cell(new_root, afs_cell_trace_see_ws); - old_root = net->ws_cell; - net->ws_cell = new_root; + old_root = rcu_replace_pointer(net->ws_cell, new_root, + lockdep_is_held(&net->cells_lock)); up_write(&net->cells_lock); afs_unuse_cell(net, old_root, afs_cell_trace_unuse_ws); @@ -945,8 +946,8 @@ void afs_cell_purge(struct afs_net *net) _enter(""); down_write(&net->cells_lock); - ws = net->ws_cell; - net->ws_cell = NULL; + ws = rcu_replace_pointer(net->ws_cell, NULL, + lockdep_is_held(&net->cells_lock)); up_write(&net->cells_lock); afs_unuse_cell(net, ws, afs_cell_trace_unuse_ws); diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index d8bf52f77d93..008698d706ca 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -314,12 +314,23 @@ static const char *afs_atcell_get_link(struct dentry *dentry, struct inode *inod const char *name; bool dotted = vnode->fid.vnode == 3; - if (!net->ws_cell) + if (!dentry) { + /* We're in RCU-pathwalk. */ + cell = rcu_dereference(net->ws_cell); + if (dotted) + name = cell->name - 1; + else + name = cell->name; + /* Shouldn't need to set a delayed call. */ + return name; + } + + if (!rcu_access_pointer(net->ws_cell)) return ERR_PTR(-ENOENT); down_read(&net->cells_lock); - cell = net->ws_cell; + cell = rcu_dereference_protected(net->ws_cell, lockdep_is_held(&net->cells_lock)); if (dotted) name = cell->name - 1; else diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 90f407774a9a..df30bd62da79 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -287,7 +287,7 @@ struct afs_net { /* Cell database */ struct rb_root cells; - struct afs_cell *ws_cell; + struct afs_cell __rcu *ws_cell; struct work_struct cells_manager; struct timer_list cells_timer; atomic_t cells_outstanding; diff --git a/fs/afs/proc.c b/fs/afs/proc.c index e7614f4f30c2..12c88d8be3fe 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -206,7 +206,7 @@ static int afs_proc_rootcell_show(struct seq_file *m, void *v) net = afs_seq2net_single(m); down_read(&net->cells_lock); - cell = net->ws_cell; + cell = rcu_dereference_protected(net->ws_cell, lockdep_is_held(&net->cells_lock)); if (cell) seq_printf(m, "%s\n", cell->name); up_read(&net->cells_lock); @@ -242,7 +242,7 @@ static int afs_proc_rootcell_write(struct file *file, char *buf, size_t size) ret = -EEXIST; inode_lock(file_inode(file)); - if (!net->ws_cell) + if (!rcu_access_pointer(net->ws_cell)) ret = afs_cell_init(net, buf); else printk("busy\n"); diff --git a/fs/afs/server.c b/fs/afs/server.c index 038f9d0ae3af..4504e16b458c 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -163,6 +163,8 @@ static struct afs_server *afs_install_server(struct afs_cell *cell, rb_insert_color(&server->uuid_rb, &net->fs_servers); hlist_add_head_rcu(&server->proc_link, &net->fs_proc); + afs_get_cell(cell, afs_cell_trace_get_server); + added_dup: write_seqlock(&net->fs_addr_lock); estate = rcu_dereference_protected(server->endpoint_state, @@ -442,6 +444,7 @@ static void afs_server_rcu(struct rcu_head *rcu) atomic_read(&server->active), afs_server_trace_free); afs_put_endpoint_state(rcu_access_pointer(server->endpoint_state), afs_estate_trace_put_server); + afs_put_cell(server->cell, afs_cell_trace_put_server); kfree(server); } diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c index 7e7e567a7f8a..d20cd902ef94 100644 --- a/fs/afs/server_list.c +++ b/fs/afs/server_list.c @@ -97,8 +97,8 @@ struct afs_server_list *afs_alloc_server_list(struct afs_volume *volume, break; if (j < slist->nr_servers) { if (slist->servers[j].server == server) { - afs_put_server(volume->cell->net, server, - afs_server_trace_put_slist_isort); + afs_unuse_server(volume->cell->net, server, + afs_server_trace_put_slist_isort); continue; } diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c index ca755e8d1a37..1ec1f90e0eb3 100644 --- a/fs/bcachefs/btree_cache.c +++ b/fs/bcachefs/btree_cache.c @@ -203,7 +203,7 @@ struct btree *__bch2_btree_node_mem_alloc(struct bch_fs *c) return NULL; } - bch2_btree_lock_init(&b->c, 0); + bch2_btree_lock_init(&b->c, 0, GFP_KERNEL); __bch2_btree_node_to_freelist(bc, b); return b; @@ -795,17 +795,18 @@ struct btree *bch2_btree_node_mem_alloc(struct btree_trans *trans, bool pcpu_rea } b = __btree_node_mem_alloc(c, GFP_NOWAIT|__GFP_NOWARN); - if (!b) { + if (b) { + bch2_btree_lock_init(&b->c, pcpu_read_locks ? SIX_LOCK_INIT_PCPU : 0, GFP_NOWAIT); + } else { mutex_unlock(&bc->lock); bch2_trans_unlock(trans); b = __btree_node_mem_alloc(c, GFP_KERNEL); if (!b) goto err; + bch2_btree_lock_init(&b->c, pcpu_read_locks ? SIX_LOCK_INIT_PCPU : 0, GFP_KERNEL); mutex_lock(&bc->lock); } - bch2_btree_lock_init(&b->c, pcpu_read_locks ? SIX_LOCK_INIT_PCPU : 0); - BUG_ON(!six_trylock_intent(&b->c.lock)); BUG_ON(!six_trylock_write(&b->c.lock)); diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c index e371e60e3133..756736f9243d 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -996,7 +996,7 @@ drop_this_key: } got_good_key: le16_add_cpu(&i->u64s, -next_good_key); - memmove_u64s_down(k, bkey_p_next(k), (u64 *) vstruct_end(i) - (u64 *) k); + memmove_u64s_down(k, (u64 *) k + next_good_key, (u64 *) vstruct_end(i) - (u64 *) k); set_btree_node_need_rewrite(b); } fsck_err: @@ -1186,7 +1186,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, le64_to_cpu(i->journal_seq), b->written, b->written + sectors, ptr_written); - b->written += sectors; + b->written = min(b->written + sectors, btree_sectors(c)); if (blacklisted && !first) continue; diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c index 1821f40c161a..edce59433375 100644 --- a/fs/bcachefs/btree_key_cache.c +++ b/fs/bcachefs/btree_key_cache.c @@ -156,7 +156,7 @@ bkey_cached_alloc(struct btree_trans *trans, struct btree_path *path, unsigned k } if (ck) { - bch2_btree_lock_init(&ck->c, pcpu_readers ? SIX_LOCK_INIT_PCPU : 0); + bch2_btree_lock_init(&ck->c, pcpu_readers ? SIX_LOCK_INIT_PCPU : 0, GFP_KERNEL); ck->c.cached = true; goto lock; } diff --git a/fs/bcachefs/btree_locking.c b/fs/bcachefs/btree_locking.c index 10b805a60f52..caef65adeae4 100644 --- a/fs/bcachefs/btree_locking.c +++ b/fs/bcachefs/btree_locking.c @@ -7,9 +7,10 @@ static struct lock_class_key bch2_btree_node_lock_key; void bch2_btree_lock_init(struct btree_bkey_cached_common *b, - enum six_lock_init_flags flags) + enum six_lock_init_flags flags, + gfp_t gfp) { - __six_lock_init(&b->lock, "b->c.lock", &bch2_btree_node_lock_key, flags); + __six_lock_init(&b->lock, "b->c.lock", &bch2_btree_node_lock_key, flags, gfp); lockdep_set_notrack_class(&b->lock); } diff --git a/fs/bcachefs/btree_locking.h b/fs/bcachefs/btree_locking.h index b54ef48eb8cc..b33ab7af8440 100644 --- a/fs/bcachefs/btree_locking.h +++ b/fs/bcachefs/btree_locking.h @@ -13,7 +13,7 @@ #include "btree_iter.h" #include "six.h" -void bch2_btree_lock_init(struct btree_bkey_cached_common *, enum six_lock_init_flags); +void bch2_btree_lock_init(struct btree_bkey_cached_common *, enum six_lock_init_flags, gfp_t gfp); void bch2_trans_unlock_noassert(struct btree_trans *); void bch2_trans_unlock_write(struct btree_trans *); diff --git a/fs/bcachefs/btree_update.h b/fs/bcachefs/btree_update.h index 8f22ef9a7651..47d8690f01bf 100644 --- a/fs/bcachefs/btree_update.h +++ b/fs/bcachefs/btree_update.h @@ -126,10 +126,18 @@ bch2_trans_jset_entry_alloc(struct btree_trans *trans, unsigned u64s) int bch2_btree_insert_clone_trans(struct btree_trans *, enum btree_id, struct bkey_i *); +int bch2_btree_write_buffer_insert_err(struct btree_trans *, + enum btree_id, struct bkey_i *); + static inline int __must_check bch2_trans_update_buffered(struct btree_trans *trans, enum btree_id btree, struct bkey_i *k) { + if (unlikely(!btree_type_uses_write_buffer(btree))) { + int ret = bch2_btree_write_buffer_insert_err(trans, btree, k); + dump_stack(); + return ret; + } /* * Most updates skip the btree write buffer until journal replay is * finished because synchronization with journal replay relies on having diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c index f4aeadbe53c1..e4e7c804625e 100644 --- a/fs/bcachefs/btree_update_interior.c +++ b/fs/bcachefs/btree_update_interior.c @@ -681,9 +681,11 @@ static void btree_update_nodes_written(struct btree_update *as) b = as->old_nodes[i]; + bch2_trans_begin(trans); btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_read); seq = b->data ? b->data->keys.seq : 0; six_unlock_read(&b->c.lock); + bch2_trans_unlock_long(trans); if (seq == as->old_nodes_seq[i]) wait_on_bit_io(&b->flags, BTREE_NODE_write_in_flight_inner, diff --git a/fs/bcachefs/btree_write_buffer.c b/fs/bcachefs/btree_write_buffer.c index b56c4987b8c9..2c09d19dd621 100644 --- a/fs/bcachefs/btree_write_buffer.c +++ b/fs/bcachefs/btree_write_buffer.c @@ -264,6 +264,22 @@ out: BUG_ON(wb->sorted.size < wb->flushing.keys.nr); } +int bch2_btree_write_buffer_insert_err(struct btree_trans *trans, + enum btree_id btree, struct bkey_i *k) +{ + struct bch_fs *c = trans->c; + struct printbuf buf = PRINTBUF; + + prt_printf(&buf, "attempting to do write buffer update on non wb btree="); + bch2_btree_id_to_text(&buf, btree); + prt_str(&buf, "\n"); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(k)); + + bch2_fs_inconsistent(c, "%s", buf.buf); + printbuf_exit(&buf); + return -EROFS; +} + static int bch2_btree_write_buffer_flush_locked(struct btree_trans *trans) { struct bch_fs *c = trans->c; @@ -312,7 +328,10 @@ static int bch2_btree_write_buffer_flush_locked(struct btree_trans *trans) darray_for_each(wb->sorted, i) { struct btree_write_buffered_key *k = &wb->flushing.keys.data[i->idx]; - BUG_ON(!btree_type_uses_write_buffer(k->btree)); + if (unlikely(!btree_type_uses_write_buffer(k->btree))) { + ret = bch2_btree_write_buffer_insert_err(trans, k->btree, &k->k); + goto err; + } for (struct wb_key_ref *n = i + 1; n < min(i + 4, &darray_top(wb->sorted)); n++) prefetch(&wb->flushing.keys.data[n->idx]); diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c index 337494facac6..642fbc60ecab 100644 --- a/fs/bcachefs/data_update.c +++ b/fs/bcachefs/data_update.c @@ -340,6 +340,7 @@ restart_drop_extra_replicas: struct printbuf buf = PRINTBUF; prt_str(&buf, "about to insert invalid key in data update path"); + prt_printf(&buf, "\nop.nonce: %u", m->op.nonce); prt_str(&buf, "\nold: "); bch2_bkey_val_to_text(&buf, c, old); prt_str(&buf, "\nk: "); diff --git a/fs/bcachefs/dirent.h b/fs/bcachefs/dirent.h index a633f83c1ac7..362b3b2f2f2e 100644 --- a/fs/bcachefs/dirent.h +++ b/fs/bcachefs/dirent.h @@ -31,11 +31,6 @@ static inline unsigned dirent_val_u64s(unsigned len) sizeof(u64)); } -static inline unsigned int dirent_occupied_size(const struct qstr *name) -{ - return (BKEY_U64s + dirent_val_u64s(name->len)) * sizeof(u64); -} - int bch2_dirent_read_target(struct btree_trans *, subvol_inum, struct bkey_s_c_dirent, subvol_inum *); diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c index 05d5f71a7ca9..2d8042f853dc 100644 --- a/fs/bcachefs/extents.c +++ b/fs/bcachefs/extents.c @@ -99,7 +99,7 @@ static inline bool ptr_better(struct bch_fs *c, /* Pick at random, biased in favor of the faster device: */ - return bch2_rand_range(l1 + l2) > l1; + return bch2_get_random_u64_below(l1 + l2) > l1; } if (bch2_force_reconstruct_read) diff --git a/fs/bcachefs/extents.h b/fs/bcachefs/extents.h index 620b284aa34f..204d765dd74c 100644 --- a/fs/bcachefs/extents.h +++ b/fs/bcachefs/extents.h @@ -704,7 +704,7 @@ static inline bool bch2_extent_ptr_eq(struct bch_extent_ptr ptr1, ptr1.unwritten == ptr2.unwritten && ptr1.offset == ptr2.offset && ptr1.dev == ptr2.dev && - ptr1.dev == ptr2.dev); + ptr1.gen == ptr2.gen); } void bch2_ptr_swab(struct bkey_s); diff --git a/fs/bcachefs/fs-common.c b/fs/bcachefs/fs-common.c index d70d9f634cea..2c3d46ac70c6 100644 --- a/fs/bcachefs/fs-common.c +++ b/fs/bcachefs/fs-common.c @@ -152,7 +152,6 @@ int bch2_create_trans(struct btree_trans *trans, if (is_subdir_for_nlink(new_inode)) dir_u->bi_nlink++; dir_u->bi_mtime = dir_u->bi_ctime = now; - dir_u->bi_size += dirent_occupied_size(name); ret = bch2_inode_write(trans, &dir_iter, dir_u); if (ret) @@ -221,7 +220,6 @@ int bch2_link_trans(struct btree_trans *trans, } dir_u->bi_mtime = dir_u->bi_ctime = now; - dir_u->bi_size += dirent_occupied_size(name); dir_hash = bch2_hash_info_init(c, dir_u); @@ -324,7 +322,6 @@ int bch2_unlink_trans(struct btree_trans *trans, dir_u->bi_mtime = dir_u->bi_ctime = inode_u->bi_ctime = now; dir_u->bi_nlink -= is_subdir_for_nlink(inode_u); - dir_u->bi_size -= dirent_occupied_size(name); ret = bch2_hash_delete_at(trans, bch2_dirent_hash_desc, &dir_hash, &dirent_iter, @@ -463,14 +460,6 @@ int bch2_rename_trans(struct btree_trans *trans, goto err; } - if (mode == BCH_RENAME) { - src_dir_u->bi_size -= dirent_occupied_size(src_name); - dst_dir_u->bi_size += dirent_occupied_size(dst_name); - } - - if (mode == BCH_RENAME_OVERWRITE) - src_dir_u->bi_size -= dirent_occupied_size(src_name); - if (src_inode_u->bi_parent_subvol) src_inode_u->bi_parent_subvol = dst_dir.subvol; diff --git a/fs/bcachefs/fs-io.c b/fs/bcachefs/fs-io.c index 94bf34b9b65f..717e7b94c66f 100644 --- a/fs/bcachefs/fs-io.c +++ b/fs/bcachefs/fs-io.c @@ -466,6 +466,7 @@ int bchfs_truncate(struct mnt_idmap *idmap, ret = bch2_truncate_folio(inode, iattr->ia_size); if (unlikely(ret < 0)) goto err; + ret = 0; truncate_setsize(&inode->v, iattr->ia_size); diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c index 53a421ff136d..0e85131d0af8 100644 --- a/fs/bcachefs/fsck.c +++ b/fs/bcachefs/fsck.c @@ -823,6 +823,7 @@ struct inode_walker_entry { struct bch_inode_unpacked inode; u32 snapshot; u64 count; + u64 i_size; }; struct inode_walker { @@ -910,8 +911,9 @@ found: if (k.k->p.snapshot != i->snapshot && !is_whiteout) { struct inode_walker_entry new = *i; - new.snapshot = k.k->p.snapshot; - new.count = 0; + new.snapshot = k.k->p.snapshot; + new.count = 0; + new.i_size = 0; struct printbuf buf = PRINTBUF; bch2_bkey_val_to_text(&buf, c, k); @@ -1116,37 +1118,6 @@ err: return ret; } -static int check_directory_size(struct btree_trans *trans, - struct bch_inode_unpacked *inode_u, - struct bkey_s_c inode_k, bool *write_inode) -{ - struct btree_iter iter; - struct bkey_s_c k; - u64 new_size = 0; - int ret; - - for_each_btree_key_max_norestart(trans, iter, BTREE_ID_dirents, - SPOS(inode_k.k->p.offset, 0, inode_k.k->p.snapshot), - POS(inode_k.k->p.offset, U64_MAX), - 0, k, ret) { - if (k.k->type != KEY_TYPE_dirent) - continue; - - struct bkey_s_c_dirent dirent = bkey_s_c_to_dirent(k); - struct qstr name = bch2_dirent_get_name(dirent); - - new_size += dirent_occupied_size(&name); - } - bch2_trans_iter_exit(trans, &iter); - - if (!ret && inode_u->bi_size != new_size) { - inode_u->bi_size = new_size; - *write_inode = true; - } - - return ret; -} - static int check_inode(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, @@ -1335,16 +1306,6 @@ static int check_inode(struct btree_trans *trans, u.bi_journal_seq = journal_cur_seq(&c->journal); do_update = true; } - - if (S_ISDIR(u.bi_mode)) { - ret = check_directory_size(trans, &u, k, &do_update); - - fsck_err_on(ret, - trans, directory_size_mismatch, - "directory inode %llu:%u with the mismatch directory size", - u.bi_inum, k.k->p.snapshot); - ret = 0; - } do_update: if (do_update) { ret = __bch2_fsck_write_inode(trans, &u); @@ -2017,7 +1978,7 @@ fsck_err: return ret; } -static int check_subdir_count(struct btree_trans *trans, struct inode_walker *w) +static int check_subdir_dirents_count(struct btree_trans *trans, struct inode_walker *w) { u32 restart_count = trans->restart_count; return check_subdir_count_notnested(trans, w) ?: @@ -2367,7 +2328,7 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter, goto out; if (dir->last_pos.inode != k.k->p.inode && dir->have_inodes) { - ret = check_subdir_count(trans, dir); + ret = check_subdir_dirents_count(trans, dir); if (ret) goto err; } @@ -2457,9 +2418,11 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter, if (ret) goto err; - if (d.v->d_type == DT_DIR) - for_each_visible_inode(c, s, dir, d.k->p.snapshot, i) + for_each_visible_inode(c, s, dir, d.k->p.snapshot, i) { + if (d.v->d_type == DT_DIR) i->count++; + i->i_size += bkey_bytes(d.k); + } out: err: fsck_err: diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c index 04ec05206f8c..339b80770f1d 100644 --- a/fs/bcachefs/inode.c +++ b/fs/bcachefs/inode.c @@ -1198,6 +1198,7 @@ void bch2_inode_opts_get(struct bch_io_opts *opts, struct bch_fs *c, opts->_name##_from_inode = true; \ } else { \ opts->_name = c->opts._name; \ + opts->_name##_from_inode = false; \ } BCH_INODE_OPTS() #undef x diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c index 8c7b2d3d779d..aa91fcf51eec 100644 --- a/fs/bcachefs/io_read.c +++ b/fs/bcachefs/io_read.c @@ -59,7 +59,7 @@ static bool bch2_target_congested(struct bch_fs *c, u16 target) } rcu_read_unlock(); - return bch2_rand_range(nr * CONGESTED_MAX) < total; + return get_random_u32_below(nr * CONGESTED_MAX) < total; } #else @@ -951,12 +951,6 @@ retry_pick: goto retry_pick; } - /* - * Unlock the iterator while the btree node's lock is still in - * cache, before doing the IO: - */ - bch2_trans_unlock(trans); - if (flags & BCH_READ_NODECODE) { /* * can happen if we retry, and the extent we were going to read @@ -1113,6 +1107,15 @@ get_bio: trace_and_count(c, read_split, &orig->bio); } + /* + * Unlock the iterator while the btree node's lock is still in + * cache, before doing the IO: + */ + if (!(flags & BCH_READ_IN_RETRY)) + bch2_trans_unlock(trans); + else + bch2_trans_unlock_long(trans); + if (!rbio->pick.idx) { if (unlikely(!rbio->have_ioref)) { struct printbuf buf = PRINTBUF; @@ -1160,6 +1163,8 @@ out: if (likely(!(flags & BCH_READ_IN_RETRY))) { return 0; } else { + bch2_trans_unlock(trans); + int ret; rbio->context = RBIO_CONTEXT_UNBOUND; diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c index 24c294d4634e..05b1250619ec 100644 --- a/fs/bcachefs/journal.c +++ b/fs/bcachefs/journal.c @@ -1021,8 +1021,8 @@ struct journal_buf *bch2_next_write_buffer_flush_journal_buf(struct journal *j, /* allocate journal on a device: */ -static int __bch2_set_nr_journal_buckets(struct bch_dev *ca, unsigned nr, - bool new_fs, struct closure *cl) +static int bch2_set_nr_journal_buckets_iter(struct bch_dev *ca, unsigned nr, + bool new_fs, struct closure *cl) { struct bch_fs *c = ca->fs; struct journal_device *ja = &ca->journal; @@ -1150,26 +1150,20 @@ err_free: return ret; } -/* - * Allocate more journal space at runtime - not currently making use if it, but - * the code works: - */ -int bch2_set_nr_journal_buckets(struct bch_fs *c, struct bch_dev *ca, - unsigned nr) +static int bch2_set_nr_journal_buckets_loop(struct bch_fs *c, struct bch_dev *ca, + unsigned nr, bool new_fs) { struct journal_device *ja = &ca->journal; - struct closure cl; int ret = 0; + struct closure cl; closure_init_stack(&cl); - down_write(&c->state_lock); - /* don't handle reducing nr of buckets yet: */ if (nr < ja->nr) - goto unlock; + return 0; - while (ja->nr < nr) { + while (!ret && ja->nr < nr) { struct disk_reservation disk_res = { 0, 0, 0 }; /* @@ -1182,25 +1176,38 @@ int bch2_set_nr_journal_buckets(struct bch_fs *c, struct bch_dev *ca, * filesystem-wide allocation will succeed, this is a device * specific allocation - we can hang here: */ + if (!new_fs) { + ret = bch2_disk_reservation_get(c, &disk_res, + bucket_to_sector(ca, nr - ja->nr), 1, 0); + if (ret) + break; + } - ret = bch2_disk_reservation_get(c, &disk_res, - bucket_to_sector(ca, nr - ja->nr), 1, 0); - if (ret) - break; + ret = bch2_set_nr_journal_buckets_iter(ca, nr, new_fs, &cl); - ret = __bch2_set_nr_journal_buckets(ca, nr, false, &cl); + if (ret == -BCH_ERR_bucket_alloc_blocked || + ret == -BCH_ERR_open_buckets_empty) + ret = 0; /* wait and retry */ bch2_disk_reservation_put(c, &disk_res); - closure_sync(&cl); - - if (ret && ret != -BCH_ERR_bucket_alloc_blocked) - break; } - bch_err_fn(c, ret); -unlock: + return ret; +} + +/* + * Allocate more journal space at runtime - not currently making use if it, but + * the code works: + */ +int bch2_set_nr_journal_buckets(struct bch_fs *c, struct bch_dev *ca, + unsigned nr) +{ + down_write(&c->state_lock); + int ret = bch2_set_nr_journal_buckets_loop(c, ca, nr, false); up_write(&c->state_lock); + + bch_err_fn(c, ret); return ret; } @@ -1226,7 +1233,7 @@ int bch2_dev_journal_alloc(struct bch_dev *ca, bool new_fs) min(1 << 13, (1 << 24) / ca->mi.bucket_size)); - ret = __bch2_set_nr_journal_buckets(ca, nr, new_fs, NULL); + ret = bch2_set_nr_journal_buckets_loop(ca->fs, ca, nr, new_fs); err: bch_err_fn(ca, ret); return ret; diff --git a/fs/bcachefs/movinggc.c b/fs/bcachefs/movinggc.c index 21805509ab9e..6718dc37c5a3 100644 --- a/fs/bcachefs/movinggc.c +++ b/fs/bcachefs/movinggc.c @@ -74,20 +74,14 @@ static int bch2_bucket_is_movable(struct btree_trans *trans, struct move_bucket *b, u64 time) { struct bch_fs *c = trans->c; - struct btree_iter iter; - struct bkey_s_c k; - struct bch_alloc_v4 _a; - const struct bch_alloc_v4 *a; - int ret; - if (bch2_bucket_is_open(trans->c, - b->k.bucket.inode, - b->k.bucket.offset)) + if (bch2_bucket_is_open(c, b->k.bucket.inode, b->k.bucket.offset)) return 0; - k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_alloc, - b->k.bucket, BTREE_ITER_cached); - ret = bkey_err(k); + struct btree_iter iter; + struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_alloc, + b->k.bucket, BTREE_ITER_cached); + int ret = bkey_err(k); if (ret) return ret; @@ -95,13 +89,18 @@ static int bch2_bucket_is_movable(struct btree_trans *trans, if (!ca) goto out; - a = bch2_alloc_to_v4(k, &_a); + if (ca->mi.state != BCH_MEMBER_STATE_rw || + !bch2_dev_is_online(ca)) + goto out_put; + + struct bch_alloc_v4 _a; + const struct bch_alloc_v4 *a = bch2_alloc_to_v4(k, &_a); b->k.gen = a->gen; b->sectors = bch2_bucket_sectors_dirty(*a); u64 lru_idx = alloc_lru_idx_fragmentation(*a, ca); ret = lru_idx && lru_idx <= time; - +out_put: bch2_dev_put(ca); out: bch2_trans_iter_exit(trans, &iter); diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c index 376fd0a6e868..441e648f28b5 100644 --- a/fs/bcachefs/reflink.c +++ b/fs/bcachefs/reflink.c @@ -172,7 +172,7 @@ static int bch2_indirect_extent_missing_error(struct btree_trans *trans, bool should_commit) { if (REFLINK_P_ERROR(p.v)) - return -BCH_ERR_missing_indirect_extent; + return 0; struct bch_fs *c = trans->c; u64 live_start = REFLINK_P_IDX(p.v); @@ -259,8 +259,6 @@ struct bkey_s_c bch2_lookup_indirect_extent(struct btree_trans *trans, return k; if (unlikely(!bkey_extent_is_reflink_data(k.k))) { - bch2_trans_iter_exit(trans, iter); - unsigned size = min((u64) k.k->size, REFLINK_P_IDX(p.v) + p.k->size + le32_to_cpu(p.v->back_pad) - reflink_offset); @@ -268,14 +266,16 @@ struct bkey_s_c bch2_lookup_indirect_extent(struct btree_trans *trans, int ret = bch2_indirect_extent_missing_error(trans, p, reflink_offset, k.k->p.offset, should_commit); - if (ret) + if (ret) { + bch2_trans_iter_exit(trans, iter); return bkey_s_c_err(ret); + } } else if (unlikely(REFLINK_P_ERROR(p.v))) { - bch2_trans_iter_exit(trans, iter); - int ret = bch2_indirect_extent_not_missing(trans, p, should_commit); - if (ret) + if (ret) { + bch2_trans_iter_exit(trans, iter); return bkey_s_c_err(ret); + } } *offset_into_extent = reflink_offset - bkey_start_offset(k.k); @@ -300,7 +300,7 @@ static int trans_trigger_reflink_p_segment(struct btree_trans *trans, if (ret) return ret; - if (bkey_deleted(k.k)) { + if (!bkey_refcount_c(k)) { if (!(flags & BTREE_TRIGGER_overwrite)) ret = -BCH_ERR_missing_indirect_extent; goto next; @@ -381,8 +381,6 @@ static s64 gc_trigger_reflink_p_segment(struct btree_trans *trans, not_found: if (flags & BTREE_TRIGGER_check_repair) { ret = bch2_indirect_extent_missing_error(trans, p, *idx, next_idx, false); - if (ret == -BCH_ERR_missing_indirect_extent) - ret = 0; if (ret) goto err; } diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c index 14f6b6a5fb38..051214fdc735 100644 --- a/fs/bcachefs/sb-downgrade.c +++ b/fs/bcachefs/sb-downgrade.c @@ -90,10 +90,7 @@ BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ BCH_FSCK_ERR_accounting_mismatch, \ BCH_FSCK_ERR_accounting_key_replicas_nr_devs_0, \ - BCH_FSCK_ERR_accounting_key_junk_at_end) \ - x(directory_size, \ - BIT_ULL(BCH_RECOVERY_PASS_check_inodes), \ - BCH_FSCK_ERR_directory_size_mismatch) \ + BCH_FSCK_ERR_accounting_key_junk_at_end) #define DOWNGRADE_TABLE() \ x(bucket_stripe_sectors, \ diff --git a/fs/bcachefs/six.c b/fs/bcachefs/six.c index 7e7c66a1e1a6..7c403427fbdb 100644 --- a/fs/bcachefs/six.c +++ b/fs/bcachefs/six.c @@ -850,7 +850,8 @@ void six_lock_exit(struct six_lock *lock) EXPORT_SYMBOL_GPL(six_lock_exit); void __six_lock_init(struct six_lock *lock, const char *name, - struct lock_class_key *key, enum six_lock_init_flags flags) + struct lock_class_key *key, enum six_lock_init_flags flags, + gfp_t gfp) { atomic_set(&lock->state, 0); raw_spin_lock_init(&lock->wait_lock); @@ -873,7 +874,7 @@ void __six_lock_init(struct six_lock *lock, const char *name, * failure if they wish by checking lock->readers, but generally * will not want to treat it as an error. */ - lock->readers = alloc_percpu(unsigned); + lock->readers = alloc_percpu_gfp(unsigned, gfp); } #endif } diff --git a/fs/bcachefs/six.h b/fs/bcachefs/six.h index c142e06b7a3a..59b851cf8bac 100644 --- a/fs/bcachefs/six.h +++ b/fs/bcachefs/six.h @@ -164,18 +164,19 @@ enum six_lock_init_flags { }; void __six_lock_init(struct six_lock *lock, const char *name, - struct lock_class_key *key, enum six_lock_init_flags flags); + struct lock_class_key *key, enum six_lock_init_flags flags, + gfp_t gfp); /** * six_lock_init - initialize a six lock * @lock: lock to initialize * @flags: optional flags, i.e. SIX_LOCK_INIT_PCPU */ -#define six_lock_init(lock, flags) \ +#define six_lock_init(lock, flags, gfp) \ do { \ static struct lock_class_key __key; \ \ - __six_lock_init((lock), #lock, &__key, flags); \ + __six_lock_init((lock), #lock, &__key, flags, gfp); \ } while (0) /** diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c index 8037ccbacf6a..a81a7b6c0989 100644 --- a/fs/bcachefs/super-io.c +++ b/fs/bcachefs/super-io.c @@ -69,14 +69,20 @@ enum bcachefs_metadata_version bch2_latest_compatible_version(enum bcachefs_meta return v; } -void bch2_set_version_incompat(struct bch_fs *c, enum bcachefs_metadata_version version) +bool bch2_set_version_incompat(struct bch_fs *c, enum bcachefs_metadata_version version) { - mutex_lock(&c->sb_lock); - SET_BCH_SB_VERSION_INCOMPAT(c->disk_sb.sb, - max(BCH_SB_VERSION_INCOMPAT(c->disk_sb.sb), version)); - c->disk_sb.sb->features[0] |= cpu_to_le64(BCH_FEATURE_incompat_version_field); - bch2_write_super(c); - mutex_unlock(&c->sb_lock); + bool ret = (c->sb.features & BIT_ULL(BCH_FEATURE_incompat_version_field)) && + version <= c->sb.version_incompat_allowed; + + if (ret) { + mutex_lock(&c->sb_lock); + SET_BCH_SB_VERSION_INCOMPAT(c->disk_sb.sb, + max(BCH_SB_VERSION_INCOMPAT(c->disk_sb.sb), version)); + bch2_write_super(c); + mutex_unlock(&c->sb_lock); + } + + return ret; } const char * const bch2_sb_fields[] = { @@ -1219,9 +1225,11 @@ void bch2_sb_upgrade(struct bch_fs *c, unsigned new_version, bool incompat) c->disk_sb.sb->version = cpu_to_le16(new_version); c->disk_sb.sb->features[0] |= cpu_to_le64(BCH_SB_FEATURES_ALL); - if (incompat) + if (incompat) { SET_BCH_SB_VERSION_INCOMPAT_ALLOWED(c->disk_sb.sb, max(BCH_SB_VERSION_INCOMPAT_ALLOWED(c->disk_sb.sb), new_version)); + c->disk_sb.sb->features[0] |= cpu_to_le64(BCH_FEATURE_incompat_version_field); + } } static int bch2_sb_ext_validate(struct bch_sb *sb, struct bch_sb_field *f, diff --git a/fs/bcachefs/super-io.h b/fs/bcachefs/super-io.h index f1ab4f943720..b4cff9ebdebb 100644 --- a/fs/bcachefs/super-io.h +++ b/fs/bcachefs/super-io.h @@ -21,17 +21,14 @@ static inline bool bch2_version_compatible(u16 version) void bch2_version_to_text(struct printbuf *, enum bcachefs_metadata_version); enum bcachefs_metadata_version bch2_latest_compatible_version(enum bcachefs_metadata_version); -void bch2_set_version_incompat(struct bch_fs *, enum bcachefs_metadata_version); +bool bch2_set_version_incompat(struct bch_fs *, enum bcachefs_metadata_version); static inline bool bch2_request_incompat_feature(struct bch_fs *c, enum bcachefs_metadata_version version) { - if (unlikely(version > c->sb.version_incompat)) { - if (version > c->sb.version_incompat_allowed) - return false; - bch2_set_version_incompat(c, version); - } - return true; + return likely(version <= c->sb.version_incompat) + ? true + : bch2_set_version_incompat(c, version); } static inline size_t bch2_sb_field_bytes(struct bch_sb_field *f) diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c index 6d97d412fed9..0459c875e189 100644 --- a/fs/bcachefs/super.c +++ b/fs/bcachefs/super.c @@ -1811,7 +1811,11 @@ int bch2_dev_add(struct bch_fs *c, const char *path) goto err_late; up_write(&c->state_lock); - return 0; +out: + printbuf_exit(&label); + printbuf_exit(&errbuf); + bch_err_fn(c, ret); + return ret; err_unlock: mutex_unlock(&c->sb_lock); @@ -1820,10 +1824,7 @@ err: if (ca) bch2_dev_free(ca); bch2_free_super(&sb); - printbuf_exit(&label); - printbuf_exit(&errbuf); - bch_err_fn(c, ret); - return ret; + goto out; err_late: up_write(&c->state_lock); ca = NULL; diff --git a/fs/bcachefs/util.c b/fs/bcachefs/util.c index e0a876cbaa6b..da2cd11b3025 100644 --- a/fs/bcachefs/util.c +++ b/fs/bcachefs/util.c @@ -653,19 +653,25 @@ int bch2_bio_alloc_pages(struct bio *bio, size_t size, gfp_t gfp_mask) return 0; } -size_t bch2_rand_range(size_t max) +u64 bch2_get_random_u64_below(u64 ceil) { - size_t rand; + if (ceil <= U32_MAX) + return __get_random_u32_below(ceil); - if (!max) - return 0; + /* this is the same (clever) algorithm as in __get_random_u32_below() */ + u64 rand = get_random_u64(); + u64 mult = ceil * rand; - do { - rand = get_random_long(); - rand &= roundup_pow_of_two(max) - 1; - } while (rand >= max); + if (unlikely(mult < ceil)) { + u64 bound; + div64_u64_rem(-ceil, ceil, &bound); + while (unlikely(mult < bound)) { + rand = get_random_u64(); + mult = ceil * rand; + } + } - return rand; + return mul_u64_u64_shr(ceil, rand, 64); } void memcpy_to_bio(struct bio *dst, struct bvec_iter dst_iter, const void *src) diff --git a/fs/bcachefs/util.h b/fs/bcachefs/util.h index e7c3541b38f3..f4a4783219d9 100644 --- a/fs/bcachefs/util.h +++ b/fs/bcachefs/util.h @@ -401,7 +401,7 @@ do { \ _ret; \ }) -size_t bch2_rand_range(size_t); +u64 bch2_get_random_u64_below(u64); void memcpy_to_bio(struct bio *, struct bvec_iter, const void *); void memcpy_from_bio(void *, struct bio *, struct bvec_iter); diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 67ce85ff0ae2..7f46abbd6311 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -1128,6 +1128,8 @@ static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_c long nr_dropped = 0; struct rb_node *node; + lockdep_assert_held_write(&tree->lock); + /* * Take the mmap lock so that we serialize with the inode logging phase * of fsync because we may need to set the full sync flag on the inode, @@ -1139,28 +1141,12 @@ static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_c * to find new extents, which may not be there yet because ordered * extents haven't completed yet. * - * We also do a try lock because otherwise we could deadlock. This is - * because the shrinker for this filesystem may be invoked while we are - * in a path that is holding the mmap lock in write mode. For example in - * a reflink operation while COWing an extent buffer, when allocating - * pages for a new extent buffer and under memory pressure, the shrinker - * may be invoked, and therefore we would deadlock by attempting to read - * lock the mmap lock while we are holding already a write lock on it. + * We also do a try lock because we don't want to block for too long and + * we are holding the extent map tree's lock in write mode. */ if (!down_read_trylock(&inode->i_mmap_lock)) return 0; - /* - * We want to be fast so if the lock is busy we don't want to spend time - * waiting for it - either some task is about to do IO for the inode or - * we may have another task shrinking extent maps, here in this code, so - * skip this inode. - */ - if (!write_trylock(&tree->lock)) { - up_read(&inode->i_mmap_lock); - return 0; - } - node = rb_first(&tree->root); while (node) { struct rb_node *next = rb_next(node); @@ -1201,12 +1187,61 @@ next: break; node = next; } - write_unlock(&tree->lock); up_read(&inode->i_mmap_lock); return nr_dropped; } +static struct btrfs_inode *find_first_inode_to_shrink(struct btrfs_root *root, + u64 min_ino) +{ + struct btrfs_inode *inode; + unsigned long from = min_ino; + + xa_lock(&root->inodes); + while (true) { + struct extent_map_tree *tree; + + inode = xa_find(&root->inodes, &from, ULONG_MAX, XA_PRESENT); + if (!inode) + break; + + tree = &inode->extent_tree; + + /* + * We want to be fast so if the lock is busy we don't want to + * spend time waiting for it (some task is about to do IO for + * the inode). + */ + if (!write_trylock(&tree->lock)) + goto next; + + /* + * Skip inode if it doesn't have loaded extent maps, so we avoid + * getting a reference and doing an iput later. This includes + * cases like files that were opened for things like stat(2), or + * files with all extent maps previously released through the + * release folio callback (btrfs_release_folio()) or released in + * a previous run, or directories which never have extent maps. + */ + if (RB_EMPTY_ROOT(&tree->root)) { + write_unlock(&tree->lock); + goto next; + } + + if (igrab(&inode->vfs_inode)) + break; + + write_unlock(&tree->lock); +next: + from = btrfs_ino(inode) + 1; + cond_resched_lock(&root->inodes.xa_lock); + } + xa_unlock(&root->inodes); + + return inode; +} + static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx *ctx) { struct btrfs_fs_info *fs_info = root->fs_info; @@ -1214,21 +1249,21 @@ static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx long nr_dropped = 0; u64 min_ino = fs_info->em_shrinker_last_ino + 1; - inode = btrfs_find_first_inode(root, min_ino); + inode = find_first_inode_to_shrink(root, min_ino); while (inode) { nr_dropped += btrfs_scan_inode(inode, ctx); + write_unlock(&inode->extent_tree.lock); min_ino = btrfs_ino(inode) + 1; fs_info->em_shrinker_last_ino = btrfs_ino(inode); - btrfs_add_delayed_iput(inode); + iput(&inode->vfs_inode); - if (ctx->scanned >= ctx->nr_to_scan || - btrfs_fs_closing(inode->root->fs_info)) + if (ctx->scanned >= ctx->nr_to_scan || btrfs_fs_closing(fs_info)) break; cond_resched(); - inode = btrfs_find_first_inode(root, min_ino); + inode = find_first_inode_to_shrink(root, min_ino); } if (inode) { diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index ed3c0d6546c5..0b568c8d24cb 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1090,7 +1090,7 @@ ssize_t btrfs_buffered_write(struct kiocb *iocb, struct iov_iter *i) u64 lockend; size_t num_written = 0; ssize_t ret; - loff_t old_isize = i_size_read(inode); + loff_t old_isize; unsigned int ilock_flags = 0; const bool nowait = (iocb->ki_flags & IOCB_NOWAIT); unsigned int bdp_flags = (nowait ? BDP_ASYNC : 0); @@ -1103,6 +1103,13 @@ ssize_t btrfs_buffered_write(struct kiocb *iocb, struct iov_iter *i) if (ret < 0) return ret; + /* + * We can only trust the isize with inode lock held, or it can race with + * other buffered writes and cause incorrect call of + * pagecache_isize_extended() to overwrite existing data. + */ + old_isize = i_size_read(inode); + ret = generic_write_checks(iocb, i); if (ret <= 0) goto out; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a9322601ab5c..38756f8cef46 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1382,8 +1382,13 @@ static noinline int cow_file_range(struct btrfs_inode *inode, continue; } if (done_offset) { - *done_offset = start - 1; - return 0; + /* + * Move @end to the end of the processed range, + * and exit the loop to unlock the processed extents. + */ + end = start - 1; + ret = 0; + break; } ret = -ENOSPC; } diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 53b846d99ece..14f53f757555 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -1330,13 +1330,13 @@ MODULE_PARM_DESC(read_policy, int btrfs_read_policy_to_enum(const char *str, s64 *value_ret) { - char param[32] = { 0 }; + char param[32]; char __maybe_unused *value_str; if (!str || strlen(str) == 0) return 0; - strncpy(param, str, sizeof(param) - 1); + strscpy(param, str); #ifdef CONFIG_BTRFS_EXPERIMENTAL /* Separate value from input in policy:value format. */ diff --git a/fs/btrfs/tests/delayed-refs-tests.c b/fs/btrfs/tests/delayed-refs-tests.c index 6558508c2ddf..265370e79a54 100644 --- a/fs/btrfs/tests/delayed-refs-tests.c +++ b/fs/btrfs/tests/delayed-refs-tests.c @@ -1009,6 +1009,7 @@ int btrfs_test_delayed_refs(u32 sectorsize, u32 nodesize) if (!ret) ret = select_delayed_refs_test(&trans); + kfree(transaction); out_free_fs_info: btrfs_free_dummy_fs_info(fs_info); return ret; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 0a0776489055..3f8afbd1ebb5 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -7155,6 +7155,7 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf, btrfs_err(fs_info, "failed to add chunk map, start=%llu len=%llu: %d", map->start, map->chunk_len, ret); + btrfs_free_chunk_map(map); } return ret; @@ -7200,8 +7201,12 @@ static struct btrfs_fs_devices *open_seed_devices(struct btrfs_fs_info *fs_info, fs_devices = find_fsid(fsid, NULL); if (!fs_devices) { - if (!btrfs_test_opt(fs_info, DEGRADED)) + if (!btrfs_test_opt(fs_info, DEGRADED)) { + btrfs_err(fs_info, + "failed to find fsid %pU when attempting to open seed devices", + fsid); return ERR_PTR(-ENOENT); + } fs_devices = alloc_fs_devices(fsid); if (IS_ERR(fs_devices)) diff --git a/fs/coredump.c b/fs/coredump.c index 591700e1b2ce..4375c70144d0 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -63,6 +63,7 @@ static void free_vma_snapshot(struct coredump_params *cprm); static int core_uses_pid; static unsigned int core_pipe_limit; +static unsigned int core_sort_vma; static char core_pattern[CORENAME_MAX_SIZE] = "core"; static int core_name_size = CORENAME_MAX_SIZE; unsigned int core_file_note_size_limit = CORE_FILE_NOTE_SIZE_DEFAULT; @@ -1026,6 +1027,15 @@ static const struct ctl_table coredump_sysctls[] = { .extra1 = (unsigned int *)&core_file_note_size_min, .extra2 = (unsigned int *)&core_file_note_size_max, }, + { + .procname = "core_sort_vma", + .data = &core_sort_vma, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_douintvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, }; static int __init init_fs_coredump_sysctls(void) @@ -1256,8 +1266,9 @@ static bool dump_vma_snapshot(struct coredump_params *cprm) cprm->vma_data_size += m->dump_size; } - sort(cprm->vma_meta, cprm->vma_count, sizeof(*cprm->vma_meta), - cmp_vma_size, NULL); + if (core_sort_vma) + sort(cprm->vma_meta, cprm->vma_count, sizeof(*cprm->vma_meta), + cmp_vma_size, NULL); return true; } diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c index cb1b6d0c3454..c294a8fc566d 100644 --- a/fs/efivarfs/file.c +++ b/fs/efivarfs/file.c @@ -57,10 +57,11 @@ static ssize_t efivarfs_file_write(struct file *file, if (bytes == -ENOENT) { /* - * zero size signals to release that the write deleted - * the variable + * FIXME: temporary workaround for fwupdate, signal + * failed write with a 1 to keep created but not + * written files */ - i_size_write(inode, 0); + i_size_write(inode, 1); } else { i_size_write(inode, datasize + sizeof(attributes)); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); @@ -124,7 +125,8 @@ static int efivarfs_file_release(struct inode *inode, struct file *file) struct efivar_entry *var = inode->i_private; inode_lock(inode); - var->removed = (--var->open_count == 0 && i_size_read(inode) == 0); + /* FIXME: temporary work around for fwupdate */ + var->removed = (--var->open_count == 0 && i_size_read(inode) == 1); inode_unlock(inode); if (var->removed) diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 09fcf731e65d..6eae8cf655c1 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -367,6 +367,8 @@ static int efivarfs_fill_super(struct super_block *sb, struct fs_context *fc) if (err) return err; + register_pm_notifier(&sfi->pm_nb); + return efivar_init(efivarfs_callback, sb, true); } @@ -552,7 +554,6 @@ static int efivarfs_init_fs_context(struct fs_context *fc) sfi->pm_nb.notifier_call = efivarfs_pm_notify; sfi->pm_nb.priority = 0; - register_pm_notifier(&sfi->pm_nb); return 0; } diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c index ce9be95c9172..9ff825f1502d 100644 --- a/fs/exfat/balloc.c +++ b/fs/exfat/balloc.c @@ -141,7 +141,7 @@ int exfat_set_bitmap(struct inode *inode, unsigned int clu, bool sync) return 0; } -void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync) +int exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync) { int i, b; unsigned int ent_idx; @@ -150,13 +150,17 @@ void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync) struct exfat_mount_options *opts = &sbi->options; if (!is_valid_cluster(sbi, clu)) - return; + return -EIO; ent_idx = CLUSTER_TO_BITMAP_ENT(clu); i = BITMAP_OFFSET_SECTOR_INDEX(sb, ent_idx); b = BITMAP_OFFSET_BIT_IN_SECTOR(sb, ent_idx); + if (!test_bit_le(b, sbi->vol_amap[i]->b_data)) + return -EIO; + clear_bit_le(b, sbi->vol_amap[i]->b_data); + exfat_update_bh(sbi->vol_amap[i], sync); if (opts->discard) { @@ -171,6 +175,8 @@ void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync) opts->discard = 0; } } + + return 0; } /* diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h index 78be6964a8a0..d30ce18a88b7 100644 --- a/fs/exfat/exfat_fs.h +++ b/fs/exfat/exfat_fs.h @@ -456,7 +456,7 @@ int exfat_count_num_clusters(struct super_block *sb, int exfat_load_bitmap(struct super_block *sb); void exfat_free_bitmap(struct exfat_sb_info *sbi); int exfat_set_bitmap(struct inode *inode, unsigned int clu, bool sync); -void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync); +int exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync); unsigned int exfat_find_free_bitmap(struct super_block *sb, unsigned int clu); int exfat_count_used_clusters(struct super_block *sb, unsigned int *ret_count); int exfat_trim_fs(struct inode *inode, struct fstrim_range *range); diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c index 9e5492ac409b..6f3651c6ca91 100644 --- a/fs/exfat/fatent.c +++ b/fs/exfat/fatent.c @@ -175,6 +175,7 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain BITMAP_OFFSET_SECTOR_INDEX(sb, CLUSTER_TO_BITMAP_ENT(clu)); if (p_chain->flags == ALLOC_NO_FAT_CHAIN) { + int err; unsigned int last_cluster = p_chain->dir + p_chain->size - 1; do { bool sync = false; @@ -189,7 +190,9 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain cur_cmap_i = next_cmap_i; } - exfat_clear_bitmap(inode, clu, (sync && IS_DIRSYNC(inode))); + err = exfat_clear_bitmap(inode, clu, (sync && IS_DIRSYNC(inode))); + if (err) + break; clu++; num_clusters++; } while (num_clusters < p_chain->size); @@ -210,12 +213,13 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain cur_cmap_i = next_cmap_i; } - exfat_clear_bitmap(inode, clu, (sync && IS_DIRSYNC(inode))); + if (exfat_clear_bitmap(inode, clu, (sync && IS_DIRSYNC(inode)))) + break; clu = n_clu; num_clusters++; if (err) - goto dec_used_clus; + break; if (num_clusters >= sbi->num_clusters - EXFAT_FIRST_CLUSTER) { /* @@ -229,7 +233,6 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain } while (clu != EXFAT_EOF_CLUSTER); } -dec_used_clus: sbi->used_clusters -= num_clusters; return 0; } diff --git a/fs/exfat/file.c b/fs/exfat/file.c index 05b51e721783..807349d8ea05 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -587,7 +587,7 @@ static ssize_t exfat_file_write_iter(struct kiocb *iocb, struct iov_iter *iter) valid_size = ei->valid_size; ret = generic_write_checks(iocb, iter); - if (ret < 0) + if (ret <= 0) goto unlock; if (iocb->ki_flags & IOCB_DIRECT) { diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index 691dd77b6ab5..8b30027d8251 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -232,7 +232,7 @@ static int exfat_search_empty_slot(struct super_block *sb, dentry = 0; } - while (dentry + num_entries < total_entries && + while (dentry + num_entries <= total_entries && clu.dir != EXFAT_EOF_CLUSTER) { i = dentry & (dentries_per_clu - 1); @@ -646,6 +646,11 @@ static int exfat_find(struct inode *dir, struct qstr *qname, info->valid_size = le64_to_cpu(ep2->dentry.stream.valid_size); info->size = le64_to_cpu(ep2->dentry.stream.size); + if (unlikely(EXFAT_B_TO_CLU_ROUND_UP(info->size, sbi) > sbi->used_clusters)) { + exfat_fs_error(sb, "data size is invalid(%lld)", info->size); + return -EIO; + } + info->start_clu = le32_to_cpu(ep2->dentry.stream.start_clu); if (!is_valid_cluster(sbi, info->start_clu) && info->size) { exfat_warn(sb, "start_clu is invalid cluster(0x%x)", diff --git a/fs/ext4/file.c b/fs/ext4/file.c index a5205149adba..3bd96c3d4cd0 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -756,9 +756,6 @@ retry: return VM_FAULT_SIGBUS; } } else { - result = filemap_fsnotify_fault(vmf); - if (unlikely(result)) - return result; filemap_invalidate_lock_shared(mapping); } result = dax_iomap_fault(vmf, order, &pfn, &error, &ext4_iomap_ops); diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 5b5f789b37eb..2c3a4d09e500 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -838,6 +838,12 @@ static int fuse_check_folio(struct folio *folio) return 0; } +/* + * Attempt to steal a page from the splice() pipe and move it into the + * pagecache. If successful, the pointer in @pagep will be updated. The + * folio that was originally in @pagep will lose a reference and the new + * folio returned in @pagep will carry a reference. + */ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) { int err; @@ -1451,7 +1457,7 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos, if (ret < 0) goto out; - if (pipe_occupancy(pipe->head, pipe->tail) + cs.nr_segs > pipe->max_usage) { + if (pipe_buf_usage(pipe) + cs.nr_segs > pipe->max_usage) { ret = -EIO; goto out; } @@ -2101,7 +2107,7 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags) { - unsigned int head, tail, mask, count; + unsigned int head, tail, count; unsigned nbuf; unsigned idx; struct pipe_buffer *bufs; @@ -2118,8 +2124,7 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, head = pipe->head; tail = pipe->tail; - mask = pipe->ring_size - 1; - count = head - tail; + count = pipe_occupancy(head, tail); bufs = kvmalloc_array(count, sizeof(struct pipe_buffer), GFP_KERNEL); if (!bufs) { @@ -2129,8 +2134,8 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, nbuf = 0; rem = 0; - for (idx = tail; idx != head && rem < len; idx++) - rem += pipe->bufs[idx & mask].len; + for (idx = tail; !pipe_empty(head, idx) && rem < len; idx++) + rem += pipe_buf(pipe, idx)->len; ret = -EINVAL; if (rem < len) @@ -2141,10 +2146,10 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, struct pipe_buffer *ibuf; struct pipe_buffer *obuf; - if (WARN_ON(nbuf >= count || tail == head)) + if (WARN_ON(nbuf >= count || pipe_empty(head, tail))) goto out_free; - ibuf = &pipe->bufs[tail & mask]; + ibuf = pipe_buf(pipe, tail); obuf = &bufs[nbuf]; if (rem >= ibuf->len) { diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 198862b086ff..3805f9b06c9d 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1636,7 +1636,7 @@ static const char *fuse_get_link(struct dentry *dentry, struct inode *inode, goto out_err; if (fc->cache_symlinks) - return page_get_link(dentry, inode, callback); + return page_get_link_raw(dentry, inode, callback); err = -ECHILD; if (!dentry) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 7d92a5479998..d63e56fd3dd2 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -955,8 +955,10 @@ static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args, fuse_invalidate_atime(inode); } - for (i = 0; i < ap->num_folios; i++) + for (i = 0; i < ap->num_folios; i++) { folio_end_read(ap->folios[i], !err); + folio_put(ap->folios[i]); + } if (ia->ff) fuse_file_put(ia->ff, false); @@ -1048,7 +1050,14 @@ static void fuse_readahead(struct readahead_control *rac) ap = &ia->ap; while (ap->num_folios < cur_pages) { - folio = readahead_folio(rac); + /* + * This returns a folio with a ref held on it. + * The ref needs to be held until the request is + * completed, since the splice case (see + * fuse_try_move_page()) drops the ref after it's + * replaced in the page cache. + */ + folio = __readahead_folio(rac); ap->folios[ap->num_folios] = folio; ap->descs[ap->num_folios].length = folio_size(folio); ap->num_folios++; diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index b521eb15759e..0e47da82b0c2 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -427,12 +427,10 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter, bio_put(bio); goto zero_tail; } - if (dio->flags & IOMAP_DIO_WRITE) { + if (dio->flags & IOMAP_DIO_WRITE) task_io_account_write(n); - } else { - if (dio->flags & IOMAP_DIO_DIRTY) - bio_set_pages_dirty(bio); - } + else if (dio->flags & IOMAP_DIO_DIRTY) + bio_set_pages_dirty(bio); dio->size += n; copied += n; diff --git a/fs/namei.c b/fs/namei.c index 3ab9440c5b93..ecb7b95c2ca3 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -5356,10 +5356,9 @@ const char *vfs_get_link(struct dentry *dentry, struct delayed_call *done) EXPORT_SYMBOL(vfs_get_link); /* get the link contents into pagecache */ -const char *page_get_link(struct dentry *dentry, struct inode *inode, - struct delayed_call *callback) +static char *__page_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *callback) { - char *kaddr; struct page *page; struct address_space *mapping = inode->i_mapping; @@ -5378,8 +5377,23 @@ const char *page_get_link(struct dentry *dentry, struct inode *inode, } set_delayed_call(callback, page_put_link, page); BUG_ON(mapping_gfp_mask(mapping) & __GFP_HIGHMEM); - kaddr = page_address(page); - nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1); + return page_address(page); +} + +const char *page_get_link_raw(struct dentry *dentry, struct inode *inode, + struct delayed_call *callback) +{ + return __page_get_link(dentry, inode, callback); +} +EXPORT_SYMBOL_GPL(page_get_link_raw); + +const char *page_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *callback) +{ + char *kaddr = __page_get_link(dentry, inode, callback); + + if (!IS_ERR(kaddr)) + nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1); return kaddr; } diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index f761d44b3436..0d1b6d35ff3b 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -155,8 +155,9 @@ static void netfs_read_cache_to_pagecache(struct netfs_io_request *rreq, netfs_cache_read_terminated, subreq); } -static void netfs_issue_read(struct netfs_io_request *rreq, - struct netfs_io_subrequest *subreq) +static void netfs_queue_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq, + bool last_subreq) { struct netfs_io_stream *stream = &rreq->io_streams[0]; @@ -177,8 +178,17 @@ static void netfs_issue_read(struct netfs_io_request *rreq, } } + if (last_subreq) { + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); + } + spin_unlock(&rreq->lock); +} +static void netfs_issue_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ switch (subreq->source) { case NETFS_DOWNLOAD_FROM_SERVER: rreq->netfs_ops->issue_read(subreq); @@ -293,11 +303,8 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) } size -= slice; start += slice; - if (size <= 0) { - smp_wmb(); /* Write lists before ALL_QUEUED. */ - set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); - } + netfs_queue_read(rreq, subreq, size <= 0); netfs_issue_read(rreq, subreq); cond_resched(); } while (size > 0); diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index eb76f98c894b..1c4f953c3d68 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -135,6 +135,8 @@ extern atomic_t netfs_n_rh_write_begin; extern atomic_t netfs_n_rh_write_done; extern atomic_t netfs_n_rh_write_failed; extern atomic_t netfs_n_rh_write_zskip; +extern atomic_t netfs_n_rh_retry_read_req; +extern atomic_t netfs_n_rh_retry_read_subreq; extern atomic_t netfs_n_wh_buffered_write; extern atomic_t netfs_n_wh_writethrough; extern atomic_t netfs_n_wh_dio_write; @@ -147,6 +149,8 @@ extern atomic_t netfs_n_wh_upload_failed; extern atomic_t netfs_n_wh_write; extern atomic_t netfs_n_wh_write_done; extern atomic_t netfs_n_wh_write_failed; +extern atomic_t netfs_n_wh_retry_write_req; +extern atomic_t netfs_n_wh_retry_write_subreq; extern atomic_t netfs_n_wb_lock_skip; extern atomic_t netfs_n_wb_lock_wait; extern atomic_t netfs_n_folioq; diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index f65affa5a9e4..636cc5a98ef5 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -470,7 +470,8 @@ void netfs_read_collection_worker(struct work_struct *work) */ void netfs_wake_read_collector(struct netfs_io_request *rreq) { - if (test_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags)) { + if (test_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags) && + !test_bit(NETFS_RREQ_RETRYING, &rreq->flags)) { if (!work_pending(&rreq->work)) { netfs_get_request(rreq, netfs_rreq_trace_get_work); if (!queue_work(system_unbound_wq, &rreq->work)) @@ -586,7 +587,8 @@ void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq) smp_mb__after_atomic(); /* Clear IN_PROGRESS before task state */ /* If we are at the head of the queue, wake up the collector. */ - if (list_is_first(&subreq->rreq_link, &stream->subrequests)) + if (list_is_first(&subreq->rreq_link, &stream->subrequests) || + test_bit(NETFS_RREQ_RETRYING, &rreq->flags)) netfs_wake_read_collector(rreq); netfs_put_subrequest(subreq, true, netfs_sreq_trace_put_terminated); diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c index 2290af0d51ac..0f294b26e08c 100644 --- a/fs/netfs/read_retry.c +++ b/fs/netfs/read_retry.c @@ -14,7 +14,7 @@ static void netfs_reissue_read(struct netfs_io_request *rreq, { __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); - netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); + netfs_stat(&netfs_n_rh_retry_read_subreq); subreq->rreq->netfs_ops->issue_read(subreq); } @@ -48,6 +48,7 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); subreq->retry_count++; netfs_reset_iter(subreq); + netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); netfs_reissue_read(rreq, subreq); } } @@ -75,7 +76,7 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) struct iov_iter source; unsigned long long start, len; size_t part; - bool boundary = false; + bool boundary = false, subreq_superfluous = false; /* Go through the subreqs and find the next span of contiguous * buffer that we then rejig (cifs, for example, needs the @@ -116,8 +117,10 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) /* Work through the sublist. */ subreq = from; list_for_each_entry_from(subreq, &stream->subrequests, rreq_link) { - if (!len) + if (!len) { + subreq_superfluous = true; break; + } subreq->source = NETFS_DOWNLOAD_FROM_SERVER; subreq->start = start - subreq->transferred; subreq->len = len + subreq->transferred; @@ -154,19 +157,21 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); netfs_reissue_read(rreq, subreq); - if (subreq == to) + if (subreq == to) { + subreq_superfluous = false; break; + } } /* If we managed to use fewer subreqs, we can discard the * excess; if we used the same number, then we're done. */ if (!len) { - if (subreq == to) + if (!subreq_superfluous) continue; list_for_each_entry_safe_from(subreq, tmp, &stream->subrequests, rreq_link) { - trace_netfs_sreq(subreq, netfs_sreq_trace_discard); + trace_netfs_sreq(subreq, netfs_sreq_trace_superfluous); list_del(&subreq->rreq_link); netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_done); if (subreq == to) @@ -187,14 +192,12 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) subreq->source = NETFS_DOWNLOAD_FROM_SERVER; subreq->start = start; subreq->len = len; - subreq->debug_index = atomic_inc_return(&rreq->subreq_counter); subreq->stream_nr = stream->stream_nr; subreq->retry_count = 1; trace_netfs_sreq_ref(rreq->debug_id, subreq->debug_index, refcount_read(&subreq->ref), netfs_sreq_trace_new); - netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); list_add(&subreq->rreq_link, &to->rreq_link); to = list_next_entry(to, rreq_link); @@ -256,14 +259,34 @@ void netfs_retry_reads(struct netfs_io_request *rreq) { struct netfs_io_subrequest *subreq; struct netfs_io_stream *stream = &rreq->io_streams[0]; + DEFINE_WAIT(myself); + + netfs_stat(&netfs_n_rh_retry_read_req); + + set_bit(NETFS_RREQ_RETRYING, &rreq->flags); /* Wait for all outstanding I/O to quiesce before performing retries as * we may need to renegotiate the I/O sizes. */ list_for_each_entry(subreq, &stream->subrequests, rreq_link) { - wait_on_bit(&subreq->flags, NETFS_SREQ_IN_PROGRESS, - TASK_UNINTERRUPTIBLE); + if (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags)) + continue; + + trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue); + for (;;) { + prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE); + + if (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags)) + break; + + trace_netfs_sreq(subreq, netfs_sreq_trace_wait_for); + schedule(); + trace_netfs_rreq(rreq, netfs_rreq_trace_woke_queue); + } + + finish_wait(&rreq->waitq, &myself); } + clear_bit(NETFS_RREQ_RETRYING, &rreq->flags); trace_netfs_rreq(rreq, netfs_rreq_trace_resubmit); netfs_retry_read_subrequests(rreq); diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c index f1af344266cc..ab6b916addc4 100644 --- a/fs/netfs/stats.c +++ b/fs/netfs/stats.c @@ -29,6 +29,8 @@ atomic_t netfs_n_rh_write_begin; atomic_t netfs_n_rh_write_done; atomic_t netfs_n_rh_write_failed; atomic_t netfs_n_rh_write_zskip; +atomic_t netfs_n_rh_retry_read_req; +atomic_t netfs_n_rh_retry_read_subreq; atomic_t netfs_n_wh_buffered_write; atomic_t netfs_n_wh_writethrough; atomic_t netfs_n_wh_dio_write; @@ -41,6 +43,8 @@ atomic_t netfs_n_wh_upload_failed; atomic_t netfs_n_wh_write; atomic_t netfs_n_wh_write_done; atomic_t netfs_n_wh_write_failed; +atomic_t netfs_n_wh_retry_write_req; +atomic_t netfs_n_wh_retry_write_subreq; atomic_t netfs_n_wb_lock_skip; atomic_t netfs_n_wb_lock_wait; atomic_t netfs_n_folioq; @@ -81,6 +85,11 @@ int netfs_stats_show(struct seq_file *m, void *v) atomic_read(&netfs_n_wh_write), atomic_read(&netfs_n_wh_write_done), atomic_read(&netfs_n_wh_write_failed)); + seq_printf(m, "Retries: rq=%u rs=%u wq=%u ws=%u\n", + atomic_read(&netfs_n_rh_retry_read_req), + atomic_read(&netfs_n_rh_retry_read_subreq), + atomic_read(&netfs_n_wh_retry_write_req), + atomic_read(&netfs_n_wh_retry_write_subreq)); seq_printf(m, "Objs : rr=%u sr=%u foq=%u wsc=%u\n", atomic_read(&netfs_n_rh_rreq), atomic_read(&netfs_n_rh_sreq), diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 69727411683e..77279fc5b5a7 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -253,6 +253,7 @@ void netfs_reissue_write(struct netfs_io_stream *stream, subreq->retry_count++; __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); + netfs_stat(&netfs_n_wh_retry_write_subreq); netfs_do_issue_write(stream, subreq); } diff --git a/fs/netfs/write_retry.c b/fs/netfs/write_retry.c index c841a851dd73..545d33079a77 100644 --- a/fs/netfs/write_retry.c +++ b/fs/netfs/write_retry.c @@ -203,6 +203,8 @@ void netfs_retry_writes(struct netfs_io_request *wreq) struct netfs_io_stream *stream; int s; + netfs_stat(&netfs_n_wh_retry_write_req); + /* Wait for all outstanding I/O to quiesce before performing retries as * we may need to renegotiate the I/O sizes. */ diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 035ba52742a5..4db912f56230 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -781,6 +781,43 @@ int nfs4_inode_return_delegation(struct inode *inode) } /** + * nfs4_inode_set_return_delegation_on_close - asynchronously return a delegation + * @inode: inode to process + * + * This routine is called to request that the delegation be returned as soon + * as the file is closed. If the file is already closed, the delegation is + * immediately returned. + */ +void nfs4_inode_set_return_delegation_on_close(struct inode *inode) +{ + struct nfs_delegation *delegation; + struct nfs_delegation *ret = NULL; + + if (!inode) + return; + rcu_read_lock(); + delegation = nfs4_get_valid_delegation(inode); + if (!delegation) + goto out; + spin_lock(&delegation->lock); + if (!delegation->inode) + goto out_unlock; + if (list_empty(&NFS_I(inode)->open_files) && + !test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) { + /* Refcount matched in nfs_end_delegation_return() */ + ret = nfs_get_delegation(delegation); + } else + set_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags); +out_unlock: + spin_unlock(&delegation->lock); + if (ret) + nfs_clear_verifier_delegated(inode); +out: + rcu_read_unlock(); + nfs_end_delegation_return(inode, ret, 0); +} + +/** * nfs4_inode_return_delegation_on_close - asynchronously return a delegation * @inode: inode to process * diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index 71524d34ed20..8ff5ab9c5c25 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -49,6 +49,7 @@ void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred, unsigned long pagemod_limit, u32 deleg_type); int nfs4_inode_return_delegation(struct inode *inode); void nfs4_inode_return_delegation_on_close(struct inode *inode); +void nfs4_inode_set_return_delegation_on_close(struct inode *inode); int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid); void nfs_inode_evict_delegation(struct inode *inode); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index f45beea92d03..f32f8d7c9122 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -56,6 +56,7 @@ #include <linux/uaccess.h> #include <linux/atomic.h> +#include "delegation.h" #include "internal.h" #include "iostat.h" #include "pnfs.h" @@ -130,6 +131,20 @@ static void nfs_direct_truncate_request(struct nfs_direct_req *dreq, dreq->count = req_start; } +static void nfs_direct_file_adjust_size_locked(struct inode *inode, + loff_t offset, size_t count) +{ + loff_t newsize = offset + (loff_t)count; + loff_t oldsize = i_size_read(inode); + + if (newsize > oldsize) { + i_size_write(inode, newsize); + NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_SIZE; + trace_nfs_size_grow(inode, newsize); + nfs_inc_stats(inode, NFSIOS_EXTENDWRITE); + } +} + /** * nfs_swap_rw - NFS address space operation for swap I/O * @iocb: target I/O control block @@ -272,6 +287,8 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr) nfs_direct_count_bytes(dreq, hdr); spin_unlock(&dreq->lock); + nfs_update_delegated_atime(dreq->inode); + while (!list_empty(&hdr->pages)) { struct nfs_page *req = nfs_list_entry(hdr->pages.next); struct page *page = req->wb_page; @@ -741,6 +758,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) struct nfs_direct_req *dreq = hdr->dreq; struct nfs_commit_info cinfo; struct nfs_page *req = nfs_list_entry(hdr->pages.next); + struct inode *inode = dreq->inode; int flags = NFS_ODIRECT_DONE; trace_nfs_direct_write_completion(dreq); @@ -762,6 +780,11 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) } spin_unlock(&dreq->lock); + spin_lock(&inode->i_lock); + nfs_direct_file_adjust_size_locked(inode, dreq->io_start, dreq->count); + nfs_update_delegated_mtime_locked(dreq->inode); + spin_unlock(&inode->i_lock); + while (!list_empty(&hdr->pages)) { req = nfs_list_entry(hdr->pages.next); diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 1bb646752e46..033feeab8c34 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -29,6 +29,7 @@ #include <linux/pagemap.h> #include <linux/gfp.h> #include <linux/swap.h> +#include <linux/compaction.h> #include <linux/uaccess.h> #include <linux/filelock.h> @@ -457,7 +458,7 @@ static bool nfs_release_folio(struct folio *folio, gfp_t gfp) /* If the private flag is set, then the folio is not freeable */ if (folio_test_private(folio)) { if ((current_gfp_context(gfp) & GFP_KERNEL) != GFP_KERNEL || - current_is_kswapd()) + current_is_kswapd() || current_is_kcompactd()) return false; if (nfs_wb_folio(folio->mapping->host, folio) < 0) return false; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index df9669d4ded7..6e95db6c17e9 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -133,6 +133,7 @@ nfs4_label_init_security(struct inode *dir, struct dentry *dentry, if (err) return NULL; + label->lsmid = shim.id; label->label = shim.context; label->len = shim.len; return label; @@ -145,7 +146,7 @@ nfs4_label_release_security(struct nfs4_label *label) if (label) { shim.context = label->label; shim.len = label->len; - shim.id = LSM_ID_UNDEF; + shim.id = label->lsmid; security_release_secctx(&shim); } } @@ -3906,8 +3907,11 @@ nfs4_atomic_open(struct inode *dir, struct nfs_open_context *ctx, static void nfs4_close_context(struct nfs_open_context *ctx, int is_sync) { + struct dentry *dentry = ctx->dentry; if (ctx->state == NULL) return; + if (dentry->d_flags & DCACHE_NFSFS_RENAMED) + nfs4_inode_set_return_delegation_on_close(d_inode(dentry)); if (is_sync) nfs4_close_sync(ctx->state, _nfs4_ctx_to_openmode(ctx)); else @@ -6269,7 +6273,7 @@ static int _nfs4_get_security_label(struct inode *inode, void *buf, size_t buflen) { struct nfs_server *server = NFS_SERVER(inode); - struct nfs4_label label = {0, 0, buflen, buf}; + struct nfs4_label label = {0, 0, 0, buflen, buf}; u32 bitmask[3] = { 0, 0, FATTR4_WORD2_SECURITY_LABEL }; struct nfs_fattr fattr = { @@ -6374,7 +6378,7 @@ static int nfs4_do_set_security_label(struct inode *inode, static int nfs4_set_security_label(struct inode *inode, const void *buf, size_t buflen) { - struct nfs4_label ilabel = {0, 0, buflen, (char *)buf }; + struct nfs4_label ilabel = {0, 0, 0, buflen, (char *)buf }; struct nfs_fattr *fattr; int status; diff --git a/fs/nsfs.c b/fs/nsfs.c index 663f8656158d..f7fddf8ecf73 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -37,7 +37,6 @@ static char *ns_dname(struct dentry *dentry, char *buffer, int buflen) } const struct dentry_operations ns_dentry_operations = { - .d_delete = always_delete_dentry, .d_dname = ns_dname, .d_prune = stashed_dentry_prune, }; diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 0c28e5fa3407..d7310fcf3888 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -618,7 +618,6 @@ static int ovl_link_up(struct ovl_copy_up_ctx *c) err = PTR_ERR(upper); if (!IS_ERR(upper)) { err = ovl_do_link(ofs, ovl_dentry_upper(c->dentry), udir, upper); - dput(upper); if (!err) { /* Restore timestamps on parent (best effort) */ @@ -626,6 +625,7 @@ static int ovl_link_up(struct ovl_copy_up_ctx *c) ovl_dentry_set_upper_alias(c->dentry); ovl_dentry_update_reval(c->dentry, upper); } + dput(upper); } inode_unlock(udir); if (err) diff --git a/fs/pidfs.c b/fs/pidfs.c index 63f9699ebac3..c0478b3c55d9 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -521,7 +521,6 @@ static char *pidfs_dname(struct dentry *dentry, char *buffer, int buflen) } const struct dentry_operations pidfs_dentry_operations = { - .d_delete = always_delete_dentry, .d_dname = pidfs_dname, .d_prune = stashed_dentry_prune, }; diff --git a/fs/pipe.c b/fs/pipe.c index ce1af7592780..4d0799e4e719 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -210,11 +210,10 @@ static const struct pipe_buf_operations anon_pipe_buf_ops = { /* Done while waiting without holding the pipe lock - thus the READ_ONCE() */ static inline bool pipe_readable(const struct pipe_inode_info *pipe) { - unsigned int head = READ_ONCE(pipe->head); - unsigned int tail = READ_ONCE(pipe->tail); + union pipe_index idx = { .head_tail = READ_ONCE(pipe->head_tail) }; unsigned int writers = READ_ONCE(pipe->writers); - return !pipe_empty(head, tail) || !writers; + return !pipe_empty(idx.head, idx.tail) || !writers; } static inline unsigned int pipe_update_tail(struct pipe_inode_info *pipe, @@ -395,7 +394,7 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) wake_next_reader = true; mutex_lock(&pipe->mutex); } - if (pipe_empty(pipe->head, pipe->tail)) + if (pipe_is_empty(pipe)) wake_next_reader = false; mutex_unlock(&pipe->mutex); @@ -417,11 +416,10 @@ static inline int is_packetized(struct file *file) /* Done while waiting without holding the pipe lock - thus the READ_ONCE() */ static inline bool pipe_writable(const struct pipe_inode_info *pipe) { - unsigned int head = READ_ONCE(pipe->head); - unsigned int tail = READ_ONCE(pipe->tail); + union pipe_index idx = { .head_tail = READ_ONCE(pipe->head_tail) }; unsigned int max_usage = READ_ONCE(pipe->max_usage); - return !pipe_full(head, tail, max_usage) || + return !pipe_full(idx.head, idx.tail, max_usage) || !READ_ONCE(pipe->readers); } @@ -579,11 +577,11 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); wait_event_interruptible_exclusive(pipe->wr_wait, pipe_writable(pipe)); mutex_lock(&pipe->mutex); - was_empty = pipe_empty(pipe->head, pipe->tail); + was_empty = pipe_is_empty(pipe); wake_next_writer = true; } out: - if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) + if (pipe_is_full(pipe)) wake_next_writer = false; mutex_unlock(&pipe->mutex); @@ -616,7 +614,7 @@ out: static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct pipe_inode_info *pipe = filp->private_data; - unsigned int count, head, tail, mask; + unsigned int count, head, tail; switch (cmd) { case FIONREAD: @@ -624,10 +622,9 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) count = 0; head = pipe->head; tail = pipe->tail; - mask = pipe->ring_size - 1; - while (tail != head) { - count += pipe->bufs[tail & mask].len; + while (!pipe_empty(head, tail)) { + count += pipe_buf(pipe, tail)->len; tail++; } mutex_unlock(&pipe->mutex); @@ -659,7 +656,7 @@ pipe_poll(struct file *filp, poll_table *wait) { __poll_t mask; struct pipe_inode_info *pipe = filp->private_data; - unsigned int head, tail; + union pipe_index idx; /* Epoll has some historical nasty semantics, this enables them */ WRITE_ONCE(pipe->poll_usage, true); @@ -680,19 +677,18 @@ pipe_poll(struct file *filp, poll_table *wait) * if something changes and you got it wrong, the poll * table entry will wake you up and fix it. */ - head = READ_ONCE(pipe->head); - tail = READ_ONCE(pipe->tail); + idx.head_tail = READ_ONCE(pipe->head_tail); mask = 0; if (filp->f_mode & FMODE_READ) { - if (!pipe_empty(head, tail)) + if (!pipe_empty(idx.head, idx.tail)) mask |= EPOLLIN | EPOLLRDNORM; if (!pipe->writers && filp->f_pipe != pipe->w_counter) mask |= EPOLLHUP; } if (filp->f_mode & FMODE_WRITE) { - if (!pipe_full(head, tail, pipe->max_usage)) + if (!pipe_full(idx.head, idx.tail, pipe->max_usage)) mask |= EPOLLOUT | EPOLLWRNORM; /* * Most Unices do not set EPOLLERR for FIFOs but on Linux they diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index a00120a3c099..10d01eb09c43 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -1524,7 +1524,7 @@ int vmcore_add_device_dump(struct vmcoredd_data *data) pr_warn_once("Unexpected adding of device dump\n"); if (vmcore_open) { ret = -EBUSY; - goto out_err; + goto unlock; } list_add_tail(&dump->list, &vmcoredd_list); @@ -1532,6 +1532,9 @@ int vmcore_add_device_dump(struct vmcoredd_data *data) mutex_unlock(&vmcore_mutex); return 0; +unlock: + mutex_unlock(&vmcore_mutex); + out_err: vfree(buf); vfree(dump); diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c index 699a3f76d083..64bd68f750f8 100644 --- a/fs/smb/client/cifsacl.c +++ b/fs/smb/client/cifsacl.c @@ -763,7 +763,7 @@ static void parse_dacl(struct smb_acl *pdacl, char *end_of_acl, struct cifs_fattr *fattr, bool mode_from_special_sid) { int i; - int num_aces = 0; + u16 num_aces = 0; int acl_size; char *acl_base; struct smb_ace **ppace; @@ -778,14 +778,15 @@ static void parse_dacl(struct smb_acl *pdacl, char *end_of_acl, } /* validate that we do not go past end of acl */ - if (end_of_acl < (char *)pdacl + le16_to_cpu(pdacl->size)) { + if (end_of_acl < (char *)pdacl + sizeof(struct smb_acl) || + end_of_acl < (char *)pdacl + le16_to_cpu(pdacl->size)) { cifs_dbg(VFS, "ACL too small to parse DACL\n"); return; } cifs_dbg(NOISY, "DACL revision %d size %d num aces %d\n", le16_to_cpu(pdacl->revision), le16_to_cpu(pdacl->size), - le32_to_cpu(pdacl->num_aces)); + le16_to_cpu(pdacl->num_aces)); /* reset rwx permissions for user/group/other. Also, if num_aces is 0 i.e. DACL has no ACEs, @@ -795,12 +796,15 @@ static void parse_dacl(struct smb_acl *pdacl, char *end_of_acl, acl_base = (char *)pdacl; acl_size = sizeof(struct smb_acl); - num_aces = le32_to_cpu(pdacl->num_aces); + num_aces = le16_to_cpu(pdacl->num_aces); if (num_aces > 0) { umode_t denied_mode = 0; - if (num_aces > ULONG_MAX / sizeof(struct smb_ace *)) + if (num_aces > (le16_to_cpu(pdacl->size) - sizeof(struct smb_acl)) / + (offsetof(struct smb_ace, sid) + + offsetof(struct smb_sid, sub_auth) + sizeof(__le16))) return; + ppace = kmalloc_array(num_aces, sizeof(struct smb_ace *), GFP_KERNEL); if (!ppace) @@ -937,12 +941,12 @@ unsigned int setup_special_user_owner_ACE(struct smb_ace *pntace) static void populate_new_aces(char *nacl_base, struct smb_sid *pownersid, struct smb_sid *pgrpsid, - __u64 *pnmode, u32 *pnum_aces, u16 *pnsize, + __u64 *pnmode, u16 *pnum_aces, u16 *pnsize, bool modefromsid, bool posix) { __u64 nmode; - u32 num_aces = 0; + u16 num_aces = 0; u16 nsize = 0; __u64 user_mode; __u64 group_mode; @@ -1050,7 +1054,7 @@ static __u16 replace_sids_and_copy_aces(struct smb_acl *pdacl, struct smb_acl *p u16 size = 0; struct smb_ace *pntace = NULL; char *acl_base = NULL; - u32 src_num_aces = 0; + u16 src_num_aces = 0; u16 nsize = 0; struct smb_ace *pnntace = NULL; char *nacl_base = NULL; @@ -1058,7 +1062,7 @@ static __u16 replace_sids_and_copy_aces(struct smb_acl *pdacl, struct smb_acl *p acl_base = (char *)pdacl; size = sizeof(struct smb_acl); - src_num_aces = le32_to_cpu(pdacl->num_aces); + src_num_aces = le16_to_cpu(pdacl->num_aces); nacl_base = (char *)pndacl; nsize = sizeof(struct smb_acl); @@ -1090,11 +1094,11 @@ static int set_chmod_dacl(struct smb_acl *pdacl, struct smb_acl *pndacl, u16 size = 0; struct smb_ace *pntace = NULL; char *acl_base = NULL; - u32 src_num_aces = 0; + u16 src_num_aces = 0; u16 nsize = 0; struct smb_ace *pnntace = NULL; char *nacl_base = NULL; - u32 num_aces = 0; + u16 num_aces = 0; bool new_aces_set = false; /* Assuming that pndacl and pnmode are never NULL */ @@ -1112,7 +1116,7 @@ static int set_chmod_dacl(struct smb_acl *pdacl, struct smb_acl *pndacl, acl_base = (char *)pdacl; size = sizeof(struct smb_acl); - src_num_aces = le32_to_cpu(pdacl->num_aces); + src_num_aces = le16_to_cpu(pdacl->num_aces); /* Retain old ACEs which we can retain */ for (i = 0; i < src_num_aces; ++i) { @@ -1158,7 +1162,7 @@ next_ace: } finalize_dacl: - pndacl->num_aces = cpu_to_le32(num_aces); + pndacl->num_aces = cpu_to_le16(num_aces); pndacl->size = cpu_to_le16(nsize); return 0; @@ -1293,7 +1297,7 @@ static int build_sec_desc(struct smb_ntsd *pntsd, struct smb_ntsd *pnntsd, dacloffset ? dacl_ptr->revision : cpu_to_le16(ACL_REVISION); ndacl_ptr->size = cpu_to_le16(0); - ndacl_ptr->num_aces = cpu_to_le32(0); + ndacl_ptr->num_aces = cpu_to_le16(0); rc = set_chmod_dacl(dacl_ptr, ndacl_ptr, owner_sid_ptr, group_sid_ptr, pnmode, mode_from_sid, posix); @@ -1653,7 +1657,7 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode, dacl_ptr = (struct smb_acl *)((char *)pntsd + dacloffset); if (mode_from_sid) nsecdesclen += - le32_to_cpu(dacl_ptr->num_aces) * sizeof(struct smb_ace); + le16_to_cpu(dacl_ptr->num_aces) * sizeof(struct smb_ace); else /* cifsacl */ nsecdesclen += le16_to_cpu(dacl_ptr->size); } diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 4bdd6a43e521..cddeb2adbf4a 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -253,6 +253,7 @@ struct cifs_cred { struct cifs_open_info_data { bool adjust_tz; bool reparse_point; + bool contains_posix_file_info; struct { /* ioctl response buffer */ struct { @@ -2324,8 +2325,8 @@ struct smb2_compound_vars { struct kvec io_iov[SMB2_IOCTL_IOV_SIZE]; struct kvec si_iov[SMB2_SET_INFO_IOV_SIZE]; struct kvec close_iov; - struct smb2_file_rename_info rename_info; - struct smb2_file_link_info link_info; + struct smb2_file_rename_info_hdr rename_info; + struct smb2_file_link_info_hdr link_info; struct kvec ea_iov; }; diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 3feaa0f68169..d07682020c64 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1338,7 +1338,8 @@ cifs_readv_callback(struct mid_q_entry *mid) rdata->credits.value = 0; rdata->subreq.error = rdata->result; rdata->subreq.transferred += rdata->got_bytes; - queue_work(cifsiod_wq, &rdata->subreq.work); + trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_progress); + netfs_read_subreq_terminated(&rdata->subreq); release_mid(mid); add_credits(server, &credits, 0); } diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index f917de020dd5..73f93a35eedd 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -1825,9 +1825,8 @@ static int match_session(struct cifs_ses *ses, struct smb3_fs_context *ctx, bool match_super) { - if (ctx->sectype != Unspecified && - ctx->sectype != ses->sectype) - return 0; + struct TCP_Server_Info *server = ses->server; + enum securityEnum ctx_sec, ses_sec; if (!match_super && ctx->dfs_root_ses != ses->dfs_root_ses) return 0; @@ -1839,11 +1838,20 @@ static int match_session(struct cifs_ses *ses, if (ses->chan_max < ctx->max_channels) return 0; - switch (ses->sectype) { + ctx_sec = server->ops->select_sectype(server, ctx->sectype); + ses_sec = server->ops->select_sectype(server, ses->sectype); + + if (ctx_sec != ses_sec) + return 0; + + switch (ctx_sec) { + case IAKerb: case Kerberos: if (!uid_eq(ctx->cred_uid, ses->cred_uid)) return 0; break; + case NTLMv2: + case RawNTLMSSP: default: /* NULL username means anonymous session */ if (ses->user_name == NULL) { diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index e9b286d9a7ba..8c73d4d60d1a 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -171,6 +171,7 @@ const struct fs_parameter_spec smb3_fs_parameters[] = { fsparam_string("username", Opt_user), fsparam_string("pass", Opt_pass), fsparam_string("password", Opt_pass), + fsparam_string("pass2", Opt_pass2), fsparam_string("password2", Opt_pass2), fsparam_string("ip", Opt_ip), fsparam_string("addr", Opt_ip), @@ -1131,6 +1132,9 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, } else if (!strcmp("user", param->key) || !strcmp("username", param->key)) { skip_parsing = true; opt = Opt_user; + } else if (!strcmp("pass2", param->key) || !strcmp("password2", param->key)) { + skip_parsing = true; + opt = Opt_pass2; } } @@ -1340,21 +1344,21 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, } break; case Opt_acregmax: - ctx->acregmax = HZ * result.uint_32; - if (ctx->acregmax > CIFS_MAX_ACTIMEO) { + if (result.uint_32 > CIFS_MAX_ACTIMEO / HZ) { cifs_errorf(fc, "acregmax too large\n"); goto cifs_parse_mount_err; } + ctx->acregmax = HZ * result.uint_32; break; case Opt_acdirmax: - ctx->acdirmax = HZ * result.uint_32; - if (ctx->acdirmax > CIFS_MAX_ACTIMEO) { + if (result.uint_32 > CIFS_MAX_ACTIMEO / HZ) { cifs_errorf(fc, "acdirmax too large\n"); goto cifs_parse_mount_err; } + ctx->acdirmax = HZ * result.uint_32; break; case Opt_actimeo: - if (HZ * result.uint_32 > CIFS_MAX_ACTIMEO) { + if (result.uint_32 > CIFS_MAX_ACTIMEO / HZ) { cifs_errorf(fc, "timeout too large\n"); goto cifs_parse_mount_err; } @@ -1366,11 +1370,11 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, ctx->acdirmax = ctx->acregmax = HZ * result.uint_32; break; case Opt_closetimeo: - ctx->closetimeo = HZ * result.uint_32; - if (ctx->closetimeo > SMB3_MAX_DCLOSETIMEO) { + if (result.uint_32 > SMB3_MAX_DCLOSETIMEO / HZ) { cifs_errorf(fc, "closetimeo too large\n"); goto cifs_parse_mount_err; } + ctx->closetimeo = HZ * result.uint_32; break; case Opt_echo_interval: ctx->echo_interval = result.uint_32; diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 9cc31cf6ebd0..616149c7f0a5 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -1215,6 +1215,19 @@ static int reparse_info_to_fattr(struct cifs_open_info_data *data, rc = server->ops->parse_reparse_point(cifs_sb, full_path, iov, data); + /* + * If the reparse point was not handled but it is the + * name surrogate which points to directory, then treat + * is as a new mount point. Name surrogate reparse point + * represents another named entity in the system. + */ + if (rc == -EOPNOTSUPP && + IS_REPARSE_TAG_NAME_SURROGATE(data->reparse.tag) && + (le32_to_cpu(data->fi.Attributes) & ATTR_DIRECTORY)) { + rc = 0; + cifs_create_junction_fattr(fattr, sb); + goto out; + } } if (data->reparse.tag == IO_REPARSE_TAG_SYMLINK && !rc) { @@ -1408,7 +1421,7 @@ int cifs_get_inode_info(struct inode **inode, struct cifs_fattr fattr = {}; int rc; - if (is_inode_cache_good(*inode)) { + if (!data && is_inode_cache_good(*inode)) { cifs_dbg(FYI, "No need to revalidate cached inode sizes\n"); return 0; } @@ -1507,7 +1520,7 @@ int smb311_posix_get_inode_info(struct inode **inode, struct cifs_fattr fattr = {}; int rc; - if (is_inode_cache_good(*inode)) { + if (!data && is_inode_cache_good(*inode)) { cifs_dbg(FYI, "No need to revalidate cached inode sizes\n"); return 0; } diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index 0a5a52a8a7dd..2b9e9885dc42 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -1088,13 +1088,12 @@ int parse_reparse_point(struct reparse_data_buffer *buf, le32_to_cpu(buf->ReparseTag)); return -EIO; } - break; + return 0; default: cifs_tcon_dbg(VFS | ONCE, "unhandled reparse tag: 0x%08x\n", le32_to_cpu(buf->ReparseTag)); - break; + return -EOPNOTSUPP; } - return 0; } int smb2_parse_reparse_point(struct cifs_sb_info *cifs_sb, diff --git a/fs/smb/client/reparse.h b/fs/smb/client/reparse.h index 5a753fec7e2c..c0be5ab45a78 100644 --- a/fs/smb/client/reparse.h +++ b/fs/smb/client/reparse.h @@ -99,14 +99,30 @@ static inline bool reparse_inode_match(struct inode *inode, static inline bool cifs_open_data_reparse(struct cifs_open_info_data *data) { - struct smb2_file_all_info *fi = &data->fi; - u32 attrs = le32_to_cpu(fi->Attributes); + u32 attrs; bool ret; - ret = data->reparse_point || (attrs & ATTR_REPARSE); - if (ret) - attrs |= ATTR_REPARSE; - fi->Attributes = cpu_to_le32(attrs); + if (data->contains_posix_file_info) { + struct smb311_posix_qinfo *fi = &data->posix_fi; + + attrs = le32_to_cpu(fi->DosAttributes); + if (data->reparse_point) { + attrs |= ATTR_REPARSE; + fi->DosAttributes = cpu_to_le32(attrs); + } + + } else { + struct smb2_file_all_info *fi = &data->fi; + + attrs = le32_to_cpu(fi->Attributes); + if (data->reparse_point) { + attrs |= ATTR_REPARSE; + fi->Attributes = cpu_to_le32(attrs); + } + } + + ret = attrs & ATTR_REPARSE; + return ret; } diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 5dfb30b0a852..826b57a5a2a8 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -650,6 +650,7 @@ finished: switch (cmds[i]) { case SMB2_OP_QUERY_INFO: idata = in_iov[i].iov_base; + idata->contains_posix_file_info = false; if (rc == 0 && cfile && cfile->symlink_target) { idata->symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL); if (!idata->symlink_target) @@ -673,6 +674,7 @@ finished: break; case SMB2_OP_POSIX_QUERY_INFO: idata = in_iov[i].iov_base; + idata->contains_posix_file_info = true; if (rc == 0 && cfile && cfile->symlink_target) { idata->symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL); if (!idata->symlink_target) @@ -770,6 +772,7 @@ finished: idata = in_iov[i].iov_base; idata->reparse.io.iov = *iov; idata->reparse.io.buftype = resp_buftype[i + 1]; + idata->contains_posix_file_info = false; /* BB VERIFY */ rbuf = reparse_buf_ptr(iov); if (IS_ERR(rbuf)) { rc = PTR_ERR(rbuf); @@ -791,6 +794,7 @@ finished: case SMB2_OP_QUERY_WSL_EA: if (!rc) { idata = in_iov[i].iov_base; + idata->contains_posix_file_info = false; qi_rsp = rsp_iov[i + 1].iov_base; data[0] = (u8 *)qi_rsp + le16_to_cpu(qi_rsp->OutputBufferOffset); size[0] = le32_to_cpu(qi_rsp->OutputBufferLength); diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index ec36bed54b0b..4dd11eafb69d 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -1001,6 +1001,7 @@ static int smb2_query_file_info(const unsigned int xid, struct cifs_tcon *tcon, if (!data->symlink_target) return -ENOMEM; } + data->contains_posix_file_info = false; return SMB2_query_info(xid, tcon, fid->persistent_fid, fid->volatile_fid, &data->fi); } @@ -4964,6 +4965,10 @@ one_more: next_buffer = (char *)cifs_buf_get(); else next_buffer = (char *)cifs_small_buf_get(); + if (!next_buffer) { + cifs_server_dbg(VFS, "No memory for (large) SMB response\n"); + return -1; + } memcpy(next_buffer, buf + next_cmd, pdu_length - next_cmd); } @@ -5146,7 +5151,7 @@ int __cifs_sfu_make_node(unsigned int xid, struct inode *inode, FILE_CREATE, CREATE_NOT_DIR | CREATE_OPTION_SPECIAL, ACL_NO_MODE); oparms.fid = &fid; - + idata.contains_posix_file_info = false; rc = server->ops->open(xid, &oparms, &oplock, &idata); if (rc) goto out; diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h index 3336df2ea5d4..c7a0efda4403 100644 --- a/fs/smb/common/smb2pdu.h +++ b/fs/smb/common/smb2pdu.h @@ -1707,23 +1707,33 @@ struct smb2_file_internal_info { } __packed; /* level 6 Query */ struct smb2_file_rename_info { /* encoding of request for level 10 */ - __u8 ReplaceIfExists; /* 1 = replace existing target with new */ - /* 0 = fail if target already exists */ - __u8 Reserved[7]; - __u64 RootDirectory; /* MBZ for network operations (why says spec?) */ - __le32 FileNameLength; + /* New members MUST be added within the struct_group() macro below. */ + __struct_group(smb2_file_rename_info_hdr, __hdr, __packed, + __u8 ReplaceIfExists; /* 1 = replace existing target with new */ + /* 0 = fail if target already exists */ + __u8 Reserved[7]; + __u64 RootDirectory; /* MBZ for network operations (why says spec?) */ + __le32 FileNameLength; + ); char FileName[]; /* New name to be assigned */ /* padding - overall struct size must be >= 24 so filename + pad >= 6 */ } __packed; /* level 10 Set */ +static_assert(offsetof(struct smb2_file_rename_info, FileName) == sizeof(struct smb2_file_rename_info_hdr), + "struct member likely outside of __struct_group()"); struct smb2_file_link_info { /* encoding of request for level 11 */ - __u8 ReplaceIfExists; /* 1 = replace existing link with new */ - /* 0 = fail if link already exists */ - __u8 Reserved[7]; - __u64 RootDirectory; /* MBZ for network operations (why says spec?) */ - __le32 FileNameLength; + /* New members MUST be added within the struct_group() macro below. */ + __struct_group(smb2_file_link_info_hdr, __hdr, __packed, + __u8 ReplaceIfExists; /* 1 = replace existing link with new */ + /* 0 = fail if link already exists */ + __u8 Reserved[7]; + __u64 RootDirectory; /* MBZ for network operations (why says spec?) */ + __le32 FileNameLength; + ); char FileName[]; /* Name to be assigned to new link */ } __packed; /* level 11 Set */ +static_assert(offsetof(struct smb2_file_link_info, FileName) == sizeof(struct smb2_file_link_info_hdr), + "struct member likely outside of __struct_group()"); /* * This level 18, although with struct with same name is different from cifs diff --git a/fs/smb/common/smbacl.h b/fs/smb/common/smbacl.h index 6a60698fc6f0..a624ec9e4a14 100644 --- a/fs/smb/common/smbacl.h +++ b/fs/smb/common/smbacl.h @@ -107,7 +107,8 @@ struct smb_sid { struct smb_acl { __le16 revision; /* revision level */ __le16 size; - __le32 num_aces; + __le16 num_aces; + __le16 reserved; } __attribute__((packed)); struct smb_ace { diff --git a/fs/smb/common/smbfsctl.h b/fs/smb/common/smbfsctl.h index 4b379e84c46b..3253a18ecb5c 100644 --- a/fs/smb/common/smbfsctl.h +++ b/fs/smb/common/smbfsctl.h @@ -159,6 +159,9 @@ #define IO_REPARSE_TAG_LX_CHR 0x80000025 #define IO_REPARSE_TAG_LX_BLK 0x80000026 +/* If Name Surrogate Bit is set, the file or directory represents another named entity in the system. */ +#define IS_REPARSE_TAG_NAME_SURROGATE(tag) (!!((tag) & 0x20000000)) + /* fsctl flags */ /* If Flags is set to this value, the request is an FSCTL not ioctl request */ #define SMB2_0_IOCTL_IS_FSCTL 0x00000001 diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index f8a40f65db6a..c1f22c129111 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -433,6 +433,26 @@ void ksmbd_conn_init_server_callbacks(struct ksmbd_conn_ops *ops) default_conn_ops.terminate_fn = ops->terminate_fn; } +void ksmbd_conn_r_count_inc(struct ksmbd_conn *conn) +{ + atomic_inc(&conn->r_count); +} + +void ksmbd_conn_r_count_dec(struct ksmbd_conn *conn) +{ + /* + * Checking waitqueue to dropping pending requests on + * disconnection. waitqueue_active is safe because it + * uses atomic operation for condition. + */ + atomic_inc(&conn->refcnt); + if (!atomic_dec_return(&conn->r_count) && waitqueue_active(&conn->r_count_q)) + wake_up(&conn->r_count_q); + + if (atomic_dec_and_test(&conn->refcnt)) + kfree(conn); +} + int ksmbd_conn_transport_init(void) { int ret; diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index b379ae4fdcdf..91c2318639e7 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -168,6 +168,8 @@ int ksmbd_conn_transport_init(void); void ksmbd_conn_transport_destroy(void); void ksmbd_conn_lock(struct ksmbd_conn *conn); void ksmbd_conn_unlock(struct ksmbd_conn *conn); +void ksmbd_conn_r_count_inc(struct ksmbd_conn *conn); +void ksmbd_conn_r_count_dec(struct ksmbd_conn *conn); /* * WARNING diff --git a/fs/smb/server/ksmbd_work.c b/fs/smb/server/ksmbd_work.c index 4af2e6007c29..72b00ca6e455 100644 --- a/fs/smb/server/ksmbd_work.c +++ b/fs/smb/server/ksmbd_work.c @@ -26,7 +26,6 @@ struct ksmbd_work *ksmbd_alloc_work_struct(void) INIT_LIST_HEAD(&work->request_entry); INIT_LIST_HEAD(&work->async_request_entry); INIT_LIST_HEAD(&work->fp_entry); - INIT_LIST_HEAD(&work->interim_entry); INIT_LIST_HEAD(&work->aux_read_list); work->iov_alloc_cnt = 4; work->iov = kcalloc(work->iov_alloc_cnt, sizeof(struct kvec), @@ -56,8 +55,6 @@ void ksmbd_free_work_struct(struct ksmbd_work *work) kfree(work->tr_buf); kvfree(work->request_buf); kfree(work->iov); - if (!list_empty(&work->interim_entry)) - list_del(&work->interim_entry); if (work->async_id) ksmbd_release_id(&work->conn->async_ida, work->async_id); diff --git a/fs/smb/server/ksmbd_work.h b/fs/smb/server/ksmbd_work.h index 8ca2c813246e..d36393ff8310 100644 --- a/fs/smb/server/ksmbd_work.h +++ b/fs/smb/server/ksmbd_work.h @@ -89,7 +89,6 @@ struct ksmbd_work { /* List head at conn->async_requests */ struct list_head async_request_entry; struct list_head fp_entry; - struct list_head interim_entry; }; /** diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 3a3fe4afbdf0..28886ff1ee57 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -46,7 +46,6 @@ static struct oplock_info *alloc_opinfo(struct ksmbd_work *work, opinfo->fid = id; opinfo->Tid = Tid; INIT_LIST_HEAD(&opinfo->op_entry); - INIT_LIST_HEAD(&opinfo->interim_list); init_waitqueue_head(&opinfo->oplock_q); init_waitqueue_head(&opinfo->oplock_brk); atomic_set(&opinfo->refcount, 1); @@ -635,6 +634,7 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) { struct smb2_oplock_break *rsp = NULL; struct ksmbd_work *work = container_of(wk, struct ksmbd_work, work); + struct ksmbd_conn *conn = work->conn; struct oplock_break_info *br_info = work->request_buf; struct smb2_hdr *rsp_hdr; struct ksmbd_file *fp; @@ -690,6 +690,7 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) out: ksmbd_free_work_struct(work); + ksmbd_conn_r_count_dec(conn); } /** @@ -724,6 +725,7 @@ static int smb2_oplock_break_noti(struct oplock_info *opinfo) work->sess = opinfo->sess; if (opinfo->op_state == OPLOCK_ACK_WAIT) { + ksmbd_conn_r_count_inc(conn); INIT_WORK(&work->work, __smb2_oplock_break_noti); ksmbd_queue_work(work); @@ -745,6 +747,7 @@ static void __smb2_lease_break_noti(struct work_struct *wk) { struct smb2_lease_break *rsp = NULL; struct ksmbd_work *work = container_of(wk, struct ksmbd_work, work); + struct ksmbd_conn *conn = work->conn; struct lease_break_info *br_info = work->request_buf; struct smb2_hdr *rsp_hdr; @@ -791,6 +794,7 @@ static void __smb2_lease_break_noti(struct work_struct *wk) out: ksmbd_free_work_struct(work); + ksmbd_conn_r_count_dec(conn); } /** @@ -803,7 +807,6 @@ out: static int smb2_lease_break_noti(struct oplock_info *opinfo) { struct ksmbd_conn *conn = opinfo->conn; - struct list_head *tmp, *t; struct ksmbd_work *work; struct lease_break_info *br_info; struct lease *lease = opinfo->o_lease; @@ -831,16 +834,7 @@ static int smb2_lease_break_noti(struct oplock_info *opinfo) work->sess = opinfo->sess; if (opinfo->op_state == OPLOCK_ACK_WAIT) { - list_for_each_safe(tmp, t, &opinfo->interim_list) { - struct ksmbd_work *in_work; - - in_work = list_entry(tmp, struct ksmbd_work, - interim_entry); - setup_async_work(in_work, NULL, NULL); - smb2_send_interim_resp(in_work, STATUS_PENDING); - list_del_init(&in_work->interim_entry); - release_async_work(in_work); - } + ksmbd_conn_r_count_inc(conn); INIT_WORK(&work->work, __smb2_lease_break_noti); ksmbd_queue_work(work); wait_for_break_ack(opinfo); @@ -871,7 +865,8 @@ static void wait_lease_breaking(struct oplock_info *opinfo) } } -static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level) +static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level, + struct ksmbd_work *in_work) { int err = 0; @@ -914,9 +909,15 @@ static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level) } if (lease->state & (SMB2_LEASE_WRITE_CACHING_LE | - SMB2_LEASE_HANDLE_CACHING_LE)) + SMB2_LEASE_HANDLE_CACHING_LE)) { + if (in_work) { + setup_async_work(in_work, NULL, NULL); + smb2_send_interim_resp(in_work, STATUS_PENDING); + release_async_work(in_work); + } + brk_opinfo->op_state = OPLOCK_ACK_WAIT; - else + } else atomic_dec(&brk_opinfo->breaking_cnt); } else { err = oplock_break_pending(brk_opinfo, req_op_level); @@ -1116,7 +1117,7 @@ void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, if (ksmbd_conn_releasing(opinfo->conn)) continue; - oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE); + oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE, NULL); opinfo_put(opinfo); } } @@ -1152,7 +1153,7 @@ void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp) if (ksmbd_conn_releasing(opinfo->conn)) continue; - oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE); + oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE, NULL); opinfo_put(opinfo); } } @@ -1252,8 +1253,7 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, goto op_break_not_needed; } - list_add(&work->interim_entry, &prev_opinfo->interim_list); - err = oplock_break(prev_opinfo, SMB2_OPLOCK_LEVEL_II); + err = oplock_break(prev_opinfo, SMB2_OPLOCK_LEVEL_II, work); opinfo_put(prev_opinfo); if (err == -ENOENT) goto set_lev; @@ -1322,8 +1322,7 @@ static void smb_break_all_write_oplock(struct ksmbd_work *work, } brk_opinfo->open_trunc = is_trunc; - list_add(&work->interim_entry, &brk_opinfo->interim_list); - oplock_break(brk_opinfo, SMB2_OPLOCK_LEVEL_II); + oplock_break(brk_opinfo, SMB2_OPLOCK_LEVEL_II, work); opinfo_put(brk_opinfo); } @@ -1386,7 +1385,7 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp, SMB2_LEASE_KEY_SIZE)) goto next; brk_op->open_trunc = is_trunc; - oplock_break(brk_op, SMB2_OPLOCK_LEVEL_NONE); + oplock_break(brk_op, SMB2_OPLOCK_LEVEL_NONE, NULL); next: opinfo_put(brk_op); rcu_read_lock(); diff --git a/fs/smb/server/oplock.h b/fs/smb/server/oplock.h index 72bc88a63a40..3f64f0787263 100644 --- a/fs/smb/server/oplock.h +++ b/fs/smb/server/oplock.h @@ -67,7 +67,6 @@ struct oplock_info { bool is_lease; bool open_trunc; /* truncate on open */ struct lease *o_lease; - struct list_head interim_list; struct list_head op_entry; struct list_head lease_entry; wait_queue_head_t oplock_q; /* Other server threads */ diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index 601e7fcbcf1e..ab533c602987 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -270,17 +270,7 @@ static void handle_ksmbd_work(struct work_struct *wk) ksmbd_conn_try_dequeue_request(work); ksmbd_free_work_struct(work); - /* - * Checking waitqueue to dropping pending requests on - * disconnection. waitqueue_active is safe because it - * uses atomic operation for condition. - */ - atomic_inc(&conn->refcnt); - if (!atomic_dec_return(&conn->r_count) && waitqueue_active(&conn->r_count_q)) - wake_up(&conn->r_count_q); - - if (atomic_dec_and_test(&conn->refcnt)) - kfree(conn); + ksmbd_conn_r_count_dec(conn); } /** @@ -310,7 +300,7 @@ static int queue_ksmbd_work(struct ksmbd_conn *conn) conn->request_buf = NULL; ksmbd_conn_enqueue_request(work); - atomic_inc(&conn->r_count); + ksmbd_conn_r_count_inc(conn); /* update activity on connection */ conn->last_active = jiffies; INIT_WORK(&work->work, handle_ksmbd_work); diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index f1efcd027475..c53121538990 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -7458,17 +7458,17 @@ out_check_cl: } no_check_cl: + flock = smb_lock->fl; + list_del(&smb_lock->llist); + if (smb_lock->zero_len) { err = 0; goto skip; } - - flock = smb_lock->fl; - list_del(&smb_lock->llist); retry: rc = vfs_lock_file(filp, smb_lock->cmd, flock, NULL); skip: - if (flags & SMB2_LOCKFLAG_UNLOCK) { + if (smb_lock->flags & SMB2_LOCKFLAG_UNLOCK) { if (!rc) { ksmbd_debug(SMB, "File unlocked\n"); } else if (rc == -ENOENT) { diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c index d39d3e553366..49b128698670 100644 --- a/fs/smb/server/smbacl.c +++ b/fs/smb/server/smbacl.c @@ -333,7 +333,7 @@ void posix_state_to_acl(struct posix_acl_state *state, pace->e_perm = state->other.allow; } -int init_acl_state(struct posix_acl_state *state, int cnt) +int init_acl_state(struct posix_acl_state *state, u16 cnt) { int alloc; @@ -368,7 +368,7 @@ static void parse_dacl(struct mnt_idmap *idmap, struct smb_fattr *fattr) { int i, ret; - int num_aces = 0; + u16 num_aces = 0; unsigned int acl_size; char *acl_base; struct smb_ace **ppace; @@ -389,16 +389,18 @@ static void parse_dacl(struct mnt_idmap *idmap, ksmbd_debug(SMB, "DACL revision %d size %d num aces %d\n", le16_to_cpu(pdacl->revision), le16_to_cpu(pdacl->size), - le32_to_cpu(pdacl->num_aces)); + le16_to_cpu(pdacl->num_aces)); acl_base = (char *)pdacl; acl_size = sizeof(struct smb_acl); - num_aces = le32_to_cpu(pdacl->num_aces); + num_aces = le16_to_cpu(pdacl->num_aces); if (num_aces <= 0) return; - if (num_aces > ULONG_MAX / sizeof(struct smb_ace *)) + if (num_aces > (le16_to_cpu(pdacl->size) - sizeof(struct smb_acl)) / + (offsetof(struct smb_ace, sid) + + offsetof(struct smb_sid, sub_auth) + sizeof(__le16))) return; ret = init_acl_state(&acl_state, num_aces); @@ -432,6 +434,7 @@ static void parse_dacl(struct mnt_idmap *idmap, offsetof(struct smb_sid, sub_auth); if (end_of_acl - acl_base < acl_size || + ppace[i]->sid.num_subauth == 0 || ppace[i]->sid.num_subauth > SID_MAX_SUB_AUTHORITIES || (end_of_acl - acl_base < acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth) || @@ -580,7 +583,7 @@ static void parse_dacl(struct mnt_idmap *idmap, static void set_posix_acl_entries_dacl(struct mnt_idmap *idmap, struct smb_ace *pndace, - struct smb_fattr *fattr, u32 *num_aces, + struct smb_fattr *fattr, u16 *num_aces, u16 *size, u32 nt_aces_num) { struct posix_acl_entry *pace; @@ -701,7 +704,7 @@ static void set_ntacl_dacl(struct mnt_idmap *idmap, struct smb_fattr *fattr) { struct smb_ace *ntace, *pndace; - int nt_num_aces = le32_to_cpu(nt_dacl->num_aces), num_aces = 0; + u16 nt_num_aces = le16_to_cpu(nt_dacl->num_aces), num_aces = 0; unsigned short size = 0; int i; @@ -728,7 +731,7 @@ static void set_ntacl_dacl(struct mnt_idmap *idmap, set_posix_acl_entries_dacl(idmap, pndace, fattr, &num_aces, &size, nt_num_aces); - pndacl->num_aces = cpu_to_le32(num_aces); + pndacl->num_aces = cpu_to_le16(num_aces); pndacl->size = cpu_to_le16(le16_to_cpu(pndacl->size) + size); } @@ -736,7 +739,7 @@ static void set_mode_dacl(struct mnt_idmap *idmap, struct smb_acl *pndacl, struct smb_fattr *fattr) { struct smb_ace *pace, *pndace; - u32 num_aces = 0; + u16 num_aces = 0; u16 size = 0, ace_size = 0; uid_t uid; const struct smb_sid *sid; @@ -792,7 +795,7 @@ static void set_mode_dacl(struct mnt_idmap *idmap, fattr->cf_mode, 0007); out: - pndacl->num_aces = cpu_to_le32(num_aces); + pndacl->num_aces = cpu_to_le16(num_aces); pndacl->size = cpu_to_le16(le16_to_cpu(pndacl->size) + size); } @@ -807,6 +810,13 @@ static int parse_sid(struct smb_sid *psid, char *end_of_acl) return -EINVAL; } + if (!psid->num_subauth) + return 0; + + if (psid->num_subauth > SID_MAX_SUB_AUTHORITIES || + end_of_acl < (char *)psid + 8 + sizeof(__le32) * psid->num_subauth) + return -EINVAL; + return 0; } @@ -848,6 +858,9 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd, pntsd->type = cpu_to_le16(DACL_PRESENT); if (pntsd->osidoffset) { + if (le32_to_cpu(pntsd->osidoffset) < sizeof(struct smb_ntsd)) + return -EINVAL; + rc = parse_sid(owner_sid_ptr, end_of_acl); if (rc) { pr_err("%s: Error %d parsing Owner SID\n", __func__, rc); @@ -863,6 +876,9 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd, } if (pntsd->gsidoffset) { + if (le32_to_cpu(pntsd->gsidoffset) < sizeof(struct smb_ntsd)) + return -EINVAL; + rc = parse_sid(group_sid_ptr, end_of_acl); if (rc) { pr_err("%s: Error %d mapping Owner SID to gid\n", @@ -884,6 +900,9 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd, pntsd->type |= cpu_to_le16(DACL_PROTECTED); if (dacloffset) { + if (dacloffset < sizeof(struct smb_ntsd)) + return -EINVAL; + parse_dacl(idmap, dacl_ptr, end_of_acl, owner_sid_ptr, group_sid_ptr, fattr); } @@ -1006,8 +1025,9 @@ int smb_inherit_dacl(struct ksmbd_conn *conn, struct smb_sid owner_sid, group_sid; struct dentry *parent = path->dentry->d_parent; struct mnt_idmap *idmap = mnt_idmap(path->mnt); - int inherited_flags = 0, flags = 0, i, ace_cnt = 0, nt_size = 0, pdacl_size; - int rc = 0, num_aces, dacloffset, pntsd_type, pntsd_size, acl_len, aces_size; + int inherited_flags = 0, flags = 0, i, nt_size = 0, pdacl_size; + int rc = 0, dacloffset, pntsd_type, pntsd_size, acl_len, aces_size; + u16 num_aces, ace_cnt = 0; char *aces_base; bool is_dir = S_ISDIR(d_inode(path->dentry)->i_mode); @@ -1023,7 +1043,7 @@ int smb_inherit_dacl(struct ksmbd_conn *conn, parent_pdacl = (struct smb_acl *)((char *)parent_pntsd + dacloffset); acl_len = pntsd_size - dacloffset; - num_aces = le32_to_cpu(parent_pdacl->num_aces); + num_aces = le16_to_cpu(parent_pdacl->num_aces); pntsd_type = le16_to_cpu(parent_pntsd->type); pdacl_size = le16_to_cpu(parent_pdacl->size); @@ -1183,7 +1203,7 @@ pass: pdacl = (struct smb_acl *)((char *)pntsd + le32_to_cpu(pntsd->dacloffset)); pdacl->revision = cpu_to_le16(2); pdacl->size = cpu_to_le16(sizeof(struct smb_acl) + nt_size); - pdacl->num_aces = cpu_to_le32(ace_cnt); + pdacl->num_aces = cpu_to_le16(ace_cnt); pace = (struct smb_ace *)((char *)pdacl + sizeof(struct smb_acl)); memcpy(pace, aces_base, nt_size); pntsd_size += sizeof(struct smb_acl) + nt_size; @@ -1264,7 +1284,7 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, const struct path *path, ace = (struct smb_ace *)((char *)pdacl + sizeof(struct smb_acl)); aces_size = acl_size - sizeof(struct smb_acl); - for (i = 0; i < le32_to_cpu(pdacl->num_aces); i++) { + for (i = 0; i < le16_to_cpu(pdacl->num_aces); i++) { if (offsetof(struct smb_ace, access_req) > aces_size) break; ace_size = le16_to_cpu(ace->size); @@ -1285,7 +1305,7 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, const struct path *path, ace = (struct smb_ace *)((char *)pdacl + sizeof(struct smb_acl)); aces_size = acl_size - sizeof(struct smb_acl); - for (i = 0; i < le32_to_cpu(pdacl->num_aces); i++) { + for (i = 0; i < le16_to_cpu(pdacl->num_aces); i++) { if (offsetof(struct smb_ace, access_req) > aces_size) break; ace_size = le16_to_cpu(ace->size); diff --git a/fs/smb/server/smbacl.h b/fs/smb/server/smbacl.h index 24ce576fc292..355adaee39b8 100644 --- a/fs/smb/server/smbacl.h +++ b/fs/smb/server/smbacl.h @@ -86,7 +86,7 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd, int build_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd, struct smb_ntsd *ppntsd, int ppntsd_size, int addition_info, __u32 *secdesclen, struct smb_fattr *fattr); -int init_acl_state(struct posix_acl_state *state, int cnt); +int init_acl_state(struct posix_acl_state *state, u16 cnt); void free_acl_state(struct posix_acl_state *state); void posix_state_to_acl(struct posix_acl_state *state, struct posix_acl_entry *pace); diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index 0460ebea6ff0..3f185ae60dc5 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -281,6 +281,7 @@ static int handle_response(int type, void *payload, size_t sz) if (entry->type + 1 != type) { pr_err("Waiting for IPC type %d, got %d. Ignore.\n", entry->type + 1, type); + continue; } entry->response = kvzalloc(sz, KSMBD_DEFAULT_GFP); diff --git a/fs/splice.c b/fs/splice.c index 28cfa63aa236..23fa5561b944 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -331,7 +331,7 @@ ssize_t copy_splice_read(struct file *in, loff_t *ppos, int i; /* Work out how much data we can actually add into the pipe */ - used = pipe_occupancy(pipe->head, pipe->tail); + used = pipe_buf_usage(pipe); npages = max_t(ssize_t, pipe->max_usage - used, 0); len = min_t(size_t, len, npages * PAGE_SIZE); npages = DIV_ROUND_UP(len, PAGE_SIZE); @@ -527,7 +527,7 @@ static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_des return -ERESTARTSYS; repeat: - while (pipe_empty(pipe->head, pipe->tail)) { + while (pipe_is_empty(pipe)) { if (!pipe->writers) return 0; @@ -820,7 +820,7 @@ ssize_t splice_to_socket(struct pipe_inode_info *pipe, struct file *out, if (signal_pending(current)) break; - while (pipe_empty(pipe->head, pipe->tail)) { + while (pipe_is_empty(pipe)) { ret = 0; if (!pipe->writers) goto out; @@ -968,7 +968,7 @@ static ssize_t do_splice_read(struct file *in, loff_t *ppos, return 0; /* Don't try to read more the pipe has space for. */ - p_space = pipe->max_usage - pipe_occupancy(pipe->head, pipe->tail); + p_space = pipe->max_usage - pipe_buf_usage(pipe); len = min_t(size_t, len, p_space << PAGE_SHIFT); if (unlikely(len > MAX_RW_COUNT)) @@ -1080,7 +1080,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, more = sd->flags & SPLICE_F_MORE; sd->flags |= SPLICE_F_MORE; - WARN_ON_ONCE(!pipe_empty(pipe->head, pipe->tail)); + WARN_ON_ONCE(!pipe_is_empty(pipe)); while (len) { size_t read_len; @@ -1268,7 +1268,7 @@ static int wait_for_space(struct pipe_inode_info *pipe, unsigned flags) send_sig(SIGPIPE, current, 0); return -EPIPE; } - if (!pipe_full(pipe->head, pipe->tail, pipe->max_usage)) + if (!pipe_is_full(pipe)) return 0; if (flags & SPLICE_F_NONBLOCK) return -EAGAIN; @@ -1652,13 +1652,13 @@ static int ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags) * Check the pipe occupancy without the inode lock first. This function * is speculative anyways, so missing one is ok. */ - if (!pipe_empty(pipe->head, pipe->tail)) + if (!pipe_is_empty(pipe)) return 0; ret = 0; pipe_lock(pipe); - while (pipe_empty(pipe->head, pipe->tail)) { + while (pipe_is_empty(pipe)) { if (signal_pending(current)) { ret = -ERESTARTSYS; break; @@ -1688,13 +1688,13 @@ static int opipe_prep(struct pipe_inode_info *pipe, unsigned int flags) * Check pipe occupancy without the inode lock first. This function * is speculative anyways, so missing one is ok. */ - if (!pipe_full(pipe->head, pipe->tail, pipe->max_usage)) + if (!pipe_is_full(pipe)) return 0; ret = 0; pipe_lock(pipe); - while (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) { + while (pipe_is_full(pipe)) { if (!pipe->readers) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c index 1d94bb784108..0bc96ab6580b 100644 --- a/fs/vboxsf/super.c +++ b/fs/vboxsf/super.c @@ -21,8 +21,7 @@ #define VBOXSF_SUPER_MAGIC 0x786f4256 /* 'VBox' little endian */ -static const unsigned char VBSF_MOUNT_SIGNATURE[4] = { '\000', '\377', '\376', - '\375' }; +static const unsigned char VBSF_MOUNT_SIGNATURE[4] __nonstring = "\000\377\376\375"; static int follow_symlinks; module_param(follow_symlinks, int, 0444); diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 3d33e17f2e5c..7839efe050bf 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -33,8 +33,6 @@ struct kmem_cache *xfs_extfree_item_cache; struct workqueue_struct *xfs_alloc_wq; -#define XFS_ABSDIFF(a,b) (((a) <= (b)) ? ((b) - (a)) : ((a) - (b))) - #define XFSA_FIXUP_BNO_OK 1 #define XFSA_FIXUP_CNT_OK 2 @@ -410,8 +408,8 @@ xfs_alloc_compute_diff( if (newbno1 != NULLAGBLOCK && newbno2 != NULLAGBLOCK) { if (newlen1 < newlen2 || (newlen1 == newlen2 && - XFS_ABSDIFF(newbno1, wantbno) > - XFS_ABSDIFF(newbno2, wantbno))) + abs_diff(newbno1, wantbno) > + abs_diff(newbno2, wantbno))) newbno1 = newbno2; } else if (newbno2 != NULLAGBLOCK) newbno1 = newbno2; @@ -427,7 +425,7 @@ xfs_alloc_compute_diff( } else newbno1 = freeend - wantlen; *newbnop = newbno1; - return newbno1 == NULLAGBLOCK ? 0 : XFS_ABSDIFF(newbno1, wantbno); + return newbno1 == NULLAGBLOCK ? 0 : abs_diff(newbno1, wantbno); } /* diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index bdcd40f0ec74..19877d99f255 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -224,7 +224,6 @@ static inline bool xchk_skip_xref(struct xfs_scrub_metadata *sm) bool xchk_dir_looks_zapped(struct xfs_inode *dp); bool xchk_pptr_looks_zapped(struct xfs_inode *ip); -#ifdef CONFIG_XFS_ONLINE_REPAIR /* Decide if a repair is required. */ static inline bool xchk_needs_repair(const struct xfs_scrub_metadata *sm) { @@ -244,10 +243,6 @@ static inline bool xchk_could_repair(const struct xfs_scrub *sc) return (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) && !(sc->flags & XREP_ALREADY_FIXED); } -#else -# define xchk_needs_repair(sc) (false) -# define xchk_could_repair(sc) (false) -#endif /* CONFIG_XFS_ONLINE_REPAIR */ int xchk_metadata_inode_forks(struct xfs_scrub *sc); diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c index 2f641b6d663e..13ff1c933cb8 100644 --- a/fs/xfs/scrub/inode_repair.c +++ b/fs/xfs/scrub/inode_repair.c @@ -1055,9 +1055,17 @@ xrep_dinode_check_dfork( return true; break; case S_IFREG: - if (fmt == XFS_DINODE_FMT_LOCAL) + switch (fmt) { + case XFS_DINODE_FMT_LOCAL: return true; - fallthrough; + case XFS_DINODE_FMT_EXTENTS: + case XFS_DINODE_FMT_BTREE: + case XFS_DINODE_FMT_META_BTREE: + break; + default: + return true; + } + break; case S_IFLNK: case S_IFDIR: switch (fmt) { diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h index 823c00d1a502..af0a3a9e5ed9 100644 --- a/fs/xfs/scrub/repair.h +++ b/fs/xfs/scrub/repair.h @@ -191,7 +191,16 @@ int xrep_reset_metafile_resv(struct xfs_scrub *sc); #else #define xrep_ino_dqattach(sc) (0) -#define xrep_will_attempt(sc) (false) + +/* + * When online repair is not built into the kernel, we still want to attempt + * the repair so that the stub xrep_attempt below will return EOPNOTSUPP. + */ +static inline bool xrep_will_attempt(const struct xfs_scrub *sc) +{ + return (sc->sm->sm_flags & XFS_SCRUB_IFLAG_FORCE_REBUILD) || + xchk_needs_repair(sc->sm); +} static inline int xrep_attempt( diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 7567dd5cad14..6fa9e3e5bab7 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -149,6 +149,18 @@ xchk_probe( if (xchk_should_terminate(sc, &error)) return error; + /* + * If the caller is probing to see if repair works but repair isn't + * built into the kernel, return EOPNOTSUPP because that's the signal + * that userspace expects. If online repair is built in, set the + * CORRUPT flag (without any of the usual tracing/logging) to force us + * into xrep_probe. + */ + if (xchk_could_repair(sc)) { + if (!IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR)) + return -EOPNOTSUPP; + sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT; + } return 0; } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 67877c36ed11..6d9965b546cb 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -19,6 +19,7 @@ #include "xfs_reflink.h" #include "xfs_errortag.h" #include "xfs_error.h" +#include "xfs_icache.h" struct xfs_writepage_ctx { struct iomap_writepage_ctx ctx; @@ -528,12 +529,44 @@ xfs_vm_readahead( } static int -xfs_iomap_swapfile_activate( +xfs_vm_swap_activate( struct swap_info_struct *sis, struct file *swap_file, sector_t *span) { - sis->bdev = xfs_inode_buftarg(XFS_I(file_inode(swap_file)))->bt_bdev; + struct xfs_inode *ip = XFS_I(file_inode(swap_file)); + + /* + * Swap file activation can race against concurrent shared extent + * removal in files that have been cloned. If this happens, + * iomap_swapfile_iter() can fail because it encountered a shared + * extent even though an operation is in progress to remove those + * shared extents. + * + * This race becomes problematic when we defer extent removal + * operations beyond the end of a syscall (i.e. use async background + * processing algorithms). Users think the extents are no longer + * shared, but iomap_swapfile_iter() still sees them as shared + * because the refcountbt entries for the extents being removed have + * not yet been updated. Hence the swapon call fails unexpectedly. + * + * The race condition is currently most obvious from the unlink() + * operation as extent removal is deferred until after the last + * reference to the inode goes away. We then process the extent + * removal asynchronously, hence triggers the "syscall completed but + * work not done" condition mentioned above. To close this race + * window, we need to flush any pending inodegc operations to ensure + * they have updated the refcountbt records before we try to map the + * swapfile. + */ + xfs_inodegc_flush(ip->i_mount); + + /* + * Direct the swap code to the correct block device when this file + * sits on the RT device. + */ + sis->bdev = xfs_inode_buftarg(ip)->bt_bdev; + return iomap_swapfile_activate(sis, swap_file, span, &xfs_read_iomap_ops); } @@ -549,11 +582,11 @@ const struct address_space_operations xfs_address_space_operations = { .migrate_folio = filemap_migrate_folio, .is_partially_uptodate = iomap_is_partially_uptodate, .error_remove_folio = generic_error_remove_folio, - .swap_activate = xfs_iomap_swapfile_activate, + .swap_activate = xfs_vm_swap_activate, }; const struct address_space_operations xfs_dax_aops = { .writepages = xfs_dax_writepages, .dirty_folio = noop_dirty_folio, - .swap_activate = xfs_iomap_swapfile_activate, + .swap_activate = xfs_vm_swap_activate, }; diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 15bb790359f8..5d560e9073f4 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -29,11 +29,6 @@ struct kmem_cache *xfs_buf_cache; /* * Locking orders * - * xfs_buf_ioacct_inc: - * xfs_buf_ioacct_dec: - * b_sema (caller holds) - * b_lock - * * xfs_buf_stale: * b_sema (caller holds) * b_lock @@ -82,51 +77,6 @@ xfs_buf_vmap_len( } /* - * Bump the I/O in flight count on the buftarg if we haven't yet done so for - * this buffer. The count is incremented once per buffer (per hold cycle) - * because the corresponding decrement is deferred to buffer release. Buffers - * can undergo I/O multiple times in a hold-release cycle and per buffer I/O - * tracking adds unnecessary overhead. This is used for sychronization purposes - * with unmount (see xfs_buftarg_drain()), so all we really need is a count of - * in-flight buffers. - * - * Buffers that are never released (e.g., superblock, iclog buffers) must set - * the XBF_NO_IOACCT flag before I/O submission. Otherwise, the buftarg count - * never reaches zero and unmount hangs indefinitely. - */ -static inline void -xfs_buf_ioacct_inc( - struct xfs_buf *bp) -{ - if (bp->b_flags & XBF_NO_IOACCT) - return; - - ASSERT(bp->b_flags & XBF_ASYNC); - spin_lock(&bp->b_lock); - if (!(bp->b_state & XFS_BSTATE_IN_FLIGHT)) { - bp->b_state |= XFS_BSTATE_IN_FLIGHT; - percpu_counter_inc(&bp->b_target->bt_io_count); - } - spin_unlock(&bp->b_lock); -} - -/* - * Clear the in-flight state on a buffer about to be released to the LRU or - * freed and unaccount from the buftarg. - */ -static inline void -__xfs_buf_ioacct_dec( - struct xfs_buf *bp) -{ - lockdep_assert_held(&bp->b_lock); - - if (bp->b_state & XFS_BSTATE_IN_FLIGHT) { - bp->b_state &= ~XFS_BSTATE_IN_FLIGHT; - percpu_counter_dec(&bp->b_target->bt_io_count); - } -} - -/* * When we mark a buffer stale, we remove the buffer from the LRU and clear the * b_lru_ref count so that the buffer is freed immediately when the buffer * reference count falls to zero. If the buffer is already on the LRU, we need @@ -149,15 +99,7 @@ xfs_buf_stale( */ bp->b_flags &= ~_XBF_DELWRI_Q; - /* - * Once the buffer is marked stale and unlocked, a subsequent lookup - * could reset b_flags. There is no guarantee that the buffer is - * unaccounted (released to LRU) before that occurs. Drop in-flight - * status now to preserve accounting consistency. - */ spin_lock(&bp->b_lock); - __xfs_buf_ioacct_dec(bp); - atomic_set(&bp->b_lru_ref, 0); if (!(bp->b_state & XFS_BSTATE_DISPOSE) && (list_lru_del_obj(&bp->b_target->bt_lru, &bp->b_lru))) @@ -794,18 +736,13 @@ out_put_perag: int _xfs_buf_read( - struct xfs_buf *bp, - xfs_buf_flags_t flags) + struct xfs_buf *bp) { - ASSERT(!(flags & XBF_WRITE)); ASSERT(bp->b_maps[0].bm_bn != XFS_BUF_DADDR_NULL); bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD | XBF_DONE); - bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD); - + bp->b_flags |= XBF_READ; xfs_buf_submit(bp); - if (flags & XBF_ASYNC) - return 0; return xfs_buf_iowait(bp); } @@ -857,6 +794,8 @@ xfs_buf_read_map( struct xfs_buf *bp; int error; + ASSERT(!(flags & (XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD))); + flags |= XBF_READ; *bpp = NULL; @@ -870,21 +809,11 @@ xfs_buf_read_map( /* Initiate the buffer read and wait. */ XFS_STATS_INC(target->bt_mount, xb_get_read); bp->b_ops = ops; - error = _xfs_buf_read(bp, flags); - - /* Readahead iodone already dropped the buffer, so exit. */ - if (flags & XBF_ASYNC) - return 0; + error = _xfs_buf_read(bp); } else { /* Buffer already read; all we need to do is check it. */ error = xfs_buf_reverify(bp, ops); - /* Readahead already finished; drop the buffer and exit. */ - if (flags & XBF_ASYNC) { - xfs_buf_relse(bp); - return 0; - } - /* We do not want read in the flags */ bp->b_flags &= ~XBF_READ; ASSERT(bp->b_ops != NULL || ops == NULL); @@ -936,6 +865,7 @@ xfs_buf_readahead_map( int nmaps, const struct xfs_buf_ops *ops) { + const xfs_buf_flags_t flags = XBF_READ | XBF_ASYNC | XBF_READ_AHEAD; struct xfs_buf *bp; /* @@ -945,9 +875,21 @@ xfs_buf_readahead_map( if (xfs_buftarg_is_mem(target)) return; - xfs_buf_read_map(target, map, nmaps, - XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD, &bp, ops, - __this_address); + if (xfs_buf_get_map(target, map, nmaps, flags | XBF_TRYLOCK, &bp)) + return; + trace_xfs_buf_readahead(bp, 0, _RET_IP_); + + if (bp->b_flags & XBF_DONE) { + xfs_buf_reverify(bp, ops); + xfs_buf_relse(bp); + return; + } + XFS_STATS_INC(target->bt_mount, xb_get_read); + bp->b_ops = ops; + bp->b_flags &= ~(XBF_WRITE | XBF_DONE); + bp->b_flags |= flags; + percpu_counter_inc(&target->bt_readahead_count); + xfs_buf_submit(bp); } /* @@ -1003,10 +945,12 @@ xfs_buf_get_uncached( struct xfs_buf *bp; DEFINE_SINGLE_BUF_MAP(map, XFS_BUF_DADDR_NULL, numblks); + /* there are currently no valid flags for xfs_buf_get_uncached */ + ASSERT(flags == 0); + *bpp = NULL; - /* flags might contain irrelevant bits, pass only what we care about */ - error = _xfs_buf_alloc(target, &map, 1, flags & XBF_NO_IOACCT, &bp); + error = _xfs_buf_alloc(target, &map, 1, flags, &bp); if (error) return error; @@ -1060,7 +1004,6 @@ xfs_buf_rele_uncached( spin_unlock(&bp->b_lock); return; } - __xfs_buf_ioacct_dec(bp); spin_unlock(&bp->b_lock); xfs_buf_free(bp); } @@ -1079,20 +1022,12 @@ xfs_buf_rele_cached( spin_lock(&bp->b_lock); ASSERT(bp->b_hold >= 1); if (bp->b_hold > 1) { - /* - * Drop the in-flight state if the buffer is already on the LRU - * and it holds the only reference. This is racy because we - * haven't acquired the pag lock, but the use of _XBF_IN_FLIGHT - * ensures the decrement occurs only once per-buf. - */ - if (--bp->b_hold == 1 && !list_empty(&bp->b_lru)) - __xfs_buf_ioacct_dec(bp); + bp->b_hold--; goto out_unlock; } /* we are asked to drop the last reference */ - __xfs_buf_ioacct_dec(bp); - if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) { + if (atomic_read(&bp->b_lru_ref)) { /* * If the buffer is added to the LRU, keep the reference to the * buffer for the LRU and clear the (now stale) dispose list @@ -1345,6 +1280,7 @@ xfs_buf_ioend_handle_error( resubmit: xfs_buf_ioerror(bp, 0); bp->b_flags |= (XBF_DONE | XBF_WRITE_FAIL); + reinit_completion(&bp->b_iowait); xfs_buf_submit(bp); return true; out_stale: @@ -1355,8 +1291,9 @@ out_stale: return false; } -static void -xfs_buf_ioend( +/* returns false if the caller needs to resubmit the I/O, else true */ +static bool +__xfs_buf_ioend( struct xfs_buf *bp) { trace_xfs_buf_iodone(bp, _RET_IP_); @@ -1369,6 +1306,8 @@ xfs_buf_ioend( bp->b_ops->verify_read(bp); if (!bp->b_error) bp->b_flags |= XBF_DONE; + if (bp->b_flags & XBF_READ_AHEAD) + percpu_counter_dec(&bp->b_target->bt_readahead_count); } else { if (!bp->b_error) { bp->b_flags &= ~XBF_WRITE_FAIL; @@ -1376,7 +1315,7 @@ xfs_buf_ioend( } if (unlikely(bp->b_error) && xfs_buf_ioend_handle_error(bp)) - return; + return false; /* clear the retry state */ bp->b_last_error = 0; @@ -1397,7 +1336,15 @@ xfs_buf_ioend( bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD | _XBF_LOGRECOVERY); + return true; +} +static void +xfs_buf_ioend( + struct xfs_buf *bp) +{ + if (!__xfs_buf_ioend(bp)) + return; if (bp->b_flags & XBF_ASYNC) xfs_buf_relse(bp); else @@ -1411,15 +1358,8 @@ xfs_buf_ioend_work( struct xfs_buf *bp = container_of(work, struct xfs_buf, b_ioend_work); - xfs_buf_ioend(bp); -} - -static void -xfs_buf_ioend_async( - struct xfs_buf *bp) -{ - INIT_WORK(&bp->b_ioend_work, xfs_buf_ioend_work); - queue_work(bp->b_mount->m_buf_workqueue, &bp->b_ioend_work); + if (__xfs_buf_ioend(bp)) + xfs_buf_relse(bp); } void @@ -1491,7 +1431,13 @@ xfs_buf_bio_end_io( XFS_TEST_ERROR(false, bp->b_mount, XFS_ERRTAG_BUF_IOERROR)) xfs_buf_ioerror(bp, -EIO); - xfs_buf_ioend_async(bp); + if (bp->b_flags & XBF_ASYNC) { + INIT_WORK(&bp->b_ioend_work, xfs_buf_ioend_work); + queue_work(bp->b_mount->m_buf_workqueue, &bp->b_ioend_work); + } else { + complete(&bp->b_iowait); + } + bio_put(bio); } @@ -1568,9 +1514,11 @@ xfs_buf_iowait( { ASSERT(!(bp->b_flags & XBF_ASYNC)); - trace_xfs_buf_iowait(bp, _RET_IP_); - wait_for_completion(&bp->b_iowait); - trace_xfs_buf_iowait_done(bp, _RET_IP_); + do { + trace_xfs_buf_iowait(bp, _RET_IP_); + wait_for_completion(&bp->b_iowait); + trace_xfs_buf_iowait_done(bp, _RET_IP_); + } while (!__xfs_buf_ioend(bp)); return bp->b_error; } @@ -1648,9 +1596,6 @@ xfs_buf_submit( */ bp->b_error = 0; - if (bp->b_flags & XBF_ASYNC) - xfs_buf_ioacct_inc(bp); - if ((bp->b_flags & XBF_WRITE) && !xfs_buf_verify_write(bp)) { xfs_force_shutdown(bp->b_mount, SHUTDOWN_CORRUPT_INCORE); xfs_buf_ioend(bp); @@ -1776,9 +1721,8 @@ xfs_buftarg_wait( struct xfs_buftarg *btp) { /* - * First wait on the buftarg I/O count for all in-flight buffers to be - * released. This is critical as new buffers do not make the LRU until - * they are released. + * First wait for all in-flight readahead buffers to be released. This is + * critical as new buffers do not make the LRU until they are released. * * Next, flush the buffer workqueue to ensure all completion processing * has finished. Just waiting on buffer locks is not sufficient for @@ -1787,7 +1731,7 @@ xfs_buftarg_wait( * all reference counts have been dropped before we start walking the * LRU list. */ - while (percpu_counter_sum(&btp->bt_io_count)) + while (percpu_counter_sum(&btp->bt_readahead_count)) delay(100); flush_workqueue(btp->bt_mount->m_buf_workqueue); } @@ -1904,8 +1848,8 @@ xfs_destroy_buftarg( struct xfs_buftarg *btp) { shrinker_free(btp->bt_shrinker); - ASSERT(percpu_counter_sum(&btp->bt_io_count) == 0); - percpu_counter_destroy(&btp->bt_io_count); + ASSERT(percpu_counter_sum(&btp->bt_readahead_count) == 0); + percpu_counter_destroy(&btp->bt_readahead_count); list_lru_destroy(&btp->bt_lru); } @@ -1959,7 +1903,7 @@ xfs_init_buftarg( if (list_lru_init(&btp->bt_lru)) return -ENOMEM; - if (percpu_counter_init(&btp->bt_io_count, 0, GFP_KERNEL)) + if (percpu_counter_init(&btp->bt_readahead_count, 0, GFP_KERNEL)) goto out_destroy_lru; btp->bt_shrinker = @@ -1973,7 +1917,7 @@ xfs_init_buftarg( return 0; out_destroy_io_count: - percpu_counter_destroy(&btp->bt_io_count); + percpu_counter_destroy(&btp->bt_readahead_count); out_destroy_lru: list_lru_destroy(&btp->bt_lru); return -ENOMEM; diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 3b4ed42e11c0..80e06eecaf56 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -27,7 +27,6 @@ struct xfs_buf; #define XBF_READ (1u << 0) /* buffer intended for reading from device */ #define XBF_WRITE (1u << 1) /* buffer intended for writing to device */ #define XBF_READ_AHEAD (1u << 2) /* asynchronous read-ahead */ -#define XBF_NO_IOACCT (1u << 3) /* bypass I/O accounting (non-LRU bufs) */ #define XBF_ASYNC (1u << 4) /* initiator will not wait for completion */ #define XBF_DONE (1u << 5) /* all pages in the buffer uptodate */ #define XBF_STALE (1u << 6) /* buffer has been staled, do not find it */ @@ -58,7 +57,6 @@ typedef unsigned int xfs_buf_flags_t; { XBF_READ, "READ" }, \ { XBF_WRITE, "WRITE" }, \ { XBF_READ_AHEAD, "READ_AHEAD" }, \ - { XBF_NO_IOACCT, "NO_IOACCT" }, \ { XBF_ASYNC, "ASYNC" }, \ { XBF_DONE, "DONE" }, \ { XBF_STALE, "STALE" }, \ @@ -77,7 +75,6 @@ typedef unsigned int xfs_buf_flags_t; * Internal state flags. */ #define XFS_BSTATE_DISPOSE (1 << 0) /* buffer being discarded */ -#define XFS_BSTATE_IN_FLIGHT (1 << 1) /* I/O in flight */ struct xfs_buf_cache { struct rhashtable bc_hash; @@ -116,7 +113,7 @@ struct xfs_buftarg { struct shrinker *bt_shrinker; struct list_lru bt_lru; - struct percpu_counter bt_io_count; + struct percpu_counter bt_readahead_count; struct ratelimit_state bt_ioerror_rl; /* Atomic write unit values */ @@ -291,7 +288,7 @@ int xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks, int xfs_buf_read_uncached(struct xfs_buftarg *target, xfs_daddr_t daddr, size_t numblks, xfs_buf_flags_t flags, struct xfs_buf **bpp, const struct xfs_buf_ops *ops); -int _xfs_buf_read(struct xfs_buf *bp, xfs_buf_flags_t flags); +int _xfs_buf_read(struct xfs_buf *bp); void xfs_buf_hold(struct xfs_buf *bp); /* Releasing Buffers */ diff --git a/fs/xfs/xfs_buf_mem.c b/fs/xfs/xfs_buf_mem.c index 07bebbfb16ee..5b64a2b3b113 100644 --- a/fs/xfs/xfs_buf_mem.c +++ b/fs/xfs/xfs_buf_mem.c @@ -117,7 +117,7 @@ xmbuf_free( struct xfs_buftarg *btp) { ASSERT(xfs_buftarg_is_mem(btp)); - ASSERT(percpu_counter_sum(&btp->bt_io_count) == 0); + ASSERT(percpu_counter_sum(&btp->bt_readahead_count) == 0); trace_xmbuf_free(btp); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index f7a7d89c345e..9a435b1ff264 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1451,9 +1451,6 @@ xfs_dax_read_fault( trace_xfs_read_fault(ip, order); - ret = filemap_fsnotify_fault(vmf); - if (unlikely(ret)) - return ret; xfs_ilock(ip, XFS_MMAPLOCK_SHARED); ret = xfs_dax_fault_locked(vmf, order, false); xfs_iunlock(ip, XFS_MMAPLOCK_SHARED); @@ -1482,16 +1479,6 @@ xfs_write_fault( vm_fault_t ret; trace_xfs_write_fault(ip, order); - /* - * Usually we get here from ->page_mkwrite callback but in case of DAX - * we will get here also for ordinary write fault. Handle HSM - * notifications for that case. - */ - if (IS_DAX(inode)) { - ret = filemap_fsnotify_fault(vmf); - if (unlikely(ret)) - return ret; - } sb_start_pagefault(inode->i_sb); file_update_time(vmf->vma->vm_file); diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index b3c27dbccce8..2f76531842f8 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -3380,7 +3380,7 @@ xlog_do_recover( */ xfs_buf_lock(bp); xfs_buf_hold(bp); - error = _xfs_buf_read(bp, XBF_READ); + error = _xfs_buf_read(bp); if (error) { if (!xlog_is_shutdown(log)) { xfs_buf_ioerror_alert(bp, __this_address); diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 477c5262cf91..b69356582b86 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -181,14 +181,11 @@ xfs_readsb( /* * Allocate a (locked) buffer to hold the superblock. This will be kept - * around at all times to optimize access to the superblock. Therefore, - * set XBF_NO_IOACCT to make sure it doesn't hold the buftarg count - * elevated. + * around at all times to optimize access to the superblock. */ reread: error = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR, - BTOBB(sector_size), XBF_NO_IOACCT, &bp, - buf_ops); + BTOBB(sector_size), 0, &bp, buf_ops); if (error) { if (loud) xfs_warn(mp, "SB validate failed with error %d.", error); diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c index 37f1230e7584..245d754f382a 100644 --- a/fs/xfs/xfs_qm_bhv.c +++ b/fs/xfs/xfs_qm_bhv.c @@ -78,6 +78,28 @@ xfs_qm_statvfs( } } +STATIC int +xfs_qm_validate_state_change( + struct xfs_mount *mp, + uint uqd, + uint gqd, + uint pqd) +{ + int state; + + /* Is quota state changing? */ + state = ((uqd && !XFS_IS_UQUOTA_ON(mp)) || + (!uqd && XFS_IS_UQUOTA_ON(mp)) || + (gqd && !XFS_IS_GQUOTA_ON(mp)) || + (!gqd && XFS_IS_GQUOTA_ON(mp)) || + (pqd && !XFS_IS_PQUOTA_ON(mp)) || + (!pqd && XFS_IS_PQUOTA_ON(mp))); + + return state && + (xfs_dev_is_read_only(mp, "changing quota state") || + xfs_has_norecovery(mp)); +} + int xfs_qm_newmount( xfs_mount_t *mp, @@ -97,24 +119,25 @@ xfs_qm_newmount( } /* - * If the device itself is read-only, we can't allow - * the user to change the state of quota on the mount - - * this would generate a transaction on the ro device, - * which would lead to an I/O error and shutdown + * If the device itself is read-only and/or in norecovery + * mode, we can't allow the user to change the state of + * quota on the mount - this would generate a transaction + * on the ro device, which would lead to an I/O error and + * shutdown. */ - if (((uquotaondisk && !XFS_IS_UQUOTA_ON(mp)) || - (!uquotaondisk && XFS_IS_UQUOTA_ON(mp)) || - (gquotaondisk && !XFS_IS_GQUOTA_ON(mp)) || - (!gquotaondisk && XFS_IS_GQUOTA_ON(mp)) || - (pquotaondisk && !XFS_IS_PQUOTA_ON(mp)) || - (!pquotaondisk && XFS_IS_PQUOTA_ON(mp))) && - xfs_dev_is_read_only(mp, "changing quota state")) { - xfs_warn(mp, "please mount with%s%s%s%s.", - (!quotaondisk ? "out quota" : ""), - (uquotaondisk ? " usrquota" : ""), - (gquotaondisk ? " grpquota" : ""), - (pquotaondisk ? " prjquota" : "")); + if (xfs_qm_validate_state_change(mp, uquotaondisk, + gquotaondisk, pquotaondisk)) { + + if (xfs_has_metadir(mp)) + xfs_warn(mp, + "metadir enabled, please mount without any quota mount options"); + else + xfs_warn(mp, "please mount with%s%s%s%s.", + (!quotaondisk ? "out quota" : ""), + (uquotaondisk ? " usrquota" : ""), + (gquotaondisk ? " grpquota" : ""), + (pquotaondisk ? " prjquota" : "")); return -EPERM; } diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index d8e6d073d64d..57bef567e011 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -1407,7 +1407,7 @@ xfs_rtmount_readsb( /* m_blkbb_log is not set up yet */ error = xfs_buf_read_uncached(mp->m_rtdev_targp, XFS_RTSB_DADDR, - mp->m_sb.sb_blocksize >> BBSHIFT, XBF_NO_IOACCT, &bp, + mp->m_sb.sb_blocksize >> BBSHIFT, 0, &bp, &xfs_rtsb_buf_ops); if (error) { xfs_warn(mp, "rt sb validate failed with error %d.", error); diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index d92d7a07ea89..0055066fb1d9 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1661,8 +1661,12 @@ xfs_fs_fill_super( #endif } - /* Filesystem claims it needs repair, so refuse the mount. */ - if (xfs_has_needsrepair(mp)) { + /* + * Filesystem claims it needs repair, so refuse the mount unless + * norecovery is also specified, in which case the filesystem can + * be mounted with no risk of further damage. + */ + if (xfs_has_needsrepair(mp) && !xfs_has_norecovery(mp)) { xfs_warn(mp, "Filesystem needs repair. Please run xfs_repair."); error = -EFSCORRUPTED; goto out_free_sb; diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index b29462363b81..bfc2f1249022 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -593,6 +593,7 @@ DEFINE_EVENT(xfs_buf_flags_class, name, \ DEFINE_BUF_FLAGS_EVENT(xfs_buf_find); DEFINE_BUF_FLAGS_EVENT(xfs_buf_get); DEFINE_BUF_FLAGS_EVENT(xfs_buf_read); +DEFINE_BUF_FLAGS_EVENT(xfs_buf_readahead); TRACE_EVENT(xfs_buf_ioerror, TP_PROTO(struct xfs_buf *bp, int error, xfs_failaddr_t caller_ip), |