diff options
Diffstat (limited to 'fs')
216 files changed, 4122 insertions, 1706 deletions
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 1ac0b3dcc077..13cf87a5f90c 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -54,11 +54,37 @@ static void v9fs_begin_writeback(struct netfs_io_request *wreq) static void v9fs_issue_write(struct netfs_io_subrequest *subreq) { struct p9_fid *fid = subreq->rreq->netfs_priv; + struct inode *inode = subreq->rreq->inode; + struct netfs_inode *ictx = netfs_inode(inode); int err, len; len = p9_client_write(fid, subreq->start, &subreq->io_iter, &err); - if (len > 0) + if (len > 0) { + uoff_t end = subreq->start + len, i_size, remote, zp; + bool set = false; + + spin_lock(&inode->i_lock); + + /* We can read the sizes directly as we hold i_lock. */ + i_size = inode->i_size; + remote = ictx->_remote_i_size; + zp = ictx->_zero_point; + + if (end > i_size) { + i_size = end; + set = true; + } + if (end > remote) { + remote = end; + set = true; + } + + if (set) + netfs_write_sizes(inode, i_size, remote, zp); + spin_unlock(&inode->i_lock); + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + } netfs_write_subrequest_terminated(subreq, len ?: err); } diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c index e549e222602e..fa6b7143db98 100644 --- a/fs/9p/vfs_dentry.c +++ b/fs/9p/vfs_dentry.c @@ -113,8 +113,7 @@ void v9fs_dentry_fid_remove(struct dentry *dentry) */ static int v9fs_dentry_init(struct dentry *dentry) { - struct v9fs_dentry *v9fs_dentry = kzalloc(sizeof(*v9fs_dentry), - GFP_KERNEL); + struct v9fs_dentry *v9fs_dentry = kzalloc_obj(*v9fs_dentry); if (!v9fs_dentry) return -ENOMEM; diff --git a/fs/adfs/super.c b/fs/adfs/super.c index a4cd0a5159dd..888aa81a6b39 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -92,10 +92,7 @@ static int adfs_checkdiscrecord(struct adfs_discrecord *dr) static void adfs_put_super(struct super_block *sb) { - struct adfs_sb_info *asb = ADFS_SB(sb); - adfs_free_map(sb); - kfree_rcu(asb, rcu); } static int adfs_show_options(struct seq_file *seq, struct dentry *root) @@ -365,7 +362,7 @@ static int adfs_fill_super(struct super_block *sb, struct fs_context *fc) ret = -EINVAL; } if (ret) - goto error; + return ret; /* set up enough so that we can read an inode */ sb->s_op = &adfs_sops; @@ -406,15 +403,9 @@ static int adfs_fill_super(struct super_block *sb, struct fs_context *fc) if (!sb->s_root) { adfs_free_map(sb); adfs_error(sb, "get root inode failed\n"); - ret = -EIO; - goto error; + return -EIO; } return 0; - -error: - sb->s_fs_info = NULL; - kfree(asb); - return ret; } static int adfs_get_tree(struct fs_context *fc) @@ -465,10 +456,19 @@ static int adfs_init_fs_context(struct fs_context *fc) return 0; } +static void adfs_kill_sb(struct super_block *sb) +{ + struct adfs_sb_info *asb = ADFS_SB(sb); + + kill_block_super(sb); + + kfree_rcu(asb, rcu); +} + static struct file_system_type adfs_fs_type = { .owner = THIS_MODULE, .name = "adfs", - .kill_sb = kill_block_super, + .kill_sb = adfs_kill_sb, .fs_flags = FS_REQUIRES_DEV, .init_fs_context = adfs_init_fs_context, .parameters = adfs_param_spec, diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c index 63bf096b721a..73195d76b481 100644 --- a/fs/afs/addr_list.c +++ b/fs/afs/addr_list.c @@ -394,8 +394,11 @@ void afs_set_peer_appdata(struct afs_server *server, struct rxrpc_peer *pn = new_alist->addrs[n].peer; struct rxrpc_peer *po = old_alist->addrs[o].peer; - if (pn == po) + if (pn == po) { + n++; + o++; continue; + } if (pn < po) { rxrpc_kernel_set_peer_data(pn, data); n++; diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 81565366d937..2db534a2c7cc 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -1801,7 +1801,7 @@ static int afs_symlink(struct mnt_idmap *idmap, struct inode *dir, goto error; ret = -ENOMEM; - symlink = kmalloc_flex(struct afs_symlink, content, clen + 1, GFP_KERNEL); + symlink = kmalloc_flex(struct afs_symlink, content, clen + 1); if (!symlink) goto error; refcount_set(&symlink->ref, 1); diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c index 3ead36a07048..c31303059444 100644 --- a/fs/afs/dir_edit.c +++ b/fs/afs/dir_edit.c @@ -442,7 +442,7 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, /* Check and clear the entry. */ de = &block->dirents[slot]; if (de->u.valid != 1) - goto error_unmap; + goto error; trace_afs_edit_dir(vnode, why, afs_edit_dir_delete, b, slot, ntohl(de->u.vnode), ntohl(de->u.unique), @@ -458,7 +458,6 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, /* Clear the constituent entries. */ next = de->u.hash_next; memset(de, 0, sizeof(*de) * iter.nr_slots); - kunmap_local(block); /* Adjust the hash chain: if iter->prev_entry is 0, the hashtable head * index is previous; otherwise it's slot number of the previous entry. @@ -485,7 +484,6 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, pde = &pblock->dirents[ps]; prev_next = pde->u.hash_next; if (prev_next != htons(entry)) { - kunmap_local(pblock); pr_warn("%llx:%llx:%x: not prev in chain b=%x p=%x,%x e=%x %*s", vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique, iter.bucket, iter.prev_entry, prev_next, entry, @@ -493,7 +491,6 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, goto error; } pde->u.hash_next = next; - kunmap_local(pblock); } netfs_single_mark_inode_dirty(&vnode->netfs.inode); @@ -503,18 +500,16 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, _debug("Remove %s from %u[%u]", name->name, b, slot); out_unmap: + afs_dir_end_iter(&iter); kunmap_local(meta); _leave(""); return; already_invalidated: - kunmap_local(block); trace_afs_edit_dir(vnode, why, afs_edit_dir_delete_inval, 0, 0, 0, 0, name->name); goto out_unmap; -error_unmap: - kunmap_local(block); error: trace_afs_edit_dir(vnode, why, afs_edit_dir_delete_error, 0, 0, 0, 0, name->name); diff --git a/fs/afs/dir_search.c b/fs/afs/dir_search.c index 104411c0692f..11ebdfffcb1d 100644 --- a/fs/afs/dir_search.c +++ b/fs/afs/dir_search.c @@ -75,10 +75,7 @@ union afs_xdr_dir_block *afs_dir_find_block(struct afs_dir_iter *iter, size_t bl _enter("%zx,%d", block, slot); - if (iter->block) { - kunmap_local(iter->block); - iter->block = NULL; - } + afs_dir_end_iter(iter); if (dvnode->directory_size < blend) goto fail; @@ -173,12 +170,8 @@ int afs_dir_search_bucket(struct afs_dir_iter *iter, const struct qstr *name, ret = -ENOENT; found: - if (iter->block) { - kunmap_local(iter->block); - iter->block = NULL; - } - bad: + afs_dir_end_iter(iter); if (ret == -ESTALE) afs_invalidate_dir(iter->dvnode, afs_dir_invalid_iter_stale); _leave(" = %d", ret); diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c index a91ad1938d07..8c62334dbfe7 100644 --- a/fs/afs/fs_probe.c +++ b/fs/afs/fs_probe.c @@ -258,6 +258,7 @@ int afs_fs_probe_fileserver(struct afs_net *net, struct afs_server *server, lockdep_is_held(&server->fs_lock)); if (old) { estate->responsive_set = old->responsive_set; + old_alist = old->addresses; if (!new_alist) new_alist = old->addresses; } diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 290873bac89b..330654ed16ec 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -1133,6 +1133,14 @@ int afs_dir_search_bucket(struct afs_dir_iter *iter, const struct qstr *name, int afs_dir_search(struct afs_vnode *dvnode, const struct qstr *name, struct afs_fid *_fid, afs_dataversion_t *_dir_version); +static inline void afs_dir_end_iter(struct afs_dir_iter *iter) +{ + if (iter->block) { + kunmap_local(iter->block); + iter->block = NULL; + } +} + /* * dir_silly.c */ diff --git a/fs/afs/server.c b/fs/afs/server.c index 0fe162ea2a36..189138bd6d71 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -242,7 +242,6 @@ struct afs_server *afs_lookup_server(struct afs_cell *cell, struct key *key, out: afs_put_addrlist(alist, afs_alist_trace_put_server_create); if (candidate) { - kfree(rcu_access_pointer(server->endpoint_state)); kfree(candidate); afs_dec_servers_outstanding(cell->net); } diff --git a/fs/afs/symlink.c b/fs/afs/symlink.c index 16b4823cb7b7..6b8c122877ca 100644 --- a/fs/afs/symlink.c +++ b/fs/afs/symlink.c @@ -119,8 +119,7 @@ static ssize_t afs_do_read_symlink(struct afs_vnode *vnode) vnode->directory_size = i_size; /* Copy the symlink. */ - symlink = kmalloc_flex(struct afs_symlink, content, i_size + 1, - GFP_KERNEL); + symlink = kmalloc_flex(struct afs_symlink, content, i_size + 1); if (!symlink) return -ENOMEM; diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index c1e210cec436..6b15a3717ba7 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -323,8 +323,10 @@ static int autofs_fill_super(struct super_block *s, struct fs_context *fc) return -ENOMEM; root_inode = autofs_get_inode(s, S_IFDIR | 0755); - if (!root_inode) + if (!root_inode) { + autofs_free_ino(ino); return -ENOMEM; + } root_inode->i_uid = ctx->uid; root_inode->i_gid = ctx->gid; diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index ddfd3aa57ac8..620da85948b4 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -331,8 +331,8 @@ static int entry_attach_interpreter(struct binfmt_misc_entry *e, return -ENOSPC; /* One allocation, both strings in it, like the entry's own buffer. */ - interp = kmalloc(struct_size(interp, name, nlen + plen + 2), - GFP_KERNEL_ACCOUNT); + interp = kmalloc_flex(*interp, name, nlen + plen + 2, + GFP_KERNEL_ACCOUNT); if (!interp) { dec_ucount(ucounts, UCOUNT_BINFMT_MISC_INTERPRETERS); return -ENOMEM; @@ -858,8 +858,7 @@ static struct binfmt_misc_entry *create_entry(const char __user *buffer, if ((count < 11) || (count > MAX_REGISTER_LENGTH)) return ERR_PTR(-EINVAL); - e = kmalloc(struct_size(e, buf, count + MISC_DELIM_PAD), - GFP_KERNEL_ACCOUNT); + e = kmalloc_flex(*e, buf, count + MISC_DELIM_PAD, GFP_KERNEL_ACCOUNT); if (!e) return ERR_PTR(-ENOMEM); diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 830460a40e86..ee182369254c 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -3074,21 +3074,25 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran return ERR_PTR(ret); } - ret = btrfs_add_new_free_space(cache, chunk_offset, chunk_offset + size, NULL); - btrfs_free_excluded_extents(cache); - if (ret) { - btrfs_put_block_group(cache); - return ERR_PTR(ret); - } - /* * Ensure the corresponding space_info object is created and * assigned to our block group. We want our bg to be added to the rbtree * with its ->space_info set. + * + * On a zoned filesystem btrfs_add_new_free_space() ends up in + * __btrfs_add_free_space_zoned(), which dereferences + * block_group->space_info, so it has to be set beforehand. */ cache->space_info = space_info; ASSERT(cache->space_info); + ret = btrfs_add_new_free_space(cache, chunk_offset, chunk_offset + size, NULL); + btrfs_free_excluded_extents(cache); + if (ret) { + btrfs_put_block_group(cache); + return ERR_PTR(ret); + } + ret = btrfs_add_block_group_cache(cache); if (ret) { btrfs_remove_free_space_cache(cache); diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index dc0834f920c3..0284be0e4e82 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -494,6 +494,7 @@ static int mark_block_group_to_copy(struct btrfs_fs_info *fs_info, path->reada = READA_FORWARD; path->search_commit_root = true; path->skip_locking = true; + path->need_commit_sem = true; key.objectid = src_dev->devid; key.type = BTRFS_DEV_EXTENT_KEY; @@ -636,7 +637,7 @@ static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, ret = mark_block_group_to_copy(fs_info, src_device); if (ret) - return ret; + goto leave; down_write(&dev_replace->rwsem); dev_replace->replace_task = current; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 819727460bcf..dc7ad92876c0 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2357,6 +2357,10 @@ static int validate_sys_chunk_array(const struct btrfs_fs_info *fs_info, key.type, cur); return -EUCLEAN; } + + if (unlikely(cur + sizeof(*chunk) > sys_array_size)) + goto short_read; + chunk = (struct btrfs_chunk *)(sb->sys_chunk_array + cur); num_stripes = btrfs_stack_chunk_num_stripes(chunk); if (unlikely(cur + btrfs_chunk_item_size(num_stripes) > sys_array_size)) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 20e15dc30bfb..f978c6524aa0 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2509,8 +2509,10 @@ int btrfs_replace_file_extents(struct btrfs_inode *inode, inode_set_ctime_current(&inode->vfs_inode)); ret = btrfs_update_inode(trans, inode); - if (ret) + if (unlikely(ret)) { + btrfs_abort_transaction(trans, ret); break; + } btrfs_end_transaction(trans); btrfs_btree_balance_dirty(fs_info); diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index 1b3d82ae3de8..b7a4a6ade30f 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -1353,7 +1353,7 @@ int btrfs_rebuild_free_space_tree(struct btrfs_fs_info *fs_info) if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); - return ret; + goto out_clear; } node = rb_first_cached(&fs_info->block_group_cache_tree); @@ -1371,14 +1371,16 @@ int btrfs_rebuild_free_space_tree(struct btrfs_fs_info *fs_info) if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); - return ret; + goto out_clear; } next: if (btrfs_should_end_transaction(trans)) { btrfs_end_transaction(trans); trans = btrfs_start_transaction(free_space_root, 1); - if (IS_ERR(trans)) - return PTR_ERR(trans); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + goto out_clear; + } } node = rb_next(node); } @@ -1390,6 +1392,10 @@ next: ret = btrfs_commit_transaction(trans); clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); return ret; + +out_clear: + clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + return ret; } static int __add_block_group_free_space(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 3c10a0ef0002..558b4a3f9633 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2339,12 +2339,27 @@ static int run_delalloc_inline(struct btrfs_inode *inode, struct folio *locked_f } else if (inode->prop_compress) { compress_type = inode->prop_compress; } + /* + * We need to pass blocksize and not i_size, otherwise we can't + * create compressed inline extents for data smaller than sector + * size with lzo. + */ cb = btrfs_compress_bio(inode, 0, blocksize, compress_type, compress_level, 0); if (IS_ERR(cb)) { cb = NULL; /* Just fall back to non-compressed case. */ } else { compressed_size = cb->bbio.bio.bi_iter.bi_size; + /* + * If we did not save space, it's pointless and wasteful + * to have an inline compressed extent, so fallback to + * an uncompressed inline extent. + */ + if (compressed_size >= i_size) { + cleanup_compressed_bio(cb); + cb = NULL; + compressed_size = 0; + } } } if (!can_cow_file_range_inline(inode, 0, i_size, compressed_size)) { @@ -3436,6 +3451,9 @@ out: */ btrfs_remove_ordered_extent(ordered_extent); + /* Cleanup any remaining biocs attached to the OE. */ + btrfs_cleanup_ordered_bioc_list(ordered_extent); + /* once for us */ btrfs_put_ordered_extent(ordered_extent); /* once for the tree */ @@ -3874,7 +3892,8 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) if (ret) goto out; } - trans = btrfs_start_transaction(root, 1); + /* Only deletes the orphan. */ + trans = btrfs_start_transaction_fallback_global_rsv(root, 1); if (IS_ERR(trans)) { ret = PTR_ERR(trans); goto out; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 72bc9d4f7708..e4b2da31a0d5 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -384,6 +384,7 @@ int btrfs_fileattr_set(struct mnt_idmap *idmap, inode_flags &= ~BTRFS_INODE_COMPRESS; inode_flags |= BTRFS_INODE_NOCOMPRESS; } else if (fsflags & FS_COMPR_FL) { + enum btrfs_compression_type comp_type; if (IS_SWAPFILE(&inode->vfs_inode)) return -ETXTBSY; @@ -391,9 +392,23 @@ int btrfs_fileattr_set(struct mnt_idmap *idmap, inode_flags |= BTRFS_INODE_COMPRESS; inode_flags &= ~BTRFS_INODE_NOCOMPRESS; - comp = btrfs_compress_type2str(fs_info->compress_type); - if (!comp || comp[0] == 0) - comp = btrfs_compress_type2str(BTRFS_COMPRESS_ZLIB); + /* + * Keep the algorithm recorded in the compression property, + * otherwise changing an unrelated attribute would reset it to + * the mount default, since FS_IOC_SETFLAGS callers write back + * the whole flag set they got from FS_IOC_GETFLAGS and that + * includes FS_COMPR_FL for any inode carrying the property. + * + * Inodes with the compress flag set but no property keep using + * the mount default, so they behave as before. + */ + if (inode->prop_compress) + comp_type = inode->prop_compress; + else if (fs_info->compress_type) + comp_type = fs_info->compress_type; + else + comp_type = BTRFS_COMPRESS_ZLIB; + comp = btrfs_compress_type2str(comp_type); } else { inode_flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS); } diff --git a/fs/btrfs/raid-stripe-tree.c b/fs/btrfs/raid-stripe-tree.c index b210371ce91e..d9e660447205 100644 --- a/fs/btrfs/raid-stripe-tree.c +++ b/fs/btrfs/raid-stripe-tree.c @@ -310,8 +310,10 @@ static int update_raid_extent_item(struct btrfs_trans_handle *trans, ret = btrfs_search_slot(trans, trans->fs_info->stripe_root, key, path, 0, 1); - if (ret) - return (ret == 1 ? ret : -EINVAL); + if (ret > 0) + ret = -ENOENT; + if (ret < 0) + return ret; leaf = path->nodes[0]; slot = path->slots[0]; @@ -337,7 +339,6 @@ int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans, stripe_extent = kzalloc(item_size, GFP_NOFS); if (unlikely(!stripe_extent)) { btrfs_abort_transaction(trans, -ENOMEM); - btrfs_end_transaction(trans); return -ENOMEM; } @@ -374,7 +375,7 @@ int btrfs_insert_raid_extent(struct btrfs_trans_handle *trans, struct btrfs_ordered_extent *ordered_extent) { struct btrfs_io_context *bioc; - int ret; + int ret = 0; if (!btrfs_fs_incompat(trans->fs_info, RAID_STRIPE_TREE)) return 0; @@ -382,17 +383,23 @@ int btrfs_insert_raid_extent(struct btrfs_trans_handle *trans, list_for_each_entry(bioc, &ordered_extent->bioc_list, rst_ordered_entry) { ret = btrfs_insert_one_raid_extent(trans, bioc); if (ret) - return ret; + break; } - while (!list_empty(&ordered_extent->bioc_list)) { - bioc = list_first_entry(&ordered_extent->bioc_list, + btrfs_cleanup_ordered_bioc_list(ordered_extent); + return ret; +} + +void btrfs_cleanup_ordered_bioc_list(struct btrfs_ordered_extent *ordered) +{ + while (!list_empty(&ordered->bioc_list)) { + struct btrfs_io_context *bioc; + + bioc = list_first_entry(&ordered->bioc_list, typeof(*bioc), rst_ordered_entry); list_del(&bioc->rst_ordered_entry); btrfs_put_bioc(bioc); } - - return 0; } int btrfs_get_raid_extent_offset(struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/raid-stripe-tree.h b/fs/btrfs/raid-stripe-tree.h index 69942ad43140..eb02cf48511b 100644 --- a/fs/btrfs/raid-stripe-tree.h +++ b/fs/btrfs/raid-stripe-tree.h @@ -28,6 +28,7 @@ int btrfs_get_raid_extent_offset(struct btrfs_fs_info *fs_info, u32 stripe_index, struct btrfs_io_stripe *stripe); int btrfs_insert_raid_extent(struct btrfs_trans_handle *trans, struct btrfs_ordered_extent *ordered_extent); +void btrfs_cleanup_ordered_bioc_list(struct btrfs_ordered_extent *ordered); #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index f209e75f0ff5..c09d4213ad89 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1023,6 +1023,10 @@ static void scrub_stripe_report_errors(struct scrub_ctx *sctx, skip: for_each_set_bit(sector_nr, &extent_bitmap, stripe->nr_sectors) { + const u64 sector_logical = stripe->logical + + ((u64)sector_nr << fs_info->sectorsize_bits); + const u64 sector_physical = physical + + ((u64)sector_nr << fs_info->sectorsize_bits); bool repaired = false; if (scrub_bitmap_test_bit_is_metadata(stripe, sector_nr)) { @@ -1051,12 +1055,12 @@ skip: if (dev) { btrfs_err_rl(fs_info, "scrub: fixed up error at logical %llu on dev %s physical %llu", - stripe->logical, btrfs_dev_name(dev), - physical); + sector_logical, btrfs_dev_name(dev), + sector_physical); } else { btrfs_err_rl(fs_info, "scrub: fixed up error at logical %llu on mirror %u", - stripe->logical, stripe->mirror_num); + sector_logical, stripe->mirror_num); } continue; } @@ -1065,30 +1069,30 @@ skip: if (dev) { btrfs_err_rl(fs_info, "scrub: unable to fixup (regular) error at logical %llu on dev %s physical %llu", - stripe->logical, btrfs_dev_name(dev), - physical); + sector_logical, btrfs_dev_name(dev), + sector_physical); } else { btrfs_err_rl(fs_info, "scrub: unable to fixup (regular) error at logical %llu on mirror %u", - stripe->logical, stripe->mirror_num); + sector_logical, stripe->mirror_num); } if (scrub_bitmap_test_bit_io_error(stripe, sector_nr)) if (__ratelimit(&rs) && dev) scrub_print_common_warning("i/o error", dev, false, - stripe->logical, physical); + sector_logical, sector_physical); if (scrub_bitmap_test_bit_csum_error(stripe, sector_nr)) if (__ratelimit(&rs) && dev) scrub_print_common_warning("checksum error", dev, false, - stripe->logical, physical); + sector_logical, sector_physical); if (scrub_bitmap_test_bit_meta_error(stripe, sector_nr)) if (__ratelimit(&rs) && dev) scrub_print_common_warning("header error", dev, false, - stripe->logical, physical); + sector_logical, sector_physical); if (scrub_bitmap_test_bit_meta_gen_error(stripe, sector_nr)) if (__ratelimit(&rs) && dev) scrub_print_common_warning("generation error", dev, false, - stripe->logical, physical); + sector_logical, sector_physical); } /* Update the device stats. */ diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index dca3570168c7..5c59b9abedcd 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -2065,7 +2065,7 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen, ret = is_inode_existent(sctx, dir, dir_gen, NULL, &parent_root_dir_gen); if (ret <= 0) - return 0; + return ret; /* * If we have a parent root we need to verify that the parent dir was @@ -6417,6 +6417,13 @@ static int process_extent(struct send_ctx *sctx, if (S_ISLNK(sctx->cur_inode_mode)) return 0; + if (unlikely(!S_ISREG(sctx->cur_inode_mode))) { + btrfs_crit(sctx->send_root->fs_info, + "send: extent for non-regular inode %llu root %llu mode 0%llo", + key->objectid, btrfs_root_id(sctx->send_root), + sctx->cur_inode_mode & S_IFMT); + return -EUCLEAN; + } if (sctx->parent_root && !sctx->cur_inode_new) { ret = is_extent_unchanged(sctx, path, key); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 464129b1b0d4..ddb620ac241b 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1836,8 +1836,12 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) f_fsid.val[0] ^= btrfs_root_id(BTRFS_I(d_inode(dentry))->root) >> 32; f_fsid.val[1] ^= btrfs_root_id(BTRFS_I(d_inode(dentry))->root); - /* Hash dev_t to avoid f_fsid collision with cloned filesystems. */ - if (fs_info->fs_devices->total_devices == 1) { + /* + * Hash dev_t to avoid f_fsid collisions with cloned filesystems. + * Only do this when a clone is present so the original filesystem + * (mounted first) maintains backward-compatible f_fsid behavior. + */ + if (fs_info->fs_devices->temp_fsid) { __kernel_fsid_t dev_fsid = u64_to_fsid(huge_encode_dev(fs_info->fs_devices->latest_dev->bdev->bd_dev)); diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c index b2aacf846c8b..23459cd4e503 100644 --- a/fs/btrfs/tests/extent-io-tests.c +++ b/fs/btrfs/tests/extent-io-tests.c @@ -133,14 +133,14 @@ static int test_find_delalloc(u32 sectorsize, u32 nodesize) if (IS_ERR(root)) { test_std_err(TEST_ALLOC_ROOT); ret = PTR_ERR(root); - goto out; + goto out_root_info; } inode = btrfs_new_test_inode(); if (!inode) { test_std_err(TEST_ALLOC_INODE); ret = -ENOMEM; - goto out; + goto out_root_info; } tmp = &BTRFS_I(inode)->io_tree; BTRFS_I(inode)->root = root; @@ -333,6 +333,7 @@ out: process_page_range(inode, 0, total_dirty - 1, PROCESS_UNLOCK | PROCESS_RELEASE); iput(inode); +out_root_info: btrfs_free_dummy_root(root); btrfs_free_dummy_fs_info(fs_info); return ret; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index bafc62cf5ebc..6802b94ed76f 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -458,8 +458,19 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans, * through btrfs_record_root_in_trans without having to take the * lock. smp_wmb() makes sure that all the writes above are * done before we pop in the zero below + * + * If @force is true, it means the call is from + * qgroup_account_snapshot(), which only requires radix tree + * tracking. + * We should not force reloc root creation here, as the root + * may have already been modified, and in that case + * root->commit_root has already been dropped. + * + * Using that commit root will cause the reloc root to refer + * to a deleted extent, causing extent tree corruption. */ - ret = btrfs_init_reloc_root(trans, root); + if (!force) + ret = btrfs_init_reloc_root(trans, root); smp_mb__before_atomic(); clear_bit(BTRFS_ROOT_IN_TRANS_SETUP, &root->state); } @@ -2583,6 +2594,12 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) ret = btrfs_write_and_wait_transaction(trans); if (unlikely(ret)) { btrfs_err(fs_info, "error while writing out transaction: %pe", ERR_PTR(ret)); + /* + * Abort before releasing tree_log_mutex, so a log sync waiting + * on it sees the fs error and skips writing super_for_commit + * for this failed transaction. See btrfs_sync_log(). + */ + btrfs_abort_transaction(trans, ret); mutex_unlock(&fs_info->tree_log_mutex); goto scrub_continue; } diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 0ce91396b517..4b1e47173c63 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1909,6 +1909,16 @@ static int check_inode_ref(struct extent_buffer *leaf, return -EUCLEAN; } + if (unlikely(btrfs_is_fstree(btrfs_header_owner(leaf)) && + (key->offset < BTRFS_FIRST_FREE_OBJECTID || + key->offset > BTRFS_LAST_FREE_OBJECTID))) { + inode_ref_err(leaf, slot, + "invalid offset for ref key, have %llu expect [%llu, %lld]", + key->offset, BTRFS_FIRST_FREE_OBJECTID, + BTRFS_LAST_FREE_OBJECTID); + return -EUCLEAN; + } + ptr = btrfs_item_ptr_offset(leaf, slot); end = ptr + btrfs_item_size(leaf, slot); while (ptr < end) { @@ -1952,12 +1962,14 @@ static int check_inode_extref(struct extent_buffer *leaf, { unsigned long ptr = btrfs_item_ptr_offset(leaf, slot); unsigned long end = ptr + btrfs_item_size(leaf, slot); + const bool is_fstree = btrfs_is_fstree(btrfs_header_owner(leaf)); if (unlikely(!check_prev_ino(leaf, key, slot, prev_key))) return -EUCLEAN; while (ptr < end) { struct btrfs_inode_extref *extref = (struct btrfs_inode_extref *)ptr; + u64 parent; u16 namelen; if (unlikely(ptr + sizeof(*extref) > end)) { @@ -1967,7 +1979,24 @@ static int check_inode_extref(struct extent_buffer *leaf, return -EUCLEAN; } + parent = btrfs_inode_extref_parent(leaf, extref); + if (unlikely(is_fstree && (parent < BTRFS_FIRST_FREE_OBJECTID || + parent > BTRFS_LAST_FREE_OBJECTID))) { + inode_ref_err(leaf, slot, + "invalid parent for extref key, have %llu expect [%llu, %lld]", + parent, BTRFS_FIRST_FREE_OBJECTID, + BTRFS_LAST_FREE_OBJECTID); + return -EUCLEAN; + } + namelen = btrfs_inode_extref_name_len(leaf, extref); + if (unlikely(namelen == 0 || namelen > BTRFS_NAME_LEN)) { + inode_ref_err(leaf, slot, + "invalid inode extref name length, has %u expect [1, %u]", + namelen, BTRFS_NAME_LEN); + return -EUCLEAN; + } + if (unlikely(ptr + sizeof(*extref) + namelen > end)) { inode_ref_err(leaf, slot, "inode extref overflow, ptr %lu end %lu namelen %u", @@ -2100,7 +2129,7 @@ static int check_dev_extent_item(const struct extent_buffer *leaf, sectorsize))) { generic_err(leaf, slot, "invalid dev extent chunk offset, has %llu not aligned to %u", - btrfs_dev_extent_chunk_objectid(leaf, de), + btrfs_dev_extent_chunk_offset(leaf, de), sectorsize); return -EUCLEAN; } @@ -2277,7 +2306,7 @@ static int check_free_space_extent(struct extent_buffer *leaf, struct btrfs_key if (unlikely(btrfs_item_size(leaf, slot) != 0)) { generic_err(leaf, slot, - "invalid item size for free space info, has %u expect 0", + "invalid item size for free space extent, has %u expect 0", btrfs_item_size(leaf, slot)); return -EUCLEAN; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 7ba7b6098aa5..a00094604e54 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -7286,6 +7286,22 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans, ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto out; + /* + * There can't be an inode ref key with offset 0 because inode numbers + * start at BTRFS_FIRST_FREE_OBJECTID. + */ + if (WARN_ON_ONCE(ret == 0)) { + btrfs_err(trans->fs_info, + "found inode ref key with offset 0 for root %llu inode %llu", + btrfs_root_id(root), ino); + ret = BTRFS_LOG_FORCE_COMMIT; + goto out; + } + /* + * Set to 0 so that in case we don't do any work below, we won't return + * 1 and trigger an unnecessary transaction commit. + */ + ret = 0; while (true) { struct extent_buffer *leaf = path->nodes[0]; diff --git a/fs/btrfs/verity.c b/fs/btrfs/verity.c index 4e0ab5842274..600337a84fbe 100644 --- a/fs/btrfs/verity.c +++ b/fs/btrfs/verity.c @@ -94,6 +94,20 @@ static loff_t merkle_file_pos(const struct inode *inode) } /* + * Start a transaction for removing verity items or the verity orphan. + * + * Like unlink, this only deletes items and frees space in the end, so the + * reservation may come from the global reserve when the filesystem is full + * (-ENOSPC) and is not subject to the qgroup limit (-EDQUOT). Otherwise a + * failed enable could never be cleaned up in either situation. + */ +static struct btrfs_trans_handle *start_verity_cleanup_trans(struct btrfs_root *root, + unsigned int num_items) +{ + return btrfs_start_transaction_fallback_global_rsv(root, num_items); +} + +/* * Drop all the items for this inode with this key_type. * * @inode: inode to drop items for @@ -120,7 +134,7 @@ static int drop_verity_items(struct btrfs_inode *inode, u8 key_type) while (1) { /* 1 for the item being dropped */ - trans = btrfs_start_transaction(root, 1); + trans = start_verity_cleanup_trans(root, 1); if (IS_ERR(trans)) return PTR_ERR(trans); @@ -466,7 +480,7 @@ static int rollback_verity(struct btrfs_inode *inode) * 1 for updating the inode flag * 1 for deleting the orphan */ - trans = btrfs_start_transaction(root, 2); + trans = start_verity_cleanup_trans(root, 2); if (IS_ERR(trans)) { ret = PTR_ERR(trans); trans = NULL; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 9b66eb584ece..85ea9c5d4536 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -749,6 +749,36 @@ const u8 *btrfs_sb_fsid_ptr(const struct btrfs_super_block *sb) return has_metadata_uuid ? sb->metadata_uuid : sb->fsid; } +static bool should_rename_device(const struct btrfs_device *dev) +{ + bool ret; + const char *old_name; + + rcu_read_lock(); + old_name = rcu_dereference(dev->name); + /* + * For systems booted without an initramfs, the rootfs has the device + * name "/dev/root". + * + * Although using btrfs without an initramfs is not recommended (if a + * new device is added to the rootfs, the system can no longer boot, as + * there is no way to register all devices), there is still a minority + * of users doing this. + * + * And after the system is up, a later device scan on the real block + * device file will never get this device's name updated, as the + * device->devt is still the same. + * + * Here we add one and only one exception for "/dev/root", to allow the + * device name to be updated even if the new path points to the same + * block device. + */ + ret = (strcmp(old_name, "/dev/root") == 0); + rcu_read_unlock(); + + return ret; +} + /* * Add new device to list of registered devices * @@ -869,7 +899,8 @@ static noinline struct btrfs_device *device_list_add(const char *path, MAJOR(path_devt), MINOR(path_devt), current->comm, task_pid_nr(current)); - } else if (!device->name || device->devt != path_devt) { + } else if (!device->name || device->devt != path_devt || + should_rename_device(device)) { const char *old_name; /* @@ -3117,7 +3148,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path error_sysfs: btrfs_sysfs_remove_device(device); mutex_lock(&fs_info->fs_devices->device_list_mutex); + if (seeding_dev) + btrfs_assign_next_active_device(device, seed_devices->latest_dev); mutex_lock(&fs_info->chunk_mutex); + if (!list_empty(&device->post_commit_list)) + list_del_init(&device->post_commit_list); list_del_rcu(&device->dev_list); list_del(&device->dev_alloc_list); fs_info->fs_devices->num_devices--; diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index a016cb471beb..08a15465a087 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -2626,16 +2626,13 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ down_read(&dev_replace->rwsem); map = block_group->physical_map; for (i = 0; i < map->num_stripes; i++) { - ret = call_zone_finish(block_group, &map->stripes[i]); - if (ret) { - up_read(&dev_replace->rwsem); - return ret; - } + if (ret) + break; } up_read(&dev_replace->rwsem); - if (!fully_written) + if (!ret && !fully_written) btrfs_dec_block_group_ro(block_group); spin_lock(&fs_info->zone_active_bgs_lock); @@ -2648,7 +2645,7 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ clear_and_wake_up_bit(BTRFS_FS_NEED_ZONE_FINISH, &fs_info->flags); - return 0; + return ret; } int btrfs_zone_finish(struct btrfs_block_group *block_group) @@ -2691,6 +2688,11 @@ bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags) switch (flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) { case 0: /* single */ + case BTRFS_BLOCK_GROUP_RAID0: + case BTRFS_BLOCK_GROUP_RAID1: + case BTRFS_BLOCK_GROUP_RAID1C3: + case BTRFS_BLOCK_GROUP_RAID1C4: + case BTRFS_BLOCK_GROUP_RAID10: ret = (atomic_read(&zinfo->active_zones_left) >= (1 + reserved)); break; case BTRFS_BLOCK_GROUP_DUP: @@ -2713,6 +2715,7 @@ int btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info, u64 logical, u64 leng { struct btrfs_block_group *block_group; u64 min_alloc_bytes; + int ret = 0; if (!btrfs_is_zoned(fs_info)) return 0; @@ -2732,11 +2735,11 @@ int btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info, u64 logical, u64 leng block_group->start + block_group->zone_capacity) goto out; - do_zone_finish(block_group, true); + ret = do_zone_finish(block_group, true); out: btrfs_put_block_group(block_group); - return 0; + return ret; } static void btrfs_zone_finish_endio_workfn(struct work_struct *work) diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c index 86919293fd54..58d9ff76fe07 100644 --- a/fs/btrfs/zstd.c +++ b/fs/btrfs/zstd.c @@ -307,8 +307,17 @@ again: DEFINE_WAIT(wait); prepare_to_wait(&zwsm->wait, &wait, TASK_UNINTERRUPTIBLE); - schedule(); + /* + * Re-check after being queued: zstd_put_workspace() only wakes + * a queue that already has a sleeper, so a workspace returned + * since the failed allocation woke nobody. + */ + ws = zstd_find_workspace(fs_info, level); + if (!ws) + schedule(); finish_wait(&zwsm->wait, &wait); + if (ws) + return ws; goto again; } diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c index f8ae78b3f7b6..c70bf67e52b0 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -13,6 +13,7 @@ #include <linux/quotaops.h> #include <linux/xattr.h> #include <linux/slab.h> +#include <linux/unaligned.h> #include "internal.h" #define CACHEFILES_COOKIE_TYPE_DATA 1 @@ -50,7 +51,7 @@ int cachefiles_set_object_xattr(struct cachefiles_object *object) _enter("%x,#%d", object->debug_id, len); - buf = kmalloc(sizeof(struct cachefiles_xattr) + len, GFP_KERNEL); + buf = kmalloc(sizeof(struct cachefiles_xattr) + max(len, sizeof(__be64)), GFP_KERNEL); if (!buf) return -ENOMEM; @@ -60,6 +61,7 @@ int cachefiles_set_object_xattr(struct cachefiles_object *object) buf->content = object->content_info; if (test_bit(FSCACHE_COOKIE_LOCAL_WRITE, &object->cookie->flags)) buf->content = CACHEFILES_CONTENT_DIRTY; + put_unaligned_be64(0, (__be64 *)buf->data); if (len > 0) memcpy(buf->data, fscache_get_aux(object->cookie), len); @@ -77,8 +79,7 @@ int cachefiles_set_object_xattr(struct cachefiles_object *object) trace_cachefiles_vfs_error(object, file_inode(file), ret, cachefiles_trace_setxattr_error); trace_cachefiles_coherency(object, file_inode(file)->i_ino, - be64_to_cpup((__be64 *)buf->data), - buf->content, + buf->data, buf->content, cachefiles_coherency_set_fail); if (ret != -ENOMEM) cachefiles_io_error_obj( @@ -86,8 +87,7 @@ int cachefiles_set_object_xattr(struct cachefiles_object *object) "Failed to set xattr with error %d", ret); } else { trace_cachefiles_coherency(object, file_inode(file)->i_ino, - be64_to_cpup((__be64 *)buf->data), - buf->content, + buf->data, buf->content, cachefiles_coherency_set_ok); } @@ -110,9 +110,10 @@ int cachefiles_check_auxdata(struct cachefiles_object *object, struct file *file int ret = -ESTALE; tlen = sizeof(struct cachefiles_xattr) + len; - buf = kmalloc(tlen, GFP_KERNEL); + buf = kmalloc(sizeof(struct cachefiles_xattr) + max(len, sizeof(__be64)), GFP_KERNEL); if (!buf) return -ENOMEM; + put_unaligned_be64(0, (__be64 *)buf->data); xlen = cachefiles_inject_read_error(); if (xlen == 0) @@ -148,8 +149,7 @@ int cachefiles_check_auxdata(struct cachefiles_object *object, struct file *file out: trace_cachefiles_coherency(object, file_inode(file)->i_ino, - be64_to_cpup((__be64 *)buf->data), - buf->content, why); + buf->data, buf->content, why); kfree(buf); return ret; } diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 657c2cb0f881..e598b2d424ec 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -2546,7 +2546,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, } pool_ns_len = pool_ns ? pool_ns->len : 0; - perm = kmalloc_flex(*perm, pool_ns, pool_ns_len + 1, GFP_KERNEL); + perm = kmalloc_flex(*perm, pool_ns, pool_ns_len + 1); if (!perm) { err = -ENOMEM; goto out_unlock; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index a091f77cedaf..085ae0cfb5f7 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -5492,7 +5492,7 @@ static void ceph_mdsc_reset_workfn(struct work_struct *work) goto out_complete; } - sessions = kcalloc(max_sessions, sizeof(*sessions), GFP_KERNEL); + sessions = kzalloc_objs(*sessions, max_sessions); if (!sessions) { mutex_unlock(&mdsc->mutex); ret = -ENOMEM; @@ -6600,11 +6600,13 @@ int ceph_mds_check_access(struct ceph_mds_client *mdsc, char *tpath, int mask) doutc(cl, "tpath '%s', mask %d, caller_uid %d, caller_gid %d\n", tpath, mask, caller_uid, caller_gid); + mutex_lock(&mdsc->mutex); for (i = 0; i < mdsc->s_cap_auths_num; i++) { struct ceph_mds_cap_auth *s = &mdsc->s_cap_auths[i]; err = ceph_mds_auth_match(mdsc, s, cred, tpath); if (err < 0) { + mutex_unlock(&mdsc->mutex); put_cred(cred); return err; } else if (err > 0) { @@ -6626,6 +6628,7 @@ int ceph_mds_check_access(struct ceph_mds_client *mdsc, char *tpath, int mask) doutc(cl, "root_squash_perms %d, rw_perms_s %p\n", root_squash_perms, rw_perms_s); if (root_squash_perms && rw_perms_s == NULL) { + mutex_unlock(&mdsc->mutex); doutc(cl, "access allowed\n"); return 0; } @@ -6640,6 +6643,7 @@ int ceph_mds_check_access(struct ceph_mds_client *mdsc, char *tpath, int mask) !!(mask & MAY_READ), !!(mask & MAY_WRITE)); } doutc(cl, "access denied\n"); + mutex_unlock(&mdsc->mutex); return -EACCES; } diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 3c62e3c3530b..e7a262c9c2ab 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -604,6 +604,7 @@ struct ceph_mds_client { struct rw_semaphore pool_perm_rwsem; struct rb_root pool_perm_tree; + /* protected by mutex */ u32 s_cap_auths_num; struct ceph_mds_cap_auth *s_cap_auths; diff --git a/fs/ceph/subvolume_metrics.c b/fs/ceph/subvolume_metrics.c index 03fda1f9257b..01419c9482f1 100644 --- a/fs/ceph/subvolume_metrics.c +++ b/fs/ceph/subvolume_metrics.c @@ -245,7 +245,7 @@ int ceph_subvolume_metrics_snapshot(struct ceph_subvolume_metrics_tracker *track return 0; } - snap = kcalloc(count, sizeof(*snap), GFP_NOFS); + snap = kzalloc_objs(*snap, count, GFP_NOFS); if (!snap) { atomic64_inc(&tracker->snapshot_failures); return -ENOMEM; diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 15edea30dc8b..72935f665f11 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -1420,6 +1420,11 @@ static int ceph_reconfigure_fc(struct fs_context *fc) else ceph_clear_mount_opt(fsc, SPARSEREAD); + if (fsopt->flags & CEPH_MOUNT_OPT_NEARFULL_SYNC) + ceph_set_mount_opt(fsc, NEARFULL_SYNC); + else + ceph_clear_mount_opt(fsc, NEARFULL_SYNC); + if (strcmp_null(fsc->mount_options->mon_addr, fsopt->mon_addr)) { kfree(fsc->mount_options->mon_addr); fsc->mount_options->mon_addr = fsopt->mon_addr; diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 3c88f13f1ca2..eda80c2a2d38 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -416,6 +416,15 @@ static void configfs_remove_dir(struct dentry *d) if (d_really_is_positive(d)) { if (unlikely(simple_rmdir(d_inode(parent), d))) pr_warn("remove_dir (%pd): attributes remain", d); + else + /* + * configfs_get_config_item() takes a hashed dentry as + * proof that ->s_element is still alive. Our caller + * is about to drop the last reference to the item and + * the VFS will not unhash until after we return, so + * unhash it here. + */ + d_drop(d); } pr_debug(" o %pd removing done (%d)\n", d, d_count(d)); diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c index 4929f3431189..d8cac1cbf3bd 100644 --- a/fs/configfs/mount.c +++ b/fs/configfs/mount.c @@ -9,6 +9,7 @@ */ #include <linux/fs.h> +#include <linux/magic.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/fs_context.h> @@ -19,9 +20,6 @@ #include <linux/configfs.h> #include "configfs_internal.h" -/* Random magic number */ -#define CONFIGFS_MAGIC 0x62656570 - static struct vfsmount *configfs_mount = NULL; struct kmem_cache *configfs_dir_cachep; static int configfs_mnt_count = 0; diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c index 31eb28b27309..3b31c714400f 100644 --- a/fs/configfs/symlink.c +++ b/fs/configfs/symlink.c @@ -76,9 +76,9 @@ static int configfs_get_target_path(struct config_item *item, static int create_link(struct config_item *parent_item, struct config_item *item, + struct configfs_dirent *target_sd, struct dentry *dentry) { - struct configfs_dirent *target_sd = item->ci_dentry->d_fsdata; char *body; int ret; @@ -115,6 +115,7 @@ static int create_link(struct config_item *parent_item, static int get_target(const char *symname, struct config_item **target, + struct configfs_dirent **target_sd, struct super_block *sb) { struct path path __free(path_put) = {}; @@ -125,7 +126,20 @@ static int get_target(const char *symname, struct config_item **target, return ret; if (path.dentry->d_sb != sb) return -EPERM; - *target = configfs_get_config_item(path.dentry); + /* + * A hashed dentry guarantees that neither the item nor the dirent + * have been released yet, as removals unhash before dropping. + * Grab both references here. An item reference alone would not keep + * ->ci_dentry alive. + */ + spin_lock(&path.dentry->d_lock); + if (!d_unhashed(path.dentry)) { + struct configfs_dirent *sd = path.dentry->d_fsdata; + + *target = config_item_get(sd->s_element); + *target_sd = configfs_get(sd); + } + spin_unlock(&path.dentry->d_lock); if (!*target) return -ENOENT; return 0; @@ -139,6 +153,7 @@ int configfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct configfs_dirent *sd; struct config_item *parent_item; struct config_item *target_item = NULL; + struct configfs_dirent *target_sd = NULL; const struct config_item_type *type; sd = dentry->d_parent->d_fsdata; @@ -182,7 +197,7 @@ int configfs_symlink(struct mnt_idmap *idmap, struct inode *dir, * AV, a thoroughly annoyed bastard. */ inode_unlock(dir); - ret = get_target(symname, &target_item, dentry->d_sb); + ret = get_target(symname, &target_item, &target_sd, dentry->d_sb); inode_lock(dir); if (ret) goto out_put; @@ -196,13 +211,14 @@ int configfs_symlink(struct mnt_idmap *idmap, struct inode *dir, ret = type->ct_item_ops->allow_link(parent_item, target_item); if (!ret) { mutex_lock(&configfs_symlink_mutex); - ret = create_link(parent_item, target_item, dentry); + ret = create_link(parent_item, target_item, target_sd, dentry); mutex_unlock(&configfs_symlink_mutex); if (ret && type->ct_item_ops->drop_link) type->ct_item_ops->drop_link(parent_item, target_item); } + configfs_put(target_sd); config_item_put(target_item); out_put: diff --git a/fs/coredump.c b/fs/coredump.c index ac3cd74808c6..6114839f5178 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -1000,7 +1000,7 @@ static bool coredump_pipe(struct core_name *cn, struct coredump_params *cprm, return false; } - helper_argv = kmalloc_array(argc + 1, sizeof(*helper_argv), GFP_KERNEL); + helper_argv = kmalloc_objs(*helper_argv, argc + 1); if (!helper_argv) { coredump_report_failure("%s failed to allocate memory", __func__); return false; @@ -480,11 +480,12 @@ static void dax_associate_entry(void *entry, struct address_space *mapping, unsigned long address, bool shared) { unsigned long size = dax_entry_size(entry), index; - struct folio *folio = dax_to_folio(entry); + struct folio *folio; if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) return; + folio = dax_to_folio(entry); index = linear_page_index(vma, address & ~(size - 1)); if (shared && (folio->mapping || dax_folio_is_shared(folio))) { if (folio->mapping) @@ -505,21 +506,23 @@ static void dax_associate_entry(void *entry, struct address_space *mapping, static void dax_disassociate_entry(void *entry, struct address_space *mapping, bool trunc) { - struct folio *folio = dax_to_folio(entry); + struct folio *folio; if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) return; + folio = dax_to_folio(entry); dax_folio_put(folio); } static struct page *dax_busy_page(void *entry) { - struct folio *folio = dax_to_folio(entry); + struct folio *folio; if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) return NULL; + folio = dax_to_folio(entry); if (folio_ref_count(folio) - folio_mapcount(folio)) return &folio->page; else diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 0885b1f2fc92..be63b89f0862 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -48,7 +48,7 @@ void *erofs_bread(struct erofs_buf *buf, erofs_off_t offset, bool need_kmap) return NULL; if (!buf->base) buf->base = kmap_local_page(buf->page); - return buf->base + (offset & ~PAGE_MASK); + return buf->base + ((buf->off + offset) & ~PAGE_MASK); } int erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb, diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c index 27caf4bebddc..d387b27c4ee2 100644 --- a/fs/erofs/decompressor.c +++ b/fs/erofs/decompressor.c @@ -7,8 +7,6 @@ #include "compress.h" #include <linux/lz4.h> -#define LZ4_MAX_DISTANCE_PAGES (DIV_ROUND_UP(LZ4_DISTANCE_MAX, PAGE_SIZE) + 1) - static int z_erofs_load_lz4_config(struct super_block *sb, struct erofs_super_block *dsb, void *data, int size) { @@ -21,8 +19,6 @@ static int z_erofs_load_lz4_config(struct super_block *sb, erofs_err(sb, "invalid lz4 cfgs, size=%u", size); return -EINVAL; } - distance = le16_to_cpu(lz4->max_distance); - sbi->lz4.max_pclusterblks = le16_to_cpu(lz4->max_pclusterblks); if (!sbi->lz4.max_pclusterblks) { sbi->lz4.max_pclusterblks = 1; /* reserved case */ @@ -39,45 +35,25 @@ static int z_erofs_load_lz4_config(struct super_block *sb, sbi->lz4.max_pclusterblks = 1; sbi->available_compr_algs = 1 << Z_EROFS_COMPRESSION_LZ4; } - - sbi->lz4.max_distance_pages = distance ? - DIV_ROUND_UP(distance, PAGE_SIZE) + 1 : - LZ4_MAX_DISTANCE_PAGES; return z_erofs_gbuf_growsize(sbi->lz4.max_pclusterblks); } /* - * Fill all gaps with bounce pages if it's a sparse page list. Also check if - * all physical pages are consecutive, which can be seen for moderate CR. + * Fill all gaps with bounce pages if it's a sparse page list (for example some + * folios are already uptodate and thus can be mapped into userspace). Also + * check if pages are physically consecutive, which can be seen for moderate CR. */ -static int z_erofs_lz4_prepare_dstpages(struct z_erofs_decompress_req *rq, - struct page **pagepool) +static int z_erofs_oneshot_prepare_dstpages(struct z_erofs_decompress_req *rq, + struct page **pagepool) { - struct page *availables[LZ4_MAX_DISTANCE_PAGES] = { NULL }; - unsigned long bounced[DIV_ROUND_UP(LZ4_MAX_DISTANCE_PAGES, - BITS_PER_LONG)] = { 0 }; - unsigned int lz4_max_distance_pages = - EROFS_SB(rq->sb)->lz4.max_distance_pages; void *kaddr = NULL; - unsigned int i, j, top; + unsigned int i; - top = 0; - for (i = j = 0; i < rq->outpages; ++i, ++j) { - struct page *const page = rq->out[i]; - struct page *victim; - - if (j >= lz4_max_distance_pages) - j = 0; - - /* 'valid' bounced can only be tested after a complete round */ - if (!rq->fillgaps && test_bit(j, bounced)) { - DBG_BUGON(i < lz4_max_distance_pages); - DBG_BUGON(top >= lz4_max_distance_pages); - availables[top++] = rq->out[i - lz4_max_distance_pages]; - } + for (i = 0; i < rq->outpages; ++i) { + struct page *page, *victim; + page = rq->out[i]; if (page) { - __clear_bit(j, bounced); if (!PageHighMem(page)) { if (!i) { kaddr = page_address(page); @@ -89,21 +65,14 @@ static int z_erofs_lz4_prepare_dstpages(struct z_erofs_decompress_req *rq, continue; } } - kaddr = NULL; - continue; - } - kaddr = NULL; - __set_bit(j, bounced); - - if (top) { - victim = availables[--top]; } else { victim = __erofs_allocpage(pagepool, rq->gfp, true); if (!victim) return -ENOMEM; set_page_private(victim, Z_EROFS_SHORTLIVED_PAGE); + rq->out[i] = victim; } - rq->out[i] = victim; + kaddr = NULL; } return kaddr ? 1 : 0; } @@ -266,7 +235,7 @@ static const char *z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, dst_maptype = 0; } else { /* general decoding path which can be used for all cases */ - ret = z_erofs_lz4_prepare_dstpages(rq, pagepool); + ret = z_erofs_oneshot_prepare_dstpages(rq, pagepool); if (ret < 0) return ERR_PTR(ret); if (ret > 0) { diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c index 6b0cdb446c6a..9d15f94cbee1 100644 --- a/fs/erofs/decompressor_lzma.c +++ b/fs/erofs/decompressor_lzma.c @@ -5,6 +5,7 @@ struct z_erofs_lzma { struct z_erofs_lzma *next; struct xz_dec_microlzma *state; + unsigned int dict_size; u8 bounce[PAGE_SIZE]; }; @@ -128,11 +129,19 @@ again: err = 0; /* 2. walk each isolated stream and grow max dict_size if needed */ for (strm = head; strm; strm = strm->next) { + struct xz_dec_microlzma *state; + + if (strm->dict_size >= dict_size) + continue; + state = xz_dec_microlzma_alloc(XZ_PREALLOC, dict_size); + if (!state) { + err = -ENOMEM; + break; + } if (strm->state) xz_dec_microlzma_end(strm->state); - strm->state = xz_dec_microlzma_alloc(XZ_PREALLOC, dict_size); - if (!strm->state) - err = -ENOMEM; + strm->state = state; + strm->dict_size = dict_size; } /* 3. push back all to the global list and update max dict_size */ @@ -142,7 +151,8 @@ again: spin_unlock(&z_erofs_lzma_lock); wake_up_all(&z_erofs_lzma_wq); - z_erofs_lzma_max_dictsize = dict_size; + if (!err) + z_erofs_lzma_max_dictsize = dict_size; mutex_unlock(&lzma_resize_mutex); return err; } diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 65974e57aebf..12e3a5b80a5a 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -71,12 +71,8 @@ struct erofs_dev_context { bool flatdev; }; -/* all filesystem-wide lz4 configurations */ struct erofs_sb_lz4_info { - /* # of pages needed for EROFS lz4 rolling decompression */ - u16 max_distance_pages; - /* maximum possible blocks for pclusters in the filesystem */ - u16 max_pclusterblks; + u16 max_pclusterblks; /* maximum physical blocks for LZ4 pclusters */ }; struct erofs_xattr_prefix_item { diff --git a/fs/erofs/sysfs.c b/fs/erofs/sysfs.c index 6734483a440f..dfcec9376cd5 100644 --- a/fs/erofs/sysfs.c +++ b/fs/erofs/sysfs.c @@ -95,6 +95,7 @@ EROFS_ATTR_FEATURE(sb_chksum); EROFS_ATTR_FEATURE(ztailpacking); EROFS_ATTR_FEATURE(fragments); EROFS_ATTR_FEATURE(dedupe); +EROFS_ATTR_FEATURE(xattr_prefixes); EROFS_ATTR_FEATURE(48bit); EROFS_ATTR_FEATURE(metabox); @@ -108,6 +109,7 @@ static struct attribute *erofs_feat_attrs[] = { ATTR_LIST(ztailpacking), ATTR_LIST(fragments), ATTR_LIST(dedupe), + ATTR_LIST(xattr_prefixes), ATTR_LIST(48bit), ATTR_LIST(metabox), NULL, diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index df7ea019526d..57cfb7520782 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -620,8 +620,8 @@ int erofs_xattr_fill_inode_fingerprint(struct erofs_inode_fingerprint *fp, { struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb); struct erofs_xattr_prefix_item *prefix; + int domainlen, valuelen, base_index; const char *infix; - int valuelen, base_index; if (!test_opt(&sbi->opt, INODE_SHARE)) return -EOPNOTSUPP; @@ -633,17 +633,18 @@ int erofs_xattr_fill_inode_fingerprint(struct erofs_inode_fingerprint *fp, valuelen = erofs_getxattr(inode, base_index, infix, NULL, 0); if (valuelen <= 0 || valuelen > (1 << sbi->blkszbits)) return -EFSCORRUPTED; - fp->size = valuelen + (domain_id ? strlen(domain_id) : 0); + domainlen = strlen(domain_id); + fp->size = domainlen + 1 + valuelen; fp->opaque = kmalloc(fp->size, GFP_KERNEL); if (!fp->opaque) return -ENOMEM; + memcpy(fp->opaque, domain_id, domainlen + 1); if (valuelen != erofs_getxattr(inode, base_index, infix, - fp->opaque, valuelen)) { + fp->opaque + domainlen + 1, valuelen)) { kfree(fp->opaque); fp->opaque = NULL; return -EFSCORRUPTED; } - memcpy(fp->opaque + valuelen, domain_id, fp->size - valuelen); return 0; } #endif diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index e1e25ca0d190..6b07e73ee2aa 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1259,7 +1259,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, bool eio) const struct z_erofs_decompressor *alg = z_erofs_decomp[pcl->algorithmformat]; bool try_free = true; - int i, j, jtop, err2, err = eio ? -EIO : 0; + int i, err2, err = eio ? -EIO : 0; struct page *page; bool overlapped; const char *reason; @@ -1348,7 +1348,6 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, bool eio) be->compressed_pages >= be->onstack_pages + Z_EROFS_ONSTACK_PAGES) kvfree(be->compressed_pages); - jtop = 0; z_erofs_fill_other_copies(be, err); for (i = 0; i < be->nr_pages; ++i) { page = be->decompressed_pages[i]; @@ -1356,22 +1355,11 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, bool eio) continue; DBG_BUGON(z_erofs_page_is_invalidated(page)); - if (!z_erofs_is_shortlived_page(page)) { + if (!z_erofs_is_shortlived_page(page)) erofs_onlinefolio_end(page_folio(page), err, true); - continue; - } - if (pcl->algorithmformat != Z_EROFS_COMPRESSION_LZ4) { + else erofs_pagepool_add(be->pagepool, page); - continue; - } - for (j = 0; j < jtop && be->decompressed_pages[j] != page; ++j) - ; - if (j >= jtop) /* this bounce page is newly detected */ - be->decompressed_pages[jtop++] = page; } - while (jtop) - erofs_pagepool_add(be->pagepool, - be->decompressed_pages[--jtop]); if (be->decompressed_pages != be->onstack_pages) kvfree(be->decompressed_pages); diff --git a/fs/exec.c b/fs/exec.c index 745f6eb5279e..819643408e6d 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1115,6 +1115,17 @@ static struct file *bprm_identity_file(const struct linux_binprm *bprm) return bprm->file; } +static void posixtimer_exec(struct task_struct *me) +{ +#ifdef CONFIG_POSIX_TIMERS + spin_lock_irq(&me->sighand->siglock); + posix_cpu_timers_exit(me); + spin_unlock_irq(&me->sighand->siglock); + exit_itimers(me); + flush_itimer_signals(); +#endif +} + /* * Calling this is the point of no return. None of the failures will be * seen by userspace since either the process is already taking a fatal @@ -1152,6 +1163,16 @@ int begin_new_exec(struct linux_binprm * bprm) retval = de_thread(me); if (retval) goto out; + + /* + * This must be done here to ensure that POSIX CPU timers which were + * armed on the current task are dequeued from me::posix_cputimers. + * Otherwise in case of a TID switch the deletion of the related POSIX + * timer would not remove an enqueued timer because the TID lookup + * of the old TID fails. + */ + posixtimer_exec(me); + /* see the comment in check_unsafe_exec() */ current->fs->in_exec = 0; /* @@ -1165,6 +1186,20 @@ int begin_new_exec(struct linux_binprm * bprm) goto out; /* + * We have to apply CLOEXEC before we change whether the process is + * dumpable (in setup_new_exec) to avoid a race with a process in userspace + * trying to access the should-be-closed file descriptors of a process + * undergoing exec(2). + * + * This can block on filesystem ->flush() handlers, including waiting + * for FUSE daemons, so do it before exec_mmap takes the + * exec_update_lock. + * This must happen after the point of no return, and after unsharing + * the FD table. + */ + do_close_on_exec(me->files); + + /* * Must be called _before_ exec_mmap() as bprm->mm is * not visible until then. Doing it here also ensures * we don't race against replace_mm_exe_file(). @@ -1192,14 +1227,6 @@ int begin_new_exec(struct linux_binprm * bprm) if (retval) goto out_unlock; -#ifdef CONFIG_POSIX_TIMERS - spin_lock_irq(&me->sighand->siglock); - posix_cpu_timers_exit(me); - spin_unlock_irq(&me->sighand->siglock); - exit_itimers(me); - flush_itimer_signals(); -#endif - /* * Make the signal table private. */ @@ -1214,14 +1241,6 @@ int begin_new_exec(struct linux_binprm * bprm) clear_syscall_work_syscall_user_dispatch(me); - /* - * We have to apply CLOEXEC before we change whether the process is - * dumpable (in setup_new_exec) to avoid a race with a process in userspace - * trying to access the should-be-closed file descriptors of a process - * undergoing exec(2). - */ - do_close_on_exec(me->files); - if (bprm->secureexec) { /* Make sure parent cannot signal privileged process. */ me->pdeath_signal = 0; @@ -1472,9 +1491,9 @@ static void free_bprm(struct linux_binprm *bprm) /* exec swapped the mm but failed before setup_new_exec() freed it */ if (bprm->old_mm) exec_mm_put_old(bprm->old_mm); - do_close_execat(bprm->file); /* An unconsumed PT_INTERP substitute from a binfmt_misc loader entry. */ bprm_drop_loader(bprm); + do_close_execat(bprm->file); do_close_execat(bprm->executable); /* If a binfmt changed the interp, free it. */ if (bprm->interp != bprm->filename) diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 062103e42cd8..0cac890cf370 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -1116,7 +1116,7 @@ static int ext4_fc_snapshot_inode(struct inode *inode, else if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) inode_len += ei->i_extra_isize; - snap = kmalloc(struct_size(snap, inode_buf, inode_len), GFP_NOFS); + snap = kmalloc_flex(*snap, inode_buf, inode_len, GFP_NOFS); if (!snap) { atomic64_inc(&stats->snap_fail_nomem); ext4_fc_set_snap_err(snap_err, EXT4_FC_SNAP_ERR_NOMEM); @@ -1522,7 +1522,7 @@ static int ext4_fc_alloc_snapshot_inodes(struct super_block *sb, if (nr_inodes > EXT4_FC_SNAPSHOT_MAX_INODES) return -E2BIG; - inodes = kvcalloc(nr_inodes, sizeof(*inodes), GFP_NOFS); + inodes = kvzalloc_objs(*inodes, nr_inodes, GFP_NOFS); if (!inodes) return -ENOMEM; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index bd4b778df9eb..26f0f9714f03 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -6456,9 +6456,10 @@ int ext4_chunk_trans_blocks(struct inode *inode, int nrblocks) int ext4_mark_iloc_dirty(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc) { + struct super_block *sb = inode->i_sb; int err = 0; - err = ext4_emergency_state(inode->i_sb); + err = ext4_emergency_state(sb); if (unlikely(err)) { put_bh(iloc->bh); return err; @@ -6473,9 +6474,13 @@ int ext4_mark_iloc_dirty(handle_t *handle, put_bh(iloc->bh); /* * Mark that there's metadata writeout pending for the inode so that it - * gets properly flushed on fsync(2) and similar. + * gets properly flushed on fsync(2) and similar. We don't bother for + * fastcommit replay as that flushes the whole bdev afterwards anyway. + * It is faster this way and we avoid entering fs writeback paths which + * aren't fully initialized yet. */ - if (!EXT4_SB(inode->i_sb)->s_journal) { + if (!ext4_handle_valid(handle) && + !(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)) { /* * Inode didn't need to go through dirtying, make sure it is * attached to wb so that writeback can handle it. diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 8d6135a6108a..9a36d0329e22 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1597,8 +1597,7 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii, * manually extract pages using iov_iter_extract_pages() and then * copy that to a folios array. */ - struct page **pages = kcalloc(max_pages, sizeof(struct page *), - GFP_KERNEL); + struct page **pages = kzalloc_objs(struct page *, max_pages); if (!pages) { ret = -ENOMEM; goto out; diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c index 5ca87151d70d..d2599043f7ec 100644 --- a/fs/fuse/readdir.c +++ b/fs/fuse/readdir.c @@ -336,7 +336,7 @@ static int parse_dirplusfile(char *buf, size_t nbytes, struct file *file, static struct page **fuse_readdir_alloc_buf(struct fuse_args_pages *ap, size_t *bufsize) { unsigned int i, nr_alloc, nr_pages = DIV_ROUND_UP(*bufsize, PAGE_SIZE); - struct page **pages = kcalloc(nr_pages, sizeof(*pages), GFP_KERNEL); + struct page **pages = kzalloc_objs(*pages, nr_pages); if (!pages) return NULL; diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c index 1b331108d9c0..fcb5b9cd17f6 100644 --- a/fs/hfs/bnode.c +++ b/fs/hfs/bnode.c @@ -312,7 +312,7 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) return NULL; } - node = kzalloc_flex(*node, page, tree->pages_per_bnode, GFP_KERNEL); + node = kzalloc_flex(*node, page, tree->pages_per_bnode); if (!node) return NULL; node->tree = tree; diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 237dcdd73fc2..abb286bc3474 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -142,10 +142,8 @@ ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size) struct kernfs_iattrs *attrs; attrs = kernfs_iattrs_noalloc(kn); - if (!attrs) - return 0; - return simple_xattr_list(d_inode(dentry), &attrs->xattrs, buf, size); + return simple_xattr_list(d_inode(dentry), attrs ? &attrs->xattrs : NULL, buf, size); } static inline void set_default_inode_attr(struct inode *inode, umode_t mode) diff --git a/fs/namespace.c b/fs/namespace.c index 1ecd96c918b3..ae5dc64f8b45 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -5999,7 +5999,7 @@ SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req, return -EPERM; } - ks = kmalloc(sizeof(*ks), GFP_KERNEL_ACCOUNT); + ks = kmalloc_obj(*ks, GFP_KERNEL_ACCOUNT); if (!ks) return -ENOMEM; diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 7fdfa4f27e34..424df70a5c30 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -55,6 +55,42 @@ static void netfs_rreq_expand(struct netfs_io_request *rreq, } /* + * Drop the folio refs acquired from the readahead API. + */ +static void netfs_bulk_drop_ra_refs(struct netfs_io_request *rreq) +{ + struct folio_batch fbatch; + struct folio *folio; + pgoff_t nr_pages = DIV_ROUND_UP(rreq->len, PAGE_SIZE); + pgoff_t first = rreq->start / PAGE_SIZE; + XA_STATE(xas, &rreq->mapping->i_pages, first); + + folio_batch_init(&fbatch); + + rcu_read_lock(); + + xas_for_each(&xas, folio, first + nr_pages - 1) { + if (xas_retry(&xas, folio)) + continue; + + if (!folio_batch_add(&fbatch, folio)) + folio_batch_release(&fbatch); + } + + rcu_read_unlock(); + folio_batch_release(&fbatch); + trace_netfs_rreq(rreq, netfs_rreq_trace_ra_put_ref); + clear_bit_unlock(NETFS_RREQ_NEED_PUT_RA_REFS, &rreq->flags); + wake_up(&rreq->waitq); +} + +static void netfs_maybe_bulk_drop_ra_refs(struct netfs_io_request *rreq) +{ + if (test_bit(NETFS_RREQ_NEED_PUT_RA_REFS, &rreq->flags)) + netfs_bulk_drop_ra_refs(rreq); +} + +/* * Begin an operation, and fetch the stored zero point value from the cookie if * available. */ @@ -74,12 +110,8 @@ static int netfs_begin_cache_read(struct netfs_io_request *rreq, struct netfs_in * * Returns the limited size if successful and -ENOMEM if insufficient memory * available. - * - * [!] NOTE: This must be run in the same thread as ->issue_read() was called - * in as we access the readahead_control struct. */ -static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq, - struct readahead_control *ractl) +static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; size_t rsize = subreq->len; @@ -87,30 +119,6 @@ static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq, if (subreq->source == NETFS_DOWNLOAD_FROM_SERVER) rsize = umin(rsize, rreq->io_streams[0].sreq_max_len); - if (ractl) { - /* If we don't have sufficient folios in the rolling buffer, - * extract a folioq's worth from the readahead region at a time - * into the buffer. Note that this acquires a ref on each page - * that we will need to release later - but we don't want to do - * that until after we've started the I/O. - */ - struct folio_batch put_batch; - - folio_batch_init(&put_batch); - while (rreq->submitted < subreq->start + rsize) { - ssize_t added; - - added = rolling_buffer_load_from_ra(&rreq->buffer, ractl, - &put_batch); - if (added < 0) { - folio_batch_release(&put_batch); - return added; - } - rreq->submitted += added; - } - folio_batch_release(&put_batch); - } - subreq->len = rsize; if (unlikely(rreq->io_streams[0].sreq_max_segs)) { size_t limit = netfs_limit_iter(&rreq->buffer.iter, 0, rsize, @@ -204,16 +212,67 @@ static void netfs_issue_read(struct netfs_io_request *rreq, } /* + * Mark folios that we want to copy to the cache. For filesystems that use + * netfslib fully, we set folio->private to NETFS_FOLIO_COPY_TO_CACHE; + * otherwise we set the deprecated PG_private_2. + */ +static void netfs_mark_copy_to_cache(struct netfs_io_request *rreq, + struct folio_queue **fq, + unsigned int *offset, + int *slot, + size_t len, + bool copy) +{ + while (len > 0) { + struct folio *folio; + size_t fsize, overlap; + + if (!*fq) + break; + if (*slot >= folioq_count(*fq)) { + *fq = (*fq)->next; + *slot = 0; + *offset = 0; + continue; + } + + /* Determine how much the subreq overlaps the folio, if at all. */ + fsize = folioq_folio_size(*fq, *slot); + overlap = min(len, fsize - *offset); + + if (overlap > 0 && copy) { + folio = folioq_folio(*fq, *slot); + if (unlikely(test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags))) { + if (!folio_test_private_2(folio)) + folio_start_private_2(folio); + } else { + if (!folio_get_private(folio)) + folio_attach_private(folio, NETFS_FOLIO_COPY_TO_CACHE); + } + trace_netfs_folio(folio, netfs_folio_trace_mark_copy); + } + + len -= overlap; + *offset += overlap; + if (*offset >= fsize) { + *slot += 1; + *offset = 0; + } + } +} + +/* * Perform a read to the pagecache from a series of sources of different types, * slicing up the region to be read according to available cache blocks and * network rsize. */ -static void netfs_read_to_pagecache(struct netfs_io_request *rreq, - struct readahead_control *ractl) +static void netfs_read_to_pagecache(struct netfs_io_request *rreq) { + struct folio_queue *fq = rreq->buffer.tail; unsigned long long start = rreq->start; + unsigned int offset = 0; ssize_t size = rreq->len; - int ret = 0; + int ret = 0, slot = 0; do { struct netfs_io_subrequest *subreq; @@ -288,7 +347,7 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq, break; issue: - slice = netfs_prepare_read_iterator(subreq, ractl); + slice = netfs_prepare_read_iterator(subreq); if (slice < 0) { ret = slice; netfs_cancel_read(subreq, ret); @@ -301,7 +360,15 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq, set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); } + if (fq) { + /* See if the cache indicated this should be cached. */ + bool copy = test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); + + netfs_mark_copy_to_cache(rreq, &fq, &slot, &offset, slice, copy); + } + netfs_issue_read(rreq, subreq); + netfs_maybe_bulk_drop_ra_refs(rreq); if (test_bit(NETFS_RREQ_PAUSE, &rreq->flags)) netfs_wait_for_paused_read(rreq); @@ -339,7 +406,8 @@ void netfs_readahead(struct readahead_control *ractl) { struct netfs_io_request *rreq; struct netfs_inode *ictx = netfs_inode(ractl->mapping->host); - unsigned long long start = readahead_pos(ractl); + ssize_t added; + uoff_t start = readahead_pos(ractl); size_t size = readahead_length(ractl); int ret; @@ -360,11 +428,24 @@ void netfs_readahead(struct readahead_control *ractl) netfs_rreq_expand(rreq, ractl); - rreq->submitted = rreq->start; - if (rolling_buffer_init(&rreq->buffer, rreq->debug_id, ITER_DEST, rreq->gfp) < 0) + /* Load the folios to be read into a bvecq chain. Note that this + * acquires a ref on each folio that we will need to release later - + * but we don't want to do that until after we've started the I/O. + */ + added = rolling_buffer_bulk_load_from_ra(&rreq->buffer, ractl, + rreq->debug_id, rreq->gfp); + if (added < 0) { + ret = added; goto cleanup_free; - netfs_read_to_pagecache(rreq, ractl); + } + __set_bit(NETFS_RREQ_NEED_PUT_RA_REFS, &rreq->flags); + + rreq->submitted = rreq->start + added; + rreq->cleaned_to = rreq->start; + netfs_read_set_unlock_at(rreq); + netfs_read_to_pagecache(rreq); + netfs_maybe_bulk_drop_ra_refs(rreq); return netfs_put_request(rreq, netfs_rreq_trace_put_return); cleanup_free: @@ -387,6 +468,7 @@ static int netfs_create_singular_buffer(struct netfs_io_request *rreq, struct fo if (added < 0) return added; rreq->submitted = rreq->start + added; + rreq->progress_at = added; return 0; } @@ -457,7 +539,7 @@ static int netfs_read_gaps(struct file *file, struct folio *folio) iov_iter_bvec(&rreq->buffer.iter, ITER_DEST, bvec, i, rreq->len); rreq->submitted = rreq->start + flen; - netfs_read_to_pagecache(rreq, NULL); + netfs_read_to_pagecache(rreq); ret = netfs_wait_for_read(rreq); if (ret >= 0) { @@ -532,7 +614,7 @@ int netfs_read_folio(struct file *file, struct folio *folio) if (ret < 0) goto discard; - netfs_read_to_pagecache(rreq, NULL); + netfs_read_to_pagecache(rreq); ret = netfs_wait_for_read(rreq); netfs_put_request(rreq, netfs_rreq_trace_put_return); return ret < 0 ? ret : 0; @@ -689,7 +771,7 @@ retry: if (ret < 0) goto error_put; - netfs_read_to_pagecache(rreq, NULL); + netfs_read_to_pagecache(rreq); ret = netfs_wait_for_read(rreq); netfs_put_request(rreq, netfs_rreq_trace_put_return); if (ret < 0) @@ -754,7 +836,7 @@ int netfs_prefetch_for_write(struct file *file, struct folio *folio, if (ret < 0) goto error_put; - netfs_read_to_pagecache(rreq, NULL); + netfs_read_to_pagecache(rreq); ret = netfs_wait_for_read(rreq); netfs_put_request(rreq, netfs_rreq_trace_put_return); return ret < 0 ? ret : 0; diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index c16fbad286a1..2361277416c7 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -21,7 +21,7 @@ static void netfs_unbuffered_write_done(struct netfs_io_request *wreq) /* Okay, declare that all I/O is complete. */ trace_netfs_rreq(wreq, netfs_rreq_trace_write_done); - if (!wreq->error) + if (wreq->transferred) netfs_update_i_size(ictx, &ictx->inode, wreq->start, wreq->transferred); if (wreq->origin == NETFS_DIO_WRITE && @@ -51,7 +51,7 @@ static void netfs_unbuffered_write_done(struct netfs_io_request *wreq) wreq->iocb->ki_pos += written; if (wreq->iocb->ki_complete) { trace_netfs_rreq(wreq, netfs_rreq_trace_ki_complete); - wreq->iocb->ki_complete(wreq->iocb, wreq->error ?: written); + wreq->iocb->ki_complete(wreq->iocb, written ?: wreq->error); } wreq->iocb = VFS_PTR_POISON; } @@ -95,7 +95,7 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq) { struct netfs_io_subrequest *subreq = NULL; struct netfs_io_stream *stream = &wreq->io_streams[0]; - int ret; + int ret = 0; _enter("%llx", wreq->len); @@ -110,6 +110,11 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq) if (!subreq) { netfs_prepare_write(wreq, stream, wreq->start + wreq->transferred); subreq = stream->construct; + if (!subreq) { + wreq->error = -ENOMEM; + ret = -ENOMEM; + break; + } stream->construct = NULL; } @@ -121,8 +126,14 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq) } iov_iter_truncate(&subreq->io_iter, wreq->len - wreq->transferred); - if (!iov_iter_count(&subreq->io_iter)) + if (!iov_iter_count(&subreq->io_iter)) { + pr_warn("netfs: Unexpected zero-length iterator R=%08x\n", + wreq->debug_id); + __set_bit(NETFS_SREQ_FAILED, &subreq->flags); + netfs_write_subrequest_terminated(subreq, -EIO); + wreq->error = -EIO; break; + } subreq->len = netfs_limit_iter(&subreq->io_iter, 0, stream->sreq_max_len, @@ -139,13 +150,11 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq) if (test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) { retry = true; } else if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) { - ret = subreq->error; - wreq->error = ret; + wreq->error = subreq->error; netfs_see_subrequest(subreq, netfs_sreq_trace_see_failed); subreq = NULL; break; } - ret = 0; if (!retry) { netfs_unbuffered_write_collect(wreq, stream, subreq); @@ -288,11 +297,11 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * ret = -EIOCBQUEUED; } else { ret = netfs_unbuffered_write(wreq); - if (ret < 0) { - _debug("begin = %zd", ret); - } else { + if (wreq->transferred) { iocb->ki_pos += wreq->transferred; - ret = wreq->transferred ?: wreq->error; + ret = wreq->transferred; + } else if (wreq->error) { + ret = wreq->error; } netfs_put_request(wreq, netfs_rreq_trace_put_complete); diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index 420ee7b26580..c79c8e69d60c 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -79,6 +79,7 @@ ssize_t netfs_wait_for_read(struct netfs_io_request *rreq); ssize_t netfs_wait_for_write(struct netfs_io_request *rreq); void netfs_wait_for_paused_read(struct netfs_io_request *rreq); void netfs_wait_for_paused_write(struct netfs_io_request *rreq); +void netfs_wait_for_put_ra_refs(struct netfs_io_request *rreq); /* * objects.c @@ -109,6 +110,8 @@ static inline void netfs_see_subrequest(struct netfs_io_subrequest *subreq, /* * read_collect.c */ +void netfs_cancel_copy_to_cache(struct netfs_io_request *rreq, struct folio *folio); +void netfs_read_set_unlock_at(struct netfs_io_request *rreq); bool netfs_read_collection(struct netfs_io_request *rreq); void netfs_read_collection_worker(struct work_struct *work); void netfs_cancel_read(struct netfs_io_subrequest *subreq, int error); diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index 5d554512ed23..f5c1c463f4ff 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -563,3 +563,22 @@ void netfs_wait_for_paused_write(struct netfs_io_request *rreq) { return netfs_wait_for_pause(rreq, netfs_write_collection); } + +/* + * Wait for the readahead-acquired refs to be put. + */ +void netfs_wait_for_put_ra_refs(struct netfs_io_request *rreq) +{ + DEFINE_WAIT(myself); + + for (;;) { + trace_netfs_rreq(rreq, netfs_rreq_trace_wait_put_ra_refs); + prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE); + if (!test_bit(NETFS_RREQ_NEED_PUT_RA_REFS, &rreq->flags)) + break; + schedule(); + } + + trace_netfs_rreq(rreq, netfs_rreq_trace_waited_put_ra_refs); + finish_wait(&rreq->waitq, &myself); +} diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c index 01461a74642d..7f6a3e912602 100644 --- a/fs/netfs/objects.c +++ b/fs/netfs/objects.c @@ -41,24 +41,32 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, memset(rreq, 0, kmem_cache_size(cache)); INIT_WORK(&rreq->cleanup_work, netfs_free_request); - rreq->gfp = gfp; - rreq->start = start; - rreq->len = len; - rreq->origin = origin; - rreq->netfs_ops = ctx->ops; - rreq->mapping = mapping; - rreq->inode = inode; - rreq->i_size = i_size_read(inode); - rreq->debug_id = atomic_inc_return(&debug_ids); - rreq->wsize = INT_MAX; + rreq->gfp = gfp; + rreq->start = start; + rreq->collected_to = start; + rreq->cleaned_to = start; + rreq->len = len; + rreq->progress_at = 0; + rreq->origin = origin; + rreq->netfs_ops = ctx->ops; + rreq->mapping = mapping; + rreq->inode = inode; + rreq->i_size = i_size_read(inode); + rreq->debug_id = atomic_inc_return(&debug_ids); + rreq->wsize = INT_MAX; rreq->io_streams[0].sreq_max_len = ULONG_MAX; rreq->io_streams[0].sreq_max_segs = 0; spin_lock_init(&rreq->lock); - INIT_LIST_HEAD(&rreq->io_streams[0].subrequests); - INIT_LIST_HEAD(&rreq->io_streams[1].subrequests); init_waitqueue_head(&rreq->waitq); refcount_set(&rreq->ref, 2); + for (int s = 0; s < NR_IO_STREAMS; s++) { + struct netfs_io_stream *stream = &rreq->io_streams[s]; + + INIT_LIST_HEAD(&stream->subrequests); + stream->collected_to = rreq->start; + } + if (origin == NETFS_READAHEAD || origin == NETFS_READPAGE || origin == NETFS_READ_GAPS || diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index 23660a590124..5cf22087d243 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -19,7 +19,6 @@ #define MADE_PROGRESS 0x04 /* Made progress cleaning up a stream or the folio set */ #define BUFFERED 0x08 /* The pagecache needs cleaning up */ #define NEED_RETRY 0x10 /* A front op requests retrying */ -#define COPY_TO_CACHE 0x40 /* Need to copy subrequest to cache */ #define ABANDON_SREQ 0x80 /* Need to abandon untransferred part of subrequest */ /* @@ -35,6 +34,30 @@ static void netfs_clear_unread(struct netfs_io_subrequest *subreq) } /* + * Cancel the copy-to-cache mark on a folio. + */ +void netfs_cancel_copy_to_cache(struct netfs_io_request *rreq, struct folio *folio) +{ + if (!test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { + if (folio_get_private(folio) == NETFS_FOLIO_COPY_TO_CACHE) { + folio_detach_private(folio); + trace_netfs_folio(folio, netfs_folio_trace_cancel_copy); + } else if (netfs_folio_group(folio) == NETFS_FOLIO_COPY_TO_CACHE) { + struct netfs_folio *finfo = netfs_folio_info(folio); + + finfo->netfs_group = NULL; + trace_netfs_folio(folio, netfs_folio_trace_cancel_copy); + } + } else { + // TODO: Use of PG_private_2 is deprecated. + if (folio_test_private_2(folio)) { + folio_end_private_2(folio); + trace_netfs_folio(folio, netfs_folio_trace_cancel_copy); + } + } +} + +/* * Flush, mark and unlock a folio that's now completely read. If we want to * cache the folio, we set the group to NETFS_FOLIO_COPY_TO_CACHE, mark it * dirty and let writeback handle it. @@ -48,37 +71,37 @@ static void netfs_unlock_read_folio(struct netfs_io_request *rreq, if (unlikely(folio_pos(folio) < rreq->abandon_to)) { trace_netfs_folio(folio, netfs_folio_trace_abandon); + netfs_cancel_copy_to_cache(rreq, folio); goto just_unlock; } flush_dcache_folio(folio); folio_mark_uptodate(folio); - if (!test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { - finfo = netfs_folio_info(folio); - if (finfo) { - trace_netfs_folio(folio, netfs_folio_trace_filled_gaps); - if (finfo->netfs_group) - folio_change_private(folio, finfo->netfs_group); - else - folio_detach_private(folio); - kfree(finfo); - } + if (unlikely(test_bit(NETFS_RREQ_CANCEL_CACHING, &rreq->flags))) + netfs_cancel_copy_to_cache(rreq, folio); - if (test_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags)) { - if (!WARN_ON_ONCE(folio_get_private(folio) != NULL)) { - trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); - folio_attach_private(folio, NETFS_FOLIO_COPY_TO_CACHE); - folio_mark_dirty(folio); - } + if (!test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { + if (netfs_folio_group(folio) == NETFS_FOLIO_COPY_TO_CACHE) { + trace_netfs_folio(folio, netfs_folio_trace_sched_copy); + folio_mark_dirty(folio); } else { + finfo = netfs_folio_info(folio); + if (finfo) { + trace_netfs_folio(folio, netfs_folio_trace_filled_gaps); + if (finfo->netfs_group) + folio_change_private(folio, finfo->netfs_group); + else + folio_detach_private(folio); + kfree(finfo); + } trace_netfs_folio(folio, netfs_folio_trace_read_done); } folioq_clear(folioq, slot); } else { // TODO: Use of PG_private_2 is deprecated. - if (test_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags)) + if (folio_test_private_2(folio)) netfs_pgpriv2_copy_to_cache(rreq, folio); } @@ -95,6 +118,35 @@ just_unlock: } /* + * Determine how much to gather before unlocking more folios. + */ +void netfs_read_set_unlock_at(struct netfs_io_request *rreq) +{ + struct folio_queue *folioq = rreq->buffer.tail; + unsigned int slot = rreq->buffer.first_tail_slot; + size_t cleaned_to = rreq->cleaned_to - rreq->start; + size_t progress_at = cleaned_to; + size_t minimum = 256 * 1024; + + while (progress_at < rreq->len) { + if (slot >= folioq_count(folioq)) { + folioq = folioq->next; + if (!folioq) + break; + slot = 0; + } + + progress_at += folioq_folio_size(folioq, slot); + if (progress_at - cleaned_to >= minimum) + break; + slot++; + } + + WRITE_ONCE(rreq->progress_at, progress_at); + trace_netfs_read_progress_at(rreq); +} + +/* * Unlock any folios we've finished with. */ static void netfs_read_unlock_folios(struct netfs_io_request *rreq, @@ -112,30 +164,31 @@ static void netfs_read_unlock_folios(struct netfs_io_request *rreq, if (slot >= folioq_nr_slots(folioq)) { folioq = rolling_buffer_delete_spent(&rreq->buffer); if (!folioq) { - rreq->front_folio_order = 0; + WRITE_ONCE(rreq->progress_at, rreq->len); return; } slot = 0; } + /* We have to wait for readahead refs to have been released before we + * can unlock any folios as the ref-dropper walks i_pages and the only + * thing preventing these folios from being removed is the folio lock. + */ + if (test_bit(NETFS_RREQ_NEED_PUT_RA_REFS, &rreq->flags)) + netfs_wait_for_put_ra_refs(rreq); + for (;;) { struct folio *folio; unsigned long long fpos, fend; - unsigned int order; size_t fsize; - if (*notes & COPY_TO_CACHE) - set_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags); - folio = folioq_folio(folioq, slot); if (WARN_ONCE(!folio_test_locked(folio), "R=%08x: folio %lx is not locked\n", rreq->debug_id, folio->index)) trace_netfs_folio(folio, netfs_folio_trace_not_locked); - order = folioq_folio_order(folioq, slot); - rreq->front_folio_order = order; - fsize = PAGE_SIZE << order; + fsize = folioq_folio_size(folioq, slot); fpos = folio_pos(folio); fend = fpos + fsize; @@ -149,8 +202,6 @@ static void netfs_read_unlock_folios(struct netfs_io_request *rreq, WRITE_ONCE(rreq->cleaned_to, fpos + fsize); *notes |= MADE_PROGRESS; - clear_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags); - /* Clean up the head folioq. If we clear an entire folioq, then * we can get rid of it provided it's not also the tail folioq * being filled by the issuer. @@ -172,6 +223,8 @@ static void netfs_read_unlock_folios(struct netfs_io_request *rreq, rreq->buffer.tail = folioq; done: rreq->buffer.first_tail_slot = slot; + + netfs_read_set_unlock_at(rreq); } /* @@ -232,7 +285,7 @@ reassess: * subreqs. */ if (notes & BUFFERED) { - size_t fsize = PAGE_SIZE << rreq->front_folio_order; + uoff_t unlock_at = rreq->start + rreq->progress_at; /* Clear the tail of a short read. */ if (!(notes & HIT_PENDING) && @@ -248,16 +301,13 @@ reassess: stream->collected_to = front->start + transferred; rreq->collected_to = stream->collected_to; - if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &front->flags)) - notes |= COPY_TO_CACHE; - if (test_bit(NETFS_SREQ_FAILED, &front->flags)) { rreq->abandon_to = front->start + front->len; front->transferred = front->len; transferred = front->len; trace_netfs_rreq(rreq, netfs_rreq_trace_set_abandon); } - if (front->start + transferred >= rreq->cleaned_to + fsize || + if (front->start + transferred >= unlock_at || test_bit(NETFS_SREQ_HIT_EOF, &front->flags)) netfs_read_unlock_folios(rreq, ¬es); } else { @@ -477,20 +527,22 @@ void netfs_read_collection_worker(struct work_struct *work) void netfs_read_subreq_progress(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; - struct netfs_io_stream *stream = &rreq->io_streams[0]; - size_t fsize = PAGE_SIZE << rreq->front_folio_order; - - trace_netfs_sreq(subreq, netfs_sreq_trace_progress); + struct netfs_io_stream *stream = &rreq->io_streams[subreq->stream_nr]; + size_t progress_at = READ_ONCE(rreq->progress_at); + uoff_t update_at = rreq->start + progress_at; + uoff_t transferred_to = subreq->start + subreq->transferred; /* If we are at the head of the queue, wake up the collector, * getting a ref to it if we were the ones to do so. */ - if (subreq->start + subreq->transferred > rreq->cleaned_to + fsize && + if (progress_at < rreq->len && + transferred_to >= update_at && (rreq->origin == NETFS_READAHEAD || rreq->origin == NETFS_READPAGE || rreq->origin == NETFS_READ_FOR_WRITE) && list_is_first(&subreq->rreq_link, &stream->subrequests) ) { + trace_netfs_sreq(subreq, netfs_sreq_trace_progress); __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); netfs_wake_collector(rreq); } diff --git a/fs/netfs/read_pgpriv2.c b/fs/netfs/read_pgpriv2.c index c31190993b76..a4b7bb88cbdb 100644 --- a/fs/netfs/read_pgpriv2.c +++ b/fs/netfs/read_pgpriv2.c @@ -54,8 +54,8 @@ static void netfs_pgpriv2_copy_folio(struct netfs_io_request *creq, struct folio /* Attach the folio to the rolling buffer. */ if (rolling_buffer_append(&creq->buffer, folio, 0, creq->gfp) < 0) { + set_bit(NETFS_RREQ_CANCEL_CACHING, &creq->flags); folio_end_private_2(folio); - clear_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &creq->flags); return; } @@ -122,13 +122,14 @@ cancel_put: netfs_put_failed_request(creq); cancel: rreq->copy_to_cache = ERR_PTR(-ENOBUFS); - clear_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags); + set_bit(NETFS_RREQ_CANCEL_CACHING, &rreq->flags); return ERR_PTR(-ENOBUFS); } /* * [DEPRECATED] Mark page as requiring copy-to-cache using PG_private_2 and add - * it to the copy write request. + * it to the copy write request. PG_private_2 should already be set on the + * folio. */ void netfs_pgpriv2_copy_to_cache(struct netfs_io_request *rreq, struct folio *folio) { @@ -136,11 +137,13 @@ void netfs_pgpriv2_copy_to_cache(struct netfs_io_request *rreq, struct folio *fo if (!creq) creq = netfs_pgpriv2_begin_copy_to_cache(rreq, folio); - if (IS_ERR(creq)) + if (IS_ERR(creq)) { + set_bit(NETFS_RREQ_CANCEL_CACHING, &rreq->flags); + netfs_cancel_copy_to_cache(rreq, folio); return; + } - trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); - folio_start_private_2(folio); + trace_netfs_folio(folio, netfs_folio_trace_pgpriv2_copy); netfs_pgpriv2_copy_folio(creq, folio); } diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c index 2b42758e01ec..4f6a36c6e214 100644 --- a/fs/netfs/read_retry.c +++ b/fs/netfs/read_retry.c @@ -292,11 +292,22 @@ void netfs_unlock_abandoned_read_pages(struct netfs_io_request *rreq) { struct folio_queue *p; + /* We have to wait for readahead refs to have been released before we + * can unlock any folios as the ref-dropper walks i_pages and the only + * thing preventing these folios from being removed is the folio lock. + */ + if (test_bit(NETFS_RREQ_NEED_PUT_RA_REFS, &rreq->flags)) + netfs_wait_for_put_ra_refs(rreq); + for (p = rreq->buffer.tail; p; p = p->next) { for (int slot = 0; slot < folioq_count(p); slot++) { struct folio *folio = folioq_folio(p, slot); - if (folio && !folioq_is_marked2(p, slot)) { + if (!folio) + continue; + netfs_cancel_copy_to_cache(rreq, folio); + + if (!folioq_is_marked2(p, slot)) { if (folio == rreq->no_unlock_folio && test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) { diff --git a/fs/netfs/read_single.c b/fs/netfs/read_single.c index 8833550d2eb6..de67ac41548d 100644 --- a/fs/netfs/read_single.c +++ b/fs/netfs/read_single.c @@ -170,6 +170,8 @@ ssize_t netfs_read_single(struct inode *inode, struct file *file, struct iov_ite if (IS_ERR(rreq)) return PTR_ERR(rreq); + rreq->progress_at = rreq->len; + ret = netfs_single_begin_cache_read(rreq, ictx); if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) goto cleanup_free; diff --git a/fs/netfs/rolling_buffer.c b/fs/netfs/rolling_buffer.c index 8c0026836f9c..424e77a9a109 100644 --- a/fs/netfs/rolling_buffer.c +++ b/fs/netfs/rolling_buffer.c @@ -115,42 +115,65 @@ int rolling_buffer_make_space(struct rolling_buffer *roll, gfp_t gfp) } /* - * Decant the list of folios to read into a rolling buffer. + * Decant the entire list of folios to read into a rolling buffer. */ -ssize_t rolling_buffer_load_from_ra(struct rolling_buffer *roll, - struct readahead_control *ractl, - struct folio_batch *put_batch) +ssize_t rolling_buffer_bulk_load_from_ra(struct rolling_buffer *roll, + struct readahead_control *ractl, + unsigned int rreq_id, gfp_t gfp) { struct folio_queue *fq; - struct page **vec; - int nr, ix, to; - ssize_t size = 0; + ssize_t loaded = 0; - if (rolling_buffer_make_space(roll, GFP_KERNEL) < 0) - return -ENOMEM; + while (ractl->_nr_pages - ractl->_batch_count > 0) { + unsigned int nr; - fq = roll->head; - vec = (struct page **)fq->vec.folios; - nr = __readahead_batch(ractl, vec + folio_batch_count(&fq->vec), - folio_batch_space(&fq->vec)); - ix = fq->vec.nr; - to = ix + nr; - fq->vec.nr = to; - for (; ix < to; ix++) { - struct folio *folio = folioq_folio(fq, ix); - unsigned int order = folio_order(folio); - - fq->orders[ix] = order; - size += PAGE_SIZE << order; - trace_netfs_folio(folio, netfs_folio_trace_read); - if (!folio_batch_add(put_batch, folio)) - folio_batch_release(put_batch); + /* Allocate a folioq to put some folios into and attach it to + * the rolling buffer. + */ + fq = netfs_folioq_alloc(rreq_id, gfp, + netfs_trace_folioq_make_space); + if (!fq) + goto nomem_unlock; + fq->prev = roll->head; + if (!roll->tail) + roll->tail = fq; + else + roll->head->next = fq; + roll->head = fq; + + /* Get a batch of folios and note their orders. */ + nr = __readahead_batch(ractl, (struct page **)fq->vec.folios, + folioq_nr_slots(fq)); + if (WARN_ON_ONCE(!nr)) + break; + fq->vec.nr = nr; + + for (int slot = 0; slot < nr; slot++) { + struct folio *folio = folioq_folio(fq, slot); + unsigned int order; + + order = folio_order(folio); + fq->orders[slot] = order; + loaded += PAGE_SIZE << order; + trace_netfs_folio(folio, netfs_folio_trace_read); + } } - WRITE_ONCE(roll->iter.count, roll->iter.count + size); - /* Store the counter after setting the slot. */ - smp_store_release(&roll->next_head_slot, to); - return size; + WRITE_ONCE(roll->iter.count, loaded); + iov_iter_folio_queue(&roll->iter, ITER_DEST, roll->tail, 0, 0, loaded); + return loaded; + +nomem_unlock: + for (fq = roll->tail; fq; fq = fq->next) { + for (int slot = 0; slot < folioq_count(fq); slot++) { + folio_unlock(fq->vec.folios[slot]); + folioq_mark(fq, slot); + } + } + rolling_buffer_clear(roll); + roll->head = NULL; + roll->tail = NULL; + return -ENOMEM; } /* diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 2d9cfcd43658..851f6f93ad45 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -170,6 +170,8 @@ void netfs_prepare_write(struct netfs_io_request *wreq, rolling_buffer_make_space(&wreq->buffer, wreq->gfp); subreq = netfs_alloc_subrequest(wreq); + if (!subreq) + return; subreq->source = stream->source; subreq->start = start; subreq->stream_nr = stream->stream_nr; diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index a47c90f40422..b6e0c543e028 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -358,7 +358,7 @@ int nfsd_nl_expkey_get_reqs_dumpit(struct sk_buff *skb, goto out_unlock; } - items = kcalloc(cnt, sizeof(*items), GFP_KERNEL); + items = kzalloc_objs(*items, cnt); seqnos = kcalloc(cnt, sizeof(*seqnos), GFP_KERNEL); if (!items || !seqnos) { ret = -ENOMEM; @@ -685,7 +685,7 @@ int nfsd_nl_svc_export_get_reqs_dumpit(struct sk_buff *skb, goto out_unlock; } - items = kcalloc(cnt, sizeof(*items), GFP_KERNEL); + items = kzalloc_objs(*items, cnt); seqnos = kcalloc(cnt, sizeof(*seqnos), GFP_KERNEL); pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); if (!items || !seqnos || !pathbuf) { @@ -786,8 +786,7 @@ static int nfsd_nl_parse_fslocations(struct nlattr *attr, if (!count) return 0; - fsloc->locations = kcalloc(count, sizeof(struct nfsd4_fs_location), - GFP_KERNEL); + fsloc->locations = kzalloc_objs(struct nfsd4_fs_location, count); if (!fsloc->locations) return -ENOMEM; @@ -1006,7 +1005,8 @@ static int nfsd_nl_parse_one_export(struct cache_detail *cd, goto out_uuid; err = 0; - nfsd4_setup_layout_type(&exp); + if (exp.ex_flags & NFSEXP_PNFS) + nfsd4_setup_layout_type(&exp); } expp = svc_export_lookup(&exp); diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index a901bbe67e03..19dc337502ca 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -1981,12 +1981,12 @@ int nfsd_net_cb_init(struct nfsd_net *nn) { struct nfsd_net_cb *cb; - cb = kzalloc(sizeof(*cb), GFP_KERNEL); + cb = kzalloc_obj(*cb); if (!cb) return -ENOMEM; cb->version4.counts = kzalloc_objs(unsigned int, - ARRAY_SIZE(nfs4_cb_procedures), GFP_KERNEL); + ARRAY_SIZE(nfs4_cb_procedures)); if (!cb->version4.counts) { kfree(cb); return -ENOMEM; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 18e17232cf94..9c4adf3110ae 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1341,7 +1341,7 @@ alloc_init_dir_deleg(struct nfs4_client *clp, struct nfs4_file *fp) return NULL; } - ncn->ncn_nf = kcalloc(NOTIFY4_EVENT_QUEUE_SIZE, sizeof(*ncn->ncn_nf), GFP_KERNEL); + ncn->ncn_nf = kzalloc_objs(*ncn->ncn_nf, NOTIFY4_EVENT_QUEUE_SIZE); if (!ncn->ncn_nf) { nfs4_put_stid(&dp->dl_stid); return NULL; @@ -10419,8 +10419,9 @@ alloc_nfsd_notify_event(u32 mask, const struct qstr *q, struct dentry *dentry, newnamelen = newname.name.len; } - ne = kmalloc(struct_size(ne, ne_name, q->len + 1 + - (newnamelen ? newnamelen + 1 : 0)), GFP_NOFS); + ne = kmalloc_flex(*ne, ne_name, + q->len + 1 + (newnamelen ? newnamelen + 1 : 0), + GFP_NOFS); if (!ne) goto out; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index adb032b7311a..5abb2d4274c9 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1647,7 +1647,7 @@ static int nfsd_nl_fh_key_set(const struct nlattr *attr, struct nfsd_net *nn) k1 = get_unaligned_le64(nla_data(attr) + 8); if (!fh_key) { - fh_key = kmalloc(sizeof(siphash_key_t), GFP_KERNEL); + fh_key = kmalloc_obj(siphash_key_t); if (!fh_key) { trace_nfsd_ctl_fh_key_set(false, -ENOMEM); return -ENOMEM; diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index 60264833bb63..c949ff765075 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -1737,8 +1737,8 @@ static struct attr_def *ntfs_attr_find_in_attrdef(const struct ntfs_volume *vol, struct attr_def *ad; WARN_ON(!type); - for (ad = vol->attrdef; (u8 *)ad - (u8 *)vol->attrdef < - vol->attrdef_size && ad->type; ++ad) { + for (ad = vol->attrdef; (u8 *)ad - (u8 *)vol->attrdef <= + vol->attrdef_size - (s32)sizeof(*ad) && ad->type; ++ad) { /* We have not found it yet, carry on searching. */ if (likely(le32_to_cpu(ad->type) < le32_to_cpu(type))) continue; @@ -2500,7 +2500,7 @@ int ntfs_resident_attr_record_add(struct ntfs_inode *ni, __le32 type, return offset; put_err_out: ntfs_attr_put_search_ctx(ctx); - return -EIO; + return err; } /* @@ -2639,7 +2639,7 @@ static int ntfs_non_resident_attr_record_add(struct ntfs_inode *ni, __le32 type, return offset; put_err_out: ntfs_attr_put_search_ctx(ctx); - return -1; + return err; } /* @@ -2917,7 +2917,7 @@ retry: attr_ni = NULL; /* Allocate new extent. */ - err = ntfs_mft_record_alloc(ni->vol, 0, &attr_ni, ni, NULL); + err = ntfs_mft_record_alloc(ni->vol, 0, &attr_ni, ni, NULL, -1); if (err) { ntfs_error(sb, "Failed to allocate extent record"); goto err_out; @@ -3550,7 +3550,7 @@ int ntfs_attr_record_move_away(struct ntfs_attr_search_ctx *ctx, int extra) * new extent and move attribute to it. */ ni = NULL; - err = ntfs_mft_record_alloc(base_ni->vol, 0, &ni, base_ni, NULL); + err = ntfs_mft_record_alloc(base_ni->vol, 0, &ni, base_ni, NULL, -1); if (err) { ntfs_error(sb, "Couldn't allocate MFT record, err : %d", err); return err; @@ -3574,7 +3574,8 @@ int ntfs_attr_record_move_away(struct ntfs_attr_search_ctx *ctx, int extra) * update allocated and compressed size. */ static int ntfs_attr_update_meta(struct attr_record *a, struct ntfs_inode *ni, - struct mft_record *m, struct ntfs_attr_search_ctx *ctx) + struct mft_record *m, struct ntfs_attr_search_ctx *ctx, + struct ntfs_inode *locked_ni, bool defer_attrlist) { int sparse, err = 0; struct ntfs_inode *base_ni; @@ -3610,6 +3611,8 @@ static int ntfs_attr_update_meta(struct attr_record *a, struct ntfs_inode *ni, le16_to_cpu(a->data.non_resident.mapping_pairs_offset) == 8) && !(le32_to_cpu(m->bytes_allocated) - le32_to_cpu(m->bytes_in_use))) { + if (defer_attrlist) + return -ENOSPC; if (!NInoAttrList(base_ni)) { err = ntfs_inode_add_attrlist(base_ni); if (err) @@ -3623,7 +3626,7 @@ static int ntfs_attr_update_meta(struct attr_record *a, struct ntfs_inode *ni, goto out; } - err = ntfs_attrlist_update(base_ni); + err = ntfs_attrlist_update_locked(base_ni, locked_ni); if (err) goto out; err = -EAGAIN; @@ -3703,6 +3706,8 @@ out: * ntfs_attr_update_mapping_pairs - update mapping pairs for ntfs attribute * @ni: non-resident ntfs inode for which we need update * @from_vcn: update runlist starting this VCN + * @locked_ni: inode whose runlist write lock is already held + * @defer_attrlist: return -ENOSPC instead of updating an attribute list * * Build mapping pairs from @na->rl and write them to the disk. Also, this * function updates sparse bit, allocated and compressed size (allocates/frees @@ -3712,7 +3717,10 @@ out: * call to this function. Vice-versa @na->compressed_size will be calculated and * set to correct value during this function. */ -int ntfs_attr_update_mapping_pairs(struct ntfs_inode *ni, s64 from_vcn) +static int __ntfs_attr_update_mapping_pairs(struct ntfs_inode *ni, + s64 from_vcn, + struct ntfs_inode *locked_ni, + bool defer_attrlist) { struct ntfs_attr_search_ctx *ctx; struct ntfs_inode *base_ni; @@ -3804,7 +3812,8 @@ retry: continue; } - err = ntfs_attr_update_meta(a, ni, m, ctx); + err = ntfs_attr_update_meta(a, ni, m, ctx, locked_ni, + defer_attrlist); if (err < 0) { if (err == -EAGAIN) { ntfs_attr_put_search_ctx(ctx); @@ -3844,18 +3853,28 @@ retry: */ if (ni->type == AT_ATTRIBUTE_LIST) { ntfs_attr_put_search_ctx(ctx); - if (ntfs_inode_free_space(base_ni, mp_size - - cur_max_mp_size)) { - ntfs_debug("Attribute list is too big. Defragment the volume\n"); - return -ENOSPC; + ctx = NULL; + if (locked_ni == ni || defer_attrlist) { + err = -ENOSPC; + goto put_err_out; } - if (ntfs_attrlist_update(base_ni)) - return -EIO; + err = ntfs_inode_free_space(base_ni, mp_size - + cur_max_mp_size); + if (err) + return err; + err = ntfs_attrlist_update_locked( + base_ni, locked_ni); + if (err) + return err; goto retry; } /* Add attribute list if it isn't present, and retry. */ if (!NInoAttrList(base_ni)) { + if (defer_attrlist) { + err = -ENOSPC; + goto put_err_out; + } ntfs_attr_put_search_ctx(ctx); if (ntfs_inode_add_attrlist(base_ni)) { ntfs_error(sb, "Can not add attrlist"); @@ -3883,13 +3902,21 @@ retry: } } + if (defer_attrlist && + (ctx->ntfs_ino->nr_extents == -1 || + NInoAttrList(ctx->ntfs_ino)) && + ctx->attr->type != AT_ATTRIBUTE_LIST) { + err = -ENOSPC; + goto put_err_out; + } + /* Update lowest vcn. */ a->data.non_resident.lowest_vcn = cpu_to_le64(stop_vcn); mark_mft_record_dirty(ctx->ntfs_ino); if ((ctx->ntfs_ino->nr_extents == -1 || NInoAttrList(ctx->ntfs_ino)) && ctx->attr->type != AT_ATTRIBUTE_LIST) { ctx->al_entry->lowest_vcn = cpu_to_le64(stop_vcn); - err = ntfs_attrlist_update(base_ni); + err = ntfs_attrlist_update_locked(base_ni, locked_ni); if (err) goto put_err_out; } @@ -3976,7 +4003,10 @@ retry: unsigned int de_cnt = 0; /* Allocate new mft record. */ - err = ntfs_mft_record_alloc(ni->vol, 0, &ext_ni, base_ni, NULL); + err = ntfs_mft_record_alloc(ni->vol, 0, &ext_ni, base_ni, NULL, + base_ni->mft_no == FILE_MFT && + ni->type == AT_DATA && + ni->name == AT_UNNAMED ? stop_vcn : -1); if (err) { ntfs_error(sb, "Failed to allocate extent record"); goto put_err_out; @@ -4061,6 +4091,19 @@ put_err_out: return err; } +int ntfs_attr_update_mapping_pairs_locked(struct ntfs_inode *ni, + s64 from_vcn, + struct ntfs_inode *locked_ni) +{ + return __ntfs_attr_update_mapping_pairs(ni, from_vcn, locked_ni, + false); +} + +int ntfs_attr_update_mapping_pairs(struct ntfs_inode *ni, s64 from_vcn) +{ + return ntfs_attr_update_mapping_pairs_locked(ni, from_vcn, NULL); +} + /* * ntfs_attr_make_resident - convert a non-resident to a resident attribute * @ni: open ntfs attribute to make resident @@ -4194,7 +4237,9 @@ static int ntfs_attr_make_resident(struct ntfs_inode *ni, struct ntfs_attr_searc * * Reduce the size of a non-resident, open ntfs attribute @na to @newsize bytes. */ -static int ntfs_non_resident_attr_shrink(struct ntfs_inode *ni, const s64 newsize) +static int ntfs_non_resident_attr_shrink(struct ntfs_inode *ni, + const s64 newsize, + struct ntfs_inode *locked_ni) { struct ntfs_volume *vol; struct ntfs_attr_search_ctx *ctx; @@ -4202,6 +4247,7 @@ static int ntfs_non_resident_attr_shrink(struct ntfs_inode *ni, const s64 newsiz s64 nr_freed_clusters; int err; struct ntfs_inode *base_ni; + bool runlist_locked = locked_ni == ni; ntfs_debug("Inode 0x%llx attr 0x%x new size %lld\n", (unsigned long long)ni->mft_no, ni->type, (long long)newsize); @@ -4247,18 +4293,24 @@ static int ntfs_non_resident_attr_shrink(struct ntfs_inode *ni, const s64 newsiz * clusters if there is a change. */ if (ntfs_bytes_to_cluster(vol, ni->allocated_size) != first_free_vcn) { - struct ntfs_attr_search_ctx *ctx; + /* + * ntfs_cluster_free() and ntfs_rl_truncate_nolock() + * both require this lock. + */ + if (!runlist_locked) + down_write(&ni->runlist.lock); err = ntfs_attr_map_whole_runlist(ni); if (err) { ntfs_debug("Eeek! ntfs_attr_map_whole_runlist failed.\n"); - return err; + goto unlock_runlist; } ctx = ntfs_attr_get_search_ctx(ni, NULL); if (!ctx) { ntfs_error(vol->sb, "%s: Failed to get search context", __func__); - return -ENOMEM; + err = -ENOMEM; + goto unlock_runlist; } /* Deallocate all clusters starting with the first free one. */ @@ -4266,7 +4318,8 @@ static int ntfs_non_resident_attr_shrink(struct ntfs_inode *ni, const s64 newsiz if (nr_freed_clusters < 0) { ntfs_debug("Eeek! Freeing of clusters failed. Aborting...\n"); ntfs_attr_put_search_ctx(ctx); - return (int)nr_freed_clusters; + err = (int)nr_freed_clusters; + goto unlock_runlist; } ntfs_attr_put_search_ctx(ctx); @@ -4279,7 +4332,8 @@ static int ntfs_non_resident_attr_shrink(struct ntfs_inode *ni, const s64 newsiz kvfree(ni->runlist.rl); ni->runlist.rl = NULL; ntfs_error(vol->sb, "Eeek! Run list truncation failed.\n"); - return -EIO; + err = -EIO; + goto unlock_runlist; } /* Prepare to mapping pairs update. */ @@ -4295,11 +4349,13 @@ static int ntfs_non_resident_attr_shrink(struct ntfs_inode *ni, const s64 newsiz VFS_I(base_ni)->i_blocks = ni->allocated_size >> 9; /* Write mapping pairs for new runlist. */ - err = ntfs_attr_update_mapping_pairs(ni, 0 /*first_free_vcn*/); + err = ntfs_attr_update_mapping_pairs_locked(ni, 0, ni); if (err) { ntfs_debug("Eeek! Mapping pairs update failed. Leaving inconstant metadata. Run chkdsk.\n"); - return err; + goto unlock_runlist; } + if (!runlist_locked) + up_write(&ni->runlist.lock); } /* Get the first attribute record. */ @@ -4341,7 +4397,11 @@ static int ntfs_non_resident_attr_shrink(struct ntfs_inode *ni, const s64 newsiz /* If the attribute now has zero size, make it resident. */ if (!newsize && !NInoEncrypted(ni) && !NInoCompressed(ni)) { + if (!runlist_locked) + down_write(&ni->runlist.lock); err = ntfs_attr_make_resident(ni, ctx); + if (!runlist_locked) + up_write(&ni->runlist.lock); if (err) { /* If couldn't make resident, just continue. */ if (err != -EPERM) @@ -4358,6 +4418,11 @@ static int ntfs_non_resident_attr_shrink(struct ntfs_inode *ni, const s64 newsiz put_err_out: ntfs_attr_put_search_ctx(ctx); return err; + +unlock_runlist: + if (!runlist_locked) + up_write(&ni->runlist.lock); + return err; } /* @@ -4366,13 +4431,14 @@ put_err_out: * @prealloc_size: preallocation size (in bytes) to which to expand the attribute * @newsize: new size (in bytes) to which to expand the attribute * @holes: how to create a hole if expanding - * @need_lock: whether mrec lock is needed or not + * @locked_ni: inode whose runlist lock is already held * * Expand the size of a non-resident, open ntfs attribute @na to @newsize bytes, * by allocating new clusters. */ static int ntfs_non_resident_attr_expand(struct ntfs_inode *ni, const s64 newsize, - const s64 prealloc_size, unsigned int holes, bool need_lock) + const s64 prealloc_size, unsigned int holes, + struct ntfs_inode *locked_ni) { s64 lcn_seek_from; s64 first_free_vcn; @@ -4519,13 +4585,39 @@ static int ntfs_non_resident_attr_expand(struct ntfs_inode *ni, const s64 newsiz ntfs_bytes_to_cluster(vol, ni->allocated_size), first_free_vcn - ntfs_bytes_to_cluster(vol, ni->allocated_size), - lcn_seek_from, DATA_ZONE, false, false, false); + lcn_seek_from, DATA_ZONE, false, + ni->type == AT_ATTRIBUTE_LIST, false); if (IS_ERR(rl)) { ntfs_debug("Cluster allocation failed (%lld)", (long long)first_free_vcn - ntfs_bytes_to_cluster(vol, ni->allocated_size)); return PTR_ERR(rl); } + /* + * A contiguous ATTRIBUTE_LIST allocation keeps its mapping + * pairs small enough to fit in the base MFT record. The + * allocator can return a short run when contiguity was + * requested, so discard it and retry normally if necessary. + */ + if (ni->type == AT_ATTRIBUTE_LIST && + (rl->vcn != ntfs_bytes_to_cluster(vol, + ni->allocated_size) || + rl->length != first_free_vcn - + ntfs_bytes_to_cluster(vol, ni->allocated_size) || + rl[1].length)) { + ntfs_cluster_free_from_rl(vol, rl); + kvfree(rl); + rl = ntfs_cluster_alloc(vol, + ntfs_bytes_to_cluster(vol, + ni->allocated_size), + first_free_vcn - + ntfs_bytes_to_cluster(vol, + ni->allocated_size), + lcn_seek_from, DATA_ZONE, false, + false, false); + if (IS_ERR(rl)) + return PTR_ERR(rl); + } } if (!NInoCompressed(ni)) { @@ -4544,7 +4636,8 @@ static int ntfs_non_resident_attr_expand(struct ntfs_inode *ni, const s64 newsiz /* Prepare to mapping pairs update. */ ni->allocated_size = ntfs_cluster_to_bytes(vol, first_free_vcn); - err = ntfs_attr_update_mapping_pairs(ni, 0); + err = ntfs_attr_update_mapping_pairs_locked( + ni, 0, locked_ni); if (err) { ntfs_debug("Mapping pairs update failed"); goto rollback; @@ -4588,11 +4681,11 @@ rollback: ntfs_debug("Leaking clusters"); /* Now, truncate the runlist itself. */ - if (need_lock) + if (ni != locked_ni) down_write(&ni->runlist.lock); err2 = ntfs_rl_truncate_nolock(vol, &ni->runlist, ntfs_bytes_to_cluster(vol, org_alloc_size)); - if (need_lock) + if (ni != locked_ni) up_write(&ni->runlist.lock); if (err2) { /* @@ -4606,11 +4699,11 @@ rollback: /* Prepare to mapping pairs update. */ ni->allocated_size = org_alloc_size; /* Restore mapping pairs. */ - if (need_lock) + if (ni != locked_ni) down_read(&ni->runlist.lock); - if (ntfs_attr_update_mapping_pairs(ni, 0)) + if (__ntfs_attr_update_mapping_pairs(ni, 0, locked_ni, true)) ntfs_error(sb, "Failed to restore old mapping pairs"); - if (need_lock) + if (ni != locked_ni) up_read(&ni->runlist.lock); if (NInoSparse(ni) || NInoCompressed(ni)) { @@ -4715,7 +4808,8 @@ attr_resize_again: mark_mft_record_dirty(ctx->ntfs_ino); ntfs_attr_put_search_ctx(ctx); /* Resize non-resident attribute */ - return ntfs_non_resident_attr_expand(attr_ni, newsize, prealloc_size, holes, true); + return ntfs_non_resident_attr_expand( + attr_ni, newsize, prealloc_size, holes, NULL); } else if (err != -ENOSPC && err != -EPERM) { ntfs_error(sb, "Failed to make attribute non-resident"); goto put_err_out; @@ -4836,7 +4930,7 @@ attr_resize_again: } /* Allocate new mft record. */ - err = ntfs_mft_record_alloc(base_ni->vol, 0, &ext_ni, base_ni, NULL); + err = ntfs_mft_record_alloc(base_ni->vol, 0, &ext_ni, base_ni, NULL, -1); if (err) { ntfs_error(sb, "Couldn't allocate MFT record"); goto put_err_out; @@ -4890,13 +4984,14 @@ int __ntfs_attr_truncate_vfs(struct ntfs_inode *ni, const s64 newsize, if (NInoNonResident(ni)) { if (newsize > i_size) { down_write(&ni->runlist.lock); - err = ntfs_non_resident_attr_expand(ni, newsize, 0, - NVolDisableSparse(ni->vol) ? - HOLES_NO : HOLES_OK, - false); + err = ntfs_non_resident_attr_expand( + ni, newsize, 0, + NVolDisableSparse(ni->vol) ? + HOLES_NO : HOLES_OK, ni); up_write(&ni->runlist.lock); } else - err = ntfs_non_resident_attr_shrink(ni, newsize); + err = ntfs_non_resident_attr_shrink( + ni, newsize, NULL); } else err = ntfs_resident_attr_resize(ni, newsize, 0, NVolDisableSparse(ni->vol) ? @@ -4905,7 +5000,9 @@ int __ntfs_attr_truncate_vfs(struct ntfs_inode *ni, const s64 newsize, return err; } -int ntfs_attr_expand(struct ntfs_inode *ni, const s64 newsize, const s64 prealloc_size) +int ntfs_attr_expand_locked(struct ntfs_inode *ni, const s64 newsize, + const s64 prealloc_size, + struct ntfs_inode *locked_ni) { int err = 0; @@ -4918,7 +5015,8 @@ int ntfs_attr_expand(struct ntfs_inode *ni, const s64 newsize, const s64 preallo ntfs_debug("Entering for inode 0x%llx, attr 0x%x, size %lld\n", (unsigned long long)ni->mft_no, ni->type, newsize); - if (ni->data_size == newsize) { + if (ni->data_size == newsize && + (!prealloc_size || prealloc_size <= ni->allocated_size)) { ntfs_debug("Size is already ok\n"); return 0; } @@ -4933,10 +5031,11 @@ int ntfs_attr_expand(struct ntfs_inode *ni, const s64 newsize, const s64 preallo } if (NInoNonResident(ni)) { - if (newsize > ni->data_size) - err = ntfs_non_resident_attr_expand(ni, newsize, prealloc_size, - NVolDisableSparse(ni->vol) ? - HOLES_NO : HOLES_OK, true); + if (newsize > ni->data_size || prealloc_size > ni->allocated_size) + err = ntfs_non_resident_attr_expand( + ni, newsize, prealloc_size, + NVolDisableSparse(ni->vol) ? + HOLES_NO : HOLES_OK, locked_ni); } else err = ntfs_resident_attr_resize(ni, newsize, prealloc_size, NVolDisableSparse(ni->vol) ? @@ -4947,6 +5046,12 @@ int ntfs_attr_expand(struct ntfs_inode *ni, const s64 newsize, const s64 preallo return err; } +int ntfs_attr_expand(struct ntfs_inode *ni, const s64 newsize, + const s64 prealloc_size) +{ + return ntfs_attr_expand_locked(ni, newsize, prealloc_size, NULL); +} + /* * ntfs_attr_truncate_i - resize an ntfs attribute * @ni: open ntfs inode to resize @@ -4959,7 +5064,9 @@ int ntfs_attr_expand(struct ntfs_inode *ni, const s64 newsize, const s64 preallo * newly allocated space is marked as not initialised and no real allocation * on disk is performed. */ -int ntfs_attr_truncate_i(struct ntfs_inode *ni, const s64 newsize, unsigned int holes) +int ntfs_attr_truncate_i_locked(struct ntfs_inode *ni, const s64 newsize, + unsigned int holes, + struct ntfs_inode *locked_ni) { int err; @@ -4993,15 +5100,23 @@ int ntfs_attr_truncate_i(struct ntfs_inode *ni, const s64 newsize, unsigned int if (NInoNonResident(ni)) { if (newsize > ni->data_size) - err = ntfs_non_resident_attr_expand(ni, newsize, 0, holes, true); + err = ntfs_non_resident_attr_expand( + ni, newsize, 0, holes, locked_ni); else - err = ntfs_non_resident_attr_shrink(ni, newsize); + err = ntfs_non_resident_attr_shrink( + ni, newsize, locked_ni); } else err = ntfs_resident_attr_resize(ni, newsize, 0, holes); ntfs_debug("Return status %d\n", err); return err; } +int ntfs_attr_truncate_i(struct ntfs_inode *ni, const s64 newsize, + unsigned int holes) +{ + return ntfs_attr_truncate_i_locked(ni, newsize, holes, NULL); +} + /* * Resize an attribute, creating a hole if relevant */ @@ -5019,10 +5134,11 @@ int ntfs_attr_map_cluster(struct ntfs_inode *ni, s64 vcn_start, s64 *lcn_start, struct ntfs_volume *vol = ni->vol; struct ntfs_attr_search_ctx *ctx; struct runlist_element *rl, *rlc; + struct runlist_element *old_rl = NULL; s64 vcn = vcn_start, lcn, clu_count; s64 lcn_seek_from = -1; int err = 0; - size_t new_rl_count; + size_t new_rl_count, old_rl_count; err = ntfs_attr_map_whole_runlist(ni); if (err) @@ -5115,6 +5231,19 @@ int ntfs_attr_map_cluster(struct ntfs_inode *ni, s64 vcn_start, s64 *lcn_start, WARN_ON(rlc->vcn != vcn); lcn = rlc->lcn; clu_count = rlc->length; + old_rl_count = ni->runlist.count; + old_rl = kmemdup(ni->runlist.rl, + old_rl_count * sizeof(*old_rl), GFP_NOFS); + if (!old_rl) { + err = -ENOMEM; + if (ntfs_cluster_free_from_rl(vol, rlc)) { + ntfs_error(vol->sb, + "Failed to free cluster allocation after runlist backup failure."); + NVolSetErrors(vol); + } + kvfree(rlc); + goto out; + } rl = ntfs_runlists_merge(&ni->runlist, rlc, 0, &new_rl_count); if (IS_ERR(rl)) { @@ -5138,15 +5267,32 @@ int ntfs_attr_map_cluster(struct ntfs_inode *ni, s64 vcn_start, s64 *lcn_start, if (update_mp) { ntfs_attr_reinit_search_ctx(ctx); - err = ntfs_attr_update_mapping_pairs(ni, 0); + err = ntfs_attr_update_mapping_pairs_locked(ni, 0, ni); if (err) { int err2; err2 = ntfs_cluster_free(ni, vcn, clu_count, ctx); - if (err2 < 0) + if (err2 < 0 || err2 != clu_count) { ntfs_error(vol->sb, - "Failed to free cluster allocation. Leaving inconstant metadata.\n"); - goto out; + "Failed to free cluster allocation. Leaving inconsistent metadata.\n"); + NVolSetErrors(vol); + goto out; + } + + /* + * Restore the runlist before repairing the on-disk + * mapping pairs. + */ + kvfree(ni->runlist.rl); + ni->runlist.rl = old_rl; + ni->runlist.count = old_rl_count; + old_rl = NULL; + if (ntfs_attr_update_mapping_pairs_locked( + ni, 0, ni)) { + ntfs_error(vol->sb, + "Failed to restore mapping pairs after allocation rollback.\n"); + NVolSetErrors(vol); + } } } else { VFS_I(ni)->i_blocks += clu_count << (vol->cluster_size_bits - 9); @@ -5158,6 +5304,7 @@ int ntfs_attr_map_cluster(struct ntfs_inode *ni, s64 vcn_start, s64 *lcn_start, *lcn_count = clu_count; *balloc = true; out: + kvfree(old_rl); ntfs_attr_put_search_ctx(ctx); return err; } @@ -5401,7 +5548,7 @@ int ntfs_non_resident_attr_insert_range(struct ntfs_inode *ni, s64 start_vcn, s6 ni->data_size += ntfs_cluster_to_bytes(vol, len); if (ntfs_cluster_to_bytes(vol, start_vcn) < ni->initialized_size) ni->initialized_size += ntfs_cluster_to_bytes(vol, len); - ret = ntfs_attr_update_mapping_pairs(ni, 0); + ret = ntfs_attr_update_mapping_pairs_locked(ni, 0, ni); up_write(&ni->runlist.lock); if (ret) return ret; @@ -5486,7 +5633,7 @@ int ntfs_non_resident_attr_collapse_range(struct ntfs_inode *ni, s64 start_vcn, } if (ni->allocated_size > 0) { - ret = ntfs_attr_update_mapping_pairs(ni, 0); + ret = ntfs_attr_update_mapping_pairs_locked(ni, 0, ni); if (ret) { up_write(&ni->runlist.lock); goto out_rl; @@ -5564,7 +5711,7 @@ int ntfs_non_resident_attr_punch_hole(struct ntfs_inode *ni, s64 start_vcn, s64 ni->runlist.rl = rl; ni->runlist.count = new_rl_count; - ret = ntfs_attr_update_mapping_pairs(ni, 0); + ret = ntfs_attr_update_mapping_pairs_locked(ni, 0, ni); up_write(&ni->runlist.lock); if (ret) { kvfree(punch_rl); @@ -5704,12 +5851,12 @@ int ntfs_attr_fallocate(struct ntfs_inode *ni, loff_t start, loff_t byte_len, bo lcn << vol->cluster_size_bits, alloc_cnt << vol->cluster_size_bits); - if (err > 0) + if (err) goto out; } if (signal_pending(current)) - goto out; + goto signal_out; vcn += alloc_cnt; try_alloc_cnt -= alloc_cnt; @@ -5730,7 +5877,7 @@ int ntfs_attr_fallocate(struct ntfs_inode *ni, loff_t start, loff_t byte_len, bo up_write(&ni->runlist.lock); mutex_unlock(&ni->mrec_lock); if (err || signal_pending(current)) - goto out; + goto signal_out; vcn += alloc_cnt; try_alloc_cnt -= alloc_cnt; @@ -5740,7 +5887,7 @@ int ntfs_attr_fallocate(struct ntfs_inode *ni, loff_t start, loff_t byte_len, bo if (NInoRunlistDirty(ni)) { mutex_lock_nested(&ni->mrec_lock, NTFS_INODE_MUTEX_NORMAL); down_write(&ni->runlist.lock); - err = ntfs_attr_update_mapping_pairs(ni, 0); + err = ntfs_attr_update_mapping_pairs_locked(ni, 0, ni); if (err) ntfs_error(ni->vol->sb, "Updating mapping pairs failed"); else @@ -5756,4 +5903,8 @@ out_unmap: mutex_unlock(&ni->mrec_lock); out: return err >= 0 ? 0 : err; +signal_out: + if (!err) + err = -EINTR; + goto out; } diff --git a/fs/ntfs/attrib.h b/fs/ntfs/attrib.h index e2224fbfaabe..6b4fa9f57640 100644 --- a/fs/ntfs/attrib.h +++ b/fs/ntfs/attrib.h @@ -112,7 +112,13 @@ int ntfs_non_resident_attr_punch_hole(struct ntfs_inode *ni, s64 start_vcn, s64 int __ntfs_attr_truncate_vfs(struct ntfs_inode *ni, const s64 newsize, const s64 i_size); int ntfs_attr_expand(struct ntfs_inode *ni, const s64 newsize, const s64 prealloc_size); +int ntfs_attr_expand_locked(struct ntfs_inode *ni, const s64 newsize, + const s64 prealloc_size, + struct ntfs_inode *locked_ni); int ntfs_attr_truncate_i(struct ntfs_inode *ni, const s64 newsize, unsigned int holes); +int ntfs_attr_truncate_i_locked(struct ntfs_inode *ni, const s64 newsize, + unsigned int holes, + struct ntfs_inode *locked_ni); int ntfs_attr_truncate(struct ntfs_inode *ni, const s64 newsize); int ntfs_attr_rm(struct ntfs_inode *ni); int ntfs_attr_exist(struct ntfs_inode *ni, const __le32 type, __le16 *name, @@ -133,6 +139,9 @@ int ntfs_resident_attr_record_add(struct ntfs_inode *ni, __le32 type, __le16 *name, u8 name_len, u8 *val, u32 size, __le16 flags); int ntfs_attr_update_mapping_pairs(struct ntfs_inode *ni, s64 from_vcn); +int ntfs_attr_update_mapping_pairs_locked(struct ntfs_inode *ni, + s64 from_vcn, + struct ntfs_inode *locked_ni); struct runlist_element *ntfs_attr_vcn_to_rl(struct ntfs_inode *ni, s64 vcn, s64 *lcn); /* diff --git a/fs/ntfs/attrlist.c b/fs/ntfs/attrlist.c index be3086d34338..bb191953dcb1 100644 --- a/fs/ntfs/attrlist.c +++ b/fs/ntfs/attrlist.c @@ -12,6 +12,9 @@ #include "mft.h" #include "attrib.h" #include "attrlist.h" +#include "lcnalloc.h" + +#define NTFS_MAX_ATTR_LIST_SIZE (256 * 1024) /* * ntfs_attrlist_need - check whether inode need attribute list @@ -51,11 +54,155 @@ int ntfs_attrlist_need(struct ntfs_inode *ni) return 0; } -int ntfs_attrlist_update(struct ntfs_inode *base_ni) +/* + * Repack the $MFT/$ATTRIBUTE_LIST data into one run. + * + * The mapping pairs for an $ATTRIBUTE_LIST must remain in the base MFT + * record. Once that record has no room left, extending a fragmented list + * can require one more mapping-pairs byte than the record can hold. There + * is no attribute that can legally be moved out in that state: $STANDARD_ + * INFORMATION, $ATTRIBUTE_LIST, and the first $MFT/$DATA extent all have to + * stay in the base record. Move the list data to one contiguous run. The + * caller supplies the minimum allocation size so a recovery can use the + * smallest useful run while normal updates can still request the maximum + * legal list size as a reserve. + */ +static int ntfs_attrlist_repack(struct inode *attr_vi, + struct ntfs_inode *attr_ni, s64 min_alloc_size, + struct ntfs_inode *locked_ni) +{ + struct ntfs_volume *vol = attr_ni->vol; + struct runlist_element *old_rl, *new_rl; + u8 *data = NULL; + s64 data_size, alloc_size, nr_clusters, written; + s64 old_alloc_size; + size_t old_rl_count, new_rl_count; + unsigned long flags; + int err, restore_err; + if (attr_ni->mft_no != FILE_MFT || !NInoNonResident(attr_ni) || + min_alloc_size < 0) + return -EINVAL; + /* The buffered I/O below can reacquire the attribute runlist lock. */ + if (attr_ni == locked_ni) + return -ENOSPC; + + err = ntfs_attr_map_whole_runlist(attr_ni); + if (err) + return err; + + data_size = attr_ni->data_size; + if (data_size < 0) + return -EIO; + + if (data_size) { + data = kvmalloc(data_size, GFP_NOFS); + if (!data) + return -ENOMEM; + + written = ntfs_inode_attr_pread(attr_vi, 0, data_size, data); + if (written != data_size) { + err = written < 0 ? (int)written : -EIO; + goto out_free_data; + } + } + + old_alloc_size = attr_ni->allocated_size; + alloc_size = max_t(s64, old_alloc_size, min_alloc_size); + nr_clusters = ntfs_bytes_to_cluster(vol, + alloc_size + vol->cluster_size - 1); + if (nr_clusters <= 0) { + err = -EFBIG; + goto out_free_data; + } + + /* A single run keeps the mapping pairs at the minimum size. */ + new_rl = ntfs_cluster_alloc(vol, 0, nr_clusters, -1, DATA_ZONE, + true, true, false); + if (IS_ERR(new_rl)) { + err = PTR_ERR(new_rl); + goto out_free_data; + } + + new_rl_count = 0; + if (new_rl->vcn == 0 && new_rl->length == nr_clusters && + !new_rl[1].length) + new_rl_count = 2; + + if (new_rl_count != 2) { + ntfs_cluster_free_from_rl(vol, new_rl); + kvfree(new_rl); + err = -ENOSPC; + goto out_free_data; + } + old_rl = attr_ni->runlist.rl; + old_rl_count = attr_ni->runlist.count; + down_write(&attr_ni->runlist.lock); + attr_ni->runlist.rl = new_rl; + attr_ni->runlist.count = new_rl_count; + up_write(&attr_ni->runlist.lock); + + write_lock_irqsave(&attr_ni->size_lock, flags); + attr_ni->allocated_size = ntfs_cluster_to_bytes(vol, nr_clusters); + write_unlock_irqrestore(&attr_ni->size_lock, flags); + + /* Populate the replacement extent before publishing its mapping pairs. */ + if (data_size) { + written = ntfs_inode_attr_pwrite(attr_vi, 0, data_size, data, true); + if (written != data_size) { + err = written < 0 ? (int)written : -EIO; + goto restore_old_runlist; + } + } + + err = ntfs_attr_update_mapping_pairs_locked(attr_ni, 0, locked_ni); + if (err) + goto restore_old_runlist; + + /* The new mapping is now authoritative; release the old data runs. */ + if (ntfs_cluster_free_from_rl(vol, old_rl)) { + ntfs_error(vol->sb, + "Failed to free old ATTRIBUTE_LIST extent: inode %#llx", + (long long)attr_ni->mft_no); + NVolSetErrors(vol); + } + kvfree(old_rl); + kvfree(data); + return 0; + +restore_old_runlist: + down_write(&attr_ni->runlist.lock); + attr_ni->runlist.rl = old_rl; + attr_ni->runlist.count = old_rl_count; + up_write(&attr_ni->runlist.lock); + + write_lock_irqsave(&attr_ni->size_lock, flags); + attr_ni->allocated_size = old_alloc_size; + write_unlock_irqrestore(&attr_ni->size_lock, flags); + + restore_err = ntfs_attr_update_mapping_pairs_locked( + attr_ni, 0, locked_ni); + if (restore_err) { + ntfs_error(vol->sb, "Failed to restore ATTRIBUTE_LIST mapping pairs (%d)", + restore_err); + NVolSetErrors(vol); + } + + ntfs_cluster_free_from_rl(vol, new_rl); + kvfree(new_rl); + err = err ? err : restore_err; + +out_free_data: + kvfree(data); + return err; +} + +int ntfs_attrlist_update_locked(struct ntfs_inode *base_ni, + struct ntfs_inode *locked_ni) { struct inode *attr_vi; struct ntfs_inode *attr_ni; - int err; + s64 written; + int err, retry_err; /* * generic_shutdown_super() clears SB_ACTIVE before evicting cached @@ -72,23 +219,66 @@ int ntfs_attrlist_update(struct ntfs_inode *base_ni) return err; } attr_ni = NTFS_I(attr_vi); + /* Truncation and page-cache writes can reacquire this runlist lock. */ + if (attr_ni == locked_ni) { + iput(attr_vi); + return -ENOSPC; + } - err = ntfs_attr_truncate_i(attr_ni, base_ni->attr_list_size, HOLES_NO); - if (err == -ENOSPC && attr_ni->mft_no == FILE_MFT) { - err = ntfs_attr_truncate(attr_ni, 0); - if (err || ntfs_attr_truncate_i(attr_ni, base_ni->attr_list_size, HOLES_NO) != 0) { + err = ntfs_attr_truncate_i_locked( + attr_ni, base_ni->attr_list_size, HOLES_NO, locked_ni); + if (err == -ENOSPC && attr_ni->mft_no == FILE_MFT && + NInoNonResident(attr_ni)) { + retry_err = ntfs_attrlist_repack(attr_vi, attr_ni, + base_ni->attr_list_size, locked_ni); + if (retry_err) { + ntfs_error(base_ni->vol->sb, "Failed to repack attribute list"); iput(attr_vi); + return retry_err; + } + + retry_err = ntfs_attr_truncate_i_locked( + attr_ni, base_ni->attr_list_size, + HOLES_NO, locked_ni); + if (retry_err) { ntfs_error(base_ni->vol->sb, - "Failed to truncate attribute list of inode %#llx", - (long long)base_ni->mft_no); - return -EIO; + "Failed to resize attribute list after repack"); + iput(attr_vi); + return retry_err; } } else if (err) { iput(attr_vi); ntfs_error(base_ni->vol->sb, "Failed to truncate attribute list of inode %#llx", (long long)base_ni->mft_no); - return -EIO; + return err; + } + + /* + * Reserve the maximum legal list size while the MFT metadata area is + * still easy to allocate contiguously. This prevents a later list entry + * from needing another mapping-pairs byte in the full base MFT record. + * Failure to obtain the optional reserve must not reject the current + * metadata update; the repack retry above remains available if needed. + */ + if (base_ni->mft_no == FILE_MFT && NInoNonResident(attr_ni) && + attr_ni->allocated_size < NTFS_MAX_ATTR_LIST_SIZE) { + retry_err = ntfs_attr_expand_locked( + attr_ni, base_ni->attr_list_size, + NTFS_MAX_ATTR_LIST_SIZE, locked_ni); + if (retry_err == -ENOSPC) { + retry_err = ntfs_attrlist_repack( + attr_vi, attr_ni, + NTFS_MAX_ATTR_LIST_SIZE, locked_ni); + if (retry_err == -ENOSPC) + retry_err = 0; + } + if (retry_err) { + ntfs_error(base_ni->vol->sb, + "Failed to reserve attribute list space"); + iput(attr_vi); + return retry_err; + } } i_size_write(attr_vi, base_ni->attr_list_size); @@ -96,14 +286,15 @@ int ntfs_attrlist_update(struct ntfs_inode *base_ni) if (NInoNonResident(attr_ni) && !NInoAttrListNonResident(base_ni)) NInoSetAttrListNonResident(base_ni); - if (ntfs_inode_attr_pwrite(attr_vi, 0, base_ni->attr_list_size, - base_ni->attr_list, false) != - base_ni->attr_list_size) { + written = ntfs_inode_attr_pwrite(attr_vi, 0, base_ni->attr_list_size, + base_ni->attr_list, false); + if (written != base_ni->attr_list_size) { + err = written < 0 ? (int)written : -EIO; iput(attr_vi); ntfs_error(base_ni->vol->sb, "Failed to write attribute list of inode %#llx", (long long)base_ni->mft_no); - return -EIO; + return err; } NInoSetAttrListDirty(base_ni); @@ -111,6 +302,11 @@ int ntfs_attrlist_update(struct ntfs_inode *base_ni) return 0; } +int ntfs_attrlist_update(struct ntfs_inode *base_ni) +{ + return ntfs_attrlist_update_locked(base_ni, NULL); +} + /* * ntfs_attrlist_entry_add - add an attribute list attribute entry * @ni: opened ntfs inode, which contains that attribute diff --git a/fs/ntfs/attrlist.h b/fs/ntfs/attrlist.h index 1892a3934d3a..10cc2cc8e208 100644 --- a/fs/ntfs/attrlist.h +++ b/fs/ntfs/attrlist.h @@ -16,5 +16,7 @@ int ntfs_attrlist_need(struct ntfs_inode *ni); int ntfs_attrlist_entry_add(struct ntfs_inode *ni, struct attr_record *attr); int ntfs_attrlist_entry_rm(struct ntfs_attr_search_ctx *ctx); int ntfs_attrlist_update(struct ntfs_inode *base_ni); +int ntfs_attrlist_update_locked(struct ntfs_inode *base_ni, + struct ntfs_inode *locked_ni); #endif /* defined _NTFS_ATTRLIST_H */ diff --git a/fs/ntfs/bdev-io.c b/fs/ntfs/bdev-io.c index 86db4d9298ed..4f27eed3b072 100644 --- a/fs/ntfs/bdev-io.c +++ b/fs/ntfs/bdev-io.c @@ -34,7 +34,7 @@ int ntfs_bdev_read(struct block_device *bdev, char *data, loff_t start, size_t s int error; struct bio *bio; blk_opf_t op; - sector_t sector = start >> SECTOR_SHIFT; + sector_t sector = ntfs_bytes_to_bio_sector(start); if (start & (SECTOR_SIZE - 1)) return -EINVAL; diff --git a/fs/ntfs/bitmap.c b/fs/ntfs/bitmap.c index b1436b3151b9..5a4457551306 100644 --- a/fs/ntfs/bitmap.c +++ b/fs/ntfs/bitmap.c @@ -40,7 +40,7 @@ int ntfs_trim_fs(struct ntfs_volume *vol, struct fstrim_range *range) end_cluster = vol->nr_clusters; } - ra = kzalloc(sizeof(*ra), GFP_NOFS); + ra = kzalloc_obj(*ra, GFP_NOFS); if (!ra) return -ENOMEM; @@ -64,7 +64,7 @@ int ntfs_trim_fs(struct ntfs_volume *vol, struct fstrim_range *range) end = start_buf; while (end < end_buf) { - u64 aligned_start, aligned_count; + u64 aligned_start, aligned_end, aligned_count; u64 start = find_next_zero_bit(bitmap, end_buf - start_buf, end - start_buf) + start_buf; if (start >= end_buf) @@ -74,8 +74,10 @@ int ntfs_trim_fs(struct ntfs_volume *vol, struct fstrim_range *range) start - start_buf) + start_buf; aligned_start = ALIGN(ntfs_cluster_to_bytes(vol, start), dq); - aligned_count = - ALIGN_DOWN(ntfs_cluster_to_bytes(vol, end - start), dq); + aligned_end = ALIGN_DOWN(ntfs_cluster_to_bytes(vol, end), dq); + if (aligned_start >= aligned_end) + continue; + aligned_count = aligned_end - aligned_start; if (aligned_count >= range->minlen) { ret = blkdev_issue_discard(vol->sb->s_bdev, aligned_start >> 9, aligned_count >> 9, GFP_NOFS); diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c index 2225630b19d7..075b57fc1de6 100644 --- a/fs/ntfs/compress.c +++ b/fs/ntfs/compress.c @@ -514,8 +514,8 @@ int ntfs_read_compressed_block(struct folio *folio) return -EIO; } - pages = kmalloc_array(nr_pages, sizeof(struct page *), GFP_NOFS); - completed_pages = kmalloc_array(nr_pages + 1, sizeof(int), GFP_NOFS); + pages = kmalloc_objs(struct page *, nr_pages, GFP_NOFS); + completed_pages = kmalloc_objs(int, nr_pages + 1, GFP_NOFS); if (unlikely(!pages || !completed_pages)) { kfree(pages); @@ -1262,7 +1262,7 @@ static int ntfs_compress_workspace_init(struct ntfs_inode *ni, size = ni->itype.compressed.block_size + 2 * (ni->itype.compressed.block_size / NTFS_SB_SIZE) + 2; ws->nr_pages = DIV_ROUND_UP(size, PAGE_SIZE); - ws->pages = kcalloc(ws->nr_pages, sizeof(*ws->pages), GFP_NOFS); + ws->pages = kzalloc_objs(*ws->pages, ws->nr_pages, GFP_NOFS); if (!ws->pages) return -ENOMEM; @@ -1414,7 +1414,7 @@ static int ntfs_write_cb(struct ntfs_inode *ni, loff_t pos, struct page **pages, bio_pos = ntfs_cluster_to_bytes(vol, bio_lcn); bio = bio_alloc(vol->sb->s_bdev, DIV_ROUND_UP(bio_size, PAGE_SIZE), REQ_OP_WRITE, GFP_NOIO); - bio->bi_iter.bi_sector = ntfs_bytes_to_sector(vol, bio_pos); + bio->bi_iter.bi_sector = ntfs_bytes_to_bio_sector(bio_pos); for (i = 0; bio_size; i++) { unsigned int len = min_t(unsigned int, bio_size, PAGE_SIZE); @@ -1450,7 +1450,7 @@ static int ntfs_write_cb(struct ntfs_inode *ni, loff_t pos, struct page **pages, ni->runlist.rl = rl; rlc = NULL; - err = ntfs_attr_update_mapping_pairs(ni, 0); + err = ntfs_attr_update_mapping_pairs_locked(ni, 0, ni); up_write(&ni->runlist.lock); if (err) err = -EIO; @@ -1483,7 +1483,7 @@ int ntfs_compress_write(struct ntfs_inode *ni, loff_t pos, size_t count, pages_per_cb = DIV_ROUND_UP(offset_in_page(pos & ~(cb_size - 1)) + cb_size, PAGE_SIZE); - pages = kmalloc_array(pages_per_cb, sizeof(struct page *), GFP_NOFS); + pages = kmalloc_objs(struct page *, pages_per_cb, GFP_NOFS); if (!pages) return -ENOMEM; ctx = kvzalloc_obj(*ctx, GFP_NOFS); diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c index 2d594cbb4ebe..df60138f9b2d 100644 --- a/fs/ntfs/dir.c +++ b/fs/ntfs/dir.c @@ -166,8 +166,8 @@ found_it: */ if (ie->key.file_name.file_name_type == FILE_NAME_DOS) { if (!name) { - name = kmalloc(sizeof(struct ntfs_name), - GFP_NOFS); + name = kmalloc_obj(struct ntfs_name, + GFP_NOFS); if (!name) { err = -ENOMEM; goto err_out; @@ -401,8 +401,8 @@ found_it2: */ if (ie->key.file_name.file_name_type == FILE_NAME_DOS) { if (!name) { - name = kmalloc(sizeof(struct ntfs_name), - GFP_NOFS); + name = kmalloc_obj(struct ntfs_name, + GFP_NOFS); if (!name) { err = -ENOMEM; goto unm_err_out; @@ -700,7 +700,7 @@ static int ntfs_ia_blocks_readahead(struct ntfs_inode *ia_ni, loff_t pos) if (dir_start_index >= dir_end_index) return 0; - dir_ra = kzalloc(sizeof(*dir_ra), GFP_NOFS); + dir_ra = kzalloc_obj(*dir_ra, GFP_NOFS); if (!dir_ra) return -ENOMEM; @@ -777,7 +777,7 @@ static int ntfs_readdir(struct file *file, struct dir_context *actor) return -ENOMEM; } - ra = kzalloc(sizeof(struct file_ra_state), GFP_NOFS); + ra = kzalloc_obj(struct file_ra_state, GFP_NOFS); if (!ra) { kfree(name); ntfs_index_ctx_put(ictx); @@ -813,7 +813,7 @@ static int ntfs_readdir(struct file *file, struct dir_context *actor) goto out; } } else if (!private) { - private = kzalloc(sizeof(struct ntfs_file_private), GFP_KERNEL); + private = kzalloc_obj(struct ntfs_file_private); if (!private) { err = -ENOMEM; goto out; @@ -949,7 +949,7 @@ nextdir: } if (!nir) { - nir = kzalloc(sizeof(struct ntfs_index_ra), GFP_KERNEL); + nir = kzalloc_obj(struct ntfs_index_ra); if (nir) { nir->start_index = index; nir->count = 1; diff --git a/fs/ntfs/ea.c b/fs/ntfs/ea.c index cdd306933d73..b4fcfbe2da4c 100644 --- a/fs/ntfs/ea.c +++ b/fs/ntfs/ea.c @@ -235,7 +235,7 @@ static int ntfs_set_ea(struct inode *inode, const char *name, size_t name_len, ea_info_qsize = le32_to_cpu(p_ea_info->ea_query_length); } else { create_ea_info: - p_ea_info = kzalloc(sizeof(struct ea_information), GFP_NOFS); + p_ea_info = kzalloc_obj(struct ea_information, GFP_NOFS); if (!p_ea_info) return -ENOMEM; @@ -404,10 +404,12 @@ alloc_new_ea: *packed_ea_size = p_ea_info->ea_length; mark_mft_record_dirty(ni); out: - if (ea_info_qsize > 0) - NInoSetHasEA(ni); - else - NInoClearHasEA(ni); + if (!err) { + if (ea_info_qsize > 0) + NInoSetHasEA(ni); + else + NInoClearHasEA(ni); + } kvfree(ea_buf); kvfree(old_ea_buf); @@ -615,7 +617,7 @@ static int ntfs_getxattr(const struct xattr_handler *handler, if (!buffer) { err = sizeof(u8); } else if (size < sizeof(u8)) { - err = -ENODATA; + err = -ERANGE; } else { err = sizeof(u8); *(u8 *)buffer = (u8)(le32_to_cpu(ni->flags) & 0x3F); @@ -628,7 +630,7 @@ static int ntfs_getxattr(const struct xattr_handler *handler, if (!buffer) { err = sizeof(u32); } else if (size < sizeof(u32)) { - err = -ENODATA; + err = -ERANGE; } else { err = sizeof(u32); *(u32 *)buffer = le32_to_cpu(ni->flags); @@ -753,18 +755,39 @@ static int ntfs_new_attr_flags(struct ntfs_inode *ni, __le32 fattr) old_arec_size = le32_to_cpu(a->length); /* - * Move payloads before shrinking the record. Otherwise resizing moves + * Move payloads before shrinking the record. Otherwise resizing moves * the following attribute over the old payload before it can be copied. + * + * When offsets increase, move mapping_pairs first to avoid name + * overwriting the start of mapping_pairs. */ if (arec_size < old_arec_size) { - if (a->name_length && name_ofs != old_name_ofs) - memmove((u8 *)a + name_ofs, (u8 *)a + old_name_ofs, - a->name_length * sizeof(__le16)); - if (mp_ofs != old_mp_ofs) - memmove((u8 *)a + mp_ofs, (u8 *)a + old_mp_ofs, mp_size); + if (name_ofs > old_name_ofs) { + /* Payload offsets increased: move mapping pairs first. */ + if (mp_ofs != old_mp_ofs) + memmove((u8 *)a + mp_ofs, + (u8 *)a + old_mp_ofs, + mp_size); + if (a->name_length && name_ofs != old_name_ofs) + memmove((u8 *)a + name_ofs, + (u8 *)a + old_name_ofs, + a->name_length * + sizeof(__le16)); + } else { + /* Payload offsets decreased or unchanged: move name first. */ + if (a->name_length && name_ofs != old_name_ofs) + memmove((u8 *)a + name_ofs, + (u8 *)a + old_name_ofs, + a->name_length * + sizeof(__le16)); + if (mp_ofs != old_mp_ofs) + memmove((u8 *)a + mp_ofs, + (u8 *)a + old_mp_ofs, + mp_size); + } } - err = ntfs_attr_record_resize(m, a, arec_size); + err = ntfs_attr_record_resize(ctx->mrec, a, arec_size); if (unlikely(err)) goto err_out; diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 88747217ba61..007d1614b9ac 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -111,7 +111,8 @@ static int ntfs_trim_prealloc(struct inode *vi) ntfs_error(vol->sb, "Preallocated block rollback failed"); } else { ni->allocated_size = ntfs_cluster_to_bytes(vol, vcn_tr); - err = ntfs_attr_update_mapping_pairs(ni, 0); + err = ntfs_attr_update_mapping_pairs_locked( + ni, 0, ni); if (err) ntfs_error(vol->sb, "Failed to rollback mapping pairs for prealloc"); @@ -270,18 +271,25 @@ static int ntfs_setattr_size(struct inode *vi, struct iattr *attr) return err; inode_dio_wait(vi); + + /* + * Serialize with page faults and pagecache instantiation so that + * readers cannot observe the size change until the attribute + * updates below have completed. + */ + filemap_invalidate_lock(vi->i_mapping); if (attr->ia_size > old_size) { truncate_pagecache(vi, old_size); i_size_write(vi, attr->ia_size); pagecache_isize_extended(vi, old_size, attr->ia_size); - } else + } else { truncate_setsize(vi, attr->ia_size); + } err = ntfs_truncate_vfs(vi, attr->ia_size, old_size); - if (err) { + if (err) i_size_write(vi, old_size); - return err; - } + filemap_invalidate_unlock(vi->i_mapping); return err; } @@ -669,6 +677,7 @@ out_lock: static vm_fault_t ntfs_filemap_page_mkwrite(struct vm_fault *vmf) { struct inode *inode = file_inode(vmf->vma->vm_file); + struct address_space *mapping = inode->i_mapping; vm_fault_t ret; if (NInoWofCompressed(NTFS_I(inode))) @@ -677,7 +686,14 @@ static vm_fault_t ntfs_filemap_page_mkwrite(struct vm_fault *vmf) sb_start_pagefault(inode->i_sb); file_update_time(vmf->vma->vm_file); + /* + * Serialize against truncate/fallocate which hold the lock + * exclusively while invalidating pagecache and changing extents. + */ + filemap_invalidate_lock_shared(mapping); ret = iomap_page_mkwrite(vmf, &ntfs_page_mkwrite_iomap_ops, NULL); + filemap_invalidate_unlock_shared(mapping); + sb_end_pagefault(inode->i_sb); return ret; } @@ -1116,7 +1132,6 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t offset, loff_t le struct ntfs_volume *vol = ni->vol; int err = 0; loff_t old_size; - bool map_locked = false; if (mode & ~(NTFS_FALLOC_FL_SUPPORTED)) return -EOPNOTSUPP; @@ -1148,16 +1163,13 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t offset, loff_t le inode_lock(vi); if (NInoCompressed(ni) || NInoEncrypted(ni) || NInoWofCompressed(ni)) { - err = -EOPNOTSUPP; - goto out; + inode_unlock(vi); + return -EOPNOTSUPP; } inode_dio_wait(vi); - if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE | - FALLOC_FL_INSERT_RANGE)) { - filemap_invalidate_lock(vi->i_mapping); - map_locked = true; - } + /* Take invalidate_lock for all fallocate operations to prevent races */ + filemap_invalidate_lock(vi->i_mapping); switch (mode & FALLOC_FL_MODE_MASK) { case FALLOC_FL_ALLOCATE_RANGE: @@ -1182,14 +1194,15 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t offset, loff_t le err = file_modified(file); out: - if (map_locked) - filemap_invalidate_unlock(vi->i_mapping); + if (!err && mode == 0 && NInoNonResident(ni) && + offset > old_size) { + truncate_pagecache(vi, old_size); + pagecache_isize_extended(vi, old_size, offset); + } + + filemap_invalidate_unlock(vi->i_mapping); + if (!err) { - if (mode == 0 && NInoNonResident(ni) && - offset > old_size) { - truncate_pagecache(vi, old_size); - pagecache_isize_extended(vi, old_size, offset); - } NInoSetFileNameDirty(ni); inode_set_mtime_to_ts(vi, inode_set_ctime_current(vi)); mark_inode_dirty(vi); diff --git a/fs/ntfs/index.c b/fs/ntfs/index.c index 46a8b19c0723..580998990bc9 100644 --- a/fs/ntfs/index.c +++ b/fs/ntfs/index.c @@ -1660,7 +1660,7 @@ resplit: goto out; } } else { - si = kzalloc(sizeof(struct split_info), GFP_NOFS); + si = kzalloc_obj(struct split_info, GFP_NOFS); if (!si) { ntfs_ibm_clear(icx, new_vcn); ret = -ENOMEM; diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index 32edb4045178..a777de8a80c7 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -170,17 +170,19 @@ struct inode *ntfs_iget(struct super_block *sb, u64 mft_no) /* If this is a freshly allocated inode, need to read it now. */ if (inode_state_read_once(vi) & I_NEW) { err = ntfs_read_locked_inode(vi); - unlock_new_inode(vi); + if (err) { + remove_inode_hash(vi); + discard_new_inode(vi); + } else + unlock_new_inode(vi); } /* * There is no point in keeping bad inodes around. This also * simplifies things in that we never need to check for bad inodes * elsewhere. */ - if (unlikely(err)) { - iput(vi); + if (unlikely(err)) vi = ERR_PTR(err); - } return vi; } @@ -231,17 +233,19 @@ struct inode *ntfs_attr_iget(struct inode *base_vi, __le32 type, /* If this is a freshly allocated inode, need to read it now. */ if (inode_state_read_once(vi) & I_NEW) { err = ntfs_read_locked_attr_inode(base_vi, vi); - unlock_new_inode(vi); + if (err) { + remove_inode_hash(vi); + discard_new_inode(vi); + } else + unlock_new_inode(vi); } /* * There is no point in keeping bad attribute inodes around. This also * simplifies things in that we never need to check for bad attribute * inodes elsewhere. */ - if (unlikely(err)) { - iput(vi); + if (unlikely(err)) vi = ERR_PTR(err); - } return vi; } @@ -286,17 +290,19 @@ struct inode *ntfs_index_iget(struct inode *base_vi, __le16 *name, /* If this is a freshly allocated inode, need to read it now. */ if (inode_state_read_once(vi) & I_NEW) { err = ntfs_read_locked_index_inode(base_vi, vi); - unlock_new_inode(vi); + if (err) { + remove_inode_hash(vi); + discard_new_inode(vi); + } else + unlock_new_inode(vi); } /* * There is no point in keeping bad index inodes around. This also * simplifies things in that we never need to check for bad index * inodes elsewhere. */ - if (unlikely(err)) { - iput(vi); + if (unlikely(err)) vi = ERR_PTR(err); - } return vi; } @@ -1241,7 +1247,8 @@ unm_err_out: if (m) unmap_mft_record(ni); err_out: - if (err != -EOPNOTSUPP && err != -ENOMEM && vol_err == true) { + if (err != -EOPNOTSUPP && err != -ENOMEM && + err != -EINTR && err != -ERESTARTSYS && vol_err == true) { ntfs_error(vol->sb, "Failed with error code %i. Marking corrupt inode 0x%llx as bad. Run chkdsk.", err, ni->mft_no); @@ -1467,12 +1474,13 @@ unm_err_out: ntfs_attr_put_search_ctx(ctx); unmap_mft_record(base_ni); err_out: - if (err != -ENOENT) + if (err != -ENOENT && err != -EINTR && err != -ERESTARTSYS) ntfs_error(vol->sb, "Failed with error code %i while reading attribute inode (mft_no 0x%llx, type 0x%x, name_len %i). Marking corrupt inode and base inode 0x%llx as bad. Run chkdsk.", err, ni->mft_no, ni->type, ni->name_len, base_ni->mft_no); - if (err != -ENOENT && err != -ENOMEM) + if (err != -ENOENT && err != -ENOMEM && + err != -EINTR && err != -ERESTARTSYS) NVolSetErrors(vol); return err; } @@ -1676,8 +1684,9 @@ static int ntfs_read_locked_index_inode(struct inode *base_vi, struct inode *vi) /* Get the index bitmap attribute inode. */ bvi = ntfs_attr_iget(base_vi, AT_BITMAP, ni->name, ni->name_len); if (IS_ERR(bvi)) { - ntfs_error(vi->i_sb, "Failed to get bitmap attribute."); err = PTR_ERR(bvi); + if (err != -EINTR && err != -ERESTARTSYS) + ntfs_error(vi->i_sb, "Failed to get bitmap attribute."); goto unm_err_out; } bni = NTFS_I(bvi); @@ -1721,10 +1730,12 @@ unm_err_out: if (m) unmap_mft_record(base_ni); err_out: - ntfs_error(vi->i_sb, - "Failed with error code %i while reading index inode (mft_no 0x%llx, name_len %i.", - err, ni->mft_no, ni->name_len); - if (err != -EOPNOTSUPP && err != -ENOMEM) + if (err != -EINTR && err != -ERESTARTSYS) + ntfs_error(vi->i_sb, + "Failed with error code %i while reading index inode (mft_no 0x%llx, name_len %i.", + err, ni->mft_no, ni->name_len); + if (err != -EOPNOTSUPP && err != -ENOMEM && + err != -EINTR && err != -ERESTARTSYS) NVolSetErrors(vol); return err; } @@ -1852,7 +1863,7 @@ int ntfs_read_inode_mount(struct inode *vi) struct mft_record *m = NULL; struct attr_record *a; struct ntfs_attr_search_ctx *ctx; - unsigned int i, nr_blocks; + unsigned int i; int err; size_t new_rl_count; @@ -1896,11 +1907,6 @@ int ntfs_read_inode_mount(struct inode *vi) goto err_out; } - /* Determine the first block of the $MFT/$DATA attribute. */ - nr_blocks = ntfs_bytes_to_sector(vol, vol->mft_record_size); - if (!nr_blocks) - nr_blocks = 1; - /* Load $MFT/$DATA's first mft record. */ err = ntfs_bdev_read(sb->s_bdev, (char *)m, ntfs_cluster_to_bytes(vol, vol->mft_lcn), i); @@ -2777,7 +2783,7 @@ int __ntfs_write_inode(struct inode *vi, int sync) if (NInoNonResident(ni) && NInoRunlistDirty(ni)) { down_write(&ni->runlist.lock); - err = ntfs_attr_update_mapping_pairs(ni, 0); + err = ntfs_attr_update_mapping_pairs_locked(ni, 0, ni); if (!err) NInoClearRunlistDirty(ni); up_write(&ni->runlist.lock); @@ -3718,7 +3724,7 @@ static s64 __ntfs_inode_non_resident_attr_pwrite(struct inode *vi, FGP_CREAT | FGP_LOCK, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) { - ret = -ENOMEM; + ret = PTR_ERR(folio); break; } } else { @@ -3750,6 +3756,7 @@ static s64 __ntfs_inode_non_resident_attr_pwrite(struct inode *vi, u64 rl_length = 0; s64 vcn; struct runlist_element *rl; + int bio_err; lcn_count = max_t(s64, 1, ntfs_bytes_to_cluster(vol, attr_len)); vcn = ntfs_pidx_to_cluster(vol, folio->index); @@ -3780,8 +3787,7 @@ static s64 __ntfs_inode_non_resident_attr_pwrite(struct inode *vi, bio = bio_alloc(vol->sb->s_bdev, 1, REQ_OP_WRITE, GFP_NOIO); bio->bi_iter.bi_sector = - ntfs_bytes_to_sector(vol, - ntfs_cluster_to_bytes(vol, lcn) + + ntfs_bytes_to_bio_sector(ntfs_cluster_to_bytes(vol, lcn) + lcn_folio_off); length = min_t(unsigned long, @@ -3793,8 +3799,15 @@ static s64 __ntfs_inode_non_resident_attr_pwrite(struct inode *vi, goto err_unlock_folio; } - submit_bio_wait(bio); + bio_err = submit_bio_wait(bio); bio_put(bio); + if (bio_err) { + ntfs_error(vi->i_sb, + "Synchronous attribute write failed (%d)", + bio_err); + ret = bio_err; + goto err_unlock_folio; + } vcn += rl_length; offset += length; } while (lcn_count != 0); diff --git a/fs/ntfs/lcnalloc.c b/fs/ntfs/lcnalloc.c index aa2e017a4384..0d6cd08ee2e7 100644 --- a/fs/ntfs/lcnalloc.c +++ b/fs/ntfs/lcnalloc.c @@ -53,10 +53,10 @@ int ntfs_cluster_free_from_rl_nolock(struct ntfs_volume *vol, if (rl->lcn < 0) continue; err = ntfs_bitmap_clear_run(lcnbmp_vi, rl->lcn, rl->length); - if (unlikely(err && (!ret || ret == -ENOMEM) && ret != err)) - ret = err; - else + if (likely(!err)) nr_freed += rl->length; + else if (!ret || ret == -ENOMEM) + ret = err; } ntfs_inc_free_clusters(vol, nr_freed); ntfs_debug("Done."); @@ -1045,8 +1045,9 @@ err_out: "Failed to rollback (error %i). Leaving inconsistent metadata! Unmount and run chkdsk.", (int)delta); NVolSetErrors(vol); + } else { + ntfs_dec_free_clusters(vol, delta); } - ntfs_dec_free_clusters(vol, delta); up_write(&vol->lcnbmp_lock); memalloc_nofs_restore(memalloc_flags); ntfs_error(vol->sb, "Aborting (error %i).", err); diff --git a/fs/ntfs/logfile.c b/fs/ntfs/logfile.c index 024ddee42dc8..1404664dacc0 100644 --- a/fs/ntfs/logfile.c +++ b/fs/ntfs/logfile.c @@ -691,7 +691,7 @@ map_vcn: memset(empty_buf, 0xff, vol->cluster_size); - ra = kzalloc(sizeof(*ra), GFP_NOFS); + ra = kzalloc_obj(*ra, GFP_NOFS); if (!ra) goto err; diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c index 984a0827f9ac..4b7449495375 100644 --- a/fs/ntfs/mft.c +++ b/fs/ntfs/mft.c @@ -213,7 +213,8 @@ struct mft_record *map_mft_record(struct ntfs_inode *ni) return m; atomic_dec(&ni->count); - ntfs_error(ni->vol->sb, "Failed with error code %lu.", -PTR_ERR(m)); + if (PTR_ERR(m) != -EINTR && PTR_ERR(m) != -ERESTARTSYS) + ntfs_error(ni->vol->sb, "Failed with error code %lu.", -PTR_ERR(m)); return m; } @@ -462,7 +463,7 @@ int ntfs_sync_mft_mirror(struct ntfs_volume *vol, const u64 mft_no, { u8 *kmirr; struct folio *folio; - unsigned int folio_ofs, lcn_folio_off = 0; + unsigned int folio_ofs; int err = 0; struct bio *bio; @@ -492,15 +493,11 @@ int ntfs_sync_mft_mirror(struct ntfs_volume *vol, const u64 mft_no, memcpy(kmirr, m, vol->mft_record_size); kunmap_local(kmirr); - if (vol->cluster_size_bits > PAGE_SHIFT) { - lcn_folio_off = folio->index << PAGE_SHIFT; - lcn_folio_off &= vol->cluster_size_mask; - } - bio = bio_alloc(vol->sb->s_bdev, 1, REQ_OP_WRITE, GFP_NOIO); bio->bi_iter.bi_sector = - NTFS_B_TO_SECTOR(vol, NTFS_CLU_TO_B(vol, vol->mftmirr_lcn) + - lcn_folio_off + folio_ofs); + ntfs_bytes_to_bio_sector(NTFS_CLU_TO_B(vol, vol->mftmirr_lcn) + + ((u64)folio->index << PAGE_SHIFT) + + folio_ofs); if (bio_add_folio(bio, folio, vol->mft_record_size, folio_ofs)) err = submit_bio_wait(bio); @@ -580,7 +577,7 @@ int write_mft_record_nolock(struct ntfs_inode *ni, struct mft_record *m, int syn err = pre_write_mst_fixup((struct ntfs_record *)fixup_m, vol->mft_record_size); if (err) { ntfs_error(vol->sb, "Failed to apply mst fixups!"); - goto err_out; + goto unmap_err_out; } folio_size = vol->mft_record_size / ni->mft_lcn_count; @@ -592,8 +589,8 @@ int write_mft_record_nolock(struct ntfs_inode *ni, struct mft_record *m, int syn bio = bio_alloc(vol->sb->s_bdev, 1, REQ_OP_WRITE, GFP_NOIO); bio->bi_iter.bi_sector = - NTFS_B_TO_SECTOR(vol, NTFS_CLU_TO_B(vol, ni->mft_lcn[i]) + - clu_off); + ntfs_bytes_to_bio_sector(NTFS_CLU_TO_B(vol, ni->mft_lcn[i]) + + clu_off); if (!bio_add_folio(bio, folio, folio_size, ni->folio_ofs + offset)) { @@ -645,6 +642,8 @@ done: return 0; put_bio_out: bio_put(bio); +unmap_err_out: + kunmap_local(kaddr); err_out: /* * The caller should mark the base inode as bad so no more I/O @@ -839,12 +838,126 @@ static bool ntfs_may_write_mft_record(struct ntfs_volume *vol, const u64 mft_no, static const char *es = " Leaving inconsistent metadata. Unmount and run chkdsk."; -#define RESERVED_MFT_RECORDS 64 +#define FIRST_NORMAL_MFT_RECORD 24 +#define MFT_RECORD_RESERVE 4 + +/* + * Records 12-15 are marked in use by Windows but normally have no name + * and no links. Keep them as the last bootstrap option when a volume + * mounted without an in-memory tail reserve needs its first $MFT metadata + * extent. + */ +static bool mft_reserved_is_free(struct ntfs_volume *vol, + struct ntfs_inode *mft_ni, s64 mft_no) +{ + struct attr_record *a; + struct mft_record *m; + struct folio *folio; + void *mapped; + pgoff_t index = NTFS_MFT_NR_TO_PIDX(vol, mft_no); + unsigned int ofs = NTFS_MFT_NR_TO_POFS(vol, mft_no); + u32 attrs_offset, bytes_in_use; + bool available = false, have_std = false; + int i; + + for (i = 0; i < mft_ni->nr_extents; i++) { + if (mft_ni->ext.extent_ntfs_inos[i] && + mft_ni->ext.extent_ntfs_inos[i]->mft_no == mft_no) + return false; + } + m = kmalloc(vol->mft_record_size, GFP_NOFS); + if (!m) + return false; + + folio = read_mapping_folio(vol->mft_ino->i_mapping, index, NULL); + if (IS_ERR(folio)) + goto free_m; + + folio_lock(folio); + mapped = kmap_local_folio(folio, 0); + memcpy(m, (u8 *)mapped + ofs, vol->mft_record_size); + kunmap_local(mapped); + folio_unlock(folio); + folio_put(folio); + if (post_read_mst_fixup((struct ntfs_record *)m, vol->mft_record_size)) + goto free_m; + + if (!ntfs_is_mft_record(m->magic) || + !(m->flags & MFT_RECORD_IN_USE) || m->base_mft_record || + m->link_count) + goto out; + + attrs_offset = le16_to_cpu(m->attrs_offset); + bytes_in_use = le32_to_cpu(m->bytes_in_use); + if (attrs_offset > bytes_in_use || bytes_in_use > vol->mft_record_size || + bytes_in_use - attrs_offset < sizeof(a->type)) + goto out; + + for (a = (struct attr_record *)((u8 *)m + attrs_offset); + (u8 *)a + sizeof(a->type) <= (u8 *)m + bytes_in_use;) { + u32 len; + + if (a->type == AT_END) { + if ((u8 *)a + sizeof(a->type) + sizeof(a->length) > + (u8 *)m + bytes_in_use) + break; + /* Also accept a record emptied by an earlier bootstrap. */ + available = have_std || + (u8 *)a == (u8 *)m + attrs_offset; + break; + } + if (a->type == AT_FILE_NAME) + break; + len = le32_to_cpu(a->length); + if (len < offsetof(struct attr_record, data) || + (u8 *)a + len > (u8 *)m + bytes_in_use) + break; + if (a->type == AT_STANDARD_INFORMATION) { + u32 value_len, value_ofs; + + if (have_std || a->non_resident || + len < offsetof(struct attr_record, + data.resident.reserved) + 1) + break; + value_len = le32_to_cpu(a->data.resident.value_length); + value_ofs = le16_to_cpu(a->data.resident.value_offset); + if (value_ofs > len || value_len > len - value_ofs) + break; + have_std = true; + } + a = (struct attr_record *)((u8 *)a + len); + } +out: + kfree(m); + return available; +free_m: + kfree(m); + return false; +} + +static s64 mft_reserve_end(const u8 *buf, s64 buf_start, s64 buf_end, + s64 start, s64 pass_end, s64 initialized_mft_records) +{ + s64 end = start + 1; + s64 limit = min_t(s64, start + MFT_RECORD_RESERVE, pass_end); + + if (limit > initialized_mft_records) + limit = initialized_mft_records; + if (limit > buf_end) + limit = buf_end; + while (end < limit && + !(buf[(end - buf_start) >> 3] & + (1 << ((end - buf_start) & 7)))) + end++; + return end; +} /* - * ntfs_mft_bitmap_find_and_alloc_free_rec_nolock - see name + * mft_bitmap_alloc_free_rec - find and allocate a free MFT record * @vol: volume on which to search for a free mft record * @base_ni: open base inode if allocating an extent mft record or NULL + * @max_mft_no: first record which must not be allocated, or -1 + * @new_reserve_end: if not NULL, end of a free run starting after the result * * Search for a free mft record in the mft bitmap attribute on the ntfs volume * @vol. @@ -860,10 +973,12 @@ static const char *es = " Leaving inconsistent metadata. Unmount and run chkds * * Locking: Caller must hold vol->mftbmp_lock for writing. */ -static s64 ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(struct ntfs_volume *vol, - struct ntfs_inode *base_ni) +static s64 mft_bitmap_alloc_free_rec(struct ntfs_volume *vol, + struct ntfs_inode *base_ni, + s64 max_mft_no, s64 *new_reserve_end) { s64 pass_end, ll, data_pos, pass_start, ofs, bit; + s64 initialized_mft_records; unsigned long flags; struct address_space *mftbmp_mapping; u8 *buf = NULL, *byte; @@ -880,30 +995,36 @@ static s64 ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(struct ntfs_volume *vo read_lock_irqsave(&NTFS_I(vol->mft_ino)->size_lock, flags); pass_end = NTFS_I(vol->mft_ino)->allocated_size >> vol->mft_record_size_bits; + initialized_mft_records = NTFS_I(vol->mft_ino)->initialized_size >> + vol->mft_record_size_bits; read_unlock_irqrestore(&NTFS_I(vol->mft_ino)->size_lock, flags); read_lock_irqsave(&NTFS_I(vol->mftbmp_ino)->size_lock, flags); ll = NTFS_I(vol->mftbmp_ino)->initialized_size << 3; read_unlock_irqrestore(&NTFS_I(vol->mftbmp_ino)->size_lock, flags); if (pass_end > ll) pass_end = ll; - pass = 1; - if (!base_ni) - data_pos = vol->mft_data_pos; - else - data_pos = base_ni->mft_no + 1; - if (data_pos < RESERVED_MFT_RECORDS) - data_pos = RESERVED_MFT_RECORDS; - if (data_pos >= pass_end) { - data_pos = RESERVED_MFT_RECORDS; + if (max_mft_no >= 0 && pass_end > max_mft_no) + pass_end = max_mft_no; + if (base_ni && base_ni->mft_no == FILE_MFT) { + data_pos = FILE_first_user; pass = 2; - /* This happens on a freshly formatted volume. */ if (data_pos >= pass_end) return -ENOSPC; - } - - if (base_ni && base_ni->mft_no == FILE_MFT) { - data_pos = 0; - pass = 2; + } else { + pass = 1; + if (!base_ni) + data_pos = vol->mft_data_pos; + else + data_pos = base_ni->mft_no + 1; + if (data_pos < FIRST_NORMAL_MFT_RECORD) + data_pos = FIRST_NORMAL_MFT_RECORD; + if (data_pos >= pass_end) { + data_pos = FIRST_NORMAL_MFT_RECORD; + pass = 2; + /* This happens on a freshly formatted volume. */ + if (data_pos >= pass_end) + return -ENOSPC; + } } pass_start = data_pos; @@ -938,38 +1059,28 @@ static s64 ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(struct ntfs_volume *vo size, data_pos, bit); for (; bit < size && data_pos + bit < pass_end; bit &= ~7ull, bit += 8) { - /* - * If we're extending $MFT and running out of the first - * mft record (base record) then give up searching since - * no guarantee that the found record will be accessible. - */ - if (base_ni && base_ni->mft_no == FILE_MFT && bit > 400) { - folio_unlock(folio); - kunmap_local(buf); - folio_put(folio); - return -ENOSPC; - } - byte = buf + (bit >> 3); if (*byte == 0xff) continue; - b = ffz((unsigned long)*byte); - if (b < 8 && b >= (bit & 7)) { + b = bit & 7; + for (; b < 8; b++) { + if (*byte & (1 << b)) + continue; ll = data_pos + (bit & ~7ull) + b; + if (ll >= pass_end) + break; + /* Keep the dynamic tail reserve for $MFT metadata. */ + if ((!base_ni || base_ni->mft_no != FILE_MFT) && + ll >= vol->mft_record_reserve_pos && + ll < vol->mft_record_reserve_end) + continue; if (unlikely(ll >= (1ll << 32))) { folio_unlock(folio); kunmap_local(buf); folio_put(folio); return -ENOSPC; } - *byte |= 1 << b; - folio_mark_dirty(folio); - folio_unlock(folio); - kunmap_local(buf); - folio_put(folio); - ntfs_debug("Done. (Found and allocated mft record 0x%llx.)", - ll); - return ll; + goto found; } } ntfs_debug("After inner for loop: size 0x%x, data_pos 0x%llx, bit 0x%llx", @@ -992,7 +1103,8 @@ static s64 ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(struct ntfs_volume *vo * part of the zone which we omitted earlier. */ pass_end = pass_start; - data_pos = pass_start = RESERVED_MFT_RECORDS; + data_pos = FIRST_NORMAL_MFT_RECORD; + pass_start = FIRST_NORMAL_MFT_RECORD; ntfs_debug("pass %i, pass_start 0x%llx, pass_end 0x%llx.", pass, pass_start, pass_end); if (data_pos >= pass_end) @@ -1002,9 +1114,22 @@ static s64 ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(struct ntfs_volume *vo /* No free mft records in currently initialized mft bitmap. */ ntfs_debug("Done. (No free mft records left in currently initialized mft bitmap.)"); return -ENOSPC; +found: + if (new_reserve_end) + *new_reserve_end = mft_reserve_end(buf, data_pos, + data_pos + size, ll, pass_end, + initialized_mft_records); + *byte |= 1 << b; + folio_mark_dirty(folio); + folio_unlock(folio); + kunmap_local(buf); + folio_put(folio); + ntfs_debug("Done. (Found and allocated mft record 0x%llx.)", ll); + return ll; } -static int ntfs_mft_attr_extend(struct ntfs_inode *ni) +static int ntfs_mft_attr_extend(struct ntfs_inode *ni, + struct ntfs_inode *locked_ni) { int ret = 0; struct ntfs_inode *base_ni; @@ -1025,7 +1150,7 @@ static int ntfs_mft_attr_extend(struct ntfs_inode *ni) } } - ret = ntfs_attr_update_mapping_pairs(ni, 0); + ret = ntfs_attr_update_mapping_pairs_locked(ni, 0, locked_ni); if (ret) pr_err("MP update failed\n"); @@ -1213,7 +1338,7 @@ static int ntfs_mft_bitmap_extend_allocation_nolock(struct ntfs_volume *vol) ret = ntfs_attr_record_resize(ctx->mrec, a, mp_size + le16_to_cpu(a->data.non_resident.mapping_pairs_offset)); if (unlikely(ret)) { - ret = ntfs_mft_attr_extend(mftbmp_ni); + ret = ntfs_mft_attr_extend(mftbmp_ni, mftbmp_ni); if (!ret) goto extended_ok; if (ret != -EAGAIN) @@ -1324,7 +1449,9 @@ undo_alloc: NVolSetErrors(vol); } mark_mft_record_dirty(ctx->ntfs_ino); - } else if (status.mp_extended && ntfs_attr_update_mapping_pairs(mftbmp_ni, 0)) { + } else if (status.mp_extended && + ntfs_attr_update_mapping_pairs_locked(mftbmp_ni, 0, + mftbmp_ni)) { ntfs_error(vol->sb, "Failed to restore mapping pairs.%s", es); NVolSetErrors(vol); } @@ -1412,7 +1539,6 @@ static int ntfs_mft_bitmap_extend_initialized_nolock(struct ntfs_volume *vol) ret = ntfs_attr_set(mftbmp_ni, old_initialized_size, 8, 0); if (likely(!ret)) { ntfs_debug("Done. (Wrote eight initialized bytes to mft bitmap."); - ntfs_inc_free_mft_records(vol, 8 * 8); return 0; } ntfs_error(vol->sb, "Failed to write to mft bitmap."); @@ -1469,8 +1595,9 @@ err_out: * @vol: volume on which to extend the mft data attribute * * Extend the mft data attribute on the ntfs volume @vol by 16 mft records - * worth of clusters or if not enough space for this by one mft record worth - * of clusters. + * worth of clusters or if not enough space for this by two mft records worth + * of clusters. Keeping at least two new records breaks the recursion between + * extending $MFT and allocating a record for a new $MFT attribute extent. * * Note: Only changes allocated_size, i.e. does not touch initialized_size or * data_size. @@ -1524,10 +1651,8 @@ static int ntfs_mft_data_extend_allocation_nolock(struct ntfs_volume *vol) } lcn = rl->lcn + rl->length; ntfs_debug("Last lcn of mft data attribute is 0x%llx.", lcn); - /* Minimum allocation is one mft record worth of clusters. */ - min_nr = NTFS_B_TO_CLU(vol, vol->mft_record_size); - if (!min_nr) - min_nr = 1; + /* Keep room for the allocating record and at least one MFT reserve. */ + min_nr = DIV_ROUND_UP_ULL((u64)vol->mft_record_size * 2, vol->cluster_size); /* Want to allocate 16 mft records worth of clusters. */ nr = vol->mft_record_size << 4 >> vol->cluster_size_bits; if (!nr) @@ -1651,7 +1776,7 @@ static int ntfs_mft_data_extend_allocation_nolock(struct ntfs_volume *vol) ret = ntfs_attr_record_resize(ctx->mrec, a, mp_size + le16_to_cpu(a->data.non_resident.mapping_pairs_offset)); if (unlikely(ret)) { - ret = ntfs_mft_attr_extend(mft_ni); + ret = ntfs_mft_attr_extend(mft_ni, NULL); if (!ret) goto extended_ok; if (ret != -EAGAIN) @@ -1926,6 +2051,7 @@ static int ntfs_mft_record_format(const struct ntfs_volume *vol, const s64 mft_n * @ni: [OUT] on success, set to the allocated ntfs inode * @base_ni: [IN] open base inode if allocating an extent mft record or NULL * @ni_mrec: [OUT] on successful return this is the mapped mft record + * @mft_data_vcn: [IN] lowest VCN of a new $MFT/$DATA extent, or -1 * * Allocate an mft record in $MFT/$DATA of an open ntfs volume @vol. * @@ -1953,30 +2079,23 @@ static int ntfs_mft_record_format(const struct ntfs_volume *vol, const s64 mft_n * optimize this we start scanning at the place specified by @base_ni or if * @base_ni is NULL we start where we last stopped and we perform wrap around * when we reach the end. Note, we do not try to allocate mft records below - * number 64 because numbers 0 to 15 are the defined system files anyway and 16 - * to 64 are special in that they are used for storing extension mft records - * for the $DATA attribute of $MFT. This is required to avoid the possibility - * of creating a runlist with a circular dependency which once written to disk - * can never be read in again. Windows will only use records 16 to 24 for - * normal files if the volume is completely out of space. We never use them - * which means that when the volume is really out of space we cannot create any - * more files while Windows can still create up to 8 small files. We can start - * doing this at some later time, it does not matter much for now. + * number 24 because numbers 0 to 15 are the defined system files and records + * 16 to 23 are kept for metadata compatibility. Records reserved dynamically + * at the initialized MFT tail are skipped by normal allocation and consumed by + * $MFT metadata extent allocation. * * When scanning the mft bitmap, we only search up to the last allocated mft - * record. If there are no free records left in the range 64 to number of + * record. If there are no free records left in the range 24 to number of * allocated mft records, then we extend the $MFT/$DATA attribute in order to * create free mft records. We extend the allocated size of $MFT/$DATA by 16 * records at a time or one cluster, if cluster size is above 16kiB. If there - * is not sufficient space to do this, we try to extend by a single mft record - * or one cluster, if cluster size is above the mft record size. + * is not sufficient space to do this, we try to extend by two mft records or + * one cluster, if a cluster already contains at least two mft records. * - * No matter how many mft records we allocate, we initialize only the first - * allocated mft record, incrementing mft data size and initialized size - * accordingly, open an struct ntfs_inode for it and return it to the caller, unless - * there are less than 64 mft records, in which case we allocate and initialize - * mft records until we reach record 64 which we consider as the first free mft - * record for use by normal files. + * When extending the initialized MFT tail, we also initialize up to four + * additional records and reserve them in memory for future $MFT metadata + * extents. If there are less than 24 mft records, records are initialized + * until record 24, which is the first record used for normal files. * * If during any stage we overflow the initialized data in the mft bitmap, we * extend the initialized size (and data size) by 8 bytes, allocating another @@ -2012,9 +2131,13 @@ static int ntfs_mft_record_format(const struct ntfs_volume *vol, const s64 mft_n */ int ntfs_mft_record_alloc(struct ntfs_volume *vol, const int mode, struct ntfs_inode **ni, struct ntfs_inode *base_ni, - struct mft_record **ni_mrec) + struct mft_record **ni_mrec, const s64 mft_data_vcn) { s64 ll, bit, old_data_initialized, old_data_size; + s64 nr_new_mft_records = 0; + s64 max_mft_no = -1, reserve_start = -1, reserve_end = -1; + s64 candidate_reserve_end = -1; + s64 *reserve_endp; unsigned long flags; struct folio *folio; struct ntfs_inode *mft_ni, *mftbmp_ni; @@ -2025,7 +2148,9 @@ int ntfs_mft_record_alloc(struct ntfs_volume *vol, const int mode, unsigned int ofs; int err; __le16 seq_no, usn; - bool record_formatted = false; + bool record_formatted = false, from_reserve = false, tail_alloc = false; + bool reserve_created = false; + bool forced_reserved_record = false; unsigned int memalloc_flags; if (base_ni && *ni) @@ -2034,6 +2159,21 @@ int ntfs_mft_record_alloc(struct ntfs_volume *vol, const int mode, /* @mode and @base_ni are mutually exclusive. */ if (mode && base_ni) return -EINVAL; + if (mft_data_vcn >= 0 && + (!base_ni || base_ni->mft_no != FILE_MFT)) + return -EINVAL; + if (mft_data_vcn >= 0) { + u64 vbo; + + if ((u64)mft_data_vcn > (U64_MAX >> vol->cluster_size_bits)) + return -EOVERFLOW; + vbo = (u64)mft_data_vcn << vol->cluster_size_bits; + /* + * The whole extent record must be reachable without this + * extent, including when an MFT record spans multiple clusters. + */ + max_mft_no = vbo >> vol->mft_record_size_bits; + } if (base_ni) ntfs_debug("Entering (allocating an extent mft record for base mft record 0x%llx).", @@ -2048,10 +2188,39 @@ int ntfs_mft_record_alloc(struct ntfs_volume *vol, const int mode, mutex_lock(&mft_ni->mrec_lock); mftbmp_ni = NTFS_I(vol->mftbmp_ino); search_free_rec: + from_reserve = false; + reserve_created = false; + candidate_reserve_end = -1; if (!base_ni || base_ni->mft_no != FILE_MFT) down_write(&vol->mftbmp_lock); - bit = ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(vol, base_ni); + if (base_ni && base_ni->mft_no == FILE_MFT && + vol->mft_record_reserve_pos < vol->mft_record_reserve_end && + (max_mft_no < 0 || vol->mft_record_reserve_pos < max_mft_no)) { + bit = vol->mft_record_reserve_pos; + err = ntfs_bitmap_set_bit(vol->mftbmp_ino, bit); + if (unlikely(err)) { + ntfs_error(vol->sb, + "Failed to allocate reserved MFT record 0x%llx.", + bit); + goto err_out; + } + vol->mft_record_reserve_pos++; + from_reserve = true; + ntfs_debug("Allocated MFT metadata record 0x%llx from tail reserve.", + bit); + goto have_alloc_rec; + } + reserve_endp = vol->mft_record_reserve_pos >= + vol->mft_record_reserve_end ? &candidate_reserve_end : NULL; + bit = mft_bitmap_alloc_free_rec(vol, base_ni, max_mft_no, reserve_endp); if (bit >= 0) { + if (candidate_reserve_end > bit + 1) { + vol->mft_record_reserve_pos = bit + 1; + vol->mft_record_reserve_end = candidate_reserve_end; + reserve_created = true; + ntfs_debug("Reserved free MFT records [0x%llx, 0x%llx) for metadata.", + bit + 1, candidate_reserve_end); + } ntfs_debug("Found and allocated free record (#1), bit 0x%llx.", (long long)bit); goto have_alloc_rec; @@ -2066,6 +2235,24 @@ search_free_rec: } if (base_ni && base_ni->mft_no == FILE_MFT) { + static const u8 bootstrap_records[] = { + FILE_reserved15, FILE_reserved12, FILE_reserved13, + FILE_reserved14, + }; + int i; + + for (i = 0; i < ARRAY_SIZE(bootstrap_records); i++) { + if (max_mft_no >= 0 && bootstrap_records[i] >= max_mft_no) + continue; + if (!mft_reserved_is_free(vol, mft_ni, + bootstrap_records[i])) + continue; + bit = bootstrap_records[i]; + forced_reserved_record = true; + ntfs_debug("Using reserved MFT record %lld to bootstrap metadata extension.", + bit); + goto have_alloc_rec; + } memalloc_nofs_restore(memalloc_flags); return bit; } @@ -2085,10 +2272,10 @@ search_free_rec: old_data_initialized = mftbmp_ni->initialized_size; read_unlock_irqrestore(&mftbmp_ni->size_lock, flags); if (old_data_initialized << 3 > ll && - old_data_initialized > RESERVED_MFT_RECORDS / 8) { + old_data_initialized << 3 > FIRST_NORMAL_MFT_RECORD) { bit = ll; - if (bit < RESERVED_MFT_RECORDS) - bit = RESERVED_MFT_RECORDS; + if (bit < FIRST_NORMAL_MFT_RECORD) + bit = FIRST_NORMAL_MFT_RECORD; if (unlikely(bit >= (1ll << 32))) goto max_err_out; ntfs_debug("Found free record (#2), bit 0x%llx.", @@ -2174,6 +2361,11 @@ have_alloc_rec: read_lock_irqsave(&mft_ni->size_lock, flags); old_data_initialized = mft_ni->initialized_size; read_unlock_irqrestore(&mft_ni->size_lock, flags); + tail_alloc = (!base_ni || base_ni->mft_no != FILE_MFT) && + bit >= (old_data_initialized >> vol->mft_record_size_bits) && + vol->mft_record_reserve_pos >= vol->mft_record_reserve_end; + if (tail_alloc) + ll = (bit + 2) << vol->mft_record_size_bits; if (ll <= old_data_initialized) { ntfs_debug("Allocated mft record already initialized."); goto mft_rec_already_initialized; @@ -2206,6 +2398,29 @@ have_alloc_rec: mft_ni->initialized_size); } read_unlock_irqrestore(&mft_ni->size_lock, flags); + if (tail_alloc) { + s64 bitmap_records; + + read_lock_irqsave(&mft_ni->size_lock, flags); + reserve_end = mft_ni->allocated_size >> + vol->mft_record_size_bits; + read_unlock_irqrestore(&mft_ni->size_lock, flags); + read_lock_irqsave(&mftbmp_ni->size_lock, flags); + bitmap_records = mftbmp_ni->initialized_size << 3; + read_unlock_irqrestore(&mftbmp_ni->size_lock, flags); + if (reserve_end > bitmap_records) + reserve_end = bitmap_records; + if (reserve_end > bit + 1 + MFT_RECORD_RESERVE) + reserve_end = bit + 1 + MFT_RECORD_RESERVE; + reserve_start = bit + 1; + if (reserve_end > reserve_start) { + ll = reserve_end << vol->mft_record_size_bits; + } else { + reserve_start = -1; + reserve_end = -1; + ll = (bit + 1) << vol->mft_record_size_bits; + } + } } else if (ll > mft_ni->allocated_size) { err = -ENOSPC; goto undo_mftbmp_alloc_nolock; @@ -2274,14 +2489,25 @@ have_alloc_rec: mark_mft_record_dirty(ctx->ntfs_ino); ntfs_attr_put_search_ctx(ctx); unmap_mft_record(mft_ni); + if (reserve_start >= 0 && reserve_end > reserve_start) { + vol->mft_record_reserve_pos = reserve_start; + vol->mft_record_reserve_end = reserve_end; + ntfs_debug("Reserved MFT records [0x%llx, 0x%llx) for metadata.", + reserve_start, reserve_end); + } read_lock_irqsave(&mft_ni->size_lock, flags); ntfs_debug("Status of mft data after mft record initialization: allocated_size 0x%llx, data_size 0x%llx, initialized_size 0x%llx.", mft_ni->allocated_size, i_size_read(vol->mft_ino), mft_ni->initialized_size); WARN_ON(i_size_read(vol->mft_ino) > mft_ni->allocated_size); WARN_ON(mft_ni->initialized_size > i_size_read(vol->mft_ino)); + nr_new_mft_records = (i_size_read(vol->mft_ino) - old_data_size) >> + vol->mft_record_size_bits; read_unlock_irqrestore(&mft_ni->size_lock, flags); mft_rec_already_initialized: + /* Account for newly visible MFT records before dropping the lock. */ + if (nr_new_mft_records > 0) + ntfs_inc_free_mft_records(vol, nr_new_mft_records); /* * We can finally drop the mft bitmap lock as the mft data attribute * has been fully updated. The only disparity left is that the @@ -2313,8 +2539,8 @@ mft_rec_already_initialized: /* If we just formatted the mft record no need to do it again. */ if (!record_formatted) { /* Sanity check that the mft record is really not in use. */ - if (ntfs_is_file_record(m->magic) && - (m->flags & MFT_RECORD_IN_USE)) { + if (!forced_reserved_record && ntfs_is_file_record(m->magic) && + (m->flags & MFT_RECORD_IN_USE)) { ntfs_warning(vol->sb, "Mft record 0x%llx was marked free in mft bitmap but is marked used itself. Unmount and run chkdsk.", bit); @@ -2387,9 +2613,13 @@ mft_rec_already_initialized: ntfs_error(vol->sb, "Failed to map allocated extent mft record 0x%llx.", bit); err = PTR_ERR(m_tmp); - /* Set the mft record itself not in use. */ - m->flags &= cpu_to_le16( - ~le16_to_cpu(MFT_RECORD_IN_USE)); + if (forced_reserved_record) { + m->base_mft_record = 0; + m->flags |= MFT_RECORD_IN_USE; + } else { + /* Set the mft record itself not in use. */ + m->flags &= cpu_to_le16(~le16_to_cpu(MFT_RECORD_IN_USE)); + } /* Make sure the mft record is written out to disk. */ ntfs_mft_mark_dirty(folio); folio_unlock(folio); @@ -2461,7 +2691,8 @@ mft_rec_already_initialized: (*ni)->mft_no = bit; if (ni_mrec) *ni_mrec = (*ni)->mrec; - ntfs_dec_free_mft_records(vol, 1); + if (!forced_reserved_record) + ntfs_dec_free_mft_records(vol, 1); return 0; undo_data_init: write_lock_irqsave(&mft_ni->size_lock, flags); @@ -2473,10 +2704,13 @@ undo_mftbmp_alloc: if (!base_ni || base_ni->mft_no != FILE_MFT) down_write(&vol->mftbmp_lock); undo_mftbmp_alloc_nolock: - if (ntfs_bitmap_clear_bit(vol->mftbmp_ino, bit)) { + if (!forced_reserved_record && ntfs_bitmap_clear_bit(vol->mftbmp_ino, bit)) { ntfs_error(vol->sb, "Failed to clear bit in mft bitmap.%s", es); NVolSetErrors(vol); } + if ((from_reserve || reserve_created) && + vol->mft_record_reserve_pos == bit + 1) + vol->mft_record_reserve_pos = bit; if (!base_ni || base_ni->mft_no != FILE_MFT) up_write(&vol->mftbmp_lock); err_out: @@ -2512,9 +2746,11 @@ int ntfs_mft_record_free(struct ntfs_volume *vol, struct ntfs_inode *ni) int err; u16 seq_no; __le16 old_seq_no; + __le64 old_base_mft_record; struct mft_record *ni_mrec; unsigned int memalloc_flags; struct ntfs_inode *base_ni; + bool keep_reserved; if (!vol || !ni) return -EINVAL; @@ -2527,9 +2763,23 @@ int ntfs_mft_record_free(struct ntfs_volume *vol, struct ntfs_inode *ni) /* Cache the mft reference for later. */ mft_no = ni->mft_no; - - /* Mark the mft record as not in use. */ - ni_mrec->flags &= ~MFT_RECORD_IN_USE; + if (likely(ni->nr_extents >= 0)) + base_ni = ni; + else + base_ni = ni->ext.base_ntfs_ino; + keep_reserved = mft_no >= FILE_reserved12 && + mft_no <= FILE_reserved15 && + base_ni->mft_no == FILE_MFT; + + old_base_mft_record = ni_mrec->base_mft_record; + if (keep_reserved) { + /* Restore the special, unnamed form used by reserved records. */ + ni_mrec->base_mft_record = 0; + ni_mrec->flags |= MFT_RECORD_IN_USE; + } else { + /* Mark the mft record as not in use. */ + ni_mrec->flags &= ~MFT_RECORD_IN_USE; + } /* Increment the sequence number, skipping zero, if it is not zero. */ old_seq_no = ni_mrec->sequence_number; @@ -2558,24 +2808,28 @@ int ntfs_mft_record_free(struct ntfs_volume *vol, struct ntfs_inode *ni) if (err) goto sync_rollback; - if (likely(ni->nr_extents >= 0)) - base_ni = ni; - else - base_ni = ni->ext.base_ntfs_ino; + if (keep_reserved) { + unmap_mft_record(ni); + return 0; + } /* Clear the bit in the $MFT/$BITMAP corresponding to this record. */ memalloc_flags = memalloc_nofs_save(); if (base_ni->mft_no != FILE_MFT) down_write(&vol->mftbmp_lock); err = ntfs_bitmap_clear_bit(vol->mftbmp_ino, mft_no); + if (!err) + ntfs_inc_free_mft_records(vol, 1); + if (!err && base_ni->mft_no == FILE_MFT && + mft_no + 1 == vol->mft_record_reserve_pos && + mft_no < vol->mft_record_reserve_end) + vol->mft_record_reserve_pos = mft_no; if (base_ni->mft_no != FILE_MFT) up_write(&vol->mftbmp_lock); memalloc_nofs_restore(memalloc_flags); if (err) goto bitmap_rollback; - unmap_mft_record(ni); - ntfs_inc_free_mft_records(vol, 1); return 0; /* Rollback what we did... */ @@ -2593,6 +2847,7 @@ sync_rollback: "Eeek! Rollback failed in %s. Leaving inconsistent metadata!\n", __func__); ni_mrec->flags |= MFT_RECORD_IN_USE; ni_mrec->sequence_number = old_seq_no; + ni_mrec->base_mft_record = old_base_mft_record; NInoSetDirty(ni); write_mft_record(ni, ni_mrec, 0); unmap_mft_record(ni); @@ -2633,11 +2888,13 @@ static int ntfs_write_mft_block(struct folio *folio, struct writeback_control *w struct ntfs_inode *ni = NTFS_I(vi); struct ntfs_volume *vol = ni->vol; u8 *kaddr; - struct ntfs_inode **locked_nis __free(kfree) = kmalloc_array(PAGE_SIZE / NTFS_BLOCK_SIZE, - sizeof(struct ntfs_inode *), GFP_NOFS); + struct ntfs_inode **locked_nis __free(kfree) = kmalloc_objs(struct ntfs_inode *, + PAGE_SIZE / NTFS_BLOCK_SIZE, + GFP_NOFS); int nr_locked_nis = 0, err = 0, mft_ofs, prev_mft_ofs; - struct inode **ref_inos __free(kfree) = kmalloc_array(PAGE_SIZE / NTFS_BLOCK_SIZE, - sizeof(struct inode *), GFP_NOFS); + struct inode **ref_inos __free(kfree) = kmalloc_objs(struct inode *, + PAGE_SIZE / NTFS_BLOCK_SIZE, + GFP_NOFS); int nr_ref_inos = 0; struct bio *bio = NULL; u64 mft_no; @@ -2740,8 +2997,8 @@ flush_bio: bio = bio_alloc(vol->sb->s_bdev, 1, REQ_OP_WRITE, GFP_NOIO); bio->bi_iter.bi_sector = - ntfs_bytes_to_sector(vol, - ntfs_cluster_to_bytes(vol, lcn) + off); + ntfs_bytes_to_bio_sector( + ntfs_cluster_to_bytes(vol, lcn) + off); } if (vol->cluster_size == NTFS_BLOCK_SIZE && diff --git a/fs/ntfs/mft.h b/fs/ntfs/mft.h index 75a51a98d0f6..ed5c1d595c0d 100644 --- a/fs/ntfs/mft.h +++ b/fs/ntfs/mft.h @@ -78,7 +78,7 @@ static inline int write_mft_record(struct ntfs_inode *ni, struct mft_record *m, int ntfs_mft_record_alloc(struct ntfs_volume *vol, const int mode, struct ntfs_inode **ni, struct ntfs_inode *base_ni, - struct mft_record **ni_mrec); + struct mft_record **ni_mrec, const s64 mft_data_vcn); int ntfs_mft_record_free(struct ntfs_volume *vol, struct ntfs_inode *ni); int ntfs_mft_records_write(const struct ntfs_volume *vol, const u64 mref, const s64 count, struct mft_record *b); diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c index 7091b2496fac..fdf52fac4329 100644 --- a/fs/ntfs/namei.c +++ b/fs/ntfs/namei.c @@ -480,7 +480,7 @@ static struct ntfs_inode *__ntfs_create(struct mnt_idmap *idmap, struct inode *d mark_inode_dirty(dir); err = ntfs_mft_record_alloc(dir_ni->vol, mode, &ni, NULL, - &ni_mrec); + &ni_mrec, -1); if (err) { iput(vi); return ERR_PTR(err); diff --git a/fs/ntfs/ntfs.h b/fs/ntfs/ntfs.h index df5a75d506f6..45f77848a9cf 100644 --- a/fs/ntfs/ntfs.h +++ b/fs/ntfs/ntfs.h @@ -19,6 +19,7 @@ #include <linux/nls.h> #include <linux/smp.h> #include <linux/pagemap.h> +#include <linux/blk_types.h> #include <linux/uidgid.h> #include "volume.h" @@ -71,8 +72,6 @@ #define NTFS_CLU_TO_POFS(vol, clu) (((u64)(clu) << (vol)->cluster_size_bits) & \ ~PAGE_MASK) -#define NTFS_B_TO_SECTOR(vol, b) ((b) >> ((vol)->sb)->s_blocksize_bits) - enum { NTFS_BLOCK_SIZE = 512, NTFS_BLOCK_SIZE_BITS = 9, @@ -154,11 +153,10 @@ static inline u64 ntfs_cluster_to_poff(const struct ntfs_volume *vol, return (clu << vol->cluster_size_bits) & ~PAGE_MASK; } -/* Convert byte offset to sector (block) number. */ -static inline sector_t ntfs_bytes_to_sector(const struct ntfs_volume *vol, - u64 bytes) +/* Convert a byte offset on the volume to a bio sector number. */ +static inline sector_t ntfs_bytes_to_bio_sector(u64 bytes) { - return bytes >> vol->sb->s_blocksize_bits; + return bytes >> SECTOR_SHIFT; } /* Global variables. */ diff --git a/fs/ntfs/reparse.c b/fs/ntfs/reparse.c index 5e483a2f9060..1a6073e22677 100644 --- a/fs/ntfs/reparse.c +++ b/fs/ntfs/reparse.c @@ -405,7 +405,7 @@ unsigned int ntfs_reparse_tag_dt_types(struct ntfs_volume *vol, unsigned long mr vi = ntfs_iget(vol->sb, mref); if (IS_ERR(vi)) - return PTR_ERR(vi); + return DT_UNKNOWN; reparse_attr = (struct reparse_point *)ntfs_attr_readall(NTFS_I(vi), AT_REPARSE_POINT, NULL, 0, &attr_size); @@ -694,8 +694,9 @@ static int update_reparse_data(struct ntfs_inode *ni, struct ntfs_index_context goto put_rp_inode; } - if (set_reparse_index(ni, xr, ((const struct reparse_point *)value)->reparse_tag) && - oldsize > 0) { + err = set_reparse_index(ni, xr, + ((const struct reparse_point *)value)->reparse_tag); + if (err && oldsize > 0) { /* * If cannot index, try to remove the reparse * data and log the error. There will be an diff --git a/fs/ntfs/runlist.c b/fs/ntfs/runlist.c index 00373e450ea7..3a61f19bcbee 100644 --- a/fs/ntfs/runlist.c +++ b/fs/ntfs/runlist.c @@ -1804,7 +1804,7 @@ merge_src_rle: new_2nd_cnt = src_cnt; new_cnt = new_1st_cnt + new_2nd_cnt + new_3rd_cnt; new_cnt += dst_rl_split.lcn >= LCN_HOLE ? 1 : 0; - new_rl = kvcalloc(new_cnt, sizeof(*new_rl), GFP_NOFS); + new_rl = kvzalloc_objs(*new_rl, new_cnt, GFP_NOFS); if (!new_rl) return ERR_PTR(-ENOMEM); @@ -1888,13 +1888,13 @@ struct runlist_element *ntfs_rl_punch_hole(struct runlist_element *dst_rl, int d punch_cnt = (int)(e_rl - s_rl) + 1; - *punch_rl = kvcalloc(punch_cnt + 1, sizeof(struct runlist_element), - GFP_NOFS); + *punch_rl = kvzalloc_objs(struct runlist_element, punch_cnt + 1, + GFP_NOFS); if (!*punch_rl) return ERR_PTR(-ENOMEM); new_cnt = dst_cnt - (int)(e_rl - s_rl + 1) + 3; - new_rl = kvcalloc(new_cnt, sizeof(struct runlist_element), GFP_NOFS); + new_rl = kvzalloc_objs(struct runlist_element, new_cnt, GFP_NOFS); if (!new_rl) { kvfree(*punch_rl); *punch_rl = NULL; @@ -2038,13 +2038,13 @@ struct runlist_element *ntfs_rl_collapse_range(struct runlist_element *dst_rl, i one_split_3 = e_rl == s_rl && begin_split && end_split; punch_cnt = (int)(e_rl - s_rl) + 1; - *punch_rl = kvcalloc(punch_cnt + 1, sizeof(struct runlist_element), - GFP_NOFS); + *punch_rl = kvzalloc_objs(struct runlist_element, punch_cnt + 1, + GFP_NOFS); if (!*punch_rl) return ERR_PTR(-ENOMEM); new_cnt = dst_cnt - (int)(e_rl - s_rl + 1) + 3; - new_rl = kvcalloc(new_cnt, sizeof(struct runlist_element), GFP_NOFS); + new_rl = kvzalloc_objs(struct runlist_element, new_cnt, GFP_NOFS); if (!new_rl) { kvfree(*punch_rl); *punch_rl = NULL; diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 30481e5d5dd4..4066bacabe37 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -557,8 +557,8 @@ static bool is_boot_sector_ntfs(const struct super_block *sb, * Check sectors per cluster value is valid and the cluster size * is not above the maximum (2MB). */ - if (b->bpb.sectors_per_cluster > 0x80 && - b->bpb.sectors_per_cluster < 0xf4) + if (b->bpb.sectors_per_cluster < 0xf4 && + !is_power_of_2(b->bpb.sectors_per_cluster)) goto not_ntfs; /* Check reserved/unused fields are really zero. */ @@ -695,7 +695,7 @@ static bool parse_ntfs_boot_sector(struct ntfs_volume *vol, * = -log2(mft_record_size) bytes. mft_record_size normaly is * 1024 bytes, which is encoded as 0xF6 (-10 in decimal). */ - vol->mft_record_size = 1 << -clusters_per_mft_record; + vol->mft_record_size = 1U << -clusters_per_mft_record; vol->mft_record_size_mask = vol->mft_record_size - 1; vol->mft_record_size_bits = ffs(vol->mft_record_size) - 1; ntfs_debug("vol->mft_record_size = %i (0x%x)", vol->mft_record_size, @@ -732,7 +732,7 @@ static bool parse_ntfs_boot_sector(struct ntfs_volume *vol, * index_record_size normaly equals 4096 bytes, which is * encoded as 0xF4 (-12 in decimal). */ - vol->index_record_size = 1 << -clusters_per_index_record; + vol->index_record_size = 1U << -clusters_per_index_record; vol->index_record_size_mask = vol->index_record_size - 1; vol->index_record_size_bits = ffs(vol->index_record_size) - 1; ntfs_debug("vol->index_record_size = %i (0x%x)", @@ -1241,9 +1241,9 @@ static bool load_and_init_attrdef(struct ntfs_volume *vol) goto failed; } NInoSetSparseDisabled(NTFS_I(ino)); - /* The size of FILE_AttrDef must be above 0 and fit inside 31 bits. */ + /* FILE_AttrDef must hold at least one entry and fit inside 31 bits. */ i_size = i_size_read(ino); - if (i_size <= 0 || i_size > 0x7fffffff) + if (i_size < (s64)sizeof(struct attr_def) || i_size > 0x7fffffff) goto iput_failed; vol->attrdef = kvzalloc(i_size, GFP_NOFS); if (!vol->attrdef) @@ -1862,7 +1862,8 @@ static int ntfs_sync_fs(struct super_block *sb, int wait) return 0; /* If there are some dirty buffers in the bdev inode */ - if (ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY)) { + if (!NVolErrors(vol) && + ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY)) { ntfs_warning(sb, "Failed to clear dirty bit in volume information flags. Run chkdsk."); err = -EIO; } @@ -2063,8 +2064,7 @@ static unsigned long __get_nr_free_mft_records(struct ntfs_volume *vol, /* If errors occurred we may well have gone below zero, fix this. */ if (nr_free < 0) nr_free = 0; - else - atomic64_set(&vol->free_mft_records, nr_free); + atomic64_set(&vol->free_mft_records, nr_free); ntfs_debug("Exiting."); return nr_free; @@ -2130,7 +2130,14 @@ static int ntfs_statfs(struct dentry *dentry, struct kstatfs *sfs) read_unlock_irqrestore(&mft_ni->size_lock, flags); /* Free inodes in fs (based on current total count). */ - sfs->f_ffree = atomic64_read(&vol->free_mft_records); + size = atomic64_read(&vol->free_mft_records); + if (unlikely(size < 0 || size > (s64)sfs->f_files)) + ntfs_warning(vol->sb, "Invalid free MFT record count %lld.", size); + if (size < 0) + size = 0; + else if (size > (s64)sfs->f_files) + size = sfs->f_files; + sfs->f_ffree = size; /* * File system id. This is extremely *nix flavour dependent and even @@ -2538,7 +2545,7 @@ static int ntfs_init_fs_context(struct fs_context *fc) struct ntfs_volume *vol; /* Allocate a new struct ntfs_volume and place it in sb->s_fs_info. */ - vol = kmalloc(sizeof(struct ntfs_volume), GFP_NOFS); + vol = kmalloc_obj(struct ntfs_volume, GFP_NOFS); if (!vol) return -ENOMEM; diff --git a/fs/ntfs/volume.h b/fs/ntfs/volume.h index 65fd3908af26..bc85a9592245 100644 --- a/fs/ntfs/volume.h +++ b/fs/ntfs/volume.h @@ -55,6 +55,10 @@ * @attrdef_size: Size of the attribute definition table in bytes. * @attrdef: Table of attribute definitions. Obtained from FILE_AttrDef. * @mft_data_pos: Mft record number at which to allocate the next mft record. + * @mft_record_reserve_pos: First record in the in-memory MFT metadata reserve + * (protected by mftbmp_lock). + * @mft_record_reserve_end: First record beyond the MFT metadata reserve + * (protected by mftbmp_lock). * @mft_zone_start: First cluster of the mft zone. * @mft_zone_end: First cluster beyond the mft zone. * @mft_zone_pos: Current position in the mft zone. @@ -119,6 +123,8 @@ struct ntfs_volume { s32 attrdef_size; struct attr_def *attrdef; s64 mft_data_pos; + s64 mft_record_reserve_pos; + s64 mft_record_reserve_end; s64 mft_zone_start; s64 mft_zone_end; s64 mft_zone_pos; @@ -252,17 +258,11 @@ static inline void ntfs_dec_free_clusters(struct ntfs_volume *vol, s64 nr) static inline void ntfs_inc_free_mft_records(struct ntfs_volume *vol, s64 nr) { - if (!NVolFreeClusterKnown(vol)) - return; - atomic64_add(nr, &vol->free_mft_records); } static inline void ntfs_dec_free_mft_records(struct ntfs_volume *vol, s64 nr) { - if (!NVolFreeClusterKnown(vol)) - return; - atomic64_sub(nr, &vol->free_mft_records); } diff --git a/fs/ntfs/wof.c b/fs/ntfs/wof.c index 8f84c2212eee..9847259e5b1a 100644 --- a/fs/ntfs/wof.c +++ b/fs/ntfs/wof.c @@ -39,8 +39,6 @@ struct ntfs_wof_workspace { struct mutex *lock; const struct ntfs_codec_ops *codec; u32 comp_unit; - void *input; - size_t input_size; void *output; void *scratch; }; @@ -97,30 +95,36 @@ static struct ntfs_wof_workspace *ntfs_wof_workspace(u8 block_size_bits) } } +/* + * Size of the buffer a chunk is read into. A chunk is read straight off the + * device, so the buffer has to hold @comp_unit bytes plus the leading partial + * sector. + */ +static size_t ntfs_wof_input_size(const struct ntfs_wof_workspace *ws) +{ + return round_up((size_t)ws->comp_unit + 511, 512); +} + static int ntfs_wof_workspace_prepare(struct ntfs_wof_workspace *ws) { - void *input, *output, *scratch; + void *output, *scratch; size_t scratch_size; - if (ws->input) + if (ws->output) return 0; - ws->input_size = round_up((size_t)ws->comp_unit + 511, 512); scratch_size = ws->codec->scratch_size(ws->comp_unit); if (!scratch_size) return -EINVAL; - input = kvmalloc(ws->input_size, GFP_NOFS); output = kvmalloc(ws->comp_unit, GFP_NOFS); scratch = kvzalloc(scratch_size, GFP_NOFS); - if (!input || !output || !scratch) { - kvfree(input); + if (!output || !scratch) { kvfree(output); kvfree(scratch); return -ENOMEM; } - ws->input = input; ws->output = output; ws->scratch = scratch; return 0; @@ -134,10 +138,8 @@ void ntfs_wof_free_workspaces(void) struct ntfs_wof_workspace *ws = ntfs_wof_workspaces[i]; mutex_lock(ws->lock); - kvfree(ws->input); kvfree(ws->output); kvfree(ws->scratch); - ws->input = NULL; ws->output = NULL; ws->scratch = NULL; mutex_unlock(ws->lock); @@ -602,6 +604,51 @@ static int ntfs_wof_try_direct(struct ntfs_wof_workspace *ws, chunk_end, src, src_len, dst_len); } +/* + * Decompress one chunk into @folio. Only this step needs the workspace, so it + * is the only step that takes the workspace lock. + */ +static int ntfs_wof_decompress_chunk(struct ntfs_wof_workspace *ws, + struct ntfs_volume *vol, + struct address_space *mapping, + struct folio *folio, loff_t folio_start, + loff_t folio_end, u64 chunk_file_offset, + char *chunk_mem, u32 chunk_size, + u32 decomp_size) +{ + loff_t chunk_end = chunk_file_offset + decomp_size; + loff_t copy_start, copy_end; + int err; + + mutex_lock(ws->lock); + err = ntfs_wof_workspace_prepare(ws); + if (err) + goto out_unlock; + + err = ntfs_wof_try_direct(ws, mapping, folio, chunk_file_offset, + chunk_end, chunk_mem, chunk_size, + decomp_size); + if (err != -EAGAIN) + goto out_unlock; + + err = ntfs_wof_decode(ws, chunk_mem, chunk_size, ws->output, + decomp_size); + if (err) { + ntfs_error(vol->sb, "Decompression failed: %d", err); + err = -EINVAL; + goto out_unlock; + } + + copy_start = max_t(loff_t, folio_start, chunk_file_offset); + copy_end = min_t(loff_t, folio_end, chunk_file_offset + decomp_size); + memcpy_to_folio(folio, copy_start - folio_start, + ws->output + copy_start - chunk_file_offset, + copy_end - copy_start); +out_unlock: + mutex_unlock(ws->lock); + return err; +} + int ntfs_read_wof_compressed_block(struct folio *folio) { struct address_space *mapping = folio->mapping; @@ -613,6 +660,8 @@ int ntfs_read_wof_compressed_block(struct folio *folio) loff_t folio_start = folio_pos(folio); loff_t folio_end = folio_next_pos(folio); char *chunk_mem; + void *input; + size_t input_size; u32 decomp_size; u64 chunk_count, chunk_idx, last_chunk, chunk_offset; int err = 0; @@ -652,10 +701,12 @@ int ntfs_read_wof_compressed_block(struct folio *folio) goto out_iput; } - mutex_lock(ws->lock); - err = ntfs_wof_workspace_prepare(ws); - if (err) - goto out_unlock_ws; + input_size = ntfs_wof_input_size(ws); + input = kvmalloc(input_size, GFP_NOFS); + if (!input) { + err = -ENOMEM; + goto out_iput; + } chunk_idx = div_u64(folio_start, ws->comp_unit); last_chunk = @@ -663,55 +714,35 @@ int ntfs_read_wof_compressed_block(struct folio *folio) chunk_count = DIV_ROUND_UP_ULL(i_size, ws->comp_unit); for (; chunk_idx <= last_chunk; chunk_idx++) { u32 chunk_size; - u64 chunk_file_offset; - loff_t chunk_end, copy_start, copy_end; decomp_size = chunk_idx + 1 == chunk_count ? i_size - chunk_idx * ws->comp_unit : ws->comp_unit; err = parse_wof_chunk_table(ni, wof_ni, chunk_idx, chunk_count, decomp_size, &chunk_offset, - &chunk_size, ws->input, - ws->input_size); + &chunk_size, input, input_size); if (err) - goto out_unlock_ws; + goto out_free_input; err = ntfs_read_wof_chunk(vol, wof_ni, chunk_offset, chunk_size, - ws->input, ws->input_size, - &chunk_mem); + input, input_size, &chunk_mem); if (err) - goto out_unlock_ws; - - chunk_file_offset = chunk_idx * ws->comp_unit; - chunk_end = chunk_file_offset + decomp_size; - err = ntfs_wof_try_direct(ws, mapping, folio, chunk_file_offset, - chunk_end, chunk_mem, chunk_size, - decomp_size); - if (!err) - continue; - if (err != -EAGAIN) - goto out_unlock_ws; + goto out_free_input; - err = ntfs_wof_decode(ws, chunk_mem, chunk_size, ws->output, - decomp_size); - if (err) { - ntfs_error(vol->sb, "Decompression failed: %d", err); - err = -EINVAL; - goto out_unlock_ws; - } - copy_start = max_t(loff_t, folio_start, chunk_file_offset); - copy_end = min_t(loff_t, folio_end, - chunk_file_offset + decomp_size); - memcpy_to_folio(folio, copy_start - folio_start, - ws->output + copy_start - chunk_file_offset, - copy_end - copy_start); + err = ntfs_wof_decompress_chunk(ws, vol, mapping, folio, + folio_start, folio_end, + chunk_idx * ws->comp_unit, + chunk_mem, chunk_size, + decomp_size); + if (err) + goto out_free_input; } if (folio_end > i_size) folio_zero_segment(folio, i_size - folio_start, folio_size(folio)); -out_unlock_ws: - mutex_unlock(ws->lock); +out_free_input: + kvfree(input); out_iput: iput(wof_inode); out: diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index e7fe29cb6028..7d6f7f6022eb 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -1044,7 +1044,7 @@ static int ovl_dir_open(struct inode *inode, struct file *file) struct ovl_dir_file *od; enum ovl_path_type type; - od = kzalloc(sizeof(struct ovl_dir_file), GFP_KERNEL); + od = kzalloc_obj(struct ovl_dir_file); if (!od) return -ENOMEM; diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index e487597337e8..bd0a3f9039d2 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1543,7 +1543,7 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc) struct ovl_fs *ofs = sb->s_fs_info; int err; - err = -EIO; + err = -EINVAL; /* The fscontext fd may have been passed to another user namespace. */ if (fc->user_ns != current_user_ns()) goto out_err; diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 204afc5e984b..1c78c695d0dd 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1240,7 +1240,7 @@ static int ignore_hardlimit(struct dquot *dquot) { struct mem_dqinfo *info = &sb_dqopt(dquot->dq_sb)->info[dquot->dq_id.type]; - return capable(CAP_SYS_RESOURCE) && + return capable_noaudit(CAP_SYS_RESOURCE) && (info->dqi_format->qf_fmt_id != QFMT_VFS_OLD || !(info->dqi_flags & DQF_ROOT_SQUASH)); } diff --git a/fs/smb/client/cifs_swn.c b/fs/smb/client/cifs_swn.c index fe10719e627e..c49ecddf4a33 100644 --- a/fs/smb/client/cifs_swn.c +++ b/fs/smb/client/cifs_swn.c @@ -443,7 +443,7 @@ static struct cifs_swn_reg *cifs_get_swn_reg(struct cifs_tcon *tcon) goto unlock; } - reg = kmalloc_obj(struct cifs_swn_reg, GFP_KERNEL); + reg = kmalloc_obj(struct cifs_swn_reg); if (reg == NULL) { ret = -ENOMEM; goto fail_unlock; diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c index 12005f46307d..c5e47a835f99 100644 --- a/fs/smb/client/cifsacl.c +++ b/fs/smb/client/cifsacl.c @@ -100,8 +100,23 @@ cifs_idmap_key_destroy(struct key *key) kfree(key->payload.data[0]); } +static int +cifs_idmap_key_vet_description(const char *description) +{ + /* + * cifs.idmap descriptions are authority-bearing inputs to the + * cifs.idmap upcall helper. Only allow the kernel to create this + * type of key using the private root_cred installed in + * init_cifs_idmap; reject userspace request_key(2)/add_key(2). + */ + if (current_cred() != root_cred) + return -EPERM; + return 0; +} + static struct key_type cifs_idmap_key_type = { .name = "cifs.idmap", + .vet_description = cifs_idmap_key_vet_description, .instantiate = cifs_idmap_key_instantiate, .destroy = cifs_idmap_key_destroy, .describe = user_describe, @@ -1081,13 +1096,13 @@ 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, u16 *pnum_aces, u16 *pnsize, + __u64 *pnmode, u16 *pnum_aces, u32 *pnsize, bool modefromsid, bool posix) { __u64 nmode; u16 num_aces = 0; - u16 nsize = 0; + u32 nsize = 0; __u64 user_mode; __u64 group_mode; __u64 other_mode; @@ -1186,17 +1201,17 @@ set_size: *pnsize = nsize; } -static __u16 replace_sids_and_copy_aces(struct smb_acl *pdacl, struct smb_acl *pndacl, - struct smb_sid *pownersid, struct smb_sid *pgrpsid, - struct smb_sid *pnownersid, struct smb_sid *pngrpsid, - int *aclflag) +static int replace_sids_and_copy_aces(struct smb_acl *pdacl, struct smb_acl *pndacl, + struct smb_sid *pownersid, struct smb_sid *pgrpsid, + struct smb_sid *pnownersid, struct smb_sid *pngrpsid, + int *aclflag, u16 *pnsize) { int i; u16 size = 0; struct smb_ace *pntace = NULL; char *acl_base = NULL; u16 src_num_aces = 0; - u16 nsize = 0; + u32 nsize = 0; struct smb_ace *pnntace = NULL; char *nacl_base = NULL; u16 ace_size = 0; @@ -1225,9 +1240,12 @@ static __u16 replace_sids_and_copy_aces(struct smb_acl *pdacl, struct smb_acl *p size += le16_to_cpu(pntace->size); nsize += ace_size; + if (nsize > U16_MAX) + return -EOVERFLOW; } - return nsize; + *pnsize = nsize; + return 0; } static int set_chmod_dacl(struct smb_acl *pdacl, struct smb_acl *pndacl, @@ -1239,7 +1257,7 @@ static int set_chmod_dacl(struct smb_acl *pdacl, struct smb_acl *pndacl, struct smb_ace *pntace = NULL; char *acl_base = NULL; u16 src_num_aces = 0; - u16 nsize = 0; + u32 nsize = 0; struct smb_ace *pnntace = NULL; char *nacl_base = NULL; u16 num_aces = 0; @@ -1290,6 +1308,8 @@ static int set_chmod_dacl(struct smb_acl *pdacl, struct smb_acl *pndacl, nsize += cifs_copy_ace(pnntace, pntace, NULL); num_aces++; + if (nsize > U16_MAX) + return -EOVERFLOW; next_ace: size += le16_to_cpu(pntace->size); @@ -1306,6 +1326,10 @@ next_ace: } finalize_dacl: + /* The DACL size field is 16-bit on the wire, see MS-DTYP 2.4.5 */ + if (nsize > U16_MAX) + return -EOVERFLOW; + pndacl->num_aces = cpu_to_le16(num_aces); pndacl->size = cpu_to_le16(nsize); @@ -1331,6 +1355,7 @@ static int parse_sec_desc(struct cifs_sb_info *cifs_sb, { int rc = 0; struct smb_sid *owner_sid_ptr, *group_sid_ptr; + unsigned int sbflags = cifs_sb_flags(cifs_sb); struct smb_acl *dacl_ptr; /* no need for SACL ptr */ char *end_of_acl; __u32 dacloffset, osidoffset, gsidoffset; @@ -1349,17 +1374,21 @@ static int parse_sec_desc(struct cifs_sb_info *cifs_sb, cifs_dbg(NOISY, "revision %d type 0x%x ooffset 0x%x goffset 0x%x sacloffset 0x%x dacloffset 0x%x\n", pntsd->revision, pntsd->type, osidoffset, gsidoffset, le32_to_cpu(pntsd->sacloffset), dacloffset); -/* cifs_dump_mem("owner_sid: ", owner_sid_ptr, 64); */ + fattr->cf_uid = cifs_sb->ctx->linux_uid; + fattr->cf_gid = cifs_sb->ctx->linux_gid; + rc = sid_from_sd(pntsd, acl_len, osidoffset, &owner_sid_ptr); if (rc) { cifs_dbg(FYI, "%s: Error %d parsing Owner SID\n", __func__, rc); return rc; } - rc = sid_to_id(cifs_sb, owner_sid_ptr, fattr, SIDOWNER); - if (rc) { - cifs_dbg(FYI, "%s: Error %d mapping Owner SID to uid\n", - __func__, rc); - return rc; + if (!(sbflags & CIFS_MOUNT_OVERR_UID)) { + rc = sid_to_id(cifs_sb, owner_sid_ptr, fattr, SIDOWNER); + if (rc) { + cifs_dbg(FYI, "%s: Error %d mapping Owner SID to uid\n", + __func__, rc); + return rc; + } } rc = sid_from_sd(pntsd, acl_len, gsidoffset, &group_sid_ptr); @@ -1368,11 +1397,13 @@ static int parse_sec_desc(struct cifs_sb_info *cifs_sb, __func__, rc); return rc; } - rc = sid_to_id(cifs_sb, group_sid_ptr, fattr, SIDGROUP); - if (rc) { - cifs_dbg(FYI, "%s: Error %d mapping Group SID to gid\n", - __func__, rc); - return rc; + if (!(sbflags & CIFS_MOUNT_OVERR_GID)) { + rc = sid_to_id(cifs_sb, group_sid_ptr, fattr, SIDGROUP); + if (rc) { + cifs_dbg(FYI, "%s: Error %d mapping Group SID to gid\n", + __func__, rc); + return rc; + } } if (dacloffset) { @@ -1451,6 +1482,8 @@ static int build_sec_desc(struct smb_ntsd *pntsd, struct smb_ntsd *pnntsd, rc = set_chmod_dacl(dacl_ptr, ndacl_ptr, owner_sid_ptr, group_sid_ptr, pnmode, mode_from_sid, posix); + if (rc) + return rc; sidsoffset = ndacloffset + le16_to_cpu(ndacl_ptr->size); /* copy the non-dacl portion of secdesc */ @@ -1526,10 +1559,12 @@ static int build_sec_desc(struct smb_ntsd *pntsd, struct smb_ntsd *pnntsd, if (dacloffset) { /* Replace ACEs for old owner with new one */ - size = replace_sids_and_copy_aces(dacl_ptr, ndacl_ptr, - owner_sid_ptr, group_sid_ptr, - nowner_sid_ptr, ngroup_sid_ptr, - aclflag); + rc = replace_sids_and_copy_aces(dacl_ptr, ndacl_ptr, + owner_sid_ptr, group_sid_ptr, + nowner_sid_ptr, ngroup_sid_ptr, + aclflag, &size); + if (rc) + goto chown_chgrp_exit; ndacl_ptr->size = cpu_to_le16(size); } @@ -1815,11 +1850,13 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode, cifs_put_tlink(tlink); return rc; } - if (mode_from_sid) - nsecdesclen += - le16_to_cpu(dacl_ptr->num_aces) * sizeof(struct smb_ace); - else /* cifsacl */ - nsecdesclen += le16_to_cpu(dacl_ptr->size); + /* + * Worst case: every ACE is rewritten with a new SID of + * SID_MAX_SUB_AUTHORITIES sub-auths -> sizeof(smb_ace) each, + * plus the smb_acl header replace_sids_and_copy_aces() emits. + */ + nsecdesclen += sizeof(struct smb_acl) + + le16_to_cpu(dacl_ptr->num_aces) * sizeof(struct smb_ace); } } diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index f5aad5f61dce..6dddbd84b93b 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1719,8 +1719,17 @@ CIFSSMBRead(const unsigned int xid, struct cifs_io_parms *io_parms, pSMBr = (READ_RSP *)rsp_iov.iov_base; if (rc) { cifs_dbg(VFS, "Send error in read = %d\n", rc); + } else if (rsp_iov.iov_len < tcon->ses->server->vals->read_rsp_size) { + /* check that the received response can hold a whole READ_RSP */ + cifs_dbg(FYI, "%s: server returned short header. got=%zu expected=%zu\n", + __func__, rsp_iov.iov_len, + tcon->ses->server->vals->read_rsp_size); + rc = smb_EIO2(smb_eio_trace_read_rsp_short, + rsp_iov.iov_len, tcon->ses->server->vals->read_rsp_size); + *nbytes = 0; } else { - int data_length = le16_to_cpu(pSMBr->DataLengthHigh); + unsigned int data_length = le16_to_cpu(pSMBr->DataLengthHigh); + __u16 data_offset = le16_to_cpu(pSMBr->DataOffset); data_length = data_length << 16; data_length += le16_to_cpu(pSMBr->DataLength); *nbytes = data_length; @@ -1728,14 +1737,21 @@ CIFSSMBRead(const unsigned int xid, struct cifs_io_parms *io_parms, /*check that DataLength would not go beyond end of SMB */ if ((data_length > CIFSMaxBufSize) || (data_length > count)) { - cifs_dbg(FYI, "bad length %d for count %d\n", - data_length, count); + cifs_dbg(FYI, "%s: bad length %u for count %u\n", + __func__, data_length, count); rc = smb_EIO2(smb_eio_trace_read_overlarge, data_length, count); *nbytes = 0; + } else if (data_offset < sizeof(*pSMBr) || + (size_t)data_offset + data_length > rsp_iov.iov_len) { + /* check that the data lies within the received response */ + cifs_dbg(FYI, "%s: bad data offset %u length %u for response of %zu\n", + __func__, data_offset, data_length, rsp_iov.iov_len); + rc = smb_EIO2(smb_eio_trace_read_bad_offset, + data_offset, data_length); + *nbytes = 0; } else { - pReadData = (char *) (&pSMBr->hdr.Protocol) + - le16_to_cpu(pSMBr->DataOffset); + pReadData = (char *) (&pSMBr->hdr.Protocol) + data_offset; /* if (rc = copy_to_user(buf, pReadData, data_length)) { cifs_dbg(VFS, "Faulting on read rc = %d\n",rc); rc = -EFAULT; @@ -3064,7 +3080,7 @@ int cifs_query_reparse_point(const unsigned int xid, end = 2 + get_bcc(&io_rsp->hdr) + (__u8 *)&io_rsp->ByteCount; start = (__u8 *)&io_rsp->hdr.Protocol + data_offset; - if (start >= end) { + if (start >= end || (size_t)(end - start) < sizeof(*buf)) { rc = smb_EIO2(smb_eio_trace_qreparse_data_area, (unsigned long)start - (unsigned long)io_rsp, (unsigned long)end - (unsigned long)io_rsp); @@ -3555,6 +3571,7 @@ int cifs_do_set_acl(const unsigned int xid, struct cifs_tcon *tcon, int rc = 0; int bytes_returned = 0; __u16 params, byte_count, data_count, param_offset, offset; + size_t cifs_acl_size, bytes_available; cifs_dbg(FYI, "In SetPosixACL (Unix) for path %s\n", fileName); setAclRetry: @@ -3574,8 +3591,7 @@ setAclRetry: } params = 6 + name_len; pSMB->MaxParameterCount = cpu_to_le16(2); - /* BB find max SMB size from sess */ - pSMB->MaxDataCount = cpu_to_le16(1000); + pSMB->MaxDataCount = cpu_to_le16(min_t(unsigned int, CIFSMaxBufSize, USHRT_MAX)); pSMB->MaxSetupCount = 0; pSMB->Reserved = 0; pSMB->Flags = 0; @@ -3587,6 +3603,15 @@ setAclRetry: parm_data = ((char *)pSMB) + offset; pSMB->ParameterOffset = cpu_to_le16(param_offset); + /* make sure we can fit the larger cifs_posix_aces in the buffer */ + cifs_acl_size = sizeof(struct cifs_posix_acl) + + (acl->a_count * sizeof(struct cifs_posix_ace)); + bytes_available = (CIFSMaxBufSize + MAX_HEADER_SIZE(tcon->ses->server)) - offset; + if (cifs_acl_size > bytes_available || cifs_acl_size > USHRT_MAX) { + rc = -E2BIG; + goto setACLerrorExit; + } + /* convert to on the wire format for POSIX ACL */ data_count = posix_acl_to_cifs(parm_data, acl, acl_type); @@ -6325,8 +6350,10 @@ CIFSSMBSetEA(const unsigned int xid, struct cifs_tcon *tcon, int name_len; int rc = 0; int bytes_returned = 0; - __u16 params, param_offset, byte_count, offset, count; + __u16 params, param_offset; + unsigned int byte_count, offset, count; int remap = cifs_remap(cifs_sb); + unsigned int total_len; cifs_dbg(FYI, "In SetEA\n"); SetEARetry: @@ -6378,6 +6405,13 @@ SetEARetry: pSMB->Reserved3 = 0; pSMB->SubCommand = cpu_to_le16(TRANS2_SET_PATH_INFORMATION); byte_count = 3 /* pad */ + params + count; + if (check_add_overflow(in_len, byte_count, &total_len) || + byte_count > U16_MAX || + total_len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE) { + cifs_dbg(VFS, "EA request too large: %u bytes\n", total_len); + cifs_buf_release(pSMB); + return -E2BIG; + } pSMB->DataCount = cpu_to_le16(count); parm_data->list_len = cpu_to_le32(count); parm_data->list.EA_flags = 0; diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index bcd7f1ae99ba..28e1ddeb6182 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -174,6 +174,8 @@ cifs_signal_cifsd_for_reconnect(struct TCP_Server_Info *server, nserver = ses->chans[i].server; if (!nserver) continue; + if (!list_empty(&nserver->rlist)) + continue; nserver->srv_count++; list_add(&nserver->rlist, &reco); } @@ -182,11 +184,15 @@ cifs_signal_cifsd_for_reconnect(struct TCP_Server_Info *server, } } + spin_lock(&cifs_tcp_ses_lock); list_for_each_entry_safe(server, nserver, &reco, rlist) { list_del_init(&server->rlist); set_need_reco(server); + spin_unlock(&cifs_tcp_ses_lock); cifs_put_tcp_session(server, 0); + spin_lock(&cifs_tcp_ses_lock); } + spin_unlock(&cifs_tcp_ses_lock); } /* @@ -1067,6 +1073,7 @@ clean_demultiplex_info(struct TCP_Server_Info *server) spin_unlock(&server->srv_lock); cancel_delayed_work_sync(&server->echo); + cancel_delayed_work_sync(&server->reconnect); spin_lock(&server->srv_lock); server->tcpStatus = CifsExiting; @@ -1823,6 +1830,7 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx, spin_lock_init(&tcp_ses->mid_counter_lock); INIT_LIST_HEAD(&tcp_ses->tcp_ses_list); INIT_LIST_HEAD(&tcp_ses->smb_ses_list); + INIT_LIST_HEAD(&tcp_ses->rlist); INIT_DELAYED_WORK(&tcp_ses->echo, cifs_echo_request); INIT_DELAYED_WORK(&tcp_ses->reconnect, smb2_reconnect_server); mutex_init(&tcp_ses->reconnect_mutex); @@ -1926,6 +1934,7 @@ out_err: kfree(tcp_ses->leaf_fullpath); if (tcp_ses->ssocket) sock_release(tcp_ses->ssocket); + smbd_destroy(tcp_ses); kfree(tcp_ses); } return ERR_PTR(rc); @@ -4189,14 +4198,25 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses, return rc; } -static int -cifs_set_vol_auth(struct smb3_fs_context *ctx, struct cifs_ses *ses) +static int set_fs_context_auth(struct smb3_fs_context *ctx, + struct cifs_ses *ses) { ctx->sectype = ses->sectype; - /* krb5 is special, since we don't need username or pw */ - if (ctx->sectype == Kerberos) + /* + * krb5 is special as we might need to pass username (passwordless) down + * to cifs.upcall(8) for keytab. + */ + if (ctx->sectype == Kerberos) { + if (ses->user_name && ses->user_name[0]) { + ctx->username = kstrndup(ses->user_name, + CIFS_MAX_USERNAME_LEN, + GFP_KERNEL); + if (!ctx->username) + return -ENOMEM; + } return 0; + } return cifs_set_cifscreds(ctx, ses); } @@ -4236,7 +4256,7 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) ctx->dfs_root_ses = master_tcon->ses->dfs_root_ses; ctx->unicode = master_tcon->ses->unicode; - rc = cifs_set_vol_auth(ctx, master_tcon->ses); + rc = set_fs_context_auth(ctx, master_tcon->ses); if (rc) { tcon = ERR_PTR(rc); goto out; diff --git a/fs/smb/client/dfs_cache.c b/fs/smb/client/dfs_cache.c index 86dba25b7a5a..29dfd7595941 100644 --- a/fs/smb/client/dfs_cache.c +++ b/fs/smb/client/dfs_cache.c @@ -123,6 +123,7 @@ static inline void free_tgts(struct cache_entry *ce) kfree(t); } + ce->numtgts = 0; WRITE_ONCE(ce->tgthint, NULL); } @@ -365,7 +366,7 @@ static struct cache_dfs_tgt *alloc_target(const char *name, int path_consumed) { struct cache_dfs_tgt *t; - t = kmalloc_obj(*t, GFP_KERNEL); + t = kmalloc_obj(*t); if (!t) return ERR_PTR(-ENOMEM); t->name = kstrdup(name, GFP_KERNEL); @@ -388,13 +389,6 @@ static int copy_ref_data(const struct dfs_info3_param *refs, int numrefs, struct cache_dfs_tgt *target; int i; - ce->ttl = max_t(int, refs[0].ttl, CACHE_MIN_TTL); - ce->etime = get_expire_time(ce->ttl); - ce->srvtype = refs[0].server_type; - ce->hdr_flags = refs[0].flags; - ce->ref_flags = refs[0].ref_flag; - ce->path_consumed = refs[0].path_consumed; - for (i = 0; i < numrefs; i++) { struct cache_dfs_tgt *t; @@ -409,12 +403,19 @@ static int copy_ref_data(const struct dfs_info3_param *refs, int numrefs, } else { list_add_tail(&t->list, &ce->tlist); } - ce->numtgts++; } target = list_first_entry_or_null(&ce->tlist, struct cache_dfs_tgt, list); + WRITE_ONCE(ce->tgthint, target); + ce->ttl = max_t(int, refs[0].ttl, CACHE_MIN_TTL); + ce->etime = get_expire_time(ce->ttl); + ce->srvtype = refs[0].server_type; + ce->hdr_flags = refs[0].flags; + ce->ref_flags = refs[0].ref_flag; + ce->path_consumed = refs[0].path_consumed; + ce->numtgts = numrefs; return 0; } @@ -634,7 +635,6 @@ static int update_cache_entry_locked(struct cache_entry *ce, const struct dfs_in } free_tgts(ce); - ce->numtgts = 0; rc = copy_ref_data(refs, numrefs, ce, th); diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index bdcd54157e6c..0d428517f454 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -999,26 +999,50 @@ static int cifs_do_truncate(const unsigned int xid, struct dentry *dentry) struct cifs_tcon *tcon; int rc; - rc = filemap_write_and_wait(inode->i_mapping); - if (is_interrupt_error(rc)) + rc = inode_lock_killable(inode); + if (rc) return -ERESTARTSYS; + + filemap_invalidate_lock(inode->i_mapping); + + rc = filemap_write_and_wait(inode->i_mapping); + if (is_interrupt_error(rc)) { + rc = -ERESTARTSYS; + goto out; + } mapping_set_error(inode->i_mapping, rc); cfile = find_writable_file(cinode, FIND_FSUID_ONLY); rc = cifs_file_flush(xid, inode, cfile); if (!rc) { if (cfile) { + struct netfs_inode *ictx = netfs_inode(inode); + tcon = tlink_tcon(cfile->tlink); server = tcon->ses->server; + netfs_wb_begin(ictx, false); rc = server->ops->set_file_size(xid, tcon, cfile, 0, false); - } - if (!rc) { - netfs_resize_file(&cinode->netfs, 0, true); - cifs_setsize(inode, 0); + if (!rc) { + netfs_resize_file(&cinode->netfs, 0, true); + cifs_setsize(inode, 0); + cifs_invalidate_cache(inode, 0); + } + netfs_wb_end(ictx); + } else { + /* + * No cached handle; evict stale pages so they can't + * be served after the file is later extended; let + * the server's O_TRUNC open response set the i_size + */ + truncate_inode_pages(inode->i_mapping, 0); cifs_invalidate_cache(inode, 0); } } + +out: + filemap_invalidate_unlock(inode->i_mapping); + inode_unlock(inode); if (cfile) cifsFileInfo_put(cfile); return rc; @@ -1491,11 +1515,18 @@ int cifs_close(struct inode *inode, struct file *file) trace_smb3_close_cached(tcon->tid, tcon->ses->Suid, cfile->fid.persistent_fid, cifs_sb->ctx->closetimeo); - queue_delayed_work(deferredclose_wq, - &cfile->deferred, cifs_sb->ctx->closetimeo); - cfile->deferred_close_scheduled = true; - spin_unlock(&cinode->deferred_lock); - return 0; + /* + * Each queued execution owns one reference. + * If nothing was queued, the reference of + * the closing file is dropped below. + */ + if (queue_delayed_work(deferredclose_wq, + &cfile->deferred, + cifs_sb->ctx->closetimeo)) { + cfile->deferred_close_scheduled = true; + spin_unlock(&cinode->deferred_lock); + return 0; + } } spin_unlock(&cinode->deferred_lock); _cifsFileInfo_put(cfile, true, false); @@ -3323,9 +3354,12 @@ void cifs_oplock_break(struct work_struct *work) wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, TASK_UNINTERRUPTIBLE); - tlink = cifs_sb_tlink(cifs_sb); - if (IS_ERR(tlink)) + tlink = cifs_get_tlink(cfile->tlink); + if (IS_ERR_OR_NULL(tlink)) { + /* drop the reference taken when the break was queued */ + _cifsFileInfo_put(cfile, false /* do not wait for ourself */, false); goto out; + } tcon = tlink_tcon(tlink); server = tcon->ses->server; diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 12ed8db10e00..1fe0ef0a95db 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -851,6 +851,7 @@ static void smb311_posix_info_to_fattr(struct cifs_fattr *fattr, struct smb311_posix_qinfo *info = &data->posix_fi; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); + unsigned int sbflags = cifs_sb_flags(cifs_sb); memset(fattr, 0, sizeof(*fattr)); @@ -895,8 +896,12 @@ out_reparse: fattr->cf_symlink_target = data->symlink_target; data->symlink_target = NULL; } - sid_to_id(cifs_sb, &data->posix_owner, fattr, SIDOWNER); - sid_to_id(cifs_sb, &data->posix_group, fattr, SIDGROUP); + fattr->cf_uid = cifs_sb->ctx->linux_uid; + fattr->cf_gid = cifs_sb->ctx->linux_gid; + if (!(sbflags & CIFS_MOUNT_OVERR_UID)) + sid_to_id(cifs_sb, &data->posix_owner, fattr, SIDOWNER); + if (!(sbflags & CIFS_MOUNT_OVERR_GID)) + sid_to_id(cifs_sb, &data->posix_group, fattr, SIDGROUP); cifs_dbg(FYI, "POSIX query info: mode 0x%x uniqueid 0x%llx nlink %d\n", fattr->cf_mode, fattr->cf_uniqueid, fattr->cf_nlink); @@ -2992,14 +2997,14 @@ int cifs_getattr(struct mnt_idmap *idmap, const struct path *path, stat->attributes |= STATX_ATTR_ENCRYPTED; /* - * If on a multiuser mount without unix extensions or cifsacl being - * enabled, and the admin hasn't overridden them, set the ownership - * to the fsuid/fsgid of the current process. + * If on a multiuser mount without unix extensions, posix extensions + * or cifsacl being enabled, and the admin hasn't overridden them, + * set the ownership to the fsuid/fsgid of the current process. */ sbflags = cifs_sb_flags(cifs_sb); if ((sbflags & CIFS_MOUNT_MULTIUSER) && !(sbflags & CIFS_MOUNT_CIFS_ACL) && - !tcon->unix_ext) { + !tcon->unix_ext && !tcon->posix_extensions) { if (!(sbflags & CIFS_MOUNT_OVERR_UID)) stat->uid = current_fsuid(); if (!(sbflags & CIFS_MOUNT_OVERR_GID)) diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index 46e1382e8e04..05168284f205 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -378,10 +378,11 @@ void cifs_queue_oplock_break(struct cifsFileInfo *cfile) * open_file_lock to enforce the validity of it for the oplock * break handler. The matching put is done at the end of the * handler. + * + * Only take a reference if the work is actually queued. */ - cifsFileInfo_get(cfile); - - queue_work(cifsoplockd_wq, &cfile->oplock_break); + if (queue_work(cifsoplockd_wq, &cfile->oplock_break)) + cifsFileInfo_get(cfile); } void cifs_done_oplock_break(struct cifsInodeInfo *cinode) @@ -787,7 +788,11 @@ parse_dfs_referrals(struct get_dfs_referral_rsp *rsp, u32 rsp_size, node->ref_flag = le16_to_cpu(ref->ReferralEntryFlags); /* copy DfsPath */ - if (le16_to_cpu(ref->DfsPathOffset) > data_end - (char *)ref) { + if (le16_to_cpu(ref->DfsPathOffset) < sizeof(*ref) || + le16_to_cpu(ref->DfsPathOffset) > data_end - (char *)ref) { + cifs_dbg(VFS, "%s: DfsPathOffset %u out of range [%zu, %td]\n", + __func__, le16_to_cpu(ref->DfsPathOffset), + sizeof(*ref), data_end - (char *)ref); rc = -EINVAL; goto parse_DFS_referrals_exit; } @@ -801,7 +806,11 @@ parse_dfs_referrals(struct get_dfs_referral_rsp *rsp, u32 rsp_size, } /* copy link target UNC */ - if (le16_to_cpu(ref->NetworkAddressOffset) > data_end - (char *)ref) { + if (le16_to_cpu(ref->NetworkAddressOffset) < sizeof(*ref) || + le16_to_cpu(ref->NetworkAddressOffset) > data_end - (char *)ref) { + cifs_dbg(VFS, "%s: NetworkAddressOffset %u out of range [%zu, %td]\n", + __func__, le16_to_cpu(ref->NetworkAddressOffset), + sizeof(*ref), data_end - (char *)ref); rc = -EINVAL; goto parse_DFS_referrals_exit; } @@ -891,8 +900,14 @@ static void tcon_super_cb(struct super_block *sb, void *arg) t1->ses->dfs_root_ses == t2->ses->dfs_root_ses) && t1->ses->server == t2->ses->server && t2->origin_fullpath && - dfs_src_pathname_equal(t2->origin_fullpath, t1->origin_fullpath)) + dfs_src_pathname_equal(t2->origin_fullpath, t1->origin_fullpath)) { + /* + * Take the active reference while iterate_supers_type() still + * holds s_umount shared. + */ + cifs_sb_active(sb); sd->sb = sb; + } spin_unlock(&t2->tc_lock); } @@ -909,15 +924,8 @@ static struct super_block *__cifs_get_super(void (*f)(struct super_block *, void for (; *fs_type; fs_type++) { iterate_supers_type(*fs_type, f, &sd); - if (sd.sb) { - /* - * Grab an active reference in order to prevent automounts (DFS links) - * of expiring and then freeing up our cifs superblock pointer while - * we're doing failover. - */ - cifs_sb_active(sd.sb); + if (sd.sb) return sd.sb; - } } pr_warn_once("%s: could not find dfs superblock\n", __func__); return ERR_PTR(-EINVAL); diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index 32a75afca8f5..9530e5b01564 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -242,9 +242,11 @@ static void cifs_posix_to_fattr(struct cifs_fattr *fattr, struct smb2_posix_info *info, struct cifs_sb_info *cifs_sb) { + unsigned int sbflags = cifs_sb_flags(cifs_sb); struct smb2_posix_info_parsed parsed; + int rc; - posix_info_parse(info, NULL, &parsed); + rc = posix_info_parse(info, NULL, &parsed); memset(fattr, 0, sizeof(*fattr)); fattr->cf_uniqueid = le64_to_cpu(info->Inode); @@ -281,8 +283,17 @@ cifs_posix_to_fattr(struct cifs_fattr *fattr, struct smb2_posix_info *info, le32_to_cpu(info->ReparseTag), le32_to_cpu(info->Mode)); - sid_to_id(cifs_sb, &parsed.owner, fattr, SIDOWNER); - sid_to_id(cifs_sb, &parsed.group, fattr, SIDGROUP); + fattr->cf_uid = cifs_sb->ctx->linux_uid; + fattr->cf_gid = cifs_sb->ctx->linux_gid; + if (rc < 0) { + cifs_dbg(VFS, "%s: failed to parse SIDs: %d\n", + __func__, rc); + } else { + if (!(sbflags & CIFS_MOUNT_OVERR_UID)) + sid_to_id(cifs_sb, &parsed.owner, fattr, SIDOWNER); + if (!(sbflags & CIFS_MOUNT_OVERR_GID)) + sid_to_id(cifs_sb, &parsed.group, fattr, SIDGROUP); + } } static void __dir_info_to_fattr(struct cifs_fattr *fattr, const void *info) diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index 5cc5b0410d48..3a27773186ae 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -3,6 +3,7 @@ * Copyright (c) 2024 Paulo Alcantara <pc@manguebit.com> */ +#include <linux/ctype.h> #include <linux/fs.h> #include <linux/stat.h> #include <linux/slab.h> @@ -159,15 +160,24 @@ static int create_native_symlink(const unsigned int xid, struct inode *inode, convert_delimiter(sym, sep); /* - * For absolute NT symlinks it is required to pass also leading - * backslash and to not mangle NT object prefix "\\??\\" and not to - * mangle colon in drive letter. But cifs_convert_path_to_utf16() - * removes leading backslash and replaces '?' and ':'. So temporary - * mask these characters in NT object prefix by '_' and then change - * them back. + * Absolute NT symlinks must retain the leading backslash, "\\??\\" + * prefix and drive-letter colon. cifs_convert_path_to_utf16() strips + * the leading backslash and maps '?' and ':', so temporarily mask + * these characters with '_' and restore them after conversion. + * + * When symlinkroot is unset, sym comes directly from the caller. + * Validate the complete "\\??\\X:" prefix before using fixed offsets + * or subtracting the NT prefix length below. Require an ASCII drive + * letter so the prefix occupies six characters in UTF-16 too. */ - if (!(sbflags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') + if (!(sbflags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') { + if (!strstarts(sym, "\\??\\") || !isascii(sym[4]) || + !isalpha(sym[4]) || sym[5] != ':') { + rc = -EINVAL; + goto out; + } sym[0] = sym[1] = sym[2] = sym[5] = '_'; + } /* * On a POSIX paths mount the symlink target is stored verbatim, so @@ -971,7 +981,8 @@ globalroot: linux_target[i*3 + 1] = '.'; linux_target[i*3 + 2] = sep; } - memcpy(linux_target + levels*3, smb_target+1, smb_target_len); /* +1 to skip leading sep */ + /* +1 to skip leading sep */ + memcpy(linux_target + levels*3, smb_target+1, smb_target_len-1); } else { /* * This is either an absolute symlink in POSIX-style format @@ -1137,25 +1148,31 @@ static bool wsl_to_fattr(struct cifs_open_info_data *data, struct cifs_sb_info *cifs_sb, u32 tag, struct cifs_fattr *fattr) { + unsigned int sbflags = cifs_sb_flags(cifs_sb); + kuid_t uid = cifs_sb->ctx->linux_uid; + kgid_t gid = cifs_sb->ctx->linux_gid; struct smb2_file_full_ea_info *ea; bool have_xattr_dev = false; + dev_t rdev = 0; + umode_t mode; u32 next = 0; + mode = fattr->cf_mode & ~S_IFMT; switch (tag) { case IO_REPARSE_TAG_LX_SYMLINK: - fattr->cf_mode |= S_IFLNK; + mode |= S_IFLNK; break; case IO_REPARSE_TAG_LX_FIFO: - fattr->cf_mode |= S_IFIFO; + mode |= S_IFIFO; break; case IO_REPARSE_TAG_AF_UNIX: - fattr->cf_mode |= S_IFSOCK; + mode |= S_IFSOCK; break; case IO_REPARSE_TAG_LX_CHR: - fattr->cf_mode |= S_IFCHR; + mode |= S_IFCHR; break; case IO_REPARSE_TAG_LX_BLK: - fattr->cf_mode |= S_IFBLK; + mode |= S_IFBLK; break; } @@ -1177,26 +1194,31 @@ static bool wsl_to_fattr(struct cifs_open_info_data *data, nlen = ea->ea_name_length; v = (void *)((u8 *)ea->ea_data + ea->ea_name_length + 1); - if (!strncmp(name, SMB2_WSL_XATTR_UID, nlen)) - fattr->cf_uid = wsl_make_kuid(cifs_sb, v); - else if (!strncmp(name, SMB2_WSL_XATTR_GID, nlen)) - fattr->cf_gid = wsl_make_kgid(cifs_sb, v); - else if (!strncmp(name, SMB2_WSL_XATTR_MODE, nlen)) { + if (!strncmp(name, SMB2_WSL_XATTR_UID, nlen)) { + if (!(sbflags & CIFS_MOUNT_OVERR_UID)) + uid = wsl_make_kuid(cifs_sb, v); + } else if (!strncmp(name, SMB2_WSL_XATTR_GID, nlen)) { + if (!(sbflags & CIFS_MOUNT_OVERR_GID)) + gid = wsl_make_kgid(cifs_sb, v); + } else if (!strncmp(name, SMB2_WSL_XATTR_MODE, nlen)) { /* File type in reparse point tag and in xattr mode must match. */ - if (S_DT(fattr->cf_mode) != S_DT(le32_to_cpu(*(__le32 *)v))) + if (S_DT(mode) != S_DT(get_unaligned_le32(v))) return false; - fattr->cf_mode = (umode_t)le32_to_cpu(*(__le32 *)v); + mode = get_unaligned_le32(v); } else if (!strncmp(name, SMB2_WSL_XATTR_DEV, nlen)) { - fattr->cf_rdev = reparse_mkdev(v); + rdev = reparse_mkdev(v); have_xattr_dev = true; } } while (next); out: - /* Major and minor numbers for char and block devices are mandatory. */ if (!have_xattr_dev && (tag == IO_REPARSE_TAG_LX_CHR || tag == IO_REPARSE_TAG_LX_BLK)) return false; + fattr->cf_uid = uid; + fattr->cf_gid = gid; + fattr->cf_mode = mode; + fattr->cf_rdev = rdev; return true; } @@ -1205,6 +1227,7 @@ static bool posix_reparse_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_open_info_data *data) { struct reparse_nfs_data_buffer *buf = (struct reparse_nfs_data_buffer *)data->reparse.buf; + umode_t ftype; if (buf == NULL) return true; @@ -1220,7 +1243,7 @@ static bool posix_reparse_to_fattr(struct cifs_sb_info *cifs_sb, WARN_ON_ONCE(1); return false; } - fattr->cf_mode |= S_IFCHR; + ftype = S_IFCHR; fattr->cf_rdev = reparse_mkdev(buf->DataBuffer); break; case NFS_SPECFILE_BLK: @@ -1228,22 +1251,23 @@ static bool posix_reparse_to_fattr(struct cifs_sb_info *cifs_sb, WARN_ON_ONCE(1); return false; } - fattr->cf_mode |= S_IFBLK; + ftype = S_IFBLK; fattr->cf_rdev = reparse_mkdev(buf->DataBuffer); break; case NFS_SPECFILE_FIFO: - fattr->cf_mode |= S_IFIFO; + ftype = S_IFIFO; break; case NFS_SPECFILE_SOCK: - fattr->cf_mode |= S_IFSOCK; + ftype = S_IFSOCK; break; case NFS_SPECFILE_LNK: - fattr->cf_mode |= S_IFLNK; + ftype = S_IFLNK; break; default: WARN_ON_ONCE(1); return false; } + fattr->cf_mode = (fattr->cf_mode & ~S_IFMT) | ftype; return true; } @@ -1271,6 +1295,7 @@ bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb, break; case 0: /* SMB1 symlink */ case IO_REPARSE_TAG_SYMLINK: + fattr->cf_mode &= ~S_IFMT; fattr->cf_mode |= S_IFLNK; break; default: diff --git a/fs/smb/client/reparse.h b/fs/smb/client/reparse.h index 49efd85b1e94..05b2cecb4495 100644 --- a/fs/smb/client/reparse.h +++ b/fs/smb/client/reparse.h @@ -9,6 +9,7 @@ #include <linux/fs.h> #include <linux/stat.h> #include <linux/uidgid.h> +#include <linux/unaligned.h> #include "fs_context.h" #include "cifsglob.h" #include "../common/smbfsctl.h" @@ -23,7 +24,7 @@ static inline dev_t reparse_mkdev(void *ptr) { - u64 v = le64_to_cpu(*(__le64 *)ptr); + u64 v = get_unaligned_le64(ptr); return MKDEV(v & 0xffffffff, v >> 32); } @@ -31,7 +32,7 @@ static inline dev_t reparse_mkdev(void *ptr) static inline kuid_t wsl_make_kuid(struct cifs_sb_info *cifs_sb, void *ptr) { - u32 uid = le32_to_cpu(*(__le32 *)ptr); + u32 uid = get_unaligned_le32(ptr); if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_OVERR_UID) return cifs_sb->ctx->linux_uid; @@ -41,7 +42,7 @@ static inline kuid_t wsl_make_kuid(struct cifs_sb_info *cifs_sb, static inline kgid_t wsl_make_kgid(struct cifs_sb_info *cifs_sb, void *ptr) { - u32 gid = le32_to_cpu(*(__le32 *)ptr); + u32 gid = get_unaligned_le32(ptr); if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_OVERR_GID) return cifs_sb->ctx->linux_gid; diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index 7cf7dd104f7c..e095f41b5882 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -149,9 +149,9 @@ int cifs_try_adding_channels(struct cifs_ses *ses) int old_chan_count, new_chan_count; int left; int rc = 0; - int tries = 0; + int tries = 0, attempts; size_t iface_weight = 0, iface_min_speed = 0; - struct cifs_server_iface *iface = NULL, *niface = NULL; + struct cifs_server_iface *iface = NULL, *candidate = NULL; struct cifs_server_iface *last_iface = NULL; spin_lock(&ses->chan_lock); @@ -197,67 +197,89 @@ int cifs_try_adding_channels(struct cifs_ses *ses) break; } - if (!iface) - iface = list_first_entry(&ses->iface_list, struct cifs_server_iface, - iface_head); last_iface = list_last_entry(&ses->iface_list, struct cifs_server_iface, iface_head); iface_min_speed = last_iface->speed; + spin_unlock(&ses->iface_lock); - list_for_each_entry_safe_from(iface, niface, &ses->iface_list, - iface_head) { - /* do not mix rdma and non-rdma interfaces */ - if (iface->rdma_capable != ses->server->rdma) - continue; - - /* skip ifaces that are unusable */ - if (!iface->is_active || - (is_ses_using_iface(ses, iface) && - !iface->rss_capable)) - continue; + attempts = 0; + while (left > 0) { + spin_lock(&ses->iface_lock); - /* check if we already allocated enough channels */ - iface_weight = iface->speed / iface_min_speed; + /* + * iface_lock must be dropped while opening a channel, + * and a concurrent interface refresh may remove and + * free entries during that window, so no list entry + * may be kept across it without a reference. Scan + * the list from the beginning each time and only pass + * a referenced candidate to cifs_ses_add_channel(); + * weight_fulfilled tracks the progress so that no + * iface is selected beyond its weight. + */ + candidate = NULL; + list_for_each_entry(iface, &ses->iface_list, iface_head) { + /* do not mix rdma and non-rdma interfaces */ + if (iface->rdma_capable != ses->server->rdma) + continue; + + /* skip ifaces that are unusable */ + if (!iface->is_active || + (is_ses_using_iface(ses, iface) && + !iface->rss_capable)) + continue; + + /* check if we already allocated enough channels */ + iface_weight = iface->speed / iface_min_speed; + + if (iface->weight_fulfilled >= iface_weight) + continue; + + /* take ref before unlock */ + kref_get(&iface->refcount); + candidate = iface; + break; + } - if (iface->weight_fulfilled >= iface_weight) - continue; + if (!candidate) { + /* no usable iface. reset weight_fulfilled and start over */ + list_for_each_entry(iface, &ses->iface_list, iface_head) + iface->weight_fulfilled = 0; + spin_unlock(&ses->iface_lock); + break; + } - /* take ref before unlock */ - kref_get(&iface->refcount); + attempts++; + if (attempts > 3 * ses->chan_max) { + kref_put(&candidate->refcount, release_iface); + spin_unlock(&ses->iface_lock); + break; + } spin_unlock(&ses->iface_lock); - rc = cifs_ses_add_channel(ses, iface); + rc = cifs_ses_add_channel(ses, candidate); spin_lock(&ses->iface_lock); if (rc) { cifs_dbg(VFS, "failed to open extra channel on iface:%pIS rc=%d\n", - &iface->sockaddr, + &candidate->sockaddr, rc); /* failure to add chan should increase weight */ - iface->weight_fulfilled++; - kref_put(&iface->refcount, release_iface); + candidate->weight_fulfilled++; + kref_put(&candidate->refcount, release_iface); + spin_unlock(&ses->iface_lock); continue; } - iface->num_channels++; - iface->weight_fulfilled++; + candidate->num_channels++; + candidate->weight_fulfilled++; cifs_info("successfully opened new channel on iface:%pIS\n", - &iface->sockaddr); - break; - } - - /* reached end of list. reset weight_fulfilled and start over */ - if (list_entry_is_head(iface, &ses->iface_list, iface_head)) { - list_for_each_entry(iface, &ses->iface_list, iface_head) - iface->weight_fulfilled = 0; + &candidate->sockaddr); spin_unlock(&ses->iface_lock); - iface = NULL; - continue; - } - spin_unlock(&ses->iface_lock); - left--; - new_chan_count++; + left--; + new_chan_count++; + break; + } } return new_chan_count - old_chan_count; diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 98ea5c6c34af..13fe8e3b48f3 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -77,6 +77,17 @@ static int parse_posix_sids(struct cifs_open_info_data *data, sidsbuf = (u8 *)qi + le16_to_cpu(qi->OutputBufferOffset) + qi_len; sidsbuf_end = sidsbuf + out_len - qi_len; + if (sidsbuf_end < sidsbuf) { + cifs_dbg(VFS, "%s: server-supplied out_len %u caused pointer wraparound\n", + __func__, out_len); + return -EINVAL; + } + if (sidsbuf_end > (u8 *)rsp_iov->iov_base + rsp_iov->iov_len) { + cifs_dbg(VFS, "%s: server-supplied out_len %u overruns iov by %td bytes\n", + __func__, out_len, + sidsbuf_end - ((u8 *)rsp_iov->iov_base + rsp_iov->iov_len)); + return -EINVAL; + } owner_len = posix_info_sid_size(sidsbuf, sidsbuf_end); if (owner_len == -1) @@ -237,7 +248,7 @@ replay_again: num_rqst = 0; server = cifs_pick_channel(ses); - vars = kzalloc_obj(*vars, GFP_KERNEL); + vars = kzalloc_obj(*vars); if (vars == NULL) { rc = -ENOMEM; goto out; diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c index 9068175e57cd..0cfe60ae42c3 100644 --- a/fs/smb/client/smb2misc.c +++ b/fs/smb/client/smb2misc.c @@ -85,6 +85,36 @@ static const __le16 smb2_rsp_struct_sizes[NUMBER_OF_SMB2_COMMANDS] = { /* SMB2_OPLOCK_BREAK */ cpu_to_le16(24) }; +/* + * Minimum received PDU size for commands whose response carries a + * variable-length data area. A non-zero entry marks the command as + * having one, and gives the length smb2_check_message() requires + * before smb2_get_data_area_len() reads the offset and length fields + * out of the fixed response struct. + */ +static const size_t smb2_min_pdu_len[NUMBER_OF_SMB2_COMMANDS] = { + /* SMB2_NEGOTIATE */ sizeof(struct smb2_negotiate_rsp), + /* SMB2_SESSION_SETUP */ sizeof(struct smb2_sess_setup_rsp), + /* SMB2_LOGOFF */ 0, + /* SMB2_TREE_CONNECT */ 0, + /* SMB2_TREE_DISCONNECT */ 0, + /* SMB2_CREATE */ sizeof(struct smb2_create_rsp), + /* SMB2_CLOSE */ 0, + /* SMB2_FLUSH */ 0, + /* SMB2_READ */ sizeof(struct smb2_read_rsp), + /* SMB2_WRITE */ 0, + /* SMB2_LOCK */ 0, + /* SMB2_IOCTL */ sizeof(struct smb2_ioctl_rsp), + /* SMB2_CANCEL */ 0, + /* SMB2_ECHO */ 0, + /* SMB2_QUERY_DIRECTORY */ sizeof(struct smb2_query_directory_rsp), + /* SMB2_CHANGE_NOTIFY */ sizeof(struct smb2_change_notify_rsp), + /* SMB2_QUERY_INFO */ sizeof(struct smb2_query_info_rsp), + /* SMB2_SET_INFO */ 0, + /* SMB2_OPLOCK_BREAK */ 0, +}; + +#define smb2_has_data_area(cmd) (smb2_min_pdu_len[cmd] != 0) #define SMB311_NEGPROT_BASE_SIZE (sizeof(struct smb2_hdr) + sizeof(struct smb2_negotiate_rsp)) static __u32 get_neg_ctxt_len(struct smb2_hdr *hdr, __u32 len, @@ -233,6 +263,16 @@ smb2_check_message(char *buf, unsigned int pdu_len, unsigned int len, } } + if ((shdr->Status == STATUS_SUCCESS || + shdr->Status == STATUS_MORE_PROCESSING_REQUIRED || + pdu->StructureSize2 != SMB2_ERROR_STRUCTURE_SIZE2_LE) && + smb2_has_data_area(command) && + len < smb2_min_pdu_len[command]) { + cifs_server_dbg(VFS, "SMB2 command %d response too short: %u < %zu\n", + command, len, smb2_min_pdu_len[command]); + return 1; + } + have_data = false; data_area_overlap = false; calc_len = __smb2_calc_size(buf, &have_data, &data_area_overlap); @@ -299,33 +339,6 @@ smb2_check_message(char *buf, unsigned int pdu_len, unsigned int len, } /* - * The size of the variable area depends on the offset and length fields - * located in different fields for various SMB2 responses. SMB2 responses - * with no variable length info, show an offset of zero for the offset field. - */ -static const bool has_smb2_data_area[NUMBER_OF_SMB2_COMMANDS] = { - /* SMB2_NEGOTIATE */ true, - /* SMB2_SESSION_SETUP */ true, - /* SMB2_LOGOFF */ false, - /* SMB2_TREE_CONNECT */ false, - /* SMB2_TREE_DISCONNECT */ false, - /* SMB2_CREATE */ true, - /* SMB2_CLOSE */ false, - /* SMB2_FLUSH */ false, - /* SMB2_READ */ true, - /* SMB2_WRITE */ false, - /* SMB2_LOCK */ false, - /* SMB2_IOCTL */ true, - /* SMB2_CANCEL */ false, /* BB CHECK this not listed in documentation */ - /* SMB2_ECHO */ false, - /* SMB2_QUERY_DIRECTORY */ true, - /* SMB2_CHANGE_NOTIFY */ true, - /* SMB2_QUERY_INFO */ true, - /* SMB2_SET_INFO */ false, - /* SMB2_OPLOCK_BREAK */ false -}; - -/* * Returns the pointer to the beginning of the data area. Length of the data * area and the offset to it (from the beginning of the smb are also returned. */ @@ -451,7 +464,7 @@ __smb2_calc_size(void *buf, bool *have_data, bool *data_area_overlap) */ len += le16_to_cpu(pdu->StructureSize2); - if (has_smb2_data_area[le16_to_cpu(shdr->Command)] == false) + if (!smb2_has_data_area(le16_to_cpu(shdr->Command))) goto calc_size_exit; smb2_get_data_area_len(&offset, &data_length, shdr); diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 7d6738ffcb80..3464470d3297 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -785,9 +785,9 @@ next_iface: break; } /* Validate that Next doesn't point beyond the buffer */ - if (next > bytes_left) { - cifs_dbg(VFS, "%s: invalid Next pointer %zu > %zd\n", - __func__, next, bytes_left); + if (next < sizeof(*p) || next > bytes_left) { + cifs_dbg(VFS, "%s: invalid Next pointer %zu out of range [%zu, %zd]\n", + __func__, next, sizeof(*p), bytes_left); rc = -EINVAL; goto out; } @@ -1053,8 +1053,9 @@ move_smb2_ea_to_cifs(char *dst, size_t dst_size, char *name, *value; size_t buf_size = dst_size; size_t name_len, value_len, user_name_len; + u32 next_off; - while (src_size > 0) { + while (src_size >= sizeof(*src)) { name_len = (size_t)src->ea_name_length; value_len = (size_t)le16_to_cpu(src->ea_value_length); @@ -1110,14 +1111,22 @@ move_smb2_ea_to_cifs(char *dst, size_t dst_size, if (!src->next_entry_offset) break; - if (src_size < le32_to_cpu(src->next_entry_offset)) { - /* stop before overrun buffer */ - rc = -ERANGE; - break; + next_off = le32_to_cpu(src->next_entry_offset); + if (next_off < sizeof(*src) || src_size < next_off) { + cifs_dbg(FYI, "EA next_entry_offset %u out of range [%zu, %zu]\n", + next_off, sizeof(*src), src_size); + rc = smb_EIO2(smb_eio_trace_ea_next_offset, + next_off, src_size); + goto out; + } + src_size -= next_off; + src = (void *)((char *)src + next_off); + if (src_size > 0 && src_size < sizeof(*src)) { + cifs_dbg(FYI, "EA next_entry_offset %u left truncated entry (%zu bytes)\n", + next_off, src_size); + rc = smb_EIO2(smb_eio_trace_ea_next_offset, next_off, src_size); + goto out; } - src_size -= le32_to_cpu(src->next_entry_offset); - src = (void *)((char *)src + - le32_to_cpu(src->next_entry_offset)); } /* didn't find the named attribute */ @@ -1839,31 +1848,31 @@ free_vars: * * @tcon: destination file tcon * @bytes_left: how many bytes are left to copy + * @chunk_size: maximum size of a single chunk * * Return: maximum number of chunks with which Chunks[] can be filled. */ static inline u32 -calc_chunk_count(struct cifs_tcon *tcon, u64 bytes_left) +calc_chunk_count(struct cifs_tcon *tcon, u64 bytes_left, u32 chunk_size) { u32 max_chunks = READ_ONCE(tcon->max_chunks); u32 max_bytes_copy = READ_ONCE(tcon->max_bytes_copy); - u32 max_bytes_chunk = READ_ONCE(tcon->max_bytes_chunk); u64 need; u32 allowed; - if (!max_bytes_chunk || !max_bytes_copy || !max_chunks) + if (!chunk_size || !max_bytes_copy || !max_chunks) return 0; /* chunks needed for the remaining bytes */ - need = DIV_ROUND_UP_ULL(bytes_left, max_bytes_chunk); + need = DIV_ROUND_UP_ULL(bytes_left, chunk_size); /* chunks allowed per cc request */ - allowed = DIV_ROUND_UP(max_bytes_copy, max_bytes_chunk); + allowed = DIV_ROUND_UP(max_bytes_copy, chunk_size); return (u32)umin(need, umin(max_chunks, allowed)); } /** - * smb2_copychunk_range - server-side copy of data range + * __smb2_copychunk_range - server-side copy of data range * * @xid: transaction id * @src_file: source file @@ -1875,15 +1884,15 @@ calc_chunk_count(struct cifs_tcon *tcon, u64 bytes_left) * Obtains a resume key for @src_file and issues FSCTL_SRV_COPYCHUNK_WRITE * IOCTLs, splitting the request into chunks limited by tcon->max_*. * - * Return: @len on success; negative errno on failure. + * Return: 0 on success; negative errno on failure. */ -static ssize_t -smb2_copychunk_range(const unsigned int xid, - struct cifsFileInfo *src_file, - struct cifsFileInfo *dst_file, - u64 src_off, - u64 len, - u64 dst_off) +static int +__smb2_copychunk_range(const unsigned int xid, + struct cifsFileInfo *src_file, + struct cifsFileInfo *dst_file, + u64 src_off, + u64 len, + u64 dst_off) { int rc = 0; unsigned int ret_data_len = 0; @@ -1891,12 +1900,14 @@ smb2_copychunk_range(const unsigned int xid, struct copychunk_ioctl_rsp *cc_rsp = NULL; struct cifs_tcon *tcon; struct srv_copychunk *chunk; - u32 chunks, chunk_count, chunk_bytes; + u32 chunks, chunk_count, chunk_bytes, chunk_size; u32 copy_bytes, copy_bytes_left; u32 chunks_written, bytes_written; u64 total_bytes_left = len; u64 src_off_prev, dst_off_prev; + u64 max_chunk = 0; u32 retries = 0; + bool reverse = false; tcon = tlink_tcon(dst_file->tlink); @@ -1904,8 +1915,50 @@ smb2_copychunk_range(const unsigned int xid, dst_file->fid.volatile_fid, tcon->tid, tcon->ses->Suid, src_off, dst_off, len); + /* + * Same-file left shifts are safe in forward order. For a right shift, + * let L be the copy length, delta the distance between the source and + * destination, and C the normal chunk size: + * + * delta >= L: copy forwards using C + * delta < L: + * delta >= C: copy backwards using C + * delta < C: copy backwards with chunks limited to delta + * + * Copying backwards prevents one chunk from overwriting data needed by + * a later chunk. Limiting the chunk size to delta prevents an individual + * chunk from overlapping itself. + * This limit can be removed once all supported servers handle overlapping + * descriptors safely. + * + * A small right shift over a large range may therefore require many + * chunks. + */ + if (src_file == dst_file && dst_off > src_off) { + u64 delta = dst_off - src_off; + + if (delta < len) { + reverse = true; + max_chunk = delta; + } + } + + /* + * A backward copy walks the offsets down from the end of the range. + * Do this once, outside the retry loop, so a retry does not move the + * offsets again. + */ + if (reverse) { + src_off += len; + dst_off += len; + } + retry: - chunk_count = calc_chunk_count(tcon, total_bytes_left); + chunk_size = READ_ONCE(tcon->max_bytes_chunk); + if (max_chunk && max_chunk < chunk_size) + chunk_size = (u32)max_chunk; + + chunk_count = calc_chunk_count(tcon, total_bytes_left, chunk_size); if (!chunk_count) { rc = -EOPNOTSUPP; goto out; @@ -1946,16 +1999,21 @@ retry: while (copy_bytes_left > 0 && chunks < chunk_count) { chunk = &cc_req->Chunks[chunks++]; + chunk_bytes = umin(copy_bytes_left, chunk_size); + if (reverse) { + src_off -= chunk_bytes; + dst_off -= chunk_bytes; + } + chunk->SourceOffset = cpu_to_le64(src_off); chunk->TargetOffset = cpu_to_le64(dst_off); - - chunk_bytes = umin(copy_bytes_left, tcon->max_bytes_chunk); - chunk->Length = cpu_to_le32(chunk_bytes); /* Buffer is zeroed, no need to set chunk->Reserved = 0 */ - src_off += chunk_bytes; - dst_off += chunk_bytes; + if (!reverse) { + src_off += chunk_bytes; + dst_off += chunk_bytes; + } copy_bytes_left -= chunk_bytes; copy_bytes += chunk_bytes; @@ -2003,6 +2061,18 @@ retry: goto out; } + /* + * A successful COPYCHUNK should copy every descriptor (MS-SMB2 + * 3.3.5.15.6). Reject a short backward copy because the rewind + * below only supports forward copying. + */ + if (unlikely(reverse && bytes_written < copy_bytes)) { + cifs_tcon_dbg(VFS, "Copychunk short write %u/%u (reverse)\n", + bytes_written, copy_bytes); + rc = -EIO; + goto out; + } + /* Partial write: rewind */ if (bytes_written < copy_bytes) { u32 delta = copy_bytes - bytes_written; @@ -2064,10 +2134,27 @@ out: trace_smb3_copychunk_done(xid, src_file->fid.volatile_fid, dst_file->fid.volatile_fid, tcon->tid, tcon->ses->Suid, src_off, dst_off, len); - return len; + return 0; } } +static ssize_t +smb2_copychunk_range(const unsigned int xid, + struct cifsFileInfo *src_file, + struct cifsFileInfo *dst_file, + u64 src_off, + u64 len, + u64 dst_off) +{ + int rc; + + rc = __smb2_copychunk_range(xid, src_file, dst_file, src_off, len, + dst_off); + if (rc) + return rc; + return len; +} + static int smb2_flush_file(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *fid) @@ -2218,7 +2305,7 @@ smb2_duplicate_extents(const unsigned int xid, trgtfile->fid.volatile_fid, tcon->tid, tcon->ses->Suid, src_off, dest_off, len); inode = d_inode(trgtfile->dentry); - if (inode->i_size < dest_off + len) { + if (i_size_read(inode) < dest_off + len) { rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false); if (rc) goto duplicate_extents_out; @@ -2235,7 +2322,10 @@ smb2_duplicate_extents(const unsigned int xid, if (ret_data_len > 0) cifs_dbg(FYI, "Non-zero response length in duplicate extents\n"); - if (rc == 0) { + if (rc) { + CIFS_I(inode)->time = 0; /* force reval */ + cifs_invalidate_cache(inode, 0); + } else { qrc = SMB2_query_info(xid, tcon, trgtfile->fid.persistent_fid, trgtfile->fid.volatile_fid, &file_inf); spin_lock(&inode->i_lock); @@ -2373,8 +2463,14 @@ smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon, * and retry the ioctl again with larger array size sufficient * to hold all of the snapshot GMT tokens on the second try. */ - if (snapshot_in.snapshot_array_size < GMT_TOKEN_SIZE) + if (snapshot_in.snapshot_array_size < GMT_TOKEN_SIZE) { + if (ret_data_len < sizeof(struct smb_snapshot_array)) { + rc = -EIO; + kfree(retbuf); + return rc; + } ret_data_len = sizeof(struct smb_snapshot_array); + } /* * We return struct SRV_SNAPSHOT_ARRAY, followed by @@ -3441,6 +3537,13 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, trace_smb3_zero_enter(xid, cfile->fid.persistent_fid, tcon->tid, ses->Suid, offset, len); + new_size = offset + len; + if (!keep_size && i_size_read(inode) < new_size) { + rc = inode_newsize_ok(inode, new_size); + if (rc) + goto out; + } + filemap_invalidate_lock(inode->i_mapping); netfs_read_sizes(inode, &i_size, &remote_i_size, &zero_point); @@ -3464,6 +3567,9 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, if (keep_size == false && !CIFS_CACHE_READ(cifsi)) goto zero_range_exit; + fscache_invalidate(cifs_inode_cookie(inode), NULL, + i_size_read(inode), 0); + rc = smb3_zero_data(file, tcon, offset, len, xid); if (rc < 0) goto zero_range_exit; @@ -3471,7 +3577,6 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, /* * do we also need to change the size of the file? */ - new_size = offset + len; if (keep_size == false && (unsigned long long)i_size_read(inode) < new_size) { rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, cfile->pid, new_size); @@ -3488,6 +3593,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, zero_range_exit: filemap_invalidate_unlock(inode->i_mapping); + out: free_xid(xid); if (rc) trace_smb3_zero_err(xid, cfile->fid.persistent_fid, tcon->tid, @@ -3533,6 +3639,8 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, */ truncate_pagecache_range(inode, offset, offset + len - 1); netfs_wait_for_outstanding_io(inode); + fscache_invalidate(cifs_inode_cookie(inode), NULL, + i_size_read(inode), 0); cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len); @@ -3938,18 +4046,26 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon, } filemap_invalidate_lock(inode->i_mapping); - rc = filemap_write_and_wait_range(inode->i_mapping, off, old_eof - 1); + rc = filemap_write_and_wait_range(inode->i_mapping, + round_down(off, PAGE_SIZE), + old_eof - 1); if (rc < 0) goto out_2; - truncate_pagecache_range(inode, off, old_eof); + netfs_wait_for_outstanding_io(inode); + /* + * Invalidate cached folios from the page containing off to EOF before + * moving data on the server, so subsequent reads do not see stale data. + */ + truncate_pagecache_range(inode, round_down(off, PAGE_SIZE), -1); + fscache_invalidate(cifs_inode_cookie(inode), NULL, old_eof, 0); + spin_lock(&inode->i_lock); netfs_write_zero_point(inode, old_eof); spin_unlock(&inode->i_lock); - netfs_wait_for_outstanding_io(inode); - rc = smb2_copychunk_range(xid, cfile, cfile, off + len, - old_eof - off - len, off); + rc = __smb2_copychunk_range(xid, cfile, cfile, off + len, + old_eof - off - len, off); if (rc < 0) goto out_2; @@ -3982,7 +4098,7 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, struct cifsFileInfo *cfile = file->private_data; struct inode *inode = file_inode(file); struct cifsInodeInfo *cifsi = CIFS_I(inode); - __u64 count, old_eof, new_eof; + loff_t old_eof, new_eof; xid = get_xid(); @@ -3992,15 +4108,32 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, goto out; } - count = old_eof - off; - new_eof = old_eof + len; + if (check_add_overflow(old_eof, len, &new_eof)) { + rc = -EFBIG; + goto out; + } + rc = inode_newsize_ok(inode, new_eof); + if (rc) + goto out; + + /* SET_ZERO_DATA creates a hole only in a sparse file. */ + rc = smb2_set_sparse(xid, tcon, cfile, inode, true); + if (rc) + goto out; filemap_invalidate_lock(inode->i_mapping); - rc = filemap_write_and_wait_range(inode->i_mapping, off, new_eof - 1); + rc = filemap_write_and_wait_range(inode->i_mapping, + round_down(off, PAGE_SIZE), + old_eof - 1); if (rc < 0) goto out_2; - truncate_pagecache_range(inode, off, old_eof); netfs_wait_for_outstanding_io(inode); + /* + * Invalidate cached folios from the page containing off to EOF before + * moving data on the server, so subsequent reads do not see stale data. + */ + truncate_pagecache_range(inode, round_down(off, PAGE_SIZE), -1); + fscache_invalidate(cifs_inode_cookie(inode), NULL, old_eof, 0); rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, cfile->pid, new_eof); @@ -4013,7 +4146,12 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, spin_unlock(&inode->i_lock); fscache_resize_cookie(cifs_inode_cookie(inode), i_size_read(inode)); - rc = smb2_copychunk_range(xid, cfile, cfile, off, count, off + len); + /* + * Move [off, old_eof) right by len. The helper copies backwards if the + * source and destination ranges overlap. + */ + rc = __smb2_copychunk_range(xid, cfile, cfile, off, old_eof - off, + off + len); if (rc < 0) goto out_2; spin_lock(&inode->i_lock); @@ -5242,11 +5380,13 @@ receive_encrypted_standard(struct TCP_Server_Info *server, length = decrypt_raw_data(server, buf, buf_size, NULL, false); if (length) return length; + pdu_length = buf_size; next_is_large = server->large_buf; one_more: shdr = (struct smb2_hdr *)buf; next_cmd = le32_to_cpu(shdr->NextCommand); + server->total_read = next_cmd ? next_cmd : pdu_length; if (*num_mids >= MAX_COMPOUND) { cifs_server_dbg(VFS, "too many PDUs in compound\n"); @@ -5254,8 +5394,15 @@ one_more: } if (next_cmd) { - if (WARN_ON_ONCE(next_cmd > pdu_length)) + if (next_cmd < MID_HEADER_SIZE(server) || + next_cmd > pdu_length || + pdu_length - next_cmd < MID_HEADER_SIZE(server)) { + unsigned int max_next = pdu_length > (unsigned int)MID_HEADER_SIZE(server) ? + pdu_length - (unsigned int)MID_HEADER_SIZE(server) : 0; + cifs_server_dbg(VFS, "invalid NextCommand offset %u out of range [%zu, %u]\n", + next_cmd, MID_HEADER_SIZE(server), max_next); return -1; + } if (next_is_large) next_buffer = (char *)cifs_buf_get(); else @@ -5291,6 +5438,7 @@ one_more: server->bigbuf = buf = next_buffer; else server->smallbuf = buf = next_buffer; + next_buffer = NULL; goto one_more; } else if (ret != 0) { /* diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index dea05aeb53a1..880ce12f50c4 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -189,18 +189,19 @@ cifs_chan_skip_or_disable(struct cifs_ses *ses, spin_unlock(&ses->chan_lock); /* - * the above reference of server by channel - * needs to be dropped without holding chan_lock - * as cifs_put_tcp_session takes a higher lock - * i.e. cifs_tcp_ses_lock + * signal the channel and its primary server to + * reconnect before dropping the above reference of + * server by channel, which is done without holding + * chan_lock as cifs_put_tcp_session takes a higher + * lock i.e. cifs_tcp_ses_lock */ - cifs_put_tcp_session(server, from_reconnect); - cifs_signal_cifsd_for_reconnect(server, false); /* mark primary server as needing reconnect */ pserver = server->primary_server; cifs_signal_cifsd_for_reconnect(pserver, false); + + cifs_put_tcp_session(server, from_reconnect); skip_terminate: return -EHOSTDOWN; } diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h index 12241abb8e2e..bb8d0197cb54 100644 --- a/fs/smb/client/trace.h +++ b/fs/smb/client/trace.h @@ -27,6 +27,7 @@ EM(smb_eio_trace_copychunk_overcopy_c, "copychunk_overcopy_c") \ EM(smb_eio_trace_create_rsp_too_small, "create_rsp_too_small") \ EM(smb_eio_trace_dfsref_no_rsp, "dfsref_no_rsp") \ + EM(smb_eio_trace_ea_next_offset, "ea_next_offset") \ EM(smb_eio_trace_ea_overrun, "ea_overrun") \ EM(smb_eio_trace_extract_will_pin, "extract_will_pin") \ EM(smb_eio_trace_forced_shutdown, "forced_shutdown") \ @@ -79,6 +80,7 @@ EM(smb_eio_trace_qreparse_setup_count, "qreparse_setup_count") \ EM(smb_eio_trace_qreparse_sizes_wrong, "qreparse_sizes_wrong") \ EM(smb_eio_trace_qsym_bcc_too_small, "qsym_bcc_too_small") \ + EM(smb_eio_trace_read_bad_offset, "read_bad_offset") \ EM(smb_eio_trace_read_mid_state_unknown, "read_mid_state_unknown") \ EM(smb_eio_trace_read_overlarge, "read_overlarge") \ EM(smb_eio_trace_read_rsp_malformed, "read_rsp_malformed") \ diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index fdf4e50c27ce..e266859818a4 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -101,12 +101,11 @@ void __release_mid(struct TCP_Server_Info *server, struct mid_q_entry *midEntry) trace_smb3_slow_rsp(smb_cmd, midEntry->mid, midEntry->pid, midEntry->when_sent, midEntry->when_received); if (cifsFYI & CIFS_TIMER) { - pr_debug("slow rsp: cmd %d mid %llu", - midEntry->command, midEntry->mid); - cifs_info("A: 0x%lx S: 0x%lx R: 0x%lx\n", - now - midEntry->when_alloc, - now - midEntry->when_sent, - now - midEntry->when_received); + pr_debug("slow rsp: cmd %d mid %llu A: 0x%lx S: 0x%lx R: 0x%lx\n", + midEntry->command, midEntry->mid, + now - midEntry->when_alloc, + now - midEntry->when_sent, + now - midEntry->when_received); } } #endif diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index 91fdd1ddc61f..d211861ff86f 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -13,6 +13,7 @@ #include "mgmt/ksmbd_ida.h" #include "mgmt/user_session.h" #include "connection.h" +#include "vfs_cache.h" #include "compress.h" #include "transport_tcp.h" #include "transport_rdma.h" @@ -21,6 +22,8 @@ static DEFINE_MUTEX(init_lock); static struct ksmbd_conn_ops default_conn_ops; +static struct delayed_work session_expiration_work; +static bool stopping_session_expiration_work; DEFINE_HASHTABLE(conn_list, CONN_HASH_BITS); DECLARE_RWSEM(conn_list_lock); @@ -157,18 +160,28 @@ static void delete_proc_clients(void) {} static struct workqueue_struct *ksmbd_conn_wq; +static void ksmbd_session_expiration_worker(struct work_struct *work); + int ksmbd_conn_wq_init(void) { ksmbd_conn_wq = alloc_workqueue("ksmbd-conn-release", WQ_UNBOUND | WQ_MEM_RECLAIM, 0); if (!ksmbd_conn_wq) return -ENOMEM; + + WRITE_ONCE(stopping_session_expiration_work, false); + INIT_DELAYED_WORK(&session_expiration_work, + ksmbd_session_expiration_worker); + queue_delayed_work(ksmbd_conn_wq, &session_expiration_work, + KSMBD_SESSION_EXPIRATION_INTERVAL); return 0; } void ksmbd_conn_wq_destroy(void) { if (ksmbd_conn_wq) { + WRITE_ONCE(stopping_session_expiration_work, true); + cancel_delayed_work_sync(&session_expiration_work); destroy_workqueue(ksmbd_conn_wq); ksmbd_conn_wq = NULL; } @@ -278,6 +291,7 @@ struct ksmbd_conn *ksmbd_conn_alloc(void) return NULL; conn->need_neg = true; + conn->creation_time = jiffies; ksmbd_conn_set_new(conn); conn->local_nls = load_nls("utf8"); if (!conn->local_nls) @@ -384,12 +398,12 @@ static void ksmbd_conn_cancel_async_requests(struct ksmbd_conn *conn) spin_lock(&conn->request_lock); list_for_each_entry_safe(work, tmp, &conn->async_requests, async_request_entry) { - if (work->state != KSMBD_WORK_ACTIVE) + if (cmpxchg(&work->state, KSMBD_WORK_ACTIVE, + KSMBD_WORK_CANCELLED) != KSMBD_WORK_ACTIVE) continue; ksmbd_debug(CONN, "Cancel async request id %d\n", work->async_id); - work->state = KSMBD_WORK_CANCELLED; if (work->cancel_fn) work->cancel_fn(work->cancel_argv); } @@ -473,6 +487,9 @@ retry_idle: if (retry_count >= max_timeout) return -EIO; + /* A blocked byte-range lock cannot drain until teardown wakes it. */ + ksmbd_wake_session_blocked_works(sess); + down_read(&conn_list_lock); hash_for_each(conn_list, bkt, conn, hlist) { if (ksmbd_session_is_bound_to_conn(sess, conn)) { @@ -584,6 +601,20 @@ bool ksmbd_conn_alive(struct ksmbd_conn *conn) if (kthread_should_stop()) return false; + /* + * Stale connections that have not completed NEGOTIATE and SESSION_SETUP + * must be disconnected. Do not race a request that is currently + * completing authentication. + */ + if (!atomic_read(&conn->req_running) && + time_after(jiffies, conn->creation_time + + KSMBD_UNAUTHENTICATED_CONN_TIMEOUT) && + (READ_ONCE(conn->need_neg) || + !ksmbd_conn_has_valid_or_expired_session(conn))) { + ksmbd_debug(CONN, "Connection setup timed out\n"); + return false; + } + if (atomic_read(&conn->stats.open_files_count) > 0) return true; @@ -601,6 +632,51 @@ bool ksmbd_conn_alive(struct ksmbd_conn *conn) return true; } +static void ksmbd_session_expiration_worker(struct work_struct *work) +{ + struct ksmbd_conn *conn, *target; + int bkt; + + if (!ksmbd_server_running()) + goto reschedule; + + ksmbd_expire_sessions(); + + /* + * An old connection without a Valid or Expired session must be + * disconnected. Process one connection at a time without holding + * conn_list_lock across transport shutdown. + */ +again: + target = NULL; + down_read(&conn_list_lock); + hash_for_each(conn_list, bkt, conn, hlist) { + if (ksmbd_conn_exiting(conn) || ksmbd_conn_releasing(conn) || + atomic_read(&conn->req_running) || + time_before_eq(jiffies, conn->creation_time + + KSMBD_UNAUTHENTICATED_CONN_TIMEOUT) || + (!READ_ONCE(conn->need_neg) && + ksmbd_conn_has_valid_or_expired_session(conn))) + continue; + + target = ksmbd_conn_get(conn); + break; + } + up_read(&conn_list_lock); + + if (target) { + ksmbd_debug(CONN, "Connection setup timed out\n"); + ksmbd_conn_abort(target); + ksmbd_conn_put(target); + goto again; + } + +reschedule: + if (!READ_ONCE(stopping_session_expiration_work)) + queue_delayed_work(ksmbd_conn_wq, &session_expiration_work, + KSMBD_SESSION_EXPIRATION_INTERVAL); +} + /* "+2" for BCC field (ByteCount, 2 bytes) */ #define SMB1_MIN_SUPPORTED_PDU_SIZE (sizeof(struct smb_hdr) + 2) #define SMB2_MIN_SUPPORTED_PDU_SIZE (sizeof(struct smb2_pdu)) diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index 63484c8efbbd..371f17b4f02a 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -77,6 +77,7 @@ struct ksmbd_conn { struct rw_semaphore session_lock; /* smb session 1 per user */ struct xarray sessions; + unsigned long creation_time; unsigned long last_active; /* How many request are running currently */ atomic_t req_running; @@ -192,6 +193,8 @@ struct ksmbd_transport { #define KSMBD_TCP_RECV_TIMEOUT (7 * HZ) #define KSMBD_TCP_SEND_TIMEOUT (5 * HZ) +#define KSMBD_SESSION_EXPIRATION_INTERVAL (5 * HZ) +#define KSMBD_UNAUTHENTICATED_CONN_TIMEOUT (45 * HZ) #define KSMBD_TCP_PEER_SOCKADDR(c) ((struct sockaddr *)&((c)->peer_addr)) #define CONN_HASH_BITS 12 diff --git a/fs/smb/server/ksmbd_work.c b/fs/smb/server/ksmbd_work.c index f35335307670..d307aefe0aec 100644 --- a/fs/smb/server/ksmbd_work.c +++ b/fs/smb/server/ksmbd_work.c @@ -30,7 +30,7 @@ static int ksmbd_reserve_iov(struct ksmbd_work *work, int need_iov_cnt) } while (new_alloc_cnt < work->iov_cnt + need_iov_cnt); if (work->iov == work->iov_inline) { - new = kcalloc(new_alloc_cnt, sizeof(*new), KSMBD_DEFAULT_GFP); + new = kzalloc_objs(*new, new_alloc_cnt, KSMBD_DEFAULT_GFP); if (!new) return -ENOMEM; diff --git a/fs/smb/server/ksmbd_work.h b/fs/smb/server/ksmbd_work.h index 5f1d3ebab4fb..0844aa929f55 100644 --- a/fs/smb/server/ksmbd_work.h +++ b/fs/smb/server/ksmbd_work.h @@ -82,7 +82,7 @@ struct ksmbd_work { /* Contiguous SMB2 compression transform owned by this work item. */ void *compress_buf; - unsigned char state; + unsigned int state; /* No response for cancelled request */ bool send_no_response:1; /* Request is encrypted */ diff --git a/fs/smb/server/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c index b2d9580bddc6..cc9f18ede80d 100644 --- a/fs/smb/server/mgmt/share_config.c +++ b/fs/smb/server/mgmt/share_config.c @@ -146,9 +146,9 @@ static struct ksmbd_share_config *__share_lookup(const char *name) static int parse_veto_list(struct ksmbd_share_config *share, char *veto_list, - int veto_list_sz) + size_t veto_list_sz) { - int sz = 0; + size_t sz; if (!veto_list_sz) return 0; @@ -156,7 +156,7 @@ static int parse_veto_list(struct ksmbd_share_config *share, while (veto_list_sz > 0) { struct ksmbd_veto_pattern *p; - sz = strlen(veto_list); + sz = strnlen(veto_list, veto_list_sz); if (!sz) break; @@ -164,7 +164,7 @@ static int parse_veto_list(struct ksmbd_share_config *share, if (!p) return -ENOMEM; - p->pattern = kstrdup(veto_list, KSMBD_DEFAULT_GFP); + p->pattern = kstrndup(veto_list, sz, KSMBD_DEFAULT_GFP); if (!p->pattern) { kfree(p); return -ENOMEM; @@ -172,6 +172,9 @@ static int parse_veto_list(struct ksmbd_share_config *share, list_add(&p->list, &share->veto_list); + if (sz == veto_list_sz) + break; + veto_list += sz + 1; veto_list_sz -= (sz + 1); } @@ -224,17 +227,28 @@ static struct ksmbd_share_config *share_config_request(struct ksmbd_work *work, } if (!test_share_config_flag(share, KSMBD_SHARE_FLAG_PIPE)) { - int path_len = PATH_MAX; - - if (resp->payload_sz) - path_len = resp->payload_sz - resp->veto_list_sz; + size_t path_len; - share->path = kstrndup(ksmbd_share_config_path(resp), path_len, - KSMBD_DEFAULT_GFP); - if (!share->path) { - ret = -ENOMEM; + if (resp->payload_sz <= resp->veto_list_sz) { + ret = -EINVAL; } else { - ret = 0; + path_len = resp->payload_sz - resp->veto_list_sz; + if (resp->veto_list_sz) + path_len--; + + if (!path_len) { + ret = -EINVAL; + } else { + share->path = kstrndup( + ksmbd_share_config_path(resp), + path_len, KSMBD_DEFAULT_GFP); + if (!share->path) + ret = -ENOMEM; + else + ret = 0; + } + } + if (share->path) { share->path_sz = strlen(share->path); while (share->path_sz > 1 && share->path[share->path_sz - 1] == '/') diff --git a/fs/smb/server/mgmt/tree_connect.c b/fs/smb/server/mgmt/tree_connect.c index 5f63e236267a..dd1db3554cae 100644 --- a/fs/smb/server/mgmt/tree_connect.c +++ b/fs/smb/server/mgmt/tree_connect.c @@ -82,6 +82,8 @@ ksmbd_tree_conn_connect(struct ksmbd_work *work, const char *share_name) down_write(&sess->tree_conns_lock); ret = xa_err(xa_store(&sess->tree_conns, tree_conn->id, tree_conn, KSMBD_DEFAULT_GFP)); + if (!ret) + atomic_inc(&tree_conn->refcount); up_write(&sess->tree_conns_lock); if (ret) { status.ret = -ENOMEM; @@ -129,6 +131,12 @@ int ksmbd_tree_conn_disconnect(struct ksmbd_session *sess, struct ksmbd_tree_connect *tree_conn) { down_write(&sess->tree_conns_lock); + if (tree_conn->t_state == TREE_DISCONNECTED || + xa_load(&sess->tree_conns, tree_conn->id) != tree_conn) { + up_write(&sess->tree_conns_lock); + return -ENOENT; + } + tree_conn->t_state = TREE_DISCONNECTED; xa_erase(&sess->tree_conns, tree_conn->id); up_write(&sess->tree_conns_lock); diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index 7022d5d656b4..44dc3f800cd4 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -22,6 +22,7 @@ static DEFINE_IDA(session_ida); #define SESSION_HASH_BITS 12 +#define KSMBD_MAX_PENDING_SESSIONS 1 static DEFINE_HASHTABLE(sessions_table, SESSION_HASH_BITS); static DECLARE_RWSEM(sessions_table_lock); @@ -432,26 +433,31 @@ struct ksmbd_session *__session_lookup(unsigned long long id) return NULL; } -static void ksmbd_expire_session(struct ksmbd_conn *conn) +static bool ksmbd_too_many_session_setups(struct ksmbd_conn *conn) { unsigned long id; struct ksmbd_session *sess; + unsigned int pending = 0; down_write(&sessions_table_lock); down_write(&conn->session_lock); xa_for_each(&conn->sessions, id, sess) { + if (READ_ONCE(sess->state) != SMB2_SESSION_IN_PROGRESS) + continue; + if (atomic_read(&sess->refcnt) <= 1 && - (sess->state != SMB2_SESSION_VALID || - time_after(jiffies, - sess->last_active + SMB2_SESSION_TIMEOUT))) { + time_after(jiffies, sess->last_active + + KSMBD_UNAUTHENTICATED_CONN_TIMEOUT)) { xa_erase(&conn->sessions, sess->id); ksmbd_session_remove_from_table(sess); ksmbd_session_destroy(sess); continue; } + pending++; } up_write(&conn->session_lock); up_write(&sessions_table_lock); + return pending >= KSMBD_MAX_PENDING_SESSIONS; } int ksmbd_session_register(struct ksmbd_conn *conn, @@ -461,9 +467,12 @@ int ksmbd_session_register(struct ksmbd_conn *conn, sess->dialect = conn->dialect; memcpy(sess->ClientGUID, conn->ClientGUID, SMB2_CLIENT_GUID_SIZE); - ksmbd_expire_session(conn); - ret = xa_err(xa_store(&conn->sessions, sess->id, sess, - KSMBD_DEFAULT_GFP)); + /* Bound abandoned SessionId-zero authentication exchanges. */ + if (ksmbd_too_many_session_setups(conn)) + ret = -ENOSPC; + else + ret = xa_err(xa_store(&conn->sessions, sess->id, sess, + KSMBD_DEFAULT_GFP)); if (ret) { down_write(&sessions_table_lock); ksmbd_session_remove_from_table(sess); @@ -474,6 +483,105 @@ int ksmbd_session_register(struct ksmbd_conn *conn, return ret; } +void ksmbd_session_unregister(struct ksmbd_conn *conn, + struct ksmbd_session *sess) +{ + struct ksmbd_conn *session_conns[KSMBD_MAX_CHANNELS]; + struct channel *chann; + unsigned long index; + unsigned int nr_conns = 0, i; + bool removed = false; + + down_write(&sessions_table_lock); + if (!hlist_unhashed(&sess->hlist)) { + /* Keep each channel connection stable under sessions_table_lock. */ + down_read(&sess->chann_lock); + xa_for_each(&sess->ksmbd_chann_list, index, chann) { + if (nr_conns == ARRAY_SIZE(session_conns)) + break; + session_conns[nr_conns++] = chann->conn; + } + up_read(&sess->chann_lock); + + ksmbd_session_remove_from_table(sess); + removed = true; + } + + down_write(&conn->session_lock); + if (xa_load(&conn->sessions, sess->id) == sess) + xa_erase(&conn->sessions, sess->id); + up_write(&conn->session_lock); + for (i = 0; i < nr_conns; i++) { + if (session_conns[i] == conn) + continue; + down_write(&session_conns[i]->session_lock); + if (xa_load(&session_conns[i]->sessions, sess->id) == sess) + xa_erase(&session_conns[i]->sessions, sess->id); + up_write(&session_conns[i]->session_lock); + } + up_write(&sessions_table_lock); + + if (removed) + ksmbd_user_session_put(sess); +} + +bool ksmbd_conn_has_valid_or_expired_session(struct ksmbd_conn *conn) +{ + struct ksmbd_session *sess; + unsigned long id; + int state, bkt; + bool found = false; + + down_read(&conn->session_lock); + xa_for_each(&conn->sessions, id, sess) { + state = READ_ONCE(sess->state); + if (state == SMB2_SESSION_VALID || + state == SMB2_SESSION_EXPIRED) { + found = true; + break; + } + } + up_read(&conn->session_lock); + if (found) + return true; + + /* A session bound through SMB3 multichannel is not in conn->sessions. */ + down_read(&sessions_table_lock); + hash_for_each(sessions_table, bkt, sess, hlist) { + state = READ_ONCE(sess->state); + if (state != SMB2_SESSION_VALID && + state != SMB2_SESSION_EXPIRED) + continue; + + down_read(&sess->chann_lock); + found = xa_load(&sess->ksmbd_chann_list, (long)conn); + up_read(&sess->chann_lock); + if (found) + break; + } + up_read(&sessions_table_lock); + return found; +} + +void ksmbd_expire_sessions(void) +{ + struct ksmbd_session *sess; + u64 now = ktime_get_real_seconds(); + int bkt; + + down_read(&sessions_table_lock); + hash_for_each(sessions_table, bkt, sess, hlist) { + if (READ_ONCE(sess->state) != SMB2_SESSION_VALID || + !sess->kerberos_expiry || now < sess->kerberos_expiry) + continue; + + if (cmpxchg(&sess->state, SMB2_SESSION_VALID, + SMB2_SESSION_EXPIRED) == SMB2_SESSION_VALID) + ksmbd_counter_inc(KSMBD_COUNTER_SESSION_TIMEOUTS); + } + up_read(&sessions_table_lock); +} + static int ksmbd_chann_del(struct ksmbd_conn *conn, struct ksmbd_session *sess) { struct channel *chann; @@ -488,7 +596,7 @@ static int ksmbd_chann_del(struct ksmbd_conn *conn, struct ksmbd_session *sess) return 0; } -void ksmbd_sessions_deregister(struct ksmbd_conn *conn) +void ksmbd_conn_sessions_cleanup(struct ksmbd_conn *conn) { struct ksmbd_session *sess; unsigned long id; @@ -666,10 +774,21 @@ void destroy_previous_session(struct ksmbd_conn *conn, memcmp(user->passkey, prev_user->passkey, user->passkey_sz)) goto out; + down_write(&prev_sess->chann_lock); + if (prev_sess->tearing_down) { + up_write(&prev_sess->chann_lock); + goto out; + } + prev_sess->tearing_down = true; + up_write(&prev_sess->chann_lock); + ksmbd_all_conn_set_status(prev_sess, KSMBD_SESS_NEED_RECONNECT); err = ksmbd_conn_wait_idle_sess(conn, prev_sess); if (err) { - ksmbd_all_conn_set_status(prev_sess, KSMBD_SESS_NEED_SETUP); + down_write(&prev_sess->chann_lock); + prev_sess->tearing_down = false; + up_write(&prev_sess->chann_lock); + ksmbd_all_conn_set_status(prev_sess, KSMBD_SESS_GOOD); goto out; } diff --git a/fs/smb/server/mgmt/user_session.h b/fs/smb/server/mgmt/user_session.h index f8a24c33f7fe..217258551d6d 100644 --- a/fs/smb/server/mgmt/user_session.h +++ b/fs/smb/server/mgmt/user_session.h @@ -42,6 +42,7 @@ struct ksmbd_session { bool sign; bool enc; + bool tearing_down; int state; __u8 *Preauth_HashValue; @@ -71,6 +72,8 @@ struct ksmbd_session { struct rw_semaphore rpc_lock; }; +#define KSMBD_MAX_CHANNELS 32 + static inline int test_session_flag(struct ksmbd_session *sess, int bit) { return sess->flags & bit; @@ -97,7 +100,11 @@ bool is_ksmbd_session_in_connection(struct ksmbd_conn *conn, unsigned long long id); int ksmbd_session_register(struct ksmbd_conn *conn, struct ksmbd_session *sess); -void ksmbd_sessions_deregister(struct ksmbd_conn *conn); +void ksmbd_session_unregister(struct ksmbd_conn *conn, + struct ksmbd_session *sess); +void ksmbd_conn_sessions_cleanup(struct ksmbd_conn *conn); +bool ksmbd_conn_has_valid_or_expired_session(struct ksmbd_conn *conn); +void ksmbd_expire_sessions(void); struct ksmbd_session *__session_lookup(unsigned long long id); struct ksmbd_session *ksmbd_session_lookup_all(struct ksmbd_conn *conn, unsigned long long id); diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 58af0fddf39f..1b8c3482d1e4 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -924,31 +924,69 @@ out: ksmbd_conn_put(conn); } +/* + * Select and pin the connection used for an oplock break before doing any + * allocations which may sleep. The caller of oplock_break() holds a live + * reference on ci (a file being opened, a file being operated on, or an + * explicit ksmbd_inode_lookup_lock() reference in the parent lease break + * paths), so the inode cannot be freed during the call and its lock is + * reachable without dereferencing opinfo->o_fp, which is not pinned by + * the oplock reference and may be freed by a concurrent close. + * + * opinfo->conn is cleared under ci->m_lock by session_fd_check() when the + * durable handle owning the oplock is disconnected, reassigned by + * ksmbd_reopen_durable_fd() under the same lock, and the last + * ksmbd_conn_put() of the old connection frees it. Holding the read lock + * excludes both writers, so the connection cannot be freed while it is + * selected. + */ +static struct ksmbd_conn *smb2_oplock_break_conn_get(struct oplock_info *opinfo, + struct ksmbd_inode *ci) +{ + struct ksmbd_conn *conn; + + down_read(&ci->m_lock); + conn = READ_ONCE(opinfo->conn); + if (conn && !ksmbd_conn_releasing(conn)) + conn = ksmbd_conn_get(conn); + else + conn = NULL; + up_read(&ci->m_lock); + + return conn; +} + /** * smb2_oplock_break_noti() - send smb2 exclusive/batch to level2 oplock * break command from server to client * @opinfo: oplock info object + * @ci: inode owning the break target's oplock list, pinned by + * the caller * * Return: 0 on success, otherwise error */ -static int smb2_oplock_break_noti(struct oplock_info *opinfo) +static int smb2_oplock_break_noti(struct oplock_info *opinfo, + struct ksmbd_inode *ci) { struct ksmbd_conn *conn; struct oplock_break_info *br_info; int ret = 0; struct ksmbd_work *work; - conn = READ_ONCE(opinfo->conn); + conn = smb2_oplock_break_conn_get(opinfo, ci); if (!conn) return ksmbd_invalidate_durable_fd(opinfo->fid); work = ksmbd_alloc_work_struct(); - if (!work) + if (!work) { + ksmbd_conn_put(conn); return -ENOMEM; + } br_info = kmalloc_obj(struct oplock_break_info, KSMBD_DEFAULT_GFP); if (!br_info) { ksmbd_free_work_struct(work); + ksmbd_conn_put(conn); return -ENOMEM; } @@ -957,7 +995,8 @@ static int smb2_oplock_break_noti(struct oplock_info *opinfo) br_info->open_trunc = opinfo->open_trunc; work->request_buf = (char *)br_info; - work->conn = ksmbd_conn_get(conn); + /* Transfer the reference acquired by smb2_oplock_break_conn_get(). */ + work->conn = conn; work->sess = opinfo->sess; ksmbd_conn_r_count_inc(conn); @@ -1154,9 +1193,9 @@ static void wait_lease_breaking(struct oplock_info *opinfo) } } -static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level, - struct ksmbd_work *in_work, bool share_break, - bool sync_lease_break) +static int oplock_break(struct oplock_info *brk_opinfo, struct ksmbd_inode *ci, + int req_op_level, struct ksmbd_work *in_work, + bool share_break, bool sync_lease_break) { int err = 0; bool sent_interim = false; @@ -1298,7 +1337,7 @@ again: } } - err = smb2_oplock_break_noti(brk_opinfo); + err = smb2_oplock_break_noti(brk_opinfo, ci); ksmbd_debug(OPLOCK, "oplock granted = %d\n", brk_opinfo->level); if (brk_opinfo->op_state == OPLOCK_CLOSING) @@ -1326,13 +1365,14 @@ static int oplock_break_add(struct list_head *head, struct oplock_info *opinfo) return 0; } -static void oplock_break_drain_none(struct list_head *head) +static void oplock_break_drain_none(struct list_head *head, + struct ksmbd_inode *ci) { struct oplock_break_entry *ent, *tmp; list_for_each_entry_safe(ent, tmp, head, list) { - oplock_break(ent->opinfo, SMB2_OPLOCK_LEVEL_NONE, NULL, false, - false); + oplock_break(ent->opinfo, ci, SMB2_OPLOCK_LEVEL_NONE, NULL, + false, false); list_del(&ent->list); opinfo_put(ent->opinfo); kfree(ent); @@ -1481,7 +1521,7 @@ void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, } up_read(&p_ci->m_lock); - oplock_break_drain_none(&brk_list); + oplock_break_drain_none(&brk_list, p_ci); ksmbd_inode_put(p_ci); } @@ -1525,7 +1565,7 @@ void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp) } up_read(&p_ci->m_lock); - oplock_break_drain_none(&brk_list); + oplock_break_drain_none(&brk_list, p_ci); ksmbd_inode_put(p_ci); } @@ -1665,7 +1705,7 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, prev_durable_detached = prev_op_snapshot.durable_detached; prev_fid = prev_op_snapshot.fid; - err = oplock_break(prev_opinfo, break_level, work, + err = oplock_break(prev_opinfo, ci, break_level, work, share_ret < 0 && prev_opinfo->is_lease, false); if (prev_durable_detached || (prev_durable_open && err == -ENOENT)) ksmbd_invalidate_durable_fd(prev_fid); @@ -1771,7 +1811,8 @@ static bool smb_break_all_write_oplock(struct ksmbd_work *work, } brk_opinfo->open_trunc = is_trunc; - oplock_break(brk_opinfo, SMB2_OPLOCK_LEVEL_II, work, false, false); + oplock_break(brk_opinfo, fp->f_ci, SMB2_OPLOCK_LEVEL_II, work, false, + false); sent_break = true; opinfo_put(brk_opinfo); @@ -1863,7 +1904,7 @@ next: brk_op->op_state = OPLOCK_STATE_NONE; spin_unlock(&brk_op->state_lock); } else { - oplock_break(brk_op, + oplock_break(brk_op, ci, brk_op->is_lease && !is_trunc ? SMB2_OPLOCK_LEVEL_II : SMB2_OPLOCK_LEVEL_NONE, send_interim && !sent_interim ? work : NULL, diff --git a/fs/smb/server/proc.c b/fs/smb/server/proc.c index 826353ed0553..19f0f2cfbf54 100644 --- a/fs/smb/server/proc.c +++ b/fs/smb/server/proc.c @@ -178,6 +178,8 @@ static int proc_show_ksmbd_stats(struct seq_file *m, void *v) proc_show_runtime_totals(m); seq_printf(m, "sessions:\t%lld\n", ksmbd_counter_sum(KSMBD_COUNTER_SESSIONS)); + seq_printf(m, "session_timeouts:\t%lld\n", + ksmbd_counter_sum(KSMBD_COUNTER_SESSION_TIMEOUTS)); seq_printf(m, "tree_connects:\t%lld\n", ksmbd_counter_sum(KSMBD_COUNTER_TREE_CONNS)); seq_printf(m, "requests:\t%lld\n", diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index 0069d4e6a60a..0827c8c51006 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -414,7 +414,7 @@ static int ksmbd_server_process_request(struct ksmbd_conn *conn) static int ksmbd_server_terminate_conn(struct ksmbd_conn *conn) { - ksmbd_sessions_deregister(conn); + ksmbd_conn_sessions_cleanup(conn); destroy_lease_table(conn); return 0; } diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index a8046f477d54..6b8809f67b92 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -85,8 +85,6 @@ struct channel *lookup_chann_list(struct ksmbd_session *sess, struct ksmbd_conn return chann; } -#define KSMBD_MAX_CHANNELS 32 - static int register_session_channel(struct ksmbd_session *sess, struct ksmbd_conn *conn, const char *sess_key) @@ -97,6 +95,11 @@ static int register_session_channel(struct ksmbd_session *sess, int rc = 0; down_write(&sess->chann_lock); + if (sess->tearing_down) { + rc = -ESHUTDOWN; + goto out; + } + if (xa_load(&sess->ksmbd_chann_list, (long)conn)) goto out; @@ -873,7 +876,8 @@ int smb2_allocate_rsp_buf(struct ksmbd_work *work) req = smb_get_msg(work->request_buf); if ((req->InfoType == SMB2_O_INFO_FILE && (req->FileInfoClass == FILE_FULL_EA_INFORMATION || - req->FileInfoClass == FILE_ALL_INFORMATION)) || + req->FileInfoClass == FILE_ALL_INFORMATION || + req->FileInfoClass == FILE_NORMALIZED_NAME_INFORMATION)) || req->InfoType == SMB2_O_INFO_SECURITY) sz = large_sz; } @@ -927,8 +931,14 @@ static bool smb2_session_expired_cmd_allowed(struct ksmbd_work *work, static bool smb2_session_kerberos_expired(struct ksmbd_session *sess) { - return sess->kerberos_expiry && - ktime_get_real_seconds() >= sess->kerberos_expiry; + if (!sess->kerberos_expiry || + ktime_get_real_seconds() < sess->kerberos_expiry) + return false; + + if (cmpxchg(&sess->state, SMB2_SESSION_VALID, + SMB2_SESSION_EXPIRED) == SMB2_SESSION_VALID) + ksmbd_counter_inc(KSMBD_COUNTER_SESSION_TIMEOUTS); + return true; } /** @@ -963,9 +973,8 @@ int smb2_check_user_session(struct ksmbd_work *work) if (!work->next_smb2_rcv_hdr_off && sess_id) work->sess = ksmbd_session_lookup_all_states(conn, sess_id); if (work->sess) { - if (smb2_session_kerberos_expired(work->sess)) { - work->sess->state = SMB2_SESSION_EXPIRED; - } else if (work->sess->state != SMB2_SESSION_VALID) { + if (!smb2_session_kerberos_expired(work->sess) && + work->sess->state != SMB2_SESSION_VALID) { ksmbd_user_session_put(work->sess); work->sess = NULL; } @@ -990,8 +999,7 @@ int smb2_check_user_session(struct ksmbd_work *work) sess_id, work->sess->id); return -EINVAL; } - if (smb2_session_kerberos_expired(work->sess)) - work->sess->state = SMB2_SESSION_EXPIRED; + smb2_session_kerberos_expired(work->sess); if (work->sess->state != SMB2_SESSION_VALID) { pr_err("compound request on a non-valid session (state %d)\n", work->sess->state); @@ -1008,7 +1016,6 @@ int smb2_check_user_session(struct ksmbd_work *work) work->sess = ksmbd_session_lookup_all_states(conn, sess_id); if (work->sess) { if (smb2_session_kerberos_expired(work->sess)) { - work->sess->state = SMB2_SESSION_EXPIRED; return smb2_session_expired_cmd_allowed(work, cmd) ? 1 : -EKEYEXPIRED; } @@ -2430,7 +2437,7 @@ int smb2_sess_setup(struct ksmbd_work *work) struct ksmbd_conn *conn = work->conn; struct smb2_sess_setup_req *req; struct smb2_sess_setup_rsp *rsp; - struct ksmbd_session *sess; + struct ksmbd_session *sess = NULL; struct negotiate_message *negblob; unsigned int negblob_len, negblob_off; int rc = 0; @@ -2586,6 +2593,9 @@ int smb2_sess_setup(struct ksmbd_work *work) goto out_err; } + if (work->session_setup_reauth) + WRITE_ONCE(sess->state, SMB2_SESSION_IN_PROGRESS); + conn->binding = false; } work->sess = sess; @@ -2697,6 +2707,14 @@ out_err: } if (rc < 0) { + bool setup_in_progress = sess && + READ_ONCE(sess->state) == SMB2_SESSION_IN_PROGRESS && + !(req->Flags & SMB2_SESSION_REQ_FLAG_BINDING); + + /* Authentication errors must not leave the new session published. */ + if (setup_in_progress) + ksmbd_session_unregister(conn, sess); + if (sess && conn->dialect == SMB311_PROT_ID && (req->Flags & SMB2_SESSION_REQ_FLAG_BINDING)) { struct preauth_session *preauth_sess; @@ -2730,7 +2748,8 @@ out_err: * For binding requests, session belongs to another * connection. Do not expire it. */ - if (!(req->Flags & SMB2_SESSION_REQ_FLAG_BINDING)) { + if (!(req->Flags & SMB2_SESSION_REQ_FLAG_BINDING) && + !setup_in_progress) { sess->last_active = jiffies; sess->kerberos_expiry = 0; sess->state = SMB2_SESSION_EXPIRED; @@ -2784,6 +2803,7 @@ int smb2_tree_connect(struct ksmbd_work *work) struct ksmbd_session *sess = work->sess; char *treename = NULL, *name = NULL; struct ksmbd_tree_conn_status status; + struct ksmbd_tree_connect *tree_conn = NULL; struct ksmbd_share_config *share = NULL; int rc = -EINVAL; @@ -2811,6 +2831,7 @@ int smb2_tree_connect(struct ksmbd_work *work) status = ksmbd_tree_conn_connect(work, name); if (status.ret == KSMBD_TREE_CONN_STATUS_OK) { + tree_conn = status.tree_conn; rsp->hdr.Id.SyncId.TreeId = cpu_to_le32(status.tree_conn->id); share = status.tree_conn->share_conf; @@ -2854,8 +2875,15 @@ int smb2_tree_connect(struct ksmbd_work *work) status.tree_conn->posix_extensions = true; down_write(&sess->tree_conns_lock); - status.tree_conn->t_state = TREE_CONNECTED; + if (status.tree_conn->t_state == TREE_DISCONNECTED) { + status.ret = KSMBD_TREE_CONN_STATUS_ERROR; + share = NULL; + } else { + status.tree_conn->t_state = TREE_CONNECTED; + } up_write(&sess->tree_conns_lock); + if (status.ret != KSMBD_TREE_CONN_STATUS_OK) + goto out_err1; rsp->StructureSize = cpu_to_le16(16); out_err1: /* @@ -2882,9 +2910,6 @@ out_err1: rc = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_tree_connect_rsp)); if (rc) { if (status.ret == KSMBD_TREE_CONN_STATUS_OK) { - down_write(&sess->tree_conns_lock); - status.tree_conn->t_state = TREE_DISCONNECTED; - up_write(&sess->tree_conns_lock); ksmbd_tree_conn_disconnect(sess, status.tree_conn); status.tree_conn = NULL; } @@ -2925,6 +2950,9 @@ out_err1: if (status.ret != KSMBD_TREE_CONN_STATUS_OK) smb2_set_err_rsp(work); + if (tree_conn) + ksmbd_tree_connect_put(tree_conn); + return rc; } @@ -3028,17 +3056,6 @@ int smb2_tree_disconnect(struct ksmbd_work *work) ksmbd_close_tree_conn_fds(work); - down_write(&sess->tree_conns_lock); - if (tcon->t_state == TREE_DISCONNECTED) { - up_write(&sess->tree_conns_lock); - rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; - err = -ENOENT; - goto err_out; - } - - tcon->t_state = TREE_DISCONNECTED; - up_write(&sess->tree_conns_lock); - err = ksmbd_tree_conn_disconnect(sess, tcon); if (err) { rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; @@ -3086,17 +3103,41 @@ int smb2_session_logoff(struct ksmbd_work *work) smb2_set_err_rsp(work); return -ENOENT; } + + down_write(&sess->chann_lock); + if (sess->tearing_down) { + up_write(&sess->chann_lock); + ksmbd_conn_unlock(conn); + rsp->hdr.Status = STATUS_USER_SESSION_DELETED; + smb2_set_err_rsp(work); + return -ENOENT; + } + sess->tearing_down = true; + up_write(&sess->chann_lock); + ksmbd_all_conn_set_status(sess, KSMBD_SESS_NEED_RECONNECT); ksmbd_conn_unlock(conn); + err = ksmbd_conn_wait_idle_sess(conn, sess); + if (err) { + down_write(&sess->chann_lock); + sess->tearing_down = false; + up_write(&sess->chann_lock); + ksmbd_all_conn_set_status(sess, KSMBD_SESS_GOOD); + rsp->hdr.Status = STATUS_UNEXPECTED_IO_ERROR; + smb2_set_err_rsp(work); + return err; + } + ksmbd_close_session_fds(work); - ksmbd_conn_wait_idle(conn); if (ksmbd_tree_conn_session_logoff(sess)) { ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; smb2_set_err_rsp(work); - return -ENOENT; + err = -ENOENT; + } else { + err = 0; } down_write(&conn->session_lock); @@ -3106,6 +3147,9 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_all_conn_set_status(sess, KSMBD_SESS_NEED_SETUP); + if (err) + return err; + rsp->StructureSize = cpu_to_le16(4); err = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_logoff_rsp)); if (err) { @@ -6231,21 +6275,18 @@ err_out2: * @reqOutputBufferLength: max buffer length expected in command response * @fixed_len: minimum fixed response length * @rsp: query info response buffer contains output buffer length - * @rsp_org: base response buffer pointer in case of chained response * * Return: 0 on success, otherwise error */ static int buffer_check_err(int reqOutputBufferLength, unsigned int fixed_len, - struct smb2_query_info_rsp *rsp, - void *rsp_org) + struct smb2_query_info_rsp *rsp) { unsigned int output_len = le32_to_cpu(rsp->OutputBufferLength); if (reqOutputBufferLength < fixed_len) { pr_err("Invalid Buffer Size Requested\n"); rsp->hdr.Status = STATUS_INFO_LENGTH_MISMATCH; - *(__be32 *)rsp_org = cpu_to_be32(sizeof(struct smb2_hdr)); return -EINVAL; } @@ -6256,8 +6297,7 @@ static int buffer_check_err(int reqOutputBufferLength, return 0; } -static void get_standard_info_pipe(struct smb2_query_info_rsp *rsp, - void *rsp_org) +static void get_standard_info_pipe(struct smb2_query_info_rsp *rsp) { struct smb2_file_standard_info *sinfo; @@ -6272,8 +6312,7 @@ static void get_standard_info_pipe(struct smb2_query_info_rsp *rsp, cpu_to_le32(sizeof(struct smb2_file_standard_info)); } -static void get_internal_info_pipe(struct smb2_query_info_rsp *rsp, u64 num, - void *rsp_org) +static void get_internal_info_pipe(struct smb2_query_info_rsp *rsp, u64 num) { struct smb2_file_internal_info *file_info; @@ -6287,8 +6326,7 @@ static void get_internal_info_pipe(struct smb2_query_info_rsp *rsp, u64 num, static int smb2_get_info_file_pipe(struct ksmbd_session *sess, struct smb2_query_info_req *req, - struct smb2_query_info_rsp *rsp, - void *rsp_org) + struct smb2_query_info_rsp *rsp) { u64 id; int rc; @@ -6313,16 +6351,16 @@ static int smb2_get_info_file_pipe(struct ksmbd_session *sess, switch (req->FileInfoClass) { case FILE_STANDARD_INFORMATION: - get_standard_info_pipe(rsp, rsp_org); + get_standard_info_pipe(rsp); rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength), le32_to_cpu(rsp->OutputBufferLength), - rsp, rsp_org); + rsp); break; case FILE_INTERNAL_INFORMATION: - get_internal_info_pipe(rsp, id, rsp_org); + get_internal_info_pipe(rsp, id); rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength), le32_to_cpu(rsp->OutputBufferLength), - rsp, rsp_org); + rsp); break; default: ksmbd_debug(SMB, "smb2_info_file_pipe for %u not supported\n", @@ -6757,7 +6795,7 @@ static int get_file_normalized_name_info(struct ksmbd_work *work, { struct smb2_file_alt_name_info *file_info; char *filename, *normalized, *stream_name; - int conv_len, filename_len; + int buf_free_len, conv_len, filename_len; if (work->conn->dialect < SMB311_PROT_ID) { rsp->hdr.Status = STATUS_NOT_SUPPORTED; @@ -6781,6 +6819,14 @@ static int get_file_normalized_name_info(struct ksmbd_work *work, return -ENOMEM; filename_len = strlen(normalized); + buf_free_len = smb2_resp_buf_len(work, sizeof(*rsp) + + sizeof(*file_info)); + if (buf_free_len < 0 || + (size_t)buf_free_len < (filename_len + 1) * sizeof(__le16)) { + kfree(normalized); + return -EINVAL; + } + file_info = (struct smb2_file_alt_name_info *)rsp->Buffer; conv_len = smbConvertToUTF16((__le16 *)file_info->FileName, normalized, filename_len, @@ -7150,8 +7196,7 @@ static int smb2_get_info_file(struct ksmbd_work *work, if (test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_PIPE)) { /* smb2 info file called for pipe */ - rc = smb2_get_info_file_pipe(work->sess, req, rsp, - work->response_buf); + rc = smb2_get_info_file_pipe(work->sess, req, rsp); goto iov_pin_out; } @@ -7260,13 +7305,16 @@ static int smb2_get_info_file(struct ksmbd_work *work, case FILE_ALTERNATE_NAME_INFORMATION: fixed_len = FILE_ALTERNATE_NAME_INFORMATION_SIZE; break; + case FILE_NORMALIZED_NAME_INFORMATION: + fixed_len = FILE_NORMALIZED_NAME_INFORMATION_SIZE; + break; case FILE_STREAM_INFORMATION: fixed_len = FILE_STREAM_INFORMATION_SIZE; break; } rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength), fixed_len, - rsp, work->response_buf); + rsp); } ksmbd_fd_put(work, fp); @@ -7444,6 +7492,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, struct object_id_info *info; info = (struct object_id_info *)(rsp->Buffer); + memset(info, 0, sizeof(*info)); if (path.mnt->mnt_sb->s_uuid_len == 16) memcpy(info->objid, path.mnt->mnt_sb->s_uuid.b, @@ -7499,6 +7548,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->FreeSpaceStopFiltering = 0; info->DefaultQuotaThreshold = cpu_to_le64(SMB2_NO_FID); info->DefaultQuotaLimit = cpu_to_le64(SMB2_NO_FID); + info->FileSystemControlFlags = 0; info->Padding = 0; rsp->OutputBufferLength = cpu_to_le32(48); fixed_len = 48; @@ -7521,6 +7571,9 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->UserBlocksAvail = cpu_to_le64(stfs.f_bavail); info->TotalFileNodes = cpu_to_le64(stfs.f_files); info->FreeFileNodes = cpu_to_le64(stfs.f_ffree); + info->FileSysIdentifier = + cpu_to_le64((u64)(u32)stfs.f_fsid.val[1] << 32 | + (u32)stfs.f_fsid.val[0]); rsp->OutputBufferLength = cpu_to_le32(56); fixed_len = 56; } @@ -7532,7 +7585,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, } rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength), fixed_len, - rsp, work->response_buf); + rsp); path_put(&path); if (!rc) @@ -7646,7 +7699,7 @@ release_acl: rsp->OutputBufferLength = cpu_to_le32(secdesclen); rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength), le32_to_cpu(rsp->OutputBufferLength), - rsp, work->response_buf); + rsp); if (rc) goto err_out; @@ -8620,13 +8673,18 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work) } aux_payload_buf = - kvmalloc(rpc_resp->payload_sz, KSMBD_DEFAULT_GFP); + kvmalloc(ALIGN(rpc_resp->payload_sz, 8), + KSMBD_DEFAULT_GFP); if (!aux_payload_buf) { err = -ENOMEM; goto out; } memcpy(aux_payload_buf, rpc_resp->payload, rpc_resp->payload_sz); + if (rpc_resp->payload_sz & 7) + memset(aux_payload_buf + rpc_resp->payload_sz, 0, + ALIGN(rpc_resp->payload_sz, 8) - + rpc_resp->payload_sz); nbytes = rpc_resp->payload_sz; err = ksmbd_iov_pin_rsp_read(work, (void *)rsp, @@ -9680,14 +9738,14 @@ int smb2_cancel(struct ksmbd_work *work) * still on conn->async_requests with a live cancel_fn * pointing at the freed file_lock. */ - if (iter->state != KSMBD_WORK_ACTIVE) + if (cmpxchg(&iter->state, KSMBD_WORK_ACTIVE, + KSMBD_WORK_CANCELLED) != KSMBD_WORK_ACTIVE) break; ksmbd_debug(SMB, "smb2 with AsyncId %llu cancelled command = 0x%x\n", le64_to_cpu(hdr->Id.AsyncId), le16_to_cpu(chdr->Command)); - iter->state = KSMBD_WORK_CANCELLED; if (iter->cancel_fn == smb2_notify_cancel_fn) cancelled_notify = smb2_notify_cancel_claim(iter->cancel_argv); @@ -9716,11 +9774,16 @@ int smb2_cancel(struct ksmbd_work *work) iter == work) continue; + if (cmpxchg(&iter->state, KSMBD_WORK_ACTIVE, + KSMBD_WORK_CANCELLED) != KSMBD_WORK_ACTIVE) + break; + ksmbd_debug(SMB, "smb2 with mid %llu cancelled command = 0x%x\n", le64_to_cpu(hdr->MessageId), le16_to_cpu(chdr->Command)); - iter->state = KSMBD_WORK_CANCELLED; + if (iter->cancel_fn) + iter->cancel_fn(iter->cancel_argv); break; } spin_unlock(&conn->request_lock); @@ -11766,7 +11829,7 @@ static void smb2_notify_cancel_fn(void **argv) return; conn = in_work->conn; - ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC); + ctx = kmalloc_obj(*ctx, GFP_ATOMIC); if (!ctx) { /* Can't defer the response -- free without sending one. */ list_del_init(&in_work->async_request_entry); diff --git a/fs/smb/server/smb2pdu.h b/fs/smb/server/smb2pdu.h index 3f08d1ca5a38..ca8e27f7b712 100644 --- a/fs/smb/server/smb2pdu.h +++ b/fs/smb/server/smb2pdu.h @@ -61,8 +61,6 @@ struct preauth_integrity_info { #define SMB2_SESSION_IN_PROGRESS BIT(0) #define SMB2_SESSION_VALID BIT(1) -#define SMB2_SESSION_TIMEOUT (10 * HZ) - /* Apple Defined Contexts */ #define SMB2_CREATE_AAPL "AAPL" @@ -214,6 +212,7 @@ struct file_sparse { #define FILE_ALLOCATION_INFORMATION_SIZE 19 #define FILE_END_OF_FILE_INFORMATION_SIZE 20 #define FILE_ALTERNATE_NAME_INFORMATION_SIZE 8 +#define FILE_NORMALIZED_NAME_INFORMATION_SIZE 8 #define FILE_STREAM_INFORMATION_SIZE 32 #define FILE_PIPE_INFORMATION_SIZE 23 #define FILE_PIPE_LOCAL_INFORMATION_SIZE 24 diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c index 8ad2e5a5cca8..1fad6ccf3a72 100644 --- a/fs/smb/server/smbacl.c +++ b/fs/smb/server/smbacl.c @@ -383,10 +383,10 @@ void free_acl_state(struct posix_acl_state *state) kfree(state->groups); } -static void parse_dacl(struct mnt_idmap *idmap, - struct smb_acl *pdacl, char *end_of_acl, - struct smb_sid *pownersid, struct smb_sid *pgrpsid, - struct smb_fattr *fattr) +static int parse_dacl(struct mnt_idmap *idmap, + struct smb_acl *pdacl, char *end_of_acl, + struct smb_sid *pownersid, struct smb_sid *pgrpsid, + struct smb_fattr *fattr) { int i, ret; u16 num_aces = 0; @@ -400,13 +400,13 @@ static void parse_dacl(struct mnt_idmap *idmap, bool owner_found = false, group_found = false, others_found = false; if (!pdacl) - return; + return 0; /* validate that we do not go past end of acl */ if (end_of_acl < (char *)pdacl + sizeof(struct smb_acl) || end_of_acl < (char *)pdacl + le16_to_cpu(pdacl->size)) { pr_err("ACL too small to parse DACL\n"); - return; + return -EINVAL; } ksmbd_debug(SMB, "DACL revision %d size %d num aces %d\n", @@ -418,31 +418,31 @@ static void parse_dacl(struct mnt_idmap *idmap, num_aces = le16_to_cpu(pdacl->num_aces); if (num_aces <= 0) - return; + return 0; dacl_size = le16_to_cpu(pdacl->size); if (dacl_size < sizeof(struct smb_acl)) - return; + return -EINVAL; if (num_aces > (dacl_size - sizeof(struct smb_acl)) / (offsetof(struct smb_ace, sid) + offsetof(struct smb_sid, sub_auth) + sizeof(__le16))) - return; + return -EINVAL; ret = init_acl_state(&acl_state, num_aces); if (ret) - return; + return ret; ret = init_acl_state(&default_acl_state, num_aces); if (ret) { free_acl_state(&acl_state); - return; + return ret; } ppace = kmalloc_objs(struct smb_ace *, num_aces, KSMBD_DEFAULT_GFP); if (!ppace) { free_acl_state(&default_acl_state); free_acl_state(&acl_state); - return; + return -ENOMEM; } /* @@ -451,8 +451,10 @@ static void parse_dacl(struct mnt_idmap *idmap, * user/group/other have no permissions */ for (i = 0; i < num_aces; ++i) { - if (end_of_acl - acl_base < acl_size) - break; + if (end_of_acl - acl_base < acl_size) { + ret = -EINVAL; + goto out; + } ppace[i] = (struct smb_ace *)(acl_base + acl_size); acl_base = (char *)ppace[i]; @@ -465,8 +467,10 @@ static void parse_dacl(struct mnt_idmap *idmap, (end_of_acl - acl_base < acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth) || (le16_to_cpu(ppace[i]->size) < - acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth)) - break; + acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth)) { + ret = -EINVAL; + goto out; + } acl_size = le16_to_cpu(ppace[i]->size); ppace[i]->access_req = @@ -524,8 +528,8 @@ static void parse_dacl(struct mnt_idmap *idmap, temp_fattr.cf_uid = INVALID_UID; ret = sid_to_id(idmap, &ppace[i]->sid, SIDOWNER, &temp_fattr); if (ret || uid_eq(temp_fattr.cf_uid, INVALID_UID)) { - pr_err("%s: Error %d mapping Owner SID to uid\n", - __func__, ret); + pr_err_ratelimited("%s: Error %d mapping Owner SID to uid\n", + __func__, ret); continue; } @@ -541,7 +545,6 @@ static void parse_dacl(struct mnt_idmap *idmap, ((acl_mode & 0700) >> 6) | 0004; } } - kfree(ppace); if (owner_found) { /* The owner must be set to at least read-only. */ @@ -584,10 +587,12 @@ static void parse_dacl(struct mnt_idmap *idmap, fattr->cf_acls = posix_acl_alloc(acl_state.users->n + acl_state.groups->n + 4, KSMBD_DEFAULT_GFP); - if (fattr->cf_acls) { - cf_pace = fattr->cf_acls->a_entries; - posix_state_to_acl(&acl_state, cf_pace); + if (!fattr->cf_acls) { + ret = -ENOMEM; + goto out; } + cf_pace = fattr->cf_acls->a_entries; + posix_state_to_acl(&acl_state, cf_pace); } } @@ -598,14 +603,20 @@ static void parse_dacl(struct mnt_idmap *idmap, fattr->cf_dacls = posix_acl_alloc(default_acl_state.users->n + default_acl_state.groups->n + 4, KSMBD_DEFAULT_GFP); - if (fattr->cf_dacls) { - cf_pdace = fattr->cf_dacls->a_entries; - posix_state_to_acl(&default_acl_state, cf_pdace); + if (!fattr->cf_dacls) { + ret = -ENOMEM; + goto out; } + cf_pdace = fattr->cf_dacls->a_entries; + posix_state_to_acl(&default_acl_state, cf_pdace); } } + ret = 0; +out: + kfree(ppace); free_acl_state(&acl_state); free_acl_state(&default_acl_state); + return ret; } static void set_posix_acl_entries_dacl(struct mnt_idmap *idmap, @@ -966,8 +977,10 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd, if (dacloffset < sizeof(struct smb_ntsd)) return -EINVAL; - parse_dacl(idmap, dacl_ptr, end_of_acl, - owner_sid_ptr, group_sid_ptr, fattr); + rc = parse_dacl(idmap, dacl_ptr, end_of_acl, + owner_sid_ptr, group_sid_ptr, fattr); + if (rc) + return rc; } return 0; diff --git a/fs/smb/server/stats.h b/fs/smb/server/stats.h index bc864efa0d46..8b32b8b4e8be 100644 --- a/fs/smb/server/stats.h +++ b/fs/smb/server/stats.h @@ -15,6 +15,7 @@ enum { KSMBD_COUNTER_SESSIONS = 0, + KSMBD_COUNTER_SESSION_TIMEOUTS, KSMBD_COUNTER_TREE_CONNS, KSMBD_COUNTER_REQUESTS, KSMBD_COUNTER_STATUS_SUCCESS, diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index 4b0b572a3e1b..e550aa41ad2c 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -532,14 +532,21 @@ static int ipc_validate_msg(struct ipc_msg_table_entry *entry) if (entry->msg_sz < sizeof(struct ksmbd_share_config_response)) return -EINVAL; - if (resp->payload_sz) { - if (resp->payload_sz < resp->veto_list_sz) - return -EINVAL; + if (strnlen(resp->share_name, sizeof(resp->share_name)) == + sizeof(resp->share_name)) + return -EINVAL; - if (check_add_overflow(sizeof(struct ksmbd_share_config_response), - resp->payload_sz, &msg_sz)) - return -EINVAL; - } + if (resp->veto_list_sz > resp->payload_sz) + return -EINVAL; + + if (resp->flags != KSMBD_SHARE_FLAG_INVALID && + !(resp->flags & KSMBD_SHARE_FLAG_PIPE) && + resp->payload_sz <= resp->veto_list_sz) + return -EINVAL; + + if (check_add_overflow(sizeof(struct ksmbd_share_config_response), + resp->payload_sz, &msg_sz)) + return -EINVAL; break; } case KSMBD_EVENT_LOGIN_REQUEST_EXT: diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index 832e93084605..4968cfc1a572 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -39,6 +39,7 @@ struct tcp_transport { static const struct ksmbd_transport_ops ksmbd_tcp_transport_ops; static void tcp_stop_kthread(struct task_struct *kthread); +static void ksmbd_tcp_stop_listener(struct interface *iface); static struct interface *alloc_iface(char *ifname); static void ksmbd_tcp_disconnect(struct ksmbd_transport *t); @@ -321,13 +322,20 @@ static int ksmbd_tcp_run_kthread(struct interface *iface) int rc; struct task_struct *kthread; - kthread = kthread_run(ksmbd_kthread_fn, (void *)iface, "ksmbd-%s", - iface->name); + kthread = kthread_create(ksmbd_kthread_fn, (void *)iface, "ksmbd-%s", + iface->name); if (IS_ERR(kthread)) { rc = PTR_ERR(kthread); return rc; } + + /* + * The listener can exit after its socket is shutdown, so keep the + * task_struct alive until the caller has stopped it. + */ + get_task_struct(kthread); iface->ksmbd_kthread = kthread; + wake_up_process(kthread); return 0; } @@ -598,12 +606,7 @@ static int ksmbd_netdev_event(struct notifier_block *nb, unsigned long event, if (iface && iface->state == IFACE_STATE_CONFIGURED) { ksmbd_debug(CONN, "netdev-down event: netdev(%s) is going down\n", iface->name); - kernel_sock_shutdown(iface->ksmbd_socket, SHUT_RDWR); - tcp_stop_kthread(iface->ksmbd_kthread); - iface->ksmbd_kthread = NULL; - sock_release(iface->ksmbd_socket); - iface->ksmbd_socket = NULL; - + ksmbd_tcp_stop_listener(iface); iface->state = IFACE_STATE_DOWN; break; } @@ -631,11 +634,25 @@ static void tcp_stop_kthread(struct task_struct *kthread) if (!kthread) return; - ret = kthread_stop(kthread); + ret = kthread_stop_put(kthread); if (ret) pr_err("failed to stop forker thread\n"); } +static void ksmbd_tcp_stop_listener(struct interface *iface) +{ + if (iface->ksmbd_socket) + kernel_sock_shutdown(iface->ksmbd_socket, SHUT_RDWR); + + tcp_stop_kthread(iface->ksmbd_kthread); + iface->ksmbd_kthread = NULL; + + if (iface->ksmbd_socket) { + sock_release(iface->ksmbd_socket); + iface->ksmbd_socket = NULL; + } +} + void ksmbd_tcp_destroy(void) { struct interface *iface, *tmp; @@ -643,6 +660,7 @@ void ksmbd_tcp_destroy(void) unregister_netdevice_notifier(&ksmbd_netdev_notifier); list_for_each_entry_safe(iface, tmp, &iface_list, entry) { + ksmbd_tcp_stop_listener(iface); list_del(&iface->entry); kfree(iface->name); kfree(iface); diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index d2b524f79cbe..c2c9aaa5de1b 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -2007,6 +2007,11 @@ out: return ret; } +static bool ksmbd_vfs_copy_range_valid(loff_t offset, size_t len) +{ + return offset >= 0 && (loff_t)len <= MAX_LFS_FILESIZE - offset; +} + int ksmbd_vfs_copy_file_ranges(struct ksmbd_work *work, struct ksmbd_file *src_fp, struct ksmbd_file *dst_fp, @@ -2042,6 +2047,10 @@ int ksmbd_vfs_copy_file_ranges(struct ksmbd_work *work, dst_off = le64_to_cpu(chunks[i].TargetOffset); len = le32_to_cpu(chunks[i].Length); + if (!ksmbd_vfs_copy_range_valid(src_off, len) || + !ksmbd_vfs_copy_range_valid(dst_off, len)) + return -E2BIG; + if (check_lock_range(src_fp->filp, src_off, src_off + len - 1, READ)) return -EAGAIN; @@ -2134,7 +2143,8 @@ int ksmbd_vfs_copy_file_ranges(struct ksmbd_work *work, len = le32_to_cpu(chunks[i].Length); copy_len = len; - if (src_off < 0) + if (!ksmbd_vfs_copy_range_valid(src_off, len) || + !ksmbd_vfs_copy_range_valid(dst_off, len)) return -E2BIG; if (src_off > src_file_size || len > src_file_size - src_off) { diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 81626d204249..fd2c595f0486 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -846,12 +846,25 @@ static void set_close_state_blocked_works(struct ksmbd_file *fp) spin_lock(&fp->f_lock); list_for_each_entry(cancel_work, &fp->blocked_works, fp_entry) { - cancel_work->state = KSMBD_WORK_CLOSED; - cancel_work->cancel_fn(cancel_work->cancel_argv); + if (xchg(&cancel_work->state, KSMBD_WORK_CLOSED) == + KSMBD_WORK_ACTIVE) + cancel_work->cancel_fn(cancel_work->cancel_argv); } spin_unlock(&fp->f_lock); } +void ksmbd_wake_session_blocked_works(struct ksmbd_session *sess) +{ + struct ksmbd_file_table *ft = &sess->file_table; + struct ksmbd_file *fp; + unsigned int id; + + read_lock(&ft->lock); + idr_for_each_entry(ft->idr, fp, id) + set_close_state_blocked_works(fp); + read_unlock(&ft->lock); +} + int ksmbd_close_fd(struct ksmbd_work *work, u64 id) { struct ksmbd_file *fp; diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index 502efb16f05f..1884f6deb9d0 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -226,6 +226,7 @@ void ksmbd_stop_durable_scavenger(void); bool ksmbd_durable_scavenger_active(void); void ksmbd_close_tree_conn_fds(struct ksmbd_work *work); void ksmbd_close_session_fds(struct ksmbd_work *work); +void ksmbd_wake_session_blocked_works(struct ksmbd_session *sess); int ksmbd_close_inode_fds(struct ksmbd_work *work, struct inode *inode); int ksmbd_init_global_file_table(void); void ksmbd_free_global_file_table(void); diff --git a/fs/super.c b/fs/super.c index 05e443173038..9d4025213521 100644 --- a/fs/super.c +++ b/fs/super.c @@ -172,19 +172,6 @@ static void super_wake(struct super_block *sb, unsigned int flag) } /* - * The s_op->nr_cached_objects hooks (used for example by btrfs and xfs) - * operate on filesystem-global state and ignore sc->memcg. Driving them - * from per-memcg shrink_slab_memcg() invocations only burns CPU walking - * per-cpu counters and queueing duplicate work: the actual reclaim happens on - * the global path (kswapd or root direct reclaim) regardless. Restrict them - * to that path. - */ -static inline bool super_fs_objects_eligible(struct shrink_control *sc) -{ - return !sc->memcg || mem_cgroup_is_root(sc->memcg); -} - -/* * One thing we have to be careful of with a per-sb shrinker is that we don't * drop the last active reference to the superblock from within the shrinker. * If that happens we could trigger unregistering the shrinker from within the @@ -213,7 +200,7 @@ static unsigned long super_cache_scan(struct shrinker *shrink, if (!super_trylock_shared(sb)) return SHRINK_STOP; - if (sb->s_op->nr_cached_objects && super_fs_objects_eligible(sc)) + if (sb->s_op->nr_cached_objects) fs_objects = sb->s_op->nr_cached_objects(sb, sc); inodes = list_lru_shrink_count(&sb->s_inode_lru, sc); @@ -274,8 +261,7 @@ static unsigned long super_cache_count(struct shrinker *shrink, return 0; smp_rmb(); - if (sb->s_op && sb->s_op->nr_cached_objects && - super_fs_objects_eligible(sc)) + if (sb->s_op && sb->s_op->nr_cached_objects) total_objects = sb->s_op->nr_cached_objects(sb, sc); total_objects += list_lru_shrink_count(&sb->s_dentry_lru, sc); @@ -2369,11 +2355,14 @@ static int thaw_super_locked(struct super_block *sb, enum freeze_holder who, goto out_unlock; /* - * All freezers share a single active reference. - * So just unlock in case there are any left. + * All freezers share a single active reference. If other freezers + * remain, drop our hold and report success; the superblock stays + * frozen until the last holder thaws it. */ - if (freeze_dec(sb, who)) + if (freeze_dec(sb, who)) { + error = 0; goto out_unlock; + } if (sb_rdonly(sb)) { sb->s_writers.frozen = SB_UNFROZEN; diff --git a/fs/ufs/cylinder.c b/fs/ufs/cylinder.c index a2813270c303..b930ee1cf853 100644 --- a/fs/ufs/cylinder.c +++ b/fs/ufs/cylinder.c @@ -68,6 +68,16 @@ static bool ufs_read_cylinder(struct super_block *sb, ucpi->c_clustersumoff = fs32_to_cpu(sb, ucg->cg_u.cg_44.cg_clustersumoff); ucpi->c_clusteroff = fs32_to_cpu(sb, ucg->cg_u.cg_44.cg_clusteroff); ucpi->c_nclusterblks = fs32_to_cpu(sb, ucg->cg_u.cg_44.cg_nclusterblks); + + /* these on-disk values become array and bitmap indices */ + if (ucpi->c_cgx != cgno || + ucpi->c_rotor >= uspi->s_fpg || + ucpi->c_frotor >= uspi->s_fpg || + ucpi->c_irotor >= uspi->s_ipg) { + ufs_error(sb, __func__, + "inconsistent metadata in cylinder group %u\n", cgno); + goto failed; + } UFSD("EXIT\n"); return true; diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c index e62fe5667671..ce43cf20b07c 100644 --- a/fs/ufs/dir.c +++ b/fs/ufs/dir.c @@ -590,7 +590,7 @@ int ufs_empty_dir(struct inode * inode) kaddr = ufs_get_folio(inode, i, &folio); if (IS_ERR(kaddr)) - continue; + return 0; de = (struct ufs_dir_entry *)kaddr; kaddr += ufs_last_byte(inode, i) - UFS_DIR_REC_LEN(1); diff --git a/fs/ufs/super.c b/fs/ufs/super.c index 6dcf6d048cce..3569ac92b065 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -1199,6 +1199,15 @@ magic_found: sb->s_maxbytes = ufs_max_bytes(sb); sb->s_max_links = UFS_LINK_MAX; + ufs_setup_cstotal(sb); + /* + * Read cylinder group structures + */ + if (!sb_rdonly(sb)) + if (!ufs_read_cylinder_structures(sb)) + goto failed; + + /* create the root dentry last, once UFS_SB(sb) is fully set up */ inode = ufs_iget(sb, UFS_ROOTINO); if (IS_ERR(inode)) { ret = PTR_ERR(inode); @@ -1210,14 +1219,6 @@ magic_found: goto failed; } - ufs_setup_cstotal(sb); - /* - * Read cylinder group structures - */ - if (!sb_rdonly(sb)) - if (!ufs_read_cylinder_structures(sb)) - goto failed; - UFSD("EXIT\n"); return 0; diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index 9f7133e02576..399a207f2d0e 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -91,6 +91,7 @@ xfs-y += xfs_aops.o \ xfs_healthmon.o \ xfs_icache.o \ xfs_ioctl.o \ + xfs_ioend.o \ xfs_iomap.o \ xfs_iops.o \ xfs_inode.o \ diff --git a/fs/xfs/libxfs/xfs_btree_mem.c b/fs/xfs/libxfs/xfs_btree_mem.c index 37136a70e56d..1d83a4251cee 100644 --- a/fs/xfs/libxfs/xfs_btree_mem.c +++ b/fs/xfs/libxfs/xfs_btree_mem.c @@ -117,6 +117,7 @@ xfbtree_init( struct xfs_buftarg *btp, const struct xfs_btree_ops *ops) { + unsigned long long owner = xfbt->owner; unsigned int blocklen = xfbtree_rec_bytes(mp, ops); unsigned int keyptr_len; int error; @@ -133,6 +134,7 @@ xfbtree_init( memset(xfbt, 0, sizeof(*xfbt)); xfbt->target = btp; + xfbt->owner = owner; /* Set up min/maxrecs for this btree. */ keyptr_len = ops->key_len + sizeof(__be64); diff --git a/fs/xfs/libxfs/xfs_btree_staging.c b/fs/xfs/libxfs/xfs_btree_staging.c index 7314dab4bcfb..561fd2c2e950 100644 --- a/fs/xfs/libxfs/xfs_btree_staging.c +++ b/fs/xfs/libxfs/xfs_btree_staging.c @@ -336,8 +336,10 @@ xfs_btree_bload_prep_block( xfs_btree_set_sibling(cur, *blockp, &new_ptr, XFS_BB_RIGHTSIB); ret = xfs_btree_bload_drop_buf(bbl, buffers_list, bpp); - if (ret) + if (ret) { + xfs_buf_relse(new_bp); return ret; + } /* Initialize the new btree block. */ xfs_btree_init_block_cur(cur, new_bp, level, nr_this_block); diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index f190c088591b..3d02a0d7ba44 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -130,7 +130,7 @@ xfs_da_state_reset( state->mp = state->args->dp->i_mount; } -static inline int xfs_dabuf_nfsb(struct xfs_mount *mp, int whichfork) +inline int xfs_dabuf_nfsb(struct xfs_mount *mp, int whichfork) { if (whichfork == XFS_DATA_FORK) return mp->m_dir_geo->fsbcount; @@ -2384,6 +2384,7 @@ xfs_da_grow_inode_int( } /* account for newly allocated blocks in reserved blocks total */ + ASSERT(args->total >= dp->i_nblocks - nblks); args->total -= dp->i_nblocks - nblks; out_free_map: @@ -2746,8 +2747,8 @@ xfs_dabuf_map( * larger one that needs to be free by the caller. */ if (nirecs > 1) { - map = kcalloc(nirecs, sizeof(struct xfs_buf_map), - GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); + map = kzalloc_objs(struct xfs_buf_map, nirecs, + GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); *mapp = map; } diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h index afcf2d3c7a21..a718b1ceb0aa 100644 --- a/fs/xfs/libxfs/xfs_da_btree.h +++ b/fs/xfs/libxfs/xfs_da_btree.h @@ -244,4 +244,6 @@ xfs_failaddr_t xfs_da3_node_header_check(struct xfs_buf *bp, xfs_ino_t owner); extern struct kmem_cache *xfs_da_state_cache; +int xfs_dabuf_nfsb(struct xfs_mount *mp, int whichfork); + #endif /* __XFS_DA_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 89501e8bd2f8..3152acdc335d 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -229,6 +229,7 @@ xfs_defer_barrier_cancel_item( } static const struct xfs_defer_op_type xfs_barrier_defer_type = { + .name = "barrier", .max_items = 1, .create_intent = xfs_defer_barrier_create_intent, .abort_intent = xfs_defer_barrier_abort_intent, @@ -583,7 +584,7 @@ xfs_defer_finish_one( const struct xfs_defer_op_type *ops = dfp->dfp_ops; struct xfs_btree_cur *state = NULL; struct list_head *li, *n; - int error; + int error = 0; trace_xfs_defer_pending_finish(tp->t_mountp, dfp); @@ -655,6 +656,7 @@ xfs_defer_finish_noroll( struct xfs_trans **tp) { struct xfs_defer_pending *dfp = NULL; + const char *what = "chain"; int error = 0; LIST_HEAD(dop_pending); LIST_HEAD(dop_paused); @@ -704,9 +706,17 @@ xfs_defer_finish_noroll( struct xfs_defer_pending, dfp_list); if (!dfp) break; + what = dfp->dfp_ops->name; error = xfs_defer_finish_one(*tp, dfp); if (error && error != -EAGAIN) goto out_shutdown; + /* + * A finished item is no longer a candidate for a later + * failure. An -EAGAIN one is not finished, so it keeps the + * attribution across the roll that completes it. + */ + if (!error) + what = "chain"; } /* Requeue the paused items in the outgoing transaction. */ @@ -718,8 +728,12 @@ xfs_defer_finish_noroll( out_shutdown: list_splice_tail_init(&dop_paused, &dop_pending); xfs_defer_trans_abort(*tp, &dop_pending); - xfs_force_shutdown((*tp)->t_mountp, SHUTDOWN_CORRUPT_INCORE); trace_xfs_defer_finish_error(*tp, error); + if (!xfs_is_shutdown((*tp)->t_mountp)) + xfs_alert((*tp)->t_mountp, + "deferred %s work failed, error %d, %u blocks reserved", + what, error, (*tp)->t_blk_res); + xfs_force_shutdown((*tp)->t_mountp, SHUTDOWN_CORRUPT_INCORE); xfs_defer_cancel_list((*tp)->t_mountp, &dop_pending); xfs_defer_cancel(*tp); return error; diff --git a/fs/xfs/libxfs/xfs_exchmaps.c b/fs/xfs/libxfs/xfs_exchmaps.c index 3efed37cb98a..49eda8d0994d 100644 --- a/fs/xfs/libxfs/xfs_exchmaps.c +++ b/fs/xfs/libxfs/xfs_exchmaps.c @@ -969,6 +969,16 @@ xmi_can_exchange_reflink_flags( if (req->flags & XFS_EXCHMAPS_INO1_WRITTEN) return false; + /* + * The INO1_WRITTEN optimization can skip exchanging hole and + * unwritten mappings, which means we cannot guarantee that all + * shared extents actually moved to the other file. Clearing the + * reflink flag of an inode that still holds shared extents breaks + * the CoW write path, so refuse to exchange the flags in that case. + */ + if (req->flags & XFS_EXCHMAPS_INO1_WRITTEN) + return false; + if (hweight32(reflink_state) != 1) return false; if (req->startoff1 != 0 || req->startoff2 != 0) diff --git a/fs/xfs/libxfs/xfs_parent.c b/fs/xfs/libxfs/xfs_parent.c index 8d111c9b6527..a2f2f5fa640e 100644 --- a/fs/xfs/libxfs/xfs_parent.c +++ b/fs/xfs/libxfs/xfs_parent.c @@ -193,7 +193,7 @@ xfs_parent_addname( const struct xfs_name *parent_name, struct xfs_inode *child) { - int error; + int error, local; error = xfs_parent_iread_extents(tp, child); if (error) @@ -203,6 +203,10 @@ xfs_parent_addname( xfs_parent_da_args_init(&ppargs->args, tp, &ppargs->rec, child, I_INO(child), parent_name); + /* Growing the attr fork needs a real reservation in args->total. */ + ppargs->args.total = xfs_attr_calc_size(&ppargs->args, &local); + ASSERT(local); + return xfs_attr_setname(&ppargs->args, 0); } @@ -239,7 +243,7 @@ xfs_parent_replacename( const struct xfs_name *new_name, struct xfs_inode *child) { - int error; + int error, local; error = xfs_parent_iread_extents(tp, child); if (error) @@ -249,6 +253,10 @@ xfs_parent_replacename( xfs_parent_da_args_init(&ppargs->args, tp, &ppargs->rec, child, I_INO(child), old_name); + /* Growing the attr fork needs a real reservation in args->total. */ + ppargs->args.total = xfs_attr_calc_size(&ppargs->args, &local); + ASSERT(local); + xfs_inode_to_parent_rec(&ppargs->new_rec, new_dp); ppargs->args.new_name = new_name->name; diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h index c0b9f9f2c413..fca2eb74908c 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.h +++ b/fs/xfs/libxfs/xfs_rtgroup.h @@ -359,7 +359,11 @@ static inline int xfs_initialize_rtgroups(struct xfs_mount *mp, # define xfs_rtgroup_unlock(rtg, gf) ((void)0) # define xfs_rtgroup_trans_join(tp, rtg, gf) ((void)0) # define xfs_update_rtsb(bp, sb_bp) ((void)0) -# define xfs_log_rtsb(tp, sb_bp) (NULL) +static inline struct xfs_buf *xfs_log_rtsb(struct xfs_trans *tp, + const struct xfs_buf *sb_bp) +{ + return NULL; +} # define xfs_rtgroup_get_geometry(rtg, rgeo) (-EOPNOTSUPP) #endif /* CONFIG_XFS_RT */ diff --git a/fs/xfs/libxfs/xfs_rtrefcount_btree.c b/fs/xfs/libxfs/xfs_rtrefcount_btree.c index 22acc1411aac..e2950dbe2068 100644 --- a/fs/xfs/libxfs/xfs_rtrefcount_btree.c +++ b/fs/xfs/libxfs/xfs_rtrefcount_btree.c @@ -489,8 +489,11 @@ xfs_rtrefcountbt_maxlevels_ondisk(void) minrecs[0] = xfs_rtrefcountbt_block_maxrecs(blocklen, true) / 2; minrecs[1] = xfs_rtrefcountbt_block_maxrecs(blocklen, false) / 2; - /* We need at most one record for every block in an rt group. */ - return xfs_btree_compute_maxlevels(minrecs, XFS_MAX_RGBLOCKS); + /* + * We need at most one record for every block in an rt group, and + * one extra level for the inode root. + */ + return xfs_btree_compute_maxlevels(minrecs, XFS_MAX_RGBLOCKS) + 1; } int __init diff --git a/fs/xfs/libxfs/xfs_rtrmap_btree.c b/fs/xfs/libxfs/xfs_rtrmap_btree.c index c264bc5651c0..a15e460a1ec7 100644 --- a/fs/xfs/libxfs/xfs_rtrmap_btree.c +++ b/fs/xfs/libxfs/xfs_rtrmap_btree.c @@ -618,7 +618,7 @@ xfs_rtrmapbt_mem_cursor( struct xfs_btree_cur *cur; cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rtrmapbt_mem_ops, - mp->m_rtrmap_maxlevels, xfs_rtrmapbt_cur_cache); + xfs_rtrmapbt_maxlevels_ondisk(), xfs_rtrmapbt_cur_cache); cur->bc_mem.xfbtree = xfbt; cur->bc_nlevels = xfbt->nlevels; cur->bc_group = xfs_group_hold(rtg_group(rtg)); @@ -716,10 +716,12 @@ xfs_rtrmapbt_maxlevels_ondisk(void) * happens, which means that we must compute the max height based on * what the btree will look like if it consumes almost all the blocks * in the data device due to maximal sharing factor. + * + * Add one extra level for the inode root. */ max_dblocks = -1U; /* max ag count */ max_dblocks *= XFS_MAX_CRC_AG_BLOCKS; - return xfs_btree_space_to_height(minrecs, max_dblocks); + return xfs_btree_space_to_height(minrecs, max_dblocks) + 1; } int __init diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 75f2a021ee6d..f0341adbb879 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -1470,36 +1470,33 @@ xfs_sync_sb_buf( bool update_rtsb) { struct xfs_trans *tp; - struct xfs_buf *bp; - struct xfs_buf *rtsb_bp = NULL; int error; error = xfs_trans_alloc(mp, &M_RES(mp)->tr_sb, 0, 0, 0, &tp); if (error) return error; - bp = xfs_trans_getsb(tp); xfs_log_sb(tp); - xfs_trans_bhold(tp, bp); - if (update_rtsb) { - rtsb_bp = xfs_log_rtsb(tp, bp); - if (rtsb_bp) - xfs_trans_bhold(tp, rtsb_bp); - } + if (update_rtsb) + xfs_log_rtsb(tp, xfs_trans_getsb(tp)); xfs_trans_set_sync(tp); error = xfs_trans_commit(tp); if (error) - goto out; - /* - * write out the sb buffer to get the changes to disk - */ - error = xfs_bwrite(bp); - if (!error && rtsb_bp) - error = xfs_bwrite(rtsb_bp); -out: - if (rtsb_bp) - xfs_buf_relse(rtsb_bp); - xfs_buf_relse(bp); + return error; + + /* Re-acquire and write the sb and rtsb to disk. */ + xfs_buf_lock(mp->m_sb_bp); + error = xfs_bwrite(mp->m_sb_bp); + xfs_buf_unlock(mp->m_sb_bp); + if (error) + return error; + + if (update_rtsb && mp->m_rtsb_bp) { + xfs_buf_lock(mp->m_rtsb_bp); + error = xfs_bwrite(mp->m_rtsb_bp); + xfs_buf_unlock(mp->m_rtsb_bp); + } + return error; } diff --git a/fs/xfs/libxfs/xfs_trans_space.c b/fs/xfs/libxfs/xfs_trans_space.c index 9b8f495c9049..c4cd547033e5 100644 --- a/fs/xfs/libxfs/xfs_trans_space.c +++ b/fs/xfs/libxfs/xfs_trans_space.c @@ -22,8 +22,23 @@ xfs_parent_calc_space_res( unsigned int namelen) { /* - * Parent pointers are always the first attr in an attr tree, and never - * larger than a block + * A parent pointer is recorded per dirent, so an inode with N links + * carries N of them and the attr fork can already be in leaf or node + * format when one is added. That does not affect the reservation: + * XFS_DAENTER_SPACE_RES covers a split at every level of a + * maximum-depth attr dabtree, whatever format the fork is in now. + * + * The name is a dirent name and the value is a struct xfs_parent_rec, + * so the leaf entry is always local and never exceeds 272 bytes. + * Parent pointers require V5, hence a 1k minimum block size, so the + * entry always stays under half a block and this needs none of the + * double split allowance that xfs_attr_calc_size() makes. + * + * The second term hands a byte count to a macro whose parameter counts + * mappings, so it asks for more extent-add allowance than the single + * mapping a parent pointer adds - how much more depends on the block + * size. It over-reserves either way, which is why it is left alone: + * correcting the unit would shrink a reservation that is only generous. */ return XFS_DAENTER_SPACE_RES(mp, XFS_ATTR_FORK) + XFS_NEXTENTADD_SPACE_RES(mp, namelen, XFS_ATTR_FORK); diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c index 1fa66aa68e16..fa5d32ec020a 100644 --- a/fs/xfs/scrub/agheader.c +++ b/fs/xfs/scrub/agheader.c @@ -418,6 +418,13 @@ xchk_superblock( xchk_block_set_corrupt(sc, bp); } + if (xfs_has_zoned(mp)) { + if (sb->sb_rtstart != cpu_to_be64(mp->m_sb.sb_rtstart)) + xchk_block_set_corrupt(sc, bp); + if (sb->sb_rtreserved != cpu_to_be64(mp->m_sb.sb_rtreserved)) + xchk_block_set_corrupt(sc, bp); + } + /* Everything else must be zero. */ sblen = xchk_superblock_ondisk_size(mp); if (memchr_inv((char *)sb + sblen, 0, BBTOB(bp->b_length) - sblen)) diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c index 2104512f1ee1..a66b611588c4 100644 --- a/fs/xfs/scrub/agheader_repair.c +++ b/fs/xfs/scrub/agheader_repair.c @@ -668,14 +668,16 @@ xrep_agfl_init_header( struct xfs_scrub *sc, struct xfs_buf *agfl_bp, struct xagb_bitmap *agfl_extents, - xfs_agblock_t flcount) + xfs_agblock_t flcount, + struct xfs_agfl *old_agfl) { struct xrep_agfl_fill af = { .sc = sc, .flcount = flcount, }; struct xfs_mount *mp = sc->mp; - struct xfs_agfl *agfl; + struct xfs_agfl *agfl = XFS_BUF_TO_AGFL(agfl_bp); + const size_t agfl_sz = BBTOB(agfl_bp->b_length); int error; ASSERT(flcount <= xfs_agfl_size(mp)); @@ -684,8 +686,8 @@ xrep_agfl_init_header( * Start rewriting the header by setting the bno[] array to * NULLAGBLOCK, then setting AGFL header fields. */ - agfl = XFS_BUF_TO_AGFL(agfl_bp); - memset(agfl, 0xFF, BBTOB(agfl_bp->b_length)); + memcpy(old_agfl, agfl, agfl_sz); + memset(agfl, 0xFF, agfl_sz); agfl->agfl_magicnum = cpu_to_be32(XFS_AGFL_MAGIC); agfl->agfl_seqno = cpu_to_be32(pag_agno(sc->sa.pag)); uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_meta_uuid); @@ -697,16 +699,23 @@ xrep_agfl_init_header( */ xagb_bitmap_init(&af.used_extents); af.agfl_bno = xfs_buf_to_agfl_bno(agfl_bp); - xagb_bitmap_walk(agfl_extents, xrep_agfl_fill, &af); + error = xagb_bitmap_walk(agfl_extents, xrep_agfl_fill, &af); + if (error && error != -ECANCELED) + goto err_undo; error = xagb_bitmap_disunion(agfl_extents, &af.used_extents); if (error) - return error; + goto err_undo; /* Write new AGFL to disk. */ xfs_trans_buf_set_type(sc->tp, agfl_bp, XFS_BLFT_AGFL_BUF); - xfs_trans_log_buf(sc->tp, agfl_bp, 0, BBTOB(agfl_bp->b_length) - 1); + xfs_trans_log_buf(sc->tp, agfl_bp, 0, agfl_sz - 1); xagb_bitmap_destroy(&af.used_extents); return 0; + +err_undo: + xagb_bitmap_destroy(&af.used_extents); + memcpy(agfl, old_agfl, agfl_sz); + return error; } /* Repair the AGFL. */ @@ -718,6 +727,7 @@ xrep_agfl( struct xfs_mount *mp = sc->mp; struct xfs_buf *agf_bp; struct xfs_buf *agfl_bp; + struct xfs_agfl *old_agfl; xfs_agblock_t flcount; int error; @@ -725,6 +735,10 @@ xrep_agfl( if (!xfs_has_rmapbt(mp)) return -EOPNOTSUPP; + old_agfl = kzalloc(BBTOB(XFS_FSS_TO_BB(mp, 1)), XCHK_GFP_FLAGS); + if (!old_agfl) + return -ENOMEM; + xagb_bitmap_init(&agfl_extents); /* @@ -734,7 +748,7 @@ xrep_agfl( */ error = xfs_alloc_read_agf(sc->sa.pag, sc->tp, 0, &agf_bp); if (error) - return error; + goto err_old_agfl; /* * Make sure we have the AGFL buffer, as scrub might have decided it @@ -745,7 +759,7 @@ xrep_agfl( XFS_AGFL_DADDR(mp)), XFS_FSS_TO_BB(mp, 1), 0, &agfl_bp, NULL); if (error) - return error; + goto err_old_agfl; agfl_bp->b_ops = &xfs_agfl_buf_ops; /* Gather all the extents we're going to put on the new AGFL. */ @@ -762,10 +776,11 @@ xrep_agfl( * we adjust the AGF flcount (which can fail) so avoid updating any * buffers until we know that part works. */ - xrep_agfl_update_agf(sc, agf_bp, flcount); - error = xrep_agfl_init_header(sc, agfl_bp, &agfl_extents, flcount); + error = xrep_agfl_init_header(sc, agfl_bp, &agfl_extents, flcount, + old_agfl); if (error) goto err; + xrep_agfl_update_agf(sc, agf_bp, flcount); /* * Ok, the AGFL should be ready to go now. Roll the transaction to @@ -785,6 +800,8 @@ xrep_agfl( err: xagb_bitmap_destroy(&agfl_extents); +err_old_agfl: + kfree(old_agfl); return error; } diff --git a/fs/xfs/scrub/alloc_repair.c b/fs/xfs/scrub/alloc_repair.c index dce6ab0429dc..95e318e4f3a6 100644 --- a/fs/xfs/scrub/alloc_repair.c +++ b/fs/xfs/scrub/alloc_repair.c @@ -571,7 +571,7 @@ xrep_abt_dispose_one( * allocation, and blocks that didn't get used can be freed via the usual * (deferred) means. */ -STATIC void +STATIC int xrep_abt_dispose_reservations( struct xrep_abt *ra, int error) @@ -582,9 +582,13 @@ xrep_abt_dispose_reservations( goto junkit; list_for_each_entry_safe(resv, n, &ra->new_bnobt.resv_list, list) { - error = xrep_abt_dispose_one(ra, resv); - if (error) + int error2 = xrep_abt_dispose_one(ra, resv); + + if (error2) { + if (!error) + error = error2; goto junkit; + } } junkit: @@ -596,6 +600,7 @@ junkit: xrep_newbt_cancel(&ra->new_bnobt); xrep_newbt_cancel(&ra->new_cntbt); + return error; } /* Retrieve free space data for bulk load. */ @@ -801,7 +806,9 @@ xrep_abt_build_new_trees( goto err_newbt; /* Dispose of any unused blocks and the accounting information. */ - xrep_abt_dispose_reservations(ra, error); + error = xrep_abt_dispose_reservations(ra, error); + if (error) + return error; return xrep_roll_ag_trans(sc); @@ -812,8 +819,7 @@ err_cur: xfs_btree_del_cursor(cnt_cur, error); xfs_btree_del_cursor(bno_cur, error); err_newbt: - xrep_abt_dispose_reservations(ra, error); - return error; + return xrep_abt_dispose_reservations(ra, error); } /* diff --git a/fs/xfs/scrub/attr_repair.c b/fs/xfs/scrub/attr_repair.c index 6e6af142f1fb..28f92e9ba72b 100644 --- a/fs/xfs/scrub/attr_repair.c +++ b/fs/xfs/scrub/attr_repair.c @@ -1294,7 +1294,7 @@ xrep_xattr_swap_prep( .geo = sc->mp->m_attr_geo, .whichfork = XFS_ATTR_FORK, .trans = sc->tp, - .total = 1, + .total = xfs_dabuf_nfsb(sc->mp, XFS_ATTR_FORK), .owner = I_INO(sc->ip), }; diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 401c278725d2..4f3c7f681bd9 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -274,7 +274,7 @@ xchk_bmap_xref_rmap_cow( unsigned long long rmap_end; uint64_t owner = XFS_RMAP_OWN_COW; - if (!info->sc->sa.rmap_cur || xchk_skip_xref(info->sc->sm)) + if (xchk_skip_xref(info->sc->sm)) return; /* Find the rmap record for this irec. */ @@ -1103,8 +1103,9 @@ xchk_bmap( * the rmap must match the combined mapping exactly. */ while (xchk_bmap_iext_iter(&info, &irec)) { - if (xchk_should_terminate(sc, &error) || - (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) + if (xchk_should_terminate(sc, &error)) + return error; + if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) return 0; if (irec.br_startoff >= endoff) { diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index 9d627fd50687..f0f073a93413 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -74,7 +74,6 @@ int xchk_setup_ag_rmapbt(struct xfs_scrub *sc); int xchk_setup_ag_refcountbt(struct xfs_scrub *sc); int xchk_setup_inode(struct xfs_scrub *sc); int xchk_setup_inode_bmap(struct xfs_scrub *sc); -int xchk_setup_inode_bmap_data(struct xfs_scrub *sc); int xchk_setup_directory(struct xfs_scrub *sc); int xchk_setup_xattr(struct xfs_scrub *sc); int xchk_setup_symlink(struct xfs_scrub *sc); diff --git a/fs/xfs/scrub/dabtree.h b/fs/xfs/scrub/dabtree.h index de291e3b77dd..d654c125feb4 100644 --- a/fs/xfs/scrub/dabtree.h +++ b/fs/xfs/scrub/dabtree.h @@ -37,8 +37,6 @@ bool xchk_da_process_error(struct xchk_da_btree *ds, int level, int *error); void xchk_da_set_corrupt(struct xchk_da_btree *ds, int level); void xchk_da_set_preen(struct xchk_da_btree *ds, int level); -void xchk_da_set_preen(struct xchk_da_btree *ds, int level); - int xchk_da_btree_hash(struct xchk_da_btree *ds, int level, __be32 *hashp); int xchk_da_btree(struct xfs_scrub *sc, int whichfork, xchk_da_btree_rec_fn scrub_fn, void *private); diff --git a/fs/xfs/scrub/dir_repair.c b/fs/xfs/scrub/dir_repair.c index 1c088cfba10e..2cfcf1c35679 100644 --- a/fs/xfs/scrub/dir_repair.c +++ b/fs/xfs/scrub/dir_repair.c @@ -484,18 +484,24 @@ xrep_dir_recover_data( while (offset < end) { struct xfs_dir2_data_unused *dup = bp->b_addr + offset; struct xfs_dir2_data_entry *dep = bp->b_addr + offset; + unsigned int advance; if (xchk_should_terminate(rd->sc, &error)) return error; /* Skip unused entries. */ if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) { + if (!dup->length) + break; offset += be16_to_cpu(dup->length); continue; } /* Don't walk off the end of the block. */ - offset += xfs_dir2_data_entsize(rd->sc->mp, dep->namelen); + advance = xfs_dir2_data_entsize(rd->sc->mp, dep->namelen); + if (!advance) + break; + offset += advance; if (offset > end) break; @@ -721,7 +727,7 @@ xrep_dir_replay_removename( const struct xfs_name *name, xfs_extlen_t total) { - struct xfs_inode *dp = rd->args.dp; + struct xfs_inode *dp = rd->sc->tempip; ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); @@ -1375,9 +1381,24 @@ xrep_dir_live_update( if (p->delta > 0) error = xrep_dir_stash_createname(rd, p->name, I_INO(p->ip)); - else - error = xrep_dir_stash_removename(rd, p->name, + else { + /* + * xfs_dentry_to_name in unlink or rename-exchange can + * pass us names with ftype FT_UNKNOWN, but we really + * must know the ftype of the child that is being + * removed so that we can do nlink updates correctly + * without holding inode references. + */ + struct xfs_name name = { + .name = p->name->name, + .len = p->name->len, + .type = xfs_mode_to_ftype( + VFS_IC(p->ip)->i_mode), + }; + + error = xrep_dir_stash_removename(rd, &name, I_INO(p->ip)); + } mutex_unlock(&rd->pscan.lock); if (error) goto out_abort; @@ -1467,7 +1488,7 @@ xrep_dir_swap_prep( .geo = sc->mp->m_dir_geo, .whichfork = XFS_DATA_FORK, .trans = sc->tp, - .total = 1, + .total = xfs_dabuf_nfsb(sc->mp, XFS_DATA_FORK), .owner = I_INO(sc->ip), }; diff --git a/fs/xfs/scrub/dirtree.c b/fs/xfs/scrub/dirtree.c index b2cf6e5439d9..9b0ab2316612 100644 --- a/fs/xfs/scrub/dirtree.c +++ b/fs/xfs/scrub/dirtree.c @@ -259,6 +259,7 @@ xchk_dirtree_create_path( dl->nr_paths++; return 0; out_path: + xino_bitmap_destroy(&path->seen_inodes); kfree(path); return error; } @@ -368,12 +369,38 @@ xchk_dirpath_step_up( struct xfs_inode *dp; xfs_ino_t parent_ino = be64_to_cpu(dl->pptr_rec.p_ino); unsigned int lock_mode; - int error; + int error = 0; + + if (xchk_should_terminate(sc, &error)) + return error; /* Grab and lock the parent directory. */ error = xchk_iget(sc, parent_ino, &dp); - if (error) + switch (error) { + case -EINVAL: + case -ENOENT: + mutex_lock(&dl->lock); + + if (dl->stale) { + /* live update detected a change in this path */ + error = -ESTALE; + } else { + /* inode doesn't exist, path invalid */ + error = -EFSCORRUPTED; + + trace_xchk_dirpath_badino(dl->sc, path->path_nr, + path->nr_steps, &dl->xname, + &dl->pptr_rec); + } + + mutex_unlock(&dl->lock); + return error; + case 0: + /* keep going */ + break; + default: return error; + } lock_mode = xfs_ilock_attr_map_shared(dp); mutex_lock(&dl->lock); diff --git a/fs/xfs/scrub/dirtree_repair.c b/fs/xfs/scrub/dirtree_repair.c index bbf6acf6fd40..1d1eafcf6eb5 100644 --- a/fs/xfs/scrub/dirtree_repair.c +++ b/fs/xfs/scrub/dirtree_repair.c @@ -479,6 +479,7 @@ again: } if (xfs_has_parent(sc->mp)) { + memset(&dl->ppargs, 0, sizeof(dl->ppargs)); error = xfs_parent_removename(sc->tp, &dl->ppargs, dp, &dl->xname, sc->ip); if (error) @@ -618,6 +619,7 @@ xrep_dirtree_create_adoption_path( return 0; out_path: + xino_bitmap_destroy(&path->seen_inodes); kfree(path); return error; } diff --git a/fs/xfs/scrub/findparent.c b/fs/xfs/scrub/findparent.c index 04b6b96b0a30..eab3ac2704be 100644 --- a/fs/xfs/scrub/findparent.c +++ b/fs/xfs/scrub/findparent.c @@ -139,32 +139,52 @@ xrep_findparent_dirent( return 0; } -/* - * If this is a directory, walk the dirents looking for any that point to the - * scrub target inode. - */ -STATIC int -xrep_findparent_walk_directory( - struct xrep_findparent_info *fpi) +static inline bool +xrep_findparent_want_scan_file( + const struct xrep_findparent_info *fpi) { - struct xfs_scrub *sc = fpi->sc; - struct xfs_inode *dp = fpi->dp; - unsigned int lock_mode; - int error = 0; + const struct xfs_scrub *sc = fpi->sc; + const struct xfs_inode *dp = fpi->dp; + + /* Only directories can be parents */ + if (!S_ISDIR(VFS_IC(dp)->i_mode)) + return false; /* * The inode being scanned cannot be its own parent, nor can any * temporary directory we created to stage this repair. */ if (dp == sc->ip || dp == sc->tempip) - return 0; + return false; /* * Similarly, temporary files created to stage a repair cannot be the * parent of this inode. */ if (xrep_is_tempfile(dp)) + return false; + + return true; +} + +/* + * If this is a directory, walk the dirents looking for any that point to the + * scrub target inode. + */ +STATIC int +xrep_findparent_walk_file( + struct xrep_findparent_info *fpi) +{ + struct xfs_scrub *sc = fpi->sc; + struct xfs_inode *dp = fpi->dp; + unsigned int lock_mode; + int error = 0; + + if (!xrep_findparent_want_scan_file(fpi)) { + if (fpi->parent_scan) + xchk_iscan_mark_visited(&fpi->parent_scan->iscan, dp); return 0; + } /* * Scan the directory to see if there it contains an entry pointing to @@ -201,6 +221,8 @@ xrep_findparent_walk_directory( goto out_unlock; out_unlock: + if (fpi->parent_scan) + xchk_iscan_mark_visited(&fpi->parent_scan->iscan, dp); xfs_iunlock(dp, lock_mode); return error; } @@ -308,11 +330,7 @@ xrep_findparent_scan( ASSERT(S_ISDIR(VFS_IC(sc->ip)->i_mode)); while ((ret = xchk_iscan_iter(&pscan->iscan, &fpi.dp)) == 1) { - if (S_ISDIR(VFS_I(fpi.dp)->i_mode)) - ret = xrep_findparent_walk_directory(&fpi); - else - ret = 0; - xchk_iscan_mark_visited(&pscan->iscan, fpi.dp); + ret = xrep_findparent_walk_file(&fpi); xchk_irele(sc, fpi.dp); if (ret) break; @@ -401,7 +419,7 @@ xrep_findparent_confirm( goto out_rele; } - error = xrep_findparent_walk_directory(&fpi); + error = xrep_findparent_walk_file(&fpi); if (error) goto out_rele; diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index 19c0b1b2a787..9270ad075fe0 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -85,6 +85,8 @@ xchk_inobt_xref_finobt( goto no_record; error = xfs_inobt_get_rec(cur, &frec, &has_record); + if (error) + return error; if (!has_record) return -EFSCORRUPTED; @@ -188,6 +190,8 @@ xchk_finobt_xref_inobt( goto no_record; error = xfs_inobt_get_rec(cur, &irec, &has_record); + if (error) + return error; if (!has_record) return -EFSCORRUPTED; diff --git a/fs/xfs/scrub/metapath.c b/fs/xfs/scrub/metapath.c index ff1ff762b300..e0ee7d9b903f 100644 --- a/fs/xfs/scrub/metapath.c +++ b/fs/xfs/scrub/metapath.c @@ -23,6 +23,7 @@ #include "xfs_rtgroup.h" #include "xfs_rtrmap_btree.h" #include "xfs_rtrefcount_btree.h" +#include "xfs_ag.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" @@ -348,12 +349,78 @@ out_cancel: } #ifdef CONFIG_XFS_ONLINE_REPAIR +/* + * Given a directory @dp, an existing inode @ip, and a @name, link @ip into @dp + * under the given @name. + */ +static int +xrep_metadir_add_child( + struct xchk_metapath *mpath, + xfs_ino_t old_dotdot) +{ + struct xfs_trans *tp = mpath->sc->tp; + struct xfs_dir_update *du = &mpath->du; + struct xfs_inode *dp = du->dp; + const struct xfs_name *name = du->name; + struct xfs_inode *ip = du->ip; + struct xfs_mount *mp = tp->t_mountp; + const unsigned int resblks = mpath->link_resblks; + int error; + + /* + * The metadata file shouldn't be on the unlinked list, but we'll fix + * it if that is the case. + */ + if (VFS_I(ip)->i_nlink == 0) { + struct xfs_perag *pag; + + pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, I_INO(ip))); + error = xfs_iunlink_remove(tp, pag, ip); + xfs_perag_put(pag); + if (error) + return error; + } + + error = xfs_dir_createname(tp, dp, name, I_INO(ip), resblks); + if (error) + return error; + + xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE); + + xfs_bumplink(tp, ip); + + /* update dotdot entry in child */ + if (S_ISDIR(VFS_I(ip)->i_mode)) { + xfs_bumplink(tp, dp); + + /* Replace the dotdot entry in the child */ + if (old_dotdot != I_INO(dp)) { + error = xfs_dir_replace(tp, ip, &xfs_name_dotdot, + I_INO(dp), resblks); + if (error) + return error; + } + } + + /* Update the child's parent pointer */ + if (du->ppargs) { + error = xfs_parent_addname(tp, du->ppargs, dp, name, ip); + if (error) + return error; + } + + xfs_dir_update_hook(dp, ip, 1, name); + return 0; +} + /* Create the dirent represented by the final component of the path. */ STATIC int xrep_metapath_link( struct xchk_metapath *mpath) { struct xfs_scrub *sc = mpath->sc; + xfs_ino_t old_dotdot = NULLFSINO; + int error; mpath->du.dp = mpath->dp; mpath->du.name = &mpath->xname; @@ -366,7 +433,21 @@ xrep_metapath_link( trace_xrep_metapath_link(sc, mpath->path, mpath->dp, I_INO(sc->ip)); - return xfs_dir_add_child(sc->tp, mpath->link_resblks, &mpath->du); + if (S_ISDIR(VFS_I(sc->ip)->i_mode)) { + error = xchk_dir_lookup(sc, sc->ip, &xfs_name_dotdot, + &old_dotdot); + if (error && error != -ENOENT) + return error; + + /* + * subdir didn't give us a dotdot entry, so we just give up + * and let the repair get marked as failed. + */ + if (old_dotdot == NULLFSINO) + return 0; + } + + return xrep_metadir_add_child(mpath, old_dotdot); } /* Remove the dirent at the final component of the path. */ @@ -397,7 +478,7 @@ xrep_metapath_unlink( /* Figure out if we're removing a parent pointer too. */ if (xfs_has_parent(mp)) { - xfs_inode_to_parent_rec(&rec, ip); + xfs_inode_to_parent_rec(&rec, mpath->dp); error = xfs_parent_lookup(sc->tp, ip, &mpath->xname, &rec, &mpath->pptr_args); switch (error) { @@ -556,6 +637,8 @@ xrep_metapath_try_unlink( error = xchk_metapath_ilock_parent_and_child(mpath, ip); if (error) { xchk_trans_cancel(sc); + if (ip) + xchk_irele(sc, ip); return error; } xfs_trans_ijoin(sc->tp, mpath->dp, 0); diff --git a/fs/xfs/scrub/quota_repair.c b/fs/xfs/scrub/quota_repair.c index 487bd4f68ebb..59302e8afc7e 100644 --- a/fs/xfs/scrub/quota_repair.c +++ b/fs/xfs/scrub/quota_repair.c @@ -325,7 +325,7 @@ xrep_quota_block( * If there's nothing that would impede a dqiterate, we're * done. */ - if ((ddq->d_type & XFS_DQTYPE_REC_MASK) != dqtype || + if ((ddq->d_type & XFS_DQTYPE_REC_MASK) == dqtype && id == be32_to_cpu(ddq->d_id)) { xfs_trans_brelse(sc->tp, bp); return 0; @@ -363,11 +363,18 @@ xrep_quota_block( ddq->d_rtbcount, &ddq->d_rtbtimer, defq->rtb.time); + /* + * This transaction operates on raw disk buffers, so we don't + * have a dquot log item to assign the LSN for us. Instead, + * set it to zero so that log recovery will always replay any + * logged dquot item atop this buffer. + */ + dqblk->dd_lsn = 0; + /* We only support v5 filesystems so always set these. */ uuid_copy(&dqblk->dd_uuid, &sc->mp->m_sb.sb_meta_uuid); xfs_update_cksum((char *)dqblk, sizeof(struct xfs_dqblk), XFS_DQUOT_CRC_OFF); - dqblk->dd_lsn = 0; } switch (dqtype) { case XFS_DQTYPE_USER: @@ -455,8 +462,7 @@ xrep_quota_data_fork( if (truncate) { /* Erase everything after the block containing the max dquot */ - error = xfs_bunmapi_range(&sc->tp, sc->ip, 0, - max_dqid_off * sc->mp->m_sb.sb_blocksize, + error = xfs_bunmapi_range(&sc->tp, sc->ip, 0, max_dqid_off + 1, XFS_MAX_FILEOFF); if (error) goto out; diff --git a/fs/xfs/scrub/quotacheck.c b/fs/xfs/scrub/quotacheck.c index c199d128538e..c32030a05440 100644 --- a/fs/xfs/scrub/quotacheck.c +++ b/fs/xfs/scrub/quotacheck.c @@ -263,8 +263,10 @@ xqcheck_mod_live_ino_dqtrx( dqa->tx_id = p->tx_id; error = rhashtable_insert_fast(&xqc->shadow_dquot_acct, &dqa->hash, xqcheck_dqacct_hash_params); - if (error) + if (error) { + kfree(dqa); goto out_abort; + } } /* Find the shadow dqtrx (or an empty slot) here. */ diff --git a/fs/xfs/scrub/reap.c b/fs/xfs/scrub/reap.c index fcd14c1703ea..f698b9be3dd1 100644 --- a/fs/xfs/scrub/reap.c +++ b/fs/xfs/scrub/reap.c @@ -601,7 +601,7 @@ xreap_configure_agextent_limits( /* Maximum overhead of invalidating one buffer. */ const unsigned int per_binval = - xfs_buf_inval_log_space(1, XFS_B_TO_FSBT(mp, max_binval)); + xfs_buf_inval_log_space(1, XFS_FSB_TO_B(mp, max_binval)); /* * For each transaction in a reap chain, we can delete some number of @@ -680,7 +680,7 @@ xreap_configure_agcow_limits( /* Overhead of invalidating one buffer */ const unsigned int per_binval = - xfs_buf_inval_log_space(1, XFS_B_TO_FSBT(mp, max_binval)); + xfs_buf_inval_log_space(1, XFS_FSB_TO_B(mp, max_binval)); /* * For each transaction in a reap chain, we can delete some number of @@ -1399,7 +1399,7 @@ xreap_bmapi_binval( * far we've gotten. */ if (!xreap_inc_binval(rs)) { - imap->br_blockcount = agbno_next - bno; + imap->br_blockcount = bno - agbno; goto out; } } diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index 4e1bf23e5b89..f8c51d8fbb3d 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -410,7 +410,7 @@ xchk_refcount_mergeable( const struct xfs_refcount_irec *r1 = &rrc->prev_rec; /* Ignore if prev_rec is not yet initialized. */ - if (r1->rc_blockcount > 0) + if (r1->rc_blockcount == 0) return false; if (r1->rc_domain != r2->rc_domain) @@ -581,8 +581,12 @@ xchk_xref_is_cow_staging( if (rc.rc_domain != XFS_REFC_DOMAIN_COW) xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0); + /* Can't start after bno */ + if (rc.rc_startblock > agbno) + xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0); + /* Must be at least as long as what was passed in */ - if (rc.rc_blockcount < len) + if (rc.rc_startblock + rc.rc_blockcount < agbno + len) xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0); } diff --git a/fs/xfs/scrub/rgsuper.c b/fs/xfs/scrub/rgsuper.c index 2bd2c0351b35..6e2abe5dc27c 100644 --- a/fs/xfs/scrub/rgsuper.c +++ b/fs/xfs/scrub/rgsuper.c @@ -36,8 +36,10 @@ xchk_rgsuperblock_xref( if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) return; - xchk_xref_is_used_rt_space(sc, xfs_rgbno_to_rtb(sc->sr.rtg, 0), 1); - xchk_xref_is_only_rt_owned_by(sc, 0, 1, &XFS_RMAP_OINFO_FS); + xchk_xref_is_used_rt_space(sc, xfs_rgbno_to_rtb(sc->sr.rtg, 0), + sc->mp->m_sb.sb_rextsize); + xchk_xref_is_only_rt_owned_by(sc, 0, sc->mp->m_sb.sb_rextsize, + &XFS_RMAP_OINFO_FS); } int diff --git a/fs/xfs/scrub/rtrefcount.c b/fs/xfs/scrub/rtrefcount.c index 4e7c540c8d23..3d916d71a135 100644 --- a/fs/xfs/scrub/rtrefcount.c +++ b/fs/xfs/scrub/rtrefcount.c @@ -20,6 +20,7 @@ #include "xfs_metafile.h" #include "xfs_rtrefcount_btree.h" #include "xfs_rtalloc.h" +#include "xfs_ag.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/btree.h" @@ -375,7 +376,7 @@ xchk_rtrefcount_mergeable( const struct xfs_refcount_irec *r1 = &rrc->prev_rec; /* Ignore if prev_rec is not yet initialized. */ - if (r1->rc_blockcount > 0) + if (r1->rc_blockcount == 0) return false; if (r1->rc_startblock + r1->rc_blockcount != r2->rc_startblock) @@ -428,7 +429,7 @@ static inline void xchk_rtrefcountbt_xref_gaps( struct xfs_scrub *sc, struct xchk_rtrefcbt_records *rrc, - xfs_rtblock_t bno) + xfs_rgblock_t bno) { struct xfs_rmap_irec low; struct xfs_rmap_irec high; @@ -504,30 +505,75 @@ xchk_rtrefcountbt_rec( return 0; } +/* Count the number of blocks used by the rtrefcount btree file in this AG. */ +static int +xchk_rtrefcount_count_agblocks( + struct xfs_scrub *sc, + xfs_agnumber_t agno, + const struct xfs_owner_info *btree_oinfo, + xfs_filblks_t *blocks) +{ + xfs_filblks_t agblocks = 0; + int error; + + error = xchk_ag_init_existing(sc, agno, &sc->sa); + if (error) + goto out_free; + + /* + * If we don't have an rmap cursor, we can't complete the cross + * referencing, so return EFSCORRUPTED to end the loop and trigger the + * XFAIL flag. + */ + if (!sc->sa.rmap_cur) { + error = -EFSCORRUPTED; + goto out_free; + } + + error = xchk_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, btree_oinfo, + &agblocks); + if (error) + goto out_free; + + *blocks += agblocks; +out_free: + xchk_ag_free(sc, &sc->sa); + return error; +} + /* Make sure we have as many refc blocks as the rmap says. */ STATIC void -xchk_refcount_xref_rmap( +xchk_rtrefcount_xref_rmap( struct xfs_scrub *sc, const struct xfs_owner_info *btree_oinfo, xfs_extlen_t cow_blocks) { xfs_filblks_t refcbt_blocks = 0; - xfs_filblks_t blocks; - int error; + xfs_filblks_t blocks = 1; /* one for the iroot */ + xfs_agnumber_t agno; + int error = 0; - if (!sc->sr.rmap_cur || !sc->sa.rmap_cur || xchk_skip_xref(sc->sm)) + if (!xfs_has_rmapbt(sc->mp) || xchk_skip_xref(sc->sm)) return; /* Check that we saw as many refcbt blocks as the rmap knows about. */ error = xfs_btree_count_blocks(sc->sr.refc_cur, &refcbt_blocks); if (!xchk_btree_process_error(sc, sc->sr.refc_cur, 0, &error)) return; - error = xchk_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, btree_oinfo, - &blocks); - if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur)) + + for (agno = 0; agno < sc->mp->m_sb.sb_agcount; agno++) { + error = xchk_rtrefcount_count_agblocks(sc, agno, btree_oinfo, + &blocks); + if (error) + break; + } + if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error)) return; if (blocks != refcbt_blocks) - xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0); + xchk_fblock_xref_set_corrupt(sc, XFS_DATA_FORK, 0); + + if (!sc->sr.rmap_cur || xchk_skip_xref(sc->sm)) + return; /* Check that we saw as many cow blocks as the rmap knows about. */ error = xchk_count_rmap_ownedby_ag(sc, sc->sr.rmap_cur, @@ -538,7 +584,7 @@ xchk_refcount_xref_rmap( xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); } -/* Scrub the refcount btree for some AG. */ +/* Scrub the refcount btree for some rtgroup. */ int xchk_rtrefcountbt( struct xfs_scrub *sc) @@ -564,11 +610,11 @@ xchk_rtrefcountbt( /* * Check that all blocks between the last refcount > 1 record and the - * end of the rt volume have at most one reverse mapping. + * end of the rtgroup have at most one reverse mapping. */ - xchk_rtrefcountbt_xref_gaps(sc, &rrc, sc->mp->m_sb.sb_rblocks); - - xchk_refcount_xref_rmap(sc, &btree_oinfo, rrc.cow_blocks); + xchk_rtrefcountbt_xref_gaps(sc, &rrc, + xfs_rtx_to_rgbno(sc->sr.rtg, sc->mp->m_sb.sb_rgextents)); + xchk_rtrefcount_xref_rmap(sc, &btree_oinfo, rrc.cow_blocks); return 0; } @@ -609,8 +655,12 @@ xchk_xref_is_rt_cow_staging( if (rc.rc_domain != XFS_REFC_DOMAIN_COW) xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); + /* Can't start after bno */ + if (rc.rc_startblock > bno) + xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); + /* Must be at least as long as what was passed in */ - if (rc.rc_blockcount < len) + if (rc.rc_startblock + rc.rc_blockcount < bno + len) xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); } diff --git a/fs/xfs/scrub/rtsummary_repair.c b/fs/xfs/scrub/rtsummary_repair.c index f065c3e51ce2..ed763290aec1 100644 --- a/fs/xfs/scrub/rtsummary_repair.c +++ b/fs/xfs/scrub/rtsummary_repair.c @@ -164,9 +164,10 @@ xrep_rtsummary( /* * Now exchange the contents. Nothing in repair uses the temporary * buffer, so we can reuse it for the tempfile exchrange information. + * Use XFS_MAX_FILEOFF here so that we correct the rtsummary file size. */ error = xrep_tempexch_trans_reserve(sc, XFS_DATA_FORK, 0, - rts->rsumblocks, &rts->tempexch); + XFS_MAX_FILEOFF, &rts->tempexch); if (error) return error; diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 8742445c86f4..12c228b7f477 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -765,8 +765,7 @@ out_nofix: out_teardown: error = xchk_teardown(sc, error); out_sc: - if (error != -ENOENT) - xchk_stats_merge(mp, sm, &run); + xchk_stats_merge(mp, sm, error, &run); kfree(sc); out: trace_xchk_done(XFS_I(file_inode(file)), sm, error); diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h index 6d7d3523b71f..737a5d6db15f 100644 --- a/fs/xfs/scrub/scrub.h +++ b/fs/xfs/scrub/scrub.h @@ -261,7 +261,6 @@ static inline int xchk_nothing(struct xfs_scrub *sc) } /* Metadata scrubbers */ -int xchk_tester(struct xfs_scrub *sc); int xchk_superblock(struct xfs_scrub *sc); int xchk_agf(struct xfs_scrub *sc); int xchk_agfl(struct xfs_scrub *sc); diff --git a/fs/xfs/scrub/stats.c b/fs/xfs/scrub/stats.c index ef3f6abdb706..3339cae4b39d 100644 --- a/fs/xfs/scrub/stats.c +++ b/fs/xfs/scrub/stats.c @@ -29,6 +29,7 @@ struct xchk_scrub_stats { uint32_t incomplete; uint32_t warning; uint32_t retries; + uint32_t runtime_errors; /* repair stats */ uint32_t repair_invocations; @@ -84,6 +85,7 @@ static const char *name_map[XFS_SCRUB_TYPE_NR] = { [XFS_SCRUB_TYPE_RGSUPER] = "rgsuper", [XFS_SCRUB_TYPE_RTRMAPBT] = "rtrmapbt", [XFS_SCRUB_TYPE_RTREFCBT] = "rtrefcountbt", + [XFS_SCRUB_TYPE_HEALTHY] = "healthy", }; /* Format the scrub stats into a text buffer, similar to pcp style. */ @@ -99,25 +101,32 @@ xchk_stats_format( int ret = 0; for (i = 0; i < XFS_SCRUB_TYPE_NR; i++, css++) { + struct xchk_scrub_stats fss; + if (!name_map[i]) continue; + spin_lock(&css->css_lock); + memcpy(&fss, css, offsetof(struct xchk_scrub_stats, css_lock)); + spin_unlock(&css->css_lock); + ret = scnprintf(buf, remaining, - "%s %u %u %u %u %u %u %u %u %u %llu %u %u %llu\n", + "%s %u %u %u %u %u %u %u %u %u %llu %u %u %llu %u\n", name_map[i], - (unsigned int)css->invocations, - (unsigned int)css->clean, - (unsigned int)css->corrupt, - (unsigned int)css->preen, - (unsigned int)css->xfail, - (unsigned int)css->xcorrupt, - (unsigned int)css->incomplete, - (unsigned int)css->warning, - (unsigned int)css->retries, - (unsigned long long)css->checktime_us, - (unsigned int)css->repair_invocations, - (unsigned int)css->repair_success, - (unsigned long long)css->repairtime_us); + (unsigned int)fss.invocations, + (unsigned int)fss.clean, + (unsigned int)fss.corrupt, + (unsigned int)fss.preen, + (unsigned int)fss.xfail, + (unsigned int)fss.xcorrupt, + (unsigned int)fss.incomplete, + (unsigned int)fss.warning, + (unsigned int)fss.retries, + (unsigned long long)fss.checktime_us, + (unsigned int)fss.repair_invocations, + (unsigned int)fss.repair_success, + (unsigned long long)fss.repairtime_us, + (unsigned int)fss.runtime_errors); if (ret <= 0) break; @@ -188,31 +197,41 @@ STATIC void xchk_stats_merge_one( struct xchk_stats *cs, const struct xfs_scrub_metadata *sm, + int error, const struct xchk_stats_run *run) { struct xchk_scrub_stats *css; + unsigned int sm_flags = sm->sm_flags; if (sm->sm_type >= XFS_SCRUB_TYPE_NR) { ASSERT(sm->sm_type < XFS_SCRUB_TYPE_NR); return; } + /* caller applies this same transformation after we return */ + if (error == -EFSCORRUPTED || error == -EFSBADCRC) { + sm_flags |= XFS_SCRUB_OFLAG_CORRUPT; + error = 0; + } + css = &cs->cs_stats[sm->sm_type]; spin_lock(&css->css_lock); css->invocations++; - if (!(sm->sm_flags & XFS_SCRUB_OFLAG_UNCLEAN)) + if (error) + css->runtime_errors++; + else if (!(sm_flags & XFS_SCRUB_OFLAG_UNCLEAN)) css->clean++; - if (sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + if (sm_flags & XFS_SCRUB_OFLAG_CORRUPT) css->corrupt++; - if (sm->sm_flags & XFS_SCRUB_OFLAG_PREEN) + if (sm_flags & XFS_SCRUB_OFLAG_PREEN) css->preen++; - if (sm->sm_flags & XFS_SCRUB_OFLAG_XFAIL) + if (sm_flags & XFS_SCRUB_OFLAG_XFAIL) css->xfail++; - if (sm->sm_flags & XFS_SCRUB_OFLAG_XCORRUPT) + if (sm_flags & XFS_SCRUB_OFLAG_XCORRUPT) css->xcorrupt++; - if (sm->sm_flags & XFS_SCRUB_OFLAG_INCOMPLETE) + if (sm_flags & XFS_SCRUB_OFLAG_INCOMPLETE) css->incomplete++; - if (sm->sm_flags & XFS_SCRUB_OFLAG_WARNING) + if (sm_flags & XFS_SCRUB_OFLAG_WARNING) css->warning++; css->retries += run->retries; css->checktime_us += howmany_64(run->scrub_ns, NSEC_PER_USEC); @@ -230,10 +249,14 @@ void xchk_stats_merge( struct xfs_mount *mp, const struct xfs_scrub_metadata *sm, + int error, const struct xchk_stats_run *run) { - xchk_stats_merge_one(&global_stats, sm, run); - xchk_stats_merge_one(mp->m_scrub_stats, sm, run); + if (error == -ENOENT) + return; + + xchk_stats_merge_one(&global_stats, sm, error, run); + xchk_stats_merge_one(mp->m_scrub_stats, sm, error, run); } /* debugfs boilerplate */ diff --git a/fs/xfs/scrub/stats.h b/fs/xfs/scrub/stats.h index b358ad8d8b90..221052b95dd0 100644 --- a/fs/xfs/scrub/stats.h +++ b/fs/xfs/scrub/stats.h @@ -27,7 +27,7 @@ void xchk_stats_register(struct xchk_stats *cs, struct dentry *parent); void xchk_stats_unregister(struct xchk_stats *cs); void xchk_stats_merge(struct xfs_mount *mp, const struct xfs_scrub_metadata *sm, - const struct xchk_stats_run *run); + int error, const struct xchk_stats_run *run); static inline u64 xchk_stats_now(void) { return ktime_get_ns(); } static inline u64 xchk_stats_elapsed_ns(u64 since) @@ -53,7 +53,7 @@ static inline u64 xchk_stats_elapsed_ns(u64 since) # define xchk_stats_unregister(cs) ((void)0) # define xchk_stats_now() (0) # define xchk_stats_elapsed_ns(x) (0 * (x)) -# define xchk_stats_merge(mp, sm, run) ((void)0) +# define xchk_stats_merge(mp, sm, error, run) ((void)0) #endif /* CONFIG_XFS_ONLINE_SCRUB_STATS */ #endif /* __XFS_SCRUB_STATS_H__ */ diff --git a/fs/xfs/scrub/symlink_repair.c b/fs/xfs/scrub/symlink_repair.c index 91c86ea0e0f1..181961364233 100644 --- a/fs/xfs/scrub/symlink_repair.c +++ b/fs/xfs/scrub/symlink_repair.c @@ -291,7 +291,7 @@ xrep_symlink_swap_prep( if (error) return error; - xfs_trans_log_inode(sc->tp, sc->ip, 0); + xfs_trans_log_inode(sc->tp, sc->tempip, logflags); error = xfs_defer_finish(&sc->tp); if (error) diff --git a/fs/xfs/scrub/tempfile.c b/fs/xfs/scrub/tempfile.c index 98820003b929..59a9213a3c7d 100644 --- a/fs/xfs/scrub/tempfile.c +++ b/fs/xfs/scrub/tempfile.c @@ -649,6 +649,19 @@ xrep_tempexch_prep_request( return 0; } +static inline unsigned int +xrep_tempexch_estimate_sf_resblks( + struct xfs_scrub *sc, + int whichfork) +{ + /* repairing a symlink target */ + if (S_ISLNK(VFS_I(sc->ip)->i_mode) && whichfork == XFS_DATA_FORK) + return 1; + + /* everything else is a directory or an xattr structure */ + return xfs_dabuf_nfsb(sc->mp, whichfork); +} + /* * Fill out the mapping exchange resource estimation structures in preparation * for exchanging the contents of a metadata file that we've rebuilt in the @@ -663,6 +676,8 @@ xrep_tempexch_estimate( struct xfs_ifork *ifp; struct xfs_ifork *tifp; int whichfork = xfs_exchmaps_reqfork(req); + unsigned int sf_resblks = + xrep_tempexch_estimate_sf_resblks(sc, whichfork); int state = 0; /* @@ -693,9 +708,9 @@ xrep_tempexch_estimate( * plus the block we converted. */ req->ip1_bcount = sc->tempip->i_nblocks; - req->ip2_bcount = 1; + req->ip2_bcount = sf_resblks; req->nr_exchanges = 1 + tifp->if_nextents; - req->resblks = 1; + req->resblks = sf_resblks; break; case 2: /* @@ -707,10 +722,10 @@ xrep_tempexch_estimate( * is (worst case) the extent count of the file being repaired * plus the block we converted. */ - req->ip1_bcount = 1; + req->ip1_bcount = sf_resblks; req->ip2_bcount = sc->ip->i_nblocks; req->nr_exchanges = 1 + ifp->if_nextents; - req->resblks = 1; + req->resblks = sf_resblks; break; case 3: /* @@ -722,10 +737,10 @@ xrep_tempexch_estimate( * fileoff 0. Presumably, the caller could not exchange the * two inode fork areas directly. */ - req->ip1_bcount = 1; - req->ip2_bcount = 1; + req->ip1_bcount = sf_resblks; + req->ip2_bcount = sf_resblks; req->nr_exchanges = 1; - req->resblks = 2; + req->resblks = 2 * sf_resblks; break; } diff --git a/fs/xfs/scrub/tempfile.h b/fs/xfs/scrub/tempfile.h index 71c1b54599c3..d44ed43bafe0 100644 --- a/fs/xfs/scrub/tempfile.h +++ b/fs/xfs/scrub/tempfile.h @@ -39,10 +39,6 @@ int xrep_tempfile_roll_trans(struct xfs_scrub *sc); void xrep_tempfile_copyout_local(struct xfs_scrub *sc, int whichfork); bool xrep_is_tempfile(const struct xfs_inode *ip); #else -static inline void xrep_tempfile_iolock_both(struct xfs_scrub *sc) -{ - xchk_ilock(sc, XFS_IOLOCK_EXCL); -} # define xrep_is_tempfile(ip) (false) # define xrep_tempfile_adjust_directory_tree(sc) (0) # define xrep_tempfile_rele(sc) diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index 14aa0ec1f09e..0f5adc293962 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -1640,7 +1640,7 @@ DECLARE_EVENT_CLASS(xchk_pptr_class, __entry->dev = ip->i_mount->m_super->s_dev; __entry->ino = I_INO(ip); __entry->namelen = name->len; - memcpy(__get_str(name), name, name->len); + memcpy(__get_str(name), name->name, name->len); __entry->far_ino = far_ino; ), TP_printk("dev %d:%d ino 0x%llx name '%.*s' far_ino 0x%llx", @@ -1706,6 +1706,39 @@ DEFINE_EVENT(xchk_dirtree_class, name, \ DEFINE_XCHK_DIRTREE_EVENT(xchk_dirtree_create_path); DEFINE_XCHK_DIRTREE_EVENT(xchk_dirpath_walk_upwards); +TRACE_EVENT(xchk_dirpath_badino, + TP_PROTO(struct xfs_scrub *sc, unsigned int path_nr, + unsigned int step_nr, const struct xfs_name *name, + const struct xfs_parent_rec *pptr), + TP_ARGS(sc, path_nr, step_nr, name, pptr), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(unsigned int, path_nr) + __field(unsigned int, step_nr) + __field(xfs_ino_t, parent_ino) + __field(unsigned int, parent_gen) + __field(unsigned int, namelen) + __dynamic_array(char, name, name->len) + ), + TP_fast_assign( + __entry->dev = sc->mp->m_super->s_dev; + __entry->path_nr = path_nr; + __entry->step_nr = step_nr; + __entry->parent_ino = be64_to_cpu(pptr->p_ino); + __entry->parent_gen = be32_to_cpu(pptr->p_gen); + __entry->namelen = name->len; + memcpy(__get_str(name), name->name, name->len); + ), + TP_printk("dev %d:%d path %u step %u parent_ino 0x%llx parent_gen 0x%x name '%.*s'", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->path_nr, + __entry->step_nr, + __entry->parent_ino, + __entry->parent_gen, + __entry->namelen, + __get_str(name)) +); + DECLARE_EVENT_CLASS(xchk_dirpath_class, TP_PROTO(struct xfs_scrub *sc, struct xfs_inode *ip, unsigned int path_nr, unsigned int step_nr, diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 74a6089abadf..8b6119776fb3 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -20,6 +20,7 @@ #include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_icache.h" +#include "xfs_ioend.h" #include "xfs_zone_alloc.h" #include "xfs_rtgroup.h" #include <linux/bio-integrity.h> @@ -37,15 +38,6 @@ XFS_WPC(struct iomap_writepage_ctx *ctx) } /* - * Fast and loose check if this write could update the on-disk inode size. - */ -static inline bool xfs_ioend_is_append(struct iomap_ioend *ioend) -{ - return ioend->io_offset + ioend->io_size > - XFS_I(ioend->io_inode)->i_disk_size; -} - -/* * Update on-disk file size now that data has been written to disk. */ int @@ -80,175 +72,6 @@ xfs_setfilesize( return xfs_trans_commit(tp); } -static void -xfs_ioend_put_open_zones( - struct iomap_ioend *ioend) -{ - struct iomap_ioend *tmp; - - /* - * Put the open zone for all ioends merged into this one (if any). - */ - list_for_each_entry(tmp, &ioend->io_list, io_list) - xfs_open_zone_put(tmp->io_private); - - /* - * The main ioend might not have an open zone if the submission failed - * before xfs_zone_alloc_and_submit got called. - */ - if (ioend->io_private) - xfs_open_zone_put(ioend->io_private); -} - -/* - * IO write completion. - */ -STATIC void -xfs_end_ioend_write( - struct iomap_ioend *ioend) -{ - struct xfs_inode *ip = XFS_I(ioend->io_inode); - struct xfs_mount *mp = ip->i_mount; - bool is_zoned = xfs_is_zoned_inode(ip); - xfs_off_t offset = ioend->io_offset; - size_t size = ioend->io_size; - unsigned int nofs_flag; - int error; - - /* - * We can allocate memory here while doing writeback on behalf of - * memory reclaim. To avoid memory allocation deadlocks set the - * task-wide nofs context for the following operations. - */ - nofs_flag = memalloc_nofs_save(); - - /* - * Just clean up the in-memory structures if the fs has been shut down. - */ - if (xfs_is_shutdown(mp)) { - error = -EIO; - goto done; - } - - /* - * Clean up all COW blocks and underlying data fork delalloc blocks on - * I/O error. The delalloc punch is required because this ioend was - * mapped to blocks in the COW fork and the associated pages are no - * longer dirty. If we don't remove delalloc blocks here, they become - * stale and can corrupt free space accounting on unmount. - */ - error = blk_status_to_errno(ioend->io_bio.bi_status); - if (unlikely(error)) { - /* - * Zoned writes update the in-core open zone accounting before - * I/O submission. A failed write leaves that state - * inconsistent, so shut down the filesystem instead of letting - * later writers wait forever for open zone space to become - * available. - */ - if (is_zoned) { - xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR); - goto done; - } - if (ioend->io_flags & IOMAP_IOEND_SHARED) { - ASSERT(!is_zoned); - xfs_reflink_cancel_cow_range(ip, offset, size, true); - xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, offset, - offset + size, NULL); - } - goto done; - } - - /* - * Success: commit the COW or unwritten blocks if needed. - */ - if (is_zoned) - error = xfs_zoned_end_io(ip, offset, size, ioend->io_sector, - ioend->io_private, NULLFSBLOCK); - else if (ioend->io_flags & IOMAP_IOEND_SHARED) - error = xfs_reflink_end_cow(ip, offset, size); - else if (ioend->io_flags & IOMAP_IOEND_UNWRITTEN) - error = xfs_iomap_write_unwritten(ip, offset, size, false); - - if (!error && - !(ioend->io_flags & IOMAP_IOEND_DIRECT) && - xfs_ioend_is_append(ioend)) - error = xfs_setfilesize(ip, offset, size); -done: - if (is_zoned) - xfs_ioend_put_open_zones(ioend); - iomap_finish_ioends(ioend, error); - memalloc_nofs_restore(nofs_flag); -} - -/* - * Finish all pending IO completions that require transactional modifications. - * - * We try to merge physical and logically contiguous ioends before completion to - * minimise the number of transactions we need to perform during IO completion. - * Both unwritten extent conversion and COW remapping need to iterate and modify - * one physical extent at a time, so we gain nothing by merging physically - * discontiguous extents here. - * - * The ioend chain length that we can be processing here is largely unbound in - * length and we may have to perform significant amounts of work on each ioend - * to complete it. Hence we have to be careful about holding the CPU for too - * long in this loop. - */ -void -xfs_end_io( - struct work_struct *work) -{ - struct xfs_inode *ip = - container_of(work, struct xfs_inode, i_ioend_work); - struct iomap_ioend *ioend; - struct list_head tmp; - unsigned long flags; - - spin_lock_irqsave(&ip->i_ioend_lock, flags); - list_replace_init(&ip->i_ioend_list, &tmp); - spin_unlock_irqrestore(&ip->i_ioend_lock, flags); - - iomap_sort_ioends(&tmp); - while ((ioend = list_first_entry_or_null(&tmp, struct iomap_ioend, - io_list))) { - list_del_init(&ioend->io_list); - iomap_ioend_try_merge(ioend, &tmp); - if (bio_op(&ioend->io_bio) == REQ_OP_READ) - iomap_finish_ioends(ioend, - blk_status_to_errno(ioend->io_bio.bi_status)); - else - xfs_end_ioend_write(ioend); - cond_resched(); - } -} - -void -xfs_end_bio( - struct bio *bio) -{ - struct iomap_ioend *ioend = iomap_ioend_from_bio(bio); - struct xfs_inode *ip = XFS_I(ioend->io_inode); - struct xfs_mount *mp = ip->i_mount; - unsigned long flags; - - /* - * For Appends record the actually written block number and set the - * boundary flag if needed. - */ - if (IS_ENABLED(CONFIG_XFS_RT) && bio_is_zone_append(bio)) { - ioend->io_sector = bio->bi_iter.bi_sector; - xfs_mark_rtg_boundary(ioend); - } - - spin_lock_irqsave(&ip->i_ioend_lock, flags); - if (list_empty(&ip->i_ioend_list)) - WARN_ON_ONCE(!queue_work(mp->m_unwritten_workqueue, - &ip->i_ioend_work)); - list_add_tail(&ioend->io_list, &ip->i_ioend_list); - spin_unlock_irqrestore(&ip->i_ioend_lock, flags); -} - /* * We cannot cancel the ioend directly on error. We may have already set other * pages under writeback and hence we have to run I/O completion to mark the @@ -631,13 +454,8 @@ xfs_zoned_map_blocks( XFS_BMAPI_REMAP); xfs_iunlock(ip, XFS_ILOCK_EXCL); - wpc->iomap.type = IOMAP_MAPPED; - wpc->iomap.flags = IOMAP_F_DIRTY; - wpc->iomap.bdev = mp->m_rtdev_targp->bt_bdev; - wpc->iomap.offset = offset; - wpc->iomap.length = XFS_FSB_TO_B(mp, count_fsb); - wpc->iomap.flags = IOMAP_F_ANON_WRITE; - + xfs_iomap_set_anon_write(ip, &wpc->iomap, offset, + XFS_FSB_TO_B(mp, count_fsb)); trace_xfs_zoned_map_blocks(ip, offset, wpc->iomap.length); return 0; } diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h index 5a7a0f1a0b49..d5ae5c9d4c26 100644 --- a/fs/xfs/xfs_aops.h +++ b/fs/xfs/xfs_aops.h @@ -10,6 +10,5 @@ extern const struct address_space_operations xfs_address_space_operations; extern const struct address_space_operations xfs_dax_aops; int xfs_setfilesize(struct xfs_inode *ip, xfs_off_t offset, size_t size); -void xfs_end_bio(struct bio *bio); #endif /* __XFS_AOPS_H__ */ diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index ee7c2e9c0340..8256c1d13ce2 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -139,7 +139,7 @@ xfs_buf_free( ASSERT(list_empty(&bp->b_lru)); if (!xfs_buftarg_is_mem(bp->b_target) && size >= PAGE_SIZE) - mm_account_reclaimed_pages(howmany(size, PAGE_SHIFT)); + mm_account_reclaimed_pages(howmany(size, PAGE_SIZE)); if (is_vmalloc_addr(bp->b_addr)) vfree(bp->b_addr); @@ -176,7 +176,7 @@ xfs_buf_alloc_kmem( ASSERT(is_power_of_2(size)); ASSERT(size < PAGE_SIZE); - bp->b_addr = kmalloc(size, gfp_mask); + bp->b_addr = kmalloc(size, gfp_mask | __GFP_RECLAIMABLE); if (!bp->b_addr) return -ENOMEM; diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h index 3159325dd17b..28c79989d725 100644 --- a/fs/xfs/xfs_buf_item.h +++ b/fs/xfs/xfs_buf_item.h @@ -60,7 +60,6 @@ static inline void xfs_buf_dquot_iodone(struct xfs_buf *bp) { } #endif /* CONFIG_XFS_QUOTA */ -void xfs_buf_iodone(struct xfs_buf *); bool xfs_buf_log_check_iovec(struct kvec *iovec); unsigned int xfs_buf_inval_log_space(unsigned int map_count, diff --git a/fs/xfs/xfs_exchmaps_item.c b/fs/xfs/xfs_exchmaps_item.c index c3745d33e54e..dd5d92ca1010 100644 --- a/fs/xfs/xfs_exchmaps_item.c +++ b/fs/xfs/xfs_exchmaps_item.c @@ -344,7 +344,17 @@ xfs_xmi_validate( if (!xfs_verify_fileext(mp, xlf->xmi_startoff1, xlf->xmi_blockcount)) return false; - return xfs_verify_fileext(mp, xlf->xmi_startoff2, xlf->xmi_blockcount); + if (!xfs_verify_fileext(mp, xlf->xmi_startoff2, xlf->xmi_blockcount)) + return false; + + if (xlf->xmi_flags & XFS_EXCHMAPS_SET_SIZES) { + if ((int64_t)xlf->xmi_isize1 < 0) + return false; + if ((int64_t)xlf->xmi_isize2 < 0) + return false; + } + + return true; } /* @@ -403,6 +413,13 @@ xfs_xmi_item_recover_intent( *ipp1 = ip1; *ipp2 = ip2; xmi = xfs_exchmaps_init_intent(req); + + /* Restore intended file sizes from recovered logged item */ + if (req->flags & XFS_EXCHMAPS_SET_SIZES) { + xmi->xmi_isize1 = xlf->xmi_isize1; + xmi->xmi_isize2 = xlf->xmi_isize2; + } + xfs_defer_add_item(dfp, &xmi->xmi_list); return xmi; diff --git a/fs/xfs/xfs_exchrange.c b/fs/xfs/xfs_exchrange.c index 94965a6c2187..c69ecd6a19de 100644 --- a/fs/xfs/xfs_exchrange.c +++ b/fs/xfs/xfs_exchrange.c @@ -504,6 +504,9 @@ xfs_exchange_range_finish( { int error; + if (fxr->flags & XFS_EXCHANGE_RANGE_DRY_RUN) + return 0; + error = file_remove_privs(fxr->file1); if (error) return error; @@ -783,9 +786,12 @@ xfs_exchange_range( if (ret) return ret; - fsnotify_modify(fxr->file1); - if (fxr->file2 != fxr->file1) - fsnotify_modify(fxr->file2); + if (!(fxr->flags & XFS_EXCHANGE_RANGE_DRY_RUN)) { + fsnotify_modify(fxr->file1); + if (fxr->file2 != fxr->file1) + fsnotify_modify(fxr->file2); + } + return 0; } diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c index 41cf0605ec22..6da8c1f938aa 100644 --- a/fs/xfs/xfs_extent_busy.c +++ b/fs/xfs/xfs_extent_busy.c @@ -161,8 +161,8 @@ xfs_extent_busy_update_extent( xfs_agblock_t fbno, xfs_extlen_t flen, bool userdata) - __releases(&eb->eb_lock) - __acquires(&eb->eb_lock) + __releases(&xg->xg_busy_extents->eb_lock) + __acquires(&xg->xg_busy_extents->eb_lock) { struct xfs_extent_busy_tree *eb = xg->xg_busy_extents; xfs_agblock_t fend = fbno + flen; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 7bff07e31cbd..d8202da15aca 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -25,7 +25,7 @@ #include "xfs_iomap.h" #include "xfs_reflink.h" #include "xfs_file.h" -#include "xfs_aops.h" +#include "xfs_ioend.h" #include "xfs_zone_alloc.h" #include "xfs_error.h" #include "xfs_errortag.h" @@ -129,9 +129,8 @@ xfs_file_fsync( int datasync) { struct xfs_inode *ip = XFS_I(file->f_mapping->host); - struct xfs_mount *mp = ip->i_mount; - int error, err2; int log_flushed = 0; + int error; trace_xfs_file_fsync(ip); @@ -139,30 +138,22 @@ xfs_file_fsync( if (error) return error; - if (xfs_is_shutdown(mp)) + if (xfs_is_shutdown(ip->i_mount)) return -EIO; xfs_iflags_clear(ip, XFS_ITRUNCATED); /* - * If we have an RT and/or log subvolume we need to make sure to flush - * the write cache the device used for file data first. This is to - * ensure newly written file data make it to disk before logging the new - * inode size in case of an extending write. - */ - if (XFS_IS_REALTIME_INODE(ip) && mp->m_rtdev_targp != mp->m_ddev_targp) - error = blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev); - else if (mp->m_logdev_targp != mp->m_ddev_targp) - error = blkdev_issue_flush(mp->m_ddev_targp->bt_bdev); - - /* - * If the inode has a inode log item attached, it may need the journal - * flushed to persist any changes the log item might be tracking. + * If the inode has a log item attached, we must force the log up to the + * last LSN in which the inode was modified to ensure all metadata is + * persisted. The log force will flush the caches for all devices + * before writing the log records unless it is a no-op because there are + * no modifications to this inode that need to be pushed out. */ if (ip->i_itemp) { - err2 = xfs_fsync_flush_log(ip, datasync, &log_flushed); - if (err2 && !error) - error = err2; + error = xfs_fsync_flush_log(ip, datasync, &log_flushed); + if (error) + return error; } /* @@ -171,21 +162,11 @@ xfs_file_fsync( * when no metadata needed to be committed. * * Use the inode's actual file data target rather than assuming the - * main data device. Realtime inodes with a separate realtime device - * are flushed before the log force, so this fallback only applies - * when the file data target is the same as the log target. + * main data device. */ - if (!log_flushed) { - struct xfs_buftarg *file_targp = xfs_inode_buftarg(ip); - - if (mp->m_logdev_targp == file_targp) { - err2 = blkdev_issue_flush(file_targp->bt_bdev); - if (err2 && !error) - error = err2; - } - } - - return error; + if (!log_flushed) + return blkdev_issue_flush(xfs_inode_buftarg(ip)->bt_bdev); + return 0; } static int diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index b6a3bc9f143c..041bb2105ec6 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -1174,8 +1174,7 @@ xfs_getfsmap( if (!xfs_getfsmap_check_keys(&head->fmh_keys[0], &head->fmh_keys[1])) return -EINVAL; - use_rmap = xfs_has_rmapbt(mp) && - has_capability_noaudit(current, CAP_SYS_ADMIN); + use_rmap = xfs_has_rmapbt(mp) && capable_noaudit(CAP_SYS_ADMIN); head->fmh_entries = 0; /* Set up our device handlers. */ diff --git a/fs/xfs/xfs_healthmon.c b/fs/xfs/xfs_healthmon.c index 4521ffdab9f1..c3749675ef19 100644 --- a/fs/xfs/xfs_healthmon.c +++ b/fs/xfs/xfs_healthmon.c @@ -87,12 +87,10 @@ xfs_healthmon_put( struct xfs_healthmon *hm) { if (refcount_dec_and_test(&hm->ref)) { - struct xfs_healthmon_event *event; - struct xfs_healthmon_event *next = hm->first_event; + struct xfs_healthmon_event *event, *s; - while ((event = next) != NULL) { + list_for_each_entry_safe(event, s, &hm->event_list, entry) { trace_xfs_healthmon_drop(hm, event); - next = event->next; kfree(event); } @@ -173,9 +171,13 @@ static inline void xfs_healthmon_bump_lost(struct xfs_healthmon *hm) */ static bool xfs_healthmon_merge_events( - struct xfs_healthmon_event *existing, + struct xfs_healthmon *hm, const struct xfs_healthmon_event *new) { + struct xfs_healthmon_event *existing = + list_last_entry_or_null(&hm->event_list, struct + xfs_healthmon_event, entry); + if (!existing) return false; @@ -192,7 +194,7 @@ xfs_healthmon_merge_events( case XFS_HEALTHMON_LOST: existing->lostcount += new->lostcount; - return true; + goto out_merge; case XFS_HEALTHMON_SICK: case XFS_HEALTHMON_CORRUPT: @@ -200,19 +202,19 @@ xfs_healthmon_merge_events( switch (existing->domain) { case XFS_HEALTHMON_FS: existing->fsmask |= new->fsmask; - return true; + goto out_merge; case XFS_HEALTHMON_AG: case XFS_HEALTHMON_RTGROUP: if (existing->group == new->group){ existing->grpmask |= new->grpmask; - return true; + goto out_merge; } return false; case XFS_HEALTHMON_INODE: if (existing->ino == new->ino && existing->gen == new->gen) { existing->imask |= new->imask; - return true; + goto out_merge; } return false; default: @@ -224,18 +226,18 @@ xfs_healthmon_merge_events( case XFS_HEALTHMON_SHUTDOWN: /* yes, we can race to shutdown */ existing->flags |= new->flags; - return true; + goto out_merge; case XFS_HEALTHMON_MEDIA_ERROR: /* physically adjacent errors can merge */ if (existing->daddr + existing->bbcount == new->daddr) { existing->bbcount += new->bbcount; - return true; + goto out_merge; } if (new->daddr + new->bbcount == existing->daddr) { existing->daddr = new->daddr; existing->bbcount += new->bbcount; - return true; + goto out_merge; } return false; @@ -250,63 +252,58 @@ xfs_healthmon_merge_events( if (existing->fpos + existing->flen == new->fpos) { existing->flen += new->flen; - return true; + goto out_merge; } if (new->fpos + new->flen == existing->fpos) { existing->fpos = new->fpos; existing->flen += new->flen; - return true; + goto out_merge; } return false; } return false; + +out_merge: + trace_xfs_healthmon_merge(hm, existing); + return true; } -/* Insert an event onto the start of the queue. */ +enum insert_where { + INSERT_HEAD, + INSERT_TAIL, +}; + +/* Add an event onto the start or the end of the queue. */ static inline void __xfs_healthmon_insert( struct xfs_healthmon *hm, + enum insert_where where, struct xfs_healthmon_event *event) { struct timespec64 now; + lockdep_assert_held(&hm->lock); + ktime_get_coarse_real_ts64(&now); event->time_ns = (now.tv_sec * NSEC_PER_SEC) + now.tv_nsec; - event->next = hm->first_event; - if (!hm->first_event) - hm->first_event = event; - if (!hm->last_event) - hm->last_event = event; - xfs_healthmon_bump_events(hm); - wake_up(&hm->wait); - - trace_xfs_healthmon_insert(hm, event); -} + switch (where) { + case INSERT_HEAD: + trace_xfs_healthmon_insert_head(hm, event); -/* Push an event onto the end of the queue. */ -static inline void -__xfs_healthmon_push( - struct xfs_healthmon *hm, - struct xfs_healthmon_event *event) -{ - struct timespec64 now; + list_add(&event->entry, &hm->event_list); + break; + case INSERT_TAIL: + trace_xfs_healthmon_insert_tail(hm, event); - ktime_get_coarse_real_ts64(&now); - event->time_ns = (now.tv_sec * NSEC_PER_SEC) + now.tv_nsec; + list_add_tail(&event->entry, &hm->event_list); + break; + } - if (!hm->first_event) - hm->first_event = event; - if (hm->last_event) - hm->last_event->next = event; - hm->last_event = event; - event->next = NULL; xfs_healthmon_bump_events(hm); wake_up(&hm->wait); - - trace_xfs_healthmon_push(hm, event); } /* Deal with any previously lost events */ @@ -321,8 +318,7 @@ xfs_healthmon_clear_lost_prev( }; struct xfs_healthmon_event *event = NULL; - if (xfs_healthmon_merge_events(hm->last_event, &lost_event)) { - trace_xfs_healthmon_merge(hm, hm->last_event); + if (xfs_healthmon_merge_events(hm, &lost_event)) { wake_up(&hm->wait); goto cleared; } @@ -330,10 +326,12 @@ xfs_healthmon_clear_lost_prev( if (hm->events < XFS_HEALTHMON_MAX_EVENTS) event = kmemdup(&lost_event, sizeof(struct xfs_healthmon_event), GFP_NOFS); - if (!event) + if (!event) { + xfs_healthmon_bump_lost(hm); return -ENOMEM; + } - __xfs_healthmon_push(hm, event); + __xfs_healthmon_insert(hm, INSERT_TAIL, event); cleared: hm->lost_prev_event = 0; return 0; @@ -369,8 +367,7 @@ xfs_healthmon_push( } /* Try to merge with the newest event */ - if (xfs_healthmon_merge_events(hm->last_event, template)) { - trace_xfs_healthmon_merge(hm, hm->last_event); + if (xfs_healthmon_merge_events(hm, template)) { wake_up(&hm->wait); goto out_unlock; } @@ -387,7 +384,7 @@ xfs_healthmon_push( goto out_unlock; } - __xfs_healthmon_push(hm, event); + __xfs_healthmon_insert(hm, INSERT_TAIL, event); out_unlock: mutex_unlock(&hm->lock); @@ -415,8 +412,10 @@ xfs_healthmon_unmount( * There's nothing actionable for userspace after an unmount. Once * we've inserted the unmount event, hm no longer owns that event. */ - __xfs_healthmon_insert(hm, hm->unmount_event); + mutex_lock(&hm->lock); + __xfs_healthmon_insert(hm, INSERT_HEAD, hm->unmount_event); hm->unmount_event = NULL; + mutex_unlock(&hm->lock); xfs_healthmon_detach(hm); xfs_healthmon_put(hm); @@ -738,6 +737,13 @@ static const unsigned int type_map[] = { [XFS_HEALTHMON_DATALOST] = XFS_HEALTH_MONITOR_TYPE_DATALOST, }; +static inline bool +xfs_healthmon_check_outbuffer_space(const struct xfs_healthmon *hm) +{ + return hm->bufhead + sizeof(struct xfs_health_monitor_event) <= + hm->bufsize; +} + /* Render event as a V0 structure */ STATIC int xfs_healthmon_format_v0( @@ -804,10 +810,10 @@ xfs_healthmon_format_v0( break; } - ASSERT(hm->bufhead + sizeof(hme) <= hm->bufsize); + ASSERT(xfs_healthmon_check_outbuffer_space(hm)); /* copy formatted object to the outbuf */ - if (hm->bufhead + sizeof(hme) <= hm->bufsize) { + if (xfs_healthmon_check_outbuffer_space(hm)) { memcpy(hm->buffer + hm->bufhead, &hme, sizeof(hme)); hm->bufhead += sizeof(hme); } @@ -890,15 +896,18 @@ xfs_healthmon_format_pop( { struct xfs_healthmon_event *event; - if (hm->bufhead + sizeof(*event) > hm->bufsize) + /* + * Don't bother if there's not enough space to format even one event in + * the outbuffer. + */ + if (!xfs_healthmon_check_outbuffer_space(hm)) return NULL; mutex_lock(&hm->lock); - event = hm->first_event; + event = list_first_entry_or_null(&hm->event_list, + struct xfs_healthmon_event, entry); if (event) { - if (hm->last_event == event) - hm->last_event = NULL; - hm->first_event = event->next; + list_del_init(&event->entry); hm->events--; trace_xfs_healthmon_pop(hm, event); @@ -1198,6 +1207,7 @@ xfs_ioc_health_monitor( return -ENOMEM; hm->dev = mp->m_super->s_dev; refcount_set(&hm->ref, 1); + INIT_LIST_HEAD(&hm->event_list); mutex_init(&hm->lock); init_waitqueue_head(&hm->wait); @@ -1213,7 +1223,9 @@ xfs_ioc_health_monitor( } running_event->type = XFS_HEALTHMON_RUNNING; running_event->domain = XFS_HEALTHMON_MOUNT; - __xfs_healthmon_insert(hm, running_event); + mutex_lock(&hm->lock); + __xfs_healthmon_insert(hm, INSERT_HEAD, running_event); + mutex_unlock(&hm->lock); /* * Preallocate the unmount event so that we can't fail to notify the diff --git a/fs/xfs/xfs_healthmon.h b/fs/xfs/xfs_healthmon.h index 0e936507037f..fa3deb187a2b 100644 --- a/fs/xfs/xfs_healthmon.h +++ b/fs/xfs/xfs_healthmon.h @@ -31,8 +31,7 @@ struct xfs_healthmon { struct mutex lock; /* list of event objects */ - struct xfs_healthmon_event *first_event; - struct xfs_healthmon_event *last_event; + struct list_head event_list; /* preallocated event for unmount */ struct xfs_healthmon_event *unmount_event; @@ -110,7 +109,7 @@ enum xfs_healthmon_domain { }; struct xfs_healthmon_event { - struct xfs_healthmon_event *next; + struct list_head entry; enum xfs_healthmon_type type; enum xfs_healthmon_domain domain; diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 9d8dd30bd927..82dac88e3c4c 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -82,24 +82,20 @@ static inline xa_mark_t ici_tag_to_mark(unsigned int tag) /* * Allocate and initialise an xfs_inode. + * + * This can happen in context of already dirtied transactions, so the memory + * allocations must not fail. */ struct xfs_inode * xfs_inode_alloc( struct xfs_mount *mp, xfs_ino_t ino) { + gfp_t gfp = GFP_KERNEL | __GFP_NOFAIL; struct xfs_inode *ip; - /* - * XXX: If this didn't occur in transactions, we could drop GFP_NOFAIL - * and return NULL here on ENOMEM. - */ - ip = alloc_inode_sb(mp->m_super, xfs_inode_cache, GFP_KERNEL | __GFP_NOFAIL); - - if (inode_init_always(mp->m_super, VFS_I(ip))) { - kmem_cache_free(xfs_inode_cache, ip); - return NULL; - } + ip = alloc_inode_sb(mp->m_super, xfs_inode_cache, gfp); + inode_init_always_gfp(mp->m_super, VFS_I(ip), gfp); VFS_I(ip)->i_ino = ino; /* VFS doesn't initialise i_mode! */ @@ -501,7 +497,8 @@ xfs_iget_cache_hit( struct xfs_inode *ip, xfs_ino_t ino, int flags, - int lock_flags) __releases(RCU) + int lock_flags) + __releases_shared(RCU) { struct inode *inode = VFS_I(ip); struct xfs_mount *mp = ip->i_mount; diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 34c1038ebfcd..1602027cd0aa 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -585,7 +585,6 @@ uint xfs_ilock_attr_map_shared(struct xfs_inode *); int xfs_ifree(struct xfs_trans *, struct xfs_inode *); int xfs_itruncate_extents_flags(struct xfs_trans **, struct xfs_inode *, int, xfs_fsize_t, int); -void xfs_iext_realloc(xfs_inode_t *, int, int); int xfs_log_force_inode(struct xfs_inode *ip); void xfs_iunpin_wait(xfs_inode_t *); diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 1b53701bebea..96ca3e480cb9 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -647,7 +647,7 @@ xfs_ioctl_setattr_get_trans( goto out_error; error = xfs_trans_alloc_ichange(ip, NULL, NULL, pdqp, - has_capability_noaudit(current, CAP_FOWNER), &tp); + capable_noaudit(CAP_FOWNER), &tp); if (error) goto out_error; diff --git a/fs/xfs/xfs_ioend.c b/fs/xfs/xfs_ioend.c new file mode 100644 index 000000000000..40695d18dac0 --- /dev/null +++ b/fs/xfs/xfs_ioend.c @@ -0,0 +1,184 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2016-2025 Christoph Hellwig. + * All Rights Reserved. + */ +#include "xfs_platform.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_inode.h" +#include "xfs_iomap.h" +#include "xfs_trace.h" +#include "xfs_bmap_util.h" +#include "xfs_reflink.h" +#include "xfs_zone_alloc.h" +#include "xfs_ioend.h" + +static void +xfs_ioend_put_open_zones( + struct iomap_ioend *ioend) +{ + struct iomap_ioend *tmp; + + /* + * Put the open zone for all ioends merged into this one (if any). + */ + list_for_each_entry(tmp, &ioend->io_list, io_list) + xfs_open_zone_put(tmp->io_private); + + /* + * The main ioend might not have an open zone if the submission failed + * before xfs_zone_alloc_and_submit got called. + */ + if (ioend->io_private) + xfs_open_zone_put(ioend->io_private); +} + +static void +xfs_end_ioend_write( + struct iomap_ioend *ioend) +{ + struct xfs_inode *ip = XFS_I(ioend->io_inode); + struct xfs_mount *mp = ip->i_mount; + bool is_zoned = xfs_is_zoned_inode(ip); + xfs_off_t offset = ioend->io_offset; + size_t size = ioend->io_size; + unsigned int nofs_flag; + int error; + + /* + * We can allocate memory here while doing writeback on behalf of + * memory reclaim. To avoid memory allocation deadlocks set the + * task-wide nofs context for the following operations. + */ + nofs_flag = memalloc_nofs_save(); + + /* + * Just clean up the in-memory structures if the fs has been shut down. + */ + if (xfs_is_shutdown(mp)) { + error = -EIO; + goto done; + } + + /* + * Clean up all COW blocks and underlying data fork delalloc blocks on + * I/O error. The delalloc punch is required because this ioend was + * mapped to blocks in the COW fork and the associated pages are no + * longer dirty. If we don't remove delalloc blocks here, they become + * stale and can corrupt free space accounting on unmount. + */ + error = blk_status_to_errno(ioend->io_bio.bi_status); + if (unlikely(error)) { + /* + * Zoned writes update the in-core open zone accounting before + * I/O submission. A failed write leaves that state + * inconsistent, so shut down the filesystem instead of letting + * later writers wait forever for open zone space to become + * available. + */ + if (is_zoned) { + xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR); + goto done; + } + if (ioend->io_flags & IOMAP_IOEND_SHARED) { + ASSERT(!is_zoned); + xfs_reflink_cancel_cow_range(ip, offset, size, true); + xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, offset, + offset + size, NULL); + } + goto done; + } + + /* + * Success: commit the COW or unwritten blocks if needed. + */ + if (is_zoned) + error = xfs_zoned_end_io(ip, offset, size, ioend->io_sector, + ioend->io_private, NULLFSBLOCK); + else if (ioend->io_flags & IOMAP_IOEND_SHARED) + error = xfs_reflink_end_cow(ip, offset, size); + else if (ioend->io_flags & IOMAP_IOEND_UNWRITTEN) + error = xfs_iomap_write_unwritten(ip, offset, size, false); + + if (!error && + !(ioend->io_flags & IOMAP_IOEND_DIRECT) && + xfs_ioend_is_append(ioend)) + error = xfs_setfilesize(ip, offset, size); +done: + if (is_zoned) + xfs_ioend_put_open_zones(ioend); + iomap_finish_ioends(ioend, error); + memalloc_nofs_restore(nofs_flag); +} + +/* + * Finish all pending IO completions that require transactional modifications. + * + * We try to merge physical and logically contiguous ioends before completion to + * minimise the number of transactions we need to perform during IO completion. + * Both unwritten extent conversion and COW remapping need to iterate and modify + * one physical extent at a time, so we gain nothing by merging physically + * discontiguous extents here. + * + * The ioend chain length that we can be processing here is largely unbound in + * length and we may have to perform significant amounts of work on each ioend + * to complete it. Hence we have to be careful about holding the CPU for too + * long in this loop. + */ +void +xfs_end_io( + struct work_struct *work) +{ + struct xfs_inode *ip = + container_of(work, struct xfs_inode, i_ioend_work); + struct iomap_ioend *ioend; + struct list_head tmp; + unsigned long flags; + + spin_lock_irqsave(&ip->i_ioend_lock, flags); + list_replace_init(&ip->i_ioend_list, &tmp); + spin_unlock_irqrestore(&ip->i_ioend_lock, flags); + + iomap_sort_ioends(&tmp); + while ((ioend = list_first_entry_or_null(&tmp, struct iomap_ioend, + io_list))) { + list_del_init(&ioend->io_list); + iomap_ioend_try_merge(ioend, &tmp); + if (bio_op(&ioend->io_bio) == REQ_OP_READ) + iomap_finish_ioends(ioend, + blk_status_to_errno(ioend->io_bio.bi_status)); + else + xfs_end_ioend_write(ioend); + cond_resched(); + } +} + +void +xfs_end_bio( + struct bio *bio) +{ + struct iomap_ioend *ioend = iomap_ioend_from_bio(bio); + struct xfs_inode *ip = XFS_I(ioend->io_inode); + struct xfs_mount *mp = ip->i_mount; + unsigned long flags; + + /* + * For Appends record the actually written block number and set the + * boundary flag if needed. + */ + if (IS_ENABLED(CONFIG_XFS_RT) && bio_is_zone_append(bio)) { + ioend->io_sector = bio->bi_iter.bi_sector; + xfs_mark_rtg_boundary(ioend); + } + + spin_lock_irqsave(&ip->i_ioend_lock, flags); + if (list_empty(&ip->i_ioend_list)) + WARN_ON_ONCE(!queue_work(mp->m_unwritten_workqueue, + &ip->i_ioend_work)); + list_add_tail(&ioend->io_list, &ip->i_ioend_list); + spin_unlock_irqrestore(&ip->i_ioend_lock, flags); +} diff --git a/fs/xfs/xfs_ioend.h b/fs/xfs/xfs_ioend.h new file mode 100644 index 000000000000..525865767fca --- /dev/null +++ b/fs/xfs/xfs_ioend.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __XFS_IOEND_H +#define __XFS_IOEND_H + +/* + * Fast and loose check if this write could update the on-disk inode size. + */ +static inline bool xfs_ioend_is_append(struct iomap_ioend *ioend) +{ + return ioend->io_offset + ioend->io_size > + XFS_I(ioend->io_inode)->i_disk_size; +} + +void xfs_end_bio(struct bio *bio); + +#endif /* __XFS_IOEND_H */ diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 71c45be8c652..7c6238fed61e 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1083,12 +1083,7 @@ xfs_zoned_direct_write_iomap_begin( return error; } - iomap->type = IOMAP_MAPPED; - iomap->flags = IOMAP_F_DIRTY; - iomap->bdev = ip->i_mount->m_rtdev_targp->bt_bdev; - iomap->offset = offset; - iomap->length = length; - iomap->flags = IOMAP_F_ANON_WRITE; + xfs_iomap_set_anon_write(ip, iomap, offset, length); return 0; } diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index cffcec532ea6..f2520a9b3a13 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -29,6 +29,22 @@ int xfs_zero_range(struct xfs_inode *ip, loff_t pos, loff_t len, int xfs_truncate_page(struct xfs_inode *ip, loff_t pos, struct xfs_zone_alloc_ctx *ac, bool *did_zero); +static inline void +xfs_iomap_set_anon_write( + struct xfs_inode *ip, + struct iomap *iomap, + loff_t offset, + loff_t length) +{ + iomap->type = IOMAP_MAPPED; + iomap->bdev = ip->i_mount->m_rtdev_targp->bt_bdev; + iomap->offset = offset; + iomap->length = length; + iomap->flags = IOMAP_F_ANON_WRITE | IOMAP_F_DIRTY; + if (bdev_has_integrity_csum(iomap->bdev)) + iomap->flags |= IOMAP_F_INTEGRITY; +} + static inline xfs_filblks_t xfs_aligned_fsb_count( xfs_fileoff_t offset_fsb, diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 4a3299abf774..d1306e723899 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -834,7 +834,7 @@ xfs_setattr_nonsize( } error = xfs_trans_alloc_ichange(ip, udqp, gdqp, NULL, - has_capability_noaudit(current, CAP_FOWNER), &tp); + capable_noaudit(CAP_FOWNER), &tp); if (error) goto out_dqrele; diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index f807f8f4f705..f4f81d893e8c 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -422,6 +422,8 @@ out_error: static void xlog_state_shutdown_callbacks( struct xlog *log) + __releases(&log->l_icloglock) + __acquires(&log->l_icloglock) { struct xlog_in_core *iclog; LIST_HEAD(cb_list); @@ -470,6 +472,8 @@ xlog_state_release_iclog( struct xlog *log, struct xlog_in_core *iclog, struct xlog_ticket *ticket) + __releases(&log->l_icloglock) + __acquires(&log->l_icloglock) { bool last_ref; @@ -744,13 +748,16 @@ xfs_log_mount_cancel( */ static inline int xlog_force_iclog( + struct xlog *log, struct xlog_in_core *iclog) + __releases(&log->l_icloglock) + __acquires(&log->l_icloglock) { atomic_inc(&iclog->ic_refcnt); iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA; if (iclog->ic_state == XLOG_STATE_ACTIVE) - xlog_state_switch_iclogs(iclog->ic_log, iclog, 0); - return xlog_state_release_iclog(iclog->ic_log, iclog, NULL); + xlog_state_switch_iclogs(log, iclog, 0); + return xlog_state_release_iclog(log, iclog, NULL); } /* @@ -778,11 +785,10 @@ xlog_wait_iclog_completion(struct xlog *log) */ int xlog_wait_on_iclog( + struct xlog *log, struct xlog_in_core *iclog) - __releases(iclog->ic_log->l_icloglock) + __releases(log->l_icloglock) { - struct xlog *log = iclog->ic_log; - trace_xlog_iclog_wait_on(iclog, _RET_IP_); if (!xlog_is_shutdown(log) && iclog->ic_state != XLOG_STATE_ACTIVE && @@ -879,8 +885,8 @@ out_err: spin_lock(&log->l_icloglock); iclog = log->l_iclog; - error = xlog_force_iclog(iclog); - xlog_wait_on_iclog(iclog); + error = xlog_force_iclog(log, iclog); + xlog_wait_on_iclog(log, iclog); if (tic) { trace_xfs_log_umount_write(log, tic); @@ -1538,6 +1544,35 @@ xlog_bio_end_io( &iclog->ic_end_io_work); } +/* + * When using multiple devices, we also need to flush the data and RT device + * caches first to ensure that all metadata writeback covered by the LSN in + * this iclog is on stable storage. This is slow, but it *must* complete + * before we issue the external log IO. + * + * If the flush fails, we cannot conclude that past metadata writeback from + * the log succeeded. Repeating the flush is not possible, hence we must + * shut down with log IO error to avoid shutdown re-entering this path and + * erroring out again. + */ +static int +xlog_flush_data_caches( + struct xlog *log) +{ + struct xfs_mount *mp = log->l_mp; + + if (log->l_targ != mp->m_ddev_targp) { + if (blkdev_issue_flush(mp->m_ddev_targp->bt_bdev)) + return -EIO; + } + if (mp->m_rtdev_targp && mp->m_rtdev_targp != mp->m_ddev_targp) { + if (blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev)) + return -EIO; + } + + return 0; +} + STATIC void xlog_write_iclog( struct xlog *log, @@ -1582,21 +1617,9 @@ xlog_write_iclog( iclog->ic_bio.bi_private = iclog; if (iclog->ic_flags & XLOG_ICL_NEED_FLUSH) { - iclog->ic_bio.bi_opf |= REQ_PREFLUSH; - /* - * For external log devices, we also need to flush the data - * device cache first to ensure all metadata writeback covered - * by the LSN in this iclog is on stable storage. This is slow, - * but it *must* complete before we issue the external log IO. - * - * If the flush fails, we cannot conclude that past metadata - * writeback from the log succeeded. Repeating the flush is - * not possible, hence we must shut down with log IO error to - * avoid shutdown re-entering this path and erroring out again. - */ - if (log->l_targ != log->l_mp->m_ddev_targp && - blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev)) + if (xlog_flush_data_caches(log)) goto shutdown; + iclog->ic_bio.bi_opf |= REQ_PREFLUSH; } if (iclog->ic_flags & XLOG_ICL_NEED_FUA) iclog->ic_bio.bi_opf |= REQ_FUA; @@ -2741,14 +2764,17 @@ xlog_state_switch_iclogs( */ static int xlog_force_and_check_iclog( + struct xlog *log, struct xlog_in_core *iclog, bool *completed) + __releases(&log->l_icloglock) + __acquires(&log->l_icloglock) { xfs_lsn_t lsn = be64_to_cpu(iclog->ic_header->h_lsn); int error; *completed = false; - error = xlog_force_iclog(iclog); + error = xlog_force_iclog(log, iclog); if (error) return error; @@ -2825,7 +2851,7 @@ xfs_log_force( /* We have exclusive access to this iclog. */ bool completed; - if (xlog_force_and_check_iclog(iclog, &completed)) + if (xlog_force_and_check_iclog(log, iclog, &completed)) goto out_error; if (completed) @@ -2850,7 +2876,7 @@ xfs_log_force( iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA; if (flags & XFS_LOG_SYNC) - return xlog_wait_on_iclog(iclog); + return xlog_wait_on_iclog(log, iclog); out_unlock: spin_unlock(&log->l_icloglock); return 0; @@ -2920,7 +2946,7 @@ xlog_force_lsn( &log->l_icloglock); return -EAGAIN; } - if (xlog_force_and_check_iclog(iclog, &completed)) + if (xlog_force_and_check_iclog(log, iclog, &completed)) goto out_error; if (log_flushed) *log_flushed = 1; @@ -2948,7 +2974,7 @@ xlog_force_lsn( } if (flags & XFS_LOG_SYNC) - return xlog_wait_on_iclog(iclog); + return xlog_wait_on_iclog(log, iclog); out_unlock: spin_unlock(&log->l_icloglock); return 0; diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h index ca66429bf6c9..f715695e8fcb 100644 --- a/fs/xfs/xfs_log.h +++ b/fs/xfs/xfs_log.h @@ -105,8 +105,6 @@ int xfs_log_mount(struct xfs_mount *mp, int num_bblocks); int xfs_log_mount_finish(struct xfs_mount *mp); void xfs_log_mount_cancel(struct xfs_mount *); -xfs_lsn_t xlog_assign_tail_lsn(struct xfs_mount *mp); -xfs_lsn_t xlog_assign_tail_lsn_locked(struct xfs_mount *mp); void xfs_log_space_wake(struct xfs_mount *mp); int xfs_log_reserve(struct xfs_mount *mp, int length, int count, struct xlog_ticket **ticket, bool permanent); diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index 639f875a8fb2..f9e07a32f60f 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -1055,9 +1055,10 @@ xlog_cil_set_ctx_write_state( spin_unlock(&cil->xc_push_lock); /* - * Make sure the metadata we are about to overwrite in the log - * has been flushed to stable storage before this iclog is - * issued. + * Flush the write cache before writing the start record so that + * the metadata we are about to overwrite in the log and the + * data that new allocations in this context refer to are + * persisted to stable storage before this iclog is written. */ spin_lock(&cil->xc_log->l_icloglock); iclog->ic_flags |= XLOG_ICL_NEED_FLUSH; @@ -1556,7 +1557,7 @@ xlog_cil_push_work( * iclogs older than ic_prev. Hence we only need to wait * on the most recent older iclog here. */ - xlog_wait_on_iclog(ctx->commit_iclog->ic_prev); + xlog_wait_on_iclog(log, ctx->commit_iclog->ic_prev); spin_lock(&log->l_icloglock); } @@ -1627,6 +1628,7 @@ out_abort_free_ticket: static void xlog_cil_push_background( struct xlog *log) + __releases_shared(&log->l_cilp->xc_ctx_lock) { struct xfs_cil *cil = log->l_cilp; int space_used = atomic_read(&cil->xc_ctx->space_used); diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index cf1e4ce61a8c..6d9673c41cdf 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -605,8 +605,8 @@ xlog_wait( remove_wait_queue(wq, &wait); } -int xlog_wait_on_iclog(struct xlog_in_core *iclog) - __releases(iclog->ic_log->l_icloglock); +int xlog_wait_on_iclog(struct xlog *log, struct xlog_in_core *iclog) + __releases(log->l_icloglock); /* Calculate the distance between two LSNs in bytes */ static inline uint64_t diff --git a/fs/xfs/xfs_mru_cache.c b/fs/xfs/xfs_mru_cache.c index d61ec8cb126d..3f3af2e2e31c 100644 --- a/fs/xfs/xfs_mru_cache.c +++ b/fs/xfs/xfs_mru_cache.c @@ -520,7 +520,7 @@ xfs_mru_cache_lookup( if (elem) { list_del(&elem->list_node); _xfs_mru_cache_list_insert(mru, elem); - __release(mru_lock); /* help sparse not be stupid */ + __release(&mru->lock); } else spin_unlock(&mru->lock); diff --git a/fs/xfs/xfs_platform.h b/fs/xfs/xfs_platform.h index 59a33c60e0ca..5d542e95fe44 100644 --- a/fs/xfs/xfs_platform.h +++ b/fs/xfs/xfs_platform.h @@ -289,15 +289,4 @@ int xfs_rw_bdev(struct block_device *bdev, sector_t sector, unsigned int count, # define PTR_FMT "%p" #endif -/* - * Helper for IO routines to grab backing pages from allocated kernel memory. - */ -static inline struct page * -kmem_to_page(void *addr) -{ - if (is_vmalloc_addr(addr)) - return vmalloc_to_page(addr); - return virt_to_page(addr); -} - #endif /* _XFS_PLATFORM_H */ diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 4b2eeb7783f7..b24db75eaedc 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -445,7 +445,7 @@ xfs_shutdown_devices( blkdev_issue_flush(mp->m_logdev_targp->bt_bdev); invalidate_bdev(mp->m_logdev_targp->bt_bdev); } - if (mp->m_rtdev_targp) { + if (mp->m_rtdev_targp && mp->m_rtdev_targp != mp->m_ddev_targp) { blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev); invalidate_bdev(mp->m_rtdev_targp->bt_bdev); } diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index f333c938fbd9..6aa379c2cf0c 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -6139,8 +6139,8 @@ DEFINE_EVENT(xfs_healthmon_event_class, name, \ TP_PROTO(const struct xfs_healthmon *hm, \ const struct xfs_healthmon_event *event), \ TP_ARGS(hm, event)) -DEFINE_HEALTHMONEVENT_EVENT(xfs_healthmon_insert); -DEFINE_HEALTHMONEVENT_EVENT(xfs_healthmon_push); +DEFINE_HEALTHMONEVENT_EVENT(xfs_healthmon_insert_head); +DEFINE_HEALTHMONEVENT_EVENT(xfs_healthmon_insert_tail); DEFINE_HEALTHMONEVENT_EVENT(xfs_healthmon_pop); DEFINE_HEALTHMONEVENT_EVENT(xfs_healthmon_format); DEFINE_HEALTHMONEVENT_EVENT(xfs_healthmon_format_overflow); diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 99a9bf3762b7..f955479a08fd 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -33,7 +33,7 @@ STATIC void xfs_ail_check( struct xfs_ail *ailp, struct xfs_log_item *lip) - __must_hold(&ailp->ail_lock) + __must_hold(&ailp->ail_lock) { struct xfs_log_item *prev_lip; struct xfs_log_item *next_lip; @@ -321,6 +321,7 @@ static void xfs_ail_delete( struct xfs_ail *ailp, struct xfs_log_item *lip) + __must_hold(&ailp->ail_lock) { xfs_ail_check(ailp, lip); list_del(&lip->li_ail); @@ -899,6 +900,7 @@ xfs_lsn_t xfs_ail_delete_one( struct xfs_ail *ailp, struct xfs_log_item *lip) + __must_hold(&ailp->ail_lock) { struct xfs_log_item *mlip = xfs_ail_min(ailp); xfs_lsn_t lsn = lip->li_lsn; diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index 1e025848811a..a5d25b703dfc 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -521,7 +521,8 @@ xfs_trans_log_buf( { struct xfs_buf_log_item *bip = bp->b_log_item; - ASSERT(first <= last && last < BBTOB(bp->b_length)); + ASSERT(first <= last); + ASSERT(last < BBTOB(bp->b_length)); ASSERT(!(bip->bli_flags & XFS_BLI_ORDERED)); xfs_trans_dirty_buf(tp, bp); diff --git a/fs/xfs/xfs_verify_media.c b/fs/xfs/xfs_verify_media.c index 5ead3976d511..b75c81f8fcc0 100644 --- a/fs/xfs/xfs_verify_media.c +++ b/fs/xfs/xfs_verify_media.c @@ -268,6 +268,8 @@ xfs_verify_media( struct xfs_buftarg *btp = NULL; struct bio *bio; struct folio *folio; + xfs_daddr_t dev_start = 0; + xfs_daddr_t dev_end = 0; xfs_daddr_t daddr; uint64_t bbcount; int error = 0; @@ -277,24 +279,33 @@ xfs_verify_media( switch (me->me_dev) { case XFS_DEV_DATA: btp = mp->m_ddev_targp; + dev_end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks); break; case XFS_DEV_LOG: - if (mp->m_logdev_targp != mp->m_ddev_targp) + if (mp->m_logdev_targp != mp->m_ddev_targp) { btp = mp->m_logdev_targp; + dev_end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks); + } break; case XFS_DEV_RT: btp = mp->m_rtdev_targp; + dev_start = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rtstart); + dev_end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rtstart + + mp->m_sb.sb_rblocks); break; } if (!btp) return -ENODEV; /* - * If the caller told us to verify beyond the end of the disk, tell the - * user exactly where that was. + * If the caller told us to verify before the start or beyond the end + * of the disk volume, tell the user exactly where the volume starts + * and ends. */ - if (me->me_end_daddr > btp->bt_nr_sectors) - me->me_end_daddr = btp->bt_nr_sectors; + if (me->me_end_daddr > dev_end) + me->me_end_daddr = dev_end; + if (me->me_start_daddr < dev_start) + me->me_start_daddr = dev_start; /* start and end have to be aligned to the lba size */ if (!IS_ALIGNED(BBTOB(me->me_start_daddr | me->me_end_daddr), @@ -323,8 +334,7 @@ xfs_verify_media( * verifying. */ daddr = me->me_start_daddr; - bbcount = min_t(sector_t, me->me_end_daddr, btp->bt_nr_sectors) - - me->me_start_daddr; + bbcount = me->me_end_daddr - me->me_start_daddr; folio = xfs_verify_alloc_folio(xfs_verify_iosize(me, btp, bbcount)); if (!folio) diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c index 7d13fa7ab30a..28c1e48909fa 100644 --- a/fs/xfs/xfs_zone_alloc.c +++ b/fs/xfs/xfs_zone_alloc.c @@ -475,6 +475,8 @@ static struct xfs_open_zone * xfs_try_open_zone( struct xfs_mount *mp, enum rw_hint write_hint) + __releases(&mp->m_zone_info->zi_open_zones_lock) + __acquires(&mp->m_zone_info->zi_open_zones_lock) { struct xfs_zone_info *zi = mp->m_zone_info; struct xfs_open_zone *oz; @@ -793,17 +795,35 @@ xfs_get_cached_zone( rcu_read_lock(); oz = VFS_I(ip)->i_private; - if (oz) { - /* - * GC only steals open zones at mount time, so no GC zones - * should end up in the cache. - */ - ASSERT(!oz->oz_is_gc); - if (!atomic_inc_not_zero(&oz->oz_ref)) + if (!oz) + goto out_unlock; + + /* + * GC only steals open zones at mount time, so no GC zones should end up + * in the cache. + */ + ASSERT(!oz->oz_is_gc); + + /* + * Drop the old cached open zone if it is full. + */ + if (oz->oz_allocated == rtg_blocks(oz->oz_rtg)) { + spin_lock(&ip->i_flags_lock); + oz = VFS_I(ip)->i_private; + if (oz && oz->oz_allocated == rtg_blocks(oz->oz_rtg)) { + VFS_I(ip)->i_private = NULL; + spin_unlock(&ip->i_flags_lock); + xfs_open_zone_put(oz); oz = NULL; + goto out_unlock; + } + spin_unlock(&ip->i_flags_lock); } - rcu_read_unlock(); + if (!atomic_inc_not_zero(&oz->oz_ref)) + oz = NULL; +out_unlock: + rcu_read_unlock(); return oz; } @@ -818,18 +838,41 @@ xfs_get_cached_zone( * that were every written to, but significantly simplifies the cached zone * lookup. Because the open_zone is clearly marked as full when all data * in the underlying RTG was written, the caching is always safe. + * + * Called with a reference on @oz held. And returns two references on the + * returned zone: one for the caller and one for pinning the zone in + * inode->i_private. */ -static void +static struct xfs_open_zone * xfs_set_cached_zone( struct xfs_inode *ip, struct xfs_open_zone *oz) { struct xfs_open_zone *old_oz; + /* + * If the open zone cached in the inode still has free space, use that + * instead of the new open zone just selected. This can happen when + * multiple threads race to perform zone selection for an inode. + * io_uring worker threads seem to be good way to trigger this. + * + * We need to grab an extra reference to this open zone as the caller + * owns a reference in addition to the i_private pointer. + */ + spin_lock(&ip->i_flags_lock); + old_oz = VFS_I(ip)->i_private; + if (old_oz && old_oz->oz_allocated < rtg_blocks(old_oz->oz_rtg) && + atomic_inc_not_zero(&old_oz->oz_ref)) { + spin_unlock(&ip->i_flags_lock); + xfs_open_zone_put(oz); + return old_oz; + } + VFS_I(ip)->i_private = oz; atomic_inc(&oz->oz_ref); - old_oz = xchg(&VFS_I(ip)->i_private, oz); + spin_unlock(&ip->i_flags_lock); if (old_oz) xfs_open_zone_put(old_oz); + return oz; } static void @@ -873,14 +916,13 @@ xfs_zone_alloc_and_submit( * the inode is still associated with a zone and use that if so. */ if (!*oz) +select_zone: *oz = xfs_get_cached_zone(ip); - if (!*oz) { -select_zone: *oz = xfs_select_zone(mp, write_hint, pack_tight); if (!*oz) goto out_error; - xfs_set_cached_zone(ip, *oz); + *oz = xfs_set_cached_zone(ip, *oz); } alloc_len = xfs_zone_alloc_blocks(*oz, XFS_B_TO_FSB(mp, ioend->io_size), diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c index d0b85179a3d2..5fdcf98a2133 100644 --- a/fs/xfs/xfs_zone_gc.c +++ b/fs/xfs/xfs_zone_gc.c @@ -869,6 +869,11 @@ xfs_zone_gc_write_chunk( WRITE_ONCE(chunk->state, XFS_GC_BIO_NEW); list_move_tail(&chunk->entry, &data->writing); + /* + * If we run on top of stacked block device, the read I/O might have + * reset bi_bdev, restore it to the one we want. + */ + bio_set_dev(&chunk->bio, mp->m_rtdev_targp->bt_bdev); bio_reuse(&chunk->bio, REQ_OP_WRITE); while ((split_chunk = xfs_zone_gc_split_write(data, chunk))) xfs_zone_gc_submit_write(data, split_chunk); diff --git a/fs/xfs/xfs_zone_space_resv.c b/fs/xfs/xfs_zone_space_resv.c index 5c6e6ef627e4..7aa3c74fb2e0 100644 --- a/fs/xfs/xfs_zone_space_resv.c +++ b/fs/xfs/xfs_zone_space_resv.c @@ -85,13 +85,13 @@ xfs_zoned_add_available( struct xfs_zone_info *zi = mp->m_zone_info; struct xfs_zone_reservation *reservation; - if (list_empty_careful(&zi->zi_reclaim_reservations)) { - xfs_add_freecounter(mp, XC_FREE_RTAVAILABLE, count_fsb); + spin_lock(&zi->zi_reservation_lock); + xfs_add_freecounter(mp, XC_FREE_RTAVAILABLE, count_fsb); + if (list_empty(&zi->zi_reclaim_reservations)) { + spin_unlock(&zi->zi_reservation_lock); return; } - spin_lock(&zi->zi_reservation_lock); - xfs_add_freecounter(mp, XC_FREE_RTAVAILABLE, count_fsb); count_fsb = xfs_sum_freecounter(mp, XC_FREE_RTAVAILABLE); list_for_each_entry(reservation, &zi->zi_reclaim_reservations, entry) { if (reservation->count_fsb > count_fsb) |