diff options
Diffstat (limited to 'fs')
80 files changed, 1130 insertions, 776 deletions
diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 7d9b23d98..229308c7f 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -70,13 +70,14 @@ static struct afs_volume *afs_lookup_volume_rcu(struct afs_cell *cell, { struct afs_volume *volume = NULL; struct rb_node *p; - int seq = 0; + int seq = 1; do { /* Unfortunately, rbtree walking doesn't give reliable results * under just the RCU read lock, so we have to check for * changes. */ + seq++; /* 2 on the 1st/lockless path, otherwise odd */ read_seqbegin_or_lock(&cell->volume_lock, &seq); p = rcu_dereference_raw(cell->volumes.rb_node); diff --git a/fs/afs/server.c b/fs/afs/server.c index 684a2b02b..733e3c470 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -27,7 +27,7 @@ struct afs_server *afs_find_server(struct afs_net *net, const struct afs_addr_list *alist; struct afs_server *server = NULL; unsigned int i; - int seq = 0, diff; + int seq = 1, diff; rcu_read_lock(); @@ -35,6 +35,7 @@ struct afs_server *afs_find_server(struct afs_net *net, if (server) afs_unuse_server_notime(net, server, afs_server_trace_put_find_rsq); server = NULL; + seq++; /* 2 on the 1st/lockless path, otherwise odd */ read_seqbegin_or_lock(&net->fs_addr_lock, &seq); if (srx->transport.family == AF_INET6) { @@ -90,7 +91,7 @@ struct afs_server *afs_find_server_by_uuid(struct afs_net *net, const uuid_t *uu { struct afs_server *server = NULL; struct rb_node *p; - int diff, seq = 0; + int diff, seq = 1; _enter("%pU", uuid); @@ -102,7 +103,7 @@ struct afs_server *afs_find_server_by_uuid(struct afs_net *net, const uuid_t *uu if (server) afs_unuse_server(net, server, afs_server_trace_put_uuid_rsq); server = NULL; - + seq++; /* 2 on the 1st/lockless path, otherwise odd */ read_seqbegin_or_lock(&net->fs_lock, &seq); p = net->fs_servers.rb_node; diff --git a/fs/afs/volume.c b/fs/afs/volume.c index f84194b79..fb19c6928 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -302,7 +302,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key) { struct afs_server_list *new, *old, *discard; struct afs_vldb_entry *vldb; - char idbuf[16]; + char idbuf[24]; int ret, idsz; _enter(""); @@ -310,7 +310,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key) /* We look up an ID by passing it as a decimal string in the * operation's name parameter. */ - idsz = sprintf(idbuf, "%llu", volume->vid); + idsz = snprintf(idbuf, sizeof(idbuf), "%llu", volume->vid); vldb = afs_vl_lookup_vldb(volume->cell, key, idbuf, idsz); if (IS_ERR(vldb)) { @@ -565,13 +565,24 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events) void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) { - struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, rw); - struct kioctx *ctx = req->ki_ctx; + struct aio_kiocb *req; + struct kioctx *ctx; unsigned long flags; + /* + * kiocb didn't come from aio or is neither a read nor a write, hence + * ignore it. + */ + if (!(iocb->ki_flags & IOCB_AIO_RW)) + return; + + req = container_of(iocb, struct aio_kiocb, rw); + if (WARN_ON_ONCE(!list_empty(&req->ki_list))) return; + ctx = req->ki_ctx; + spin_lock_irqsave(&ctx->ctx_lock, flags); list_add_tail(&req->ki_list, &ctx->active_reqs); req->ki_cancel = cancel; @@ -1454,7 +1465,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) req->ki_complete = aio_complete_rw; req->private = NULL; req->ki_pos = iocb->aio_offset; - req->ki_flags = iocb_flags(req->ki_filp); + req->ki_flags = iocb_flags(req->ki_filp) | IOCB_AIO_RW; if (iocb->aio_flags & IOCB_FLAG_RESFD) req->ki_flags |= IOCB_EVENTFD; req->ki_hint = ki_hint_validate(file_write_hint(req->ki_filp)); diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index d2f77b124..f1731eeb8 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -2315,20 +2315,14 @@ struct btrfs_data_container *init_data_container(u32 total_bytes) size_t alloc_bytes; alloc_bytes = max_t(size_t, total_bytes, sizeof(*data)); - data = kvmalloc(alloc_bytes, GFP_KERNEL); + data = kvzalloc(alloc_bytes, GFP_KERNEL); if (!data) return ERR_PTR(-ENOMEM); - if (total_bytes >= sizeof(*data)) { + if (total_bytes >= sizeof(*data)) data->bytes_left = total_bytes - sizeof(*data); - data->bytes_missing = 0; - } else { + else data->bytes_missing = sizeof(*data) - total_bytes; - data->bytes_left = 0; - } - - data->elem_cnt = 0; - data->elem_missed = 0; return data; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 67831868e..3ddb09f2b 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2879,7 +2879,7 @@ struct btrfs_dir_item * btrfs_lookup_dir_index_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 dir, - u64 objectid, const char *name, int name_len, + u64 index, const char *name, int name_len, int mod); struct btrfs_dir_item * btrfs_search_dir_index_item(struct btrfs_root *root, diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index bcffe7886..cdfc791b3 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1135,6 +1135,9 @@ __btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans, if (ret) return ret; + ret = btrfs_record_root_in_trans(trans, node->root); + if (ret) + return ret; ret = btrfs_update_delayed_inode(trans, node->root, path, node); return ret; } diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index be6935d19..9a6055659 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -566,6 +566,23 @@ leave: return ret; } +static int btrfs_check_replace_dev_names(struct btrfs_ioctl_dev_replace_args *args) +{ + if (args->start.srcdevid == 0) { + if (memchr(args->start.srcdev_name, 0, + sizeof(args->start.srcdev_name)) == NULL) + return -ENAMETOOLONG; + } else { + args->start.srcdev_name[0] = 0; + } + + if (memchr(args->start.tgtdev_name, 0, + sizeof(args->start.tgtdev_name)) == NULL) + return -ENAMETOOLONG; + + return 0; +} + int btrfs_dev_replace_by_ioctl(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_dev_replace_args *args) { @@ -578,10 +595,9 @@ int btrfs_dev_replace_by_ioctl(struct btrfs_fs_info *fs_info, default: return -EINVAL; } - - if ((args->start.srcdevid == 0 && args->start.srcdev_name[0] == '\0') || - args->start.tgtdev_name[0] == '\0') - return -EINVAL; + ret = btrfs_check_replace_dev_names(args); + if (ret < 0) + return ret; ret = btrfs_dev_replace_start(fs_info, args->start.tgtdev_name, args->start.srcdevid, diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index 863367c2c..98c6faa8c 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -171,10 +171,40 @@ out_free: return 0; } +static struct btrfs_dir_item *btrfs_lookup_match_dir( + struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct btrfs_path *path, + struct btrfs_key *key, const char *name, + int name_len, int mod) +{ + const int ins_len = (mod < 0 ? -1 : 0); + const int cow = (mod != 0); + int ret; + + ret = btrfs_search_slot(trans, root, key, path, ins_len, cow); + if (ret < 0) + return ERR_PTR(ret); + if (ret > 0) + return ERR_PTR(-ENOENT); + + return btrfs_match_dir_item_name(root->fs_info, path, name, name_len); +} + /* - * lookup a directory item based on name. 'dir' is the objectid - * we're searching in, and 'mod' tells us if you plan on deleting the - * item (use mod < 0) or changing the options (use mod > 0) + * Lookup for a directory item by name. + * + * @trans: The transaction handle to use. Can be NULL if @mod is 0. + * @root: The root of the target tree. + * @path: Path to use for the search. + * @dir: The inode number (objectid) of the directory. + * @name: The name associated to the directory entry we are looking for. + * @name_len: The length of the name. + * @mod: Used to indicate if the tree search is meant for a read only + * lookup, for a modification lookup or for a deletion lookup, so + * its value should be 0, 1 or -1, respectively. + * + * Returns: NULL if the dir item does not exists, an error pointer if an error + * happened, or a pointer to a dir item if a dir item exists for the given name. */ struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -182,23 +212,18 @@ struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans, const char *name, int name_len, int mod) { - int ret; struct btrfs_key key; - int ins_len = mod < 0 ? -1 : 0; - int cow = mod != 0; + struct btrfs_dir_item *di; key.objectid = dir; key.type = BTRFS_DIR_ITEM_KEY; - key.offset = btrfs_name_hash(name, name_len); - ret = btrfs_search_slot(trans, root, &key, path, ins_len, cow); - if (ret < 0) - return ERR_PTR(ret); - if (ret > 0) + di = btrfs_lookup_match_dir(trans, root, path, &key, name, name_len, mod); + if (IS_ERR(di) && PTR_ERR(di) == -ENOENT) return NULL; - return btrfs_match_dir_item_name(root->fs_info, path, name, name_len); + return di; } int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir, @@ -212,7 +237,6 @@ int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir, int slot; struct btrfs_path *path; - path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -221,20 +245,20 @@ int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir, key.type = BTRFS_DIR_ITEM_KEY; key.offset = btrfs_name_hash(name, name_len); - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - - /* return back any errors */ - if (ret < 0) - goto out; + di = btrfs_lookup_match_dir(NULL, root, path, &key, name, name_len, 0); + if (IS_ERR(di)) { + ret = PTR_ERR(di); + /* Nothing found, we're safe */ + if (ret == -ENOENT) { + ret = 0; + goto out; + } - /* nothing found, we're safe */ - if (ret > 0) { - ret = 0; - goto out; + if (ret < 0) + goto out; } /* we found an item, look for our name in the item */ - di = btrfs_match_dir_item_name(root->fs_info, path, name, name_len); if (di) { /* our exact name was found */ ret = -EEXIST; @@ -261,35 +285,42 @@ out: } /* - * lookup a directory item based on index. 'dir' is the objectid - * we're searching in, and 'mod' tells us if you plan on deleting the - * item (use mod < 0) or changing the options (use mod > 0) + * Lookup for a directory index item by name and index number. + * + * @trans: The transaction handle to use. Can be NULL if @mod is 0. + * @root: The root of the target tree. + * @path: Path to use for the search. + * @dir: The inode number (objectid) of the directory. + * @index: The index number. + * @name: The name associated to the directory entry we are looking for. + * @name_len: The length of the name. + * @mod: Used to indicate if the tree search is meant for a read only + * lookup, for a modification lookup or for a deletion lookup, so + * its value should be 0, 1 or -1, respectively. * - * The name is used to make sure the index really points to the name you were - * looking for. + * Returns: NULL if the dir index item does not exists, an error pointer if an + * error happened, or a pointer to a dir item if the dir index item exists and + * matches the criteria (name and index number). */ struct btrfs_dir_item * btrfs_lookup_dir_index_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 dir, - u64 objectid, const char *name, int name_len, + u64 index, const char *name, int name_len, int mod) { - int ret; + struct btrfs_dir_item *di; struct btrfs_key key; - int ins_len = mod < 0 ? -1 : 0; - int cow = mod != 0; key.objectid = dir; key.type = BTRFS_DIR_INDEX_KEY; - key.offset = objectid; + key.offset = index; - ret = btrfs_search_slot(trans, root, &key, path, ins_len, cow); - if (ret < 0) - return ERR_PTR(ret); - if (ret > 0) - return ERR_PTR(-ENOENT); - return btrfs_match_dir_item_name(root->fs_info, path, name, name_len); + di = btrfs_lookup_match_dir(trans, root, path, &key, name, name_len, mod); + if (di == ERR_PTR(-ENOENT)) + return NULL; + + return di; } struct btrfs_dir_item * @@ -346,21 +377,18 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans, const char *name, u16 name_len, int mod) { - int ret; struct btrfs_key key; - int ins_len = mod < 0 ? -1 : 0; - int cow = mod != 0; + struct btrfs_dir_item *di; key.objectid = dir; key.type = BTRFS_XATTR_ITEM_KEY; key.offset = btrfs_name_hash(name, name_len); - ret = btrfs_search_slot(trans, root, &key, path, ins_len, cow); - if (ret < 0) - return ERR_PTR(ret); - if (ret > 0) + + di = btrfs_lookup_match_dir(trans, root, path, &key, name, name_len, mod); + if (IS_ERR(di) && PTR_ERR(di) == -ENOENT) return NULL; - return btrfs_match_dir_item_name(root->fs_info, path, name, name_len); + return di; } /* diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 0e25a3f64..019f0925f 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1553,8 +1553,17 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, again: root = btrfs_lookup_fs_root(fs_info, objectid); if (root) { - /* Shouldn't get preallocated anon_dev for cached roots */ - ASSERT(!anon_dev); + /* + * Some other caller may have read out the newly inserted + * subvolume already (for things like backref walk etc). Not + * that common but still possible. In that case, we just need + * to free the anon_dev. + */ + if (unlikely(anon_dev)) { + free_anon_bdev(anon_dev); + anon_dev = 0; + } + if (check_ref && btrfs_root_refs(&root->root_item) == 0) { btrfs_put_root(root); return ERR_PTR(-ENOENT); diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index bfa2bf445..d908afa1f 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -161,8 +161,15 @@ struct dentry *btrfs_get_parent(struct dentry *child) ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto fail; + if (ret == 0) { + /* + * Key with offset of -1 found, there would have to exist an + * inode with such number or a root with such id. + */ + ret = -EUCLEAN; + goto fail; + } - BUG_ON(ret == 0); /* Key with offset of -1 found */ if (path->slots[0] == 0) { ret = -ENOENT; goto fail; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 8f62e1710..3ba43a400 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1202,7 +1202,8 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len, u64 bytes_left, end; u64 aligned_start = ALIGN(start, 1 << 9); - if (WARN_ON(start != aligned_start)) { + /* Adjust the range to be aligned to 512B sectors if necessary. */ + if (start != aligned_start) { len -= aligned_start - start; len = round_down(len, 1 << 9); start = aligned_start; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c900a3966..591caac2b 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4007,7 +4007,8 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) struct btrfs_block_rsv block_rsv; u64 root_flags; int ret; - int err; + + down_write(&fs_info->subvol_sem); /* * Don't allow to delete a subvolume with send in progress. This is @@ -4020,25 +4021,25 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) btrfs_warn(fs_info, "attempt to delete subvolume %llu during send", dest->root_key.objectid); - return -EPERM; + ret = -EPERM; + goto out_up_write; } if (atomic_read(&dest->nr_swapfiles)) { spin_unlock(&dest->root_item_lock); btrfs_warn(fs_info, "attempt to delete subvolume %llu with active swapfile", root->root_key.objectid); - return -EPERM; + ret = -EPERM; + goto out_up_write; } root_flags = btrfs_root_flags(&dest->root_item); btrfs_set_root_flags(&dest->root_item, root_flags | BTRFS_ROOT_SUBVOL_DEAD); spin_unlock(&dest->root_item_lock); - down_write(&fs_info->subvol_sem); - - err = may_destroy_subvol(dest); - if (err) - goto out_up_write; + ret = may_destroy_subvol(dest); + if (ret) + goto out_undead; btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP); /* @@ -4046,13 +4047,13 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) * two for dir entries, * two for root ref/backref. */ - err = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true); - if (err) - goto out_up_write; + ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true); + if (ret) + goto out_undead; trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { - err = PTR_ERR(trans); + ret = PTR_ERR(trans); goto out_release; } trans->block_rsv = &block_rsv; @@ -4062,7 +4063,6 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) ret = btrfs_unlink_subvol(trans, dir, dentry); if (ret) { - err = ret; btrfs_abort_transaction(trans, ret); goto out_end_trans; } @@ -4080,7 +4080,6 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) dest->root_key.objectid); if (ret) { btrfs_abort_transaction(trans, ret); - err = ret; goto out_end_trans; } } @@ -4090,7 +4089,6 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) dest->root_key.objectid); if (ret && ret != -ENOENT) { btrfs_abort_transaction(trans, ret); - err = ret; goto out_end_trans; } if (!btrfs_is_empty_uuid(dest->root_item.received_uuid)) { @@ -4100,7 +4098,6 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) dest->root_key.objectid); if (ret && ret != -ENOENT) { btrfs_abort_transaction(trans, ret); - err = ret; goto out_end_trans; } } @@ -4111,20 +4108,20 @@ out_end_trans: trans->block_rsv = NULL; trans->bytes_reserved = 0; ret = btrfs_end_transaction(trans); - if (ret && !err) - err = ret; inode->i_flags |= S_DEAD; out_release: btrfs_subvolume_release_metadata(root, &block_rsv); -out_up_write: - up_write(&fs_info->subvol_sem); - if (err) { +out_undead: + if (ret) { spin_lock(&dest->root_item_lock); root_flags = btrfs_root_flags(&dest->root_item); btrfs_set_root_flags(&dest->root_item, root_flags & ~BTRFS_ROOT_SUBVOL_DEAD); spin_unlock(&dest->root_item_lock); - } else { + } +out_up_write: + up_write(&fs_info->subvol_sem); + if (!ret) { d_invalidate(dentry); btrfs_prune_dentries(dest); ASSERT(dest->send_in_progress == 0); @@ -4136,7 +4133,7 @@ out_up_write: } } - return err; + return ret; } static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) @@ -8971,8 +8968,6 @@ static int btrfs_rename_exchange(struct inode *old_dir, /* force full log commit if subvolume involved. */ btrfs_set_log_full_commit(trans); } else { - btrfs_pin_log_trans(root); - root_log_pinned = true; ret = btrfs_insert_inode_ref(trans, dest, new_dentry->d_name.name, new_dentry->d_name.len, @@ -8989,8 +8984,6 @@ static int btrfs_rename_exchange(struct inode *old_dir, /* force full log commit if subvolume involved. */ btrfs_set_log_full_commit(trans); } else { - btrfs_pin_log_trans(dest); - dest_log_pinned = true; ret = btrfs_insert_inode_ref(trans, root, old_dentry->d_name.name, old_dentry->d_name.len, @@ -9021,6 +9014,29 @@ static int btrfs_rename_exchange(struct inode *old_dir, BTRFS_I(new_inode), 1); } + /* + * Now pin the logs of the roots. We do it to ensure that no other task + * can sync the logs while we are in progress with the rename, because + * that could result in an inconsistency in case any of the inodes that + * are part of this rename operation were logged before. + * + * We pin the logs even if at this precise moment none of the inodes was + * logged before. This is because right after we checked for that, some + * other task fsyncing some other inode not involved with this rename + * operation could log that one of our inodes exists. + * + * We don't need to pin the logs before the above calls to + * btrfs_insert_inode_ref(), since those don't ever need to change a log. + */ + if (old_ino != BTRFS_FIRST_FREE_OBJECTID) { + btrfs_pin_log_trans(root); + root_log_pinned = true; + } + if (new_ino != BTRFS_FIRST_FREE_OBJECTID) { + btrfs_pin_log_trans(dest); + dest_log_pinned = true; + } + /* src is a subvolume */ if (old_ino == BTRFS_FIRST_FREE_OBJECTID) { ret = btrfs_unlink_subvol(trans, old_dir, old_dentry); @@ -9270,8 +9286,6 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, /* force full log commit if subvolume involved. */ btrfs_set_log_full_commit(trans); } else { - btrfs_pin_log_trans(root); - log_pinned = true; ret = btrfs_insert_inode_ref(trans, dest, new_dentry->d_name.name, new_dentry->d_name.len, @@ -9295,6 +9309,25 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) { ret = btrfs_unlink_subvol(trans, old_dir, old_dentry); } else { + /* + * Now pin the log. We do it to ensure that no other task can + * sync the log while we are in progress with the rename, as + * that could result in an inconsistency in case any of the + * inodes that are part of this rename operation were logged + * before. + * + * We pin the log even if at this precise moment none of the + * inodes was logged before. This is because right after we + * checked for that, some other task fsyncing some other inode + * not involved with this rename operation could log that one of + * our inodes exists. + * + * We don't need to pin the logs before the above call to + * btrfs_insert_inode_ref(), since that does not need to change + * a log. + */ + btrfs_pin_log_trans(root); + log_pinned = true; ret = __btrfs_unlink_inode(trans, root, BTRFS_I(old_dir), BTRFS_I(d_inode(old_dentry)), old_dentry->d_name.name, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index f06824bea..ab8ed1877 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -798,6 +798,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, struct btrfs_trans_handle *trans; int ret; + if (btrfs_root_refs(&root->root_item) == 0) + return -ENOENT; + if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) return -EINVAL; @@ -3145,7 +3148,7 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp) { struct inode *inode = file_inode(file); struct btrfs_root *root = BTRFS_I(inode)->root; - struct btrfs_ioctl_defrag_range_args *range; + struct btrfs_ioctl_defrag_range_args range = {0}; int ret; ret = mnt_want_write_file(file); @@ -3177,33 +3180,28 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp) goto out; } - range = kzalloc(sizeof(*range), GFP_KERNEL); - if (!range) { - ret = -ENOMEM; - goto out; - } - if (argp) { - if (copy_from_user(range, argp, - sizeof(*range))) { + if (copy_from_user(&range, argp, sizeof(range))) { ret = -EFAULT; - kfree(range); + goto out; + } + if (range.flags & ~BTRFS_DEFRAG_RANGE_FLAGS_SUPP) { + ret = -EOPNOTSUPP; goto out; } /* compression requires us to start the IO */ - if ((range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)) { - range->flags |= BTRFS_DEFRAG_RANGE_START_IO; - range->extent_thresh = (u32)-1; + if ((range.flags & BTRFS_DEFRAG_RANGE_COMPRESS)) { + range.flags |= BTRFS_DEFRAG_RANGE_START_IO; + range.extent_thresh = (u32)-1; } } else { /* the rest are all set to zero by kzalloc */ - range->len = (u64)-1; + range.len = (u64)-1; } ret = btrfs_defrag_file(file_inode(file), file, - range, BTRFS_OLDEST_GENERATION, 0); + &range, BTRFS_OLDEST_GENERATION, 0); if (ret > 0) ret = 0; - kfree(range); break; default: ret = -EINVAL; @@ -4318,6 +4316,11 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg) goto out; } + if (sa->create && is_fstree(sa->qgroupid)) { + ret = -EINVAL; + goto out; + } + trans = btrfs_join_transaction(root); if (IS_ERR(trans)) { ret = PTR_ERR(trans); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index a67323c2d..50669ff93 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1608,6 +1608,15 @@ out: return ret; } +static bool qgroup_has_usage(struct btrfs_qgroup *qgroup) +{ + return (qgroup->rfer > 0 || qgroup->rfer_cmpr > 0 || + qgroup->excl > 0 || qgroup->excl_cmpr > 0 || + qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA] > 0 || + qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC] > 0 || + qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS] > 0); +} + int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) { struct btrfs_fs_info *fs_info = trans->fs_info; @@ -1627,6 +1636,11 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) goto out; } + if (is_fstree(qgroupid) && qgroup_has_usage(qgroup)) { + ret = -EBUSY; + goto out; + } + /* Check if there are no children of this qgroup */ if (!list_empty(&qgroup->members)) { ret = -EBUSY; @@ -4100,6 +4114,8 @@ void btrfs_qgroup_convert_reserved_meta(struct btrfs_root *root, int num_bytes) BTRFS_QGROUP_RSV_META_PREALLOC); trace_qgroup_meta_convert(root, num_bytes); qgroup_convert_meta(fs_info, root->root_key.objectid, num_bytes); + if (!sb_rdonly(fs_info->sb)) + add_root_meta_rsv(root, num_bytes, BTRFS_QGROUP_RSV_META_PERTRANS); } /* diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index bd3bb94cc..c3711598a 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -899,8 +899,10 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, out_unlock: spin_unlock(&fs_info->ref_verify_lock); out: - if (ret) + if (ret) { + btrfs_free_ref_cache(fs_info); btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY); + } return ret; } @@ -1029,8 +1031,8 @@ int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info) } } if (ret) { - btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY); btrfs_free_ref_cache(fs_info); + btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY); } btrfs_free_path(path); return ret; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index af9701afc..0519a3557 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -966,7 +966,15 @@ static int iterate_inode_ref(struct btrfs_root *root, struct btrfs_path *path, ret = PTR_ERR(start); goto out; } - BUG_ON(start < p->buf); + if (unlikely(start < p->buf)) { + btrfs_err(root->fs_info, + "send: path ref buffer underflow for key (%llu %u %llu)", + found_key->objectid, + found_key->type, + found_key->offset); + ret = -EINVAL; + goto out; + } } p->start = start; } else { @@ -7285,7 +7293,7 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) } if (arg->flags & ~BTRFS_SEND_FLAG_MASK) { - ret = -EINVAL; + ret = -EOPNOTSUPP; goto out; } diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 32f1b15b2..5b952f69b 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1189,7 +1189,8 @@ static void extent_err(const struct extent_buffer *eb, int slot, } static int check_extent_item(struct extent_buffer *leaf, - struct btrfs_key *key, int slot) + struct btrfs_key *key, int slot, + struct btrfs_key *prev_key) { struct btrfs_fs_info *fs_info = leaf->fs_info; struct btrfs_extent_item *ei; @@ -1334,7 +1335,7 @@ static int check_extent_item(struct extent_buffer *leaf, if (ptr + btrfs_extent_inline_ref_size(inline_type) > end) { extent_err(leaf, slot, "inline ref item overflows extent item, ptr %lu iref size %u end %lu", - ptr, inline_type, end); + ptr, btrfs_extent_inline_ref_size(inline_type), end); return -EUCLEAN; } @@ -1400,6 +1401,26 @@ static int check_extent_item(struct extent_buffer *leaf, total_refs, inline_refs); return -EUCLEAN; } + + if ((prev_key->type == BTRFS_EXTENT_ITEM_KEY) || + (prev_key->type == BTRFS_METADATA_ITEM_KEY)) { + u64 prev_end = prev_key->objectid; + + if (prev_key->type == BTRFS_METADATA_ITEM_KEY) + prev_end += fs_info->nodesize; + else + prev_end += prev_key->offset; + + if (unlikely(prev_end > key->objectid)) { + extent_err(leaf, slot, + "previous extent [%llu %u %llu] overlaps current extent [%llu %u %llu]", + prev_key->objectid, prev_key->type, + prev_key->offset, key->objectid, key->type, + key->offset); + return -EUCLEAN; + } + } + return 0; } @@ -1568,7 +1589,7 @@ static int check_leaf_item(struct extent_buffer *leaf, break; case BTRFS_EXTENT_ITEM_KEY: case BTRFS_METADATA_ITEM_KEY: - ret = check_extent_item(leaf, key, slot); + ret = check_extent_item(leaf, key, slot, prev_key); break; case BTRFS_TREE_BLOCK_REF_KEY: case BTRFS_SHARED_DATA_REF_KEY: diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 10a0913ff..34e9eb501 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -912,8 +912,7 @@ static noinline int inode_in_dir(struct btrfs_root *root, di = btrfs_lookup_dir_index_item(NULL, root, path, dirid, index, name, name_len, 0); if (IS_ERR(di)) { - if (PTR_ERR(di) != -ENOENT) - ret = PTR_ERR(di); + ret = PTR_ERR(di); goto out; } else if (di) { btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location); @@ -1149,8 +1148,7 @@ next: di = btrfs_lookup_dir_index_item(trans, root, path, btrfs_ino(dir), ref_index, name, namelen, 0); if (IS_ERR(di)) { - if (PTR_ERR(di) != -ENOENT) - return PTR_ERR(di); + return PTR_ERR(di); } else if (di) { ret = drop_one_dir_item(trans, root, path, dir, di); if (ret) @@ -1976,9 +1974,6 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, goto out; } - if (dst_di == ERR_PTR(-ENOENT)) - dst_di = NULL; - if (IS_ERR(dst_di)) { ret = PTR_ERR(dst_di); goto out; @@ -2286,7 +2281,7 @@ again: dir_key->offset, name, name_len, 0); } - if (!log_di || log_di == ERR_PTR(-ENOENT)) { + if (!log_di) { btrfs_dir_item_key_to_cpu(eb, di, &location); btrfs_release_path(path); btrfs_release_path(log_path); @@ -3495,8 +3490,7 @@ out_unlock: if (err == -ENOSPC) { btrfs_set_log_full_commit(trans); err = 0; - } else if (err < 0 && err != -ENOENT) { - /* ENOENT can be returned if the entry hasn't been fsynced yet */ + } else if (err < 0) { btrfs_abort_transaction(trans, err); } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index eaf5cd043..09c23626f 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1471,7 +1471,7 @@ static bool contains_pending_extent(struct btrfs_device *device, u64 *start, if (in_range(physical_start, *start, len) || in_range(*start, physical_start, - physical_end - physical_start)) { + physical_end + 1 - physical_start)) { *start = physical_end + 1; return true; } @@ -3178,7 +3178,17 @@ again: mutex_unlock(&fs_info->delete_unused_bgs_mutex); goto error; } - BUG_ON(ret == 0); /* Corruption */ + if (ret == 0) { + /* + * On the first search we would find chunk tree with + * offset -1, which is not possible. On subsequent + * loops this would find an existing item on an invalid + * offset (one less than the previous one, wrong + * alignment and size). + */ + ret = -EUCLEAN; + goto error; + } ret = btrfs_previous_item(chunk_root, path, key.objectid, key.type); diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c index dfb14dbdd..3b39552c2 100644 --- a/fs/cachefiles/bind.c +++ b/fs/cachefiles/bind.c @@ -245,6 +245,8 @@ error_open_root: kmem_cache_free(cachefiles_object_jar, fsdef); error_root_object: cachefiles_end_secure(cache, saved_cred); + put_cred(cache->cache_cred); + cache->cache_cred = NULL; pr_err("Failed to register: %d\n", ret); return ret; } @@ -265,6 +267,7 @@ void cachefiles_daemon_unbind(struct cachefiles_cache *cache) dput(cache->graveyard); mntput(cache->mnt); + put_cred(cache->cache_cred); kfree(cache->rootdirname); kfree(cache->secctx); diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 432dc2a16..8e43d07ff 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1402,7 +1402,7 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap, if (flushing & CEPH_CAP_XATTR_EXCL) { arg->old_xattr_buf = __ceph_build_xattrs_blob(ci); arg->xattr_version = ci->i_xattrs.version; - arg->xattr_buf = ci->i_xattrs.blob; + arg->xattr_buf = ceph_buffer_get(ci->i_xattrs.blob); } else { arg->xattr_buf = NULL; arg->old_xattr_buf = NULL; @@ -1468,6 +1468,7 @@ static void __send_cap(struct cap_msg_args *arg, struct ceph_inode_info *ci) encode_cap_msg(msg, arg); ceph_con_send(&arg->session->s_con, msg); ceph_buffer_put(arg->old_xattr_buf); + ceph_buffer_put(arg->xattr_buf); if (arg->wake) wake_up_all(&ci->i_cap_wq); } @@ -4598,12 +4599,14 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry, struct inode *dir, int mds, int drop, int unless) { - struct dentry *parent = NULL; struct ceph_mds_request_release *rel = *p; struct ceph_dentry_info *di = ceph_dentry(dentry); int force = 0; int ret; + /* This shouldn't happen */ + BUG_ON(!dir); + /* * force an record for the directory caps if we have a dentry lease. * this is racy (can't take i_ceph_lock and d_lock together), but it @@ -4613,14 +4616,9 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry, spin_lock(&dentry->d_lock); if (di->lease_session && di->lease_session->s_mds == mds) force = 1; - if (!dir) { - parent = dget(dentry->d_parent); - dir = d_inode(parent); - } spin_unlock(&dentry->d_lock); ret = ceph_encode_inode_release(p, dir, mds, drop, unless, force); - dput(parent); spin_lock(&dentry->d_lock); if (ret && di->lease_session && di->lease_session->s_mds == mds) { diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index b98bba887..660e00eb4 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -117,7 +117,7 @@ static __u32 get_neg_ctxt_len(struct smb2_sync_hdr *hdr, __u32 len, } else if (nc_offset + 1 == non_ctxlen) { cifs_dbg(FYI, "no SPNEGO security blob in negprot rsp\n"); size_of_pad_before_neg_ctxts = 0; - } else if (non_ctxlen == SMB311_NEGPROT_BASE_SIZE) + } else if (non_ctxlen == SMB311_NEGPROT_BASE_SIZE + 1) /* has padding, but no SPNEGO blob */ size_of_pad_before_neg_ctxts = nc_offset - non_ctxlen + 1; else diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 26edaeb42..b2a7238a3 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -82,6 +82,7 @@ smb2_add_credits(struct TCP_Server_Info *server, *val = 65000; /* Don't get near 64K credits, avoid srv bugs */ pr_warn_once("server overflowed SMB3 credits\n"); } + WARN_ON_ONCE(server->in_flight == 0); server->in_flight--; if (server->in_flight == 0 && (optype & CIFS_OP_MASK) != CIFS_NEG_OP) rc = change_conf(server); @@ -818,10 +819,12 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, if (o_rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) { kref_get(&tcon->crfid.refcount); tcon->crfid.has_lease = true; - smb2_parse_contexts(server, o_rsp, + rc = smb2_parse_contexts(server, rsp_iov, &oparms.fid->epoch, oparms.fid->lease_key, &oplock, NULL, NULL); + if (rc) + goto oshr_exit; } else goto oshr_exit; @@ -4892,6 +4895,7 @@ receive_encrypted_standard(struct TCP_Server_Info *server, struct smb2_sync_hdr *shdr; unsigned int pdu_length = server->pdu_size; unsigned int buf_size; + unsigned int next_cmd; struct mid_q_entry *mid_entry; int next_is_large; char *next_buffer = NULL; @@ -4920,14 +4924,15 @@ receive_encrypted_standard(struct TCP_Server_Info *server, next_is_large = server->large_buf; one_more: shdr = (struct smb2_sync_hdr *)buf; - if (shdr->NextCommand) { + next_cmd = le32_to_cpu(shdr->NextCommand); + if (next_cmd) { + if (WARN_ON_ONCE(next_cmd > pdu_length)) + return -1; if (next_is_large) next_buffer = (char *)cifs_buf_get(); else next_buffer = (char *)cifs_small_buf_get(); - memcpy(next_buffer, - buf + le32_to_cpu(shdr->NextCommand), - pdu_length - le32_to_cpu(shdr->NextCommand)); + memcpy(next_buffer, buf + next_cmd, pdu_length - next_cmd); } mid_entry = smb2_find_mid(server, buf); @@ -4951,8 +4956,8 @@ one_more: else ret = cifs_handle_standard(server, mid_entry); - if (ret == 0 && shdr->NextCommand) { - pdu_length -= le32_to_cpu(shdr->NextCommand); + if (ret == 0 && next_cmd) { + pdu_length -= next_cmd; server->large_buf = next_is_large; if (next_is_large) server->bigbuf = buf = next_buffer; @@ -5561,7 +5566,7 @@ struct smb_version_values smb20_values = { .header_size = sizeof(struct smb2_sync_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5583,7 +5588,7 @@ struct smb_version_values smb21_values = { .header_size = sizeof(struct smb2_sync_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5604,7 +5609,7 @@ struct smb_version_values smb3any_values = { .header_size = sizeof(struct smb2_sync_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5625,7 +5630,7 @@ struct smb_version_values smbdefault_values = { .header_size = sizeof(struct smb2_sync_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5646,7 +5651,7 @@ struct smb_version_values smb30_values = { .header_size = sizeof(struct smb2_sync_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5667,7 +5672,7 @@ struct smb_version_values smb302_values = { .header_size = sizeof(struct smb2_sync_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5688,7 +5693,7 @@ struct smb_version_values smb311_values = { .header_size = sizeof(struct smb2_sync_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 76679dc4e..aa3211d8c 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1261,7 +1261,7 @@ SMB2_sess_sendreceive(struct SMB2_sess_data *sess_data) /* Testing shows that buffer offset must be at location of Buffer[0] */ req->SecurityBufferOffset = - cpu_to_le16(sizeof(struct smb2_sess_setup_req) - 1 /* pad */); + cpu_to_le16(sizeof(struct smb2_sess_setup_req)); req->SecurityBufferLength = cpu_to_le16(sess_data->iov[1].iov_len); memset(&rqst, 0, sizeof(struct smb_rqst)); @@ -1760,8 +1760,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, iov[0].iov_len = total_len - 1; /* Testing shows that buffer offset must be at location of Buffer[0] */ - req->PathOffset = cpu_to_le16(sizeof(struct smb2_tree_connect_req) - - 1 /* pad */); + req->PathOffset = cpu_to_le16(sizeof(struct smb2_tree_connect_req)); req->PathLength = cpu_to_le16(unc_path_len - 2); iov[1].iov_base = unc_path; iov[1].iov_len = unc_path_len; @@ -1992,17 +1991,18 @@ parse_posix_ctxt(struct create_context *cc, struct smb2_file_all_info *info, posix->nlink, posix->mode, posix->reparse_tag); } -void -smb2_parse_contexts(struct TCP_Server_Info *server, - struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key, __u8 *oplock, - struct smb2_file_all_info *buf, - struct create_posix_rsp *posix) +int smb2_parse_contexts(struct TCP_Server_Info *server, + struct kvec *rsp_iov, + unsigned int *epoch, + char *lease_key, __u8 *oplock, + struct smb2_file_all_info *buf, + struct create_posix_rsp *posix) { - char *data_offset; + struct smb2_create_rsp *rsp = rsp_iov->iov_base; struct create_context *cc; - unsigned int next; - unsigned int remaining; + size_t rem, off, len; + size_t doff, dlen; + size_t noff, nlen; char *name; static const char smb3_create_tag_posix[] = { 0x93, 0xAD, 0x25, 0x50, 0x9C, @@ -2011,45 +2011,63 @@ smb2_parse_contexts(struct TCP_Server_Info *server, }; *oplock = 0; - data_offset = (char *)rsp + le32_to_cpu(rsp->CreateContextsOffset); - remaining = le32_to_cpu(rsp->CreateContextsLength); - cc = (struct create_context *)data_offset; + + off = le32_to_cpu(rsp->CreateContextsOffset); + rem = le32_to_cpu(rsp->CreateContextsLength); + if (check_add_overflow(off, rem, &len) || len > rsp_iov->iov_len) + return -EINVAL; + cc = (struct create_context *)((u8 *)rsp + off); /* Initialize inode number to 0 in case no valid data in qfid context */ if (buf) buf->IndexNumber = 0; - while (remaining >= sizeof(struct create_context)) { - name = le16_to_cpu(cc->NameOffset) + (char *)cc; - if (le16_to_cpu(cc->NameLength) == 4 && - strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4) == 0) - *oplock = server->ops->parse_lease_buf(cc, epoch, - lease_key); - else if (buf && (le16_to_cpu(cc->NameLength) == 4) && - strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4) == 0) - parse_query_id_ctxt(cc, buf); - else if ((le16_to_cpu(cc->NameLength) == 16)) { - if (posix && - memcmp(name, smb3_create_tag_posix, 16) == 0) + while (rem >= sizeof(*cc)) { + doff = le16_to_cpu(cc->DataOffset); + dlen = le32_to_cpu(cc->DataLength); + if (check_add_overflow(doff, dlen, &len) || len > rem) + return -EINVAL; + + noff = le16_to_cpu(cc->NameOffset); + nlen = le16_to_cpu(cc->NameLength); + if (noff + nlen > doff) + return -EINVAL; + + name = (char *)cc + noff; + switch (nlen) { + case 4: + if (!strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4)) { + *oplock = server->ops->parse_lease_buf(cc, epoch, + lease_key); + } else if (buf && + !strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4)) { + parse_query_id_ctxt(cc, buf); + } + break; + case 16: + if (posix && !memcmp(name, smb3_create_tag_posix, 16)) parse_posix_ctxt(cc, buf, posix); + break; + default: + cifs_dbg(FYI, "%s: unhandled context (nlen=%zu dlen=%zu)\n", + __func__, nlen, dlen); + if (IS_ENABLED(CONFIG_CIFS_DEBUG2)) + cifs_dump_mem("context data: ", cc, dlen); + break; } - /* else { - cifs_dbg(FYI, "Context not matched with len %d\n", - le16_to_cpu(cc->NameLength)); - cifs_dump_mem("Cctxt name: ", name, 4); - } */ - - next = le32_to_cpu(cc->Next); - if (!next) + + off = le32_to_cpu(cc->Next); + if (!off) break; - remaining -= next; - cc = (struct create_context *)((char *)cc + next); + if (check_sub_overflow(rem, off, &rem)) + return -EINVAL; + cc = (struct create_context *)((u8 *)cc + off); } if (rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) *oplock = rsp->OplockLevel; - return; + return 0; } static int @@ -2916,8 +2934,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, } - smb2_parse_contexts(server, rsp, &oparms->fid->epoch, - oparms->fid->lease_key, oplock, buf, posix); + rc = smb2_parse_contexts(server, &rsp_iov, &oparms->fid->epoch, + oparms->fid->lease_key, oplock, buf, posix); creat_exit: SMB2_open_free(&rqst); free_rsp_buf(resp_buftype, rsp); @@ -4676,7 +4694,7 @@ int SMB2_query_directory_init(const unsigned int xid, memcpy(bufptr, &asteriks, len); req->FileNameOffset = - cpu_to_le16(sizeof(struct smb2_query_directory_req) - 1); + cpu_to_le16(sizeof(struct smb2_query_directory_req)); req->FileNameLength = cpu_to_le16(len); /* * BB could be 30 bytes or so longer if we used SMB2 specific @@ -4873,7 +4891,7 @@ SMB2_set_info_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, req->AdditionalInformation = cpu_to_le32(additional_info); req->BufferOffset = - cpu_to_le16(sizeof(struct smb2_set_info_req) - 1); + cpu_to_le16(sizeof(struct smb2_set_info_req)); req->BufferLength = cpu_to_le32(*size); memcpy(req->Buffer, *data, *size); @@ -5105,9 +5123,9 @@ build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon, req->VolatileFileId = volatile_fid; /* 1 for pad */ req->InputBufferOffset = - cpu_to_le16(sizeof(struct smb2_query_info_req) - 1); + cpu_to_le16(sizeof(struct smb2_query_info_req)); req->OutputBufferLength = cpu_to_le32( - outbuf_len + sizeof(struct smb2_query_info_rsp) - 1); + outbuf_len + sizeof(struct smb2_query_info_rsp)); iov->iov_base = (char *)req; iov->iov_len = total_len; diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 89a732b31..eaa873175 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -220,7 +220,7 @@ struct smb2_err_rsp { __le16 StructureSize; __le16 Reserved; /* MBZ */ __le32 ByteCount; /* even if zero, at least one byte follows */ - __u8 ErrorData[1]; /* variable length */ + __u8 ErrorData[]; /* variable length */ } __packed; #define SYMLINK_ERROR_TAG 0x4c4d5953 @@ -464,7 +464,7 @@ struct smb2_negotiate_rsp { __le16 SecurityBufferOffset; __le16 SecurityBufferLength; __le32 NegotiateContextOffset; /* Pre:SMB3.1.1 was reserved/ignored */ - __u8 Buffer[1]; /* variable length GSS security buffer */ + __u8 Buffer[]; /* variable length GSS security buffer */ } __packed; /* Flags */ @@ -481,7 +481,7 @@ struct smb2_sess_setup_req { __le16 SecurityBufferOffset; __le16 SecurityBufferLength; __u64 PreviousSessionId; - __u8 Buffer[1]; /* variable length GSS security buffer */ + __u8 Buffer[]; /* variable length GSS security buffer */ } __packed; /* Currently defined SessionFlags */ @@ -494,7 +494,7 @@ struct smb2_sess_setup_rsp { __le16 SessionFlags; __le16 SecurityBufferOffset; __le16 SecurityBufferLength; - __u8 Buffer[1]; /* variable length GSS security buffer */ + __u8 Buffer[]; /* variable length GSS security buffer */ } __packed; struct smb2_logoff_req { @@ -520,7 +520,7 @@ struct smb2_tree_connect_req { __le16 Flags; /* Reserved MBZ for dialects prior to SMB3.1.1 */ __le16 PathOffset; __le16 PathLength; - __u8 Buffer[1]; /* variable length */ + __u8 Buffer[]; /* variable length */ } __packed; /* See MS-SMB2 section 2.2.9.2 */ @@ -828,7 +828,7 @@ struct smb2_create_rsp { __u64 VolatileFileId; /* opaque endianness */ __le32 CreateContextsOffset; __le32 CreateContextsLength; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; struct create_context { @@ -1289,7 +1289,7 @@ struct smb2_read_plain_req { __le32 RemainingBytes; __le16 ReadChannelInfoOffset; __le16 ReadChannelInfoLength; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; /* Read flags */ @@ -1304,7 +1304,7 @@ struct smb2_read_rsp { __le32 DataLength; __le32 DataRemaining; __u32 Flags; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; /* For write request Flags field below the following flags are defined: */ @@ -1324,7 +1324,7 @@ struct smb2_write_req { __le16 WriteChannelInfoOffset; __le16 WriteChannelInfoLength; __le32 Flags; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; struct smb2_write_rsp { @@ -1335,7 +1335,7 @@ struct smb2_write_rsp { __le32 DataLength; __le32 DataRemaining; __u32 Reserved2; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; /* notify flags */ @@ -1371,7 +1371,7 @@ struct smb2_change_notify_rsp { __le16 StructureSize; /* Must be 9 */ __le16 OutputBufferOffset; __le32 OutputBufferLength; - __u8 Buffer[1]; /* array of file notify structs */ + __u8 Buffer[]; /* array of file notify structs */ } __packed; #define SMB2_LOCKFLAG_SHARED_LOCK 0x0001 @@ -1394,7 +1394,10 @@ struct smb2_lock_req { __u64 PersistentFileId; /* opaque endianness */ __u64 VolatileFileId; /* opaque endianness */ /* Followed by at least one */ - struct smb2_lock_element locks[1]; + union { + struct smb2_lock_element lock; + DECLARE_FLEX_ARRAY(struct smb2_lock_element, locks); + }; } __packed; struct smb2_lock_rsp { @@ -1434,7 +1437,7 @@ struct smb2_query_directory_req { __le16 FileNameOffset; __le16 FileNameLength; __le32 OutputBufferLength; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; struct smb2_query_directory_rsp { @@ -1442,7 +1445,7 @@ struct smb2_query_directory_rsp { __le16 StructureSize; /* Must be 9 */ __le16 OutputBufferOffset; __le32 OutputBufferLength; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; /* Possible InfoType values */ @@ -1483,7 +1486,7 @@ struct smb2_query_info_req { __le32 Flags; __u64 PersistentFileId; /* opaque endianness */ __u64 VolatileFileId; /* opaque endianness */ - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; struct smb2_query_info_rsp { @@ -1491,7 +1494,7 @@ struct smb2_query_info_rsp { __le16 StructureSize; /* Must be 9 */ __le16 OutputBufferOffset; __le32 OutputBufferLength; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; /* @@ -1514,7 +1517,7 @@ struct smb2_set_info_req { __le32 AdditionalInformation; __u64 PersistentFileId; /* opaque endianness */ __u64 VolatileFileId; /* opaque endianness */ - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; struct smb2_set_info_rsp { @@ -1716,7 +1719,10 @@ struct smb2_file_all_info { /* data block encoding of response to level 18 */ __le32 Mode; __le32 AlignmentRequirement; __le32 FileNameLength; - char FileName[1]; + union { + char __pad; /* Legacy structure padding */ + DECLARE_FLEX_ARRAY(char, FileName); + }; } __packed; /* level 18 Query */ struct smb2_file_eof_info { /* encoding of request for level 10 */ diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index ed2b4fb01..3184a5efc 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -270,11 +270,13 @@ extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *); extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *, enum securityEnum); -extern void smb2_parse_contexts(struct TCP_Server_Info *server, - struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key, - __u8 *oplock, struct smb2_file_all_info *buf, - struct create_posix_rsp *posix); +int smb2_parse_contexts(struct TCP_Server_Info *server, + struct kvec *rsp_iov, + unsigned int *epoch, + char *lease_key, __u8 *oplock, + struct smb2_file_all_info *buf, + struct create_posix_rsp *posix); + extern int smb3_encryption_required(const struct cifs_tcon *tcon); extern int smb2_validate_iov(unsigned int offset, unsigned int buffer_length, struct kvec *iov, unsigned int min_buf_size); diff --git a/fs/dcache.c b/fs/dcache.c index ea0485861..976c7474d 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -759,12 +759,12 @@ static inline bool fast_dput(struct dentry *dentry) */ if (unlikely(ret < 0)) { spin_lock(&dentry->d_lock); - if (dentry->d_lockref.count > 1) { - dentry->d_lockref.count--; + if (WARN_ON_ONCE(dentry->d_lockref.count <= 0)) { spin_unlock(&dentry->d_lock); return true; } - return false; + dentry->d_lockref.count--; + goto locked; } /* @@ -815,6 +815,7 @@ static inline bool fast_dput(struct dentry *dentry) * else could have killed it and marked it dead. Either way, we * don't need to do anything else. */ +locked: if (dentry->d_lockref.count) { spin_unlock(&dentry->d_lock); return true; diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index e23752d9a..c867a0d62 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -76,6 +76,14 @@ static struct inode *__ecryptfs_get_inode(struct inode *lower_inode, if (lower_inode->i_sb != ecryptfs_superblock_to_lower(sb)) return ERR_PTR(-EXDEV); + + /* Reject dealing with casefold directories. */ + if (IS_CASEFOLDED(lower_inode)) { + pr_err_ratelimited("%s: Can't handle casefolded directory.\n", + __func__); + return ERR_PTR(-EREMOTE); + } + if (!igrab(lower_inode)) return ERR_PTR(-ESTALE); inode = iget5_locked(sb, (unsigned long)lower_inode, diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c index f921580b5..36693924d 100644 --- a/fs/erofs/decompressor.c +++ b/fs/erofs/decompressor.c @@ -24,7 +24,8 @@ struct z_erofs_decompressor { */ int (*prepare_destpages)(struct z_erofs_decompress_req *rq, struct list_head *pagepool); - int (*decompress)(struct z_erofs_decompress_req *rq, u8 *out); + int (*decompress)(struct z_erofs_decompress_req *rq, u8 *out, + u8 *obase); char *name; }; @@ -114,10 +115,13 @@ static void *generic_copy_inplace_data(struct z_erofs_decompress_req *rq, return tmp; } -static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out) +static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out, + u8 *obase) { + const uint nrpages_out = PAGE_ALIGN(rq->pageofs_out + + rq->outputsize) >> PAGE_SHIFT; unsigned int inputmargin, inlen; - u8 *src; + u8 *src, *src2; bool copied, support_0padding; int ret; @@ -125,6 +129,7 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out) return -EOPNOTSUPP; src = kmap_atomic(*rq->in); + src2 = src; inputmargin = 0; support_0padding = false; @@ -148,16 +153,15 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out) if (rq->inplace_io) { const uint oend = (rq->pageofs_out + rq->outputsize) & ~PAGE_MASK; - const uint nr = PAGE_ALIGN(rq->pageofs_out + - rq->outputsize) >> PAGE_SHIFT; - if (rq->partial_decoding || !support_0padding || - rq->out[nr - 1] != rq->in[0] || + rq->out[nrpages_out - 1] != rq->in[0] || rq->inputsize - oend < LZ4_DECOMPRESS_INPLACE_MARGIN(inlen)) { src = generic_copy_inplace_data(rq, src, inputmargin); inputmargin = 0; copied = true; + } else { + src = obase + ((nrpages_out - 1) << PAGE_SHIFT); } } @@ -187,7 +191,7 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out) if (copied) erofs_put_pcpubuf(src); else - kunmap_atomic(src); + kunmap_atomic(src2); return ret; } @@ -257,7 +261,7 @@ static int z_erofs_decompress_generic(struct z_erofs_decompress_req *rq, return PTR_ERR(dst); rq->inplace_io = false; - ret = alg->decompress(rq, dst); + ret = alg->decompress(rq, dst, NULL); if (!ret) copy_from_pcpubuf(rq->out, dst, rq->pageofs_out, rq->outputsize); @@ -291,7 +295,7 @@ static int z_erofs_decompress_generic(struct z_erofs_decompress_req *rq, dst_maptype = 2; dstmap_out: - ret = alg->decompress(rq, dst + rq->pageofs_out); + ret = alg->decompress(rq, dst + rq->pageofs_out, dst); if (!dst_maptype) kunmap_atomic(dst); @@ -888,6 +888,7 @@ int transfer_args_to_stack(struct linux_binprm *bprm, goto out; } + bprm->exec += *sp_location - MAX_ARG_PAGES * PAGE_SIZE; *sp_location = sp; out: @@ -1392,6 +1393,9 @@ int begin_new_exec(struct linux_binprm * bprm) out_unlock: up_write(&me->signal->exec_update_lock); + if (!bprm->cred) + mutex_unlock(&me->signal->cred_guard_mutex); + out: return retval; } diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 193b13630..9e1259272 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2222,7 +2222,7 @@ static int ext4_fill_es_cache_info(struct inode *inode, /* - * ext4_ext_determine_hole - determine hole around given block + * ext4_ext_find_hole - find hole around given block according to the given path * @inode: inode we lookup in * @path: path in extent tree to @lblk * @lblk: pointer to logical block around which we want to determine hole @@ -2234,9 +2234,9 @@ static int ext4_fill_es_cache_info(struct inode *inode, * The function returns the length of a hole starting at @lblk. We update @lblk * to the beginning of the hole if we managed to find it. */ -static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode, - struct ext4_ext_path *path, - ext4_lblk_t *lblk) +static ext4_lblk_t ext4_ext_find_hole(struct inode *inode, + struct ext4_ext_path *path, + ext4_lblk_t *lblk) { int depth = ext_depth(inode); struct ext4_extent *ex; @@ -2264,30 +2264,6 @@ static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode, } /* - * ext4_ext_put_gap_in_cache: - * calculate boundaries of the gap that the requested block fits into - * and cache this gap - */ -static void -ext4_ext_put_gap_in_cache(struct inode *inode, ext4_lblk_t hole_start, - ext4_lblk_t hole_len) -{ - struct extent_status es; - - ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start, - hole_start + hole_len - 1, &es); - if (es.es_len) { - /* There's delayed extent containing lblock? */ - if (es.es_lblk <= hole_start) - return; - hole_len = min(es.es_lblk - hole_start, hole_len); - } - ext_debug(inode, " -> %u:%u\n", hole_start, hole_len); - ext4_es_insert_extent(inode, hole_start, hole_len, ~0, - EXTENT_STATUS_HOLE); -} - -/* * ext4_ext_rm_idx: * removes index from the index block. */ @@ -3131,8 +3107,9 @@ static int ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex) if (ee_len == 0) return 0; - return ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock, - EXTENT_STATUS_WRITTEN); + ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock, + EXTENT_STATUS_WRITTEN); + return 0; } /* FIXME!! we need to try to merge to left or right after zero-out */ @@ -4058,6 +4035,69 @@ static int get_implied_cluster_alloc(struct super_block *sb, return 0; } +/* + * Determine hole length around the given logical block, first try to + * locate and expand the hole from the given @path, and then adjust it + * if it's partially or completely converted to delayed extents, insert + * it into the extent cache tree if it's indeed a hole, finally return + * the length of the determined extent. + */ +static ext4_lblk_t ext4_ext_determine_insert_hole(struct inode *inode, + struct ext4_ext_path *path, + ext4_lblk_t lblk) +{ + ext4_lblk_t hole_start, len; + struct extent_status es; + + hole_start = lblk; + len = ext4_ext_find_hole(inode, path, &hole_start); +again: + ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start, + hole_start + len - 1, &es); + if (!es.es_len) + goto insert_hole; + + /* + * There's a delalloc extent in the hole, handle it if the delalloc + * extent is in front of, behind and straddle the queried range. + */ + if (lblk >= es.es_lblk + es.es_len) { + /* + * The delalloc extent is in front of the queried range, + * find again from the queried start block. + */ + len -= lblk - hole_start; + hole_start = lblk; + goto again; + } else if (in_range(lblk, es.es_lblk, es.es_len)) { + /* + * The delalloc extent containing lblk, it must have been + * added after ext4_map_blocks() checked the extent status + * tree, adjust the length to the delalloc extent's after + * lblk. + */ + len = es.es_lblk + es.es_len - lblk; + return len; + } else { + /* + * The delalloc extent is partially or completely behind + * the queried range, update hole length until the + * beginning of the delalloc extent. + */ + len = min(es.es_lblk - hole_start, len); + } + +insert_hole: + /* Put just found gap into cache to speed up subsequent requests */ + ext_debug(inode, " -> %u:%u\n", hole_start, len); + ext4_es_insert_extent(inode, hole_start, len, ~0, EXTENT_STATUS_HOLE); + + /* Update hole_len to reflect hole size after lblk */ + if (hole_start != lblk) + len -= lblk - hole_start; + + return len; +} /* * Block allocation/map/preallocation routine for extents based files @@ -4175,22 +4215,12 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, * we couldn't try to create block if create flag is zero */ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { - ext4_lblk_t hole_start, hole_len; + ext4_lblk_t len; - hole_start = map->m_lblk; - hole_len = ext4_ext_determine_hole(inode, path, &hole_start); - /* - * put just found gap into cache to speed up - * subsequent requests - */ - ext4_ext_put_gap_in_cache(inode, hole_start, hole_len); + len = ext4_ext_determine_insert_hole(inode, path, map->m_lblk); - /* Update hole_len to reflect hole size after map->m_lblk */ - if (hole_start != map->m_lblk) - hole_len -= map->m_lblk - hole_start; map->m_pblk = 0; - map->m_len = min_t(unsigned int, map->m_len, hole_len); - + map->m_len = min_t(unsigned int, map->m_len, len); goto out; } diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index cccbdfd49..f37e62546 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -846,12 +846,10 @@ out: /* * ext4_es_insert_extent() adds information to an inode's extent * status tree. - * - * Return 0 on success, error code on failure. */ -int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, - ext4_lblk_t len, ext4_fsblk_t pblk, - unsigned int status) +void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len, ext4_fsblk_t pblk, + unsigned int status) { struct extent_status newes; ext4_lblk_t end = lblk + len - 1; @@ -863,13 +861,13 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, bool revise_pending = false; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) - return 0; + return; es_debug("add [%u/%u) %llu %x to extent status tree of inode %lu\n", lblk, len, pblk, status, inode->i_ino); if (!len) - return 0; + return; BUG_ON(end < lblk); @@ -938,7 +936,7 @@ error: goto retry; ext4_es_print_tree(inode); - return 0; + return; } /* diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h index 4ec30a798..481ec4381 100644 --- a/fs/ext4/extents_status.h +++ b/fs/ext4/extents_status.h @@ -127,9 +127,9 @@ extern int __init ext4_init_es(void); extern void ext4_exit_es(void); extern void ext4_es_init_tree(struct ext4_es_tree *tree); -extern int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, - ext4_lblk_t len, ext4_fsblk_t pblk, - unsigned int status); +extern void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len, ext4_fsblk_t pblk, + unsigned int status); extern void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk, unsigned int status); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 365c4d3a4..8b48ed351 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -589,10 +589,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, ext4_es_scan_range(inode, &ext4_es_is_delayed, map->m_lblk, map->m_lblk + map->m_len - 1)) status |= EXTENT_STATUS_DELAYED; - ret = ext4_es_insert_extent(inode, map->m_lblk, - map->m_len, map->m_pblk, status); - if (ret < 0) - retval = ret; + ext4_es_insert_extent(inode, map->m_lblk, map->m_len, + map->m_pblk, status); } up_read((&EXT4_I(inode)->i_data_sem)); @@ -701,12 +699,8 @@ found: ext4_es_scan_range(inode, &ext4_es_is_delayed, map->m_lblk, map->m_lblk + map->m_len - 1)) status |= EXTENT_STATUS_DELAYED; - ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len, - map->m_pblk, status); - if (ret < 0) { - retval = ret; - goto out_sem; - } + ext4_es_insert_extent(inode, map->m_lblk, map->m_len, + map->m_pblk, status); } out_sem: @@ -1734,11 +1728,8 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, /* Lookup extent status tree firstly */ if (ext4_es_lookup_extent(inode, iblock, NULL, &es)) { - if (ext4_es_is_hole(&es)) { - retval = 0; - down_read(&EXT4_I(inode)->i_data_sem); + if (ext4_es_is_hole(&es)) goto add_delayed; - } /* * Delayed extent could be allocated by fallocate. @@ -1780,27 +1771,11 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, retval = ext4_ext_map_blocks(NULL, inode, map, 0); else retval = ext4_ind_map_blocks(NULL, inode, map, 0); - -add_delayed: - if (retval == 0) { - int ret; - - /* - * XXX: __block_prepare_write() unmaps passed block, - * is it OK? - */ - - ret = ext4_insert_delayed_block(inode, map->m_lblk); - if (ret != 0) { - retval = ret; - goto out_unlock; - } - - map_bh(bh, inode->i_sb, invalid_block); - set_buffer_new(bh); - set_buffer_delay(bh); - } else if (retval > 0) { - int ret; + if (retval < 0) { + up_read(&EXT4_I(inode)->i_data_sem); + return retval; + } + if (retval > 0) { unsigned int status; if (unlikely(retval != map->m_len)) { @@ -1813,15 +1788,23 @@ add_delayed: status = map->m_flags & EXT4_MAP_UNWRITTEN ? EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; - ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len, - map->m_pblk, status); - if (ret != 0) - retval = ret; + ext4_es_insert_extent(inode, map->m_lblk, map->m_len, + map->m_pblk, status); + up_read(&EXT4_I(inode)->i_data_sem); + return retval; } + up_read(&EXT4_I(inode)->i_data_sem); -out_unlock: - up_read((&EXT4_I(inode)->i_data_sem)); +add_delayed: + down_write(&EXT4_I(inode)->i_data_sem); + retval = ext4_insert_delayed_block(inode, map->m_lblk); + up_write(&EXT4_I(inode)->i_data_sem); + if (retval) + return retval; + map_bh(bh, inode->i_sb, invalid_block); + set_buffer_new(bh); + set_buffer_delay(bh); return retval; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 3babc07ae..c1d632725 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -823,6 +823,24 @@ void ext4_mb_generate_buddy(struct super_block *sb, atomic64_add(period, &sbi->s_mb_generation_time); } +static void mb_regenerate_buddy(struct ext4_buddy *e4b) +{ + int count; + int order = 1; + void *buddy; + + while ((buddy = mb_find_buddy(e4b, order++, &count))) + ext4_set_bits(buddy, 0, count); + + e4b->bd_info->bb_fragments = 0; + memset(e4b->bd_info->bb_counters, 0, + sizeof(*e4b->bd_info->bb_counters) * + (e4b->bd_sb->s_blocksize_bits + 2)); + + ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy, + e4b->bd_bitmap, e4b->bd_group, e4b->bd_info); +} + /* The buddy information is attached the buddy cache inode * for convenience. The information regarding each group * is loaded via ext4_mb_load_buddy. The information involve @@ -1476,11 +1494,6 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, mb_check_buddy(e4b); mb_free_blocks_double(inode, e4b, first, count); - this_cpu_inc(discard_pa_seq); - e4b->bd_info->bb_free += count; - if (first < e4b->bd_info->bb_first_free) - e4b->bd_info->bb_first_free = first; - /* access memory sequentially: check left neighbour, * clear range and then check right neighbour */ @@ -1494,21 +1507,31 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t blocknr; + /* + * Fastcommit replay can free already freed blocks which + * corrupts allocation info. Regenerate it. + */ + if (sbi->s_mount_state & EXT4_FC_REPLAY) { + mb_regenerate_buddy(e4b); + goto check; + } + blocknr = ext4_group_first_block_no(sb, e4b->bd_group); blocknr += EXT4_C2B(sbi, block); - if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) { - ext4_grp_locked_error(sb, e4b->bd_group, - inode ? inode->i_ino : 0, - blocknr, - "freeing already freed block (bit %u); block bitmap corrupt.", - block); - ext4_mark_group_bitmap_corrupted( - sb, e4b->bd_group, + ext4_grp_locked_error(sb, e4b->bd_group, + inode ? inode->i_ino : 0, blocknr, + "freeing already freed block (bit %u); block bitmap corrupt.", + block); + ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); - } - goto done; + return; } + this_cpu_inc(discard_pa_seq); + e4b->bd_info->bb_free += count; + if (first < e4b->bd_info->bb_first_free) + e4b->bd_info->bb_first_free = first; + /* let's maintain fragments counter */ if (left_is_free && right_is_free) e4b->bd_info->bb_fragments--; @@ -1533,8 +1556,8 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, if (first <= last) mb_buddy_mark_free(e4b, first >> 1, last >> 1); -done: mb_set_largest_free_order(sb, e4b->bd_info); +check: mb_check_buddy(e4b); } @@ -1854,6 +1877,9 @@ int ext4_mb_try_best_found(struct ext4_allocation_context *ac, return err; ext4_lock_group(ac->ac_sb, group); + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) + goto out; + max = mb_find_extent(e4b, ex.fe_start, ex.fe_len, &ex); if (max > 0) { @@ -1861,6 +1887,7 @@ int ext4_mb_try_best_found(struct ext4_allocation_context *ac, ext4_mb_use_best_found(ac, e4b); } +out: ext4_unlock_group(ac->ac_sb, group); ext4_mb_unload_buddy(e4b); @@ -1889,12 +1916,10 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, if (err) return err; - if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) { - ext4_mb_unload_buddy(e4b); - return 0; - } - ext4_lock_group(ac->ac_sb, group); + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) + goto out; + max = mb_find_extent(e4b, ac->ac_g_ex.fe_start, ac->ac_g_ex.fe_len, &ex); ex.fe_logical = 0xDEADFA11; /* debug value */ @@ -1927,6 +1952,7 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } +out: ext4_unlock_group(ac->ac_sb, group); ext4_mb_unload_buddy(e4b); @@ -2565,7 +2591,10 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) for (i = 0; i <= 13; i++) seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ? sg.info.bb_counters[i] : 0); - seq_puts(seq, " ]\n"); + seq_puts(seq, " ]"); + if (EXT4_MB_GRP_BBITMAP_CORRUPT(&sg.info)) + seq_puts(seq, " Block bitmap corrupted!"); + seq_puts(seq, "\n"); return 0; } @@ -4136,10 +4165,16 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) .fe_len = ac->ac_g_ex.fe_len, }; loff_t orig_goal_end = extent_logical_end(sbi, &ex); + loff_t o_ex_end = extent_logical_end(sbi, &ac->ac_o_ex); - /* we can't allocate as much as normalizer wants. - * so, found space must get proper lstart - * to cover original request */ + /* + * We can't allocate as much as normalizer wants, so we try + * to get proper lstart to cover the original request, except + * when the goal doesn't cover the original request as below: + * + * orig_ex:2045/2055(10), isize:8417280 -> normalized:0/2048 + * best_ex:0/200(200) -> adjusted: 1848/2048(200) + */ BUG_ON(ac->ac_g_ex.fe_logical > ac->ac_o_ex.fe_logical); BUG_ON(ac->ac_g_ex.fe_len < ac->ac_o_ex.fe_len); @@ -4151,7 +4186,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) * 1. Check if best ex can be kept at end of goal and still * cover original start * 2. Else, check if best ex can be kept at start of goal and - * still cover original start + * still cover original end * 3. Else, keep the best ex at start of original request. */ ex.fe_len = ac->ac_b_ex.fe_len; @@ -4161,7 +4196,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) goto adjust_bex; ex.fe_logical = ac->ac_g_ex.fe_logical; - if (ac->ac_o_ex.fe_logical < extent_logical_end(sbi, &ex)) + if (o_ex_end <= extent_logical_end(sbi, &ex)) goto adjust_bex; ex.fe_logical = ac->ac_o_ex.fe_logical; @@ -4169,7 +4204,6 @@ adjust_bex: ac->ac_b_ex.fe_logical = ex.fe_logical; BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical); - BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len); BUG_ON(extent_logical_end(sbi, &ex) > orig_goal_end); } @@ -5895,11 +5929,16 @@ __acquires(bitlock) static ext4_grpblk_t ext4_last_grp_cluster(struct super_block *sb, ext4_group_t grp) { - if (grp < ext4_get_groups_count(sb)) - return EXT4_CLUSTERS_PER_GROUP(sb) - 1; - return (ext4_blocks_count(EXT4_SB(sb)->s_es) - - ext4_group_first_block_no(sb, grp) - 1) >> - EXT4_CLUSTER_BITS(sb); + unsigned long nr_clusters_in_group; + + if (grp < (ext4_get_groups_count(sb) - 1)) + nr_clusters_in_group = EXT4_CLUSTERS_PER_GROUP(sb); + else + nr_clusters_in_group = (ext4_blocks_count(EXT4_SB(sb)->s_es) - + ext4_group_first_block_no(sb, grp)) + >> EXT4_CLUSTER_BITS(sb); + + return nr_clusters_in_group - 1; } static bool ext4_trim_interrupted(void) @@ -5911,13 +5950,15 @@ static int ext4_try_to_trim_range(struct super_block *sb, struct ext4_buddy *e4b, ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks) { - ext4_grpblk_t next, count, free_count; + ext4_grpblk_t next, count, free_count, last, origin_start; bool set_trimmed = false; void *bitmap; + last = ext4_last_grp_cluster(sb, e4b->bd_group); bitmap = e4b->bd_bitmap; - if (start == 0 && max >= ext4_last_grp_cluster(sb, e4b->bd_group)) + if (start == 0 && max >= last) set_trimmed = true; + origin_start = start; start = max(e4b->bd_info->bb_first_free, start); count = 0; free_count = 0; @@ -5926,7 +5967,10 @@ static int ext4_try_to_trim_range(struct super_block *sb, start = mb_find_next_zero_bit(bitmap, max + 1, start); if (start > max) break; - next = mb_find_next_bit(bitmap, max + 1, start); + + next = mb_find_next_bit(bitmap, last + 1, start); + if (origin_start == 0 && next >= last) + set_trimmed = true; if ((next - start) >= minblocks) { int ret = ext4_trim_extent(sb, start, next - start, e4b); diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 64a579734..f8dd5d972 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -615,6 +615,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, goto out; o_end = o_start + len; + *moved_len = 0; while (o_start < o_end) { struct ext4_extent *ex; ext4_lblk_t cur_blk, next_blk; @@ -670,7 +671,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, */ ext4_double_up_write_data_sem(orig_inode, donor_inode); /* Swap original branches with new branches */ - move_extent_per_page(o_filp, donor_inode, + *moved_len += move_extent_per_page(o_filp, donor_inode, orig_page_index, donor_page_index, offset_in_page, cur_len, unwritten, &ret); @@ -680,9 +681,6 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, o_start += cur_len; d_start += cur_len; } - *moved_len = o_start - orig_blk; - if (*moved_len > len) - *moved_len = len; out: if (*moved_len) { diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 9b4199a1e..5d45ec29e 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -227,17 +227,24 @@ struct ext4_new_flex_group_data { in the flex group */ __u16 *bg_flags; /* block group flags of groups in @groups */ + ext4_group_t resize_bg; /* number of allocated + new_group_data */ ext4_group_t count; /* number of groups in @groups */ }; /* + * Avoiding memory allocation failures due to too many groups added each time. + */ +#define MAX_RESIZE_BG 16384 + +/* * alloc_flex_gd() allocates a ext4_new_flex_group_data with size of * @flexbg_size. * * Returns NULL on failure otherwise address of the allocated structure. */ -static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size) +static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned int flexbg_size) { struct ext4_new_flex_group_data *flex_gd; @@ -245,17 +252,18 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size) if (flex_gd == NULL) goto out3; - if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data)) - goto out2; - flex_gd->count = flexbg_size; + if (unlikely(flexbg_size > MAX_RESIZE_BG)) + flex_gd->resize_bg = MAX_RESIZE_BG; + else + flex_gd->resize_bg = flexbg_size; - flex_gd->groups = kmalloc_array(flexbg_size, + flex_gd->groups = kmalloc_array(flex_gd->resize_bg, sizeof(struct ext4_new_group_data), GFP_NOFS); if (flex_gd->groups == NULL) goto out2; - flex_gd->bg_flags = kmalloc_array(flexbg_size, sizeof(__u16), + flex_gd->bg_flags = kmalloc_array(flex_gd->resize_bg, sizeof(__u16), GFP_NOFS); if (flex_gd->bg_flags == NULL) goto out1; @@ -292,7 +300,7 @@ static void free_flex_gd(struct ext4_new_flex_group_data *flex_gd) */ static int ext4_alloc_group_tables(struct super_block *sb, struct ext4_new_flex_group_data *flex_gd, - int flexbg_size) + unsigned int flexbg_size) { struct ext4_new_group_data *group_data = flex_gd->groups; ext4_fsblk_t start_blk; @@ -393,12 +401,12 @@ next_group: group = group_data[0].group; printk(KERN_DEBUG "EXT4-fs: adding a flex group with " - "%d groups, flexbg size is %d:\n", flex_gd->count, + "%u groups, flexbg size is %u:\n", flex_gd->count, flexbg_size); for (i = 0; i < flex_gd->count; i++) { ext4_debug( - "adding %s group %u: %u blocks (%d free, %d mdata blocks)\n", + "adding %s group %u: %u blocks (%u free, %u mdata blocks)\n", ext4_bg_has_super(sb, group + i) ? "normal" : "no-super", group + i, group_data[i].blocks_count, @@ -1537,7 +1545,8 @@ exit_journal: int gdb_num = group / EXT4_DESC_PER_BLOCK(sb); int gdb_num_end = ((group + flex_gd->count - 1) / EXT4_DESC_PER_BLOCK(sb)); - int meta_bg = ext4_has_feature_meta_bg(sb); + int meta_bg = ext4_has_feature_meta_bg(sb) && + gdb_num >= le32_to_cpu(es->s_first_meta_bg); sector_t padding_blocks = meta_bg ? 0 : sbi->s_sbh->b_blocknr - ext4_group_first_block_no(sb, 0); sector_t old_gdb = 0; @@ -1562,8 +1571,7 @@ exit: static int ext4_setup_next_flex_gd(struct super_block *sb, struct ext4_new_flex_group_data *flex_gd, - ext4_fsblk_t n_blocks_count, - unsigned long flexbg_size) + ext4_fsblk_t n_blocks_count) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; @@ -1587,7 +1595,7 @@ static int ext4_setup_next_flex_gd(struct super_block *sb, BUG_ON(last); ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &last); - last_group = group | (flexbg_size - 1); + last_group = group | (flex_gd->resize_bg - 1); if (last_group > n_group) last_group = n_group; @@ -1941,8 +1949,9 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count) ext4_fsblk_t o_blocks_count; ext4_fsblk_t n_blocks_count_retry = 0; unsigned long last_update_time = 0; - int err = 0, flexbg_size = 1 << sbi->s_log_groups_per_flex; + int err = 0; int meta_bg; + unsigned int flexbg_size = ext4_flex_bg_size(sbi); /* See if the device is actually as big as what was requested */ bh = ext4_sb_bread(sb, n_blocks_count - 1, 0); @@ -2083,8 +2092,7 @@ retry: /* Add flex groups. Note that a regular group is a * flex group with 1 group. */ - while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count, - flexbg_size)) { + while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count)) { if (jiffies - last_update_time > HZ * 10) { if (last_update_time) ext4_msg(sb, KERN_INFO, diff --git a/fs/ext4/super.c b/fs/ext4/super.c index e386d67cf..0149d3c2c 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -6205,6 +6205,10 @@ static int ext4_write_dquot(struct dquot *dquot) if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_commit(dquot); + if (ret < 0) + ext4_error_err(dquot->dq_sb, -ret, + "Failed to commit dquot type %d", + dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; @@ -6221,6 +6225,10 @@ static int ext4_acquire_dquot(struct dquot *dquot) if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_acquire(dquot); + if (ret < 0) + ext4_error_err(dquot->dq_sb, -ret, + "Failed to acquire dquot type %d", + dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; @@ -6240,6 +6248,10 @@ static int ext4_release_dquot(struct dquot *dquot) return PTR_ERR(handle); } ret = dquot_release(dquot); + if (ret < 0) + ext4_error_err(dquot->dq_sb, -ret, + "Failed to release dquot type %d", + dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 55818bd51..40e805014 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -3663,7 +3663,13 @@ static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count) goto next; } - if (__is_valid_data_blkaddr(blkaddr)) { + /* + * compressed cluster was not released due to it + * fails in release_compress_blocks(), so NEW_ADDR + * is a possible case. + */ + if (blkaddr == NEW_ADDR || + __is_valid_data_blkaddr(blkaddr)) { compr_blocks++; continue; } @@ -3673,6 +3679,11 @@ static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count) } reserved = cluster_size - compr_blocks; + + /* for the case all blocks in cluster were reserved */ + if (reserved == 1) + goto next; + ret = inc_valid_block_count(sbi, dn->inode, &reserved); if (ret) return ret; diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index c3c527afd..cd56af93d 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -641,7 +641,16 @@ retry_dn: */ if (dest == NEW_ADDR) { f2fs_truncate_data_blocks_range(&dn, 1); - f2fs_reserve_new_block(&dn); + do { + err = f2fs_reserve_new_block(&dn); + if (err == -ENOSPC) { + f2fs_bug_on(sbi, 1); + break; + } + } while (err && + IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)); + if (err) + goto err; continue; } @@ -649,12 +658,14 @@ retry_dn: if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) { if (src == NULL_ADDR) { - err = f2fs_reserve_new_block(&dn); - while (err && - IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)) + do { err = f2fs_reserve_new_block(&dn); - /* We should not get -ENOSPC */ - f2fs_bug_on(sbi, err); + if (err == -ENOSPC) { + f2fs_bug_on(sbi, 1); + break; + } + } while (err && + IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)); if (err) goto err; } @@ -844,6 +855,8 @@ skip: if (!err && fix_curseg_write_pointer && !f2fs_readonly(sbi->sb) && f2fs_sb_has_blkzoned(sbi)) { err = f2fs_fix_curseg_write_pointer(sbi); + if (!err) + err = f2fs_check_write_pointer(sbi); ret = err; } diff --git a/fs/fat/nfs.c b/fs/fat/nfs.c index af191371c..bab63eeaf 100644 --- a/fs/fat/nfs.c +++ b/fs/fat/nfs.c @@ -130,6 +130,12 @@ fat_encode_fh_nostale(struct inode *inode, __u32 *fh, int *lenp, fid->parent_i_gen = parent->i_generation; type = FILEID_FAT_WITH_PARENT; *lenp = FAT_FID_SIZE_WITH_PARENT; + } else { + /* + * We need to initialize this field because the fh is actually + * 12 bytes long + */ + fid->parent_i_pos_hi = 0; } return type; diff --git a/fs/fhandle.c b/fs/fhandle.c index 01263ffbc..9a5f153c8 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -37,7 +37,7 @@ static long do_sys_name_to_handle(struct path *path, if (f_handle.handle_bytes > MAX_HANDLE_SZ) return -EINVAL; - handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes, + handle = kzalloc(sizeof(struct file_handle) + f_handle.handle_bytes, GFP_KERNEL); if (!handle) return -ENOMEM; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index b0c701c00..d131f34cd 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -451,6 +451,10 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name goto out_put_forget; if (fuse_invalid_attr(&outarg->attr)) goto out_put_forget; + if (outarg->nodeid == FUSE_ROOT_ID && outarg->generation != 0) { + pr_warn_once("root generation should be zero\n"); + outarg->generation = 0; + } *inode = fuse_iget(sb, outarg->nodeid, outarg->generation, &outarg->attr, entry_attr_timeout(outarg), diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index ceaa68683..33eb5fefc 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -873,7 +873,6 @@ static inline bool fuse_stale_inode(const struct inode *inode, int generation, static inline void fuse_make_bad(struct inode *inode) { - remove_inode_hash(inode); set_bit(FUSE_I_BAD, &get_fuse_inode(inode)->state); } diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 9ea175ff9..4a7ebccd3 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -352,8 +352,11 @@ retry: } else if (fuse_stale_inode(inode, generation, attr)) { /* nodeid was reused, any I/O on the old inode should fail */ fuse_make_bad(inode); - iput(inode); - goto retry; + if (inode != d_inode(sb->s_root)) { + remove_inode_hash(inode); + iput(inode); + goto retry; + } } done: fi = get_fuse_inode(inode); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 5181e6d4e..bf3cda498 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -135,6 +135,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) loff_t len, vma_len; int ret; struct hstate *h = hstate_file(file); + vm_flags_t vm_flags; /* * vma address alignment (but not the pgoff alignment) has @@ -176,10 +177,20 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) file_accessed(file); ret = -ENOMEM; - if (hugetlb_reserve_pages(inode, + + vm_flags = vma->vm_flags; + /* + * for SHM_HUGETLB, the pages are reserved in the shmget() call so skip + * reserving here. Note: only for SHM hugetlbfs file, the inode + * flag S_PRIVATE is set. + */ + if (inode->i_flags & S_PRIVATE) + vm_flags |= VM_NORESERVE; + + if (!hugetlb_reserve_pages(inode, vma->vm_pgoff >> huge_page_order(h), len >> huge_page_shift(h), vma, - vma->vm_flags)) + vm_flags)) goto out; ret = 0; @@ -1234,6 +1245,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par { struct hugetlbfs_fs_context *ctx = fc->fs_private; struct fs_parse_result result; + struct hstate *h; char *rest; unsigned long ps; int opt; @@ -1278,11 +1290,12 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par case Opt_pagesize: ps = memparse(param->string, &rest); - ctx->hstate = size_to_hstate(ps); - if (!ctx->hstate) { + h = size_to_hstate(ps); + if (!h) { pr_err("Unsupported page size %lu MB\n", ps >> 20); return -EINVAL; } + ctx->hstate = h; return 0; case Opt_min_size: @@ -1498,7 +1511,7 @@ struct file *hugetlb_file_setup(const char *name, size_t size, inode->i_size = size; clear_nlink(inode); - if (hugetlb_reserve_pages(inode, 0, + if (!hugetlb_reserve_pages(inode, 0, size >> huge_page_shift(hstate_inode(inode)), NULL, acctflag)) file = ERR_PTR(-ENOMEM); diff --git a/fs/ioctl.c b/fs/ioctl.c index 7bcc60091..b2d06f016 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -799,8 +799,7 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, if (!f.file) return -EBADF; - /* RED-PEN how should LSM module know it's handling 32bit? */ - error = security_file_ioctl(f.file, cmd, arg); + error = security_file_ioctl_compat(f.file, cmd, arg); if (error) goto out; diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index f62b5a501..4c763f573 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -907,8 +907,22 @@ root_found: * we then decide whether to use the Joliet descriptor. */ inode = isofs_iget(s, sbi->s_firstdatazone, 0); - if (IS_ERR(inode)) - goto out_no_root; + + /* + * Fix for broken CDs with a corrupt root inode but a correct Joliet + * root directory. + */ + if (IS_ERR(inode)) { + if (joliet_level && sbi->s_firstdatazone != first_data_zone) { + printk(KERN_NOTICE + "ISOFS: root inode is unusable. " + "Disabling Rock Ridge and switching to Joliet."); + sbi->s_rock = 0; + inode = NULL; + } else { + goto out_no_root; + } + } /* * Fix for broken CDs with Rock Ridge and empty ISO root directory but diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 472932b9e..7898983c9 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -58,28 +58,6 @@ static inline void __buffer_unlink(struct journal_head *jh) } /* - * Move a buffer from the checkpoint list to the checkpoint io list - * - * Called with j_list_lock held - */ -static inline void __buffer_relink_io(struct journal_head *jh) -{ - transaction_t *transaction = jh->b_cp_transaction; - - __buffer_unlink_first(jh); - - if (!transaction->t_checkpoint_io_list) { - jh->b_cpnext = jh->b_cpprev = jh; - } else { - jh->b_cpnext = transaction->t_checkpoint_io_list; - jh->b_cpprev = transaction->t_checkpoint_io_list->b_cpprev; - jh->b_cpprev->b_cpnext = jh; - jh->b_cpnext->b_cpprev = jh; - } - transaction->t_checkpoint_io_list = jh; -} - -/* * Try to release a checkpointed buffer from its transaction. * Returns 1 if we released it and 2 if we also released the * whole transaction. @@ -91,8 +69,7 @@ static int __try_to_free_cp_buf(struct journal_head *jh) int ret = 0; struct buffer_head *bh = jh2bh(jh); - if (jh->b_transaction == NULL && !buffer_locked(bh) && - !buffer_dirty(bh) && !buffer_write_io_error(bh)) { + if (!jh->b_transaction && !buffer_locked(bh) && !buffer_dirty(bh)) { JBUFFER_TRACE(jh, "remove from checkpoint list"); ret = __jbd2_journal_remove_checkpoint(jh) + 1; } @@ -191,6 +168,7 @@ __flush_batch(journal_t *journal, int *batch_count) struct buffer_head *bh = journal->j_chkpt_bhs[i]; BUFFER_TRACE(bh, "brelse"); __brelse(bh); + journal->j_chkpt_bhs[i] = NULL; } *batch_count = 0; } @@ -228,7 +206,6 @@ int jbd2_log_do_checkpoint(journal_t *journal) * OK, we need to start writing disk blocks. Take one transaction * and write it. */ - result = 0; spin_lock(&journal->j_list_lock); if (!journal->j_checkpoint_transactions) goto out; @@ -251,15 +228,6 @@ restart: jh = transaction->t_checkpoint_list; bh = jh2bh(jh); - if (buffer_locked(bh)) { - get_bh(bh); - spin_unlock(&journal->j_list_lock); - wait_on_buffer(bh); - /* the journal_head may have gone by now */ - BUFFER_TRACE(bh, "brelse"); - __brelse(bh); - goto retry; - } if (jh->b_transaction != NULL) { transaction_t *t = jh->b_transaction; tid_t tid = t->t_tid; @@ -294,32 +262,50 @@ restart: spin_lock(&journal->j_list_lock); goto restart; } - if (!buffer_dirty(bh)) { - if (unlikely(buffer_write_io_error(bh)) && !result) - result = -EIO; + if (!trylock_buffer(bh)) { + /* + * The buffer is locked, it may be writing back, or + * flushing out in the last couple of cycles, or + * re-adding into a new transaction, need to check + * it again until it's unlocked. + */ + get_bh(bh); + spin_unlock(&journal->j_list_lock); + wait_on_buffer(bh); + /* the journal_head may have gone by now */ + BUFFER_TRACE(bh, "brelse"); + __brelse(bh); + goto retry; + } else if (!buffer_dirty(bh)) { + unlock_buffer(bh); BUFFER_TRACE(bh, "remove from checkpoint"); - if (__jbd2_journal_remove_checkpoint(jh)) - /* The transaction was released; we're done */ + /* + * If the transaction was released or the checkpoint + * list was empty, we're done. + */ + if (__jbd2_journal_remove_checkpoint(jh) || + !transaction->t_checkpoint_list) goto out; - continue; + } else { + unlock_buffer(bh); + /* + * We are about to write the buffer, it could be + * raced by some other transaction shrink or buffer + * re-log logic once we release the j_list_lock, + * leave it on the checkpoint list and check status + * again to make sure it's clean. + */ + BUFFER_TRACE(bh, "queue"); + get_bh(bh); + J_ASSERT_BH(bh, !buffer_jwrite(bh)); + journal->j_chkpt_bhs[batch_count++] = bh; + transaction->t_chp_stats.cs_written++; + transaction->t_checkpoint_list = jh->b_cpnext; } - /* - * Important: we are about to write the buffer, and - * possibly block, while still holding the journal - * lock. We cannot afford to let the transaction - * logic start messing around with this buffer before - * we write it to disk, as that would break - * recoverability. - */ - BUFFER_TRACE(bh, "queue"); - get_bh(bh); - J_ASSERT_BH(bh, !buffer_jwrite(bh)); - journal->j_chkpt_bhs[batch_count++] = bh; - __buffer_relink_io(jh); - transaction->t_chp_stats.cs_written++; + if ((batch_count == JBD2_NR_BATCH) || - need_resched() || - spin_needbreak(&journal->j_list_lock)) + need_resched() || spin_needbreak(&journal->j_list_lock) || + jh2bh(transaction->t_checkpoint_list) == journal->j_chkpt_bhs[0]) goto unlock_and_flush; } @@ -333,46 +319,9 @@ restart: goto restart; } - /* - * Now we issued all of the transaction's buffers, let's deal - * with the buffers that are out for I/O. - */ -restart2: - /* Did somebody clean up the transaction in the meanwhile? */ - if (journal->j_checkpoint_transactions != transaction || - transaction->t_tid != this_tid) - goto out; - - while (transaction->t_checkpoint_io_list) { - jh = transaction->t_checkpoint_io_list; - bh = jh2bh(jh); - if (buffer_locked(bh)) { - get_bh(bh); - spin_unlock(&journal->j_list_lock); - wait_on_buffer(bh); - /* the journal_head may have gone by now */ - BUFFER_TRACE(bh, "brelse"); - __brelse(bh); - spin_lock(&journal->j_list_lock); - goto restart2; - } - if (unlikely(buffer_write_io_error(bh)) && !result) - result = -EIO; - - /* - * Now in whatever state the buffer currently is, we - * know that it has been written out and so we can - * drop it from the list - */ - if (__jbd2_journal_remove_checkpoint(jh)) - break; - } out: spin_unlock(&journal->j_list_lock); - if (result < 0) - jbd2_journal_abort(journal, result); - else - result = jbd2_cleanup_journal_tail(journal); + result = jbd2_cleanup_journal_tail(journal); return (result < 0) ? result : 0; } diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index 72eb5ed54..9b6849b9b 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -63,10 +63,10 @@ */ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks); -static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval); -static int dbBackSplit(dmtree_t * tp, int leafno); -static int dbJoin(dmtree_t * tp, int leafno, int newval); -static void dbAdjTree(dmtree_t * tp, int leafno, int newval); +static void dbSplit(dmtree_t *tp, int leafno, int splitsz, int newval, bool is_ctl); +static int dbBackSplit(dmtree_t *tp, int leafno, bool is_ctl); +static int dbJoin(dmtree_t *tp, int leafno, int newval, bool is_ctl); +static void dbAdjTree(dmtree_t *tp, int leafno, int newval, bool is_ctl); static int dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level); static int dbAllocAny(struct bmap * bmp, s64 nblocks, int l2nb, s64 * results); @@ -2171,7 +2171,7 @@ static int dbFreeDmap(struct bmap * bmp, struct dmap * dp, s64 blkno, * system. */ if (dp->tree.stree[word] == NOFREE) - dbBackSplit((dmtree_t *) & dp->tree, word); + dbBackSplit((dmtree_t *)&dp->tree, word, false); dbAllocBits(bmp, dp, blkno, nblocks); } @@ -2257,7 +2257,7 @@ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno, * the binary system of the leaves if need be. */ dbSplit(tp, word, BUDMIN, - dbMaxBud((u8 *) & dp->wmap[word])); + dbMaxBud((u8 *)&dp->wmap[word]), false); word += 1; } else { @@ -2297,7 +2297,7 @@ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno, * system of the leaves to reflect the current * allocation (size). */ - dbSplit(tp, word, size, NOFREE); + dbSplit(tp, word, size, NOFREE, false); /* get the number of dmap words handled */ nw = BUDSIZE(size, BUDMIN); @@ -2404,7 +2404,7 @@ static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno, /* update the leaf for this dmap word. */ rc = dbJoin(tp, word, - dbMaxBud((u8 *) & dp->wmap[word])); + dbMaxBud((u8 *)&dp->wmap[word]), false); if (rc) return rc; @@ -2437,7 +2437,7 @@ static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno, /* update the leaf. */ - rc = dbJoin(tp, word, size); + rc = dbJoin(tp, word, size, false); if (rc) return rc; @@ -2589,14 +2589,14 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level) * that it is at the front of a binary buddy system. */ if (oldval == NOFREE) { - rc = dbBackSplit((dmtree_t *) dcp, leafno); + rc = dbBackSplit((dmtree_t *)dcp, leafno, true); if (rc) return rc; oldval = dcp->stree[ti]; } - dbSplit((dmtree_t *) dcp, leafno, dcp->budmin, newval); + dbSplit((dmtree_t *) dcp, leafno, dcp->budmin, newval, true); } else { - rc = dbJoin((dmtree_t *) dcp, leafno, newval); + rc = dbJoin((dmtree_t *) dcp, leafno, newval, true); if (rc) return rc; } @@ -2625,7 +2625,7 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level) */ if (alloc) { dbJoin((dmtree_t *) dcp, leafno, - oldval); + oldval, true); } else { /* the dbJoin() above might have * caused a larger binary buddy system @@ -2635,9 +2635,9 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level) */ if (dcp->stree[ti] == NOFREE) dbBackSplit((dmtree_t *) - dcp, leafno); + dcp, leafno, true); dbSplit((dmtree_t *) dcp, leafno, - dcp->budmin, oldval); + dcp->budmin, oldval, true); } /* release the buffer and return the error. @@ -2685,7 +2685,7 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level) * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ -static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval) +static void dbSplit(dmtree_t *tp, int leafno, int splitsz, int newval, bool is_ctl) { int budsz; int cursz; @@ -2707,7 +2707,7 @@ static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval) while (cursz >= splitsz) { /* update the buddy's leaf with its new value. */ - dbAdjTree(tp, leafno ^ budsz, cursz); + dbAdjTree(tp, leafno ^ budsz, cursz, is_ctl); /* on to the next size and buddy. */ @@ -2719,7 +2719,7 @@ static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval) /* adjust the dmap tree to reflect the specified leaf's new * value. */ - dbAdjTree(tp, leafno, newval); + dbAdjTree(tp, leafno, newval, is_ctl); } @@ -2750,7 +2750,7 @@ static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval) * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ -static int dbBackSplit(dmtree_t * tp, int leafno) +static int dbBackSplit(dmtree_t *tp, int leafno, bool is_ctl) { int budsz, bud, w, bsz, size; int cursz; @@ -2801,7 +2801,7 @@ static int dbBackSplit(dmtree_t * tp, int leafno) * system in two. */ cursz = leaf[bud] - 1; - dbSplit(tp, bud, cursz, cursz); + dbSplit(tp, bud, cursz, cursz, is_ctl); break; } } @@ -2829,7 +2829,7 @@ static int dbBackSplit(dmtree_t * tp, int leafno) * * RETURN VALUES: none */ -static int dbJoin(dmtree_t * tp, int leafno, int newval) +static int dbJoin(dmtree_t *tp, int leafno, int newval, bool is_ctl) { int budsz, buddy; s8 *leaf; @@ -2884,12 +2884,12 @@ static int dbJoin(dmtree_t * tp, int leafno, int newval) if (leafno < buddy) { /* leafno is the left buddy. */ - dbAdjTree(tp, buddy, NOFREE); + dbAdjTree(tp, buddy, NOFREE, is_ctl); } else { /* buddy is the left buddy and becomes * leafno. */ - dbAdjTree(tp, leafno, NOFREE); + dbAdjTree(tp, leafno, NOFREE, is_ctl); leafno = buddy; } @@ -2902,7 +2902,7 @@ static int dbJoin(dmtree_t * tp, int leafno, int newval) /* update the leaf value. */ - dbAdjTree(tp, leafno, newval); + dbAdjTree(tp, leafno, newval, is_ctl); return 0; } @@ -2923,15 +2923,20 @@ static int dbJoin(dmtree_t * tp, int leafno, int newval) * * RETURN VALUES: none */ -static void dbAdjTree(dmtree_t * tp, int leafno, int newval) +static void dbAdjTree(dmtree_t *tp, int leafno, int newval, bool is_ctl) { int lp, pp, k; - int max; + int max, size; + + size = is_ctl ? CTLTREESIZE : TREESIZE; /* pick up the index of the leaf for this leafno. */ lp = leafno + le32_to_cpu(tp->dmt_leafidx); + if (WARN_ON_ONCE(lp >= size || lp < 0)) + return; + /* is the current value the same as the old value ? if so, * there is nothing to do. */ diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c index 837d42f61..a222a9d71 100644 --- a/fs/jfs/jfs_dtree.c +++ b/fs/jfs/jfs_dtree.c @@ -633,6 +633,11 @@ int dtSearch(struct inode *ip, struct component_name * key, ino_t * data, for (base = 0, lim = p->header.nextindex; lim; lim >>= 1) { index = base + (lim >> 1); + if (stbl[index] < 0) { + rc = -EIO; + goto out; + } + if (p->header.flag & BT_LEAF) { /* uppercase leaf name to compare */ cmp = @@ -1970,7 +1975,7 @@ static int dtSplitRoot(tid_t tid, do { f = &rp->slot[fsi]; fsi = f->next; - } while (fsi != -1); + } while (fsi >= 0); f->next = n; } diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index 14f918a48..b0965f3ef 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -2181,6 +2181,9 @@ static int diNewExt(struct inomap * imap, struct iag * iagp, int extno) /* get the ag and iag numbers for this iag. */ agno = BLKTOAG(le64_to_cpu(iagp->agstart), sbi); + if (agno >= MAXAG || agno < 0) + return -EIO; + iagno = le32_to_cpu(iagp->iagnum); /* check if this is the last free extent within the diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c index aa4ff7bca..55702b31a 100644 --- a/fs/jfs/jfs_mount.c +++ b/fs/jfs/jfs_mount.c @@ -172,15 +172,15 @@ int jfs_mount(struct super_block *sb) } jfs_info("jfs_mount: ipimap:0x%p", ipimap); - /* map further access of per fileset inodes by the fileset inode */ - sbi->ipimap = ipimap; - /* initialize fileset inode allocation map */ if ((rc = diMount(ipimap))) { jfs_err("jfs_mount: diMount failed w/rc = %d", rc); goto err_ipimap; } + /* map further access of per fileset inodes by the fileset inode */ + sbi->ipimap = ipimap; + return rc; /* diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index c91ee05cc..0ba056e06 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -696,6 +696,18 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, { struct kernfs_node *kn; + if (parent->mode & S_ISGID) { + /* this code block imitates inode_init_owner() for + * kernfs + */ + + if (parent->iattr) + gid = parent->iattr->ia_gid; + + if (flags & KERNFS_DIR) + mode |= S_ISGID; + } + kn = __kernfs_new_node(kernfs_root(parent), parent, name, mode, uid, gid, flags); if (kn) { diff --git a/fs/namei.c b/fs/namei.c index 3ff954a2b..cb37d7c47 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2771,20 +2771,14 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) p = d_ancestor(p2, p1); if (p) { inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); - inode_lock_nested(p1->d_inode, I_MUTEX_CHILD); + inode_lock_nested(p1->d_inode, I_MUTEX_PARENT2); return p; } p = d_ancestor(p1, p2); - if (p) { - inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); - inode_lock_nested(p2->d_inode, I_MUTEX_CHILD); - return p; - } - - lock_two_inodes(p1->d_inode, p2->d_inode, - I_MUTEX_PARENT, I_MUTEX_PARENT2); - return NULL; + inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); + inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2); + return p; } EXPORT_SYMBOL(lock_rename); @@ -4260,11 +4254,12 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname * * a) we can get into loop creation. * b) race potential - two innocent renames can create a loop together. - * That's where 4.4 screws up. Current fix: serialization on + * That's where 4.4BSD screws up. Current fix: serialization on * sb->s_vfs_rename_mutex. We might be more accurate, but that's another * story. - * c) we have to lock _four_ objects - parents and victim (if it exists), - * and source. + * c) we may have to lock up to _four_ objects - parents and victim (if it exists), + * and source (if it's a non-directory or a subdirectory that moves to + * different parent). * And that - after we got ->i_mutex on parents (until then we don't know * whether the target exists). Solution: try to be smart with locking * order for inodes. We rely on the fact that tree topology may change @@ -4293,6 +4288,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, bool new_is_dir = false; unsigned max_links = new_dir->i_sb->s_max_links; struct name_snapshot old_name; + bool lock_old_subdir, lock_new_subdir; if (source == target) return 0; @@ -4342,15 +4338,32 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, take_dentry_name_snapshot(&old_name, old_dentry); dget(new_dentry); /* - * Lock all moved children. Moved directories may need to change parent - * pointer so they need the lock to prevent against concurrent - * directory changes moving parent pointer. For regular files we've - * historically always done this. The lockdep locking subclasses are - * somewhat arbitrary but RENAME_EXCHANGE in particular can swap - * regular files and directories so it's difficult to tell which - * subclasses to use. + * Lock children. + * The source subdirectory needs to be locked on cross-directory + * rename or cross-directory exchange since its parent changes. + * The target subdirectory needs to be locked on cross-directory + * exchange due to parent change and on any rename due to becoming + * a victim. + * Non-directories need locking in all cases (for NFS reasons); + * they get locked after any subdirectories (in inode address order). + * + * NOTE: WE ONLY LOCK UNRELATED DIRECTORIES IN CROSS-DIRECTORY CASE. + * NEVER, EVER DO THAT WITHOUT ->s_vfs_rename_mutex. */ - lock_two_inodes(source, target, I_MUTEX_NORMAL, I_MUTEX_NONDIR2); + lock_old_subdir = new_dir != old_dir; + lock_new_subdir = new_dir != old_dir || !(flags & RENAME_EXCHANGE); + if (is_dir) { + if (lock_old_subdir) + inode_lock_nested(source, I_MUTEX_CHILD); + if (target && (!new_is_dir || lock_new_subdir)) + inode_lock(target); + } else if (new_is_dir) { + if (lock_new_subdir) + inode_lock_nested(target, I_MUTEX_CHILD); + inode_lock(source); + } else { + lock_two_nondirectories(source, target); + } error = -EBUSY; if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry)) @@ -4394,8 +4407,9 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, d_exchange(old_dentry, new_dentry); } out: - inode_unlock(source); - if (target) + if (!is_dir || lock_old_subdir) + inode_unlock(source); + if (target && (!new_is_dir || lock_new_subdir)) inode_unlock(target); dput(new_dentry); if (!error) { diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 5d86ffa72..499519f0f 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -678,10 +678,17 @@ static void nfs_direct_commit_schedule(struct nfs_direct_req *dreq) LIST_HEAD(mds_list); nfs_init_cinfo_from_dreq(&cinfo, dreq); + nfs_commit_begin(cinfo.mds); nfs_scan_commit(dreq->inode, &mds_list, &cinfo); res = nfs_generic_commit_list(dreq->inode, &mds_list, 0, &cinfo); - if (res < 0) /* res == -ENOMEM */ - nfs_direct_write_reschedule(dreq); + if (res < 0) { /* res == -ENOMEM */ + spin_lock(&dreq->lock); + if (dreq->flags == 0) + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; + spin_unlock(&dreq->lock); + } + if (nfs_commit_end(cinfo.mds)) + nfs_direct_write_complete(dreq); } static void nfs_direct_write_clear_reqs(struct nfs_direct_req *dreq) diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h index 0fe5aacbc..e7192d0ee 100644 --- a/fs/nfs/nfs42.h +++ b/fs/nfs/nfs42.h @@ -54,11 +54,14 @@ int nfs42_proc_removexattr(struct inode *inode, const char *name); * They would be 7 bytes long in the eventual buffer ("user.x\0"), and * 8 bytes long XDR-encoded. * - * Include the trailing eof word as well. + * Include the trailing eof word as well and make the result a multiple + * of 4 bytes. */ static inline u32 nfs42_listxattr_xdrsize(u32 buflen) { - return ((buflen / (XATTR_USER_PREFIX_LEN + 2)) * 8) + 4; + u32 size = 8 * buflen / (XATTR_USER_PREFIX_LEN + 2) + 4; + + return (size + 3) & ~3; } #endif /* CONFIG_NFS_V4_2 */ #endif /* __LINUX_FS_NFS_NFS4_2_H */ diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 7c3c96ed6..8e546e6a5 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -10370,29 +10370,33 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = { static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size) { ssize_t error, error2, error3; + size_t left = size; - error = generic_listxattr(dentry, list, size); + error = generic_listxattr(dentry, list, left); if (error < 0) return error; if (list) { list += error; - size -= error; + left -= error; } - error2 = nfs4_listxattr_nfs4_label(d_inode(dentry), list, size); + error2 = nfs4_listxattr_nfs4_label(d_inode(dentry), list, left); if (error2 < 0) return error2; if (list) { list += error2; - size -= error2; + left -= error2; } - error3 = nfs4_listxattr_nfs4_user(d_inode(dentry), list, size); + error3 = nfs4_listxattr_nfs4_user(d_inode(dentry), list, left); if (error3 < 0) return error3; - return error + error2 + error3; + error += error2 + error3; + if (size && error > size) + return -ERANGE; + return error; } static void nfs4_enable_swap(struct inode *inode) diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c index fa1483088..c2cf4ff62 100644 --- a/fs/nfs/nfsroot.c +++ b/fs/nfs/nfsroot.c @@ -175,10 +175,10 @@ static int __init root_nfs_cat(char *dest, const char *src, size_t len = strlen(dest); if (len && dest[len - 1] != ',') - if (strlcat(dest, ",", destlen) > destlen) + if (strlcat(dest, ",", destlen) >= destlen) return -1; - if (strlcat(dest, src, destlen) > destlen) + if (strlcat(dest, src, destlen) >= destlen) return -1; return 0; } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index d3cd099ff..4cf060691 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1637,7 +1637,7 @@ static int wait_on_commit(struct nfs_mds_commit_info *cinfo) !atomic_read(&cinfo->rpcs_out)); } -static void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) +void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) { atomic_inc(&cinfo->rpcs_out); } diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 65cd599cb..4905b7cd7 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -724,7 +724,7 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, dat = nilfs_bmap_get_dat(btree); ret = nilfs_dat_translate(dat, ptr, &blocknr); if (ret < 0) - goto out; + goto dat_error; ptr = blocknr; } cnt = 1; @@ -743,7 +743,7 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, if (dat) { ret = nilfs_dat_translate(dat, ptr2, &blocknr); if (ret < 0) - goto out; + goto dat_error; ptr2 = blocknr; } if (ptr2 != ptr + cnt || ++cnt == maxblocks) @@ -782,6 +782,11 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, out: nilfs_btree_free_path(path); return ret; + + dat_error: + if (ret == -ENOENT) + ret = -EINVAL; /* Notify bmap layer of metadata corruption */ + goto out; } static void nilfs_btree_promote_key(struct nilfs_bmap *btree, diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index 8fedc7104..22b1ca5c3 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -40,8 +40,21 @@ static inline struct nilfs_dat_info *NILFS_DAT_I(struct inode *dat) static int nilfs_dat_prepare_entry(struct inode *dat, struct nilfs_palloc_req *req, int create) { - return nilfs_palloc_get_entry_block(dat, req->pr_entry_nr, - create, &req->pr_entry_bh); + int ret; + + ret = nilfs_palloc_get_entry_block(dat, req->pr_entry_nr, + create, &req->pr_entry_bh); + if (unlikely(ret == -ENOENT)) { + nilfs_err(dat->i_sb, + "DAT doesn't have a block to manage vblocknr = %llu", + (unsigned long long)req->pr_entry_nr); + /* + * Return internal code -EINVAL to notify bmap layer of + * metadata corruption. + */ + ret = -EINVAL; + } + return ret; } static void nilfs_dat_commit_entry(struct inode *dat, @@ -123,11 +136,7 @@ static void nilfs_dat_commit_free(struct inode *dat, int nilfs_dat_prepare_start(struct inode *dat, struct nilfs_palloc_req *req) { - int ret; - - ret = nilfs_dat_prepare_entry(dat, req, 0); - WARN_ON(ret == -ENOENT); - return ret; + return nilfs_dat_prepare_entry(dat, req, 0); } void nilfs_dat_commit_start(struct inode *dat, struct nilfs_palloc_req *req, @@ -154,10 +163,8 @@ int nilfs_dat_prepare_end(struct inode *dat, struct nilfs_palloc_req *req) int ret; ret = nilfs_dat_prepare_entry(dat, req, 0); - if (ret < 0) { - WARN_ON(ret == -ENOENT); + if (ret < 0) return ret; - } kaddr = kmap_atomic(req->pr_entry_bh->b_page); entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr, diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index 81394e22d..eb7de9e2a 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -243,7 +243,7 @@ nilfs_filetype_table[NILFS_FT_MAX] = { #define S_SHIFT 12 static unsigned char -nilfs_type_by_mode[S_IFMT >> S_SHIFT] = { +nilfs_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = { [S_IFREG >> S_SHIFT] = NILFS_FT_REG_FILE, [S_IFDIR >> S_SHIFT] = NILFS_FT_DIR, [S_IFCHR >> S_SHIFT] = NILFS_FT_CHRDEV, diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c index f35310195..7faf8c285 100644 --- a/fs/nilfs2/direct.c +++ b/fs/nilfs2/direct.c @@ -66,7 +66,7 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, dat = nilfs_bmap_get_dat(direct); ret = nilfs_dat_translate(dat, ptr, &blocknr); if (ret < 0) - return ret; + goto dat_error; ptr = blocknr; } @@ -79,7 +79,7 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, if (dat) { ret = nilfs_dat_translate(dat, ptr2, &blocknr); if (ret < 0) - return ret; + goto dat_error; ptr2 = blocknr; } if (ptr2 != ptr + cnt) @@ -87,6 +87,11 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, } *ptrp = ptr; return cnt; + + dat_error: + if (ret == -ENOENT) + ret = -EINVAL; /* Notify bmap layer of metadata corruption */ + return ret; } static __u64 diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index e1bd592ce..5611a3534 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -105,7 +105,13 @@ static vm_fault_t nilfs_page_mkwrite(struct vm_fault *vmf) nilfs_transaction_commit(inode->i_sb); mapped: - wait_for_stable_page(page); + /* + * Since checksumming including data blocks is performed to determine + * the validity of the log to be written and used for recovery, it is + * necessary to wait for writeback to finish here, regardless of the + * stable write requirement of the backing device. + */ + wait_on_page_writeback(page); out: sb_end_pagefault(inode->i_sb); return block_page_mkwrite_return(ret); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index d144e08a9..06f4deb55 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -112,7 +112,7 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff, "%s (ino=%lu): a race condition while inserting a data block at offset=%llu", __func__, inode->i_ino, (unsigned long long)blkoff); - err = 0; + err = -EAGAIN; } nilfs_transaction_abort(inode->i_sb); goto out; diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index 2217f904a..188b8cc52 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -472,9 +472,10 @@ static int nilfs_prepare_segment_for_recovery(struct the_nilfs *nilfs, static int nilfs_recovery_copy_block(struct the_nilfs *nilfs, struct nilfs_recovery_block *rb, - struct page *page) + loff_t pos, struct page *page) { struct buffer_head *bh_org; + size_t from = pos & ~PAGE_MASK; void *kaddr; bh_org = __bread(nilfs->ns_bdev, rb->blocknr, nilfs->ns_blocksize); @@ -482,7 +483,7 @@ static int nilfs_recovery_copy_block(struct the_nilfs *nilfs, return -EIO; kaddr = kmap_atomic(page); - memcpy(kaddr + bh_offset(bh_org), bh_org->b_data, bh_org->b_size); + memcpy(kaddr + from, bh_org->b_data, bh_org->b_size); kunmap_atomic(kaddr); brelse(bh_org); return 0; @@ -521,7 +522,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs, goto failed_inode; } - err = nilfs_recovery_copy_block(nilfs, rb, page); + err = nilfs_recovery_copy_block(nilfs, rb, pos, page); if (unlikely(err)) goto failed_page; diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 418055ac9..be0ca35b8 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -1707,7 +1707,6 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) { - set_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { if (bh->b_page != bd_page) { lock_page(bd_page); @@ -1718,6 +1717,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) } break; } + set_buffer_async_write(bh); if (bh->b_page != fs_page) { nilfs_begin_page_io(fs_page); fs_page = bh->b_page; @@ -1803,7 +1803,6 @@ static void nilfs_abort_logs(struct list_head *logs, int err) list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) { - clear_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { clear_buffer_uptodate(bh); if (bh->b_page != bd_page) { @@ -1812,6 +1811,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) } break; } + clear_buffer_async_write(bh); if (bh->b_page != fs_page) { nilfs_end_page_io(fs_page, err); fs_page = bh->b_page; @@ -1899,8 +1899,9 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci) BIT(BH_Delay) | BIT(BH_NILFS_Volatile) | BIT(BH_NILFS_Redirected)); - set_mask_bits(&bh->b_state, clear_bits, set_bits); if (bh == segbuf->sb_super_root) { + set_buffer_uptodate(bh); + clear_buffer_dirty(bh); if (bh->b_page != bd_page) { end_page_writeback(bd_page); bd_page = bh->b_page; @@ -1908,6 +1909,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci) update_sr = true; break; } + set_mask_bits(&bh->b_state, clear_bits, set_bits); if (bh->b_page != fs_page) { nilfs_end_page_io(fs_page, 0); fs_page = bh->b_page; @@ -435,12 +435,10 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) goto out; } -#ifdef CONFIG_WATCH_QUEUE - if (pipe->watch_queue) { + if (pipe_has_watch_queue(pipe)) { ret = -EXDEV; goto out; } -#endif /* * If it wasn't empty we try to merge new data into @@ -1302,6 +1300,11 @@ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) pipe->tail = tail; pipe->head = head; + if (!pipe_has_watch_queue(pipe)) { + pipe->max_usage = nr_slots; + pipe->nr_accounted = nr_slots; + } + spin_unlock_irq(&pipe->rd_wait.lock); /* This might have made more room for writers */ @@ -1319,10 +1322,8 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) unsigned int nr_slots, size; long ret = 0; -#ifdef CONFIG_WATCH_QUEUE - if (pipe->watch_queue) + if (pipe_has_watch_queue(pipe)) return -EBUSY; -#endif size = round_pipe_size(arg); nr_slots = size >> PAGE_SHIFT; @@ -1355,8 +1356,6 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) if (ret < 0) goto out_revert_acct; - pipe->max_usage = nr_slots; - pipe->nr_accounted = nr_slots; return pipe->max_usage * PAGE_SIZE; out_revert_acct: @@ -1375,10 +1374,8 @@ struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice) if (file->f_op != &pipefifo_fops || !pipe) return NULL; -#ifdef CONFIG_WATCH_QUEUE - if (for_splice && pipe->watch_queue) + if (for_splice && pipe_has_watch_queue(pipe)) return NULL; -#endif return pipe; } diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 98e579ce0..44fc3b396 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -519,6 +519,7 @@ static int ramoops_init_przs(const char *name, } zone_sz = mem_sz / *cnt; + zone_sz = ALIGN_DOWN(zone_sz, 2); if (!zone_sz) { dev_err(dev, "%s zone size == 0\n", name); goto fail; diff --git a/fs/pstore/zone.c b/fs/pstore/zone.c index b50fc33f2..2426fb679 100644 --- a/fs/pstore/zone.c +++ b/fs/pstore/zone.c @@ -973,6 +973,8 @@ static ssize_t psz_kmsg_read(struct pstore_zone *zone, char *buf = kasprintf(GFP_KERNEL, "%s: Total %d times\n", kmsg_dump_reason_str(record->reason), record->count); + if (!buf) + return -ENOMEM; hlen = strlen(buf); record->buf = krealloc(buf, hlen + size, GFP_KERNEL); if (!record->buf) { diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 4bb4b4b79..6a7b7d447 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -401,15 +401,17 @@ int dquot_mark_dquot_dirty(struct dquot *dquot) EXPORT_SYMBOL(dquot_mark_dquot_dirty); /* Dirtify all the dquots - this can block when journalling */ -static inline int mark_all_dquot_dirty(struct dquot * const *dquot) +static inline int mark_all_dquot_dirty(struct dquot __rcu * const *dquots) { int ret, err, cnt; + struct dquot *dquot; ret = err = 0; for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (dquot[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (dquot) /* Even in case of error we have to continue */ - ret = mark_dquot_dirty(dquot[cnt]); + ret = mark_dquot_dirty(dquot); if (!err) err = ret; } @@ -1006,14 +1008,15 @@ out: } EXPORT_SYMBOL(dqget); -static inline struct dquot **i_dquot(struct inode *inode) +static inline struct dquot __rcu **i_dquot(struct inode *inode) { - return inode->i_sb->s_op->get_dquots(inode); + /* Force __rcu for now until filesystems are fixed */ + return (struct dquot __rcu **)inode->i_sb->s_op->get_dquots(inode); } static int dqinit_needed(struct inode *inode, int type) { - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; int cnt; if (IS_NOQUOTA(inode)) @@ -1086,59 +1089,7 @@ out: return err; } -/* - * Remove references to dquots from inode and add dquot to list for freeing - * if we have the last reference to dquot - */ -static void remove_inode_dquot_ref(struct inode *inode, int type, - struct list_head *tofree_head) -{ - struct dquot **dquots = i_dquot(inode); - struct dquot *dquot = dquots[type]; - - if (!dquot) - return; - - dquots[type] = NULL; - if (list_empty(&dquot->dq_free)) { - /* - * The inode still has reference to dquot so it can't be in the - * free list - */ - spin_lock(&dq_list_lock); - list_add(&dquot->dq_free, tofree_head); - spin_unlock(&dq_list_lock); - } else { - /* - * Dquot is already in a list to put so we won't drop the last - * reference here. - */ - dqput(dquot); - } -} - -/* - * Free list of dquots - * Dquots are removed from inodes and no new references can be got so we are - * the only ones holding reference - */ -static void put_dquot_list(struct list_head *tofree_head) -{ - struct list_head *act_head; - struct dquot *dquot; - - act_head = tofree_head->next; - while (act_head != tofree_head) { - dquot = list_entry(act_head, struct dquot, dq_free); - act_head = act_head->next; - /* Remove dquot from the list so we won't have problems... */ - list_del_init(&dquot->dq_free); - dqput(dquot); - } -} - -static void remove_dquot_ref(struct super_block *sb, int type, - struct list_head *tofree_head) +static void remove_dquot_ref(struct super_block *sb, int type) { struct inode *inode; #ifdef CONFIG_QUOTA_DEBUG @@ -1155,11 +1106,18 @@ static void remove_dquot_ref(struct super_block *sb, int type, */ spin_lock(&dq_data_lock); if (!IS_NOQUOTA(inode)) { + struct dquot __rcu **dquots = i_dquot(inode); + struct dquot *dquot = srcu_dereference_check( + dquots[type], &dquot_srcu, + lockdep_is_held(&dq_data_lock)); + #ifdef CONFIG_QUOTA_DEBUG if (unlikely(inode_get_rsv_space(inode) > 0)) reserved = 1; #endif - remove_inode_dquot_ref(inode, type, tofree_head); + rcu_assign_pointer(dquots[type], NULL); + if (dquot) + dqput(dquot); } spin_unlock(&dq_data_lock); } @@ -1176,13 +1134,8 @@ static void remove_dquot_ref(struct super_block *sb, int type, /* Gather all references from inodes and drop them */ static void drop_dquot_ref(struct super_block *sb, int type) { - LIST_HEAD(tofree_head); - - if (sb->dq_op) { - remove_dquot_ref(sb, type, &tofree_head); - synchronize_srcu(&dquot_srcu); - put_dquot_list(&tofree_head); - } + if (sb->dq_op) + remove_dquot_ref(sb, type); } static inline @@ -1515,7 +1468,8 @@ static int inode_quota_active(const struct inode *inode) static int __dquot_initialize(struct inode *inode, int type) { int cnt, init_needed = 0; - struct dquot **dquots, *got[MAXQUOTAS] = {}; + struct dquot __rcu **dquots; + struct dquot *got[MAXQUOTAS] = {}; struct super_block *sb = inode->i_sb; qsize_t rsv; int ret = 0; @@ -1590,7 +1544,7 @@ static int __dquot_initialize(struct inode *inode, int type) if (!got[cnt]) continue; if (!dquots[cnt]) { - dquots[cnt] = got[cnt]; + rcu_assign_pointer(dquots[cnt], got[cnt]); got[cnt] = NULL; /* * Make quota reservation system happy if someone @@ -1598,12 +1552,16 @@ static int __dquot_initialize(struct inode *inode, int type) */ rsv = inode_get_rsv_space(inode); if (unlikely(rsv)) { + struct dquot *dquot = srcu_dereference_check( + dquots[cnt], &dquot_srcu, + lockdep_is_held(&dq_data_lock)); + spin_lock(&inode->i_lock); /* Get reservation again under proper lock */ rsv = __inode_get_rsv_space(inode); - spin_lock(&dquots[cnt]->dq_dqb_lock); - dquots[cnt]->dq_dqb.dqb_rsvspace += rsv; - spin_unlock(&dquots[cnt]->dq_dqb_lock); + spin_lock(&dquot->dq_dqb_lock); + dquot->dq_dqb.dqb_rsvspace += rsv; + spin_unlock(&dquot->dq_dqb_lock); spin_unlock(&inode->i_lock); } } @@ -1625,7 +1583,7 @@ EXPORT_SYMBOL(dquot_initialize); bool dquot_initialize_needed(struct inode *inode) { - struct dquot **dquots; + struct dquot __rcu **dquots; int i; if (!inode_quota_active(inode)) @@ -1650,13 +1608,14 @@ EXPORT_SYMBOL(dquot_initialize_needed); static void __dquot_drop(struct inode *inode) { int cnt; - struct dquot **dquots = i_dquot(inode); + struct dquot __rcu **dquots = i_dquot(inode); struct dquot *put[MAXQUOTAS]; spin_lock(&dq_data_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - put[cnt] = dquots[cnt]; - dquots[cnt] = NULL; + put[cnt] = srcu_dereference_check(dquots[cnt], &dquot_srcu, + lockdep_is_held(&dq_data_lock)); + rcu_assign_pointer(dquots[cnt], NULL); } spin_unlock(&dq_data_lock); dqput_all(put); @@ -1664,7 +1623,7 @@ static void __dquot_drop(struct inode *inode) void dquot_drop(struct inode *inode) { - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; int cnt; if (IS_NOQUOTA(inode)) @@ -1737,7 +1696,8 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) int cnt, ret = 0, index; struct dquot_warn warn[MAXQUOTAS]; int reserve = flags & DQUOT_SPACE_RESERVE; - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; if (!inode_quota_active(inode)) { if (reserve) { @@ -1757,27 +1717,26 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; if (reserve) { - ret = dquot_add_space(dquots[cnt], 0, number, flags, - &warn[cnt]); + ret = dquot_add_space(dquot, 0, number, flags, &warn[cnt]); } else { - ret = dquot_add_space(dquots[cnt], number, 0, flags, - &warn[cnt]); + ret = dquot_add_space(dquot, number, 0, flags, &warn[cnt]); } if (ret) { /* Back out changes we already did */ for (cnt--; cnt >= 0; cnt--) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - spin_lock(&dquots[cnt]->dq_dqb_lock); + spin_lock(&dquot->dq_dqb_lock); if (reserve) - dquot_free_reserved_space(dquots[cnt], - number); + dquot_free_reserved_space(dquot, number); else - dquot_decr_space(dquots[cnt], number); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + dquot_decr_space(dquot, number); + spin_unlock(&dquot->dq_dqb_lock); } spin_unlock(&inode->i_lock); goto out_flush_warn; @@ -1807,7 +1766,8 @@ int dquot_alloc_inode(struct inode *inode) { int cnt, ret = 0, index; struct dquot_warn warn[MAXQUOTAS]; - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; + struct dquot *dquot; if (!inode_quota_active(inode)) return 0; @@ -1818,17 +1778,19 @@ int dquot_alloc_inode(struct inode *inode) index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - ret = dquot_add_inodes(dquots[cnt], 1, &warn[cnt]); + ret = dquot_add_inodes(dquot, 1, &warn[cnt]); if (ret) { for (cnt--; cnt >= 0; cnt--) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; /* Back out changes we already did */ - spin_lock(&dquots[cnt]->dq_dqb_lock); - dquot_decr_inodes(dquots[cnt], 1); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + spin_lock(&dquot->dq_dqb_lock); + dquot_decr_inodes(dquot, 1); + spin_unlock(&dquot->dq_dqb_lock); } goto warn_put_all; } @@ -1849,7 +1811,8 @@ EXPORT_SYMBOL(dquot_alloc_inode); */ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) { - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; int cnt, index; if (!inode_quota_active(inode)) { @@ -1865,9 +1828,8 @@ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) spin_lock(&inode->i_lock); /* Claim reserved quotas to allocated quotas */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (dquots[cnt]) { - struct dquot *dquot = dquots[cnt]; - + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (dquot) { spin_lock(&dquot->dq_dqb_lock); if (WARN_ON_ONCE(dquot->dq_dqb.dqb_rsvspace < number)) number = dquot->dq_dqb.dqb_rsvspace; @@ -1891,7 +1853,8 @@ EXPORT_SYMBOL(dquot_claim_space_nodirty); */ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) { - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; int cnt, index; if (!inode_quota_active(inode)) { @@ -1907,9 +1870,8 @@ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) spin_lock(&inode->i_lock); /* Claim reserved quotas to allocated quotas */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (dquots[cnt]) { - struct dquot *dquot = dquots[cnt]; - + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (dquot) { spin_lock(&dquot->dq_dqb_lock); if (WARN_ON_ONCE(dquot->dq_dqb.dqb_curspace < number)) number = dquot->dq_dqb.dqb_curspace; @@ -1935,7 +1897,8 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) { unsigned int cnt; struct dquot_warn warn[MAXQUOTAS]; - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; int reserve = flags & DQUOT_SPACE_RESERVE, index; if (!inode_quota_active(inode)) { @@ -1956,17 +1919,18 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) int wtype; warn[cnt].w_type = QUOTA_NL_NOWARN; - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - spin_lock(&dquots[cnt]->dq_dqb_lock); - wtype = info_bdq_free(dquots[cnt], number); + spin_lock(&dquot->dq_dqb_lock); + wtype = info_bdq_free(dquot, number); if (wtype != QUOTA_NL_NOWARN) - prepare_warning(&warn[cnt], dquots[cnt], wtype); + prepare_warning(&warn[cnt], dquot, wtype); if (reserve) - dquot_free_reserved_space(dquots[cnt], number); + dquot_free_reserved_space(dquot, number); else - dquot_decr_space(dquots[cnt], number); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + dquot_decr_space(dquot, number); + spin_unlock(&dquot->dq_dqb_lock); } if (reserve) *inode_reserved_space(inode) -= number; @@ -1990,7 +1954,8 @@ void dquot_free_inode(struct inode *inode) { unsigned int cnt; struct dquot_warn warn[MAXQUOTAS]; - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; + struct dquot *dquot; int index; if (!inode_quota_active(inode)) @@ -2001,16 +1966,16 @@ void dquot_free_inode(struct inode *inode) spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { int wtype; - warn[cnt].w_type = QUOTA_NL_NOWARN; - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - spin_lock(&dquots[cnt]->dq_dqb_lock); - wtype = info_idq_free(dquots[cnt], 1); + spin_lock(&dquot->dq_dqb_lock); + wtype = info_idq_free(dquot, 1); if (wtype != QUOTA_NL_NOWARN) - prepare_warning(&warn[cnt], dquots[cnt], wtype); - dquot_decr_inodes(dquots[cnt], 1); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + prepare_warning(&warn[cnt], dquot, wtype); + dquot_decr_inodes(dquot, 1); + spin_unlock(&dquot->dq_dqb_lock); } spin_unlock(&inode->i_lock); mark_all_dquot_dirty(dquots); @@ -2036,8 +2001,9 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) qsize_t cur_space; qsize_t rsv_space = 0; qsize_t inode_usage = 1; + struct dquot __rcu **dquots; struct dquot *transfer_from[MAXQUOTAS] = {}; - int cnt, ret = 0; + int cnt, index, ret = 0; char is_valid[MAXQUOTAS] = {}; struct dquot_warn warn_to[MAXQUOTAS]; struct dquot_warn warn_from_inodes[MAXQUOTAS]; @@ -2068,6 +2034,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) } cur_space = __inode_get_bytes(inode); rsv_space = __inode_get_rsv_space(inode); + dquots = i_dquot(inode); /* * Build the transfer_from list, check limits, and update usage in * the target structures. @@ -2082,7 +2049,8 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) if (!sb_has_quota_active(inode->i_sb, cnt)) continue; is_valid[cnt] = 1; - transfer_from[cnt] = i_dquot(inode)[cnt]; + transfer_from[cnt] = srcu_dereference_check(dquots[cnt], + &dquot_srcu, lockdep_is_held(&dq_data_lock)); ret = dquot_add_inodes(transfer_to[cnt], inode_usage, &warn_to[cnt]); if (ret) @@ -2121,13 +2089,21 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) rsv_space); spin_unlock(&transfer_from[cnt]->dq_dqb_lock); } - i_dquot(inode)[cnt] = transfer_to[cnt]; + rcu_assign_pointer(dquots[cnt], transfer_to[cnt]); } spin_unlock(&inode->i_lock); spin_unlock(&dq_data_lock); - mark_all_dquot_dirty(transfer_from); - mark_all_dquot_dirty(transfer_to); + /* + * These arrays are local and we hold dquot references so we don't need + * the srcu protection but still take dquot_srcu to avoid warning in + * mark_all_dquot_dirty(). + */ + index = srcu_read_lock(&dquot_srcu); + mark_all_dquot_dirty((struct dquot __rcu **)transfer_from); + mark_all_dquot_dirty((struct dquot __rcu **)transfer_to); + srcu_read_unlock(&dquot_srcu, index); + flush_warnings(warn_to); flush_warnings(warn_from_inodes); flush_warnings(warn_from_space); diff --git a/fs/select.c b/fs/select.c index 5edffee11..668a52005 100644 --- a/fs/select.c +++ b/fs/select.c @@ -475,7 +475,7 @@ static inline void wait_key_set(poll_table *wait, unsigned long in, wait->_key |= POLLOUT_SET; } -static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) +static noinline_for_stack int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) { ktime_t expire, *to = NULL; struct poll_wqueues table; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 96d0da65e..f51b23968 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -429,6 +429,8 @@ struct kernfs_node *sysfs_break_active_protection(struct kobject *kobj, kn = kernfs_find_and_get(kobj->sd, attr->name); if (kn) kernfs_break_active_protection(kn); + else + kobject_put(kobj); return kn; } EXPORT_SYMBOL_GPL(sysfs_break_active_protection); diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index e3d1673b8..ef9bcfeec 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -82,9 +82,6 @@ static inline sysv_zone_t *block_end(struct buffer_head *bh) return (sysv_zone_t*)((char*)bh->b_data + bh->b_size); } -/* - * Requires read_lock(&pointers_lock) or write_lock(&pointers_lock) - */ static Indirect *get_branch(struct inode *inode, int depth, int offsets[], @@ -104,15 +101,18 @@ static Indirect *get_branch(struct inode *inode, bh = sb_bread(sb, block); if (!bh) goto failure; + read_lock(&pointers_lock); if (!verify_chain(chain, p)) goto changed; add_chain(++p, bh, (sysv_zone_t*)bh->b_data + *++offsets); + read_unlock(&pointers_lock); if (!p->key) goto no_block; } return NULL; changed: + read_unlock(&pointers_lock); brelse(bh); *err = -EAGAIN; goto no_block; @@ -218,9 +218,7 @@ static int get_block(struct inode *inode, sector_t iblock, struct buffer_head *b goto out; reread: - read_lock(&pointers_lock); partial = get_branch(inode, depth, offsets, chain, &err); - read_unlock(&pointers_lock); /* Simplest case - block found, no allocation needed */ if (!partial) { @@ -290,9 +288,9 @@ static Indirect *find_shared(struct inode *inode, *top = 0; for (k = depth; k > 1 && !offsets[k-1]; k--) ; + partial = get_branch(inode, k, offsets, chain, &err); write_lock(&pointers_lock); - partial = get_branch(inode, k, offsets, chain, &err); if (!partial) partial = chain + k-1; /* diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index bc562b107..11cd921df 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -1198,6 +1198,8 @@ out_cancel: dir_ui->ui_size = dir->i_size; mutex_unlock(&dir_ui->ui_mutex); out_inode: + /* Free inode->i_link before inode is marked as bad. */ + fscrypt_free_inode(inode); make_bad_inode(inode); iput(inode); out_fname: diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 19fdcda04..18df7a825 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -262,9 +262,6 @@ static int write_begin_slow(struct address_space *mapping, return err; } } - - SetPageUptodate(page); - ClearPageError(page); } if (PagePrivate(page)) @@ -463,9 +460,6 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, return err; } } - - SetPageUptodate(page); - ClearPageError(page); } err = allocate_budget(c, page, ui, appending); @@ -475,10 +469,8 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, * If we skipped reading the page because we were going to * write all of it, then it is not up to date. */ - if (skipped_read) { + if (skipped_read) ClearPageChecked(page); - ClearPageUptodate(page); - } /* * Budgeting failed which means it would have to force * write-back but didn't, because we set the @fast flag in the @@ -569,6 +561,9 @@ static int ubifs_write_end(struct file *file, struct address_space *mapping, goto out; } + if (len == PAGE_SIZE) + SetPageUptodate(page); + if (!PagePrivate(page)) { attach_page_private(page, (void *)1); atomic_long_inc(&c->dirty_pg_cnt); diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c index c578e772c..f11bcbac7 100644 --- a/fs/vboxsf/super.c +++ b/fs/vboxsf/super.c @@ -151,7 +151,7 @@ static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc) if (!sbi->nls) { vbg_err("vboxsf: Count not load '%s' nls\n", nls_name); err = -EINVAL; - goto fail_free; + goto fail_destroy_idr; } } @@ -224,6 +224,7 @@ fail_free: ida_simple_remove(&vboxsf_bdi_ida, sbi->bdi_id); if (sbi->nls) unload_nls(sbi->nls); +fail_destroy_idr: idr_destroy(&sbi->ino_idr); kfree(sbi); return err; diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index b9522eee1..f9ecade9e 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -319,16 +319,18 @@ static loff_t zonefs_check_zone_condition(struct inode *inode, } } -struct zonefs_ioerr_data { - struct inode *inode; - bool write; -}; - static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, void *data) { - struct zonefs_ioerr_data *err = data; - struct inode *inode = err->inode; + struct blk_zone *z = data; + + *z = *zone; + return 0; +} + +static void zonefs_handle_io_error(struct inode *inode, struct blk_zone *zone, + bool write) +{ struct zonefs_inode_info *zi = ZONEFS_I(inode); struct super_block *sb = inode->i_sb; struct zonefs_sb_info *sbi = ZONEFS_SB(sb); @@ -344,8 +346,8 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, isize = i_size_read(inode); if (zone->cond != BLK_ZONE_COND_OFFLINE && zone->cond != BLK_ZONE_COND_READONLY && - !err->write && isize == data_size) - return 0; + !write && isize == data_size) + return; /* * At this point, we detected either a bad zone or an inconsistency @@ -366,8 +368,9 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, * In all cases, warn about inode size inconsistency and handle the * IO error according to the zone condition and to the mount options. */ - if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && isize != data_size) - zonefs_warn(sb, "inode %lu: invalid size %lld (should be %lld)\n", + if (isize != data_size) + zonefs_warn(sb, + "inode %lu: invalid size %lld (should be %lld)\n", inode->i_ino, isize, data_size); /* @@ -427,8 +430,6 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, zonefs_update_stats(inode, data_size); zonefs_i_size_write(inode, data_size); zi->i_wpoffset = data_size; - - return 0; } /* @@ -442,23 +443,25 @@ static void __zonefs_io_error(struct inode *inode, bool write) { struct zonefs_inode_info *zi = ZONEFS_I(inode); struct super_block *sb = inode->i_sb; - struct zonefs_sb_info *sbi = ZONEFS_SB(sb); unsigned int noio_flag; - unsigned int nr_zones = 1; - struct zonefs_ioerr_data err = { - .inode = inode, - .write = write, - }; + struct blk_zone zone; int ret; /* - * The only files that have more than one zone are conventional zone - * files with aggregated conventional zones, for which the inode zone - * size is always larger than the device zone size. + * Conventional zone have no write pointer and cannot become read-only + * or offline. So simply fake a report for a single or aggregated zone + * and let zonefs_handle_io_error() correct the zone inode information + * according to the mount options. */ - if (zi->i_zone_size > bdev_zone_sectors(sb->s_bdev)) - nr_zones = zi->i_zone_size >> - (sbi->s_zone_sectors_shift + SECTOR_SHIFT); + if (zi->i_ztype != ZONEFS_ZTYPE_SEQ) { + zone.start = zi->i_zsector; + zone.len = zi->i_max_size >> SECTOR_SHIFT; + zone.wp = zone.start + zone.len; + zone.type = BLK_ZONE_TYPE_CONVENTIONAL; + zone.cond = BLK_ZONE_COND_NOT_WP; + zone.capacity = zone.len; + goto handle_io_error; + } /* * Memory allocations in blkdev_report_zones() can trigger a memory @@ -469,12 +472,19 @@ static void __zonefs_io_error(struct inode *inode, bool write) * the GFP_NOIO context avoids both problems. */ noio_flag = memalloc_noio_save(); - ret = blkdev_report_zones(sb->s_bdev, zi->i_zsector, nr_zones, - zonefs_io_error_cb, &err); - if (ret != nr_zones) + ret = blkdev_report_zones(sb->s_bdev, zi->i_zsector, 1, + zonefs_io_error_cb, &zone); + memalloc_noio_restore(noio_flag); + if (ret != 1) { zonefs_err(sb, "Get inode %lu zone information failed %d\n", inode->i_ino, ret); - memalloc_noio_restore(noio_flag); + zonefs_warn(sb, "remounting filesystem read-only\n"); + sb->s_flags |= SB_RDONLY; + return; + } + +handle_io_error: + zonefs_handle_io_error(inode, &zone, write); } static void zonefs_io_error(struct inode *inode, bool write) |